Lines Matching defs:in
7 * [ISO-10646] UTF-8 and UTF-16 in Annexes
12 * described in Unicode Technical Report #4.
162 * @in: a pointer to an array of ASCII chars
163 * @inlen: the length of @in
165 * Take a block of ASCII chars in and try to convert it to an UTF-8
174 const unsigned char* in, int *inlen) {
176 const unsigned char* base = in;
177 const unsigned char* processed = in;
182 inend = in + (*inlen);
183 while ((in < inend) && (out - outstart + 5 < *outlen)) {
184 c= *in++;
196 processed = (const unsigned char*) in;
208 * @in: a pointer to an array of UTF-8 chars
209 * @inlen: the length of @in
211 * Take a block of UTF-8 chars in and try to convert it to an ASCII
221 const unsigned char* in, int *inlen) {
222 const unsigned char* processed = in;
225 const unsigned char* instart = in;
231 if (in == NULL) {
239 inend = in + (*inlen);
241 while (in < inend) {
242 d = *in++;
245 /* trailing byte in leading position */
253 /* no chance for this in Ascii */
259 if (inend - in < trailing) {
264 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
276 /* no chance for this in Ascii */
281 processed = in;
293 * @in: a pointer to an array of ISO Latin 1 chars
294 * @inlen: the length of @in
296 * Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
305 const unsigned char* in, int *inlen) {
307 const unsigned char* base = in;
312 if ((out == NULL) || (in == NULL) || (outlen == NULL) || (inlen == NULL))
316 inend = in + (*inlen);
319 while ((in < inend) && (out < outend - 1)) {
320 if (*in >= 0x80) {
321 *out++ = (((*in) >> 6) & 0x1F) | 0xC0;
322 *out++ = ((*in) & 0x3F) | 0x80;
323 ++in;
325 if ((instop - in) > (outend - out)) instop = in + (outend - out);
326 while ((in < instop) && (*in < 0x80)) {
327 *out++ = *in++;
330 if ((in < inend) && (out < outend) && (*in < 0x80)) {
331 *out++ = *in++;
334 *inlen = in - base;
343 * @inlenb: the length of @in in UTF-8 chars
380 * @in: a pointer to an array of UTF-8 chars
381 * @inlen: the length of @in
383 * Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
394 const unsigned char* in, int *inlen) {
395 const unsigned char* processed = in;
398 const unsigned char* instart = in;
404 if (in == NULL) {
412 inend = in + (*inlen);
414 while (in < inend) {
415 d = *in++;
418 /* trailing byte in leading position */
426 /* no chance for this in IsoLat1 */
432 if (inend - in < trailing) {
437 if (in >= inend)
439 if (((d= *in++) & 0xC0) != 0x80) {
454 /* no chance for this in IsoLat1 */
459 processed = in;
472 * @inlenb: the length of @in in UTF-16LE chars
474 * Take a block of UTF-16LE ushorts in and try to convert it to an UTF-8
480 * if the transcoding fails (if *in is not a valid utf16 string)
491 unsigned short* in = (unsigned short*) inb;
500 inend = in + inlen;
501 while ((in < inend) && (out - outstart + 5 < *outlen)) {
503 c= *in++;
505 tmp = (unsigned char *) in;
508 in++;
511 if (in >= inend) { /* (in > inend) shouldn't happens */
515 d = *in++;
517 tmp = (unsigned char *) in;
520 in++;
548 processed = (const unsigned char*) in;
560 * @in: a pointer to an array of UTF-8 chars
561 * @inlen: the length of @in
563 * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE
571 const unsigned char* in, int *inlen)
574 const unsigned char* processed = in;
575 const unsigned char *const instart = in;
586 if (in == NULL) {
591 inend= in + *inlen;
593 while (in < inend) {
594 d= *in++;
597 /* trailing byte in leading position */
605 /* no chance for this in UTF-16 */
611 if (inend - in < trailing) {
616 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
658 processed = in;
669 * @in: a pointer to an array of UTF-8 chars
670 * @inlen: the length of @in
672 * Take a block of UTF-8 chars in and try to convert it to an UTF-16
680 const unsigned char* in, int *inlen)
682 if (in == NULL) {
701 return (UTF8ToUTF16LE(outb, outlen, in, inlen));
710 * @inlenb: the length of @in in UTF-16 chars
712 * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8
718 * if the transcoding fails (if *in is not a valid utf16 string)
729 unsigned short* in = (unsigned short*) inb;
738 inend= in + inlen;
739 while (in < inend) {
741 tmp = (unsigned char *) in;
745 in++;
747 c= *in++;
750 if (in >= inend) { /* (in > inend) shouldn't happens */
756 tmp = (unsigned char *) in;
760 in++;
762 d= *in++;
790 processed = (const unsigned char*) in;
802 * @in: a pointer to an array of UTF-8 chars
803 * @inlen: the length of @in
805 * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE
813 const unsigned char* in, int *inlen)
816 const unsigned char* processed = in;
817 const unsigned char *const instart = in;
828 if (in == NULL) {
833 inend= in + *inlen;
835 while (in < inend) {
836 d= *in++;
839 /* trailing byte in leading position */
847 /* no chance for this in UTF-16 */
853 if (inend - in < trailing) {
858 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) break;
897 processed = in;
913 * @in: a pointer to the first bytes of the XML entity, must be at least
923 xmlDetectCharEncoding(const unsigned char* in, int len)
925 if (in == NULL)
928 if ((in[0] == 0x00) && (in[1] == 0x00) &&
929 (in[2] == 0x00) && (in[3] == 0x3C))
931 if ((in[0] == 0x3C) && (in[1] == 0x00) &&
932 (in[2] == 0x00) && (in[3] == 0x00))
934 if ((in[0] == 0x00) && (in[1] == 0x00) &&
935 (in[2] == 0x3C) && (in[3] == 0x00))
937 if ((in[0] == 0x00) && (in[1] == 0x3C) &&
938 (in[2] == 0x00) && (in[3] == 0x00))
940 if ((in[0] == 0x4C) && (in[1] == 0x6F) &&
941 (in[2] == 0xA7) && (in[3] == 0x94))
943 if ((in[0] == 0x3C) && (in[1] == 0x3F) &&
944 (in[2] == 0x78) && (in[3] == 0x6D))
951 if ((in[0] == 0x3C) && (in[1] == 0x00) &&
952 (in[2] == 0x3F) && (in[3] == 0x00))
954 if ((in[0] == 0x00) && (in[1] == 0x3C) &&
955 (in[2] == 0x00) && (in[3] == 0x3F))
963 if ((in[0] == 0xEF) && (in[1] == 0xBB) &&
964 (in[2] == 0xBF))
969 if ((in[0] == 0xFE) && (in[1] == 0xFF))
971 if ((in[0] == 0xFF) && (in[1] == 0xFE))
1003 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1039 * @name: the encoding name as parsed, in UTF-8 format (ASCII actually)
1040 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1045 * Returns 0 in case of success, -1 in case of error
1098 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1102 * Returns 0 in case of success, -1 in case of error
1131 * @name: the encoding name as parsed, in UTF-8 format (ASCII actually)
1135 * [XML] 4.3.3 Character Encoding in Entities.
1169 * already found and in use
1180 * already found and in use
1219 * Section 4.3.3 Character Encoding in Entities
1300 * @name: the encoding name, in UTF-8 format (ASCII actually)
1306 * Returns the xmlCharEncodingHandlerPtr created (or NULL in case of error).
1385 * in normal processing.
1493 * Search in the registered set the handler able to read/write that encoding.
1553 * We used to keep ISO Latin encodings native in the
1627 * Search in the registered set the handler able to read/write that encoding.
1778 * @in: a pointer to an array of ISO Latin 1 chars
1779 * @inlen: the length of @in
1783 * -2 if the transcoding fails (for *in is not valid utf8 string or
1793 const unsigned char *in, int *inlen) {
1795 const char *icv_in = (const char *) in;
1799 if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || (in == NULL)) {
1845 * @in: a pointer to an array of ISO Latin 1 chars
1846 * @inlen: the length of @in
1850 * -2 if the transcoding fails (for *in is not valid utf8 string or
1860 const unsigned char *in, int *inlen) {
1861 const char *ucv_in = (const char *) in;
1865 if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || (in == NULL)) {
1888 *inlen = ucv_in - (const char*) in;
1911 * @in: an xmlBuffer for the input
1919 * -2 if the transcoding fails (for *in is not valid utf8 string or
1924 xmlBufferPtr in, int len) {
1931 if (in == NULL) return(-1);
1935 toconv = in->use;
1958 in->content, &toconv);
1959 xmlBufferShrink(in, toconv);
1966 &written, in->content, &toconv);
1967 xmlBufferShrink(in, toconv);
1976 &written, in->content, &toconv);
1977 xmlBufferShrink(in, toconv);
1992 toconv, written, in->use);
2000 toconv, written, in->use);
2018 * @in: an xmlBuffer for the input
2025 * -2 if the transcoding fails (for *in is not valid utf8 string or
2030 xmlBufferPtr in) {
2031 return(xmlCharEncFirstLineInt(handler, out, in, -1));
2046 * -2 if the transcoding fails (for *in is not valid utf8 string or
2057 xmlBufPtr in;
2064 in = input->raw;
2066 toconv = xmlBufUse(in);
2096 xmlBufContent(in), &c_in);
2097 xmlBufShrink(in, c_in);
2103 &c_out, xmlBufContent(in), &c_in);
2104 xmlBufShrink(in, c_in);
2113 &c_out, xmlBufContent(in), &c_in);
2114 xmlBufShrink(in, c_in);
2132 c_in, c_out, (int)xmlBufUse(in));
2139 c_in, c_out, (int)xmlBufUse(in));
2144 const xmlChar *content = xmlBufContent(in);
2172 * -2 if the transcoding fails (for *in is not valid utf8 string or
2183 xmlBufPtr in;
2190 in = input->raw;
2192 toconv = xmlBufUse(in);
2213 xmlBufContent(in), &c_in);
2214 xmlBufShrink(in, c_in);
2220 &c_out, xmlBufContent(in), &c_in);
2221 xmlBufShrink(in, c_in);
2230 &c_out, xmlBufContent(in), &c_in);
2231 xmlBufShrink(in, c_in);
2249 c_in, c_out, (int)xmlBufUse(in));
2256 c_in, c_out, (int)xmlBufUse(in));
2261 const xmlChar *content = xmlBufContent(in);
2284 * @in: an xmlBuffer for the input
2290 * -2 if the transcoding fails (for *in is not valid utf8 string or
2295 xmlBufferPtr in)
2305 if (in == NULL)
2308 toconv = in->use;
2318 in->content, &toconv);
2319 xmlBufferShrink(in, toconv);
2326 &written, in->content, &toconv);
2327 xmlBufferShrink(in, toconv);
2337 &written, in->content, &toconv);
2338 xmlBufferShrink(in, toconv);
2357 toconv, written, in->use);
2364 toconv, written, in->use);
2371 in->content[0], in->content[1],
2372 in->content[2], in->content[3]);
2395 * output in case of non-stateless encoding needing to initiate their
2396 * state or the output (like the BOM in UTF16).
2397 * In case of UTF8 sequence conversion errors for the given encoder,
2402 * -2 if the transcoding fails (for *in is not valid utf8 string or
2414 xmlBufPtr in;
2422 in = output->buffer;
2466 toconv = xmlBufUse(in);
2482 xmlBufContent(in), &c_in);
2484 xmlBufShrink(in, c_in);
2492 &c_out, xmlBufContent(in), &c_in);
2493 xmlBufShrink(in, c_in);
2511 &c_out, xmlBufContent(in), &c_in);
2512 xmlBufShrink(in, c_in);
2555 c_in, c_out, (int) xmlBufUse(in));
2559 int len = (int) xmlBufUse(in);
2560 xmlChar *content = xmlBufContent(in);
2571 xmlBufShrink(in, charref_len - c_out);
2594 xmlBufShrink(in, len);
2595 xmlBufAddHead(in, charref, -1);
2608 if (xmlBufGetAllocationScheme(in) != XML_BUFFER_ALLOC_IMMUTABLE)
2622 * @in: an xmlBuffer for the input
2625 * a first call with @in == NULL has to be made firs to initiate the
2626 * output in case of non-stateless encoding needing to initiate their
2627 * state or the output (like the BOM in UTF16).
2628 * In case of UTF8 sequence conversion errors for the given encoder,
2633 * -2 if the transcoding fails (for *in is not valid utf8 string or
2638 xmlBufferPtr in) {
2657 * First specific handling of in = NULL, i.e. the initialization call
2659 if (in == NULL) {
2696 toconv = in->use;
2705 in->content, &toconv);
2707 xmlBufferShrink(in, toconv);
2716 &written, in->content, &toconv);
2717 xmlBufferShrink(in, toconv);
2737 &written, in->content, &toconv);
2738 xmlBufferShrink(in, toconv);
2782 toconv, written, in->use);
2786 int len = in->use;
2787 const xmlChar *utf = (const xmlChar *) in->content;
2798 xmlBufferShrink(in, charref_len - written);
2811 in->content[0], in->content[1],
2812 in->content[2], in->content[3]);
2821 xmlBufferShrink(in, len);
2822 xmlBufferAddHead(in, charref, -1);
2829 in->content[0], in->content[1],
2830 in->content[2], in->content[3]);
2835 if (in->alloc != XML_BUFFER_ALLOC_IMMUTABLE)
2836 in->content[0] = ' ';
2850 * Returns 0 if success, or -1 in case of error
2926 * to the start of the current entity. This function is computed in
2928 * size in byte of the file if parsing a file. The function is
2932 * Returns the index in bytes from the beginning of the entity or -1
2933 * in case the index could not be computed.
2937 xmlParserInputPtr in;
2940 in = ctxt->input;
2941 if (in == NULL) return(-1);
2942 if ((in->buf != NULL) && (in->buf->encoder != NULL)) {
2944 xmlCharEncodingHandler * handler = in->buf->encoder;
2950 if (in->end - in->cur > 0) {
2952 const unsigned char *cur = (const unsigned char *)in->cur;
2953 int toconv = in->end - in->cur, written = 32000;
2959 toconv = in->end - cur;
2970 toconv = in->end - cur;
2987 toconv = in->end - cur;
3006 if (in->buf->rawconsumed < unused)
3008 return(in->buf->rawconsumed - unused);
3010 return(in->consumed + (in->cur - in->base));
3020 * @in: a pointer to an array of UTF-8 chars
3021 * @inlen: the length of @in
3024 * Take a block of UTF-8 chars in and try to convert it to an ISO 8859-*
3034 const unsigned char* in, int *inlen,
3038 const unsigned char* instart = in;
3039 const unsigned char* processed = in;
3044 if (in == NULL) {
3052 inend = in + (*inlen);
3053 while (in < inend) {
3054 unsigned char d = *in++;
3058 /* trailing byte in leading position */
3064 if (!(in < inend)) {
3065 /* trailing byte not in input buffer */
3070 c = *in++;
3081 /* not in character set */
3090 if (!(in < inend - 1)) {
3091 /* trailing bytes not in input buffer */
3096 c1 = *in++;
3103 c2 = *in++;
3116 /* not in character set */
3128 processed = in;
3139 * @in: a pointer to an array of ISO Latin 1 chars
3140 * @inlen: the length of @in
3142 * Take a block of ISO 8859-* chars in and try to convert it to an UTF-8
3150 const unsigned char* in, int *inlen,
3154 const unsigned char* instart = in;
3160 (in == NULL) || (unicodetable == NULL))
3163 inend = in + *inlen;
3166 while ((in < inend) && (out < outend - 2)) {
3167 if (*in >= 0x80) {
3168 c = unicodetable [*in - 0x80];
3172 *inlen = in - instart;
3183 ++in;
3185 if (instop - in > outend - out) instop = in + (outend - out);
3186 while ((*in < 0x80) && (in < instop)) {
3187 *out++ = *in++;
3190 if ((in < inend) && (out < outend) && (*in < 0x80)) {
3191 *out++ = *in++;
3193 if ((in < inend) && (out < outend) && (*in < 0x80)) {
3194 *out++ = *in++;
3197 *inlen = in - instart;
3938 const unsigned char* in, int *inlen) {
3939 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_2);
3942 const unsigned char* in, int *inlen) {
3943 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_2);
3947 const unsigned char* in, int *inlen) {
3948 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_3);
3951 const unsigned char* in, int *inlen) {
3952 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_3);
3956 const unsigned char* in, int *inlen) {
3957 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_4);
3960 const unsigned char* in, int *inlen) {
3961 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_4);
3965 const unsigned char* in, int *inlen) {
3966 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_5);
3969 const unsigned char* in, int *inlen) {
3970 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_5);
3974 const unsigned char* in, int *inlen) {
3975 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_6);
3978 const unsigned char* in, int *inlen) {
3979 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_6);
3983 const unsigned char* in, int *inlen) {
3984 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_7);
3987 const unsigned char* in, int *inlen) {
3988 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_7);
3992 const unsigned char* in, int *inlen) {
3993 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_8);
3996 const unsigned char* in, int *inlen) {
3997 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_8);
4001 const unsigned char* in, int *inlen) {
4002 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_9);
4005 const unsigned char* in, int *inlen) {
4006 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_9);
4010 const unsigned char* in, int *inlen) {
4011 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_10);
4014 const unsigned char* in, int *inlen) {
4015 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_10);
4019 const unsigned char* in, int *inlen) {
4020 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_11);
4023 const unsigned char* in, int *inlen) {
4024 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_11);
4028 const unsigned char* in, int *inlen) {
4029 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_13);
4032 const unsigned char* in, int *inlen) {
4033 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_13);
4037 const unsigned char* in, int *inlen) {
4038 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_14);
4041 const unsigned char* in, int *inlen) {
4042 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_14);
4046 const unsigned char* in, int *inlen) {
4047 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_15);
4050 const unsigned char* in, int *inlen) {
4051 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_15);
4055 const unsigned char* in, int *inlen) {
4056 return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_16);
4059 const unsigned char* in, int *inlen) {
4060 return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_16);
