| 1 | /*
|
|---|
| 2 | Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd
|
|---|
| 3 | See the file COPYING for copying permission.
|
|---|
| 4 | */
|
|---|
| 5 |
|
|---|
| 6 | #ifndef XmlParse_INCLUDED
|
|---|
| 7 | #define XmlParse_INCLUDED 1
|
|---|
| 8 |
|
|---|
| 9 | #include <stdlib.h>
|
|---|
| 10 |
|
|---|
| 11 | #include "expat\expat_setup.h"
|
|---|
| 12 | // V0.9.9 (2001-02-10) [umoeller]
|
|---|
| 13 | // to save the app from having to include this as well
|
|---|
| 14 |
|
|---|
| 15 | #ifndef XMLPARSEAPI
|
|---|
| 16 | # ifdef __declspec
|
|---|
| 17 | # define XMLPARSEAPI __declspec(dllimport)
|
|---|
| 18 | # else
|
|---|
| 19 | # define XMLPARSEAPI /* nothing */
|
|---|
| 20 | # endif
|
|---|
| 21 | #endif /* not defined XMLPARSEAPI */
|
|---|
| 22 |
|
|---|
| 23 | #ifdef __cplusplus
|
|---|
| 24 | extern "C" {
|
|---|
| 25 | #endif
|
|---|
| 26 |
|
|---|
| 27 | typedef void *XML_Parser;
|
|---|
| 28 |
|
|---|
| 29 | /* Information is UTF-8 encoded. */
|
|---|
| 30 | typedef char XML_Char;
|
|---|
| 31 | typedef char XML_LChar;
|
|---|
| 32 |
|
|---|
| 33 | enum XML_Content_Type
|
|---|
| 34 | {
|
|---|
| 35 | XML_CTYPE_EMPTY = 1,
|
|---|
| 36 | XML_CTYPE_ANY,
|
|---|
| 37 | XML_CTYPE_MIXED,
|
|---|
| 38 | XML_CTYPE_NAME,
|
|---|
| 39 | XML_CTYPE_CHOICE,
|
|---|
| 40 | XML_CTYPE_SEQ
|
|---|
| 41 | };
|
|---|
| 42 |
|
|---|
| 43 | enum XML_Content_Quant
|
|---|
| 44 | {
|
|---|
| 45 | XML_CQUANT_NONE,
|
|---|
| 46 | XML_CQUANT_OPT,
|
|---|
| 47 | XML_CQUANT_REP,
|
|---|
| 48 | XML_CQUANT_PLUS
|
|---|
| 49 | };
|
|---|
| 50 |
|
|---|
| 51 | /*
|
|---|
| 52 | *@@ XMLCONTENT:
|
|---|
| 53 | * structure passed with the @expat "element declaration handler"
|
|---|
| 54 | * (see XML_SetElementDeclHandler).
|
|---|
| 55 | *
|
|---|
| 56 | * The model argument is the root of a tree of XMLCONTENT
|
|---|
| 57 | * nodes. If type equals XML_CTYPE_EMPTY or XML_CTYPE_ANY,
|
|---|
| 58 | * then quant will be XML_CQUANT_NONE, and the other fields
|
|---|
| 59 | * will be zero or NULL.
|
|---|
| 60 | *
|
|---|
| 61 | * If type is XML_CTYPE_MIXED:
|
|---|
| 62 | *
|
|---|
| 63 | * -- "quant" will be XML_CQUANT_NONE or XML_CQUANT_REP.
|
|---|
| 64 | *
|
|---|
| 65 | * -- "numchildren" will contain the number of elements that
|
|---|
| 66 | * are allowed to be mixed in.
|
|---|
| 67 | *
|
|---|
| 68 | * -- "children" points to a sub-array of XMLCONTENT structures
|
|---|
| 69 | * that will all have type XML_CTYPE_NAME with no quantification.
|
|---|
| 70 | *
|
|---|
| 71 | * Only the root node can be type XML_CTYPE_EMPTY, XML_CTYPE_ANY,
|
|---|
| 72 | * or XML_CTYPE_MIXED.
|
|---|
| 73 | *
|
|---|
| 74 | * For type XML_CTYPE_NAME, the name field points to the
|
|---|
| 75 | * name and the numchildren and children fields will be
|
|---|
| 76 | * zero and NULL. The quant field will indicate any
|
|---|
| 77 | * quantifiers placed on the name.
|
|---|
| 78 | *
|
|---|
| 79 | * Types XML_CTYPE_CHOICE and XML_CTYPE_SEQ indicate a
|
|---|
| 80 | * choice or sequence respectively. The numchildren field
|
|---|
| 81 | * indicates how many nodes in the choice or sequence and
|
|---|
| 82 | * children points to the nodes.
|
|---|
| 83 | *
|
|---|
| 84 | *@@added V0.9.9 (2001-02-14) [umoeller]
|
|---|
| 85 | */
|
|---|
| 86 |
|
|---|
| 87 | typedef struct _XMLCONTENT
|
|---|
| 88 | {
|
|---|
| 89 | enum XML_Content_Type type;
|
|---|
| 90 | // one of:
|
|---|
| 91 | // -- XML_CTYPE_EMPTY --> quant will be XML_CQUANT_NONE, rest is NULL
|
|---|
| 92 | // -- XML_CTYPE_ANY, --> quant will be XML_CQUANT_NONE, rest is NULL
|
|---|
| 93 | // -- XML_CTYPE_MIXED, --> (#PCDATA) gives us this
|
|---|
| 94 | // -- XML_CTYPE_CHOICE, --> choice ("|" list)
|
|---|
| 95 | // -- XML_CTYPE_SEQ --> sequence (comma list)
|
|---|
| 96 |
|
|---|
| 97 | // -- XML_CTYPE_NAME: used for sub-content if content has CML_CTYPE_MIXED;
|
|---|
| 98 | // only "name" is valid for sub-content
|
|---|
| 99 |
|
|---|
| 100 | enum XML_Content_Quant quant;
|
|---|
| 101 | // one of:
|
|---|
| 102 | // -- XML_CQUANT_NONE --> all fields below are NULL
|
|---|
| 103 | // -- XML_CQUANT_OPT, question mark
|
|---|
| 104 | // -- XML_CQUANT_REP, asterisk
|
|---|
| 105 | // -- XML_CQUANT_PLUS plus sign
|
|---|
| 106 |
|
|---|
| 107 | const XML_Char *name;
|
|---|
| 108 |
|
|---|
| 109 | unsigned int numchildren;
|
|---|
| 110 |
|
|---|
| 111 | struct _XMLCONTENT *children;
|
|---|
| 112 |
|
|---|
| 113 | } XMLCONTENT, *PXMLCONTENT;
|
|---|
| 114 |
|
|---|
| 115 |
|
|---|
| 116 | /* This is called for an element declaration. See above for
|
|---|
| 117 | description of the model argument. It's the caller's responsibility
|
|---|
| 118 | to free model when finished with it.
|
|---|
| 119 | */
|
|---|
| 120 |
|
|---|
| 121 | typedef void (* EXPATENTRY XML_ElementDeclHandler) (void *userData,
|
|---|
| 122 | const XML_Char *name,
|
|---|
| 123 | XMLCONTENT *model);
|
|---|
| 124 |
|
|---|
| 125 | void XMLPARSEAPI XML_SetElementDeclHandler(XML_Parser parser,
|
|---|
| 126 | XML_ElementDeclHandler eldecl);
|
|---|
| 127 |
|
|---|
| 128 | /*
|
|---|
| 129 | The Attlist declaration handler is called for *each* attribute. So
|
|---|
| 130 | a single Attlist declaration with multiple attributes declared will
|
|---|
| 131 | generate multiple calls to this handler. The "default" parameter
|
|---|
| 132 | may be NULL in the case of the "#IMPLIED" or "#REQUIRED" keyword.
|
|---|
| 133 | The "isrequired" parameter will be true and the default value will
|
|---|
| 134 | be NULL in the case of "#REQUIRED". If "isrequired" is true and
|
|---|
| 135 | default is non-NULL, then this is a "#FIXED" default.
|
|---|
| 136 | */
|
|---|
| 137 |
|
|---|
| 138 | typedef void (* EXPATENTRY XML_AttlistDeclHandler) (void *userData,
|
|---|
| 139 | const XML_Char *elname,
|
|---|
| 140 | const XML_Char *attname,
|
|---|
| 141 | const XML_Char *att_type,
|
|---|
| 142 | const XML_Char *dflt,
|
|---|
| 143 | int isrequired);
|
|---|
| 144 |
|
|---|
| 145 | void XMLPARSEAPI XML_SetAttlistDeclHandler(XML_Parser parser,
|
|---|
| 146 | XML_AttlistDeclHandler attdecl);
|
|---|
| 147 |
|
|---|
| 148 |
|
|---|
| 149 | /* The XML declaration handler is called for *both* XML declarations and
|
|---|
| 150 | text declarations. The way to distinguish is that the version parameter
|
|---|
| 151 | will be null for text declarations. The encoding parameter may be null
|
|---|
| 152 | for XML declarations. The standalone parameter will be -1, 0, or 1
|
|---|
| 153 | indicating respectively that there was no standalone parameter in
|
|---|
| 154 | the declaration, that it was given as no, or that it was given as yes.
|
|---|
| 155 | */
|
|---|
| 156 |
|
|---|
| 157 | typedef void (* EXPATENTRY XML_XmlDeclHandler) (void *userData,
|
|---|
| 158 | const XML_Char *version,
|
|---|
| 159 | const XML_Char *encoding,
|
|---|
| 160 | int standalone);
|
|---|
| 161 |
|
|---|
| 162 | void XMLPARSEAPI XML_SetXmlDeclHandler(XML_Parser parser,
|
|---|
| 163 | XML_XmlDeclHandler xmldecl);
|
|---|
| 164 |
|
|---|
| 165 |
|
|---|
| 166 | typedef struct {
|
|---|
| 167 | void *(*malloc_fcn)(size_t size);
|
|---|
| 168 | void *(*realloc_fcn)(void *ptr, size_t size);
|
|---|
| 169 | void (*free_fcn)(void *ptr);
|
|---|
| 170 | } XML_Memory_Handling_Suite;
|
|---|
| 171 |
|
|---|
| 172 | /* Constructs a new parser; encoding is the encoding specified by the external
|
|---|
| 173 | protocol or null if there is none specified. */
|
|---|
| 174 |
|
|---|
| 175 | XML_Parser XMLPARSEAPI XML_ParserCreate(const XML_Char *encoding);
|
|---|
| 176 |
|
|---|
| 177 | /* Constructs a new parser and namespace processor. Element type names
|
|---|
| 178 | and attribute names that belong to a namespace will be expanded;
|
|---|
| 179 | unprefixed attribute names are never expanded; unprefixed element type
|
|---|
| 180 | names are expanded only if there is a default namespace. The expanded
|
|---|
| 181 | name is the concatenation of the namespace URI, the namespace separator character,
|
|---|
| 182 | and the local part of the name. If the namespace separator is '\0' then
|
|---|
| 183 | the namespace URI and the local part will be concatenated without any
|
|---|
| 184 | separator. When a namespace is not declared, the name and prefix will be
|
|---|
| 185 | passed through without expansion. */
|
|---|
| 186 |
|
|---|
| 187 | XML_Parser XMLPARSEAPI XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
|
|---|
| 188 |
|
|---|
| 189 |
|
|---|
| 190 | /* Constructs a new parser using the memory management suit referred to
|
|---|
| 191 | by memsuite. If memsuite is NULL, then use the standard library memory
|
|---|
| 192 | suite. If namespaceSeparator is non-NULL it creates a parser with
|
|---|
| 193 | namespace processing as described above. The character pointed at
|
|---|
| 194 | will serve as the namespace separator.
|
|---|
| 195 |
|
|---|
| 196 | All further memory operations used for the created parser will come from
|
|---|
| 197 | the given suite.
|
|---|
| 198 | */
|
|---|
| 199 |
|
|---|
| 200 | XML_Parser XMLPARSEAPI XML_ParserCreate_MM(const XML_Char *encoding,
|
|---|
| 201 | const XML_Memory_Handling_Suite *memsuite,
|
|---|
| 202 | const XML_Char *namespaceSeparator);
|
|---|
| 203 |
|
|---|
| 204 | /* atts is array of name/value pairs, terminated by 0;
|
|---|
| 205 | names and values are 0 terminated. */
|
|---|
| 206 |
|
|---|
| 207 | typedef void (* EXPATENTRY XML_StartElementHandler)(void *userData,
|
|---|
| 208 | const XML_Char *name,
|
|---|
| 209 | const XML_Char **atts);
|
|---|
| 210 |
|
|---|
| 211 | typedef void (* EXPATENTRY XML_EndElementHandler)(void *userData,
|
|---|
| 212 | const XML_Char *name);
|
|---|
| 213 |
|
|---|
| 214 |
|
|---|
| 215 | /* s is not 0 terminated. */
|
|---|
| 216 | typedef void (* EXPATENTRY XML_CharacterDataHandler)(void *userData,
|
|---|
| 217 | const XML_Char *s,
|
|---|
| 218 | int len);
|
|---|
| 219 |
|
|---|
| 220 | /* target and data are 0 terminated */
|
|---|
| 221 | typedef void (* EXPATENTRY XML_ProcessingInstructionHandler)(void *userData,
|
|---|
| 222 | const XML_Char *target,
|
|---|
| 223 | const XML_Char *data);
|
|---|
| 224 |
|
|---|
| 225 | /* data is 0 terminated */
|
|---|
| 226 | typedef void (* EXPATENTRY XML_CommentHandler)(void *userData, const XML_Char *data);
|
|---|
| 227 |
|
|---|
| 228 | typedef void (* EXPATENTRY XML_StartCdataSectionHandler)(void *userData);
|
|---|
| 229 | typedef void (* EXPATENTRY XML_EndCdataSectionHandler)(void *userData);
|
|---|
| 230 |
|
|---|
| 231 | /* This is called for any characters in the XML document for
|
|---|
| 232 | which there is no applicable handler. This includes both
|
|---|
| 233 | characters that are part of markup which is of a kind that is
|
|---|
| 234 | not reported (comments, markup declarations), or characters
|
|---|
| 235 | that are part of a construct which could be reported but
|
|---|
| 236 | for which no handler has been supplied. The characters are passed
|
|---|
| 237 | exactly as they were in the XML document except that
|
|---|
| 238 | they will be encoded in UTF-8. Line boundaries are not normalized.
|
|---|
| 239 | Note that a byte order mark character is not passed to the default handler.
|
|---|
| 240 | There are no guarantees about how characters are divided between calls
|
|---|
| 241 | to the default handler: for example, a comment might be split between
|
|---|
| 242 | multiple calls. */
|
|---|
| 243 |
|
|---|
| 244 | typedef void (* EXPATENTRY XML_DefaultHandler)(void *userData,
|
|---|
| 245 | const XML_Char *s,
|
|---|
| 246 | int len);
|
|---|
| 247 |
|
|---|
| 248 | /* This is called for the start of the DOCTYPE declaration, before
|
|---|
| 249 | any DTD or internal subset is parsed. */
|
|---|
| 250 |
|
|---|
| 251 | typedef void (* EXPATENTRY XML_StartDoctypeDeclHandler)(void *userData,
|
|---|
| 252 | const XML_Char *doctypeName,
|
|---|
| 253 | const XML_Char *sysid,
|
|---|
| 254 | const XML_Char *pubid,
|
|---|
| 255 | int has_internal_subset);
|
|---|
| 256 |
|
|---|
| 257 | /* This is called for the start of the DOCTYPE declaration when the
|
|---|
| 258 | closing > is encountered, but after processing any external subset. */
|
|---|
| 259 | typedef void (* EXPATENTRY XML_EndDoctypeDeclHandler)(void *userData);
|
|---|
| 260 |
|
|---|
| 261 | /* This is called for entity declarations. The is_parameter_entity
|
|---|
| 262 | argument will be non-zero if the entity is a parameter entity, zero
|
|---|
| 263 | otherwise.
|
|---|
| 264 |
|
|---|
| 265 | For internal entities (<!ENTITY foo "bar">), value will
|
|---|
| 266 | be non-null and systemId, publicID, and notationName will be null.
|
|---|
| 267 | The value string is NOT null terminated; the length is provided in
|
|---|
| 268 | the value_length argument. Since it is legal to have zero-length
|
|---|
| 269 | values, do not use this argument to test for internal entities.
|
|---|
| 270 |
|
|---|
| 271 | For external entities, value will be null and systemId will be non-null.
|
|---|
| 272 | The publicId argument will be null unless a public identifier was
|
|---|
| 273 | provided. The notationName argument will have a non-null value only
|
|---|
| 274 | for unparsed entity declarations.
|
|---|
| 275 | */
|
|---|
| 276 |
|
|---|
| 277 | typedef void (* EXPATENTRY XML_EntityDeclHandler)(void *userData,
|
|---|
| 278 | const XML_Char *entityName,
|
|---|
| 279 | int is_parameter_entity,
|
|---|
| 280 | const XML_Char *value,
|
|---|
| 281 | int value_length,
|
|---|
| 282 | const XML_Char *base,
|
|---|
| 283 | const XML_Char *systemId,
|
|---|
| 284 | const XML_Char *publicId,
|
|---|
| 285 | const XML_Char *notationName);
|
|---|
| 286 |
|
|---|
| 287 | void XMLPARSEAPI XML_SetEntityDeclHandler(XML_Parser parser,
|
|---|
| 288 | XML_EntityDeclHandler handler);
|
|---|
| 289 |
|
|---|
| 290 | /* OBSOLETE -- OBSOLETE -- OBSOLETE
|
|---|
| 291 | This handler has been superceded by the EntityDeclHandler above.
|
|---|
| 292 | It is provided here for backward compatibility.
|
|---|
| 293 | This is called for a declaration of an unparsed (NDATA)
|
|---|
| 294 | entity. The base argument is whatever was set by XML_SetBase.
|
|---|
| 295 | The entityName, systemId and notationName arguments will never be null.
|
|---|
| 296 | The other arguments may be. */
|
|---|
| 297 |
|
|---|
| 298 | typedef void (* EXPATENTRY XML_UnparsedEntityDeclHandler)(void *userData,
|
|---|
| 299 | const XML_Char *entityName,
|
|---|
| 300 | const XML_Char *base,
|
|---|
| 301 | const XML_Char *systemId,
|
|---|
| 302 | const XML_Char *publicId,
|
|---|
| 303 | const XML_Char *notationName);
|
|---|
| 304 |
|
|---|
| 305 | /* This is called for a declaration of notation.
|
|---|
| 306 | The base argument is whatever was set by XML_SetBase.
|
|---|
| 307 | The notationName will never be null. The other arguments can be. */
|
|---|
| 308 |
|
|---|
| 309 | typedef void (* EXPATENTRY XML_NotationDeclHandler)(void *userData,
|
|---|
| 310 | const XML_Char *notationName,
|
|---|
| 311 | const XML_Char *base,
|
|---|
| 312 | const XML_Char *systemId,
|
|---|
| 313 | const XML_Char *publicId);
|
|---|
| 314 |
|
|---|
| 315 | /* When namespace processing is enabled, these are called once for
|
|---|
| 316 | each namespace declaration. The call to the start and end element
|
|---|
| 317 | handlers occur between the calls to the start and end namespace
|
|---|
| 318 | declaration handlers. For an xmlns attribute, prefix will be null.
|
|---|
| 319 | For an xmlns="" attribute, uri will be null. */
|
|---|
| 320 |
|
|---|
| 321 | typedef void (* EXPATENTRY XML_StartNamespaceDeclHandler)(void *userData,
|
|---|
| 322 | const XML_Char *prefix,
|
|---|
| 323 | const XML_Char *uri);
|
|---|
| 324 |
|
|---|
| 325 | typedef void (* EXPATENTRY XML_EndNamespaceDeclHandler)(void *userData,
|
|---|
| 326 | const XML_Char *prefix);
|
|---|
| 327 |
|
|---|
| 328 | /* This is called if the document is not standalone (it has an
|
|---|
| 329 | external subset or a reference to a parameter entity, but does not
|
|---|
| 330 | have standalone="yes"). If this handler returns 0, then processing
|
|---|
| 331 | will not continue, and the parser will return a
|
|---|
| 332 | ERROR_EXPAT_NOT_STANDALONE error. */
|
|---|
| 333 |
|
|---|
| 334 | typedef int (* EXPATENTRY XML_NotStandaloneHandler)(void *userData);
|
|---|
| 335 |
|
|---|
| 336 | /* This is called for a reference to an external parsed general entity.
|
|---|
| 337 | The referenced entity is not automatically parsed.
|
|---|
| 338 | The application can parse it immediately or later using
|
|---|
| 339 | XML_ExternalEntityParserCreate.
|
|---|
| 340 | The parser argument is the parser parsing the entity containing the reference;
|
|---|
| 341 | it can be passed as the parser argument to XML_ExternalEntityParserCreate.
|
|---|
| 342 | The systemId argument is the system identifier as specified in the entity declaration;
|
|---|
| 343 | it will not be null.
|
|---|
| 344 | The base argument is the system identifier that should be used as the base for
|
|---|
| 345 | resolving systemId if systemId was relative; this is set by XML_SetBase;
|
|---|
| 346 | it may be null.
|
|---|
| 347 | The publicId argument is the public identifier as specified in the entity declaration,
|
|---|
| 348 | or null if none was specified; the whitespace in the public identifier
|
|---|
| 349 | will have been normalized as required by the XML spec.
|
|---|
| 350 | The context argument specifies the parsing context in the format
|
|---|
| 351 | expected by the context argument to
|
|---|
| 352 | XML_ExternalEntityParserCreate; context is valid only until the handler
|
|---|
| 353 | returns, so if the referenced entity is to be parsed later, it must be copied.
|
|---|
| 354 | The handler should return 0 if processing should not continue because of
|
|---|
| 355 | a fatal error in the handling of the external entity.
|
|---|
| 356 | In this case the calling parser will return an ERROR_EXPAT_EXTERNAL_ENTITY_HANDLING
|
|---|
| 357 | error.
|
|---|
| 358 | Note that unlike other handlers the first argument is the parser, not userData. */
|
|---|
| 359 |
|
|---|
| 360 | typedef int (* EXPATENTRY XML_ExternalEntityRefHandler)(XML_Parser parser,
|
|---|
| 361 | const XML_Char *context,
|
|---|
| 362 | const XML_Char *base,
|
|---|
| 363 | const XML_Char *systemId,
|
|---|
| 364 | const XML_Char *publicId);
|
|---|
| 365 |
|
|---|
| 366 | /* This structure is filled in by the XML_UnknownEncodingHandler
|
|---|
| 367 | to provide information to the parser about encodings that are unknown
|
|---|
| 368 | to the parser.
|
|---|
| 369 | The map[b] member gives information about byte sequences
|
|---|
| 370 | whose first byte is b.
|
|---|
| 371 | If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar value c.
|
|---|
| 372 | If map[b] is -1, then the byte sequence is malformed.
|
|---|
| 373 | If map[b] is -n, where n >= 2, then b is the first byte of an n-byte
|
|---|
| 374 | sequence that encodes a single Unicode scalar value.
|
|---|
| 375 | The data member will be passed as the first argument to the convert function.
|
|---|
| 376 | The convert function is used to convert multibyte sequences;
|
|---|
| 377 | s will point to a n-byte sequence where map[(unsigned char)*s] == -n.
|
|---|
| 378 | The convert function must return the Unicode scalar value
|
|---|
| 379 | represented by this byte sequence or -1 if the byte sequence is malformed.
|
|---|
| 380 | The convert function may be null if the encoding is a single-byte encoding,
|
|---|
| 381 | that is if map[b] >= -1 for all bytes b.
|
|---|
| 382 | When the parser is finished with the encoding, then if release is not null,
|
|---|
| 383 | it will call release passing it the data member;
|
|---|
| 384 | once release has been called, the convert function will not be called again.
|
|---|
| 385 |
|
|---|
| 386 | Expat places certain restrictions on the encodings that are supported
|
|---|
| 387 | using this mechanism.
|
|---|
| 388 |
|
|---|
| 389 | 1. Every ASCII character that can appear in a well-formed XML document,
|
|---|
| 390 | other than the characters
|
|---|
| 391 |
|
|---|
| 392 | $@\^`{}~
|
|---|
| 393 |
|
|---|
| 394 | must be represented by a single byte, and that byte must be the
|
|---|
| 395 | same byte that represents that character in ASCII.
|
|---|
| 396 |
|
|---|
| 397 | 2. No character may require more than 4 bytes to encode.
|
|---|
| 398 |
|
|---|
| 399 | 3. All characters encoded must have Unicode scalar values <= 0xFFFF,
|
|---|
| 400 | (ie characters that would be encoded by surrogates in UTF-16
|
|---|
| 401 | are not allowed). Note that this restriction doesn't apply to
|
|---|
| 402 | the built-in support for UTF-8 and UTF-16.
|
|---|
| 403 |
|
|---|
| 404 | 4. No Unicode character may be encoded by more than one distinct sequence
|
|---|
| 405 | of bytes. */
|
|---|
| 406 |
|
|---|
| 407 | /*
|
|---|
| 408 | *@@ XML_Encoding:
|
|---|
| 409 | * structure passed with the UnknownEncodingHandler (see
|
|---|
| 410 | * XML_SetUnknownEncodingHandler).
|
|---|
| 411 | *
|
|---|
| 412 | * The map array contains information for every possible
|
|---|
| 413 | * possible leading byte in a byte sequence.
|
|---|
| 414 | *
|
|---|
| 415 | * -- If the corresponding value is >= 0, then it's a single byte
|
|---|
| 416 | * sequence and the byte encodes that Unicode value.
|
|---|
| 417 | *
|
|---|
| 418 | * -- If the value is -1, then that byte is invalid as the
|
|---|
| 419 | * initial byte in a sequence.
|
|---|
| 420 | *
|
|---|
| 421 | * -- If the value is -2, -3, or -4, then the byte is the beginning
|
|---|
| 422 | * of a 2, 3, or 4 byte sequence, respectively. The actual
|
|---|
| 423 | * conversion is then accomplished by a call to the function
|
|---|
| 424 | * pointed at by "convert". This function should return the
|
|---|
| 425 | * Unicode scalar value for the sequence or -1 if the sequence
|
|---|
| 426 | * is malformed.
|
|---|
| 427 | *
|
|---|
| 428 | * The "convert" pointer may be null if there are only
|
|---|
| 429 | * single byte codes. The data parameter passed to the
|
|---|
| 430 | * convert function is the data pointer from
|
|---|
| 431 | * XML_Encoding. The string s is NOT null terminated and
|
|---|
| 432 | * points at the sequence of bytes to be converted.
|
|---|
| 433 | *
|
|---|
| 434 | * The function pointed at by "release" is called by the parser
|
|---|
| 435 | * when it is finished with the encoding. It may be null.
|
|---|
| 436 | */
|
|---|
| 437 |
|
|---|
| 438 | typedef struct _XML_Encoding
|
|---|
| 439 | {
|
|---|
| 440 | int map[256];
|
|---|
| 441 | void *data;
|
|---|
| 442 | int (* EXPATENTRY convert)(void *data, const char *s);
|
|---|
| 443 | void (* EXPATENTRY release)(void *data);
|
|---|
| 444 | } XML_Encoding;
|
|---|
| 445 |
|
|---|
| 446 | typedef int (* EXPATENTRY XML_UnknownEncodingHandler)(void *encodingHandlerData,
|
|---|
| 447 | const XML_Char *name,
|
|---|
| 448 | XML_Encoding *info);
|
|---|
| 449 |
|
|---|
| 450 | void XMLPARSEAPI XML_SetElementHandler(XML_Parser parser,
|
|---|
| 451 | XML_StartElementHandler start,
|
|---|
| 452 | XML_EndElementHandler end);
|
|---|
| 453 |
|
|---|
| 454 | void XMLPARSEAPI XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler);
|
|---|
| 455 |
|
|---|
| 456 | void XMLPARSEAPI XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler);
|
|---|
| 457 |
|
|---|
| 458 | void XMLPARSEAPI XML_SetCharacterDataHandler(XML_Parser parser,
|
|---|
| 459 | XML_CharacterDataHandler handler);
|
|---|
| 460 |
|
|---|
| 461 | void XMLPARSEAPI XML_SetProcessingInstructionHandler(XML_Parser parser,
|
|---|
| 462 | XML_ProcessingInstructionHandler handler);
|
|---|
| 463 | void XMLPARSEAPI XML_SetCommentHandler(XML_Parser parser,
|
|---|
| 464 | XML_CommentHandler handler);
|
|---|
| 465 |
|
|---|
| 466 | void XMLPARSEAPI XML_SetCdataSectionHandler(XML_Parser parser,
|
|---|
| 467 | XML_StartCdataSectionHandler start,
|
|---|
| 468 | XML_EndCdataSectionHandler end);
|
|---|
| 469 |
|
|---|
| 470 | void XMLPARSEAPI XML_SetStartCdataSectionHandler(XML_Parser parser,
|
|---|
| 471 | XML_StartCdataSectionHandler start);
|
|---|
| 472 |
|
|---|
| 473 | void XMLPARSEAPI XML_SetEndCdataSectionHandler(XML_Parser parser,
|
|---|
| 474 | XML_EndCdataSectionHandler end);
|
|---|
| 475 |
|
|---|
| 476 | /* This sets the default handler and also inhibits expansion of internal entities.
|
|---|
| 477 | The entity reference will be passed to the default handler. */
|
|---|
| 478 |
|
|---|
| 479 | void XMLPARSEAPI XML_SetDefaultHandler(XML_Parser parser,
|
|---|
| 480 | XML_DefaultHandler handler);
|
|---|
| 481 |
|
|---|
| 482 | /* This sets the default handler but does not inhibit expansion of internal entities.
|
|---|
| 483 | The entity reference will not be passed to the default handler. */
|
|---|
| 484 |
|
|---|
| 485 | void XMLPARSEAPI XML_SetDefaultHandlerExpand(XML_Parser parser,
|
|---|
| 486 | XML_DefaultHandler handler);
|
|---|
| 487 |
|
|---|
| 488 | void XMLPARSEAPI XML_SetDoctypeDeclHandler(XML_Parser parser,
|
|---|
| 489 | XML_StartDoctypeDeclHandler start,
|
|---|
| 490 | XML_EndDoctypeDeclHandler end);
|
|---|
| 491 |
|
|---|
| 492 | void XMLPARSEAPI XML_SetStartDoctypeDeclHandler(XML_Parser parser,
|
|---|
| 493 | XML_StartDoctypeDeclHandler start);
|
|---|
| 494 |
|
|---|
| 495 | void XMLPARSEAPI XML_SetEndDoctypeDeclHandler(XML_Parser parser,
|
|---|
| 496 | XML_EndDoctypeDeclHandler end);
|
|---|
| 497 |
|
|---|
| 498 | void XMLPARSEAPI XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
|
|---|
| 499 | XML_UnparsedEntityDeclHandler handler);
|
|---|
| 500 |
|
|---|
| 501 | void XMLPARSEAPI XML_SetNotationDeclHandler(XML_Parser parser,
|
|---|
| 502 | XML_NotationDeclHandler handler);
|
|---|
| 503 |
|
|---|
| 504 | void XMLPARSEAPI XML_SetNamespaceDeclHandler(XML_Parser parser,
|
|---|
| 505 | XML_StartNamespaceDeclHandler start,
|
|---|
| 506 | XML_EndNamespaceDeclHandler end);
|
|---|
| 507 |
|
|---|
| 508 | void XMLPARSEAPI XML_SetStartNamespaceDeclHandler(XML_Parser parser,
|
|---|
| 509 | XML_StartNamespaceDeclHandler start);
|
|---|
| 510 |
|
|---|
| 511 | void XMLPARSEAPI XML_SetEndNamespaceDeclHandler(XML_Parser parser,
|
|---|
| 512 | XML_EndNamespaceDeclHandler end);
|
|---|
| 513 |
|
|---|
| 514 | void XMLPARSEAPI XML_SetNotStandaloneHandler(XML_Parser parser,
|
|---|
| 515 | XML_NotStandaloneHandler handler);
|
|---|
| 516 |
|
|---|
| 517 | void XMLPARSEAPI XML_SetExternalEntityRefHandler(XML_Parser parser,
|
|---|
| 518 | XML_ExternalEntityRefHandler handler);
|
|---|
| 519 |
|
|---|
| 520 | /* If a non-null value for arg is specified here, then it will be passed
|
|---|
| 521 | as the first argument to the external entity ref handler instead
|
|---|
| 522 | of the parser object. */
|
|---|
| 523 | void XMLPARSEAPI XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg);
|
|---|
| 524 |
|
|---|
| 525 | void XMLPARSEAPI XML_SetUnknownEncodingHandler(XML_Parser parser,
|
|---|
| 526 | XML_UnknownEncodingHandler handler,
|
|---|
| 527 | void *encodingHandlerData);
|
|---|
| 528 |
|
|---|
| 529 | /* This can be called within a handler for a start element, end element,
|
|---|
| 530 | processing instruction or character data. It causes the corresponding
|
|---|
| 531 | markup to be passed to the default handler. */
|
|---|
| 532 | void XML_DefaultCurrent(XML_Parser parser);
|
|---|
| 533 |
|
|---|
| 534 | /* If do_nst is non-zero, and namespace processing is in effect, and
|
|---|
| 535 | a name has a prefix (i.e. an explicit namespace qualifier) then
|
|---|
| 536 | that name is returned as a triplet in a single
|
|---|
| 537 | string separated by the separator character specified when the parser
|
|---|
| 538 | was created: URI + sep + local_name + sep + prefix.
|
|---|
| 539 |
|
|---|
| 540 | If do_nst is zero, then namespace information is returned in the
|
|---|
| 541 | default manner (URI + sep + local_name) whether or not the names
|
|---|
| 542 | has a prefix.
|
|---|
| 543 | */
|
|---|
| 544 |
|
|---|
| 545 | void XMLPARSEAPI XML_SetReturnNSTriplet(XML_Parser parser, int do_nst);
|
|---|
| 546 |
|
|---|
| 547 | /* This value is passed as the userData argument to callbacks. */
|
|---|
| 548 | void XMLPARSEAPI XML_SetUserData(XML_Parser parser, void *userData);
|
|---|
| 549 |
|
|---|
| 550 | /* Returns the last value set by XML_SetUserData or null. */
|
|---|
| 551 | #define XML_GetUserData(parser) (*(void **)(parser))
|
|---|
| 552 |
|
|---|
| 553 | /* This is equivalent to supplying an encoding argument
|
|---|
| 554 | to XML_ParserCreate. It must not be called after XML_Parse
|
|---|
| 555 | or XML_ParseBuffer. */
|
|---|
| 556 |
|
|---|
| 557 | int XMLPARSEAPI XML_SetEncoding(XML_Parser parser, const XML_Char *encoding);
|
|---|
| 558 |
|
|---|
| 559 | /* If this function is called, then the parser will be passed
|
|---|
| 560 | as the first argument to callbacks instead of userData.
|
|---|
| 561 | The userData will still be accessible using XML_GetUserData. */
|
|---|
| 562 |
|
|---|
| 563 | void XMLPARSEAPI XML_UseParserAsHandlerArg(XML_Parser parser);
|
|---|
| 564 |
|
|---|
| 565 | /* Sets the base to be used for resolving relative URIs in system identifiers in
|
|---|
| 566 | declarations. Resolving relative identifiers is left to the application:
|
|---|
| 567 | this value will be passed through as the base argument to the
|
|---|
| 568 | XML_ExternalEntityRefHandler, XML_NotationDeclHandler
|
|---|
| 569 | and XML_UnparsedEntityDeclHandler. The base argument will be copied.
|
|---|
| 570 | Returns zero if out of memory, non-zero otherwise. */
|
|---|
| 571 |
|
|---|
| 572 | int XMLPARSEAPI XML_SetBase(XML_Parser parser, const XML_Char *base);
|
|---|
| 573 |
|
|---|
| 574 | const XML_Char XMLPARSEAPI * XML_GetBase(XML_Parser parser);
|
|---|
| 575 |
|
|---|
| 576 | /* Returns the number of the attribute/value pairs passed in last call
|
|---|
| 577 | to the XML_StartElementHandler that were specified in the start-tag
|
|---|
| 578 | rather than defaulted. Each attribute/value pair counts as 2; thus
|
|---|
| 579 | this correspondds to an index into the atts array passed to the
|
|---|
| 580 | XML_StartElementHandler. */
|
|---|
| 581 |
|
|---|
| 582 | int XMLPARSEAPI XML_GetSpecifiedAttributeCount(XML_Parser parser);
|
|---|
| 583 |
|
|---|
| 584 | /* Returns the index of the ID attribute passed in the last call to
|
|---|
| 585 | XML_StartElementHandler, or -1 if there is no ID attribute. Each
|
|---|
| 586 | attribute/value pair counts as 2; thus this correspondds to an index
|
|---|
| 587 | into the atts array passed to the XML_StartElementHandler. */
|
|---|
| 588 |
|
|---|
| 589 | int XMLPARSEAPI XML_GetIdAttributeIndex(XML_Parser parser);
|
|---|
| 590 |
|
|---|
| 591 | /* Parses some input. Returns 0 if a fatal error is detected.
|
|---|
| 592 | The last call to XML_Parse must have isFinal true;
|
|---|
| 593 | len may be zero for this call (or any other). */
|
|---|
| 594 | int XMLPARSEAPI XML_Parse(XML_Parser parser, const char *s, int len, int isFinal);
|
|---|
| 595 |
|
|---|
| 596 | void XMLPARSEAPI * XML_GetBuffer(XML_Parser parser, int len);
|
|---|
| 597 |
|
|---|
| 598 | int XMLPARSEAPI XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
|
|---|
| 599 |
|
|---|
| 600 | /* Creates an XML_Parser object that can parse an external general entity;
|
|---|
| 601 | context is a '\0'-terminated string specifying the parse context;
|
|---|
| 602 | encoding is a '\0'-terminated string giving the name of the externally specified encoding,
|
|---|
| 603 | or null if there is no externally specified encoding.
|
|---|
| 604 | The context string consists of a sequence of tokens separated by formfeeds (\f);
|
|---|
| 605 | a token consisting of a name specifies that the general entity of the name
|
|---|
| 606 | is open; a token of the form prefix=uri specifies the namespace for a particular
|
|---|
| 607 | prefix; a token of the form =uri specifies the default namespace.
|
|---|
| 608 | This can be called at any point after the first call to an ExternalEntityRefHandler
|
|---|
| 609 | so longer as the parser has not yet been freed.
|
|---|
| 610 | The new parser is completely independent and may safely be used in a separate thread.
|
|---|
| 611 | The handlers and userData are initialized from the parser argument.
|
|---|
| 612 | Returns 0 if out of memory. Otherwise returns a new XML_Parser object. */
|
|---|
| 613 | XML_Parser XMLPARSEAPI XML_ExternalEntityParserCreate(XML_Parser parser,
|
|---|
| 614 | const XML_Char *context,
|
|---|
| 615 | const XML_Char *encoding);
|
|---|
| 616 |
|
|---|
| 617 | enum XML_ParamEntityParsing {
|
|---|
| 618 | XML_PARAM_ENTITY_PARSING_NEVER,
|
|---|
| 619 | XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE,
|
|---|
| 620 | XML_PARAM_ENTITY_PARSING_ALWAYS
|
|---|
| 621 | };
|
|---|
| 622 |
|
|---|
| 623 | int XMLPARSEAPI XML_SetParamEntityParsing(XML_Parser parser,
|
|---|
| 624 | enum XML_ParamEntityParsing parsing);
|
|---|
| 625 |
|
|---|
| 626 | #define ERROR_XML_FIRST 40000 // first error code used
|
|---|
| 627 |
|
|---|
| 628 | typedef unsigned long XMLERROR; // V0.9.12 (2001-05-20) [umoeller]
|
|---|
| 629 |
|
|---|
| 630 | #define ERROR_EXPAT_NONE 0
|
|---|
| 631 | #define ERROR_EXPAT_NO_MEMORY (ERROR_XML_FIRST)
|
|---|
| 632 | #define ERROR_EXPAT_SYNTAX (ERROR_XML_FIRST + 1)
|
|---|
| 633 | #define ERROR_EXPAT_NO_ELEMENTS (ERROR_XML_FIRST + 2)
|
|---|
| 634 | #define ERROR_EXPAT_INVALID_TOKEN (ERROR_XML_FIRST + 3)
|
|---|
| 635 | #define ERROR_EXPAT_UNCLOSED_TOKEN (ERROR_XML_FIRST + 4)
|
|---|
| 636 | #define ERROR_EXPAT_PARTIAL_CHAR (ERROR_XML_FIRST + 5)
|
|---|
| 637 | #define ERROR_EXPAT_TAG_MISMATCH (ERROR_XML_FIRST + 6)
|
|---|
| 638 | #define ERROR_EXPAT_DUPLICATE_ATTRIBUTE (ERROR_XML_FIRST + 7)
|
|---|
| 639 | #define ERROR_EXPAT_JUNK_AFTER_DOC_ELEMENT (ERROR_XML_FIRST + 8)
|
|---|
| 640 | #define ERROR_EXPAT_PARAM_ENTITY_REF (ERROR_XML_FIRST + 10)
|
|---|
| 641 | #define ERROR_EXPAT_UNDEFINED_ENTITY (ERROR_XML_FIRST + 11)
|
|---|
| 642 | #define ERROR_EXPAT_RECURSIVE_ENTITY_REF (ERROR_XML_FIRST + 12)
|
|---|
| 643 | #define ERROR_EXPAT_ASYNC_ENTITY (ERROR_XML_FIRST + 13)
|
|---|
| 644 | #define ERROR_EXPAT_BAD_CHAR_REF (ERROR_XML_FIRST + 14)
|
|---|
| 645 | #define ERROR_EXPAT_BINARY_ENTITY_REF (ERROR_XML_FIRST + 15)
|
|---|
| 646 | #define ERROR_EXPAT_ATTRIBUTE_EXTERNAL_ENTITY_REF (ERROR_XML_FIRST + 16)
|
|---|
| 647 | #define ERROR_EXPAT_MISPLACED_XML_PI (ERROR_XML_FIRST + 17)
|
|---|
| 648 | #define ERROR_EXPAT_UNKNOWN_ENCODING (ERROR_XML_FIRST + 18)
|
|---|
| 649 | #define ERROR_EXPAT_INCORRECT_ENCODING (ERROR_XML_FIRST + 19)
|
|---|
| 650 | #define ERROR_EXPAT_UNCLOSED_CDATA_SECTION (ERROR_XML_FIRST + 20)
|
|---|
| 651 | #define ERROR_EXPAT_EXTERNAL_ENTITY_HANDLING (ERROR_XML_FIRST + 21)
|
|---|
| 652 | #define ERROR_EXPAT_NOT_STANDALONE (ERROR_XML_FIRST + 22)
|
|---|
| 653 | #define ERROR_EXPAT_UNEXPECTED_STATE (ERROR_XML_FIRST + 23)
|
|---|
| 654 |
|
|---|
| 655 | /* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode
|
|---|
| 656 | returns information about the error. */
|
|---|
| 657 |
|
|---|
| 658 | XMLERROR XMLPARSEAPI XML_GetErrorCode(XML_Parser parser);
|
|---|
| 659 |
|
|---|
| 660 | /* These functions return information about the current parse location.
|
|---|
| 661 | They may be called when XML_Parse or XML_ParseBuffer return 0;
|
|---|
| 662 | in this case the location is the location of the character at which
|
|---|
| 663 | the error was detected.
|
|---|
| 664 | They may also be called from any other callback called to report
|
|---|
| 665 | some parse event; in this the location is the location of the first
|
|---|
| 666 | of the sequence of characters that generated the event. */
|
|---|
| 667 |
|
|---|
| 668 | int XMLPARSEAPI XML_GetCurrentLineNumber(XML_Parser parser);
|
|---|
| 669 | int XMLPARSEAPI XML_GetCurrentColumnNumber(XML_Parser parser);
|
|---|
| 670 | long XMLPARSEAPI XML_GetCurrentByteIndex(XML_Parser parser);
|
|---|
| 671 |
|
|---|
| 672 | /* Return the number of bytes in the current event.
|
|---|
| 673 | Returns 0 if the event is in an internal entity. */
|
|---|
| 674 |
|
|---|
| 675 | int XMLPARSEAPI XML_GetCurrentByteCount(XML_Parser parser);
|
|---|
| 676 |
|
|---|
| 677 | /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets
|
|---|
| 678 | the integer pointed to by offset to the offset within this buffer
|
|---|
| 679 | of the current parse position, and sets the integer pointed to by size
|
|---|
| 680 | to the size of this buffer (the number of input bytes). Otherwise
|
|---|
| 681 | returns a null pointer. Also returns a null pointer if a parse isn't active.
|
|---|
| 682 |
|
|---|
| 683 | NOTE: The character pointer returned should not be used outside
|
|---|
| 684 | the handler that makes the call. */
|
|---|
| 685 |
|
|---|
| 686 | const char XMLPARSEAPI * XML_GetInputContext(XML_Parser parser,
|
|---|
| 687 | int *offset,
|
|---|
| 688 | int *size);
|
|---|
| 689 |
|
|---|
| 690 | /* For backwards compatibility with previous versions. */
|
|---|
| 691 | #define XML_GetErrorLineNumber XML_GetCurrentLineNumber
|
|---|
| 692 | #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
|
|---|
| 693 | #define XML_GetErrorByteIndex XML_GetCurrentByteIndex
|
|---|
| 694 |
|
|---|
| 695 | /* Frees memory used by the parser. */
|
|---|
| 696 | void XMLPARSEAPI XML_ParserFree(XML_Parser parser);
|
|---|
| 697 |
|
|---|
| 698 | /* Returns a string describing the error. */
|
|---|
| 699 | // const XML_LChar XMLPARSEAPI * XML_ErrorString(int code);
|
|---|
| 700 | // moved this to xml.c V0.9.9 (2001-02-16) [umoeller]
|
|---|
| 701 |
|
|---|
| 702 | /* Return a string containing the version number of this expat */
|
|---|
| 703 | const XML_LChar XMLPARSEAPI *XML_ExpatVersion(void);
|
|---|
| 704 |
|
|---|
| 705 | #ifdef __cplusplus
|
|---|
| 706 | }
|
|---|
| 707 | #endif
|
|---|
| 708 |
|
|---|
| 709 | #endif /* not XmlParse_INCLUDED */
|
|---|