diff options
Diffstat (limited to 'src/xlibi18n/lcCT.c')
| -rw-r--r-- | src/xlibi18n/lcCT.c | 1581 |
1 files changed, 983 insertions, 598 deletions
diff --git a/src/xlibi18n/lcCT.c b/src/xlibi18n/lcCT.c index 5dd2ddcc..fcaca229 100644 --- a/src/xlibi18n/lcCT.c +++ b/src/xlibi18n/lcCT.c @@ -31,70 +31,107 @@ * Modifier: Takanori Tateno FUJITSU LIMITED * */ +/* + * 2000 + * Modifier: Ivan Pascal The XFree86 Project + * Modifier: Bruno Haible The XFree86 Project + */ +/* $XFree86: xc/lib/X11/lcCT.c,v 3.27 2002/10/08 23:31:35 dawes Exp $ */ #include "Xlibint.h" #include "XlcPubI.h" #include <X11/Xos.h> #include <stdio.h> -typedef struct _StateRec { - XlcCharSet charset; - XlcCharSet GL_charset; - XlcCharSet GR_charset; - XlcCharSet ext_seg_charset; - int ext_seg_left; -} StateRec, *State; +/* ====================== Built-in Character Sets ====================== */ + +/* + * Static representation of a character set that can be used in Compound Text. + */ typedef struct _CTDataRec { - char *name; - char *encoding; /* Compound Text encoding */ + const char *name; + const char *ct_sequence; /* Compound Text encoding, ESC sequence */ } CTDataRec, *CTData; -typedef struct _CTInfoRec { - XlcCharSet charset; - int encoding_len; - char *encoding; /* Compound Text encoding */ - int ext_segment_len; - char *ext_segment; /* extended segment */ - struct _CTInfoRec *next; -} CTInfoRec, *CTInfo; - static CTDataRec default_ct_data[] = { - { "ISO8859-1:GL", "\033(B" }, - { "ISO8859-1:GR", "\033-A" }, - { "ISO8859-2:GR", "\033-B" }, - { "ISO8859-3:GR", "\033-C" }, - { "ISO8859-4:GR", "\033-D" }, - { "ISO8859-7:GR", "\033-F" }, - { "ISO8859-6:GR", "\033-G" }, - { "ISO8859-8:GR", "\033-H" }, - { "ISO8859-5:GR", "\033-L" }, - { "ISO8859-9:GR", "\033-M" }, - { "ISO8859-10:GR", "\033-V" }, - { "JISX0201.1976-0:GL", "\033(J" }, - { "JISX0201.1976-0:GR", "\033)I" }, - - { "GB2312.1980-0:GL", "\033$(A" }, - { "GB2312.1980-0:GR", "\033$)A" }, - { "JISX0208.1983-0:GL", "\033$(B" }, - { "JISX0208.1983-0:GR", "\033$)B" }, - { "KSC5601.1987-0:GL", "\033$(C" }, - { "KSC5601.1987-0:GR", "\033$)C" }, -#ifdef notdef - { "JISX0212.1990-0:GL", "\033$(D" }, - { "JISX0212.1990-0:GR", "\033$)D" }, - { "CNS11643.1986-1:GL", "\033$(G" }, - { "CNS11643.1986-1:GR", "\033$)G" }, - { "CNS11643.1986-2:GL", "\033$(H" }, - { "CNS11643.1986-2:GR", "\033$)H" }, + /* */ + /* X11 registry name MIME name ISO-IR ESC sequence */ + /* */ + + /* Registered character sets with one byte per character */ + { "ISO8859-1:GL", /* US-ASCII 6 */ "\033(B" }, + { "ISO8859-1:GR", /* ISO-8859-1 100 */ "\033-A" }, + { "ISO8859-2:GR", /* ISO-8859-2 101 */ "\033-B" }, + { "ISO8859-3:GR", /* ISO-8859-3 109 */ "\033-C" }, + { "ISO8859-4:GR", /* ISO-8859-4 110 */ "\033-D" }, + { "ISO8859-5:GR", /* ISO-8859-5 144 */ "\033-L" }, + { "ISO8859-6:GR", /* ISO-8859-6 127 */ "\033-G" }, + { "ISO8859-7:GR", /* ISO-8859-7 126 */ "\033-F" }, + { "ISO8859-8:GR", /* ISO-8859-8 138 */ "\033-H" }, + { "ISO8859-9:GR", /* ISO-8859-9 148 */ "\033-M" }, + { "ISO8859-10:GR", /* ISO-8859-10 157 */ "\033-V" }, + { "ISO8859-11:GR", /* ISO-8859-11 166 */ "\033-T" }, + { "ISO8859-13:GR", /* ISO-8859-13 179 */ "\033-Y" }, + { "ISO8859-14:GR", /* ISO-8859-14 199 */ "\033-_" }, + { "ISO8859-15:GR", /* ISO-8859-15 203 */ "\033-b" }, + { "ISO8859-16:GR", /* ISO-8859-16 226 */ "\033-f" }, + { "JISX0201.1976-0:GL", /* ISO-646-JP 14 */ "\033(J" }, + { "JISX0201.1976-0:GR", "\033)I" }, +#if 0 + { "TIS620-0:GR", /* TIS-620 166 */ "\033-T" }, #endif - { "TIS620.2533-1:GR", "\033-T"}, - { "ISO10646-1", "\033%B"}, - /* Non-Standard Character Set Encodings */ - { "KOI8-R:GR", "\033%/1\200\210koi8-r\002"}, - { "FCD8859-15:GR", "\033%/1\200\213fcd8859-15\002"}, -} ; + + /* Registered character sets with two byte per character */ + { "GB2312.1980-0:GL", /* GB_2312-80 58 */ "\033$(A" }, + { "GB2312.1980-0:GR", /* GB_2312-80 58 */ "\033$)A" }, + { "JISX0208.1983-0:GL", /* JIS_X0208-1983 87 */ "\033$(B" }, + { "JISX0208.1983-0:GR", /* JIS_X0208-1983 87 */ "\033$)B" }, + { "JISX0208.1990-0:GL", /* JIS_X0208-1990 168 */ "\033$(B" }, + { "JISX0208.1990-0:GR", /* JIS_X0208-1990 168 */ "\033$)B" }, + { "JISX0212.1990-0:GL", /* JIS_X0212-1990 159 */ "\033$(D" }, + { "JISX0212.1990-0:GR", /* JIS_X0212-1990 159 */ "\033$)D" }, + { "KSC5601.1987-0:GL", /* KS_C_5601-1987 149 */ "\033$(C" }, + { "KSC5601.1987-0:GR", /* KS_C_5601-1987 149 */ "\033$)C" }, + { "CNS11643.1986-1:GL", /* CNS 11643-1992 pl.1 171 */ "\033$(G" }, + { "CNS11643.1986-1:GR", /* CNS 11643-1992 pl.1 171 */ "\033$)G" }, + { "CNS11643.1986-2:GL", /* CNS 11643-1992 pl.2 172 */ "\033$(H" }, + { "CNS11643.1986-2:GR", /* CNS 11643-1992 pl.2 172 */ "\033$)H" }, + { "CNS11643.1992-3:GL", /* CNS 11643-1992 pl.3 183 */ "\033$(I" }, + { "CNS11643.1992-3:GR", /* CNS 11643-1992 pl.3 183 */ "\033$)I" }, + { "CNS11643.1992-4:GL", /* CNS 11643-1992 pl.4 184 */ "\033$(J" }, + { "CNS11643.1992-4:GR", /* CNS 11643-1992 pl.4 184 */ "\033$)J" }, + { "CNS11643.1992-5:GL", /* CNS 11643-1992 pl.5 185 */ "\033$(K" }, + { "CNS11643.1992-5:GR", /* CNS 11643-1992 pl.5 185 */ "\033$)K" }, + { "CNS11643.1992-6:GL", /* CNS 11643-1992 pl.6 186 */ "\033$(L" }, + { "CNS11643.1992-6:GR", /* CNS 11643-1992 pl.6 186 */ "\033$)L" }, + { "CNS11643.1992-7:GL", /* CNS 11643-1992 pl.7 187 */ "\033$(M" }, + { "CNS11643.1992-7:GR", /* CNS 11643-1992 pl.7 187 */ "\033$)M" }, + + /* Registered encodings with a varying number of bytes per character */ + { "ISO10646-1", /* UTF-8 196 */ "\033%G" }, + + /* Encodings without ISO-IR assigned escape sequence must be + defined in XLC_LOCALE files, using "\033%/1" or "\033%/2". */ + + /* Backward compatibility with XFree86 3.x */ + { "ISO8859-14:GR", "\033%/1" }, + { "ISO8859-15:GR", "\033%/1" }, + /* For use by utf8 -> ctext */ + { "BIG5-0:GLGR", "\033%/2"}, + /* used by Emacs, but not backed by ISO-IR */ + { "BIG5-E0:GL", "\033$(0" }, + { "BIG5-E0:GR", "\033$)0" }, + { "BIG5-E1:GL", "\033$(1" }, + { "BIG5-E1:GR", "\033$)1" }, + +}; + +/* We represent UTF-8 as an XlcGLGR charset, not in extended segments. */ +#define UTF8_IN_EXTSEQ 0 + +/* ======================= Parsing ESC Sequences ======================= */ #define XctC0 0x0000 #define XctHT 0x0009 @@ -104,6 +141,7 @@ static CTDataRec default_ct_data[] = #define XctC1 0x0080 #define XctCSI 0x009b #define XctGR 0x00a0 +#define XctSTX 0x0002 #define XctCntrlFunc 0x0023 #define XctMB 0x0024 @@ -122,268 +160,282 @@ static CTDataRec default_ct_data[] = #define XctGL94MB 0x2428 #define XctGR94MB 0x2429 #define XctExtSeg 0x252f -#define XctOtherSeg 0x2f00 - -#define XctESCSeq 0x1b00 -#define XctCSISeq 0x9b00 - -#define SKIP_I(str) while (*(str) >= 0x20 && *(str) <= 0x2f) (str)++; -#define SKIP_P(str) while (*(str) >= 0x30 && *(str) <= 0x3f) (str)++; - -typedef struct { - XlcSide side; - int char_size; - int set_size; - int ext_seg_length; - int version; - CTInfo ct_info; -} CTParseRec, *CTParse; - -CTDataRec *default_ct_data_list() -{ - return(default_ct_data); -} - -size_t default_ct_data_list_num() -{ - size_t num = sizeof(default_ct_data) / sizeof(CTDataRec); - return(num); -} - -static CTInfo ct_list = NULL; - -static CTInfo -_XlcGetCTInfoFromEncoding(encoding, length) - register char *encoding; - register int length; -{ - register CTInfo ct_info; - - for (ct_info = ct_list; ct_info; ct_info = ct_info->next) { - if (length >= ct_info->encoding_len) { - if (ct_info->ext_segment) { - if (!strncmp(ct_info->encoding, encoding, 4) && - !strncmp(ct_info->ext_segment, encoding + 6, - ct_info->ext_segment_len)) - return ct_info; - } else if (!strncmp(ct_info->encoding, encoding, - ct_info->encoding_len)) { - return ct_info; - } - } - } - - return (CTInfo) NULL; -} +#define XctReturn 0x2540 +/* + * Parses the header of a Compound Text segment, i.e. the charset designator. + * The string starts at *text and has *length bytes. + * Return value is one of: + * 0 (no valid charset designator), + * XctGL94, XctGR94, XctGR96, XctGL94MB, XctGR94MB, + * XctLeftToRight, XctRightToLeft, XctDirectionEnd, + * XctExtSeg, XctOtherCoding, XctReturn, XctIgnoreExt, XctNotIgnoreExt. + * If the return value is not 0, *text is incremented and *length decremented, + * to point past the charset designator. If the return value is one of + * XctGL94, XctGR94, XctGR96, XctGL94MB, XctGR94MB, + * XctExtSeg, XctOtherCoding, XctIgnoreExt, XctNotIgnoreExt, + * *final_byte is set to the "final byte" of the charset designator. + */ static unsigned int -_XlcParseCT(parse, text, length) - register CTParse parse; - char **text; - int *length; +_XlcParseCT( + const char **text, + int *length, + unsigned char *final_byte) { unsigned int ret = 0; unsigned char ch; - register unsigned char *str = (unsigned char *) *text; + const unsigned char *str = (const unsigned char *) *text; - bzero((char *) parse, sizeof(CTParseRec)); + *final_byte = 0; + if (*length < 1) + return 0; switch (ch = *str++) { - case XctESC: - if (*str == XctOtherCoding && *(str + 1) == XctNonStandard - && *(str + 2) >= 0x30 && *(str + 2) <= 0x3f && *length >= 6) { - - /* non-standard encodings */ - parse->side = XlcGLGR; - parse->set_size = 0; - str += 2; - if (*str <= 0x34) { - parse->char_size = *str - 0x30; - if (parse->char_size == 0) parse->char_size = 1; - ret = XctExtSeg; - parse->ct_info = _XlcGetCTInfoFromEncoding(*text, *length); - } else - ret = XctOtherSeg; - str++; - parse->ext_seg_length = (*str - 128) * 128 + *(str + 1) - 128; - str += 2; - - goto done; - } else if (*str == XctCntrlFunc && *length >= 4 && - *(str + 1) >= 0x20 && *(str + 1) <= 0x2f && - (*(str + 2) == XctIgnoreExt || - *(str + 2) == XctNotIgnoreExt)) { - - /* ignore extension or not */ - str++; - parse->version = *str++ - 0x20; - ret = *str++; - - goto done; - } - - if (*str == XctMB) { /* multiple-byte sets */ - parse->char_size = 2; - str++; - } else - parse->char_size = 1; - - switch (*str) { - case XctGL94: - parse->side = XlcGL; - parse->set_size = 94; - ret = (parse->char_size == 1) ? XctGL94 : XctGL94MB; - break; - case XctGR94: - parse->side = XlcGR; - parse->set_size = 94; - ret = (parse->char_size == 1) ? XctGR94 : XctGR94MB; - break; - case XctGR96: - if (parse->char_size == 1) { - parse->side = XlcGR; - parse->set_size = 96; - ret = XctGR96; - } - break; - } - if (ret) { - str++; - if (*str >= 0x24 && *str <= 0x2f) { /* non-standard */ - ret = 0; - str++; - } - } - - SKIP_I(str) - - if (ret && *str < 0x40) /* non-standard */ - ret = 0; - - if (*str < 0x30 || *str > 0x7e || (char *) str - *text >= *length) - break; - - if (ret == 0) - ret = XctESCSeq; - else { - if (parse->char_size == 2) { - if (*str >= 0x70) - parse->char_size = 4; - else if (*str >= 0x60) - parse->char_size = 3; - } - parse->ct_info = _XlcGetCTInfoFromEncoding(*text, *length); - } - str++; - goto done; - case XctCSI: + case XctESC: + if (*length < 2) + return 0; + switch (ch = *str++) { + case XctOtherCoding: /* % */ + if (*length < 3) + return 0; + ch = *str++; + if (ch == XctNonStandard) { /* / */ + if (*length < 4) + return 0; + ret = XctExtSeg; + ch = *str++; + } else if (ch == '@') { + ret = XctReturn; + } else { + ret = XctOtherCoding; + } + *final_byte = ch; + break; + + case XctCntrlFunc: /* # */ + if (*length < 4) + return 0; + *final_byte = *str++; + switch (*str++) { + case XctIgnoreExt: /* 0 */ + ret = XctIgnoreExt; + break; + case XctNotIgnoreExt: /* 1 */ + ret = XctNotIgnoreExt; + break; + default: + ret = 0; + break; + } + break; + + case XctMB: /* $ */ + if (*length < 4) + return 0; + ch = *str++; + switch (ch) { + case XctGL94: /* ( */ + ret = XctGL94MB; + break; + case XctGR94: /* ) */ + ret = XctGR94MB; + break; + default: + ret = 0; + break; + } + *final_byte = *str++; + break; + + case XctGL94: /* ( */ + if (*length < 3) + return 0; + ret = XctGL94; + *final_byte = *str++; + break; + case XctGR94: /* ) */ + if (*length < 3) + return 0; + ret = XctGR94; + *final_byte = *str++; + break; + case XctGR96: /* - */ + if (*length < 3) + return 0; + ret = XctGR96; + *final_byte = *str++; + break; + } + break; + case XctCSI: /* direction */ - if (*str == XctLeftToRight && *(str + 1) == XctDirection) { - ret = XctLeftToRight; - str += 2; - goto done; - } else if (*str == XctRightToLeft && *(str + 1) == XctDirection) { - ret = XctRightToLeft; - str += 2; - goto done; - } else if (*str == XctDirectionEnd) { - ret = XctDirectionEnd; - str++; - goto done; - } + if (*length < 2) + return 0; + switch (*str++) { + case XctLeftToRight: + if (*length < 3) + return 0; + if (*str++ == XctDirection) + ret = XctLeftToRight; + break; + case XctRightToLeft: + if (*length < 3) + return 0; + if (*str++ == XctDirection) + ret = XctRightToLeft; + break; + case XctDirectionEnd: + ret = XctDirectionEnd; + break; + } + break; + } - SKIP_P(str) - SKIP_I(str) + if (ret) { + *length -= (const char *) str - *text; + *text = (const char *) str; + } + return ret; +} - if (*str < 0x40 && *str > 0x7e) - break; +/* + * Fills into a freshly created XlcCharSet the fields that can be inferred + * from the ESC sequence. These are side, char_size, set_size. + * Returns True if the charset can be used with Compound Text. + * + * Used by _XlcCreateDefaultCharSet. + */ +Bool +_XlcParseCharSet( + XlcCharSet charset) +{ + unsigned int type; + unsigned char final_byte; + const char *ptr = charset->ct_sequence; + int length; + int char_size; + + if (*ptr == '\0') + return False; - ret = XctCSISeq; - str++; - goto done; - } + length = strlen(ptr); - if (ch & 0x80) { - if (ch < 0xa0) - ret = XctC1; - else - ret = XctGR; - } else { - if (ch == XctHT || ch == XctNL) - ret = ch; - else if (ch < 0x20) - ret = XctC0; - else - ret = XctGL; + type = _XlcParseCT(&ptr, &length, &final_byte); + + /* Check for validity and determine char_size. + char_size = 0 means varying number of bytes per character. */ + switch (type) { + case XctGL94: + case XctGR94: + case XctGR96: + char_size = 1; + break; + case XctGL94MB: + case XctGR94MB: + char_size = (final_byte < 0x60 ? 2 : final_byte < 0x70 ? 3 : 4); + break; + case XctExtSeg: + char_size = final_byte - '0'; + if (!(char_size >= 0 && char_size <= 4)) + return False; + break; + case XctOtherCoding: + char_size = 0; + break; + default: + return False; } - return ret; + charset->char_size = char_size; + + /* Fill in other values. */ + switch (type) { + case XctGL94: + case XctGL94MB: + charset->side = XlcGL; + charset->set_size = 94; + break; + case XctGR94: + case XctGR94MB: + charset->side = XlcGR; + charset->set_size = 94; + break; + case XctGR96: + charset->side = XlcGR; + charset->set_size = 96; + break; + case XctExtSeg: + case XctOtherCoding: + charset->side = XlcGLGR; + charset->set_size = 0; + break; + } + return True; +} -done: - *length -= (char *) str - *text; - *text = (char *) str; - return ret; -} +/* =============== Management of the List of Character Sets =============== */ -XlcCharSet -_XlcAddCT(name, encoding) - char *name; - char *encoding; -{ - CTInfo ct_info; +/* + * Representation of a character set that can be used for Compound Text, + * at run time. + * Note: This information is not contained in the XlcCharSet, because + * multiple ESC sequences may be used for the same XlcCharSet. + */ +typedef struct _CTInfoRec { XlcCharSet charset; - CTParseRec parse; - char *ct_ptr = encoding; - int length; + const char *ct_sequence; /* Compound Text ESC sequence */ unsigned int type; + unsigned char final_byte; + /* If type == XctExtSeg: */ + const char *ext_segment; /* extended segment name, then '\002' */ + int ext_segment_len; /* length of above, including final '\002' */ - length = strlen(encoding); + struct _CTInfoRec *next; +} CTInfoRec, *CTInfo; - switch (type = _XlcParseCT(&parse, &ct_ptr, &length)) { - case XctExtSeg: - case XctGL94: - case XctGL94MB: - case XctGR94: - case XctGR94MB: - case XctGR96: - if (parse.ct_info) /* existed */ - return parse.ct_info->charset; - break; - default: - return (XlcCharSet) NULL; - } +/* + * List of character sets that can be used for Compound Text, + * Includes all that are listed in default_ct_data, but more can be added + * at runtime through _XlcAddCT. + */ +static CTInfo ct_list = NULL; +static CTInfo *ct_list_end = &ct_list; - charset = _XlcCreateDefaultCharSet(name, encoding); - if (charset == NULL) - return (XlcCharSet) NULL; - _XlcAddCharSet(charset); +/* + * Returns a Compound Text info record for an ESC sequence. + * The first part of the ESC sequence has already been parsed into 'type' + * and 'final_byte'. The remainder starts at 'text', at least 'text_len' + * bytes (only used if type == XctExtSeg). + */ +static CTInfo +_XlcGetCTInfo( + unsigned int type, + unsigned char final_byte, + const char *text, + int text_len) +{ + CTInfo ct_info; - ct_info = (CTInfo) Xmalloc(sizeof(CTInfoRec)); - if (ct_info == NULL) - return (XlcCharSet) NULL; - - ct_info->charset = charset; - ct_info->encoding = charset->ct_sequence; - ct_info->encoding_len = strlen(ct_info->encoding); - if (type == XctExtSeg) { - ct_info->ext_segment = ct_info->encoding + 6; - ct_info->ext_segment_len = strlen(ct_info->ext_segment); - } else { - ct_info->ext_segment = NULL; - ct_info->ext_segment_len = 0; - } - ct_info->next = ct_list; - ct_list = ct_info; + for (ct_info = ct_list; ct_info; ct_info = ct_info->next) + if (ct_info->type == type + && ct_info->final_byte == final_byte + && (type != XctExtSeg + || (text_len >= ct_info->ext_segment_len + && memcmp(text, ct_info->ext_segment, + ct_info->ext_segment_len) == 0))) + return ct_info; - return charset; + return (CTInfo) NULL; } +/* Returns the Compound Text info for a given XlcCharSet. + Returns NULL if none is found. */ static CTInfo -_XlcGetCTInfoFromCharSet(charset) - register XlcCharSet charset; +_XlcGetCTInfoFromCharSet( + XlcCharSet charset) { - register CTInfo ct_info; + CTInfo ct_info; for (ct_info = ct_list; ct_info; ct_info = ct_info->next) if (ct_info->charset == charset) @@ -392,244 +444,445 @@ _XlcGetCTInfoFromCharSet(charset) return (CTInfo) NULL; } -Bool -_XlcParseCharSet(charset) - XlcCharSet charset; +/* Creates a new XlcCharSet, given its name (including side suffix) and + Compound Text ESC sequence (normally at most 4 bytes), and makes it + eligible for Compound Text processing. */ +XlcCharSet +_XlcAddCT( + const char *name, + const char *ct_sequence) { - CTParseRec parse; - char *ptr, *bufp, buf[BUFSIZ]; + CTInfo ct_info, existing_info; + XlcCharSet charset; + const char *ct_ptr; int length; + unsigned int type; + unsigned char final_byte; - if (charset->ct_sequence == NULL) - return False; - - ptr = charset->ct_sequence; - length = strlen(ptr); - - (void) _XlcParseCT(&parse, &ptr, &length); - - if (charset->name) { - charset->xrm_name = XrmStringToQuark(charset->name); - - if ((length = strlen (charset->name)) < sizeof buf) bufp = buf; - else bufp = Xmalloc (length + 1); - - if (bufp == NULL) return False; - strcpy(bufp, charset->name); - if ((ptr = strchr(bufp, ':'))) - *ptr = '\0'; - charset->xrm_encoding_name = XrmStringToQuark(bufp); - if (bufp != buf) Xfree (bufp); - charset->encoding_name = XrmQuarkToString(charset->xrm_encoding_name); + charset = _XlcGetCharSet(name); + if (charset != NULL) { + /* Even if the charset already exists, it is OK to register a second + Compound Text sequence for it. */ } else { - charset->xrm_name = 0; - charset->encoding_name = NULL; - charset->xrm_encoding_name = 0; + /* Attempt to create the charset. */ + charset = _XlcCreateDefaultCharSet(name, ct_sequence); + if (charset == NULL) + return (XlcCharSet) NULL; + _XlcAddCharSet(charset); } - charset->side = parse.side; - charset->char_size = parse.char_size; - charset->set_size = parse.set_size; + /* Allocate a CTinfo record. */ + length = strlen(ct_sequence); + ct_info = (CTInfo) Xmalloc(sizeof(CTInfoRec) + length+1); + if (ct_info == NULL) + return charset; - return True; -} + ct_info->charset = charset; + ct_info->ct_sequence = strcpy((char *) (ct_info + 1), ct_sequence); -static void init_converter(); + /* Parse the Compound Text sequence. */ + ct_ptr = ct_sequence; + type = _XlcParseCT(&ct_ptr, &length, &final_byte); -Bool -_XlcInitCTInfo() -{ - register XlcCharSet charset; - register CTData ct_data; - register int num; + ct_info->type = type; + ct_info->final_byte = final_byte; - if (ct_list == NULL) { - num = sizeof(default_ct_data) / sizeof(CTDataRec); - for (ct_data = default_ct_data; num-- > 0; ct_data++) { - charset = _XlcAddCT(ct_data->name, ct_data->encoding); - if (charset == NULL) - continue; - } - init_converter(); + switch (type) { + case XctGL94: + case XctGR94: + case XctGR96: + case XctGL94MB: + case XctGR94MB: + case XctOtherCoding: + ct_info->ext_segment = NULL; + ct_info->ext_segment_len = 0; + break; + case XctExtSeg: { + /* By convention, the extended segment name is the encoding_name + in lowercase. */ + const char *q = charset->encoding_name; + int n = strlen(q); + char *p; + + /* Ensure ct_info->ext_segment_len <= 0x3fff - 6. */ + if (n > 0x3fff - 6 - 1) { + Xfree(ct_info); + return charset; + } + p = (char *) Xmalloc(n+1); + if (p == NULL) { + Xfree(ct_info); + return charset; + } + ct_info->ext_segment = p; + ct_info->ext_segment_len = n+1; + for ( ; n > 0; p++, q++, n--) + *p = (*q >= 'A' && *q <= 'Z' ? *q - 'A' + 'a' : *q); + *p = XctSTX; + break; + } + default: + Xfree(ct_info); + return (XlcCharSet) NULL; } - return True; + /* Insert it into the list, if not already present. */ + existing_info = + _XlcGetCTInfo(type, ct_info->final_byte, + ct_info->ext_segment, ct_info->ext_segment_len); + if (existing_info == NULL) { + /* Insert it at the end. If there are duplicates CTinfo entries + for the same XlcCharSet, we want the first (standard) one to + override the second (user defined) one. */ + ct_info->next = *ct_list_end; + *ct_list_end = ct_info; + } else { + if (existing_info->charset != charset + /* We have a conflict, with one exception: JISX0208.1983-0 and + JISX0208.1990-0 are the same for all practical purposes. */ + && !(strncmp(existing_info->charset->name, "JISX0208", 8) == 0 + && strncmp(charset->name, "JISX0208", 8) == 0)) { + fprintf(stderr, + "Xlib: charsets %s and %s have the same CT sequence\n", + charset->name, existing_info->charset->name); + if (strcmp(charset->ct_sequence, ct_sequence) == 0) + charset->ct_sequence = ""; + } + Xfree(ct_info); + } + + return charset; } -static int -_XlcCheckCTSequence(state, ctext, ctext_len) - State state; - char **ctext; - int *ctext_len; +/* ========== Converters String <--> CharSet <--> Compound Text ========== */ + +/* + * Structure representing the parse state of a Compound Text string. + */ +typedef struct _StateRec { + XlcCharSet charset; /* The charset of the current segment */ + XlcCharSet GL_charset; /* The charset responsible for 0x00..0x7F */ + XlcCharSet GR_charset; /* The charset responsible for 0x80..0xFF */ + XlcCharSet Other_charset; /* != NULL if currently in an other segment */ + int ext_seg_left; /* > 0 if currently in an extended segment */ +} StateRec, *State; + + +/* Subroutine for parsing an ESC sequence. */ + +typedef enum { + resOK, /* Charset saved in 'state', sequence skipped */ + resNotInList, /* Charset not found, sequence skipped */ + resNotCTSeq /* EscSeq not recognized, pointers not changed */ +} CheckResult; + +static CheckResult +_XlcCheckCTSequence( + State state, + const char **ctext, + int *ctext_len) { XlcCharSet charset; - CTParseRec parse; CTInfo ct_info; - int length; + const char *tmp_ctext = *ctext; + int tmp_ctext_len = *ctext_len; + unsigned int type; + unsigned char final_byte; + int ext_seg_left = 0; - _XlcParseCT(&parse, ctext, ctext_len); - - ct_info = parse.ct_info; - if (parse.ext_seg_length > 0) { /* XctExtSeg or XctOtherSeg */ - if (ct_info) { - length = ct_info->ext_segment_len; - *ctext += length; - *ctext_len -= length; - state->ext_seg_left = parse.ext_seg_length - length; - state->ext_seg_charset = ct_info->charset; - } else { - state->ext_seg_left = parse.ext_seg_length; - state->ext_seg_charset = NULL; - } - } else if (ct_info) { - if ((charset = ct_info->charset)) { - if (charset->side == XlcGL) - state->GL_charset = charset; - else if (charset->side == XlcGR) - state->GR_charset = charset; - } + /* Check for validity. */ + type = _XlcParseCT(&tmp_ctext, &tmp_ctext_len, &final_byte); + + switch (type) { + case XctGL94: + case XctGR94: + case XctGR96: + case XctGL94MB: + case XctGR94MB: + case XctOtherCoding: + *ctext = tmp_ctext; + *ctext_len = tmp_ctext_len; + break; + case XctReturn: + *ctext = tmp_ctext; + *ctext_len = tmp_ctext_len; + state->Other_charset = NULL; + return resOK; + case XctExtSeg: + if (tmp_ctext_len > 2 + && (tmp_ctext[0] & 0x80) && (tmp_ctext[0] & 0x80)) { + unsigned int msb = tmp_ctext[0] & 0x7f; + unsigned int lsb = tmp_ctext[1] & 0x7f; + ext_seg_left = (msb << 7) + lsb; + if (ext_seg_left <= tmp_ctext_len - 2) { + *ctext = tmp_ctext + 2; + *ctext_len = tmp_ctext_len - 2; + break; + } + } + return resNotCTSeq; + default: + return resNotCTSeq; } - return 0; + ct_info = _XlcGetCTInfo(type, final_byte, *ctext, ext_seg_left); + + if (ct_info) { + charset = ct_info->charset; + state->ext_seg_left = ext_seg_left; + if (type == XctExtSeg) { + state->charset = charset; + /* Skip past the extended segment name and the separator. */ + *ctext += ct_info->ext_segment_len; + *ctext_len -= ct_info->ext_segment_len; + state->ext_seg_left -= ct_info->ext_segment_len; + } else if (type == XctOtherCoding) { + state->Other_charset = charset; + } else { + if (charset->side == XlcGL) { + state->GL_charset = charset; + } else if (charset->side == XlcGR) { + state->GR_charset = charset; + } else { + state->GL_charset = charset; + state->GR_charset = charset; + } + } + return resOK; + } else { + state->ext_seg_left = 0; + if (type == XctExtSeg) { + /* Skip the entire extended segment. */ + *ctext += ext_seg_left; + *ctext_len -= ext_seg_left; + } + return resNotInList; + } } - static void -init_state(conv) - XlcConv conv; +init_state( + XlcConv conv) { State state = (State) conv->state; - static XlcCharSet GL_charset = NULL; - static XlcCharSet GR_charset = NULL; + static XlcCharSet default_GL_charset = NULL; + static XlcCharSet default_GR_charset = NULL; - if (GL_charset == NULL) { - GL_charset = _XlcGetCharSet("ISO8859-1:GL"); - GR_charset = _XlcGetCharSet("ISO8859-1:GR"); + if (default_GL_charset == NULL) { + default_GL_charset = _XlcGetCharSet("ISO8859-1:GL"); + default_GR_charset = _XlcGetCharSet("ISO8859-1:GR"); } - state->GL_charset = state->charset = GL_charset; - state->GR_charset = GR_charset; - state->ext_seg_charset = NULL; + /* The initial state is ISO-8859-1 on both sides. */ + state->GL_charset = state->charset = default_GL_charset; + state->GR_charset = default_GR_charset; + + state->Other_charset = NULL; + state->ext_seg_left = 0; } +/* from XlcNCompoundText to XlcNCharSet */ + static int -cttocs(conv, from, from_left, to, to_left, args, num_args) - XlcConv conv; - XPointer *from; - int *from_left; - XPointer *to; - int *to_left; - XPointer *args; - int num_args; +cttocs( + XlcConv conv, + XPointer *from, + int *from_left, + XPointer *to, + int *to_left, + XPointer *args, + int num_args) { - register State state = (State) conv->state; - register unsigned char ch; - int length; + State state = (State) conv->state; XlcCharSet charset = NULL; - char *ctptr, *bufptr; + const char *ctptr; + char *bufptr; int ctext_len, buf_len; + int unconv_num = 0; - ctptr = *((char **) from); - bufptr = *((char **) to); + ctptr = (const char *) *from; + bufptr = (char *) *to; ctext_len = *from_left; buf_len = *to_left; while (ctext_len > 0 && buf_len > 0) { - if (state->ext_seg_left > 0) { - length = min(state->ext_seg_left, ctext_len); - length = min(length, buf_len); - - ctext_len -= length; - state->ext_seg_left -= length; - - if (state->ext_seg_charset) { - charset = state->ext_seg_charset; - buf_len -= length; - if (charset->side == XlcGL) { - while (length-- > 0) - *bufptr++ = *ctptr++ & 0x7f; - } else if (charset->side == XlcGR) { - while (length-- > 0) - *bufptr++ = *ctptr++ | 0x80; - } else { - while (length-- > 0) - *bufptr++ = *ctptr++; - } - - if (state->ext_seg_left < 1) - state->ext_seg_charset = NULL; - } - break; - } - ch = *((unsigned char *) ctptr); - if (ch == 0x1b || ch == 0x9b) { - length = _XlcCheckCTSequence(state, &ctptr, &ctext_len); - if (length < 0) - return -1; - if (state->ext_seg_left > 0 && charset) - break; - } else { - if (charset) { - if (charset != (ch & 0x80 ? state->GR_charset : - state->GL_charset)) - break; - } else - charset = ch & 0x80 ? state->GR_charset : state->GL_charset; - - if ((ch < 0x20 && ch != '\0' && ch != '\n' && ch != '\t') || - (ch >= 0x80 && ch < 0xa0)) - return -1; - - *bufptr++ = *ctptr++; - ctext_len--; - buf_len--; - } + if (state->ext_seg_left == 0) { + /* Not in the middle of an extended segment; look at next byte. */ + unsigned char ch = *ctptr; + XlcCharSet ch_charset; + + if (ch == XctESC) { + CheckResult ret = + _XlcCheckCTSequence(state, &ctptr, &ctext_len); + if (ret == resOK) + /* state has been modified. */ + continue; + if (ret == resNotInList) { + /* XXX Just continue with previous charset. */ + unconv_num++; + continue; + } + } else if (ch == XctCSI) { + /* XXX Simply ignore the XctLeftToRight, XctRightToLeft, + XctDirectionEnd sequences for the moment. */ + unsigned char dummy; + if (_XlcParseCT(&ctptr, &ctext_len, &dummy)) { + unconv_num++; + continue; + } + } + + /* Find the charset which is responsible for this byte. */ + ch_charset = (state->Other_charset != NULL ? state->Other_charset : + (ch & 0x80 ? state->GR_charset : state->GL_charset)); + + /* Set the charset of this run, or continue the current run, + or stop the current run. */ + if (charset) { + if (charset != ch_charset) + break; + } else { + state->charset = charset = ch_charset; + } + + /* We don't want to split a character into multiple pieces. */ + if (buf_len < 6) { + if (charset->char_size > 0) { + if (buf_len < charset->char_size) + break; + } else { + /* char_size == 0 is tricky. The code here is good only + for valid UTF-8 input. */ + if (charset->ct_sequence[0] == XctESC + && charset->ct_sequence[1] == XctOtherCoding + && charset->ct_sequence[2] == 'G') { + int char_size = (ch < 0xc0 ? 1 : + ch < 0xe0 ? 2 : + ch < 0xf0 ? 3 : + ch < 0xf8 ? 4 : + ch < 0xfc ? 5 : + 6); + if (buf_len < char_size) + break; + } + } + } + + *bufptr++ = *ctptr++; + ctext_len--; + buf_len--; + } else { + /* Copy as much as possible from the current extended segment + to the buffer. */ + int char_size; + + /* Set the charset of this run, or continue the current run, + or stop the current run. */ + if (charset) { + if (charset != state->charset) + break; + } else { + charset = state->charset; + } + + char_size = charset->char_size; + + if (state->ext_seg_left <= buf_len || char_size > 0) { + int n = (state->ext_seg_left <= buf_len + ? state->ext_seg_left + : (buf_len / char_size) * char_size); + memcpy(bufptr, ctptr, n); + ctptr += n; ctext_len -= n; + bufptr += n; buf_len -= n; + state->ext_seg_left -= n; + } else { +#if UTF8_IN_EXTSEQ + /* char_size == 0 is tricky. The code here is good only + for valid UTF-8 input. */ + if (strcmp(charset->name, "ISO10646-1") == 0) { + unsigned char ch = *ctptr; + int char_size = (ch < 0xc0 ? 1 : + ch < 0xe0 ? 2 : + ch < 0xf0 ? 3 : + ch < 0xf8 ? 4 : + ch < 0xfc ? 5 : + 6); + int i; + if (buf_len < char_size) + break; + /* A small loop is faster than calling memcpy. */ + for (i = char_size; i > 0; i--) + *bufptr++ = *ctptr++; + ctext_len -= char_size; + buf_len -= char_size; + state->ext_seg_left -= char_size; + } else +#endif + { + /* Here ctext_len >= state->ext_seg_left > buf_len. + We may be splitting a character into multiple pieces. + Oh well. */ + int n = buf_len; + memcpy(bufptr, ctptr, n); + ctptr += n; ctext_len -= n; + bufptr += n; buf_len -= n; + state->ext_seg_left -= n; + } + } + } } - if (charset) - state->charset = charset; + /* 'charset' is the charset for the current run. In some cases, + 'state->charset' contains the charset for the next run. Therefore, + return 'charset'. + 'charset' may still be NULL only if no output was produced. */ if (num_args > 0) - *((XlcCharSet *) args[0]) = state->charset; + *((XlcCharSet *) args[0]) = charset; - *from_left -= ctptr - *((char **) from); + *from_left -= ctptr - *((const char **) from); *from = (XPointer) ctptr; *to_left -= bufptr - *((char **) to); *to = (XPointer) bufptr; - return 0; + return unconv_num; } +/* from XlcNCharSet to XlcNCompoundText */ + static int -cstoct(conv, from, from_left, to, to_left, args, num_args) - XlcConv conv; - XPointer *from; - int *from_left; - XPointer *to; - int *to_left; - XPointer *args; - int num_args; +cstoct( + XlcConv conv, + XPointer *from, + int *from_left, + XPointer *to, + int *to_left, + XPointer *args, + int num_args) { State state = (State) conv->state; XlcSide side; - unsigned char min_ch, max_ch; - register unsigned char ch; - int length; + unsigned char min_ch = 0, max_ch = 0; + int length, unconv_num; CTInfo ct_info; XlcCharSet charset; - char *csptr, *ctptr; + const char *csptr; + char *ctptr; int csstr_len, ct_len; + char *ext_segment_start; + int char_size; + /* One argument is required, of type XlcCharSet. */ if (num_args < 1) return -1; - - csptr = *((char **) from); + + csptr = *((const char **) from); ctptr = *((char **) to); csstr_len = *from_left; ct_len = *to_left; - + charset = (XlcCharSet) args[0]; ct_info = _XlcGetCTInfoFromCharSet(charset); @@ -637,74 +890,170 @@ cstoct(conv, from, from_left, to, to_left, args, num_args) return -1; side = charset->side; + length = strlen(ct_info->ct_sequence); + + ext_segment_start = NULL; + + if (ct_info->type == XctOtherCoding) { + /* Output the Escape sequence for switching to the charset, and + reserve room now for the XctReturn sequence at the end. */ + if (ct_len < length + 3) + return -1; + + memcpy(ctptr, ct_info->ct_sequence, length); + ctptr += length; + ct_len -= length + 3; + } else + /* Test whether the charset is already active. */ + if (((side == XlcGR || side == XlcGLGR) + && charset != state->GR_charset) + || ((side == XlcGL || side == XlcGLGR) + && charset != state->GL_charset)) { + + /* Output the Escape sequence for switching to the charset. */ + if (ct_info->type == XctExtSeg) { + if (ct_len < length + 2 + ct_info->ext_segment_len) + return -1; + + memcpy(ctptr, ct_info->ct_sequence, length); + ctptr += length; + ct_len -= length; + + ctptr += 2; + ct_len -= 2; + ext_segment_start = ctptr; + + /* The size of an extended segment must fit in 14 bits. */ + if (ct_len > 0x3fff) + ct_len = 0x3fff; + + memcpy(ctptr, ct_info->ext_segment, ct_info->ext_segment_len); + ctptr += ct_info->ext_segment_len; + ct_len -= ct_info->ext_segment_len; + } else { + if (ct_len < length) + return -1; + + memcpy(ctptr, ct_info->ct_sequence, length); + ctptr += length; + ct_len -= length; + } + } - if (ct_info->ext_segment) { - if (charset != state->ext_seg_charset && state->ext_seg_left < 1) { - length = ct_info->encoding_len; - if (ct_len < length) - return -1; - strcpy(ctptr, ct_info->encoding); - ctptr[4] = ((ct_info->ext_segment_len + csstr_len) / 128) | 0x80; - ctptr[5] = ((ct_info->ext_segment_len + csstr_len) % 128) | 0x80; - ctptr += length; - ct_len -= length; - state->ext_seg_left = csstr_len; - } - length = min(state->ext_seg_left, csstr_len); - state->ext_seg_left -= length; - - if (side == XlcGL) { - while (length-- > 0) - *ctptr++ = *csptr++ & 0x7f; - } else if (side == XlcGR) { - while (length-- > 0) - *ctptr++ = *csptr++ | 0x80; - } else { - while (length-- > 0) - *ctptr++ = *csptr++; - } - state->ext_seg_charset = (state->ext_seg_left > 0) ? charset : NULL; - } else { - if ((side == XlcGR && charset != state->GR_charset) || - (side == XlcGL && charset != state->GL_charset)) { - - ct_len -= ct_info->encoding_len; - if (ct_len < 0) - return -1; - strcpy(ctptr, ct_info->encoding); - ctptr += ct_info->encoding_len; - } - - min_ch = 0x20; - max_ch = 0x7f; - - if (charset->set_size == 94) { - max_ch--; + /* If the charset has side GL or GR, prepare remapping the characters + to the correct side. */ + if (charset->set_size) { + min_ch = 0x20; + max_ch = 0x7f; + if (charset->set_size == 94) { + max_ch--; if (charset->char_size > 1 || side == XlcGR) min_ch++; - } + } + } + /* Actually copy the contents. */ + unconv_num = 0; + char_size = charset->char_size; + if (char_size == 1) { while (csstr_len > 0 && ct_len > 0) { - ch = *((unsigned char *) csptr++) & 0x7f; - if (ch < min_ch || ch > max_ch) - if (ch != 0x00 && ch != 0x09 && ch != 0x0a && ch != 0x1b) - continue; /* XXX */ + if (charset->set_size) { + /* The CompoundText specification says that the only + control characters allowed are 0x09, 0x0a, 0x1b, 0x9b. + Therefore here we eliminate other control characters. */ + unsigned char ch = *((unsigned char *) csptr) & 0x7f; + if (!((ch >= min_ch && ch <= max_ch) + || (side == XlcGL + && (ch == 0x00 || ch == 0x09 || ch == 0x0a)) + || ((side == XlcGL || side == XlcGR) + && (ch == 0x1b)))) { + csptr++; + csstr_len--; + unconv_num++; + continue; + } + } + if (side == XlcGL) - *ctptr++ = ch & 0x7f; + *ctptr++ = *csptr++ & 0x7f; else if (side == XlcGR) - *ctptr++ = ch | 0x80; + *ctptr++ = *csptr++ | 0x80; else - *ctptr++ = ch; + *ctptr++ = *csptr++; csstr_len--; ct_len--; } - if (side == XlcGR) - state->GR_charset = charset; - else if (side == XlcGL) - state->GL_charset = charset; + } else if (char_size > 1) { + while (csstr_len >= char_size && ct_len >= char_size) { + if (side == XlcGL) { + int i; + for (i = char_size; i > 0; i--) + *ctptr++ = *csptr++ & 0x7f; + } else if (side == XlcGR) { + int i; + for (i = char_size; i > 0; i--) + *ctptr++ = *csptr++ | 0x80; + } else { + int i; + for (i = char_size; i > 0; i--) + *ctptr++ = *csptr++; + } + csstr_len -= char_size; + ct_len -= char_size; + } + } else { + /* char_size = 0. The code here is good only for valid UTF-8 input. */ + if ((charset->ct_sequence[0] == XctESC + && charset->ct_sequence[1] == XctOtherCoding + && charset->ct_sequence[2] == 'G') +#if UTF8_IN_EXTSEQ + || strcmp(charset->name, "ISO10646-1") == 0 +#endif + ) { + while (csstr_len > 0 && ct_len > 0) { + unsigned char ch = * (unsigned char *) csptr; + int char_size = (ch < 0xc0 ? 1 : + ch < 0xe0 ? 2 : + ch < 0xf0 ? 3 : + ch < 0xf8 ? 4 : + ch < 0xfc ? 5 : + 6); + int i; + if (!(csstr_len >= char_size && ct_len >= char_size)) + break; + for (i = char_size; i > 0; i--) + *ctptr++ = *csptr++; + csstr_len -= char_size; + ct_len -= char_size; + } + } else { + while (csstr_len > 0 && ct_len > 0) { + *ctptr++ = *csptr++; + csstr_len--; + ct_len--; + } + } } - *from_left -= csptr - *((char **) from); + if (ct_info->type == XctOtherCoding) { + /* Terminate with an XctReturn sequence. */ + ctptr[0] = XctESC; + ctptr[1] = XctOtherCoding; + ctptr[2] = '@'; + ctptr += 3; + } else if (ext_segment_start != NULL) { + /* Backpatch the extended segment's length. */ + int ext_segment_length = ctptr - ext_segment_start; + *(ext_segment_start - 2) = (ext_segment_length >> 7) | 0x80; + *(ext_segment_start - 1) = (ext_segment_length & 0x7f) | 0x80; + } else { + if (side == XlcGR || side == XlcGLGR) + state->GR_charset = charset; + if (side == XlcGL || side == XlcGLGR) + state->GL_charset = charset; + } + + *from_left -= csptr - *((const char **) from); *from = (XPointer) csptr; *to_left -= ctptr - *((char **) to); @@ -713,22 +1062,25 @@ cstoct(conv, from, from_left, to, to_left, args, num_args) return 0; } +/* from XlcNString to XlcNCharSet */ + static int -strtocs(conv, from, from_left, to, to_left, args, num_args) - XlcConv conv; - XPointer *from; - int *from_left; - XPointer *to; - int *to_left; - XPointer *args; - int num_args; +strtocs( + XlcConv conv, + XPointer *from, + int *from_left, + XPointer *to, + int *to_left, + XPointer *args, + int num_args) { State state = (State) conv->state; - register char *src, *dst; + const char *src; + char *dst; unsigned char side; - register int length; + int length; - src = (char *) *from; + src = (const char *) *from; dst = (char *) *to; length = min(*from_left, *to_left); @@ -737,46 +1089,54 @@ strtocs(conv, from, from_left, to, to_left, args, num_args) while (side == (*((unsigned char *) src) & 0x80) && length-- > 0) *dst++ = *src++; - *from_left -= src - (char *) *from; + *from_left -= src - (const char *) *from; *from = (XPointer) src; *to_left -= dst - (char *) *to; *to = (XPointer) dst; if (num_args > 0) - *((XlcCharSet *)args[0]) = side ? state->GR_charset : state->GL_charset; + *((XlcCharSet *)args[0]) = (side ? state->GR_charset : state->GL_charset); return 0; } +/* from XlcNCharSet to XlcNString */ + static int -cstostr(conv, from, from_left, to, to_left, args, num_args) - XlcConv conv; - XPointer *from; - int *from_left; - XPointer *to; - int *to_left; - XPointer *args; - int num_args; +cstostr( + XlcConv conv, + XPointer *from, + int *from_left, + XPointer *to, + int *to_left, + XPointer *args, + int num_args) { State state = (State) conv->state; - char *csptr, *string_ptr; + const char *csptr; + char *string_ptr; int csstr_len, str_len; unsigned char ch; int unconv_num = 0; - if (num_args < 1 || (state->GL_charset != (XlcCharSet) args[0] && - state->GR_charset != (XlcCharSet) args[0])) + /* This converter can only convert from ISO8859-1:GL and ISO8859-1:GR. */ + if (num_args < 1 + || !((XlcCharSet) args[0] == state->GL_charset + || (XlcCharSet) args[0] == state->GR_charset)) return -1; - csptr = *((char **) from); + csptr = *((const char **) from); string_ptr = *((char **) to); csstr_len = *from_left; str_len = *to_left; - while (csstr_len-- > 0 && str_len > 0) { + while (csstr_len > 0 && str_len > 0) { ch = *((unsigned char *) csptr++); - if ((ch < 0x20 && ch != 0x00 && ch != 0x09 && ch != 0x0a) || - ch == 0x7f || ((ch & 0x80) && ch < 0xa0)) { + csstr_len--; + /* Citing ICCCM: "STRING as a type specifies the ISO Latin-1 character + set plus the control characters TAB and NEWLINE." */ + if ((ch < 0x20 && ch != 0x00 && ch != 0x09 && ch != 0x0a) + || (ch >= 0x7f && ch < 0xa0)) { unconv_num++; continue; } @@ -784,7 +1144,7 @@ cstostr(conv, from, from_left, to, to_left, args, num_args) str_len--; } - *from_left -= csptr - *((char **) from); + *from_left -= csptr - *((const char **) from); *from = (XPointer) csptr; *to_left -= string_ptr - *((char **) to); @@ -794,116 +1154,141 @@ cstostr(conv, from, from_left, to, to_left, args, num_args) } -static void -close_converter(conv) - XlcConv conv; -{ - if (conv->state) - Xfree((char *) conv->state); - - Xfree((char *) conv); -} - static XlcConv -create_conv(methods) - XlcConvMethods methods; +create_conv( + XlcConvMethods methods) { - register XlcConv conv; + XlcConv conv; - conv = (XlcConv) Xmalloc(sizeof(XlcConvRec)); + conv = (XlcConv) Xmalloc(sizeof(XlcConvRec) + sizeof(StateRec)); if (conv == NULL) return (XlcConv) NULL; - conv->state = (XPointer) Xmalloc(sizeof(StateRec)); - if (conv->state == NULL) - goto err; - + conv->state = (XPointer) &conv[1]; + conv->methods = methods; init_state(conv); return conv; +} -err: - close_converter(conv); - - return (XlcConv) NULL; +static void +close_converter( + XlcConv conv) +{ + /* conv->state is allocated together with conv, free both at once. */ + Xfree((char *) conv); } + static XlcConvMethodsRec cttocs_methods = { close_converter, cttocs, init_state -} ; +}; static XlcConv -open_cttocs(from_lcd, from_type, to_lcd, to_type) - XLCd from_lcd; - char *from_type; - XLCd to_lcd; - char *to_type; +open_cttocs( + XLCd from_lcd, + const char *from_type, + XLCd to_lcd, + const char *to_type) { return create_conv(&cttocs_methods); } + static XlcConvMethodsRec cstoct_methods = { close_converter, cstoct, init_state -} ; +}; static XlcConv -open_cstoct(from_lcd, from_type, to_lcd, to_type) - XLCd from_lcd; - char *from_type; - XLCd to_lcd; - char *to_type; +open_cstoct( + XLCd from_lcd, + const char *from_type, + XLCd to_lcd, + const char *to_type) { return create_conv(&cstoct_methods); } + static XlcConvMethodsRec strtocs_methods = { close_converter, strtocs, init_state -} ; +}; static XlcConv -open_strtocs(from_lcd, from_type, to_lcd, to_type) - XLCd from_lcd; - char *from_type; - XLCd to_lcd; - char *to_type; +open_strtocs( + XLCd from_lcd, + const char *from_type, + XLCd to_lcd, + const char *to_type) { return create_conv(&strtocs_methods); } + static XlcConvMethodsRec cstostr_methods = { close_converter, cstostr, init_state -} ; +}; static XlcConv -open_cstostr(from_lcd, from_type, to_lcd, to_type) - XLCd from_lcd; - char *from_type; - XLCd to_lcd; - char *to_type; +open_cstostr( + XLCd from_lcd, + const char *from_type, + XLCd to_lcd, + const char *to_type) { return create_conv(&cstostr_methods); } -static void -init_converter() + +/* =========================== Initialization =========================== */ + +Bool +_XlcInitCTInfo() { - _XlcSetConverter((XLCd) NULL, XlcNCompoundText, (XLCd) NULL, XlcNCharSet, - open_cttocs); - _XlcSetConverter((XLCd) NULL, XlcNString, (XLCd) NULL, XlcNCharSet, - open_strtocs); - - _XlcSetConverter((XLCd) NULL, XlcNCharSet, (XLCd) NULL, XlcNCompoundText, - open_cstoct); - _XlcSetConverter((XLCd) NULL, XlcNCharSet, (XLCd) NULL, XlcNString, - open_cstostr); + if (ct_list == NULL) { + CTData ct_data; + int num; + XlcCharSet charset; + + /* Initialize ct_list. */ + + num = sizeof(default_ct_data) / sizeof(CTDataRec); + for (ct_data = default_ct_data; num > 0; ct_data++, num--) { + charset = _XlcAddCT(ct_data->name, ct_data->ct_sequence); + if (charset == NULL) + continue; + if (strncmp(charset->ct_sequence, "\x1b\x25\x2f", 3) != 0) + charset->source = CSsrcStd; + else + charset->source = CSsrcXLC; + } + + /* Register CompoundText and CharSet converters. */ + + _XlcSetConverter((XLCd) NULL, XlcNCompoundText, + (XLCd) NULL, XlcNCharSet, + open_cttocs); + _XlcSetConverter((XLCd) NULL, XlcNString, + (XLCd) NULL, XlcNCharSet, + open_strtocs); + + _XlcSetConverter((XLCd) NULL, XlcNCharSet, + (XLCd) NULL, XlcNCompoundText, + open_cstoct); + _XlcSetConverter((XLCd) NULL, XlcNCharSet, + (XLCd) NULL, XlcNString, + open_cstostr); + } + + return True; } |