Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1 | /* |
Daniel Veillard | be58697 | 2003-11-18 20:56:51 +0000 | [diff] [blame] | 2 | * Summary: interface for the encoding conversion functions |
| 3 | * Description: interface for the encoding conversion functions needed for |
| 4 | * XML basic encoding and iconv() support. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 5 | * |
Daniel Veillard | be58697 | 2003-11-18 20:56:51 +0000 | [diff] [blame] | 6 | * Related specs are |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 7 | * rfc2044 (UTF-8 and UTF-16) F. Yergeau Alis Technologies |
| 8 | * [ISO-10646] UTF-8 and UTF-16 in Annexes |
| 9 | * [ISO-8859-1] ISO Latin-1 characters codes. |
| 10 | * [UNICODE] The Unicode Consortium, "The Unicode Standard -- |
| 11 | * Worldwide Character Encoding -- Version 1.0", Addison- |
| 12 | * Wesley, Volume 1, 1991, Volume 2, 1992. UTF-8 is |
| 13 | * described in Unicode Technical Report #4. |
| 14 | * [US-ASCII] Coded Character Set--7-bit American Standard Code for |
| 15 | * Information Interchange, ANSI X3.4-1986. |
| 16 | * |
Daniel Veillard | be58697 | 2003-11-18 20:56:51 +0000 | [diff] [blame] | 17 | * Copy: See Copyright for the status of this software. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 18 | * |
Daniel Veillard | be58697 | 2003-11-18 20:56:51 +0000 | [diff] [blame] | 19 | * Author: Daniel Veillard |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 20 | */ |
| 21 | |
| 22 | #ifndef __XML_CHAR_ENCODING_H__ |
| 23 | #define __XML_CHAR_ENCODING_H__ |
| 24 | |
| 25 | #include <libxml/xmlversion.h> |
Igor Zlatkovic | 7ae91bc | 2002-11-08 17:18:52 +0000 | [diff] [blame] | 26 | |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 27 | #ifdef LIBXML_ICONV_ENABLED |
| 28 | #include <iconv.h> |
| 29 | #endif |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 30 | #ifdef __cplusplus |
| 31 | extern "C" { |
| 32 | #endif |
| 33 | |
William M. Brack | 60f394e | 2003-11-16 06:25:42 +0000 | [diff] [blame] | 34 | /* |
Daniel Veillard | f69bb4b | 2001-05-19 13:24:56 +0000 | [diff] [blame] | 35 | * xmlCharEncoding: |
| 36 | * |
Daniel Veillard | 61f2617 | 2002-03-12 18:46:39 +0000 | [diff] [blame] | 37 | * Predefined values for some standard encodings. |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 38 | * Libxml does not do beforehand translation on UTF8 and ISOLatinX. |
| 39 | * It also supports ASCII, ISO-8859-1, and UTF16 (LE and BE) by default. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 40 | * |
| 41 | * Anything else would have to be translated to UTF8 before being |
| 42 | * given to the parser itself. The BOM for UTF16 and the encoding |
| 43 | * declaration are looked at and a converter is looked for at that |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 44 | * point. If not found the parser stops here as asked by the XML REC. A |
| 45 | * converter can be registered by the user using xmlRegisterCharEncodingHandler |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 46 | * but the current form doesn't allow stateful transcoding (a serious |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 47 | * problem agreed !). If iconv has been found it will be used |
| 48 | * automatically and allow stateful transcoding, the simplest is then |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 49 | * to be sure to enable iconv and to provide iconv libs for the encoding |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 50 | * support needed. |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 51 | * |
| 52 | * Note that the generic "UTF-16" is not a predefined value. Instead, only |
| 53 | * the specific UTF-16LE and UTF-16BE are present. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 54 | */ |
| 55 | typedef enum { |
| 56 | XML_CHAR_ENCODING_ERROR= -1, /* No char encoding detected */ |
| 57 | XML_CHAR_ENCODING_NONE= 0, /* No char encoding detected */ |
| 58 | XML_CHAR_ENCODING_UTF8= 1, /* UTF-8 */ |
| 59 | XML_CHAR_ENCODING_UTF16LE= 2, /* UTF-16 little endian */ |
| 60 | XML_CHAR_ENCODING_UTF16BE= 3, /* UTF-16 big endian */ |
| 61 | XML_CHAR_ENCODING_UCS4LE= 4, /* UCS-4 little endian */ |
| 62 | XML_CHAR_ENCODING_UCS4BE= 5, /* UCS-4 big endian */ |
| 63 | XML_CHAR_ENCODING_EBCDIC= 6, /* EBCDIC uh! */ |
| 64 | XML_CHAR_ENCODING_UCS4_2143=7, /* UCS-4 unusual ordering */ |
| 65 | XML_CHAR_ENCODING_UCS4_3412=8, /* UCS-4 unusual ordering */ |
| 66 | XML_CHAR_ENCODING_UCS2= 9, /* UCS-2 */ |
| 67 | XML_CHAR_ENCODING_8859_1= 10,/* ISO-8859-1 ISO Latin 1 */ |
| 68 | XML_CHAR_ENCODING_8859_2= 11,/* ISO-8859-2 ISO Latin 2 */ |
| 69 | XML_CHAR_ENCODING_8859_3= 12,/* ISO-8859-3 */ |
| 70 | XML_CHAR_ENCODING_8859_4= 13,/* ISO-8859-4 */ |
| 71 | XML_CHAR_ENCODING_8859_5= 14,/* ISO-8859-5 */ |
| 72 | XML_CHAR_ENCODING_8859_6= 15,/* ISO-8859-6 */ |
| 73 | XML_CHAR_ENCODING_8859_7= 16,/* ISO-8859-7 */ |
| 74 | XML_CHAR_ENCODING_8859_8= 17,/* ISO-8859-8 */ |
| 75 | XML_CHAR_ENCODING_8859_9= 18,/* ISO-8859-9 */ |
| 76 | XML_CHAR_ENCODING_2022_JP= 19,/* ISO-2022-JP */ |
| 77 | XML_CHAR_ENCODING_SHIFT_JIS=20,/* Shift_JIS */ |
| 78 | XML_CHAR_ENCODING_EUC_JP= 21,/* EUC-JP */ |
| 79 | XML_CHAR_ENCODING_ASCII= 22 /* pure ASCII */ |
| 80 | } xmlCharEncoding; |
| 81 | |
| 82 | /** |
| 83 | * xmlCharEncodingInputFunc: |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 84 | * @out: a pointer to an array of bytes to store the UTF-8 result |
Daniel Veillard | 60087f3 | 2001-10-10 09:45:09 +0000 | [diff] [blame] | 85 | * @outlen: the length of @out |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 86 | * @in: a pointer to an array of chars in the original encoding |
Daniel Veillard | 60087f3 | 2001-10-10 09:45:09 +0000 | [diff] [blame] | 87 | * @inlen: the length of @in |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 88 | * |
| 89 | * Take a block of chars in the original encoding and try to convert |
| 90 | * it to an UTF-8 block of chars out. |
| 91 | * |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 92 | * Returns the number of bytes written, -1 if lack of space, or -2 |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 93 | * if the transcoding failed. |
| 94 | * The value of @inlen after return is the number of octets consumed |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 95 | * if the return value is positive, else unpredictiable. |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 96 | * The value of @outlen after return is the number of octets consumed. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 97 | */ |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 98 | typedef int (* xmlCharEncodingInputFunc)(unsigned char *out, int *outlen, |
| 99 | const unsigned char *in, int *inlen); |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 100 | |
| 101 | |
| 102 | /** |
| 103 | * xmlCharEncodingOutputFunc: |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 104 | * @out: a pointer to an array of bytes to store the result |
Daniel Veillard | 60087f3 | 2001-10-10 09:45:09 +0000 | [diff] [blame] | 105 | * @outlen: the length of @out |
Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 106 | * @in: a pointer to an array of UTF-8 chars |
Daniel Veillard | 60087f3 | 2001-10-10 09:45:09 +0000 | [diff] [blame] | 107 | * @inlen: the length of @in |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 108 | * |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 109 | * Take a block of UTF-8 chars in and try to convert it to another |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 110 | * encoding. |
| 111 | * Note: a first call designed to produce heading info is called with |
Daniel Veillard | 61f2617 | 2002-03-12 18:46:39 +0000 | [diff] [blame] | 112 | * in = NULL. If stateful this should also initialize the encoder state. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 113 | * |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 114 | * Returns the number of bytes written, -1 if lack of space, or -2 |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 115 | * if the transcoding failed. |
| 116 | * The value of @inlen after return is the number of octets consumed |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 117 | * if the return value is positive, else unpredictiable. |
Daniel Veillard | 3671190 | 2004-02-11 13:25:26 +0000 | [diff] [blame] | 118 | * The value of @outlen after return is the number of octets produced. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 119 | */ |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 120 | typedef int (* xmlCharEncodingOutputFunc)(unsigned char *out, int *outlen, |
| 121 | const unsigned char *in, int *inlen); |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 122 | |
| 123 | |
| 124 | /* |
| 125 | * Block defining the handlers for non UTF-8 encodings. |
William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 126 | * If iconv is supported, there are two extra fields. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 127 | */ |
| 128 | |
| 129 | typedef struct _xmlCharEncodingHandler xmlCharEncodingHandler; |
| 130 | typedef xmlCharEncodingHandler *xmlCharEncodingHandlerPtr; |
| 131 | struct _xmlCharEncodingHandler { |
| 132 | char *name; |
| 133 | xmlCharEncodingInputFunc input; |
| 134 | xmlCharEncodingOutputFunc output; |
| 135 | #ifdef LIBXML_ICONV_ENABLED |
| 136 | iconv_t iconv_in; |
| 137 | iconv_t iconv_out; |
| 138 | #endif /* LIBXML_ICONV_ENABLED */ |
| 139 | }; |
| 140 | |
Daniel Veillard | 6c4ffaf | 2002-02-11 08:54:05 +0000 | [diff] [blame] | 141 | #ifdef __cplusplus |
| 142 | } |
| 143 | #endif |
| 144 | #include <libxml/tree.h> |
| 145 | #ifdef __cplusplus |
| 146 | extern "C" { |
| 147 | #endif |
| 148 | |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 149 | /* |
Daniel Veillard | 61f2617 | 2002-03-12 18:46:39 +0000 | [diff] [blame] | 150 | * Interfaces for encoding handlers. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 151 | */ |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 152 | XMLPUBFUN void XMLCALL |
| 153 | xmlInitCharEncodingHandlers (void); |
| 154 | XMLPUBFUN void XMLCALL |
| 155 | xmlCleanupCharEncodingHandlers (void); |
| 156 | XMLPUBFUN void XMLCALL |
| 157 | xmlRegisterCharEncodingHandler (xmlCharEncodingHandlerPtr handler); |
| 158 | XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 159 | xmlGetCharEncodingHandler (xmlCharEncoding enc); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 160 | XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 161 | xmlFindCharEncodingHandler (const char *name); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 162 | XMLPUBFUN xmlCharEncodingHandlerPtr XMLCALL |
Daniel Veillard | 6f46f6c | 2002-08-01 12:22:24 +0000 | [diff] [blame] | 163 | xmlNewCharEncodingHandler (const char *name, |
| 164 | xmlCharEncodingInputFunc input, |
| 165 | xmlCharEncodingOutputFunc output); |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 166 | |
| 167 | /* |
Daniel Veillard | 61f2617 | 2002-03-12 18:46:39 +0000 | [diff] [blame] | 168 | * Interfaces for encoding names and aliases. |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 169 | */ |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 170 | XMLPUBFUN int XMLCALL |
| 171 | xmlAddEncodingAlias (const char *name, |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 172 | const char *alias); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 173 | XMLPUBFUN int XMLCALL |
| 174 | xmlDelEncodingAlias (const char *alias); |
| 175 | XMLPUBFUN const char * XMLCALL |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 176 | xmlGetEncodingAlias (const char *alias); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 177 | XMLPUBFUN void XMLCALL |
| 178 | xmlCleanupEncodingAliases (void); |
| 179 | XMLPUBFUN xmlCharEncoding XMLCALL |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 180 | xmlParseCharEncoding (const char *name); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 181 | XMLPUBFUN const char * XMLCALL |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 182 | xmlGetCharEncodingName (xmlCharEncoding enc); |
| 183 | |
| 184 | /* |
| 185 | * Interfaces directly used by the parsers. |
| 186 | */ |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 187 | XMLPUBFUN xmlCharEncoding XMLCALL |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 188 | xmlDetectCharEncoding (const unsigned char *in, |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 189 | int len); |
| 190 | |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 191 | XMLPUBFUN int XMLCALL |
| 192 | xmlCharEncOutFunc (xmlCharEncodingHandler *handler, |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 193 | xmlBufferPtr out, |
| 194 | xmlBufferPtr in); |
| 195 | |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 196 | XMLPUBFUN int XMLCALL |
| 197 | xmlCharEncInFunc (xmlCharEncodingHandler *handler, |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 198 | xmlBufferPtr out, |
| 199 | xmlBufferPtr in); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 200 | XMLPUBFUN int XMLCALL |
| 201 | xmlCharEncFirstLine (xmlCharEncodingHandler *handler, |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 202 | xmlBufferPtr out, |
| 203 | xmlBufferPtr in); |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 204 | XMLPUBFUN int XMLCALL |
| 205 | xmlCharEncCloseFunc (xmlCharEncodingHandler *handler); |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 206 | |
Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 207 | /* |
| 208 | * Export a few useful functions |
| 209 | */ |
William M. Brack | 21e4ef2 | 2005-01-02 09:53:13 +0000 | [diff] [blame] | 210 | #ifdef LIBXML_OUTPUT_ENABLED |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 211 | XMLPUBFUN int XMLCALL |
| 212 | UTF8Toisolat1 (unsigned char *out, |
Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 213 | int *outlen, |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 214 | const unsigned char *in, |
Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 215 | int *inlen); |
William M. Brack | 21e4ef2 | 2005-01-02 09:53:13 +0000 | [diff] [blame] | 216 | #endif /* LIBXML_OUTPUT_ENABLED */ |
Igor Zlatkovic | 76874e4 | 2003-08-25 09:05:12 +0000 | [diff] [blame] | 217 | XMLPUBFUN int XMLCALL |
| 218 | isolat1ToUTF8 (unsigned char *out, |
Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 219 | int *outlen, |
Daniel Veillard | 963d2ae | 2002-01-20 22:08:18 +0000 | [diff] [blame] | 220 | const unsigned char *in, |
Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 221 | int *inlen); |
Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 222 | #ifdef __cplusplus |
| 223 | } |
| 224 | #endif |
| 225 | |
| 226 | #endif /* __XML_CHAR_ENCODING_H__ */ |