Lines Matching refs:utf
5 * rfc2044 (UTF-8 and UTF-16) F. Yergeau Alis Technologies
6 * rfc2781 UTF-16, an encoding of ISO 10646, P. Hoffman, F. Yergeau
7 * [ISO-10646] UTF-8 and UTF-16 in Annexes
11 * Wesley, Volume 1, 1991, Volume 2, 1992. UTF-8 is
20 * Original code for IsoLatin1 and UTF-16 by "Martin J. Duerst" <duerst@w3.org>
130 conv->utf8 = ucnv_open("UTF-8", &status);
165 * Take a block of ASCII chars in and try to convert it to an UTF-8
208 * @in: a pointer to an array of UTF-8 chars
211 * Take a block of UTF-8 chars in and try to convert it to an ASCII
270 /* assertion: c is a single UTF-4 value */
296 * Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
342 * @inb: a pointer to an array of UTF-8 chars
343 * @inlenb: the length of @in in UTF-8 chars
380 * @in: a pointer to an array of UTF-8 chars
383 * Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
448 /* assertion: c is a single UTF-4 value */
471 * @inb: a pointer to an array of UTF-16LE passwd as a byte array
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
535 /* assertion: c is a single UTF-4 value */
560 * @in: a pointer to an array of UTF-8 chars
563 * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE
605 /* no chance for this in UTF-16 */
622 /* assertion: c is a single UTF-4 value */
669 * @in: a pointer to an array of UTF-8 chars
672 * Take a block of UTF-8 chars in and try to convert it to an UTF-16
684 * initialization, add the Byte Order Mark for UTF-16LE
709 * @inb: a pointer to an array of UTF-16 passed as a byte array
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
777 /* assertion: c is a single UTF-4 value */
802 * @in: a pointer to an array of UTF-8 chars
805 * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE
826 /* UTF-16BE has no BOM */
847 /* no chance for this in UTF-16 */
863 /* assertion: c is a single UTF-4 value */
948 * attempt an "auto-recognition" of UTF-16LE and
949 * UTF-16BE encodings.
967 /* For UTF-16 we can recognize by the BOM */
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)
1098 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1131 * @name: the encoding name as parsed, in UTF-8 format (ASCII actually)
1164 if (!strcmp(upper, "UTF-8")) return(XML_CHAR_ENCODING_UTF8);
1171 if (!strcmp(upper, "UTF-16")) return(XML_CHAR_ENCODING_UTF16LE);
1232 return("UTF-8");
1234 return("UTF-16");
1236 return("UTF-16");
1292 * The default is UTF-8 for XML, that's also the default used for the
1300 * @name: the encoding name, in UTF-8 format (ASCII actually)
1408 xmlNewCharEncodingHandler("UTF-8", UTF8ToUTF8, UTF8ToUTF8);
1411 xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE);
1413 xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE);
1414 xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, UTF8ToUTF16);
1423 xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, NULL);
1425 xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, NULL);
1426 xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, NULL);
1682 icv_in = iconv_open("UTF-8", name);
1683 icv_out = iconv_open(name, "UTF-8");
1685 icv_in = iconv_open("UTF-8", upper);
1688 icv_out = iconv_open(upper, "UTF-8");
1878 /* encoding => UTF-16 => UTF-8 */
1883 /* UTF-8 => UTF-16 => encoding */
1940 * on UTF-16 this means 90bytes, on UCS4 this means 180
2074 * on UTF-16 this means 90bytes, on UCS4 this means 180
2787 const xmlChar *utf = (const xmlChar *) in->content;
2790 cur = xmlGetUTF8Char(utf, &len);
2929 * of constant cost if the input is UTF-8 but can be costly if run
2930 * on non-UTF-8 input.
3020 * @in: a pointer to an array of UTF-8 chars
3024 * Take a block of UTF-8 chars in and try to convert it to an ISO 8859-*
3142 * Take a block of ISO 8859-* chars in and try to convert it to an UTF-8
