diff options
Diffstat (limited to '.pc/Fix-silly-quantifier-size-check.patch')
| -rw-r--r-- | .pc/Fix-silly-quantifier-size-check.patch/pcre_compile.c | 9484 | ||||
| -rw-r--r-- | .pc/Fix-silly-quantifier-size-check.patch/testdata/testoutput2 | 14152 |
2 files changed, 0 insertions, 23636 deletions
diff --git a/.pc/Fix-silly-quantifier-size-check.patch/pcre_compile.c b/.pc/Fix-silly-quantifier-size-check.patch/pcre_compile.c deleted file mode 100644 index 8a5b723..0000000 --- a/.pc/Fix-silly-quantifier-size-check.patch/pcre_compile.c +++ /dev/null @@ -1,9484 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2014 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_compile(), along with -supporting internal functions that are not used by other modules. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK cd /* Block containing newline information */ -#define PSSTART start_pattern /* Field containing processed string start */ -#define PSEND end_pattern /* Field containing processed string end */ - -#include "pcre_internal.h" - - -/* When PCRE_DEBUG is defined, we need the pcre(16|32)_printint() function, which -is also used by pcretest. PCRE_DEBUG is not defined when building a production -library. We do not need to select pcre16_printint.c specially, because the -COMPILE_PCREx macro will already be appropriately set. */ - -#ifdef PCRE_DEBUG -/* pcre_printint.c should not include any headers */ -#define PCRE_INCLUDED -#include "pcre_printint.c" -#undef PCRE_INCLUDED -#endif - - -/* Macro for setting individual bits in class bitmaps. */ - -#define SETBIT(a,b) a[(b)/8] |= (1 << ((b)&7)) - -/* Maximum length value to check against when making sure that the integer that -holds the compiled pattern length does not overflow. We make it a bit less than -INT_MAX to allow for adding in group terminating bytes, so that we don't have -to check them every time. */ - -#define OFLOW_MAX (INT_MAX - 20) - -/* Definitions to allow mutual recursion */ - -static int - add_list_to_class(pcre_uint8 *, pcre_uchar **, int, compile_data *, - const pcre_uint32 *, unsigned int); - -static BOOL - compile_regex(int, pcre_uchar **, const pcre_uchar **, int *, BOOL, BOOL, int, int, - pcre_uint32 *, pcre_int32 *, pcre_uint32 *, pcre_int32 *, branch_chain *, - compile_data *, int *); - - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* This value specifies the size of stack workspace that is used during the -first pre-compile phase that determines how much memory is required. The regex -is partly compiled into this space, but the compiled parts are discarded as -soon as they can be, so that hopefully there will never be an overrun. The code -does, however, check for an overrun. The largest amount I've seen used is 218, -so this number is very generous. - -The same workspace is used during the second, actual compile phase for -remembering forward references to groups so that they can be filled in at the -end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE -is 4 there is plenty of room for most patterns. However, the memory can get -filled up by repetitions of forward references, for example patterns like -/(?1){0,1999}(b)/, and one user did hit the limit. The code has been changed so -that the workspace is expanded using malloc() in this situation. The value -below is therefore a minimum, and we put a maximum on it for safety. The -minimum is now also defined in terms of LINK_SIZE so that the use of malloc() -kicks in at the same number of forward references in all cases. */ - -#define COMPILE_WORK_SIZE (2048*LINK_SIZE) -#define COMPILE_WORK_SIZE_MAX (100*COMPILE_WORK_SIZE) - -/* This value determines the size of the initial vector that is used for -remembering named groups during the pre-compile. It is allocated on the stack, -but if it is too small, it is expanded using malloc(), in a similar way to the -workspace. The value is the number of slots in the list. */ - -#define NAMED_GROUP_LIST_SIZE 20 - -/* The overrun tests check for a slightly smaller size so that they detect the -overrun before it actually does run off the end of the data block. */ - -#define WORK_SIZE_SAFETY_MARGIN (100) - -/* Private flags added to firstchar and reqchar. */ - -#define REQ_CASELESS (1 << 0) /* Indicates caselessness */ -#define REQ_VARY (1 << 1) /* Reqchar followed non-literal item */ -/* Negative values for the firstchar and reqchar flags */ -#define REQ_UNSET (-2) -#define REQ_NONE (-1) - -/* Repeated character flags. */ - -#define UTF_LENGTH 0x10000000l /* The char contains its length. */ - -/* Table for handling escaped characters in the range '0'-'z'. Positive returns -are simple data values; negative values are for special things like \d and so -on. Zero means further processing is needed (for things like \x), or the escape -is invalid. */ - -#ifndef EBCDIC - -/* This is the "normal" table for ASCII systems or for EBCDIC systems running -in UTF-8 mode. */ - -static const short int escapes[] = { - 0, 0, - 0, 0, - 0, 0, - 0, 0, - 0, 0, - CHAR_COLON, CHAR_SEMICOLON, - CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, - CHAR_GREATER_THAN_SIGN, CHAR_QUESTION_MARK, - CHAR_COMMERCIAL_AT, -ESC_A, - -ESC_B, -ESC_C, - -ESC_D, -ESC_E, - 0, -ESC_G, - -ESC_H, 0, - 0, -ESC_K, - 0, 0, - -ESC_N, 0, - -ESC_P, -ESC_Q, - -ESC_R, -ESC_S, - 0, 0, - -ESC_V, -ESC_W, - -ESC_X, 0, - -ESC_Z, CHAR_LEFT_SQUARE_BRACKET, - CHAR_BACKSLASH, CHAR_RIGHT_SQUARE_BRACKET, - CHAR_CIRCUMFLEX_ACCENT, CHAR_UNDERSCORE, - CHAR_GRAVE_ACCENT, 7, - -ESC_b, 0, - -ESC_d, ESC_e, - ESC_f, 0, - -ESC_h, 0, - 0, -ESC_k, - 0, 0, - ESC_n, 0, - -ESC_p, 0, - ESC_r, -ESC_s, - ESC_tee, 0, - -ESC_v, -ESC_w, - 0, 0, - -ESC_z -}; - -#else - -/* This is the "abnormal" table for EBCDIC systems without UTF-8 support. */ - -static const short int escapes[] = { -/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', -/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, -/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', -/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, -/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', -/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', -/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, -/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, -/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, -/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', -/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, -ESC_K, 0, 0,-ESC_N, 0, -ESC_P, -/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, -/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, -/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 -}; -#endif - - -/* Table of special "verbs" like (*PRUNE). This is a short table, so it is -searched linearly. Put all the names into a single string, in order to reduce -the number of relocations when a shared library is dynamically linked. The -string is built from string macros so that it works in UTF-8 mode on EBCDIC -platforms. */ - -typedef struct verbitem { - int len; /* Length of verb name */ - int op; /* Op when no arg, or -1 if arg mandatory */ - int op_arg; /* Op when arg present, or -1 if not allowed */ -} verbitem; - -static const char verbnames[] = - "\0" /* Empty name is a shorthand for MARK */ - STRING_MARK0 - STRING_ACCEPT0 - STRING_COMMIT0 - STRING_F0 - STRING_FAIL0 - STRING_PRUNE0 - STRING_SKIP0 - STRING_THEN; - -static const verbitem verbs[] = { - { 0, -1, OP_MARK }, - { 4, -1, OP_MARK }, - { 6, OP_ACCEPT, -1 }, - { 6, OP_COMMIT, -1 }, - { 1, OP_FAIL, -1 }, - { 4, OP_FAIL, -1 }, - { 5, OP_PRUNE, OP_PRUNE_ARG }, - { 4, OP_SKIP, OP_SKIP_ARG }, - { 4, OP_THEN, OP_THEN_ARG } -}; - -static const int verbcount = sizeof(verbs)/sizeof(verbitem); - - -/* Substitutes for [[:<:]] and [[:>:]], which mean start and end of word in -another regex library. */ - -static const pcre_uchar sub_start_of_word[] = { - CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, - CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, CHAR_RIGHT_PARENTHESIS, '\0' }; - -static const pcre_uchar sub_end_of_word[] = { - CHAR_BACKSLASH, CHAR_b, CHAR_LEFT_PARENTHESIS, CHAR_QUESTION_MARK, - CHAR_LESS_THAN_SIGN, CHAR_EQUALS_SIGN, CHAR_BACKSLASH, CHAR_w, - CHAR_RIGHT_PARENTHESIS, '\0' }; - - -/* Tables of names of POSIX character classes and their lengths. The names are -now all in a single string, to reduce the number of relocations when a shared -library is dynamically loaded. The list of lengths is terminated by a zero -length entry. The first three must be alpha, lower, upper, as this is assumed -for handling case independence. The indices for graph, print, and punct are -needed, so identify them. */ - -static const char posix_names[] = - STRING_alpha0 STRING_lower0 STRING_upper0 STRING_alnum0 - STRING_ascii0 STRING_blank0 STRING_cntrl0 STRING_digit0 - STRING_graph0 STRING_print0 STRING_punct0 STRING_space0 - STRING_word0 STRING_xdigit; - -static const pcre_uint8 posix_name_lengths[] = { - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; - -#define PC_GRAPH 8 -#define PC_PRINT 9 -#define PC_PUNCT 10 - - -/* Table of class bit maps for each POSIX class. Each class is formed from a -base map, with an optional addition or removal of another map. Then, for some -classes, there is some additional tweaking: for [:blank:] the vertical space -characters are removed, and for [:alpha:] and [:alnum:] the underscore -character is removed. The triples in the table consist of the base map offset, -second map offset or -1 if no second map, and a non-negative value for map -addition or a negative value for map subtraction (if there are two maps). The -absolute value of the third field has these meanings: 0 => no tweaking, 1 => -remove vertical space characters, 2 => remove underscore. */ - -static const int posix_class_maps[] = { - cbit_word, cbit_digit, -2, /* alpha */ - cbit_lower, -1, 0, /* lower */ - cbit_upper, -1, 0, /* upper */ - cbit_word, -1, 2, /* alnum - word without underscore */ - cbit_print, cbit_cntrl, 0, /* ascii */ - cbit_space, -1, 1, /* blank - a GNU extension */ - cbit_cntrl, -1, 0, /* cntrl */ - cbit_digit, -1, 0, /* digit */ - cbit_graph, -1, 0, /* graph */ - cbit_print, -1, 0, /* print */ - cbit_punct, -1, 0, /* punct */ - cbit_space, -1, 0, /* space */ - cbit_word, -1, 0, /* word - a Perl extension */ - cbit_xdigit,-1, 0 /* xdigit */ -}; - -/* Table of substitutes for \d etc when PCRE_UCP is set. They are replaced by -Unicode property escapes. */ - -#ifdef SUPPORT_UCP -static const pcre_uchar string_PNd[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pNd[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_N, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXsp[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXsp[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_s, CHAR_p, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXwd[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXwd[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_w, CHAR_d, CHAR_RIGHT_CURLY_BRACKET, '\0' }; - -static const pcre_uchar *substitutes[] = { - string_PNd, /* \D */ - string_pNd, /* \d */ - string_PXsp, /* \S */ /* Xsp is Perl space, but from 8.34, Perl */ - string_pXsp, /* \s */ /* space and POSIX space are the same. */ - string_PXwd, /* \W */ - string_pXwd /* \w */ -}; - -/* The POSIX class substitutes must be in the order of the POSIX class names, -defined above, and there are both positive and negative cases. NULL means no -general substitute of a Unicode property escape (\p or \P). However, for some -POSIX classes (e.g. graph, print, punct) a special property code is compiled -directly. */ - -static const pcre_uchar string_pL[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pLl[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pLu[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_pXan[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_h[] = { - CHAR_BACKSLASH, CHAR_h, '\0' }; -static const pcre_uchar string_pXps[] = { - CHAR_BACKSLASH, CHAR_p, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PL[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PLl[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_l, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PLu[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_L, CHAR_u, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_PXan[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_a, CHAR_n, CHAR_RIGHT_CURLY_BRACKET, '\0' }; -static const pcre_uchar string_H[] = { - CHAR_BACKSLASH, CHAR_H, '\0' }; -static const pcre_uchar string_PXps[] = { - CHAR_BACKSLASH, CHAR_P, CHAR_LEFT_CURLY_BRACKET, - CHAR_X, CHAR_p, CHAR_s, CHAR_RIGHT_CURLY_BRACKET, '\0' }; - -static const pcre_uchar *posix_substitutes[] = { - string_pL, /* alpha */ - string_pLl, /* lower */ - string_pLu, /* upper */ - string_pXan, /* alnum */ - NULL, /* ascii */ - string_h, /* blank */ - NULL, /* cntrl */ - string_pNd, /* digit */ - NULL, /* graph */ - NULL, /* print */ - NULL, /* punct */ - string_pXps, /* space */ /* Xps is POSIX space, but from 8.34 */ - string_pXwd, /* word */ /* Perl and POSIX space are the same */ - NULL, /* xdigit */ - /* Negated cases */ - string_PL, /* ^alpha */ - string_PLl, /* ^lower */ - string_PLu, /* ^upper */ - string_PXan, /* ^alnum */ - NULL, /* ^ascii */ - string_H, /* ^blank */ - NULL, /* ^cntrl */ - string_PNd, /* ^digit */ - NULL, /* ^graph */ - NULL, /* ^print */ - NULL, /* ^punct */ - string_PXps, /* ^space */ /* Xps is POSIX space, but from 8.34 */ - string_PXwd, /* ^word */ /* Perl and POSIX space are the same */ - NULL /* ^xdigit */ -}; -#define POSIX_SUBSIZE (sizeof(posix_substitutes) / sizeof(pcre_uchar *)) -#endif - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. Do not ever re-use any error number, because -they are documented. Always add a new error instead. Messages marked DEAD below -are no longer used. This used to be a table of strings, but in order to reduce -the number of relocations needed when a shared library is loaded dynamically, -it is now one long string. We cannot use a table of offsets, because the -lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we -simply count through to the one we want - this isn't a performance issue -because these strings are used only when there is a compilation error. - -Each substring ends with \0 to insert a null character. This includes the final -substring, so that the whole string ends with \0\0, which can be detected when -counting through. */ - -static const char error_texts[] = - "no error\0" - "\\ at end of pattern\0" - "\\c at end of pattern\0" - "unrecognized character follows \\\0" - "numbers out of order in {} quantifier\0" - /* 5 */ - "number too big in {} quantifier\0" - "missing terminating ] for character class\0" - "invalid escape sequence in character class\0" - "range out of order in character class\0" - "nothing to repeat\0" - /* 10 */ - "operand of unlimited repeat could match the empty string\0" /** DEAD **/ - "internal error: unexpected repeat\0" - "unrecognized character after (? or (?-\0" - "POSIX named classes are supported only within a class\0" - "missing )\0" - /* 15 */ - "reference to non-existent subpattern\0" - "erroffset passed as NULL\0" - "unknown option bit(s) set\0" - "missing ) after comment\0" - "parentheses nested too deeply\0" /** DEAD **/ - /* 20 */ - "regular expression is too large\0" - "failed to get memory\0" - "unmatched parentheses\0" - "internal error: code overflow\0" - "unrecognized character after (?<\0" - /* 25 */ - "lookbehind assertion is not fixed length\0" - "malformed number or name after (?(\0" - "conditional group contains more than two branches\0" - "assertion expected after (?(\0" - "(?R or (?[+-]digits must be followed by )\0" - /* 30 */ - "unknown POSIX class name\0" - "POSIX collating elements are not supported\0" - "this version of PCRE is compiled without UTF support\0" - "spare error\0" /** DEAD **/ - "character value in \\x{} or \\o{} is too large\0" - /* 35 */ - "invalid condition (?(0)\0" - "\\C not allowed in lookbehind assertion\0" - "PCRE does not support \\L, \\l, \\N{name}, \\U, or \\u\0" - "number after (?C is > 255\0" - "closing ) for (?C expected\0" - /* 40 */ - "recursive call could loop indefinitely\0" - "unrecognized character after (?P\0" - "syntax error in subpattern name (missing terminator)\0" - "two named subpatterns have the same name\0" - "invalid UTF-8 string\0" - /* 45 */ - "support for \\P, \\p, and \\X has not been compiled\0" - "malformed \\P or \\p sequence\0" - "unknown property name after \\P or \\p\0" - "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" - "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" - /* 50 */ - "repeated subpattern is too long\0" /** DEAD **/ - "octal value is greater than \\377 in 8-bit non-UTF-8 mode\0" - "internal error: overran compiling workspace\0" - "internal error: previously-checked referenced subpattern not found\0" - "DEFINE group contains more than one branch\0" - /* 55 */ - "repeating a DEFINE group is not allowed\0" /** DEAD **/ - "inconsistent NEWLINE options\0" - "\\g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number\0" - "a numbered reference must not be zero\0" - "an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)\0" - /* 60 */ - "(*VERB) not recognized or malformed\0" - "number is too big\0" - "subpattern name expected\0" - "digit expected after (?+\0" - "] is an invalid data character in JavaScript compatibility mode\0" - /* 65 */ - "different names for subpatterns of the same number are not allowed\0" - "(*MARK) must have an argument\0" - "this version of PCRE is not compiled with Unicode property support\0" - "\\c must be followed by an ASCII character\0" - "\\k is not followed by a braced, angle-bracketed, or quoted name\0" - /* 70 */ - "internal error: unknown opcode in find_fixedlength()\0" - "\\N is not supported in a class\0" - "too many forward references\0" - "disallowed Unicode code point (>= 0xd800 && <= 0xdfff)\0" - "invalid UTF-16 string\0" - /* 75 */ - "name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)\0" - "character value in \\u.... sequence is too large\0" - "invalid UTF-32 string\0" - "setting UTF is disabled by the application\0" - "non-hex character in \\x{} (closing brace missing?)\0" - /* 80 */ - "non-octal character in \\o{} (closing brace missing?)\0" - "missing opening brace after \\o\0" - "parentheses are too deeply nested\0" - "invalid range in character class\0" - "group name must start with a non-digit\0" - /* 85 */ - "parentheses are too deeply nested (stack check)\0" - ; - -/* Table to identify digits and hex digits. This is used when compiling -patterns. Note that the tables in chartables are dependent on the locale, and -may mark arbitrary characters as digits - but the PCRE compiling code expects -to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have -a private table here. It costs 256 bytes, but it is a lot faster than doing -character value tests (at least in some simple cases I timed), and in some -applications one wants PCRE to compile efficiently as well as match -efficiently. - -For convenience, we use the same bit definitions as in chartables: - - 0x04 decimal digit - 0x08 hexadecimal digit - -Then we can use ctype_digit and ctype_xdigit in the code. */ - -/* Using a simple comparison for decimal numbers rather than a memory read -is much faster, and the resulting code is simpler (the compiler turns it -into a subtraction and unsigned comparison). */ - -#define IS_DIGIT(x) ((x) >= CHAR_0 && (x) <= CHAR_9) - -#ifndef EBCDIC - -/* This is the "normal" case, for ASCII systems, and EBCDIC systems running in -UTF-8 mode. */ - -static const pcre_uint8 digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -#else - -/* This is the "abnormal" case, for EBCDIC systems not running in UTF-8 mode. */ - -static const pcre_uint8 digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ - -static const pcre_uint8 ebcdic_chartab[] = { /* chartable partial dup */ - 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ - 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ - 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ - 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ -#endif - - -/* This table is used to check whether auto-possessification is possible -between adjacent character-type opcodes. The left-hand (repeated) opcode is -used to select the row, and the right-hand opcode is use to select the column. -A value of 1 means that auto-possessification is OK. For example, the second -value in the first row means that \D+\d can be turned into \D++\d. - -The Unicode property types (\P and \p) have to be present to fill out the table -because of what their opcode values are, but the table values should always be -zero because property types are handled separately in the code. The last four -columns apply to items that cannot be repeated, so there is no need to have -rows for them. Note that OP_DIGIT etc. are generated only when PCRE_UCP is -*not* set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ - -#define APTROWS (LAST_AUTOTAB_LEFT_OP - FIRST_AUTOTAB_OP + 1) -#define APTCOLS (LAST_AUTOTAB_RIGHT_OP - FIRST_AUTOTAB_OP + 1) - -static const pcre_uint8 autoposstab[APTROWS][APTCOLS] = { -/* \D \d \S \s \W \w . .+ \C \P \p \R \H \h \V \v \X \Z \z $ $M */ - { 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \D */ - { 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \d */ - { 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \S */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \s */ - { 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \W */ - { 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1 }, /* \w */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* . */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* .+ */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 }, /* \C */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \P */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* \p */ - { 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \R */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0 }, /* \H */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \h */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0 }, /* \V */ - { 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0 }, /* \v */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0 } /* \X */ -}; - - -/* This table is used to check whether auto-possessification is possible -between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP). The -left-hand (repeated) opcode is used to select the row, and the right-hand -opcode is used to select the column. The values are as follows: - - 0 Always return FALSE (never auto-possessify) - 1 Character groups are distinct (possessify if both are OP_PROP) - 2 Check character categories in the same group (general or particular) - 3 TRUE if the two opcodes are not the same (PROP vs NOTPROP) - - 4 Check left general category vs right particular category - 5 Check right general category vs left particular category - - 6 Left alphanum vs right general category - 7 Left space vs right general category - 8 Left word vs right general category - - 9 Right alphanum vs left general category - 10 Right space vs left general category - 11 Right word vs left general category - - 12 Left alphanum vs right particular category - 13 Left space vs right particular category - 14 Left word vs right particular category - - 15 Right alphanum vs left particular category - 16 Right space vs left particular category - 17 Right word vs left particular category -*/ - -static const pcre_uint8 propposstab[PT_TABSIZE][PT_TABSIZE] = { -/* ANY LAMP GC PC SC ALNUM SPACE PXSPACE WORD CLIST UCNC */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_ANY */ - { 0, 3, 0, 0, 0, 3, 1, 1, 0, 0, 0 }, /* PT_LAMP */ - { 0, 0, 2, 4, 0, 9, 10, 10, 11, 0, 0 }, /* PT_GC */ - { 0, 0, 5, 2, 0, 15, 16, 16, 17, 0, 0 }, /* PT_PC */ - { 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0 }, /* PT_SC */ - { 0, 3, 6, 12, 0, 3, 1, 1, 0, 0, 0 }, /* PT_ALNUM */ - { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_SPACE */ - { 0, 1, 7, 13, 0, 1, 3, 3, 1, 0, 0 }, /* PT_PXSPACE */ - { 0, 0, 8, 14, 0, 0, 1, 1, 3, 0, 0 }, /* PT_WORD */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, /* PT_CLIST */ - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3 } /* PT_UCNC */ -}; - -/* This table is used to check whether auto-possessification is possible -between adjacent Unicode property opcodes (OP_PROP and OP_NOTPROP) when one -specifies a general category and the other specifies a particular category. The -row is selected by the general category and the column by the particular -category. The value is 1 if the particular category is not part of the general -category. */ - -static const pcre_uint8 catposstab[7][30] = { -/* Cc Cf Cn Co Cs Ll Lm Lo Lt Lu Mc Me Mn Nd Nl No Pc Pd Pe Pf Pi Po Ps Sc Sk Sm So Zl Zp Zs */ - { 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* C */ - { 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* L */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* M */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 }, /* N */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1 }, /* P */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1 }, /* S */ - { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0 } /* Z */ -}; - -/* This table is used when checking ALNUM, (PX)SPACE, SPACE, and WORD against -a general or particular category. The properties in each row are those -that apply to the character set in question. Duplication means that a little -unnecessary work is done when checking, but this keeps things much simpler -because they can all use the same code. For more details see the comment where -this table is used. - -Note: SPACE and PXSPACE used to be different because Perl excluded VT from -"space", but from Perl 5.18 it's included, so both categories are treated the -same here. */ - -static const pcre_uint8 posspropstab[3][4] = { - { ucp_L, ucp_N, ucp_N, ucp_Nl }, /* ALNUM, 3rd and 4th values redundant */ - { ucp_Z, ucp_Z, ucp_C, ucp_Cc }, /* SPACE and PXSPACE, 2nd value redundant */ - { ucp_L, ucp_N, ucp_P, ucp_Po } /* WORD */ -}; - -/* This table is used when converting repeating opcodes into possessified -versions as a result of an explicit possessive quantifier such as ++. A zero -value means there is no possessified version - in those cases the item in -question must be wrapped in ONCE brackets. The table is truncated at OP_CALLOUT -because all relevant opcodes are less than that. */ - -static const pcre_uint8 opcode_possessify[] = { - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 15 */ - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 16 - 31 */ - - 0, /* NOTI */ - OP_POSSTAR, 0, /* STAR, MINSTAR */ - OP_POSPLUS, 0, /* PLUS, MINPLUS */ - OP_POSQUERY, 0, /* QUERY, MINQUERY */ - OP_POSUPTO, 0, /* UPTO, MINUPTO */ - 0, /* EXACT */ - 0, 0, 0, 0, /* POS{STAR,PLUS,QUERY,UPTO} */ - - OP_POSSTARI, 0, /* STARI, MINSTARI */ - OP_POSPLUSI, 0, /* PLUSI, MINPLUSI */ - OP_POSQUERYI, 0, /* QUERYI, MINQUERYI */ - OP_POSUPTOI, 0, /* UPTOI, MINUPTOI */ - 0, /* EXACTI */ - 0, 0, 0, 0, /* POS{STARI,PLUSI,QUERYI,UPTOI} */ - - OP_NOTPOSSTAR, 0, /* NOTSTAR, NOTMINSTAR */ - OP_NOTPOSPLUS, 0, /* NOTPLUS, NOTMINPLUS */ - OP_NOTPOSQUERY, 0, /* NOTQUERY, NOTMINQUERY */ - OP_NOTPOSUPTO, 0, /* NOTUPTO, NOTMINUPTO */ - 0, /* NOTEXACT */ - 0, 0, 0, 0, /* NOTPOS{STAR,PLUS,QUERY,UPTO} */ - - OP_NOTPOSSTARI, 0, /* NOTSTARI, NOTMINSTARI */ - OP_NOTPOSPLUSI, 0, /* NOTPLUSI, NOTMINPLUSI */ - OP_NOTPOSQUERYI, 0, /* NOTQUERYI, NOTMINQUERYI */ - OP_NOTPOSUPTOI, 0, /* NOTUPTOI, NOTMINUPTOI */ - 0, /* NOTEXACTI */ - 0, 0, 0, 0, /* NOTPOS{STARI,PLUSI,QUERYI,UPTOI} */ - - OP_TYPEPOSSTAR, 0, /* TYPESTAR, TYPEMINSTAR */ - OP_TYPEPOSPLUS, 0, /* TYPEPLUS, TYPEMINPLUS */ - OP_TYPEPOSQUERY, 0, /* TYPEQUERY, TYPEMINQUERY */ - OP_TYPEPOSUPTO, 0, /* TYPEUPTO, TYPEMINUPTO */ - 0, /* TYPEEXACT */ - 0, 0, 0, 0, /* TYPEPOS{STAR,PLUS,QUERY,UPTO} */ - - OP_CRPOSSTAR, 0, /* CRSTAR, CRMINSTAR */ - OP_CRPOSPLUS, 0, /* CRPLUS, CRMINPLUS */ - OP_CRPOSQUERY, 0, /* CRQUERY, CRMINQUERY */ - OP_CRPOSRANGE, 0, /* CRRANGE, CRMINRANGE */ - 0, 0, 0, 0, /* CRPOS{STAR,PLUS,QUERY,RANGE} */ - - 0, 0, 0, /* CLASS, NCLASS, XCLASS */ - 0, 0, /* REF, REFI */ - 0, 0, /* DNREF, DNREFI */ - 0, 0 /* RECURSE, CALLOUT */ -}; - - - -/************************************************* -* Find an error text * -*************************************************/ - -/* The error texts are now all in one long string, to save on relocations. As -some of the text is of unknown length, we can't use a table of offsets. -Instead, just count through the strings. This is not a performance issue -because it happens only when there has been a compilation error. - -Argument: the error number -Returns: pointer to the error string -*/ - -static const char * -find_error_text(int n) -{ -const char *s = error_texts; -for (; n > 0; n--) - { - while (*s++ != CHAR_NULL) {}; - if (*s == CHAR_NULL) return "Error text not found (please report)"; - } -return s; -} - - - -/************************************************* -* Expand the workspace * -*************************************************/ - -/* This function is called during the second compiling phase, if the number of -forward references fills the existing workspace, which is originally a block on -the stack. A larger block is obtained from malloc() unless the ultimate limit -has been reached or the increase will be rather small. - -Argument: pointer to the compile data block -Returns: 0 if all went well, else an error number -*/ - -static int -expand_workspace(compile_data *cd) -{ -pcre_uchar *newspace; -int newsize = cd->workspace_size * 2; - -if (newsize > COMPILE_WORK_SIZE_MAX) newsize = COMPILE_WORK_SIZE_MAX; -if (cd->workspace_size >= COMPILE_WORK_SIZE_MAX || - newsize - cd->workspace_size < WORK_SIZE_SAFETY_MARGIN) - return ERR72; - -newspace = (PUBL(malloc))(IN_UCHARS(newsize)); -if (newspace == NULL) return ERR21; -memcpy(newspace, cd->start_workspace, cd->workspace_size * sizeof(pcre_uchar)); -cd->hwm = (pcre_uchar *)newspace + (cd->hwm - cd->start_workspace); -if (cd->workspace_size > COMPILE_WORK_SIZE) - (PUBL(free))((void *)cd->start_workspace); -cd->start_workspace = newspace; -cd->workspace_size = newsize; -return 0; -} - - - -/************************************************* -* Check for counted repeat * -*************************************************/ - -/* This function is called when a '{' is encountered in a place where it might -start a quantifier. It looks ahead to see if it really is a quantifier or not. -It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} -where the ddds are digits. - -Arguments: - p pointer to the first char after '{' - -Returns: TRUE or FALSE -*/ - -static BOOL -is_counted_repeat(const pcre_uchar *p) -{ -if (!IS_DIGIT(*p)) return FALSE; -p++; -while (IS_DIGIT(*p)) p++; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if (*p++ != CHAR_COMMA) return FALSE; -if (*p == CHAR_RIGHT_CURLY_BRACKET) return TRUE; - -if (!IS_DIGIT(*p)) return FALSE; -p++; -while (IS_DIGIT(*p)) p++; - -return (*p == CHAR_RIGHT_CURLY_BRACKET); -} - - - -/************************************************* -* Handle escapes * -*************************************************/ - -/* This function is called when a \ has been encountered. It either returns a -positive value for a simple escape such as \n, or 0 for a data character which -will be placed in chptr. A backreference to group n is returned as negative n. -When UTF-8 is enabled, a positive value greater than 255 may be returned in -chptr. On entry, ptr is pointing at the \. On exit, it is on the final -character of the escape sequence. - -Arguments: - ptrptr points to the pattern position pointer - chptr points to a returned data character - errorcodeptr points to the errorcode variable - bracount number of previous extracting brackets - options the options bits - isclass TRUE if inside a character class - -Returns: zero => a data character - positive => a special escape sequence - negative => a back reference - on error, errorcodeptr is set -*/ - -static int -check_escape(const pcre_uchar **ptrptr, pcre_uint32 *chptr, int *errorcodeptr, - int bracount, int options, BOOL isclass) -{ -/* PCRE_UTF16 has the same value as PCRE_UTF8. */ -BOOL utf = (options & PCRE_UTF8) != 0; -const pcre_uchar *ptr = *ptrptr + 1; -pcre_uint32 c; -int escape = 0; -int i; - -GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ -ptr--; /* Set pointer back to the last byte */ - -/* If backslash is at the end of the pattern, it's an error. */ - -if (c == CHAR_NULL) *errorcodeptr = ERR1; - -/* Non-alphanumerics are literals. For digits or letters, do an initial lookup -in a table. A non-zero result is something that can be returned immediately. -Otherwise further processing may be required. */ - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ -/* Not alphanumeric */ -else if (c < CHAR_0 || c > CHAR_z) {} -else if ((i = escapes[c - CHAR_0]) != 0) - { if (i > 0) c = (pcre_uint32)i; else escape = -i; } - -#else /* EBCDIC coding */ -/* Not alphanumeric */ -else if (c < CHAR_a || (!MAX_255(c) || (ebcdic_chartab[c] & 0x0E) == 0)) {} -else if ((i = escapes[c - 0x48]) != 0) { if (i > 0) c = (pcre_uint32)i; else escape = -i; } -#endif - -/* Escapes that need further processing, or are illegal. */ - -else - { - const pcre_uchar *oldptr; - BOOL braced, negated, overflow; - int s; - - switch (c) - { - /* A number of Perl escapes are not handled by PCRE. We give an explicit - error. */ - - case CHAR_l: - case CHAR_L: - *errorcodeptr = ERR37; - break; - - case CHAR_u: - if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - /* In JavaScript, \u must be followed by four hexadecimal numbers. - Otherwise it is a lowercase u letter. */ - if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 - && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0 - && MAX_255(ptr[3]) && (digitab[ptr[3]] & ctype_xdigit) != 0 - && MAX_255(ptr[4]) && (digitab[ptr[4]] & ctype_xdigit) != 0) - { - c = 0; - for (i = 0; i < 4; ++i) - { - register pcre_uint32 cc = *(++ptr); -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) -#endif - { - *errorcodeptr = ERR76; - } - else if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - } - else - *errorcodeptr = ERR37; - break; - - case CHAR_U: - /* In JavaScript, \U is an uppercase U letter. */ - if ((options & PCRE_JAVASCRIPT_COMPAT) == 0) *errorcodeptr = ERR37; - break; - - /* In a character class, \g is just a literal "g". Outside a character - class, \g must be followed by one of a number of specific things: - - (1) A number, either plain or braced. If positive, it is an absolute - backreference. If negative, it is a relative backreference. This is a Perl - 5.10 feature. - - (2) Perl 5.10 also supports \g{name} as a reference to a named group. This - is part of Perl's movement towards a unified syntax for back references. As - this is synonymous with \k{name}, we fudge it up by pretending it really - was \k. - - (3) For Oniguruma compatibility we also support \g followed by a name or a - number either in angle brackets or in single quotes. However, these are - (possibly recursive) subroutine calls, _not_ backreferences. Just return - the ESC_g code (cf \k). */ - - case CHAR_g: - if (isclass) break; - if (ptr[1] == CHAR_LESS_THAN_SIGN || ptr[1] == CHAR_APOSTROPHE) - { - escape = ESC_g; - break; - } - - /* Handle the Perl-compatible cases */ - - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - const pcre_uchar *p; - for (p = ptr+2; *p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET; p++) - if (*p != CHAR_MINUS && !IS_DIGIT(*p)) break; - if (*p != CHAR_NULL && *p != CHAR_RIGHT_CURLY_BRACKET) - { - escape = ESC_k; - break; - } - braced = TRUE; - ptr++; - } - else braced = FALSE; - - if (ptr[1] == CHAR_MINUS) - { - negated = TRUE; - ptr++; - } - else negated = FALSE; - - /* The integer range is limited by the machine's int representation. */ - s = 0; - overflow = FALSE; - while (IS_DIGIT(ptr[1])) - { - if (s > INT_MAX / 10 - 1) /* Integer overflow */ - { - overflow = TRUE; - break; - } - s = s * 10 + (int)(*(++ptr) - CHAR_0); - } - if (overflow) /* Integer overflow */ - { - while (IS_DIGIT(ptr[1])) - ptr++; - *errorcodeptr = ERR61; - break; - } - - if (braced && *(++ptr) != CHAR_RIGHT_CURLY_BRACKET) - { - *errorcodeptr = ERR57; - break; - } - - if (s == 0) - { - *errorcodeptr = ERR58; - break; - } - - if (negated) - { - if (s > bracount) - { - *errorcodeptr = ERR15; - break; - } - s = bracount - (s - 1); - } - - escape = -s; - break; - - /* The handling of escape sequences consisting of a string of digits - starting with one that is not zero is not straightforward. Perl has changed - over the years. Nowadays \g{} for backreferences and \o{} for octal are - recommended to avoid the ambiguities in the old syntax. - - Outside a character class, the digits are read as a decimal number. If the - number is less than 8 (used to be 10), or if there are that many previous - extracting left brackets, then it is a back reference. Otherwise, up to - three octal digits are read to form an escaped byte. Thus \123 is likely to - be octal 123 (cf \0123, which is octal 012 followed by the literal 3). If - the octal value is greater than 377, the least significant 8 bits are - taken. \8 and \9 are treated as the literal characters 8 and 9. - - Inside a character class, \ followed by a digit is always either a literal - 8 or 9 or an octal number. */ - - case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: case CHAR_5: - case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - - if (!isclass) - { - oldptr = ptr; - /* The integer range is limited by the machine's int representation. */ - s = (int)(c -CHAR_0); - overflow = FALSE; - while (IS_DIGIT(ptr[1])) - { - if (s > INT_MAX / 10 - 1) /* Integer overflow */ - { - overflow = TRUE; - break; - } - s = s * 10 + (int)(*(++ptr) - CHAR_0); - } - if (overflow) /* Integer overflow */ - { - while (IS_DIGIT(ptr[1])) - ptr++; - *errorcodeptr = ERR61; - break; - } - if (s < 8 || s <= bracount) /* Check for back reference */ - { - escape = -s; - break; - } - ptr = oldptr; /* Put the pointer back and fall through */ - } - - /* Handle a digit following \ when the number is not a back reference. If - the first digit is 8 or 9, Perl used to generate a binary zero byte and - then treat the digit as a following literal. At least by Perl 5.18 this - changed so as not to insert the binary zero. */ - - if ((c = *ptr) >= CHAR_8) break; - - /* Fall through with a digit less than 8 */ - - /* \0 always starts an octal number, but we may drop through to here with a - larger first octal digit. The original code used just to take the least - significant 8 bits of octal numbers (I think this is what early Perls used - to do). Nowadays we allow for larger numbers in UTF-8 mode and 16-bit mode, - but no more than 3 octal digits. */ - - case CHAR_0: - c -= CHAR_0; - while(i++ < 2 && ptr[1] >= CHAR_0 && ptr[1] <= CHAR_7) - c = c * 8 + *(++ptr) - CHAR_0; -#ifdef COMPILE_PCRE8 - if (!utf && c > 0xff) *errorcodeptr = ERR51; -#endif - break; - - /* \o is a relatively new Perl feature, supporting a more general way of - specifying character codes in octal. The only supported form is \o{ddd}. */ - - case CHAR_o: - if (ptr[1] != CHAR_LEFT_CURLY_BRACKET) *errorcodeptr = ERR81; else - { - ptr += 2; - c = 0; - overflow = FALSE; - while (*ptr >= CHAR_0 && *ptr <= CHAR_7) - { - register pcre_uint32 cc = *ptr++; - if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ -#ifdef COMPILE_PCRE32 - if (c >= 0x20000000l) { overflow = TRUE; break; } -#endif - c = (c << 3) + cc - CHAR_0 ; -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) { overflow = TRUE; break; } -#endif - } - if (overflow) - { - while (*ptr >= CHAR_0 && *ptr <= CHAR_7) ptr++; - *errorcodeptr = ERR34; - } - else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) - { - if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - else *errorcodeptr = ERR80; - } - break; - - /* \x is complicated. In JavaScript, \x must be followed by two hexadecimal - numbers. Otherwise it is a lowercase x letter. */ - - case CHAR_x: - if ((options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - if (MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0 - && MAX_255(ptr[2]) && (digitab[ptr[2]] & ctype_xdigit) != 0) - { - c = 0; - for (i = 0; i < 2; ++i) - { - register pcre_uint32 cc = *(++ptr); -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - } - } /* End JavaScript handling */ - - /* Handle \x in Perl's style. \x{ddd} is a character number which can be - greater than 0xff in utf or non-8bit mode, but only if the ddd are hex - digits. If not, { used to be treated as a data character. However, Perl - seems to read hex digits up to the first non-such, and ignore the rest, so - that, for example \x{zz} matches a binary zero. This seems crazy, so PCRE - now gives an error. */ - - else - { - if (ptr[1] == CHAR_LEFT_CURLY_BRACKET) - { - ptr += 2; - c = 0; - overflow = FALSE; - while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) - { - register pcre_uint32 cc = *ptr++; - if (c == 0 && cc == CHAR_0) continue; /* Leading zeroes */ - -#ifdef COMPILE_PCRE32 - if (c >= 0x10000000l) { overflow = TRUE; break; } -#endif - -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc >= CHAR_a && cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - -#if defined COMPILE_PCRE8 - if (c > (utf ? 0x10ffffU : 0xffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE16 - if (c > (utf ? 0x10ffffU : 0xffffU)) { overflow = TRUE; break; } -#elif defined COMPILE_PCRE32 - if (utf && c > 0x10ffffU) { overflow = TRUE; break; } -#endif - } - - if (overflow) - { - while (MAX_255(*ptr) && (digitab[*ptr] & ctype_xdigit) != 0) ptr++; - *errorcodeptr = ERR34; - } - - else if (*ptr == CHAR_RIGHT_CURLY_BRACKET) - { - if (utf && c >= 0xd800 && c <= 0xdfff) *errorcodeptr = ERR73; - } - - /* If the sequence of hex digits does not end with '}', give an error. - We used just to recognize this construct and fall through to the normal - \x handling, but nowadays Perl gives an error, which seems much more - sensible, so we do too. */ - - else *errorcodeptr = ERR79; - } /* End of \x{} processing */ - - /* Read a single-byte hex-defined char (up to two hex digits after \x) */ - - else - { - c = 0; - while (i++ < 2 && MAX_255(ptr[1]) && (digitab[ptr[1]] & ctype_xdigit) != 0) - { - pcre_uint32 cc; /* Some compilers don't like */ - cc = *(++ptr); /* ++ in initializers */ -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (cc >= CHAR_a) cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < CHAR_A)? CHAR_0 : (CHAR_A - 10)); -#else /* EBCDIC coding */ - if (cc <= CHAR_z) cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= CHAR_0)? CHAR_0 : (CHAR_A - 10)); -#endif - } - } /* End of \xdd handling */ - } /* End of Perl-style \x handling */ - break; - - /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. - An error is given if the byte following \c is not an ASCII character. This - coding is ASCII-specific, but then the whole concept of \cx is - ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ - - case CHAR_c: - c = *(++ptr); - if (c == CHAR_NULL) - { - *errorcodeptr = ERR2; - break; - } -#ifndef EBCDIC /* ASCII/UTF-8 coding */ - if (c > 127) /* Excludes all non-ASCII in either mode */ - { - *errorcodeptr = ERR68; - break; - } - if (c >= CHAR_a && c <= CHAR_z) c -= 32; - c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= CHAR_a && c <= CHAR_z) c += 64; - c ^= 0xC0; -#endif - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphanumeric following \ is an error if PCRE_EXTRA was set; - otherwise, for Perl compatibility, it is a literal. This code looks a bit - odd, but there used to be some cases other than the default, and there may - be again in future, so I haven't "optimized" it. */ - - default: - if ((options & PCRE_EXTRA) != 0) switch(c) - { - default: - *errorcodeptr = ERR3; - break; - } - break; - } - } - -/* Perl supports \N{name} for character names, as well as plain \N for "not -newline". PCRE does not support \N{name}. However, it does support -quantification such as \N{2,3}. */ - -if (escape == ESC_N && ptr[1] == CHAR_LEFT_CURLY_BRACKET && - !is_counted_repeat(ptr+2)) - *errorcodeptr = ERR37; - -/* If PCRE_UCP is set, we change the values for \d etc. */ - -if ((options & PCRE_UCP) != 0 && escape >= ESC_D && escape <= ESC_w) - escape += (ESC_DU - ESC_D); - -/* Set the pointer to the final character before returning. */ - -*ptrptr = ptr; -*chptr = c; -return escape; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Handle \P and \p * -*************************************************/ - -/* This function is called after \P or \p has been encountered, provided that -PCRE is compiled with support for Unicode properties. On entry, ptrptr is -pointing at the P or p. On exit, it is pointing at the final character of the -escape sequence. - -Argument: - ptrptr points to the pattern position pointer - negptr points to a boolean that is set TRUE for negation else FALSE - ptypeptr points to an unsigned int that is set to the type value - pdataptr points to an unsigned int that is set to the detailed property value - errorcodeptr points to the error code variable - -Returns: TRUE if the type value was found, or FALSE for an invalid type -*/ - -static BOOL -get_ucp(const pcre_uchar **ptrptr, BOOL *negptr, unsigned int *ptypeptr, - unsigned int *pdataptr, int *errorcodeptr) -{ -pcre_uchar c; -int i, bot, top; -const pcre_uchar *ptr = *ptrptr; -pcre_uchar name[32]; - -c = *(++ptr); -if (c == CHAR_NULL) goto ERROR_RETURN; - -*negptr = FALSE; - -/* \P or \p can be followed by a name in {}, optionally preceded by ^ for -negation. */ - -if (c == CHAR_LEFT_CURLY_BRACKET) - { - if (ptr[1] == CHAR_CIRCUMFLEX_ACCENT) - { - *negptr = TRUE; - ptr++; - } - for (i = 0; i < (int)(sizeof(name) / sizeof(pcre_uchar)) - 1; i++) - { - c = *(++ptr); - if (c == CHAR_NULL) goto ERROR_RETURN; - if (c == CHAR_RIGHT_CURLY_BRACKET) break; - name[i] = c; - } - if (c != CHAR_RIGHT_CURLY_BRACKET) goto ERROR_RETURN; - name[i] = 0; - } - -/* Otherwise there is just one following character */ - -else - { - name[0] = c; - name[1] = 0; - } - -*ptrptr = ptr; - -/* Search for a recognized property name using binary chop */ - -bot = 0; -top = PRIV(utt_size); - -while (bot < top) - { - int r; - i = (bot + top) >> 1; - r = STRCMP_UC_C8(name, PRIV(utt_names) + PRIV(utt)[i].name_offset); - if (r == 0) - { - *ptypeptr = PRIV(utt)[i].type; - *pdataptr = PRIV(utt)[i].value; - return TRUE; - } - if (r > 0) bot = i + 1; else top = i; - } - -*errorcodeptr = ERR47; -*ptrptr = ptr; -return FALSE; - -ERROR_RETURN: -*errorcodeptr = ERR46; -*ptrptr = ptr; -return FALSE; -} -#endif - - - -/************************************************* -* Read repeat counts * -*************************************************/ - -/* Read an item of the form {n,m} and return the values. This is called only -after is_counted_repeat() has confirmed that a repeat-count quantifier exists, -so the syntax is guaranteed to be correct, but we need to check the values. - -Arguments: - p pointer to first char after '{' - minp pointer to int for min - maxp pointer to int for max - returned as -1 if no max - errorcodeptr points to error code variable - -Returns: pointer to '}' on success; - current ptr on error, with errorcodeptr set non-zero -*/ - -static const pcre_uchar * -read_repeat_counts(const pcre_uchar *p, int *minp, int *maxp, int *errorcodeptr) -{ -int min = 0; -int max = -1; - -/* Read the minimum value and do a paranoid check: a negative value indicates -an integer overflow. */ - -while (IS_DIGIT(*p)) min = min * 10 + (int)(*p++ - CHAR_0); -if (min < 0 || min > 65535) - { - *errorcodeptr = ERR5; - return p; - } - -/* Read the maximum value if there is one, and again do a paranoid on its size. -Also, max must not be less than min. */ - -if (*p == CHAR_RIGHT_CURLY_BRACKET) max = min; else - { - if (*(++p) != CHAR_RIGHT_CURLY_BRACKET) - { - max = 0; - while(IS_DIGIT(*p)) max = max * 10 + (int)(*p++ - CHAR_0); - if (max < 0 || max > 65535) - { - *errorcodeptr = ERR5; - return p; - } - if (max < min) - { - *errorcodeptr = ERR4; - return p; - } - } - } - -/* Fill in the required variables, and pass back the pointer to the terminating -'}'. */ - -*minp = min; -*maxp = max; -return p; -} - - - -/************************************************* -* Find first significant op code * -*************************************************/ - -/* This is called by several functions that scan a compiled expression looking -for a fixed first character, or an anchoring op code etc. It skips over things -that do not influence this. For some calls, it makes sense to skip negative -forward and all backward assertions, and also the \b assertion; for others it -does not. - -Arguments: - code pointer to the start of the group - skipassert TRUE if certain assertions are to be skipped - -Returns: pointer to the first significant opcode -*/ - -static const pcre_uchar* -first_significant_code(const pcre_uchar *code, BOOL skipassert) -{ -for (;;) - { - switch ((int)*code) - { - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - if (!skipassert) return code; - do code += GET(code, 1); while (*code == OP_ALT); - code += PRIV(OP_lengths)[*code]; - break; - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - if (!skipassert) return code; - /* Fall through */ - - case OP_CALLOUT: - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - code += PRIV(OP_lengths)[*code]; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - -/************************************************* -* Find the fixed length of a branch * -*************************************************/ - -/* Scan a branch and compute the fixed length of subject that will match it, -if the length is fixed. This is needed for dealing with backward assertions. -In UTF8 mode, the result is in characters rather than bytes. The branch is -temporarily terminated with OP_END when this function is called. - -This function is called when a backward assertion is encountered, so that if it -fails, the error message can point to the correct place in the pattern. -However, we cannot do this when the assertion contains subroutine calls, -because they can be forward references. We solve this by remembering this case -and doing the check at the end; a flag specifies which mode we are running in. - -Arguments: - code points to the start of the pattern (the bracket) - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - atend TRUE if called when the pattern is complete - cd the "compile data" structure - -Returns: the fixed length, - or -1 if there is no fixed length, - or -2 if \C was encountered (in UTF-8 mode only) - or -3 if an OP_RECURSE item was encountered and atend is FALSE - or -4 if an unknown opcode was encountered (internal error) -*/ - -static int -find_fixedlength(pcre_uchar *code, BOOL utf, BOOL atend, compile_data *cd) -{ -int length = -1; - -register int branchlength = 0; -register pcre_uchar *cc = code + 1 + LINK_SIZE; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d; - pcre_uchar *ce, *cs; - register pcre_uchar op = *cc; - - switch (op) - { - /* We only need to continue for OP_CBRA (normal capturing bracket) and - OP_BRA (normal non-capturing bracket) because the other variants of these - opcodes are all concerned with unlimited repeated groups, which of course - are not of fixed length. */ - - case OP_CBRA: - case OP_BRA: - case OP_ONCE: - case OP_ONCE_NC: - case OP_COND: - d = find_fixedlength(cc + ((op == OP_CBRA)? IMM2_SIZE : 0), utf, atend, cd); - if (d < 0) return d; - branchlength += d; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Reached end of a branch; if it's a ket it is the end of a nested call. - If it's ALT it is an alternation in a nested call. An ACCEPT is effectively - an ALT. If it is END it's the end of the outer call. All can be handled by - the same code. Note that we must not include the OP_KETRxxx opcodes here, - because they all imply an unlimited repeat. */ - - case OP_ALT: - case OP_KET: - case OP_END: - case OP_ACCEPT: - case OP_ASSERT_ACCEPT: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - break; - - /* A true recursion implies not fixed length, but a subroutine call may - be OK. If the subroutine is a forward reference, we can't deal with - it until the end of the pattern, so return -3. */ - - case OP_RECURSE: - if (!atend) return -3; - cs = ce = (pcre_uchar *)cd->start_code + GET(cc, 1); /* Start subpattern */ - do ce += GET(ce, 1); while (*ce == OP_ALT); /* End subpattern */ - if (cc > cs && cc < ce) return -1; /* Recursion */ - d = find_fixedlength(cs + IMM2_SIZE, utf, atend, cd); - if (d < 0) return d; - branchlength += d; - cc += 1 + LINK_SIZE; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += PRIV(OP_lengths)[*cc]; - break; - - /* Skip over things that don't match chars */ - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - cc += cc[1] + PRIV(OP_lengths)[*cc]; - break; - - case OP_CALLOUT: - case OP_CIRC: - case OP_CIRCM: - case OP_CLOSE: - case OP_COMMIT: - case OP_CREF: - case OP_DEF: - case OP_DNCREF: - case OP_DNRREF: - case OP_DOLL: - case OP_DOLLM: - case OP_EOD: - case OP_EODN: - case OP_FAIL: - case OP_NOT_WORD_BOUNDARY: - case OP_PRUNE: - case OP_REVERSE: - case OP_RREF: - case OP_SET_SOM: - case OP_SKIP: - case OP_SOD: - case OP_SOM: - case OP_THEN: - case OP_WORD_BOUNDARY: - cc += PRIV(OP_lengths)[*cc]; - break; - - /* Handle literal characters */ - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - /* Handle exact repetitions. The count is already in characters, but we - need to skip over a multibyte character in UTF8 mode. */ - - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - branchlength += (int)GET2(cc,1); - cc += 2 + IMM2_SIZE; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(cc[-1])) cc += GET_EXTRALEN(cc[-1]); -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - if (cc[1 + IMM2_SIZE] == OP_PROP || cc[1 + IMM2_SIZE] == OP_NOTPROP) - cc += 2; - cc += 1 + IMM2_SIZE + 1; - break; - - /* Handle single-char matchers */ - - case OP_PROP: - case OP_NOTPROP: - cc += 2; - /* Fall through */ - - case OP_HSPACE: - case OP_VSPACE: - case OP_NOT_HSPACE: - case OP_NOT_VSPACE: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - branchlength++; - cc++; - break; - - /* The single-byte matcher isn't allowed. This only happens in UTF-8 mode; - otherwise \C is coded as OP_ALLANY. */ - - case OP_ANYBYTE: - return -2; - - /* Check a class for variable quantification */ - - case OP_CLASS: - case OP_NCLASS: -#if defined SUPPORT_UTF || defined COMPILE_PCRE16 || defined COMPILE_PCRE32 - case OP_XCLASS: - /* The original code caused an unsigned overflow in 64 bit systems, - so now we use a conditional statement. */ - if (op == OP_XCLASS) - cc += GET(cc, 1); - else - cc += PRIV(OP_lengths)[OP_CLASS]; -#else - cc += PRIV(OP_lengths)[OP_CLASS]; -#endif - - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSPLUS: - case OP_CRPOSQUERY: - return -1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - if (GET2(cc,1) != GET2(cc,1+IMM2_SIZE)) return -1; - branchlength += (int)GET2(cc,1); - cc += 1 + 2 * IMM2_SIZE; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - case OP_ANYNL: - case OP_BRAMINZERO: - case OP_BRAPOS: - case OP_BRAPOSZERO: - case OP_BRAZERO: - case OP_CBRAPOS: - case OP_EXTUNI: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_PLUS: - case OP_PLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_QUERY: - case OP_QUERYI: - case OP_REF: - case OP_REFI: - case OP_DNREF: - case OP_DNREFI: - case OP_SBRA: - case OP_SBRAPOS: - case OP_SCBRA: - case OP_SCBRAPOS: - case OP_SCOND: - case OP_SKIPZERO: - case OP_STAR: - case OP_STARI: - case OP_TYPEMINPLUS: - case OP_TYPEMINQUERY: - case OP_TYPEMINSTAR: - case OP_TYPEMINUPTO: - case OP_TYPEPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSUPTO: - case OP_TYPEQUERY: - case OP_TYPESTAR: - case OP_TYPEUPTO: - case OP_UPTO: - case OP_UPTOI: - return -1; - - /* Catch unrecognized opcodes so that when new ones are added they - are not forgotten, as has happened in the past. */ - - default: - return -4; - } - } -/* Control never gets here */ -} - - - -/************************************************* -* Scan compiled regex for specific bracket * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds a -capturing bracket with the given number, or, if the number is negative, an -instance of OP_REVERSE for a lookbehind. The function is global in the C sense -so that it can be called from pcre_study() when finding the minimum matching -length. - -Arguments: - code points to start of expression - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - number the required bracket number or negative to find a lookbehind - -Returns: pointer to the opcode for the bracket, or NULL if not found -*/ - -const pcre_uchar * -PRIV(find_bracket)(const pcre_uchar *code, BOOL utf, int number) -{ -for (;;) - { - register pcre_uchar c = *code; - - if (c == OP_END) return NULL; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Handle recursion */ - - else if (c == OP_REVERSE) - { - if (number < 0) return (pcre_uchar *)code; - code += PRIV(OP_lengths)[c]; - } - - /* Handle capturing bracket */ - - else if (c == OP_CBRA || c == OP_SCBRA || - c == OP_CBRAPOS || c == OP_SCBRAPOS) - { - int n = (int)GET2(code, 1+LINK_SIZE); - if (n == number) return (pcre_uchar *)code; - code += PRIV(OP_lengths)[c]; - } - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we - must add in its length. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_EXACT: - case OP_EXACTI: - case OP_UPTO: - case OP_UPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_STAR: - case OP_STARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_PLUS: - case OP_PLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_QUERY: - case OP_QUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_POSQUERY: - case OP_POSQUERYI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled regex for recursion reference * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds an -instance of OP_RECURSE. - -Arguments: - code points to start of expression - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - -Returns: pointer to the opcode for OP_RECURSE, or NULL if not found -*/ - -static const pcre_uchar * -find_recurse(const pcre_uchar *code, BOOL utf) -{ -for (;;) - { - register pcre_uchar c = *code; - if (c == OP_END) return NULL; - if (c == OP_RECURSE) return code; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters, and for MARK/PRUNE/SKIP/THEN with an argument, we - must add in its length. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEPOSUPTO: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed - by a multi-byte character. The length in the table is a minimum, so we have - to arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - case OP_PLUS: - case OP_PLUSI: - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } - } -} - - - -/************************************************* -* Scan compiled branch for non-emptiness * -*************************************************/ - -/* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called from could_be_empty() -below and from compile_branch() when checking for an unlimited repeat of a -group that can match nothing. Note that first_significant_code() skips over -backward and negative forward assertions when its final argument is TRUE. If we -hit an unclosed bracket, we return "empty" - this means we've struck an inner -bracket whose current branch will already have been scanned. - -Arguments: - code points to start of search - endcode points to where to stop - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - cd contains pointers to tables etc. - recurses chain of recurse_check to catch mutual recursion - -Returns: TRUE if what is matched could be empty -*/ - -typedef struct recurse_check { - struct recurse_check *prev; - const pcre_uchar *group; -} recurse_check; - -static BOOL -could_be_empty_branch(const pcre_uchar *code, const pcre_uchar *endcode, - BOOL utf, compile_data *cd, recurse_check *recurses) -{ -register pcre_uchar c; -recurse_check this_recurse; - -for (code = first_significant_code(code + PRIV(OP_lengths)[*code], TRUE); - code < endcode; - code = first_significant_code(code + PRIV(OP_lengths)[c], TRUE)) - { - const pcre_uchar *ccode; - - c = *code; - - /* Skip over forward assertions; the other assertions are skipped by - first_significant_code() with a TRUE final argument. */ - - if (c == OP_ASSERT) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For a recursion/subroutine call, if its end has been reached, which - implies a backward reference subroutine call, we can scan it. If it's a - forward reference subroutine call, we can't. To detect forward reference - we have to scan up the list that is kept in the workspace. This function is - called only when doing the real compile, not during the pre-compile that - measures the size of the compiled pattern. */ - - if (c == OP_RECURSE) - { - const pcre_uchar *scode = cd->start_code + GET(code, 1); - BOOL empty_branch; - - /* Test for forward reference or uncompleted reference. This is disabled - when called to scan a completed pattern by setting cd->start_workspace to - NULL. */ - - if (cd->start_workspace != NULL) - { - const pcre_uchar *tcode; - for (tcode = cd->start_workspace; tcode < cd->hwm; tcode += LINK_SIZE) - if ((int)GET(tcode, 0) == (int)(code + 1 - cd->start_code)) return TRUE; - if (GET(scode, 1) == 0) return TRUE; /* Unclosed */ - } - - /* If we are scanning a completed pattern, there are no forward references - and all groups are complete. We need to detect whether this is a recursive - call, as otherwise there will be an infinite loop. If it is a recursion, - just skip over it. Simple recursions are easily detected. For mutual - recursions we keep a chain on the stack. */ - - else - { - recurse_check *r = recurses; - const pcre_uchar *endgroup = scode; - - do endgroup += GET(endgroup, 1); while (*endgroup == OP_ALT); - if (code >= scode && code <= endgroup) continue; /* Simple recursion */ - - for (r = recurses; r != NULL; r = r->prev) - if (r->group == scode) break; - if (r != NULL) continue; /* Mutual recursion */ - } - - /* Completed reference; scan the referenced group, remembering it on the - stack chain to detect mutual recursions. */ - - empty_branch = FALSE; - this_recurse.prev = recurses; - this_recurse.group = scode; - - do - { - if (could_be_empty_branch(scode, endcode, utf, cd, &this_recurse)) - { - empty_branch = TRUE; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - - if (!empty_branch) return FALSE; /* All branches are non-empty */ - continue; - } - - /* Groups with zero repeats can of course be empty; skip them. */ - - if (c == OP_BRAZERO || c == OP_BRAMINZERO || c == OP_SKIPZERO || - c == OP_BRAPOSZERO) - { - code += PRIV(OP_lengths)[c]; - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* A nested group that is already marked as "could be empty" can just be - skipped. */ - - if (c == OP_SBRA || c == OP_SBRAPOS || - c == OP_SCBRA || c == OP_SCBRAPOS) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For other groups, scan the branches. */ - - if (c == OP_BRA || c == OP_BRAPOS || - c == OP_CBRA || c == OP_CBRAPOS || - c == OP_ONCE || c == OP_ONCE_NC || - c == OP_COND) - { - BOOL empty_branch; - if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - - /* If a conditional group has only one branch, there is a second, implied, - empty branch, so just skip over the conditional, because it could be empty. - Otherwise, scan the individual branches of the group. */ - - if (c == OP_COND && code[GET(code, 1)] != OP_ALT) - code += GET(code, 1); - else - { - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf, cd, NULL)) - empty_branch = TRUE; - code += GET(code, 1); - } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - } - - c = *code; - continue; - } - - /* Handle the other opcodes */ - - switch (c) - { - /* Check for quantifiers after a class. XCLASS is used for classes that - cannot be represented just by a bit map. This includes negated single - high-valued characters. The length in PRIV(OP_lengths)[] is zero; the - actual length is stored in the compiled code, so we must update "code" - here. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - ccode = code += GET(code, 1); - goto CHECK_CLASS_REPEAT; -#endif - - case OP_CLASS: - case OP_NCLASS: - ccode = code + PRIV(OP_lengths)[OP_CLASS]; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - CHECK_CLASS_REPEAT: -#endif - - switch (*ccode) - { - case OP_CRSTAR: /* These could be empty; continue */ - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - break; - - default: /* Non-repeat => class must match */ - case OP_CRPLUS: /* These repeats aren't empty */ - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - return FALSE; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ - break; - } - break; - - /* Opcodes that must match a character */ - - case OP_ANY: - case OP_ALLANY: - case OP_ANYBYTE: - - case OP_PROP: - case OP_NOTPROP: - case OP_ANYNL: - - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - - case OP_PLUS: - case OP_PLUSI: - case OP_MINPLUS: - case OP_MINPLUSI: - - case OP_NOTPLUS: - case OP_NOTPLUSI: - case OP_NOTMINPLUS: - case OP_NOTMINPLUSI: - - case OP_POSPLUS: - case OP_POSPLUSI: - case OP_NOTPOSPLUS: - case OP_NOTPOSPLUSI: - - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEEXACT: - - return FALSE; - - /* These are going to continue, as they may be empty, but we have to - fudge the length for the \p and \P cases. */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - /* Same for these */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - - /* End of branch */ - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_KETRPOS: - case OP_ALT: - return TRUE; - - /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, - MINUPTO, and POSUPTO and their caseless and negative versions may be - followed by a multibyte character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - case OP_STAR: - case OP_STARI: - case OP_NOTSTAR: - case OP_NOTSTARI: - - case OP_MINSTAR: - case OP_MINSTARI: - case OP_NOTMINSTAR: - case OP_NOTMINSTARI: - - case OP_POSSTAR: - case OP_POSSTARI: - case OP_NOTPOSSTAR: - case OP_NOTPOSSTARI: - - case OP_QUERY: - case OP_QUERYI: - case OP_NOTQUERY: - case OP_NOTQUERYI: - - case OP_MINQUERY: - case OP_MINQUERYI: - case OP_NOTMINQUERY: - case OP_NOTMINQUERYI: - - case OP_POSQUERY: - case OP_POSQUERYI: - case OP_NOTPOSQUERY: - case OP_NOTPOSQUERYI: - - if (utf && HAS_EXTRALEN(code[1])) code += GET_EXTRALEN(code[1]); - break; - - case OP_UPTO: - case OP_UPTOI: - case OP_NOTUPTO: - case OP_NOTUPTOI: - - case OP_MINUPTO: - case OP_MINUPTOI: - case OP_NOTMINUPTO: - case OP_NOTMINUPTOI: - - case OP_POSUPTO: - case OP_POSUPTOI: - case OP_NOTPOSUPTO: - case OP_NOTPOSUPTOI: - - if (utf && HAS_EXTRALEN(code[1 + IMM2_SIZE])) code += GET_EXTRALEN(code[1 + IMM2_SIZE]); - break; -#endif - - /* MARK, and PRUNE/SKIP/THEN with an argument must skip over the argument - string. */ - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - - /* None of the remaining opcodes are required to match a character. */ - - default: - break; - } - } - -return TRUE; -} - - - -/************************************************* -* Scan compiled regex for non-emptiness * -*************************************************/ - -/* This function is called to check for left recursive calls. We want to check -the current branch of the current pattern to see if it could match the empty -string. If it could, we must look outwards for branches at other levels, -stopping when we pass beyond the bracket which is the subject of the recursion. -This function is called only during the real compile, not during the -pre-compile. - -Arguments: - code points to start of the recursion - endcode points to where to stop (current RECURSE item) - bcptr points to the chain of current (unclosed) branch starts - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - cd pointers to tables etc - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty(const pcre_uchar *code, const pcre_uchar *endcode, - branch_chain *bcptr, BOOL utf, compile_data *cd) -{ -while (bcptr != NULL && bcptr->current_branch >= code) - { - if (!could_be_empty_branch(bcptr->current_branch, endcode, utf, cd, NULL)) - return FALSE; - bcptr = bcptr->outer; - } -return TRUE; -} - - - -/************************************************* -* Base opcode of repeated opcodes * -*************************************************/ - -/* Returns the base opcode for repeated single character type opcodes. If the -opcode is not a repeated character type, it returns with the original value. - -Arguments: c opcode -Returns: base opcode for the type -*/ - -static pcre_uchar -get_repeat_base(pcre_uchar c) -{ -return (c > OP_TYPEPOSUPTO)? c : - (c >= OP_TYPESTAR)? OP_TYPESTAR : - (c >= OP_NOTSTARI)? OP_NOTSTARI : - (c >= OP_NOTSTAR)? OP_NOTSTAR : - (c >= OP_STARI)? OP_STARI : - OP_STAR; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Check a character and a property * -*************************************************/ - -/* This function is called by check_auto_possessive() when a property item -is adjacent to a fixed character. - -Arguments: - c the character - ptype the property type - pdata the data for the type - negated TRUE if it's a negated property (\P or \p{^) - -Returns: TRUE if auto-possessifying is OK -*/ - -static BOOL -check_char_prop(pcre_uint32 c, unsigned int ptype, unsigned int pdata, - BOOL negated) -{ -const pcre_uint32 *p; -const ucd_record *prop = GET_UCD(c); - -switch(ptype) - { - case PT_LAMP: - return (prop->chartype == ucp_Lu || - prop->chartype == ucp_Ll || - prop->chartype == ucp_Lt) == negated; - - case PT_GC: - return (pdata == PRIV(ucp_gentype)[prop->chartype]) == negated; - - case PT_PC: - return (pdata == prop->chartype) == negated; - - case PT_SC: - return (pdata == prop->script) == negated; - - /* These are specials */ - - case PT_ALNUM: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N) == negated; - - /* Perl space used to exclude VT, but from Perl 5.18 it is included, which - means that Perl space and POSIX space are now identical. PCRE was changed - at release 8.34. */ - - case PT_SPACE: /* Perl space */ - case PT_PXSPACE: /* POSIX space */ - switch(c) - { - HSPACE_CASES: - VSPACE_CASES: - return negated; - - default: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_Z) == negated; - } - break; /* Control never reaches here */ - - case PT_WORD: - return (PRIV(ucp_gentype)[prop->chartype] == ucp_L || - PRIV(ucp_gentype)[prop->chartype] == ucp_N || - c == CHAR_UNDERSCORE) == negated; - - case PT_CLIST: - p = PRIV(ucd_caseless_sets) + prop->caseset; - for (;;) - { - if (c < *p) return !negated; - if (c == *p++) return negated; - } - break; /* Control never reaches here */ - } - -return FALSE; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Fill the character property list * -*************************************************/ - -/* Checks whether the code points to an opcode that can take part in auto- -possessification, and if so, fills a list with its properties. - -Arguments: - code points to start of expression - utf TRUE if in UTF-8 / UTF-16 / UTF-32 mode - fcc points to case-flipping table - list points to output list - list[0] will be filled with the opcode - list[1] will be non-zero if this opcode - can match an empty character string - list[2..7] depends on the opcode - -Returns: points to the start of the next opcode if *code is accepted - NULL if *code is not accepted -*/ - -static const pcre_uchar * -get_chr_property_list(const pcre_uchar *code, BOOL utf, - const pcre_uint8 *fcc, pcre_uint32 *list) -{ -pcre_uchar c = *code; -pcre_uchar base; -const pcre_uchar *end; -pcre_uint32 chr; - -#ifdef SUPPORT_UCP -pcre_uint32 *clist_dest; -const pcre_uint32 *clist_src; -#else -utf = utf; /* Suppress "unused parameter" compiler warning */ -#endif - -list[0] = c; -list[1] = FALSE; -code++; - -if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) - { - base = get_repeat_base(c); - c -= (base - OP_STAR); - - if (c == OP_UPTO || c == OP_MINUPTO || c == OP_EXACT || c == OP_POSUPTO) - code += IMM2_SIZE; - - list[1] = (c != OP_PLUS && c != OP_MINPLUS && c != OP_EXACT && c != OP_POSPLUS); - - switch(base) - { - case OP_STAR: - list[0] = OP_CHAR; - break; - - case OP_STARI: - list[0] = OP_CHARI; - break; - - case OP_NOTSTAR: - list[0] = OP_NOT; - break; - - case OP_NOTSTARI: - list[0] = OP_NOTI; - break; - - case OP_TYPESTAR: - list[0] = *code; - code++; - break; - } - c = list[0]; - } - -switch(c) - { - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ALLANY: - case OP_ANYNL: - case OP_NOT_HSPACE: - case OP_HSPACE: - case OP_NOT_VSPACE: - case OP_VSPACE: - case OP_EXTUNI: - case OP_EODN: - case OP_EOD: - case OP_DOLL: - case OP_DOLLM: - return code; - - case OP_CHAR: - case OP_NOT: - GETCHARINCTEST(chr, code); - list[2] = chr; - list[3] = NOTACHAR; - return code; - - case OP_CHARI: - case OP_NOTI: - list[0] = (c == OP_CHARI) ? OP_CHAR : OP_NOT; - GETCHARINCTEST(chr, code); - list[2] = chr; - -#ifdef SUPPORT_UCP - if (chr < 128 || (chr < 256 && !utf)) - list[3] = fcc[chr]; - else - list[3] = UCD_OTHERCASE(chr); -#elif defined SUPPORT_UTF || !defined COMPILE_PCRE8 - list[3] = (chr < 256) ? fcc[chr] : chr; -#else - list[3] = fcc[chr]; -#endif - - /* The othercase might be the same value. */ - - if (chr == list[3]) - list[3] = NOTACHAR; - else - list[4] = NOTACHAR; - return code; - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (code[0] != PT_CLIST) - { - list[2] = code[0]; - list[3] = code[1]; - return code + 2; - } - - /* Convert only if we have enough space. */ - - clist_src = PRIV(ucd_caseless_sets) + code[1]; - clist_dest = list + 2; - code += 2; - - do { - if (clist_dest >= list + 8) - { - /* Early return if there is not enough space. This should never - happen, since all clists are shorter than 5 character now. */ - list[2] = code[0]; - list[3] = code[1]; - return code; - } - *clist_dest++ = *clist_src; - } - while(*clist_src++ != NOTACHAR); - - /* All characters are stored. The terminating NOTACHAR - is copied form the clist itself. */ - - list[0] = (c == OP_PROP) ? OP_CHAR : OP_NOT; - return code; -#endif - - case OP_NCLASS: - case OP_CLASS: -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - if (c == OP_XCLASS) - end = code + GET(code, 0) - 1; - else -#endif - end = code + 32 / sizeof(pcre_uchar); - - switch(*end) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - case OP_CRPOSSTAR: - case OP_CRPOSQUERY: - list[1] = TRUE; - end++; - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRPOSPLUS: - end++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - case OP_CRPOSRANGE: - list[1] = (GET2(end, 1) == 0); - end += 1 + 2 * IMM2_SIZE; - break; - } - list[2] = end - code; - return end; - } -return NULL; /* Opcode not accepted */ -} - - - -/************************************************* -* Scan further character sets for match * -*************************************************/ - -/* Checks whether the base and the current opcode have a common character, in -which case the base cannot be possessified. - -Arguments: - code points to the byte code - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd static compile data - base_list the data list of the base opcode - -Returns: TRUE if the auto-possessification is possible -*/ - -static BOOL -compare_opcodes(const pcre_uchar *code, BOOL utf, const compile_data *cd, - const pcre_uint32 *base_list, const pcre_uchar *base_end) -{ -pcre_uchar c; -pcre_uint32 list[8]; -const pcre_uint32 *chr_ptr; -const pcre_uint32 *ochr_ptr; -const pcre_uint32 *list_ptr; -const pcre_uchar *next_code; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -const pcre_uchar *xclass_flags; -#endif -const pcre_uint8 *class_bitset; -const pcre_uint8 *set1, *set2, *set_end; -pcre_uint32 chr; -BOOL accepted, invert_bits; - -/* Note: the base_list[1] contains whether the current opcode has greedy -(represented by a non-zero value) quantifier. This is a different from -other character type lists, which stores here that the character iterator -matches to an empty string (also represented by a non-zero value). */ - -for(;;) - { - /* All operations move the code pointer forward. - Therefore infinite recursions are not possible. */ - - c = *code; - - /* Skip over callouts */ - - if (c == OP_CALLOUT) - { - code += PRIV(OP_lengths)[c]; - continue; - } - - if (c == OP_ALT) - { - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - } - - switch(c) - { - case OP_END: - case OP_KETRPOS: - /* TRUE only in greedy case. The non-greedy case could be replaced by - an OP_EXACT, but it is probably not worth it. (And note that OP_EXACT - uses more memory, which we cannot get at this stage.) */ - - return base_list[1] != 0; - - case OP_KET: - /* If the bracket is capturing, and referenced by an OP_RECURSE, or - it is an atomic sub-pattern (assert, once, etc.) the non-greedy case - cannot be converted to a possessive form. */ - - if (base_list[1] == 0) return FALSE; - - switch(*(code - GET(code, 1))) - { - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_ONCE_NC: - /* Atomic sub-patterns and assertions can always auto-possessify their - last iterator. */ - return TRUE; - } - - code += PRIV(OP_lengths)[c]; - continue; - - case OP_ONCE: - case OP_ONCE_NC: - case OP_BRA: - case OP_CBRA: - next_code = code + GET(code, 1); - code += PRIV(OP_lengths)[c]; - - while (*next_code == OP_ALT) - { - if (!compare_opcodes(code, utf, cd, base_list, base_end)) return FALSE; - code = next_code + 1 + LINK_SIZE; - next_code += GET(next_code, 1); - } - continue; - - case OP_BRAZERO: - case OP_BRAMINZERO: - - next_code = code + 1; - if (*next_code != OP_BRA && *next_code != OP_CBRA - && *next_code != OP_ONCE && *next_code != OP_ONCE_NC) return FALSE; - - do next_code += GET(next_code, 1); while (*next_code == OP_ALT); - - /* The bracket content will be checked by the - OP_BRA/OP_CBRA case above. */ - next_code += 1 + LINK_SIZE; - if (!compare_opcodes(next_code, utf, cd, base_list, base_end)) - return FALSE; - - code += PRIV(OP_lengths)[c]; - continue; - } - - /* Check for a supported opcode, and load its properties. */ - - code = get_chr_property_list(code, utf, cd->fcc, list); - if (code == NULL) return FALSE; /* Unsupported */ - - /* If either opcode is a small character list, set pointers for comparing - characters from that list with another list, or with a property. */ - - if (base_list[0] == OP_CHAR) - { - chr_ptr = base_list + 2; - list_ptr = list; - } - else if (list[0] == OP_CHAR) - { - chr_ptr = list + 2; - list_ptr = base_list; - } - - /* Character bitsets can also be compared to certain opcodes. */ - - else if (base_list[0] == OP_CLASS || list[0] == OP_CLASS -#ifdef COMPILE_PCRE8 - /* In 8 bit, non-UTF mode, OP_CLASS and OP_NCLASS are the same. */ - || (!utf && (base_list[0] == OP_NCLASS || list[0] == OP_NCLASS)) -#endif - ) - { -#ifdef COMPILE_PCRE8 - if (base_list[0] == OP_CLASS || (!utf && base_list[0] == OP_NCLASS)) -#else - if (base_list[0] == OP_CLASS) -#endif - { - set1 = (pcre_uint8 *)(base_end - base_list[2]); - list_ptr = list; - } - else - { - set1 = (pcre_uint8 *)(code - list[2]); - list_ptr = base_list; - } - - invert_bits = FALSE; - switch(list_ptr[0]) - { - case OP_CLASS: - case OP_NCLASS: - set2 = (pcre_uint8 *) - ((list_ptr == list ? code : base_end) - list_ptr[2]); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - xclass_flags = (list_ptr == list ? code : base_end) - list_ptr[2] + LINK_SIZE; - if ((*xclass_flags & XCL_HASPROP) != 0) return FALSE; - if ((*xclass_flags & XCL_MAP) == 0) - { - /* No bits are set for characters < 256. */ - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - set2 = (pcre_uint8 *)(xclass_flags + 1); - break; -#endif - - case OP_NOT_DIGIT: - invert_bits = TRUE; - /* Fall through */ - case OP_DIGIT: - set2 = (pcre_uint8 *)(cd->cbits + cbit_digit); - break; - - case OP_NOT_WHITESPACE: - invert_bits = TRUE; - /* Fall through */ - case OP_WHITESPACE: - set2 = (pcre_uint8 *)(cd->cbits + cbit_space); - break; - - case OP_NOT_WORDCHAR: - invert_bits = TRUE; - /* Fall through */ - case OP_WORDCHAR: - set2 = (pcre_uint8 *)(cd->cbits + cbit_word); - break; - - default: - return FALSE; - } - - /* Because the sets are unaligned, we need - to perform byte comparison here. */ - set_end = set1 + 32; - if (invert_bits) - { - do - { - if ((*set1++ & ~(*set2++)) != 0) return FALSE; - } - while (set1 < set_end); - } - else - { - do - { - if ((*set1++ & *set2++) != 0) return FALSE; - } - while (set1 < set_end); - } - - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - - /* Some property combinations also acceptable. Unicode property opcodes are - processed specially; the rest can be handled with a lookup table. */ - - else - { - pcre_uint32 leftop, rightop; - - leftop = base_list[0]; - rightop = list[0]; - -#ifdef SUPPORT_UCP - accepted = FALSE; /* Always set in non-unicode case. */ - if (leftop == OP_PROP || leftop == OP_NOTPROP) - { - if (rightop == OP_EOD) - accepted = TRUE; - else if (rightop == OP_PROP || rightop == OP_NOTPROP) - { - int n; - const pcre_uint8 *p; - BOOL same = leftop == rightop; - BOOL lisprop = leftop == OP_PROP; - BOOL risprop = rightop == OP_PROP; - BOOL bothprop = lisprop && risprop; - - /* There's a table that specifies how each combination is to be - processed: - 0 Always return FALSE (never auto-possessify) - 1 Character groups are distinct (possessify if both are OP_PROP) - 2 Check character categories in the same group (general or particular) - 3 Return TRUE if the two opcodes are not the same - ... see comments below - */ - - n = propposstab[base_list[2]][list[2]]; - switch(n) - { - case 0: break; - case 1: accepted = bothprop; break; - case 2: accepted = (base_list[3] == list[3]) != same; break; - case 3: accepted = !same; break; - - case 4: /* Left general category, right particular category */ - accepted = risprop && catposstab[base_list[3]][list[3]] == same; - break; - - case 5: /* Right general category, left particular category */ - accepted = lisprop && catposstab[list[3]][base_list[3]] == same; - break; - - /* This code is logically tricky. Think hard before fiddling with it. - The posspropstab table has four entries per row. Each row relates to - one of PCRE's special properties such as ALNUM or SPACE or WORD. - Only WORD actually needs all four entries, but using repeats for the - others means they can all use the same code below. - - The first two entries in each row are Unicode general categories, and - apply always, because all the characters they include are part of the - PCRE character set. The third and fourth entries are a general and a - particular category, respectively, that include one or more relevant - characters. One or the other is used, depending on whether the check - is for a general or a particular category. However, in both cases the - category contains more characters than the specials that are defined - for the property being tested against. Therefore, it cannot be used - in a NOTPROP case. - - Example: the row for WORD contains ucp_L, ucp_N, ucp_P, ucp_Po. - Underscore is covered by ucp_P or ucp_Po. */ - - case 6: /* Left alphanum vs right general category */ - case 7: /* Left space vs right general category */ - case 8: /* Left word vs right general category */ - p = posspropstab[n-6]; - accepted = risprop && lisprop == - (list[3] != p[0] && - list[3] != p[1] && - (list[3] != p[2] || !lisprop)); - break; - - case 9: /* Right alphanum vs left general category */ - case 10: /* Right space vs left general category */ - case 11: /* Right word vs left general category */ - p = posspropstab[n-9]; - accepted = lisprop && risprop == - (base_list[3] != p[0] && - base_list[3] != p[1] && - (base_list[3] != p[2] || !risprop)); - break; - - case 12: /* Left alphanum vs right particular category */ - case 13: /* Left space vs right particular category */ - case 14: /* Left word vs right particular category */ - p = posspropstab[n-12]; - accepted = risprop && lisprop == - (catposstab[p[0]][list[3]] && - catposstab[p[1]][list[3]] && - (list[3] != p[3] || !lisprop)); - break; - - case 15: /* Right alphanum vs left particular category */ - case 16: /* Right space vs left particular category */ - case 17: /* Right word vs left particular category */ - p = posspropstab[n-15]; - accepted = lisprop && risprop == - (catposstab[p[0]][base_list[3]] && - catposstab[p[1]][base_list[3]] && - (base_list[3] != p[3] || !risprop)); - break; - } - } - } - - else -#endif /* SUPPORT_UCP */ - - accepted = leftop >= FIRST_AUTOTAB_OP && leftop <= LAST_AUTOTAB_LEFT_OP && - rightop >= FIRST_AUTOTAB_OP && rightop <= LAST_AUTOTAB_RIGHT_OP && - autoposstab[leftop - FIRST_AUTOTAB_OP][rightop - FIRST_AUTOTAB_OP]; - - if (!accepted) - return FALSE; - - if (list[1] == 0) return TRUE; - /* Might be an empty repeat. */ - continue; - } - - /* Control reaches here only if one of the items is a small character list. - All characters are checked against the other side. */ - - do - { - chr = *chr_ptr; - - switch(list_ptr[0]) - { - case OP_CHAR: - ochr_ptr = list_ptr + 2; - do - { - if (chr == *ochr_ptr) return FALSE; - ochr_ptr++; - } - while(*ochr_ptr != NOTACHAR); - break; - - case OP_NOT: - ochr_ptr = list_ptr + 2; - do - { - if (chr == *ochr_ptr) - break; - ochr_ptr++; - } - while(*ochr_ptr != NOTACHAR); - if (*ochr_ptr == NOTACHAR) return FALSE; /* Not found */ - break; - - /* Note that OP_DIGIT etc. are generated only when PCRE_UCP is *not* - set. When it is set, \d etc. are converted into OP_(NOT_)PROP codes. */ - - case OP_DIGIT: - if (chr < 256 && (cd->ctypes[chr] & ctype_digit) != 0) return FALSE; - break; - - case OP_NOT_DIGIT: - if (chr > 255 || (cd->ctypes[chr] & ctype_digit) == 0) return FALSE; - break; - - case OP_WHITESPACE: - if (chr < 256 && (cd->ctypes[chr] & ctype_space) != 0) return FALSE; - break; - - case OP_NOT_WHITESPACE: - if (chr > 255 || (cd->ctypes[chr] & ctype_space) == 0) return FALSE; - break; - - case OP_WORDCHAR: - if (chr < 255 && (cd->ctypes[chr] & ctype_word) != 0) return FALSE; - break; - - case OP_NOT_WORDCHAR: - if (chr > 255 || (cd->ctypes[chr] & ctype_word) == 0) return FALSE; - break; - - case OP_HSPACE: - switch(chr) - { - HSPACE_CASES: return FALSE; - default: break; - } - break; - - case OP_NOT_HSPACE: - switch(chr) - { - HSPACE_CASES: break; - default: return FALSE; - } - break; - - case OP_ANYNL: - case OP_VSPACE: - switch(chr) - { - VSPACE_CASES: return FALSE; - default: break; - } - break; - - case OP_NOT_VSPACE: - switch(chr) - { - VSPACE_CASES: break; - default: return FALSE; - } - break; - - case OP_DOLL: - case OP_EODN: - switch (chr) - { - case CHAR_CR: - case CHAR_LF: - case CHAR_VT: - case CHAR_FF: - case CHAR_NEL: -#ifndef EBCDIC - case 0x2028: - case 0x2029: -#endif /* Not EBCDIC */ - return FALSE; - } - break; - - case OP_EOD: /* Can always possessify before \z */ - break; - -#ifdef SUPPORT_UCP - case OP_PROP: - case OP_NOTPROP: - if (!check_char_prop(chr, list_ptr[2], list_ptr[3], - list_ptr[0] == OP_NOTPROP)) - return FALSE; - break; -#endif - - case OP_NCLASS: - if (chr > 255) return FALSE; - /* Fall through */ - - case OP_CLASS: - if (chr > 255) break; - class_bitset = (pcre_uint8 *) - ((list_ptr == list ? code : base_end) - list_ptr[2]); - if ((class_bitset[chr >> 3] & (1 << (chr & 7))) != 0) return FALSE; - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - if (PRIV(xclass)(chr, (list_ptr == list ? code : base_end) - - list_ptr[2] + LINK_SIZE, utf)) return FALSE; - break; -#endif - - default: - return FALSE; - } - - chr_ptr++; - } - while(*chr_ptr != NOTACHAR); - - /* At least one character must be matched from this opcode. */ - - if (list[1] == 0) return TRUE; - } - -/* Control never reaches here. There used to be a fail-save return FALSE; here, -but some compilers complain about an unreachable statement. */ - -} - - - -/************************************************* -* Scan compiled regex for auto-possession * -*************************************************/ - -/* Replaces single character iterations with their possessive alternatives -if appropriate. This function modifies the compiled opcode! - -Arguments: - code points to start of the byte code - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd static compile data - -Returns: nothing -*/ - -static void -auto_possessify(pcre_uchar *code, BOOL utf, const compile_data *cd) -{ -register pcre_uchar c; -const pcre_uchar *end; -pcre_uchar *repeat_opcode; -pcre_uint32 list[8]; - -for (;;) - { - c = *code; - - if (c >= OP_STAR && c <= OP_TYPEPOSUPTO) - { - c -= get_repeat_base(c) - OP_STAR; - end = (c <= OP_MINUPTO) ? - get_chr_property_list(code, utf, cd->fcc, list) : NULL; - list[1] = c == OP_STAR || c == OP_PLUS || c == OP_QUERY || c == OP_UPTO; - - if (end != NULL && compare_opcodes(end, utf, cd, list, end)) - { - switch(c) - { - case OP_STAR: - *code += OP_POSSTAR - OP_STAR; - break; - - case OP_MINSTAR: - *code += OP_POSSTAR - OP_MINSTAR; - break; - - case OP_PLUS: - *code += OP_POSPLUS - OP_PLUS; - break; - - case OP_MINPLUS: - *code += OP_POSPLUS - OP_MINPLUS; - break; - - case OP_QUERY: - *code += OP_POSQUERY - OP_QUERY; - break; - - case OP_MINQUERY: - *code += OP_POSQUERY - OP_MINQUERY; - break; - - case OP_UPTO: - *code += OP_POSUPTO - OP_UPTO; - break; - - case OP_MINUPTO: - *code += OP_POSUPTO - OP_MINUPTO; - break; - } - } - c = *code; - } - else if (c == OP_CLASS || c == OP_NCLASS || c == OP_XCLASS) - { -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (c == OP_XCLASS) - repeat_opcode = code + GET(code, 1); - else -#endif - repeat_opcode = code + 1 + (32 / sizeof(pcre_uchar)); - - c = *repeat_opcode; - if (c >= OP_CRSTAR && c <= OP_CRMINRANGE) - { - /* end must not be NULL. */ - end = get_chr_property_list(code, utf, cd->fcc, list); - - list[1] = (c & 1) == 0; - - if (compare_opcodes(end, utf, cd, list, end)) - { - switch (c) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - *repeat_opcode = OP_CRPOSSTAR; - break; - - case OP_CRPLUS: - case OP_CRMINPLUS: - *repeat_opcode = OP_CRPOSPLUS; - break; - - case OP_CRQUERY: - case OP_CRMINQUERY: - *repeat_opcode = OP_CRPOSQUERY; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - *repeat_opcode = OP_CRPOSRANGE; - break; - } - } - } - c = *code; - } - - switch(c) - { - case OP_END: - return; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[1 + IMM2_SIZE] == OP_PROP || code[1 + IMM2_SIZE] == OP_NOTPROP) - code += 2; - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - code += GET(code, 1); - break; -#endif - - case OP_MARK: - case OP_PRUNE_ARG: - case OP_SKIP_ARG: - case OP_THEN_ARG: - code += code[1]; - break; - } - - /* Add in the fixed length from the table */ - - code += PRIV(OP_lengths)[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf) switch(c) - { - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_EXACT: - case OP_POSSTAR: - case OP_POSPLUS: - case OP_POSQUERY: - case OP_POSUPTO: - case OP_STARI: - case OP_MINSTARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_QUERYI: - case OP_MINQUERYI: - case OP_UPTOI: - case OP_MINUPTOI: - case OP_EXACTI: - case OP_POSSTARI: - case OP_POSPLUSI: - case OP_POSQUERYI: - case OP_POSUPTOI: - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTEXACT: - case OP_NOTPOSSTAR: - case OP_NOTPOSPLUS: - case OP_NOTPOSQUERY: - case OP_NOTPOSUPTO: - case OP_NOTSTARI: - case OP_NOTMINSTARI: - case OP_NOTPLUSI: - case OP_NOTMINPLUSI: - case OP_NOTQUERYI: - case OP_NOTMINQUERYI: - case OP_NOTUPTOI: - case OP_NOTMINUPTOI: - case OP_NOTEXACTI: - case OP_NOTPOSSTARI: - case OP_NOTPOSPLUSI: - case OP_NOTPOSQUERYI: - case OP_NOTPOSUPTOI: - if (HAS_EXTRALEN(code[-1])) code += GET_EXTRALEN(code[-1]); - break; - } -#else - (void)(utf); /* Keep compiler happy by referencing function argument */ -#endif - } -} - - - -/************************************************* -* Check for POSIX class syntax * -*************************************************/ - -/* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by a -sequence of characters terminated by a matching ":]" or ".]" or "=]". If we -reach an unescaped ']' without the special preceding character, return FALSE. - -Originally, this function only recognized a sequence of letters between the -terminators, but it seems that Perl recognizes any sequence of characters, -though of course unknown POSIX names are subsequently rejected. Perl gives an -"Unknown POSIX class" error for [:f\oo:] for example, where previously PCRE -didn't consider this to be a POSIX class. Likewise for [:1234:]. - -The problem in trying to be exactly like Perl is in the handling of escapes. We -have to be sure that [abc[:x\]pqr] is *not* treated as containing a POSIX -class, but [abc[:x\]pqr:]] is (so that an error can be generated). The code -below handles the special case of \], but does not try to do any other escape -processing. This makes it different from Perl for cases such as [:l\ower:] -where Perl recognizes it as the POSIX class "lower" but PCRE does not recognize -"l\ower". This is a lesser evil than not diagnosing bad classes when Perl does, -I think. - -A user pointed out that PCRE was rejecting [:a[:digit:]] whereas Perl was not. -It seems that the appearance of a nested POSIX class supersedes an apparent -external class. For example, [:a[:digit:]b:] matches "a", "b", ":", or -a digit. - -In Perl, unescaped square brackets may also appear as part of class names. For -example, [:a[:abc]b:] gives unknown POSIX class "[:abc]b:]". However, for -[:a[:abc]b][b:] it gives unknown POSIX class "[:abc]b][b:]", which does not -seem right at all. PCRE does not allow closing square brackets in POSIX class -names. - -Arguments: - ptr pointer to the initial [ - endptr where to return the end pointer - -Returns: TRUE or FALSE -*/ - -static BOOL -check_posix_syntax(const pcre_uchar *ptr, const pcre_uchar **endptr) -{ -pcre_uchar terminator; /* Don't combine these lines; the Solaris cc */ -terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -for (++ptr; *ptr != CHAR_NULL; ptr++) - { - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - ptr++; - else if (*ptr == CHAR_RIGHT_SQUARE_BRACKET) return FALSE; - else - { - if (*ptr == terminator && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - *endptr = ptr; - return TRUE; - } - if (*ptr == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, endptr)) - return FALSE; - } - } -return FALSE; -} - - - - -/************************************************* -* Check POSIX class name * -*************************************************/ - -/* This function is called to check the name given in a POSIX-style class entry -such as [:alnum:]. - -Arguments: - ptr points to the first letter - len the length of the name - -Returns: a value representing the name, or -1 if unknown -*/ - -static int -check_posix_name(const pcre_uchar *ptr, int len) -{ -const char *pn = posix_names; -register int yield = 0; -while (posix_name_lengths[yield] != 0) - { - if (len == posix_name_lengths[yield] && - STRNCMP_UC_C8(ptr, pn, (unsigned int)len) == 0) return yield; - pn += posix_name_lengths[yield] + 1; - yield++; - } -return -1; -} - - -/************************************************* -* Adjust OP_RECURSE items in repeated group * -*************************************************/ - -/* OP_RECURSE items contain an offset from the start of the regex to the group -that is referenced. This means that groups can be replicated for fixed -repetition simply by copying (because the recursion is allowed to refer to -earlier groups that are outside the current group). However, when a group is -optional (i.e. the minimum quantifier is zero), OP_BRAZERO or OP_SKIPZERO is -inserted before it, after it has been compiled. This means that any OP_RECURSE -items within it that refer to the group itself or any contained groups have to -have their offsets adjusted. That one of the jobs of this function. Before it -is called, the partially compiled regex must be temporarily terminated with -OP_END. - -This function has been extended with the possibility of forward references for -recursions and subroutine calls. It must also check the list of such references -for the group we are dealing with. If it finds that one of the recursions in -the current group is on this list, it adjusts the offset in the list, not the -value in the reference (which is a group number). - -Arguments: - group points to the start of the group - adjust the amount by which the group is to be moved - utf TRUE in UTF-8 / UTF-16 / UTF-32 mode - cd contains pointers to tables etc. - save_hwm the hwm forward reference pointer at the start of the group - -Returns: nothing -*/ - -static void -adjust_recurse(pcre_uchar *group, int adjust, BOOL utf, compile_data *cd, - pcre_uchar *save_hwm) -{ -pcre_uchar *ptr = group; - -while ((ptr = (pcre_uchar *)find_recurse(ptr, utf)) != NULL) - { - int offset; - pcre_uchar *hc; - - /* See if this recursion is on the forward reference list. If so, adjust the - reference. */ - - for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) - { - offset = (int)GET(hc, 0); - if (cd->start_code + offset == ptr + 1) - { - PUT(hc, 0, offset + adjust); - break; - } - } - - /* Otherwise, adjust the recursion offset if it's after the start of this - group. */ - - if (hc >= cd->hwm) - { - offset = (int)GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); - } - - ptr += 1 + LINK_SIZE; - } -} - - - -/************************************************* -* Insert an automatic callout point * -*************************************************/ - -/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert -callout points before each pattern item. - -Arguments: - code current code pointer - ptr current pattern pointer - cd pointers to tables etc - -Returns: new code pointer -*/ - -static pcre_uchar * -auto_callout(pcre_uchar *code, const pcre_uchar *ptr, compile_data *cd) -{ -*code++ = OP_CALLOUT; -*code++ = 255; -PUT(code, 0, (int)(ptr - cd->start_pattern)); /* Pattern offset */ -PUT(code, LINK_SIZE, 0); /* Default length */ -return code + 2 * LINK_SIZE; -} - - - -/************************************************* -* Complete a callout item * -*************************************************/ - -/* A callout item contains the length of the next item in the pattern, which -we can't fill in till after we have reached the relevant point. This is used -for both automatic and manual callouts. - -Arguments: - previous_callout points to previous callout item - ptr current pattern pointer - cd pointers to tables etc - -Returns: nothing -*/ - -static void -complete_callout(pcre_uchar *previous_callout, const pcre_uchar *ptr, compile_data *cd) -{ -int length = (int)(ptr - cd->start_pattern - GET(previous_callout, 2)); -PUT(previous_callout, 2 + LINK_SIZE, length); -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Get othercase range * -*************************************************/ - -/* This function is passed the start and end of a class range, in UTF-8 mode -with UCP support. It searches up the characters, looking for ranges of -characters in the "other" case. Each call returns the next one, updating the -start address. A character with multiple other cases is returned on its own -with a special return value. - -Arguments: - cptr points to starting character value; updated - d end value - ocptr where to put start of othercase range - odptr where to put end of othercase range - -Yield: -1 when no more - 0 when a range is returned - >0 the CASESET offset for char with multiple other cases - in this case, ocptr contains the original -*/ - -static int -get_othercase_range(pcre_uint32 *cptr, pcre_uint32 d, pcre_uint32 *ocptr, - pcre_uint32 *odptr) -{ -pcre_uint32 c, othercase, next; -unsigned int co; - -/* Find the first character that has an other case. If it has multiple other -cases, return its case offset value. */ - -for (c = *cptr; c <= d; c++) - { - if ((co = UCD_CASESET(c)) != 0) - { - *ocptr = c++; /* Character that has the set */ - *cptr = c; /* Rest of input range */ - return (int)co; - } - if ((othercase = UCD_OTHERCASE(c)) != c) break; - } - -if (c > d) return -1; /* Reached end of range */ - -/* Found a character that has a single other case. Search for the end of the -range, which is either the end of the input range, or a character that has zero -or more than one other cases. */ - -*ocptr = othercase; -next = othercase + 1; - -for (++c; c <= d; c++) - { - if ((co = UCD_CASESET(c)) != 0 || UCD_OTHERCASE(c) != next) break; - next++; - } - -*odptr = next - 1; /* End of othercase range */ -*cptr = c; /* Rest of input range */ -return 0; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Add a character or range to a class * -*************************************************/ - -/* This function packages up the logic of adding a character or range of -characters to a class. The character values in the arguments will be within the -valid values for the current mode (8-bit, 16-bit, UTF, etc). This function is -mutually recursive with the function immediately below. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - start start of range character - end end of range character - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, - compile_data *cd, pcre_uint32 start, pcre_uint32 end) -{ -pcre_uint32 c; -pcre_uint32 classbits_end = (end <= 0xff ? end : 0xff); -int n8 = 0; - -/* If caseless matching is required, scan the range and process alternate -cases. In Unicode, there are 8-bit characters that have alternate cases that -are greater than 255 and vice-versa. Sometimes we can just extend the original -range. */ - -if ((options & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UCP - if ((options & PCRE_UTF8) != 0) - { - int rc; - pcre_uint32 oc, od; - - options &= ~PCRE_CASELESS; /* Remove for recursive calls */ - c = start; - - while ((rc = get_othercase_range(&c, end, &oc, &od)) >= 0) - { - /* Handle a single character that has more than one other case. */ - - if (rc > 0) n8 += add_list_to_class(classbits, uchardptr, options, cd, - PRIV(ucd_caseless_sets) + rc, oc); - - /* Do nothing if the other case range is within the original range. */ - - else if (oc >= start && od <= end) continue; - - /* Extend the original range if there is overlap, noting that if oc < c, we - can't have od > end because a subrange is always shorter than the basic - range. Otherwise, use a recursive call to add the additional range. */ - - else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */ - else if (od > end && oc <= end + 1) end = od; /* Extend upwards */ - else n8 += add_to_class(classbits, uchardptr, options, cd, oc, od); - } - } - else -#endif /* SUPPORT_UCP */ - - /* Not UTF-mode, or no UCP */ - - for (c = start; c <= classbits_end; c++) - { - SETBIT(classbits, cd->fcc[c]); - n8++; - } - } - -/* Now handle the original range. Adjust the final value according to the bit -length - this means that the same lists of (e.g.) horizontal spaces can be used -in all cases. */ - -#if defined COMPILE_PCRE8 -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF8) == 0) -#endif - if (end > 0xff) end = 0xff; - -#elif defined COMPILE_PCRE16 -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF16) == 0) -#endif - if (end > 0xffff) end = 0xffff; - -#endif /* COMPILE_PCRE[8|16] */ - -/* Use the bitmap for characters < 256. Otherwise use extra data.*/ - -for (c = start; c <= classbits_end; c++) - { - /* Regardless of start, c will always be <= 255. */ - SETBIT(classbits, c); - n8++; - } - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -if (start <= 0xff) start = 0xff + 1; - -if (end >= start) - { - pcre_uchar *uchardata = *uchardptr; -#ifdef SUPPORT_UTF - if ((options & PCRE_UTF8) != 0) /* All UTFs use the same flag bit */ - { - if (start < end) - { - *uchardata++ = XCL_RANGE; - uchardata += PRIV(ord2utf)(start, uchardata); - uchardata += PRIV(ord2utf)(end, uchardata); - } - else if (start == end) - { - *uchardata++ = XCL_SINGLE; - uchardata += PRIV(ord2utf)(start, uchardata); - } - } - else -#endif /* SUPPORT_UTF */ - - /* Without UTF support, character values are constrained by the bit length, - and can only be > 256 for 16-bit and 32-bit libraries. */ - -#ifdef COMPILE_PCRE8 - {} -#else - if (start < end) - { - *uchardata++ = XCL_RANGE; - *uchardata++ = start; - *uchardata++ = end; - } - else if (start == end) - { - *uchardata++ = XCL_SINGLE; - *uchardata++ = start; - } -#endif - - *uchardptr = uchardata; /* Updata extra data pointer */ - } -#endif /* SUPPORT_UTF || !COMPILE_PCRE8 */ - -return n8; /* Number of 8-bit characters */ -} - - - - -/************************************************* -* Add a list of characters to a class * -*************************************************/ - -/* This function is used for adding a list of case-equivalent characters to a -class, and also for adding a list of horizontal or vertical whitespace. If the -list is in order (which it should be), ranges of characters are detected and -handled appropriately. This function is mutually recursive with the function -above. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR - except character to omit; this is used when adding lists of - case-equivalent characters to avoid including the one we - already know about - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, int options, - compile_data *cd, const pcre_uint32 *p, unsigned int except) -{ -int n8 = 0; -while (p[0] < NOTACHAR) - { - int n = 0; - if (p[0] != except) - { - while(p[n+1] == p[0] + n + 1) n++; - n8 += add_to_class(classbits, uchardptr, options, cd, p[0], p[n]); - } - p += n + 1; - } -return n8; -} - - - -/************************************************* -* Add characters not in a list to a class * -*************************************************/ - -/* This function is used for adding the complement of a list of horizontal or -vertical whitespace to a class. The list must be in order. - -Arguments: - classbits the bit map for characters < 256 - uchardptr points to the pointer for extra data - options the options word - cd contains pointers to tables etc. - p points to row of 32-bit values, terminated by NOTACHAR - -Returns: the number of < 256 characters added - the pointer to extra data is updated -*/ - -static int -add_not_list_to_class(pcre_uint8 *classbits, pcre_uchar **uchardptr, - int options, compile_data *cd, const pcre_uint32 *p) -{ -BOOL utf = (options & PCRE_UTF8) != 0; -int n8 = 0; -if (p[0] > 0) - n8 += add_to_class(classbits, uchardptr, options, cd, 0, p[0] - 1); -while (p[0] < NOTACHAR) - { - while (p[1] == p[0] + 1) p++; - n8 += add_to_class(classbits, uchardptr, options, cd, p[0] + 1, - (p[1] == NOTACHAR) ? (utf ? 0x10ffffu : 0xffffffffu) : p[1] - 1); - p++; - } -return n8; -} - - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the a vector. If the options are -changed during the branch, the pointer is used to change the external options -bits. This function is used during the pre-compile phase when we are trying -to find out the amount of memory needed, as well as during the real compile -phase. The value of lengthptr distinguishes the two phases. - -Arguments: - optionsptr pointer to the option bits - codeptr points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorcodeptr points to error code variable - firstcharptr place to put the first required character - firstcharflagsptr place to put the first character flags, or a negative number - reqcharptr place to put the last required character - reqcharflagsptr place to put the last required character flags, or a negative number - bcptr points to current branch chain - cond_depth conditional nesting depth - cd contains pointers to tables etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success - FALSE, with *errorcodeptr set non-zero on error -*/ - -static BOOL -compile_branch(int *optionsptr, pcre_uchar **codeptr, - const pcre_uchar **ptrptr, int *errorcodeptr, - pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, - pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, - branch_chain *bcptr, int cond_depth, - compile_data *cd, int *lengthptr) -{ -int repeat_type, op_type; -int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ -int bravalue = 0; -int greedy_default, greedy_non_default; -pcre_uint32 firstchar, reqchar; -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 zeroreqchar, zerofirstchar; -pcre_int32 zeroreqcharflags, zerofirstcharflags; -pcre_int32 req_caseopt, reqvary, tempreqvary; -int options = *optionsptr; /* May change dynamically */ -int after_manual_callout = 0; -int length_prevgroup = 0; -register pcre_uint32 c; -int escape; -register pcre_uchar *code = *codeptr; -pcre_uchar *last_code = code; -pcre_uchar *orig_code = code; -pcre_uchar *tempcode; -BOOL inescq = FALSE; -BOOL groupsetfirstchar = FALSE; -const pcre_uchar *ptr = *ptrptr; -const pcre_uchar *tempptr; -const pcre_uchar *nestptr = NULL; -pcre_uchar *previous = NULL; -pcre_uchar *previous_callout = NULL; -pcre_uchar *save_hwm = NULL; -pcre_uint8 classbits[32]; - -/* We can fish out the UTF-8 setting once and for all into a BOOL, but we -must not do this for other options (e.g. PCRE_EXTENDED) because they may change -dynamically as we process the pattern. */ - -#ifdef SUPPORT_UTF -/* PCRE_UTF[16|32] have the same value as PCRE_UTF8. */ -BOOL utf = (options & PCRE_UTF8) != 0; -#ifndef COMPILE_PCRE32 -pcre_uchar utf_chars[6]; -#endif -#else -BOOL utf = FALSE; -#endif - -/* Helper variables for OP_XCLASS opcode (for characters > 255). We define -class_uchardata always so that it can be passed to add_to_class() always, -though it will not be used in non-UTF 8-bit cases. This avoids having to supply -alternative calls for the different cases. */ - -pcre_uchar *class_uchardata; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 -BOOL xclass; -pcre_uchar *class_uchardata_base; -#endif - -#ifdef PCRE_DEBUG -if (lengthptr != NULL) DPRINTF((">> start branch\n")); -#endif - -/* Set up the default and non-default settings for greediness */ - -greedy_default = ((options & PCRE_UNGREEDY) != 0); -greedy_non_default = greedy_default ^ 1; - -/* Initialize no first byte, no required byte. REQ_UNSET means "no char -matching encountered yet". It gets changed to REQ_NONE if we hit something that -matches a non-fixed char first char; reqchar just remains unset if we never -find one. - -When we hit a repeat whose minimum is zero, we may have to adjust these values -to take the zero repeat into account. This is implemented by setting them to -zerofirstbyte and zeroreqchar when such a repeat is encountered. The individual -item types that can be repeated set these backoff variables appropriately. */ - -firstchar = reqchar = zerofirstchar = zeroreqchar = 0; -firstcharflags = reqcharflags = zerofirstcharflags = zeroreqcharflags = REQ_UNSET; - -/* The variable req_caseopt contains either the REQ_CASELESS value -or zero, according to the current setting of the caseless flag. The -REQ_CASELESS leaves the lower 28 bit empty. It is added into the -firstchar or reqchar variables to record the case status of the -value. This is used only for ASCII characters. */ - -req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS:0; - -/* Switch on next character until the end of the branch */ - -for (;; ptr++) - { - BOOL negate_class; - BOOL should_flip_negation; - BOOL possessive_quantifier; - BOOL is_quantifier; - BOOL is_recurse; - BOOL reset_bracount; - int class_has_8bitchar; - int class_one_char; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - BOOL xclass_has_prop; -#endif - int newoptions; - int recno; - int refsign; - int skipbytes; - pcre_uint32 subreqchar, subfirstchar; - pcre_int32 subreqcharflags, subfirstcharflags; - int terminator; - unsigned int mclength; - unsigned int tempbracount; - pcre_uint32 ec; - pcre_uchar mcbuffer[8]; - - /* Get next character in the pattern */ - - c = *ptr; - - /* If we are at the end of a nested substitution, revert to the outer level - string. Nesting only happens one level deep. */ - - if (c == CHAR_NULL && nestptr != NULL) - { - ptr = nestptr; - nestptr = NULL; - c = *ptr; - } - - /* If we are in the pre-compile phase, accumulate the length used for the - previous cycle of this loop. */ - - if (lengthptr != NULL) - { -#ifdef PCRE_DEBUG - if (code > cd->hwm) cd->hwm = code; /* High water info */ -#endif - if (code > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) /* Check for overrun */ - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* There is at least one situation where code goes backwards: this is the - case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, - the class is simply eliminated. However, it is created first, so we have to - allow memory for it. Therefore, don't ever reduce the length at this point. - */ - - if (code < last_code) code = last_code; - - /* Paranoid check for integer overflow */ - - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - - *lengthptr += (int)(code - last_code); - DPRINTF(("length=%d added %d c=%c (0x%x)\n", *lengthptr, - (int)(code - last_code), c, c)); - - /* If "previous" is set and it is not at the start of the work space, move - it back to there, in order to avoid filling up the work space. Otherwise, - if "previous" is NULL, reset the current code pointer to the start. */ - - if (previous != NULL) - { - if (previous > orig_code) - { - memmove(orig_code, previous, IN_UCHARS(code - previous)); - code -= previous - orig_code; - previous = orig_code; - } - } - else code = orig_code; - - /* Remember where this code item starts so we can pick up the length - next time round. */ - - last_code = code; - } - - /* In the real compile phase, just check the workspace used by the forward - reference list. */ - - else if (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* If in \Q...\E, check for the end; if not, we have a literal */ - - if (inescq && c != CHAR_NULL) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { - inescq = FALSE; - ptr++; - continue; - } - else - { - if (previous_callout != NULL) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - if ((options & PCRE_AUTO_CALLOUT) != 0) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - goto NORMAL_CHAR; - } - /* Control does not reach here. */ - } - - /* In extended mode, skip white space and comments. We need a loop in order - to check for more white space and more comments after a comment. */ - - if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while (MAX_255(c) && (cd->ctypes[c] & ctype_space) != 0) c = *(++ptr); - if (c != CHAR_NUMBER_SIGN) break; - ptr++; - while (*ptr != CHAR_NULL) - { - if (IS_NEWLINE(ptr)) /* For non-fixed-length newline cases, */ - { /* IS_NEWLINE sets cd->nllen. */ - ptr += cd->nllen; - break; - } - ptr++; -#ifdef SUPPORT_UTF - if (utf) FORWARDCHAR(ptr); -#endif - } - c = *ptr; /* Either NULL or the char after a newline */ - } - } - - /* See if the next thing is a quantifier. */ - - is_quantifier = - c == CHAR_ASTERISK || c == CHAR_PLUS || c == CHAR_QUESTION_MARK || - (c == CHAR_LEFT_CURLY_BRACKET && is_counted_repeat(ptr+1)); - - /* Fill in length of a previous callout, except when the next thing is a - quantifier or when processing a property substitution string in UCP mode. */ - - if (!is_quantifier && previous_callout != NULL && nestptr == NULL && - after_manual_callout-- <= 0) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - - /* Create auto callout, except for quantifiers, or while processing property - strings that are substituted for \w etc in UCP mode. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier && nestptr == NULL) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - - /* Process the next pattern item. */ - - switch(c) - { - /* ===================================================================*/ - case CHAR_NULL: /* The branch terminates at string end */ - case CHAR_VERTICAL_LINE: /* or | or ) */ - case CHAR_RIGHT_PARENTHESIS: - *firstcharptr = firstchar; - *firstcharflagsptr = firstcharflags; - *reqcharptr = reqchar; - *reqcharflagsptr = reqcharflags; - *codeptr = code; - *ptrptr = ptr; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += (int)(code - last_code); /* To include callout length */ - DPRINTF((">> end branch\n")); - } - return TRUE; - - - /* ===================================================================*/ - /* Handle single-character metacharacters. In multiline mode, ^ disables - the setting of any following char as a first character. */ - - case CHAR_CIRCUMFLEX_ACCENT: - previous = NULL; - if ((options & PCRE_MULTILINE) != 0) - { - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - *code++ = OP_CIRCM; - } - else *code++ = OP_CIRC; - break; - - case CHAR_DOLLAR_SIGN: - previous = NULL; - *code++ = ((options & PCRE_MULTILINE) != 0)? OP_DOLLM : OP_DOLL; - break; - - /* There can never be a first char if '.' is first, whatever happens about - repeats. The value of reqchar doesn't change either. */ - - case CHAR_DOT: - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - previous = code; - *code++ = ((options & PCRE_DOTALL) != 0)? OP_ALLANY: OP_ANY; - break; - - - /* ===================================================================*/ - /* Character classes. If the included characters are all < 256, we build a - 32-byte bitmap of the permitted characters, except in the special case - where there is only one such character. For negated classes, we build the - map as usual, then invert it at the end. However, we use a different opcode - so that data characters > 255 can be handled correctly. - - If the class contains characters outside the 0-255 range, a different - opcode is compiled. It may optionally have a bit map for characters < 256, - but those above are are explicitly listed afterwards. A flag byte tells - whether the bitmap is present, and whether this is a negated class or not. - - In JavaScript compatibility mode, an isolated ']' causes an error. In - default (Perl) mode, it is treated as a data character. */ - - case CHAR_RIGHT_SQUARE_BRACKET: - if ((cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *errorcodeptr = ERR64; - goto FAILED; - } - goto NORMAL_CHAR; - - /* In another (POSIX) regex library, the ugly syntax [[:<:]] and [[:>:]] is - used for "start of word" and "end of word". As these are otherwise illegal - sequences, we don't break anything by recognizing them. They are replaced - by \b(?=\w) and \b(?<=\w) respectively. Sequences like [a[:<:]] are - erroneous and are handled by the normal code below. */ - - case CHAR_LEFT_SQUARE_BRACKET: - if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_STARTWORD, 6) == 0) - { - nestptr = ptr + 7; - ptr = sub_start_of_word - 1; - continue; - } - - if (STRNCMP_UC_C8(ptr+1, STRING_WEIRD_ENDWORD, 6) == 0) - { - nestptr = ptr + 7; - ptr = sub_end_of_word - 1; - continue; - } - - /* Handle a real character class. */ - - previous = code; - - /* PCRE supports POSIX class stuff inside a class. Perl gives an error if - they are encountered at the top level, so we'll do that too. */ - - if ((ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, &tempptr)) - { - *errorcodeptr = (ptr[1] == CHAR_COLON)? ERR13 : ERR31; - goto FAILED; - } - - /* If the first character is '^', set the negation flag and skip it. Also, - if the first few characters (either before or after ^) are \Q\E or \E we - skip them too. This makes for compatibility with Perl. */ - - negate_class = FALSE; - for (;;) - { - c = *(++ptr); - if (c == CHAR_BACKSLASH) - { - if (ptr[1] == CHAR_E) - ptr++; - else if (STRNCMP_UC_C8(ptr + 1, STR_Q STR_BACKSLASH STR_E, 3) == 0) - ptr += 3; - else - break; - } - else if (!negate_class && c == CHAR_CIRCUMFLEX_ACCENT) - negate_class = TRUE; - else break; - } - - /* Empty classes are allowed in JavaScript compatibility mode. Otherwise, - an initial ']' is taken as a data character -- the code below handles - that. In JS mode, [] must always fail, so generate OP_FAIL, whereas - [^] must match any character, so generate OP_ALLANY. */ - - if (c == CHAR_RIGHT_SQUARE_BRACKET && - (cd->external_options & PCRE_JAVASCRIPT_COMPAT) != 0) - { - *code++ = negate_class? OP_ALLANY : OP_FAIL; - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - break; - } - - /* If a class contains a negative special such as \S, we need to flip the - negation flag at the end, so that support for characters > 255 works - correctly (they are all included in the class). */ - - should_flip_negation = FALSE; - - /* Extended class (xclass) will be used when characters > 255 - might match. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - xclass = FALSE; - class_uchardata = code + LINK_SIZE + 2; /* For XCLASS items */ - class_uchardata_base = class_uchardata; /* Save the start */ -#endif - - /* For optimization purposes, we track some properties of the class: - class_has_8bitchar will be non-zero if the class contains at least one < - 256 character; class_one_char will be 1 if the class contains just one - character; xclass_has_prop will be TRUE if unicode property checks - are present in the class. */ - - class_has_8bitchar = 0; - class_one_char = 0; -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - xclass_has_prop = FALSE; -#endif - - /* Initialize the 32-char bit map to all zeros. We build the map in a - temporary bit of memory, in case the class contains fewer than two - 8-bit characters because in that case the compiled code doesn't use the bit - map. */ - - memset(classbits, 0, 32 * sizeof(pcre_uint8)); - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. At the start of the - loop, c contains the first byte of the character. */ - - if (c != CHAR_NULL) do - { - const pcre_uchar *oldptr; - -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(c)) - { /* Braces are required because the */ - GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ - } -#endif - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - /* In the pre-compile phase, accumulate the length of any extra - data and reset the pointer. This is so that very large classes that - contain a zillion > 255 characters no longer overwrite the work space - (which is on the stack). We have to remember that there was XCLASS data, - however. */ - - if (lengthptr != NULL && class_uchardata > class_uchardata_base) - { - xclass = TRUE; - *lengthptr += class_uchardata - class_uchardata_base; - class_uchardata = class_uchardata_base; - } -#endif - - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (c == CHAR_BACKSLASH && ptr[1] == CHAR_E) /* If we are at \E */ - { - inescq = FALSE; /* Reset literal state */ - ptr++; /* Skip the 'E' */ - continue; /* Carry on with next */ - } - goto CHECK_RANGE; /* Could be range if \E follows */ - } - - /* Handle POSIX class names. Perl allows a negation extension of the - form [:^name:]. A square bracket that doesn't match the syntax is - treated as a literal. We also recognize the POSIX constructions - [.ch.] and [=ch=] ("collating elements") and fault them, as Perl - 5.6 and 5.8 do. */ - - if (c == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && check_posix_syntax(ptr, &tempptr)) - { - BOOL local_negate = FALSE; - int posix_class, taboffset, tabopt; - register const pcre_uint8 *cbits = cd->cbits; - pcre_uint8 pbits[32]; - - if (ptr[1] != CHAR_COLON) - { - *errorcodeptr = ERR31; - goto FAILED; - } - - ptr += 2; - if (*ptr == CHAR_CIRCUMFLEX_ACCENT) - { - local_negate = TRUE; - should_flip_negation = TRUE; /* Note negative special */ - ptr++; - } - - posix_class = check_posix_name(ptr, (int)(tempptr - ptr)); - if (posix_class < 0) - { - *errorcodeptr = ERR30; - goto FAILED; - } - - /* If matching is caseless, upper and lower are converted to - alpha. This relies on the fact that the class table starts with - alpha, lower, upper as the first 3 entries. */ - - if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) - posix_class = 0; - - /* When PCRE_UCP is set, some of the POSIX classes are converted to - different escape sequences that use Unicode properties \p or \P. Others - that are not available via \p or \P generate XCL_PROP/XCL_NOTPROP - directly. */ - -#ifdef SUPPORT_UCP - if ((options & PCRE_UCP) != 0) - { - unsigned int ptype = 0; - int pc = posix_class + ((local_negate)? POSIX_SUBSIZE/2 : 0); - - /* The posix_substitutes table specifies which POSIX classes can be - converted to \p or \P items. */ - - if (posix_substitutes[pc] != NULL) - { - nestptr = tempptr + 1; - ptr = posix_substitutes[pc] - 1; - continue; - } - - /* There are three other classes that generate special property calls - that are recognized only in an XCLASS. */ - - else switch(posix_class) - { - case PC_GRAPH: - ptype = PT_PXGRAPH; - /* Fall through */ - case PC_PRINT: - if (ptype == 0) ptype = PT_PXPRINT; - /* Fall through */ - case PC_PUNCT: - if (ptype == 0) ptype = PT_PXPUNCT; - *class_uchardata++ = local_negate? XCL_NOTPROP : XCL_PROP; - *class_uchardata++ = ptype; - *class_uchardata++ = 0; - xclass_has_prop = TRUE; - ptr = tempptr + 1; - continue; - - /* For all other POSIX classes, no special action is taken in UCP - mode. Fall through to the non_UCP case. */ - - default: - break; - } - } -#endif - /* In the non-UCP case, or when UCP makes no difference, we build the - bit map for the POSIX class in a chunk of local store because we may be - adding and subtracting from it, and we don't want to subtract bits that - may be in the main map already. At the end we or the result into the - bit map that is being built. */ - - posix_class *= 3; - - /* Copy in the first table (always present) */ - - memcpy(pbits, cbits + posix_class_maps[posix_class], - 32 * sizeof(pcre_uint8)); - - /* If there is a second table, add or remove it as required. */ - - taboffset = posix_class_maps[posix_class + 1]; - tabopt = posix_class_maps[posix_class + 2]; - - if (taboffset >= 0) - { - if (tabopt >= 0) - for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; - else - for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; - } - - /* Now see if we need to remove any special characters. An option - value of 1 removes vertical space and 2 removes underscore. */ - - if (tabopt < 0) tabopt = -tabopt; - if (tabopt == 1) pbits[1] &= ~0x3c; - else if (tabopt == 2) pbits[11] &= 0x7f; - - /* Add the POSIX table or its complement into the main table that is - being built and we are done. */ - - if (local_negate) - for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; - else - for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; - - ptr = tempptr + 1; - /* Every class contains at least one < 256 character. */ - class_has_8bitchar = 1; - /* Every class contains at least two characters. */ - class_one_char = 2; - continue; /* End of POSIX syntax handling */ - } - - /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. The sequence \b is a special - case. Inside a class (and only there) it is treated as backspace. We - assume that other escapes have more than one character in them, so - speculatively set both class_has_8bitchar and class_one_char bigger - than one. Unrecognized escapes fall through and are either treated - as literal characters (by default), or are faulted if - PCRE_EXTRA is set. */ - - if (c == CHAR_BACKSLASH) - { - escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, - TRUE); - if (*errorcodeptr != 0) goto FAILED; - if (escape == 0) c = ec; - else if (escape == ESC_b) c = CHAR_BS; /* \b is backspace in a class */ - else if (escape == ESC_N) /* \N is not supported in a class */ - { - *errorcodeptr = ERR71; - goto FAILED; - } - else if (escape == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - ptr += 2; /* avoid empty string */ - } - else inescq = TRUE; - continue; - } - else if (escape == ESC_E) continue; /* Ignore orphan \E */ - - else - { - register const pcre_uint8 *cbits = cd->cbits; - /* Every class contains at least two < 256 characters. */ - class_has_8bitchar++; - /* Every class contains at least two characters. */ - class_one_char += 2; - - switch (escape) - { -#ifdef SUPPORT_UCP - case ESC_du: /* These are the values given for \d etc */ - case ESC_DU: /* when PCRE_UCP is set. We replace the */ - case ESC_wu: /* escape sequence with an appropriate \p */ - case ESC_WU: /* or \P to test Unicode properties instead */ - case ESC_su: /* of the default ASCII testing. */ - case ESC_SU: - nestptr = ptr; - ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ - class_has_8bitchar--; /* Undo! */ - continue; -#endif - case ESC_d: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; - continue; - - case ESC_w: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; - continue; - - case ESC_W: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; - continue; - - /* Perl 5.004 onwards omitted VT from \s, but restored it at Perl - 5.18. Before PCRE 8.34, we had to preserve the VT bit if it was - previously set by something earlier in the character class. - Luckily, the value of CHAR_VT is 0x0b in both ASCII and EBCDIC, so - we could just adjust the appropriate bit. From PCRE 8.34 we no - longer treat \s and \S specially. */ - - case ESC_s: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; - continue; - - case ESC_S: - should_flip_negation = TRUE; - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; - continue; - - /* The rest apply in both UCP and non-UCP cases. */ - - case ESC_h: - (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(hspace_list), NOTACHAR); - continue; - - case ESC_H: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(hspace_list)); - continue; - - case ESC_v: - (void)add_list_to_class(classbits, &class_uchardata, options, cd, - PRIV(vspace_list), NOTACHAR); - continue; - - case ESC_V: - (void)add_not_list_to_class(classbits, &class_uchardata, options, - cd, PRIV(vspace_list)); - continue; - -#ifdef SUPPORT_UCP - case ESC_p: - case ESC_P: - { - BOOL negated; - unsigned int ptype = 0, pdata = 0; - if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) - goto FAILED; - *class_uchardata++ = ((escape == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_uchardata++ = ptype; - *class_uchardata++ = pdata; - xclass_has_prop = TRUE; - class_has_8bitchar--; /* Undo! */ - continue; - } -#endif - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ - - default: - if ((options & PCRE_EXTRA) != 0) - { - *errorcodeptr = ERR7; - goto FAILED; - } - class_has_8bitchar--; /* Undo the speculative increase. */ - class_one_char -= 2; /* Undo the speculative increase. */ - c = *ptr; /* Get the final character and fall through */ - break; - } - } - - /* Fall through if the escape just defined a single character (c >= 0). - This may be greater than 256. */ - - escape = 0; - - } /* End of backslash handling */ - - /* A character may be followed by '-' to form a range. However, Perl does - not permit ']' to be the end of the range. A '-' character at the end is - treated as a literal. Perl ignores orphaned \E sequences entirely. The - code for handling \Q and \E is messy. */ - - CHECK_RANGE: - while (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - { - inescq = FALSE; - ptr += 2; - } - oldptr = ptr; - - /* Remember if \r or \n were explicitly used */ - - if (c == CHAR_CR || c == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - /* Check for range */ - - if (!inescq && ptr[1] == CHAR_MINUS) - { - pcre_uint32 d; - ptr += 2; - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) ptr += 2; - - /* If we hit \Q (not followed by \E) at this point, go into escaped - mode. */ - - while (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_Q) - { - ptr += 2; - if (*ptr == CHAR_BACKSLASH && ptr[1] == CHAR_E) - { ptr += 2; continue; } - inescq = TRUE; - break; - } - - /* Minus (hyphen) at the end of a class is treated as a literal, so put - back the pointer and jump to handle the character that preceded it. */ - - if (*ptr == CHAR_NULL || (!inescq && *ptr == CHAR_RIGHT_SQUARE_BRACKET)) - { - ptr = oldptr; - goto CLASS_SINGLE_CHARACTER; - } - - /* Otherwise, we have a potential range; pick up the next character */ - -#ifdef SUPPORT_UTF - if (utf) - { /* Braces are required because the */ - GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ - } - else -#endif - d = *ptr; /* Not UTF-8 mode */ - - /* The second part of a range can be a single-character escape - sequence, but not any of the other escapes. Perl treats a hyphen as a - literal in such circumstances. However, in Perl's warning mode, a - warning is given, so PCRE now faults it as it is almost certainly a - mistake on the user's part. */ - - if (!inescq) - { - if (d == CHAR_BACKSLASH) - { - int descape; - descape = check_escape(&ptr, &d, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - /* 0 means a character was put into d; \b is backspace; any other - special causes an error. */ - - if (descape != 0) - { - if (descape == ESC_b) d = CHAR_BS; else - { - *errorcodeptr = ERR83; - goto FAILED; - } - } - } - - /* A hyphen followed by a POSIX class is treated in the same way. */ - - else if (d == CHAR_LEFT_SQUARE_BRACKET && - (ptr[1] == CHAR_COLON || ptr[1] == CHAR_DOT || - ptr[1] == CHAR_EQUALS_SIGN) && - check_posix_syntax(ptr, &tempptr)) - { - *errorcodeptr = ERR83; - goto FAILED; - } - } - - /* Check that the two values are in the correct order. Optimize - one-character ranges. */ - - if (d < c) - { - *errorcodeptr = ERR8; - goto FAILED; - } - if (d == c) goto CLASS_SINGLE_CHARACTER; /* A few lines below */ - - /* We have found a character range, so single character optimizations - cannot be done anymore. Any value greater than 1 indicates that there - is more than one character. */ - - class_one_char = 2; - - /* Remember an explicit \r or \n, and add the range to the class. */ - - if (d == CHAR_CR || d == CHAR_NL) cd->external_flags |= PCRE_HASCRORLF; - - class_has_8bitchar += - add_to_class(classbits, &class_uchardata, options, cd, c, d); - - continue; /* Go get the next char in the class */ - } - - /* Handle a single character - we can get here for a normal non-escape - char, or after \ that introduces a single character or for an apparent - range that isn't. Only the value 1 matters for class_one_char, so don't - increase it if it is already 2 or more ... just in case there's a class - with a zillion characters in it. */ - - CLASS_SINGLE_CHARACTER: - if (class_one_char < 2) class_one_char++; - - /* If class_one_char is 1, we have the first single character in the - class, and there have been no prior ranges, or XCLASS items generated by - escapes. If this is the final character in the class, we can optimize by - turning the item into a 1-character OP_CHAR[I] if it's positive, or - OP_NOT[I] if it's negative. In the positive case, it can cause firstchar - to be set. Otherwise, there can be no first char if this item is first, - whatever repeat count may follow. In the case of reqchar, save the - previous value for reinstating. */ - - if (class_one_char == 1 && ptr[1] == CHAR_RIGHT_SQUARE_BRACKET) - { - ptr++; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - if (negate_class) - { -#ifdef SUPPORT_UCP - int d; -#endif - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - - /* For caseless UTF-8 mode when UCP support is available, check - whether this character has more than one other case. If so, generate - a special OP_NOTPROP item instead of OP_NOTI. */ - -#ifdef SUPPORT_UCP - if (utf && (options & PCRE_CASELESS) != 0 && - (d = UCD_CASESET(c)) != 0) - { - *code++ = OP_NOTPROP; - *code++ = PT_CLIST; - *code++ = d; - } - else -#endif - /* Char has only one other case, or UCP not available */ - - { - *code++ = ((options & PCRE_CASELESS) != 0)? OP_NOTI: OP_NOT; -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - code += PRIV(ord2utf)(c, code); - else -#endif - *code++ = c; - } - - /* We are finished with this character class */ - - goto END_CLASS; - } - - /* For a single, positive character, get the value into mcbuffer, and - then we can handle this with the normal one-character code. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - mclength = PRIV(ord2utf)(c, mcbuffer); - else -#endif - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - } /* End of 1-char optimization */ - - /* There is more than one character in the class, or an XCLASS item - has been generated. Add this character to the class. */ - - class_has_8bitchar += - add_to_class(classbits, &class_uchardata, options, cd, c, c); - } - - /* Loop until ']' reached. This "while" is the end of the "do" far above. - If we are at the end of an internal nested string, revert to the outer - string. */ - - while (((c = *(++ptr)) != CHAR_NULL || - (nestptr != NULL && - (ptr = nestptr, nestptr = NULL, c = *(++ptr)) != CHAR_NULL)) && - (c != CHAR_RIGHT_SQUARE_BRACKET || inescq)); - - /* Check for missing terminating ']' */ - - if (c == CHAR_NULL) - { - *errorcodeptr = ERR6; - goto FAILED; - } - - /* We will need an XCLASS if data has been placed in class_uchardata. In - the second phase this is a sufficient test. However, in the pre-compile - phase, class_uchardata gets emptied to prevent workspace overflow, so it - only if the very last character in the class needs XCLASS will it contain - anything at this point. For this reason, xclass gets set TRUE above when - uchar_classdata is emptied, and that's why this code is the way it is here - instead of just doing a test on class_uchardata below. */ - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - if (class_uchardata > class_uchardata_base) xclass = TRUE; -#endif - - /* If this is the first thing in the branch, there can be no first char - setting, whatever the repeat count. Any reqchar setting must remain - unchanged after any kind of repeat. */ - - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode, unless there was a negated special - such as \S in the class, and PCRE_UCP is not set, because in that case all - characters > 255 are in the class, so any that were explicitly given as - well can be ignored. If (when there are explicit characters > 255 that must - be listed) there are no characters < 256, we can omit the bitmap in the - actual compiled code. */ - -#ifdef SUPPORT_UTF - if (xclass && (!should_flip_negation || (options & PCRE_UCP) != 0)) -#elif !defined COMPILE_PCRE8 - if (xclass && !should_flip_negation) -#endif -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - { - *class_uchardata++ = XCL_END; /* Marks the end of extra data */ - *code++ = OP_XCLASS; - code += LINK_SIZE; - *code = negate_class? XCL_NOT:0; - if (xclass_has_prop) *code |= XCL_HASPROP; - - /* If the map is required, move up the extra data to make room for it; - otherwise just move the code pointer to the end of the extra data. */ - - if (class_has_8bitchar > 0) - { - *code++ |= XCL_MAP; - memmove(code + (32 / sizeof(pcre_uchar)), code, - IN_UCHARS(class_uchardata - code)); - if (negate_class && !xclass_has_prop) - for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; - memcpy(code, classbits, 32); - code = class_uchardata + (32 / sizeof(pcre_uchar)); - } - else code = class_uchardata; - - /* Now fill in the complete length of the item */ - - PUT(previous, 1, (int)(code - previous)); - break; /* End of class handling */ - } -#endif - - /* If there are no characters > 255, or they are all to be included or - excluded, set the opcode to OP_CLASS or OP_NCLASS, depending on whether the - whole class was negated and whether there were negative specials such as \S - (non-UCP) in the class. Then copy the 32-byte map into the code vector, - negating it if necessary. */ - - *code++ = (negate_class == should_flip_negation) ? OP_CLASS : OP_NCLASS; - if (lengthptr == NULL) /* Save time in the pre-compile phase */ - { - if (negate_class) - for (c = 0; c < 32; c++) classbits[c] = ~classbits[c]; - memcpy(code, classbits, 32); - } - code += 32 / sizeof(pcre_uchar); - - END_CLASS: - break; - - - /* ===================================================================*/ - /* Various kinds of repeat; '{' is not necessarily a quantifier, but this - has been tested above. */ - - case CHAR_LEFT_CURLY_BRACKET: - if (!is_quantifier) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); - if (*errorcodeptr != 0) goto FAILED; - goto REPEAT; - - case CHAR_ASTERISK: - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case CHAR_PLUS: - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case CHAR_QUESTION_MARK: - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorcodeptr = ERR9; - goto FAILED; - } - - if (repeat_min == 0) - { - firstchar = zerofirstchar; /* Adjust for zero repeat */ - firstcharflags = zerofirstcharflags; - reqchar = zeroreqchar; /* Ditto */ - reqcharflags = zeroreqcharflags; - } - - /* Remember whether this is a variable length repeat */ - - reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; - - op_type = 0; /* Default single-char op codes */ - possessive_quantifier = FALSE; /* Default not possessive quantifier */ - - /* Save start of previous item, in case we have to move it up in order to - insert something before it. */ - - tempcode = previous; - - /* Before checking for a possessive quantifier, we must skip over - whitespace and comments in extended mode because Perl allows white space at - this point. */ - - if ((options & PCRE_EXTENDED) != 0) - { - const pcre_uchar *p = ptr + 1; - for (;;) - { - while (MAX_255(*p) && (cd->ctypes[*p] & ctype_space) != 0) p++; - if (*p != CHAR_NUMBER_SIGN) break; - p++; - while (*p != CHAR_NULL) - { - if (IS_NEWLINE(p)) /* For non-fixed-length newline cases, */ - { /* IS_NEWLINE sets cd->nllen. */ - p += cd->nllen; - break; - } - p++; -#ifdef SUPPORT_UTF - if (utf) FORWARDCHAR(p); -#endif - } /* Loop for comment characters */ - } /* Loop for multiple comments */ - ptr = p - 1; /* Character before the next significant one. */ - } - - /* If the next character is '+', we have a possessive quantifier. This - implies greediness, whatever the setting of the PCRE_UNGREEDY option. - If the next character is '?' this is a minimizing repeat, by default, - but if PCRE_UNGREEDY is set, it works the other way round. We change the - repeat type to the non-default. */ - - if (ptr[1] == CHAR_PLUS) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - ptr++; - } - else if (ptr[1] == CHAR_QUESTION_MARK) - { - repeat_type = greedy_non_default; - ptr++; - } - else repeat_type = greedy_default; - - /* If previous was a recursion call, wrap it in atomic brackets so that - previous becomes the atomic group. All recursions were so wrapped in the - past, but it no longer happens for non-repeated recursions. In fact, the - repeated ones could be re-implemented independently so as not to need this, - but for the moment we rely on the code for repeating groups. */ - - if (*previous == OP_RECURSE) - { - memmove(previous + 1 + LINK_SIZE, previous, IN_UCHARS(1 + LINK_SIZE)); - *previous = OP_ONCE; - PUT(previous, 1, 2 + 2*LINK_SIZE); - previous[2 + 2*LINK_SIZE] = OP_KET; - PUT(previous, 3 + 2*LINK_SIZE, 2 + 2*LINK_SIZE); - code += 2 + 2 * LINK_SIZE; - length_prevgroup = 3 + 3*LINK_SIZE; - - /* When actually compiling, we need to check whether this was a forward - reference, and if so, adjust the offset. */ - - if (lengthptr == NULL && cd->hwm >= cd->start_workspace + LINK_SIZE) - { - int offset = GET(cd->hwm, -LINK_SIZE); - if (offset == previous + 1 - cd->start_code) - PUT(cd->hwm, -LINK_SIZE, offset + 1 + LINK_SIZE); - } - } - - /* Now handle repetition for the different types of item. */ - - /* If previous was a character or negated character match, abolish the item - and generate a repeat item instead. If a char item has a minimum of more - than one, ensure that it is set in reqchar - it might not be if a sequence - such as x{3} is the first thing in a branch because the x will have gone - into firstchar instead. */ - - if (*previous == OP_CHAR || *previous == OP_CHARI - || *previous == OP_NOT || *previous == OP_NOTI) - { - switch (*previous) - { - default: /* Make compiler happy. */ - case OP_CHAR: op_type = OP_STAR - OP_STAR; break; - case OP_CHARI: op_type = OP_STARI - OP_STAR; break; - case OP_NOT: op_type = OP_NOTSTAR - OP_STAR; break; - case OP_NOTI: op_type = OP_NOTSTARI - OP_STAR; break; - } - - /* Deal with UTF characters that take up more than one character. It's - easier to write this out separately than try to macrify it. Use c to - hold the length of the character in bytes, plus UTF_LENGTH to flag that - it's a length rather than a small character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && NOT_FIRSTCHAR(code[-1])) - { - pcre_uchar *lastchar = code - 1; - BACKCHAR(lastchar); - c = (int)(code - lastchar); /* Length of UTF-8 character */ - memcpy(utf_chars, lastchar, IN_UCHARS(c)); /* Save the char */ - c |= UTF_LENGTH; /* Flag c as a length */ - } - else -#endif /* SUPPORT_UTF */ - - /* Handle the case of a single charater - either with no UTF support, or - with UTF disabled, or for a single character UTF character. */ - { - c = code[-1]; - if (*previous <= OP_CHARI && repeat_min > 1) - { - reqchar = c; - reqcharflags = req_caseopt | cd->req_varyopt; - } - } - - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a character type match (\d or similar), abolish it and - create a suitable repeat item. The code is shared with single-character - repeats by setting op_type to add a suitable offset into repeat_type. Note - the the Unicode property types will be present only when SUPPORT_UCP is - defined, but we don't wrap the little bits of code here because it just - makes it horribly messy. */ - - else if (*previous < OP_EODN) - { - pcre_uchar *oldcode; - int prop_type, prop_value; - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - - OUTPUT_SINGLE_REPEAT: - if (*previous == OP_PROP || *previous == OP_NOTPROP) - { - prop_type = previous[1]; - prop_value = previous[2]; - } - else prop_type = prop_value = -1; - - oldcode = code; - code = previous; /* Usually overwrite previous item */ - - /* If the maximum is zero then the minimum must also be zero; Perl allows - this case, so we do too - by simply omitting the item altogether. */ - - if (repeat_max == 0) goto END_REPEAT; - - /* Combine the op_type with the repeat_type */ - - repeat_type += op_type; - - /* A minimum of zero is handled either as the special case * or ?, or as - an UPTO, with the maximum given. */ - - if (repeat_min == 0) - { - if (repeat_max == -1) *code++ = OP_STAR + repeat_type; - else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - - /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item is - left in place and, if the maximum is greater than 1, we use OP_UPTO with - one less than the maximum. */ - - else if (repeat_min == 1) - { - if (repeat_max == -1) - *code++ = OP_PLUS + repeat_type; - else - { - code = oldcode; /* leave previous item in place */ - if (repeat_max == 1) goto END_REPEAT; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max - 1); - } - } - - /* The case {n,n} is just an EXACT, while the general case {n,m} is - handled as an EXACT followed by an UPTO. */ - - else - { - *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ - PUT2INC(code, 0, repeat_min); - - /* If the maximum is unlimited, insert an OP_STAR. Before doing so, - we have to insert the character for the previous code. For a repeated - Unicode property match, there are two extra bytes that define the - required property. In UTF-8 mode, long characters have their length in - c, with the UTF_LENGTH bit as a flag. */ - - if (repeat_max < 0) - { -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - { - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - } - *code++ = OP_STAR + repeat_type; - } - - /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. If the - UPTO is just for 1 instance, we can use QUERY instead. */ - - else if (repeat_max != repeat_min) - { -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - repeat_max -= repeat_min; - - if (repeat_max == 1) - { - *code++ = OP_QUERY + repeat_type; - } - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - } - - /* The character or character type itself comes last in all cases. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && (c & UTF_LENGTH) != 0) - { - memcpy(code, utf_chars, IN_UCHARS(c & 7)); - code += c & 7; - } - else -#endif - *code++ = c; - - /* For a repeated Unicode property match, there are two extra bytes that - define the required property. */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } -#endif - } - - /* If previous was a character class or a back reference, we put the repeat - stuff after it, but just skip the item if the repeat was {0,0}. */ - - else if (*previous == OP_CLASS || *previous == OP_NCLASS || -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - *previous == OP_XCLASS || -#endif - *previous == OP_REF || *previous == OP_REFI || - *previous == OP_DNREF || *previous == OP_DNREFI) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - if (repeat_min == 0 && repeat_max == -1) - *code++ = OP_CRSTAR + repeat_type; - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_CRPLUS + repeat_type; - else if (repeat_min == 0 && repeat_max == 1) - *code++ = OP_CRQUERY + repeat_type; - else - { - *code++ = OP_CRRANGE + repeat_type; - PUT2INC(code, 0, repeat_min); - if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ - PUT2INC(code, 0, repeat_max); - } - } - - /* If previous was a bracket group, we may have to replicate it in certain - cases. Note that at this point we can encounter only the "basic" bracket - opcodes such as BRA and CBRA, as this is the place where they get converted - into the more special varieties such as BRAPOS and SBRA. A test for >= - OP_ASSERT and <= OP_COND includes ASSERT, ASSERT_NOT, ASSERTBACK, - ASSERTBACK_NOT, ONCE, ONCE_NC, BRA, BRAPOS, CBRA, CBRAPOS, and COND. - Originally, PCRE did not allow repetition of assertions, but now it does, - for Perl compatibility. */ - - else if (*previous >= OP_ASSERT && *previous <= OP_COND) - { - register int i; - int len = (int)(code - previous); - pcre_uchar *bralink = NULL; - pcre_uchar *brazeroptr = NULL; - - /* Repeating a DEFINE group is pointless, but Perl allows the syntax, so - we just ignore the repeat. */ - - if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) - goto END_REPEAT; - - /* There is no sense in actually repeating assertions. The only potential - use of repetition is in cases when the assertion is optional. Therefore, - if the minimum is greater than zero, just ignore the repeat. If the - maximum is not zero or one, set it to 1. */ - - if (*previous < OP_ONCE) /* Assertion */ - { - if (repeat_min > 0) goto END_REPEAT; - if (repeat_max < 0 || repeat_max > 1) repeat_max = 1; - } - - /* The case of a zero minimum is special because of the need to stick - OP_BRAZERO in front of it, and because the group appears once in the - data, whereas in other cases it appears the minimum number of times. For - this reason, it is simplest to treat this case separately, as otherwise - the code gets far too messy. There are several special subcases when the - minimum is zero. */ - - if (repeat_min == 0) - { - /* If the maximum is also zero, we used to just omit the group from the - output altogether, like this: - - ** if (repeat_max == 0) - ** { - ** code = previous; - ** goto END_REPEAT; - ** } - - However, that fails when a group or a subgroup within it is referenced - as a subroutine from elsewhere in the pattern, so now we stick in - OP_SKIPZERO in front of it so that it is skipped on execution. As we - don't have a list of which groups are referenced, we cannot do this - selectively. - - If the maximum is 1 or unlimited, we just have to stick in the BRAZERO - and do no more at this point. However, we do need to adjust any - OP_RECURSE calls inside the group that refer to the group itself or any - internal or forward referenced group, because the offset is from the - start of the whole regex. Temporarily terminate the pattern while doing - this. */ - - if (repeat_max <= 1) /* Covers 0, 1, and unlimited */ - { - *code = OP_END; - adjust_recurse(previous, 1, utf, cd, save_hwm); - memmove(previous + 1, previous, IN_UCHARS(len)); - code++; - if (repeat_max == 0) - { - *previous++ = OP_SKIPZERO; - goto END_REPEAT; - } - brazeroptr = previous; /* Save for possessive optimizing */ - *previous++ = OP_BRAZERO + repeat_type; - } - - /* If the maximum is greater than 1 and limited, we have to replicate - in a nested fashion, sticking OP_BRAZERO before each set of brackets. - The first one has to be handled carefully because it's the original - copy, which has to be moved up. The remainder can be handled by code - that is common with the non-zero minimum case below. We have to - adjust the value or repeat_max, since one less copy is required. Once - again, we may have to adjust any OP_RECURSE calls inside the group. */ - - else - { - int offset; - *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf, cd, save_hwm); - memmove(previous + 2 + LINK_SIZE, previous, IN_UCHARS(len)); - code += 2 + LINK_SIZE; - *previous++ = OP_BRAZERO + repeat_type; - *previous++ = OP_BRA; - - /* We chain together the bracket offset fields that have to be - filled in later when the ends of the brackets are reached. */ - - offset = (bralink == NULL)? 0 : (int)(previous - bralink); - bralink = previous; - PUTINC(previous, 0, offset); - } - - repeat_max--; - } - - /* If the minimum is greater than zero, replicate the group as many - times as necessary, and adjust the maximum to the number of subsequent - copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. If there are any - forward reference subroutine calls in the group, there will be entries on - the workspace list; replicate these with an appropriate increment. */ - - else - { - if (repeat_min > 1) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. Do some paranoid checks for - potential integer overflow. The INT64_OR_DOUBLE type is a 64-bit - integer type when available, otherwise double. */ - - if (lengthptr != NULL) - { - int delta = (repeat_min - 1)*length_prevgroup; - if ((INT64_OR_DOUBLE)(repeat_min - 1)* - (INT64_OR_DOUBLE)length_prevgroup > - (INT64_OR_DOUBLE)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real. If there is a set first byte for - the group, and we have not yet set a "required byte", set it. Make - sure there is enough workspace for copying forward references before - doing the copy. */ - - else - { - if (groupsetfirstchar && reqcharflags < 0) - { - reqchar = firstchar; - reqcharflags = firstcharflags; - } - - for (i = 1; i < repeat_min; i++) - { - pcre_uchar *hc; - pcre_uchar *this_hwm = cd->hwm; - memcpy(code, previous, IN_UCHARS(len)); - - while (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm)) - { - int save_offset = save_hwm - cd->start_workspace; - int this_offset = this_hwm - cd->start_workspace; - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - save_hwm = (pcre_uchar *)cd->start_workspace + save_offset; - this_hwm = (pcre_uchar *)cd->start_workspace + this_offset; - } - - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - } - } - - if (repeat_max > 0) repeat_max -= repeat_min; - } - - /* This code is common to both the zero and non-zero minimum cases. If - the maximum is limited, it replicates the group in a nested fashion, - remembering the bracket starts on a stack. In the case of a zero minimum, - the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. Again, we must remember to - replicate entries on the forward reference list. */ - - if (repeat_max >= 0) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. For each repetition we must add 1 - to the length for BRAZERO and for all but the last repetition we must - add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some - paranoid checks to avoid integer overflow. The INT64_OR_DOUBLE type is - a 64-bit integer type when available, otherwise double. */ - - if (lengthptr != NULL && repeat_max > 0) - { - int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - - 2 - 2*LINK_SIZE; /* Last one doesn't nest */ - if ((INT64_OR_DOUBLE)repeat_max * - (INT64_OR_DOUBLE)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) - > (INT64_OR_DOUBLE)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else for (i = repeat_max - 1; i >= 0; i--) - { - pcre_uchar *hc; - pcre_uchar *this_hwm = cd->hwm; - - *code++ = OP_BRAZERO + repeat_type; - - /* All but the final copy start a new nesting, maintaining the - chain of brackets outstanding. */ - - if (i != 0) - { - int offset; - *code++ = OP_BRA; - offset = (bralink == NULL)? 0 : (int)(code - bralink); - bralink = code; - PUTINC(code, 0, offset); - } - - memcpy(code, previous, IN_UCHARS(len)); - - /* Ensure there is enough workspace for forward references before - copying them. */ - - while (cd->hwm > cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN - (this_hwm - save_hwm)) - { - int save_offset = save_hwm - cd->start_workspace; - int this_offset = this_hwm - cd->start_workspace; - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - save_hwm = (pcre_uchar *)cd->start_workspace + save_offset; - this_hwm = (pcre_uchar *)cd->start_workspace + this_offset; - } - - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - - /* Now chain through the pending brackets, and fill in their length - fields (which are holding the chain links pro tem). */ - - while (bralink != NULL) - { - int oldlinkoffset; - int offset = (int)(code - bralink + 1); - pcre_uchar *bra = code - offset; - oldlinkoffset = GET(bra, 1); - bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; - *code++ = OP_KET; - PUTINC(code, 0, offset); - PUT(bra, 1, offset); - } - } - - /* If the maximum is unlimited, set a repeater in the final copy. For - ONCE brackets, that's all we need to do. However, possessively repeated - ONCE brackets can be converted into non-capturing brackets, as the - behaviour of (?:xx)++ is the same as (?>xx)++ and this saves having to - deal with possessive ONCEs specially. - - Otherwise, when we are doing the actual compile phase, check to see - whether this group is one that could match an empty string. If so, - convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so - that runtime checking can be done. [This check is also applied to ONCE - groups at runtime, but in a different way.] - - Then, if the quantifier was possessive and the bracket is not a - conditional, we convert the BRA code to the POS form, and the KET code to - KETRPOS. (It turns out to be convenient at runtime to detect this kind of - subpattern at both the start and at the end.) The use of special opcodes - makes it possible to reduce greatly the stack usage in pcre_exec(). If - the group is preceded by OP_BRAZERO, convert this to OP_BRAPOSZERO. - - Then, if the minimum number of matches is 1 or 0, cancel the possessive - flag so that the default action below, of wrapping everything inside - atomic brackets, does not happen. When the minimum is greater than 1, - there will be earlier copies of the group, and so we still have to wrap - the whole thing. */ - - else - { - pcre_uchar *ketcode = code - 1 - LINK_SIZE; - pcre_uchar *bracode = ketcode - GET(ketcode, 1); - - /* Convert possessive ONCE brackets to non-capturing */ - - if ((*bracode == OP_ONCE || *bracode == OP_ONCE_NC) && - possessive_quantifier) *bracode = OP_BRA; - - /* For non-possessive ONCE brackets, all we need to do is to - set the KET. */ - - if (*bracode == OP_ONCE || *bracode == OP_ONCE_NC) - *ketcode = OP_KETRMAX + repeat_type; - - /* Handle non-ONCE brackets and possessive ONCEs (which have been - converted to non-capturing above). */ - - else - { - /* In the compile phase, check for empty string matching. */ - - if (lengthptr == NULL) - { - pcre_uchar *scode = bracode; - do - { - if (could_be_empty_branch(scode, ketcode, utf, cd, NULL)) - { - *bracode += OP_SBRA - OP_BRA; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - } - - /* Handle possessive quantifiers. */ - - if (possessive_quantifier) - { - /* For COND brackets, we wrap the whole thing in a possessively - repeated non-capturing bracket, because we have not invented POS - versions of the COND opcodes. Because we are moving code along, we - must ensure that any pending recursive references are updated. */ - - if (*bracode == OP_COND || *bracode == OP_SCOND) - { - int nlen = (int)(code - bracode); - *code = OP_END; - adjust_recurse(bracode, 1 + LINK_SIZE, utf, cd, save_hwm); - memmove(bracode + 1 + LINK_SIZE, bracode, IN_UCHARS(nlen)); - code += 1 + LINK_SIZE; - nlen += 1 + LINK_SIZE; - *bracode = OP_BRAPOS; - *code++ = OP_KETRPOS; - PUTINC(code, 0, nlen); - PUT(bracode, 1, nlen); - } - - /* For non-COND brackets, we modify the BRA code and use KETRPOS. */ - - else - { - *bracode += 1; /* Switch to xxxPOS opcodes */ - *ketcode = OP_KETRPOS; - } - - /* If the minimum is zero, mark it as possessive, then unset the - possessive flag when the minimum is 0 or 1. */ - - if (brazeroptr != NULL) *brazeroptr = OP_BRAPOSZERO; - if (repeat_min < 2) possessive_quantifier = FALSE; - } - - /* Non-possessive quantifier */ - - else *ketcode = OP_KETRMAX + repeat_type; - } - } - } - - /* If previous is OP_FAIL, it was generated by an empty class [] in - JavaScript mode. The other ways in which OP_FAIL can be generated, that is - by (*FAIL) or (?!) set previous to NULL, which gives a "nothing to repeat" - error above. We can just ignore the repeat in JS case. */ - - else if (*previous == OP_FAIL) goto END_REPEAT; - - /* Else there's some kind of shambles */ - - else - { - *errorcodeptr = ERR11; - goto FAILED; - } - - /* If the character following a repeat is '+', possessive_quantifier is - TRUE. For some opcodes, there are special alternative opcodes for this - case. For anything else, we wrap the entire repeated item inside OP_ONCE - brackets. Logically, the '+' notation is just syntactic sugar, taken from - Sun's Java package, but the special opcodes can optimize it. - - Some (but not all) possessively repeated subpatterns have already been - completely handled in the code just above. For them, possessive_quantifier - is always FALSE at this stage. Note that the repeated item starts at - tempcode, not at previous, which might be the first part of a string whose - (former) last char we repeated. */ - - if (possessive_quantifier) - { - int len; - - /* Possessifying an EXACT quantifier has no effect, so we can ignore it. - However, QUERY, STAR, or UPTO may follow (for quantifiers such as {5,6}, - {5,}, or {5,10}). We skip over an EXACT item; if the length of what - remains is greater than zero, there's a further opcode that can be - handled. If not, do nothing, leaving the EXACT alone. */ - - switch(*tempcode) - { - case OP_TYPEEXACT: - tempcode += PRIV(OP_lengths)[*tempcode] + - ((tempcode[1 + IMM2_SIZE] == OP_PROP - || tempcode[1 + IMM2_SIZE] == OP_NOTPROP)? 2 : 0); - break; - - /* CHAR opcodes are used for exacts whose count is 1. */ - - case OP_CHAR: - case OP_CHARI: - case OP_NOT: - case OP_NOTI: - case OP_EXACT: - case OP_EXACTI: - case OP_NOTEXACT: - case OP_NOTEXACTI: - tempcode += PRIV(OP_lengths)[*tempcode]; -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(tempcode[-1])) - tempcode += GET_EXTRALEN(tempcode[-1]); -#endif - break; - - /* For the class opcodes, the repeat operator appears at the end; - adjust tempcode to point to it. */ - - case OP_CLASS: - case OP_NCLASS: - tempcode += 1 + 32/sizeof(pcre_uchar); - break; - -#if defined SUPPORT_UTF || !defined COMPILE_PCRE8 - case OP_XCLASS: - tempcode += GET(tempcode, 1); - break; -#endif - } - - /* If tempcode is equal to code (which points to the end of the repeated - item), it means we have skipped an EXACT item but there is no following - QUERY, STAR, or UPTO; the value of len will be 0, and we do nothing. In - all other cases, tempcode will be pointing to the repeat opcode, and will - be less than code, so the value of len will be greater than 0. */ - - len = (int)(code - tempcode); - if (len > 0) - { - unsigned int repcode = *tempcode; - - /* There is a table for possessifying opcodes, all of which are less - than OP_CALLOUT. A zero entry means there is no possessified version. - */ - - if (repcode < OP_CALLOUT && opcode_possessify[repcode] > 0) - *tempcode = opcode_possessify[repcode]; - - /* For opcode without a special possessified version, wrap the item in - ONCE brackets. Because we are moving code along, we must ensure that any - pending recursive references are updated. */ - - else - { - *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm); - memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - } - } - -#ifdef NEVER - if (len > 0) switch (*tempcode) - { - case OP_STAR: *tempcode = OP_POSSTAR; break; - case OP_PLUS: *tempcode = OP_POSPLUS; break; - case OP_QUERY: *tempcode = OP_POSQUERY; break; - case OP_UPTO: *tempcode = OP_POSUPTO; break; - - case OP_STARI: *tempcode = OP_POSSTARI; break; - case OP_PLUSI: *tempcode = OP_POSPLUSI; break; - case OP_QUERYI: *tempcode = OP_POSQUERYI; break; - case OP_UPTOI: *tempcode = OP_POSUPTOI; break; - - case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; - case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; - case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; - case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; - - case OP_NOTSTARI: *tempcode = OP_NOTPOSSTARI; break; - case OP_NOTPLUSI: *tempcode = OP_NOTPOSPLUSI; break; - case OP_NOTQUERYI: *tempcode = OP_NOTPOSQUERYI; break; - case OP_NOTUPTOI: *tempcode = OP_NOTPOSUPTOI; break; - - case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; - case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; - case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; - case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; - - case OP_CRSTAR: *tempcode = OP_CRPOSSTAR; break; - case OP_CRPLUS: *tempcode = OP_CRPOSPLUS; break; - case OP_CRQUERY: *tempcode = OP_CRPOSQUERY; break; - case OP_CRRANGE: *tempcode = OP_CRPOSRANGE; break; - - /* Because we are moving code along, we must ensure that any - pending recursive references are updated. */ - - default: - *code = OP_END; - adjust_recurse(tempcode, 1 + LINK_SIZE, utf, cd, save_hwm); - memmove(tempcode + 1 + LINK_SIZE, tempcode, IN_UCHARS(len)); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - break; - } -#endif - } - - /* In all case we no longer have a previous item. We also set the - "follows varying string" flag for subsequently encountered reqchars if - it isn't already set and we have just passed a varying length item. */ - - END_REPEAT: - previous = NULL; - cd->req_varyopt |= reqvary; - break; - - - /* ===================================================================*/ - /* Start of nested parenthesized sub-expression, or comment or lookahead or - lookbehind or option setting or condition or all the other extended - parenthesis forms. */ - - case CHAR_LEFT_PARENTHESIS: - newoptions = options; - skipbytes = 0; - bravalue = OP_CBRA; - save_hwm = cd->hwm; - reset_bracount = FALSE; - - /* First deal with various "verbs" that can be introduced by '*'. */ - - ptr++; - if (ptr[0] == CHAR_ASTERISK && (ptr[1] == ':' - || (MAX_255(ptr[1]) && ((cd->ctypes[ptr[1]] & ctype_letter) != 0)))) - { - int i, namelen; - int arglen = 0; - const char *vn = verbnames; - const pcre_uchar *name = ptr + 1; - const pcre_uchar *arg = NULL; - previous = NULL; - ptr++; - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; - namelen = (int)(ptr - name); - - /* It appears that Perl allows any characters whatsoever, other than - a closing parenthesis, to appear in arguments, so we no longer insist on - letters, digits, and underscores. */ - - if (*ptr == CHAR_COLON) - { - arg = ++ptr; - while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - arglen = (int)(ptr - arg); - if ((unsigned int)arglen > MAX_MARK) - { - *errorcodeptr = ERR75; - goto FAILED; - } - } - - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR60; - goto FAILED; - } - - /* Scan the table of verb names */ - - for (i = 0; i < verbcount; i++) - { - if (namelen == verbs[i].len && - STRNCMP_UC_C8(name, vn, namelen) == 0) - { - int setverb; - - /* Check for open captures before ACCEPT and convert it to - ASSERT_ACCEPT if in an assertion. */ - - if (verbs[i].op == OP_ACCEPT) - { - open_capitem *oc; - if (arglen != 0) - { - *errorcodeptr = ERR59; - goto FAILED; - } - cd->had_accept = TRUE; - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - *code++ = OP_CLOSE; - PUT2INC(code, 0, oc->number); - } - setverb = *code++ = - (cd->assert_depth > 0)? OP_ASSERT_ACCEPT : OP_ACCEPT; - - /* Do not set firstchar after *ACCEPT */ - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - } - - /* Handle other cases with/without an argument */ - - else if (arglen == 0) - { - if (verbs[i].op < 0) /* Argument is mandatory */ - { - *errorcodeptr = ERR66; - goto FAILED; - } - setverb = *code++ = verbs[i].op; - } - - else - { - if (verbs[i].op_arg < 0) /* Argument is forbidden */ - { - *errorcodeptr = ERR59; - goto FAILED; - } - setverb = *code++ = verbs[i].op_arg; - *code++ = arglen; - memcpy(code, arg, IN_UCHARS(arglen)); - code += arglen; - *code++ = 0; - } - - switch (setverb) - { - case OP_THEN: - case OP_THEN_ARG: - cd->external_flags |= PCRE_HASTHEN; - break; - - case OP_PRUNE: - case OP_PRUNE_ARG: - case OP_SKIP: - case OP_SKIP_ARG: - cd->had_pruneorskip = TRUE; - break; - } - - break; /* Found verb, exit loop */ - } - - vn += verbs[i].len + 1; - } - - if (i < verbcount) continue; /* Successfully handled a verb */ - *errorcodeptr = ERR60; /* Verb not recognized */ - goto FAILED; - } - - /* Deal with the extended parentheses; all are introduced by '?', and the - appearance of any of them means that this is not a capturing group. */ - - else if (*ptr == CHAR_QUESTION_MARK) - { - int i, set, unset, namelen; - int *optset; - const pcre_uchar *name; - pcre_uchar *slot; - - switch (*(++ptr)) - { - case CHAR_NUMBER_SIGN: /* Comment; skip to ket */ - ptr++; - while (*ptr != CHAR_NULL && *ptr != CHAR_RIGHT_PARENTHESIS) ptr++; - if (*ptr == CHAR_NULL) - { - *errorcodeptr = ERR18; - goto FAILED; - } - continue; - - - /* ------------------------------------------------------------ */ - case CHAR_VERTICAL_LINE: /* Reset capture count for each branch */ - reset_bracount = TRUE; - /* Fall through */ - - /* ------------------------------------------------------------ */ - case CHAR_COLON: /* Non-capturing bracket */ - bravalue = OP_BRA; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LEFT_PARENTHESIS: - bravalue = OP_COND; /* Conditional group */ - tempptr = ptr; - - /* A condition can be an assertion, a number (referring to a numbered - group's having been set), a name (referring to a named group), or 'R', - referring to recursion. R<digits> and R&name are also permitted for - recursion tests. - - There are ways of testing a named group: (?(name)) is used by Python; - Perl 5.10 onwards uses (?(<name>) or (?('name')). - - There is one unfortunate ambiguity, caused by history. 'R' can be the - recursive thing or the name 'R' (and similarly for 'R' followed by - digits). We look for a name first; if not found, we try the other case. - - For compatibility with auto-callouts, we allow a callout to be - specified before a condition that is an assertion. First, check for the - syntax of a callout; if found, adjust the temporary pointer that is - used to check for an assertion condition. That's all that is needed! */ - - if (ptr[1] == CHAR_QUESTION_MARK && ptr[2] == CHAR_C) - { - for (i = 3;; i++) if (!IS_DIGIT(ptr[i])) break; - if (ptr[i] == CHAR_RIGHT_PARENTHESIS) - tempptr += i + 1; - } - - /* For conditions that are assertions, check the syntax, and then exit - the switch. This will take control down to where bracketed groups, - including assertions, are processed. */ - - if (tempptr[1] == CHAR_QUESTION_MARK && - (tempptr[2] == CHAR_EQUALS_SIGN || - tempptr[2] == CHAR_EXCLAMATION_MARK || - tempptr[2] == CHAR_LESS_THAN_SIGN)) - break; - - /* Other conditions use OP_CREF/OP_DNCREF/OP_RREF/OP_DNRREF, and all - need to skip at least 1+IMM2_SIZE bytes at the start of the group. */ - - code[1+LINK_SIZE] = OP_CREF; - skipbytes = 1+IMM2_SIZE; - refsign = -1; /* => not a number */ - namelen = -1; /* => not a name; must set to avoid warning */ - name = NULL; /* Always set to avoid warning */ - recno = 0; /* Always set to avoid warning */ - - /* Check for a test for recursion in a named group. */ - - ptr++; - if (*ptr == CHAR_R && ptr[1] == CHAR_AMPERSAND) - { - terminator = -1; - ptr += 2; - code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ - } - - /* Check for a test for a named group's having been set, using the Perl - syntax (?(<name>) or (?('name'), and also allow for the original PCRE - syntax of (?(name) or for (?(+n), (?(-n), and just (?(n). */ - - else if (*ptr == CHAR_LESS_THAN_SIGN) - { - terminator = CHAR_GREATER_THAN_SIGN; - ptr++; - } - else if (*ptr == CHAR_APOSTROPHE) - { - terminator = CHAR_APOSTROPHE; - ptr++; - } - else - { - terminator = CHAR_NULL; - if (*ptr == CHAR_MINUS || *ptr == CHAR_PLUS) refsign = *ptr++; - else if (IS_DIGIT(*ptr)) refsign = 0; - } - - /* Handle a number */ - - if (refsign >= 0) - { - while (IS_DIGIT(*ptr)) - { - recno = recno * 10 + (int)(*ptr - CHAR_0); - ptr++; - } - } - - /* Otherwise we expect to read a name; anything else is an error. When - a name is one of a number of duplicates, a different opcode is used and - it needs more memory. Unfortunately we cannot tell whether a name is a - duplicate in the first pass, so we have to allow for more memory. */ - - else - { - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; - goto FAILED; - } - if (!MAX_255(*ptr) || (cd->ctypes[*ptr] & ctype_word) == 0) - { - *errorcodeptr = ERR28; /* Assertion expected */ - goto FAILED; - } - name = ptr++; - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) - { - ptr++; - } - namelen = (int)(ptr - name); - if (lengthptr != NULL) *lengthptr += IMM2_SIZE; - } - - /* Check the terminator */ - - if ((terminator > 0 && *ptr++ != (pcre_uchar)terminator) || - *ptr++ != CHAR_RIGHT_PARENTHESIS) - { - ptr--; /* Error offset */ - *errorcodeptr = ERR26; /* Malformed number or name */ - goto FAILED; - } - - /* Do no further checking in the pre-compile phase. */ - - if (lengthptr != NULL) break; - - /* In the real compile we do the work of looking for the actual - reference. If refsign is not negative, it means we have a number in - recno. */ - - if (refsign >= 0) - { - if (recno <= 0) - { - *errorcodeptr = ERR35; - goto FAILED; - } - if (refsign != 0) recno = (refsign == CHAR_MINUS)? - cd->bracount - recno + 1 : recno + cd->bracount; - if (recno <= 0 || recno > cd->final_bracount) - { - *errorcodeptr = ERR15; - goto FAILED; - } - PUT2(code, 2+LINK_SIZE, recno); - break; - } - - /* Otherwise look for the name. */ - - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found the named subpattern. If the name is duplicated, add one to - the opcode to change CREF/RREF into DNCREF/DNRREF and insert - appropriate data values. Otherwise, just insert the unique subpattern - number. */ - - if (i < cd->names_found) - { - int offset = i++; - int count = 1; - recno = GET2(slot, 0); /* Number from first found */ - for (; i < cd->names_found; i++) - { - slot += cd->name_entry_size; - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) != 0) break; - count++; - } - if (count > 1) - { - PUT2(code, 2+LINK_SIZE, offset); - PUT2(code, 2+LINK_SIZE+IMM2_SIZE, count); - skipbytes += IMM2_SIZE; - code[1+LINK_SIZE]++; - } - else /* Not a duplicated name */ - { - PUT2(code, 2+LINK_SIZE, recno); - } - } - - /* If terminator == CHAR_NULL it means that the name followed directly - after the opening parenthesis [e.g. (?(abc)...] and in this case there - are some further alternatives to try. For the cases where terminator != - CHAR_NULL [things like (?(<name>... or (?('name')... or (?(R&name)... ] - we have now checked all the possibilities, so give an error. */ - - else if (terminator != CHAR_NULL) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Check for (?(R) for recursion. Allow digits after R to specify a - specific group number. */ - - else if (*name == CHAR_R) - { - recno = 0; - for (i = 1; i < namelen; i++) - { - if (!IS_DIGIT(name[i])) - { - *errorcodeptr = ERR15; - goto FAILED; - } - recno = recno * 10 + name[i] - CHAR_0; - } - if (recno == 0) recno = RREF_ANY; - code[1+LINK_SIZE] = OP_RREF; /* Change test type */ - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Similarly, check for the (?(DEFINE) "condition", which is always - false. */ - - else if (namelen == 6 && STRNCMP_UC_C8(name, STRING_DEFINE, 6) == 0) - { - code[1+LINK_SIZE] = OP_DEF; - skipbytes = 1; - } - - /* Reference to an unidentified subpattern. */ - - else - { - *errorcodeptr = ERR15; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_EQUALS_SIGN: /* Positive lookahead */ - bravalue = OP_ASSERT; - cd->assert_depth += 1; - ptr++; - break; - - /* Optimize (?!) to (*FAIL) unless it is quantified - which is a weird - thing to do, but Perl allows all assertions to be quantified, and when - they contain capturing parentheses there may be a potential use for - this feature. Not that that applies to a quantified (?!) but we allow - it for uniformity. */ - - /* ------------------------------------------------------------ */ - case CHAR_EXCLAMATION_MARK: /* Negative lookahead */ - ptr++; - if (*ptr == CHAR_RIGHT_PARENTHESIS && ptr[1] != CHAR_ASTERISK && - ptr[1] != CHAR_PLUS && ptr[1] != CHAR_QUESTION_MARK && - (ptr[1] != CHAR_LEFT_CURLY_BRACKET || !is_counted_repeat(ptr+2))) - { - *code++ = OP_FAIL; - previous = NULL; - continue; - } - bravalue = OP_ASSERT_NOT; - cd->assert_depth += 1; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_LESS_THAN_SIGN: /* Lookbehind or named define */ - switch (ptr[1]) - { - case CHAR_EQUALS_SIGN: /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - cd->assert_depth += 1; - ptr += 2; - break; - - case CHAR_EXCLAMATION_MARK: /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - cd->assert_depth += 1; - ptr += 2; - break; - - default: /* Could be name define, else bad */ - if (MAX_255(ptr[1]) && (cd->ctypes[ptr[1]] & ctype_word) != 0) - goto DEFINE_NAME; - ptr++; /* Correct offset for error */ - *errorcodeptr = ERR24; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case CHAR_GREATER_THAN_SIGN: /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case CHAR_C: /* Callout - may be followed by digits; */ - previous_callout = code; /* Save for later completion */ - after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; - { - int n = 0; - ptr++; - while(IS_DIGIT(*ptr)) - n = n * 10 + *ptr++ - CHAR_0; - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR39; - goto FAILED; - } - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, (int)(ptr - cd->start_pattern + 1)); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; - } - previous = NULL; - continue; - - - /* ------------------------------------------------------------ */ - case CHAR_P: /* Python-style named subpattern handling */ - if (*(++ptr) == CHAR_EQUALS_SIGN || - *ptr == CHAR_GREATER_THAN_SIGN) /* Reference or recursion */ - { - is_recurse = *ptr == CHAR_GREATER_THAN_SIGN; - terminator = CHAR_RIGHT_PARENTHESIS; - goto NAMED_REF_OR_RECURSE; - } - else if (*ptr != CHAR_LESS_THAN_SIGN) /* Test for Python-style defn */ - { - *errorcodeptr = ERR41; - goto FAILED; - } - /* Fall through to handle (?P< as (?< is handled */ - - - /* ------------------------------------------------------------ */ - DEFINE_NAME: /* Come here from (?< handling */ - case CHAR_APOSTROPHE: - terminator = (*ptr == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - name = ++ptr; - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; /* Group name must start with non-digit */ - goto FAILED; - } - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = (int)(ptr - name); - - /* In the pre-compile phase, do a syntax check, remember the longest - name, and then remember the group in a vector, expanding it if - necessary. Duplicates for the same number are skipped; other duplicates - are checked for validity. In the actual compile, there is nothing to - do. */ - - if (lengthptr != NULL) - { - named_group *ng; - pcre_uint32 number = cd->bracount + 1; - - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - - if (cd->names_found >= MAX_NAME_COUNT) - { - *errorcodeptr = ERR49; - goto FAILED; - } - - if (namelen + IMM2_SIZE + 1 > cd->name_entry_size) - { - cd->name_entry_size = namelen + IMM2_SIZE + 1; - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - } - - /* Scan the list to check for duplicates. For duplicate names, if the - number is the same, break the loop, which causes the name to be - discarded; otherwise, if DUPNAMES is not set, give an error. - If it is set, allow the name with a different number, but continue - scanning in case this is a duplicate with the same number. For - non-duplicate names, give an error if the number is duplicated. */ - - ng = cd->named_groups; - for (i = 0; i < cd->names_found; i++, ng++) - { - if (namelen == ng->length && - STRNCMP_UC_UC(name, ng->name, namelen) == 0) - { - if (ng->number == number) break; - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - cd->dupnames = TRUE; /* Duplicate names exist */ - } - else if (ng->number == number) - { - *errorcodeptr = ERR65; - goto FAILED; - } - } - - if (i >= cd->names_found) /* Not a duplicate with same number */ - { - /* Increase the list size if necessary */ - - if (cd->names_found >= cd->named_group_list_size) - { - int newsize = cd->named_group_list_size * 2; - named_group *newspace = (PUBL(malloc)) - (newsize * sizeof(named_group)); - - if (newspace == NULL) - { - *errorcodeptr = ERR21; - goto FAILED; - } - - memcpy(newspace, cd->named_groups, - cd->named_group_list_size * sizeof(named_group)); - if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) - (PUBL(free))((void *)cd->named_groups); - cd->named_groups = newspace; - cd->named_group_list_size = newsize; - } - - cd->named_groups[cd->names_found].name = name; - cd->named_groups[cd->names_found].length = namelen; - cd->named_groups[cd->names_found].number = number; - cd->names_found++; - } - } - - ptr++; /* Move past > or ' in both passes. */ - goto NUMBERED_GROUP; - - - /* ------------------------------------------------------------ */ - case CHAR_AMPERSAND: /* Perl recursion/subroutine syntax */ - terminator = CHAR_RIGHT_PARENTHESIS; - is_recurse = TRUE; - /* Fall through */ - - /* We come here from the Python syntax above that handles both - references (?P=name) and recursion (?P>name), as well as falling - through from the Perl recursion syntax (?&name). We also come here from - the Perl \k<name> or \k'name' back reference syntax and the \k{name} - .NET syntax, and the Oniguruma \g<...> and \g'...' subroutine syntax. */ - - NAMED_REF_OR_RECURSE: - name = ++ptr; - if (IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR84; /* Group name must start with non-digit */ - goto FAILED; - } - while (MAX_255(*ptr) && (cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = (int)(ptr - name); - - /* In the pre-compile phase, do a syntax check. We used to just set - a dummy reference number, because it was not used in the first pass. - However, with the change of recursive back references to be atomic, - we have to look for the number so that this state can be identified, as - otherwise the incorrect length is computed. If it's not a backwards - reference, the dummy number will do. */ - - if (lengthptr != NULL) - { - named_group *ng; - - if (namelen == 0) - { - *errorcodeptr = ERR62; - goto FAILED; - } - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - - /* The name table does not exist in the first pass; instead we must - scan the list of names encountered so far in order to get the - number. If the name is not found, set the value to 0 for a forward - reference. */ - - ng = cd->named_groups; - for (i = 0; i < cd->names_found; i++, ng++) - { - if (namelen == ng->length && - STRNCMP_UC_UC(name, ng->name, namelen) == 0) - break; - } - recno = (i < cd->names_found)? ng->number : 0; - - /* Count named back references. */ - - if (!is_recurse) cd->namedrefcount++; - } - - /* In the real compile, search the name table. We check the name - first, and then check that we have reached the end of the name in the - table. That way, if the name is longer than any in the table, the - comparison will fail without reading beyond the table entry. */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (STRNCMP_UC_UC(name, slot+IMM2_SIZE, namelen) == 0 && - slot[IMM2_SIZE+namelen] == 0) - break; - slot += cd->name_entry_size; - } - - if (i < cd->names_found) - { - recno = GET2(slot, 0); - } - else - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - - /* In both phases, for recursions, we can now go to the code than - handles numerical recursion. */ - - if (is_recurse) goto HANDLE_RECURSION; - - /* In the second pass we must see if the name is duplicated. If so, we - generate a different opcode. */ - - if (lengthptr == NULL && cd->dupnames) - { - int count = 1; - unsigned int index = i; - pcre_uchar *cslot = slot + cd->name_entry_size; - - for (i++; i < cd->names_found; i++) - { - if (STRCMP_UC_UC(slot + IMM2_SIZE, cslot + IMM2_SIZE) != 0) break; - count++; - cslot += cd->name_entry_size; - } - - if (count > 1) - { - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - previous = code; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_DNREFI : OP_DNREF; - PUT2INC(code, 0, index); - PUT2INC(code, 0, count); - - /* Process each potentially referenced group. */ - - for (; slot < cslot; slot += cd->name_entry_size) - { - open_capitem *oc; - recno = GET2(slot, 0); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - - /* Check to see if this back reference is recursive, that it, it - is inside the group that it references. A flag is set so that the - group can be made atomic. */ - - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - if (oc->number == recno) - { - oc->flag = TRUE; - break; - } - } - } - - continue; /* End of back ref handling */ - } - } - - /* First pass, or a non-duplicated name. */ - - goto HANDLE_REFERENCE; - - - /* ------------------------------------------------------------ */ - case CHAR_R: /* Recursion */ - ptr++; /* Same as (?0) */ - /* Fall through */ - - - /* ------------------------------------------------------------ */ - case CHAR_MINUS: case CHAR_PLUS: /* Recursion or subroutine */ - case CHAR_0: case CHAR_1: case CHAR_2: case CHAR_3: case CHAR_4: - case CHAR_5: case CHAR_6: case CHAR_7: case CHAR_8: case CHAR_9: - { - const pcre_uchar *called; - terminator = CHAR_RIGHT_PARENTHESIS; - - /* Come here from the \g<...> and \g'...' code (Oniguruma - compatibility). However, the syntax has been checked to ensure that - the ... are a (signed) number, so that neither ERR63 nor ERR29 will - be called on this path, nor with the jump to OTHER_CHAR_AFTER_QUERY - ever be taken. */ - - HANDLE_NUMERICAL_RECURSION: - - if ((refsign = *ptr) == CHAR_PLUS) - { - ptr++; - if (!IS_DIGIT(*ptr)) - { - *errorcodeptr = ERR63; - goto FAILED; - } - } - else if (refsign == CHAR_MINUS) - { - if (!IS_DIGIT(ptr[1])) - goto OTHER_CHAR_AFTER_QUERY; - ptr++; - } - - recno = 0; - while(IS_DIGIT(*ptr)) - recno = recno * 10 + *ptr++ - CHAR_0; - - if (*ptr != (pcre_uchar)terminator) - { - *errorcodeptr = ERR29; - goto FAILED; - } - - if (refsign == CHAR_MINUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - else if (refsign == CHAR_PLUS) - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno += cd->bracount; - } - - /* Come here from code above that handles a named recursion */ - - HANDLE_RECURSION: - - previous = code; - called = cd->start_code; - - /* When we are actually compiling, find the bracket that is being - referenced. Temporarily end the regex in case it doesn't exist before - this point. If we end up with a forward reference, first check that - the bracket does occur later so we can give the error (and position) - now. Then remember this forward reference in the workspace so it can - be filled in at the end. */ - - if (lengthptr == NULL) - { - *code = OP_END; - if (recno != 0) - called = PRIV(find_bracket)(cd->start_code, utf, recno); - - /* Forward reference */ - - if (called == NULL) - { - if (recno > cd->final_bracount) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Fudge the value of "called" so that when it is inserted as an - offset below, what it actually inserted is the reference number - of the group. Then remember the forward reference. */ - - called = cd->start_code + recno; - if (cd->hwm >= cd->start_workspace + cd->workspace_size - - WORK_SIZE_SAFETY_MARGIN) - { - *errorcodeptr = expand_workspace(cd); - if (*errorcodeptr != 0) goto FAILED; - } - PUTINC(cd->hwm, 0, (int)(code + 1 - cd->start_code)); - } - - /* If not a forward reference, and the subpattern is still open, - this is a recursive call. We check to see if this is a left - recursion that could loop for ever, and diagnose that case. We - must not, however, do this check if we are in a conditional - subpattern because the condition might be testing for recursion in - a pattern such as /(?(R)a+|(?R)b)/, which is perfectly valid. - Forever loops are also detected at runtime, so those that occur in - conditional subpatterns will be picked up then. */ - - else if (GET(called, 1) == 0 && cond_depth <= 0 && - could_be_empty(called, code, bcptr, utf, cd)) - { - *errorcodeptr = ERR40; - goto FAILED; - } - } - - /* Insert the recursion/subroutine item. It does not have a set first - character (relevant if it is repeated, because it will then be - wrapped with ONCE brackets). */ - - *code = OP_RECURSE; - PUT(code, 1, (int)(called - cd->start_code)); - code += 1 + LINK_SIZE; - groupsetfirstchar = FALSE; - } - - /* Can't determine a first byte now */ - - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - continue; - - - /* ------------------------------------------------------------ */ - default: /* Other characters: check option setting */ - OTHER_CHAR_AFTER_QUERY: - set = unset = 0; - optset = &set; - - while (*ptr != CHAR_RIGHT_PARENTHESIS && *ptr != CHAR_COLON) - { - switch (*ptr++) - { - case CHAR_MINUS: optset = &unset; break; - - case CHAR_J: /* Record that it changed in the external options */ - *optset |= PCRE_DUPNAMES; - cd->external_flags |= PCRE_JCHANGED; - break; - - case CHAR_i: *optset |= PCRE_CASELESS; break; - case CHAR_m: *optset |= PCRE_MULTILINE; break; - case CHAR_s: *optset |= PCRE_DOTALL; break; - case CHAR_x: *optset |= PCRE_EXTENDED; break; - case CHAR_U: *optset |= PCRE_UNGREEDY; break; - case CHAR_X: *optset |= PCRE_EXTRA; break; - - default: *errorcodeptr = ERR12; - ptr--; /* Correct the offset */ - goto FAILED; - } - } - - /* Set up the changed option bits, but don't change anything yet. */ - - newoptions = (options | set) & (~unset); - - /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. If this - item is right at the start of the pattern, the options can be - abstracted and made external in the pre-compile phase, and ignored in - the compile phase. This can be helpful when matching -- for instance in - caseless checking of required bytes. - - If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are - definitely *not* at the start of the pattern because something has been - compiled. In the pre-compile phase, however, the code pointer can have - that value after the start, because it gets reset as code is discarded - during the pre-compile. However, this can happen only at top level - if - we are within parentheses, the starting BRA will still be present. At - any parenthesis level, the length value can be used to test if anything - has been compiled at that level. Thus, a test for both these conditions - is necessary to ensure we correctly detect the start of the pattern in - both phases. - - If we are not at the pattern start, reset the greedy defaults and the - case value for firstchar and reqchar. */ - - if (*ptr == CHAR_RIGHT_PARENTHESIS) - { - if (code == cd->start_code + 1 + LINK_SIZE && - (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) - { - cd->external_options = newoptions; - } - else - { - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((newoptions & PCRE_CASELESS) != 0)? REQ_CASELESS:0; - } - - /* Change options at this level, and pass them back for use - in subsequent branches. */ - - *optionsptr = options = newoptions; - previous = NULL; /* This item can't be repeated */ - continue; /* It is complete */ - } - - /* If the options ended with ':' we are heading into a nested group - with possible change of options. Such groups are non-capturing and are - not assertions of any kind. All we need to do is skip over the ':'; - the newoptions value is handled below. */ - - bravalue = OP_BRA; - ptr++; - } /* End of switch for character following (? */ - } /* End of (? handling */ - - /* Opening parenthesis not followed by '*' or '?'. If PCRE_NO_AUTO_CAPTURE - is set, all unadorned brackets become non-capturing and behave like (?:...) - brackets. */ - - else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) - { - bravalue = OP_BRA; - } - - /* Else we have a capturing group. */ - - else - { - NUMBERED_GROUP: - cd->bracount += 1; - PUT2(code, 1+LINK_SIZE, cd->bracount); - skipbytes = IMM2_SIZE; - } - - /* Process nested bracketed regex. First check for parentheses nested too - deeply. */ - - if ((cd->parens_depth += 1) > PARENS_NEST_LIMIT) - { - *errorcodeptr = ERR82; - goto FAILED; - } - - /* Assertions used not to be repeatable, but this was changed for Perl - compatibility, so all kinds can now be repeated. We copy code into a - non-register variable (tempcode) in order to be able to pass its address - because some compilers complain otherwise. */ - - previous = code; /* For handling repetition */ - *code = bravalue; - tempcode = code; - tempreqvary = cd->req_varyopt; /* Save value before bracket */ - tempbracount = cd->bracount; /* Save value before bracket */ - length_prevgroup = 0; /* Initialize for pre-compile phase */ - - if (!compile_regex( - newoptions, /* The complete new option state */ - &tempcode, /* Where to put code (updated) */ - &ptr, /* Input pointer (updated) */ - errorcodeptr, /* Where to put an error message */ - (bravalue == OP_ASSERTBACK || - bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - reset_bracount, /* True if (?| group */ - skipbytes, /* Skip over bracket number */ - cond_depth + - ((bravalue == OP_COND)?1:0), /* Depth of condition subpatterns */ - &subfirstchar, /* For possible first char */ - &subfirstcharflags, - &subreqchar, /* For possible last char */ - &subreqcharflags, - bcptr, /* Current branch chain */ - cd, /* Tables block */ - (lengthptr == NULL)? NULL : /* Actual compile phase */ - &length_prevgroup /* Pre-compile phase */ - )) - goto FAILED; - - cd->parens_depth -= 1; - - /* If this was an atomic group and there are no capturing groups within it, - generate OP_ONCE_NC instead of OP_ONCE. */ - - if (bravalue == OP_ONCE && cd->bracount <= tempbracount) - *code = OP_ONCE_NC; - - if (bravalue >= OP_ASSERT && bravalue <= OP_ASSERTBACK_NOT) - cd->assert_depth -= 1; - - /* At the end of compiling, code is still pointing to the start of the - group, while tempcode has been updated to point past the end of the group. - The pattern pointer (ptr) is on the bracket. - - If this is a conditional bracket, check that there are no more than - two branches in the group, or just one if it's a DEFINE group. We do this - in the real compile phase, not in the pre-pass, where the whole group may - not be available. */ - - if (bravalue == OP_COND && lengthptr == NULL) - { - pcre_uchar *tc = code; - int condcount = 0; - - do { - condcount++; - tc += GET(tc,1); - } - while (*tc != OP_KET); - - /* A DEFINE group is never obeyed inline (the "condition" is always - false). It must have only one branch. */ - - if (code[LINK_SIZE+1] == OP_DEF) - { - if (condcount > 1) - { - *errorcodeptr = ERR54; - goto FAILED; - } - bravalue = OP_DEF; /* Just a flag to suppress char handling below */ - } - - /* A "normal" conditional group. If there is just one branch, we must not - make use of its firstchar or reqchar, because this is equivalent to an - empty second branch. */ - - else - { - if (condcount > 2) - { - *errorcodeptr = ERR27; - goto FAILED; - } - if (condcount == 1) subfirstcharflags = subreqcharflags = REQ_NONE; - } - } - - /* Error if hit end of pattern */ - - if (*ptr != CHAR_RIGHT_PARENTHESIS) - { - *errorcodeptr = ERR14; - goto FAILED; - } - - /* In the pre-compile phase, update the length by the length of the group, - less the brackets at either end. Then reduce the compiled code to just a - set of non-capturing brackets so that it doesn't use much memory if it is - duplicated by a quantifier.*/ - - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; - code++; /* This already contains bravalue */ - PUTINC(code, 0, 1 + LINK_SIZE); - *code++ = OP_KET; - PUTINC(code, 0, 1 + LINK_SIZE); - break; /* No need to waste time with special character handling */ - } - - /* Otherwise update the main code pointer to the end of the group. */ - - code = tempcode; - - /* For a DEFINE group, required and first character settings are not - relevant. */ - - if (bravalue == OP_DEF) break; - - /* Handle updating of the required and first characters for other types of - group. Update for normal brackets of all kinds, and conditions with two - branches (see code above). If the bracket is followed by a quantifier with - zero repeat, we have to back off. Hence the definition of zeroreqchar and - zerofirstchar outside the main loop so that they can be accessed for the - back off. */ - - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - groupsetfirstchar = FALSE; - - if (bravalue >= OP_ONCE) - { - /* If we have not yet set a firstchar in this branch, take it from the - subpattern, remembering that it was set here so that a repeat of more - than one can replicate it as reqchar if necessary. If the subpattern has - no firstchar, set "none" for the whole branch. In both cases, a zero - repeat forces firstchar to "none". */ - - if (firstcharflags == REQ_UNSET) - { - if (subfirstcharflags >= 0) - { - firstchar = subfirstchar; - firstcharflags = subfirstcharflags; - groupsetfirstchar = TRUE; - } - else firstcharflags = REQ_NONE; - zerofirstcharflags = REQ_NONE; - } - - /* If firstchar was previously set, convert the subpattern's firstchar - into reqchar if there wasn't one, using the vary flag that was in - existence beforehand. */ - - else if (subfirstcharflags >= 0 && subreqcharflags < 0) - { - subreqchar = subfirstchar; - subreqcharflags = subfirstcharflags | tempreqvary; - } - - /* If the subpattern set a required byte (or set a first byte that isn't - really the first byte - see above), set it. */ - - if (subreqcharflags >= 0) - { - reqchar = subreqchar; - reqcharflags = subreqcharflags; - } - } - - /* For a forward assertion, we take the reqchar, if set. This can be - helpful if the pattern that follows the assertion doesn't set a different - char. For example, it's useful for /(?=abcde).+/. We can't set firstchar - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqchar instead - of a firstchar. This is overcome by a scan at the end if there's no - firstchar, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqcharflags >= 0) - { - reqchar = subreqchar; - reqcharflags = subreqcharflags; - } - break; /* End of processing '(' */ - - - /* ===================================================================*/ - /* Handle metasequences introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values in the - default case when PCRE_UCP is not set. For the back references, the values - are negative the reference number. Only back references and those types - that consume a character may be repeated. We can test for values between - ESC_b and ESC_Z for the latter; this may have to change if any new ones are - ever created. */ - - case CHAR_BACKSLASH: - tempptr = ptr; - escape = check_escape(&ptr, &ec, errorcodeptr, cd->bracount, options, FALSE); - if (*errorcodeptr != 0) goto FAILED; - - if (escape == 0) /* The escape coded a single character */ - c = ec; - else - { - if (escape == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == CHAR_BACKSLASH && ptr[2] == CHAR_E) - ptr += 2; /* avoid empty string */ - else inescq = TRUE; - continue; - } - - if (escape == ESC_E) continue; /* Perl ignores an orphan \E */ - - /* For metasequences that actually match a character, we disable the - setting of a first character if it hasn't already been set. */ - - if (firstcharflags == REQ_UNSET && escape > ESC_b && escape < ESC_Z) - firstcharflags = REQ_NONE; - - /* Set values to reset to if this is followed by a zero repeat. */ - - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* \g<name> or \g'name' is a subroutine call by name and \g<n> or \g'n' - is a subroutine call by number (Oniguruma syntax). In fact, the value - ESC_g is returned only for these cases. So we don't need to check for < - or ' if the value is ESC_g. For the Perl syntax \g{n} the value is - -n, and for the Perl syntax \g{name} the result is ESC_k (as - that is a synonym for a named back reference). */ - - if (escape == ESC_g) - { - const pcre_uchar *p; - pcre_uint32 cf; - - save_hwm = cd->hwm; /* Normally this is set when '(' is read */ - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : CHAR_APOSTROPHE; - - /* These two statements stop the compiler for warning about possibly - unset variables caused by the jump to HANDLE_NUMERICAL_RECURSION. In - fact, because we do the check for a number below, the paths that - would actually be in error are never taken. */ - - skipbytes = 0; - reset_bracount = FALSE; - - /* If it's not a signed or unsigned number, treat it as a name. */ - - cf = ptr[1]; - if (cf != CHAR_PLUS && cf != CHAR_MINUS && !IS_DIGIT(cf)) - { - is_recurse = TRUE; - goto NAMED_REF_OR_RECURSE; - } - - /* Signed or unsigned number (cf = ptr[1]) is known to be plus or minus - or a digit. */ - - p = ptr + 2; - while (IS_DIGIT(*p)) p++; - if (*p != (pcre_uchar)terminator) - { - *errorcodeptr = ERR57; - break; - } - ptr++; - goto HANDLE_NUMERICAL_RECURSION; - } - - /* \k<name> or \k'name' is a back reference by name (Perl syntax). - We also support \k{name} (.NET syntax). */ - - if (escape == ESC_k) - { - if ((ptr[1] != CHAR_LESS_THAN_SIGN && - ptr[1] != CHAR_APOSTROPHE && ptr[1] != CHAR_LEFT_CURLY_BRACKET)) - { - *errorcodeptr = ERR69; - break; - } - is_recurse = FALSE; - terminator = (*(++ptr) == CHAR_LESS_THAN_SIGN)? - CHAR_GREATER_THAN_SIGN : (*ptr == CHAR_APOSTROPHE)? - CHAR_APOSTROPHE : CHAR_RIGHT_CURLY_BRACKET; - goto NAMED_REF_OR_RECURSE; - } - - /* Back references are handled specially; must disable firstchar if - not set to cope with cases like (?=(\w+))\1: which would otherwise set - ':' later. */ - - if (escape < 0) - { - open_capitem *oc; - recno = -escape; - - /* Come here from named backref handling when the reference is to a - single group (i.e. not to a duplicated name. */ - - HANDLE_REFERENCE: - if (firstcharflags == REQ_UNSET) firstcharflags = REQ_NONE; - previous = code; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_REFI : OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - - /* Check to see if this back reference is recursive, that it, it - is inside the group that it references. A flag is set so that the - group can be made atomic. */ - - for (oc = cd->open_caps; oc != NULL; oc = oc->next) - { - if (oc->number == recno) - { - oc->flag = TRUE; - break; - } - } - } - - /* So are Unicode property matches, if supported. */ - -#ifdef SUPPORT_UCP - else if (escape == ESC_P || escape == ESC_p) - { - BOOL negated; - unsigned int ptype = 0, pdata = 0; - if (!get_ucp(&ptr, &negated, &ptype, &pdata, errorcodeptr)) - goto FAILED; - previous = code; - *code++ = ((escape == ESC_p) != negated)? OP_PROP : OP_NOTPROP; - *code++ = ptype; - *code++ = pdata; - } -#else - - /* If Unicode properties are not supported, \X, \P, and \p are not - allowed. */ - - else if (escape == ESC_X || escape == ESC_P || escape == ESC_p) - { - *errorcodeptr = ERR45; - goto FAILED; - } -#endif - - /* For the rest (including \X when Unicode properties are supported), we - can obtain the OP value by negating the escape value in the default - situation when PCRE_UCP is not set. When it *is* set, we substitute - Unicode property tests. Note that \b and \B do a one-character - lookbehind, and \A also behaves as if it does. */ - - else - { - if ((escape == ESC_b || escape == ESC_B || escape == ESC_A) && - cd->max_lookbehind == 0) - cd->max_lookbehind = 1; -#ifdef SUPPORT_UCP - if (escape >= ESC_DU && escape <= ESC_wu) - { - nestptr = ptr + 1; /* Where to resume */ - ptr = substitutes[escape - ESC_DU] - 1; /* Just before substitute */ - } - else -#endif - /* In non-UTF-8 mode, we turn \C into OP_ALLANY instead of OP_ANYBYTE - so that it works in DFA mode and in lookbehinds. */ - - { - previous = (escape > ESC_b && escape < ESC_Z)? code : NULL; - *code++ = (!utf && escape == ESC_C)? OP_ALLANY : escape; - } - } - continue; - } - - /* We have a data character whose value is in c. In UTF-8 mode it may have - a value > 127. We set its representation in the length/buffer, and then - handle it as a data character. */ - -#if defined SUPPORT_UTF && !defined COMPILE_PCRE32 - if (utf && c > MAX_VALUE_FOR_SINGLE_CHAR) - mclength = PRIV(ord2utf)(c, mcbuffer); - else -#endif - - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - - - /* ===================================================================*/ - /* Handle a literal character. It is guaranteed not to be whitespace or # - when the extended flag is set. If we are in a UTF mode, it may be a - multi-unit literal character. */ - - default: - NORMAL_CHAR: - mclength = 1; - mcbuffer[0] = c; - -#ifdef SUPPORT_UTF - if (utf && HAS_EXTRALEN(c)) - ACROSSCHAR(TRUE, ptr[1], mcbuffer[mclength++] = *(++ptr)); -#endif - - /* At this point we have the character's bytes in mcbuffer, and the length - in mclength. When not in UTF-8 mode, the length is always 1. */ - - ONE_CHAR: - previous = code; - - /* For caseless UTF-8 mode when UCP support is available, check whether - this character has more than one other case. If so, generate a special - OP_PROP item instead of OP_CHARI. */ - -#ifdef SUPPORT_UCP - if (utf && (options & PCRE_CASELESS) != 0) - { - GETCHAR(c, mcbuffer); - if ((c = UCD_CASESET(c)) != 0) - { - *code++ = OP_PROP; - *code++ = PT_CLIST; - *code++ = c; - if (firstcharflags == REQ_UNSET) - firstcharflags = zerofirstcharflags = REQ_NONE; - break; - } - } -#endif - - /* Caseful matches, or not one of the multicase characters. */ - - *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARI : OP_CHAR; - for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; - - /* Remember if \r or \n were seen */ - - if (mcbuffer[0] == CHAR_CR || mcbuffer[0] == CHAR_NL) - cd->external_flags |= PCRE_HASCRORLF; - - /* Set the first and required bytes appropriately. If no previous first - byte, set it from this character, but revert to none on a zero repeat. - Otherwise, leave the firstchar value alone, and don't change it on a zero - repeat. */ - - if (firstcharflags == REQ_UNSET) - { - zerofirstcharflags = REQ_NONE; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - - /* If the character is more than one byte long, we can set firstchar - only if it is not to be matched caselessly. */ - - if (mclength == 1 || req_caseopt == 0) - { - firstchar = mcbuffer[0] | req_caseopt; - firstchar = mcbuffer[0]; - firstcharflags = req_caseopt; - - if (mclength != 1) - { - reqchar = code[-1]; - reqcharflags = cd->req_varyopt; - } - } - else firstcharflags = reqcharflags = REQ_NONE; - } - - /* firstchar was previously set; we can set reqchar only if the length is - 1 or the matching is caseful. */ - - else - { - zerofirstchar = firstchar; - zerofirstcharflags = firstcharflags; - zeroreqchar = reqchar; - zeroreqcharflags = reqcharflags; - if (mclength == 1 || req_caseopt == 0) - { - reqchar = code[-1]; - reqcharflags = req_caseopt | cd->req_varyopt; - } - } - - break; /* End of literal character handling */ - } - } /* end of big loop */ - - -/* Control never reaches here by falling through, only by a goto for all the -error states. Pass back the position in the pattern so that it can be displayed -to the user for diagnosing the error. */ - -FAILED: -*ptrptr = ptr; -return FALSE; -} - - - -/************************************************* -* Compile sequence of alternatives * -*************************************************/ - -/* On entry, ptr is pointing past the bracket character, but on return it -points to the closing bracket, or vertical bar, or end of string. The code -variable is pointing at the byte into which the BRA operator has been stored. -This function is used during the pre-compile phase when we are trying to find -out the amount of memory needed, as well as during the real compile phase. The -value of lengthptr distinguishes the two phases. - -Arguments: - options option bits, including any changes for this subpattern - codeptr -> the address of the current code pointer - ptrptr -> the address of the current pattern pointer - errorcodeptr -> pointer to error code variable - lookbehind TRUE if this is a lookbehind assertion - reset_bracount TRUE to reset the count for each branch - skipbytes skip this many bytes at start (for brackets and OP_COND) - cond_depth depth of nesting for conditional subpatterns - firstcharptr place to put the first required character - firstcharflagsptr place to put the first character flags, or a negative number - reqcharptr place to put the last required character - reqcharflagsptr place to put the last required character flags, or a negative number - bcptr pointer to the chain of currently open branches - cd points to the data block with tables pointers etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, pcre_uchar **codeptr, const pcre_uchar **ptrptr, - int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, - int cond_depth, - pcre_uint32 *firstcharptr, pcre_int32 *firstcharflagsptr, - pcre_uint32 *reqcharptr, pcre_int32 *reqcharflagsptr, - branch_chain *bcptr, compile_data *cd, int *lengthptr) -{ -const pcre_uchar *ptr = *ptrptr; -pcre_uchar *code = *codeptr; -pcre_uchar *last_branch = code; -pcre_uchar *start_bracket = code; -pcre_uchar *reverse_count = NULL; -open_capitem capitem; -int capnumber = 0; -pcre_uint32 firstchar, reqchar; -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 branchfirstchar, branchreqchar; -pcre_int32 branchfirstcharflags, branchreqcharflags; -int length; -unsigned int orig_bracount; -unsigned int max_bracount; -branch_chain bc; - -/* If set, call the external function that checks for stack availability. */ - -if (PUBL(stack_guard) != NULL && PUBL(stack_guard)()) - { - *errorcodeptr= ERR85; - return FALSE; - } - -/* Miscellaneous initialization */ - -bc.outer = bcptr; -bc.current_branch = code; - -firstchar = reqchar = 0; -firstcharflags = reqcharflags = REQ_UNSET; - -/* Accumulate the length for use in the pre-compile phase. Start with the -length of the BRA and KET and any extra bytes that are required at the -beginning. We accumulate in a local variable to save frequent testing of -lenthptr for NULL. We cannot do this by looking at the value of code at the -start and end of each alternative, because compiled items are discarded during -the pre-compile phase so that the work space is not exceeded. */ - -length = 2 + 2*LINK_SIZE + skipbytes; - -/* WARNING: If the above line is changed for any reason, you must also change -the code that abstracts option settings at the start of the pattern and makes -them global. It tests the value of length for (2 + 2*LINK_SIZE) in the -pre-compile phase to find out whether anything has yet been compiled or not. */ - -/* If this is a capturing subpattern, add to the chain of open capturing items -so that we can detect them if (*ACCEPT) is encountered. This is also used to -detect groups that contain recursive back references to themselves. Note that -only OP_CBRA need be tested here; changing this opcode to one of its variants, -e.g. OP_SCBRAPOS, happens later, after the group has been compiled. */ - -if (*code == OP_CBRA) - { - capnumber = GET2(code, 1 + LINK_SIZE); - capitem.number = capnumber; - capitem.next = cd->open_caps; - capitem.flag = FALSE; - cd->open_caps = &capitem; - } - -/* Offset is set zero to mark that this bracket is still open */ - -PUT(code, 1, 0); -code += 1 + LINK_SIZE + skipbytes; - -/* Loop for each alternative branch */ - -orig_bracount = max_bracount = cd->bracount; -for (;;) - { - /* For a (?| group, reset the capturing bracket count so that each branch - uses the same numbers. */ - - if (reset_bracount) cd->bracount = orig_bracount; - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - PUTINC(code, 0, 0); - length += 1 + LINK_SIZE; - } - - /* Now compile the branch; in the pre-compile phase its length gets added - into the length. */ - - if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstchar, - &branchfirstcharflags, &branchreqchar, &branchreqcharflags, &bc, - cond_depth, cd, (lengthptr == NULL)? NULL : &length)) - { - *ptrptr = ptr; - return FALSE; - } - - /* Keep the highest bracket count in case (?| was used and some branch - has fewer than the rest. */ - - if (cd->bracount > max_bracount) max_bracount = cd->bracount; - - /* In the real compile phase, there is some post-processing to be done. */ - - if (lengthptr == NULL) - { - /* If this is the first branch, the firstchar and reqchar values for the - branch become the values for the regex. */ - - if (*last_branch != OP_ALT) - { - firstchar = branchfirstchar; - firstcharflags = branchfirstcharflags; - reqchar = branchreqchar; - reqcharflags = branchreqcharflags; - } - - /* If this is not the first branch, the first char and reqchar have to - match the values from all the previous branches, except that if the - previous value for reqchar didn't have REQ_VARY set, it can still match, - and we set REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstchar, but it doesn't match the new branch, - we have to abandon the firstchar for the regex, but if there was - previously no reqchar, it takes on the value of the old firstchar. */ - - if (firstcharflags >= 0 && - (firstcharflags != branchfirstcharflags || firstchar != branchfirstchar)) - { - if (reqcharflags < 0) - { - reqchar = firstchar; - reqcharflags = firstcharflags; - } - firstcharflags = REQ_NONE; - } - - /* If we (now or from before) have no firstchar, a firstchar from the - branch becomes a reqchar if there isn't a branch reqchar. */ - - if (firstcharflags < 0 && branchfirstcharflags >= 0 && branchreqcharflags < 0) - { - branchreqchar = branchfirstchar; - branchreqcharflags = branchfirstcharflags; - } - - /* Now ensure that the reqchars match */ - - if (((reqcharflags & ~REQ_VARY) != (branchreqcharflags & ~REQ_VARY)) || - reqchar != branchreqchar) - reqcharflags = REQ_NONE; - else - { - reqchar = branchreqchar; - reqcharflags |= branchreqcharflags; /* To "or" REQ_VARY */ - } - } - - /* If lookbehind, check that this branch matches a fixed-length string, and - put the length into the OP_REVERSE item. Temporarily mark the end of the - branch with OP_END. If the branch contains OP_RECURSE, the result is -3 - because there may be forward references that we can't check here. Set a - flag to cause another lookbehind check at the end. Why not do it all at the - end? Because common, erroneous checks are picked up here and the offset of - the problem can be shown. */ - - if (lookbehind) - { - int fixed_length; - *code = OP_END; - fixed_length = find_fixedlength(last_branch, (options & PCRE_UTF8) != 0, - FALSE, cd); - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length == -3) - { - cd->check_lookbehind = TRUE; - } - else if (fixed_length < 0) - { - *errorcodeptr = (fixed_length == -2)? ERR36 : - (fixed_length == -4)? ERR70: ERR25; - *ptrptr = ptr; - return FALSE; - } - else - { - if (fixed_length > cd->max_lookbehind) - cd->max_lookbehind = fixed_length; - PUT(reverse_count, 0, fixed_length); - } - } - } - - /* Reached end of expression, either ')' or end of pattern. In the real - compile phase, go back through the alternative branches and reverse the chain - of offsets, with the field in the BRA item now becoming an offset to the - first alternative. If there are no alternatives, it points to the end of the - group. The length in the terminating ket is always the length of the whole - bracketed item. Return leaving the pointer at the terminating char. */ - - if (*ptr != CHAR_VERTICAL_LINE) - { - if (lengthptr == NULL) - { - int branch_length = (int)(code - last_branch); - do - { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, branch_length); - branch_length = prev_length; - last_branch -= branch_length; - } - while (branch_length > 0); - } - - /* Fill in the ket */ - - *code = OP_KET; - PUT(code, 1, (int)(code - start_bracket)); - code += 1 + LINK_SIZE; - - /* If it was a capturing subpattern, check to see if it contained any - recursive back references. If so, we must wrap it in atomic brackets. - In any event, remove the block from the chain. */ - - if (capnumber > 0) - { - if (cd->open_caps->flag) - { - memmove(start_bracket + 1 + LINK_SIZE, start_bracket, - IN_UCHARS(code - start_bracket)); - *start_bracket = OP_ONCE; - code += 1 + LINK_SIZE; - PUT(start_bracket, 1, (int)(code - start_bracket)); - *code = OP_KET; - PUT(code, 1, (int)(code - start_bracket)); - code += 1 + LINK_SIZE; - length += 2 + 2*LINK_SIZE; - } - cd->open_caps = cd->open_caps->next; - } - - /* Retain the highest bracket number, in case resetting was used. */ - - cd->bracount = max_bracount; - - /* Set values to pass back */ - - *codeptr = code; - *ptrptr = ptr; - *firstcharptr = firstchar; - *firstcharflagsptr = firstcharflags; - *reqcharptr = reqchar; - *reqcharflagsptr = reqcharflags; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length) - { - *errorcodeptr = ERR20; - return FALSE; - } - *lengthptr += length; - } - return TRUE; - } - - /* Another branch follows. In the pre-compile phase, we can move the code - pointer back to where it was for the start of the first branch. (That is, - pretend that each branch is the only one.) - - In the real compile phase, insert an ALT node. Its length field points back - to the previous branch while the bracket remains open. At the end the chain - is reversed. It's done like this so that the start of the bracket has a - zero offset until it is closed, making it possible to detect recursion. */ - - if (lengthptr != NULL) - { - code = *codeptr + 1 + LINK_SIZE + skipbytes; - length += 1 + LINK_SIZE; - } - else - { - *code = OP_ALT; - PUT(code, 1, (int)(code - last_branch)); - bc.current_branch = last_branch = code; - code += 1 + LINK_SIZE; - } - - ptr++; - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Check for anchored expression * -*************************************************/ - -/* Try to find out if this is an anchored regular expression. Consider each -alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket -all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then -it's anchored. However, if this is a multiline pattern, then only OP_SOD will -be found, because ^ generates OP_CIRCM in that mode. - -We can also consider a regex to be anchored if OP_SOM starts all its branches. -This is the code for \G, which means "match at start of match position, taking -into account the match offset". - -A branch is also implicitly anchored if it starts with .* and DOTALL is set, -because that will try the rest of the pattern at all possible matching points, -so there is no point trying again.... er .... - -.... except when the .* appears inside capturing parentheses, and there is a -subsequent back reference to those parentheses. We haven't enough information -to catch that case precisely. - -At first, the best we could do was to detect when .* was in capturing brackets -and the highest back reference was greater than or equal to that level. -However, by keeping a bitmap of the first 31 back references, we can catch some -of the more common cases more precisely. - -... A second exception is when the .* appears inside an atomic group, because -this prevents the number of characters it matches from being adjusted. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - cd points to the compile data block - atomcount atomic group level - -Returns: TRUE or FALSE -*/ - -static BOOL -is_anchored(register const pcre_uchar *code, unsigned int bracket_map, - compile_data *cd, int atomcount) -{ -do { - const pcre_uchar *scode = first_significant_code( - code + PRIV(OP_lengths)[*code], FALSE); - register int op = *scode; - - /* Non-capturing brackets */ - - if (op == OP_BRA || op == OP_BRAPOS || - op == OP_SBRA || op == OP_SBRAPOS) - { - if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA || op == OP_CBRAPOS || - op == OP_SCBRA || op == OP_SCBRAPOS) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_anchored(scode, new_map, cd, atomcount)) return FALSE; - } - - /* Positive forward assertions and conditions */ - - else if (op == OP_ASSERT || op == OP_COND) - { - if (!is_anchored(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Atomic groups */ - - else if (op == OP_ONCE || op == OP_ONCE_NC) - { - if (!is_anchored(scode, bracket_map, cd, atomcount + 1)) - return FALSE; - } - - /* .* is not anchored unless DOTALL is set (which generates OP_ALLANY) and - it isn't in brackets that are or may be referenced or inside an atomic - group. */ - - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || - op == OP_TYPEPOSSTAR)) - { - if (scode[1] != OP_ALLANY || (bracket_map & cd->backref_map) != 0 || - atomcount > 0 || cd->had_pruneorskip) - return FALSE; - } - - /* Check for explicit anchoring */ - - else if (op != OP_SOD && op != OP_SOM && op != OP_CIRC) return FALSE; - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for starting with ^ or .* * -*************************************************/ - -/* This is called to find out if every branch starts with ^ or .* so that -"first char" processing can be done to speed things up in multiline -matching and for non-DOTALL patterns that start with .* (which must start at -the beginning or after \n). As in the case of is_anchored() (see above), we -have to take account of back references to capturing brackets that contain .* -because in that case we can't make the assumption. Also, the appearance of .* -inside atomic brackets or in a pattern that contains *PRUNE or *SKIP does not -count, because once again the assumption no longer holds. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - cd points to the compile data - atomcount atomic group level - -Returns: TRUE or FALSE -*/ - -static BOOL -is_startline(const pcre_uchar *code, unsigned int bracket_map, - compile_data *cd, int atomcount) -{ -do { - const pcre_uchar *scode = first_significant_code( - code + PRIV(OP_lengths)[*code], FALSE); - register int op = *scode; - - /* If we are at the start of a conditional assertion group, *both* the - conditional assertion *and* what follows the condition must satisfy the test - for start of line. Other kinds of condition fail. Note that there may be an - auto-callout at the start of a condition. */ - - if (op == OP_COND) - { - scode += 1 + LINK_SIZE; - if (*scode == OP_CALLOUT) scode += PRIV(OP_lengths)[OP_CALLOUT]; - switch (*scode) - { - case OP_CREF: - case OP_DNCREF: - case OP_RREF: - case OP_DNRREF: - case OP_DEF: - return FALSE; - - default: /* Assertion */ - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - do scode += GET(scode, 1); while (*scode == OP_ALT); - scode += 1 + LINK_SIZE; - break; - } - scode = first_significant_code(scode, FALSE); - op = *scode; - } - - /* Non-capturing brackets */ - - if (op == OP_BRA || op == OP_BRAPOS || - op == OP_SBRA || op == OP_SBRAPOS) - { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA || op == OP_CBRAPOS || - op == OP_SCBRA || op == OP_SCBRAPOS) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_startline(scode, new_map, cd, atomcount)) return FALSE; - } - - /* Positive forward assertions */ - - else if (op == OP_ASSERT) - { - if (!is_startline(scode, bracket_map, cd, atomcount)) return FALSE; - } - - /* Atomic brackets */ - - else if (op == OP_ONCE || op == OP_ONCE_NC) - { - if (!is_startline(scode, bracket_map, cd, atomcount + 1)) return FALSE; - } - - /* .* means "start at start or after \n" if it isn't in atomic brackets or - brackets that may be referenced, as long as the pattern does not contain - *PRUNE or *SKIP, because these break the feature. Consider, for example, - /.*?a(*PRUNE)b/ with the subject "aab", which matches "ab", i.e. not at the - start of a line. */ - - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) - { - if (scode[1] != OP_ANY || (bracket_map & cd->backref_map) != 0 || - atomcount > 0 || cd->had_pruneorskip) - return FALSE; - } - - /* Check for explicit circumflex; anything else gives a FALSE result. Note - in particular that this includes atomic brackets OP_ONCE and OP_ONCE_NC - because the number of characters matched by .* cannot be adjusted inside - them. */ - - else if (op != OP_CIRC && op != OP_CIRCM) return FALSE; - - /* Move on to the next alternative */ - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for asserted fixed first char * -*************************************************/ - -/* During compilation, the "first char" settings from forward assertions are -discarded, because they can cause conflicts with actual literals that follow. -However, if we end up without a first char setting for an unanchored pattern, -it is worth scanning the regex to see if there is an initial asserted first -char. If all branches start with the same asserted char, or with a -non-conditional bracket all of whose alternatives start with the same asserted -char (recurse ad lib), then we return that char, with the flags set to zero or -REQ_CASELESS; otherwise return zero with REQ_NONE in the flags. - -Arguments: - code points to start of expression (the bracket) - flags points to the first char flags, or to REQ_NONE - inassert TRUE if in an assertion - -Returns: the fixed first char, or 0 with REQ_NONE in flags -*/ - -static pcre_uint32 -find_firstassertedchar(const pcre_uchar *code, pcre_int32 *flags, - BOOL inassert) -{ -register pcre_uint32 c = 0; -int cflags = REQ_NONE; - -*flags = REQ_NONE; -do { - pcre_uint32 d; - int dflags; - int xl = (*code == OP_CBRA || *code == OP_SCBRA || - *code == OP_CBRAPOS || *code == OP_SCBRAPOS)? IMM2_SIZE:0; - const pcre_uchar *scode = first_significant_code(code + 1+LINK_SIZE + xl, - TRUE); - register pcre_uchar op = *scode; - - switch(op) - { - default: - return 0; - - case OP_BRA: - case OP_BRAPOS: - case OP_CBRA: - case OP_SCBRA: - case OP_CBRAPOS: - case OP_SCBRAPOS: - case OP_ASSERT: - case OP_ONCE: - case OP_ONCE_NC: - d = find_firstassertedchar(scode, &dflags, op == OP_ASSERT); - if (dflags < 0) - return 0; - if (cflags < 0) { c = d; cflags = dflags; } else if (c != d || cflags != dflags) return 0; - break; - - case OP_EXACT: - scode += IMM2_SIZE; - /* Fall through */ - - case OP_CHAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - if (!inassert) return 0; - if (cflags < 0) { c = scode[1]; cflags = 0; } - else if (c != scode[1]) return 0; - break; - - case OP_EXACTI: - scode += IMM2_SIZE; - /* Fall through */ - - case OP_CHARI: - case OP_PLUSI: - case OP_MINPLUSI: - case OP_POSPLUSI: - if (!inassert) return 0; - if (cflags < 0) { c = scode[1]; cflags = REQ_CASELESS; } - else if (c != scode[1]) return 0; - break; - } - - code += GET(code, 1); - } -while (*code == OP_ALT); - -*flags = cflags; -return c; -} - - - -/************************************************* -* Add an entry to the name/number table * -*************************************************/ - -/* This function is called between compiling passes to add an entry to the -name/number table, maintaining alphabetical order. Checking for permitted -and forbidden duplicates has already been done. - -Arguments: - cd the compile data block - name the name to add - length the length of the name - groupno the group number - -Returns: nothing -*/ - -static void -add_name(compile_data *cd, const pcre_uchar *name, int length, - unsigned int groupno) -{ -int i; -pcre_uchar *slot = cd->name_table; - -for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+IMM2_SIZE, IN_UCHARS(length)); - if (crc == 0 && slot[IMM2_SIZE+length] != 0) - crc = -1; /* Current name is a substring */ - - /* Make space in the table and break the loop for an earlier name. For a - duplicate or later name, carry on. We do this for duplicates so that in the - simple case (when ?(| is not used) they are in order of their numbers. In all - cases they are in the order in which they appear in the pattern. */ - - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - IN_UCHARS((cd->names_found - i) * cd->name_entry_size)); - break; - } - - /* Continue the loop for a later or duplicate name */ - - slot += cd->name_entry_size; - } - -PUT2(slot, 0, groupno); -memcpy(slot + IMM2_SIZE, name, IN_UCHARS(length)); -slot[IMM2_SIZE + length] = 0; -cd->names_found++; -} - - - -/************************************************* -* Compile a Regular Expression * -*************************************************/ - -/* This function takes a string and returns a pointer to a block of store -holding a compiled version of the expression. The original API for this -function had no error code return variable; it is retained for backwards -compatibility. The new function is given a new name. - -Arguments: - pattern the regular expression - options various option bits - errorcodeptr pointer to error code variable (pcre_compile2() only) - can be NULL if you don't want a code value - errorptr pointer to pointer to error text - erroroffset ptr offset in pattern where error was detected - tables pointer to character tables or NULL - -Returns: pointer to compiled data block, or NULL on error, - with errorptr and erroroffset set -*/ - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION -pcre16_compile(PCRE_SPTR16 pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION -pcre32_compile(PCRE_SPTR32 pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -#endif -{ -#if defined COMPILE_PCRE8 -return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#elif defined COMPILE_PCRE16 -return pcre16_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#elif defined COMPILE_PCRE32 -return pcre32_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -#endif -} - - -#if defined COMPILE_PCRE8 -PCRE_EXP_DEFN pcre * PCRE_CALL_CONVENTION -pcre_compile2(const char *pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE16 -PCRE_EXP_DEFN pcre16 * PCRE_CALL_CONVENTION -pcre16_compile2(PCRE_SPTR16 pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#elif defined COMPILE_PCRE32 -PCRE_EXP_DEFN pcre32 * PCRE_CALL_CONVENTION -pcre32_compile2(PCRE_SPTR32 pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -#endif -{ -REAL_PCRE *re; -int length = 1; /* For final END opcode */ -pcre_int32 firstcharflags, reqcharflags; -pcre_uint32 firstchar, reqchar; -pcre_uint32 limit_match = PCRE_UINT32_MAX; -pcre_uint32 limit_recursion = PCRE_UINT32_MAX; -int newline; -int errorcode = 0; -int skipatstart = 0; -BOOL utf; -BOOL never_utf = FALSE; -size_t size; -pcre_uchar *code; -const pcre_uchar *codestart; -const pcre_uchar *ptr; -compile_data compile_block; -compile_data *cd = &compile_block; - -/* This space is used for "compiling" into during the first phase, when we are -computing the amount of memory that is needed. Compiled items are thrown away -as soon as possible, so that a fairly large buffer should be sufficient for -this purpose. The same space is used in the second phase for remembering where -to fill in forward references to subpatterns. That may overflow, in which case -new memory is obtained from malloc(). */ - -pcre_uchar cworkspace[COMPILE_WORK_SIZE]; - -/* This vector is used for remembering name groups during the pre-compile. In a -similar way to cworkspace, it can be expanded using malloc() if necessary. */ - -named_group named_groups[NAMED_GROUP_LIST_SIZE]; - -/* Set this early so that early errors get offset 0. */ - -ptr = (const pcre_uchar *)pattern; - -/* We can't pass back an error message if errorptr is NULL; I guess the best we -can do is just return NULL, but we can set a code value if there is a code -pointer. */ - -if (errorptr == NULL) - { - if (errorcodeptr != NULL) *errorcodeptr = 99; - return NULL; - } - -*errorptr = NULL; -if (errorcodeptr != NULL) *errorcodeptr = ERR0; - -/* However, we can give a message for this error */ - -if (erroroffset == NULL) - { - errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN2; - } - -*erroroffset = 0; - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = PRIV(default_tables); -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Check that all undefined public option bits are zero */ - -if ((options & ~PUBLIC_COMPILE_OPTIONS) != 0) - { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* If PCRE_NEVER_UTF is set, remember it. */ - -if ((options & PCRE_NEVER_UTF) != 0) never_utf = TRUE; - -/* Check for global one-time settings at the start of the pattern, and remember -the offset for later. */ - -cd->external_flags = 0; /* Initialize here for LIMIT_MATCH/RECURSION */ - -while (ptr[skipatstart] == CHAR_LEFT_PARENTHESIS && - ptr[skipatstart+1] == CHAR_ASTERISK) - { - int newnl = 0; - int newbsr = 0; - -/* For completeness and backward compatibility, (*UTFn) is supported in the -relevant libraries, but (*UTF) is generic and always supported. Note that -PCRE_UTF8 == PCRE_UTF16 == PCRE_UTF32. */ - -#ifdef COMPILE_PCRE8 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF8_RIGHTPAR, 5) == 0) - { skipatstart += 7; options |= PCRE_UTF8; continue; } -#endif -#ifdef COMPILE_PCRE16 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF16_RIGHTPAR, 6) == 0) - { skipatstart += 8; options |= PCRE_UTF16; continue; } -#endif -#ifdef COMPILE_PCRE32 - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF32_RIGHTPAR, 6) == 0) - { skipatstart += 8; options |= PCRE_UTF32; continue; } -#endif - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UTF_RIGHTPAR, 4) == 0) - { skipatstart += 6; options |= PCRE_UTF8; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_UCP_RIGHTPAR, 4) == 0) - { skipatstart += 6; options |= PCRE_UCP; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_AUTO_POSSESS_RIGHTPAR, 16) == 0) - { skipatstart += 18; options |= PCRE_NO_AUTO_POSSESS; continue; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_NO_START_OPT_RIGHTPAR, 13) == 0) - { skipatstart += 15; options |= PCRE_NO_START_OPTIMIZE; continue; } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_MATCH_EQ, 12) == 0) - { - pcre_uint32 c = 0; - int p = skipatstart + 14; - while (isdigit(ptr[p])) - { - if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow */ - c = c*10 + ptr[p++] - CHAR_0; - } - if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; - if (c < limit_match) - { - limit_match = c; - cd->external_flags |= PCRE_MLSET; - } - skipatstart = p; - continue; - } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LIMIT_RECURSION_EQ, 16) == 0) - { - pcre_uint32 c = 0; - int p = skipatstart + 18; - while (isdigit(ptr[p])) - { - if (c > PCRE_UINT32_MAX / 10 - 1) break; /* Integer overflow check */ - c = c*10 + ptr[p++] - CHAR_0; - } - if (ptr[p++] != CHAR_RIGHT_PARENTHESIS) break; - if (c < limit_recursion) - { - limit_recursion = c; - cd->external_flags |= PCRE_RLSET; - } - skipatstart = p; - continue; - } - - if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CR_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_LF_RIGHTPAR, 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_CRLF_RIGHTPAR, 5) == 0) - { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANY_RIGHTPAR, 4) == 0) - { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_ANYCRLF_RIGHTPAR, 8) == 0) - { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } - - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_ANYCRLF_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } - else if (STRNCMP_UC_C8(ptr+skipatstart+2, STRING_BSR_UNICODE_RIGHTPAR, 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } - - if (newnl != 0) - options = (options & ~PCRE_NEWLINE_BITS) | newnl; - else if (newbsr != 0) - options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; - else break; - } - -/* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ -utf = (options & PCRE_UTF8) != 0; -if (utf && never_utf) - { - errorcode = ERR78; - goto PCRE_EARLY_ERROR_RETURN2; - } - -/* Can't support UTF unless PCRE has been compiled to include the code. The -return of an error code from PRIV(valid_utf)() is a new feature, introduced in -release 8.13. It is passed back from pcre_[dfa_]exec(), but at the moment is -not used here. */ - -#ifdef SUPPORT_UTF -if (utf && (options & PCRE_NO_UTF8_CHECK) == 0 && - (errorcode = PRIV(valid_utf)((PCRE_PUCHAR)pattern, -1, erroroffset)) != 0) - { -#if defined COMPILE_PCRE8 - errorcode = ERR44; -#elif defined COMPILE_PCRE16 - errorcode = ERR74; -#elif defined COMPILE_PCRE32 - errorcode = ERR77; -#endif - goto PCRE_EARLY_ERROR_RETURN2; - } -#else -if (utf) - { - errorcode = ERR32; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -/* Can't support UCP unless PCRE has been compiled to include the code. */ - -#ifndef SUPPORT_UCP -if ((options & PCRE_UCP) != 0) - { - errorcode = ERR67; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -/* Check validity of \R options. */ - -if ((options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) == - (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - errorcode = ERR56; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Handle different types of newline. The three bits give seven cases. The -current code allows for fixed one- or two-byte sequences, plus "any" and -"anycrlf". */ - -switch (options & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Build-time default */ - case PCRE_NEWLINE_CR: newline = CHAR_CR; break; - case PCRE_NEWLINE_LF: newline = CHAR_NL; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = (CHAR_CR << 8) | CHAR_NL; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -if (newline == -2) - { - cd->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - cd->nltype = NLTYPE_ANY; - } -else - { - cd->nltype = NLTYPE_FIXED; - if (newline > 255) - { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; - } - else - { - cd->nllen = 1; - cd->nl[0] = newline; - } - } - -/* Maximum back reference and backref bitmap. The bitmap records up to 31 back -references to help in deciding whether (.*) can be treated as anchored or not. -*/ - -cd->top_backref = 0; -cd->backref_map = 0; - -/* Reflect pattern for debugging output */ - -DPRINTF(("------------------------------------------------------------------\n")); -#ifdef PCRE_DEBUG -print_puchar(stdout, (PCRE_PUCHAR)pattern); -#endif -DPRINTF(("\n")); - -/* Pretend to compile the pattern while actually just accumulating the length -of memory required. This behaviour is triggered by passing a non-NULL final -argument to compile_regex(). We pass a block of workspace (cworkspace) for it -to compile parts of the pattern into; the compiled code is discarded when it is -no longer needed, so hopefully this workspace will never overflow, though there -is a test for its doing so. */ - -cd->bracount = cd->final_bracount = 0; -cd->names_found = 0; -cd->name_entry_size = 0; -cd->name_table = NULL; -cd->dupnames = FALSE; -cd->namedrefcount = 0; -cd->start_code = cworkspace; -cd->hwm = cworkspace; -cd->start_workspace = cworkspace; -cd->workspace_size = COMPILE_WORK_SIZE; -cd->named_groups = named_groups; -cd->named_group_list_size = NAMED_GROUP_LIST_SIZE; -cd->start_pattern = (const pcre_uchar *)pattern; -cd->end_pattern = (const pcre_uchar *)(pattern + STRLEN_UC((const pcre_uchar *)pattern)); -cd->req_varyopt = 0; -cd->parens_depth = 0; -cd->assert_depth = 0; -cd->max_lookbehind = 0; -cd->external_options = options; -cd->open_caps = NULL; - -/* Now do the pre-compile. On error, errorcode will be set non-zero, so we -don't need to look at the result of the function here. The initial options have -been put into the cd block so that they can be changed if an option setting is -found within the regex right at the beginning. Bringing initial option settings -outside can help speed up starting point checks. */ - -ptr += skipatstart; -code = cworkspace; -*code = OP_BRA; - -(void)compile_regex(cd->external_options, &code, &ptr, &errorcode, FALSE, - FALSE, 0, 0, &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, - cd, &length); -if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; - -DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, - (int)(cd->hwm - cworkspace))); - -if (length > MAX_PATTERN_SIZE) - { - errorcode = ERR20; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* If there are groups with duplicate names and there are also references by -name, we must allow for the possibility of named references to duplicated -groups. These require an extra data item each. */ - -if (cd->dupnames && cd->namedrefcount > 0) - length += cd->namedrefcount * IMM2_SIZE * sizeof(pcre_uchar); - -/* Compute the size of the data block for storing the compiled pattern. Integer -overflow should no longer be possible because nowadays we limit the maximum -value of cd->names_found and cd->name_entry_size. */ - -size = sizeof(REAL_PCRE) + - (length + cd->names_found * cd->name_entry_size) * sizeof(pcre_uchar); - -/* Get the memory. */ - -re = (REAL_PCRE *)(PUBL(malloc))(size); -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, initial options, internal -flags, and character table pointer. NULL is used for the default character -tables. The nullpad field is at the end; it's there to help in the case when a -regex compiled on a system with 4-byte pointers is run on another with 8-byte -pointers. */ - -re->magic_number = MAGIC_NUMBER; -re->size = (int)size; -re->options = cd->external_options; -re->flags = cd->external_flags; -re->limit_match = limit_match; -re->limit_recursion = limit_recursion; -re->first_char = 0; -re->req_char = 0; -re->name_table_offset = sizeof(REAL_PCRE) / sizeof(pcre_uchar); -re->name_entry_size = cd->name_entry_size; -re->name_count = cd->names_found; -re->ref_count = 0; -re->tables = (tables == PRIV(default_tables))? NULL : tables; -re->nullpad = NULL; -#ifdef COMPILE_PCRE32 -re->dummy = 0; -#else -re->dummy1 = re->dummy2 = re->dummy3 = 0; -#endif - -/* The starting points of the name/number translation table and of the code are -passed around in the compile data block. The start/end pattern and initial -options are already set from the pre-compile phase, as is the name_entry_size -field. Reset the bracket count and the names_found field. Also reset the hwm -field; this time it's used for remembering forward references to subpatterns. -*/ - -cd->final_bracount = cd->bracount; /* Save for checking forward references */ -cd->parens_depth = 0; -cd->assert_depth = 0; -cd->bracount = 0; -cd->max_lookbehind = 0; -cd->name_table = (pcre_uchar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->hwm = (pcre_uchar *)(cd->start_workspace); -cd->req_varyopt = 0; -cd->had_accept = FALSE; -cd->had_pruneorskip = FALSE; -cd->check_lookbehind = FALSE; -cd->open_caps = NULL; - -/* If any named groups were found, create the name/number table from the list -created in the first pass. */ - -if (cd->names_found > 0) - { - int i = cd->names_found; - named_group *ng = cd->named_groups; - cd->names_found = 0; - for (; i > 0; i--, ng++) - add_name(cd, ng->name, ng->length, ng->number); - if (cd->named_group_list_size > NAMED_GROUP_LIST_SIZE) - (PUBL(free))((void *)cd->named_groups); - } - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, errorcode will be set non-zero, so we don't need to look at the result -of the function here. */ - -ptr = (const pcre_uchar *)pattern + skipatstart; -code = (pcre_uchar *)codestart; -*code = OP_BRA; -(void)compile_regex(re->options, &code, &ptr, &errorcode, FALSE, FALSE, 0, 0, - &firstchar, &firstcharflags, &reqchar, &reqcharflags, NULL, cd, NULL); -re->top_bracket = cd->bracount; -re->top_backref = cd->top_backref; -re->max_lookbehind = cd->max_lookbehind; -re->flags = cd->external_flags | PCRE_MODE; - -if (cd->had_accept) - { - reqchar = 0; /* Must disable after (*ACCEPT) */ - reqcharflags = REQ_NONE; - } - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (errorcode == 0 && *ptr != CHAR_NULL) errorcode = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef PCRE_DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -#ifdef SUPPORT_VALGRIND -/* If the estimated length exceeds the really used length, mark the extra -allocated memory as unaddressable, so that any out-of-bound reads can be -detected. */ -VALGRIND_MAKE_MEM_NOACCESS(code, (length - (code - codestart)) * sizeof(pcre_uchar)); -#endif - -/* Fill in any forward references that are required. There may be repeated -references; optimize for them, as searching a large regex takes time. */ - -if (cd->hwm > cd->start_workspace) - { - int prev_recno = -1; - const pcre_uchar *groupptr = NULL; - while (errorcode == 0 && cd->hwm > cd->start_workspace) - { - int offset, recno; - cd->hwm -= LINK_SIZE; - offset = GET(cd->hwm, 0); - recno = GET(codestart, offset); - if (recno != prev_recno) - { - groupptr = PRIV(find_bracket)(codestart, utf, recno); - prev_recno = recno; - } - if (groupptr == NULL) errorcode = ERR53; - else PUT(((pcre_uchar *)codestart), offset, (int)(groupptr - codestart)); - } - } - -/* If the workspace had to be expanded, free the new memory. Set the pointer to -NULL to indicate that forward references have been filled in. */ - -if (cd->workspace_size > COMPILE_WORK_SIZE) - (PUBL(free))((void *)cd->start_workspace); -cd->start_workspace = NULL; - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Unless disabled, check whether single character iterators can be -auto-possessified. The function overwrites the appropriate opcode values. */ - -if ((options & PCRE_NO_AUTO_POSSESS) == 0) - auto_possessify((pcre_uchar *)codestart, utf, cd); - -/* If there were any lookbehind assertions that contained OP_RECURSE -(recursions or subroutine calls), a flag is set for them to be checked here, -because they may contain forward references. Actual recursions cannot be fixed -length, but subroutine calls can. It is done like this so that those without -OP_RECURSE that are not fixed length get a diagnosic with a useful offset. The -exceptional ones forgo this. We scan the pattern to check that they are fixed -length, and set their lengths. */ - -if (cd->check_lookbehind) - { - pcre_uchar *cc = (pcre_uchar *)codestart; - - /* Loop, searching for OP_REVERSE items, and process those that do not have - their length set. (Actually, it will also re-process any that have a length - of zero, but that is a pathological case, and it does no harm.) When we find - one, we temporarily terminate the branch it is in while we scan it. */ - - for (cc = (pcre_uchar *)PRIV(find_bracket)(codestart, utf, -1); - cc != NULL; - cc = (pcre_uchar *)PRIV(find_bracket)(cc, utf, -1)) - { - if (GET(cc, 1) == 0) - { - int fixed_length; - pcre_uchar *be = cc - 1 - LINK_SIZE + GET(cc, -LINK_SIZE); - int end_op = *be; - *be = OP_END; - fixed_length = find_fixedlength(cc, (re->options & PCRE_UTF8) != 0, TRUE, - cd); - *be = end_op; - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length < 0) - { - errorcode = (fixed_length == -2)? ERR36 : - (fixed_length == -4)? ERR70 : ERR25; - break; - } - if (fixed_length > cd->max_lookbehind) cd->max_lookbehind = fixed_length; - PUT(cc, 1, fixed_length); - } - cc += 1 + LINK_SIZE; - } - } - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (PUBL(free))(re); - PCRE_EARLY_ERROR_RETURN: - *erroroffset = (int)(ptr - (const pcre_uchar *)pattern); - PCRE_EARLY_ERROR_RETURN2: - *errorptr = find_error_text(errorcode); - if (errorcodeptr != NULL) *errorcodeptr = errorcode; - return NULL; - } - -/* If the anchored option was not passed, set the flag if we can determine that -the pattern is anchored by virtue of ^ characters or \A or anything else, such -as starting with non-atomic .* when DOTALL is set and there are no occurrences -of *PRUNE or *SKIP. - -Otherwise, if we know what the first byte has to be, save it, because that -speeds up unanchored matches no end. If not, see if we can set the -PCRE_STARTLINE flag. This is helpful for multiline matches when all branches -start with ^. and also when all branches start with non-atomic .* for -non-DOTALL matches when *PRUNE and SKIP are not present. */ - -if ((re->options & PCRE_ANCHORED) == 0) - { - if (is_anchored(codestart, 0, cd, 0)) re->options |= PCRE_ANCHORED; - else - { - if (firstcharflags < 0) - firstchar = find_firstassertedchar(codestart, &firstcharflags, FALSE); - if (firstcharflags >= 0) /* Remove caseless flag for non-caseable chars */ - { -#if defined COMPILE_PCRE8 - re->first_char = firstchar & 0xff; -#elif defined COMPILE_PCRE16 - re->first_char = firstchar & 0xffff; -#elif defined COMPILE_PCRE32 - re->first_char = firstchar; -#endif - if ((firstcharflags & REQ_CASELESS) != 0) - { -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - /* We ignore non-ASCII first chars in 8 bit mode. */ - if (utf) - { - if (re->first_char < 128) - { - if (cd->fcc[re->first_char] != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - else if (UCD_OTHERCASE(re->first_char) != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - else -#endif - if (MAX_255(re->first_char) - && cd->fcc[re->first_char] != re->first_char) - re->flags |= PCRE_FCH_CASELESS; - } - - re->flags |= PCRE_FIRSTSET; - } - - else if (is_startline(codestart, 0, cd, 0)) re->flags |= PCRE_STARTLINE; - } - } - -/* For an anchored pattern, we use the "required byte" only if it follows a -variable length item in the regex. Remove the caseless flag for non-caseable -bytes. */ - -if (reqcharflags >= 0 && - ((re->options & PCRE_ANCHORED) == 0 || (reqcharflags & REQ_VARY) != 0)) - { -#if defined COMPILE_PCRE8 - re->req_char = reqchar & 0xff; -#elif defined COMPILE_PCRE16 - re->req_char = reqchar & 0xffff; -#elif defined COMPILE_PCRE32 - re->req_char = reqchar; -#endif - if ((reqcharflags & REQ_CASELESS) != 0) - { -#if defined SUPPORT_UCP && !(defined COMPILE_PCRE8) - /* We ignore non-ASCII first chars in 8 bit mode. */ - if (utf) - { - if (re->req_char < 128) - { - if (cd->fcc[re->req_char] != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - else if (UCD_OTHERCASE(re->req_char) != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - else -#endif - if (MAX_255(re->req_char) && cd->fcc[re->req_char] != re->req_char) - re->flags |= PCRE_RCH_CASELESS; - } - - re->flags |= PCRE_REQCHSET; - } - -/* Print out the compiled data if debugging is enabled. This is never the -case when building a production library. */ - -#ifdef PCRE_DEBUG -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -printf("Options=%08x\n", re->options); - -if ((re->flags & PCRE_FIRSTSET) != 0) - { - pcre_uchar ch = re->first_char; - const char *caseless = - ((re->flags & PCRE_FCH_CASELESS) == 0)? "" : " (caseless)"; - if (PRINTABLE(ch)) printf("First char = %c%s\n", ch, caseless); - else printf("First char = \\x%02x%s\n", ch, caseless); - } - -if ((re->flags & PCRE_REQCHSET) != 0) - { - pcre_uchar ch = re->req_char; - const char *caseless = - ((re->flags & PCRE_RCH_CASELESS) == 0)? "" : " (caseless)"; - if (PRINTABLE(ch)) printf("Req char = %c%s\n", ch, caseless); - else printf("Req char = \\x%02x%s\n", ch, caseless); - } - -#if defined COMPILE_PCRE8 -pcre_printint((pcre *)re, stdout, TRUE); -#elif defined COMPILE_PCRE16 -pcre16_printint((pcre *)re, stdout, TRUE); -#elif defined COMPILE_PCRE32 -pcre32_printint((pcre *)re, stdout, TRUE); -#endif - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - codestart > length) - { - (PUBL(free))(re); - *errorptr = find_error_text(ERR23); - *erroroffset = ptr - (pcre_uchar *)pattern; - if (errorcodeptr != NULL) *errorcodeptr = ERR23; - return NULL; - } -#endif /* PCRE_DEBUG */ - -/* Check for a pattern than can match an empty string, so that this information -can be provided to applications. */ - -do - { - if (could_be_empty_branch(codestart, code, utf, cd, NULL)) - { - re->flags |= PCRE_MATCH_EMPTY; - break; - } - codestart += GET(codestart, 1); - } -while (*codestart == OP_ALT); - -#if defined COMPILE_PCRE8 -return (pcre *)re; -#elif defined COMPILE_PCRE16 -return (pcre16 *)re; -#elif defined COMPILE_PCRE32 -return (pcre32 *)re; -#endif -} - -/* End of pcre_compile.c */ - diff --git a/.pc/Fix-silly-quantifier-size-check.patch/testdata/testoutput2 b/.pc/Fix-silly-quantifier-size-check.patch/testdata/testoutput2 deleted file mode 100644 index b6da7df..0000000 --- a/.pc/Fix-silly-quantifier-size-check.patch/testdata/testoutput2 +++ /dev/null @@ -1,14152 +0,0 @@ -/-- This set of tests is not Perl-compatible. It checks on special features - of PCRE's API, error diagnostics, and the compiled code of some patterns. - It also checks the non-Perl syntax the PCRE supports (Python, .NET, - Oniguruma). Finally, there are some tests where PCRE and Perl differ, - either because PCRE can't be compatible, or there is a possible Perl - bug. - - NOTE: This is a non-UTF set of tests. When UTF support is needed, use - test 5, and if Unicode Property Support is needed, use test 7. --/ - -< forbid 8W - -/(a)b|/I -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - abc - 0: abc - defabc - 0: abc - \Aabc - 0: abc - *** Failers -No match - \Adefabc -No match - ABC -No match - -/^abc/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - \Aabc - 0: abc - *** Failers -No match - defabc -No match - \Adefabc -No match - -/a+bc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/a*bc/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/a{3}bc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(abc|a+z)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/^abc$/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - *** Failers -No match - def\nabc -No match - -/ab\idef/X -Failed: unrecognized character follows \ at offset 3 - -/(?X)ab\idef/X -Failed: unrecognized character follows \ at offset 7 - -/x{5,4}/ -Failed: numbers out of order in {} quantifier at offset 5 - -/z{65536}/ -Failed: number too big in {} quantifier at offset 7 - -/[abcd/ -Failed: missing terminating ] for character class at offset 5 - -/(?X)[\B]/ -Failed: invalid escape sequence in character class at offset 6 - -/(?X)[\R]/ -Failed: invalid escape sequence in character class at offset 6 - -/(?X)[\X]/ -Failed: invalid escape sequence in character class at offset 6 - -/[\B]/BZ ------------------------------------------------------------------- - Bra - B - Ket - End ------------------------------------------------------------------- - -/[\R]/BZ ------------------------------------------------------------------- - Bra - R - Ket - End ------------------------------------------------------------------- - -/[\X]/BZ ------------------------------------------------------------------- - Bra - X - Ket - End ------------------------------------------------------------------- - -/[z-a]/ -Failed: range out of order in character class at offset 3 - -/^*/ -Failed: nothing to repeat at offset 1 - -/(abc/ -Failed: missing ) at offset 4 - -/(?# abc/ -Failed: missing ) after comment at offset 7 - -/(?z)abc/ -Failed: unrecognized character after (? or (?- at offset 2 - -/.*b/I -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 'b' - -/.*?b/I -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 'b' - -/cat|dog|elephant/I -Capturing subpattern count = 0 -No options -No first char -No need char - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 3 -Starting chars: c d e - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/IiS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Subject length lower bound = 3 -Starting chars: C D E c d e - this sentence eventually mentions a CAT cat - 0: CAT - this sentences rambles on and on for a while to elephant ElePhant - 0: elephant - -/a|[bcd]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b c d - -/(a|[^\dZ])/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > - ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d - e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 - \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 - \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 - \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 - \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf - \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce - \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd - \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec - \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb - \xfc \xfd \xfe \xff - -/(a|b)*[\s]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: \x09 \x0a \x0b \x0c \x0d \x20 a b - -/(ab\2)/ -Failed: reference to non-existent subpattern at offset 6 - -/{4,5}abc/ -Failed: nothing to repeat at offset 4 - -/(a)(b)(c)\2/I -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -Need char = 'c' - abcb - 0: abcb - 1: a - 2: b - 3: c - \O0abcb -Matched, but too many substrings - \O3abcb -Matched, but too many substrings - 0: abcb - \O6abcb -Matched, but too many substrings - 0: abcb - 1: a - \O9abcb -Matched, but too many substrings - 0: abcb - 1: a - 2: b - \O12abcb - 0: abcb - 1: a - 2: b - 3: c - -/(a)bc|(a)(b)\2/I -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -No need char - abc - 0: abc - 1: a - \O0abc -Matched, but too many substrings - \O3abc -Matched, but too many substrings - 0: abc - \O6abc - 0: abc - 1: a - aba - 0: aba - 1: <unset> - 2: a - 3: b - \O0aba -Matched, but too many substrings - \O3aba -Matched, but too many substrings - 0: aba - \O6aba -Matched, but too many substrings - 0: aba - 1: <unset> - \O9aba -Matched, but too many substrings - 0: aba - 1: <unset> - 2: a - \O12aba - 0: aba - 1: <unset> - 2: a - 3: b - -/abc$/IE -Capturing subpattern count = 0 -Options: dollar_endonly -First char = 'a' -Need char = 'c' - abc - 0: abc - *** Failers -No match - abc\n -No match - abc\ndef -No match - -/(a)(b)(c)(d)(e)\6/ -Failed: reference to non-existent subpattern at offset 17 - -/the quick brown fox/I -Capturing subpattern count = 0 -No options -First char = 't' -Need char = 'x' - the quick brown fox - 0: the quick brown fox - this is a line with the quick brown fox - 0: the quick brown fox - -/the quick brown fox/IA -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - the quick brown fox - 0: the quick brown fox - *** Failers -No match - this is a line with the quick brown fox -No match - -/ab(?z)cd/ -Failed: unrecognized character after (? or (?- at offset 4 - -/^abc|def/I -Capturing subpattern count = 0 -No options -No first char -No need char - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/I -Capturing subpattern count = 3 -No options -First char at start or follows newline -No need char - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 2: <unset> - 3: def - -/)/ -Failed: unmatched parentheses at offset 0 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/[^aeiou ]{3,}/I -Capturing subpattern count = 0 -No options -No first char -No need char - co-processors, and for - 0: -pr - -/<.*>/I -Capturing subpattern count = 0 -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/<.*?>/I -Capturing subpattern count = 0 -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*>/IU -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/(?U)<.*>/I -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*?>/IU -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/={3,}/IU -Capturing subpattern count = 0 -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: === - -/(?U)={3,}?/I -Capturing subpattern count = 0 -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: ======== - -/(?<!bar|cattle)foo/I -Capturing subpattern count = 0 -Max lookbehind = 6 -No options -First char = 'f' -Need char = 'o' - foo - 0: foo - catfoo - 0: foo - *** Failers -No match - the barfoo -No match - and cattlefoo -No match - -/(?<=a+)b/ -Failed: lookbehind assertion is not fixed length at offset 6 - -/(?<=aaa|b{0,3})b/ -Failed: lookbehind assertion is not fixed length at offset 14 - -/(?<!(foo)a\1)bar/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?i)abc/I -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/(a|(?m)a)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?i)^1234/I -Capturing subpattern count = 0 -Options: anchored caseless -No first char -No need char - -/(^b|(?i)^d)/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - -/(?s).*/I -Capturing subpattern count = 0 -May match empty string -Options: anchored dotall -No first char -No need char - -/[abcd]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b c d - -/(?i)[abcd]/IS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Subject length lower bound = 1 -Starting chars: A B C D a b c d - -/(?m)[xy]|(b|c)/IS -Capturing subpattern count = 1 -Options: multiline -No first char -No need char -Subject length lower bound = 1 -Starting chars: b c x y - -/(^a|^b)/Im -Capturing subpattern count = 1 -Options: multiline -First char at start or follows newline -No need char - -/(?i)(^a|^b)/Im -Capturing subpattern count = 1 -Options: caseless multiline -First char at start or follows newline -No need char - -/(a)(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 13 - -/(?(?=a)a|b|c)/ -Failed: conditional group contains more than two branches at offset 12 - -/(?(1a)/ -Failed: malformed number or name after (?( at offset 4 - -/(?(1a))/ -Failed: malformed number or name after (?( at offset 4 - -/(?(?i))/ -Failed: assertion expected after (?( at offset 3 - -/(?(abc))/ -Failed: reference to non-existent subpattern at offset 7 - -/(?(?<ab))/ -Failed: syntax error in subpattern name (missing terminator) at offset 7 - -/((?s)blah)\s+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -First char = 'b' -Need char = 'h' - -/((?i)blah)\s+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -First char = 'b' (caseless) -Need char = 'h' (caseless) - -/((?i)b)/IDZS ------------------------------------------------------------------- - Bra - CBra 1 - /i b - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'b' (caseless) -No need char -Subject length lower bound = 1 -No starting char list - -/(a*b|(?i:c*(?-i)d))/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: C a b c d - -/a$/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - a - 0: a - a\n - 0: a - *** Failers -No match - \Za -No match - \Za\n -No match - -/a$/Im -Capturing subpattern count = 0 -Options: multiline -First char = 'a' -No need char - a - 0: a - a\n - 0: a - \Za\n - 0: a - *** Failers -No match - \Za -No match - -/\Aabc/Im -Capturing subpattern count = 0 -Max lookbehind = 1 -Options: anchored multiline -No first char -No need char - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/I -Capturing subpattern count = 5 -Options: anchored -No first char -No need char - aaaaabbbbbcccccdef - 0: aaaaabbbbbcccccdef - 1: aaaaabbbbbcccccdef - 2: aaaaa - 3: b - 4: bbbbccccc - 5: def - -/(?<=foo)[ab]/IS -Capturing subpattern count = 0 -Max lookbehind = 3 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b - -/(?<!foo)(alpha|omega)/IS -Capturing subpattern count = 1 -Max lookbehind = 3 -No options -No first char -Need char = 'a' -Subject length lower bound = 5 -Starting chars: a o - -/(?!alphabet)[ab]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b - -/(?<=foo\n)^bar/Im -Capturing subpattern count = 0 -Max lookbehind = 4 -Contains explicit CR or LF match -Options: multiline -No first char -Need char = 'r' - foo\nbarbar - 0: bar - ***Failers -No match - rhubarb -No match - barbell -No match - abc\nbarton -No match - -/^(?<=foo\n)bar/Im -Capturing subpattern count = 0 -Max lookbehind = 4 -Contains explicit CR or LF match -Options: multiline -First char at start or follows newline -Need char = 'r' - foo\nbarbar - 0: bar - ***Failers -No match - rhubarb -No match - barbell -No match - abc\nbarton -No match - -/(?>^abc)/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - abc - 0: abc - def\nabc - 0: abc - *** Failers -No match - defabc -No match - -/(?<=ab(c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 11 - -/(?<=ab(?<=c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?<=ab(c|de)f)g/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/I -Capturing subpattern count = 0 -Max lookbehind = 7 -No options -First char = '-' -Need char = 't' - the bullock-cart - 0: -cart - a donkey-cart race - 0: -cart - *** Failers -No match - cart -No match - horse-and-cart -No match - -/(?<=ab(?i)x|y|z)/I -Capturing subpattern count = 0 -Max lookbehind = 3 -May match empty string -No options -No first char -No need char - -/(?>.*)(?<=(abcd)|(xyz))/I -Capturing subpattern count = 2 -Max lookbehind = 4 -May match empty string -No options -No first char -No need char - alphabetabcd - 0: alphabetabcd - 1: abcd - endingxyz - 0: endingxyz - 1: <unset> - 2: xyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/I -Capturing subpattern count = 0 -Max lookbehind = 4 -No options -First char = 'Z' -Need char = 'Z' - abxyZZ - 0: ZZ - abXyZZ - 0: ZZ - ZZZ - 0: ZZ - zZZ - 0: ZZ - bZZ - 0: ZZ - BZZ - 0: ZZ - *** Failers -No match - ZZ -No match - abXYZZ -No match - zzz -No match - bzz -No match - -/(?<!(foo)a)bar/I -Capturing subpattern count = 1 -Max lookbehind = 4 -No options -First char = 'b' -Need char = 'r' - bar - 0: bar - foobbar - 0: bar - *** Failers -No match - fooabar -No match - -/This one is here because Perl behaves differently; see also the following/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'g' - -/^(a\1?){4}$/I -Capturing subpattern count = 1 -Max back reference = 1 -Options: anchored -No first char -No need char - aaaa -No match - aaaaaa -No match - -/Perl does not fail these two for the final subjects. Neither did PCRE until/ -/release 8.01. The problem is in backtracking into a subpattern that contains/ -No match -/a recursive reference to itself. PCRE has now made these into atomic patterns./ -No match - -/^(xa|=?\1a){2}$/ - xa=xaa - 0: xa=xaa - 1: =xaa - ** Failers -No match - xa=xaaa -No match - -/^(xa|=?\1a)+$/ - xa=xaa - 0: xa=xaa - 1: =xaa - ** Failers -No match - xa=xaaa -No match - -/These are syntax tests from Perl 5.005/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = '5' - -/a[b-a]/ -Failed: range out of order in character class at offset 4 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/a[/ -Failed: missing terminating ] for character class at offset 2 - -/*a/ -Failed: nothing to repeat at offset 0 - -/(*)b/ -Failed: nothing to repeat at offset 1 - -/abc)/ -Failed: unmatched parentheses at offset 3 - -/(abc/ -Failed: missing ) at offset 4 - -/a**/ -Failed: nothing to repeat at offset 2 - -/)(/ -Failed: unmatched parentheses at offset 0 - -/\1/ -Failed: reference to non-existent subpattern at offset 2 - -/\2/ -Failed: reference to non-existent subpattern at offset 2 - -/(a)|\2/ -Failed: reference to non-existent subpattern at offset 6 - -/a[b-a]/Ii -Failed: range out of order in character class at offset 4 - -/a[]b/Ii -Failed: missing terminating ] for character class at offset 4 - -/a[/Ii -Failed: missing terminating ] for character class at offset 2 - -/*a/Ii -Failed: nothing to repeat at offset 0 - -/(*)b/Ii -Failed: nothing to repeat at offset 1 - -/abc)/Ii -Failed: unmatched parentheses at offset 3 - -/(abc/Ii -Failed: missing ) at offset 4 - -/a**/Ii -Failed: nothing to repeat at offset 2 - -/)(/Ii -Failed: unmatched parentheses at offset 0 - -/:(?:/ -Failed: missing ) at offset 4 - -/(?<%)b/ -Failed: unrecognized character after (?< at offset 3 - -/a(?{)b/ -Failed: unrecognized character after (? or (?- at offset 3 - -/a(?{{})b/ -Failed: unrecognized character after (? or (?- at offset 3 - -/a(?{}})b/ -Failed: unrecognized character after (? or (?- at offset 3 - -/a(?{"{"})b/ -Failed: unrecognized character after (? or (?- at offset 3 - -/a(?{"{"}})b/ -Failed: unrecognized character after (? or (?- at offset 3 - -/(?(1?)a|b)/ -Failed: malformed number or name after (?( at offset 4 - -/[a[:xyz:/ -Failed: missing terminating ] for character class at offset 8 - -/(?<=x+)y/ -Failed: lookbehind assertion is not fixed length at offset 6 - -/a{37,17}/ -Failed: numbers out of order in {} quantifier at offset 7 - -/abc/\ -Failed: \ at end of pattern at offset 4 - -/abc/\i -Failed: \ at end of pattern at offset 4 - -/(a)bc(d)/I -Capturing subpattern count = 2 -No options -First char = 'a' -Need char = 'd' - abcd - 0: abcd - 1: a - 2: d - abcd\C2 - 0: abcd - 1: a - 2: d - 2C d (1) - abcd\C5 - 0: abcd - 1: a - 2: d -copy substring 5 failed -7 - -/(.{20})/I -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst - abcdefghijklmnopqrstuvwxyz\C1 - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst - 1C abcdefghijklmnopqrst (20) - abcdefghijklmnopqrstuvwxyz\G1 - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst - 1G abcdefghijklmnopqrst (20) - -/(.{15})/I -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmno - 1: abcdefghijklmno - abcdefghijklmnopqrstuvwxyz\C1\G1 - 0: abcdefghijklmno - 1: abcdefghijklmno - 1C abcdefghijklmno (15) - 1G abcdefghijklmno (15) - -/(.{16})/I -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmnop - 1: abcdefghijklmnop - abcdefghijklmnopqrstuvwxyz\C1\G1\L - 0: abcdefghijklmnop - 1: abcdefghijklmnop - 1C abcdefghijklmnop (16) - 1G abcdefghijklmnop (16) - 0L abcdefghijklmnop - 1L abcdefghijklmnop - -/^(a|(bc))de(f)/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - adef\G1\G2\G3\G4\L - 0: adef - 1: a - 2: <unset> - 3: f - 1G a (1) - 2G (0) - 3G f (1) -get substring 4 failed -7 - 0L adef - 1L a - 2L - 3L f - bcdef\G1\G2\G3\G4\L - 0: bcdef - 1: bc - 2: bc - 3: f - 1G bc (2) - 2G bc (2) - 3G f (1) -get substring 4 failed -7 - 0L bcdef - 1L bc - 2L bc - 3L f - adefghijk\C0 - 0: adef - 1: a - 2: <unset> - 3: f - 0C adef (4) - -/^abc\00def/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc\00def\L\C0 - 0: abc\x00def - 0C abc\x00def (7) - 0L abc - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/I -Capturing subpattern count = 8 -Contains explicit CR or LF match -No options -First char = 'w' -Need char = 'd' - -/.*X/IDZ ------------------------------------------------------------------- - Bra - Any* - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 'X' - -/.*X/IDZs ------------------------------------------------------------------- - Bra - AllAny* - X - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored dotall -No first char -Need char = 'X' - -/(.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - CBra 1 - Any* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char at start or follows newline -No need char - -/(.*X|^B)/IDZs ------------------------------------------------------------------- - Bra - CBra 1 - AllAny* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(?s)(.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - CBra 1 - AllAny* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(?s:.*X|^B)/IDZ ------------------------------------------------------------------- - Bra - Bra - AllAny* - X - Alt - ^ - B - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/\Biss\B/I+ -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/iss/IG+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/\Biss\B/IG+ -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/Ig+ -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - *** Failers -No match - Mississippi\A -No match - -/(?<=[Ms])iss/Ig+ -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/(?<=[Ms])iss/IG+ -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/^iss/Ig+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ississippi - 0: iss - 0+ issippi - -/.*iss/Ig+ -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 's' - abciss\nxyzisspqr - 0: abciss - 0+ \x0axyzisspqr - 0: xyziss - 0+ pqr - -/.i./I+g -Capturing subpattern count = 0 -No options -No first char -Need char = 'i' - Mississippi - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Mississippi\A - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Missouri river - 0: Mis - 0+ souri river - 0: ri - 0+ river - 0: riv - 0+ er - Missouri river\A - 0: Mis - 0+ souri river - -/^.is/I+g -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - Mississippi - 0: Mis - 0+ sissippi - -/^ab\n/Ig+ -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: anchored -No first char -No need char - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - -/^ab\n/Img+ -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: multiline -First char at start or follows newline -Need char = \x0a - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - 0: ab\x0a - 0+ cd - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/abc|bac/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(abc|bac)/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' - -/(abc|(c|dc))/I -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/(abc|(d|de)c)/I -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/a*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - -/a+/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(baa|a+)/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' - -/a{0,3}/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - -/baa{3,}/I -Capturing subpattern count = 0 -No options -First char = 'b' -Need char = 'a' - -/"([^\\"]+|\\.)*"/I -Capturing subpattern count = 1 -No options -First char = '"' -Need char = '"' - -/(abc|ab[cd])/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a|.)/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/a|ba|\w/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?=pqr)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'r' - -/...(?<=abc)/I -Capturing subpattern count = 0 -Max lookbehind = 3 -No options -No first char -No need char - -/abc(?!pqr)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/ab./I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab[xyz]/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/abc*/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab.c*/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a.c*/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/.c*/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/ac*/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(a.c*|b.c*)/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/a.c*|aba/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/.+a/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'a' - -/(?=abcda)a.*/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'a' - -/(?=a)a.*/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(b)*/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a\d*/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/ab\d*/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a(\d)*/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/abcde{0,0}/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'd' - -/ab\d+/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a(?(1)b)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)bag|big)*(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)+(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)b..|b..)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/ab\d{0}e/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - -/a?b?/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - a - 0: a - b - 0: b - ab - 0: ab - \ - 0: - *** Failers - 0: - \N -No match - -/|-/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - abcd - 0: - -abc - 0: - \Nab-c - 0: - - *** Failers - 0: - \Nabc -No match - -/^.?abcd/IS -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'd' -Subject length lower bound = 4 -No starting char list - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /Ix -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (abcd)xyz - 0: (abcd) - xyz(abcd) - 0: (abcd) - (ab(xy)cd)pqr - 0: (ab(xy)cd) - (ab(xycd)pqr - 0: (xycd) - () abc () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (abcde(fsh)xyz(foo(bar))lmno) - *** Failers -No match - abcd -No match - abcd) -No match - (abcd -No match - -/\( ( (?>[^()]+) | (?R) )* \) /Ixg -Capturing subpattern count = 1 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd)pqr - 0: (ab(xy)cd) - 1: cd - 1(abcd)(x(y)z)pqr - 0: (abcd) - 1: abcd - 0: (x(y)z) - 1: z - -/\( (?: (?>[^()]+) | (?R) ) \) /Ix -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (ab(xy)cd) - 0: (xy) - (a(b(c)d)e) - 0: (c) - ((ab)) - 0: ((ab)) - *** Failers -No match - () -No match - -/\( (?: (?>[^()]+) | (?R) )? \) /Ix -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (fsh) - -/\( ( (?>[^()]+) | (?R) )* \) /Ix -Capturing subpattern count = 1 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: cd - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 2 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: cd - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: <unset> - 2: ab(xy)cd - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123 - 2: ab(xy)cd - 3: cd - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: <unset> - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123ab(xy)cd - 2: 123 - 3: cd - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /Ix -Capturing subpattern count = 11 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: ab(xy)cd - 3: ab(xy)cd - 4: ab(xy)cd - 5: ab(xy)cd - 6: ab(xy)cd - 7: ab(xy)cd - 8: ab(xy)cd - 9: ab(xy)cd -10: ab(xy)cd -11: cd - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /Ix -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (abcd(xyz<p>qrs)123) - 0: (abcd(xyz<p>qrs)123) - 1: abcd(xyz<p>qrs)123 - 2: 123 - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /Ix -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(cd)ef) - 0: (ab(cd)ef) - 1: ab(cd)ef - 2: ef - 3: (cd) - (ab(cd(ef)gh)ij) - 0: (ab(cd(ef)gh)ij) - 1: ab(cd(ef)gh)ij - 2: ij - 3: (cd(ef)gh) - -/^[[:alnum:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alnum:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-/:-@[-`{-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:alpha:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^alpha:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-@[-`{-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[_[:alpha:]]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: A B C D E F G H I J K L M N O P Q R S T U V W X Y Z - _ a b c d e f g h i j k l m n o p q r s t u v w x y z - -/^[[:ascii:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x7f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^ascii:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x80-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x09 ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x08\x0a-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[\n\x0b\x0c\x0d[:blank:]]/IS -Capturing subpattern count = 0 -Contains explicit CR or LF match -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: \x09 \x0a \x0b \x0c \x0d \x20 - -/^[[:cntrl:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x1f\x7f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:digit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:graph:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [!-~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:lower:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [a-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:print:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [ -~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:punct:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [!-/:-@[-`{-~] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:space:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:upper:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [A-Z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:xdigit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Fa-f] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:word:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [0-9A-Z_a-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^cntrl:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [ -~\x80-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[12[:^digit:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-/12:-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/DZ ------------------------------------------------------------------- - Bra - ^ - [\x00-\x08\x0a-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[01[:alpha:]%]/DZ ------------------------------------------------------------------- - Bra - [%01A-Za-z] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[.ch.]]/I -Failed: POSIX collating elements are not supported at offset 1 - -/[[=ch=]]/I -Failed: POSIX collating elements are not supported at offset 1 - -/[[:rhubarb:]]/I -Failed: unknown POSIX class name at offset 3 - -/[[:upper:]]/Ii -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/[[:lower:]]/Ii -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/((?-i)[[:lower:]])[[:lower:]]/Ii -Capturing subpattern count = 1 -Options: caseless -No first char -No need char - ab - 0: ab - 1: a - aB - 0: aB - 1: a - *** Failers - 0: ai - 1: a - Ab -No match - AB -No match - -/[\200-\110]/I -Failed: range out of order in character class at offset 9 - -/^(?(0)f|b)oo/I -Failed: invalid condition (?(0) at offset 6 - -/This one's here because of the large output vector needed/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'd' - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/I -Capturing subpattern count = 271 -Max back reference = 270 -No options -No first char -No need char - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 1: 1 - 2: 2 - 3: 3 - 4: 4 - 5: 5 - 6: 6 - 7: 7 - 8: 8 - 9: 9 -10: 10 -11: 11 -12: 12 -13: 13 -14: 14 -15: 15 -16: 16 -17: 17 -18: 18 -19: 19 -20: 20 -21: 21 -22: 22 -23: 23 -24: 24 -25: 25 -26: 26 -27: 27 -28: 28 -29: 29 -30: 30 -31: 31 -32: 32 -33: 33 -34: 34 -35: 35 -36: 36 -37: 37 -38: 38 -39: 39 -40: 40 -41: 41 -42: 42 -43: 43 -44: 44 -45: 45 -46: 46 -47: 47 -48: 48 -49: 49 -50: 50 -51: 51 -52: 52 -53: 53 -54: 54 -55: 55 -56: 56 -57: 57 -58: 58 -59: 59 -60: 60 -61: 61 -62: 62 -63: 63 -64: 64 -65: 65 -66: 66 -67: 67 -68: 68 -69: 69 -70: 70 -71: 71 -72: 72 -73: 73 -74: 74 -75: 75 -76: 76 -77: 77 -78: 78 -79: 79 -80: 80 -81: 81 -82: 82 -83: 83 -84: 84 -85: 85 -86: 86 -87: 87 -88: 88 -89: 89 -90: 90 -91: 91 -92: 92 -93: 93 -94: 94 -95: 95 -96: 96 -97: 97 -98: 98 -99: 99 -100: 100 -101: 101 -102: 102 -103: 103 -104: 104 -105: 105 -106: 106 -107: 107 -108: 108 -109: 109 -110: 110 -111: 111 -112: 112 -113: 113 -114: 114 -115: 115 -116: 116 -117: 117 -118: 118 -119: 119 -120: 120 -121: 121 -122: 122 -123: 123 -124: 124 -125: 125 -126: 126 -127: 127 -128: 128 -129: 129 -130: 130 -131: 131 -132: 132 -133: 133 -134: 134 -135: 135 -136: 136 -137: 137 -138: 138 -139: 139 -140: 140 -141: 141 -142: 142 -143: 143 -144: 144 -145: 145 -146: 146 -147: 147 -148: 148 -149: 149 -150: 150 -151: 151 -152: 152 -153: 153 -154: 154 -155: 155 -156: 156 -157: 157 -158: 158 -159: 159 -160: 160 -161: 161 -162: 162 -163: 163 -164: 164 -165: 165 -166: 166 -167: 167 -168: 168 -169: 169 -170: 170 -171: 171 -172: 172 -173: 173 -174: 174 -175: 175 -176: 176 -177: 177 -178: 178 -179: 179 -180: 180 -181: 181 -182: 182 -183: 183 -184: 184 -185: 185 -186: 186 -187: 187 -188: 188 -189: 189 -190: 190 -191: 191 -192: 192 -193: 193 -194: 194 -195: 195 -196: 196 -197: 197 -198: 198 -199: 199 -200: 200 -201: 201 -202: 202 -203: 203 -204: 204 -205: 205 -206: 206 -207: 207 -208: 208 -209: 209 -210: 210 -211: 211 -212: 212 -213: 213 -214: 214 -215: 215 -216: 216 -217: 217 -218: 218 -219: 219 -220: 220 -221: 221 -222: 222 -223: 223 -224: 224 -225: 225 -226: 226 -227: 227 -228: 228 -229: 229 -230: 230 -231: 231 -232: 232 -233: 233 -234: 234 -235: 235 -236: 236 -237: 237 -238: 238 -239: 239 -240: 240 -241: 241 -242: 242 -243: 243 -244: 244 -245: 245 -246: 246 -247: 247 -248: 248 -249: 249 -250: 250 -251: 251 -252: 252 -253: 253 -254: 254 -255: 255 -256: 256 -257: 257 -258: 258 -259: 259 -260: 260 -261: 261 -262: 262 -263: 263 -264: 264 -265: 265 -266: 266 -267: 267 -268: 268 -269: 269 -270: ABC -271: ABC - -/This one's here because Perl does this differently and PCRE can't at present/I -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/(main(O)?)+/I -Capturing subpattern count = 2 -No options -First char = 'm' -Need char = 'n' - mainmain - 0: mainmain - 1: main - mainOmain - 0: mainOmain - 1: main - 2: O - -/These are all cases where Perl does it differently (nested captures)/I -Capturing subpattern count = 1 -No options -First char = 'T' -Need char = 's' - -/^(a(b)?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aba - 0: aba - 1: a - 2: b - -/^(aa(bb)?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa|aa(bb))+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa(bb)??)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(?:aa(bb)?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(aa(b(b))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - 3: b - -/^(?:aa(b(b))?)+$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - 2: b - -/^(?:aa(b(?:b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(?:aa(bb(?:b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(b(?:bb))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(?:b(b))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: b - -/^(?:aa(?:b(bb))?)+$/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bb - -/^(aa(b(bb))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: aa - 2: bbb - 3: bb - -/^(aa(bb(bb))?)+$/I -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbbaa - 0: aabbbbaa - 1: aa - 2: bbbb - 3: bb - -/--------------------------------------------------------------------/I -Capturing subpattern count = 0 -No options -First char = '-' -Need char = '-' - -/#/IxDZ ------------------------------------------------------------------- - Bra - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -May match empty string -Options: extended -No first char -No need char - -/a#/IxDZ ------------------------------------------------------------------- - Bra - a - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -First char = 'a' -No need char - -/[\s]/DZ ------------------------------------------------------------------- - Bra - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\S]/DZ ------------------------------------------------------------------- - Bra - [\x00-\x08\x0e-\x1f!-\xff] (neg) - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/a(?i)b/DZ ------------------------------------------------------------------- - Bra - a - /i b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - aB - 0: aB - *** Failers -No match - AB -No match - -/(a(?i)b)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - /i b - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - 1: ab - aB - 0: aB - 1: aB - *** Failers -No match - AB -No match - -/ (?i)abc/IxDZ ------------------------------------------------------------------- - Bra - /i abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/#this is a comment - (?i)abc/IxDZ ------------------------------------------------------------------- - Bra - /i abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------- - Bra - 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/DZ ------------------------------------------------------------------- - Bra - 123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q\E/DZ ------------------------------------------------------------------- - Bra - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - \ - 0: - -/\Q\Ex/DZ ------------------------------------------------------------------- - Bra - x - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/ \Q\E/DZ ------------------------------------------------------------------- - Bra - - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = ' ' -No need char - -/a\Q\E/DZ ------------------------------------------------------------------- - Bra - a - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - abc - 0: a - bca - 0: a - bac - 0: a - -/a\Q\Eb/DZ ------------------------------------------------------------------- - Bra - ab - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - abc - 0: ab - -/\Q\Eabc/DZ ------------------------------------------------------------------- - Bra - abc - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/x*+\w/DZ ------------------------------------------------------------------- - Bra - x*+ - \w - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - *** Failers - 0: F - xxxxx -No match - -/x?+/DZ ------------------------------------------------------------------- - Bra - x?+ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - -/x++/DZ ------------------------------------------------------------------- - Bra - x++ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/x{1,3}+/BZO ------------------------------------------------------------------- - Bra - x - x{0,2}+ - Ket - End ------------------------------------------------------------------- - -/x{1,3}+/BZOi ------------------------------------------------------------------- - Bra - /i x - /i x{0,2}+ - Ket - End ------------------------------------------------------------------- - -/[^x]{1,3}+/BZO ------------------------------------------------------------------- - Bra - [^x] - [^x]{0,2}+ - Ket - End ------------------------------------------------------------------- - -/[^x]{1,3}+/BZOi ------------------------------------------------------------------- - Bra - /i [^x] - /i [^x]{0,2}+ - Ket - End ------------------------------------------------------------------- - -/(x)*+/DZ ------------------------------------------------------------------- - Bra - Braposzero - CBraPos 1 - x - KetRpos - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - -/^(\w++|\s++)*$/I -Capturing subpattern count = 1 -May match empty string -Options: anchored -No first char -No need char - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d++)(\w)/I -Capturing subpattern count = 2 -No options -No first char -No need char - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/a++b/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - -/(a++b)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaab - -/(a++)b/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaa - -/([^()]++|\([^()]*\))+/I -Capturing subpattern count = 1 -No options -No first char -No need char - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(([^()]++|\([^()]+\))+\)/I -Capturing subpattern count = 1 -No options -First char = '(' -Need char = ')' - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(abc){1,3}+/DZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - abc - Ket - Brazero - Bra - CBra 1 - abc - Ket - Brazero - CBra 1 - abc - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'c' - -/a+?+/I -Failed: nothing to repeat at offset 3 - -/a{2,3}?+b/I -Failed: nothing to repeat at offset 7 - -/(?U)a+?+/I -Failed: nothing to repeat at offset 7 - -/a{2,3}?+b/IU -Failed: nothing to repeat at offset 7 - -/x(?U)a++b/DZ ------------------------------------------------------------------- - Bra - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/(?U)xa++b/DZ ------------------------------------------------------------------- - Bra - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: ungreedy -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/DZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - CBra 2 - a+ - Ket - CBra 3 - [ab]+? - Ket - CBra 4 - [bc]+ - Ket - CBra 5 - \w*+ - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 5 -Options: anchored -No first char -No need char - -/^x(?U)a+b/DZ ------------------------------------------------------------------- - Bra - ^ - x - a++ - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'b' - -/^x(?U)(a+)b/DZ ------------------------------------------------------------------- - Bra - ^ - x - CBra 1 - a+? - Ket - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = 'b' - -/[.x.]/I -Failed: POSIX collating elements are not supported at offset 0 - -/[=x=]/I -Failed: POSIX collating elements are not supported at offset 0 - -/[:x:]/I -Failed: POSIX named classes are supported only within a class at offset 0 - -/\l/I -Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1 - -/\L/I -Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1 - -/\N{name}/I -Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1 - -/\u/I -Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1 - -/\U/I -Failed: PCRE does not support \L, \l, \N{name}, \U, or \u at offset 1 - -/a{1,3}b/U - ab - 0: ab - -/[/I -Failed: missing terminating ] for character class at offset 1 - -/[a-/I -Failed: missing terminating ] for character class at offset 3 - -/[[:space:]/I -Failed: missing terminating ] for character class at offset 10 - -/[\s]/IDZ ------------------------------------------------------------------- - Bra - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]]/IDZ ------------------------------------------------------------------- - Bra - [\x09-\x0d ] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]abcde]/IDZ ------------------------------------------------------------------- - Bra - [\x09-\x0d a-e] - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/Ix -Capturing subpattern count = 0 -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - <abcd> - 0: <abcd> - <abc <123> hij> - 0: <abc <123> hij> - <abc <def> hij> - 0: <def> - <abc<>def> - 0: <abc<>def> - <abc<> - 0: <> - *** Failers -No match - <abc -No match - -|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------- - Bra - 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X - \b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = '8' -Need char = 'X' - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|IDZ ------------------------------------------------------------------- - Bra - $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X - \b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = '$' -Need char = 'X' - -/(.*)\d+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char - -/(.*)\d+/I -Capturing subpattern count = 1 -No options -First char at start or follows newline -No need char - -/(.*)\d+\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Options: dotall -No first char -No need char - -/(.*)\d+/Is -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(.*(xyz))\d+\2/I -Capturing subpattern count = 2 -Max back reference = 2 -No options -First char at start or follows newline -Need char = 'z' - -/((.*))\d+\1/I -Capturing subpattern count = 2 -Max back reference = 1 -No options -No first char -No need char - abc123bc - 0: bc123bc - 1: bc - 2: bc - -/a[b]/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?=a).*/I -Capturing subpattern count = 0 -May match empty string -No options -First char = 'a' -No need char - -/(?=abc).xyz/IiI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'z' (caseless) - -/(?=abc)(?i).xyz/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'z' (caseless) - -/(?=a)(?=b)/I -Capturing subpattern count = 0 -May match empty string -No options -First char = 'a' -No need char - -/(?=.)a/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/((?=abcda)a)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/((?=abcda)ab)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/()a/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' - -/(?(1)ab|ac)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?(1)abz|acz)(.)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'z' - -/(?(1)abz)(.)/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/(?(1)abz)(1)23/I -Capturing subpattern count = 1 -No options -No first char -Need char = '3' - -/(a)+/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a){2,3}/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/(a)*/I -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - -/[a]/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/[ab]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/[ab]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b - -/[^a]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/\d456/I -Capturing subpattern count = 0 -No options -No first char -Need char = '6' - -/\d456/IS -Capturing subpattern count = 0 -No options -No first char -Need char = '6' -Subject length lower bound = 4 -Starting chars: 0 1 2 3 4 5 6 7 8 9 - -/a^b/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/^a/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'a' - abcde - 0: a - xy\nabc - 0: a - *** Failers -No match - xyabc -No match - -/c|abc/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(?i)[ab]/IS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Subject length lower bound = 1 -Starting chars: A B a b - -/[ab](?i)cd/IS -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' (caseless) -Subject length lower bound = 3 -Starting chars: a b - -/abc(?C)def/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - abcdef ---->abcdef - 0 ^ ^ d - 0: abcdef - 1234abcdef ---->1234abcdef - 0 ^ ^ d - 0: abcdef - *** Failers -No match - abcxyz -No match - abcxyzf ---->abcxyzf - 0 ^ ^ d -No match - -/abc(?C)de(?C1)f/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f - 0: abcdef - -/(?C1)\dabc(?C2)def/IS -Capturing subpattern count = 0 -No options -No first char -Need char = 'f' -Subject length lower bound = 7 -Starting chars: 0 1 2 3 4 5 6 7 8 9 - 1234abcdef ---->1234abcdef - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 2 ^ ^ d - 0: 4abcdef - *** Failers -No match - abcdef -No match - -/(?C1)\dabc(?C2)def/ISS -Capturing subpattern count = 0 -No options -No first char -Need char = 'f' - 1234abcdef ---->1234abcdef - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 2 ^ ^ d - 0: 4abcdef - *** Failers -No match - abcdef ---->abcdef - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d - 1 ^ \d -No match - -/(?C255)ab/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?C256)ab/I -Failed: number after (?C is > 255 at offset 6 - -/(?Cab)xx/I -Failed: closing ) for (?C expected at offset 3 - -/(?C12vr)x/I -Failed: closing ) for (?C expected at offset 5 - -/abc(?C)def/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - *** Failers -No match - \x83\x0\x61bcdef ---->\x83\x00abcdef - 0 ^ ^ d - 0: abcdef - -/(abc)(?C)de(?C1)f/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f - 0: abcdef - 1: abc - 123abcdef\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->123abcdef - ^ ^ d -Callout 1: last capture = 1 - 0: <unset> - 1: abc ---->123abcdef - ^ ^ f - 0: abcdef - 1: abc - 123abcdef\C- - 0: abcdef - 1: abc - *** Failers -No match - 123abcdef\C!1 ---->123abcdef - 0 ^ ^ d - 1 ^ ^ f -No match - -/(?C0)(abc(?C1))*/I -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - abcabcabc ---->abcabcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabcabc - 1: abc - abcabc\C!1!3 ---->abcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabc - 1: abc - *** Failers ---->*** Failers - 0 ^ (abc(?C1))* - 0: - abcabcabc\C!1!3 ---->abcabcabc - 0 ^ (abc(?C1))* - 1 ^ ^ ) - 1 ^ ^ ) - 1 ^ ^ ) - 0: abcabc - 1: abc - -/(\d{3}(?C))*/I -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - 123\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123 - ^ ^ ) - 0: 123 - 1: 123 - 123456\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123456 - ^ ^ ) -Callout 0: last capture = 1 - 0: <unset> - 1: 123 ---->123456 - ^ ^ ) - 0: 123456 - 1: 456 - 123456789\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123456789 - ^ ^ ) -Callout 0: last capture = 1 - 0: <unset> - 1: 123 ---->123456789 - ^ ^ ) -Callout 0: last capture = 1 - 0: <unset> - 1: 456 ---->123456789 - ^ ^ ) - 0: 123456789 - 1: 789 - -/((xyz)(?C)p|(?C1)xyzabc)/I -Capturing subpattern count = 2 -No options -First char = 'x' -No need char - xyzabc\C+ -Callout 0: last capture = 2 - 0: <unset> - 1: <unset> - 2: xyz ---->xyzabc - ^ ^ p -Callout 1: last capture = -1 - 0: <unset> ---->xyzabc - ^ x - 0: xyzabc - 1: xyzabc - -/(X)((xyz)(?C)p|(?C1)xyzabc)/I -Capturing subpattern count = 3 -No options -First char = 'X' -Need char = 'x' - Xxyzabc\C+ -Callout 0: last capture = 3 - 0: <unset> - 1: X - 2: <unset> - 3: xyz ---->Xxyzabc - ^ ^ p -Callout 1: last capture = 1 - 0: <unset> - 1: X ---->Xxyzabc - ^^ x - 0: Xxyzabc - 1: X - 2: xyzabc - -/(?=(abc))(?C)abcdef/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - abcdef\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->abcdef - ^ a - 0: abcdef - 1: abc - -/(?!(abc)(?C1)d)(?C2)abcxyz/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'z' - abcxyz\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: abc ---->abcxyz - ^ ^ d -Callout 2: last capture = -1 - 0: <unset> ---->abcxyz - ^ a - 0: abcxyz - -/(?<=(abc)(?C))xyz/I -Capturing subpattern count = 1 -Max lookbehind = 3 -No options -First char = 'x' -Need char = 'z' - abcxyz\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->abcxyz - ^ ) - 0: xyz - 1: abc - -/a(b+)(c*)(?C1)/I -Capturing subpattern count = 2 -No options -First char = 'a' -Need char = 'b' - abbbbbccc\C*1 ---->abbbbbccc - 1 ^ ^ -Callout data = 1 -No match - -/a(b+?)(c*?)(?C1)/I -Capturing subpattern count = 2 -No options -First char = 'a' -Need char = 'b' - abbbbbccc\C*1 ---->abbbbbccc - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 - 1 ^ ^ -Callout data = 1 -No match - -/(?C)abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(?C)^abc/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?C)a|b/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b - -/(?R)/I -Failed: recursive call could loop indefinitely at offset 3 - -/(a|(?R))/I -Failed: recursive call could loop indefinitely at offset 6 - -/(ab|(bc|(de|(?R))))/I -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?R))))/I -Capturing subpattern count = 3 -No options -First char = 'x' -No need char - xab - 0: xab - 1: ab - xbc - 0: xbc - 1: bc - 2: bc - xde - 0: xde - 1: de - 2: de - 3: de - xxab - 0: xxab - 1: xab - 2: xab - 3: xab - xxxab - 0: xxxab - 1: xxab - 2: xxab - 3: xxab - *** Failers -No match - xyab -No match - -/(ab|(bc|(de|(?1))))/I -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?1)x)x)x)/I -Failed: recursive call could loop indefinitely at offset 16 - -/^([^()]|\((?1)*\))*$/I -Capturing subpattern count = 1 -May match empty string -Options: anchored -No first char -No need char - abc - 0: abc - 1: c - a(b)c - 0: a(b)c - 1: c - a(b(c))d - 0: a(b(c))d - 1: d - *** Failers) -No match - a(b(c)d -No match - -/^>abc>([^()]|\((?1)*\))*<xyz<$/I -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = '<' - >abc>123<xyz< - 0: >abc>123<xyz< - 1: 3 - >abc>1(2)3<xyz< - 0: >abc>1(2)3<xyz< - 1: 3 - >abc>(1(2)3)<xyz< - 0: >abc>(1(2)3)<xyz< - 1: (1(2)3) - -/(a(?1)b)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Recurse - b - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/(a(?1)+b)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Once - Recurse - KetRmax - b - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - 12 - 0: 12 - 1: 12 - (((2+2)*-3)-7) - 0: (((2+2)*-3)-7) - 1: (((2+2)*-3)-7) - 2: - - -12 - 0: -12 - 1: -12 - *** Failers -No match - ((2+2)*-3)-7) -No match - -/^(x(y|(?1){2})z)/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - xyz - 0: xyz - 1: xyz - 2: y - xxyzxyzz - 0: xxyzxyzz - 1: xxyzxyzz - 2: xyzxyz - *** Failers -No match - xxyzz -No match - xxyzxyzxyzz -No match - -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/Ix -Capturing subpattern count = 2 -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - 1: <> - 2: <> - <abcd> - 0: <abcd> - 1: <abcd> - 2: <abcd> - <abc <123> hij> - 0: <abc <123> hij> - 1: <abc <123> hij> - 2: <abc <123> hij> - <abc <def> hij> - 0: <def> - 1: <def> - 2: <def> - <abc<>def> - 0: <abc<>def> - 1: <abc<>def> - 2: <abc<>def> - <abc<> - 0: <> - 1: <> - 2: <> - *** Failers -No match - <abc -No match - -/(?1)/I -Failed: reference to non-existent subpattern at offset 3 - -/((?2)(abc)/I -Failed: missing ) at offset 10 - -/^(abc)def(?1)/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - abcdefabc - 0: abcdefabc - 1: abc - -/^(a|b|c)=(?1)+/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - a=a - 0: a=a - 1: a - a=b - 0: a=b - 1: a - a=bc - 0: a=bc - 1: a - -/^(a|b|c)=((?1))+/I -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - a=a - 0: a=a - 1: a - 2: a - a=b - 0: a=b - 1: a - 2: b - a=bc - 0: a=bc - 1: a - 2: c - -/a(?P<name1>b|c)d(?P<longername2>e)/DZ ------------------------------------------------------------------- - Bra - a - CBra 1 - b - Alt - c - Ket - d - CBra 2 - e - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - longername2 2 - name1 1 -No options -First char = 'a' -Need char = 'e' - abde - 0: abde - 1: b - 2: e - acde - 0: acde - 1: c - 2: e - -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/DZ ------------------------------------------------------------------- - Bra - Bra - a - CBra 1 - c - CBra 2 - d - Ket - Ket - Ket - CBra 3 - a - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 3 -Named capturing subpatterns: - a 3 - c 1 - d 2 -No options -First char = 'a' -Need char = 'a' - -/(?P<a>a)...(?P=a)bbb(?P>a)d/DZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Ket - Any - Any - Any - \1 - bbb - Recurse - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - a 1 -No options -First char = 'a' -Need char = 'd' - -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/Ii -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -May match empty string -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: <unset> - 2: <unset> - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: <unset> - 2: <unset> - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: <unset> - 2: <unset> - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/((?(R)a|b))\1(?1)?/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char - bb - 0: bb - 1: b - bbaa - 0: bba - 1: b - -/(.*)a/Is -Capturing subpattern count = 1 -Options: anchored dotall -No first char -Need char = 'a' - -/(.*)a\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Options: dotall -No first char -Need char = 'a' - -/(.*)a(b)\2/Is -Capturing subpattern count = 2 -Max back reference = 2 -Options: anchored dotall -No first char -Need char = 'b' - -/((.*)a|(.*)b)z/Is -Capturing subpattern count = 3 -Options: anchored dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\1/Is -Capturing subpattern count = 3 -Max back reference = 1 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\2/Is -Capturing subpattern count = 3 -Max back reference = 2 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\3/Is -Capturing subpattern count = 3 -Max back reference = 3 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|^(.*)b)z\3/Is -Capturing subpattern count = 3 -Max back reference = 3 -Options: anchored dotall -No first char -Need char = 'z' - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/Is -Capturing subpattern count = 31 -May match empty string -Options: anchored dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/Is -Capturing subpattern count = 31 -Max back reference = 31 -May match empty string -Options: dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/Is -Capturing subpattern count = 32 -Max back reference = 32 -May match empty string -Options: dotall -No first char -No need char - -/(a)(bc)/INDZ ------------------------------------------------------------------- - Bra - Bra - a - Ket - Bra - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - abc - 0: abc - -/(?P<one>a)(bc)/INDZ ------------------------------------------------------------------- - Bra - CBra 1 - a - Ket - Bra - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - one 1 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - abc - 0: abc - 1: a - -/(a)(?P<named>bc)/INDZ ------------------------------------------------------------------- - Bra - Bra - a - Ket - CBra 1 - bc - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - named 1 -Options: no_auto_capture -First char = 'a' -Need char = 'c' - -/(a+)*zz/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M -Minimum match() limit = 8 -Minimum match() recursion limit = 6 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz - 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaz\M -Minimum match() limit = 32768 -Minimum match() recursion limit = 29 -No match - -/(aaa(?C1)bbb|ab)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaabbb ---->aaabbb - 1 ^ ^ b - 0: aaabbb - 1: aaabbb - aaabbb\C*0 ---->aaabbb - 1 ^ ^ b - 0: aaabbb - 1: aaabbb - aaabbb\C*1 ---->aaabbb - 1 ^ ^ b -Callout data = 1 - 0: ab - 1: ab - aaabbb\C*-1 ---->aaabbb - 1 ^ ^ b -Callout data = -1 -No match - -/ab(?P<one>cd)ef(?P<two>gh)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - one 1 - two 2 -No options -First char = 'a' -Need char = 'h' - abcdefgh - 0: abcdefgh - 1: cd - 2: gh - abcdefgh\C1\Gtwo - 0: abcdefgh - 1: cd - 2: gh - 1C cd (2) - G gh (2) two - abcdefgh\Cone\Ctwo - 0: abcdefgh - 1: cd - 2: gh - C cd (2) one - C gh (2) two - abcdefgh\Cthree -no parentheses with name "three" - 0: abcdefgh - 1: cd - 2: gh -copy substring three failed -7 - -/(?P<Tes>)(?P<Test>)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - Ket - CBra 2 - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 1 - Test 2 -May match empty string -No options -No first char -No need char - -/(?P<Test>)(?P<Tes>)/DZ ------------------------------------------------------------------- - Bra - CBra 1 - Ket - CBra 2 - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 2 - Test 1 -May match empty string -No options -No first char -No need char - -/(?P<Z>zz)(?P<A>aa)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - A 2 - Z 1 -No options -First char = 'z' -Need char = 'a' - zzaa\CZ - 0: zzaa - 1: zz - 2: aa - C zz (2) Z - zzaa\CA - 0: zzaa - 1: zz - 2: aa - C aa (2) A - -/(?P<x>eks)(?P<x>eccs)/I -Failed: two named subpatterns have the same name at offset 15 - -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/I -Failed: two named subpatterns have the same name at offset 30 - -"\[((?P<elem>\d+)(,(?P>elem))*)\]"I -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - *** Failers -No match - [] -No match - -"\[((?P<elem>\d+)(,(?P>elem))*)?\]"I -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - [] - 0: [] - -/(a(b(?2)c))?/DZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - CBra 2 - b - Recurse - c - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -May match empty string -No options -No first char -No need char - -/(a(b(?2)c))*/DZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - CBra 2 - b - Recurse - c - Ket - KetRmax - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -May match empty string -No options -No first char -No need char - -/(a(b(?2)c)){0,2}/DZ ------------------------------------------------------------------- - Bra - Brazero - Bra - CBra 1 - a - CBra 2 - b - Recurse - c - Ket - Ket - Brazero - CBra 1 - a - CBra 2 - b - Recurse - c - Ket - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 2 -May match empty string -No options -No first char -No need char - -/[ab]{1}+/DZ ------------------------------------------------------------------- - Bra - [ab]{1,1}+ - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/Ii -Capturing subpattern count = 3 -Options: caseless -No first char -Need char = 'g' (caseless) - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/IiS -Capturing subpattern count = 3 -Options: caseless -No first char -Need char = 'g' (caseless) -Subject length lower bound = 8 -No starting char list - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/ISDZ ------------------------------------------------------------------- - Bra - a* - Any* - b - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' -Subject length lower bound = 1 -No starting char list - -/(a|b)*.?c/ISDZ ------------------------------------------------------------------- - Bra - Brazero - CBra 1 - a - Alt - b - KetRmax - Any? - c - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' -Subject length lower bound = 1 -No starting char list - -/abc(?C255)de(?C)f/DZ ------------------------------------------------------------------- - Bra - abc - Callout 255 10 1 - de - Callout 0 16 1 - f - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - -/abcde/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 1 - a - Callout 255 1 1 - b - Callout 255 2 1 - c - Callout 255 3 1 - d - Callout 255 4 1 - e - Callout 255 5 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -First char = 'a' -Need char = 'e' - abcde ---->abcde - +0 ^ a - +1 ^^ b - +2 ^ ^ c - +3 ^ ^ d - +4 ^ ^ e - +5 ^ ^ - 0: abcde - abcdfe ---->abcdfe - +0 ^ a - +1 ^^ b - +2 ^ ^ c - +3 ^ ^ d - +4 ^ ^ e -No match - -/a*b/ICDZS ------------------------------------------------------------------- - Bra - Callout 255 0 2 - a*+ - Callout 255 2 1 - b - Callout 255 3 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -No first char -Need char = 'b' -Subject length lower bound = 1 -Starting chars: a b - ab ---->ab - +0 ^ a* - +2 ^^ b - +3 ^ ^ - 0: ab - aaaab ---->aaaab - +0 ^ a* - +2 ^ ^ b - +3 ^ ^ - 0: aaaab - aaaacb ---->aaaacb - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^^ b - +0 ^ a* - +2 ^ b - +3 ^^ - 0: b - -/a*b/ICDZSS ------------------------------------------------------------------- - Bra - Callout 255 0 2 - a*+ - Callout 255 2 1 - b - Callout 255 3 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -No first char -Need char = 'b' - ab ---->ab - +0 ^ a* - +2 ^^ b - +3 ^ ^ - 0: ab - aaaab ---->aaaab - +0 ^ a* - +2 ^ ^ b - +3 ^ ^ - 0: aaaab - aaaacb ---->aaaacb - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^ ^ b - +0 ^ a* - +2 ^^ b - +0 ^ a* - +2 ^ b - +0 ^ a* - +2 ^ b - +3 ^^ - 0: b - -/a+b/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 2 - a++ - Callout 255 2 1 - b - Callout 255 3 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -First char = 'a' -Need char = 'b' - ab ---->ab - +0 ^ a+ - +2 ^^ b - +3 ^ ^ - 0: ab - aaaab ---->aaaab - +0 ^ a+ - +2 ^ ^ b - +3 ^ ^ - 0: aaaab - aaaacb ---->aaaacb - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^ ^ b - +0 ^ a+ - +2 ^^ b -No match - -/(abc|def)x/ICDZS ------------------------------------------------------------------- - Bra - Callout 255 0 9 - CBra 1 - Callout 255 1 1 - a - Callout 255 2 1 - b - Callout 255 3 1 - c - Callout 255 4 0 - Alt - Callout 255 5 1 - d - Callout 255 6 1 - e - Callout 255 7 1 - f - Callout 255 8 0 - Ket - Callout 255 9 1 - x - Callout 255 10 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -Need char = 'x' -Subject length lower bound = 4 -Starting chars: a d - abcx ---->abcx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x -+10 ^ ^ - 0: abcx - 1: abc - defx ---->defx - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x -+10 ^ ^ - 0: defx - 1: def - ** Failers -No match - abcdefzx ---->abcdefzx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x -No match - -/(abc|def)x/ICDZSS ------------------------------------------------------------------- - Bra - Callout 255 0 9 - CBra 1 - Callout 255 1 1 - a - Callout 255 2 1 - b - Callout 255 3 1 - c - Callout 255 4 0 - Alt - Callout 255 5 1 - d - Callout 255 6 1 - e - Callout 255 7 1 - f - Callout 255 8 0 - Ket - Callout 255 9 1 - x - Callout 255 10 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -Need char = 'x' - abcx ---->abcx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x -+10 ^ ^ - 0: abcx - 1: abc - defx ---->defx - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x -+10 ^ ^ - 0: defx - 1: def - ** Failers -No match - abcdefzx ---->abcdefzx - +0 ^ (abc|def) - +1 ^ a - +2 ^^ b - +3 ^ ^ c - +4 ^ ^ | - +9 ^ ^ x - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +6 ^^ e - +7 ^ ^ f - +8 ^ ^ ) - +9 ^ ^ x - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d - +0 ^ (abc|def) - +1 ^ a - +5 ^ d -No match - -/(ab|cd){3,4}/IC -Capturing subpattern count = 1 -Options: -No first char -No need char - ababab ---->ababab - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c -+12 ^ ^ - 0: ababab - 1: ab - abcdabcd ---->abcdabcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +2 ^ ^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdabcd - 1: cd - abcdcdcdcdcd ---->abcdcdcdcdcd - +0 ^ (ab|cd){3,4} - +1 ^ a - +2 ^^ b - +3 ^ ^ | - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) - +1 ^ ^ a - +4 ^ ^ c - +5 ^ ^ d - +6 ^ ^ ) -+12 ^ ^ - 0: abcdcdcd - 1: cd - -/([ab]{,4}c|xy)/ICDZS ------------------------------------------------------------------- - Bra - Callout 255 0 14 - CBra 1 - Callout 255 1 4 - [ab] - Callout 255 5 1 - { - Callout 255 6 1 - , - Callout 255 7 1 - 4 - Callout 255 8 1 - } - Callout 255 9 1 - c - Callout 255 10 0 - Alt - Callout 255 11 1 - x - Callout 255 12 1 - y - Callout 255 13 0 - Ket - Callout 255 14 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b x - Note: that { does NOT introduce a quantifier ---->Note: that { does NOT introduce a quantifier - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x -No match - -/([ab]{,4}c|xy)/ICDZSS ------------------------------------------------------------------- - Bra - Callout 255 0 14 - CBra 1 - Callout 255 1 4 - [ab] - Callout 255 5 1 - { - Callout 255 6 1 - , - Callout 255 7 1 - 4 - Callout 255 8 1 - } - Callout 255 9 1 - c - Callout 255 10 0 - Alt - Callout 255 11 1 - x - Callout 255 12 1 - y - Callout 255 13 0 - Ket - Callout 255 14 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -No need char - Note: that { does NOT introduce a quantifier ---->Note: that { does NOT introduce a quantifier - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] - +5 ^^ { -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x - +0 ^ ([ab]{,4}c|xy) - +1 ^ [ab] -+11 ^ x -No match - -/([ab]{1,4}c|xy){4,5}?123/ICDZ ------------------------------------------------------------------- - Bra - Callout 255 0 21 - CBra 1 - Callout 255 1 9 - [ab]{1,4}+ - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4}+ - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4}+ - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - CBra 1 - Callout 255 1 9 - [ab]{1,4}+ - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - Braminzero - CBra 1 - Callout 255 1 9 - [ab]{1,4}+ - Callout 255 10 1 - c - Callout 255 11 0 - Alt - Callout 255 12 1 - x - Callout 255 13 1 - y - Callout 255 14 0 - Ket - Callout 255 21 1 - 1 - Callout 255 22 1 - 2 - Callout 255 23 1 - 3 - Callout 255 24 0 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: -No first char -Need char = '3' - aacaacaacaacaac123 ---->aacaacaacaacaac123 - +0 ^ ([ab]{1,4}c|xy){4,5}? - +1 ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | -+21 ^ ^ 1 - +1 ^ ^ [ab]{1,4} -+10 ^ ^ c -+11 ^ ^ | -+21 ^ ^ 1 -+22 ^ ^ 2 -+23 ^ ^ 3 -+24 ^ ^ - 0: aacaacaacaacaac123 - 1: aac - -/\b.*/I -Capturing subpattern count = 0 -Max lookbehind = 1 -May match empty string -No options -No first char -No need char - ab cd\>1 - 0: cd - -/\b.*/Is -Capturing subpattern count = 0 -Max lookbehind = 1 -May match empty string -Options: dotall -No first char -No need char - ab cd\>1 - 0: cd - -/(?!.bcd).*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - Xbcd12345 - 0: bcd12345 - -/abcde/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - ab\P -Partial match: ab - abc\P -Partial match: abc - abcd\P -Partial match: abcd - abcde\P - 0: abcde - the quick brown abc\P -Partial match: abc - ** Failers\P -No match - the quick brown abxyz fox\P -No match - -"^(0?[1-9]|[12][0-9]|3[01])/(0?[1-9]|1[012])/(20)?\d\d$"I -Capturing subpattern count = 3 -Options: anchored -No first char -Need char = '/' - 13/05/04\P - 0: 13/05/04 - 1: 13 - 2: 05 - 13/5/2004\P - 0: 13/5/2004 - 1: 13 - 2: 5 - 3: 20 - 02/05/09\P - 0: 02/05/09 - 1: 02 - 2: 05 - 1\P -Partial match: 1 - 1/2\P -Partial match: 1/2 - 1/2/0\P -Partial match: 1/2/0 - 1/2/04\P - 0: 1/2/04 - 1: 1 - 2: 2 - 0\P -Partial match: 0 - 02/\P -Partial match: 02/ - 02/0\P -Partial match: 02/0 - 02/1\P -Partial match: 02/1 - ** Failers\P -No match - \P -No match - 123\P -No match - 33/4/04\P -No match - 3/13/04\P -No match - 0/1/2003\P -No match - 0/\P -No match - 02/0/\P -No match - 02/13\P -No match - -/0{0,2}ABC/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'C' - -/\d{3,}ABC/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'C' - -/\d*ABC/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'C' - -/[abc]+DE/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'E' - -/[abc]?123/I -Capturing subpattern count = 0 -No options -No first char -Need char = '3' - 123\P - 0: 123 - a\P -Partial match: a - b\P -Partial match: b - c\P -Partial match: c - c12\P -Partial match: c12 - c123\P - 0: c123 - -/^(?:\d){3,5}X/I -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'X' - 1\P -Partial match: 1 - 123\P -Partial match: 123 - 123X - 0: 123X - 1234\P -Partial match: 1234 - 1234X - 0: 1234X - 12345\P -Partial match: 12345 - 12345X - 0: 12345X - *** Failers -No match - 1X -No match - 123456\P -No match - -/abc/IS>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Subject length lower bound = 3 -No starting char list -Compiled pattern written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled pattern loaded from testsavedregex -Study data loaded from testsavedregex - abc - 0: abc - ** Failers -No match - bca -No match - -/abc/ISS>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled pattern written to testsavedregex -<testsavedregex -Compiled pattern loaded from testsavedregex -No study data - abc - 0: abc - ** Failers -No match - bca -No match - -/abc/IFS>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Subject length lower bound = 3 -No starting char list -Compiled pattern written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled pattern (byte-inverted) loaded from testsavedregex -Study data loaded from testsavedregex - abc - 0: abc - ** Failers -No match - bca -No match - -/abc/IFSS>testsavedregex -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' -Compiled pattern written to testsavedregex -<testsavedregex -Compiled pattern (byte-inverted) loaded from testsavedregex -No study data - abc - 0: abc - ** Failers -No match - bca -No match - -/(a|b)/IS>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b -Compiled pattern written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled pattern loaded from testsavedregex -Study data loaded from testsavedregex - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -/(a|b)/ISS>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Compiled pattern written to testsavedregex -<testsavedregex -Compiled pattern loaded from testsavedregex -No study data - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -/(a|b)/ISF>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b -Compiled pattern written to testsavedregex -Study data written to testsavedregex -<testsavedregex -Compiled pattern (byte-inverted) loaded from testsavedregex -Study data loaded from testsavedregex - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -/(a|b)/ISSF>testsavedregex -Capturing subpattern count = 1 -No options -No first char -No need char -Compiled pattern written to testsavedregex -<testsavedregex -Compiled pattern (byte-inverted) loaded from testsavedregex -No study data - abc - 0: a - 1: a - ** Failers - 0: a - 1: a - def -No match - -~<(\w+)/?>(.)*</(\1)>~smgI -Capturing subpattern count = 3 -Max back reference = 1 -Options: multiline dotall -First char = '<' -Need char = '>' - \J1024<!DOCTYPE seite SYSTEM "http://www.lco.lineas.de/xmlCms.dtd">\n<seite>\n<dokumenteninformation>\n<seitentitel>Partner der LCO</seitentitel>\n<sprache>de</sprache>\n<seitenbeschreibung>Partner der LINEAS Consulting\nGmbH</seitenbeschreibung>\n<schluesselworte>LINEAS Consulting GmbH Hamburg\nPartnerfirmen</schluesselworte>\n<revisit>30 days</revisit>\n<robots>index,follow</robots>\n<menueinformation>\n<aktiv>ja</aktiv>\n<menueposition>3</menueposition>\n<menuetext>Partner</menuetext>\n</menueinformation>\n<lastedited>\n<autor>LCO</autor>\n<firma>LINEAS Consulting</firma>\n<datum>15.10.2003</datum>\n</lastedited>\n</dokumenteninformation>\n<inhalt>\n\n<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\nGmbH</absatzueberschrift>\n\n<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\n<bild name="logo_ca.gif" rahmen="no"/></link> <link\nziel="http://www.ey.com/" zielfenster="_blank"><bild\nname="logo_euy.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\n<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\n\n<absatz><link ziel="http://www.atelion.de/"\nzielfenster="_blank"><bild\nname="logo_atelion.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><link ziel="http://www.line-information.de/"\nzielfenster="_blank">\n<bild name="logo_line_information.gif" rahmen="no"/></link>\n</absatz>\n\n<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\n\n<absatz><link ziel="http://www.incognis.de/"\nzielfenster="_blank"><bild\nname="logo_incognis.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.addcraft.com/"\nzielfenster="_blank"><bild\nname="logo_addcraft.gif" rahmen="no"/></link></absatz>\n\n<absatz><link ziel="http://www.comendo.com/"\nzielfenster="_blank"><bild\nname="logo_comendo.gif" rahmen="no"/></link></absatz>\n\n</inhalt>\n</seite> - 0: <seite>\x0a<dokumenteninformation>\x0a<seitentitel>Partner der LCO</seitentitel>\x0a<sprache>de</sprache>\x0a<seitenbeschreibung>Partner der LINEAS Consulting\x0aGmbH</seitenbeschreibung>\x0a<schluesselworte>LINEAS Consulting GmbH Hamburg\x0aPartnerfirmen</schluesselworte>\x0a<revisit>30 days</revisit>\x0a<robots>index,follow</robots>\x0a<menueinformation>\x0a<aktiv>ja</aktiv>\x0a<menueposition>3</menueposition>\x0a<menuetext>Partner</menuetext>\x0a</menueinformation>\x0a<lastedited>\x0a<autor>LCO</autor>\x0a<firma>LINEAS Consulting</firma>\x0a<datum>15.10.2003</datum>\x0a</lastedited>\x0a</dokumenteninformation>\x0a<inhalt>\x0a\x0a<absatzueberschrift>Die Partnerfirmen der LINEAS Consulting\x0aGmbH</absatzueberschrift>\x0a\x0a<absatz><link ziel="http://www.ca.com/" zielfenster="_blank">\x0a<bild name="logo_ca.gif" rahmen="no"/></link> <link\x0aziel="http://www.ey.com/" zielfenster="_blank"><bild\x0aname="logo_euy.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><link ziel="http://www.cisco.de/" zielfenster="_blank">\x0a<bild name="logo_cisco.gif" rahmen="ja"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.atelion.de/"\x0azielfenster="_blank"><bild\x0aname="logo_atelion.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><link ziel="http://www.line-information.de/"\x0azielfenster="_blank">\x0a<bild name="logo_line_information.gif" rahmen="no"/></link>\x0a</absatz>\x0a\x0a<absatz><bild name="logo_aw.gif" rahmen="no"/></absatz>\x0a\x0a<absatz><link ziel="http://www.incognis.de/"\x0azielfenster="_blank"><bild\x0aname="logo_incognis.gif" rahmen="no"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.addcraft.com/"\x0azielfenster="_blank"><bild\x0aname="logo_addcraft.gif" rahmen="no"/></link></absatz>\x0a\x0a<absatz><link ziel="http://www.comendo.com/"\x0azielfenster="_blank"><bild\x0aname="logo_comendo.gif" rahmen="no"/></link></absatz>\x0a\x0a</inhalt>\x0a</seite> - 1: seite - 2: \x0a - 3: seite - -/^a/IF -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/line\nbreak/I -Capturing subpattern count = 0 -Contains explicit CR or LF match -No options -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - line one\nthis is a line\nbreak in the second line - 0: line\x0abreak - -/line\nbreak/If -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: firstline -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - ** Failers -No match - line one\nthis is a line\nbreak in the second line -No match - -/line\nbreak/Imf -Capturing subpattern count = 0 -Contains explicit CR or LF match -Options: multiline firstline -First char = 'l' -Need char = 'k' - this is a line\nbreak - 0: line\x0abreak - ** Failers -No match - line one\nthis is a line\nbreak in the second line -No match - -/(?i)(?-i)AbCd/I -Capturing subpattern count = 0 -No options -First char = 'A' -Need char = 'd' - AbCd - 0: AbCd - ** Failers -No match - abcd -No match - -/a{11111111111111111111}/I -Failed: number too big in {} quantifier at offset 22 - -/(){64294967295}/I -Failed: number too big in {} quantifier at offset 14 - -/(){2,4294967295}/I -Failed: number too big in {} quantifier at offset 15 - -"(?i:a)(?i:b)(?i:c)(?i:d)(?i:e)(?i:f)(?i:g)(?i:h)(?i:i)(?i:j)(k)(?i:l)A\1B"I -Capturing subpattern count = 1 -Max back reference = 1 -No options -First char = 'a' (caseless) -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: k - -"(?P<n0>a)(?P<n1>b)(?P<n2>c)(?P<n3>d)(?P<n4>e)(?P<n5>f)(?P<n6>g)(?P<n7>h)(?P<n8>i)(?P<n9>j)(?P<n10>k)(?P<n11>l)A\11B"I -Capturing subpattern count = 12 -Max back reference = 11 -Named capturing subpatterns: - n0 1 - n1 2 - n10 11 - n11 12 - n2 3 - n3 4 - n4 5 - n5 6 - n6 7 - n7 8 - n8 9 - n9 10 -No options -First char = 'a' -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: l - -"(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)A\11B"I -Capturing subpattern count = 12 -Max back reference = 11 -No options -First char = 'a' -Need char = 'B' - abcdefghijklAkB - 0: abcdefghijklAkB - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: l - -"(?P<name0>a)(?P<name1>a)(?P<name2>a)(?P<name3>a)(?P<name4>a)(?P<name5>a)(?P<name6>a)(?P<name7>a)(?P<name8>a)(?P<name9>a)(?P<name10>a)(?P<name11>a)(?P<name12>a)(?P<name13>a)(?P<name14>a)(?P<name15>a)(?P<name16>a)(?P<name17>a)(?P<name18>a)(?P<name19>a)(?P<name20>a)(?P<name21>a)(?P<name22>a)(?P<name23>a)(?P<name24>a)(?P<name25>a)(?P<name26>a)(?P<name27>a)(?P<name28>a)(?P<name29>a)(?P<name30>a)(?P<name31>a)(?P<name32>a)(?P<name33>a)(?P<name34>a)(?P<name35>a)(?P<name36>a)(?P<name37>a)(?P<name38>a)(?P<name39>a)(?P<name40>a)(?P<name41>a)(?P<name42>a)(?P<name43>a)(?P<name44>a)(?P<name45>a)(?P<name46>a)(?P<name47>a)(?P<name48>a)(?P<name49>a)(?P<name50>a)(?P<name51>a)(?P<name52>a)(?P<name53>a)(?P<name54>a)(?P<name55>a)(?P<name56>a)(?P<name57>a)(?P<name58>a)(?P<name59>a)(?P<name60>a)(?P<name61>a)(?P<name62>a)(?P<name63>a)(?P<name64>a)(?P<name65>a)(?P<name66>a)(?P<name67>a)(?P<name68>a)(?P<name69>a)(?P<name70>a)(?P<name71>a)(?P<name72>a)(?P<name73>a)(?P<name74>a)(?P<name75>a)(?P<name76>a)(?P<name77>a)(?P<name78>a)(?P<name79>a)(?P<name80>a)(?P<name81>a)(?P<name82>a)(?P<name83>a)(?P<name84>a)(?P<name85>a)(?P<name86>a)(?P<name87>a)(?P<name88>a)(?P<name89>a)(?P<name90>a)(?P<name91>a)(?P<name92>a)(?P<name93>a)(?P<name94>a)(?P<name95>a)(?P<name96>a)(?P<name97>a)(?P<name98>a)(?P<name99>a)(?P<name100>a)"I -Capturing subpattern count = 101 -Named capturing subpatterns: - name0 1 - name1 2 - name10 11 - name100 101 - name11 12 - name12 13 - name13 14 - name14 15 - name15 16 - name16 17 - name17 18 - name18 19 - name19 20 - name2 3 - name20 21 - name21 22 - name22 23 - name23 24 - name24 25 - name25 26 - name26 27 - name27 28 - name28 29 - name29 30 - name3 4 - name30 31 - name31 32 - name32 33 - name33 34 - name34 35 - name35 36 - name36 37 - name37 38 - name38 39 - name39 40 - name4 5 - name40 41 - name41 42 - name42 43 - name43 44 - name44 45 - name45 46 - name46 47 - name47 48 - name48 49 - name49 50 - name5 6 - name50 51 - name51 52 - name52 53 - name53 54 - name54 55 - name55 56 - name56 57 - name57 58 - name58 59 - name59 60 - name6 7 - name60 61 - name61 62 - name62 63 - name63 64 - name64 65 - name65 66 - name66 67 - name67 68 - name68 69 - name69 70 - name7 8 - name70 71 - name71 72 - name72 73 - name73 74 - name74 75 - name75 76 - name76 77 - name77 78 - name78 79 - name79 80 - name8 9 - name80 81 - name81 82 - name82 83 - name83 84 - name84 85 - name85 86 - name86 87 - name87 88 - name88 89 - name89 90 - name9 10 - name90 91 - name91 92 - name92 93 - name93 94 - name94 95 - name95 96 - name96 97 - name97 98 - name98 99 - name99 100 -No options -First char = 'a' -Need char = 'a' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -Matched, but too many substrings - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -"(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)(a)"I -Capturing subpattern count = 101 -No options -First char = 'a' -Need char = 'a' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -Matched, but too many substrings - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -/[^()]*(?:\((?R)\)[^()]*)*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - (this(and)that)stuff - 0: (this(and)that)stuff - -/[^()]*(?:\((?>(?R))\)[^()]*)*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/[^()]*(?:\((?R)\))*[^()]*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: (this(and)that) - -/(?:\((?R)\))*[^()]*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - ((this)) - 0: ((this)) - -/(?:\((?R)\))|[^()]*/I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char - (this(and)that - 0: - (this(and)that) - 0: - (this) - 0: (this) - ((this)) - 0: ((this)) - -/\x{0000ff}/I -Capturing subpattern count = 0 -No options -First char = \xff -No need char - -/^((?P<A>a1)|(?P<A>a2)b)/I -Failed: two named subpatterns have the same name at offset 17 - -/^((?P<A>a1)|(?P<A>a2)b)/IJ -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -No first char -No need char - a1b\CA - 0: a1 - 1: a1 - 2: a1 - C a1 (2) A - a2b\CA - 0: a2b - 1: a2b - 2: <unset> - 3: a2 - C a2 (2) A - ** Failers -No match - a1b\CZ\CA -no parentheses with name "Z" - 0: a1 - 1: a1 - 2: a1 -copy substring Z failed -7 - C a1 (2) A - -/(?|(?<a>)(?<b>)(?<a>)|(?<a>)(?<b>)(?<a>))/IJ -Capturing subpattern count = 3 -Named capturing subpatterns: - a 1 - a 3 - b 2 -May match empty string -Options: dupnames -No first char -No need char - -/^(?P<A>a)(?P<A>b)/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: anchored dupnames -No first char -No need char - ab\CA - 0: ab - 1: a - 2: b - C a (1) A - -/^(?P<A>a)(?P<A>b)|cd/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: dupnames -No first char -No need char - ab\CA - 0: ab - 1: a - 2: b - C a (1) A - cd\CA - 0: cd -copy substring A failed -7 - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - A 2 - A 3 - A 4 -Options: dupnames -No first char -No need char - cdefgh\CA - 0: cdefgh - 1: <unset> - 2: <unset> - 3: ef - 4: gh - C ef (2) A - -/^((?P<A>a1)|(?P<A>a2)b)/IJ -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -No first char -No need char - a1b\GA - 0: a1 - 1: a1 - 2: a1 - G a1 (2) A - a2b\GA - 0: a2b - 1: a2b - 2: <unset> - 3: a2 - G a2 (2) A - ** Failers -No match - a1b\GZ\GA -no parentheses with name "Z" - 0: a1 - 1: a1 - 2: a1 -get substring Z failed -7 - G a1 (2) A - -/^(?P<A>a)(?P<A>b)/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: anchored dupnames -No first char -No need char - ab\GA - 0: ab - 1: a - 2: b - G a (1) A - -/^(?P<A>a)(?P<A>b)|cd/IJ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 1 - A 2 -Options: dupnames -No first char -No need char - ab\GA - 0: ab - 1: a - 2: b - G a (1) A - cd\GA - 0: cd -get substring A failed -7 - -/^(?P<A>a)(?P<A>b)|cd(?P<A>ef)(?P<A>gh)/IJ -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - A 2 - A 3 - A 4 -Options: dupnames -No first char -No need char - cdefgh\GA - 0: cdefgh - 1: <unset> - 2: <unset> - 3: ef - 4: gh - G ef (2) A - -/(?J)^((?P<A>a1)|(?P<A>a2)b)/I -Capturing subpattern count = 3 -Named capturing subpatterns: - A 2 - A 3 -Options: anchored dupnames -Duplicate name status changes -No first char -No need char - a1b\CA - 0: a1 - 1: a1 - 2: a1 - C a1 (2) A - a2b\CA - 0: a2b - 1: a2b - 2: <unset> - 3: a2 - C a2 (2) A - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<A>d)/I -Failed: two named subpatterns have the same name at offset 37 - -/ In this next test, J is not set at the outer level; consequently it isn't -set in the pattern's options; consequently pcre_get_named_substring() produces -a random value. /Ix -Capturing subpattern count = 1 -Options: extended -First char = 'I' -Need char = 'e' - -/^(?P<A>a) (?J:(?P<B>b)(?P<B>c)) (?P<C>d)/I -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - B 2 - B 3 - C 4 -Options: anchored -Duplicate name status changes -No first char -No need char - a bc d\CA\CB\CC - 0: a bc d - 1: a - 2: b - 3: c - 4: d - C a (1) A - C b (1) B - C d (1) C - -/^(?P<A>a)?(?(A)a|b)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - A 1 -Options: anchored -No first char -No need char - aabc - 0: aa - 1: a - bc - 0: b - ** Failers -No match - abc -No match - -/(?:(?(ZZ)a|b)(?P<ZZ>X))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - bXaX - 0: bXaX - 1: X - -/(?:(?(2y)a|b)(X))+/I -Failed: malformed number or name after (?( at offset 7 - -/(?:(?(ZA)a|b)(?P<ZZ>X))+/I -Failed: reference to non-existent subpattern at offset 9 - -/(?:(?(ZZ)a|b)(?(ZZ)a|b)(?P<ZZ>X))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - bbXaaX - 0: bbXaaX - 1: X - -/(?:(?(ZZ)a|\(b\))\\(?P<ZZ>X))+/I -Capturing subpattern count = 1 -Named capturing subpatterns: - ZZ 1 -No options -No first char -Need char = 'X' - (b)\\Xa\\X - 0: (b)\Xa\X - 1: X - -/(?P<ABC/I -Failed: syntax error in subpattern name (missing terminator) at offset 7 - -/(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - A 1 -No options -No first char -No need char - bXXaYYaY - 0: bXXaYYaY - 1: Y - bXYaXXaX - 0: bX - 1: X - -/()()()()()()()()()(?:(?(A)(?P=A)a|b)(?P<A>X|Y))+/I -Capturing subpattern count = 10 -Max back reference = 10 -Named capturing subpatterns: - A 10 -No options -No first char -No need char - bXXaYYaY - 0: bXXaYYaY - 1: - 2: - 3: - 4: - 5: - 6: - 7: - 8: - 9: -10: Y - -/\s*,\s*/IS -Capturing subpattern count = 0 -No options -No first char -Need char = ',' -Subject length lower bound = 1 -Starting chars: \x09 \x0a \x0b \x0c \x0d \x20 , - \x0b,\x0b - 0: \x0b,\x0b - \x0c,\x0d - 0: \x0c,\x0d - -/^abc/Im -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - xyz\nabc - 0: abc - xyz\nabc\<lf> - 0: abc - xyz\r\nabc\<lf> - 0: abc - xyz\rabc\<cr> - 0: abc - xyz\r\nabc\<crlf> - 0: abc - ** Failers -No match - xyz\nabc\<cr> -No match - xyz\r\nabc\<cr> -No match - xyz\nabc\<crlf> -No match - xyz\rabc\<crlf> -No match - xyz\rabc\<lf> -No match - -/abc$/Im<lf> -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: LF -First char = 'a' -Need char = 'c' - xyzabc - 0: abc - xyzabc\n - 0: abc - xyzabc\npqr - 0: abc - xyzabc\r\<cr> - 0: abc - xyzabc\rpqr\<cr> - 0: abc - xyzabc\r\n\<crlf> - 0: abc - xyzabc\r\npqr\<crlf> - 0: abc - ** Failers -No match - xyzabc\r -No match - xyzabc\rpqr -No match - xyzabc\r\n -No match - xyzabc\r\npqr -No match - -/^abc/Im<cr> -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: CR -First char at start or follows newline -Need char = 'c' - xyz\rabcdef - 0: abc - xyz\nabcdef\<lf> - 0: abc - ** Failers -No match - xyz\nabcdef -No match - -/^abc/Im<lf> -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: LF -First char at start or follows newline -Need char = 'c' - xyz\nabcdef - 0: abc - xyz\rabcdef\<cr> - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/^abc/Im<crlf> -Capturing subpattern count = 0 -Options: multiline -Forced newline sequence: CRLF -First char at start or follows newline -Need char = 'c' - xyz\r\nabcdef - 0: abc - xyz\rabcdef\<cr> - 0: abc - ** Failers -No match - xyz\rabcdef -No match - -/^abc/Im<bad> -Unknown modifier at: <bad> - - -/abc/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - xyz\rabc\<bad> -Unknown escape sequence at: <bad> - abc - 0: abc - -/.*/I<lf> -Capturing subpattern count = 0 -May match empty string -Options: -Forced newline sequence: LF -First char at start or follows newline -No need char - abc\ndef - 0: abc - abc\rdef - 0: abc\x0ddef - abc\r\ndef - 0: abc\x0d - \<cr>abc\ndef - 0: abc\x0adef - \<cr>abc\rdef - 0: abc - \<cr>abc\r\ndef - 0: abc - \<crlf>abc\ndef - 0: abc\x0adef - \<crlf>abc\rdef - 0: abc\x0ddef - \<crlf>abc\r\ndef - 0: abc - -/\w+(.)(.)?def/Is -Capturing subpattern count = 2 -Options: dotall -No first char -Need char = 'f' - abc\ndef - 0: abc\x0adef - 1: \x0a - abc\rdef - 0: abc\x0ddef - 1: \x0d - abc\r\ndef - 0: abc\x0d\x0adef - 1: \x0d - 2: \x0a - -+((?:\s|//.*\\n|/[*](?:\\n|.)*?[*]/)*)+I -Capturing subpattern count = 1 -May match empty string -No options -No first char -No need char - /* this is a C style comment */\M -Minimum match() limit = 120 -Minimum match() recursion limit = 6 - 0: /* this is a C style comment */ - 1: /* this is a C style comment */ - -/(?P<B>25[0-5]|2[0-4]\d|[01]?\d?\d)(?:\.(?P>B)){3}/I -Capturing subpattern count = 1 -Named capturing subpatterns: - B 1 -No options -No first char -Need char = '.' - -/()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - ()()()()()()()()()()()()()()()()()()()() - (.(.))/Ix -Capturing subpattern count = 102 -Options: extended -No first char -No need char - XY\O400 - 0: XY - 1: - 2: - 3: - 4: - 5: - 6: - 7: - 8: - 9: -10: -11: -12: -13: -14: -15: -16: -17: -18: -19: -20: -21: -22: -23: -24: -25: -26: -27: -28: -29: -30: -31: -32: -33: -34: -35: -36: -37: -38: -39: -40: -41: -42: -43: -44: -45: -46: -47: -48: -49: -50: -51: -52: -53: -54: -55: -56: -57: -58: -59: -60: -61: -62: -63: -64: -65: -66: -67: -68: -69: -70: -71: -72: -73: -74: -75: -76: -77: -78: -79: -80: -81: -82: -83: -84: -85: -86: -87: -88: -89: -90: -91: -92: -93: -94: -95: -96: -97: -98: -99: -100: -101: XY -102: Y - -/(a*b|(?i:c*(?-i)d))/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: C a b c d - -/()[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b - -/(|)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b - -/(|c)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b c - -/(|c?)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b c - -/(d?|c?)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b c d - -/(d?|c)[ab]xyz/IS -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' -Subject length lower bound = 4 -Starting chars: a b c d - -/^a*b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'b' - -/^a*+b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'b' - -/^a*?b\d/DZ ------------------------------------------------------------------- - Bra - ^ - a*+ - b - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'b' - -/^a+A\d/DZ ------------------------------------------------------------------- - Bra - ^ - a++ - A - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'A' - aaaA5 - 0: aaaA5 - ** Failers -No match - aaaa5 -No match - -/^a*A\d/IiDZ ------------------------------------------------------------------- - Bra - ^ - /i a* - /i A - \d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored caseless -No first char -Need char = 'A' (caseless) - aaaA5 - 0: aaaA5 - aaaa5 - 0: aaaa5 - -/(a*|b*)[cd]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b c d - -/(a+|b*)[cd]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b c d - -/(a*|b+)[cd]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: a b c d - -/(a+|b+)[cd]/IS -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((( - ((( - a - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - )))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) - ))) -/Ix -Capturing subpattern count = 203 -Options: extended -First char = 'a' -No need char - large nest -Matched, but too many substrings - 0: a - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a -11: a -12: a -13: a -14: a - -/a*\d/BZ ------------------------------------------------------------------- - Bra - a*+ - \d - Ket - End ------------------------------------------------------------------- - -/a*\D/BZ ------------------------------------------------------------------- - Bra - a* - \D - Ket - End ------------------------------------------------------------------- - -/0*\d/BZ ------------------------------------------------------------------- - Bra - 0* - \d - Ket - End ------------------------------------------------------------------- - -/0*\D/BZ ------------------------------------------------------------------- - Bra - 0*+ - \D - Ket - End ------------------------------------------------------------------- - -/a*\s/BZ ------------------------------------------------------------------- - Bra - a*+ - \s - Ket - End ------------------------------------------------------------------- - -/a*\S/BZ ------------------------------------------------------------------- - Bra - a* - \S - Ket - End ------------------------------------------------------------------- - -/ *\s/BZ ------------------------------------------------------------------- - Bra - * - \s - Ket - End ------------------------------------------------------------------- - -/ *\S/BZ ------------------------------------------------------------------- - Bra - *+ - \S - Ket - End ------------------------------------------------------------------- - -/a*\w/BZ ------------------------------------------------------------------- - Bra - a* - \w - Ket - End ------------------------------------------------------------------- - -/a*\W/BZ ------------------------------------------------------------------- - Bra - a*+ - \W - Ket - End ------------------------------------------------------------------- - -/=*\w/BZ ------------------------------------------------------------------- - Bra - =*+ - \w - Ket - End ------------------------------------------------------------------- - -/=*\W/BZ ------------------------------------------------------------------- - Bra - =* - \W - Ket - End ------------------------------------------------------------------- - -/\d*a/BZ ------------------------------------------------------------------- - Bra - \d*+ - a - Ket - End ------------------------------------------------------------------- - -/\d*2/BZ ------------------------------------------------------------------- - Bra - \d* - 2 - Ket - End ------------------------------------------------------------------- - -/\d*\d/BZ ------------------------------------------------------------------- - Bra - \d* - \d - Ket - End ------------------------------------------------------------------- - -/\d*\D/BZ ------------------------------------------------------------------- - Bra - \d*+ - \D - Ket - End ------------------------------------------------------------------- - -/\d*\s/BZ ------------------------------------------------------------------- - Bra - \d*+ - \s - Ket - End ------------------------------------------------------------------- - -/\d*\S/BZ ------------------------------------------------------------------- - Bra - \d* - \S - Ket - End ------------------------------------------------------------------- - -/\d*\w/BZ ------------------------------------------------------------------- - Bra - \d* - \w - Ket - End ------------------------------------------------------------------- - -/\d*\W/BZ ------------------------------------------------------------------- - Bra - \d*+ - \W - Ket - End ------------------------------------------------------------------- - -/\D*a/BZ ------------------------------------------------------------------- - Bra - \D* - a - Ket - End ------------------------------------------------------------------- - -/\D*2/BZ ------------------------------------------------------------------- - Bra - \D*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\D*\d/BZ ------------------------------------------------------------------- - Bra - \D*+ - \d - Ket - End ------------------------------------------------------------------- - -/\D*\D/BZ ------------------------------------------------------------------- - Bra - \D* - \D - Ket - End ------------------------------------------------------------------- - -/\D*\s/BZ ------------------------------------------------------------------- - Bra - \D* - \s - Ket - End ------------------------------------------------------------------- - -/\D*\S/BZ ------------------------------------------------------------------- - Bra - \D* - \S - Ket - End ------------------------------------------------------------------- - -/\D*\w/BZ ------------------------------------------------------------------- - Bra - \D* - \w - Ket - End ------------------------------------------------------------------- - -/\D*\W/BZ ------------------------------------------------------------------- - Bra - \D* - \W - Ket - End ------------------------------------------------------------------- - -/\s*a/BZ ------------------------------------------------------------------- - Bra - \s*+ - a - Ket - End ------------------------------------------------------------------- - -/\s*2/BZ ------------------------------------------------------------------- - Bra - \s*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\s*\d/BZ ------------------------------------------------------------------- - Bra - \s*+ - \d - Ket - End ------------------------------------------------------------------- - -/\s*\D/BZ ------------------------------------------------------------------- - Bra - \s* - \D - Ket - End ------------------------------------------------------------------- - -/\s*\s/BZ ------------------------------------------------------------------- - Bra - \s* - \s - Ket - End ------------------------------------------------------------------- - -/\s*\S/BZ ------------------------------------------------------------------- - Bra - \s*+ - \S - Ket - End ------------------------------------------------------------------- - -/\s*\w/BZ ------------------------------------------------------------------- - Bra - \s*+ - \w - Ket - End ------------------------------------------------------------------- - -/\s*\W/BZ ------------------------------------------------------------------- - Bra - \s* - \W - Ket - End ------------------------------------------------------------------- - -/\S*a/BZ ------------------------------------------------------------------- - Bra - \S* - a - Ket - End ------------------------------------------------------------------- - -/\S*2/BZ ------------------------------------------------------------------- - Bra - \S* - 2 - Ket - End ------------------------------------------------------------------- - -/\S*\d/BZ ------------------------------------------------------------------- - Bra - \S* - \d - Ket - End ------------------------------------------------------------------- - -/\S*\D/BZ ------------------------------------------------------------------- - Bra - \S* - \D - Ket - End ------------------------------------------------------------------- - -/\S*\s/BZ ------------------------------------------------------------------- - Bra - \S*+ - \s - Ket - End ------------------------------------------------------------------- - -/\S*\S/BZ ------------------------------------------------------------------- - Bra - \S* - \S - Ket - End ------------------------------------------------------------------- - -/\S*\w/BZ ------------------------------------------------------------------- - Bra - \S* - \w - Ket - End ------------------------------------------------------------------- - -/\S*\W/BZ ------------------------------------------------------------------- - Bra - \S* - \W - Ket - End ------------------------------------------------------------------- - -/\w*a/BZ ------------------------------------------------------------------- - Bra - \w* - a - Ket - End ------------------------------------------------------------------- - -/\w*2/BZ ------------------------------------------------------------------- - Bra - \w* - 2 - Ket - End ------------------------------------------------------------------- - -/\w*\d/BZ ------------------------------------------------------------------- - Bra - \w* - \d - Ket - End ------------------------------------------------------------------- - -/\w*\D/BZ ------------------------------------------------------------------- - Bra - \w* - \D - Ket - End ------------------------------------------------------------------- - -/\w*\s/BZ ------------------------------------------------------------------- - Bra - \w*+ - \s - Ket - End ------------------------------------------------------------------- - -/\w*\S/BZ ------------------------------------------------------------------- - Bra - \w* - \S - Ket - End ------------------------------------------------------------------- - -/\w*\w/BZ ------------------------------------------------------------------- - Bra - \w* - \w - Ket - End ------------------------------------------------------------------- - -/\w*\W/BZ ------------------------------------------------------------------- - Bra - \w*+ - \W - Ket - End ------------------------------------------------------------------- - -/\W*a/BZ ------------------------------------------------------------------- - Bra - \W*+ - a - Ket - End ------------------------------------------------------------------- - -/\W*2/BZ ------------------------------------------------------------------- - Bra - \W*+ - 2 - Ket - End ------------------------------------------------------------------- - -/\W*\d/BZ ------------------------------------------------------------------- - Bra - \W*+ - \d - Ket - End ------------------------------------------------------------------- - -/\W*\D/BZ ------------------------------------------------------------------- - Bra - \W* - \D - Ket - End ------------------------------------------------------------------- - -/\W*\s/BZ ------------------------------------------------------------------- - Bra - \W* - \s - Ket - End ------------------------------------------------------------------- - -/\W*\S/BZ ------------------------------------------------------------------- - Bra - \W* - \S - Ket - End ------------------------------------------------------------------- - -/\W*\w/BZ ------------------------------------------------------------------- - Bra - \W*+ - \w - Ket - End ------------------------------------------------------------------- - -/\W*\W/BZ ------------------------------------------------------------------- - Bra - \W* - \W - Ket - End ------------------------------------------------------------------- - -/[^a]+a/BZ ------------------------------------------------------------------- - Bra - [^a]++ - a - Ket - End ------------------------------------------------------------------- - -/[^a]+a/BZi ------------------------------------------------------------------- - Bra - /i [^a]++ - /i a - Ket - End ------------------------------------------------------------------- - -/[^a]+A/BZi ------------------------------------------------------------------- - Bra - /i [^a]++ - /i A - Ket - End ------------------------------------------------------------------- - -/[^a]+b/BZ ------------------------------------------------------------------- - Bra - [^a]+ - b - Ket - End ------------------------------------------------------------------- - -/[^a]+\d/BZ ------------------------------------------------------------------- - Bra - [^a]+ - \d - Ket - End ------------------------------------------------------------------- - -/a*[^a]/BZ ------------------------------------------------------------------- - Bra - a*+ - [^a] - Ket - End ------------------------------------------------------------------- - -/(?P<abc>x)(?P<xyz>y)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - abc 1 - xyz 2 -No options -First char = 'x' -Need char = 'y' - xy\Cabc\Cxyz - 0: xy - 1: x - 2: y - C x (1) abc - C y (1) xyz - -/(?<abc>x)(?'xyz'y)/I -Capturing subpattern count = 2 -Named capturing subpatterns: - abc 1 - xyz 2 -No options -First char = 'x' -Need char = 'y' - xy\Cabc\Cxyz - 0: xy - 1: x - 2: y - C x (1) abc - C y (1) xyz - -/(?<abc'x)(?'xyz'y)/I -Failed: syntax error in subpattern name (missing terminator) at offset 6 - -/(?<abc>x)(?'xyz>y)/I -Failed: syntax error in subpattern name (missing terminator) at offset 15 - -/(?P'abc'x)(?P<xyz>y)/I -Failed: unrecognized character after (?P at offset 3 - -/^(?:(?(ZZ)a|b)(?<ZZ>X))+/ - bXaX - 0: bXaX - 1: X - bXbX - 0: bX - 1: X - ** Failers -No match - aXaX -No match - aXbX -No match - -/^(?P>abc)(?<abcd>xxx)/ -Failed: reference to non-existent subpattern at offset 8 - -/^(?P>abc)(?<abc>x|y)/ - xx - 0: xx - 1: x - xy - 0: xy - 1: y - yy - 0: yy - 1: y - yx - 0: yx - 1: x - -/^(?P>abc)(?P<abc>x|y)/ - xx - 0: xx - 1: x - xy - 0: xy - 1: y - yy - 0: yy - 1: y - yx - 0: yx - 1: x - -/^((?(abc)a|b)(?<abc>x|y))+/ - bxay - 0: bxay - 1: ay - 2: y - bxby - 0: bx - 1: bx - 2: x - ** Failers -No match - axby -No match - -/^(((?P=abc)|X)(?<abc>x|y))+/ - XxXxxx - 0: XxXxxx - 1: xx - 2: x - 3: x - XxXyyx - 0: XxXyyx - 1: yx - 2: y - 3: x - XxXyxx - 0: XxXy - 1: Xy - 2: X - 3: y - ** Failers -No match - x -No match - -/^(?1)(abc)/ - abcabc - 0: abcabc - 1: abc - -/^(?:(?:\1|X)(a|b))+/ - Xaaa - 0: Xaaa - 1: a - Xaba - 0: Xa - 1: a - -/^[\E\Qa\E-\Qz\E]+/BZ ------------------------------------------------------------------- - Bra - ^ - [a-z]++ - Ket - End ------------------------------------------------------------------- - -/^[a\Q]bc\E]/BZ ------------------------------------------------------------------- - Bra - ^ - [\]a-c] - Ket - End ------------------------------------------------------------------- - -/^[a-\Q\E]/BZ ------------------------------------------------------------------- - Bra - ^ - [\-a] - Ket - End ------------------------------------------------------------------- - -/^(?P>abc)[()](?<abc>)/BZ ------------------------------------------------------------------- - Bra - ^ - Recurse - [()] - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^((?(abc)y)[()](?P<abc>x))+/BZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - Cond - 2 Cond ref - y - Ket - [()] - CBra 2 - x - Ket - KetRmax - Ket - End ------------------------------------------------------------------- - (xy)x - 0: (xy)x - 1: y)x - 2: x - -/^(?P>abc)\Q()\E(?<abc>)/BZ ------------------------------------------------------------------- - Bra - ^ - Recurse - () - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^(?P>abc)[a\Q(]\E(](?<abc>)/BZ ------------------------------------------------------------------- - Bra - ^ - Recurse - [(\]a] - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^(?P>abc) # this is (a comment) - (?<abc>)/BZx ------------------------------------------------------------------- - Bra - ^ - Recurse - CBra 1 - Ket - Ket - End ------------------------------------------------------------------- - -/^\W*(?:(?<one>(?<two>.)\W*(?&one)\W*\k<two>|)|(?<three>(?<four>.)\W*(?&three)\W*\k'four'|\W*.\W*))\W*$/Ii -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -May match empty string -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: <unset> - 2: <unset> - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: <unset> - 2: <unset> - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: <unset> - 2: <unset> - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/(?=(\w+))\1:/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -Need char = ':' - abcd: - 0: abcd: - 1: abcd - -/(?=(?'abc'\w+))\k<abc>:/I -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - abc 1 -No options -No first char -Need char = ':' - abcd: - 0: abcd: - 1: abcd - -/(?'abc'a|b)(?<abc>d|e)\k<abc>{2}/J - adaa - 0: adaa - 1: a - 2: d - ** Failers -No match - addd -No match - adbb -No match - -/(?'abc'a|b)(?<abc>d|e)(?&abc){2}/J - bdaa - 0: bdaa - 1: b - 2: d - bdab - 0: bdab - 1: b - 2: d - ** Failers -No match - bddd -No match - -/(?(<bc))/ -Failed: malformed number or name after (?( at offset 6 - -/(?(''))/ -Failed: assertion expected after (?( at offset 4 - -/(?('R')stuff)/ -Failed: reference to non-existent subpattern at offset 7 - -/((abc (?(R) (?(R1)1) (?(R2)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - 0: abcabc1Xabc2XabcX - 1: abcabc1Xabc2XabcX - 2: abcabc1Xabc2XabcX - -/(?<A> (?'B' abc (?(R) (?(R&A)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x - abcabc1Xabc2XabcXabcabc - 0: abcabc1Xabc2XabcX - 1: abcabc1Xabc2XabcX - 2: abcabc1Xabc2XabcX - -/(?<A> (?'B' abc (?(R) (?(R&C)1) (?(R&B)2) X | (?1) (?2) (?R) ))) /x -Failed: reference to non-existent subpattern at offset 29 - -/^(?(DEFINE) abc | xyz ) /x -Failed: DEFINE group contains more than one branch at offset 22 - -/(?(DEFINE) abc) xyz/xI -Capturing subpattern count = 0 -Options: extended -First char = 'x' -Need char = 'z' - -/(a|)*\d/ - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - \O0aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa4 -Matched, but too many substrings - -/^a.b/<lf> - a\rb - 0: a\x0db - a\nb\<cr> - 0: a\x0ab - a\x85b\<anycrlf> - 0: a\x85b - ** Failers -No match - a\nb -No match - a\nb\<any> -No match - a\rb\<cr> -No match - a\rb\<any> -No match - a\x85b\<any> -No match - a\rb\<anycrlf> -No match - -/^abc./mgx<any> - abc1 \x0aabc2 \x0babc3xx \x0cabc4 \x0dabc5xx \x0d\x0aabc6 \x85abc7 JUNK - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc7 - -/abc.$/mgx<any> - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc7 abc9 - 0: abc1 - 0: abc2 - 0: abc3 - 0: abc4 - 0: abc5 - 0: abc6 - 0: abc9 - -/a/<cr><any> - -/a/<any><crlf> -Failed: inconsistent NEWLINE options at offset 0 - -/^a\Rb/<bsr_unicode> - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - ** Failers -No match - a\n\rb -No match - -/^a\R*b/<bsr_unicode> - ab - 0: ab - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - -/^a\R+b/<bsr_unicode> - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - a\r\nb - 0: a\x0d\x0ab - a\x0bb - 0: a\x0bb - a\x0cb - 0: a\x0cb - a\x85b - 0: a\x85b - a\n\rb - 0: a\x0a\x0db - a\n\r\x85\x0cb - 0: a\x0a\x0d\x85\x0cb - ** Failers -No match - ab -No match - -/^a\R{1,3}b/<bsr_unicode> - a\nb - 0: a\x0ab - a\n\rb - 0: a\x0a\x0db - a\n\r\x85b - 0: a\x0a\x0d\x85b - a\r\n\r\nb - 0: a\x0d\x0a\x0d\x0ab - a\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0ab - a\n\r\n\rb - 0: a\x0a\x0d\x0a\x0db - a\n\n\r\nb - 0: a\x0a\x0a\x0d\x0ab - ** Failers -No match - a\n\n\n\rb -No match - a\r -No match - -/^a[\R]b/<bsr_unicode> - aRb - 0: aRb - ** Failers -No match - a\nb -No match - -/(?&abc)X(?<abc>P)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - abc 1 -No options -No first char -Need char = 'P' - abcPXP123 - 0: PXP - 1: P - -/(?1)X(?<abc>P)/I -Capturing subpattern count = 1 -Named capturing subpatterns: - abc 1 -No options -No first char -Need char = 'P' - abcPXP123 - 0: PXP - 1: P - -/(?:a(?&abc)b)*(?<abc>x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - 123axbaxbaxb456 - 0: x - 1: x - -/(?:a(?&abc)b){1,5}(?<abc>x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(?:a(?&abc)b){2,5}(?<abc>x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(?:a(?&abc)b){2,}(?<abc>x)/ - 123axbaxbaxbx456 - 0: axbaxbaxbx - 1: x - -/(abc)(?i:(?1))/ - defabcabcxyz - 0: abcabc - 1: abc - DEFabcABCXYZ -No match - -/(abc)(?:(?i)(?1))/ - defabcabcxyz - 0: abcabc - 1: abc - DEFabcABCXYZ -No match - -/^(a)\g-2/ -Failed: reference to non-existent subpattern at offset 7 - -/^(a)\g/ -Failed: a numbered reference must not be zero at offset 5 - -/^(a)\g{0}/ -Failed: a numbered reference must not be zero at offset 8 - -/^(a)\g{3/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 8 - -/^(a)\g{aa}/ -Failed: reference to non-existent subpattern at offset 9 - -/^a.b/<lf> - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/.+foo/ - afoo - 0: afoo - ** Failers -No match - \r\nfoo -No match - \nfoo -No match - -/.+foo/<crlf> - afoo - 0: afoo - \nfoo - 0: \x0afoo - ** Failers -No match - \r\nfoo -No match - -/.+foo/<any> - afoo - 0: afoo - ** Failers -No match - \nfoo -No match - \r\nfoo -No match - -/.+foo/s - afoo - 0: afoo - \r\nfoo - 0: \x0d\x0afoo - \nfoo - 0: \x0afoo - -/^$/mg<any> - abc\r\rxyz - 0: - abc\n\rxyz - 0: - ** Failers -No match - abc\r\nxyz -No match - -/(?m)^$/<any>g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a - -/(?m)^$|^\r\n/<any>g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a - 0: \x0d\x0a - 0+ - -/(?m)$/<any>g+ - abc\r\n\r\n - 0: - 0+ \x0d\x0a\x0d\x0a - 0: - 0+ \x0d\x0a - 0: - 0+ - -/abc.$/mgx<anycrlf> - abc1\x0a abc2\x0b abc3\x0c abc4\x0d abc5\x0d\x0a abc6\x85 abc9 - 0: abc1 - 0: abc4 - 0: abc5 - 0: abc9 - -/^X/m - XABC - 0: X - ** Failers -No match - XABC\B -No match - -/(ab|c)(?-1)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - ab - Alt - c - Ket - Recurse - Ket - End ------------------------------------------------------------------- - abc - 0: abc - 1: ab - -/xy(?+1)(abc)/BZ ------------------------------------------------------------------- - Bra - xy - Recurse - CBra 1 - abc - Ket - Ket - End ------------------------------------------------------------------- - xyabcabc - 0: xyabcabc - 1: abc - ** Failers -No match - xyabc -No match - -/x(?-0)y/ -Failed: a numbered reference must not be zero at offset 5 - -/x(?-1)y/ -Failed: reference to non-existent subpattern at offset 5 - -/x(?+0)y/ -Failed: a numbered reference must not be zero at offset 5 - -/x(?+1)y/ -Failed: reference to non-existent subpattern at offset 5 - -/^(abc)?(?(-1)X|Y)/BZ ------------------------------------------------------------------- - Bra - ^ - Brazero - CBra 1 - abc - Ket - Cond - 1 Cond ref - X - Alt - Y - Ket - Ket - End ------------------------------------------------------------------- - abcX - 0: abcX - 1: abc - Y - 0: Y - ** Failers -No match - abcY -No match - -/^((?(+1)X|Y)(abc))+/BZ ------------------------------------------------------------------- - Bra - ^ - CBra 1 - Cond - 2 Cond ref - X - Alt - Y - Ket - CBra 2 - abc - Ket - KetRmax - Ket - End ------------------------------------------------------------------- - YabcXabc - 0: YabcXabc - 1: Xabc - 2: abc - YabcXabcXabc - 0: YabcXabcXabc - 1: Xabc - 2: abc - ** Failers -No match - XabcXabc -No match - -/(?(-1)a)/BZ -Failed: reference to non-existent subpattern at offset 6 - -/((?(-1)a))/BZ ------------------------------------------------------------------- - Bra - CBra 1 - Cond - 1 Cond ref - a - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/((?(-2)a))/BZ -Failed: reference to non-existent subpattern at offset 7 - -/^(?(+1)X|Y)(.)/BZ ------------------------------------------------------------------- - Bra - ^ - Cond - 1 Cond ref - X - Alt - Y - Ket - CBra 1 - Any - Ket - Ket - End ------------------------------------------------------------------- - Y! - 0: Y! - 1: ! - -/(?<A>tom|bon)-\k{A}/ - tom-tom - 0: tom-tom - 1: tom - bon-bon - 0: bon-bon - 1: bon - ** Failers -No match - tom-bon -No match - -/\g{A/ -Failed: syntax error in subpattern name (missing terminator) at offset 4 - -/(?|(abc)|(xyz))/BZ ------------------------------------------------------------------- - Bra - Bra - CBra 1 - abc - Ket - Alt - CBra 1 - xyz - Ket - Ket - Ket - End ------------------------------------------------------------------- - >abc< - 0: abc - 1: abc - >xyz< - 0: xyz - 1: xyz - -/(x)(?|(abc)|(xyz))(x)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - x - Ket - Bra - CBra 2 - abc - Ket - Alt - CBra 2 - xyz - Ket - Ket - CBra 3 - x - Ket - Ket - End ------------------------------------------------------------------- - xabcx - 0: xabcx - 1: x - 2: abc - 3: x - xxyzx - 0: xxyzx - 1: x - 2: xyz - 3: x - -/(x)(?|(abc)(pqr)|(xyz))(x)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - x - Ket - Bra - CBra 2 - abc - Ket - CBra 3 - pqr - Ket - Alt - CBra 2 - xyz - Ket - Ket - CBra 4 - x - Ket - Ket - End ------------------------------------------------------------------- - xabcpqrx - 0: xabcpqrx - 1: x - 2: abc - 3: pqr - 4: x - xxyzx - 0: xxyzx - 1: x - 2: xyz - 3: <unset> - 4: x - -/\H++X/BZ ------------------------------------------------------------------- - Bra - \H++ - X - Ket - End ------------------------------------------------------------------- - ** Failers -No match - XXXX -No match - -/\H+\hY/BZ ------------------------------------------------------------------- - Bra - \H++ - \h - Y - Ket - End ------------------------------------------------------------------- - XXXX Y - 0: XXXX Y - -/\H+ Y/BZ ------------------------------------------------------------------- - Bra - \H++ - Y - Ket - End ------------------------------------------------------------------- - -/\h+A/BZ ------------------------------------------------------------------- - Bra - \h++ - A - Ket - End ------------------------------------------------------------------- - -/\v*B/BZ ------------------------------------------------------------------- - Bra - \v*+ - B - Ket - End ------------------------------------------------------------------- - -/\V+\x0a/BZ ------------------------------------------------------------------- - Bra - \V++ - \x0a - Ket - End ------------------------------------------------------------------- - -/A+\h/BZ ------------------------------------------------------------------- - Bra - A++ - \h - Ket - End ------------------------------------------------------------------- - -/ *\H/BZ ------------------------------------------------------------------- - Bra - *+ - \H - Ket - End ------------------------------------------------------------------- - -/A*\v/BZ ------------------------------------------------------------------- - Bra - A*+ - \v - Ket - End ------------------------------------------------------------------- - -/\x0b*\V/BZ ------------------------------------------------------------------- - Bra - \x0b*+ - \V - Ket - End ------------------------------------------------------------------- - -/\d+\h/BZ ------------------------------------------------------------------- - Bra - \d++ - \h - Ket - End ------------------------------------------------------------------- - -/\d*\v/BZ ------------------------------------------------------------------- - Bra - \d*+ - \v - Ket - End ------------------------------------------------------------------- - -/S+\h\S+\v/BZ ------------------------------------------------------------------- - Bra - S++ - \h - \S++ - \v - Ket - End ------------------------------------------------------------------- - -/\w{3,}\h\w+\v/BZ ------------------------------------------------------------------- - Bra - \w{3} - \w*+ - \h - \w++ - \v - Ket - End ------------------------------------------------------------------- - -/\h+\d\h+\w\h+\S\h+\H/BZ ------------------------------------------------------------------- - Bra - \h++ - \d - \h++ - \w - \h++ - \S - \h++ - \H - Ket - End ------------------------------------------------------------------- - -/\v+\d\v+\w\v+\S\v+\V/BZ ------------------------------------------------------------------- - Bra - \v++ - \d - \v++ - \w - \v++ - \S - \v++ - \V - Ket - End ------------------------------------------------------------------- - -/\H+\h\H+\d/BZ ------------------------------------------------------------------- - Bra - \H++ - \h - \H+ - \d - Ket - End ------------------------------------------------------------------- - -/\V+\v\V+\w/BZ ------------------------------------------------------------------- - Bra - \V++ - \v - \V+ - \w - Ket - End ------------------------------------------------------------------- - -/\( (?: [^()]* | (?R) )* \)/x -\J1024(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) - 0: (0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(0(00)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0)0) - -/[\E]AAA/ -Failed: missing terminating ] for character class at offset 7 - -/[\Q\E]AAA/ -Failed: missing terminating ] for character class at offset 9 - -/[^\E]AAA/ -Failed: missing terminating ] for character class at offset 8 - -/[^\Q\E]AAA/ -Failed: missing terminating ] for character class at offset 10 - -/[\E^]AAA/ -Failed: missing terminating ] for character class at offset 8 - -/[\Q\E^]AAA/ -Failed: missing terminating ] for character class at offset 10 - -/A(*PRUNE)B(*SKIP)C(*THEN)D(*COMMIT)E(*F)F(*FAIL)G(?!)H(*ACCEPT)I/BZ ------------------------------------------------------------------- - Bra - A - *PRUNE - B - *SKIP - C - *THEN - D - *COMMIT - E - *FAIL - F - *FAIL - G - *FAIL - H - *ACCEPT - I - Ket - End ------------------------------------------------------------------- - -/^a+(*FAIL)/C - aaaaaa ---->aaaaaa - +0 ^ ^ - +1 ^ a+ - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^ ^ (*FAIL) - +3 ^^ (*FAIL) -No match - -/a+b?c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ c+ - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) - +6 ^ ^ (*FAIL) -No match - -/a+b?(*PRUNE)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ (*PRUNE) -+12 ^ ^ c+ -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -+14 ^ ^ (*FAIL) -No match - -/a+b?(*COMMIT)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*COMMIT) -+13 ^ ^ c+ -+15 ^ ^ (*FAIL) -+15 ^ ^ (*FAIL) -+15 ^ ^ (*FAIL) -No match - -/a+b?(*SKIP)c+(*FAIL)/C - aaabcccaaabccc ---->aaabcccaaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*SKIP) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*SKIP) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -No match - -/a+b?(*THEN)c+(*FAIL)/C - aaabccc ---->aaabccc - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^ ^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) - +0 ^ a+ - +2 ^^ b? - +4 ^ ^ (*THEN) -+11 ^ ^ c+ -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -+13 ^ ^ (*FAIL) -No match - -/a(*MARK)b/ -Failed: (*MARK) must have an argument at offset 7 - -/(?i:A{1,}\6666666666)/ -Failed: number is too big at offset 19 - -/\g6666666666/ -Failed: number is too big at offset 11 - -/[\g6666666666]/BZ ------------------------------------------------------------------- - Bra - [6g] - Ket - End ------------------------------------------------------------------- - -/(?1)\c[/ -Failed: reference to non-existent subpattern at offset 3 - -/.+A/<crlf> - \r\nA -No match - -/\nA/<crlf> - \r\nA - 0: \x0aA - -/[\r\n]A/<crlf> - \r\nA - 0: \x0aA - -/(\r|\n)A/<crlf> - \r\nA - 0: \x0aA - 1: \x0a - -/a(*CR)b/ -Failed: (*VERB) not recognized or malformed at offset 5 - -/(*CR)a.b/ - a\nb - 0: a\x0ab - ** Failers -No match - a\rb -No match - -/(*CR)a.b/<lf> - a\nb - 0: a\x0ab - ** Failers -No match - a\rb -No match - -/(*LF)a.b/<CRLF> - a\rb - 0: a\x0db - ** Failers -No match - a\nb -No match - -/(*CRLF)a.b/ - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - ** Failers -No match - a\r\nb -No match - -/(*ANYCRLF)a.b/<CR> - ** Failers -No match - a\rb -No match - a\nb -No match - a\r\nb -No match - -/(*ANY)a.b/<cr> - ** Failers -No match - a\rb -No match - a\nb -No match - a\r\nb -No match - a\x85b -No match - -/(*ANY).*/g - abc\r\ndef - 0: abc - 0: - 0: def - 0: - -/(*ANYCRLF).*/g - abc\r\ndef - 0: abc - 0: - 0: def - 0: - -/(*CRLF).*/g - abc\r\ndef - 0: abc - 0: - 0: def - 0: - -/a\Rb/I<bsr_anycrlf> -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\Rb/I<bsr_unicode> -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\<bsr_anycrlf> -No match - a\x0bb\<bsr_anycrlf> -No match - -/a\R?b/I<bsr_anycrlf> -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - ** Failers -No match - a\x85b -No match - a\x0bb -No match - -/a\R?b/I<bsr_unicode> -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\rb - 0: a\x0db - a\nb - 0: a\x0ab - a\r\nb - 0: a\x0d\x0ab - a\x85b - 0: a\x85b - a\x0bb - 0: a\x0bb - ** Failers -No match - a\x85b\<bsr_anycrlf> -No match - a\x0bb\<bsr_anycrlf> -No match - -/a\R{2,4}b/I<bsr_anycrlf> -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\r\n\nb - 0: a\x0d\x0a\x0ab - a\n\r\rb - 0: a\x0a\x0d\x0db - a\r\n\r\n\r\n\r\nb - 0: a\x0d\x0a\x0d\x0a\x0d\x0a\x0d\x0ab - ** Failers -No match - a\x85\85b -No match - a\x0b\0bb -No match - -/a\R{2,4}b/I<bsr_unicode> -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\r\rb - 0: a\x0d\x0db - a\n\n\nb - 0: a\x0a\x0a\x0ab - a\r\n\n\r\rb - 0: a\x0d\x0a\x0a\x0d\x0db - a\x85\85b -No match - a\x0b\0bb -No match - ** Failers -No match - a\r\r\r\r\rb -No match - a\x85\85b\<bsr_anycrlf> -No match - a\x0b\0bb\<bsr_anycrlf> -No match - -/(*BSR_ANYCRLF)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -First char = 'a' -Need char = 'b' - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - -/(*BSR_UNICODE)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -First char = 'a' -Need char = 'b' - a\x85b - 0: a\x85b - -/(*BSR_ANYCRLF)(*CRLF)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -Forced newline sequence: CRLF -First char = 'a' -Need char = 'b' - a\nb - 0: a\x0ab - a\rb - 0: a\x0db - -/(*CRLF)(*BSR_UNICODE)a\Rb/I -Capturing subpattern count = 0 -Options: bsr_unicode -Forced newline sequence: CRLF -First char = 'a' -Need char = 'b' - a\x85b - 0: a\x85b - -/(*CRLF)(*BSR_ANYCRLF)(*CR)ab/I -Capturing subpattern count = 0 -Options: bsr_anycrlf -Forced newline sequence: CR -First char = 'a' -Need char = 'b' - -/(?<a>)(?&)/ -Failed: subpattern name expected at offset 9 - -/(?<abc>)(?&a)/ -Failed: reference to non-existent subpattern at offset 12 - -/(?<a>)(?&aaaaaaaaaaaaaaaaaaaaaaa)/ -Failed: reference to non-existent subpattern at offset 32 - -/(?+-a)/ -Failed: digit expected after (?+ at offset 3 - -/(?-+a)/ -Failed: unrecognized character after (? or (?- at offset 3 - -/(?(-1))/ -Failed: reference to non-existent subpattern at offset 6 - -/(?(+10))/ -Failed: reference to non-existent subpattern at offset 7 - -/(?(10))/ -Failed: reference to non-existent subpattern at offset 6 - -/(?(+2))()()/ - -/(?(2))()()/ - -/\k''/ -Failed: subpattern name expected at offset 3 - -/\k<>/ -Failed: subpattern name expected at offset 3 - -/\k{}/ -Failed: subpattern name expected at offset 3 - -/\k/ -Failed: \k is not followed by a braced, angle-bracketed, or quoted name at offset 2 - -/\kabc/ -Failed: \k is not followed by a braced, angle-bracketed, or quoted name at offset 5 - -/(?P=)/ -Failed: subpattern name expected at offset 4 - -/(?P>)/ -Failed: subpattern name expected at offset 4 - -/(?!\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 9 - -/(?=\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 9 - -/(?<!\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 10 - -/(?<=\w)(?R)/ -Failed: recursive call could loop indefinitely at offset 10 - -/[[:foo:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:1234:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:f\oo:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[: :]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:...:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:l\ower:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:abc\:]]/ -Failed: unknown POSIX class name at offset 3 - -/[abc[:x\]pqr:]]/ -Failed: unknown POSIX class name at offset 6 - -/[[:a\dz:]]/ -Failed: unknown POSIX class name at offset 3 - -/(^(a|b\g<-1'c))/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 15 - -/^(?+1)(?<a>x|y){0}z/ - xzxx - 0: xz - yzyy - 0: yz - ** Failers -No match - xxz -No match - -/(\3)(\1)(a)/ - cat -No match - -/(\3)(\1)(a)/<JS> - cat - 0: a - 1: - 2: - 3: a - -/TA]/ - The ACTA] comes - 0: TA] - -/TA]/<JS> -Failed: ] is an invalid data character in JavaScript compatibility mode at offset 2 - -/(?2)[]a()b](abc)/ -Failed: reference to non-existent subpattern at offset 3 - -/(?2)[^]a()b](abc)/ -Failed: reference to non-existent subpattern at offset 3 - -/(?1)[]a()b](abc)/ - abcbabc - 0: abcbabc - 1: abc - ** Failers -No match - abcXabc -No match - -/(?1)[^]a()b](abc)/ - abcXabc - 0: abcXabc - 1: abc - ** Failers -No match - abcbabc -No match - -/(?2)[]a()b](abc)(xyz)/ - xyzbabcxyz - 0: xyzbabcxyz - 1: abc - 2: xyz - -/(?&N)[]a(?<N>)](?<M>abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/(?&N)[]a(?<N>)](abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/a[^]b/ -Failed: missing terminating ] for character class at offset 5 - -/a[]b/<JS> - ** Failers -No match - ab -No match - -/a[]+b/<JS> - ** Failers -No match - ab -No match - -/a[]*+b/<JS> - ** Failers -No match - ab -No match - -/a[^]b/<JS> - aXb - 0: aXb - a\nb - 0: a\x0ab - ** Failers -No match - ab -No match - -/a[^]+b/<JS> - aXb - 0: aXb - a\nX\nXb - 0: a\x0aX\x0aXb - ** Failers -No match - ab -No match - -/a(?!)b/BZ ------------------------------------------------------------------- - Bra - a - *FAIL - b - Ket - End ------------------------------------------------------------------- - -/(?!)?a/BZ ------------------------------------------------------------------- - Bra - Brazero - Assert not - Ket - a - Ket - End ------------------------------------------------------------------- - ab - 0: a - -/a(*FAIL)+b/ -Failed: nothing to repeat at offset 8 - -/(abc|pqr|123){0}[xyz]/SI -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 1 -Starting chars: x y z - -/(?(?=.*b)b|^)/CI -Capturing subpattern count = 0 -May match empty string -Options: -No first char -No need char - adc ---->adc - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^ ^ b - +7 ^^ b - +7 ^ b -+11 ^ ^ -+12 ^ ) -+13 ^ - 0: - abc ---->abc - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^ ^ b - +7 ^^ b - +8 ^ ^ ) - +9 ^ b - +0 ^ (?(?=.*b)b|^) - +2 ^ (?=.*b) - +5 ^ .* - +7 ^ ^ b - +7 ^^ b - +7 ^ b - +8 ^^ ) - +9 ^ b -+10 ^^ | -+13 ^^ - 0: b - -/(?(?=b).*b|^d)/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/(?(?=.*b).*b|^d)/I -Capturing subpattern count = 0 -No options -First char at start or follows newline -No need char - -/xyz/C - xyz ---->xyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz ---->abcxyz - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - abcxyz\Y ---->abcxyz - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - ** Failers -No match - abc -No match - abc\Y ---->abc - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - abcxypqr -No match - abcxypqr\Y ---->abcxypqr - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x -No match - -/(*NO_START_OPT)xyz/C - abcxyz ---->abcxyz -+15 ^ x -+15 ^ x -+15 ^ x -+15 ^ x -+16 ^^ y -+17 ^ ^ z -+18 ^ ^ - 0: xyz - -/(*NO_AUTO_POSSESS)a+b/BZ ------------------------------------------------------------------- - Bra - a+ - b - Ket - End ------------------------------------------------------------------- - -/xyz/CY - abcxyz ---->abcxyz - +0 ^ x - +0 ^ x - +0 ^ x - +0 ^ x - +1 ^^ y - +2 ^ ^ z - +3 ^ ^ - 0: xyz - -/^"((?(?=[a])[^"])|b)*"$/C - "ab" ---->"ab" - +0 ^ ^ - +1 ^ " - +2 ^^ ((?(?=[a])[^"])|b)* - +3 ^^ (?(?=[a])[^"]) - +5 ^^ (?=[a]) - +8 ^^ [a] -+11 ^ ^ ) -+12 ^^ [^"] -+16 ^ ^ ) -+17 ^ ^ | - +3 ^ ^ (?(?=[a])[^"]) - +5 ^ ^ (?=[a]) - +8 ^ ^ [a] -+17 ^ ^ | -+21 ^ ^ " -+18 ^ ^ b -+19 ^ ^ ) - +3 ^ ^ (?(?=[a])[^"]) - +5 ^ ^ (?=[a]) - +8 ^ ^ [a] -+17 ^ ^ | -+21 ^ ^ " -+22 ^ ^ $ -+23 ^ ^ - 0: "ab" - 1: - -/^"((?(?=[a])[^"])|b)*"$/ - "ab" - 0: "ab" - 1: - -/^X(?5)(a)(?|(b)|(q))(c)(d)Y/ -Failed: reference to non-existent subpattern at offset 5 - -/^X(?&N)(a)(?|(b)|(q))(c)(d)(?<N>Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: c - 4: d - 5: Y - -/Xa{2,4}b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/Xa{2,4}?b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/Xa{2,4}+b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X\d{2,4}b/ - X\P -Partial match: X - X3\P -Partial match: X3 - X33\P -Partial match: X33 - X333\P -Partial match: X333 - X3333\P -Partial match: X3333 - -/X\d{2,4}?b/ - X\P -Partial match: X - X3\P -Partial match: X3 - X33\P -Partial match: X33 - X333\P -Partial match: X333 - X3333\P -Partial match: X3333 - -/X\d{2,4}+b/ - X\P -Partial match: X - X3\P -Partial match: X3 - X33\P -Partial match: X33 - X333\P -Partial match: X333 - X3333\P -Partial match: X3333 - -/X\D{2,4}b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X\D{2,4}?b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X\D{2,4}+b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X[abc]{2,4}b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X[abc]{2,4}?b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X[abc]{2,4}+b/ - X\P -Partial match: X - Xa\P -Partial match: Xa - Xaa\P -Partial match: Xaa - Xaaa\P -Partial match: Xaaa - Xaaaa\P -Partial match: Xaaaa - -/X[^a]{2,4}b/ - X\P -Partial match: X - Xz\P -Partial match: Xz - Xzz\P -Partial match: Xzz - Xzzz\P -Partial match: Xzzz - Xzzzz\P -Partial match: Xzzzz - -/X[^a]{2,4}?b/ - X\P -Partial match: X - Xz\P -Partial match: Xz - Xzz\P -Partial match: Xzz - Xzzz\P -Partial match: Xzzz - Xzzzz\P -Partial match: Xzzzz - -/X[^a]{2,4}+b/ - X\P -Partial match: X - Xz\P -Partial match: Xz - Xzz\P -Partial match: Xzz - Xzzz\P -Partial match: Xzzz - Xzzzz\P -Partial match: Xzzzz - -/(Y)X\1{2,4}b/ - YX\P -Partial match: YX - YXY\P -Partial match: YXY - YXYY\P -Partial match: YXYY - YXYYY\P -Partial match: YXYYY - YXYYYY\P -Partial match: YXYYYY - -/(Y)X\1{2,4}?b/ - YX\P -Partial match: YX - YXY\P -Partial match: YXY - YXYY\P -Partial match: YXYY - YXYYY\P -Partial match: YXYYY - YXYYYY\P -Partial match: YXYYYY - -/(Y)X\1{2,4}+b/ - YX\P -Partial match: YX - YXY\P -Partial match: YXY - YXYY\P -Partial match: YXYY - YXYYY\P -Partial match: YXYYY - YXYYYY\P -Partial match: YXYYYY - -/\++\KZ|\d+X|9+Y/ - ++++123999\P -Partial match: 123999 - ++++123999Y\P - 0: 999Y - ++++Z1234\P - 0: Z - -/Z(*F)/ - Z\P -No match - ZA\P -No match - -/Z(?!)/ - Z\P -No match - ZA\P -No match - -/dog(sbody)?/ - dogs\P - 0: dog - dogs\P\P -Partial match: dogs - -/dog(sbody)??/ - dogs\P - 0: dog - dogs\P\P - 0: dog - -/dog|dogsbody/ - dogs\P - 0: dog - dogs\P\P - 0: dog - -/dogsbody|dog/ - dogs\P - 0: dog - dogs\P\P -Partial match: dogs - -/\bthe cat\b/ - the cat\P - 0: the cat - the cat\P\P -Partial match: the cat - -/abc/ - abc\P - 0: abc - abc\P\P - 0: abc - -/abc\K123/ - xyzabc123pqr - 0: 123 - xyzabc12\P -Partial match: abc12 - xyzabc12\P\P -Partial match: abc12 - -/(?<=abc)123/ - xyzabc123pqr - 0: 123 - xyzabc12\P -Partial match at offset 6: abc12 - xyzabc12\P\P -Partial match at offset 6: abc12 - -/\babc\b/ - +++abc+++ - 0: abc - +++ab\P -Partial match at offset 3: +ab - +++ab\P\P -Partial match at offset 3: +ab - -/(?&word)(?&element)(?(DEFINE)(?<element><[^m][^>]>[^<])(?<word>\w*+))/BZ ------------------------------------------------------------------- - Bra - Recurse - Recurse - Cond - Cond def - CBra 1 - < - [^m] - [^>] - > - [^<] - Ket - CBra 2 - \w*+ - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/(?&word)(?&element)(?(DEFINE)(?<element><[^\d][^>]>[^<])(?<word>\w*+))/BZ ------------------------------------------------------------------- - Bra - Recurse - Recurse - Cond - Cond def - CBra 1 - < - [\x00-/:-\xff] (neg) - [^>] - > - [^<] - Ket - CBra 2 - \w*+ - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/(ab)(x(y)z(cd(*ACCEPT)))pq/BZ ------------------------------------------------------------------- - Bra - CBra 1 - ab - Ket - CBra 2 - x - CBra 3 - y - Ket - z - CBra 4 - cd - Close 4 - Close 2 - *ACCEPT - Ket - Ket - pq - Ket - End ------------------------------------------------------------------- - -/abc\K/+ - abcdef - 0: - 0+ def - abcdef\N\N - 0: - 0+ def - xyzabcdef\N\N - 0: - 0+ def - ** Failers -No match - abcdef\N -No match - xyzabcdef\N -No match - -/^(?:(?=abc)|abc\K)/+ - abcdef - 0: - 0+ abcdef - abcdef\N\N - 0: - 0+ def - ** Failers -No match - abcdef\N -No match - -/a?b?/+ - xyz - 0: - 0+ xyz - xyzabc - 0: - 0+ xyzabc - xyzabc\N - 0: ab - 0+ c - xyzabc\N\N - 0: - 0+ yzabc - xyz\N\N - 0: - 0+ yz - ** Failers - 0: - 0+ ** Failers - xyz\N -No match - -/^a?b?/+ - xyz - 0: - 0+ xyz - xyzabc - 0: - 0+ xyzabc - ** Failers - 0: - 0+ ** Failers - xyzabc\N -No match - xyzabc\N\N -No match - xyz\N\N -No match - xyz\N -No match - -/^(?<name>a|b\g<name>c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(?<name>a|b\g'name'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g<1>c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g'1'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/^(a|b\g'-1'c)/ - aaaa - 0: a - 1: a - bacxxx - 0: bac - 1: bac - bbaccxxx - 0: bbacc - 1: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - -/(^(a|b\g<-1>c))/ - aaaa - 0: a - 1: a - 2: a - bacxxx - 0: bac - 1: bac - 2: bac - bbaccxxx - 0: bbacc - 1: bbacc - 2: bbacc - bbbacccxx - 0: bbbaccc - 1: bbbaccc - 2: bbbaccc - -/(?-i:\g<name>)(?i:(?<name>a))/ - XaaX - 0: aa - 1: a - XAAX - 0: AA - 1: A - -/(?i:\g<name>)(?-i:(?<name>a))/ - XaaX - 0: aa - 1: a - ** Failers -No match - XAAX -No match - -/(?-i:\g<+1>)(?i:(a))/ - XaaX - 0: aa - 1: a - XAAX - 0: AA - 1: A - -/(?=(?<regex>(?#simplesyntax)\$(?<name>[a-zA-Z_\x{7f}-\x{ff}][a-zA-Z0-9_\x{7f}-\x{ff}]*)(?:\[(?<index>[a-zA-Z0-9_\x{7f}-\x{ff}]+|\$\g<name>)\]|->\g<name>(\(.*?\))?)?|(?#simple syntax withbraces)\$\{(?:\g<name>(?<indices>\[(?:\g<index>|'(?:\\.|[^'\\])*'|"(?:\g<regex>|\\.|[^"\\])*")\])?|\g<complex>|\$\{\g<complex>\})\}|(?#complexsyntax)\{(?<complex>\$(?<segment>\g<name>(\g<indices>*|\(.*?\))?)(?:->\g<segment>)*|\$\g<complex>|\$\{\g<complex>\})\}))\{/ - -/(?<n>a|b|c)\g<n>*/ - abc - 0: abc - 1: a - accccbbb - 0: accccbbb - 1: a - -/^X(?7)(a)(?|(b)|(q)(r)(s))(c)(d)(Y)/ - XYabcdY - 0: XYabcdY - 1: a - 2: b - 3: <unset> - 4: <unset> - 5: c - 6: d - 7: Y - -/(?<=b(?1)|zzz)(a)/ - xbaax - 0: a - 1: a - xzzzax - 0: a - 1: a - -/(a)(?<=b\1)/ -Failed: lookbehind assertion is not fixed length at offset 10 - -/(a)(?<=b+(?1))/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/(a+)(?<=b(?1))/ -Failed: lookbehind assertion is not fixed length at offset 14 - -/(a(?<=b(?1)))/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/(?<=b(?1))xyz/ -Failed: reference to non-existent subpattern at offset 8 - -/(?<=b(?1))xyz(b+)pqrstuvew/ -Failed: lookbehind assertion is not fixed length at offset 26 - -/(a|bc)\1/SI -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(a|bc)\1{2,3}/SI -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 3 -Starting chars: a b - -/(a|bc)(?1)/SI -Capturing subpattern count = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(a|b\1)(a|b\1)/SI -Capturing subpattern count = 2 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(a|b\1){2}/SI -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(a|bbbb\1)(a|bbbb\1)/SI -Capturing subpattern count = 2 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/(a|bbbb\1){2}/SI -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char -Subject length lower bound = 2 -Starting chars: a b - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/SI -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = ':' -Subject length lower bound = 22 -No starting char list - -/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/isIS -Capturing subpattern count = 11 -Options: caseless dotall -First char = '<' -Need char = '>' -Subject length lower bound = 47 -No starting char list - -"(?>.*/)foo"SI -Capturing subpattern count = 0 -No options -No first char -Need char = 'o' -Subject length lower bound = 4 -No starting char list - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /xSI -Capturing subpattern count = 0 -Options: extended -No first char -Need char = '-' -Subject length lower bound = 8 -No starting char list - -/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/iSI -Capturing subpattern count = 1 -Options: caseless -No first char -No need char -Subject length lower bound = 1 -Starting chars: A B C a b c - -/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/SI -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' -Subject length lower bound = 41 -Starting chars: c d - -/<a[\s]+href[\s]*=[\s]* # find <a href= - ([\"\'])? # find single or double quote - (?(1) (.*?)\1 | ([^\s]+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isxSI -Capturing subpattern count = 3 -Max back reference = 1 -Options: caseless extended dotall -First char = '<' -Need char = '=' -Subject length lower bound = 9 -No starting char list - -/^(?!:) # colon disallowed at start - (?: # start of item - (?: [0-9a-f]{1,4} | # 1-4 hex digits or - (?(1)0 | () ) ) # if null previously matched, fail; else null - : # followed by colon - ){1,7} # end item; 1-7 of them required - [0-9a-f]{1,4} $ # final hex number at end of string - (?(1)|.) # check that there was an empty component - /xiIS -Capturing subpattern count = 1 -Options: anchored caseless extended -No first char -Need char = ':' -Subject length lower bound = 2 -No starting char list - -/(?|(?<a>A)|(?<a>B))/I -Capturing subpattern count = 1 -Named capturing subpatterns: - a 1 -No options -No first char -No need char - AB\Ca - 0: A - 1: A - C A (1) a - BA\Ca - 0: B - 1: B - C B (1) a - -/(?|(?<a>A)|(?<b>B))/ -Failed: different names for subpatterns of the same number are not allowed at offset 15 - -/(?:a(?<quote> (?<apostrophe>')|(?<realquote>")) | - b(?<quote> (?<apostrophe>')|(?<realquote>")) ) - (?('quote')[a-z]+|[0-9]+)/JIx -Capturing subpattern count = 6 -Named capturing subpatterns: - apostrophe 2 - apostrophe 5 - quote 1 - quote 4 - realquote 3 - realquote 6 -Options: extended dupnames -No first char -No need char - a"aaaaa - 0: a"aaaaa - 1: " - 2: <unset> - 3: " - b"aaaaa - 0: b"aaaaa - 1: <unset> - 2: <unset> - 3: <unset> - 4: " - 5: <unset> - 6: " - ** Failers -No match - b"11111 -No match - a"11111 -No match - -/^(?|(a)(b)(c)(?<D>d)|(?<D>e)) (?('D')X|Y)/JDZx ------------------------------------------------------------------- - Bra - ^ - Bra - CBra 1 - a - Ket - CBra 2 - b - Ket - CBra 3 - c - Ket - CBra 4 - d - Ket - Alt - CBra 1 - e - Ket - Ket - Cond - Cond ref <D>2 - X - Alt - Y - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 4 -Named capturing subpatterns: - D 4 - D 1 -Options: anchored extended dupnames -No first char -No need char - abcdX - 0: abcdX - 1: a - 2: b - 3: c - 4: d - eX - 0: eX - 1: e - ** Failers -No match - abcdY -No match - ey -No match - -/(?<A>a) (b)(c) (?<A>d (?(R&A)$ | (?4)) )/JDZx ------------------------------------------------------------------- - Bra - CBra 1 - a - Ket - CBra 2 - b - Ket - CBra 3 - c - Ket - CBra 4 - d - Cond - Cond recurse <A>2 - $ - Alt - Recurse - Ket - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 4 -Named capturing subpatterns: - A 1 - A 4 -Options: extended dupnames -First char = 'a' -Need char = 'd' - abcdd - 0: abcdd - 1: a - 2: b - 3: c - 4: dd - ** Failers -No match - abcdde -No match - -/abcd*/ - xxxxabcd\P - 0: abcd - xxxxabcd\P\P -Partial match: abcd - -/abcd*/i - xxxxabcd\P - 0: abcd - xxxxabcd\P\P -Partial match: abcd - XXXXABCD\P - 0: ABCD - XXXXABCD\P\P -Partial match: ABCD - -/abc\d*/ - xxxxabc1\P - 0: abc1 - xxxxabc1\P\P -Partial match: abc1 - -/(a)bc\1*/ - xxxxabca\P - 0: abca - 1: a - xxxxabca\P\P -Partial match: abca - -/abc[de]*/ - xxxxabcde\P - 0: abcde - xxxxabcde\P\P -Partial match: abcde - -/-- This is not in the Perl-compatible test because Perl seems currently to be - broken and not behaving as specified in that it *does* bumpalong after - hitting (*COMMIT). --/ - -/(?1)(A(*COMMIT)|B)D/ - ABD - 0: ABD - 1: B - XABD - 0: ABD - 1: B - BAD - 0: BAD - 1: A - ABXABD - 0: ABD - 1: B - ** Failers -No match - ABX -No match - BAXBAD -No match - -/(\3)(\1)(a)/<JS> - cat - 0: a - 1: - 2: - 3: a - -/(\3)(\1)(a)/SI<JS> -Capturing subpattern count = 3 -Max back reference = 3 -Options: -No first char -Need char = 'a' -Subject length lower bound = 1 -No starting char list - cat - 0: a - 1: - 2: - 3: a - -/(\3)(\1)(a)/SI -Capturing subpattern count = 3 -Max back reference = 3 -No options -No first char -Need char = 'a' -Subject length lower bound = 3 -No starting char list - cat -No match - -/i(?(DEFINE)(?<s>a))/SI -Capturing subpattern count = 1 -Named capturing subpatterns: - s 1 -No options -First char = 'i' -No need char -Subject length lower bound = 1 -No starting char list - i - 0: i - -/()i(?(1)a)/SI -Capturing subpattern count = 1 -No options -No first char -Need char = 'i' -Subject length lower bound = 1 -Starting chars: i - ia - 0: ia - 1: - -/(?i)a(?-i)b|c/BZ ------------------------------------------------------------------- - Bra - /i a - b - Alt - c - Ket - End ------------------------------------------------------------------- - XabX - 0: ab - XAbX - 0: Ab - CcC - 0: c - ** Failers -No match - XABX -No match - -/(?i)a(?s)b|c/BZ ------------------------------------------------------------------- - Bra - /i ab - Alt - /i c - Ket - End ------------------------------------------------------------------- - -/(?i)a(?s-i)b|c/BZ ------------------------------------------------------------------- - Bra - /i a - b - Alt - c - Ket - End ------------------------------------------------------------------- - -/^(ab(c\1)d|x){2}$/BZ ------------------------------------------------------------------- - Bra - ^ - Once - CBra 1 - ab - CBra 2 - c - \1 - Ket - d - Alt - x - Ket - Ket - Once - CBra 1 - ab - CBra 2 - c - \1 - Ket - d - Alt - x - Ket - Ket - $ - Ket - End ------------------------------------------------------------------- - xabcxd - 0: xabcxd - 1: abcxd - 2: cx - -/^(?&t)*+(?(DEFINE)(?<t>.))$/BZ ------------------------------------------------------------------- - Bra - ^ - Braposzero - SBraPos - Recurse - KetRpos - Cond - Cond def - CBra 1 - Any - Ket - Ket - $ - Ket - End ------------------------------------------------------------------- - -/^(?&t)*(?(DEFINE)(?<t>.))$/BZ ------------------------------------------------------------------- - Bra - ^ - Brazero - Once - Recurse - KetRmax - Cond - Cond def - CBra 1 - Any - Ket - Ket - $ - Ket - End ------------------------------------------------------------------- - -/ -- This one is here because Perl gives the match as "b" rather than "ab". I - believe this to be a Perl bug. --/ - -/(?>a\Kb)z|(ab)/ - ab - 0: ab - 1: ab - -/(?P<L1>(?P<L2>0|)|(?P>L2)(?P>L1))/ -Failed: recursive call could loop indefinitely at offset 31 - -/abc(*MARK:)pqr/ -Failed: (*MARK) must have an argument at offset 10 - -/abc(*:)pqr/ -Failed: (*MARK) must have an argument at offset 6 - -/abc(*FAIL:123)xyz/ -Failed: an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) at offset 13 - -/--- This should, and does, fail. In Perl, it does not, which I think is a - bug because replacing the B in the pattern by (B|D) does make it fail. ---/ - -/A(*COMMIT)B/+K - ACABX -No match - -/--- These should be different, but in Perl they are not, which I think - is a bug in Perl. ---/ - -/A(*THEN)B|A(*THEN)C/K - AC - 0: AC - -/A(*PRUNE)B|A(*PRUNE)C/K - AC -No match - -/--- Mark names can be duplicated. Perl doesn't give a mark for this one, -though PCRE does. ---/ - -/^A(*:A)B|^X(*:A)Y/K - ** Failers -No match - XAQQ -No match, mark = A - -/--- COMMIT at the start of a pattern should be the same as an anchor. Perl -optimizations defeat this. So does the PCRE optimization unless we disable it -with \Y. ---/ - -/(*COMMIT)ABC/ - ABCDEFG - 0: ABC - ** Failers -No match - DEFGABC\Y -No match - -/^(ab (c+(*THEN)cd) | xyz)/x - abcccd -No match - -/^(ab (c+(*PRUNE)cd) | xyz)/x - abcccd -No match - -/^(ab (c+(*FAIL)cd) | xyz)/x - abcccd -No match - -/--- Perl gets some of these wrong ---/ - -/(?>.(*ACCEPT))*?5/ - abcde - 0: a - -/(.(*ACCEPT))*?5/ - abcde - 0: a - 1: a - -/(.(*ACCEPT))5/ - abcde - 0: a - 1: a - -/(.(*ACCEPT))*5/ - abcde - 0: a - 1: a - -/A\NB./BZ ------------------------------------------------------------------- - Bra - A - Any - B - Any - Ket - End ------------------------------------------------------------------- - ACBD - 0: ACBD - *** Failers -No match - A\nB -No match - ACB\n -No match - -/A\NB./sBZ ------------------------------------------------------------------- - Bra - A - Any - B - AllAny - Ket - End ------------------------------------------------------------------- - ACBD - 0: ACBD - ACB\n - 0: ACB\x0a - *** Failers -No match - A\nB -No match - -/A\NB/<crlf> - A\nB - 0: A\x0aB - A\rB - 0: A\x0dB - ** Failers -No match - A\r\nB -No match - -/\R+b/BZ ------------------------------------------------------------------- - Bra - \R++ - b - Ket - End ------------------------------------------------------------------- - -/\R+\n/BZ ------------------------------------------------------------------- - Bra - \R+ - \x0a - Ket - End ------------------------------------------------------------------- - -/\R+\d/BZ ------------------------------------------------------------------- - Bra - \R++ - \d - Ket - End ------------------------------------------------------------------- - -/\d*\R/BZ ------------------------------------------------------------------- - Bra - \d*+ - \R - Ket - End ------------------------------------------------------------------- - -/\s*\R/BZ ------------------------------------------------------------------- - Bra - \s* - \R - Ket - End ------------------------------------------------------------------- - \x20\x0a - 0: \x0a - \x20\x0d - 0: \x0d - \x20\x0d\x0a - 0: \x0d\x0a - -/\S*\R/BZ ------------------------------------------------------------------- - Bra - \S*+ - \R - Ket - End ------------------------------------------------------------------- - a\x0a - 0: a\x0a - -/X\h*\R/BZ ------------------------------------------------------------------- - Bra - X - \h*+ - \R - Ket - End ------------------------------------------------------------------- - X\x20\x0a - 0: X \x0a - -/X\H*\R/BZ ------------------------------------------------------------------- - Bra - X - \H* - \R - Ket - End ------------------------------------------------------------------- - X\x0d\x0a - 0: X\x0d\x0a - -/X\H+\R/BZ ------------------------------------------------------------------- - Bra - X - \H+ - \R - Ket - End ------------------------------------------------------------------- - X\x0d\x0a - 0: X\x0d\x0a - -/X\H++\R/BZ ------------------------------------------------------------------- - Bra - X - \H++ - \R - Ket - End ------------------------------------------------------------------- - X\x0d\x0a -No match - -/(?<=abc)def/ - abc\P\P -Partial match at offset 3: abc - -/abc$/ - abc - 0: abc - abc\P - 0: abc - abc\P\P -Partial match: abc - -/abc$/m - abc - 0: abc - abc\n - 0: abc - abc\P\P -Partial match: abc - abc\n\P\P - 0: abc - abc\P - 0: abc - abc\n\P - 0: abc - -/abc\z/ - abc - 0: abc - abc\P - 0: abc - abc\P\P -Partial match: abc - -/abc\Z/ - abc - 0: abc - abc\P - 0: abc - abc\P\P -Partial match: abc - -/abc\b/ - abc - 0: abc - abc\P - 0: abc - abc\P\P -Partial match: abc - -/abc\B/ - abc -No match - abc\P -Partial match: abc - abc\P\P -Partial match: abc - -/.+/ - abc\>0 - 0: abc - abc\>1 - 0: bc - abc\>2 - 0: c - abc\>3 -No match - abc\>4 -Error -24 (bad offset value) - abc\>-4 -Error -24 (bad offset value) - -/^\cģ/ -Failed: \c must be followed by an ASCII character at offset 3 - -/(?P<abn>(?P=abn)xxx)/BZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - \1 - xxx - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/(a\1z)/BZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - a - \1 - z - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/(?P<abn>(?P=abn)(?<badstufxxx)/BZ -Failed: syntax error in subpattern name (missing terminator) at offset 29 - -/(?P<abn>(?P=axn)xxx)/BZ -Failed: reference to non-existent subpattern at offset 15 - -/(?P<abn>(?P=axn)xxx)(?<axn>yy)/BZ ------------------------------------------------------------------- - Bra - CBra 1 - \2 - xxx - Ket - CBra 2 - yy - Ket - Ket - End ------------------------------------------------------------------- - -/-- These tests are here because Perl gets the first one wrong. --/ - -/(\R*)(.)/s - \r\n - 0: \x0d - 1: - 2: \x0d - \r\r\n\n\r - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0d\x0d\x0a\x0a - 2: \x0d - \r\r\n\n\r\n - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0d\x0d\x0a\x0a - 2: \x0d - -/(\R)*(.)/s - \r\n - 0: \x0d - 1: <unset> - 2: \x0d - \r\r\n\n\r - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0a - 2: \x0d - \r\r\n\n\r\n - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0a - 2: \x0d - -/((?>\r\n|\n|\x0b|\f|\r|\x85)*)(.)/s - \r\n - 0: \x0d - 1: - 2: \x0d - \r\r\n\n\r - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0d\x0d\x0a\x0a - 2: \x0d - \r\r\n\n\r\n - 0: \x0d\x0d\x0a\x0a\x0d - 1: \x0d\x0d\x0a\x0a - 2: \x0d - -/-- --/ - -/^abc$/BZ ------------------------------------------------------------------- - Bra - ^ - abc - $ - Ket - End ------------------------------------------------------------------- - -/^abc$/BZm ------------------------------------------------------------------- - Bra - /m ^ - abc - /m $ - Ket - End ------------------------------------------------------------------- - -/^(a)*+(\w)/S - aaaaX - 0: aaaaX - 1: a - 2: X - ** Failers -No match - aaaa -No match - -/^(?:a)*+(\w)/S - aaaaX - 0: aaaaX - 1: X - ** Failers -No match - aaaa -No match - -/(a)++1234/SDZ ------------------------------------------------------------------- - Bra - CBraPos 1 - a - KetRpos - 1234 - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = '4' -Subject length lower bound = 5 -No starting char list - -/([abc])++1234/SI -Capturing subpattern count = 1 -No options -No first char -Need char = '4' -Subject length lower bound = 5 -Starting chars: a b c - -/(?<=(abc)+)X/ -Failed: lookbehind assertion is not fixed length at offset 10 - -/(^ab)/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - -/(^ab)++/I -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - -/(^ab|^)+/I -Capturing subpattern count = 1 -May match empty string -Options: anchored -No first char -No need char - -/(^ab|^)++/I -Capturing subpattern count = 1 -May match empty string -Options: anchored -No first char -No need char - -/(?:^ab)/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?:^ab)++/I -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?:^ab|^)+/I -Capturing subpattern count = 0 -May match empty string -Options: anchored -No first char -No need char - -/(?:^ab|^)++/I -Capturing subpattern count = 0 -May match empty string -Options: anchored -No first char -No need char - -/(.*ab)/I -Capturing subpattern count = 1 -No options -First char at start or follows newline -Need char = 'b' - -/(.*ab)++/I -Capturing subpattern count = 1 -No options -First char at start or follows newline -Need char = 'b' - -/(.*ab|.*)+/I -Capturing subpattern count = 1 -May match empty string -No options -First char at start or follows newline -No need char - -/(.*ab|.*)++/I -Capturing subpattern count = 1 -May match empty string -No options -First char at start or follows newline -No need char - -/(?:.*ab)/I -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 'b' - -/(?:.*ab)++/I -Capturing subpattern count = 0 -No options -First char at start or follows newline -Need char = 'b' - -/(?:.*ab|.*)+/I -Capturing subpattern count = 0 -May match empty string -No options -First char at start or follows newline -No need char - -/(?:.*ab|.*)++/I -Capturing subpattern count = 0 -May match empty string -No options -First char at start or follows newline -No need char - -/(?=a)[bcd]/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/((?=a))[bcd]/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/((?=a))+[bcd]/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/((?=a))++[bcd]/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?=a+)[bcd]/iI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -No need char - -/(?=a+?)[bcd]/iI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -No need char - -/(?=a++)[bcd]/iI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -No need char - -/(?=a{3})[bcd]/iI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'a' (caseless) - -/(abc)\1+/S - -/-- Perl doesn't get these right IMO (the 3rd is PCRE-specific) --/ - -/(?1)(?:(b(*ACCEPT))){0}/ - b - 0: b - -/(?1)(?:(b(*ACCEPT))){0}c/ - bc - 0: bc - ** Failers -No match - b -No match - -/(?1)(?:((*ACCEPT))){0}c/ - c - 0: c - c\N - 0: c - -/^.*?(?(?=a)a|b(*THEN)c)/ - ba -No match - -/^.*?(?(?=a)a|bc)/ - ba - 0: ba - -/^.*?(?(?=a)a(*THEN)b|c)/ - ac -No match - -/^.*?(?(?=a)a(*THEN)b)c/ - ac -No match - -/^.*?(a(*THEN)b)c/ - aabc -No match - -/^.*? (?1) c (?(DEFINE)(a(*THEN)b))/x - aabc - 0: aabc - -/^.*?(a(*THEN)b|z)c/ - aabc - 0: aabc - 1: ab - -/^.*?(z|a(*THEN)b)c/ - aabc - 0: aabc - 1: ab - -/-- --/ - -/-- These studied versions are here because they are not Perl-compatible; the - studying means the mark is not seen. --/ - -/(*MARK:A)(*SKIP:B)(C|X)/KS - C - 0: C - 1: C -MK: A - D -No match, mark = A - -/(*:A)A+(*SKIP:A)(B|Z)/KS - AAAC -No match, mark = A - -/-- --/ - -"(?=a*(*ACCEPT)b)c" - c - 0: c - c\N - 0: c - -/(?1)c(?(DEFINE)((*ACCEPT)b))/ - c - 0: c - c\N - 0: c - -/(?>(*ACCEPT)b)c/ - c - 0: - c\N -No match - -/(?:(?>(a)))+a%/++ - %aa% - 0: aa% - 0+ - 1: a - 1+ a% - -/(a)b|ac/++SS - ac\O3 - 0: ac - 0+ - -/(a)(b)x|abc/++ - abc\O6 - 0: abc - 0+ - -/(a)bc|(a)(b)\2/ - \O3abc -Matched, but too many substrings - 0: abc - \O4abc -Matched, but too many substrings - 0: abc - -/(?(DEFINE)(a(?2)|b)(b(?1)|a))(?:(?1)|(?2))/SI -Capturing subpattern count = 2 -No options -No first char -No need char -Subject length lower bound = 1 -No starting char list - -/(a(?2)|b)(b(?1)|a)(?:(?1)|(?2))/SI -Capturing subpattern count = 2 -No options -No first char -No need char -Subject length lower bound = 3 -Starting chars: a b - -/(a(?2)|b)(b(?1)|a)(?1)(?2)/SI -Capturing subpattern count = 2 -No options -No first char -No need char -Subject length lower bound = 4 -Starting chars: a b - -/(abc)(?1)/SI -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'c' -Subject length lower bound = 6 -No starting char list - -/^(?>a)++/ - aa\M -Minimum match() limit = 5 -Minimum match() recursion limit = 2 - 0: aa - aaaaaaaaa\M -Minimum match() limit = 12 -Minimum match() recursion limit = 2 - 0: aaaaaaaaa - -/(a)(?1)++/ - aa\M -Minimum match() limit = 7 -Minimum match() recursion limit = 4 - 0: aa - 1: a - aaaaaaaaa\M -Minimum match() limit = 21 -Minimum match() recursion limit = 4 - 0: aaaaaaaaa - 1: a - -/(?:(foo)|(bar)|(baz))X/SS= - bazfooX - 0: fooX - 1: foo - 2: <unset> - 3: <unset> - foobazbarX - 0: barX - 1: <unset> - 2: bar - 3: <unset> - barfooX - 0: fooX - 1: foo - 2: <unset> - 3: <unset> - bazX - 0: bazX - 1: <unset> - 2: <unset> - 3: baz - foobarbazX - 0: bazX - 1: <unset> - 2: <unset> - 3: baz - bazfooX\O0 -Matched, but too many substrings - bazfooX\O2 -Matched, but too many substrings - 0: fooX - bazfooX\O4 -Matched, but too many substrings - 0: fooX - 1: <unset> - bazfooX\O6 -Matched, but too many substrings - 0: fooX - 1: foo - 2: <unset> - bazfooX\O8 -Matched, but too many substrings - 0: fooX - 1: foo - 2: <unset> - 3: <unset> - bazfooX\O10 - 0: fooX - 1: foo - 2: <unset> - 3: <unset> - -/(?=abc){3}abc/BZ ------------------------------------------------------------------- - Bra - Assert - abc - Ket - abc - Ket - End ------------------------------------------------------------------- - -/(?=abc)+abc/BZ ------------------------------------------------------------------- - Bra - Assert - abc - Ket - abc - Ket - End ------------------------------------------------------------------- - -/(?=abc)++abc/BZ ------------------------------------------------------------------- - Bra - Assert - abc - Ket - abc - Ket - End ------------------------------------------------------------------- - -/(?=abc){0}xyz/BZ ------------------------------------------------------------------- - Bra - Skip zero - Assert - abc - Ket - xyz - Ket - End ------------------------------------------------------------------- - -/(?=(a))?./BZ ------------------------------------------------------------------- - Bra - Brazero - Assert - CBra 1 - a - Ket - Ket - Any - Ket - End ------------------------------------------------------------------- - -/(?=(a))??./BZ ------------------------------------------------------------------- - Bra - Braminzero - Assert - CBra 1 - a - Ket - Ket - Any - Ket - End ------------------------------------------------------------------- - -/^(?=(a)){0}b(?1)/BZ ------------------------------------------------------------------- - Bra - ^ - Skip zero - Assert - CBra 1 - a - Ket - Ket - b - Recurse - Ket - End ------------------------------------------------------------------- - -/(?(DEFINE)(a))?b(?1)/BZ ------------------------------------------------------------------- - Bra - Cond - Cond def - CBra 1 - a - Ket - Ket - b - Recurse - Ket - End ------------------------------------------------------------------- - -/^(?=(?1))?[az]([abc])d/BZ ------------------------------------------------------------------- - Bra - ^ - Brazero - Assert - Recurse - Ket - [az] - CBra 1 - [a-c] - Ket - d - Ket - End ------------------------------------------------------------------- - -/^(?!a){0}\w+/BZ ------------------------------------------------------------------- - Bra - ^ - Skip zero - Assert not - a - Ket - \w++ - Ket - End ------------------------------------------------------------------- - -/(?<=(abc))?xyz/BZ ------------------------------------------------------------------- - Bra - Brazero - AssertB - Reverse - CBra 1 - abc - Ket - Ket - xyz - Ket - End ------------------------------------------------------------------- - -/[:a[:abc]b:]/BZ ------------------------------------------------------------------- - Bra - [:[a-c] - b:] - Ket - End ------------------------------------------------------------------- - -/((?2))((?1))/SS - abc -Error -26 (nested recursion at the same subject position) - -/((?(R2)a+|(?1)b))/SS - aaaabcde -Error -26 (nested recursion at the same subject position) - -/(?(R)a*(?1)|((?R))b)/SS - aaaabcde -Error -26 (nested recursion at the same subject position) - -/(a+|(?R)b)/ -Failed: recursive call could loop indefinitely at offset 7 - -/^(a(*:A)(d|e(*:B))z|aeq)/C - adz ---->adz - +0 ^ ^ - +1 ^ (a(*:A)(d|e(*:B))z|aeq) - +2 ^ a - +3 ^^ (*:A) - +8 ^^ (d|e(*:B)) -Latest Mark: A - +9 ^^ d -+10 ^ ^ | -+18 ^ ^ z -+19 ^ ^ | -+24 ^ ^ - 0: adz - 1: adz - 2: d - aez ---->aez - +0 ^ ^ - +1 ^ (a(*:A)(d|e(*:B))z|aeq) - +2 ^ a - +3 ^^ (*:A) - +8 ^^ (d|e(*:B)) -Latest Mark: A - +9 ^^ d -+11 ^^ e -+12 ^ ^ (*:B) -+17 ^ ^ ) -Latest Mark: B -+18 ^ ^ z -+19 ^ ^ | -+24 ^ ^ - 0: aez - 1: aez - 2: e - aeqwerty ---->aeqwerty - +0 ^ ^ - +1 ^ (a(*:A)(d|e(*:B))z|aeq) - +2 ^ a - +3 ^^ (*:A) - +8 ^^ (d|e(*:B)) -Latest Mark: A - +9 ^^ d -+11 ^^ e -+12 ^ ^ (*:B) -+17 ^ ^ ) -Latest Mark: B -+18 ^ ^ z -+20 ^ a -+21 ^^ e -+22 ^ ^ q -+23 ^ ^ ) -+24 ^ ^ - 0: aeq - 1: aeq - -/.(*F)/ - \P\Pabc -No match - -/\btype\b\W*?\btext\b\W*?\bjavascript\b/IS -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -First char = 't' -Need char = 't' -Subject length lower bound = 18 -No starting char list - -/\btype\b\W*?\btext\b\W*?\bjavascript\b|\burl\b\W*?\bshell:|<input\b.*?\btype\b\W*?\bimage\b|\bonkeyup\b\W*?\=/IS -Capturing subpattern count = 0 -Max lookbehind = 1 -No options -No first char -No need char -Subject length lower bound = 8 -Starting chars: < o t u - -/a(*SKIP)c|b(*ACCEPT)|/+S!I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char -Subject length lower bound = -1 -No starting char list - a - 0: - 0+ - -/a(*SKIP)c|b(*ACCEPT)cd(*ACCEPT)|x/SI -Capturing subpattern count = 0 -No options -No first char -No need char -Subject length lower bound = -1 -Starting chars: a b x - ax - 0: x - -'a*(*ACCEPT)b'+ - \N\N -No match - abc\N\N - 0: a - 0+ bc - bbb\N\N - 0: - 0+ bb - -/(*ACCEPT)a/+I -Capturing subpattern count = 0 -No options -No first char -No need char - bax - 0: - 0+ bax - -/z(*ACCEPT)a/+I -Capturing subpattern count = 0 -No options -First char = 'z' -No need char - baxzbx - 0: z - 0+ bx - -/a(?:.)*?a/ims - \Mabbbbbbbbbbbbbbbbbbbbba -Minimum match() limit = 65 -Minimum match() recursion limit = 2 - 0: abbbbbbbbbbbbbbbbbbbbba - -/a(?:.(*THEN))*?a/ims - \Mabbbbbbbbbbbbbbbbbbbbba -Minimum match() limit = 86 -Minimum match() recursion limit = 45 - 0: abbbbbbbbbbbbbbbbbbbbba - -/a(?:.(*THEN:ABC))*?a/ims - \Mabbbbbbbbbbbbbbbbbbbbba -Minimum match() limit = 86 -Minimum match() recursion limit = 45 - 0: abbbbbbbbbbbbbbbbbbbbba - -/^(?>a+)(?>(z+))\w/BZ ------------------------------------------------------------------- - Bra - ^ - Once_NC - a++ - Ket - Once - CBra 1 - z++ - Ket - Ket - \w - Ket - End ------------------------------------------------------------------- - aaaazzzzb - 0: aaaazzzzb - 1: zzzz - ** Failers -No match - aazz -No match - -/(.)(\1|a(?2))/ - bab - 0: bab - 1: b - 2: ab - -/\1|(.)(?R)\1/ - cbbbc - 0: cbbbc - 1: c - -/(.)((?(1)c|a)|a(?2))/ - baa -No match - -/(?P<abn>(?P=abn)xxx)/BZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - \1 - xxx - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/(a\1z)/BZ ------------------------------------------------------------------- - Bra - Once - CBra 1 - a - \1 - z - Ket - Ket - Ket - End ------------------------------------------------------------------- - -/^(?>a+)(?>b+)(?>c+)(?>d+)(?>e+)/ - \Maabbccddee -Minimum match() limit = 7 -Minimum match() recursion limit = 2 - 0: aabbccddee - -/^(?>(a+))(?>(b+))(?>(c+))(?>(d+))(?>(e+))/ - \Maabbccddee -Minimum match() limit = 17 -Minimum match() recursion limit = 16 - 0: aabbccddee - 1: aa - 2: bb - 3: cc - 4: dd - 5: ee - -/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/ - \Maabbccddee -Minimum match() limit = 13 -Minimum match() recursion limit = 10 - 0: aabbccddee - 1: aa - 2: cc - 3: ee - -/^a\x41z/<JS> - aAz - 0: aAz - *** Failers -No match - ax41z -No match - -/^a[m\x41]z/<JS> - aAz - 0: aAz - -/^a\x1z/<JS> - ax1z - 0: ax1z - -/^a\u0041z/<JS> - aAz - 0: aAz - *** Failers -No match - au0041z -No match - -/^a[m\u0041]z/<JS> - aAz - 0: aAz - -/^a\u041z/<JS> - au041z - 0: au041z - *** Failers -No match - aAz -No match - -/^a\U0041z/<JS> - aU0041z - 0: aU0041z - *** Failers -No match - aAz -No match - -/(?(?=c)c|d)++Y/BZ ------------------------------------------------------------------- - Bra - BraPos - Cond - Assert - c - Ket - c - Alt - d - Ket - KetRpos - Y - Ket - End ------------------------------------------------------------------- - -/(?(?=c)c|d)*+Y/BZ ------------------------------------------------------------------- - Bra - Braposzero - BraPos - Cond - Assert - c - Ket - c - Alt - d - Ket - KetRpos - Y - Ket - End ------------------------------------------------------------------- - -/a[\NB]c/ -Failed: \N is not supported in a class at offset 3 - -/a[B-\Nc]/ -Failed: invalid range in character class at offset 5 - -/a[B\Nc]/ -Failed: \N is not supported in a class at offset 4 - -/(a)(?2){0,1999}?(b)/ - -/(a)(?(DEFINE)(b))(?2){0,1999}?(?2)/ - -/--- This test, with something more complicated than individual letters, causes -different behaviour in Perl. Perhaps it disables some optimization; no tag is -passed back for the failures, whereas in PCRE there is a tag. ---/ - -/(A|P)(*:A)(B|P) | (X|P)(X|P)(*:B)(Y|P)/xK - AABC - 0: AB - 1: A - 2: B -MK: A - XXYZ - 0: XXY - 1: <unset> - 2: <unset> - 3: X - 4: X - 5: Y -MK: B - ** Failers -No match - XAQQ -No match, mark = A - XAQQXZZ -No match, mark = A - AXQQQ -No match, mark = A - AXXQQQ -No match, mark = B - -/-- Perl doesn't give marks for these, though it does if the alternatives are -replaced by single letters. --/ - -/(b|q)(*:m)f|a(*:n)w/K - aw - 0: aw -MK: n - ** Failers -No match, mark = n - abc -No match, mark = m - -/(q|b)(*:m)f|a(*:n)w/K - aw - 0: aw -MK: n - ** Failers -No match, mark = n - abc -No match, mark = m - -/-- After a partial match, the behaviour is as for a failure. --/ - -/^a(*:X)bcde/K - abc\P -Partial match, mark=X: abc - -/-- These are here because Perl doesn't return a mark, except for the first --/ - -/(?=(*:x))(q|)/K+ - abc - 0: - 0+ abc - 1: -MK: x - -/(?=(*:x))((*:y)q|)/K+ - abc - 0: - 0+ abc - 1: -MK: x - -/(?=(*:x))(?:(*:y)q|)/K+ - abc - 0: - 0+ abc -MK: x - -/(?=(*:x))(?>(*:y)q|)/K+ - abc - 0: - 0+ abc -MK: x - -/(?=a(*:x))(?!a(*:y)c)/K+ - ab - 0: - 0+ ab -MK: x - -/(?=a(*:x))(?=a(*:y)c|)/K+ - ab - 0: - 0+ ab -MK: x - -/(..)\1/ - ab\P -Partial match: ab - aba\P -Partial match: aba - abab\P - 0: abab - 1: ab - -/(..)\1/i - ab\P -Partial match: ab - abA\P -Partial match: abA - aBAb\P - 0: aBAb - 1: aB - -/(..)\1{2,}/ - ab\P -Partial match: ab - aba\P -Partial match: aba - abab\P -Partial match: abab - ababa\P -Partial match: ababa - ababab\P - 0: ababab - 1: ab - ababab\P\P -Partial match: ababab - abababa\P - 0: ababab - 1: ab - abababa\P\P -Partial match: abababa - -/(..)\1{2,}/i - ab\P -Partial match: ab - aBa\P -Partial match: aBa - aBAb\P -Partial match: aBAb - AbaBA\P -Partial match: AbaBA - abABAb\P - 0: abABAb - 1: ab - aBAbaB\P\P -Partial match: aBAbaB - abABabA\P - 0: abABab - 1: ab - abaBABa\P\P -Partial match: abaBABa - -/(..)\1{2,}?x/i - ab\P -Partial match: ab - abA\P -Partial match: abA - aBAb\P -Partial match: aBAb - abaBA\P -Partial match: abaBA - abAbaB\P -Partial match: abAbaB - abaBabA\P -Partial match: abaBabA - abAbABaBx\P - 0: abAbABaBx - 1: ab - -/^(..)\1/ - aba\P -Partial match: aba - -/^(..)\1{2,3}x/ - aba\P -Partial match: aba - ababa\P -Partial match: ababa - ababa\P\P -Partial match: ababa - abababx - 0: abababx - 1: ab - ababababx - 0: ababababx - 1: ab - -/^(..)\1{2,3}?x/ - aba\P -Partial match: aba - ababa\P -Partial match: ababa - ababa\P\P -Partial match: ababa - abababx - 0: abababx - 1: ab - ababababx - 0: ababababx - 1: ab - -/^(..)(\1{2,3})ab/ - abababab - 0: abababab - 1: ab - 2: abab - -/^\R/ - \r\P - 0: \x0d - \r\P\P -Partial match: \x0d - -/^\R{2,3}x/ - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - \r\r\P -Partial match: \x0d\x0d - \r\r\P\P -Partial match: \x0d\x0d - \r\r\r\P -Partial match: \x0d\x0d\x0d - \r\r\r\P\P -Partial match: \x0d\x0d\x0d - \r\rx - 0: \x0d\x0dx - \r\r\rx - 0: \x0d\x0d\x0dx - -/^\R{2,3}?x/ - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - \r\r\P -Partial match: \x0d\x0d - \r\r\P\P -Partial match: \x0d\x0d - \r\r\r\P -Partial match: \x0d\x0d\x0d - \r\r\r\P\P -Partial match: \x0d\x0d\x0d - \r\rx - 0: \x0d\x0dx - \r\r\rx - 0: \x0d\x0d\x0dx - -/^\R?x/ - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - x - 0: x - \rx - 0: \x0dx - -/^\R+x/ - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - \r\n\P -Partial match: \x0d\x0a - \r\n\P\P -Partial match: \x0d\x0a - \rx - 0: \x0dx - -/^a$/<CRLF> - a\r\P -Partial match: a\x0d - a\r\P\P -Partial match: a\x0d - -/^a$/m<CRLF> - a\r\P -Partial match: a\x0d - a\r\P\P -Partial match: a\x0d - -/^(a$|a\r)/<CRLF> - a\r\P - 0: a\x0d - 1: a\x0d - a\r\P\P -Partial match: a\x0d - -/^(a$|a\r)/m<CRLF> - a\r\P - 0: a\x0d - 1: a\x0d - a\r\P\P -Partial match: a\x0d - -/./<CRLF> - \r\P - 0: \x0d - \r\P\P -Partial match: \x0d - -/.{2,3}/<CRLF> - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - \r\r\P - 0: \x0d\x0d - \r\r\P\P -Partial match: \x0d\x0d - \r\r\r\P - 0: \x0d\x0d\x0d - \r\r\r\P\P -Partial match: \x0d\x0d\x0d - -/.{2,3}?/<CRLF> - \r\P -Partial match: \x0d - \r\P\P -Partial match: \x0d - \r\r\P - 0: \x0d\x0d - \r\r\P\P -Partial match: \x0d\x0d - \r\r\r\P - 0: \x0d\x0d - \r\r\r\P\P - 0: \x0d\x0d - -"AB(C(D))(E(F))?(?(?=\2)(?=\4))" - ABCDGHI\O03 -Matched, but too many substrings - 0: ABCD - -/-- These are all run as real matches in test 1; here we are just checking the -settings of the anchored and startline bits. --/ - -/(?>.*?a)(?<=ba)/I -Capturing subpattern count = 0 -Max lookbehind = 2 -No options -No first char -Need char = 'a' - -/(?:.*?a)(?<=ba)/I -Capturing subpattern count = 0 -Max lookbehind = 2 -No options -First char at start or follows newline -Need char = 'a' - -/.*?a(*PRUNE)b/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' - -/.*?a(*PRUNE)b/sI -Capturing subpattern count = 0 -Options: dotall -No first char -Need char = 'b' - -/^a(*PRUNE)b/sI -Capturing subpattern count = 0 -Options: anchored dotall -No first char -No need char - -/.*?a(*SKIP)b/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' - -/(?>.*?a)b/sI -Capturing subpattern count = 0 -Options: dotall -No first char -Need char = 'b' - -/(?>.*?a)b/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' - -/(?>^a)b/sI -Capturing subpattern count = 0 -Options: anchored dotall -No first char -No need char - -/(?>.*?)(?<=(abcd)|(wxyz))/I -Capturing subpattern count = 2 -Max lookbehind = 4 -May match empty string -No options -No first char -No need char - -/(?>.*)(?<=(abcd)|(wxyz))/I -Capturing subpattern count = 2 -Max lookbehind = 4 -May match empty string -No options -No first char -No need char - -"(?>.*)foo"I -Capturing subpattern count = 0 -No options -No first char -Need char = 'o' - -"(?>.*?)foo"I -Capturing subpattern count = 0 -No options -No first char -Need char = 'o' - -/(?>^abc)/mI -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - -/(?>.*abc)/mI -Capturing subpattern count = 0 -Options: multiline -No first char -Need char = 'c' - -/(?:.*abc)/mI -Capturing subpattern count = 0 -Options: multiline -First char at start or follows newline -Need char = 'c' - -/-- Check PCRE_STUDY_EXTRA_NEEDED --/ - -/.?/S-I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char -Study returned NULL - -/.?/S!I -Capturing subpattern count = 0 -May match empty string -No options -No first char -No need char -Subject length lower bound = -1 -No starting char list - -/(?:(a)+(?C1)bb|aa(?C2)b)/ - aab\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^ ^ b -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^^ b -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ b - 0: aab - -/(?:(a)++(?C1)bb|aa(?C2)b)/ - aab\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^ ^ b -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ b - 0: aab - -/(?:(?>(a))(?C1)bb|aa(?C2)b)/ - aab\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^^ b -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ b - 0: aab - -/(?:(?1)(?C1)x|ab(?C2))((a)){0}/ - aab\C+ -Callout 1: last capture = -1 - 0: <unset> ---->aab - ^^ x -Callout 1: last capture = -1 - 0: <unset> ---->aab - ^^ x -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ ) - 0: ab - -/(?1)(?C1)((a)(?C2)){0}/ - aab\C+ -Callout 2: last capture = 2 - 0: <unset> - 1: <unset> - 2: a ---->aab - ^^ ) -Callout 1: last capture = -1 - 0: <unset> ---->aab - ^^ ((a)(?C2)){0} - 0: a - -/(?:(a)+(?C1)bb|aa(?C2)b)++/ - aab\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^ ^ b -Callout 1: last capture = 1 - 0: <unset> - 1: a ---->aab - ^^ b -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ b - 0: aab - aab\C+\O2 -Callout 1: last capture = 1 - 0: <unset> ---->aab - ^ ^ b -Callout 1: last capture = 1 - 0: <unset> ---->aab - ^^ b -Callout 2: last capture = -1 - 0: <unset> ---->aab - ^ ^ b - 0: aab - -/(ab)x|ab/ - ab\O3 - 0: ab - ab\O2 - 0: ab - -/(ab)/ - ab\O3 -Matched, but too many substrings - 0: ab - ab\O2 -Matched, but too many substrings - 0: ab - -/(?<=123)(*MARK:xx)abc/K - xxxx123a\P\P -Partial match at offset 7, mark=xx: 123a - xxxx123a\P -Partial match at offset 7, mark=xx: 123a - -/123\Kabc/ - xxxx123a\P\P -Partial match: 123a - xxxx123a\P -Partial match: 123a - -/^(?(?=a)aa|bb)/C - bb ---->bb - +0 ^ ^ - +1 ^ (?(?=a)aa|bb) - +3 ^ (?=a) - +6 ^ a -+11 ^ b -+12 ^^ b -+13 ^ ^ ) -+14 ^ ^ - 0: bb - -/(?C1)^(?C2)(?(?C99)(?=(?C3)a(?C4))(?C5)a(?C6)a(?C7)|(?C8)b(?C9)b(?C10))(?C11)/ - bb ---->bb - 1 ^ ^ - 2 ^ (?(?C99)(?=(?C3)a(?C4))(?C5)a(?C6)a(?C7)|(?C8)b(?C9)b(?C10)) - 99 ^ (?=(?C3)a(?C4)) - 3 ^ a - 8 ^ b - 9 ^^ b - 10 ^ ^ ) - 11 ^ ^ - 0: bb - -/-- Perl seems to have a bug with this one --/ - -/aaaaa(*COMMIT)(*PRUNE)b|a+c/ - aaaaaac - 0: aaaac - -/-- Here are some that Perl treats differently because of the way it handles -backtracking verbs. --/ - - /(?!a(*COMMIT)b)ac|ad/ - ac - 0: ac - ad - 0: ad - -/^(?!a(*THEN)b|ac)../ - ac -No match - ad - 0: ad - -/^(?=a(*THEN)b|ac)/ - ac - 0: - -/\A.*?(?:a|b(*THEN)c)/ - ba - 0: ba - -/\A.*?(?:a|b(*THEN)c)++/ - ba - 0: ba - -/\A.*?(?:a|b(*THEN)c|d)/ - ba - 0: ba - -/(?:(a(*MARK:X)a+(*SKIP:X)b)){0}(?:(?1)|aac)/ - aac - 0: aac - -/\A.*?(a|b(*THEN)c)/ - ba - 0: ba - 1: a - -/^(A(*THEN)B|A(*THEN)D)/ - AD - 0: AD - 1: AD - -/(?!b(*THEN)a)bn|bnn/ - bnn - 0: bn - -/(?(?=b(*SKIP)a)bn|bnn)/ - bnn -No match - -/(?=b(*THEN)a|)bn|bnn/ - bnn - 0: bn - -/-------------------------/ - -/(*LIMIT_MATCH=12bc)abc/ -Failed: (*VERB) not recognized or malformed at offset 7 - -/(*LIMIT_MATCH=4294967290)abc/ -Failed: (*VERB) not recognized or malformed at offset 7 - -/(*LIMIT_RECURSION=4294967280)abc/I -Capturing subpattern count = 0 -Recursion limit = 4294967280 -No options -First char = 'a' -Need char = 'c' - -/(a+)*zz/ - aaaaaaaaaaaaaz -No match - aaaaaaaaaaaaaz\q3000 -Error -8 (match limit exceeded) - -/(a+)*zz/S- - aaaaaaaaaaaaaz\Q10 -Error -21 (recursion limit exceeded) - -/(*LIMIT_MATCH=3000)(a+)*zz/I -Capturing subpattern count = 1 -Match limit = 3000 -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaz -Error -8 (match limit exceeded) - aaaaaaaaaaaaaz\q60000 -Error -8 (match limit exceeded) - -/(*LIMIT_MATCH=60000)(*LIMIT_MATCH=3000)(a+)*zz/I -Capturing subpattern count = 1 -Match limit = 3000 -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaz -Error -8 (match limit exceeded) - -/(*LIMIT_MATCH=60000)(a+)*zz/I -Capturing subpattern count = 1 -Match limit = 60000 -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaz -No match - aaaaaaaaaaaaaz\q3000 -Error -8 (match limit exceeded) - -/(*LIMIT_RECURSION=10)(a+)*zz/IS- -Capturing subpattern count = 1 -Recursion limit = 10 -No options -No first char -Need char = 'z' -Subject length lower bound = 2 -Starting chars: a z - aaaaaaaaaaaaaz -Error -21 (recursion limit exceeded) - aaaaaaaaaaaaaz\Q1000 -Error -21 (recursion limit exceeded) - -/(*LIMIT_RECURSION=10)(*LIMIT_RECURSION=1000)(a+)*zz/IS- -Capturing subpattern count = 1 -Recursion limit = 10 -No options -No first char -Need char = 'z' -Subject length lower bound = 2 -Starting chars: a z - aaaaaaaaaaaaaz -Error -21 (recursion limit exceeded) - -/(*LIMIT_RECURSION=1000)(a+)*zz/IS- -Capturing subpattern count = 1 -Recursion limit = 1000 -No options -No first char -Need char = 'z' -Subject length lower bound = 2 -Starting chars: a z - aaaaaaaaaaaaaz -No match - aaaaaaaaaaaaaz\Q10 -Error -21 (recursion limit exceeded) - -/-- This test causes a segfault with Perl 5.18.0 --/ - -/^(?=(a)){0}b(?1)/ - backgammon - 0: ba - -/(?|(?<n>f)|(?<n>b))/JI -Capturing subpattern count = 1 -Named capturing subpatterns: - n 1 -Options: dupnames -No first char -No need char - -/(?<a>abc)(?<a>z)\k<a>()/JDZS ------------------------------------------------------------------- - Bra - CBra 1 - abc - Ket - CBra 2 - z - Ket - \k<a>2 - CBra 3 - Ket - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 3 -Max back reference = 2 -Named capturing subpatterns: - a 1 - a 2 -Options: dupnames -First char = 'a' -Need char = 'z' -Subject length lower bound = 5 -No starting char list - -/a*[bcd]/BZ ------------------------------------------------------------------- - Bra - a*+ - [b-d] - Ket - End ------------------------------------------------------------------- - -/[bcd]*a/BZ ------------------------------------------------------------------- - Bra - [b-d]*+ - a - Ket - End ------------------------------------------------------------------- - -/-- A complete set of tests for auto-possessification of character types --/ - -/\D+\D \D+\d \D+\S \D+\s \D+\W \D+\w \D+. \D+\C \D+\R \D+\H \D+\h \D+\V \D+\v \D+\Z \D+\z \D+$/BZx ------------------------------------------------------------------- - Bra - \D+ - \D - \D++ - \d - \D+ - \S - \D+ - \s - \D+ - \W - \D+ - \w - \D+ - Any - \D+ - AllAny - \D+ - \R - \D+ - \H - \D+ - \h - \D+ - \V - \D+ - \v - \D+ - \Z - \D++ - \z - \D+ - $ - Ket - End ------------------------------------------------------------------- - -/\d+\D \d+\d \d+\S \d+\s \d+\W \d+\w \d+. \d+\C \d+\R \d+\H \d+\h \d+\V \d+\v \d+\Z \d+\z \d+$/BZx ------------------------------------------------------------------- - Bra - \d++ - \D - \d+ - \d - \d+ - \S - \d++ - \s - \d++ - \W - \d+ - \w - \d+ - Any - \d+ - AllAny - \d++ - \R - \d+ - \H - \d++ - \h - \d+ - \V - \d++ - \v - \d++ - \Z - \d++ - \z - \d++ - $ - Ket - End ------------------------------------------------------------------- - -/\S+\D \S+\d \S+\S \S+\s \S+\W \S+\w \S+. \S+\C \S+\R \S+\H \S+\h \S+\V \S+\v \S+\Z \S+\z \S+$/BZx ------------------------------------------------------------------- - Bra - \S+ - \D - \S+ - \d - \S+ - \S - \S++ - \s - \S+ - \W - \S+ - \w - \S+ - Any - \S+ - AllAny - \S++ - \R - \S+ - \H - \S++ - \h - \S+ - \V - \S++ - \v - \S++ - \Z - \S++ - \z - \S++ - $ - Ket - End ------------------------------------------------------------------- - -/\s+\D \s+\d \s+\S \s+\s \s+\W \s+\w \s+. \s+\C \s+\R \s+\H \s+\h \s+\V \s+\v \s+\Z \s+\z \s+$/BZx ------------------------------------------------------------------- - Bra - \s+ - \D - \s++ - \d - \s++ - \S - \s+ - \s - \s+ - \W - \s++ - \w - \s+ - Any - \s+ - AllAny - \s+ - \R - \s+ - \H - \s+ - \h - \s+ - \V - \s+ - \v - \s+ - \Z - \s++ - \z - \s+ - $ - Ket - End ------------------------------------------------------------------- - -/\W+\D \W+\d \W+\S \W+\s \W+\W \W+\w \W+. \W+\C \W+\R \W+\H \W+\h \W+\V \W+\v \W+\Z \W+\z \W+$/BZx ------------------------------------------------------------------- - Bra - \W+ - \D - \W++ - \d - \W+ - \S - \W+ - \s - \W+ - \W - \W++ - \w - \W+ - Any - \W+ - AllAny - \W+ - \R - \W+ - \H - \W+ - \h - \W+ - \V - \W+ - \v - \W+ - \Z - \W++ - \z - \W+ - $ - Ket - End ------------------------------------------------------------------- - -/\w+\D \w+\d \w+\S \w+\s \w+\W \w+\w \w+. \w+\C \w+\R \w+\H \w+\h \w+\V \w+\v \w+\Z \w+\z \w+$/BZx ------------------------------------------------------------------- - Bra - \w+ - \D - \w+ - \d - \w+ - \S - \w++ - \s - \w++ - \W - \w+ - \w - \w+ - Any - \w+ - AllAny - \w++ - \R - \w+ - \H - \w++ - \h - \w+ - \V - \w++ - \v - \w++ - \Z - \w++ - \z - \w++ - $ - Ket - End ------------------------------------------------------------------- - -/\C+\D \C+\d \C+\S \C+\s \C+\W \C+\w \C+. \C+\C \C+\R \C+\H \C+\h \C+\V \C+\v \C+\Z \C+\z \C+$/BZx ------------------------------------------------------------------- - Bra - AllAny+ - \D - AllAny+ - \d - AllAny+ - \S - AllAny+ - \s - AllAny+ - \W - AllAny+ - \w - AllAny+ - Any - AllAny+ - AllAny - AllAny+ - \R - AllAny+ - \H - AllAny+ - \h - AllAny+ - \V - AllAny+ - \v - AllAny+ - \Z - AllAny++ - \z - AllAny+ - $ - Ket - End ------------------------------------------------------------------- - -/\R+\D \R+\d \R+\S \R+\s \R+\W \R+\w \R+. \R+\C \R+\R \R+\H \R+\h \R+\V \R+\v \R+\Z \R+\z \R+$/BZx ------------------------------------------------------------------- - Bra - \R+ - \D - \R++ - \d - \R+ - \S - \R++ - \s - \R+ - \W - \R++ - \w - \R++ - Any - \R+ - AllAny - \R+ - \R - \R+ - \H - \R++ - \h - \R+ - \V - \R+ - \v - \R+ - \Z - \R++ - \z - \R+ - $ - Ket - End ------------------------------------------------------------------- - -/\H+\D \H+\d \H+\S \H+\s \H+\W \H+\w \H+. \H+\C \H+\R \H+\H \H+\h \H+\V \H+\v \H+\Z \H+\z \H+$/BZx ------------------------------------------------------------------- - Bra - \H+ - \D - \H+ - \d - \H+ - \S - \H+ - \s - \H+ - \W - \H+ - \w - \H+ - Any - \H+ - AllAny - \H+ - \R - \H+ - \H - \H++ - \h - \H+ - \V - \H+ - \v - \H+ - \Z - \H++ - \z - \H+ - $ - Ket - End ------------------------------------------------------------------- - -/\h+\D \h+\d \h+\S \h+\s \h+\W \h+\w \h+. \h+\C \h+\R \h+\H \h+\h \h+\V \h+\v \h+\Z \h+\z \h+$/BZx ------------------------------------------------------------------- - Bra - \h+ - \D - \h++ - \d - \h++ - \S - \h+ - \s - \h+ - \W - \h++ - \w - \h+ - Any - \h+ - AllAny - \h++ - \R - \h++ - \H - \h+ - \h - \h+ - \V - \h++ - \v - \h+ - \Z - \h++ - \z - \h+ - $ - Ket - End ------------------------------------------------------------------- - -/\V+\D \V+\d \V+\S \V+\s \V+\W \V+\w \V+. \V+\C \V+\R \V+\H \V+\h \V+\V \V+\v \V+\Z \V+\z \V+$/BZx ------------------------------------------------------------------- - Bra - \V+ - \D - \V+ - \d - \V+ - \S - \V+ - \s - \V+ - \W - \V+ - \w - \V+ - Any - \V+ - AllAny - \V++ - \R - \V+ - \H - \V+ - \h - \V+ - \V - \V++ - \v - \V+ - \Z - \V++ - \z - \V+ - $ - Ket - End ------------------------------------------------------------------- - -/\v+\D \v+\d \v+\S \v+\s \v+\W \v+\w \v+. \v+\C \v+\R \v+\H \v+\h \v+\V \v+\v \v+\Z \v+\z \v+$/BZx ------------------------------------------------------------------- - Bra - \v+ - \D - \v++ - \d - \v++ - \S - \v+ - \s - \v+ - \W - \v++ - \w - \v+ - Any - \v+ - AllAny - \v+ - \R - \v+ - \H - \v++ - \h - \v++ - \V - \v+ - \v - \v+ - \Z - \v++ - \z - \v+ - $ - Ket - End ------------------------------------------------------------------- - -/ a+\D a+\d a+\S a+\s a+\W a+\w a+. a+\C a+\R a+\H a+\h a+\V a+\v a+\Z a+\z a+$/BZx ------------------------------------------------------------------- - Bra - a+ - \D - a++ - \d - a+ - \S - a++ - \s - a++ - \W - a+ - \w - a+ - Any - a+ - AllAny - a++ - \R - a+ - \H - a++ - \h - a+ - \V - a++ - \v - a++ - \Z - a++ - \z - a++ - $ - Ket - End ------------------------------------------------------------------- - -/\n+\D \n+\d \n+\S \n+\s \n+\W \n+\w \n+. \n+\C \n+\R \n+\H \n+\h \n+\V \n+\v \n+\Z \n+\z \n+$/BZx ------------------------------------------------------------------- - Bra - \x0a+ - \D - \x0a++ - \d - \x0a++ - \S - \x0a+ - \s - \x0a+ - \W - \x0a++ - \w - \x0a+ - Any - \x0a+ - AllAny - \x0a+ - \R - \x0a+ - \H - \x0a++ - \h - \x0a++ - \V - \x0a+ - \v - \x0a+ - \Z - \x0a++ - \z - \x0a+ - $ - Ket - End ------------------------------------------------------------------- - -/ .+\D .+\d .+\S .+\s .+\W .+\w .+. .+\C .+\R .+\H .+\h .+\V .+\v .+\Z .+\z .+$/BZx ------------------------------------------------------------------- - Bra - Any+ - \D - Any+ - \d - Any+ - \S - Any+ - \s - Any+ - \W - Any+ - \w - Any+ - Any - Any+ - AllAny - Any++ - \R - Any+ - \H - Any+ - \h - Any+ - \V - Any+ - \v - Any+ - \Z - Any++ - \z - Any+ - $ - Ket - End ------------------------------------------------------------------- - -/ .+\D .+\d .+\S .+\s .+\W .+\w .+. .+\C .+\R .+\H .+\h .+\V .+\v .+\Z .+\z .+$/BZxs ------------------------------------------------------------------- - Bra - AllAny+ - \D - AllAny+ - \d - AllAny+ - \S - AllAny+ - \s - AllAny+ - \W - AllAny+ - \w - AllAny+ - AllAny - AllAny+ - AllAny - AllAny+ - \R - AllAny+ - \H - AllAny+ - \h - AllAny+ - \V - AllAny+ - \v - AllAny+ - \Z - AllAny++ - \z - AllAny+ - $ - Ket - End ------------------------------------------------------------------- - -/\D+$ \d+$ \S+$ \s+$ \W+$ \w+$ \C+$ \R+$ \H+$ \h+$ \V+$ \v+$ a+$ \n+$ .+$ .+$/BZxm ------------------------------------------------------------------- - Bra - \D+ - /m $ - \d++ - /m $ - \S++ - /m $ - \s+ - /m $ - \W+ - /m $ - \w++ - /m $ - AllAny+ - /m $ - \R+ - /m $ - \H+ - /m $ - \h+ - /m $ - \V+ - /m $ - \v+ - /m $ - a+ - /m $ - \x0a+ - /m $ - Any+ - /m $ - Any+ - /m $ - Ket - End ------------------------------------------------------------------- - -/(?=a+)a(a+)++a/BZ ------------------------------------------------------------------- - Bra - Assert - a++ - Ket - a - CBraPos 1 - a++ - KetRpos - a - Ket - End ------------------------------------------------------------------- - -/a+(bb|cc)a+(?:bb|cc)a+(?>bb|cc)a+(?:bb|cc)+a+(aa)a+(?:bb|aa)/BZ ------------------------------------------------------------------- - Bra - a++ - CBra 1 - bb - Alt - cc - Ket - a++ - Bra - bb - Alt - cc - Ket - a++ - Once_NC - bb - Alt - cc - Ket - a++ - Bra - bb - Alt - cc - KetRmax - a+ - CBra 2 - aa - Ket - a+ - Bra - bb - Alt - aa - Ket - Ket - End ------------------------------------------------------------------- - -/a+(bb|cc)?#a+(?:bb|cc)??#a+(?:bb|cc)?+#a+(?:bb|cc)*#a+(bb|cc)?a#a+(?:aa)?/BZ ------------------------------------------------------------------- - Bra - a++ - Brazero - CBra 1 - bb - Alt - cc - Ket - # - a++ - Braminzero - Bra - bb - Alt - cc - Ket - # - a++ - Once - Brazero - Bra - bb - Alt - cc - Ket - Ket - # - a++ - Brazero - Bra - bb - Alt - cc - KetRmax - # - a+ - Brazero - CBra 2 - bb - Alt - cc - Ket - a# - a+ - Brazero - Bra - aa - Ket - Ket - End ------------------------------------------------------------------- - -/a+(?:bb)?a#a+(?:|||)#a+(?:|b)a#a+(?:|||)?a/BZ ------------------------------------------------------------------- - Bra - a+ - Brazero - Bra - bb - Ket - a# - a++ - Bra - Alt - Alt - Alt - Ket - # - a+ - Bra - Alt - b - Ket - a# - a+ - Brazero - Bra - Alt - Alt - Alt - Ket - a - Ket - End ------------------------------------------------------------------- - -/[ab]*/BZ ------------------------------------------------------------------- - Bra - [ab]*+ - Ket - End ------------------------------------------------------------------- - aaaa - 0: aaaa - -/[ab]*?/BZ ------------------------------------------------------------------- - Bra - [ab]*? - Ket - End ------------------------------------------------------------------- - aaaa - 0: - -/[ab]?/BZ ------------------------------------------------------------------- - Bra - [ab]?+ - Ket - End ------------------------------------------------------------------- - aaaa - 0: a - -/[ab]??/BZ ------------------------------------------------------------------- - Bra - [ab]?? - Ket - End ------------------------------------------------------------------- - aaaa - 0: - -/[ab]+/BZ ------------------------------------------------------------------- - Bra - [ab]++ - Ket - End ------------------------------------------------------------------- - aaaa - 0: aaaa - -/[ab]+?/BZ ------------------------------------------------------------------- - Bra - [ab]+? - Ket - End ------------------------------------------------------------------- - aaaa - 0: a - -/[ab]{2,3}/BZ ------------------------------------------------------------------- - Bra - [ab]{2,3}+ - Ket - End ------------------------------------------------------------------- - aaaa - 0: aaa - -/[ab]{2,3}?/BZ ------------------------------------------------------------------- - Bra - [ab]{2,3}? - Ket - End ------------------------------------------------------------------- - aaaa - 0: aa - -/[ab]{2,}/BZ ------------------------------------------------------------------- - Bra - [ab]{2,}+ - Ket - End ------------------------------------------------------------------- - aaaa - 0: aaaa - -/[ab]{2,}?/BZ ------------------------------------------------------------------- - Bra - [ab]{2,}? - Ket - End ------------------------------------------------------------------- - aaaa - 0: aa - -/\d+\s{0,5}=\s*\S?=\w{0,4}\W*/BZ ------------------------------------------------------------------- - Bra - \d++ - \s{0,5}+ - = - \s*+ - \S? - = - \w{0,4}+ - \W*+ - Ket - End ------------------------------------------------------------------- - -/[a-d]{5,12}[e-z0-9]*#[^a-z]+[b-y]*a[2-7]?[^0-9a-z]+/BZ ------------------------------------------------------------------- - Bra - [a-d]{5,12}+ - [0-9e-z]*+ - # - [\x00-`{-\xff] (neg)++ - [b-y]*+ - a - [2-7]?+ - [\x00-/:-`{-\xff] (neg)++ - Ket - End ------------------------------------------------------------------- - -/[a-z]*\s#[ \t]?\S#[a-c]*\S#[C-G]+?\d#[4-8]*\D#[4-9,]*\D#[!$]{0,5}\w#[M-Xf-l]+\W#[a-c,]?\W/BZ ------------------------------------------------------------------- - Bra - [a-z]*+ - \s - # - [\x09 ]?+ - \S - # - [a-c]* - \S - # - [C-G]++ - \d - # - [4-8]*+ - \D - # - [,4-9]* - \D - # - [!$]{0,5}+ - \w - # - [M-Xf-l]++ - \W - # - [,a-c]? - \W - Ket - End ------------------------------------------------------------------- - -/a+(aa|bb)*c#a*(bb|cc)*a#a?(bb|cc)*d#[a-f]*(g|hh)*f/BZ ------------------------------------------------------------------- - Bra - a+ - Brazero - CBra 1 - aa - Alt - bb - KetRmax - c# - a* - Brazero - CBra 2 - bb - Alt - cc - KetRmax - a# - a?+ - Brazero - CBra 3 - bb - Alt - cc - KetRmax - d# - [a-f]* - Brazero - CBra 4 - g - Alt - hh - KetRmax - f - Ket - End ------------------------------------------------------------------- - -/[a-f]*(g|hh|i)*i#[a-x]{4,}(y{0,6})*y#[a-k]+(ll|mm)+n/BZ ------------------------------------------------------------------- - Bra - [a-f]*+ - Brazero - CBra 1 - g - Alt - hh - Alt - i - KetRmax - i# - [a-x]{4,} - Brazero - SCBra 2 - y{0,6} - KetRmax - y# - [a-k]++ - CBra 3 - ll - Alt - mm - KetRmax - n - Ket - End ------------------------------------------------------------------- - -/[a-f]*(?>gg|hh)+#[a-f]*(?>gg|hh)?#[a-f]*(?>gg|hh)*a#[a-f]*(?>gg|hh)*h/BZ ------------------------------------------------------------------- - Bra - [a-f]*+ - Once_NC - gg - Alt - hh - KetRmax - # - [a-f]*+ - Brazero - Once_NC - gg - Alt - hh - Ket - # - [a-f]* - Brazero - Once_NC - gg - Alt - hh - KetRmax - a# - [a-f]*+ - Brazero - Once_NC - gg - Alt - hh - KetRmax - h - Ket - End ------------------------------------------------------------------- - -/[a-c]*d/DZS ------------------------------------------------------------------- - Bra - [a-c]*+ - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' -Subject length lower bound = 1 -Starting chars: a b c d - -/[a-c]+d/DZS ------------------------------------------------------------------- - Bra - [a-c]++ - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' -Subject length lower bound = 2 -Starting chars: a b c - -/[a-c]?d/DZS ------------------------------------------------------------------- - Bra - [a-c]?+ - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' -Subject length lower bound = 1 -Starting chars: a b c d - -/[a-c]{4,6}d/DZS ------------------------------------------------------------------- - Bra - [a-c]{4,6}+ - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' -Subject length lower bound = 5 -Starting chars: a b c - -/[a-c]{0,6}d/DZS ------------------------------------------------------------------- - Bra - [a-c]{0,6}+ - d - Ket - End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'd' -Subject length lower bound = 1 -Starting chars: a b c d - -/-- End of special auto-possessive tests --/ - -/^A\o{1239}B/ -Failed: non-octal character in \o{} (closing brace missing?) at offset 8 - -/^A\oB/ -Failed: missing opening brace after \o at offset 3 - -/^A\x{zz}B/ -Failed: non-hex character in \x{} (closing brace missing?) at offset 5 - -/^A\x{12Z/ -Failed: non-hex character in \x{} (closing brace missing?) at offset 7 - -/^A\x{/ -Failed: non-hex character in \x{} (closing brace missing?) at offset 5 - -/[ab]++/BZO ------------------------------------------------------------------- - Bra - [ab]++ - Ket - End ------------------------------------------------------------------- - -/[^ab]*+/BZO ------------------------------------------------------------------- - Bra - [\x00-`c-\xff] (neg)*+ - Ket - End ------------------------------------------------------------------- - -/a{4}+/BZO ------------------------------------------------------------------- - Bra - a{4} - Ket - End ------------------------------------------------------------------- - -/a{4}+/BZOi ------------------------------------------------------------------- - Bra - /i a{4} - Ket - End ------------------------------------------------------------------- - -/[a-[:digit:]]+/ -Failed: invalid range in character class at offset 3 - -/[A-[:digit:]]+/ -Failed: invalid range in character class at offset 3 - -/[a-[.xxx.]]+/ -Failed: invalid range in character class at offset 3 - -/[a-[=xxx=]]+/ -Failed: invalid range in character class at offset 3 - -/[a-[!xxx!]]+/ -Failed: range out of order in character class at offset 3 - -/[A-[!xxx!]]+/ - A]]] - 0: A]]] - -/[a-\d]+/ -Failed: invalid range in character class at offset 4 - -/(?<0abc>xx)/ -Failed: group name must start with a non-digit at offset 3 - -/(?&1abc)xx(?<1abc>y)/ -Failed: group name must start with a non-digit at offset 3 - -/(?<ab-cd>xx)/ -Failed: syntax error in subpattern name (missing terminator) at offset 5 - -/(?'0abc'xx)/ -Failed: group name must start with a non-digit at offset 3 - -/(?P<0abc>xx)/ -Failed: group name must start with a non-digit at offset 4 - -/\k<5ghj>/ -Failed: group name must start with a non-digit at offset 3 - -/\k'5ghj'/ -Failed: group name must start with a non-digit at offset 3 - -/\k{2fgh}/ -Failed: group name must start with a non-digit at offset 3 - -/(?P=8yuki)/ -Failed: group name must start with a non-digit at offset 4 - -/\g{4df}/ -Failed: group name must start with a non-digit at offset 3 - -/(?&1abc)xx(?<1abc>y)/ -Failed: group name must start with a non-digit at offset 3 - -/(?P>1abc)xx(?<1abc>y)/ -Failed: group name must start with a non-digit at offset 4 - -/\g'3gh'/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 7 - -/\g<5fg>/ -Failed: \g is not followed by a braced, angle-bracketed, or quoted name/number or by a plain number at offset 7 - -/(?(<4gh>)abc)/ -Failed: group name must start with a non-digit at offset 4 - -/(?('4gh')abc)/ -Failed: group name must start with a non-digit at offset 4 - -/(?(4gh)abc)/ -Failed: malformed number or name after (?( at offset 4 - -/(?(R&6yh)abc)/ -Failed: group name must start with a non-digit at offset 5 - -/-- Test the ugly "start or end of word" compatibility syntax --/ - -/[[:<:]]red[[:>:]]/BZ ------------------------------------------------------------------- - Bra - \b - Assert - \w - Ket - red - \b - AssertB - Reverse - \w - Ket - Ket - End ------------------------------------------------------------------- - little red riding hood - 0: red - a /red/ thing - 0: red - red is a colour - 0: red - put it all on red - 0: red - ** Failers -No match - no reduction -No match - Alfred Winifred -No match - -/[a[:<:]] should give error/ -Failed: unknown POSIX class name at offset 4 - -/(?=ab\K)/+ - abcd -Start of matched string is beyond its end - displaying from end to start. - 0: ab - 0+ abcd - -/abcd/f<lf> - xx\nxabcd -No match - -/ -- Test stack check external calls --/ - -/(((((a)))))/Q0 - -/(((((a)))))/Q1 -Failed: parentheses are too deeply nested (stack check) at offset 0 - -/(((((a)))))/Q -** Missing 0 or 1 after /Q - -/-- End of testinput2 --/ |