Lines Matching defs: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>
133 conv->utf8 = ucnv_open("UTF-8", &status);
168 * Take a block of ASCII chars in and try to convert it to an UTF-8
211 * @in: a pointer to an array of UTF-8 chars
214 * Take a block of UTF-8 chars in and try to convert it to an ASCII
273 /* assertion: c is a single UTF-4 value */
299 * Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
345 * @inb: a pointer to an array of UTF-8 chars
346 * @inlenb: the length of @in in UTF-8 chars
389 * @in: a pointer to an array of UTF-8 chars
392 * Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
457 /* assertion: c is a single UTF-4 value */
480 * @inb: a pointer to an array of UTF-16LE passwd as a byte array
481 * @inlenb: the length of @in in UTF-16LE chars
483 * Take a block of UTF-16LE ushorts in and try to convert it to an UTF-8
544 /* assertion: c is a single UTF-4 value */
569 * @in: a pointer to an array of UTF-8 chars
572 * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE
614 /* no chance for this in UTF-16 */
631 /* assertion: c is a single UTF-4 value */
678 * @in: a pointer to an array of UTF-8 chars
681 * Take a block of UTF-8 chars in and try to convert it to an UTF-16
693 * initialization, add the Byte Order Mark for UTF-16LE
718 * @inb: a pointer to an array of UTF-16 passed as a byte array
719 * @inlenb: the length of @in in UTF-16 chars
721 * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8
786 /* assertion: c is a single UTF-4 value */
811 * @in: a pointer to an array of UTF-8 chars
814 * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE
835 /* UTF-16BE has no BOM */
856 /* no chance for this in UTF-16 */
872 /* assertion: c is a single UTF-4 value */
957 * attempt an "auto-recognition" of UTF-16LE and
958 * UTF-16BE encodings.
976 /* For UTF-16 we can recognize by the BOM */
1012 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1048 * @name: the encoding name as parsed, in UTF-8 format (ASCII actually)
1049 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1107 * @alias: the alias name as parsed, in UTF-8 format (ASCII actually)
1140 * @name: the encoding name as parsed, in UTF-8 format (ASCII actually)
1173 if (!strcmp(upper, "UTF-8")) return(XML_CHAR_ENCODING_UTF8);
1180 if (!strcmp(upper, "UTF-16")) return(XML_CHAR_ENCODING_UTF16LE);
1241 return("UTF-8");
1243 return("UTF-16");
1245 return("UTF-16");
1301 * The default is UTF-8 for XML, that's also the default used for the
1309 * @name: the encoding name, in UTF-8 format (ASCII actually)
1417 xmlNewCharEncodingHandler("UTF-8", UTF8ToUTF8, UTF8ToUTF8);
1420 xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE);
1422 xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE);
1423 xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, UTF8ToUTF16);
1432 xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, NULL);
1434 xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, NULL);
1435 xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, NULL);
1691 icv_in = iconv_open("UTF-8", name);
1692 icv_out = iconv_open(name, "UTF-8");
1694 icv_in = iconv_open("UTF-8", upper);
1697 icv_out = iconv_open(upper, "UTF-8");
1881 /* encoding => UTF-16 => UTF-8 */
1887 /* UTF-8 => UTF-16 => encoding */
2006 * on UTF-16 this means 90bytes, on UCS4 this means 180
2120 * on UTF-16 this means 90bytes, on UCS4 this means 180
2660 const xmlChar *utf = (const xmlChar *) in->content;
2663 cur = xmlGetUTF8Char(utf, &len);
2798 * of constant cost if the input is UTF-8 but can be costly if run
2799 * on non-UTF-8 input.
2855 * @in: a pointer to an array of UTF-8 chars
2859 * Take a block of UTF-8 chars in and try to convert it to an ISO 8859-*
2977 * Take a block of ISO 8859-* chars in and try to convert it to an UTF-8
