/engine/source/MochaString.cpp
C++ | 412 lines | 300 code | 63 blank | 49 comment | 87 complexity | 88fa9fe75237f33bcc4bed8dda1d83dd MD5 | raw file
- #include <Mocha/MochaString.h>
- namespace Mocha{
- /*
- CRC-32
- Copyright (C) 1995-1998 Mark Adler
- */
-
- const U32 CRC32_INIT_VALUE = 0xffffffffL;
- const U32 CRC32_XOR_VALUE = 0xffffffffL;
-
- #ifdef CREATE_CRC_TABLE
-
- static U32 crctable32[256];
-
- /*
- Generate a table for a byte-wise 32-bit CRC calculation on the polynomial:
- x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0.
-
- Polynomials over GF(2) are represented in binary, one bit per coefficient,
- with the lowest powers in the most significant bit. Then adding polynomials
- is just exclusive-or, and multiplying a polynomial by x is a right shift by
- one. If we call the above polynomial p, and represent a byte as the
- polynomial q, also with the lowest power in the most significant bit (so the
- byte 0xb1 is the polynomial x^7+x^3+x^1+x^0), then the CRC is (q*x^32) mod p,
- where a mod b means the remainder after dividing a by b.
-
- This calculation is done using the shift-register method of multiplying and
- taking the remainder. The register is initialized to zero, and for each
- incoming bit, x^32 is added mod p to the register if the bit is a one (where
- x^32 mod p is p+x^32 = x^26+...+x^0), and the register is multiplied mod p by
- x (which is shifting right by one and adding x^32 mod p if the bit shifted
- out is a one). We start with the highest power (least significant bit) of
- q and repeat for all eight bits of q.
-
- The table is simply the CRC of all possible eight bit values. This is all
- the information needed to generate CRC's on data a byte at a time for all
- combinations of CRC register values and incoming bytes.
- */
-
- static void make_crc_table( void ) {
- int i, j;
- U32 c, poly;
- /* terms of polynomial defining this crc (except x^32): */
- static const U8 p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26};
-
- /* make exclusive-or pattern from polynomial (0xedb88320L) */
- poly = 0L;
- for ( i = 0; i < sizeof( p ) / sizeof( U8 ); i++ ) {
- poly |= 1L << ( 31 - p[i] );
- }
-
- for ( i = 0; i < 256; i++ ) {
- c = (U32)i;
- for ( j = 0; j < 8; j++ ) {
- c = ( c & 1 ) ? poly ^ ( c >> 1 ) : ( c >> 1 );
- }
- crctable32[i] = c;
- }
- }
-
- #else
-
- /*
- Table of CRC-32's of all single-U8 values (made by make_crc_table)
- */
- static U32 crctable32[256] = {
- 0x00000000L, 0x77073096L, 0xee0e612cL, 0x990951baL,
- 0x076dc419L, 0x706af48fL, 0xe963a535L, 0x9e6495a3L,
- 0x0edb8832L, 0x79dcb8a4L, 0xe0d5e91eL, 0x97d2d988L,
- 0x09b64c2bL, 0x7eb17cbdL, 0xe7b82d07L, 0x90bf1d91L,
- 0x1db71064L, 0x6ab020f2L, 0xf3b97148L, 0x84be41deL,
- 0x1adad47dL, 0x6ddde4ebL, 0xf4d4b551L, 0x83d385c7L,
- 0x136c9856L, 0x646ba8c0L, 0xfd62f97aL, 0x8a65c9ecL,
- 0x14015c4fL, 0x63066cd9L, 0xfa0f3d63L, 0x8d080df5L,
- 0x3b6e20c8L, 0x4c69105eL, 0xd56041e4L, 0xa2677172L,
- 0x3c03e4d1L, 0x4b04d447L, 0xd20d85fdL, 0xa50ab56bL,
- 0x35b5a8faL, 0x42b2986cL, 0xdbbbc9d6L, 0xacbcf940L,
- 0x32d86ce3L, 0x45df5c75L, 0xdcd60dcfL, 0xabd13d59L,
- 0x26d930acL, 0x51de003aL, 0xc8d75180L, 0xbfd06116L,
- 0x21b4f4b5L, 0x56b3c423L, 0xcfba9599L, 0xb8bda50fL,
- 0x2802b89eL, 0x5f058808L, 0xc60cd9b2L, 0xb10be924L,
- 0x2f6f7c87L, 0x58684c11L, 0xc1611dabL, 0xb6662d3dL,
- 0x76dc4190L, 0x01db7106L, 0x98d220bcL, 0xefd5102aL,
- 0x71b18589L, 0x06b6b51fL, 0x9fbfe4a5L, 0xe8b8d433L,
- 0x7807c9a2L, 0x0f00f934L, 0x9609a88eL, 0xe10e9818L,
- 0x7f6a0dbbL, 0x086d3d2dL, 0x91646c97L, 0xe6635c01L,
- 0x6b6b51f4L, 0x1c6c6162L, 0x856530d8L, 0xf262004eL,
- 0x6c0695edL, 0x1b01a57bL, 0x8208f4c1L, 0xf50fc457L,
- 0x65b0d9c6L, 0x12b7e950L, 0x8bbeb8eaL, 0xfcb9887cL,
- 0x62dd1ddfL, 0x15da2d49L, 0x8cd37cf3L, 0xfbd44c65L,
- 0x4db26158L, 0x3ab551ceL, 0xa3bc0074L, 0xd4bb30e2L,
- 0x4adfa541L, 0x3dd895d7L, 0xa4d1c46dL, 0xd3d6f4fbL,
- 0x4369e96aL, 0x346ed9fcL, 0xad678846L, 0xda60b8d0L,
- 0x44042d73L, 0x33031de5L, 0xaa0a4c5fL, 0xdd0d7cc9L,
- 0x5005713cL, 0x270241aaL, 0xbe0b1010L, 0xc90c2086L,
- 0x5768b525L, 0x206f85b3L, 0xb966d409L, 0xce61e49fL,
- 0x5edef90eL, 0x29d9c998L, 0xb0d09822L, 0xc7d7a8b4L,
- 0x59b33d17L, 0x2eb40d81L, 0xb7bd5c3bL, 0xc0ba6cadL,
- 0xedb88320L, 0x9abfb3b6L, 0x03b6e20cL, 0x74b1d29aL,
- 0xead54739L, 0x9dd277afL, 0x04db2615L, 0x73dc1683L,
- 0xe3630b12L, 0x94643b84L, 0x0d6d6a3eL, 0x7a6a5aa8L,
- 0xe40ecf0bL, 0x9309ff9dL, 0x0a00ae27L, 0x7d079eb1L,
- 0xf00f9344L, 0x8708a3d2L, 0x1e01f268L, 0x6906c2feL,
- 0xf762575dL, 0x806567cbL, 0x196c3671L, 0x6e6b06e7L,
- 0xfed41b76L, 0x89d32be0L, 0x10da7a5aL, 0x67dd4accL,
- 0xf9b9df6fL, 0x8ebeeff9L, 0x17b7be43L, 0x60b08ed5L,
- 0xd6d6a3e8L, 0xa1d1937eL, 0x38d8c2c4L, 0x4fdff252L,
- 0xd1bb67f1L, 0xa6bc5767L, 0x3fb506ddL, 0x48b2364bL,
- 0xd80d2bdaL, 0xaf0a1b4cL, 0x36034af6L, 0x41047a60L,
- 0xdf60efc3L, 0xa867df55L, 0x316e8eefL, 0x4669be79L,
- 0xcb61b38cL, 0xbc66831aL, 0x256fd2a0L, 0x5268e236L,
- 0xcc0c7795L, 0xbb0b4703L, 0x220216b9L, 0x5505262fL,
- 0xc5ba3bbeL, 0xb2bd0b28L, 0x2bb45a92L, 0x5cb36a04L,
- 0xc2d7ffa7L, 0xb5d0cf31L, 0x2cd99e8bL, 0x5bdeae1dL,
- 0x9b64c2b0L, 0xec63f226L, 0x756aa39cL, 0x026d930aL,
- 0x9c0906a9L, 0xeb0e363fL, 0x72076785L, 0x05005713L,
- 0x95bf4a82L, 0xe2b87a14L, 0x7bb12baeL, 0x0cb61b38L,
- 0x92d28e9bL, 0xe5d5be0dL, 0x7cdcefb7L, 0x0bdbdf21L,
- 0x86d3d2d4L, 0xf1d4e242L, 0x68ddb3f8L, 0x1fda836eL,
- 0x81be16cdL, 0xf6b9265bL, 0x6fb077e1L, 0x18b74777L,
- 0x88085ae6L, 0xff0f6a70L, 0x66063bcaL, 0x11010b5cL,
- 0x8f659effL, 0xf862ae69L, 0x616bffd3L, 0x166ccf45L,
- 0xa00ae278L, 0xd70dd2eeL, 0x4e048354L, 0x3903b3c2L,
- 0xa7672661L, 0xd06016f7L, 0x4969474dL, 0x3e6e77dbL,
- 0xaed16a4aL, 0xd9d65adcL, 0x40df0b66L, 0x37d83bf0L,
- 0xa9bcae53L, 0xdebb9ec5L, 0x47b2cf7fL, 0x30b5ffe9L,
- 0xbdbdf21cL, 0xcabac28aL, 0x53b39330L, 0x24b4a3a6L,
- 0xbad03605L, 0xcdd70693L, 0x54de5729L, 0x23d967bfL,
- 0xb3667a2eL, 0xc4614ab8L, 0x5d681b02L, 0x2a6f2b94L,
- 0xb40bbe37L, 0xc30c8ea1L, 0x5a05df1bL, 0x2d02ef8dL
- };
-
- #endif
-
- static U32 hashCRC32( const void* data, std::size_t size ){
- U32 crc;
- crc = CRC32_INIT_VALUE;
- const U8 *buf = (const U8 *)data;
-
- while(size--)
- crc = crctable32[ ( crc ^ ( *buf++ ) ) & 0xff ] ^ ( crc >> 8 );
-
- crc ^= CRC32_XOR_VALUE;
-
- return crc;
- }
-
- static U16 hashBSD( const void* data, std::size_t size ){
- U32 checksum = 0;
- const U8* buf = (const U8*)data;
-
- while(size--){
- checksum = (checksum >> 1) + ((checksum & 1) << 15);
- checksum = (checksum + *buf++) & 0xffff;
- }
-
- return checksum;
- }
-
- }
- namespace Mocha{
-
- static const U32 _prefix_mask[] = { 0x80, 0xE0, 0xF0, 0xF8 };
- static const U32 _prefix_value[] = { 0x00, 0xC0, 0xE0, 0xF0 };
- static const U32 _content_mask[] = { 0x7F, 0x1F, 0x0F, 0x07 };
- static const U32 _char_bytes[] = { 1, 2, 2, 3 };
-
- static inline int _utf8char_class( const C8* ch ){
- const C8 c = *ch;
-
- for(int i=0;i<4;i++){
- if( (c & _prefix_mask[i]) == _prefix_value[i] )
- return i;
- }
-
- return -1;
- }
-
- static inline std::size_t _utf8char_bytes( const C8* ch ){
- const int index = _utf8char_class(ch);
- if(index<0)
- return 0;
-
- return _char_bytes[ index ];
- }
-
- static inline U32 _utf8char_value( const C8* ch ){
- int index = _utf8char_class(ch);
- if(index<0)
- return UTF8String::BADCODE;
-
- int i=0;
- U32 result = ch[i++] & _content_mask[index];
-
- while(index--)
- result = (result << 6) | (ch[i++] & 0x3F);
-
- return result;
- }
-
- // MARK: Public
-
- U32 UTF8String::firstChar( const C8* str ){
- return _utf8char_value(str);
- }
-
- std::size_t UTF8String::firstCharBytes( const C8* str ){
- return _utf8char_bytes(str);
- }
-
- std::size_t UTF8String::byteLength( const C8* str ){
- const C8 *s;
- for (s = str; *s; ++s);
- return (s - str);
- }
-
- std::size_t UTF8String::charLength( const C8* str ){
- std::size_t result = 0;
-
- for(const C8* p = str; *p; ){
-
- const int index = _utf8char_class(p);
- if(index<0)
- break;
-
- result++;
-
- p += _char_bytes[index];
- }
-
- return result;
- }
-
- std::size_t UTF8String::copy( C8* dst, const C8* src, std::size_t siz ){
- C8* d = dst;
- const C8* s = src;
- std::size_t n = siz;
-
- /* Copy as many bytes as will fit */
- if (n != 0 && --n != 0) {
- do {
- if ((*d++ = *s++) == 0)
- break;
- } while (--n != 0);
- }
-
- /* Not enough room in dst, add NUL and traverse rest of src */
- if (n == 0) {
- if (siz != 0)
- *d = 0; /* NUL-terminate dst */
- while (*s++)
- ;
- }
-
- return (s - src - 1);
- /* count does not include NUL */
- }
-
- std::size_t UTF8String::concate
- ( C8* dst, const C8* src, std::size_t siz )
- {
- C8* d = dst;
- const C8* s = src;
- std::size_t n = siz, dlen;
-
- /* Find the end of dst and adjust bytes left but don't go past end */
- while (n-- != 0 && *d != 0)
- d++;
- dlen = d - dst;
- n = siz - dlen;
-
- if (n == 0)
- return(dlen + byteLength(s));
- while (*s != 0) {
- if (n != 1) {
- *d++ = *s;
- n--;
- }
- s++;
- }
- *d = 0;
-
- return (dlen + (s - src));
- /* count does not include NUL */
- }
-
- const C8* UTF8String::findFirstChar( const C8* str, C8 ch ){
- C8 c = ch;
- const C8*p = str;
- for (;; ++p) {
- if (*p == c)
- return (p);
- if (*p == 0)
- return (NULL);
- }
- /* NOTREACHED */
- return NULL;
- }
-
- const C8* UTF8String::findFirstChar( const C8* str, const C8* str2 ){
- const C8 *scanp;
- int c, sc;
-
- while ((c = *str++) != 0) {
- for (scanp = str2; (sc = *scanp++) != 0;)
- if (sc == c)
- return (str - 1);
- }
- return (NULL);
- }
-
- const C8* UTF8String::findLastChar( const C8* str, C8 ch ){
- C8 c = ch;
- const C8*p = str;
- for (const C8* save = NULL;; ++p){
- if (*p == c)
- save = p;
- if (*p == 0)
- return (save);
- }
- /* NOTREACHED */
- return NULL;
- }
-
- const C8* UTF8String::findStr( const C8* str, const C8* pat ){
- C8 c, sc;
- std::size_t len;
-
- if ((c = *pat++) != 0) {
- len = byteLength(pat);
- do {
- do {
- if ((sc = *str++) == 0)
- return (NULL);
- } while (sc != c);
- } while (compare(str, pat, len) != 0);
- str--;
- }
- return (str);
- }
-
- int UTF8String::compare( const C8* s1, const C8* s2, std::size_t n ){
- if (n == 0)
- return (0);
- do {
- if (*s1 != *s2++)
- return (*(const unsigned C8 *)s1 - *(const unsigned C8 *)(s2-1));
- if (*s1++ == 0)
- break;
- } while (--n != 0);
- return (0);
- }
-
- int UTF8String::compare( const C8* s1, const C8* s2 ){
- while (*s1 == *s2++)
- if (*s1++ == 0)
- return (0);
- return (*(const unsigned C8 *)s1 - *(const unsigned C8 *)--s2);
- }
-
- C8* UTF8String::token( C8* s, const C8* delim, C8** last ){
- C8 *spanp, *tok;
- int c, sc;
-
- if (s == NULL && (s = *last) == NULL)
- return (NULL);
-
- /*
- * Skip (span) leading delimiters (s += strspn(s, delim), sort of).
- */
- cont:
- c = *s++;
- for (spanp = const_cast<C8*>(delim); (sc = *spanp++) != 0;) {
- if (c == sc)
- goto cont;
- }
-
- if (c == 0) { /* no non-delimiter characters */
- *last = NULL;
- return (NULL);
- }
- tok = s - 1;
-
- /*
- * Scan token (scan for delimiters: s += strcspn(s, delim), sort of).
- * Note that delim must have one NUL; we stop if we see that, too.
- */
- for (;;) {
- c = *s++;
- spanp = const_cast<C8*>(delim);
- do {
- if ((sc = *spanp++) == c) {
- if (c == 0)
- s = NULL;
- else
- s[-1] = 0;
- *last = s;
- return (tok);
- }
- } while (sc != 0);
- }
- /* NOTREACHED */
- return NULL;
- }
-
- U32 UTF8String::hash( const C8* s ){
- return hashCRC32( s, byteLength(s) );
- }
-
- }