| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1 | /* | 
|  | 2 | * encoding.c : implements the encoding conversion functions needed for XML | 
|  | 3 | * | 
|  | 4 | * Related specs: | 
|  | 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 | 
|  | 8 | * [ISO-8859-1]   ISO Latin-1 characters codes. | 
|  | 9 | * [UNICODE]      The Unicode Consortium, "The Unicode Standard -- | 
|  | 10 | *                Worldwide Character Encoding -- Version 1.0", Addison- | 
|  | 11 | *                Wesley, Volume 1, 1991, Volume 2, 1992.  UTF-8 is | 
|  | 12 | *                described in Unicode Technical Report #4. | 
|  | 13 | * [US-ASCII]     Coded Character Set--7-bit American Standard Code for | 
|  | 14 | *                Information Interchange, ANSI X3.4-1986. | 
|  | 15 | * | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 16 | * See Copyright for the status of this software. | 
|  | 17 | * | 
| Daniel Veillard | c5d6434 | 2001-06-24 12:13:24 +0000 | [diff] [blame] | 18 | * daniel@veillard.com | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 19 | * | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 20 | * Original code for IsoLatin1 and UTF-16 by "Martin J. Duerst" <duerst@w3.org> | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 21 | */ | 
|  | 22 |  | 
| Daniel Veillard | 34ce8be | 2002-03-18 19:37:11 +0000 | [diff] [blame] | 23 | #define IN_LIBXML | 
| Bjorn Reese | 70a9da5 | 2001-04-21 16:57:29 +0000 | [diff] [blame] | 24 | #include "libxml.h" | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 25 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 26 | #include <string.h> | 
|  | 27 |  | 
|  | 28 | #ifdef HAVE_CTYPE_H | 
|  | 29 | #include <ctype.h> | 
|  | 30 | #endif | 
|  | 31 | #ifdef HAVE_STDLIB_H | 
|  | 32 | #include <stdlib.h> | 
|  | 33 | #endif | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 34 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 35 | #ifdef HAVE_ERRNO_H | 
|  | 36 | #include <errno.h> | 
|  | 37 | #endif | 
|  | 38 | #endif | 
|  | 39 | #include <libxml/encoding.h> | 
|  | 40 | #include <libxml/xmlmemory.h> | 
|  | 41 | #ifdef LIBXML_HTML_ENABLED | 
|  | 42 | #include <libxml/HTMLparser.h> | 
|  | 43 | #endif | 
| Daniel Veillard | 64a411c | 2001-10-15 12:32:07 +0000 | [diff] [blame] | 44 | #include <libxml/globals.h> | 
| Daniel Veillard | a4617b8 | 2001-11-04 20:19:12 +0000 | [diff] [blame] | 45 | #include <libxml/xmlerror.h> | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 46 |  | 
| Daniel Veillard | 2209073 | 2001-07-16 00:06:07 +0000 | [diff] [blame] | 47 | static xmlCharEncodingHandlerPtr xmlUTF16LEHandler = NULL; | 
|  | 48 | static xmlCharEncodingHandlerPtr xmlUTF16BEHandler = NULL; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 49 |  | 
|  | 50 | typedef struct _xmlCharEncodingAlias xmlCharEncodingAlias; | 
|  | 51 | typedef xmlCharEncodingAlias *xmlCharEncodingAliasPtr; | 
|  | 52 | struct _xmlCharEncodingAlias { | 
|  | 53 | const char *name; | 
|  | 54 | const char *alias; | 
|  | 55 | }; | 
|  | 56 |  | 
|  | 57 | static xmlCharEncodingAliasPtr xmlCharEncodingAliases = NULL; | 
|  | 58 | static int xmlCharEncodingAliasesNb = 0; | 
|  | 59 | static int xmlCharEncodingAliasesMax = 0; | 
|  | 60 |  | 
|  | 61 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 62 | #if 0 | 
|  | 63 | #define DEBUG_ENCODING  /* Define this to get encoding traces */ | 
|  | 64 | #endif | 
| William M. Brack | 16db7b6 | 2003-08-07 13:12:49 +0000 | [diff] [blame] | 65 | #else | 
|  | 66 | #ifdef LIBXML_ISO8859X_ENABLED | 
|  | 67 | static void xmlRegisterCharEncodingHandlersISO8859x (void); | 
|  | 68 | #endif | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 69 | #endif | 
|  | 70 |  | 
|  | 71 | static int xmlLittleEndian = 1; | 
|  | 72 |  | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 73 |  | 
|  | 74 | /************************************************************************ | 
|  | 75 | *									* | 
|  | 76 | *		Conversions To/From UTF8 encoding			* | 
|  | 77 | *									* | 
|  | 78 | ************************************************************************/ | 
|  | 79 |  | 
|  | 80 | /** | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 81 | * asciiToUTF8: | 
|  | 82 | * @out:  a pointer to an array of bytes to store the result | 
|  | 83 | * @outlen:  the length of @out | 
|  | 84 | * @in:  a pointer to an array of ASCII chars | 
|  | 85 | * @inlen:  the length of @in | 
|  | 86 | * | 
|  | 87 | * Take a block of ASCII chars in and try to convert it to an UTF-8 | 
|  | 88 | * block of chars out. | 
|  | 89 | * Returns 0 if success, or -1 otherwise | 
|  | 90 | * 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] | 91 | *     if the return value is positive, else unpredictable. | 
|  | 92 | * The value of @outlen after return is the number of octets consumed. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 93 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 94 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 95 | asciiToUTF8(unsigned char* out, int *outlen, | 
|  | 96 | const unsigned char* in, int *inlen) { | 
|  | 97 | unsigned char* outstart = out; | 
|  | 98 | const unsigned char* base = in; | 
|  | 99 | const unsigned char* processed = in; | 
|  | 100 | unsigned char* outend = out + *outlen; | 
|  | 101 | const unsigned char* inend; | 
|  | 102 | unsigned int c; | 
|  | 103 | int bits; | 
|  | 104 |  | 
|  | 105 | inend = in + (*inlen); | 
|  | 106 | while ((in < inend) && (out - outstart + 5 < *outlen)) { | 
|  | 107 | c= *in++; | 
|  | 108 |  | 
|  | 109 | /* assertion: c is a single UTF-4 value */ | 
|  | 110 | if (out >= outend) | 
|  | 111 | break; | 
|  | 112 | if      (c <    0x80) {  *out++=  c;                bits= -6; } | 
|  | 113 | else { | 
|  | 114 | *outlen = out - outstart; | 
|  | 115 | *inlen = processed - base; | 
|  | 116 | return(-1); | 
|  | 117 | } | 
|  | 118 |  | 
|  | 119 | for ( ; bits >= 0; bits-= 6) { | 
|  | 120 | if (out >= outend) | 
|  | 121 | break; | 
|  | 122 | *out++= ((c >> bits) & 0x3F) | 0x80; | 
|  | 123 | } | 
|  | 124 | processed = (const unsigned char*) in; | 
|  | 125 | } | 
|  | 126 | *outlen = out - outstart; | 
|  | 127 | *inlen = processed - base; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 128 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 129 | } | 
|  | 130 |  | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 131 | #ifdef LIBXML_OUTPUT_ENABLED | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 132 | /** | 
|  | 133 | * UTF8Toascii: | 
|  | 134 | * @out:  a pointer to an array of bytes to store the result | 
|  | 135 | * @outlen:  the length of @out | 
|  | 136 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 137 | * @inlen:  the length of @in | 
|  | 138 | * | 
|  | 139 | * Take a block of UTF-8 chars in and try to convert it to an ASCII | 
|  | 140 | * block of chars out. | 
|  | 141 | * | 
|  | 142 | * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise | 
|  | 143 | * 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] | 144 | *     if the return value is positive, else unpredictable. | 
|  | 145 | * The value of @outlen after return is the number of octets consumed. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 146 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 147 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 148 | UTF8Toascii(unsigned char* out, int *outlen, | 
|  | 149 | const unsigned char* in, int *inlen) { | 
|  | 150 | const unsigned char* processed = in; | 
|  | 151 | const unsigned char* outend; | 
|  | 152 | const unsigned char* outstart = out; | 
|  | 153 | const unsigned char* instart = in; | 
|  | 154 | const unsigned char* inend; | 
|  | 155 | unsigned int c, d; | 
|  | 156 | int trailing; | 
|  | 157 |  | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 158 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL)) return(-1); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 159 | if (in == NULL) { | 
|  | 160 | /* | 
|  | 161 | * initialization nothing to do | 
|  | 162 | */ | 
|  | 163 | *outlen = 0; | 
|  | 164 | *inlen = 0; | 
|  | 165 | return(0); | 
|  | 166 | } | 
|  | 167 | inend = in + (*inlen); | 
|  | 168 | outend = out + (*outlen); | 
|  | 169 | while (in < inend) { | 
|  | 170 | d = *in++; | 
|  | 171 | if      (d < 0x80)  { c= d; trailing= 0; } | 
|  | 172 | else if (d < 0xC0) { | 
|  | 173 | /* trailing byte in leading position */ | 
|  | 174 | *outlen = out - outstart; | 
|  | 175 | *inlen = processed - instart; | 
|  | 176 | return(-2); | 
|  | 177 | } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; } | 
|  | 178 | else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; } | 
|  | 179 | else if (d < 0xF8)  { c= d & 0x07; trailing= 3; } | 
|  | 180 | else { | 
|  | 181 | /* no chance for this in Ascii */ | 
|  | 182 | *outlen = out - outstart; | 
|  | 183 | *inlen = processed - instart; | 
|  | 184 | return(-2); | 
|  | 185 | } | 
|  | 186 |  | 
|  | 187 | if (inend - in < trailing) { | 
|  | 188 | break; | 
|  | 189 | } | 
|  | 190 |  | 
|  | 191 | for ( ; trailing; trailing--) { | 
|  | 192 | if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) | 
|  | 193 | break; | 
|  | 194 | c <<= 6; | 
|  | 195 | c |= d & 0x3F; | 
|  | 196 | } | 
|  | 197 |  | 
|  | 198 | /* assertion: c is a single UTF-4 value */ | 
|  | 199 | if (c < 0x80) { | 
|  | 200 | if (out >= outend) | 
|  | 201 | break; | 
|  | 202 | *out++ = c; | 
|  | 203 | } else { | 
|  | 204 | /* no chance for this in Ascii */ | 
|  | 205 | *outlen = out - outstart; | 
|  | 206 | *inlen = processed - instart; | 
|  | 207 | return(-2); | 
|  | 208 | } | 
|  | 209 | processed = in; | 
|  | 210 | } | 
|  | 211 | *outlen = out - outstart; | 
|  | 212 | *inlen = processed - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 213 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 214 | } | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 215 | #endif /* LIBXML_OUTPUT_ENABLED */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 216 |  | 
|  | 217 | /** | 
|  | 218 | * isolat1ToUTF8: | 
|  | 219 | * @out:  a pointer to an array of bytes to store the result | 
|  | 220 | * @outlen:  the length of @out | 
|  | 221 | * @in:  a pointer to an array of ISO Latin 1 chars | 
|  | 222 | * @inlen:  the length of @in | 
|  | 223 | * | 
|  | 224 | * Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8 | 
|  | 225 | * block of chars out. | 
|  | 226 | * Returns 0 if success, or -1 otherwise | 
|  | 227 | * 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] | 228 | *     if the return value is positive, else unpredictable. | 
|  | 229 | * The value of @outlen after return is the number of octets consumed. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 230 | */ | 
|  | 231 | int | 
|  | 232 | isolat1ToUTF8(unsigned char* out, int *outlen, | 
|  | 233 | const unsigned char* in, int *inlen) { | 
|  | 234 | unsigned char* outstart = out; | 
|  | 235 | const unsigned char* base = in; | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 236 | unsigned char* outend; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 237 | const unsigned char* inend; | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 238 | const unsigned char* instop; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 239 |  | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 240 | if ((out == NULL) || (in == NULL) || (outlen == NULL) || (inlen == NULL)) | 
|  | 241 | return(-1); | 
|  | 242 |  | 
|  | 243 | outend = out + *outlen; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 244 | inend = in + (*inlen); | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 245 | instop = inend; | 
|  | 246 |  | 
|  | 247 | while (in < inend && out < outend - 1) { | 
| Daniel Veillard | 182d32a | 2004-02-09 12:42:55 +0000 | [diff] [blame] | 248 | if (*in >= 0x80) { | 
|  | 249 | *out++ = (((*in) >>  6) & 0x1F) | 0xC0; | 
|  | 250 | *out++ = ((*in) & 0x3F) | 0x80; | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 251 | ++in; | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 252 | } | 
|  | 253 | if (instop - in > outend - out) instop = in + (outend - out); | 
| Daniel Veillard | 182d32a | 2004-02-09 12:42:55 +0000 | [diff] [blame] | 254 | while (in < instop && *in < 0x80) { | 
|  | 255 | *out++ = *in++; | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 256 | } | 
|  | 257 | } | 
| Daniel Veillard | 182d32a | 2004-02-09 12:42:55 +0000 | [diff] [blame] | 258 | if (in < inend && out < outend && *in < 0x80) { | 
|  | 259 | *out++ = *in++; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 260 | } | 
|  | 261 | *outlen = out - outstart; | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 262 | *inlen = in - base; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 263 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 264 | } | 
|  | 265 |  | 
| Daniel Veillard | 81601f9 | 2003-01-14 13:42:37 +0000 | [diff] [blame] | 266 | /** | 
|  | 267 | * UTF8ToUTF8: | 
|  | 268 | * @out:  a pointer to an array of bytes to store the result | 
|  | 269 | * @outlen:  the length of @out | 
|  | 270 | * @inb:  a pointer to an array of UTF-8 chars | 
|  | 271 | * @inlenb:  the length of @in in UTF-8 chars | 
|  | 272 | * | 
|  | 273 | * No op copy operation for UTF8 handling. | 
|  | 274 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 275 | * Returns the number of bytes written, or -1 if lack of space. | 
| Daniel Veillard | 81601f9 | 2003-01-14 13:42:37 +0000 | [diff] [blame] | 276 | *     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] | 277 | *     if the return value is positive, else unpredictable. | 
| Daniel Veillard | 81601f9 | 2003-01-14 13:42:37 +0000 | [diff] [blame] | 278 | */ | 
|  | 279 | static int | 
|  | 280 | UTF8ToUTF8(unsigned char* out, int *outlen, | 
|  | 281 | const unsigned char* inb, int *inlenb) | 
|  | 282 | { | 
|  | 283 | int len; | 
|  | 284 |  | 
|  | 285 | if ((out == NULL) || (inb == NULL) || (outlen == NULL) || (inlenb == NULL)) | 
|  | 286 | return(-1); | 
|  | 287 | if (*outlen > *inlenb) { | 
|  | 288 | len = *inlenb; | 
|  | 289 | } else { | 
|  | 290 | len = *outlen; | 
|  | 291 | } | 
|  | 292 | if (len < 0) | 
|  | 293 | return(-1); | 
|  | 294 |  | 
|  | 295 | memcpy(out, inb, len); | 
|  | 296 |  | 
|  | 297 | *outlen = len; | 
|  | 298 | *inlenb = len; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 299 | return(*outlen); | 
| Daniel Veillard | 81601f9 | 2003-01-14 13:42:37 +0000 | [diff] [blame] | 300 | } | 
|  | 301 |  | 
| Daniel Veillard | e72c756 | 2002-05-31 09:47:30 +0000 | [diff] [blame] | 302 |  | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 303 | #ifdef LIBXML_OUTPUT_ENABLED | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 304 | /** | 
|  | 305 | * UTF8Toisolat1: | 
|  | 306 | * @out:  a pointer to an array of bytes to store the result | 
|  | 307 | * @outlen:  the length of @out | 
|  | 308 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 309 | * @inlen:  the length of @in | 
|  | 310 | * | 
|  | 311 | * Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1 | 
|  | 312 | * block of chars out. | 
|  | 313 | * | 
|  | 314 | * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise | 
|  | 315 | * 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] | 316 | *     if the return value is positive, else unpredictable. | 
|  | 317 | * The value of @outlen after return is the number of octets consumed. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 318 | */ | 
|  | 319 | int | 
|  | 320 | UTF8Toisolat1(unsigned char* out, int *outlen, | 
|  | 321 | const unsigned char* in, int *inlen) { | 
|  | 322 | const unsigned char* processed = in; | 
|  | 323 | const unsigned char* outend; | 
|  | 324 | const unsigned char* outstart = out; | 
|  | 325 | const unsigned char* instart = in; | 
|  | 326 | const unsigned char* inend; | 
|  | 327 | unsigned int c, d; | 
|  | 328 | int trailing; | 
|  | 329 |  | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 330 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL)) return(-1); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 331 | if (in == NULL) { | 
|  | 332 | /* | 
|  | 333 | * initialization nothing to do | 
|  | 334 | */ | 
|  | 335 | *outlen = 0; | 
|  | 336 | *inlen = 0; | 
|  | 337 | return(0); | 
|  | 338 | } | 
|  | 339 | inend = in + (*inlen); | 
|  | 340 | outend = out + (*outlen); | 
|  | 341 | while (in < inend) { | 
|  | 342 | d = *in++; | 
|  | 343 | if      (d < 0x80)  { c= d; trailing= 0; } | 
|  | 344 | else if (d < 0xC0) { | 
|  | 345 | /* trailing byte in leading position */ | 
|  | 346 | *outlen = out - outstart; | 
|  | 347 | *inlen = processed - instart; | 
|  | 348 | return(-2); | 
|  | 349 | } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; } | 
|  | 350 | else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; } | 
|  | 351 | else if (d < 0xF8)  { c= d & 0x07; trailing= 3; } | 
|  | 352 | else { | 
|  | 353 | /* no chance for this in IsoLat1 */ | 
|  | 354 | *outlen = out - outstart; | 
|  | 355 | *inlen = processed - instart; | 
|  | 356 | return(-2); | 
|  | 357 | } | 
|  | 358 |  | 
|  | 359 | if (inend - in < trailing) { | 
|  | 360 | break; | 
|  | 361 | } | 
|  | 362 |  | 
|  | 363 | for ( ; trailing; trailing--) { | 
|  | 364 | if (in >= inend) | 
|  | 365 | break; | 
|  | 366 | if (((d= *in++) & 0xC0) != 0x80) { | 
|  | 367 | *outlen = out - outstart; | 
|  | 368 | *inlen = processed - instart; | 
|  | 369 | return(-2); | 
|  | 370 | } | 
|  | 371 | c <<= 6; | 
|  | 372 | c |= d & 0x3F; | 
|  | 373 | } | 
|  | 374 |  | 
|  | 375 | /* assertion: c is a single UTF-4 value */ | 
|  | 376 | if (c <= 0xFF) { | 
|  | 377 | if (out >= outend) | 
|  | 378 | break; | 
|  | 379 | *out++ = c; | 
|  | 380 | } else { | 
|  | 381 | /* no chance for this in IsoLat1 */ | 
|  | 382 | *outlen = out - outstart; | 
|  | 383 | *inlen = processed - instart; | 
|  | 384 | return(-2); | 
|  | 385 | } | 
|  | 386 | processed = in; | 
|  | 387 | } | 
|  | 388 | *outlen = out - outstart; | 
|  | 389 | *inlen = processed - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 390 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 391 | } | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 392 | #endif /* LIBXML_OUTPUT_ENABLED */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 393 |  | 
|  | 394 | /** | 
|  | 395 | * UTF16LEToUTF8: | 
|  | 396 | * @out:  a pointer to an array of bytes to store the result | 
|  | 397 | * @outlen:  the length of @out | 
|  | 398 | * @inb:  a pointer to an array of UTF-16LE passwd as a byte array | 
|  | 399 | * @inlenb:  the length of @in in UTF-16LE chars | 
|  | 400 | * | 
|  | 401 | * Take a block of UTF-16LE ushorts in and try to convert it to an UTF-8 | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 402 | * block of chars out. This function assumes the endian property | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 403 | * is the same between the native type of this machine and the | 
|  | 404 | * inputed one. | 
|  | 405 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 406 | * Returns the number of bytes written, or -1 if lack of space, or -2 | 
|  | 407 | *     if the transcoding fails (if *in is not a valid utf16 string) | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 408 | *     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] | 409 | *     if the return value is positive, else unpredictable. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 410 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 411 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 412 | UTF16LEToUTF8(unsigned char* out, int *outlen, | 
|  | 413 | const unsigned char* inb, int *inlenb) | 
|  | 414 | { | 
|  | 415 | unsigned char* outstart = out; | 
|  | 416 | const unsigned char* processed = inb; | 
|  | 417 | unsigned char* outend = out + *outlen; | 
|  | 418 | unsigned short* in = (unsigned short*) inb; | 
|  | 419 | unsigned short* inend; | 
|  | 420 | unsigned int c, d, inlen; | 
|  | 421 | unsigned char *tmp; | 
|  | 422 | int bits; | 
|  | 423 |  | 
|  | 424 | if ((*inlenb % 2) == 1) | 
|  | 425 | (*inlenb)--; | 
|  | 426 | inlen = *inlenb / 2; | 
|  | 427 | inend = in + inlen; | 
|  | 428 | while ((in < inend) && (out - outstart + 5 < *outlen)) { | 
|  | 429 | if (xmlLittleEndian) { | 
|  | 430 | c= *in++; | 
|  | 431 | } else { | 
|  | 432 | tmp = (unsigned char *) in; | 
|  | 433 | c = *tmp++; | 
|  | 434 | c = c | (((unsigned int)*tmp) << 8); | 
|  | 435 | in++; | 
|  | 436 | } | 
|  | 437 | if ((c & 0xFC00) == 0xD800) {    /* surrogates */ | 
|  | 438 | if (in >= inend) {           /* (in > inend) shouldn't happens */ | 
|  | 439 | break; | 
|  | 440 | } | 
|  | 441 | if (xmlLittleEndian) { | 
|  | 442 | d = *in++; | 
|  | 443 | } else { | 
|  | 444 | tmp = (unsigned char *) in; | 
|  | 445 | d = *tmp++; | 
|  | 446 | d = d | (((unsigned int)*tmp) << 8); | 
|  | 447 | in++; | 
|  | 448 | } | 
|  | 449 | if ((d & 0xFC00) == 0xDC00) { | 
|  | 450 | c &= 0x03FF; | 
|  | 451 | c <<= 10; | 
|  | 452 | c |= d & 0x03FF; | 
|  | 453 | c += 0x10000; | 
|  | 454 | } | 
|  | 455 | else { | 
|  | 456 | *outlen = out - outstart; | 
|  | 457 | *inlenb = processed - inb; | 
|  | 458 | return(-2); | 
|  | 459 | } | 
|  | 460 | } | 
|  | 461 |  | 
|  | 462 | /* assertion: c is a single UTF-4 value */ | 
|  | 463 | if (out >= outend) | 
|  | 464 | break; | 
|  | 465 | if      (c <    0x80) {  *out++=  c;                bits= -6; } | 
|  | 466 | else if (c <   0x800) {  *out++= ((c >>  6) & 0x1F) | 0xC0;  bits=  0; } | 
|  | 467 | else if (c < 0x10000) {  *out++= ((c >> 12) & 0x0F) | 0xE0;  bits=  6; } | 
|  | 468 | else                  {  *out++= ((c >> 18) & 0x07) | 0xF0;  bits= 12; } | 
|  | 469 |  | 
|  | 470 | for ( ; bits >= 0; bits-= 6) { | 
|  | 471 | if (out >= outend) | 
|  | 472 | break; | 
|  | 473 | *out++= ((c >> bits) & 0x3F) | 0x80; | 
|  | 474 | } | 
|  | 475 | processed = (const unsigned char*) in; | 
|  | 476 | } | 
|  | 477 | *outlen = out - outstart; | 
|  | 478 | *inlenb = processed - inb; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 479 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 480 | } | 
|  | 481 |  | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 482 | #ifdef LIBXML_OUTPUT_ENABLED | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 483 | /** | 
|  | 484 | * UTF8ToUTF16LE: | 
|  | 485 | * @outb:  a pointer to an array of bytes to store the result | 
|  | 486 | * @outlen:  the length of @outb | 
|  | 487 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 488 | * @inlen:  the length of @in | 
|  | 489 | * | 
|  | 490 | * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE | 
|  | 491 | * block of chars out. | 
|  | 492 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 493 | * Returns the number of bytes written, or -1 if lack of space, or -2 | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 494 | *     if the transcoding failed. | 
|  | 495 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 496 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 497 | UTF8ToUTF16LE(unsigned char* outb, int *outlen, | 
|  | 498 | const unsigned char* in, int *inlen) | 
|  | 499 | { | 
|  | 500 | unsigned short* out = (unsigned short*) outb; | 
|  | 501 | const unsigned char* processed = in; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 502 | const unsigned char *const instart = in; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 503 | unsigned short* outstart= out; | 
|  | 504 | unsigned short* outend; | 
|  | 505 | const unsigned char* inend= in+*inlen; | 
|  | 506 | unsigned int c, d; | 
|  | 507 | int trailing; | 
|  | 508 | unsigned char *tmp; | 
|  | 509 | unsigned short tmp1, tmp2; | 
|  | 510 |  | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 511 | /* UTF16LE encoding has no BOM */ | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 512 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL)) return(-1); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 513 | if (in == NULL) { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 514 | *outlen = 0; | 
|  | 515 | *inlen = 0; | 
|  | 516 | return(0); | 
|  | 517 | } | 
|  | 518 | outend = out + (*outlen / 2); | 
|  | 519 | while (in < inend) { | 
|  | 520 | d= *in++; | 
|  | 521 | if      (d < 0x80)  { c= d; trailing= 0; } | 
|  | 522 | else if (d < 0xC0) { | 
|  | 523 | /* trailing byte in leading position */ | 
|  | 524 | *outlen = (out - outstart) * 2; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 525 | *inlen = processed - instart; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 526 | return(-2); | 
|  | 527 | } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; } | 
|  | 528 | else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; } | 
|  | 529 | else if (d < 0xF8)  { c= d & 0x07; trailing= 3; } | 
|  | 530 | else { | 
|  | 531 | /* no chance for this in UTF-16 */ | 
|  | 532 | *outlen = (out - outstart) * 2; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 533 | *inlen = processed - instart; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 534 | return(-2); | 
|  | 535 | } | 
|  | 536 |  | 
|  | 537 | if (inend - in < trailing) { | 
|  | 538 | break; | 
|  | 539 | } | 
|  | 540 |  | 
|  | 541 | for ( ; trailing; trailing--) { | 
|  | 542 | if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) | 
|  | 543 | break; | 
|  | 544 | c <<= 6; | 
|  | 545 | c |= d & 0x3F; | 
|  | 546 | } | 
|  | 547 |  | 
|  | 548 | /* assertion: c is a single UTF-4 value */ | 
|  | 549 | if (c < 0x10000) { | 
|  | 550 | if (out >= outend) | 
|  | 551 | break; | 
|  | 552 | if (xmlLittleEndian) { | 
|  | 553 | *out++ = c; | 
|  | 554 | } else { | 
|  | 555 | tmp = (unsigned char *) out; | 
|  | 556 | *tmp = c ; | 
|  | 557 | *(tmp + 1) = c >> 8 ; | 
|  | 558 | out++; | 
|  | 559 | } | 
|  | 560 | } | 
|  | 561 | else if (c < 0x110000) { | 
|  | 562 | if (out+1 >= outend) | 
|  | 563 | break; | 
|  | 564 | c -= 0x10000; | 
|  | 565 | if (xmlLittleEndian) { | 
|  | 566 | *out++ = 0xD800 | (c >> 10); | 
|  | 567 | *out++ = 0xDC00 | (c & 0x03FF); | 
|  | 568 | } else { | 
|  | 569 | tmp1 = 0xD800 | (c >> 10); | 
|  | 570 | tmp = (unsigned char *) out; | 
|  | 571 | *tmp = (unsigned char) tmp1; | 
|  | 572 | *(tmp + 1) = tmp1 >> 8; | 
|  | 573 | out++; | 
|  | 574 |  | 
|  | 575 | tmp2 = 0xDC00 | (c & 0x03FF); | 
|  | 576 | tmp = (unsigned char *) out; | 
|  | 577 | *tmp  = (unsigned char) tmp2; | 
|  | 578 | *(tmp + 1) = tmp2 >> 8; | 
|  | 579 | out++; | 
|  | 580 | } | 
|  | 581 | } | 
|  | 582 | else | 
|  | 583 | break; | 
|  | 584 | processed = in; | 
|  | 585 | } | 
|  | 586 | *outlen = (out - outstart) * 2; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 587 | *inlen = processed - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 588 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 589 | } | 
|  | 590 |  | 
|  | 591 | /** | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 592 | * UTF8ToUTF16: | 
|  | 593 | * @outb:  a pointer to an array of bytes to store the result | 
|  | 594 | * @outlen:  the length of @outb | 
|  | 595 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 596 | * @inlen:  the length of @in | 
|  | 597 | * | 
|  | 598 | * Take a block of UTF-8 chars in and try to convert it to an UTF-16 | 
|  | 599 | * block of chars out. | 
|  | 600 | * | 
|  | 601 | * Returns the number of bytes written, or -1 if lack of space, or -2 | 
|  | 602 | *     if the transcoding failed. | 
|  | 603 | */ | 
|  | 604 | static int | 
|  | 605 | UTF8ToUTF16(unsigned char* outb, int *outlen, | 
|  | 606 | const unsigned char* in, int *inlen) | 
|  | 607 | { | 
|  | 608 | if (in == NULL) { | 
|  | 609 | /* | 
|  | 610 | * initialization, add the Byte Order Mark for UTF-16LE | 
|  | 611 | */ | 
|  | 612 | if (*outlen >= 2) { | 
|  | 613 | outb[0] = 0xFF; | 
|  | 614 | outb[1] = 0xFE; | 
|  | 615 | *outlen = 2; | 
|  | 616 | *inlen = 0; | 
|  | 617 | #ifdef DEBUG_ENCODING | 
|  | 618 | xmlGenericError(xmlGenericErrorContext, | 
|  | 619 | "Added FFFE Byte Order Mark\n"); | 
|  | 620 | #endif | 
|  | 621 | return(2); | 
|  | 622 | } | 
|  | 623 | *outlen = 0; | 
|  | 624 | *inlen = 0; | 
|  | 625 | return(0); | 
|  | 626 | } | 
|  | 627 | return (UTF8ToUTF16LE(outb, outlen, in, inlen)); | 
|  | 628 | } | 
| William M. Brack | 030a7a1 | 2004-02-10 12:48:57 +0000 | [diff] [blame] | 629 | #endif /* LIBXML_OUTPUT_ENABLED */ | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 630 |  | 
|  | 631 | /** | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 632 | * UTF16BEToUTF8: | 
|  | 633 | * @out:  a pointer to an array of bytes to store the result | 
|  | 634 | * @outlen:  the length of @out | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 635 | * @inb:  a pointer to an array of UTF-16 passed as a byte array | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 636 | * @inlenb:  the length of @in in UTF-16 chars | 
|  | 637 | * | 
|  | 638 | * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8 | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 639 | * block of chars out. This function assumes the endian property | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 640 | * is the same between the native type of this machine and the | 
|  | 641 | * inputed one. | 
|  | 642 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 643 | * Returns the number of bytes written, or -1 if lack of space, or -2 | 
|  | 644 | *     if the transcoding fails (if *in is not a valid utf16 string) | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 645 | * 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] | 646 | *     if the return value is positive, else unpredictable. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 647 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 648 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 649 | UTF16BEToUTF8(unsigned char* out, int *outlen, | 
|  | 650 | const unsigned char* inb, int *inlenb) | 
|  | 651 | { | 
|  | 652 | unsigned char* outstart = out; | 
|  | 653 | const unsigned char* processed = inb; | 
|  | 654 | unsigned char* outend = out + *outlen; | 
|  | 655 | unsigned short* in = (unsigned short*) inb; | 
|  | 656 | unsigned short* inend; | 
|  | 657 | unsigned int c, d, inlen; | 
|  | 658 | unsigned char *tmp; | 
|  | 659 | int bits; | 
|  | 660 |  | 
|  | 661 | if ((*inlenb % 2) == 1) | 
|  | 662 | (*inlenb)--; | 
|  | 663 | inlen = *inlenb / 2; | 
|  | 664 | inend= in + inlen; | 
|  | 665 | while (in < inend) { | 
|  | 666 | if (xmlLittleEndian) { | 
|  | 667 | tmp = (unsigned char *) in; | 
|  | 668 | c = *tmp++; | 
|  | 669 | c = c << 8; | 
|  | 670 | c = c | (unsigned int) *tmp; | 
|  | 671 | in++; | 
|  | 672 | } else { | 
|  | 673 | c= *in++; | 
|  | 674 | } | 
|  | 675 | if ((c & 0xFC00) == 0xD800) {    /* surrogates */ | 
|  | 676 | if (in >= inend) {           /* (in > inend) shouldn't happens */ | 
|  | 677 | *outlen = out - outstart; | 
|  | 678 | *inlenb = processed - inb; | 
|  | 679 | return(-2); | 
|  | 680 | } | 
|  | 681 | if (xmlLittleEndian) { | 
|  | 682 | tmp = (unsigned char *) in; | 
|  | 683 | d = *tmp++; | 
|  | 684 | d = d << 8; | 
|  | 685 | d = d | (unsigned int) *tmp; | 
|  | 686 | in++; | 
|  | 687 | } else { | 
|  | 688 | d= *in++; | 
|  | 689 | } | 
|  | 690 | if ((d & 0xFC00) == 0xDC00) { | 
|  | 691 | c &= 0x03FF; | 
|  | 692 | c <<= 10; | 
|  | 693 | c |= d & 0x03FF; | 
|  | 694 | c += 0x10000; | 
|  | 695 | } | 
|  | 696 | else { | 
|  | 697 | *outlen = out - outstart; | 
|  | 698 | *inlenb = processed - inb; | 
|  | 699 | return(-2); | 
|  | 700 | } | 
|  | 701 | } | 
|  | 702 |  | 
|  | 703 | /* assertion: c is a single UTF-4 value */ | 
|  | 704 | if (out >= outend) | 
|  | 705 | break; | 
|  | 706 | if      (c <    0x80) {  *out++=  c;                bits= -6; } | 
|  | 707 | else if (c <   0x800) {  *out++= ((c >>  6) & 0x1F) | 0xC0;  bits=  0; } | 
|  | 708 | else if (c < 0x10000) {  *out++= ((c >> 12) & 0x0F) | 0xE0;  bits=  6; } | 
|  | 709 | else                  {  *out++= ((c >> 18) & 0x07) | 0xF0;  bits= 12; } | 
|  | 710 |  | 
|  | 711 | for ( ; bits >= 0; bits-= 6) { | 
|  | 712 | if (out >= outend) | 
|  | 713 | break; | 
|  | 714 | *out++= ((c >> bits) & 0x3F) | 0x80; | 
|  | 715 | } | 
|  | 716 | processed = (const unsigned char*) in; | 
|  | 717 | } | 
|  | 718 | *outlen = out - outstart; | 
|  | 719 | *inlenb = processed - inb; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 720 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 721 | } | 
|  | 722 |  | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 723 | #ifdef LIBXML_OUTPUT_ENABLED | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 724 | /** | 
|  | 725 | * UTF8ToUTF16BE: | 
|  | 726 | * @outb:  a pointer to an array of bytes to store the result | 
|  | 727 | * @outlen:  the length of @outb | 
|  | 728 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 729 | * @inlen:  the length of @in | 
|  | 730 | * | 
|  | 731 | * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE | 
|  | 732 | * block of chars out. | 
|  | 733 | * | 
|  | 734 | * Returns the number of byte written, or -1 by lack of space, or -2 | 
|  | 735 | *     if the transcoding failed. | 
|  | 736 | */ | 
| Daniel Veillard | 56a4cb8 | 2001-03-24 17:00:36 +0000 | [diff] [blame] | 737 | static int | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 738 | UTF8ToUTF16BE(unsigned char* outb, int *outlen, | 
|  | 739 | const unsigned char* in, int *inlen) | 
|  | 740 | { | 
|  | 741 | unsigned short* out = (unsigned short*) outb; | 
|  | 742 | const unsigned char* processed = in; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 743 | const unsigned char *const instart = in; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 744 | unsigned short* outstart= out; | 
|  | 745 | unsigned short* outend; | 
|  | 746 | const unsigned char* inend= in+*inlen; | 
|  | 747 | unsigned int c, d; | 
|  | 748 | int trailing; | 
|  | 749 | unsigned char *tmp; | 
|  | 750 | unsigned short tmp1, tmp2; | 
|  | 751 |  | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 752 | /* UTF-16BE has no BOM */ | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 753 | if ((outb == NULL) || (outlen == NULL) || (inlen == NULL)) return(-1); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 754 | if (in == NULL) { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 755 | *outlen = 0; | 
|  | 756 | *inlen = 0; | 
|  | 757 | return(0); | 
|  | 758 | } | 
|  | 759 | outend = out + (*outlen / 2); | 
|  | 760 | while (in < inend) { | 
|  | 761 | d= *in++; | 
|  | 762 | if      (d < 0x80)  { c= d; trailing= 0; } | 
|  | 763 | else if (d < 0xC0)  { | 
|  | 764 | /* trailing byte in leading position */ | 
|  | 765 | *outlen = out - outstart; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 766 | *inlen = processed - instart; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 767 | return(-2); | 
|  | 768 | } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; } | 
|  | 769 | else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; } | 
|  | 770 | else if (d < 0xF8)  { c= d & 0x07; trailing= 3; } | 
|  | 771 | else { | 
|  | 772 | /* no chance for this in UTF-16 */ | 
|  | 773 | *outlen = out - outstart; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 774 | *inlen = processed - instart; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 775 | return(-2); | 
|  | 776 | } | 
|  | 777 |  | 
|  | 778 | if (inend - in < trailing) { | 
|  | 779 | break; | 
|  | 780 | } | 
|  | 781 |  | 
|  | 782 | for ( ; trailing; trailing--) { | 
|  | 783 | if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))  break; | 
|  | 784 | c <<= 6; | 
|  | 785 | c |= d & 0x3F; | 
|  | 786 | } | 
|  | 787 |  | 
|  | 788 | /* assertion: c is a single UTF-4 value */ | 
|  | 789 | if (c < 0x10000) { | 
|  | 790 | if (out >= outend)  break; | 
|  | 791 | if (xmlLittleEndian) { | 
|  | 792 | tmp = (unsigned char *) out; | 
|  | 793 | *tmp = c >> 8; | 
|  | 794 | *(tmp + 1) = c; | 
|  | 795 | out++; | 
|  | 796 | } else { | 
|  | 797 | *out++ = c; | 
|  | 798 | } | 
|  | 799 | } | 
|  | 800 | else if (c < 0x110000) { | 
|  | 801 | if (out+1 >= outend)  break; | 
|  | 802 | c -= 0x10000; | 
|  | 803 | if (xmlLittleEndian) { | 
|  | 804 | tmp1 = 0xD800 | (c >> 10); | 
|  | 805 | tmp = (unsigned char *) out; | 
|  | 806 | *tmp = tmp1 >> 8; | 
|  | 807 | *(tmp + 1) = (unsigned char) tmp1; | 
|  | 808 | out++; | 
|  | 809 |  | 
|  | 810 | tmp2 = 0xDC00 | (c & 0x03FF); | 
|  | 811 | tmp = (unsigned char *) out; | 
|  | 812 | *tmp = tmp2 >> 8; | 
|  | 813 | *(tmp + 1) = (unsigned char) tmp2; | 
|  | 814 | out++; | 
|  | 815 | } else { | 
|  | 816 | *out++ = 0xD800 | (c >> 10); | 
|  | 817 | *out++ = 0xDC00 | (c & 0x03FF); | 
|  | 818 | } | 
|  | 819 | } | 
|  | 820 | else | 
|  | 821 | break; | 
|  | 822 | processed = in; | 
|  | 823 | } | 
|  | 824 | *outlen = (out - outstart) * 2; | 
| Daniel Veillard | ab1ae3a | 2003-08-14 12:19:54 +0000 | [diff] [blame] | 825 | *inlen = processed - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 826 | return(*outlen); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 827 | } | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 828 | #endif /* LIBXML_OUTPUT_ENABLED */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 829 |  | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 830 | /************************************************************************ | 
|  | 831 | *									* | 
|  | 832 | *		Generic encoding handling routines			* | 
|  | 833 | *									* | 
|  | 834 | ************************************************************************/ | 
|  | 835 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 836 | /** | 
|  | 837 | * xmlDetectCharEncoding: | 
|  | 838 | * @in:  a pointer to the first bytes of the XML entity, must be at least | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 839 | *       2 bytes long (at least 4 if encoding is UTF4 variant). | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 840 | * @len:  pointer to the length of the buffer | 
|  | 841 | * | 
|  | 842 | * Guess the encoding of the entity using the first bytes of the entity content | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 843 | * according to the non-normative appendix F of the XML-1.0 recommendation. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 844 | * | 
|  | 845 | * Returns one of the XML_CHAR_ENCODING_... values. | 
|  | 846 | */ | 
|  | 847 | xmlCharEncoding | 
|  | 848 | xmlDetectCharEncoding(const unsigned char* in, int len) | 
|  | 849 | { | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 850 | if (in == NULL) | 
|  | 851 | return(XML_CHAR_ENCODING_NONE); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 852 | if (len >= 4) { | 
|  | 853 | if ((in[0] == 0x00) && (in[1] == 0x00) && | 
|  | 854 | (in[2] == 0x00) && (in[3] == 0x3C)) | 
|  | 855 | return(XML_CHAR_ENCODING_UCS4BE); | 
|  | 856 | if ((in[0] == 0x3C) && (in[1] == 0x00) && | 
|  | 857 | (in[2] == 0x00) && (in[3] == 0x00)) | 
|  | 858 | return(XML_CHAR_ENCODING_UCS4LE); | 
|  | 859 | if ((in[0] == 0x00) && (in[1] == 0x00) && | 
|  | 860 | (in[2] == 0x3C) && (in[3] == 0x00)) | 
|  | 861 | return(XML_CHAR_ENCODING_UCS4_2143); | 
|  | 862 | if ((in[0] == 0x00) && (in[1] == 0x3C) && | 
|  | 863 | (in[2] == 0x00) && (in[3] == 0x00)) | 
|  | 864 | return(XML_CHAR_ENCODING_UCS4_3412); | 
|  | 865 | if ((in[0] == 0x4C) && (in[1] == 0x6F) && | 
|  | 866 | (in[2] == 0xA7) && (in[3] == 0x94)) | 
|  | 867 | return(XML_CHAR_ENCODING_EBCDIC); | 
|  | 868 | if ((in[0] == 0x3C) && (in[1] == 0x3F) && | 
|  | 869 | (in[2] == 0x78) && (in[3] == 0x6D)) | 
|  | 870 | return(XML_CHAR_ENCODING_UTF8); | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 871 | /* | 
|  | 872 | * Although not part of the recommendation, we also | 
|  | 873 | * attempt an "auto-recognition" of UTF-16LE and | 
|  | 874 | * UTF-16BE encodings. | 
|  | 875 | */ | 
|  | 876 | if ((in[0] == 0x3C) && (in[1] == 0x00) && | 
|  | 877 | (in[2] == 0x3F) && (in[3] == 0x00)) | 
|  | 878 | return(XML_CHAR_ENCODING_UTF16LE); | 
|  | 879 | if ((in[0] == 0x00) && (in[1] == 0x3C) && | 
|  | 880 | (in[2] == 0x00) && (in[3] == 0x3F)) | 
|  | 881 | return(XML_CHAR_ENCODING_UTF16BE); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 882 | } | 
| Daniel Veillard | 87a764e | 2001-06-20 17:41:10 +0000 | [diff] [blame] | 883 | if (len >= 3) { | 
|  | 884 | /* | 
|  | 885 | * Errata on XML-1.0 June 20 2001 | 
|  | 886 | * We now allow an UTF8 encoded BOM | 
|  | 887 | */ | 
|  | 888 | if ((in[0] == 0xEF) && (in[1] == 0xBB) && | 
|  | 889 | (in[2] == 0xBF)) | 
|  | 890 | return(XML_CHAR_ENCODING_UTF8); | 
|  | 891 | } | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 892 | /* For UTF-16 we can recognize by the BOM */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 893 | if (len >= 2) { | 
|  | 894 | if ((in[0] == 0xFE) && (in[1] == 0xFF)) | 
|  | 895 | return(XML_CHAR_ENCODING_UTF16BE); | 
|  | 896 | if ((in[0] == 0xFF) && (in[1] == 0xFE)) | 
|  | 897 | return(XML_CHAR_ENCODING_UTF16LE); | 
|  | 898 | } | 
|  | 899 | return(XML_CHAR_ENCODING_NONE); | 
|  | 900 | } | 
|  | 901 |  | 
|  | 902 | /** | 
|  | 903 | * xmlCleanupEncodingAliases: | 
|  | 904 | * | 
|  | 905 | * Unregisters all aliases | 
|  | 906 | */ | 
|  | 907 | void | 
|  | 908 | xmlCleanupEncodingAliases(void) { | 
|  | 909 | int i; | 
|  | 910 |  | 
|  | 911 | if (xmlCharEncodingAliases == NULL) | 
|  | 912 | return; | 
|  | 913 |  | 
|  | 914 | for (i = 0;i < xmlCharEncodingAliasesNb;i++) { | 
|  | 915 | if (xmlCharEncodingAliases[i].name != NULL) | 
|  | 916 | xmlFree((char *) xmlCharEncodingAliases[i].name); | 
|  | 917 | if (xmlCharEncodingAliases[i].alias != NULL) | 
|  | 918 | xmlFree((char *) xmlCharEncodingAliases[i].alias); | 
|  | 919 | } | 
|  | 920 | xmlCharEncodingAliasesNb = 0; | 
|  | 921 | xmlCharEncodingAliasesMax = 0; | 
|  | 922 | xmlFree(xmlCharEncodingAliases); | 
| Daniel Veillard | 73c6e53 | 2002-01-08 13:15:33 +0000 | [diff] [blame] | 923 | xmlCharEncodingAliases = NULL; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 924 | } | 
|  | 925 |  | 
|  | 926 | /** | 
|  | 927 | * xmlGetEncodingAlias: | 
|  | 928 | * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually) | 
|  | 929 | * | 
|  | 930 | * Lookup an encoding name for the given alias. | 
|  | 931 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 932 | * Returns NULL if not found, otherwise the original name | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 933 | */ | 
|  | 934 | const char * | 
|  | 935 | xmlGetEncodingAlias(const char *alias) { | 
|  | 936 | int i; | 
|  | 937 | char upper[100]; | 
|  | 938 |  | 
|  | 939 | if (alias == NULL) | 
|  | 940 | return(NULL); | 
|  | 941 |  | 
|  | 942 | if (xmlCharEncodingAliases == NULL) | 
|  | 943 | return(NULL); | 
|  | 944 |  | 
|  | 945 | for (i = 0;i < 99;i++) { | 
|  | 946 | upper[i] = toupper(alias[i]); | 
|  | 947 | if (upper[i] == 0) break; | 
|  | 948 | } | 
|  | 949 | upper[i] = 0; | 
|  | 950 |  | 
|  | 951 | /* | 
|  | 952 | * Walk down the list looking for a definition of the alias | 
|  | 953 | */ | 
|  | 954 | for (i = 0;i < xmlCharEncodingAliasesNb;i++) { | 
|  | 955 | if (!strcmp(xmlCharEncodingAliases[i].alias, upper)) { | 
|  | 956 | return(xmlCharEncodingAliases[i].name); | 
|  | 957 | } | 
|  | 958 | } | 
|  | 959 | return(NULL); | 
|  | 960 | } | 
|  | 961 |  | 
|  | 962 | /** | 
|  | 963 | * xmlAddEncodingAlias: | 
|  | 964 | * @name:  the encoding name as parsed, in UTF-8 format (ASCII actually) | 
|  | 965 | * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually) | 
|  | 966 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 967 | * Registers an alias @alias for an encoding named @name. Existing alias | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 968 | * will be overwritten. | 
|  | 969 | * | 
|  | 970 | * Returns 0 in case of success, -1 in case of error | 
|  | 971 | */ | 
|  | 972 | int | 
|  | 973 | xmlAddEncodingAlias(const char *name, const char *alias) { | 
|  | 974 | int i; | 
|  | 975 | char upper[100]; | 
|  | 976 |  | 
|  | 977 | if ((name == NULL) || (alias == NULL)) | 
|  | 978 | return(-1); | 
|  | 979 |  | 
|  | 980 | for (i = 0;i < 99;i++) { | 
|  | 981 | upper[i] = toupper(alias[i]); | 
|  | 982 | if (upper[i] == 0) break; | 
|  | 983 | } | 
|  | 984 | upper[i] = 0; | 
|  | 985 |  | 
|  | 986 | if (xmlCharEncodingAliases == NULL) { | 
|  | 987 | xmlCharEncodingAliasesNb = 0; | 
|  | 988 | xmlCharEncodingAliasesMax = 20; | 
|  | 989 | xmlCharEncodingAliases = (xmlCharEncodingAliasPtr) | 
|  | 990 | xmlMalloc(xmlCharEncodingAliasesMax * sizeof(xmlCharEncodingAlias)); | 
|  | 991 | if (xmlCharEncodingAliases == NULL) | 
|  | 992 | return(-1); | 
|  | 993 | } else if (xmlCharEncodingAliasesNb >= xmlCharEncodingAliasesMax) { | 
|  | 994 | xmlCharEncodingAliasesMax *= 2; | 
|  | 995 | xmlCharEncodingAliases = (xmlCharEncodingAliasPtr) | 
|  | 996 | xmlRealloc(xmlCharEncodingAliases, | 
|  | 997 | xmlCharEncodingAliasesMax * sizeof(xmlCharEncodingAlias)); | 
|  | 998 | } | 
|  | 999 | /* | 
|  | 1000 | * Walk down the list looking for a definition of the alias | 
|  | 1001 | */ | 
|  | 1002 | for (i = 0;i < xmlCharEncodingAliasesNb;i++) { | 
|  | 1003 | if (!strcmp(xmlCharEncodingAliases[i].alias, upper)) { | 
|  | 1004 | /* | 
|  | 1005 | * Replace the definition. | 
|  | 1006 | */ | 
|  | 1007 | xmlFree((char *) xmlCharEncodingAliases[i].name); | 
|  | 1008 | xmlCharEncodingAliases[i].name = xmlMemStrdup(name); | 
|  | 1009 | return(0); | 
|  | 1010 | } | 
|  | 1011 | } | 
|  | 1012 | /* | 
|  | 1013 | * Add the definition | 
|  | 1014 | */ | 
|  | 1015 | xmlCharEncodingAliases[xmlCharEncodingAliasesNb].name = xmlMemStrdup(name); | 
|  | 1016 | xmlCharEncodingAliases[xmlCharEncodingAliasesNb].alias = xmlMemStrdup(upper); | 
|  | 1017 | xmlCharEncodingAliasesNb++; | 
|  | 1018 | return(0); | 
|  | 1019 | } | 
|  | 1020 |  | 
|  | 1021 | /** | 
|  | 1022 | * xmlDelEncodingAlias: | 
|  | 1023 | * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually) | 
|  | 1024 | * | 
|  | 1025 | * Unregisters an encoding alias @alias | 
|  | 1026 | * | 
|  | 1027 | * Returns 0 in case of success, -1 in case of error | 
|  | 1028 | */ | 
|  | 1029 | int | 
|  | 1030 | xmlDelEncodingAlias(const char *alias) { | 
|  | 1031 | int i; | 
|  | 1032 |  | 
|  | 1033 | if (alias == NULL) | 
|  | 1034 | return(-1); | 
|  | 1035 |  | 
|  | 1036 | if (xmlCharEncodingAliases == NULL) | 
|  | 1037 | return(-1); | 
|  | 1038 | /* | 
|  | 1039 | * Walk down the list looking for a definition of the alias | 
|  | 1040 | */ | 
|  | 1041 | for (i = 0;i < xmlCharEncodingAliasesNb;i++) { | 
|  | 1042 | if (!strcmp(xmlCharEncodingAliases[i].alias, alias)) { | 
|  | 1043 | xmlFree((char *) xmlCharEncodingAliases[i].name); | 
|  | 1044 | xmlFree((char *) xmlCharEncodingAliases[i].alias); | 
|  | 1045 | xmlCharEncodingAliasesNb--; | 
|  | 1046 | memmove(&xmlCharEncodingAliases[i], &xmlCharEncodingAliases[i + 1], | 
|  | 1047 | sizeof(xmlCharEncodingAlias) * (xmlCharEncodingAliasesNb - i)); | 
|  | 1048 | return(0); | 
|  | 1049 | } | 
|  | 1050 | } | 
|  | 1051 | return(-1); | 
|  | 1052 | } | 
|  | 1053 |  | 
|  | 1054 | /** | 
|  | 1055 | * xmlParseCharEncoding: | 
|  | 1056 | * @name:  the encoding name as parsed, in UTF-8 format (ASCII actually) | 
|  | 1057 | * | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 1058 | * Compare the string to the encoding schemes already known. Note | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1059 | * that the comparison is case insensitive accordingly to the section | 
|  | 1060 | * [XML] 4.3.3 Character Encoding in Entities. | 
|  | 1061 | * | 
|  | 1062 | * Returns one of the XML_CHAR_ENCODING_... values or XML_CHAR_ENCODING_NONE | 
|  | 1063 | * if not recognized. | 
|  | 1064 | */ | 
|  | 1065 | xmlCharEncoding | 
|  | 1066 | xmlParseCharEncoding(const char* name) | 
|  | 1067 | { | 
|  | 1068 | const char *alias; | 
|  | 1069 | char upper[500]; | 
|  | 1070 | int i; | 
|  | 1071 |  | 
|  | 1072 | if (name == NULL) | 
|  | 1073 | return(XML_CHAR_ENCODING_NONE); | 
|  | 1074 |  | 
|  | 1075 | /* | 
|  | 1076 | * Do the alias resolution | 
|  | 1077 | */ | 
|  | 1078 | alias = xmlGetEncodingAlias(name); | 
|  | 1079 | if (alias != NULL) | 
|  | 1080 | name = alias; | 
|  | 1081 |  | 
|  | 1082 | for (i = 0;i < 499;i++) { | 
|  | 1083 | upper[i] = toupper(name[i]); | 
|  | 1084 | if (upper[i] == 0) break; | 
|  | 1085 | } | 
|  | 1086 | upper[i] = 0; | 
|  | 1087 |  | 
|  | 1088 | if (!strcmp(upper, "")) return(XML_CHAR_ENCODING_NONE); | 
|  | 1089 | if (!strcmp(upper, "UTF-8")) return(XML_CHAR_ENCODING_UTF8); | 
|  | 1090 | if (!strcmp(upper, "UTF8")) return(XML_CHAR_ENCODING_UTF8); | 
|  | 1091 |  | 
|  | 1092 | /* | 
|  | 1093 | * NOTE: if we were able to parse this, the endianness of UTF16 is | 
|  | 1094 | *       already found and in use | 
|  | 1095 | */ | 
|  | 1096 | if (!strcmp(upper, "UTF-16")) return(XML_CHAR_ENCODING_UTF16LE); | 
|  | 1097 | if (!strcmp(upper, "UTF16")) return(XML_CHAR_ENCODING_UTF16LE); | 
|  | 1098 |  | 
|  | 1099 | if (!strcmp(upper, "ISO-10646-UCS-2")) return(XML_CHAR_ENCODING_UCS2); | 
|  | 1100 | if (!strcmp(upper, "UCS-2")) return(XML_CHAR_ENCODING_UCS2); | 
|  | 1101 | if (!strcmp(upper, "UCS2")) return(XML_CHAR_ENCODING_UCS2); | 
|  | 1102 |  | 
|  | 1103 | /* | 
|  | 1104 | * NOTE: if we were able to parse this, the endianness of UCS4 is | 
|  | 1105 | *       already found and in use | 
|  | 1106 | */ | 
|  | 1107 | if (!strcmp(upper, "ISO-10646-UCS-4")) return(XML_CHAR_ENCODING_UCS4LE); | 
|  | 1108 | if (!strcmp(upper, "UCS-4")) return(XML_CHAR_ENCODING_UCS4LE); | 
|  | 1109 | if (!strcmp(upper, "UCS4")) return(XML_CHAR_ENCODING_UCS4LE); | 
|  | 1110 |  | 
|  | 1111 |  | 
|  | 1112 | if (!strcmp(upper,  "ISO-8859-1")) return(XML_CHAR_ENCODING_8859_1); | 
|  | 1113 | if (!strcmp(upper,  "ISO-LATIN-1")) return(XML_CHAR_ENCODING_8859_1); | 
|  | 1114 | if (!strcmp(upper,  "ISO LATIN 1")) return(XML_CHAR_ENCODING_8859_1); | 
|  | 1115 |  | 
|  | 1116 | if (!strcmp(upper,  "ISO-8859-2")) return(XML_CHAR_ENCODING_8859_2); | 
|  | 1117 | if (!strcmp(upper,  "ISO-LATIN-2")) return(XML_CHAR_ENCODING_8859_2); | 
|  | 1118 | if (!strcmp(upper,  "ISO LATIN 2")) return(XML_CHAR_ENCODING_8859_2); | 
|  | 1119 |  | 
|  | 1120 | if (!strcmp(upper,  "ISO-8859-3")) return(XML_CHAR_ENCODING_8859_3); | 
|  | 1121 | if (!strcmp(upper,  "ISO-8859-4")) return(XML_CHAR_ENCODING_8859_4); | 
|  | 1122 | if (!strcmp(upper,  "ISO-8859-5")) return(XML_CHAR_ENCODING_8859_5); | 
|  | 1123 | if (!strcmp(upper,  "ISO-8859-6")) return(XML_CHAR_ENCODING_8859_6); | 
|  | 1124 | if (!strcmp(upper,  "ISO-8859-7")) return(XML_CHAR_ENCODING_8859_7); | 
|  | 1125 | if (!strcmp(upper,  "ISO-8859-8")) return(XML_CHAR_ENCODING_8859_8); | 
|  | 1126 | if (!strcmp(upper,  "ISO-8859-9")) return(XML_CHAR_ENCODING_8859_9); | 
|  | 1127 |  | 
|  | 1128 | if (!strcmp(upper, "ISO-2022-JP")) return(XML_CHAR_ENCODING_2022_JP); | 
|  | 1129 | if (!strcmp(upper, "SHIFT_JIS")) return(XML_CHAR_ENCODING_SHIFT_JIS); | 
|  | 1130 | if (!strcmp(upper, "EUC-JP")) return(XML_CHAR_ENCODING_EUC_JP); | 
|  | 1131 |  | 
|  | 1132 | #ifdef DEBUG_ENCODING | 
|  | 1133 | xmlGenericError(xmlGenericErrorContext, "Unknown encoding %s\n", name); | 
|  | 1134 | #endif | 
|  | 1135 | return(XML_CHAR_ENCODING_ERROR); | 
|  | 1136 | } | 
|  | 1137 |  | 
|  | 1138 | /** | 
|  | 1139 | * xmlGetCharEncodingName: | 
|  | 1140 | * @enc:  the encoding | 
|  | 1141 | * | 
|  | 1142 | * The "canonical" name for XML encoding. | 
|  | 1143 | * C.f. http://www.w3.org/TR/REC-xml#charencoding | 
|  | 1144 | * Section 4.3.3  Character Encoding in Entities | 
|  | 1145 | * | 
|  | 1146 | * Returns the canonical name for the given encoding | 
|  | 1147 | */ | 
|  | 1148 |  | 
|  | 1149 | const char* | 
|  | 1150 | xmlGetCharEncodingName(xmlCharEncoding enc) { | 
|  | 1151 | switch (enc) { | 
|  | 1152 | case XML_CHAR_ENCODING_ERROR: | 
|  | 1153 | return(NULL); | 
|  | 1154 | case XML_CHAR_ENCODING_NONE: | 
|  | 1155 | return(NULL); | 
|  | 1156 | case XML_CHAR_ENCODING_UTF8: | 
|  | 1157 | return("UTF-8"); | 
|  | 1158 | case XML_CHAR_ENCODING_UTF16LE: | 
|  | 1159 | return("UTF-16"); | 
|  | 1160 | case XML_CHAR_ENCODING_UTF16BE: | 
|  | 1161 | return("UTF-16"); | 
|  | 1162 | case XML_CHAR_ENCODING_EBCDIC: | 
|  | 1163 | return("EBCDIC"); | 
|  | 1164 | case XML_CHAR_ENCODING_UCS4LE: | 
|  | 1165 | return("ISO-10646-UCS-4"); | 
|  | 1166 | case XML_CHAR_ENCODING_UCS4BE: | 
|  | 1167 | return("ISO-10646-UCS-4"); | 
|  | 1168 | case XML_CHAR_ENCODING_UCS4_2143: | 
|  | 1169 | return("ISO-10646-UCS-4"); | 
|  | 1170 | case XML_CHAR_ENCODING_UCS4_3412: | 
|  | 1171 | return("ISO-10646-UCS-4"); | 
|  | 1172 | case XML_CHAR_ENCODING_UCS2: | 
|  | 1173 | return("ISO-10646-UCS-2"); | 
|  | 1174 | case XML_CHAR_ENCODING_8859_1: | 
|  | 1175 | return("ISO-8859-1"); | 
|  | 1176 | case XML_CHAR_ENCODING_8859_2: | 
|  | 1177 | return("ISO-8859-2"); | 
|  | 1178 | case XML_CHAR_ENCODING_8859_3: | 
|  | 1179 | return("ISO-8859-3"); | 
|  | 1180 | case XML_CHAR_ENCODING_8859_4: | 
|  | 1181 | return("ISO-8859-4"); | 
|  | 1182 | case XML_CHAR_ENCODING_8859_5: | 
|  | 1183 | return("ISO-8859-5"); | 
|  | 1184 | case XML_CHAR_ENCODING_8859_6: | 
|  | 1185 | return("ISO-8859-6"); | 
|  | 1186 | case XML_CHAR_ENCODING_8859_7: | 
|  | 1187 | return("ISO-8859-7"); | 
|  | 1188 | case XML_CHAR_ENCODING_8859_8: | 
|  | 1189 | return("ISO-8859-8"); | 
|  | 1190 | case XML_CHAR_ENCODING_8859_9: | 
|  | 1191 | return("ISO-8859-9"); | 
|  | 1192 | case XML_CHAR_ENCODING_2022_JP: | 
|  | 1193 | return("ISO-2022-JP"); | 
|  | 1194 | case XML_CHAR_ENCODING_SHIFT_JIS: | 
|  | 1195 | return("Shift-JIS"); | 
|  | 1196 | case XML_CHAR_ENCODING_EUC_JP: | 
|  | 1197 | return("EUC-JP"); | 
|  | 1198 | case XML_CHAR_ENCODING_ASCII: | 
|  | 1199 | return(NULL); | 
|  | 1200 | } | 
|  | 1201 | return(NULL); | 
|  | 1202 | } | 
|  | 1203 |  | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 1204 | /************************************************************************ | 
|  | 1205 | *									* | 
|  | 1206 | *			Char encoding handlers				* | 
|  | 1207 | *									* | 
|  | 1208 | ************************************************************************/ | 
|  | 1209 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1210 |  | 
|  | 1211 | /* the size should be growable, but it's not a big deal ... */ | 
|  | 1212 | #define MAX_ENCODING_HANDLERS 50 | 
|  | 1213 | static xmlCharEncodingHandlerPtr *handlers = NULL; | 
|  | 1214 | static int nbCharEncodingHandler = 0; | 
|  | 1215 |  | 
|  | 1216 | /* | 
|  | 1217 | * The default is UTF-8 for XML, that's also the default used for the | 
|  | 1218 | * parser internals, so the default encoding handler is NULL | 
|  | 1219 | */ | 
|  | 1220 |  | 
|  | 1221 | static xmlCharEncodingHandlerPtr xmlDefaultCharEncodingHandler = NULL; | 
|  | 1222 |  | 
|  | 1223 | /** | 
|  | 1224 | * xmlNewCharEncodingHandler: | 
|  | 1225 | * @name:  the encoding name, in UTF-8 format (ASCII actually) | 
|  | 1226 | * @input:  the xmlCharEncodingInputFunc to read that encoding | 
|  | 1227 | * @output:  the xmlCharEncodingOutputFunc to write that encoding | 
|  | 1228 | * | 
|  | 1229 | * Create and registers an xmlCharEncodingHandler. | 
| Daniel Veillard | 6f46f6c | 2002-08-01 12:22:24 +0000 | [diff] [blame] | 1230 | * | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1231 | * Returns the xmlCharEncodingHandlerPtr created (or NULL in case of error). | 
|  | 1232 | */ | 
| Daniel Veillard | 6f46f6c | 2002-08-01 12:22:24 +0000 | [diff] [blame] | 1233 | xmlCharEncodingHandlerPtr | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1234 | xmlNewCharEncodingHandler(const char *name, | 
|  | 1235 | xmlCharEncodingInputFunc input, | 
|  | 1236 | xmlCharEncodingOutputFunc output) { | 
|  | 1237 | xmlCharEncodingHandlerPtr handler; | 
|  | 1238 | const char *alias; | 
|  | 1239 | char upper[500]; | 
|  | 1240 | int i; | 
|  | 1241 | char *up = 0; | 
|  | 1242 |  | 
|  | 1243 | /* | 
|  | 1244 | * Do the alias resolution | 
|  | 1245 | */ | 
|  | 1246 | alias = xmlGetEncodingAlias(name); | 
|  | 1247 | if (alias != NULL) | 
|  | 1248 | name = alias; | 
|  | 1249 |  | 
|  | 1250 | /* | 
|  | 1251 | * Keep only the uppercase version of the encoding. | 
|  | 1252 | */ | 
|  | 1253 | if (name == NULL) { | 
|  | 1254 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1255 | "xmlNewCharEncodingHandler : no name !\n"); | 
|  | 1256 | return(NULL); | 
|  | 1257 | } | 
|  | 1258 | for (i = 0;i < 499;i++) { | 
|  | 1259 | upper[i] = toupper(name[i]); | 
|  | 1260 | if (upper[i] == 0) break; | 
|  | 1261 | } | 
|  | 1262 | upper[i] = 0; | 
|  | 1263 | up = xmlMemStrdup(upper); | 
|  | 1264 | if (up == NULL) { | 
|  | 1265 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1266 | "xmlNewCharEncodingHandler : out of memory !\n"); | 
|  | 1267 | return(NULL); | 
|  | 1268 | } | 
|  | 1269 |  | 
|  | 1270 | /* | 
|  | 1271 | * allocate and fill-up an handler block. | 
|  | 1272 | */ | 
|  | 1273 | handler = (xmlCharEncodingHandlerPtr) | 
|  | 1274 | xmlMalloc(sizeof(xmlCharEncodingHandler)); | 
|  | 1275 | if (handler == NULL) { | 
| William M. Brack | a3215c7 | 2004-07-31 16:24:01 +0000 | [diff] [blame] | 1276 | xmlFree(up); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1277 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1278 | "xmlNewCharEncodingHandler : out of memory !\n"); | 
|  | 1279 | return(NULL); | 
|  | 1280 | } | 
|  | 1281 | handler->input = input; | 
|  | 1282 | handler->output = output; | 
|  | 1283 | handler->name = up; | 
|  | 1284 |  | 
|  | 1285 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1286 | handler->iconv_in = NULL; | 
|  | 1287 | handler->iconv_out = NULL; | 
|  | 1288 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1289 |  | 
|  | 1290 | /* | 
|  | 1291 | * registers and returns the handler. | 
|  | 1292 | */ | 
|  | 1293 | xmlRegisterCharEncodingHandler(handler); | 
|  | 1294 | #ifdef DEBUG_ENCODING | 
|  | 1295 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1296 | "Registered encoding handler for %s\n", name); | 
|  | 1297 | #endif | 
|  | 1298 | return(handler); | 
|  | 1299 | } | 
|  | 1300 |  | 
|  | 1301 | /** | 
|  | 1302 | * xmlInitCharEncodingHandlers: | 
|  | 1303 | * | 
|  | 1304 | * Initialize the char encoding support, it registers the default | 
|  | 1305 | * encoding supported. | 
|  | 1306 | * NOTE: while public, this function usually doesn't need to be called | 
|  | 1307 | *       in normal processing. | 
|  | 1308 | */ | 
|  | 1309 | void | 
|  | 1310 | xmlInitCharEncodingHandlers(void) { | 
|  | 1311 | unsigned short int tst = 0x1234; | 
|  | 1312 | unsigned char *ptr = (unsigned char *) &tst; | 
|  | 1313 |  | 
|  | 1314 | if (handlers != NULL) return; | 
|  | 1315 |  | 
|  | 1316 | handlers = (xmlCharEncodingHandlerPtr *) | 
|  | 1317 | xmlMalloc(MAX_ENCODING_HANDLERS * sizeof(xmlCharEncodingHandlerPtr)); | 
|  | 1318 |  | 
|  | 1319 | if (*ptr == 0x12) xmlLittleEndian = 0; | 
|  | 1320 | else if (*ptr == 0x34) xmlLittleEndian = 1; | 
|  | 1321 | else xmlGenericError(xmlGenericErrorContext, | 
|  | 1322 | "Odd problem at endianness detection\n"); | 
|  | 1323 |  | 
|  | 1324 | if (handlers == NULL) { | 
|  | 1325 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1326 | "xmlInitCharEncodingHandlers : out of memory !\n"); | 
|  | 1327 | return; | 
|  | 1328 | } | 
| Daniel Veillard | 81601f9 | 2003-01-14 13:42:37 +0000 | [diff] [blame] | 1329 | xmlNewCharEncodingHandler("UTF-8", UTF8ToUTF8, UTF8ToUTF8); | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 1330 | #ifdef LIBXML_OUTPUT_ENABLED | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1331 | xmlUTF16LEHandler = | 
|  | 1332 | xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE); | 
|  | 1333 | xmlUTF16BEHandler = | 
|  | 1334 | xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE); | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 1335 | xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, UTF8ToUTF16); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1336 | xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, UTF8Toisolat1); | 
|  | 1337 | xmlNewCharEncodingHandler("ASCII", asciiToUTF8, UTF8Toascii); | 
| Daniel Veillard | 2004242 | 2001-05-31 18:22:04 +0000 | [diff] [blame] | 1338 | xmlNewCharEncodingHandler("US-ASCII", asciiToUTF8, UTF8Toascii); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1339 | #ifdef LIBXML_HTML_ENABLED | 
|  | 1340 | xmlNewCharEncodingHandler("HTML", NULL, UTF8ToHtml); | 
|  | 1341 | #endif | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 1342 | #else | 
|  | 1343 | xmlUTF16LEHandler = | 
|  | 1344 | xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, NULL); | 
|  | 1345 | xmlUTF16BEHandler = | 
|  | 1346 | xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, NULL); | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 1347 | xmlNewCharEncodingHandler("UTF-16", UTF16LEToUTF8, NULL); | 
| Daniel Veillard | a9cce9c | 2003-09-29 13:20:24 +0000 | [diff] [blame] | 1348 | xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, NULL); | 
|  | 1349 | xmlNewCharEncodingHandler("ASCII", asciiToUTF8, NULL); | 
|  | 1350 | xmlNewCharEncodingHandler("US-ASCII", asciiToUTF8, NULL); | 
|  | 1351 | #endif /* LIBXML_OUTPUT_ENABLED */ | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 1352 | #ifndef LIBXML_ICONV_ENABLED | 
|  | 1353 | #ifdef LIBXML_ISO8859X_ENABLED | 
|  | 1354 | xmlRegisterCharEncodingHandlersISO8859x (); | 
|  | 1355 | #endif | 
|  | 1356 | #endif | 
|  | 1357 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1358 | } | 
|  | 1359 |  | 
|  | 1360 | /** | 
|  | 1361 | * xmlCleanupCharEncodingHandlers: | 
|  | 1362 | * | 
|  | 1363 | * Cleanup the memory allocated for the char encoding support, it | 
|  | 1364 | * unregisters all the encoding handlers and the aliases. | 
|  | 1365 | */ | 
|  | 1366 | void | 
|  | 1367 | xmlCleanupCharEncodingHandlers(void) { | 
|  | 1368 | xmlCleanupEncodingAliases(); | 
|  | 1369 |  | 
|  | 1370 | if (handlers == NULL) return; | 
|  | 1371 |  | 
|  | 1372 | for (;nbCharEncodingHandler > 0;) { | 
|  | 1373 | nbCharEncodingHandler--; | 
|  | 1374 | if (handlers[nbCharEncodingHandler] != NULL) { | 
|  | 1375 | if (handlers[nbCharEncodingHandler]->name != NULL) | 
|  | 1376 | xmlFree(handlers[nbCharEncodingHandler]->name); | 
|  | 1377 | xmlFree(handlers[nbCharEncodingHandler]); | 
|  | 1378 | } | 
|  | 1379 | } | 
|  | 1380 | xmlFree(handlers); | 
|  | 1381 | handlers = NULL; | 
|  | 1382 | nbCharEncodingHandler = 0; | 
|  | 1383 | xmlDefaultCharEncodingHandler = NULL; | 
|  | 1384 | } | 
|  | 1385 |  | 
|  | 1386 | /** | 
|  | 1387 | * xmlRegisterCharEncodingHandler: | 
|  | 1388 | * @handler:  the xmlCharEncodingHandlerPtr handler block | 
|  | 1389 | * | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1390 | * Register the char encoding handler, surprising, isn't it ? | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1391 | */ | 
|  | 1392 | void | 
|  | 1393 | xmlRegisterCharEncodingHandler(xmlCharEncodingHandlerPtr handler) { | 
|  | 1394 | if (handlers == NULL) xmlInitCharEncodingHandlers(); | 
|  | 1395 | if (handler == NULL) { | 
|  | 1396 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1397 | "xmlRegisterCharEncodingHandler: NULL handler !\n"); | 
|  | 1398 | return; | 
|  | 1399 | } | 
|  | 1400 |  | 
|  | 1401 | if (nbCharEncodingHandler >= MAX_ENCODING_HANDLERS) { | 
|  | 1402 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1403 | "xmlRegisterCharEncodingHandler: Too many handler registered\n"); | 
|  | 1404 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1405 | "\tincrease MAX_ENCODING_HANDLERS : %s\n", __FILE__); | 
|  | 1406 | return; | 
|  | 1407 | } | 
|  | 1408 | handlers[nbCharEncodingHandler++] = handler; | 
|  | 1409 | } | 
|  | 1410 |  | 
|  | 1411 | /** | 
|  | 1412 | * xmlGetCharEncodingHandler: | 
|  | 1413 | * @enc:  an xmlCharEncoding value. | 
|  | 1414 | * | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1415 | * Search in the registered set the handler able to read/write that encoding. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1416 | * | 
|  | 1417 | * Returns the handler or NULL if not found | 
|  | 1418 | */ | 
|  | 1419 | xmlCharEncodingHandlerPtr | 
|  | 1420 | xmlGetCharEncodingHandler(xmlCharEncoding enc) { | 
|  | 1421 | xmlCharEncodingHandlerPtr handler; | 
|  | 1422 |  | 
|  | 1423 | if (handlers == NULL) xmlInitCharEncodingHandlers(); | 
|  | 1424 | switch (enc) { | 
|  | 1425 | case XML_CHAR_ENCODING_ERROR: | 
|  | 1426 | return(NULL); | 
|  | 1427 | case XML_CHAR_ENCODING_NONE: | 
|  | 1428 | return(NULL); | 
|  | 1429 | case XML_CHAR_ENCODING_UTF8: | 
|  | 1430 | return(NULL); | 
|  | 1431 | case XML_CHAR_ENCODING_UTF16LE: | 
|  | 1432 | return(xmlUTF16LEHandler); | 
|  | 1433 | case XML_CHAR_ENCODING_UTF16BE: | 
|  | 1434 | return(xmlUTF16BEHandler); | 
|  | 1435 | case XML_CHAR_ENCODING_EBCDIC: | 
|  | 1436 | handler = xmlFindCharEncodingHandler("EBCDIC"); | 
|  | 1437 | if (handler != NULL) return(handler); | 
|  | 1438 | handler = xmlFindCharEncodingHandler("ebcdic"); | 
|  | 1439 | if (handler != NULL) return(handler); | 
|  | 1440 | break; | 
|  | 1441 | case XML_CHAR_ENCODING_UCS4BE: | 
|  | 1442 | handler = xmlFindCharEncodingHandler("ISO-10646-UCS-4"); | 
|  | 1443 | if (handler != NULL) return(handler); | 
|  | 1444 | handler = xmlFindCharEncodingHandler("UCS-4"); | 
|  | 1445 | if (handler != NULL) return(handler); | 
|  | 1446 | handler = xmlFindCharEncodingHandler("UCS4"); | 
|  | 1447 | if (handler != NULL) return(handler); | 
|  | 1448 | break; | 
|  | 1449 | case XML_CHAR_ENCODING_UCS4LE: | 
|  | 1450 | handler = xmlFindCharEncodingHandler("ISO-10646-UCS-4"); | 
|  | 1451 | if (handler != NULL) return(handler); | 
|  | 1452 | handler = xmlFindCharEncodingHandler("UCS-4"); | 
|  | 1453 | if (handler != NULL) return(handler); | 
|  | 1454 | handler = xmlFindCharEncodingHandler("UCS4"); | 
|  | 1455 | if (handler != NULL) return(handler); | 
|  | 1456 | break; | 
|  | 1457 | case XML_CHAR_ENCODING_UCS4_2143: | 
|  | 1458 | break; | 
|  | 1459 | case XML_CHAR_ENCODING_UCS4_3412: | 
|  | 1460 | break; | 
|  | 1461 | case XML_CHAR_ENCODING_UCS2: | 
|  | 1462 | handler = xmlFindCharEncodingHandler("ISO-10646-UCS-2"); | 
|  | 1463 | if (handler != NULL) return(handler); | 
|  | 1464 | handler = xmlFindCharEncodingHandler("UCS-2"); | 
|  | 1465 | if (handler != NULL) return(handler); | 
|  | 1466 | handler = xmlFindCharEncodingHandler("UCS2"); | 
|  | 1467 | if (handler != NULL) return(handler); | 
|  | 1468 | break; | 
|  | 1469 |  | 
|  | 1470 | /* | 
|  | 1471 | * We used to keep ISO Latin encodings native in the | 
|  | 1472 | * generated data. This led to so many problems that | 
|  | 1473 | * this has been removed. One can still change this | 
|  | 1474 | * back by registering no-ops encoders for those | 
|  | 1475 | */ | 
|  | 1476 | case XML_CHAR_ENCODING_8859_1: | 
|  | 1477 | handler = xmlFindCharEncodingHandler("ISO-8859-1"); | 
|  | 1478 | if (handler != NULL) return(handler); | 
|  | 1479 | break; | 
|  | 1480 | case XML_CHAR_ENCODING_8859_2: | 
|  | 1481 | handler = xmlFindCharEncodingHandler("ISO-8859-2"); | 
|  | 1482 | if (handler != NULL) return(handler); | 
|  | 1483 | break; | 
|  | 1484 | case XML_CHAR_ENCODING_8859_3: | 
|  | 1485 | handler = xmlFindCharEncodingHandler("ISO-8859-3"); | 
|  | 1486 | if (handler != NULL) return(handler); | 
|  | 1487 | break; | 
|  | 1488 | case XML_CHAR_ENCODING_8859_4: | 
|  | 1489 | handler = xmlFindCharEncodingHandler("ISO-8859-4"); | 
|  | 1490 | if (handler != NULL) return(handler); | 
|  | 1491 | break; | 
|  | 1492 | case XML_CHAR_ENCODING_8859_5: | 
|  | 1493 | handler = xmlFindCharEncodingHandler("ISO-8859-5"); | 
|  | 1494 | if (handler != NULL) return(handler); | 
|  | 1495 | break; | 
|  | 1496 | case XML_CHAR_ENCODING_8859_6: | 
|  | 1497 | handler = xmlFindCharEncodingHandler("ISO-8859-6"); | 
|  | 1498 | if (handler != NULL) return(handler); | 
|  | 1499 | break; | 
|  | 1500 | case XML_CHAR_ENCODING_8859_7: | 
|  | 1501 | handler = xmlFindCharEncodingHandler("ISO-8859-7"); | 
|  | 1502 | if (handler != NULL) return(handler); | 
|  | 1503 | break; | 
|  | 1504 | case XML_CHAR_ENCODING_8859_8: | 
|  | 1505 | handler = xmlFindCharEncodingHandler("ISO-8859-8"); | 
|  | 1506 | if (handler != NULL) return(handler); | 
|  | 1507 | break; | 
|  | 1508 | case XML_CHAR_ENCODING_8859_9: | 
|  | 1509 | handler = xmlFindCharEncodingHandler("ISO-8859-9"); | 
|  | 1510 | if (handler != NULL) return(handler); | 
|  | 1511 | break; | 
|  | 1512 |  | 
|  | 1513 |  | 
|  | 1514 | case XML_CHAR_ENCODING_2022_JP: | 
|  | 1515 | handler = xmlFindCharEncodingHandler("ISO-2022-JP"); | 
|  | 1516 | if (handler != NULL) return(handler); | 
|  | 1517 | break; | 
|  | 1518 | case XML_CHAR_ENCODING_SHIFT_JIS: | 
|  | 1519 | handler = xmlFindCharEncodingHandler("SHIFT-JIS"); | 
|  | 1520 | if (handler != NULL) return(handler); | 
|  | 1521 | handler = xmlFindCharEncodingHandler("SHIFT_JIS"); | 
|  | 1522 | if (handler != NULL) return(handler); | 
|  | 1523 | handler = xmlFindCharEncodingHandler("Shift_JIS"); | 
|  | 1524 | if (handler != NULL) return(handler); | 
|  | 1525 | break; | 
|  | 1526 | case XML_CHAR_ENCODING_EUC_JP: | 
|  | 1527 | handler = xmlFindCharEncodingHandler("EUC-JP"); | 
|  | 1528 | if (handler != NULL) return(handler); | 
|  | 1529 | break; | 
|  | 1530 | default: | 
|  | 1531 | break; | 
|  | 1532 | } | 
|  | 1533 |  | 
|  | 1534 | #ifdef DEBUG_ENCODING | 
|  | 1535 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1536 | "No handler found for encoding %d\n", enc); | 
|  | 1537 | #endif | 
|  | 1538 | return(NULL); | 
|  | 1539 | } | 
|  | 1540 |  | 
|  | 1541 | /** | 
| Daniel Veillard | 5e2dace | 2001-07-18 19:30:27 +0000 | [diff] [blame] | 1542 | * xmlFindCharEncodingHandler: | 
|  | 1543 | * @name:  a string describing the char encoding. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1544 | * | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1545 | * Search in the registered set the handler able to read/write that encoding. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1546 | * | 
|  | 1547 | * Returns the handler or NULL if not found | 
|  | 1548 | */ | 
|  | 1549 | xmlCharEncodingHandlerPtr | 
|  | 1550 | xmlFindCharEncodingHandler(const char *name) { | 
|  | 1551 | const char *nalias; | 
|  | 1552 | const char *norig; | 
|  | 1553 | xmlCharEncoding alias; | 
|  | 1554 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1555 | xmlCharEncodingHandlerPtr enc; | 
|  | 1556 | iconv_t icv_in, icv_out; | 
|  | 1557 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1558 | char upper[100]; | 
|  | 1559 | int i; | 
|  | 1560 |  | 
|  | 1561 | if (handlers == NULL) xmlInitCharEncodingHandlers(); | 
|  | 1562 | if (name == NULL) return(xmlDefaultCharEncodingHandler); | 
|  | 1563 | if (name[0] == 0) return(xmlDefaultCharEncodingHandler); | 
|  | 1564 |  | 
|  | 1565 | /* | 
|  | 1566 | * Do the alias resolution | 
|  | 1567 | */ | 
|  | 1568 | norig = name; | 
|  | 1569 | nalias = xmlGetEncodingAlias(name); | 
|  | 1570 | if (nalias != NULL) | 
|  | 1571 | name = nalias; | 
|  | 1572 |  | 
|  | 1573 | /* | 
|  | 1574 | * Check first for directly registered encoding names | 
|  | 1575 | */ | 
|  | 1576 | for (i = 0;i < 99;i++) { | 
|  | 1577 | upper[i] = toupper(name[i]); | 
|  | 1578 | if (upper[i] == 0) break; | 
|  | 1579 | } | 
|  | 1580 | upper[i] = 0; | 
|  | 1581 |  | 
|  | 1582 | for (i = 0;i < nbCharEncodingHandler; i++) | 
|  | 1583 | if (!strcmp(upper, handlers[i]->name)) { | 
|  | 1584 | #ifdef DEBUG_ENCODING | 
|  | 1585 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1586 | "Found registered handler for encoding %s\n", name); | 
|  | 1587 | #endif | 
|  | 1588 | return(handlers[i]); | 
|  | 1589 | } | 
|  | 1590 |  | 
|  | 1591 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1592 | /* check whether iconv can handle this */ | 
|  | 1593 | icv_in = iconv_open("UTF-8", name); | 
|  | 1594 | icv_out = iconv_open(name, "UTF-8"); | 
|  | 1595 | if ((icv_in != (iconv_t) -1) && (icv_out != (iconv_t) -1)) { | 
|  | 1596 | enc = (xmlCharEncodingHandlerPtr) | 
|  | 1597 | xmlMalloc(sizeof(xmlCharEncodingHandler)); | 
|  | 1598 | if (enc == NULL) { | 
|  | 1599 | iconv_close(icv_in); | 
|  | 1600 | iconv_close(icv_out); | 
|  | 1601 | return(NULL); | 
|  | 1602 | } | 
|  | 1603 | enc->name = xmlMemStrdup(name); | 
|  | 1604 | enc->input = NULL; | 
|  | 1605 | enc->output = NULL; | 
|  | 1606 | enc->iconv_in = icv_in; | 
|  | 1607 | enc->iconv_out = icv_out; | 
|  | 1608 | #ifdef DEBUG_ENCODING | 
|  | 1609 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1610 | "Found iconv handler for encoding %s\n", name); | 
|  | 1611 | #endif | 
|  | 1612 | return enc; | 
|  | 1613 | } else if ((icv_in != (iconv_t) -1) || icv_out != (iconv_t) -1) { | 
|  | 1614 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1615 | "iconv : problems with filters for '%s'\n", name); | 
|  | 1616 | } | 
|  | 1617 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1618 |  | 
|  | 1619 | #ifdef DEBUG_ENCODING | 
|  | 1620 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1621 | "No handler found for encoding %s\n", name); | 
|  | 1622 | #endif | 
|  | 1623 |  | 
|  | 1624 | /* | 
|  | 1625 | * Fallback using the canonical names | 
|  | 1626 | */ | 
|  | 1627 | alias = xmlParseCharEncoding(norig); | 
|  | 1628 | if (alias != XML_CHAR_ENCODING_ERROR) { | 
|  | 1629 | const char* canon; | 
|  | 1630 | canon = xmlGetCharEncodingName(alias); | 
|  | 1631 | if ((canon != NULL) && (strcmp(name, canon))) { | 
|  | 1632 | return(xmlFindCharEncodingHandler(canon)); | 
|  | 1633 | } | 
|  | 1634 | } | 
|  | 1635 |  | 
| William M. Brack | f9415e4 | 2003-11-28 09:39:10 +0000 | [diff] [blame] | 1636 | /* If "none of the above", give up */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1637 | return(NULL); | 
|  | 1638 | } | 
|  | 1639 |  | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 1640 | /************************************************************************ | 
|  | 1641 | *									* | 
|  | 1642 | *		ICONV based generic conversion functions		* | 
|  | 1643 | *									* | 
|  | 1644 | ************************************************************************/ | 
|  | 1645 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1646 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1647 | /** | 
|  | 1648 | * xmlIconvWrapper: | 
|  | 1649 | * @cd:		iconv converter data structure | 
|  | 1650 | * @out:  a pointer to an array of bytes to store the result | 
|  | 1651 | * @outlen:  the length of @out | 
|  | 1652 | * @in:  a pointer to an array of ISO Latin 1 chars | 
|  | 1653 | * @inlen:  the length of @in | 
|  | 1654 | * | 
|  | 1655 | * Returns 0 if success, or | 
|  | 1656 | *     -1 by lack of space, or | 
|  | 1657 | *     -2 if the transcoding fails (for *in is not valid utf8 string or | 
|  | 1658 | *        the result of transformation can't fit into the encoding we want), or | 
|  | 1659 | *     -3 if there the last byte can't form a single output char. | 
|  | 1660 | * | 
|  | 1661 | * The value of @inlen after return is the number of octets consumed | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1662 | *     as the return value is positive, else unpredictable. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1663 | * The value of @outlen after return is the number of ocetes consumed. | 
|  | 1664 | */ | 
|  | 1665 | static int | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 1666 | xmlIconvWrapper(iconv_t cd, unsigned char *out, int *outlen, | 
|  | 1667 | const unsigned char *in, int *inlen) { | 
|  | 1668 | size_t icv_inlen, icv_outlen; | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1669 | const char *icv_in = (const char *) in; | 
|  | 1670 | char *icv_out = (char *) out; | 
|  | 1671 | int ret; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1672 |  | 
| Daniel Veillard | 01ca83c | 2004-11-06 13:26:59 +0000 | [diff] [blame] | 1673 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || (in == NULL)) { | 
|  | 1674 | if (outlen != NULL) *outlen = 0; | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 1675 | return(-1); | 
| Daniel Veillard | 01ca83c | 2004-11-06 13:26:59 +0000 | [diff] [blame] | 1676 | } | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 1677 | icv_inlen = *inlen; | 
|  | 1678 | icv_outlen = *outlen; | 
| Darin Adler | 699613b | 2001-07-27 22:47:14 +0000 | [diff] [blame] | 1679 | ret = iconv(cd, (char **) &icv_in, &icv_inlen, &icv_out, &icv_outlen); | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1680 | if (in != NULL) { | 
|  | 1681 | *inlen -= icv_inlen; | 
|  | 1682 | *outlen -= icv_outlen; | 
|  | 1683 | } else { | 
|  | 1684 | *inlen = 0; | 
|  | 1685 | *outlen = 0; | 
|  | 1686 | } | 
|  | 1687 | if ((icv_inlen != 0) || (ret == -1)) { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1688 | #ifdef EILSEQ | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1689 | if (errno == EILSEQ) { | 
|  | 1690 | return -2; | 
|  | 1691 | } else | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1692 | #endif | 
|  | 1693 | #ifdef E2BIG | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1694 | if (errno == E2BIG) { | 
|  | 1695 | return -1; | 
|  | 1696 | } else | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1697 | #endif | 
|  | 1698 | #ifdef EINVAL | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1699 | if (errno == EINVAL) { | 
|  | 1700 | return -3; | 
|  | 1701 | } else | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1702 | #endif | 
| Daniel Veillard | 9403a04 | 2001-05-28 11:00:53 +0000 | [diff] [blame] | 1703 | { | 
|  | 1704 | return -3; | 
|  | 1705 | } | 
|  | 1706 | } | 
|  | 1707 | return 0; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1708 | } | 
|  | 1709 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1710 |  | 
| Daniel Veillard | 97ac131 | 2001-05-30 19:14:17 +0000 | [diff] [blame] | 1711 | /************************************************************************ | 
|  | 1712 | *									* | 
|  | 1713 | *		The real API used by libxml for on-the-fly conversion	* | 
|  | 1714 | *									* | 
|  | 1715 | ************************************************************************/ | 
|  | 1716 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1717 | /** | 
|  | 1718 | * xmlCharEncFirstLine: | 
|  | 1719 | * @handler:	char enconding transformation data structure | 
|  | 1720 | * @out:  an xmlBuffer for the output. | 
|  | 1721 | * @in:  an xmlBuffer for the input | 
|  | 1722 | * | 
|  | 1723 | * Front-end for the encoding handler input function, but handle only | 
|  | 1724 | * the very first line, i.e. limit itself to 45 chars. | 
|  | 1725 | * | 
|  | 1726 | * Returns the number of byte written if success, or | 
|  | 1727 | *     -1 general error | 
|  | 1728 | *     -2 if the transcoding fails (for *in is not valid utf8 string or | 
|  | 1729 | *        the result of transformation can't fit into the encoding we want), or | 
|  | 1730 | */ | 
|  | 1731 | int | 
|  | 1732 | xmlCharEncFirstLine(xmlCharEncodingHandler *handler, xmlBufferPtr out, | 
|  | 1733 | xmlBufferPtr in) { | 
|  | 1734 | int ret = -2; | 
|  | 1735 | int written; | 
|  | 1736 | int toconv; | 
|  | 1737 |  | 
|  | 1738 | if (handler == NULL) return(-1); | 
|  | 1739 | if (out == NULL) return(-1); | 
|  | 1740 | if (in == NULL) return(-1); | 
|  | 1741 |  | 
|  | 1742 | written = out->size - out->use; | 
|  | 1743 | toconv = in->use; | 
|  | 1744 | if (toconv * 2 >= written) { | 
|  | 1745 | xmlBufferGrow(out, toconv); | 
|  | 1746 | written = out->size - out->use - 1; | 
|  | 1747 | } | 
|  | 1748 |  | 
|  | 1749 | /* | 
|  | 1750 | * echo '<?xml version="1.0" encoding="UCS4"?>' | wc -c => 38 | 
|  | 1751 | * 45 chars should be sufficient to reach the end of the encoding | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1752 | * declaration without going too far inside the document content. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1753 | */ | 
|  | 1754 | written = 45; | 
|  | 1755 |  | 
|  | 1756 | if (handler->input != NULL) { | 
|  | 1757 | ret = handler->input(&out->content[out->use], &written, | 
|  | 1758 | in->content, &toconv); | 
|  | 1759 | xmlBufferShrink(in, toconv); | 
|  | 1760 | out->use += written; | 
|  | 1761 | out->content[out->use] = 0; | 
|  | 1762 | } | 
|  | 1763 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1764 | else if (handler->iconv_in != NULL) { | 
|  | 1765 | ret = xmlIconvWrapper(handler->iconv_in, &out->content[out->use], | 
|  | 1766 | &written, in->content, &toconv); | 
|  | 1767 | xmlBufferShrink(in, toconv); | 
|  | 1768 | out->use += written; | 
|  | 1769 | out->content[out->use] = 0; | 
|  | 1770 | if (ret == -1) ret = -3; | 
|  | 1771 | } | 
|  | 1772 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1773 | #ifdef DEBUG_ENCODING | 
|  | 1774 | switch (ret) { | 
|  | 1775 | case 0: | 
|  | 1776 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1777 | "converted %d bytes to %d bytes of input\n", | 
|  | 1778 | toconv, written); | 
|  | 1779 | break; | 
|  | 1780 | case -1: | 
|  | 1781 | xmlGenericError(xmlGenericErrorContext,"converted %d bytes to %d bytes of input, %d left\n", | 
|  | 1782 | toconv, written, in->use); | 
|  | 1783 | break; | 
|  | 1784 | case -2: | 
|  | 1785 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1786 | "input conversion failed due to input error\n"); | 
|  | 1787 | break; | 
|  | 1788 | case -3: | 
|  | 1789 | xmlGenericError(xmlGenericErrorContext,"converted %d bytes to %d bytes of input, %d left\n", | 
|  | 1790 | toconv, written, in->use); | 
|  | 1791 | break; | 
|  | 1792 | default: | 
|  | 1793 | xmlGenericError(xmlGenericErrorContext,"Unknown input conversion failed %d\n", ret); | 
|  | 1794 | } | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1795 | #endif /* DEBUG_ENCODING */ | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1796 | /* | 
|  | 1797 | * Ignore when input buffer is not on a boundary | 
|  | 1798 | */ | 
|  | 1799 | if (ret == -3) ret = 0; | 
|  | 1800 | if (ret == -1) ret = 0; | 
|  | 1801 | return(ret); | 
|  | 1802 | } | 
|  | 1803 |  | 
|  | 1804 | /** | 
|  | 1805 | * xmlCharEncInFunc: | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1806 | * @handler:	char encoding transformation data structure | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1807 | * @out:  an xmlBuffer for the output. | 
|  | 1808 | * @in:  an xmlBuffer for the input | 
|  | 1809 | * | 
|  | 1810 | * Generic front-end for the encoding handler input function | 
|  | 1811 | * | 
|  | 1812 | * Returns the number of byte written if success, or | 
|  | 1813 | *     -1 general error | 
|  | 1814 | *     -2 if the transcoding fails (for *in is not valid utf8 string or | 
|  | 1815 | *        the result of transformation can't fit into the encoding we want), or | 
|  | 1816 | */ | 
|  | 1817 | int | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1818 | xmlCharEncInFunc(xmlCharEncodingHandler * handler, xmlBufferPtr out, | 
|  | 1819 | xmlBufferPtr in) | 
|  | 1820 | { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1821 | int ret = -2; | 
|  | 1822 | int written; | 
|  | 1823 | int toconv; | 
|  | 1824 |  | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1825 | if (handler == NULL) | 
|  | 1826 | return (-1); | 
|  | 1827 | if (out == NULL) | 
|  | 1828 | return (-1); | 
|  | 1829 | if (in == NULL) | 
|  | 1830 | return (-1); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1831 |  | 
|  | 1832 | toconv = in->use; | 
|  | 1833 | if (toconv == 0) | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1834 | return (0); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1835 | written = out->size - out->use; | 
|  | 1836 | if (toconv * 2 >= written) { | 
|  | 1837 | xmlBufferGrow(out, out->size + toconv * 2); | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1838 | written = out->size - out->use - 1; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1839 | } | 
|  | 1840 | if (handler->input != NULL) { | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1841 | ret = handler->input(&out->content[out->use], &written, | 
|  | 1842 | in->content, &toconv); | 
|  | 1843 | xmlBufferShrink(in, toconv); | 
|  | 1844 | out->use += written; | 
|  | 1845 | out->content[out->use] = 0; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1846 | } | 
|  | 1847 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1848 | else if (handler->iconv_in != NULL) { | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1849 | ret = xmlIconvWrapper(handler->iconv_in, &out->content[out->use], | 
|  | 1850 | &written, in->content, &toconv); | 
|  | 1851 | xmlBufferShrink(in, toconv); | 
|  | 1852 | out->use += written; | 
|  | 1853 | out->content[out->use] = 0; | 
|  | 1854 | if (ret == -1) | 
|  | 1855 | ret = -3; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1856 | } | 
|  | 1857 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1858 | switch (ret) { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1859 | case 0: | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1860 | #ifdef DEBUG_ENCODING | 
|  | 1861 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1862 | "converted %d bytes to %d bytes of input\n", | 
|  | 1863 | toconv, written); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1864 | #endif | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1865 | break; | 
|  | 1866 | case -1: | 
|  | 1867 | #ifdef DEBUG_ENCODING | 
|  | 1868 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1869 | "converted %d bytes to %d bytes of input, %d left\n", | 
|  | 1870 | toconv, written, in->use); | 
|  | 1871 | #endif | 
|  | 1872 | break; | 
|  | 1873 | case -3: | 
|  | 1874 | #ifdef DEBUG_ENCODING | 
|  | 1875 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1876 | "converted %d bytes to %d bytes of input, %d left\n", | 
|  | 1877 | toconv, written, in->use); | 
|  | 1878 | #endif | 
|  | 1879 | break; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1880 | case -2: | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1881 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1882 | "input conversion failed due to input error\n"); | 
|  | 1883 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1884 | "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", | 
|  | 1885 | in->content[0], in->content[1], | 
|  | 1886 | in->content[2], in->content[3]); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1887 | } | 
|  | 1888 | /* | 
|  | 1889 | * Ignore when input buffer is not on a boundary | 
|  | 1890 | */ | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 1891 | if (ret == -3) | 
|  | 1892 | ret = 0; | 
| Daniel Veillard | d076a20 | 2002-11-20 13:28:31 +0000 | [diff] [blame] | 1893 | return (written); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1894 | } | 
|  | 1895 |  | 
|  | 1896 | /** | 
|  | 1897 | * xmlCharEncOutFunc: | 
|  | 1898 | * @handler:	char enconding transformation data structure | 
|  | 1899 | * @out:  an xmlBuffer for the output. | 
|  | 1900 | * @in:  an xmlBuffer for the input | 
|  | 1901 | * | 
|  | 1902 | * Generic front-end for the encoding handler output function | 
|  | 1903 | * a first call with @in == NULL has to be made firs to initiate the | 
|  | 1904 | * output in case of non-stateless encoding needing to initiate their | 
|  | 1905 | * state or the output (like the BOM in UTF16). | 
|  | 1906 | * In case of UTF8 sequence conversion errors for the given encoder, | 
|  | 1907 | * the content will be automatically remapped to a CharRef sequence. | 
|  | 1908 | * | 
|  | 1909 | * Returns the number of byte written if success, or | 
|  | 1910 | *     -1 general error | 
|  | 1911 | *     -2 if the transcoding fails (for *in is not valid utf8 string or | 
|  | 1912 | *        the result of transformation can't fit into the encoding we want), or | 
|  | 1913 | */ | 
|  | 1914 | int | 
|  | 1915 | xmlCharEncOutFunc(xmlCharEncodingHandler *handler, xmlBufferPtr out, | 
|  | 1916 | xmlBufferPtr in) { | 
|  | 1917 | int ret = -2; | 
|  | 1918 | int written; | 
|  | 1919 | int writtentot = 0; | 
|  | 1920 | int toconv; | 
|  | 1921 | int output = 0; | 
|  | 1922 |  | 
|  | 1923 | if (handler == NULL) return(-1); | 
|  | 1924 | if (out == NULL) return(-1); | 
|  | 1925 |  | 
|  | 1926 | retry: | 
|  | 1927 |  | 
|  | 1928 | written = out->size - out->use; | 
|  | 1929 |  | 
| Igor Zlatkovic | 73267db | 2003-03-08 13:29:24 +0000 | [diff] [blame] | 1930 | if (written > 0) | 
|  | 1931 | written--; /* Gennady: count '/0' */ | 
|  | 1932 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1933 | /* | 
|  | 1934 | * First specific handling of in = NULL, i.e. the initialization call | 
|  | 1935 | */ | 
|  | 1936 | if (in == NULL) { | 
|  | 1937 | toconv = 0; | 
|  | 1938 | if (handler->output != NULL) { | 
|  | 1939 | ret = handler->output(&out->content[out->use], &written, | 
|  | 1940 | NULL, &toconv); | 
| Daniel Veillard | 8caa9c2 | 2003-06-02 13:35:24 +0000 | [diff] [blame] | 1941 | if (ret >= 0) { /* Gennady: check return value */ | 
| Igor Zlatkovic | 73267db | 2003-03-08 13:29:24 +0000 | [diff] [blame] | 1942 | out->use += written; | 
|  | 1943 | out->content[out->use] = 0; | 
|  | 1944 | } | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1945 | } | 
|  | 1946 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1947 | else if (handler->iconv_out != NULL) { | 
|  | 1948 | ret = xmlIconvWrapper(handler->iconv_out, &out->content[out->use], | 
|  | 1949 | &written, NULL, &toconv); | 
|  | 1950 | out->use += written; | 
|  | 1951 | out->content[out->use] = 0; | 
|  | 1952 | } | 
|  | 1953 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1954 | #ifdef DEBUG_ENCODING | 
|  | 1955 | xmlGenericError(xmlGenericErrorContext, | 
|  | 1956 | "initialized encoder\n"); | 
|  | 1957 | #endif | 
|  | 1958 | return(0); | 
|  | 1959 | } | 
|  | 1960 |  | 
|  | 1961 | /* | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 1962 | * Conversion itself. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 1963 | */ | 
|  | 1964 | toconv = in->use; | 
|  | 1965 | if (toconv == 0) | 
|  | 1966 | return(0); | 
|  | 1967 | if (toconv * 2 >= written) { | 
|  | 1968 | xmlBufferGrow(out, toconv * 2); | 
|  | 1969 | written = out->size - out->use - 1; | 
|  | 1970 | } | 
|  | 1971 | if (handler->output != NULL) { | 
|  | 1972 | ret = handler->output(&out->content[out->use], &written, | 
|  | 1973 | in->content, &toconv); | 
|  | 1974 | xmlBufferShrink(in, toconv); | 
|  | 1975 | out->use += written; | 
|  | 1976 | writtentot += written; | 
|  | 1977 | out->content[out->use] = 0; | 
|  | 1978 | } | 
|  | 1979 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 1980 | else if (handler->iconv_out != NULL) { | 
|  | 1981 | ret = xmlIconvWrapper(handler->iconv_out, &out->content[out->use], | 
|  | 1982 | &written, in->content, &toconv); | 
|  | 1983 | xmlBufferShrink(in, toconv); | 
|  | 1984 | out->use += written; | 
|  | 1985 | writtentot += written; | 
|  | 1986 | out->content[out->use] = 0; | 
|  | 1987 | if (ret == -1) { | 
|  | 1988 | if (written > 0) { | 
|  | 1989 | /* | 
|  | 1990 | * Can be a limitation of iconv | 
|  | 1991 | */ | 
|  | 1992 | goto retry; | 
|  | 1993 | } | 
|  | 1994 | ret = -3; | 
|  | 1995 | } | 
|  | 1996 | } | 
|  | 1997 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 1998 | else { | 
|  | 1999 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2000 | "xmlCharEncOutFunc: no output function !\n"); | 
|  | 2001 | return(-1); | 
|  | 2002 | } | 
|  | 2003 |  | 
|  | 2004 | if (ret >= 0) output += ret; | 
|  | 2005 |  | 
|  | 2006 | /* | 
|  | 2007 | * Attempt to handle error cases | 
|  | 2008 | */ | 
|  | 2009 | switch (ret) { | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2010 | case 0: | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 2011 | #ifdef DEBUG_ENCODING | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2012 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2013 | "converted %d bytes to %d bytes of output\n", | 
|  | 2014 | toconv, written); | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 2015 | #endif | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2016 | break; | 
|  | 2017 | case -1: | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 2018 | #ifdef DEBUG_ENCODING | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2019 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2020 | "output conversion failed by lack of space\n"); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2021 | #endif | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 2022 | break; | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2023 | case -3: | 
| Daniel Veillard | 809faa5 | 2003-02-10 15:43:53 +0000 | [diff] [blame] | 2024 | #ifdef DEBUG_ENCODING | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2025 | xmlGenericError(xmlGenericErrorContext,"converted %d bytes to %d bytes of output %d left\n", | 
|  | 2026 | toconv, written, in->use); | 
| Daniel Veillard | 809faa5 | 2003-02-10 15:43:53 +0000 | [diff] [blame] | 2027 | #endif | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2028 | break; | 
|  | 2029 | case -2: { | 
|  | 2030 | int len = in->use; | 
|  | 2031 | const xmlChar *utf = (const xmlChar *) in->content; | 
|  | 2032 | int cur; | 
|  | 2033 |  | 
|  | 2034 | cur = xmlGetUTF8Char(utf, &len); | 
|  | 2035 | if (cur > 0) { | 
|  | 2036 | xmlChar charref[20]; | 
|  | 2037 |  | 
|  | 2038 | #ifdef DEBUG_ENCODING | 
|  | 2039 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2040 | "handling output conversion error\n"); | 
|  | 2041 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2042 | "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", | 
|  | 2043 | in->content[0], in->content[1], | 
|  | 2044 | in->content[2], in->content[3]); | 
|  | 2045 | #endif | 
|  | 2046 | /* | 
|  | 2047 | * Removes the UTF8 sequence, and replace it by a charref | 
|  | 2048 | * and continue the transcoding phase, hoping the error | 
|  | 2049 | * did not mangle the encoder state. | 
|  | 2050 | */ | 
| Aleksey Sanin | 49cc975 | 2002-06-14 17:07:10 +0000 | [diff] [blame] | 2051 | snprintf((char *) charref, sizeof(charref), "&#%d;", cur); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2052 | xmlBufferShrink(in, len); | 
|  | 2053 | xmlBufferAddHead(in, charref, -1); | 
|  | 2054 |  | 
|  | 2055 | goto retry; | 
|  | 2056 | } else { | 
|  | 2057 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2058 | "output conversion failed due to conv error\n"); | 
|  | 2059 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2060 | "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", | 
|  | 2061 | in->content[0], in->content[1], | 
|  | 2062 | in->content[2], in->content[3]); | 
|  | 2063 | in->content[0] = ' '; | 
|  | 2064 | } | 
|  | 2065 | break; | 
|  | 2066 | } | 
|  | 2067 | } | 
|  | 2068 | return(ret); | 
|  | 2069 | } | 
|  | 2070 |  | 
|  | 2071 | /** | 
|  | 2072 | * xmlCharEncCloseFunc: | 
|  | 2073 | * @handler:	char enconding transformation data structure | 
|  | 2074 | * | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 2075 | * Generic front-end for encoding handler close function | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2076 | * | 
|  | 2077 | * Returns 0 if success, or -1 in case of error | 
|  | 2078 | */ | 
|  | 2079 | int | 
|  | 2080 | xmlCharEncCloseFunc(xmlCharEncodingHandler *handler) { | 
|  | 2081 | int ret = 0; | 
|  | 2082 | if (handler == NULL) return(-1); | 
|  | 2083 | if (handler->name == NULL) return(-1); | 
|  | 2084 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 2085 | /* | 
| Daniel Veillard | cbaf399 | 2001-12-31 16:16:02 +0000 | [diff] [blame] | 2086 | * Iconv handlers can be used only once, free the whole block. | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2087 | * and the associated icon resources. | 
|  | 2088 | */ | 
|  | 2089 | if ((handler->iconv_out != NULL) || (handler->iconv_in != NULL)) { | 
|  | 2090 | if (handler->name != NULL) | 
|  | 2091 | xmlFree(handler->name); | 
|  | 2092 | handler->name = NULL; | 
|  | 2093 | if (handler->iconv_out != NULL) { | 
|  | 2094 | if (iconv_close(handler->iconv_out)) | 
|  | 2095 | ret = -1; | 
|  | 2096 | handler->iconv_out = NULL; | 
|  | 2097 | } | 
|  | 2098 | if (handler->iconv_in != NULL) { | 
|  | 2099 | if (iconv_close(handler->iconv_in)) | 
|  | 2100 | ret = -1; | 
|  | 2101 | handler->iconv_in = NULL; | 
|  | 2102 | } | 
|  | 2103 | xmlFree(handler); | 
|  | 2104 | } | 
|  | 2105 | #endif /* LIBXML_ICONV_ENABLED */ | 
|  | 2106 | #ifdef DEBUG_ENCODING | 
|  | 2107 | if (ret) | 
|  | 2108 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2109 | "failed to close the encoding handler\n"); | 
|  | 2110 | else | 
|  | 2111 | xmlGenericError(xmlGenericErrorContext, | 
|  | 2112 | "closed the encoding handler\n"); | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2113 | #endif | 
| Daniel Veillard | d79bcd1 | 2001-06-21 22:07:42 +0000 | [diff] [blame] | 2114 |  | 
| Owen Taylor | 3473f88 | 2001-02-23 17:55:21 +0000 | [diff] [blame] | 2115 | return(ret); | 
|  | 2116 | } | 
|  | 2117 |  | 
| Daniel Veillard | 3671190 | 2004-02-11 13:25:26 +0000 | [diff] [blame] | 2118 | /** | 
|  | 2119 | * xmlByteConsumed: | 
|  | 2120 | * @ctxt: an XML parser context | 
|  | 2121 | * | 
|  | 2122 | * This function provides the current index of the parser relative | 
|  | 2123 | * to the start of the current entity. This function is computed in | 
|  | 2124 | * bytes from the beginning starting at zero and finishing at the | 
|  | 2125 | * size in byte of the file if parsing a file. The function is | 
|  | 2126 | * of constant cost if the input is UTF-8 but can be costly if run | 
|  | 2127 | * on non-UTF-8 input. | 
|  | 2128 | * | 
|  | 2129 | * Returns the index in bytes from the beginning of the entity or -1 | 
|  | 2130 | *         in case the index could not be computed. | 
|  | 2131 | */ | 
|  | 2132 | long | 
|  | 2133 | xmlByteConsumed(xmlParserCtxtPtr ctxt) { | 
|  | 2134 | xmlParserInputPtr in; | 
|  | 2135 |  | 
|  | 2136 | if (ctxt == NULL) return(-1); | 
|  | 2137 | in = ctxt->input; | 
|  | 2138 | if (in == NULL)  return(-1); | 
|  | 2139 | if ((in->buf != NULL) && (in->buf->encoder != NULL)) { | 
|  | 2140 | unsigned int unused = 0; | 
|  | 2141 | xmlCharEncodingHandler * handler = in->buf->encoder; | 
|  | 2142 | /* | 
|  | 2143 | * Encoding conversion, compute the number of unused original | 
|  | 2144 | * bytes from the input not consumed and substract that from | 
|  | 2145 | * the raw consumed value, this is not a cheap operation | 
|  | 2146 | */ | 
|  | 2147 | if (in->end - in->cur > 0) { | 
|  | 2148 | static unsigned char convbuf[32000]; | 
| William M. Brack | 13dfa87 | 2004-09-18 04:52:08 +0000 | [diff] [blame] | 2149 | const unsigned char *cur = (const unsigned char *)in->cur; | 
| Daniel Veillard | 3671190 | 2004-02-11 13:25:26 +0000 | [diff] [blame] | 2150 | int toconv = in->end - in->cur, written = 32000; | 
|  | 2151 |  | 
|  | 2152 | int ret; | 
|  | 2153 |  | 
|  | 2154 | if (handler->output != NULL) { | 
|  | 2155 | do { | 
|  | 2156 | toconv = in->end - cur; | 
|  | 2157 | written = 32000; | 
|  | 2158 | ret = handler->output(&convbuf[0], &written, | 
|  | 2159 | cur, &toconv); | 
|  | 2160 | if (ret == -1) return(-1); | 
|  | 2161 | unused += written; | 
|  | 2162 | cur += toconv; | 
|  | 2163 | } while (ret == -2); | 
|  | 2164 | #ifdef LIBXML_ICONV_ENABLED | 
|  | 2165 | } else if (handler->iconv_out != NULL) { | 
|  | 2166 | do { | 
|  | 2167 | toconv = in->end - cur; | 
|  | 2168 | written = 32000; | 
|  | 2169 | ret = xmlIconvWrapper(handler->iconv_out, &convbuf[0], | 
|  | 2170 | &written, cur, &toconv); | 
| Daniel Veillard | 01ca83c | 2004-11-06 13:26:59 +0000 | [diff] [blame] | 2171 | if (ret < 0) { | 
| Daniel Veillard | 3671190 | 2004-02-11 13:25:26 +0000 | [diff] [blame] | 2172 | if (written > 0) | 
|  | 2173 | ret = -2; | 
|  | 2174 | else | 
|  | 2175 | return(-1); | 
|  | 2176 | } | 
|  | 2177 | unused += written; | 
|  | 2178 | cur += toconv; | 
|  | 2179 | } while (ret == -2); | 
|  | 2180 | #endif | 
|  | 2181 | } else { | 
|  | 2182 | /* could not find a converter */ | 
|  | 2183 | return(-1); | 
|  | 2184 | } | 
|  | 2185 | } | 
|  | 2186 | if (in->buf->rawconsumed < unused) | 
|  | 2187 | return(-1); | 
|  | 2188 | return(in->buf->rawconsumed - unused); | 
|  | 2189 | } | 
|  | 2190 | return(in->consumed + (in->cur - in->base)); | 
|  | 2191 | } | 
|  | 2192 |  | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2193 | #ifndef LIBXML_ICONV_ENABLED | 
|  | 2194 | #ifdef LIBXML_ISO8859X_ENABLED | 
|  | 2195 |  | 
|  | 2196 | /** | 
|  | 2197 | * UTF8ToISO8859x: | 
|  | 2198 | * @out:  a pointer to an array of bytes to store the result | 
|  | 2199 | * @outlen:  the length of @out | 
|  | 2200 | * @in:  a pointer to an array of UTF-8 chars | 
|  | 2201 | * @inlen:  the length of @in | 
|  | 2202 | * @xlattable: the 2-level transcoding table | 
|  | 2203 | * | 
|  | 2204 | * Take a block of UTF-8 chars in and try to convert it to an ISO 8859-* | 
|  | 2205 | * block of chars out. | 
|  | 2206 | * | 
|  | 2207 | * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise | 
|  | 2208 | * The value of @inlen after return is the number of octets consumed | 
|  | 2209 | *     as the return value is positive, else unpredictable. | 
|  | 2210 | * The value of @outlen after return is the number of ocetes consumed. | 
|  | 2211 | */ | 
|  | 2212 | static int | 
|  | 2213 | UTF8ToISO8859x(unsigned char* out, int *outlen, | 
|  | 2214 | const unsigned char* in, int *inlen, | 
|  | 2215 | unsigned char const *xlattable) { | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2216 | const unsigned char* outstart = out; | 
|  | 2217 | const unsigned char* inend; | 
|  | 2218 | const unsigned char* instart = in; | 
|  | 2219 |  | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2220 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || | 
|  | 2221 | (xlattable == NULL)) | 
|  | 2222 | return(-1); | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2223 | if (in == NULL) { | 
|  | 2224 | /* | 
|  | 2225 | * initialization nothing to do | 
|  | 2226 | */ | 
|  | 2227 | *outlen = 0; | 
|  | 2228 | *inlen = 0; | 
|  | 2229 | return(0); | 
|  | 2230 | } | 
|  | 2231 | inend = in + (*inlen); | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2232 | while (in < inend) { | 
|  | 2233 | unsigned char d = *in++; | 
|  | 2234 | if  (d < 0x80)  { | 
|  | 2235 | *out++ = d; | 
|  | 2236 | } else if (d < 0xC0) { | 
|  | 2237 | /* trailing byte in leading position */ | 
|  | 2238 | *outlen = out - outstart; | 
|  | 2239 | *inlen = in - instart - 1; | 
|  | 2240 | return(-2); | 
|  | 2241 | } else if (d < 0xE0) { | 
|  | 2242 | unsigned char c; | 
|  | 2243 | if (!(in < inend)) { | 
|  | 2244 | /* trailing byte not in input buffer */ | 
|  | 2245 | *outlen = out - outstart; | 
|  | 2246 | *inlen = in - instart - 1; | 
|  | 2247 | return(-2); | 
|  | 2248 | } | 
|  | 2249 | c = *in++; | 
| William M. Brack | f54924b | 2004-09-09 14:35:17 +0000 | [diff] [blame] | 2250 | if ((c & 0xC0) != 0x80) { | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2251 | /* not a trailing byte */ | 
|  | 2252 | *outlen = out - outstart; | 
|  | 2253 | *inlen = in - instart - 2; | 
|  | 2254 | return(-2); | 
|  | 2255 | } | 
|  | 2256 | c = c & 0x3F; | 
|  | 2257 | d = d & 0x1F; | 
|  | 2258 | d = xlattable [48 + c + xlattable [d] * 64]; | 
|  | 2259 | if (d == 0) { | 
|  | 2260 | /* not in character set */ | 
|  | 2261 | *outlen = out - outstart; | 
|  | 2262 | *inlen = in - instart - 2; | 
|  | 2263 | return(-2); | 
|  | 2264 | } | 
|  | 2265 | *out++ = d; | 
|  | 2266 | } else if (d < 0xF0) { | 
|  | 2267 | unsigned char c1; | 
|  | 2268 | unsigned char c2; | 
|  | 2269 | if (!(in < inend - 1)) { | 
|  | 2270 | /* trailing bytes not in input buffer */ | 
|  | 2271 | *outlen = out - outstart; | 
|  | 2272 | *inlen = in - instart - 1; | 
|  | 2273 | return(-2); | 
|  | 2274 | } | 
|  | 2275 | c1 = *in++; | 
| William M. Brack | f54924b | 2004-09-09 14:35:17 +0000 | [diff] [blame] | 2276 | if ((c1 & 0xC0) != 0x80) { | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2277 | /* not a trailing byte (c1) */ | 
|  | 2278 | *outlen = out - outstart; | 
|  | 2279 | *inlen = in - instart - 2; | 
|  | 2280 | return(-2); | 
|  | 2281 | } | 
|  | 2282 | c2 = *in++; | 
| William M. Brack | f54924b | 2004-09-09 14:35:17 +0000 | [diff] [blame] | 2283 | if ((c2 & 0xC0) != 0x80) { | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2284 | /* not a trailing byte (c2) */ | 
|  | 2285 | *outlen = out - outstart; | 
|  | 2286 | *inlen = in - instart - 2; | 
|  | 2287 | return(-2); | 
|  | 2288 | } | 
|  | 2289 | c1 = c1 & 0x3F; | 
|  | 2290 | c2 = c2 & 0x3F; | 
| William M. Brack | f54924b | 2004-09-09 14:35:17 +0000 | [diff] [blame] | 2291 | d = d & 0x0F; | 
|  | 2292 | d = xlattable [48 + c2 + xlattable [48 + c1 + | 
|  | 2293 | xlattable [32 + d] * 64] * 64]; | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2294 | if (d == 0) { | 
|  | 2295 | /* not in character set */ | 
|  | 2296 | *outlen = out - outstart; | 
|  | 2297 | *inlen = in - instart - 3; | 
|  | 2298 | return(-2); | 
|  | 2299 | } | 
|  | 2300 | *out++ = d; | 
|  | 2301 | } else { | 
|  | 2302 | /* cannot transcode >= U+010000 */ | 
|  | 2303 | *outlen = out - outstart; | 
|  | 2304 | *inlen = in - instart - 1; | 
|  | 2305 | return(-2); | 
|  | 2306 | } | 
|  | 2307 | } | 
|  | 2308 | *outlen = out - outstart; | 
|  | 2309 | *inlen = in - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 2310 | return(*outlen); | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2311 | } | 
|  | 2312 |  | 
|  | 2313 | /** | 
|  | 2314 | * ISO8859xToUTF8 | 
|  | 2315 | * @out:  a pointer to an array of bytes to store the result | 
|  | 2316 | * @outlen:  the length of @out | 
|  | 2317 | * @in:  a pointer to an array of ISO Latin 1 chars | 
|  | 2318 | * @inlen:  the length of @in | 
|  | 2319 | * | 
|  | 2320 | * Take a block of ISO 8859-* chars in and try to convert it to an UTF-8 | 
|  | 2321 | * block of chars out. | 
|  | 2322 | * Returns 0 if success, or -1 otherwise | 
|  | 2323 | * The value of @inlen after return is the number of octets consumed | 
|  | 2324 | * The value of @outlen after return is the number of ocetes produced. | 
|  | 2325 | */ | 
|  | 2326 | static int | 
|  | 2327 | ISO8859xToUTF8(unsigned char* out, int *outlen, | 
|  | 2328 | const unsigned char* in, int *inlen, | 
|  | 2329 | unsigned short const *unicodetable) { | 
|  | 2330 | unsigned char* outstart = out; | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2331 | unsigned char* outend; | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2332 | const unsigned char* instart = in; | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2333 | const unsigned char* inend; | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2334 | const unsigned char* instop = inend; | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2335 | unsigned int c; | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2336 |  | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2337 | if ((out == NULL) || (outlen == NULL) || (inlen == NULL) || | 
| Daniel Veillard | aba37df | 2004-11-11 20:42:04 +0000 | [diff] [blame^] | 2338 | (in == NULL) || (unicodetable == NULL)) | 
| Daniel Veillard | ce682bc | 2004-11-05 17:22:25 +0000 | [diff] [blame] | 2339 | return(-1); | 
|  | 2340 | outend = out + *outlen; | 
|  | 2341 | inend = in + *inlen; | 
|  | 2342 | c = *in; | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2343 | while (in < inend && out < outend - 1) { | 
|  | 2344 | if (c >= 0x80) { | 
|  | 2345 | c = unicodetable [c - 0x80]; | 
|  | 2346 | if (c == 0) { | 
|  | 2347 | /* undefined code point */ | 
|  | 2348 | *outlen = out - outstart; | 
|  | 2349 | *inlen = in - instart; | 
|  | 2350 | return (-1); | 
|  | 2351 | } | 
|  | 2352 | if (c < 0x800) { | 
|  | 2353 | *out++ = ((c >>  6) & 0x1F) | 0xC0; | 
|  | 2354 | *out++ = (c & 0x3F) | 0x80; | 
|  | 2355 | } else { | 
|  | 2356 | *out++ = ((c >>  12) & 0x0F) | 0xE0; | 
|  | 2357 | *out++ = ((c >>  6) & 0x3F) | 0x80; | 
|  | 2358 | *out++ = (c & 0x3F) | 0x80; | 
|  | 2359 | } | 
|  | 2360 | ++in; | 
|  | 2361 | c = *in; | 
|  | 2362 | } | 
|  | 2363 | if (instop - in > outend - out) instop = in + (outend - out); | 
|  | 2364 | while (c < 0x80 && in < instop) { | 
|  | 2365 | *out++ =  c; | 
|  | 2366 | ++in; | 
|  | 2367 | c = *in; | 
|  | 2368 | } | 
|  | 2369 | } | 
|  | 2370 | if (in < inend && out < outend && c < 0x80) { | 
|  | 2371 | *out++ =  c; | 
|  | 2372 | ++in; | 
|  | 2373 | } | 
|  | 2374 | *outlen = out - outstart; | 
|  | 2375 | *inlen = in - instart; | 
| Daniel Veillard | 05f9735 | 2004-10-31 15:35:32 +0000 | [diff] [blame] | 2376 | return (*outlen); | 
| Daniel Veillard | 01fc1a9 | 2003-07-30 15:12:01 +0000 | [diff] [blame] | 2377 | } | 
|  | 2378 |  | 
|  | 2379 |  | 
|  | 2380 | /************************************************************************ | 
|  | 2381 | * Lookup tables for ISO-8859-2..ISO-8859-16 transcoding                * | 
|  | 2382 | ************************************************************************/ | 
|  | 2383 |  | 
|  | 2384 | static unsigned short const xmlunicodetable_ISO8859_2 [128] = { | 
|  | 2385 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2386 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2387 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2388 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2389 | 0x00a0, 0x0104, 0x02d8, 0x0141, 0x00a4, 0x013d, 0x015a, 0x00a7, | 
|  | 2390 | 0x00a8, 0x0160, 0x015e, 0x0164, 0x0179, 0x00ad, 0x017d, 0x017b, | 
|  | 2391 | 0x00b0, 0x0105, 0x02db, 0x0142, 0x00b4, 0x013e, 0x015b, 0x02c7, | 
|  | 2392 | 0x00b8, 0x0161, 0x015f, 0x0165, 0x017a, 0x02dd, 0x017e, 0x017c, | 
|  | 2393 | 0x0154, 0x00c1, 0x00c2, 0x0102, 0x00c4, 0x0139, 0x0106, 0x00c7, | 
|  | 2394 | 0x010c, 0x00c9, 0x0118, 0x00cb, 0x011a, 0x00cd, 0x00ce, 0x010e, | 
|  | 2395 | 0x0110, 0x0143, 0x0147, 0x00d3, 0x00d4, 0x0150, 0x00d6, 0x00d7, | 
|  | 2396 | 0x0158, 0x016e, 0x00da, 0x0170, 0x00dc, 0x00dd, 0x0162, 0x00df, | 
|  | 2397 | 0x0155, 0x00e1, 0x00e2, 0x0103, 0x00e4, 0x013a, 0x0107, 0x00e7, | 
|  | 2398 | 0x010d, 0x00e9, 0x0119, 0x00eb, 0x011b, 0x00ed, 0x00ee, 0x010f, | 
|  | 2399 | 0x0111, 0x0144, 0x0148, 0x00f3, 0x00f4, 0x0151, 0x00f6, 0x00f7, | 
|  | 2400 | 0x0159, 0x016f, 0x00fa, 0x0171, 0x00fc, 0x00fd, 0x0163, 0x02d9, | 
|  | 2401 | }; | 
|  | 2402 |  | 
|  | 2403 | static unsigned char const xmltranscodetable_ISO8859_2 [48 + 6 * 64] = { | 
|  | 2404 | "\x00\x00\x01\x05\x02\x04\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00" | 
|  | 2405 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2406 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2407 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2408 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2409 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2410 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2411 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2412 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2413 | "\xa0\x00\x00\x00\xa4\x00\x00\xa7\xa8\x00\x00\x00\x00\xad\x00\x00" | 
|  | 2414 | "\xb0\x00\x00\x00\xb4\x00\x00\x00\xb8\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2415 | "\x00\x00\xc3\xe3\xa1\xb1\xc6\xe6\x00\x00\x00\x00\xc8\xe8\xcf\xef" | 
|  | 2416 | "\xd0\xf0\x00\x00\x00\x00\x00\x00\xca\xea\xcc\xec\x00\x00\x00\x00" | 
|  | 2417 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2418 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\xc5\xe5\x00\x00\xa5\xb5\x00" | 
|  | 2419 | "\x00\x00\x00\x00\x00\x00\x00\xb7\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2420 | "\x00\x00\x00\x00\x00\x00\x00\x00\xa2\xff\x00\xb2\x00\xbd\x00\x00" | 
|  | 2421 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2422 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2423 | "\x00\xa3\xb3\xd1\xf1\x00\x00\xd2\xf2\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2424 | "\xd5\xf5\x00\x00\xc0\xe0\x00\x00\xd8\xf8\xa6\xb6\x00\x00\xaa\xba" | 
|  | 2425 | "\xa9\xb9\xde\xfe\xab\xbb\x00\x00\x00\x00\x00\x00\x00\x00\xd9\xf9" | 
|  | 2426 | "\xdb\xfb\x00\x00\x00\x00\x00\x00\x00\xac\xbc\xaf\xbf\xae\xbe\x00" | 
|  | 2427 | "\x00\xc1\xc2\x00\xc4\x00\x00\xc7\x00\xc9\x00\xcb\x00\xcd\xce\x00" | 
|  | 2428 | "\x00\x00\x00\xd3\xd4\x00\xd6\xd7\x00\x00\xda\x00\xdc\xdd\x00\xdf" | 
|  | 2429 | "\x00\xe1\xe2\x00\xe4\x00\x00\xe7\x00\xe9\x00\xeb\x00\xed\xee\x00" | 
|  | 2430 | "\x00\x00\x00\xf3\xf4\x00\xf6\xf7\x00\x00\xfa\x00\xfc\xfd\x00\x00" | 
|  | 2431 | }; | 
|  | 2432 |  | 
|  | 2433 | static unsigned short const xmlunicodetable_ISO8859_3 [128] = { | 
|  | 2434 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2435 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2436 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2437 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2438 | 0x00a0, 0x0126, 0x02d8, 0x00a3, 0x00a4, 0x0000, 0x0124, 0x00a7, | 
|  | 2439 | 0x00a8, 0x0130, 0x015e, 0x011e, 0x0134, 0x00ad, 0x0000, 0x017b, | 
|  | 2440 | 0x00b0, 0x0127, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x0125, 0x00b7, | 
|  | 2441 | 0x00b8, 0x0131, 0x015f, 0x011f, 0x0135, 0x00bd, 0x0000, 0x017c, | 
|  | 2442 | 0x00c0, 0x00c1, 0x00c2, 0x0000, 0x00c4, 0x010a, 0x0108, 0x00c7, | 
|  | 2443 | 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, | 
|  | 2444 | 0x0000, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x0120, 0x00d6, 0x00d7, | 
|  | 2445 | 0x011c, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x016c, 0x015c, 0x00df, | 
|  | 2446 | 0x00e0, 0x00e1, 0x00e2, 0x0000, 0x00e4, 0x010b, 0x0109, 0x00e7, | 
|  | 2447 | 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, | 
|  | 2448 | 0x0000, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x0121, 0x00f6, 0x00f7, | 
|  | 2449 | 0x011d, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x016d, 0x015d, 0x02d9, | 
|  | 2450 | }; | 
|  | 2451 |  | 
|  | 2452 | static unsigned char const xmltranscodetable_ISO8859_3 [48 + 7 * 64] = { | 
|  | 2453 | "\x04\x00\x01\x06\x02\x05\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00" | 
|  | 2454 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2455 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2456 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2457 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2458 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2459 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2460 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2461 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2462 | "\xa0\x00\x00\xa3\xa4\x00\x00\xa7\xa8\x00\x00\x00\x00\xad\x00\x00" | 
|  | 2463 | "\xb0\x00\xb2\xb3\xb4\xb5\x00\xb7\xb8\x00\x00\x00\x00\xbd\x00\x00" | 
|  | 2464 | "\x00\x00\x00\x00\x00\x00\x00\x00\xc6\xe6\xc5\xe5\x00\x00\x00\x00" | 
|  | 2465 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xd8\xf8\xab\xbb" | 
|  | 2466 | "\xd5\xf5\x00\x00\xa6\xb6\xa1\xb1\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2467 | "\xa9\xb9\x00\x00\xac\xbc\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2468 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2469 | "\x00\x00\x00\x00\x00\x00\x00\x00\xa2\xff\x00\x00\x00\x00\x00\x00" | 
|  | 2470 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2471 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2472 | "\xf0\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2473 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2474 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2475 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2476 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2477 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xde\xfe\xaa\xba" | 
|  | 2478 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xdd\xfd\x00\x00" | 
|  | 2479 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xaf\xbf\x00\x00\x00" | 
|  | 2480 | "\xc0\xc1\xc2\x00\xc4\x00\x00\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2481 | "\x00\xd1\xd2\xd3\xd4\x00\xd6\xd7\x00\xd9\xda\xdb\xdc\x00\x00\xdf" | 
|  | 2482 | "\xe0\xe1\xe2\x00\xe4\x00\x00\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2483 | "\x00\xf1\xf2\xf3\xf4\x00\xf6\xf7\x00\xf9\xfa\xfb\xfc\x00\x00\x00" | 
|  | 2484 | }; | 
|  | 2485 |  | 
|  | 2486 | static unsigned short const xmlunicodetable_ISO8859_4 [128] = { | 
|  | 2487 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2488 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2489 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2490 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2491 | 0x00a0, 0x0104, 0x0138, 0x0156, 0x00a4, 0x0128, 0x013b, 0x00a7, | 
|  | 2492 | 0x00a8, 0x0160, 0x0112, 0x0122, 0x0166, 0x00ad, 0x017d, 0x00af, | 
|  | 2493 | 0x00b0, 0x0105, 0x02db, 0x0157, 0x00b4, 0x0129, 0x013c, 0x02c7, | 
|  | 2494 | 0x00b8, 0x0161, 0x0113, 0x0123, 0x0167, 0x014a, 0x017e, 0x014b, | 
|  | 2495 | 0x0100, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x012e, | 
|  | 2496 | 0x010c, 0x00c9, 0x0118, 0x00cb, 0x0116, 0x00cd, 0x00ce, 0x012a, | 
|  | 2497 | 0x0110, 0x0145, 0x014c, 0x0136, 0x00d4, 0x00d5, 0x00d6, 0x00d7, | 
|  | 2498 | 0x00d8, 0x0172, 0x00da, 0x00db, 0x00dc, 0x0168, 0x016a, 0x00df, | 
|  | 2499 | 0x0101, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x012f, | 
|  | 2500 | 0x010d, 0x00e9, 0x0119, 0x00eb, 0x0117, 0x00ed, 0x00ee, 0x012b, | 
|  | 2501 | 0x0111, 0x0146, 0x014d, 0x0137, 0x00f4, 0x00f5, 0x00f6, 0x00f7, | 
|  | 2502 | 0x00f8, 0x0173, 0x00fa, 0x00fb, 0x00fc, 0x0169, 0x016b, 0x02d9, | 
|  | 2503 | }; | 
|  | 2504 |  | 
|  | 2505 | static unsigned char const xmltranscodetable_ISO8859_4 [48 + 6 * 64] = { | 
|  | 2506 | "\x00\x00\x01\x05\x02\x03\x00\x00\x00\x00\x00\x04\x00\x00\x00\x00" | 
|  | 2507 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2508 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2509 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2510 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2511 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2512 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2513 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2514 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2515 | "\xa0\x00\x00\x00\xa4\x00\x00\xa7\xa8\x00\x00\x00\x00\xad\x00\xaf" | 
|  | 2516 | "\xb0\x00\x00\x00\xb4\x00\x00\x00\xb8\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2517 | "\xc0\xe0\x00\x00\xa1\xb1\x00\x00\x00\x00\x00\x00\xc8\xe8\x00\x00" | 
|  | 2518 | "\xd0\xf0\xaa\xba\x00\x00\xcc\xec\xca\xea\x00\x00\x00\x00\x00\x00" | 
|  | 2519 | "\x00\x00\xab\xbb\x00\x00\x00\x00\xa5\xb5\xcf\xef\x00\x00\xc7\xe7" | 
|  | 2520 | "\x00\x00\x00\x00\x00\x00\xd3\xf3\xa2\x00\x00\xa6\xb6\x00\x00\x00" | 
|  | 2521 | "\x00\x00\x00\x00\x00\xd1\xf1\x00\x00\x00\xbd\xbf\xd2\xf2\x00\x00" | 
|  | 2522 | "\x00\x00\x00\x00\x00\x00\xa3\xb3\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2523 | "\xa9\xb9\x00\x00\x00\x00\xac\xbc\xdd\xfd\xde\xfe\x00\x00\x00\x00" | 
|  | 2524 | "\x00\x00\xd9\xf9\x00\x00\x00\x00\x00\x00\x00\x00\x00\xae\xbe\x00" | 
|  | 2525 | "\x00\x00\x00\x00\x00\x00\x00\xb7\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2526 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\xff\x00\xb2\x00\x00\x00\x00" | 
|  | 2527 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2528 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2529 | "\x00\xc1\xc2\xc3\xc4\xc5\xc6\x00\x00\xc9\x00\xcb\x00\xcd\xce\x00" | 
|  | 2530 | "\x00\x00\x00\x00\xd4\xd5\xd6\xd7\xd8\x00\xda\xdb\xdc\x00\x00\xdf" | 
|  | 2531 | "\x00\xe1\xe2\xe3\xe4\xe5\xe6\x00\x00\xe9\x00\xeb\x00\xed\xee\x00" | 
|  | 2532 | "\x00\x00\x00\x00\xf4\xf5\xf6\xf7\xf8\x00\xfa\xfb\xfc\x00\x00\x00" | 
|  | 2533 | }; | 
|  | 2534 |  | 
|  | 2535 | static unsigned short const xmlunicodetable_ISO8859_5 [128] = { | 
|  | 2536 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2537 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2538 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2539 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2540 | 0x00a0, 0x0401, 0x0402, 0x0403, 0x0404, 0x0405, 0x0406, 0x0407, | 
|  | 2541 | 0x0408, 0x0409, 0x040a, 0x040b, 0x040c, 0x00ad, 0x040e, 0x040f, | 
|  | 2542 | 0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417, | 
|  | 2543 | 0x0418, 0x0419, 0x041a, 0x041b, 0x041c, 0x041d, 0x041e, 0x041f, | 
|  | 2544 | 0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427, | 
|  | 2545 | 0x0428, 0x0429, 0x042a, 0x042b, 0x042c, 0x042d, 0x042e, 0x042f, | 
|  | 2546 | 0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437, | 
|  | 2547 | 0x0438, 0x0439, 0x043a, 0x043b, 0x043c, 0x043d, 0x043e, 0x043f, | 
|  | 2548 | 0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447, | 
|  | 2549 | 0x0448, 0x0449, 0x044a, 0x044b, 0x044c, 0x044d, 0x044e, 0x044f, | 
|  | 2550 | 0x2116, 0x0451, 0x0452, 0x0453, 0x0454, 0x0455, 0x0456, 0x0457, | 
|  | 2551 | 0x0458, 0x0459, 0x045a, 0x045b, 0x045c, 0x00a7, 0x045e, 0x045f, | 
|  | 2552 | }; | 
|  | 2553 |  | 
|  | 2554 | static unsigned char const xmltranscodetable_ISO8859_5 [48 + 6 * 64] = { | 
|  | 2555 | "\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2556 | "\x02\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2557 | "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2558 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2559 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2560 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2561 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2562 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2563 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2564 | "\xa0\x00\x00\x00\x00\x00\x00\xfd\x00\x00\x00\x00\x00\xad\x00\x00" | 
|  | 2565 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2566 | "\x00\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\x00\xae\xaf" | 
|  | 2567 | "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" | 
|  | 2568 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2569 | "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" | 
|  | 2570 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2571 | "\x00\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\x00\xfe\xff" | 
|  | 2572 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2573 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2574 | "\x00\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2575 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2576 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2577 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2578 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2579 | "\x00\x00\x00\x00\x00\x00\xf0\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2580 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2581 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2582 | }; | 
|  | 2583 |  | 
|  | 2584 | static unsigned short const xmlunicodetable_ISO8859_6 [128] = { | 
|  | 2585 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2586 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2587 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2588 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2589 | 0x00a0, 0x0000, 0x0000, 0x0000, 0x00a4, 0x0000, 0x0000, 0x0000, | 
|  | 2590 | 0x0000, 0x0000, 0x0000, 0x0000, 0x060c, 0x00ad, 0x0000, 0x0000, | 
|  | 2591 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2592 | 0x0000, 0x0000, 0x0000, 0x061b, 0x0000, 0x0000, 0x0000, 0x061f, | 
|  | 2593 | 0x0000, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627, | 
|  | 2594 | 0x0628, 0x0629, 0x062a, 0x062b, 0x062c, 0x062d, 0x062e, 0x062f, | 
|  | 2595 | 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x0637, | 
|  | 2596 | 0x0638, 0x0639, 0x063a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2597 | 0x0640, 0x0641, 0x0642, 0x0643, 0x0644, 0x0645, 0x0646, 0x0647, | 
|  | 2598 | 0x0648, 0x0649, 0x064a, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, | 
|  | 2599 | 0x0650, 0x0651, 0x0652, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2600 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2601 | }; | 
|  | 2602 |  | 
|  | 2603 | static unsigned char const xmltranscodetable_ISO8859_6 [48 + 5 * 64] = { | 
|  | 2604 | "\x02\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2605 | "\x00\x00\x00\x00\x00\x00\x00\x00\x03\x04\x00\x00\x00\x00\x00\x00" | 
|  | 2606 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2607 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2608 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2609 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2610 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2611 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2612 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2613 | "\xa0\x00\x00\x00\xa4\x00\x00\x00\x00\x00\x00\x00\x00\xad\x00\x00" | 
|  | 2614 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2615 | "\xff\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2616 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2617 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2618 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2619 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xac\x00\x00\x00" | 
|  | 2620 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xbb\x00\x00\x00\xbf" | 
|  | 2621 | "\x00\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2622 | "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\x00\x00\x00\x00\x00" | 
|  | 2623 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2624 | "\xf0\xf1\xf2\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2625 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2626 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2627 | }; | 
|  | 2628 |  | 
|  | 2629 | static unsigned short const xmlunicodetable_ISO8859_7 [128] = { | 
|  | 2630 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2631 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2632 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2633 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2634 | 0x00a0, 0x2018, 0x2019, 0x00a3, 0x0000, 0x0000, 0x00a6, 0x00a7, | 
|  | 2635 | 0x00a8, 0x00a9, 0x0000, 0x00ab, 0x00ac, 0x00ad, 0x0000, 0x2015, | 
|  | 2636 | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x0384, 0x0385, 0x0386, 0x00b7, | 
|  | 2637 | 0x0388, 0x0389, 0x038a, 0x00bb, 0x038c, 0x00bd, 0x038e, 0x038f, | 
|  | 2638 | 0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397, | 
|  | 2639 | 0x0398, 0x0399, 0x039a, 0x039b, 0x039c, 0x039d, 0x039e, 0x039f, | 
|  | 2640 | 0x03a0, 0x03a1, 0x0000, 0x03a3, 0x03a4, 0x03a5, 0x03a6, 0x03a7, | 
|  | 2641 | 0x03a8, 0x03a9, 0x03aa, 0x03ab, 0x03ac, 0x03ad, 0x03ae, 0x03af, | 
|  | 2642 | 0x03b0, 0x03b1, 0x03b2, 0x03b3, 0x03b4, 0x03b5, 0x03b6, 0x03b7, | 
|  | 2643 | 0x03b8, 0x03b9, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03be, 0x03bf, | 
|  | 2644 | 0x03c0, 0x03c1, 0x03c2, 0x03c3, 0x03c4, 0x03c5, 0x03c6, 0x03c7, | 
|  | 2645 | 0x03c8, 0x03c9, 0x03ca, 0x03cb, 0x03cc, 0x03cd, 0x03ce, 0x0000, | 
|  | 2646 | }; | 
|  | 2647 |  | 
|  | 2648 | static unsigned char const xmltranscodetable_ISO8859_7 [48 + 7 * 64] = { | 
|  | 2649 | "\x04\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x05\x06" | 
|  | 2650 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2651 | "\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2652 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2653 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2654 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2655 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2656 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2657 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2658 | "\xa0\x00\x00\xa3\x00\x00\xa6\xa7\xa8\xa9\x00\xab\xac\xad\x00\x00" | 
|  | 2659 | "\xb0\xb1\xb2\xb3\x00\x00\x00\xb7\x00\x00\x00\xbb\x00\xbd\x00\x00" | 
|  | 2660 | "\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2661 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2662 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2663 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2664 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2665 | "\x00\x00\x00\x00\x00\xaf\x00\x00\xa1\xa2\x00\x00\x00\x00\x00\x00" | 
|  | 2666 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2667 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2668 | "\xff\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2669 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2670 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2671 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2672 | "\x00\x00\x00\x00\xb4\xb5\xb6\x00\xb8\xb9\xba\x00\xbc\x00\xbe\xbf" | 
|  | 2673 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2674 | "\xd0\xd1\x00\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" | 
|  | 2675 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2676 | "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\x00" | 
|  | 2677 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2678 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2679 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2680 | }; | 
|  | 2681 |  | 
|  | 2682 | static unsigned short const xmlunicodetable_ISO8859_8 [128] = { | 
|  | 2683 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2684 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2685 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2686 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2687 | 0x00a0, 0x0000, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, | 
|  | 2688 | 0x00a8, 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, | 
|  | 2689 | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, | 
|  | 2690 | 0x00b8, 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x0000, | 
|  | 2691 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2692 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2693 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2694 | 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x2017, | 
|  | 2695 | 0x05d0, 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7, | 
|  | 2696 | 0x05d8, 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df, | 
|  | 2697 | 0x05e0, 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7, | 
|  | 2698 | 0x05e8, 0x05e9, 0x05ea, 0x0000, 0x0000, 0x200e, 0x200f, 0x0000, | 
|  | 2699 | }; | 
|  | 2700 |  | 
|  | 2701 | static unsigned char const xmltranscodetable_ISO8859_8 [48 + 7 * 64] = { | 
|  | 2702 | "\x02\x00\x01\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2703 | "\x00\x00\x00\x00\x00\x00\x00\x06\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2704 | "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2705 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2706 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2707 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2708 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2709 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2710 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2711 | "\xa0\x00\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\x00\xab\xac\xad\xae\xaf" | 
|  | 2712 | "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\x00\xbb\xbc\xbd\xbe\x00" | 
|  | 2713 | "\xff\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2714 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2715 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2716 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2717 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2718 | "\x00\x00\x00\x00\x00\x00\x00\xaa\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2719 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2720 | "\x00\x00\x00\x00\x00\x00\x00\xba\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2721 | "\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2722 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2723 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2724 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2725 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xfd\xfe" | 
|  | 2726 | "\x00\x00\x00\x00\x00\x00\x00\xdf\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2727 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2728 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2729 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2730 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2731 | "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\x00\x00\x00\x00\x00" | 
|  | 2732 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2733 | }; | 
|  | 2734 |  | 
|  | 2735 | static unsigned short const xmlunicodetable_ISO8859_9 [128] = { | 
|  | 2736 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2737 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2738 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2739 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2740 | 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, | 
|  | 2741 | 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, | 
|  | 2742 | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, | 
|  | 2743 | 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf, | 
|  | 2744 | 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, | 
|  | 2745 | 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, | 
|  | 2746 | 0x011e, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, | 
|  | 2747 | 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x0130, 0x015e, 0x00df, | 
|  | 2748 | 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, | 
|  | 2749 | 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, | 
|  | 2750 | 0x011f, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, | 
|  | 2751 | 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x0131, 0x015f, 0x00ff, | 
|  | 2752 | }; | 
|  | 2753 |  | 
|  | 2754 | static unsigned char const xmltranscodetable_ISO8859_9 [48 + 5 * 64] = { | 
|  | 2755 | "\x00\x00\x01\x02\x03\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2756 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2757 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2758 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2759 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2760 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2761 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2762 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2763 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2764 | "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf" | 
|  | 2765 | "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" | 
|  | 2766 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2767 | "\x00\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\x00\x00\xdf" | 
|  | 2768 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2769 | "\x00\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\x00\x00\xff" | 
|  | 2770 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2771 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xd0\xf0" | 
|  | 2772 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2773 | "\xdd\xfd\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2774 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2775 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xde\xfe" | 
|  | 2776 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2777 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2778 | }; | 
|  | 2779 |  | 
|  | 2780 | static unsigned short const xmlunicodetable_ISO8859_10 [128] = { | 
|  | 2781 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2782 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2783 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2784 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2785 | 0x00a0, 0x0104, 0x0112, 0x0122, 0x012a, 0x0128, 0x0136, 0x00a7, | 
|  | 2786 | 0x013b, 0x0110, 0x0160, 0x0166, 0x017d, 0x00ad, 0x016a, 0x014a, | 
|  | 2787 | 0x00b0, 0x0105, 0x0113, 0x0123, 0x012b, 0x0129, 0x0137, 0x00b7, | 
|  | 2788 | 0x013c, 0x0111, 0x0161, 0x0167, 0x017e, 0x2015, 0x016b, 0x014b, | 
|  | 2789 | 0x0100, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x012e, | 
|  | 2790 | 0x010c, 0x00c9, 0x0118, 0x00cb, 0x0116, 0x00cd, 0x00ce, 0x00cf, | 
|  | 2791 | 0x00d0, 0x0145, 0x014c, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x0168, | 
|  | 2792 | 0x00d8, 0x0172, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, | 
|  | 2793 | 0x0101, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x012f, | 
|  | 2794 | 0x010d, 0x00e9, 0x0119, 0x00eb, 0x0117, 0x00ed, 0x00ee, 0x00ef, | 
|  | 2795 | 0x00f0, 0x0146, 0x014d, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x0169, | 
|  | 2796 | 0x00f8, 0x0173, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x0138, | 
|  | 2797 | }; | 
|  | 2798 |  | 
|  | 2799 | static unsigned char const xmltranscodetable_ISO8859_10 [48 + 7 * 64] = { | 
|  | 2800 | "\x00\x00\x01\x06\x02\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2801 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2802 | "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2803 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2804 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2805 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2806 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2807 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2808 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2809 | "\xa0\x00\x00\x00\x00\x00\x00\xa7\x00\x00\x00\x00\x00\xad\x00\x00" | 
|  | 2810 | "\xb0\x00\x00\x00\x00\x00\x00\xb7\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2811 | "\xc0\xe0\x00\x00\xa1\xb1\x00\x00\x00\x00\x00\x00\xc8\xe8\x00\x00" | 
|  | 2812 | "\xa9\xb9\xa2\xb2\x00\x00\xcc\xec\xca\xea\x00\x00\x00\x00\x00\x00" | 
|  | 2813 | "\x00\x00\xa3\xb3\x00\x00\x00\x00\xa5\xb5\xa4\xb4\x00\x00\xc7\xe7" | 
|  | 2814 | "\x00\x00\x00\x00\x00\x00\xa6\xb6\xff\x00\x00\xa8\xb8\x00\x00\x00" | 
|  | 2815 | "\x00\x00\x00\x00\x00\xd1\xf1\x00\x00\x00\xaf\xbf\xd2\xf2\x00\x00" | 
|  | 2816 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2817 | "\xaa\xba\x00\x00\x00\x00\xab\xbb\xd7\xf7\xae\xbe\x00\x00\x00\x00" | 
|  | 2818 | "\x00\x00\xd9\xf9\x00\x00\x00\x00\x00\x00\x00\x00\x00\xac\xbc\x00" | 
|  | 2819 | "\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2820 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2821 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2822 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2823 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2824 | "\x00\x00\x00\x00\x00\xbd\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2825 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2826 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2827 | "\x00\xc1\xc2\xc3\xc4\xc5\xc6\x00\x00\xc9\x00\xcb\x00\xcd\xce\xcf" | 
|  | 2828 | "\xd0\x00\x00\xd3\xd4\xd5\xd6\x00\xd8\x00\xda\xdb\xdc\xdd\xde\xdf" | 
|  | 2829 | "\x00\xe1\xe2\xe3\xe4\xe5\xe6\x00\x00\xe9\x00\xeb\x00\xed\xee\xef" | 
|  | 2830 | "\xf0\x00\x00\xf3\xf4\xf5\xf6\x00\xf8\x00\xfa\xfb\xfc\xfd\xfe\x00" | 
|  | 2831 | }; | 
|  | 2832 |  | 
|  | 2833 | static unsigned short const xmlunicodetable_ISO8859_11 [128] = { | 
|  | 2834 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2835 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2836 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2837 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2838 | 0x00a0, 0x0e01, 0x0e02, 0x0e03, 0x0e04, 0x0e05, 0x0e06, 0x0e07, | 
|  | 2839 | 0x0e08, 0x0e09, 0x0e0a, 0x0e0b, 0x0e0c, 0x0e0d, 0x0e0e, 0x0e0f, | 
|  | 2840 | 0x0e10, 0x0e11, 0x0e12, 0x0e13, 0x0e14, 0x0e15, 0x0e16, 0x0e17, | 
|  | 2841 | 0x0e18, 0x0e19, 0x0e1a, 0x0e1b, 0x0e1c, 0x0e1d, 0x0e1e, 0x0e1f, | 
|  | 2842 | 0x0e20, 0x0e21, 0x0e22, 0x0e23, 0x0e24, 0x0e25, 0x0e26, 0x0e27, | 
|  | 2843 | 0x0e28, 0x0e29, 0x0e2a, 0x0e2b, 0x0e2c, 0x0e2d, 0x0e2e, 0x0e2f, | 
|  | 2844 | 0x0e30, 0x0e31, 0x0e32, 0x0e33, 0x0e34, 0x0e35, 0x0e36, 0x0e37, | 
|  | 2845 | 0x0e38, 0x0e39, 0x0e3a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0e3f, | 
|  | 2846 | 0x0e40, 0x0e41, 0x0e42, 0x0e43, 0x0e44, 0x0e45, 0x0e46, 0x0e47, | 
|  | 2847 | 0x0e48, 0x0e49, 0x0e4a, 0x0e4b, 0x0e4c, 0x0e4d, 0x0e4e, 0x0e4f, | 
|  | 2848 | 0x0e50, 0x0e51, 0x0e52, 0x0e53, 0x0e54, 0x0e55, 0x0e56, 0x0e57, | 
|  | 2849 | 0x0e58, 0x0e59, 0x0e5a, 0x0e5b, 0x0000, 0x0000, 0x0000, 0x0000, | 
|  | 2850 | }; | 
|  | 2851 |  | 
|  | 2852 | static unsigned char const xmltranscodetable_ISO8859_11 [48 + 6 * 64] = { | 
|  | 2853 | "\x04\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2854 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2855 | "\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2856 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2857 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2858 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2859 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2860 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2861 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2862 | "\xa0\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2863 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2864 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2865 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2866 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2867 | "\x00\x00\x00\x00\x00\x00\x00\x00\x03\x05\x00\x00\x00\x00\x00\x00" | 
|  | 2868 | "\x00\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf" | 
|  | 2869 | "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf" | 
|  | 2870 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2871 | "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\x00\x00\x00\x00\xdf" | 
|  | 2872 | "\xff\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2873 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2874 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2875 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2876 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2877 | "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\x00\x00\x00\x00" | 
|  | 2878 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2879 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2880 | }; | 
|  | 2881 |  | 
|  | 2882 | static unsigned short const xmlunicodetable_ISO8859_13 [128] = { | 
|  | 2883 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2884 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2885 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2886 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2887 | 0x00a0, 0x201d, 0x00a2, 0x00a3, 0x00a4, 0x201e, 0x00a6, 0x00a7, | 
|  | 2888 | 0x00d8, 0x00a9, 0x0156, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00c6, | 
|  | 2889 | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x201c, 0x00b5, 0x00b6, 0x00b7, | 
|  | 2890 | 0x00f8, 0x00b9, 0x0157, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00e6, | 
|  | 2891 | 0x0104, 0x012e, 0x0100, 0x0106, 0x00c4, 0x00c5, 0x0118, 0x0112, | 
|  | 2892 | 0x010c, 0x00c9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012a, 0x013b, | 
|  | 2893 | 0x0160, 0x0143, 0x0145, 0x00d3, 0x014c, 0x00d5, 0x00d6, 0x00d7, | 
|  | 2894 | 0x0172, 0x0141, 0x015a, 0x016a, 0x00dc, 0x017b, 0x017d, 0x00df, | 
|  | 2895 | 0x0105, 0x012f, 0x0101, 0x0107, 0x00e4, 0x00e5, 0x0119, 0x0113, | 
|  | 2896 | 0x010d, 0x00e9, 0x017a, 0x0117, 0x0123, 0x0137, 0x012b, 0x013c, | 
|  | 2897 | 0x0161, 0x0144, 0x0146, 0x00f3, 0x014d, 0x00f5, 0x00f6, 0x00f7, | 
|  | 2898 | 0x0173, 0x0142, 0x015b, 0x016b, 0x00fc, 0x017c, 0x017e, 0x2019, | 
|  | 2899 | }; | 
|  | 2900 |  | 
|  | 2901 | static unsigned char const xmltranscodetable_ISO8859_13 [48 + 7 * 64] = { | 
|  | 2902 | "\x00\x00\x01\x04\x06\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2903 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2904 | "\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2905 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2906 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2907 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2908 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2909 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2910 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2911 | "\xa0\x00\xa2\xa3\xa4\x00\xa6\xa7\x00\xa9\x00\xab\xac\xad\xae\x00" | 
|  | 2912 | "\xb0\xb1\xb2\xb3\x00\xb5\xb6\xb7\x00\xb9\x00\xbb\xbc\xbd\xbe\x00" | 
|  | 2913 | "\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2914 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2915 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2916 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2917 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2918 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\xff\x00\x00\xb4\xa1\xa5\x00" | 
|  | 2919 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2920 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2921 | "\x00\x00\x00\x00\xc4\xc5\xaf\x00\x00\xc9\x00\x00\x00\x00\x00\x00" | 
|  | 2922 | "\x00\x00\x00\xd3\x00\xd5\xd6\xd7\xa8\x00\x00\x00\xdc\x00\x00\xdf" | 
|  | 2923 | "\x00\x00\x00\x00\xe4\xe5\xbf\x00\x00\xe9\x00\x00\x00\x00\x00\x00" | 
|  | 2924 | "\x00\x00\x00\xf3\x00\xf5\xf6\xf7\xb8\x00\x00\x00\xfc\x00\x00\x00" | 
|  | 2925 | "\x00\xd9\xf9\xd1\xf1\xd2\xf2\x00\x00\x00\x00\x00\xd4\xf4\x00\x00" | 
|  | 2926 | "\x00\x00\x00\x00\x00\x00\xaa\xba\x00\x00\xda\xfa\x00\x00\x00\x00" | 
|  | 2927 | "\xd0\xf0\x00\x00\x00\x00\x00\x00\x00\x00\xdb\xfb\x00\x00\x00\x00" | 
|  | 2928 | "\x00\x00\xd8\xf8\x00\x00\x00\x00\x00\xca\xea\xdd\xfd\xde\xfe\x00" | 
|  | 2929 | "\xc2\xe2\x00\x00\xc0\xe0\xc3\xe3\x00\x00\x00\x00\xc8\xe8\x00\x00" | 
|  | 2930 | "\x00\x00\xc7\xe7\x00\x00\xcb\xeb\xc6\xe6\x00\x00\x00\x00\x00\x00" | 
|  | 2931 | "\x00\x00\xcc\xec\x00\x00\x00\x00\x00\x00\xce\xee\x00\x00\xc1\xe1" | 
|  | 2932 | "\x00\x00\x00\x00\x00\x00\xcd\xed\x00\x00\x00\xcf\xef\x00\x00\x00" | 
|  | 2933 | }; | 
|  | 2934 |  | 
|  | 2935 | static unsigned short const xmlunicodetable_ISO8859_14 [128] = { | 
|  | 2936 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 2937 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 2938 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 2939 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 2940 | 0x00a0, 0x1e02, 0x1e03, 0x00a3, 0x010a, 0x010b, 0x1e0a, 0x00a7, | 
|  | 2941 | 0x1e80, 0x00a9, 0x1e82, 0x1e0b, 0x1ef2, 0x00ad, 0x00ae, 0x0178, | 
|  | 2942 | 0x1e1e, 0x1e1f, 0x0120, 0x0121, 0x1e40, 0x1e41, 0x00b6, 0x1e56, | 
|  | 2943 | 0x1e81, 0x1e57, 0x1e83, 0x1e60, 0x1ef3, 0x1e84, 0x1e85, 0x1e61, | 
|  | 2944 | 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, | 
|  | 2945 | 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, | 
|  | 2946 | 0x0174, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x1e6a, | 
|  | 2947 | 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x0176, 0x00df, | 
|  | 2948 | 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, | 
|  | 2949 | 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, | 
|  | 2950 | 0x0175, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x1e6b, | 
|  | 2951 | 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x0177, 0x00ff, | 
|  | 2952 | }; | 
|  | 2953 |  | 
|  | 2954 | static unsigned char const xmltranscodetable_ISO8859_14 [48 + 10 * 64] = { | 
|  | 2955 | "\x00\x00\x01\x09\x04\x07\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2956 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2957 | "\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2958 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2959 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2960 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2961 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2962 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 2963 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 2964 | "\xa0\x00\x00\xa3\x00\x00\x00\xa7\x00\xa9\x00\x00\x00\xad\xae\x00" | 
|  | 2965 | "\x00\x00\x00\x00\x00\x00\xb6\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2966 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2967 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2968 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2969 | "\x00\x00\x00\x00\x00\x00\x00\x00\x03\x08\x05\x06\x00\x00\x00\x00" | 
|  | 2970 | "\x00\x00\xa1\xa2\x00\x00\x00\x00\x00\x00\xa6\xab\x00\x00\x00\x00" | 
|  | 2971 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xb0\xb1" | 
|  | 2972 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2973 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2974 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\xa5\x00\x00\x00\x00" | 
|  | 2975 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2976 | "\xb2\xb3\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2977 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2978 | "\xa8\xb8\xaa\xba\xbd\xbe\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2979 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2980 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2981 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2982 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2983 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2984 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2985 | "\x00\x00\xac\xbc\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2986 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2987 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2988 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2989 | "\x00\x00\x00\x00\xd0\xf0\xde\xfe\xaf\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2990 | "\xb4\xb5\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2991 | "\x00\x00\x00\x00\x00\x00\xb7\xb9\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2992 | "\xbb\xbf\x00\x00\x00\x00\x00\x00\x00\x00\xd7\xf7\x00\x00\x00\x00" | 
|  | 2993 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 2994 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 2995 | "\x00\xd1\xd2\xd3\xd4\xd5\xd6\x00\xd8\xd9\xda\xdb\xdc\xdd\x00\xdf" | 
|  | 2996 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 2997 | "\x00\xf1\xf2\xf3\xf4\xf5\xf6\x00\xf8\xf9\xfa\xfb\xfc\xfd\x00\xff" | 
|  | 2998 | }; | 
|  | 2999 |  | 
|  | 3000 | static unsigned short const xmlunicodetable_ISO8859_15 [128] = { | 
|  | 3001 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 3002 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 3003 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 3004 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 3005 | 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x20ac, 0x00a5, 0x0160, 0x00a7, | 
|  | 3006 | 0x0161, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af, | 
|  | 3007 | 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x017d, 0x00b5, 0x00b6, 0x00b7, | 
|  | 3008 | 0x017e, 0x00b9, 0x00ba, 0x00bb, 0x0152, 0x0153, 0x0178, 0x00bf, | 
|  | 3009 | 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7, | 
|  | 3010 | 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, | 
|  | 3011 | 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7, | 
|  | 3012 | 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df, | 
|  | 3013 | 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7, | 
|  | 3014 | 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, | 
|  | 3015 | 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7, | 
|  | 3016 | 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff, | 
|  | 3017 | }; | 
|  | 3018 |  | 
|  | 3019 | static unsigned char const xmltranscodetable_ISO8859_15 [48 + 6 * 64] = { | 
|  | 3020 | "\x00\x00\x01\x05\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3021 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3022 | "\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3023 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3024 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3025 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3026 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3027 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 3028 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 3029 | "\xa0\xa1\xa2\xa3\x00\xa5\x00\xa7\x00\xa9\xaa\xab\xac\xad\xae\xaf" | 
|  | 3030 | "\xb0\xb1\xb2\xb3\x00\xb5\xb6\xb7\x00\xb9\xba\xbb\x00\x00\x00\xbf" | 
|  | 3031 | "\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3032 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3033 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3034 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3035 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3036 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3037 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x00\x00\x00" | 
|  | 3038 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3039 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3040 | "\x00\x00\xbc\xbd\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3041 | "\xa6\xa8\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3042 | "\x00\x00\x00\x00\x00\x00\x00\x00\xbe\x00\x00\x00\x00\xb4\xb8\x00" | 
|  | 3043 | "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 3044 | "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf" | 
|  | 3045 | "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 3046 | "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff" | 
|  | 3047 | }; | 
|  | 3048 |  | 
|  | 3049 | static unsigned short const xmlunicodetable_ISO8859_16 [128] = { | 
|  | 3050 | 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, | 
|  | 3051 | 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, | 
|  | 3052 | 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, | 
|  | 3053 | 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, | 
|  | 3054 | 0x00a0, 0x0104, 0x0105, 0x0141, 0x20ac, 0x201e, 0x0160, 0x00a7, | 
|  | 3055 | 0x0161, 0x00a9, 0x0218, 0x00ab, 0x0179, 0x00ad, 0x017a, 0x017b, | 
|  | 3056 | 0x00b0, 0x00b1, 0x010c, 0x0142, 0x017d, 0x201d, 0x00b6, 0x00b7, | 
|  | 3057 | 0x017e, 0x010d, 0x0219, 0x00bb, 0x0152, 0x0153, 0x0178, 0x017c, | 
|  | 3058 | 0x00c0, 0x00c1, 0x00c2, 0x0102, 0x00c4, 0x0106, 0x00c6, 0x00c7, | 
|  | 3059 | 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf, | 
|  | 3060 | 0x0110, 0x0143, 0x00d2, 0x00d3, 0x00d4, 0x0150, 0x00d6, 0x015a, | 
|  | 3061 | 0x0170, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x0118, 0x021a, 0x00df, | 
|  | 3062 | 0x00e0, 0x00e1, 0x00e2, 0x0103, 0x00e4, 0x0107, 0x00e6, 0x00e7, | 
|  | 3063 | 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef, | 
|  | 3064 | 0x0111, 0x0144, 0x00f2, 0x00f3, 0x00f4, 0x0151, 0x00f6, 0x015b, | 
|  | 3065 | 0x0171, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x0119, 0x021b, 0x00ff, | 
|  | 3066 | }; | 
|  | 3067 |  | 
|  | 3068 | static unsigned char const xmltranscodetable_ISO8859_16 [48 + 9 * 64] = { | 
|  | 3069 | "\x00\x00\x01\x08\x02\x03\x00\x00\x07\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3070 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3071 | "\x00\x00\x04\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3072 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3073 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3074 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3075 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3076 | "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f" | 
|  | 3077 | "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f" | 
|  | 3078 | "\xa0\x00\x00\x00\x00\x00\x00\xa7\x00\xa9\x00\xab\x00\xad\x00\x00" | 
|  | 3079 | "\xb0\xb1\x00\x00\x00\x00\xb6\xb7\x00\x00\x00\xbb\x00\x00\x00\x00" | 
|  | 3080 | "\x00\x00\xc3\xe3\xa1\xa2\xc5\xe5\x00\x00\x00\x00\xb2\xb9\x00\x00" | 
|  | 3081 | "\xd0\xf0\x00\x00\x00\x00\x00\x00\xdd\xfd\x00\x00\x00\x00\x00\x00" | 
|  | 3082 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3083 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3084 | "\x00\xa3\xb3\xd1\xf1\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3085 | "\xd5\xf5\xbc\xbd\x00\x00\x00\x00\x00\x00\xd7\xf7\x00\x00\x00\x00" | 
|  | 3086 | "\xa6\xa8\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3087 | "\xd8\xf8\x00\x00\x00\x00\x00\x00\xbe\xac\xae\xaf\xbf\xb4\xb8\x00" | 
|  | 3088 | "\x06\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3089 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3090 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3091 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3092 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3093 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3094 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x00\x00\x00" | 
|  | 3095 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3096 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3097 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\xb5\xa5\x00" | 
|  | 3098 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3099 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3100 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3101 | "\x00\x00\x00\x00\x00\x00\x00\x00\xaa\xba\xde\xfe\x00\x00\x00\x00" | 
|  | 3102 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3103 | "\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00" | 
|  | 3104 | "\xc0\xc1\xc2\x00\xc4\x00\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf" | 
|  | 3105 | "\x00\x00\xd2\xd3\xd4\x00\xd6\x00\x00\xd9\xda\xdb\xdc\x00\x00\xdf" | 
|  | 3106 | "\xe0\xe1\xe2\x00\xe4\x00\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef" | 
|  | 3107 | "\x00\x00\xf2\xf3\xf4\x00\xf6\x00\x00\xf9\xfa\xfb\xfc\x00\x00\xff" | 
|  | 3108 | }; | 
|  | 3109 |  | 
|  | 3110 |  | 
|  | 3111 | /* | 
|  | 3112 | * auto-generated functions for ISO-8859-2 .. ISO-8859-16 | 
|  | 3113 | */ | 
|  | 3114 |  | 
|  | 3115 | static int ISO8859_2ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3116 | const unsigned char* in, int *inlen) { | 
|  | 3117 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_2); | 
|  | 3118 | } | 
|  | 3119 | static int UTF8ToISO8859_2 (unsigned char* out, int *outlen, | 
|  | 3120 | const unsigned char* in, int *inlen) { | 
|  | 3121 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_2); | 
|  | 3122 | } | 
|  | 3123 |  | 
|  | 3124 | static int ISO8859_3ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3125 | const unsigned char* in, int *inlen) { | 
|  | 3126 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_3); | 
|  | 3127 | } | 
|  | 3128 | static int UTF8ToISO8859_3 (unsigned char* out, int *outlen, | 
|  | 3129 | const unsigned char* in, int *inlen) { | 
|  | 3130 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_3); | 
|  | 3131 | } | 
|  | 3132 |  | 
|  | 3133 | static int ISO8859_4ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3134 | const unsigned char* in, int *inlen) { | 
|  | 3135 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_4); | 
|  | 3136 | } | 
|  | 3137 | static int UTF8ToISO8859_4 (unsigned char* out, int *outlen, | 
|  | 3138 | const unsigned char* in, int *inlen) { | 
|  | 3139 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_4); | 
|  | 3140 | } | 
|  | 3141 |  | 
|  | 3142 | static int ISO8859_5ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3143 | const unsigned char* in, int *inlen) { | 
|  | 3144 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_5); | 
|  | 3145 | } | 
|  | 3146 | static int UTF8ToISO8859_5 (unsigned char* out, int *outlen, | 
|  | 3147 | const unsigned char* in, int *inlen) { | 
|  | 3148 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_5); | 
|  | 3149 | } | 
|  | 3150 |  | 
|  | 3151 | static int ISO8859_6ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3152 | const unsigned char* in, int *inlen) { | 
|  | 3153 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_6); | 
|  | 3154 | } | 
|  | 3155 | static int UTF8ToISO8859_6 (unsigned char* out, int *outlen, | 
|  | 3156 | const unsigned char* in, int *inlen) { | 
|  | 3157 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_6); | 
|  | 3158 | } | 
|  | 3159 |  | 
|  | 3160 | static int ISO8859_7ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3161 | const unsigned char* in, int *inlen) { | 
|  | 3162 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_7); | 
|  | 3163 | } | 
|  | 3164 | static int UTF8ToISO8859_7 (unsigned char* out, int *outlen, | 
|  | 3165 | const unsigned char* in, int *inlen) { | 
|  | 3166 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_7); | 
|  | 3167 | } | 
|  | 3168 |  | 
|  | 3169 | static int ISO8859_8ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3170 | const unsigned char* in, int *inlen) { | 
|  | 3171 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_8); | 
|  | 3172 | } | 
|  | 3173 | static int UTF8ToISO8859_8 (unsigned char* out, int *outlen, | 
|  | 3174 | const unsigned char* in, int *inlen) { | 
|  | 3175 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_8); | 
|  | 3176 | } | 
|  | 3177 |  | 
|  | 3178 | static int ISO8859_9ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3179 | const unsigned char* in, int *inlen) { | 
|  | 3180 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_9); | 
|  | 3181 | } | 
|  | 3182 | static int UTF8ToISO8859_9 (unsigned char* out, int *outlen, | 
|  | 3183 | const unsigned char* in, int *inlen) { | 
|  | 3184 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_9); | 
|  | 3185 | } | 
|  | 3186 |  | 
|  | 3187 | static int ISO8859_10ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3188 | const unsigned char* in, int *inlen) { | 
|  | 3189 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_10); | 
|  | 3190 | } | 
|  | 3191 | static int UTF8ToISO8859_10 (unsigned char* out, int *outlen, | 
|  | 3192 | const unsigned char* in, int *inlen) { | 
|  | 3193 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_10); | 
|  | 3194 | } | 
|  | 3195 |  | 
|  | 3196 | static int ISO8859_11ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3197 | const unsigned char* in, int *inlen) { | 
|  | 3198 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_11); | 
|  | 3199 | } | 
|  | 3200 | static int UTF8ToISO8859_11 (unsigned char* out, int *outlen, | 
|  | 3201 | const unsigned char* in, int *inlen) { | 
|  | 3202 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_11); | 
|  | 3203 | } | 
|  | 3204 |  | 
|  | 3205 | static int ISO8859_13ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3206 | const unsigned char* in, int *inlen) { | 
|  | 3207 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_13); | 
|  | 3208 | } | 
|  | 3209 | static int UTF8ToISO8859_13 (unsigned char* out, int *outlen, | 
|  | 3210 | const unsigned char* in, int *inlen) { | 
|  | 3211 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_13); | 
|  | 3212 | } | 
|  | 3213 |  | 
|  | 3214 | static int ISO8859_14ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3215 | const unsigned char* in, int *inlen) { | 
|  | 3216 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_14); | 
|  | 3217 | } | 
|  | 3218 | static int UTF8ToISO8859_14 (unsigned char* out, int *outlen, | 
|  | 3219 | const unsigned char* in, int *inlen) { | 
|  | 3220 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_14); | 
|  | 3221 | } | 
|  | 3222 |  | 
|  | 3223 | static int ISO8859_15ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3224 | const unsigned char* in, int *inlen) { | 
|  | 3225 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_15); | 
|  | 3226 | } | 
|  | 3227 | static int UTF8ToISO8859_15 (unsigned char* out, int *outlen, | 
|  | 3228 | const unsigned char* in, int *inlen) { | 
|  | 3229 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_15); | 
|  | 3230 | } | 
|  | 3231 |  | 
|  | 3232 | static int ISO8859_16ToUTF8 (unsigned char* out, int *outlen, | 
|  | 3233 | const unsigned char* in, int *inlen) { | 
|  | 3234 | return ISO8859xToUTF8 (out, outlen, in, inlen, xmlunicodetable_ISO8859_16); | 
|  | 3235 | } | 
|  | 3236 | static int UTF8ToISO8859_16 (unsigned char* out, int *outlen, | 
|  | 3237 | const unsigned char* in, int *inlen) { | 
|  | 3238 | return UTF8ToISO8859x (out, outlen, in, inlen, xmltranscodetable_ISO8859_16); | 
|  | 3239 | } | 
|  | 3240 |  | 
|  | 3241 | static void | 
|  | 3242 | xmlRegisterCharEncodingHandlersISO8859x (void) { | 
|  | 3243 | xmlNewCharEncodingHandler ("ISO-8859-2", ISO8859_2ToUTF8, UTF8ToISO8859_2); | 
|  | 3244 | xmlNewCharEncodingHandler ("ISO-8859-3", ISO8859_3ToUTF8, UTF8ToISO8859_3); | 
|  | 3245 | xmlNewCharEncodingHandler ("ISO-8859-4", ISO8859_4ToUTF8, UTF8ToISO8859_4); | 
|  | 3246 | xmlNewCharEncodingHandler ("ISO-8859-5", ISO8859_5ToUTF8, UTF8ToISO8859_5); | 
|  | 3247 | xmlNewCharEncodingHandler ("ISO-8859-6", ISO8859_6ToUTF8, UTF8ToISO8859_6); | 
|  | 3248 | xmlNewCharEncodingHandler ("ISO-8859-7", ISO8859_7ToUTF8, UTF8ToISO8859_7); | 
|  | 3249 | xmlNewCharEncodingHandler ("ISO-8859-8", ISO8859_8ToUTF8, UTF8ToISO8859_8); | 
|  | 3250 | xmlNewCharEncodingHandler ("ISO-8859-9", ISO8859_9ToUTF8, UTF8ToISO8859_9); | 
|  | 3251 | xmlNewCharEncodingHandler ("ISO-8859-10", ISO8859_10ToUTF8, UTF8ToISO8859_10); | 
|  | 3252 | xmlNewCharEncodingHandler ("ISO-8859-11", ISO8859_11ToUTF8, UTF8ToISO8859_11); | 
|  | 3253 | xmlNewCharEncodingHandler ("ISO-8859-13", ISO8859_13ToUTF8, UTF8ToISO8859_13); | 
|  | 3254 | xmlNewCharEncodingHandler ("ISO-8859-14", ISO8859_14ToUTF8, UTF8ToISO8859_14); | 
|  | 3255 | xmlNewCharEncodingHandler ("ISO-8859-15", ISO8859_15ToUTF8, UTF8ToISO8859_15); | 
|  | 3256 | xmlNewCharEncodingHandler ("ISO-8859-16", ISO8859_16ToUTF8, UTF8ToISO8859_16); | 
|  | 3257 | } | 
|  | 3258 |  | 
|  | 3259 | #endif | 
|  | 3260 | #endif | 
|  | 3261 |  | 
|  | 3262 |  |