diff options
Diffstat (limited to 'src/modules/common')
| -rw-r--r-- | src/modules/common/Makefile | 4 | ||||
| -rw-r--r-- | src/modules/common/Makefile.am | 21 | ||||
| -rw-r--r-- | src/modules/common/compress.cpp | 767 | ||||
| -rw-r--r-- | src/modules/common/entriesblk.cpp | 169 | ||||
| -rw-r--r-- | src/modules/common/lzsscomprs.cpp | 668 | ||||
| -rw-r--r-- | src/modules/common/rawstr.cpp | 555 | ||||
| -rw-r--r-- | src/modules/common/rawstr4.cpp | 561 | ||||
| -rw-r--r-- | src/modules/common/rawverse.cpp | 353 | ||||
| -rw-r--r-- | src/modules/common/sapphire.cpp | 231 | ||||
| -rw-r--r-- | src/modules/common/swcipher.cpp | 128 | ||||
| -rw-r--r-- | src/modules/common/swcomprs.cpp | 193 | ||||
| -rw-r--r-- | src/modules/common/swcomprs.doc | 802 | ||||
| -rw-r--r-- | src/modules/common/zipcomprs.cpp | 161 | ||||
| -rw-r--r-- | src/modules/common/zstr.cpp | 718 | ||||
| -rw-r--r-- | src/modules/common/zverse.cpp | 538 |
15 files changed, 0 insertions, 5869 deletions
diff --git a/src/modules/common/Makefile b/src/modules/common/Makefile deleted file mode 100644 index 81f7721..0000000 --- a/src/modules/common/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -root := ../../.. - -all: - make -C ${root} diff --git a/src/modules/common/Makefile.am b/src/modules/common/Makefile.am deleted file mode 100644 index b411660..0000000 --- a/src/modules/common/Makefile.am +++ /dev/null @@ -1,21 +0,0 @@ -commondir = $(top_srcdir)/src/modules/common - -libsword_la_SOURCES += $(commondir)/rawstr.cpp -libsword_la_SOURCES += $(commondir)/rawstr4.cpp -libsword_la_SOURCES += $(commondir)/swcomprs.cpp -libsword_la_SOURCES += $(commondir)/lzsscomprs.cpp - -if ZLIB -SWZLIB = $(commondir)/zipcomprs.cpp -else -SWZLIB = -endif -libsword_la_SOURCES += $(SWZLIB) -libsword_la_SOURCES += $(commondir)/rawverse.cpp -libsword_la_SOURCES += $(commondir)/swcipher.cpp -libsword_la_SOURCES += $(commondir)/zverse.cpp -libsword_la_SOURCES += $(commondir)/zstr.cpp -libsword_la_SOURCES += $(commondir)/entriesblk.cpp - -libsword_la_SOURCES += $(commondir)/sapphire.cpp - diff --git a/src/modules/common/compress.cpp b/src/modules/common/compress.cpp deleted file mode 100644 index 5031adb..0000000 --- a/src/modules/common/compress.cpp +++ /dev/null @@ -1,767 +0,0 @@ -Compression Info, 10-11-95 -Jeff Wheeler - -Source of Algorithm -------------------- - -The compression algorithms used here are based upon the algorithms developed and published by Haruhiko Okumura in a paper entitled "Data Compression Algorithms of LARC and LHarc." This paper discusses three compression algorithms, LSZZ, LZARI, and LZHUF. LZSS is described as the "first" of these, and is described as providing moderate compression with good speed. LZARI is described as an improved LZSS, a combination of the LZSS algorithm with adaptive arithmetic compression. It is described as being slower than LZSS but with better compression. LZHUF (the basis of the common LHA compression program) was included in the paper, however, a free usage license was not included. - -The following are copies of the statements included at the beginning of each source code listing that was supplied in the working paper. - - LZSS, dated 4/6/89, marked as "Use, distribute and - modify this program freely." - - LZARI, dated 4/7/89, marked as "Use, distribute and - modify this program freely." - - LZHUF, dated 11/20/88, written by Haruyasu Yoshizaki, - translated by Haruhiko Okumura on 4/7/89. Not - expressly marked as redistributable or modifiable. - -Since both LZSS and LZARI are marked as "use, distribute and modify freely" we have felt at liberty basing our compression algorithm on either of these. - -Selection of Algorithm ----------------------- - -Working samples of three possible compression algorithms are supplied in Okumura's paper. Which should be used? - -LZSS is the fastest at decompression, but does not generated as small a compressed file as the other methods. The other two methods provided, perhaps, a 15% improvement in compression. Or, put another way, on a 100K file, LZSS might compress it to 50K while the others might approach 40-45K. For STEP purposes, it was decided that decoding speed was of more importance than tighter compression. For these reasons, the first compression algorithm implemented is the LZSS algorithm. - -About LZSS Encoding -------------------- - -(adapted from Haruhiko Okumura's paper) - -This scheme was proposed by Ziv and Lempel [1]. A slightly modified version is described by Storer and Szymanski [2]. An implementation using a binary tree has been proposed by Bell [3]. - -The algorithm is quite simple. -1. Keep a ring buffer which initially contains all space characters. -2. Read several letters from the file to the buffer. -3. Search the buffer for the longest string that matches the letters just read, and send its length and position into the buffer. - -If the ring buffer is 4096 bytes, the position can be stored in 12 bits. If the length is represented in 4 bits, the <position, length> pair is two bytes long. If the longest match is no more than two characters, then just one character is sent without encoding. The process starts again with the next character. An extra bit is sent each time to tell the decoder whether the next item is a character of a <position, length> pair. - -[1] J. Ziv and A. Lempel, IEEE Transactions IT-23, 337-343 (1977). -[2] J. A. Storer and T. G. Szymanski, J. ACM, 29, 928-951 (1982). -[3] T.C. Gell, IEEE Transactions COM-34, 1176-1182 (1986). - -void InitTree( // no return value - void); // no parameters - -void InsertNode( // no return value - short int Pos); // position in the buffer - -void DeleteNode( // no return value - short int Node); // node to be removed - -void Encode( // no return value - void); // no parameters - -void Decode( // no return value - void); // no parameters - -// The following are constant sizes used by the compression algorithm. -// -// N - This is the size of the ring buffer. It is set -// to 4K. It is important to note that a position -// within the ring buffer requires 12 bits. -// -// F - This is the maximum length of a character sequence -// that can be taken from the ring buffer. It is set -// to 18. Note that a length must be 3 before it is -// worthwhile to store a position/length pair, so the -// length can be encoded in only 4 bits. Or, put yet -// another way, it is not necessary to encode a length -// of 0-18, it is necessary to encode a length of -// 3-18, which requires 4 bits. -// -// THRESHOLD - It takes 2 bytes to store an offset and -// a length. If a character sequence only -// requires 1 or 2 characters to store -// uncompressed, then it is better to store -// it uncompressed than as an offset into -// the ring buffer. -// -// Note that the 12 bits used to store the position and the 4 bits -// used to store the length equal a total of 16 bits, or 2 bytes. - -#define N 4096 -#define F 18 -#define THRESHOLD 3 -#define NOT_USED N - -// m_ring_buffer is a text buffer. It contains "nodes" of -// uncompressed text that can be indexed by position. That is, -// a substring of the ring buffer can be indexed by a position -// and a length. When decoding, the compressed text may contain -// a position in the ring buffer and a count of the number of -// bytes from the ring buffer that are to be moved into the -// uncompressed buffer. -// -// This ring buffer is not maintained as part of the compressed -// text. Instead, it is reconstructed dynamically. That is, -// it starts out empty and gets built as the text is decompressed. -// -// The ring buffer contain N bytes, with an additional F - 1 bytes -// to facilitate string comparison. - -unsigned char m_ring_buffer[N + F - 1]; - -// m_match_position and m_match_length are set by InsertNode(). -// -// These variables indicate the position in the ring buffer -// and the number of characters at that position that match -// a given string. - -short int m_match_position; -short int m_match_length; - -// m_lson, m_rson, and m_dad are the Japanese way of referring to -// a tree structure. The dad is the parent and it has a right and -// left son (child). -// -// For i = 0 to N-1, m_rson[i] and m_lson[i] will be the right -// and left children of node i. -// -// For i = 0 to N-1, m_dad[i] is the parent of node i. -// -// For i = 0 to 255, rson[N + i + 1] is the root of the tree for -// strings that begin with the character i. Note that this requires -// one byte characters. -// -// These nodes store values of 0...(N-1). Memory requirements -// can be reduces by using 2-byte integers instead of full 4-byte -// integers (for 32-bit applications). Therefore, these are -// defined as "short ints." - -short int m_lson[N + 1]; -short int m_rson[N + 257]; -short int m_dad[N + 1]; - -/* - ------------------------------------------------------------------------- - cLZSS::InitTree - - This function initializes the tree nodes to "empty" states. - ------------------------------------------------------------------------- -*/ - -void cLZSS::InitTree( // no return value - void) // no parameters - throw() // exception list - - { - int i; - - // For i = 0 to N - 1, m_rson[i] and m_lson[i] will be the right - // and left children of node i. These nodes need not be - // initialized. However, for debugging purposes, it is nice to - // have them initialized. Since this is only used for compression - // (not decompression), I don't mind spending the time to do it. - // - // For the same range of i, m_dad[i] is the parent of node i. - // These are initialized to a known value that can represent - // a "not used" state. - - for (i = 0; i < N; i++) - { - m_lson[i] = NOT_USED; - m_rson[i] = NOT_USED; - m_dad[i] = NOT_USED; - } - - // For i = 0 to 255, m_rson[N + i + 1] is the root of the tree - // for strings that begin with the character i. This is why - // the right child array is larger than the left child array. - // These are also initialzied to a "not used" state. - // - // Note that there are 256 of these, one for each of the possible - // 256 characters. - - for (i = N + 1; i <= (N + 256); i++) - { - m_rson[i] = NOT_USED; - } - - // Done. - } - -/* - ------------------------------------------------------------------------- - cLZSS::InsertNode - - This function inserts a string from the ring buffer into one of - the trees. It loads the match position and length member variables - for the longest match. - - The string to be inserted is identified by the parameter Pos, - A full F bytes are inserted. So, m_ring_buffer[Pos ... Pos+F-1] - are inserted. - - If the matched length is exactly F, then an old node is removed - in favor of the new one (because the old one will be deleted - sooner). - - Note that Pos plays a dual role. It is used as both a position - in the ring buffer and also as a tree node. m_ring_buffer[Pos] - defines a character that is used to identify a tree node. - ------------------------------------------------------------------------- -*/ - -void cLZSS::InsertNode( // no return value - short int Pos) // position in the buffer - throw() // exception list - - { - short int i; - short int p; - int cmp; - unsigned char * key; - - ASSERT(Pos >= 0); - ASSERT(Pos < N); - - cmp = 1; - key = &(m_ring_buffer[Pos]); - - // The last 256 entries in m_rson contain the root nodes for - // strings that begin with a letter. Get an index for the - // first letter in this string. - - p = (short int) (N + 1 + key[0]); - - // Set the left and right tree nodes for this position to "not - // used." - - m_lson[Pos] = NOT_USED; - m_rson[Pos] = NOT_USED; - - // Haven't matched anything yet. - - m_match_length = 0; - - for ( ; ; ) - { - if (cmp >= 0) - { - if (m_rson[p] != NOT_USED) - { - p = m_rson[p]; - } - else - { - m_rson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - else - { - if (m_lson[p] != NOT_USED) - { - p = m_lson[p]; - } - else - { - m_lson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - - // Should we go to the right or the left to look for the - // next match? - - for (i = 1; i < F; i++) - { - cmp = key[i] - m_ring_buffer[p + i]; - if (cmp != 0) - break; - } - - if (i > m_match_length) - { - m_match_position = p; - m_match_length = i; - - if (i >= F) - break; - } - } - - m_dad[Pos] = m_dad[p]; - m_lson[Pos] = m_lson[p]; - m_rson[Pos] = m_rson[p]; - - m_dad[ m_lson[p] ] = Pos; - m_dad[ m_rson[p] ] = Pos; - - if (m_rson[ m_dad[p] ] == p) - { - m_rson[ m_dad[p] ] = Pos; - } - else - { - m_lson[ m_dad[p] ] = Pos; - } - - // Remove "p" - - m_dad[p] = NOT_USED; - } - -/* - ------------------------------------------------------------------------- - cLZSS::DeleteNode - - This function removes the node "Node" from the tree. - ------------------------------------------------------------------------- -*/ - -void cLZSS::DeleteNode( // no return value - short int Node) // node to be removed - throw() // exception list - - { - short int q; - - ASSERT(Node >= 0); - ASSERT(Node < (N+1)); - - if (m_dad[Node] == NOT_USED) - { - // not in tree, nothing to do - return; - } - - if (m_rson[Node] == NOT_USED) - { - q = m_lson[Node]; - } - else if (m_lson[Node] == NOT_USED) - { - q = m_rson[Node]; - } - else - { - q = m_lson[Node]; - if (m_rson[q] != NOT_USED) - { - do - { - q = m_rson[q]; - } - while (m_rson[q] != NOT_USED); - - m_rson[ m_dad[q] ] = m_lson[q]; - m_dad[ m_lson[q] ] = m_dad[q]; - m_lson[q] = m_lson[Node]; - m_dad[ m_lson[Node] ] = q; - } - - m_rson[q] = m_rson[Node]; - m_dad[ m_rson[Node] ] = q; - } - - m_dad[q] = m_dad[Node]; - - if (m_rson[ m_dad[Node] ] == Node) - { - m_rson[ m_dad[Node] ] = q; - } - else - { - m_lson[ m_dad[Node] ] = q; - } - - m_dad[Node] = NOT_USED; - } - -/* - ------------------------------------------------------------------------- - cLZSS::Encode - - This function "encodes" the input stream into the output stream. - The GetChars() and SendChars() functions are used to separate - this method from the actual i/o. - ------------------------------------------------------------------------- -*/ - -void cLZSS::Encode( // no return value - void) // no parameters - - { - short int i; // an iterator - short int r; // node number in the binary tree - short int s; // position in the ring buffer - unsigned short int len; // len of initial string - short int last_match_length; // length of last match - short int code_buf_pos; // position in the output buffer - unsigned char code_buf[17]; // the output buffer - unsigned char mask; // bit mask for byte 0 of out buf - unsigned char c; // character read from string - - // Start with a clean tree. - - InitTree(); - - // code_buf[0] works as eight flags. A "1" represents that the - // unit is an unencoded letter (1 byte), and a "0" represents - // that the next unit is a <position,length> pair (2 bytes). - // - // code_buf[1..16] stores eight units of code. Since the best - // we can do is store eight <position,length> pairs, at most 16 - // bytes are needed to store this. - // - // This is why the maximum size of the code buffer is 17 bytes. - - code_buf[0] = 0; - code_buf_pos = 1; - - // Mask iterates over the 8 bits in the code buffer. The first - // character ends up being stored in the low bit. - // - // bit 8 7 6 5 4 3 2 1 - // | | - // | first sequence in code buffer - // | - // last sequence in code buffer - - mask = 1; - - s = 0; - r = (short int) N - (short int) F; - - // Initialize the ring buffer with spaces... - - // Note that the last F bytes of the ring buffer are not filled. - // This is because those F bytes will be filled in immediately - // with bytes from the input stream. - - memset(m_ring_buffer, ' ', N - F); - - // Read F bytes into the last F bytes of the ring buffer. - // - // This function loads the buffer with X characters and returns - // the actual amount loaded. - - len = GetChars(&(m_ring_buffer[r]), F); - - // Make sure there is something to be compressed. - - if (len == 0) - return; - - // Insert the F strings, each of which begins with one or more - // 'space' characters. Note the order in which these strings - // are inserted. This way, degenerate trees will be less likely - // to occur. - - for (i = 1; i <= F; i++) - { - InsertNode((short int) (r - i)); - } - - // Finally, insert the whole string just read. The - // member variables match_length and match_position are set. - - InsertNode(r); - - // Now that we're preloaded, continue till done. - - do - { - - // m_match_length may be spuriously long near the end of - // text. - - if (m_match_length > len) - { - m_match_length = len; - } - - // Is it cheaper to store this as a single character? If so, - // make it so. - - if (m_match_length < THRESHOLD) - { - // Send one character. Remember that code_buf[0] is the - // set of flags for the next eight items. - - m_match_length = 1; - code_buf[0] |= mask; - code_buf[code_buf_pos++] = m_ring_buffer[r]; - } - - // Otherwise, we do indeed have a string that can be stored - // compressed to save space. - - else - { - // The next 16 bits need to contain the position (12 bits) - // and the length (4 bits). - - code_buf[code_buf_pos++] = (unsigned char) m_match_position; - code_buf[code_buf_pos++] = (unsigned char) ( - ((m_match_position >> 4) & 0xf0) | - (m_match_length - THRESHOLD) ); - } - - // Shift the mask one bit to the left so that it will be ready - // to store the new bit. - - mask = (unsigned char) (mask << 1); - - // If the mask is now 0, then we know that we have a full set - // of flags and items in the code buffer. These need to be - // output. - - if (mask == 0) - { - // code_buf is the buffer of characters to be output. - // code_buf_pos is the number of characters it contains. - - SendChars(code_buf, code_buf_pos); - - // Reset for next buffer... - - code_buf[0] = 0; - code_buf_pos = 1; - mask = 1; - } - - last_match_length = m_match_length; - - // Delete old strings and read new bytes... - - for (i = 0; i < last_match_length; i++) - { - - // Get next character... - - if (GetChars(&c, 1) != 1) - break; - - // Delete "old strings" - - DeleteNode(s); - - // Put this character into the ring buffer. - // - // The original comment here says "If the position is near - // the end of the buffer, extend the buffer to make - // string comparison easier." - // - // That's a little misleading, because the "end" of the - // buffer is really what we consider to be the "beginning" - // of the buffer, that is, positions 0 through F. - // - // The idea is that the front end of the buffer is duplicated - // into the back end so that when you're looking at characters - // at the back end of the buffer, you can index ahead (beyond - // the normal end of the buffer) and see the characters - // that are at the front end of the buffer wihtout having - // to adjust the index. - // - // That is... - // - // 1234xxxxxxxxxxxxxxxxxxxxxxxxxxxxx1234 - // | | | - // position 0 end of buffer | - // | - // duplicate of front of buffer - - m_ring_buffer[s] = c; - - if (s < F - 1) - { - m_ring_buffer[s + N] = c; - } - - // Increment the position, and wrap around when we're at - // the end. Note that this relies on N being a power of 2. - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Register the string that is found in - // m_ring_buffer[r..r+F-1]. - - InsertNode(r); - } - - // If we didn't quit because we hit the last_match_length, - // then we must have quit because we ran out of characters - // to process. - - while (i++ < last_match_length) - { - DeleteNode(s); - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Note that len hitting 0 is the key that causes the - // do...while() to terminate. This is the only place - // within the loop that len is modified. - // - // Its original value is F (or a number less than F for - // short strings). - - if (--len) - { - InsertNode(r); /* buffer may not be empty. */ - } - } - - // End of do...while() loop. Continue processing until there - // are no more characters to be compressed. The variable - // "len" is used to signal this condition. - } - while (len > 0); - - // There could still be something in the output buffer. Send it - // now. - - if (code_buf_pos > 1) - { - // code_buf is the encoded string to send. - // code_buf_ptr is the number of characters. - - SendChars(code_buf, code_buf_pos); - } - - // Done! - } - -/* - ------------------------------------------------------------------------- - cLZSS::Decode - - This function "decodes" the input stream into the output stream. - The GetChars() and SendChars() functions are used to separate - this method from the actual i/o. - ------------------------------------------------------------------------- -*/ - -void cLZSS::Decode( // no return value - void) // no parameters - - { - int k; - int r; // node number - unsigned char c[F]; // an array of chars - unsigned char flags; // 8 bits of flags - int flag_count; // which flag we're on - short int pos; // position in the ring buffer - short int len; // number of chars in ring buffer - - // Initialize the ring buffer with a common string. - // - // Note that the last F bytes of the ring buffer are not filled. - - memset(m_ring_buffer, ' ', N - F); - - r = N - F; - - flags = (char) 0; - flag_count = 0; - - for ( ; ; ) - { - - // If there are more bits of interest in this flag, then - // shift that next interesting bit into the 1's position. - // - // If this flag has been exhausted, the next byte must - // be a flag. - - if (flag_count > 0) - { - flags = (unsigned char) (flags >> 1); - flag_count--; - } - else - { - // Next byte must be a flag. - - if (GetChars(&flags, 1) != 1) - break; - - // Set the flag counter. While at first it might appear - // that this should be an 8 since there are 8 bits in the - // flag, it should really be a 7 because the shift must - // be performed 7 times in order to see all 8 bits. - - flag_count = 7; - } - - // If the low order bit of the flag is now set, then we know - // that the next byte is a single, unencoded character. - - if (flags & 1) - { - if (GetChars(c, 1) != 1) - break; - - if (SendChars(c, 1) != 1) - break; - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[0]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Otherwise, we know that the next two bytes are a - // <position,length> pair. The position is in 12 bits and - // the length is in 4 bits. - - else - { - // Original code: - // if ((i = getc(infile)) == EOF) - // break; - // if ((j = getc(infile)) == EOF) - // break; - // i |= ((j & 0xf0) << 4); - // j = (j & 0x0f) + THRESHOLD; - // - // I've modified this to only make one input call, and - // have changed the variable names to something more - // obvious. - - if (GetChars(c, 2) != 2) - break; - - // Convert these two characters into the position and - // length. Note that the length is always at least - // THRESHOLD, which is why we're able to get a length - // of 18 out of only 4 bits. - - pos = (short int) ( c[0] | ((c[1] & 0xf0) << 4) ); - - len = (short int) ( (c[1] & 0x0f) + THRESHOLD ); - - // There are now "len" characters at position "pos" in - // the ring buffer that can be pulled out. Note that - // len is never more than F. - - for (k = 0; k < len; k++) - { - c[k] = m_ring_buffer[(pos + k) & (N - 1)]; - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[k]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Add the "len" characters to the output stream. - - if (SendChars(c, len) != len) - break; - } - } - } - diff --git a/src/modules/common/entriesblk.cpp b/src/modules/common/entriesblk.cpp deleted file mode 100644 index f4fbdeb..0000000 --- a/src/modules/common/entriesblk.cpp +++ /dev/null @@ -1,169 +0,0 @@ -#include <entriesblk.h> -#include <stdlib.h> -#include <string.h> - -SWORD_NAMESPACE_START - -const int EntriesBlock::METAHEADERSIZE = 4; - // count(4); -const int EntriesBlock::METAENTRYSIZE = 8; - // offset(4); size(4); - -EntriesBlock::EntriesBlock(const char *iBlock, unsigned long size) { - block = (char *)calloc(1, size); - memcpy(block, iBlock, size); -} - - -EntriesBlock::EntriesBlock() { - block = (char *)calloc(1, sizeof(__u32)); -} - - -EntriesBlock::~EntriesBlock() { - free(block); -} - - -void EntriesBlock::setCount(int count) { - __u32 rawCount = archtosword32(count); - memcpy(block, &rawCount, sizeof(__u32)); -} - - -int EntriesBlock::getCount() { - __u32 count = 0; - memcpy(&count, block, sizeof(__u32)); - count = swordtoarch32(count); - return count; -} - - -void EntriesBlock::getMetaEntry(int index, unsigned long *offset, unsigned long *size) { - __u32 rawOffset = 0; - __u32 rawSize = 0; - *offset = 0; - *size = 0; - if (index >= getCount()) // assert index < count - return; - - // first 4 bytes is count, each 6 bytes after is each meta entry - memcpy(&rawOffset, block + METAHEADERSIZE + (index * METAENTRYSIZE), sizeof(rawOffset)); - memcpy(&rawSize, block + METAHEADERSIZE + (index * METAENTRYSIZE) + sizeof(rawOffset), sizeof(rawSize)); - - *offset = (unsigned long)swordtoarch32(rawOffset); - *size = (unsigned long)swordtoarch32(rawSize); -} - - -void EntriesBlock::setMetaEntry(int index, unsigned long offset, unsigned long size) { - __u32 rawOffset = archtosword32(offset); - __u32 rawSize = archtosword32(size); - - if (index >= getCount()) // assert index < count - return; - - // first 4 bytes is count, each 6 bytes after is each meta entry - memcpy(block + METAHEADERSIZE + (index * METAENTRYSIZE), &rawOffset, sizeof(rawOffset)); - memcpy(block + METAHEADERSIZE + (index * METAENTRYSIZE) + sizeof(rawOffset), &rawSize, sizeof(rawSize)); -} - - -const char *EntriesBlock::getRawData(unsigned long *retSize) { - unsigned long max = 4; - int loop; - unsigned long offset; - unsigned long size; - for (loop = 0; loop < getCount(); loop++) { - getMetaEntry(loop, &offset, &size); - max = ((offset + size) > max) ? (offset + size) : max; - } - *retSize = max; - return block; -} - - -int EntriesBlock::addEntry(const char *entry) { - unsigned long dataSize; - getRawData(&dataSize); - unsigned long len = strlen(entry); - unsigned long offset; - unsigned long size; - int count = getCount(); - unsigned long dataStart = METAHEADERSIZE + (count * METAENTRYSIZE); - // new meta entry + new data size + 1 because null - block = (char *)realloc(block, dataSize + METAENTRYSIZE + len + 1); - // shift right to make room for new meta entry - memmove(block + dataStart + METAENTRYSIZE, block + dataStart, dataSize - dataStart); - - for (int loop = 0; loop < count; loop++) { - getMetaEntry(loop, &offset, &size); - if (offset) { // if not a deleted entry - offset += METAENTRYSIZE; - setMetaEntry(loop, offset, size); - } - } - - offset = dataSize; // original dataSize before realloc - size = len + 1; - // add our text to the end - memcpy(block + offset + METAENTRYSIZE, entry, size); - // increment count - setCount(count + 1); - // add our meta entry - setMetaEntry(count, offset + METAENTRYSIZE, size); - // return index of our new entry - return count; -} - - -const char *EntriesBlock::getEntry(int entryIndex) { - unsigned long offset; - unsigned long size; - static char *empty = ""; - - getMetaEntry(entryIndex, &offset, &size); - return (offset) ? block+offset : empty; -} - - -unsigned long EntriesBlock::getEntrySize(int entryIndex) { - unsigned long offset; - unsigned long size; - - getMetaEntry(entryIndex, &offset, &size); - return (offset) ? size : 0; -} - - -void EntriesBlock::removeEntry(int entryIndex) { - unsigned long offset; - unsigned long size, size2; - unsigned long dataSize; - getRawData(&dataSize); - getMetaEntry(entryIndex, &offset, &size); - unsigned long len = size - 1; - int count = getCount(); - unsigned long dataStart = METAHEADERSIZE + (count * METAENTRYSIZE); - - if (!offset) // already deleted - return; - - // shift left to retrieve space used for old entry - memmove(block + offset, block + offset + size, dataSize - (offset + size)); - - // fix offset for all entries after our entry that were shifted left - for (int loop = entryIndex + 1; loop < count; loop++) { - getMetaEntry(loop, &offset, &size2); - if (offset) { // if not a deleted entry - offset -= size; - setMetaEntry(loop, offset, size2); - } - } - - // zero out our meta entry - setMetaEntry(entryIndex, 0L, 0); -} - - -SWORD_NAMESPACE_END diff --git a/src/modules/common/lzsscomprs.cpp b/src/modules/common/lzsscomprs.cpp deleted file mode 100644 index bd8f768..0000000 --- a/src/modules/common/lzsscomprs.cpp +++ /dev/null @@ -1,668 +0,0 @@ -/****************************************************************************** - * lzsscomprs.cpp - code for class 'LZSSCompress'- a driver class that - * provides LZSS compression - */ - -#include <stdlib.h> -#include <string.h> -#include <lzsscomprs.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * LZSSCompress Statics - */ - -// m_ring_buffer is a text buffer. It contains "nodes" of -// uncompressed text that can be indexed by position. That is, -// a substring of the ring buffer can be indexed by a position -// and a length. When decoding, the compressed text may contain -// a position in the ring buffer and a count of the number of -// bytes from the ring buffer that are to be moved into the -// uncompressed buffer. -// -// This ring buffer is not maintained as part of the compressed -// text. Instead, it is reconstructed dynamically. That is, -// it starts out empty and gets built as the text is decompressed. -// -// The ring buffer contain N bytes, with an additional F - 1 bytes -// to facilitate string comparison. - -unsigned char LZSSCompress::m_ring_buffer[N + F - 1]; - -// m_match_position and m_match_length are set by InsertNode(). -// -// These variables indicate the position in the ring buffer -// and the number of characters at that position that match -// a given string. - -short int LZSSCompress::m_match_position; -short int LZSSCompress::m_match_length; - -// m_lson, m_rson, and m_dad are the Japanese way of referring to -// a tree structure. The dad is the parent and it has a right and -// left son (child). -// -// For i = 0 to N-1, m_rson[i] and m_lson[i] will be the right -// and left children of node i. -// -// For i = 0 to N-1, m_dad[i] is the parent of node i. -// -// For i = 0 to 255, rson[N + i + 1] is the root of the tree for -// strings that begin with the character i. Note that this requires -// one byte characters. -// -// These nodes store values of 0...(N-1). Memory requirements -// can be reduces by using 2-byte integers instead of full 4-byte -// integers (for 32-bit applications). Therefore, these are -// defined as "short ints." - -short int LZSSCompress::m_lson[N + 1]; -short int LZSSCompress::m_rson[N + 257]; -short int LZSSCompress::m_dad[N + 1]; - - -/****************************************************************************** - * LZSSCompress Constructor - Initializes data for instance of LZSSCompress - * - */ - -LZSSCompress::LZSSCompress() : SWCompress() { -} - - -/****************************************************************************** - * LZSSCompress Destructor - Cleans up instance of LZSSCompress - */ - -LZSSCompress::~LZSSCompress() { -} - - -/****************************************************************************** - * LZSSCompress::InitTree - This function initializes the tree nodes to - * "empty" states. - */ - -void LZSSCompress::InitTree(void) { - int i; - - // For i = 0 to N - 1, m_rson[i] and m_lson[i] will be the right - // and left children of node i. These nodes need not be - // initialized. However, for debugging purposes, it is nice to - // have them initialized. Since this is only used for compression - // (not decompression), I don't mind spending the time to do it. - // - // For the same range of i, m_dad[i] is the parent of node i. - // These are initialized to a known value that can represent - // a "not used" state. - - for (i = 0; i < N; i++) { - m_lson[i] = NOT_USED; - m_rson[i] = NOT_USED; - m_dad[i] = NOT_USED; - } - - // For i = 0 to 255, m_rson[N + i + 1] is the root of the tree - // for strings that begin with the character i. This is why - // the right child array is larger than the left child array. - // These are also initialzied to a "not used" state. - // - // Note that there are 256 of these, one for each of the possible - // 256 characters. - - for (i = N + 1; i <= (N + 256); i++) { - m_rson[i] = NOT_USED; - } -} - - -/****************************************************************************** - * LZSSCompress::InsertNode - This function inserts a string from the ring - * buffer into one of the trees. It loads the - * match position and length member variables - * for the longest match. - * - * The string to be inserted is identified by - * the parameter Pos, A full F bytes are - * inserted. So, - * m_ring_buffer[Pos ... Pos+F-1] - * are inserted. - * - * If the matched length is exactly F, then an - * old node is removed in favor of the new one - * (because the old one will be deleted - * sooner). - * - * Note that Pos plays a dual role. It is - * used as both a position in the ring buffer - * and also as a tree node. - * m_ring_buffer[Pos] defines a character that - * is used to identify a tree node. - * - * ENT: pos - position in the buffer - */ - -void LZSSCompress::InsertNode(short int Pos) -{ - short int i; - short int p; - int cmp; - unsigned char * key; - -/* - ASSERT(Pos >= 0); - ASSERT(Pos < N); -*/ - - cmp = 1; - key = &(m_ring_buffer[Pos]); - - // The last 256 entries in m_rson contain the root nodes for - // strings that begin with a letter. Get an index for the - // first letter in this string. - - p = (short int) (N + 1 + key[0]); - - // Set the left and right tree nodes for this position to "not - // used." - - m_lson[Pos] = NOT_USED; - m_rson[Pos] = NOT_USED; - - // Haven't matched anything yet. - - m_match_length = 0; - - for ( ; ; ) { - if (cmp >= 0) { - if (m_rson[p] != NOT_USED) { - p = m_rson[p]; - } - else { - m_rson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - else { - if (m_lson[p] != NOT_USED) { - p = m_lson[p]; - } - else { - m_lson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - - // Should we go to the right or the left to look for the - // next match? - - for (i = 1; i < F; i++) { - cmp = key[i] - m_ring_buffer[p + i]; - if (cmp != 0) - break; - } - - if (i > m_match_length) { - m_match_position = p; - m_match_length = i; - - if (i >= F) - break; - } - } - - m_dad[Pos] = m_dad[p]; - m_lson[Pos] = m_lson[p]; - m_rson[Pos] = m_rson[p]; - - m_dad[ m_lson[p] ] = Pos; - m_dad[ m_rson[p] ] = Pos; - - if (m_rson[ m_dad[p] ] == p) { - m_rson[ m_dad[p] ] = Pos; - } - else { - m_lson[ m_dad[p] ] = Pos; - } - - // Remove "p" - - m_dad[p] = NOT_USED; -} - - -/****************************************************************************** - * LZSSCompress::DeleteNode - This function removes the node "Node" from the - * tree. - * - * ENT: node - node to be removed - */ - -void LZSSCompress::DeleteNode(short int Node) -{ - short int q; - -/* - ASSERT(Node >= 0); - ASSERT(Node < (N+1)); -*/ - - if (m_dad[Node] == NOT_USED) { // not in tree, nothing to do - return; - } - - if (m_rson[Node] == NOT_USED) { - q = m_lson[Node]; - } - else if (m_lson[Node] == NOT_USED) { - q = m_rson[Node]; - } - else { - q = m_lson[Node]; - if (m_rson[q] != NOT_USED) { - do { - q = m_rson[q]; - } while (m_rson[q] != NOT_USED); - - m_rson[ m_dad[q] ] = m_lson[q]; - m_dad[ m_lson[q] ] = m_dad[q]; - m_lson[q] = m_lson[Node]; - m_dad[ m_lson[Node] ] = q; - } - - m_rson[q] = m_rson[Node]; - m_dad[ m_rson[Node] ] = q; - } - - m_dad[q] = m_dad[Node]; - - if (m_rson[ m_dad[Node] ] == Node) { - m_rson[ m_dad[Node] ] = q; - } - else { - m_lson[ m_dad[Node] ] = q; - } - - m_dad[Node] = NOT_USED; -} - - -/****************************************************************************** - * LZSSCompress::Encode - This function "encodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - * NOTE: must set zlen for parent class to know length of - * compressed buffer. - */ - -void LZSSCompress::Encode(void) -{ - short int i; // an iterator - short int r; // node number in the binary tree - short int s; // position in the ring buffer - unsigned short int len; // len of initial string - short int last_match_length; // length of last match - short int code_buf_pos; // position in the output buffer - unsigned char code_buf[17]; // the output buffer - unsigned char mask; // bit mask for byte 0 of out buf - unsigned char c; // character read from string - - // Start with a clean tree. - - InitTree(); - direct = 0; // set direction needed by parent [Get|Send]Chars() - - // code_buf[0] works as eight flags. A "1" represents that the - // unit is an unencoded letter (1 byte), and a "0" represents - // that the next unit is a <position,length> pair (2 bytes). - // - // code_buf[1..16] stores eight units of code. Since the best - // we can do is store eight <position,length> pairs, at most 16 - // bytes are needed to store this. - // - // This is why the maximum size of the code buffer is 17 bytes. - - code_buf[0] = 0; - code_buf_pos = 1; - - // Mask iterates over the 8 bits in the code buffer. The first - // character ends up being stored in the low bit. - // - // bit 8 7 6 5 4 3 2 1 - // | | - // | first sequence in code buffer - // | - // last sequence in code buffer - - mask = 1; - - s = 0; - r = (short int) N - (short int) F; - - // Initialize the ring buffer with spaces... - - // Note that the last F bytes of the ring buffer are not filled. - // This is because those F bytes will be filled in immediately - // with bytes from the input stream. - - memset(m_ring_buffer, ' ', N - F); - - // Read F bytes into the last F bytes of the ring buffer. - // - // This function loads the buffer with X characters and returns - // the actual amount loaded. - - len = GetChars((char *) &(m_ring_buffer[r]), F); - - // Make sure there is something to be compressed. - - if (len == 0) - return; - - // Insert the F strings, each of which begins with one or more - // 'space' characters. Note the order in which these strings - // are inserted. This way, degenerate trees will be less likely - // to occur. - - for (i = 1; i <= F; i++) { - InsertNode((short int) (r - i)); - } - - // Finally, insert the whole string just read. The - // member variables match_length and match_position are set. - - InsertNode(r); - - // Now that we're preloaded, continue till done. - - do { - - // m_match_length may be spuriously long near the end of - // text. - - if (m_match_length > len) { - m_match_length = len; - } - - // Is it cheaper to store this as a single character? If so, - // make it so. - - if (m_match_length < THRESHOLD) { - // Send one character. Remember that code_buf[0] is the - // set of flags for the next eight items. - - m_match_length = 1; - code_buf[0] |= mask; - code_buf[code_buf_pos++] = m_ring_buffer[r]; - } - - // Otherwise, we do indeed have a string that can be stored - // compressed to save space. - - else { - // The next 16 bits need to contain the position (12 bits) - // and the length (4 bits). - - code_buf[code_buf_pos++] = (unsigned char) m_match_position; - code_buf[code_buf_pos++] = (unsigned char) ( - ((m_match_position >> 4) & 0xf0) | - (m_match_length - THRESHOLD) ); - } - - // Shift the mask one bit to the left so that it will be ready - // to store the new bit. - - mask = (unsigned char) (mask << 1); - - // If the mask is now 0, then we know that we have a full set - // of flags and items in the code buffer. These need to be - // output. - - if (!mask) { - // code_buf is the buffer of characters to be output. - // code_buf_pos is the number of characters it contains. - - SendChars((char *) code_buf, code_buf_pos); - - // Reset for next buffer... - - code_buf[0] = 0; - code_buf_pos = 1; - mask = 1; - } - - last_match_length = m_match_length; - - // Delete old strings and read new bytes... - - for (i = 0; i < last_match_length; i++) { - // Get next character... - - if (GetChars((char *) &c, 1) != 1) - break; - - // Delete "old strings" - - DeleteNode(s); - - // Put this character into the ring buffer. - // - // The original comment here says "If the position is near - // the end of the buffer, extend the buffer to make - // string comparison easier." - // - // That's a little misleading, because the "end" of the - // buffer is really what we consider to be the "beginning" - // of the buffer, that is, positions 0 through F. - // - // The idea is that the front end of the buffer is duplicated - // into the back end so that when you're looking at characters - // at the back end of the buffer, you can index ahead (beyond - // the normal end of the buffer) and see the characters - // that are at the front end of the buffer wihtout having - // to adjust the index. - // - // That is... - // - // 1234xxxxxxxxxxxxxxxxxxxxxxxxxxxxx1234 - // | | | - // position 0 end of buffer | - // | - // duplicate of front of buffer - - m_ring_buffer[s] = c; - - if (s < F - 1) { - m_ring_buffer[s + N] = c; - } - - // Increment the position, and wrap around when we're at - // the end. Note that this relies on N being a power of 2. - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Register the string that is found in - // m_ring_buffer[r..r+F-1]. - - InsertNode(r); - } - - // If we didn't quit because we hit the last_match_length, - // then we must have quit because we ran out of characters - // to process. - - while (i++ < last_match_length) { - DeleteNode(s); - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Note that len hitting 0 is the key that causes the - // do...while() to terminate. This is the only place - // within the loop that len is modified. - // - // Its original value is F (or a number less than F for - // short strings). - - if (--len) { - InsertNode(r); /* buffer may not be empty. */ - } - } - - // End of do...while() loop. Continue processing until there - // are no more characters to be compressed. The variable - // "len" is used to signal this condition. - } while (len > 0); - - // There could still be something in the output buffer. Send it - // now. - - if (code_buf_pos > 1) { - // code_buf is the encoded string to send. - // code_buf_ptr is the number of characters. - - SendChars((char *) code_buf, code_buf_pos); - } - - - // must set zlen for parent class to know length of compressed buffer - zlen = zpos; -} - - -/****************************************************************************** - * LZSSCompress::Decode - This function "decodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void LZSSCompress::Decode(void) -{ - int k; - int r; // node number - unsigned char c[F]; // an array of chars - unsigned char flags; // 8 bits of flags - int flag_count; // which flag we're on - short int pos; // position in the ring buffer - short int len; // number of chars in ring buffer - unsigned long totalLen = 0; - - direct = 1; // set direction needed by parent [Get|Send]Chars() - - // Initialize the ring buffer with a common string. - // - // Note that the last F bytes of the ring buffer are not filled. - - memset(m_ring_buffer, ' ', N - F); - - r = N - F; - - flags = (char) 0; - flag_count = 0; - - for ( ; ; ) { - - // If there are more bits of interest in this flag, then - // shift that next interesting bit into the 1's position. - // - // If this flag has been exhausted, the next byte must - // be a flag. - - if (flag_count > 0) { - flags = (unsigned char) (flags >> 1); - flag_count--; - } - else { - // Next byte must be a flag. - - if (GetChars((char *) &flags, 1) != 1) - break; - - // Set the flag counter. While at first it might appear - // that this should be an 8 since there are 8 bits in the - // flag, it should really be a 7 because the shift must - // be performed 7 times in order to see all 8 bits. - - flag_count = 7; - } - - // If the low order bit of the flag is now set, then we know - // that the next byte is a single, unencoded character. - - if (flags & 1) { - if (GetChars((char *) c, 1) != 1) - break; - - if (SendChars((char *) c, 1) != 1) { - totalLen++; - break; - } - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[0]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Otherwise, we know that the next two bytes are a - // <position,length> pair. The position is in 12 bits and - // the length is in 4 bits. - - else { - // Original code: - // if ((i = getc(infile)) == EOF) - // break; - // if ((j = getc(infile)) == EOF) - // break; - // i |= ((j & 0xf0) << 4); - // j = (j & 0x0f) + THRESHOLD; - // - // I've modified this to only make one input call, and - // have changed the variable names to something more - // obvious. - - if (GetChars((char *) c, 2) != 2) - break; - - // Convert these two characters into the position and - // length. Note that the length is always at least - // THRESHOLD, which is why we're able to get a length - // of 18 out of only 4 bits. - - pos = (short int) ( c[0] | ((c[1] & 0xf0) << 4) ); - - len = (short int) ( (c[1] & 0x0f) + THRESHOLD ); - - // There are now "len" characters at position "pos" in - // the ring buffer that can be pulled out. Note that - // len is never more than F. - - for (k = 0; k < len; k++) { - c[k] = m_ring_buffer[(pos + k) & (N - 1)]; - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[k]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Add the "len" :characters to the output stream. - - if (SendChars((char *) c, len) != (unsigned int)len) { - totalLen += len; - break; - } - } - } - slen = totalLen; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/rawstr.cpp b/src/modules/common/rawstr.cpp deleted file mode 100644 index 5c4ef0e..0000000 --- a/src/modules/common/rawstr.cpp +++ /dev/null @@ -1,555 +0,0 @@ -/****************************************************************************** - * rawstr.cpp - code for class 'RawStr'- a module that reads raw text - * files: ot and nt using indexs ??.bks ??.cps ??.vss - * and provides lookup and parsing functions based on - * class StrKey - */ - - -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> - -#ifndef __GNUC__ -#include <io.h> -#else -#include <unistd.h> -#endif - -#include <stdlib.h> -#include <utilfuns.h> -#include <rawstr.h> -#include <sysdata.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * RawStr Statics - */ - -int RawStr::instance = 0; -char RawStr::nl = '\n'; - - -/****************************************************************************** - * RawStr Constructor - Initializes data for instance of RawStr - * - * ENT: ipath - path of the directory where data and index files are located. - * be sure to include the trailing separator (e.g. '/' or '\') - * (e.g. 'modules/texts/rawtext/webster/') - */ - -RawStr::RawStr(const char *ipath, int fileMode) -{ - char buf[127]; - - lastoff = -1; - path = 0; - stdstr(&path, ipath); - -#ifndef O_BINARY // O_BINARY is needed in Borland C++ 4.53 -#define O_BINARY 0 // If it hasn't been defined than we probably -#endif // don't need it. - - if (fileMode == -1) { // try read/write if possible - fileMode = O_RDWR; - } - - sprintf(buf, "%s.idx", path); - idxfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s.dat", path); - datfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - if (datfd < 0) { - sprintf(buf, "Error: %d", errno); - perror(buf); - } - - instance++; -} - - -/****************************************************************************** - * RawStr Destructor - Cleans up instance of RawStr - */ - -RawStr::~RawStr() -{ - if (path) - delete [] path; - - --instance; - - FileMgr::systemFileMgr.close(idxfd); - FileMgr::systemFileMgr.close(datfd); -} - - -/****************************************************************************** - * RawStr::getidxbufdat - Gets the index string at the given idx offset - * NOTE: buf is allocated and must be freed by - * calling function - * - * ENT: ioffset - offset in dat file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void RawStr::getIDXBufDat(long ioffset, char **buf) -{ - int size; - char ch; - if (datfd > 0) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - for (size = 0; read(datfd->getFd(), &ch, 1) == 1; size++) { - if ((ch == '\\') || (ch == 10) || (ch == 13)) - break; - } - *buf = (*buf) ? (char *)realloc(*buf, size*2 + 1) : (char *)malloc(size*2 + 1); - if (size) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - read(datfd->getFd(), *buf, size); - } - (*buf)[size] = 0; - toupperstr_utf8(*buf, size*2); - } - else { - *buf = (*buf) ? (char *)realloc(*buf, 1) : (char *)malloc(1); - **buf = 0; - } -} - - -/****************************************************************************** - * RawStr::getidxbuf - Gets the index string at the given idx offset - * NOTE: buf is allocated and must be freed by - * calling function - * - * ENT: ioffset - offset in idx file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void RawStr::getIDXBuf(long ioffset, char **buf) -{ - char *trybuf, *targetbuf; - long offset; - - if (idxfd > 0) { - lseek(idxfd->getFd(), ioffset, SEEK_SET); - read(idxfd->getFd(), &offset, 4); - - offset = swordtoarch32(offset); - - getIDXBufDat(offset, buf); - } -} - - -/****************************************************************************** - * RawStr::findoffset - Finds the offset of the key string from the indexes - * - * ENT: key - key string to lookup - * start - address to store the starting offset - * size - address to store the size of the entry - * away - number of entries before of after to jump - * (default = 0) - * - * RET: error status -1 general error; -2 new file - */ - -signed char RawStr::findOffset(const char *ikey, long *start, unsigned short *size, long away, long *idxoff) -{ - char *trybuf, *targetbuf, *key = 0, quitflag = 0; - signed char retval = -1; - long headoff, tailoff, tryoff = 0, maxoff = 0; - - if (idxfd->getFd() >=0) { - tailoff = maxoff = lseek(idxfd->getFd(), 0, SEEK_END) - 6; - retval = (tailoff >= 0) ? 0 : -2; // if NOT new file - if (*ikey) { - headoff = 0; - - stdstr(&key, ikey, 3); - toupperstr_utf8(key, strlen(key)*3); - - trybuf = 0; - - while (headoff < tailoff) { - tryoff = (lastoff == -1) ? headoff + ((((tailoff / 6) - (headoff / 6))) / 2) * 6 : lastoff; - lastoff = -1; - getIDXBuf(tryoff, &trybuf); - - if (!*trybuf && tryoff) { // In case of extra entry at end of idx (not first entry) - tryoff += (tryoff > (maxoff / 2))?-6:6; - retval = -1; - break; - } - - if (!strcmp(key, trybuf)) - break; - - int diff = strcmp(key, trybuf); - if (diff < 0) - tailoff = (tryoff == headoff) ? headoff : tryoff; - else headoff = tryoff; - if (tailoff == headoff + 6) { - if (quitflag++) - headoff = tailoff; - } - } - if (headoff >= tailoff) - tryoff = headoff; - if (trybuf) - free(trybuf); - delete [] key; - } - else tryoff = 0; - - lseek(idxfd->getFd(), tryoff, SEEK_SET); - - *start = *size = 0; - read(idxfd->getFd(), start, 4); - read(idxfd->getFd(), size, 2); - if (idxoff) - *idxoff = tryoff; - - *start = swordtoarch32(*start); - *size = swordtoarch16(*size); - - while (away) { - long laststart = *start; - unsigned short lastsize = *size; - long lasttry = tryoff; - tryoff += (away > 0) ? 6 : -6; - - bool bad = false; - if (((tryoff + (away*6)) < -6) || (tryoff + (away*6) > (maxoff+6))) - bad = true; - else if (lseek(idxfd->getFd(), tryoff, SEEK_SET) < 0) - bad = true; - if (bad) { - retval = -1; - *start = laststart; - *size = lastsize; - tryoff = lasttry; - if (idxoff) - *idxoff = tryoff; - break; - } - read(idxfd->getFd(), start, 4); - read(idxfd->getFd(), size, 2); - if (idxoff) - *idxoff = tryoff; - - *start = swordtoarch32(*start); - *size = swordtoarch16(*size); - - if (((laststart != *start) || (lastsize != *size)) && (*start >= 0) && (*size)) - away += (away < 0) ? 1 : -1; - } - - lastoff = tryoff; - } - else { - *start = 0; - *size = 0; - if (idxoff) - *idxoff = 0; - retval = -1; - } - return retval; -} - - -/****************************************************************************** - * RawStr::preptext - Prepares the text before returning it to external - * objects - * - * ENT: buf - buffer where text is stored and where to store the prep'd - * text. - */ - -void RawStr::prepText(SWBuf &buf) { - unsigned int to, from; - char space = 0, cr = 0, realdata = 0, nlcnt = 0; - char *rawBuf = buf.getRawData(); - for (to = from = 0; rawBuf[from]; from++) { - switch (rawBuf[from]) { - case 10: - if (!realdata) - continue; - space = (cr) ? 0 : 1; - cr = 0; - nlcnt++; - if (nlcnt > 1) { -// *to++ = nl; - rawBuf[to++] = 10; -// *to++ = nl[1]; -// nlcnt = 0; - } - continue; - case 13: - if (!realdata) - continue; -// *to++ = nl[0]; - rawBuf[to++] = 10; - space = 0; - cr = 1; - continue; - } - realdata = 1; - nlcnt = 0; - if (space) { - space = 0; - if (rawBuf[from] != ' ') { - rawBuf[to++] = ' '; - from--; - continue; - } - } - rawBuf[to++] = rawBuf[from]; - } - buf.setSize(to); - - while (to > 1) { // remove trailing excess - to--; - if ((rawBuf[to] == 10) || (rawBuf[to] == ' ')) - buf.setSize(to); - else break; - } -} - - -/****************************************************************************** - * RawStr::readtext - gets text at a given offset - * - * ENT: - * start - starting offset where the text is located in the file - * size - size of text entry - * buf - buffer to store text - * - */ - -void RawStr::readText(long istart, unsigned short *isize, char **idxbuf, SWBuf &buf) -{ - unsigned int ch; - char *idxbuflocal = 0; - getIDXBufDat(istart, &idxbuflocal); - long start = istart; - - do { - if (*idxbuf) - delete [] *idxbuf; - buf = ""; - buf.setFillByte(0); - buf.setSize(++(*isize)); - - *idxbuf = new char [ (*isize) ]; - - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), buf.getRawData(), (int)((*isize) - 1)); - - for (ch = 0; buf[ch]; ch++) { // skip over index string - if (buf[ch] == 10) { - ch++; - break; - } - } - buf = SWBuf(buf.c_str()+ch); - // resolve link - if (!strncmp(buf.c_str(), "@LINK", 5)) { - for (ch = 0; buf[ch]; ch++) { // null before nl - if (buf[ch] == 10) { - buf[ch] = 0; - break; - } - } - findOffset(buf.c_str() + 6, &start, isize); - } - else break; - } - while (true); // while we're resolving links - - if (idxbuflocal) { - int localsize = strlen(idxbuflocal); - localsize = (localsize < (*isize - 1)) ? localsize : (*isize - 1); - strncpy(*idxbuf, idxbuflocal, localsize); - (*idxbuf)[localsize] = 0; - free(idxbuflocal); - } -} - - -/****************************************************************************** - * RawLD::settext - Sets text for current offset - * - * ENT: key - key for this entry - * buf - buffer to store - * len - length of buffer (0 - null terminated) - */ - -void RawStr::doSetText(const char *ikey, const char *buf, long len) -{ - - long start, outstart; - long idxoff; - long endoff; - long shiftSize; - unsigned short size; - unsigned short outsize; - static const char nl[] = {13, 10}; - char *tmpbuf = 0; - char *key = 0; - char *dbKey = 0; - char *idxBytes = 0; - char *outbuf = 0; - char *ch = 0; - - char errorStatus = findOffset(ikey, &start, &size, 0, &idxoff); - stdstr(&key, ikey, 2); - toupperstr_utf8(key, strlen(key)*2); - - len = (len < 0) ? strlen(buf) : len; - - getIDXBufDat(start, &dbKey); - - if (strcmp(key, dbKey) < 0) { - } - else if (strcmp(key, dbKey) > 0) { - if (errorStatus != -2) // not a new file - idxoff += 6; - else idxoff = 0; - } - else if ((!strcmp(key, dbKey)) && (len>0 /*we're not deleting*/)) { // got absolute entry - do { - tmpbuf = new char [ size + 2 ]; - memset(tmpbuf, 0, size + 2); - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), tmpbuf, (int)(size - 1)); - - for (ch = tmpbuf; *ch; ch++) { // skip over index string - if (*ch == 10) { - ch++; - break; - } - } - memmove(tmpbuf, ch, size - (unsigned short)(ch-tmpbuf)); - - // resolve link - if (!strncmp(tmpbuf, "@LINK", 5) && (len)) { - for (ch = tmpbuf; *ch; ch++) { // null before nl - if (*ch == 10) { - *ch = 0; - break; - } - } - findOffset(tmpbuf + 6, &start, &size, 0, &idxoff); - } - else break; - } - while (true); // while we're resolving links - } - - endoff = lseek(idxfd->getFd(), 0, SEEK_END); - - shiftSize = endoff - idxoff; - - if (shiftSize > 0) { - idxBytes = new char [ shiftSize ]; - lseek(idxfd->getFd(), idxoff, SEEK_SET); - read(idxfd->getFd(), idxBytes, shiftSize); - } - - outbuf = new char [ len + strlen(key) + 5 ]; - sprintf(outbuf, "%s%c%c", key, 13, 10); - size = strlen(outbuf); - memcpy(outbuf + size, buf, len); - size = outsize = size + (len); - - start = outstart = lseek(datfd->getFd(), 0, SEEK_END); - - outstart = archtosword32(start); - outsize = archtosword16(size); - - lseek(idxfd->getFd(), idxoff, SEEK_SET); - if (len > 0) { - lseek(datfd->getFd(), start, SEEK_SET); - write(datfd->getFd(), outbuf, (int)size); - - // add a new line to make data file easier to read in an editor - write(datfd->getFd(), &nl, 2); - - write(idxfd->getFd(), &outstart, 4); - write(idxfd->getFd(), &outsize, 2); - if (idxBytes) { - write(idxfd->getFd(), idxBytes, shiftSize); - delete [] idxBytes; - } - } - else { // delete entry - if (idxBytes) { - write(idxfd->getFd(), idxBytes+6, shiftSize-6); - lseek(idxfd->getFd(), -1, SEEK_CUR); // last valid byte - FileMgr::systemFileMgr.trunc(idxfd); // truncate index - delete [] idxBytes; - } - } - - delete [] key; - delete [] outbuf; - free(dbKey); -} - - -/****************************************************************************** - * RawLD::linkentry - links one entry to another - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * destidxoff - dest offset into .vss - * srcidxoff - source offset into .vss - */ - -void RawStr::doLinkEntry(const char *destkey, const char *srckey) { - char *text = new char [ strlen(destkey) + 7 ]; - sprintf(text, "@LINK %s", destkey); - doSetText(srckey, text); - delete [] text; -} - - -/****************************************************************************** - * RawLD::CreateModule - Creates new module files - * - * ENT: path - directory to store module files - * RET: error status - */ - -signed char RawStr::createModule(const char *ipath) -{ - char *path = 0; - char *buf = new char [ strlen (ipath) + 20 ]; - FileDesc *fd, *fd2; - - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - sprintf(buf, "%s.dat", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s.idx", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd2); - - delete [] path; - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/rawstr4.cpp b/src/modules/common/rawstr4.cpp deleted file mode 100644 index e278675..0000000 --- a/src/modules/common/rawstr4.cpp +++ /dev/null @@ -1,561 +0,0 @@ -/****************************************************************************** - * rawstr.cpp - code for class 'RawStr'- a module that reads raw text - * files: ot and nt using indexs ??.bks ??.cps ??.vss - * and provides lookup and parsing functions based on - * class StrKey - */ - -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> - -#ifndef __GNUC__ -#include <io.h> -#else -#include <unistd.h> -#endif - -#include <stdlib.h> -#include <utilfuns.h> -#include <rawstr4.h> -#include <sysdata.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * RawStr Statics - */ - -int RawStr4::instance = 0; - - -/****************************************************************************** - * RawStr Constructor - Initializes data for instance of RawStr - * - * ENT: ipath - path of the directory where data and index files are located. - * be sure to include the trailing separator (e.g. '/' or '\') - * (e.g. 'modules/texts/rawtext/webster/') - */ - -RawStr4::RawStr4(const char *ipath, int fileMode) -{ - char buf[127]; - - nl = '\n'; - lastoff = -1; - path = 0; - stdstr(&path, ipath); - -#ifndef O_BINARY // O_BINARY is needed in Borland C++ 4.53 -#define O_BINARY 0 // If it hasn't been defined than we probably -#endif // don't need it. - - if (fileMode == -1) { // try read/write if possible - fileMode = O_RDWR; - } - - sprintf(buf, "%s.idx", path); - idxfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s.dat", path); - datfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - if (datfd < 0) { - sprintf(buf, "Error: %d", errno); - perror(buf); - } - - instance++; -} - - -/****************************************************************************** - * RawStr Destructor - Cleans up instance of RawStr - */ - -RawStr4::~RawStr4() -{ - if (path) - delete [] path; - - --instance; - - FileMgr::systemFileMgr.close(idxfd); - FileMgr::systemFileMgr.close(datfd); -} - - -/****************************************************************************** - * RawStr4::getidxbufdat - Gets the index string at the given idx offset - * NOTE: buf is allocated and must be freed by - * calling function - * - * ENT: ioffset - offset in dat file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void RawStr4::getIDXBufDat(long ioffset, char **buf) { - int size; - char ch; - if (datfd > 0) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - for (size = 0; read(datfd->getFd(), &ch, 1) == 1; size++) { - if ((ch == '\\') || (ch == 10) || (ch == 13)) - break; - } - *buf = (*buf) ? (char *)realloc(*buf, size*2 + 1) : (char *)malloc(size*2 + 1); - if (size) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - read(datfd->getFd(), *buf, size); - } - (*buf)[size] = 0; - toupperstr_utf8(*buf, size*2); - } - else { - *buf = (*buf) ? (char *)realloc(*buf, 1) : (char *)malloc(1); - **buf = 0; - } -} - - -/****************************************************************************** - * RawStr4::getidxbuf - Gets the index string at the given idx offset - * NOTE: buf is allocated and must be freed by - * calling function - * - * ENT: ioffset - offset in idx file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void RawStr4::getIDXBuf(long ioffset, char **buf) -{ - char *trybuf, *targetbuf; - long offset; - - if (idxfd > 0) { - lseek(idxfd->getFd(), ioffset, SEEK_SET); - read(idxfd->getFd(), &offset, 4); - - offset = swordtoarch32(offset); - - getIDXBufDat(offset, buf); - -/* What the heck is this supposed to do?????? - for (trybuf = targetbuf = *buf; *trybuf; trybuf++, targetbuf++) { - *targetbuf = *trybuf; - } - *targetbuf = 0; - trybuf = 0; - toupperstr_utf8(targetbuf); -*/ - } -} - - -/****************************************************************************** - * RawStr4::findoffset - Finds the offset of the key string from the indexes - * - * ENT: key - key string to lookup - * start - address to store the starting offset - * size - address to store the size of the entry - * away - number of entries before of after to jump - * (default = 0) - * - * RET: error status -1 general error; -2 new file - */ - -signed char RawStr4::findOffset(const char *ikey, long *start, unsigned long *size, long away, long *idxoff) -{ - char *trybuf, *targetbuf, *key = 0, quitflag = 0; - signed char retval = -1; - long headoff, tailoff, tryoff = 0, maxoff = 0; - - if (idxfd->getFd() >=0) { - tailoff = maxoff = lseek(idxfd->getFd(), 0, SEEK_END) - 8; - retval = (tailoff >= 0) ? 0 : -2; // if NOT new file - if (*ikey) { - headoff = 0; - - stdstr(&key, ikey, 3); - toupperstr_utf8(key, strlen(key)*3); - - trybuf = 0; - - while (headoff < tailoff) { - tryoff = (lastoff == -1) ? headoff + ((((tailoff / 8) - (headoff / 8))) / 2) * 8 : lastoff; - lastoff = -1; - getIDXBuf(tryoff, &trybuf); - - if (!*trybuf) { // In case of extra entry at end of idx - tryoff += (tryoff > (maxoff / 2))?-8:8; - retval = -1; - break; - } - - if (!strcmp(key, trybuf)) - break; - - int diff = strcmp(key, trybuf); - if (diff < 0) - tailoff = (tryoff == headoff) ? headoff : tryoff; - else headoff = tryoff; - if (tailoff == headoff + 8) { - if (quitflag++) - headoff = tailoff; - } - } - if (headoff >= tailoff) - tryoff = headoff; - if (trybuf) - free(trybuf); - delete [] key; - } - else tryoff = 0; - - lseek(idxfd->getFd(), tryoff, SEEK_SET); - - *start = *size = 0; - read(idxfd->getFd(), start, 4); - read(idxfd->getFd(), size, 4); - if (idxoff) - *idxoff = tryoff; - - *start = swordtoarch32(*start); - *size = swordtoarch32(*size); - - while (away) { - long laststart = *start; - unsigned long lastsize = *size; - long lasttry = tryoff; - tryoff += (away > 0) ? 8 : -8; - - bool bad = false; - if (((tryoff + (away*8)) < -8) || (tryoff + (away*8) > (maxoff+8))) - bad = true; - else if (lseek(idxfd->getFd(), tryoff, SEEK_SET) < 0) - bad = true; - if (bad) { - retval = -1; - *start = laststart; - *size = lastsize; - tryoff = lasttry; - if (idxoff) - *idxoff = tryoff; - break; - } - read(idxfd->getFd(), start, 4); - read(idxfd->getFd(), size, 4); - if (idxoff) - *idxoff = tryoff; - - *start = swordtoarch32(*start); - *size = swordtoarch32(*size); - - if (((laststart != *start) || (lastsize != *size)) && (*start >= 0) && (*size)) - away += (away < 0) ? 1 : -1; - } - - lastoff = tryoff; - } - else { - *start = 0; - *size = 0; - if (idxoff) - *idxoff = 0; - retval = -1; - } - return retval; -} - - -/****************************************************************************** - * RawStr4::preptext - Prepares the text before returning it to external - * objects - * - * ENT: buf - buffer where text is stored and where to store the prep'd - * text. - */ - -void RawStr4::prepText(SWBuf &buf) { - unsigned int to, from; - char space = 0, cr = 0, realdata = 0, nlcnt = 0; - char *rawBuf = buf.getRawData(); - for (to = from = 0; rawBuf[from]; from++) { - switch (rawBuf[from]) { - case 10: - if (!realdata) - continue; - space = (cr) ? 0 : 1; - cr = 0; - nlcnt++; - if (nlcnt > 1) { -// *to++ = nl; - rawBuf[to++] = 10; -// *to++ = nl[1]; -// nlcnt = 0; - } - continue; - case 13: - if (!realdata) - continue; -// *to++ = nl[0]; - rawBuf[to++] = 10; - space = 0; - cr = 1; - continue; - } - realdata = 1; - nlcnt = 0; - if (space) { - space = 0; - if (rawBuf[from] != ' ') { - rawBuf[to++] = ' '; - from--; - continue; - } - } - rawBuf[to++] = rawBuf[from]; - } - buf.setSize(to); - - while (to > 1) { // remove trailing excess - to--; - if ((rawBuf[to] == 10) || (rawBuf[to] == ' ')) - buf.setSize(to); - else break; - } -} - - -/****************************************************************************** - * RawStr4::readtext - gets text at a given offset - * - * ENT: - * start - starting offset where the text is located in the file - * size - size of text entry - * buf - buffer to store text - * - */ - -void RawStr4::readText(long istart, unsigned long *isize, char **idxbuf, SWBuf &buf) -{ - unsigned int ch; - char *idxbuflocal = 0; - getIDXBufDat(istart, &idxbuflocal); - long start = istart; - - do { - if (*idxbuf) - delete [] *idxbuf; - *idxbuf = new char [ (*isize) ]; - - buf = ""; - buf.setFillByte(0); - buf.setSize(*isize); - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), buf.getRawData(), (int)((*isize) - 1)); - - for (ch = 0; buf[ch]; ch++) { // skip over index string - if (buf[ch] == 10) { - ch++; - break; - } - } - buf = SWBuf(buf.c_str()+ch); - // resolve link - if (!strncmp(buf.c_str(), "@LINK", 5)) { - for (ch = 0; buf[ch]; ch++) { // null before nl - if (buf[ch] == 10) { - buf[ch] = 0; - break; - } - } - findOffset(buf.c_str() + 6, &start, isize); - - } - else break; - } - while (true); // while we're resolving links - - if (idxbuflocal) { - int localsize = strlen(idxbuflocal); - localsize = (localsize < (*isize - 1)) ? localsize : (*isize - 1); - strncpy(*idxbuf, idxbuflocal, localsize); - (*idxbuf)[localsize] = 0; - free(idxbuflocal); - } -} - - -/****************************************************************************** - * RawLD::settext - Sets text for current offset - * - * ENT: key - key for this entry - * buf - buffer to store - * len - length of buffer (0 - null terminated) - */ - -void RawStr4::doSetText(const char *ikey, const char *buf, long len) { - - long start, outstart; - long idxoff; - long endoff; - long shiftSize; - unsigned long size; - unsigned long outsize; - static const char nl[] = {13, 10}; - char *tmpbuf = 0; - char *key = 0; - char *dbKey = 0; - char *idxBytes = 0; - char *outbuf = 0; - char *ch = 0; - - char errorStatus = findOffset(ikey, &start, &size, 0, &idxoff); - stdstr(&key, ikey, 3); - toupperstr_utf8(key, strlen(key)*3); - - len = (len < 0) ? strlen(buf) : len; - getIDXBufDat(start, &dbKey); - - if (strcmp(key, dbKey) < 0) { - } - else if (strcmp(key, dbKey) > 0) { - if (errorStatus != -2) // not a new file - idxoff += 8; - else idxoff = 0; - } - else if ((!strcmp(key, dbKey)) && (len>0/*we're not deleting*/)) { // got absolute entry - do { - tmpbuf = new char [ size + 2 ]; - memset(tmpbuf, 0, size + 2); - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), tmpbuf, (int)(size - 1)); - - for (ch = tmpbuf; *ch; ch++) { // skip over index string - if (*ch == 10) { - ch++; - break; - } - } - memmove(tmpbuf, ch, size - (unsigned long)(ch-tmpbuf)); - - // resolve link - if (!strncmp(tmpbuf, "@LINK", 5) && (len > 0)) { - for (ch = tmpbuf; *ch; ch++) { // null before nl - if (*ch == 10) { - *ch = 0; - break; - } - } - findOffset(tmpbuf + 8, &start, &size, 0, &idxoff); - ++size; - } - else break; - } - while (true); // while we're resolving links - } - - endoff = lseek(idxfd->getFd(), 0, SEEK_END); - - shiftSize = endoff - idxoff; - - if (shiftSize > 0) { - idxBytes = new char [ shiftSize ]; - lseek(idxfd->getFd(), idxoff, SEEK_SET); - read(idxfd->getFd(), idxBytes, shiftSize); - } - - outbuf = new char [ len + strlen(key) + 5 ]; - sprintf(outbuf, "%s%c%c", key, 13, 10); - size = strlen(outbuf); - memcpy(outbuf + size, buf, len); - size = outsize = size + len; - - start = outstart = lseek(datfd->getFd(), 0, SEEK_END); - - outstart = archtosword32(start); - outsize = archtosword32(size); - - lseek(idxfd->getFd(), idxoff, SEEK_SET); - if (len>0) { - lseek(datfd->getFd(), start, SEEK_SET); - write(datfd->getFd(), outbuf, (long)size); - - // add a new line to make data file easier to read in an editor - write(datfd->getFd(), &nl, 2); - - write(idxfd->getFd(), &outstart, 4); - write(idxfd->getFd(), &outsize, 4); - if (idxBytes) { - write(idxfd->getFd(), idxBytes, shiftSize); - delete [] idxBytes; - } - } - else { // delete entry - if (idxBytes) { - write(idxfd->getFd(), idxBytes+8, shiftSize-8); - lseek(idxfd->getFd(), -1, SEEK_CUR); // last valid byte - FileMgr::systemFileMgr.trunc(idxfd); // truncate index - delete [] idxBytes; - } - } - - delete [] key; - delete [] outbuf; - free(dbKey); -} - - -/****************************************************************************** - * RawLD::linkentry - links one entry to another - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * destidxoff - dest offset into .vss - * srcidxoff - source offset into .vss - */ - -void RawStr4::doLinkEntry(const char *destkey, const char *srckey) { - char *text = new char [ strlen(destkey) + 7 ]; - sprintf(text, "@LINK %s", destkey); - doSetText(srckey, text); - delete [] text; -} - - -/****************************************************************************** - * RawLD::CreateModule - Creates new module files - * - * ENT: path - directory to store module files - * RET: error status - */ - -signed char RawStr4::createModule(const char *ipath) -{ - char *path = 0; - char *buf = new char [ strlen (ipath) + 20 ]; - FileDesc *fd, *fd2; - - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - sprintf(buf, "%s.dat", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s.idx", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd2); - - delete [] path; - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/rawverse.cpp b/src/modules/common/rawverse.cpp deleted file mode 100644 index b5bff9f..0000000 --- a/src/modules/common/rawverse.cpp +++ /dev/null @@ -1,353 +0,0 @@ -/****************************************************************************** - * rawverse.cpp - code for class 'RawVerse'- a module that reads raw text - * files: ot and nt using indexs ??.bks ??.cps ??.vss - * and provides lookup and parsing functions based on - * class VerseKey - */ - - -#include <ctype.h> -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> - -#ifndef __GNUC__ -#include <io.h> -#include <sys/stat.h> -#else -#include <unistd.h> -#endif - -#include <utilfuns.h> -#include <rawverse.h> -#include <versekey.h> -#include <sysdata.h> - -#ifndef O_BINARY // O_BINARY is needed in Borland C++ 4.53 -#define O_BINARY 0 // If it hasn't been defined than we probably -#endif // don't need it. - -SWORD_NAMESPACE_START - -/****************************************************************************** - * RawVerse Statics - */ - -int RawVerse::instance = 0; -const char *RawVerse::nl = "\r\n"; - - -/****************************************************************************** - * RawVerse Constructor - Initializes data for instance of RawVerse - * - * ENT: ipath - path of the directory where data and index files are located. - * be sure to include the trailing separator (e.g. '/' or '\') - * (e.g. 'modules/texts/rawtext/webster/') - */ - -RawVerse::RawVerse(const char *ipath, int fileMode) -{ - char *buf; - - path = 0; - stdstr(&path, ipath); - buf = new char [ strlen(path) + 80 ]; - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - if (fileMode == -1) { // try read/write if possible - fileMode = O_RDWR; - } - - sprintf(buf, "%s/ot.vss", path); - idxfp[0] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/nt.vss", path); - idxfp[1] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/ot", path); - textfp[0] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/nt", path); - textfp[1] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - delete [] buf; - instance++; -} - - -/****************************************************************************** - * RawVerse Destructor - Cleans up instance of RawVerse - */ - -RawVerse::~RawVerse() -{ - int loop1; - - if (path) - delete [] path; - - --instance; - - for (loop1 = 0; loop1 < 2; loop1++) { - FileMgr::systemFileMgr.close(idxfp[loop1]); - FileMgr::systemFileMgr.close(textfp[loop1]); - } -} - - -/****************************************************************************** - * RawVerse::findoffset - Finds the offset of the key verse from the indexes - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * idxoff - offset into .vss - * start - address to store the starting offset - * size - address to store the size of the entry - */ - -void RawVerse::findOffset(char testmt, long idxoff, long *start, unsigned short *size) { - idxoff *= 6; - if (!testmt) - testmt = ((idxfp[1]) ? 1:2); - - if (idxfp[testmt-1]->getFd() >= 0) { - lseek(idxfp[testmt-1]->getFd(), idxoff, SEEK_SET); - read(idxfp[testmt-1]->getFd(), start, 4); - long len = read(idxfp[testmt-1]->getFd(), size, 2); // read size - - *start = swordtoarch32(*start); - *size = swordtoarch16(*size); - - if (len < 2) { - *size = (unsigned short)((*start) ? (lseek(textfp[testmt-1]->getFd(), 0, SEEK_END) - (long)*start) : 0); // if for some reason we get an error reading size, make size to end of file - } - } - else { - *start = 0; - *size = 0; - } -} - - -/****************************************************************************** - * RawVerse::preptext - Prepares the text before returning it to external - * objects - * - * ENT: buf - buffer where text is stored and where to store the prep'd - * text. - */ - -void RawVerse::prepText(SWBuf &buf) { - unsigned int to, from; - char space = 0, cr = 0, realdata = 0, nlcnt = 0; - char *rawBuf = buf.getRawData(); - for (to = from = 0; rawBuf[from]; from++) { - switch (rawBuf[from]) { - case 10: - if (!realdata) - continue; - space = (cr) ? 0 : 1; - cr = 0; - nlcnt++; - if (nlcnt > 1) { -// *to++ = nl; - rawBuf[to++] = 10; -// *to++ = nl[1]; -// nlcnt = 0; - } - continue; - case 13: - if (!realdata) - continue; -// *to++ = nl[0]; - rawBuf[to++] = 10; - space = 0; - cr = 1; - continue; - } - realdata = 1; - nlcnt = 0; - if (space) { - space = 0; - if (rawBuf[from] != ' ') { - rawBuf[to++] = ' '; - from--; - continue; - } - } - rawBuf[to++] = rawBuf[from]; - } - buf.setSize(to); - - while (to > 1) { // remove trailing excess - to--; - if ((rawBuf[to] == 10) || (rawBuf[to] == ' ')) - buf.setSize(to); - else break; - } -} - - -/****************************************************************************** - * RawVerse::readtext - gets text at a given offset - * - * ENT: testmt - testament file to search in (0 - Old; 1 - New) - * start - starting offset where the text is located in the file - * size - size of text entry + 2 (null)(null) - * buf - buffer to store text - * - */ - -void RawVerse::readText(char testmt, long start, unsigned short size, SWBuf &buf) { - buf = ""; - buf.setFillByte(0); - buf.setSize(size + 1); - if (!testmt) - testmt = ((idxfp[1]) ? 1:2); - if (size) { - if (textfp[testmt-1]->getFd() >= 0) { - lseek(textfp[testmt-1]->getFd(), start, SEEK_SET); - read(textfp[testmt-1]->getFd(), buf.getRawData(), (int)size); - } - } -} - - -/****************************************************************************** - * RawVerse::settext - Sets text for current offset - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * idxoff - offset into .vss - * buf - buffer to store - * len - length of buffer (0 - null terminated) - */ - -void RawVerse::doSetText(char testmt, long idxoff, const char *buf, long len) -{ - long start, outstart; - unsigned short size; - unsigned short outsize; - - idxoff *= 6; - if (!testmt) - testmt = ((idxfp[1]) ? 1:2); - - size = outsize = (len < 0) ? strlen(buf) : len; - - start = outstart = lseek(textfp[testmt-1]->getFd(), 0, SEEK_END); - lseek(idxfp[testmt-1]->getFd(), idxoff, SEEK_SET); - - if (size) { - lseek(textfp[testmt-1]->getFd(), start, SEEK_SET); - write(textfp[testmt-1]->getFd(), buf, (int)size); - - // add a new line to make data file easier to read in an editor - write(textfp[testmt-1]->getFd(), nl, 2); - } - else { - start = 0; - } - - outstart = archtosword32(start); - outsize = archtosword16(size); - - write(idxfp[testmt-1]->getFd(), &outstart, 4); - write(idxfp[testmt-1]->getFd(), &outsize, 2); - - -} - - -/****************************************************************************** - * RawVerse::linkentry - links one entry to another - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * destidxoff - dest offset into .vss - * srcidxoff - source offset into .vss - */ - -void RawVerse::doLinkEntry(char testmt, long destidxoff, long srcidxoff) { - long start; - unsigned short size; - - destidxoff *= 6; - srcidxoff *= 6; - - if (!testmt) - testmt = ((idxfp[1]) ? 1:2); - - // get source - lseek(idxfp[testmt-1]->getFd(), srcidxoff, SEEK_SET); - read(idxfp[testmt-1]->getFd(), &start, 4); - read(idxfp[testmt-1]->getFd(), &size, 2); - - // write dest - lseek(idxfp[testmt-1]->getFd(), destidxoff, SEEK_SET); - write(idxfp[testmt-1]->getFd(), &start, 4); - write(idxfp[testmt-1]->getFd(), &size, 2); -} - - -/****************************************************************************** - * RawVerse::CreateModule - Creates new module files - * - * ENT: path - directory to store module files - * RET: error status - */ - -char RawVerse::createModule(const char *ipath) -{ - char *path = 0; - char *buf = new char [ strlen (ipath) + 20 ]; - FileDesc *fd, *fd2; - - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - sprintf(buf, "%s/ot", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/nt", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/ot.vss", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - - sprintf(buf, "%s/nt.vss", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - - VerseKey vk; - vk.Headings(1); - long offset = 0; - short size = 0; - for (vk = TOP; !vk.Error(); vk++) { - write((vk.Testament() == 1) ? fd->getFd() : fd2->getFd(), &offset, 4); - write((vk.Testament() == 1) ? fd->getFd() : fd2->getFd(), &size, 2); - } - - FileMgr::systemFileMgr.close(fd); - FileMgr::systemFileMgr.close(fd2); - - delete [] path; - delete [] buf; -/* - RawVerse rv(path); - VerseKey mykey("Rev 22:21"); -*/ - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/sapphire.cpp b/src/modules/common/sapphire.cpp deleted file mode 100644 index 1c97934..0000000 --- a/src/modules/common/sapphire.cpp +++ /dev/null @@ -1,231 +0,0 @@ -/* sapphire.cpp -- the Saphire II stream cipher class. - Dedicated to the Public Domain the author and inventor: - (Michael Paul Johnson). This code comes with no warranty. - Use it at your own risk. - Ported from the Pascal implementation of the Sapphire Stream - Cipher 9 December 1994. - Added hash pre- and post-processing 27 December 1994. - Modified initialization to make index variables key dependent, - made the output function more resistant to cryptanalysis, - and renamed to Sapphire II 2 January 1995 -*/ - - -#ifdef WIN32 -#include <memory.h> -#endif - -#ifdef UNIX -#include <memory.h> -#include <unistd.h> -#else -#ifndef _MSC_VER -#include <mem.h> -#endif -#endif - -#ifdef _WIN32_WCE -#include <string.h> -#endif - -#include "sapphire.h" - -SWORD_NAMESPACE_START - -unsigned char sapphire::keyrand(int limit, - unsigned char *user_key, - unsigned char keysize, - unsigned char *rsum, - unsigned *keypos) - { - unsigned u, // Value from 0 to limit to return. - retry_limiter, // No infinite loops allowed. - mask; // Select just enough bits. - - if (!limit) return 0; // Avoid divide by zero error. - retry_limiter = 0; - mask = 1; // Fill mask with enough bits to cover - while (mask < (unsigned)limit) // the desired range. - mask = (mask << 1) + 1; - do - { - *rsum = cards[*rsum] + user_key[(*keypos)++]; - if (*keypos >= keysize) - { - *keypos = 0; // Recycle the user key. - *rsum += keysize; // key "aaaa" != key "aaaaaaaa" - } - u = mask & *rsum; - if (++retry_limiter > 11) - u %= limit; // Prevent very rare long loops. - } - while (u > (unsigned)limit); - return u; - } - -void sapphire::initialize(unsigned char *key, unsigned char keysize) - { - // Key size may be up to 256 bytes. - // Pass phrases may be used directly, with longer length - // compensating for the low entropy expected in such keys. - // Alternatively, shorter keys hashed from a pass phrase or - // generated randomly may be used. For random keys, lengths - // of from 4 to 16 bytes are recommended, depending on how - // secure you want this to be. - - int i; - unsigned char toswap, swaptemp, rsum; - unsigned keypos; - - // If we have been given no key, assume the default hash setup. - - if (keysize < 1) - { - hash_init(); - return; - } - - // Start with cards all in order, one of each. - - for (i=0;i<256;i++) - cards[i] = i; - - // Swap the card at each position with some other card. - - toswap = 0; - keypos = 0; // Start with first byte of user key. - rsum = 0; - for (i=255;i>=0;i--) - { - toswap = keyrand(i, key, keysize, &rsum, &keypos); - swaptemp = cards[i]; - cards[i] = cards[toswap]; - cards[toswap] = swaptemp; - } - - // Initialize the indices and data dependencies. - // Indices are set to different values instead of all 0 - // to reduce what is known about the state of the cards - // when the first byte is emitted. - - rotor = cards[1]; - ratchet = cards[3]; - avalanche = cards[5]; - last_plain = cards[7]; - last_cipher = cards[rsum]; - - toswap = swaptemp = rsum = 0; - keypos = 0; - } - -void sapphire::hash_init(void) - { - // This function is used to initialize non-keyed hash - // computation. - - int i, j; - - // Initialize the indices and data dependencies. - - rotor = 1; - ratchet = 3; - avalanche = 5; - last_plain = 7; - last_cipher = 11; - - // Start with cards all in inverse order. - - for (i=0, j=255;i<256;i++,j--) - cards[i] = (unsigned char) j; - } - -sapphire::sapphire(unsigned char *key, unsigned char keysize) - { - if (key && keysize) - initialize(key, keysize); - } - -void sapphire::burn(void) - { - // Destroy the key and state information in RAM. - memset(cards, 0, 256); - rotor = ratchet = avalanche = last_plain = last_cipher = 0; - } - -sapphire::~sapphire() - { - burn(); - } - -unsigned char sapphire::encrypt(unsigned char b) - { -#ifdef USBINARY - // Picture a single enigma rotor with 256 positions, rewired - // on the fly by card-shuffling. - - // This cipher is a variant of one invented and written - // by Michael Paul Johnson in November, 1993. - - unsigned char swaptemp; - - // Shuffle the deck a little more. - - ratchet += cards[rotor++]; - swaptemp = cards[last_cipher]; - cards[last_cipher] = cards[ratchet]; - cards[ratchet] = cards[last_plain]; - cards[last_plain] = cards[rotor]; - cards[rotor] = swaptemp; - avalanche += cards[swaptemp]; - - // Output one byte from the state in such a way as to make it - // very hard to figure out which one you are looking at. - - last_cipher = b^cards[(cards[ratchet] + cards[rotor]) & 0xFF] ^ - cards[cards[(cards[last_plain] + - cards[last_cipher] + - cards[avalanche])&0xFF]]; - last_plain = b; - return last_cipher; -#else - return b; -#endif - } - -unsigned char sapphire::decrypt(unsigned char b) - { - unsigned char swaptemp; - - // Shuffle the deck a little more. - - ratchet += cards[rotor++]; - swaptemp = cards[last_cipher]; - cards[last_cipher] = cards[ratchet]; - cards[ratchet] = cards[last_plain]; - cards[last_plain] = cards[rotor]; - cards[rotor] = swaptemp; - avalanche += cards[swaptemp]; - - // Output one byte from the state in such a way as to make it - // very hard to figure out which one you are looking at. - - last_plain = b^cards[(cards[ratchet] + cards[rotor]) & 0xFF] ^ - cards[cards[(cards[last_plain] + - cards[last_cipher] + - cards[avalanche])&0xFF]]; - last_cipher = b; - return last_plain; - } - -void sapphire::hash_final(unsigned char *hash, // Destination - unsigned char hashlength) // Size of hash. - { - int i; - - for (i=255;i>=0;i--) - encrypt((unsigned char) i); - for (i=0;i<hashlength;i++) - hash[i] = encrypt(0); - } - -SWORD_NAMESPACE_END diff --git a/src/modules/common/swcipher.cpp b/src/modules/common/swcipher.cpp deleted file mode 100644 index bd4d551..0000000 --- a/src/modules/common/swcipher.cpp +++ /dev/null @@ -1,128 +0,0 @@ -/****************************************************************************** - * swcipher.cpp - code for class 'SWCipher'- a driver class that provides - * cipher utilities. - */ - -#include <stdlib.h> -#include <string.h> -#include <swcipher.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * SWCipher Constructor - Initializes data for instance of SWCipher - * - */ - -SWCipher::SWCipher(unsigned char *key) { - master.initialize(key, strlen((char *)key)); - buf = 0; -} - - -/****************************************************************************** - * SWCipher Destructor - Cleans up instance of SWCipher - */ - -SWCipher::~SWCipher() -{ - if (buf) - free(buf); -} - - -char *SWCipher::Buf(const char *ibuf, unsigned long ilen) -{ - if (ibuf) { - - if (buf) - free(buf); - - if (!ilen) { - len = strlen(buf); - ilen = len + 1; - } - else len = ilen; - - buf = (char *) malloc(ilen); - memcpy(buf, ibuf, ilen); - cipher = false; - } - - Decode(); - - return buf; -} - - -char *SWCipher::cipherBuf(unsigned long *ilen, const char *ibuf) -{ - if (ibuf) { - - if (buf) - free(buf); - - buf = (char *) malloc(*ilen+1); - memcpy(buf, ibuf, *ilen); - len = *ilen; - cipher = true; - } - - Encode(); - - *ilen = len; - return buf; -} - - -/****************************************************************************** - * SWCipher::Encode - This function "encodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void SWCipher::Encode(void) -{ - if (!cipher) { - work = master; - for (unsigned long i = 0; i < len; i++) - buf[i] = work.encrypt(buf[i]); - cipher = true; - } -} - - -/****************************************************************************** - * SWCipher::Decode - This function "decodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void SWCipher::Decode(void) -{ - if (cipher) { - work = master; - unsigned long i; - for (i = 0; i < len; i++) - buf[i] = work.decrypt(buf[i]); - buf[i] = 0; - cipher = false; - } -} - - -/****************************************************************************** - * SWCipher::setCipherKey - setter for a new CipherKey - * - */ - -void SWCipher::setCipherKey(const char *ikey) { - unsigned char *key = (unsigned char *)ikey; - master.initialize(key, strlen((char *)key)); -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/swcomprs.cpp b/src/modules/common/swcomprs.cpp deleted file mode 100644 index 02d7d7b..0000000 --- a/src/modules/common/swcomprs.cpp +++ /dev/null @@ -1,193 +0,0 @@ -/****************************************************************************** - * swcomprs.cpp - code for class 'SWCompress'- a driver class that provides - * compression utilities. - */ - -#include <stdlib.h> -#include <string.h> -#include <swcomprs.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * SWCompress Constructor - Initializes data for instance of SWCompress - * - */ - -SWCompress::SWCompress() -{ - buf = zbuf = 0; - Init(); -} - - -/****************************************************************************** - * SWCompress Destructor - Cleans up instance of SWCompress - */ - -SWCompress::~SWCompress() -{ - if (zbuf) - free(zbuf); - - if (buf) - free(buf); -} - - -void SWCompress::Init() -{ - if (buf) - free(buf); - - if (zbuf) - free(zbuf); - - buf = 0; - zbuf = 0; - direct = 0; - zlen = 0; - slen = 0; - zpos = 0; - pos = 0; -} - - -char *SWCompress::Buf(const char *ibuf, unsigned long *len) { - // setting an uncompressed buffer - if (ibuf) { - Init(); - slen = (len) ? *len : strlen(ibuf); - buf = (char *) calloc(slen + 1, 1); - memcpy(buf, ibuf, slen); - } - - // getting an uncompressed buffer - if (!buf) { - buf = (char *)calloc(1,1); // be sure we at least allocate an empty buf for return; - direct = 1; - Decode(); -// slen = strlen(buf); - if (len) - *len = slen; - } - return buf; -} - - -char *SWCompress::zBuf(unsigned long *len, char *ibuf) -{ - // setting a compressed buffer - if (ibuf) { - Init(); - zbuf = (char *) malloc(*len); - memcpy(zbuf, ibuf, *len); - zlen = *len; - } - - // getting a compressed buffer - if (!zbuf) { - direct = 0; - Encode(); - } - - *len = zlen; - return zbuf; -} - - -unsigned long SWCompress::GetChars(char *ibuf, unsigned long len) -{ - if (direct) { - len = (((zlen - zpos) > (unsigned)len) ? len : zlen - zpos); - if (len > 0) { - memmove(ibuf, &zbuf[zpos], len); - zpos += len; - } - } - else { -// slen = strlen(buf); - len = (((slen - pos) > (unsigned)len) ? len : slen - pos); - if (len > 0) { - memmove(ibuf, &buf[pos], len); - pos += len; - } - } - return len; -} - - -unsigned long SWCompress::SendChars(char *ibuf, unsigned long len) -{ - if (direct) { - if (buf) { -// slen = strlen(buf); - if ((pos + len) > (unsigned)slen) { - buf = (char *) realloc(buf, pos + len + 1024); - memset(&buf[pos], 0, len + 1024); - } - } - else buf = (char *)calloc(1, len + 1024); - memmove(&buf[pos], ibuf, len); - pos += len; - } - else { - if (zbuf) { - if ((zpos + len) > zlen) { - zbuf = (char *) realloc(zbuf, zpos + len + 1024); - zlen = zpos + len + 1024; - } - } - else { - zbuf = (char *)calloc(1, len + 1024); - zlen = len + 1024; - } - memmove(&zbuf[zpos], ibuf, len); - zpos += len; - } - return len; -} - - -/****************************************************************************** - * SWCompress::Encode - This function "encodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void SWCompress::Encode(void) -{ - cycleStream(); -} - - -/****************************************************************************** - * SWCompress::Decode - This function "decodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void SWCompress::Decode(void) -{ - cycleStream(); -} - - -void SWCompress::cycleStream() { - char buf[1024]; - unsigned long len, totlen = 0; - - do { - len = GetChars(buf, 1024); - if (len) - totlen += SendChars(buf, len); - } while (len == 1024); - - zlen = slen = totlen; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/swcomprs.doc b/src/modules/common/swcomprs.doc deleted file mode 100644 index b6817f2..0000000 --- a/src/modules/common/swcomprs.doc +++ /dev/null @@ -1,802 +0,0 @@ -The following is the original information send from Parson's Technologies via -Craig Rairden. -_______________________________________________________________________________ -Compression Info, 10-11-95 -Jeff Wheeler - -Source of Algorithm -------------------- - -The compression algorithms used here are based upon the algorithms developed -and published by Haruhiko Okumura in a paper entitled "Data Compression -Algorithms of LARC and LHarc." This paper discusses three compression -algorithms, LSZZ, LZARI, and LZHUF. LZSS is described as the "first" of -these, and is described as providing moderate compression with good speed. -LZARI is described as an improved LZSS, a combination of the LZSS algorithm -with adaptive arithmetic compression. It is described as being slower than -LZSS but with better compression. LZHUF (the basis of the common LHA -compression program) was included in the paper, however, a free usage license -was not included. - -The following are copies of the statements included at the beginning of each -source code listing that was supplied in the working paper. - - LZSS, dated 4/6/89, marked as "Use, distribute and - modify this program freely." - - LZARI, dated 4/7/89, marked as "Use, distribute and - modify this program freely." - - LZHUF, dated 11/20/88, written by Haruyasu Yoshizaki, - translated by Haruhiko Okumura on 4/7/89. Not - expressly marked as redistributable or modifiable. - -Since both LZSS and LZARI are marked as "use, distribute and modify freely" we -have felt at liberty basing our compression algorithm on either of these. - -Selection of Algorithm ----------------------- - -Working samples of three possible compression algorithms are supplied in -Okumura's paper. Which should be used? - -LZSS is the fastest at decompression, but does not generated as small a -compressed file as the other methods. The other two methods provided, perhaps, -a 15% improvement in compression. Or, put another way, on a 100K file, LZSS -might compress it to 50K while the others might approach 40-45K. For STEP -purposes, it was decided that decoding speed was of more importance than -tighter compression. For these reasons, the first compression algorithm -implemented is the LZSS algorithm. - -About LZSS Encoding -------------------- - -(adapted from Haruhiko Okumura's paper) - -This scheme was proposed by Ziv and Lempel [1]. A slightly modified version -is described by Storer and Szymanski [2]. An implementation using a binary -tree has been proposed by Bell [3]. - -The algorithm is quite simple. -1. Keep a ring buffer which initially contains all space characters. -2. Read several letters from the file to the buffer. -3. Search the buffer for the longest string that matches the letters just - read, and send its length and position into the buffer. - -If the ring buffer is 4096 bytes, the position can be stored in 12 bits. If the -length is represented in 4 bits, the <position, length> pair is two bytes -long. If the longest match is no more than two characters, then just one -character is sent without encoding. The process starts again with the next -character. An extra bit is sent each time to tell the decoder whether the -next item is a character of a <position, length> pair. - -[1] J. Ziv and A. Lempel, IEEE Transactions IT-23, 337-343 (1977). -[2] J. A. Storer and T. G. Szymanski, J. ACM, 29, 928-951 (1982). -[3] T.C. Gell, IEEE Transactions COM-34, 1176-1182 (1986). - -class SWCompress { -public: -void InitTree( // no return value - void); // no parameters - -void InsertNode( // no return value - short int Pos); // position in the buffer - -void DeleteNode( // no return value - short int Node); // node to be removed - -void Encode( // no return value - void); // no parameters - -void Decode( // no return value - void); // no parameters -}; - -// The following are constant sizes used by the compression algorithm. -// -// N - This is the size of the ring buffer. It is set -// to 4K. It is important to note that a position -// within the ring buffer requires 12 bits. -// -// F - This is the maximum length of a character sequence -// that can be taken from the ring buffer. It is set -// to 18. Note that a length must be 3 before it is -// worthwhile to store a position/length pair, so the -// length can be encoded in only 4 bits. Or, put yet -// another way, it is not necessary to encode a length -// of 0-18, it is necessary to encode a length of -// 3-18, which requires 4 bits. -// -// THRESHOLD - It takes 2 bytes to store an offset and -// a length. If a character sequence only -// requires 1 or 2 characters to store -// uncompressed, then it is better to store -// it uncompressed than as an offset into -// the ring buffer. -// -// Note that the 12 bits used to store the position and the 4 bits -// used to store the length equal a total of 16 bits, or 2 bytes. - -#define N 4096 -#define F 18 -#define THRESHOLD 3 -#define NOT_USED N - -// m_ring_buffer is a text buffer. It contains "nodes" of -// uncompressed text that can be indexed by position. That is, -// a substring of the ring buffer can be indexed by a position -// and a length. When decoding, the compressed text may contain -// a position in the ring buffer and a count of the number of -// bytes from the ring buffer that are to be moved into the -// uncompressed buffer. -// -// This ring buffer is not maintained as part of the compressed -// text. Instead, it is reconstructed dynamically. That is, -// it starts out empty and gets built as the text is decompressed. -// -// The ring buffer contain N bytes, with an additional F - 1 bytes -// to facilitate string comparison. - -unsigned char m_ring_buffer[N + F - 1]; - -// m_match_position and m_match_length are set by InsertNode(). -// -// These variables indicate the position in the ring buffer -// and the number of characters at that position that match -// a given string. - -short int m_match_position; -short int m_match_length; - -// m_lson, m_rson, and m_dad are the Japanese way of referring to -// a tree structure. The dad is the parent and it has a right and -// left son (child). -// -// For i = 0 to N-1, m_rson[i] and m_lson[i] will be the right -// and left children of node i. -// -// For i = 0 to N-1, m_dad[i] is the parent of node i. -// -// For i = 0 to 255, rson[N + i + 1] is the root of the tree for -// strings that begin with the character i. Note that this requires -// one byte characters. -// -// These nodes store values of 0...(N-1). Memory requirements -// can be reduces by using 2-byte integers instead of full 4-byte -// integers (for 32-bit applications). Therefore, these are -// defined as "short ints." - -short int m_lson[N + 1]; -short int m_rson[N + 257]; -short int m_dad[N + 1]; - - - - -/* - ------------------------------------------------------------------------- - cLZSS::InitTree - - This function initializes the tree nodes to "empty" states. - ------------------------------------------------------------------------- -*/ - -void cLZSS::InitTree( // no return value - void) // no parameters - throw() // exception list - - { - int i; - - // For i = 0 to N - 1, m_rson[i] and m_lson[i] will be the right - // and left children of node i. These nodes need not be - // initialized. However, for debugging purposes, it is nice to - // have them initialized. Since this is only used for compression - // (not decompression), I don't mind spending the time to do it. - // - // For the same range of i, m_dad[i] is the parent of node i. - // These are initialized to a known value that can represent - // a "not used" state. - - for (i = 0; i < N; i++) - { - m_lson[i] = NOT_USED; - m_rson[i] = NOT_USED; - m_dad[i] = NOT_USED; - } - - // For i = 0 to 255, m_rson[N + i + 1] is the root of the tree - // for strings that begin with the character i. This is why - // the right child array is larger than the left child array. - // These are also initialzied to a "not used" state. - // - // Note that there are 256 of these, one for each of the possible - // 256 characters. - - for (i = N + 1; i <= (N + 256); i++) - { - m_rson[i] = NOT_USED; - } - - // Done. - } - -/* - ------------------------------------------------------------------------- - cLZSS::InsertNode - - This function inserts a string from the ring buffer into one of - the trees. It loads the match position and length member variables - for the longest match. - - The string to be inserted is identified by the parameter Pos, - A full F bytes are inserted. So, m_ring_buffer[Pos ... Pos+F-1] - are inserted. - - If the matched length is exactly F, then an old node is removed - in favor of the new one (because the old one will be deleted - sooner). - - Note that Pos plays a dual role. It is used as both a position - in the ring buffer and also as a tree node. m_ring_buffer[Pos] - defines a character that is used to identify a tree node. - ------------------------------------------------------------------------- -*/ - -void cLZSS::InsertNode( // no return value - short int Pos) // position in the buffer - throw() // exception list - - { - short int i; - short int p; - int cmp; - unsigned char * key; - - ASSERT(Pos >= 0); - ASSERT(Pos < N); - - cmp = 1; - key = &(m_ring_buffer[Pos]); - - // The last 256 entries in m_rson contain the root nodes for - // strings that begin with a letter. Get an index for the - // first letter in this string. - - p = (short int) (N + 1 + key[0]); - - // Set the left and right tree nodes for this position to "not - // used." - - m_lson[Pos] = NOT_USED; - m_rson[Pos] = NOT_USED; - - // Haven't matched anything yet. - - m_match_length = 0; - - for ( ; ; ) - { - if (cmp >= 0) - { - if (m_rson[p] != NOT_USED) - { - p = m_rson[p]; - } - else - { - m_rson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - else - { - if (m_lson[p] != NOT_USED) - { - p = m_lson[p]; - } - else - { - m_lson[p] = Pos; - m_dad[Pos] = p; - return; - } - } - - // Should we go to the right or the left to look for the - // next match? - - for (i = 1; i < F; i++) - { - cmp = key[i] - m_ring_buffer[p + i]; - if (cmp != 0) - break; - } - - if (i > m_match_length) - { - m_match_position = p; - m_match_length = i; - - if (i >= F) - break; - } - } - - m_dad[Pos] = m_dad[p]; - m_lson[Pos] = m_lson[p]; - m_rson[Pos] = m_rson[p]; - - m_dad[ m_lson[p] ] = Pos; - m_dad[ m_rson[p] ] = Pos; - - if (m_rson[ m_dad[p] ] == p) - { - m_rson[ m_dad[p] ] = Pos; - } - else - { - m_lson[ m_dad[p] ] = Pos; - } - - // Remove "p" - - m_dad[p] = NOT_USED; - } - -/* - ------------------------------------------------------------------------- - cLZSS::DeleteNode - - This function removes the node "Node" from the tree. - ------------------------------------------------------------------------- -*/ - -void cLZSS::DeleteNode( // no return value - short int Node) // node to be removed - throw() // exception list - - { - short int q; - - ASSERT(Node >= 0); - ASSERT(Node < (N+1)); - - if (m_dad[Node] == NOT_USED) - { - // not in tree, nothing to do - return; - } - - if (m_rson[Node] == NOT_USED) - { - q = m_lson[Node]; - } - else if (m_lson[Node] == NOT_USED) - { - q = m_rson[Node]; - } - else - { - q = m_lson[Node]; - if (m_rson[q] != NOT_USED) - { - do - { - q = m_rson[q]; - } - while (m_rson[q] != NOT_USED); - - m_rson[ m_dad[q] ] = m_lson[q]; - m_dad[ m_lson[q] ] = m_dad[q]; - m_lson[q] = m_lson[Node]; - m_dad[ m_lson[Node] ] = q; - } - - m_rson[q] = m_rson[Node]; - m_dad[ m_rson[Node] ] = q; - } - - m_dad[q] = m_dad[Node]; - - if (m_rson[ m_dad[Node] ] == Node) - { - m_rson[ m_dad[Node] ] = q; - } - else - { - m_lson[ m_dad[Node] ] = q; - } - - m_dad[Node] = NOT_USED; - } - -/* - ------------------------------------------------------------------------- - cLZSS::Encode - - This function "encodes" the input stream into the output stream. - The GetChars() and SendChars() functions are used to separate - this method from the actual i/o. - ------------------------------------------------------------------------- -*/ - -void cLZSS::Encode( // no return value - void) // no parameters - - { - short int i; // an iterator - short int r; // node number in the binary tree - short int s; // position in the ring buffer - unsigned short int len; // len of initial string - short int last_match_length; // length of last match - short int code_buf_pos; // position in the output buffer - unsigned char code_buf[17]; // the output buffer - unsigned char mask; // bit mask for byte 0 of out buf - unsigned char c; // character read from string - - // Start with a clean tree. - - InitTree(); - - // code_buf[0] works as eight flags. A "1" represents that the - // unit is an unencoded letter (1 byte), and a "0" represents - // that the next unit is a <position,length> pair (2 bytes). - // - // code_buf[1..16] stores eight units of code. Since the best - // we can do is store eight <position,length> pairs, at most 16 - // bytes are needed to store this. - // - // This is why the maximum size of the code buffer is 17 bytes. - - code_buf[0] = 0; - code_buf_pos = 1; - - // Mask iterates over the 8 bits in the code buffer. The first - // character ends up being stored in the low bit. - // - // bit 8 7 6 5 4 3 2 1 - // | | - // | first sequence in code buffer - // | - // last sequence in code buffer - - mask = 1; - - s = 0; - r = (short int) N - (short int) F; - - // Initialize the ring buffer with spaces... - - // Note that the last F bytes of the ring buffer are not filled. - // This is because those F bytes will be filled in immediately - // with bytes from the input stream. - - memset(m_ring_buffer, ' ', N - F); - - // Read F bytes into the last F bytes of the ring buffer. - // - // This function loads the buffer with X characters and returns - // the actual amount loaded. - - len = GetChars(&(m_ring_buffer[r]), F); - - // Make sure there is something to be compressed. - - if (len == 0) - return; - - // Insert the F strings, each of which begins with one or more - // 'space' characters. Note the order in which these strings - // are inserted. This way, degenerate trees will be less likely - // to occur. - - for (i = 1; i <= F; i++) - { - InsertNode((short int) (r - i)); - } - - // Finally, insert the whole string just read. The - // member variables match_length and match_position are set. - - InsertNode(r); - - // Now that we're preloaded, continue till done. - - do - { - - // m_match_length may be spuriously long near the end of - // text. - - if (m_match_length > len) - { - m_match_length = len; - } - - // Is it cheaper to store this as a single character? If so, - // make it so. - - if (m_match_length < THRESHOLD) - { - // Send one character. Remember that code_buf[0] is the - // set of flags for the next eight items. - - m_match_length = 1; - code_buf[0] |= mask; - code_buf[code_buf_pos++] = m_ring_buffer[r]; - } - - // Otherwise, we do indeed have a string that can be stored - // compressed to save space. - - else - { - // The next 16 bits need to contain the position (12 bits) - // and the length (4 bits). - - code_buf[code_buf_pos++] = (unsigned char) m_match_position; - code_buf[code_buf_pos++] = (unsigned char) ( - ((m_match_position >> 4) & 0xf0) | - (m_match_length - THRESHOLD) ); - } - - // Shift the mask one bit to the left so that it will be ready - // to store the new bit. - - mask = (unsigned char) (mask << 1); - - // If the mask is now 0, then we know that we have a full set - // of flags and items in the code buffer. These need to be - // output. - - if (mask == 0) - { - // code_buf is the buffer of characters to be output. - // code_buf_pos is the number of characters it contains. - - SendChars(code_buf, code_buf_pos); - - // Reset for next buffer... - - code_buf[0] = 0; - code_buf_pos = 1; - mask = 1; - } - - last_match_length = m_match_length; - - // Delete old strings and read new bytes... - - for (i = 0; i < last_match_length; i++) - { - - // Get next character... - - if (GetChars(&c, 1) != 1) - break; - - // Delete "old strings" - - DeleteNode(s); - - // Put this character into the ring buffer. - // - // The original comment here says "If the position is near - // the end of the buffer, extend the buffer to make - // string comparison easier." - // - // That's a little misleading, because the "end" of the - // buffer is really what we consider to be the "beginning" - // of the buffer, that is, positions 0 through F. - // - // The idea is that the front end of the buffer is duplicated - // into the back end so that when you're looking at characters - // at the back end of the buffer, you can index ahead (beyond - // the normal end of the buffer) and see the characters - // that are at the front end of the buffer wihtout having - // to adjust the index. - // - // That is... - // - // 1234xxxxxxxxxxxxxxxxxxxxxxxxxxxxx1234 - // | | | - // position 0 end of buffer | - // | - // duplicate of front of buffer - - m_ring_buffer[s] = c; - - if (s < F - 1) - { - m_ring_buffer[s + N] = c; - } - - // Increment the position, and wrap around when we're at - // the end. Note that this relies on N being a power of 2. - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Register the string that is found in - // m_ring_buffer[r..r+F-1]. - - InsertNode(r); - } - - // If we didn't quit because we hit the last_match_length, - // then we must have quit because we ran out of characters - // to process. - - while (i++ < last_match_length) - { - DeleteNode(s); - - s = (short int) ( (s + 1) & (N - 1) ); - r = (short int) ( (r + 1) & (N - 1) ); - - // Note that len hitting 0 is the key that causes the - // do...while() to terminate. This is the only place - // within the loop that len is modified. - // - // Its original value is F (or a number less than F for - // short strings). - - if (--len) - { - InsertNode(r); /* buffer may not be empty. */ - } - } - - // End of do...while() loop. Continue processing until there - // are no more characters to be compressed. The variable - // "len" is used to signal this condition. - } - while (len > 0); - - // There could still be something in the output buffer. Send it - // now. - - if (code_buf_pos > 1) - { - // code_buf is the encoded string to send. - // code_buf_ptr is the number of characters. - - SendChars(code_buf, code_buf_pos); - } - - // Done! - } - -/* - ------------------------------------------------------------------------- - cLZSS::Decode - - This function "decodes" the input stream into the output stream. - The GetChars() and SendChars() functions are used to separate - this method from the actual i/o. - ------------------------------------------------------------------------- -*/ - -void cLZSS::Decode( // no return value - void) // no parameters - - { - int k; - int r; // node number - unsigned char c[F]; // an array of chars - unsigned char flags; // 8 bits of flags - int flag_count; // which flag we're on - short int pos; // position in the ring buffer - short int len; // number of chars in ring buffer - - // Initialize the ring buffer with a common string. - // - // Note that the last F bytes of the ring buffer are not filled. - - memset(m_ring_buffer, ' ', N - F); - - r = N - F; - - flags = (char) 0; - flag_count = 0; - - for ( ; ; ) - { - - // If there are more bits of interest in this flag, then - // shift that next interesting bit into the 1's position. - // - // If this flag has been exhausted, the next byte must - // be a flag. - - if (flag_count > 0) - { - flags = (unsigned char) (flags >> 1); - flag_count--; - } - else - { - // Next byte must be a flag. - - if (GetChars(&flags, 1) != 1) - break; - - // Set the flag counter. While at first it might appear - // that this should be an 8 since there are 8 bits in the - // flag, it should really be a 7 because the shift must - // be performed 7 times in order to see all 8 bits. - - flag_count = 7; - } - - // If the low order bit of the flag is now set, then we know - // that the next byte is a single, unencoded character. - - if (flags & 1) - { - if (GetChars(c, 1) != 1) - break; - - if (SendChars(c, 1) != 1) - break; - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[0]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Otherwise, we know that the next two bytes are a - // <position,length> pair. The position is in 12 bits and - // the length is in 4 bits. - - else - { - // Original code: - // if ((i = getc(infile)) == EOF) - // break; - // if ((j = getc(infile)) == EOF) - // break; - // i |= ((j & 0xf0) << 4); - // j = (j & 0x0f) + THRESHOLD; - // - // I've modified this to only make one input call, and - // have changed the variable names to something more - // obvious. - - if (GetChars(c, 2) != 2) - break; - - // Convert these two characters into the position and - // length. Note that the length is always at least - // THRESHOLD, which is why we're able to get a length - // of 18 out of only 4 bits. - - pos = (short int) ( c[0] | ((c[1] & 0xf0) << 4) ); - - len = (short int) ( (c[1] & 0x0f) + THRESHOLD ); - - // There are now "len" characters at position "pos" in - // the ring buffer that can be pulled out. Note that - // len is never more than F. - - for (k = 0; k < len; k++) - { - c[k] = m_ring_buffer[(pos + k) & (N - 1)]; - - // Add to buffer, and increment to next spot. Wrap at end. - - m_ring_buffer[r] = c[k]; - r = (short int) ( (r + 1) & (N - 1) ); - } - - // Add the "len" characters to the output stream. - - if (SendChars(c, len) != len) - break; - } - } - } - diff --git a/src/modules/common/zipcomprs.cpp b/src/modules/common/zipcomprs.cpp deleted file mode 100644 index 6a5ed22..0000000 --- a/src/modules/common/zipcomprs.cpp +++ /dev/null @@ -1,161 +0,0 @@ -/****************************************************************************** - * swcomprs.cpp - code for class 'ZipCompress'- a driver class that provides - * compression utilities. - using zlib - */ - -#include <stdlib.h> -#include <string.h> -#include <stdio.h> -#include <zipcomprs.h> -#include <zlib.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * ZipCompress Constructor - Initializes data for instance of ZipCompress - * - */ - -ZipCompress::ZipCompress() : SWCompress() -{ -// fprintf(stderr, "init compress\n"); -} - - -/****************************************************************************** - * ZipCompress Destructor - Cleans up instance of ZipCompress - */ - -ZipCompress::~ZipCompress() { -} - - -/****************************************************************************** - * ZipCompress::Encode - This function "encodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - * NOTE: must set zlen for parent class to know length of - * compressed buffer. - */ - -void ZipCompress::Encode(void) -{ -/* -ZEXTERN int ZEXPORT compress OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong sourceLen)); - Compresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total - size of the destination buffer, which must be at least 0.1% larger than - sourceLen plus 12 bytes. Upon exit, destLen is the actual size of the - compressed buffer. - This function can be used to compress a whole file at once if the - input file is mmap'ed. - compress returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer. -*/ - direct = 0; // set direction needed by parent [Get|Send]Chars() - - // get buffer - char chunk[1024]; - char *buf = (char *)calloc(1, 1024); - char *chunkbuf = buf; - unsigned long chunklen; - unsigned long len = 0; - while((chunklen = GetChars(chunk, 1023))) { - memcpy(chunkbuf, chunk, chunklen); - len += chunklen; - if (chunklen < 1023) - break; - else buf = (char *)realloc(buf, len + 1024); - chunkbuf = buf+len; - } - - - zlen = (long) (len*1.001)+15; - char *zbuf = new char[zlen+1]; - if (len) - { - //printf("Doing compress\n"); - if (compress((Bytef*)zbuf, &zlen, (const Bytef*)buf, len)!=Z_OK) - { - printf("ERROR in compression\n"); - } - else { - SendChars(zbuf, zlen); - } - } - else - { - fprintf(stderr, "No buffer to compress\n"); - } - delete [] zbuf; - free (buf); -} - - -/****************************************************************************** - * ZipCompress::Decode - This function "decodes" the input stream into the - * output stream. - * The GetChars() and SendChars() functions are - * used to separate this method from the actual - * i/o. - */ - -void ZipCompress::Decode(void) -{ -/* -ZEXTERN int ZEXPORT uncompress OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong sourceLen)); - Decompresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total - size of the destination buffer, which must be large enough to hold the - entire uncompressed data. (The size of the uncompressed data must have - been saved previously by the compressor and transmitted to the decompressor - by some mechanism outside the scope of this compression library.) - Upon exit, destLen is the actual size of the compressed buffer. - This function can be used to decompress a whole file at once if the - input file is mmap'ed. - - uncompress returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer, or Z_DATA_ERROR if the input data was corrupted. -*/ - - // get buffer - char chunk[1024]; - char *zbuf = (char *)calloc(1, 1024); - char *chunkbuf = zbuf; - int chunklen; - unsigned long zlen = 0; - while((chunklen = GetChars(chunk, 1023))) { - memcpy(chunkbuf, chunk, chunklen); - zlen += chunklen; - if (chunklen < 1023) - break; - else zbuf = (char *)realloc(zbuf, zlen + 1024); - chunkbuf = zbuf + zlen; - } - - //printf("Decoding complength{%ld} uncomp{%ld}\n", zlen, blen); - if (zlen) { - unsigned long blen = zlen*20; // trust compression is less than 1000% - char *buf = new char[blen]; - //printf("Doing decompress {%s}\n", zbuf); - if (uncompress((Bytef*)buf, &blen, (Bytef*)zbuf, zlen) != Z_OK) { - fprintf(stderr, "no room in outbuffer to during decompression. see zipcomp.cpp\n"); - } - SendChars(buf, blen); - delete [] buf; - slen = blen; - } - else { - fprintf(stderr, "No buffer to decompress!\n"); - } - //printf("Finished decoding\n"); - free (zbuf); -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/zstr.cpp b/src/modules/common/zstr.cpp deleted file mode 100644 index 92a4960..0000000 --- a/src/modules/common/zstr.cpp +++ /dev/null @@ -1,718 +0,0 @@ -/****************************************************************************** - * zstr.cpp - code for class 'zStr'- a module that reads compressed text - * files and provides lookup and parsing functions based on - * class StrKey - */ - -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> - -#ifndef __GNUC__ -#include <io.h> -#else -#include <unistd.h> -#endif - -#include <stdlib.h> -#include <utilfuns.h> -#include <zstr.h> -#include <swcomprs.h> - -#include <sysdata.h> -#include <entriesblk.h> - -SWORD_NAMESPACE_START - -/****************************************************************************** - * zStr Statics - */ - -int zStr::instance = 0; -const int zStr::IDXENTRYSIZE = 8; -const int zStr::ZDXENTRYSIZE = 8; - - -/****************************************************************************** - * zStr Constructor - Initializes data for instance of zStr - * - * ENT: ipath - path of the directory where data and index files are located. - */ - -zStr::zStr(const char *ipath, int fileMode, long blockCount, SWCompress *icomp) { - char buf[127]; - - nl = '\n'; - lastoff = -1; - path = 0; - stdstr(&path, ipath); - - compressor = (icomp) ? icomp : new SWCompress(); - this->blockCount = blockCount; -#ifndef O_BINARY // O_BINARY is needed in Borland C++ 4.53 -#define O_BINARY 0 // If it hasn't been defined than we probably -#endif // don't need it. - - if (fileMode == -1) { // try read/write if possible - fileMode = O_RDWR; - } - - sprintf(buf, "%s.idx", path); - idxfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s.dat", path); - datfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s.zdx", path); - zdxfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s.zdt", path); - zdtfd = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - if (datfd <= 0) { - sprintf(buf, "Error: %d", errno); - perror(buf); - } - - cacheBlock = 0; - cacheBlockIndex = -1; - cacheDirty = false; - - instance++; -} - - -/****************************************************************************** - * zStr Destructor - Cleans up instance of zStr - */ - -zStr::~zStr() { - - flushCache(); - - if (path) - delete [] path; - - --instance; - - FileMgr::systemFileMgr.close(idxfd); - FileMgr::systemFileMgr.close(datfd); - FileMgr::systemFileMgr.close(zdxfd); - FileMgr::systemFileMgr.close(zdtfd); - - - if (compressor) - delete compressor; - -} - - -/****************************************************************************** - * zStr::getidxbufdat - Gets the index string at the given dat offset - * NOTE: buf is calloc'd, or if not null, realloc'd and must - * be free'd by calling function - * - * ENT: ioffset - offset in dat file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void zStr::getKeyFromDatOffset(long ioffset, char **buf) { - int size; - char ch; - if (datfd > 0) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - for (size = 0; read(datfd->getFd(), &ch, 1) == 1; size++) { - if ((ch == '\\') || (ch == 10) || (ch == 13)) - break; - } - *buf = (*buf) ? (char *)realloc(*buf, size*2 + 1) : (char *)malloc(size*2 + 1); - if (size) { - lseek(datfd->getFd(), ioffset, SEEK_SET); - read(datfd->getFd(), *buf, size); - } - (*buf)[size] = 0; - toupperstr_utf8(*buf, size*2); - } - else { - *buf = (*buf) ? (char *)realloc(*buf, 1) : (char *)malloc(1); - **buf = 0; - } -} - - -/****************************************************************************** - * zStr::getidxbuf - Gets the index string at the given idx offset - * NOTE: buf is calloc'd, or if not null, realloc'd - * and must be freed by calling function - * - * ENT: ioffset - offset in idx file to lookup - * buf - address of pointer to allocate for storage of string - */ - -void zStr::getKeyFromIdxOffset(long ioffset, char **buf) { - __u32 offset; - - if (idxfd > 0) { - lseek(idxfd->getFd(), ioffset, SEEK_SET); - read(idxfd->getFd(), &offset, sizeof(__u32)); - offset = swordtoarch32(offset); - getKeyFromDatOffset(offset, buf); - } -} - - -/****************************************************************************** - * zStr::findoffset - Finds the offset of the key string from the indexes - * - * ENT: key - key string to lookup - * offset - address to store the starting offset - * size - address to store the size of the entry - * away - number of entries before of after to jump - * (default = 0) - * - * RET: error status - */ - -signed char zStr::findKeyIndex(const char *ikey, long *idxoff, long away) { - char *trybuf = 0, *key = 0, quitflag = 0; - signed char retval = 0; - __s32 headoff, tailoff, tryoff = 0, maxoff = 0; - __u32 start, size; - - if (idxfd->getFd() >= 0) { - tailoff = maxoff = lseek(idxfd->getFd(), 0, SEEK_END) - IDXENTRYSIZE; - if (*ikey) { - headoff = 0; - stdstr(&key, ikey, 3); - toupperstr_utf8(key, strlen(key)*3); - - while (headoff < tailoff) { - tryoff = (lastoff == -1) ? headoff + (((((tailoff / IDXENTRYSIZE) - (headoff / IDXENTRYSIZE))) / 2) * IDXENTRYSIZE) : lastoff; - lastoff = -1; - - getKeyFromIdxOffset(tryoff, &trybuf); - - if (!*trybuf && tryoff) { // In case of extra entry at end of idx (not first entry) - tryoff += (tryoff > (maxoff / 2))?-IDXENTRYSIZE:IDXENTRYSIZE; - retval = -1; - break; - } - - int diff = strcmp(key, trybuf); - if (!diff) - break; - - if (diff < 0) - tailoff = (tryoff == headoff) ? headoff : tryoff; - else headoff = tryoff; - if (tailoff == headoff + IDXENTRYSIZE) { - if (quitflag++) - headoff = tailoff; - } - } - if (headoff >= tailoff) - tryoff = headoff; - if (trybuf) - free(trybuf); - delete [] key; - } - else { tryoff = 0; } - - lseek(idxfd->getFd(), tryoff, SEEK_SET); - - start = size = 0; - retval = (read(idxfd->getFd(), &start, sizeof(__u32))==sizeof(__u32)) ? retval : -1; - retval = (read(idxfd->getFd(), &size, sizeof(__u32))==sizeof(__u32)) ? retval : -1; - start = swordtoarch32(start); - size = swordtoarch32(size); - - if (idxoff) - *idxoff = tryoff; - - while (away) { - __u32 laststart = start; - __u32 lastsize = size; - __s32 lasttry = tryoff; - tryoff += (away > 0) ? IDXENTRYSIZE : -IDXENTRYSIZE; - - bool bad = false; - if (((long)(tryoff + (away*IDXENTRYSIZE)) < -IDXENTRYSIZE) || (tryoff + (away*IDXENTRYSIZE) > (maxoff+IDXENTRYSIZE))) - bad = true; - else if (lseek(idxfd->getFd(), tryoff, SEEK_SET) < 0) - bad = true; - if (bad) { - retval = -1; - start = laststart; - size = lastsize; - tryoff = lasttry; - if (idxoff) - *idxoff = tryoff; - break; - } - read(idxfd->getFd(), &start, sizeof(__u32)); - read(idxfd->getFd(), &size, sizeof(__u32)); - start = swordtoarch32(start); - size = swordtoarch32(size); - - if (idxoff) - *idxoff = tryoff; - - - if (((laststart != start) || (lastsize != size)) && (start >= 0) && (size)) - away += (away < 0) ? 1 : -1; - } - - lastoff = tryoff; - } - else { - if (idxoff) - *idxoff = 0; - retval = -1; - } - return retval; -} - - -/****************************************************************************** - * zStr::preptext - Prepares the text before returning it to external - * objects - * - * ENT: buf - buffer where text is stored and where to store the prep'd - * text. - */ - -void zStr::prepText(SWBuf &buf) { - unsigned int to, from; - char space = 0, cr = 0, realdata = 0, nlcnt = 0; - char *rawBuf = buf.getRawData(); - for (to = from = 0; rawBuf[from]; from++) { - switch (rawBuf[from]) { - case 10: - if (!realdata) - continue; - space = (cr) ? 0 : 1; - cr = 0; - nlcnt++; - if (nlcnt > 1) { -// *to++ = nl; - rawBuf[to++] = 10; -// *to++ = nl[1]; -// nlcnt = 0; - } - continue; - case 13: - if (!realdata) - continue; -// *to++ = nl[0]; - rawBuf[to++] = 10; - space = 0; - cr = 1; - continue; - } - realdata = 1; - nlcnt = 0; - if (space) { - space = 0; - if (rawBuf[from] != ' ') { - rawBuf[to++] = ' '; - from--; - continue; - } - } - rawBuf[to++] = rawBuf[from]; - } - buf.setSize(to); - - while (to > 1) { // remove trailing excess - to--; - if ((rawBuf[to] == 10) || (rawBuf[to] == ' ')) - buf.setSize(to); - else break; - } -} - - -/****************************************************************************** - * zStr::getText - gets text at a given offset - * - * ENT: - * offset - idxoffset where the key is located. - * buf - buffer to store text - * idxbuf - buffer to store index key - * NOTE: buffer will be alloc'd / realloc'd and - * should be free'd by the client - * - */ - -void zStr::getText(long offset, char **idxbuf, char **buf) { - char *ch; - char *idxbuflocal = 0; - getKeyFromIdxOffset(offset, &idxbuflocal); - __u32 start; - __u32 size; - - do { - lseek(idxfd->getFd(), offset, SEEK_SET); - read(idxfd->getFd(), &start, sizeof(__u32)); - read(idxfd->getFd(), &size, sizeof(__u32)); - start = swordtoarch32(start); - size = swordtoarch32(size); - - *buf = (*buf) ? (char *)realloc(*buf, size*2 + 1) : (char *)malloc(size*2 + 1); - *idxbuf = (*idxbuf) ? (char *)realloc(*idxbuf, size*2 + 1) : (char *)malloc(size*2 + 1); - memset(*buf, 0, size + 1); - memset(*idxbuf, 0, size + 1); - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), *buf, (int)(size)); - - for (ch = *buf; *ch; ch++) { // skip over index string - if (*ch == 10) { - ch++; - break; - } - } - memmove(*buf, ch, size - (unsigned long)(ch-*buf)); - - // resolve link - if (!strncmp(*buf, "@LINK", 5)) { - for (ch = *buf; *ch; ch++) { // null before nl - if (*ch == 10) { - *ch = 0; - break; - } - } - findKeyIndex(*buf + 6, &offset); - } - else break; - } - while (true); // while we're resolving links - - if (idxbuflocal) { - __u32 localsize = strlen(idxbuflocal); - localsize = (localsize < (size - 1)) ? localsize : (size - 1); - strncpy(*idxbuf, idxbuflocal, localsize); - (*idxbuf)[localsize] = 0; - free(idxbuflocal); - } - __u32 block = 0; - __u32 entry = 0; - memmove(&block, *buf, sizeof(__u32)); - memmove(&entry, *buf + sizeof(__u32), sizeof(__u32)); - block = swordtoarch32(block); - entry = swordtoarch32(entry); - getCompressedText(block, entry, buf); -} - - -/****************************************************************************** - * zStr::getCompressedText - Get text entry from a compressed index / zdata - * file. - */ - -void zStr::getCompressedText(long block, long entry, char **buf) { - - __u32 size = 0; - - if (cacheBlockIndex != block) { - __u32 start = 0; - - lseek(zdxfd->getFd(), block * ZDXENTRYSIZE, SEEK_SET); - read(zdxfd->getFd(), &start, sizeof(__u32)); - read(zdxfd->getFd(), &size, sizeof(__u32)); - start = swordtoarch32(start); - size = swordtoarch32(size); - - SWBuf buf; - buf.setSize(size + 5); - lseek(zdtfd->getFd(), start, SEEK_SET); - read(zdtfd->getFd(), buf.getRawData(), size); - - flushCache(); - - unsigned long len = size; - buf.setSize(size); - rawZFilter(buf, 0); // 0 = decipher - - compressor->zBuf(&len, buf.getRawData()); - char *rawBuf = compressor->Buf(0, &len); - cacheBlock = new EntriesBlock(rawBuf, len); - cacheBlockIndex = block; - } - size = cacheBlock->getEntrySize(entry); - *buf = (*buf) ? (char *)realloc(*buf, size*2 + 1) : (char *)malloc(size*2 + 1); - strcpy(*buf, cacheBlock->getEntry(entry)); -} - - -/****************************************************************************** - * zLD::settext - Sets text for current offset - * - * ENT: key - key for this entry - * buf - buffer to store - * len - length of buffer (0 - null terminated) - */ - -void zStr::setText(const char *ikey, const char *buf, long len) { - - __u32 start, outstart; - __u32 size, outsize; - __s32 endoff; - long idxoff = 0; - __s32 shiftSize; - static const char nl[] = {13, 10}; - char *tmpbuf = 0; - char *key = 0; - char *dbKey = 0; - char *idxBytes = 0; - char *outbuf = 0; - char *ch = 0; - - len = (len < 0) ? strlen(buf) : len; - stdstr(&key, ikey, 3); - toupperstr_utf8(key, strlen(key)*3); - - char notFound = findKeyIndex(ikey, &idxoff, 0); - if (!notFound) { - getKeyFromIdxOffset(idxoff, &dbKey); - int diff = strcmp(key, dbKey); - if (diff < 0) { - } - else if (diff > 0) { - idxoff += IDXENTRYSIZE; - } - else if ((!diff) && (len > 0 /*we're not deleting*/)) { // got absolute entry - do { - lseek(idxfd->getFd(), idxoff, SEEK_SET); - read(idxfd->getFd(), &start, sizeof(__u32)); - read(idxfd->getFd(), &size, sizeof(__u32)); - start = swordtoarch32(start); - size = swordtoarch32(size); - - tmpbuf = new char [ size + 2 ]; - memset(tmpbuf, 0, size + 2); - lseek(datfd->getFd(), start, SEEK_SET); - read(datfd->getFd(), tmpbuf, size); - - for (ch = tmpbuf; *ch; ch++) { // skip over index string - if (*ch == 10) { - ch++; - break; - } - } - memmove(tmpbuf, ch, size - (unsigned long)(ch-tmpbuf)); - - // resolve link - if (!strncmp(tmpbuf, "@LINK", 5) && (len)) { - for (ch = tmpbuf; *ch; ch++) { // null before nl - if (*ch == 10) { - *ch = 0; - break; - } - } - findKeyIndex(tmpbuf + IDXENTRYSIZE, &idxoff); - delete [] tmpbuf; - } - else break; - } - while (true); // while we're resolving links - } - } - - endoff = lseek(idxfd->getFd(), 0, SEEK_END); - - shiftSize = endoff - idxoff; - - if (shiftSize > 0) { - idxBytes = new char [ shiftSize ]; - lseek(idxfd->getFd(), idxoff, SEEK_SET); - read(idxfd->getFd(), idxBytes, shiftSize); - } - - outbuf = new char [ len + strlen(key) + 5 ]; - sprintf(outbuf, "%s%c%c", key, 13, 10); - size = strlen(outbuf); - if (len > 0) { // NOT a link - if (!cacheBlock) { - flushCache(); - cacheBlock = new EntriesBlock(); - cacheBlockIndex = (lseek(zdxfd->getFd(), 0, SEEK_END) / ZDXENTRYSIZE); - } - else if (cacheBlock->getCount() >= blockCount) { - flushCache(); - cacheBlock = new EntriesBlock(); - cacheBlockIndex = (lseek(zdxfd->getFd(), 0, SEEK_END) / ZDXENTRYSIZE); - } - __u32 entry = cacheBlock->addEntry(buf); - cacheDirty = true; - outstart = archtosword32(cacheBlockIndex); - outsize = archtosword32(entry); - memcpy (outbuf + size, &outstart, sizeof(__u32)); - memcpy (outbuf + size + sizeof(__u32), &outsize, sizeof(__u32)); - size += (sizeof(__u32) * 2); - } - else { // link - memcpy(outbuf + size, buf, len); - size += len; - } - - start = lseek(datfd->getFd(), 0, SEEK_END); - - outstart = archtosword32(start); - outsize = archtosword32(size); - - lseek(idxfd->getFd(), idxoff, SEEK_SET); - if (len > 0) { - lseek(datfd->getFd(), start, SEEK_SET); - write(datfd->getFd(), outbuf, size); - - // add a new line to make data file easier to read in an editor - write(datfd->getFd(), &nl, 2); - - write(idxfd->getFd(), &outstart, sizeof(__u32)); - write(idxfd->getFd(), &outsize, sizeof(__u32)); - if (idxBytes) { - write(idxfd->getFd(), idxBytes, shiftSize); - } - } - else { // delete entry - if (idxBytes) { - write(idxfd->getFd(), idxBytes+IDXENTRYSIZE, shiftSize-IDXENTRYSIZE); - lseek(idxfd->getFd(), -1, SEEK_CUR); // last valid byte - FileMgr::systemFileMgr.trunc(idxfd); // truncate index - } - } - - if (idxBytes) - delete [] idxBytes; - delete [] key; - delete [] outbuf; - free(dbKey); -} - - -/****************************************************************************** - * zLD::linkentry - links one entry to another - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * destidxoff - dest offset into .vss - * srcidxoff - source offset into .vss - */ - -void zStr::linkEntry(const char *destkey, const char *srckey) { - char *text = new char [ strlen(destkey) + 7 ]; - sprintf(text, "@LINK %s", destkey); - setText(srckey, text); - delete [] text; -} - - -void zStr::flushCache() { - if (cacheBlock) { - if (cacheDirty) { - __u32 start = 0; - unsigned long size = 0; - __u32 outstart = 0, outsize = 0; - - const char *rawBuf = cacheBlock->getRawData(&size); - compressor->Buf(rawBuf, &size); - compressor->zBuf(&size); - - SWBuf buf; - buf.setSize(size + 5); - memcpy(buf.getRawData(), compressor->zBuf(&size), size); // 1 = encipher - buf.setSize(size); - rawZFilter(buf, 1); // 1 = encipher - - long zdxSize = lseek(zdxfd->getFd(), 0, SEEK_END); - long zdtSize = lseek(zdtfd->getFd(), 0, SEEK_END); - - if ((cacheBlockIndex * ZDXENTRYSIZE) > (zdxSize - ZDXENTRYSIZE)) { // New Block - start = zdtSize; - } - else { - lseek(zdxfd->getFd(), cacheBlockIndex * ZDXENTRYSIZE, SEEK_SET); - read(zdxfd->getFd(), &start, sizeof(__u32)); - read(zdxfd->getFd(), &outsize, sizeof(__u32)); - start = swordtoarch32(start); - outsize = swordtoarch32(outsize); - if (start + outsize >= zdtSize) { // last entry, just overwrite - // start is already set - } - else if (size < outsize) { // middle entry, but smaller, that's fine and let's preserve bigger size - size = outsize; - } - else { // middle and bigger-- we have serious problems, for now let's put it at the end = lots of wasted space - start = zdtSize; - } - } - - - - outstart = archtosword32(start); - outsize = archtosword32((__u32)size); - - lseek(zdxfd->getFd(), cacheBlockIndex * ZDXENTRYSIZE, SEEK_SET); - lseek(zdtfd->getFd(), start, SEEK_SET); - write(zdtfd->getFd(), buf, size); - - // add a new line to make data file easier to read in an editor - write(zdtfd->getFd(), &nl, 2); - - write(zdxfd->getFd(), &outstart, sizeof(__u32)); - write(zdxfd->getFd(), &outsize, sizeof(__u32)); - } - delete cacheBlock; - cacheBlock = 0; - } - cacheBlockIndex = -1; - cacheDirty = false; -} - - -/****************************************************************************** - * zLD::CreateModule - Creates new module files - * - * ENT: path - directory to store module files - * RET: error status - */ - -signed char zStr::createModule(const char *ipath) { - char *path = 0; - char *buf = new char [ strlen (ipath) + 20 ]; - FileDesc *fd, *fd2; - - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - sprintf(buf, "%s.dat", path); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s.idx", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd2); - - sprintf(buf, "%s.zdt", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd2); - - sprintf(buf, "%s.zdx", path); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd2); - - delete [] path; - - return 0; -} - -SWORD_NAMESPACE_END diff --git a/src/modules/common/zverse.cpp b/src/modules/common/zverse.cpp deleted file mode 100644 index 1f7f25d..0000000 --- a/src/modules/common/zverse.cpp +++ /dev/null @@ -1,538 +0,0 @@ -/****************************************************************************** - * zverse.h - code for class 'zVerse'- a module that reads raw text - * files: ot and nt using indexs ??.bks ??.cps ??.vss - * and provides lookup and parsing functions based on - * class VerseKey for compressed modules - */ - - -#include <ctype.h> -#include <stdio.h> -#include <fcntl.h> -#include <errno.h> -#include <stdlib.h> - -#ifndef __GNUC__ -#include <io.h> -#else -#include <unistd.h> -#endif - -#include <utilfuns.h> -#include <versekey.h> -#include <zverse.h> -#include <sysdata.h> -#include <swbuf.h> - - -#ifndef O_BINARY -#define O_BINARY 0 -#endif - -SWORD_NAMESPACE_START - -/****************************************************************************** - * zVerse Statics - */ - -int zVerse::instance = 0; - -const char zVerse::uniqueIndexID[] = {'X', 'r', 'v', 'c', 'b'}; - -/****************************************************************************** - * zVerse Constructor - Initializes data for instance of zVerse - * - * ENT: ipath - path of the directory where data and index files are located. - * be sure to include the trailing separator (e.g. '/' or '\') - * (e.g. 'modules/texts/rawtext/webster/') - * fileMode - open mode for the files (O_RDONLY, etc.) - * blockType - verse, chapter, book, etc. - */ - -zVerse::zVerse(const char *ipath, int fileMode, int blockType, SWCompress *icomp) -{ - char buf[127]; - - nl = '\n'; - path = 0; - cacheBufIdx = -1; - cacheTestament = 0; - cacheBuf = 0; - dirtyCache = false; - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - compressor = (icomp) ? icomp : new SWCompress(); - - if (fileMode == -1) { // try read/write if possible - fileMode = O_RDWR; - } - - sprintf(buf, "%s/ot.%czs", path, uniqueIndexID[blockType]); - idxfp[0] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/nt.%czs", path, uniqueIndexID[blockType]); - idxfp[1] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/ot.%czz", path, uniqueIndexID[blockType]); - textfp[0] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/nt.%czz", path, uniqueIndexID[blockType]); - textfp[1] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/ot.%czv", path, uniqueIndexID[blockType]); - compfp[0] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - sprintf(buf, "%s/nt.%czv", path, uniqueIndexID[blockType]); - compfp[1] = FileMgr::systemFileMgr.open(buf, fileMode|O_BINARY, true); - - instance++; -} - - -/****************************************************************************** - * zVerse Destructor - Cleans up instance of zVerse - */ - -zVerse::~zVerse() -{ - int loop1; - - if (cacheBuf) { - flushCache(); - free(cacheBuf); - } - - if (path) - delete [] path; - - if (compressor) - delete compressor; - - --instance; - - for (loop1 = 0; loop1 < 2; loop1++) { - FileMgr::systemFileMgr.close(idxfp[loop1]); - FileMgr::systemFileMgr.close(textfp[loop1]); - FileMgr::systemFileMgr.close(compfp[loop1]); - } -} - - -/****************************************************************************** - * zVerse::findoffset - Finds the offset of the key verse from the indexes - * - * - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * book - book to find (0 - testament introduction) - * chapter - chapter to find (0 - book introduction) - * verse - verse to find (0 - chapter introduction) - * start - address to store the starting offset - * size - address to store the size of the entry - */ - -void zVerse::findOffset(char testmt, long idxoff, long *start, unsigned short *size) -{ - // set start to offset in - // set size to - // set - unsigned long ulBuffNum=0; // buffer number - unsigned long ulVerseStart=0; // verse offset within buffer - unsigned short usVerseSize=0; // verse size - unsigned long ulCompOffset=0; // compressed buffer start - unsigned long ulCompSize=0; // buffer size compressed - unsigned long ulUnCompSize=0; // buffer size uncompressed - char *pcCompText=NULL; // compressed text - - *start = *size = 0; - //printf ("Finding offset %ld\n", idxoff); - idxoff *= 10; - if (!testmt) { - testmt = ((idxfp[0]) ? 1:2); - } - - // assert we have and valid file descriptor - if (compfp[testmt-1]->getFd() < 1) - return; - - long newOffset = lseek(compfp[testmt-1]->getFd(), idxoff, SEEK_SET); - if (newOffset == idxoff) { - if (read(compfp[testmt-1]->getFd(), &ulBuffNum, 4) != 4) { - printf ("Error reading ulBuffNum\n"); - return; - } - } - else return; - - ulBuffNum = swordtoarch32(ulBuffNum); - - if (read(compfp[testmt-1]->getFd(), &ulVerseStart, 4) < 2) - { - printf ("Error reading ulVerseStart\n"); - return; - } - if (read(compfp[testmt-1]->getFd(), &usVerseSize, 2) < 2) - { - printf ("Error reading usVerseSize\n"); - return; - } - - *start = swordtoarch32(ulVerseStart); - *size = swordtoarch16(usVerseSize); - - if (*size) { - if (((long) ulBuffNum == cacheBufIdx) && (testmt == cacheTestament) && (cacheBuf)) { - // have the text buffered - return; - } - - //printf ("Got buffer number{%ld} versestart{%ld} versesize{%d}\n", ulBuffNum, ulVerseStart, usVerseSize); - - - if (lseek(idxfp[testmt-1]->getFd(), ulBuffNum*12, SEEK_SET)!=(long) ulBuffNum*12) - { - printf ("Error seeking compressed file index\n"); - return; - } - if (read(idxfp[testmt-1]->getFd(), &ulCompOffset, 4)<4) - { - printf ("Error reading ulCompOffset\n"); - return; - } - if (read(idxfp[testmt-1]->getFd(), &ulCompSize, 4)<4) - { - printf ("Error reading ulCompSize\n"); - return; - } - if (read(idxfp[testmt-1]->getFd(), &ulUnCompSize, 4)<4) - { - printf ("Error reading ulUnCompSize\n"); - return; - } - - ulCompOffset = swordtoarch32(ulCompOffset); - ulCompSize = swordtoarch32(ulCompSize); - ulUnCompSize = swordtoarch32(ulUnCompSize); - - if (lseek(textfp[testmt-1]->getFd(), ulCompOffset, SEEK_SET)!=(long)ulCompOffset) - { - printf ("Error: could not seek to right place in compressed text\n"); - return; - } - SWBuf pcCompText; - pcCompText.setSize(ulCompSize+5); - - if (read(textfp[testmt-1]->getFd(), pcCompText.getRawData(), ulCompSize)<(long)ulCompSize) { - printf ("Error reading compressed text\n"); - return; - } - pcCompText.setSize(ulCompSize); - rawZFilter(pcCompText, 0); // 0 = decipher - - compressor->zBuf(&ulCompSize, pcCompText.getRawData()); - - if (cacheBuf) { - flushCache(); - free(cacheBuf); - } - - unsigned long len = 0; - compressor->Buf(0, &len); - cacheBuf = (char *)calloc(len + 1, 1); - memcpy(cacheBuf, compressor->Buf(), len); - - cacheTestament = testmt; - cacheBufIdx = ulBuffNum; - } -} - - -/****************************************************************************** - * zVerse::zreadtext - gets text at a given offset - * - * ENT: testmt - testament file to search in (0 - Old; 1 - New) - * start - starting offset where the text is located in the file - * size - size of text entry + 1 (null) - * buf - buffer to store text - * - */ - -void zVerse::zReadText(char testmt, long start, unsigned short size, SWBuf &inBuf) { - inBuf = ""; - inBuf.setFillByte(0); - inBuf.setSize(size+1); - if (size > 0) { - if (cacheBuf) - strncpy(inBuf.getRawData(), &(cacheBuf[start]), size); - } - inBuf.setSize(strlen(inBuf.c_str())); -} - - -/****************************************************************************** - * zVerse::settext - Sets text for current offset - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * idxoff - offset into .vss - * buf - buffer to store - * len - length of buffer (0 - null terminated) - */ - -void zVerse::doSetText(char testmt, long idxoff, const char *buf, long len) { - - len = (len < 0) ? strlen(buf) : len; - if (!testmt) - testmt = ((idxfp[0]) ? 1:2); - if ((!dirtyCache) || (cacheBufIdx < 0)) { - cacheBufIdx = lseek(idxfp[testmt-1]->getFd(), 0, SEEK_END) / 12; - cacheTestament = testmt; - if (cacheBuf) - free(cacheBuf); - cacheBuf = (char *)calloc(len + 1, 1); - } - else cacheBuf = (char *)((cacheBuf)?realloc(cacheBuf, strlen(cacheBuf)+(len + 1)):calloc((len + 1), 1)); - - dirtyCache = true; - - unsigned long start, outstart; - unsigned long outBufIdx = cacheBufIdx; - unsigned short size; - unsigned short outsize; - - idxoff *= 10; - size = outsize = len; - - start = strlen(cacheBuf); - - if (!size) - start = outBufIdx = 0; - - outBufIdx = archtosword32(outBufIdx); - outstart = archtosword32(start); - outsize = archtosword16(size); - - lseek(compfp[testmt-1]->getFd(), idxoff, SEEK_SET); - write(compfp[testmt-1]->getFd(), &outBufIdx, 4); - write(compfp[testmt-1]->getFd(), &outstart, 4); - write(compfp[testmt-1]->getFd(), &outsize, 2); - strcat(cacheBuf, buf); -} - - -void zVerse::flushCache() { - if (dirtyCache) { - unsigned long idxoff; - unsigned long start, outstart; - unsigned long size, outsize; - unsigned long zsize, outzsize; - - idxoff = cacheBufIdx * 12; - if (cacheBuf) { - size = outsize = zsize = outzsize = strlen(cacheBuf); - if (size) { - // if (compressor) { - // delete compressor; - // compressor = new LZSSCompress(); - // } - compressor->Buf(cacheBuf); - compressor->zBuf(&zsize); - outzsize = zsize; - - SWBuf buf; - buf.setSize(zsize + 5); - memcpy(buf.getRawData(), compressor->zBuf(&zsize), zsize); - buf.setSize(zsize); - rawZFilter(buf, 1); // 1 = encipher - - start = outstart = lseek(textfp[cacheTestament-1]->getFd(), 0, SEEK_END); - - outstart = archtosword32(start); - outsize = archtosword32(size); - outzsize = archtosword32(zsize); - - write(textfp[cacheTestament-1]->getFd(), buf, zsize); - - lseek(idxfp[cacheTestament-1]->getFd(), idxoff, SEEK_SET); - write(idxfp[cacheTestament-1]->getFd(), &outstart, 4); - write(idxfp[cacheTestament-1]->getFd(), &outzsize, 4); - write(idxfp[cacheTestament-1]->getFd(), &outsize, 4); - } - free(cacheBuf); - cacheBuf = 0; - } - dirtyCache = false; - } -} - -/****************************************************************************** - * RawVerse::linkentry - links one entry to another - * - * ENT: testmt - testament to find (0 - Bible/module introduction) - * destidxoff - dest offset into .vss - * srcidxoff - source offset into .vss - */ - -void zVerse::doLinkEntry(char testmt, long destidxoff, long srcidxoff) { - long bufidx; - long start; - unsigned short size; - - destidxoff *= 10; - srcidxoff *= 10; - - if (!testmt) - testmt = ((idxfp[1]) ? 1:2); - - // get source - lseek(compfp[testmt-1]->getFd(), srcidxoff, SEEK_SET); - read(compfp[testmt-1]->getFd(), &bufidx, 4); - read(compfp[testmt-1]->getFd(), &start, 4); - read(compfp[testmt-1]->getFd(), &size, 2); - - // write dest - lseek(compfp[testmt-1]->getFd(), destidxoff, SEEK_SET); - write(compfp[testmt-1]->getFd(), &bufidx, 4); - write(compfp[testmt-1]->getFd(), &start, 4); - write(compfp[testmt-1]->getFd(), &size, 2); -} - - -/****************************************************************************** - * RawVerse::CreateModule - Creates new module files - * - * ENT: path - directory to store module files - * RET: error status - */ - -char zVerse::createModule(const char *ipath, int blockBound) -{ - char *path = 0; - char *buf = new char [ strlen (ipath) + 20 ]; - FileDesc *fd, *fd2; - - stdstr(&path, ipath); - - if ((path[strlen(path)-1] == '/') || (path[strlen(path)-1] == '\\')) - path[strlen(path)-1] = 0; - - sprintf(buf, "%s/ot.%czs", path, uniqueIndexID[blockBound]); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/nt.%czs", path, uniqueIndexID[blockBound]); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/ot.%czz", path, uniqueIndexID[blockBound]); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/nt.%czz", path, uniqueIndexID[blockBound]); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - FileMgr::systemFileMgr.close(fd); - - sprintf(buf, "%s/ot.%czv", path, uniqueIndexID[blockBound]); - unlink(buf); - fd = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd->getFd(); - - sprintf(buf, "%s/nt.%czv", path, uniqueIndexID[blockBound]); - unlink(buf); - fd2 = FileMgr::systemFileMgr.open(buf, O_CREAT|O_WRONLY|O_BINARY, S_IREAD|S_IWRITE); - fd2->getFd(); - - VerseKey vk; - vk.Headings(1); - long offset = 0; - short size = 0; - for (vk = TOP; !vk.Error(); vk++) { - write((vk.Testament() == 1) ? fd->getFd() : fd2->getFd(), &offset, 4); //compBufIdxOffset - write((vk.Testament() == 1) ? fd->getFd() : fd2->getFd(), &offset, 4); - write((vk.Testament() == 1) ? fd->getFd() : fd2->getFd(), &size, 2); - } - - FileMgr::systemFileMgr.close(fd); - FileMgr::systemFileMgr.close(fd2); - - delete [] path; - delete [] buf; -/* - RawVerse rv(path); - VerseKey mykey("Rev 22:21"); -*/ - - return 0; -} - - -/****************************************************************************** - * zVerse::preptext - Prepares the text before returning it to external - * objects - * - * ENT: buf - buffer where text is stored and where to store the prep'd - * text. - */ - -void zVerse::prepText(SWBuf &buf) { - unsigned int to, from; - char space = 0, cr = 0, realdata = 0, nlcnt = 0; - char *rawBuf = buf.getRawData(); - for (to = from = 0; rawBuf[from]; from++) { - switch (rawBuf[from]) { - case 10: - if (!realdata) - continue; - space = (cr) ? 0 : 1; - cr = 0; - nlcnt++; - if (nlcnt > 1) { -// *to++ = nl; - rawBuf[to++] = 10; -// *to++ = nl[1]; -// nlcnt = 0; - } - continue; - case 13: - if (!realdata) - continue; -// *to++ = nl[0]; - rawBuf[to++] = 10; - space = 0; - cr = 1; - continue; - } - realdata = 1; - nlcnt = 0; - if (space) { - space = 0; - if (rawBuf[from] != ' ') { - rawBuf[to++] = ' '; - from--; - continue; - } - } - rawBuf[to++] = rawBuf[from]; - } - buf.setSize(to); - - while (to > 1) { // remove trailing excess - to--; - if ((rawBuf[to] == 10) || (rawBuf[to] == ' ')) - buf.setSize(to); - else break; - } -} - - -SWORD_NAMESPACE_END |