diff options
Diffstat (limited to 'engines/sludge/CommonCode/utf8.cpp')
| -rw-r--r-- | engines/sludge/CommonCode/utf8.cpp | 555 |
1 files changed, 0 insertions, 555 deletions
diff --git a/engines/sludge/CommonCode/utf8.cpp b/engines/sludge/CommonCode/utf8.cpp deleted file mode 100644 index 291bef4fb9..0000000000 --- a/engines/sludge/CommonCode/utf8.cpp +++ /dev/null @@ -1,555 +0,0 @@ -/* ScummVM - Graphic Adventure Engine - * - * ScummVM is the legal property of its developers, whose names - * are too numerous to list here. Please refer to the COPYRIGHT - * file distributed with this source distribution. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * - */ -/* - Basic UTF-8 manipulation routines - by Jeff Bezanson - placed in the public domain Fall 2005 - - This code is designed to provide the utilities you need to manipulate - UTF-8 as an internal string encoding. These functions do not perform the - error checking normally needed when handling UTF-8 data, so if you happen - to be from the Unicode Consortium you will want to flay me alive. - I do this because error checking can be performed at the boundaries (I/O), - with these routines reserved for higher performance on data known to be - valid. -*/ - -#include "common/debug.h" - -#include "sludge/CommonCode/utf8.h" - -static const uint32 offsetsFromUTF8[6] = { - 0x00000000UL, 0x00003080UL, 0x000E2080UL, - 0x03C82080UL, 0xFA082080UL, 0x82082080UL -}; - -static const char trailingBytesForUTF8[256] = { - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 -}; - -/* returns length of next utf-8 sequence */ -int u8_seqlen(char *s) -{ - return trailingBytesForUTF8[(unsigned int)(unsigned char)s[0]] + 1; -} - -/* conversions without error checking - only works for valid UTF-8, i.e. no 5- or 6-byte sequences - srcsz = source size in bytes, or -1 if 0-terminated - sz = dest size in # of wide characters - - returns # characters converted - dest will always be L'\0'-terminated, even if there isn't enough room - for all the characters. - if sz = srcsz+1 (i.e. 4*srcsz+4 bytes), there will always be enough space. -*/ -int u8_toucs(uint32 *dest, int sz, char *src, int srcsz) -{ - uint32 ch; - char *src_end = src + srcsz; - int nb; - int i=0; - - while (i < sz-1) { - nb = trailingBytesForUTF8[(unsigned char)*src]; - if (srcsz == -1) { - if (*src == 0) - goto done_toucs; - } - else { - if (src + nb >= src_end) - goto done_toucs; - } - ch = 0; - switch (nb) { - /* these fall through deliberately */ - case 3: ch += (unsigned char)*src++; ch <<= 6; - case 2: ch += (unsigned char)*src++; ch <<= 6; - case 1: ch += (unsigned char)*src++; ch <<= 6; - case 0: ch += (unsigned char)*src++; - } - ch -= offsetsFromUTF8[nb]; - dest[i++] = ch; - } - done_toucs: - dest[i] = 0; - return i; -} - -/* srcsz = number of source characters, or -1 if 0-terminated - sz = size of dest buffer in bytes - - returns # characters converted - dest will only be '\0'-terminated if there is enough space. this is - for consistency; imagine there are 2 bytes of space left, but the next - character requires 3 bytes. in this case we could NUL-terminate, but in - general we can't when there's insufficient space. therefore this function - only NUL-terminates if all the characters fit, and there's space for - the NUL as well. - the destination string will never be bigger than the source string. -*/ -int u8_toutf8(char *dest, int sz, uint32 *src, int srcsz) -{ - uint32 ch; - int i = 0; - char *dest_end = dest + sz; - - while (srcsz<0 ? src[i]!=0 : i < srcsz) { - ch = src[i]; - if (ch < 0x80) { - if (dest >= dest_end) - return i; - *dest++ = (char)ch; - } - else if (ch < 0x800) { - if (dest >= dest_end-1) - return i; - *dest++ = (ch>>6) | 0xC0; - *dest++ = (ch & 0x3F) | 0x80; - } - else if (ch < 0x10000) { - if (dest >= dest_end-2) - return i; - *dest++ = (ch>>12) | 0xE0; - *dest++ = ((ch>>6) & 0x3F) | 0x80; - *dest++ = (ch & 0x3F) | 0x80; - } - else if (ch < 0x110000) { - if (dest >= dest_end-3) - return i; - *dest++ = (ch>>18) | 0xF0; - *dest++ = ((ch>>12) & 0x3F) | 0x80; - *dest++ = ((ch>>6) & 0x3F) | 0x80; - *dest++ = (ch & 0x3F) | 0x80; - } - i++; - } - if (dest < dest_end) - *dest = '\0'; - return i; -} - -int u8_wc_toutf8(char *dest, uint32 ch) -{ - if (ch < 0x80) { - dest[0] = (char)ch; - return 1; - } - if (ch < 0x800) { - dest[0] = (ch>>6) | 0xC0; - dest[1] = (ch & 0x3F) | 0x80; - return 2; - } - if (ch < 0x10000) { - dest[0] = (ch>>12) | 0xE0; - dest[1] = ((ch>>6) & 0x3F) | 0x80; - dest[2] = (ch & 0x3F) | 0x80; - return 3; - } - if (ch < 0x110000) { - dest[0] = (ch>>18) | 0xF0; - dest[1] = ((ch>>12) & 0x3F) | 0x80; - dest[2] = ((ch>>6) & 0x3F) | 0x80; - dest[3] = (ch & 0x3F) | 0x80; - return 4; - } - return 0; -} - -/* charnum => byte offset */ -int u8_offset(char *str, int charnum) -{ - int offs=0; - - while (charnum > 0 && str[offs]) { - (void)(isutf(str[++offs]) || isutf(str[++offs]) || - isutf(str[++offs]) || ++offs); - charnum--; - } - return offs; -} - -/* byte offset => charnum */ -int u8_charnum(char *s, int offset) -{ - int charnum = 0, offs=0; - - while (offs < offset && s[offs]) { - (void)(isutf(s[++offs]) || isutf(s[++offs]) || - isutf(s[++offs]) || ++offs); - charnum++; - } - return charnum; -} - -/* number of characters */ -int u8_strlen(char *s) -{ - int count = 0; - int i = 0; - - while (u8_nextchar(s, &i) != 0) - count++; - - return count; -} - -/* reads the next utf-8 sequence out of a string, updating an index */ -uint32 u8_nextchar(const char *s, int *i) -{ - uint32 ch = 0; - int sz = 0; - - do { - ch <<= 6; - ch += (unsigned char)s[(*i)++]; - sz++; - } while (s[*i] && !isutf(s[*i])); - ch -= offsetsFromUTF8[sz-1]; - - return ch; -} - -void u8_inc(char *s, int *i) -{ - (void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) || - isutf(s[++(*i)]) || ++(*i)); -} - -void u8_dec(char *s, int *i) -{ - (void)(isutf(s[--(*i)]) || isutf(s[--(*i)]) || - isutf(s[--(*i)]) || --(*i)); -} - -int octal_digit(char c) -{ - return (c >= '0' && c <= '7'); -} - -int hex_digit(char c) -{ - return ((c >= '0' && c <= '9') || - (c >= 'A' && c <= 'F') || - (c >= 'a' && c <= 'f')); -} - -/* assumes that src points to the character after a backslash - returns number of input characters processed */ -int u8_read_escape_sequence(char *str, uint32 *dest) -{ - uint32 ch; - char digs[9]="\0\0\0\0\0\0\0\0"; - int dno=0, i=1; - - ch = (uint32)str[0]; /* take literal character */ - if (str[0] == 'n') - ch = L'\n'; - else if (str[0] == 't') - ch = L'\t'; - else if (str[0] == 'r') - ch = L'\r'; - else if (str[0] == 'b') - ch = L'\b'; - else if (str[0] == 'f') - ch = L'\f'; - else if (str[0] == 'v') - ch = L'\v'; - else if (str[0] == 'a') - ch = L'\a'; - else if (octal_digit(str[0])) { - i = 0; - do { - digs[dno++] = str[i++]; - } while (octal_digit(str[i]) && dno < 3); - ch = strtol(digs, NULL, 8); - } - else if (str[0] == 'x') { - while (hex_digit(str[i]) && dno < 2) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - else if (str[0] == 'u') { - while (hex_digit(str[i]) && dno < 4) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - else if (str[0] == 'U') { - while (hex_digit(str[i]) && dno < 8) { - digs[dno++] = str[i++]; - } - if (dno > 0) - ch = strtol(digs, NULL, 16); - } - *dest = ch; - - return i; -} - -/* convert a string with literal \uxxxx or \Uxxxxxxxx characters to UTF-8 - example: u8_unescape(mybuf, 256, "hello\\u220e") - note the double backslash is needed if called on a C string literal */ -int u8_unescape(char *buf, int sz, char *src) -{ - int c=0, amt; - uint32 ch; - char temp[4]; - - while (*src && c < sz) { - if (*src == '\\') { - src++; - amt = u8_read_escape_sequence(src, &ch); - } - else { - ch = (uint32)*src; - amt = 1; - } - src += amt; - amt = u8_wc_toutf8(temp, ch); - if (amt > sz-c) - break; - memcpy(&buf[c], temp, amt); - c += amt; - } - if (c < sz) - buf[c] = '\0'; - return c; -} - -int u8_escape_wchar(char *buf, int sz, uint32 ch) -{ - if (ch == L'\n') - return snprintf(buf, sz, "\\n"); - else if (ch == L'\t') - return snprintf(buf, sz, "\\t"); - else if (ch == L'\r') - return snprintf(buf, sz, "\\r"); - else if (ch == L'\b') - return snprintf(buf, sz, "\\b"); - else if (ch == L'\f') - return snprintf(buf, sz, "\\f"); - else if (ch == L'\v') - return snprintf(buf, sz, "\\v"); - else if (ch == L'\a') - return snprintf(buf, sz, "\\a"); - else if (ch == L'\\') - return snprintf(buf, sz, "\\\\"); - else if (ch < 32 || ch == 0x7f) - return snprintf(buf, sz, "\\x%hhX", (unsigned char)ch); - else if (ch > 0xFFFF) - return snprintf(buf, sz, "\\U%.8X", (uint32)ch); - else if (ch >= 0x80 && ch <= 0xFFFF) - return snprintf(buf, sz, "\\u%.4hX", (unsigned short)ch); - - return snprintf(buf, sz, "%c", (char)ch); -} - -int u8_escape(char *buf, int sz, char *src, int escape_quotes) -{ - int c=0, i=0, amt; - - while (src[i] && c < sz) { - if (escape_quotes && src[i] == '"') { - amt = snprintf(buf, sz - c, "\\\""); - i++; - } - else { - amt = u8_escape_wchar(buf, sz - c, u8_nextchar(src, &i)); - } - c += amt; - buf += amt; - } - if (c < sz) - *buf = '\0'; - return c; -} - -char *u8_strchr(char *s, uint32 ch, int *charn) -{ - int i = 0, lasti=0; - uint32 c; - - *charn = 0; - while (s[i]) { - c = u8_nextchar(s, &i); - if (c == ch) { - return &s[lasti]; - } - lasti = i; - (*charn)++; - } - return NULL; -} - -char *u8_memchr(char *s, uint32 ch, size_t sz, int *charn) -{ - int i = 0, lasti=0; - uint32 c; - int csz; - - *charn = 0; - while (i < sz) { - c = csz = 0; - do { - c <<= 6; - c += (unsigned char)s[i++]; - csz++; - } while (i < sz && !isutf(s[i])); - c -= offsetsFromUTF8[csz-1]; - - if (c == ch) { - return &s[lasti]; - } - lasti = i; - (*charn)++; - } - return NULL; -} - -int u8_is_locale_utf8(char *locale) -{ - /* this code based on libutf8 */ - const char* cp = locale; - - for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) { - if (*cp == '.') { - const char* encoding = ++cp; - for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) - ; - if ((cp-encoding == 5 && !strncmp(encoding, "UTF-8", 5)) - || (cp-encoding == 4 && !strncmp(encoding, "utf8", 4))) - return 1; /* it's UTF-8 */ - break; - } - } - return 0; -} - -int u8_vprintf(char *fmt, va_list ap) -{ - int cnt, sz=0; - char *buf; - uint32 *wcs; - - sz = 512; - buf = (char*)alloca(sz); - try_print: - cnt = vsnprintf(buf, sz, fmt, ap); - if (cnt >= sz) { - buf = (char*)alloca(cnt - sz + 1); - sz = cnt + 1; - goto try_print; - } - wcs = (uint32*)alloca((cnt+1) * sizeof(uint32)); - cnt = u8_toucs(wcs, cnt+1, buf, cnt); - debug("%ls", (wchar_t*)wcs); - return cnt; -} - -int u8_printf(char *fmt, ...) -{ - int cnt; - va_list args; - - va_start(args, fmt); - - cnt = u8_vprintf(fmt, args); - - va_end(args); - return cnt; -} - - -// This function checks a string to see if it's valid UTF-8 -// It returns true if the string is valid. -// -// based on the valid_utf8 routine from the PCRE library by Philip Hazel - -int u8_isvalid(const char *str) -{ - const unsigned char *p; - unsigned char c; - int ab; - - for (p = (unsigned char*)str; *p; p++) { - c = *p; - if (c < 128) - continue; - if ((c & 0xc0) != 0xc0) - return 0; - ab = trailingBytesForUTF8[c]; - - p++; - /* Check top bits in the second byte */ - if ((*p & 0xc0) != 0x80) - return 0; - - /* Check for overlong sequences for each different length */ - switch (ab) { - /* Check for xx00 000x */ - case 1: - if ((c & 0x3e) == 0) return 0; - continue; /* We know there aren't any more bytes to check */ - - /* Check for 1110 0000, xx0x xxxx */ - case 2: - if (c == 0xe0 && (*p & 0x20) == 0) return 0; - break; - - /* Check for 1111 0000, xx00 xxxx */ - case 3: - if (c == 0xf0 && (*p & 0x30) == 0) return 0; - break; - - /* Check for 1111 1000, xx00 0xxx */ - case 4: - if (c == 0xf8 && (*p & 0x38) == 0) return 0; - break; - - /* Check for leading 0xfe or 0xff, - and then for 1111 1100, xx00 00xx */ - case 5: - if (c == 0xfe || c == 0xff || - (c == 0xfc && (*p & 0x3c) == 0)) return 0; - break; - } - - /* Check for valid bytes after the 2nd, if any; all must start 10 */ - while (--ab > 0) { - if ((*(++p) & 0xc0) != 0x80) return 0; - } - } - - return 1; -} - |