/************************************************* * 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) 1997-2012 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. ----------------------------------------------------------------------------- */ #ifndef PCRE_INCLUDED /* This module contains some fixed tables that are used by more than one of the PCRE code modules. The tables are also #included by the pcretest program, which uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name clashes with the library. */ #ifdef HAVE_CONFIG_H #include "config.h" #endif #include "pcre_internal.h" #endif /* PCRE_INCLUDED */ /* Table of sizes for the fixed-length opcodes. It's defined in a macro so that the definition is next to the definition of the opcodes in pcre_internal.h. */ const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; /* Tables of horizontal and vertical whitespace characters, suitable for adding to classes. */ const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST }; const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST }; /************************************************* * Tables for UTF-8 support * *************************************************/ /* These are the breakpoints for different numbers of bytes in a UTF-8 character. */ #if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32)) /* These tables are also required by pcretest in 16- or 32-bit mode. */ const int PRIV(utf8_table1)[] = { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; const int PRIV(utf8_table1_size) = sizeof(PRIV(utf8_table1)) / sizeof(int); /* These are the indicator bits and the mask for the data bits to set in the first byte of a character, indexed by the number of additional bytes. */ const int PRIV(utf8_table2)[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; const int PRIV(utf8_table3)[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; /* Table of the number of extra bytes, indexed by the first byte masked with 0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ const pcre_uint8 PRIV(utf8_table4)[] = { 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/ #ifdef SUPPORT_UTF /* Table to translate from particular type value to the general value. */ const pcre_uint32 PRIV(ucp_gentype)[] = { ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ ucp_N, ucp_N, ucp_N, /* Nd, Nl, No */ ucp_P, ucp_P, ucp_P, ucp_P, ucp_P, /* Pc, Pd, Pe, Pf, Pi */ ucp_P, ucp_P, /* Ps, Po */ ucp_S, ucp_S, ucp_S, ucp_S, /* Sc, Sk, Sm, So */ ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ }; /* This table encodes the rules for finding the end of an extended grapheme cluster. Every code point has a grapheme break property which is one of the ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the properties of two adjacent code points. The left property selects a word from the table, and the right property selects a bit from that word like this: ucp_gbtable[left-property] & (1 << right-property) The value is non-zero if a grapheme break is NOT permitted between the relevant two code points. The breaking rules are as follows: 1. Break at the start and end of text (pretty obviously). 2. Do not break between a CR and LF; otherwise, break before and after controls. 3. Do not break Hangul syllable sequences, the rules for which are: L may be followed by L, V, LV or LVT LV or V may be followed by V or T LVT or T may be followed by T 4. Do not break before extending characters. The next two rules are only for extended grapheme clusters (but that's what we are implementing). 5. Do not break before SpacingMarks. 6. Do not break after Prepend characters. 7. Otherwise, break everywhere. */ const pcre_uint32 PRIV(ucp_gbtable[]) = { (1<