1 | /* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd |
---|
2 | See the file COPYING for copying permission. |
---|
3 | */ |
---|
4 | |
---|
5 | #ifndef XmlParse_INCLUDED |
---|
6 | #define XmlParse_INCLUDED 1 |
---|
7 | |
---|
8 | #ifdef __VMS |
---|
9 | /* 0 1 2 3 0 1 2 3 |
---|
10 | 1234567890123456789012345678901 1234567890123456789012345678901 */ |
---|
11 | #define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler |
---|
12 | #define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler |
---|
13 | #define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler |
---|
14 | #define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg |
---|
15 | #endif |
---|
16 | |
---|
17 | #include <stdlib.h> |
---|
18 | |
---|
19 | #ifndef XMLPARSEAPI |
---|
20 | #if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) |
---|
21 | #ifdef _STATIC |
---|
22 | #define XMLPARSEAPI(type) type __cdecl |
---|
23 | #else |
---|
24 | #define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl |
---|
25 | #endif |
---|
26 | #else |
---|
27 | #define XMLPARSEAPI(type) type |
---|
28 | #endif |
---|
29 | #endif /* not defined XMLPARSEAPI */ |
---|
30 | |
---|
31 | #ifdef __cplusplus |
---|
32 | extern "C" { |
---|
33 | #endif |
---|
34 | |
---|
35 | #ifdef XML_UNICODE_WCHAR_T |
---|
36 | #define XML_UNICODE |
---|
37 | #endif |
---|
38 | |
---|
39 | struct XML_ParserStruct; |
---|
40 | typedef struct XML_ParserStruct *XML_Parser; |
---|
41 | |
---|
42 | #ifdef XML_UNICODE /* Information is UTF-16 encoded. */ |
---|
43 | #ifdef XML_UNICODE_WCHAR_T |
---|
44 | typedef wchar_t XML_Char; |
---|
45 | typedef wchar_t XML_LChar; |
---|
46 | #else |
---|
47 | typedef unsigned short XML_Char; |
---|
48 | typedef char XML_LChar; |
---|
49 | #endif /* XML_UNICODE_WCHAR_T */ |
---|
50 | #else /* Information is UTF-8 encoded. */ |
---|
51 | typedef char XML_Char; |
---|
52 | typedef char XML_LChar; |
---|
53 | #endif /* XML_UNICODE */ |
---|
54 | |
---|
55 | /* Should this be defined using stdbool.h when C99 is available? */ |
---|
56 | typedef unsigned char XML_Bool; |
---|
57 | #define XML_TRUE ((XML_Bool) 1) |
---|
58 | #define XML_FALSE ((XML_Bool) 0) |
---|
59 | |
---|
60 | enum XML_Error { |
---|
61 | XML_ERROR_NONE, |
---|
62 | XML_ERROR_NO_MEMORY, |
---|
63 | XML_ERROR_SYNTAX, |
---|
64 | XML_ERROR_NO_ELEMENTS, |
---|
65 | XML_ERROR_INVALID_TOKEN, |
---|
66 | XML_ERROR_UNCLOSED_TOKEN, |
---|
67 | XML_ERROR_PARTIAL_CHAR, |
---|
68 | XML_ERROR_TAG_MISMATCH, |
---|
69 | XML_ERROR_DUPLICATE_ATTRIBUTE, |
---|
70 | XML_ERROR_JUNK_AFTER_DOC_ELEMENT, |
---|
71 | XML_ERROR_PARAM_ENTITY_REF, |
---|
72 | XML_ERROR_UNDEFINED_ENTITY, |
---|
73 | XML_ERROR_RECURSIVE_ENTITY_REF, |
---|
74 | XML_ERROR_ASYNC_ENTITY, |
---|
75 | XML_ERROR_BAD_CHAR_REF, |
---|
76 | XML_ERROR_BINARY_ENTITY_REF, |
---|
77 | XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, |
---|
78 | XML_ERROR_MISPLACED_XML_PI, |
---|
79 | XML_ERROR_UNKNOWN_ENCODING, |
---|
80 | XML_ERROR_INCORRECT_ENCODING, |
---|
81 | XML_ERROR_UNCLOSED_CDATA_SECTION, |
---|
82 | XML_ERROR_EXTERNAL_ENTITY_HANDLING, |
---|
83 | XML_ERROR_NOT_STANDALONE, |
---|
84 | XML_ERROR_UNEXPECTED_STATE, |
---|
85 | XML_ERROR_ENTITY_DECLARED_IN_PE, |
---|
86 | XML_ERROR_FEATURE_REQUIRES_XML_DTD, |
---|
87 | XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING |
---|
88 | }; |
---|
89 | |
---|
90 | enum XML_Content_Type { |
---|
91 | XML_CTYPE_EMPTY = 1, |
---|
92 | XML_CTYPE_ANY, |
---|
93 | XML_CTYPE_MIXED, |
---|
94 | XML_CTYPE_NAME, |
---|
95 | XML_CTYPE_CHOICE, |
---|
96 | XML_CTYPE_SEQ |
---|
97 | }; |
---|
98 | |
---|
99 | enum XML_Content_Quant { |
---|
100 | XML_CQUANT_NONE, |
---|
101 | XML_CQUANT_OPT, |
---|
102 | XML_CQUANT_REP, |
---|
103 | XML_CQUANT_PLUS |
---|
104 | }; |
---|
105 | |
---|
106 | /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be |
---|
107 | XML_CQUANT_NONE, and the other fields will be zero or NULL. |
---|
108 | If type == XML_CTYPE_MIXED, then quant will be NONE or REP and |
---|
109 | numchildren will contain number of elements that may be mixed in |
---|
110 | and children point to an array of XML_Content cells that will be |
---|
111 | all of XML_CTYPE_NAME type with no quantification. |
---|
112 | |
---|
113 | If type == XML_CTYPE_NAME, then the name points to the name, and |
---|
114 | the numchildren field will be zero and children will be NULL. The |
---|
115 | quant fields indicates any quantifiers placed on the name. |
---|
116 | |
---|
117 | CHOICE and SEQ will have name NULL, the number of children in |
---|
118 | numchildren and children will point, recursively, to an array |
---|
119 | of XML_Content cells. |
---|
120 | |
---|
121 | The EMPTY, ANY, and MIXED types will only occur at top level. |
---|
122 | */ |
---|
123 | |
---|
124 | typedef struct XML_cp XML_Content; |
---|
125 | |
---|
126 | struct XML_cp { |
---|
127 | enum XML_Content_Type type; |
---|
128 | enum XML_Content_Quant quant; |
---|
129 | XML_Char * name; |
---|
130 | unsigned int numchildren; |
---|
131 | XML_Content * children; |
---|
132 | }; |
---|
133 | |
---|
134 | |
---|
135 | /* This is called for an element declaration. See above for |
---|
136 | description of the model argument. It's the caller's responsibility |
---|
137 | to free model when finished with it. |
---|
138 | */ |
---|
139 | typedef void (*XML_ElementDeclHandler) (void *userData, |
---|
140 | const XML_Char *name, |
---|
141 | XML_Content *model); |
---|
142 | |
---|
143 | XMLPARSEAPI(void) |
---|
144 | XML_SetElementDeclHandler(XML_Parser parser, |
---|
145 | XML_ElementDeclHandler eldecl); |
---|
146 | |
---|
147 | /* The Attlist declaration handler is called for *each* attribute. So |
---|
148 | a single Attlist declaration with multiple attributes declared will |
---|
149 | generate multiple calls to this handler. The "default" parameter |
---|
150 | may be NULL in the case of the "#IMPLIED" or "#REQUIRED" |
---|
151 | keyword. The "isrequired" parameter will be true and the default |
---|
152 | value will be NULL in the case of "#REQUIRED". If "isrequired" is |
---|
153 | true and default is non-NULL, then this is a "#FIXED" default. |
---|
154 | */ |
---|
155 | typedef void (*XML_AttlistDeclHandler) (void *userData, |
---|
156 | const XML_Char *elname, |
---|
157 | const XML_Char *attname, |
---|
158 | const XML_Char *att_type, |
---|
159 | const XML_Char *dflt, |
---|
160 | int isrequired); |
---|
161 | |
---|
162 | XMLPARSEAPI(void) |
---|
163 | XML_SetAttlistDeclHandler(XML_Parser parser, |
---|
164 | XML_AttlistDeclHandler attdecl); |
---|
165 | |
---|
166 | /* The XML declaration handler is called for *both* XML declarations |
---|
167 | and text declarations. The way to distinguish is that the version |
---|
168 | parameter will be NULL for text declarations. The encoding |
---|
169 | parameter may be NULL for XML declarations. The standalone |
---|
170 | parameter will be -1, 0, or 1 indicating respectively that there |
---|
171 | was no standalone parameter in the declaration, that it was given |
---|
172 | as no, or that it was given as yes. |
---|
173 | */ |
---|
174 | typedef void (*XML_XmlDeclHandler) (void *userData, |
---|
175 | const XML_Char *version, |
---|
176 | const XML_Char *encoding, |
---|
177 | int standalone); |
---|
178 | |
---|
179 | XMLPARSEAPI(void) |
---|
180 | XML_SetXmlDeclHandler(XML_Parser parser, |
---|
181 | XML_XmlDeclHandler xmldecl); |
---|
182 | |
---|
183 | |
---|
184 | typedef struct { |
---|
185 | void *(*malloc_fcn)(size_t size); |
---|
186 | void *(*realloc_fcn)(void *ptr, size_t size); |
---|
187 | void (*free_fcn)(void *ptr); |
---|
188 | } XML_Memory_Handling_Suite; |
---|
189 | |
---|
190 | /* Constructs a new parser; encoding is the encoding specified by the |
---|
191 | external protocol or NULL if there is none specified. |
---|
192 | */ |
---|
193 | XMLPARSEAPI(XML_Parser) |
---|
194 | XML_ParserCreate(const XML_Char *encoding); |
---|
195 | |
---|
196 | /* Constructs a new parser and namespace processor. Element type |
---|
197 | names and attribute names that belong to a namespace will be |
---|
198 | expanded; unprefixed attribute names are never expanded; unprefixed |
---|
199 | element type names are expanded only if there is a default |
---|
200 | namespace. The expanded name is the concatenation of the namespace |
---|
201 | URI, the namespace separator character, and the local part of the |
---|
202 | name. If the namespace separator is '\0' then the namespace URI |
---|
203 | and the local part will be concatenated without any separator. |
---|
204 | When a namespace is not declared, the name and prefix will be |
---|
205 | passed through without expansion. |
---|
206 | */ |
---|
207 | XMLPARSEAPI(XML_Parser) |
---|
208 | XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); |
---|
209 | |
---|
210 | |
---|
211 | /* Constructs a new parser using the memory management suit referred to |
---|
212 | by memsuite. If memsuite is NULL, then use the standard library memory |
---|
213 | suite. If namespaceSeparator is non-NULL it creates a parser with |
---|
214 | namespace processing as described above. The character pointed at |
---|
215 | will serve as the namespace separator. |
---|
216 | |
---|
217 | All further memory operations used for the created parser will come from |
---|
218 | the given suite. |
---|
219 | */ |
---|
220 | XMLPARSEAPI(XML_Parser) |
---|
221 | XML_ParserCreate_MM(const XML_Char *encoding, |
---|
222 | const XML_Memory_Handling_Suite *memsuite, |
---|
223 | const XML_Char *namespaceSeparator); |
---|
224 | |
---|
225 | /* Prepare a parser object to be re-used. This is particularly |
---|
226 | valuable when memory allocation overhead is disproportionatly high, |
---|
227 | such as when a large number of small documnents need to be parsed. |
---|
228 | All handlers are cleared from the parser, except for the |
---|
229 | unknownEncodingHandler. The parser's external state is re-initialized |
---|
230 | except for the values of ns and ns_triplets. |
---|
231 | |
---|
232 | Added in Expat 1.95.3. |
---|
233 | */ |
---|
234 | XMLPARSEAPI(XML_Bool) |
---|
235 | XML_ParserReset(XML_Parser parser, const XML_Char *encoding); |
---|
236 | |
---|
237 | /* atts is array of name/value pairs, terminated by 0; |
---|
238 | names and values are 0 terminated. |
---|
239 | */ |
---|
240 | typedef void (*XML_StartElementHandler)(void *userData, |
---|
241 | const XML_Char *name, |
---|
242 | const XML_Char **atts); |
---|
243 | |
---|
244 | typedef void (*XML_EndElementHandler)(void *userData, |
---|
245 | const XML_Char *name); |
---|
246 | |
---|
247 | |
---|
248 | /* s is not 0 terminated. */ |
---|
249 | typedef void (*XML_CharacterDataHandler)(void *userData, |
---|
250 | const XML_Char *s, |
---|
251 | int len); |
---|
252 | |
---|
253 | /* target and data are 0 terminated */ |
---|
254 | typedef void (*XML_ProcessingInstructionHandler)(void *userData, |
---|
255 | const XML_Char *target, |
---|
256 | const XML_Char *data); |
---|
257 | |
---|
258 | /* data is 0 terminated */ |
---|
259 | typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data); |
---|
260 | |
---|
261 | typedef void (*XML_StartCdataSectionHandler)(void *userData); |
---|
262 | typedef void (*XML_EndCdataSectionHandler)(void *userData); |
---|
263 | |
---|
264 | /* This is called for any characters in the XML document for which |
---|
265 | there is no applicable handler. This includes both characters that |
---|
266 | are part of markup which is of a kind that is not reported |
---|
267 | (comments, markup declarations), or characters that are part of a |
---|
268 | construct which could be reported but for which no handler has been |
---|
269 | supplied. The characters are passed exactly as they were in the XML |
---|
270 | document except that they will be encoded in UTF-8 or UTF-16. |
---|
271 | Line boundaries are not normalized. Note that a byte order mark |
---|
272 | character is not passed to the default handler. There are no |
---|
273 | guarantees about how characters are divided between calls to the |
---|
274 | default handler: for example, a comment might be split between |
---|
275 | multiple calls. |
---|
276 | */ |
---|
277 | typedef void (*XML_DefaultHandler)(void *userData, |
---|
278 | const XML_Char *s, |
---|
279 | int len); |
---|
280 | |
---|
281 | /* This is called for the start of the DOCTYPE declaration, before |
---|
282 | any DTD or internal subset is parsed. |
---|
283 | */ |
---|
284 | typedef void (*XML_StartDoctypeDeclHandler)(void *userData, |
---|
285 | const XML_Char *doctypeName, |
---|
286 | const XML_Char *sysid, |
---|
287 | const XML_Char *pubid, |
---|
288 | int has_internal_subset); |
---|
289 | |
---|
290 | /* This is called for the start of the DOCTYPE declaration when the |
---|
291 | closing > is encountered, but after processing any external |
---|
292 | subset. |
---|
293 | */ |
---|
294 | typedef void (*XML_EndDoctypeDeclHandler)(void *userData); |
---|
295 | |
---|
296 | /* This is called for entity declarations. The is_parameter_entity |
---|
297 | argument will be non-zero if the entity is a parameter entity, zero |
---|
298 | otherwise. |
---|
299 | |
---|
300 | For internal entities (<!ENTITY foo "bar">), value will |
---|
301 | be non-NULL and systemId, publicID, and notationName will be NULL. |
---|
302 | The value string is NOT nul-terminated; the length is provided in |
---|
303 | the value_length argument. Since it is legal to have zero-length |
---|
304 | values, do not use this argument to test for internal entities. |
---|
305 | |
---|
306 | For external entities, value will be NULL and systemId will be |
---|
307 | non-NULL. The publicId argument will be NULL unless a public |
---|
308 | identifier was provided. The notationName argument will have a |
---|
309 | non-NULL value only for unparsed entity declarations. |
---|
310 | |
---|
311 | Note that is_parameter_entity can't be changed to XML_Bool, since |
---|
312 | that would break binary compatibility. |
---|
313 | */ |
---|
314 | typedef void (*XML_EntityDeclHandler) (void *userData, |
---|
315 | const XML_Char *entityName, |
---|
316 | int is_parameter_entity, |
---|
317 | const XML_Char *value, |
---|
318 | int value_length, |
---|
319 | const XML_Char *base, |
---|
320 | const XML_Char *systemId, |
---|
321 | const XML_Char *publicId, |
---|
322 | const XML_Char *notationName); |
---|
323 | |
---|
324 | XMLPARSEAPI(void) |
---|
325 | XML_SetEntityDeclHandler(XML_Parser parser, |
---|
326 | XML_EntityDeclHandler handler); |
---|
327 | |
---|
328 | /* OBSOLETE -- OBSOLETE -- OBSOLETE |
---|
329 | This handler has been superceded by the EntityDeclHandler above. |
---|
330 | It is provided here for backward compatibility. |
---|
331 | |
---|
332 | This is called for a declaration of an unparsed (NDATA) entity. |
---|
333 | The base argument is whatever was set by XML_SetBase. The |
---|
334 | entityName, systemId and notationName arguments will never be |
---|
335 | NULL. The other arguments may be. |
---|
336 | */ |
---|
337 | typedef void (*XML_UnparsedEntityDeclHandler)(void *userData, |
---|
338 | const XML_Char *entityName, |
---|
339 | const XML_Char *base, |
---|
340 | const XML_Char *systemId, |
---|
341 | const XML_Char *publicId, |
---|
342 | const XML_Char *notationName); |
---|
343 | |
---|
344 | /* This is called for a declaration of notation. The base argument is |
---|
345 | whatever was set by XML_SetBase. The notationName will never be |
---|
346 | NULL. The other arguments can be. |
---|
347 | */ |
---|
348 | typedef void (*XML_NotationDeclHandler)(void *userData, |
---|
349 | const XML_Char *notationName, |
---|
350 | const XML_Char *base, |
---|
351 | const XML_Char *systemId, |
---|
352 | const XML_Char *publicId); |
---|
353 | |
---|
354 | /* When namespace processing is enabled, these are called once for |
---|
355 | each namespace declaration. The call to the start and end element |
---|
356 | handlers occur between the calls to the start and end namespace |
---|
357 | declaration handlers. For an xmlns attribute, prefix will be |
---|
358 | NULL. For an xmlns="" attribute, uri will be NULL. |
---|
359 | */ |
---|
360 | typedef void (*XML_StartNamespaceDeclHandler)(void *userData, |
---|
361 | const XML_Char *prefix, |
---|
362 | const XML_Char *uri); |
---|
363 | |
---|
364 | typedef void (*XML_EndNamespaceDeclHandler)(void *userData, |
---|
365 | const XML_Char *prefix); |
---|
366 | |
---|
367 | /* This is called if the document is not standalone, that is, it has an |
---|
368 | external subset or a reference to a parameter entity, but does not |
---|
369 | have standalone="yes". If this handler returns 0, then processing |
---|
370 | will not continue, and the parser will return a |
---|
371 | XML_ERROR_NOT_STANDALONE error. |
---|
372 | If parameter entity parsing is enabled, then in addition to the |
---|
373 | conditions above this handler will only be called if the referenced |
---|
374 | entity was actually read. |
---|
375 | */ |
---|
376 | typedef int (*XML_NotStandaloneHandler)(void *userData); |
---|
377 | |
---|
378 | /* This is called for a reference to an external parsed general |
---|
379 | entity. The referenced entity is not automatically parsed. The |
---|
380 | application can parse it immediately or later using |
---|
381 | XML_ExternalEntityParserCreate. |
---|
382 | |
---|
383 | The parser argument is the parser parsing the entity containing the |
---|
384 | reference; it can be passed as the parser argument to |
---|
385 | XML_ExternalEntityParserCreate. The systemId argument is the |
---|
386 | system identifier as specified in the entity declaration; it will |
---|
387 | not be NULL. |
---|
388 | |
---|
389 | The base argument is the system identifier that should be used as |
---|
390 | the base for resolving systemId if systemId was relative; this is |
---|
391 | set by XML_SetBase; it may be NULL. |
---|
392 | |
---|
393 | The publicId argument is the public identifier as specified in the |
---|
394 | entity declaration, or NULL if none was specified; the whitespace |
---|
395 | in the public identifier will have been normalized as required by |
---|
396 | the XML spec. |
---|
397 | |
---|
398 | The context argument specifies the parsing context in the format |
---|
399 | expected by the context argument to XML_ExternalEntityParserCreate; |
---|
400 | context is valid only until the handler returns, so if the |
---|
401 | referenced entity is to be parsed later, it must be copied. |
---|
402 | |
---|
403 | The handler should return 0 if processing should not continue |
---|
404 | because of a fatal error in the handling of the external entity. |
---|
405 | In this case the calling parser will return an |
---|
406 | XML_ERROR_EXTERNAL_ENTITY_HANDLING error. |
---|
407 | |
---|
408 | Note that unlike other handlers the first argument is the parser, |
---|
409 | not userData. |
---|
410 | */ |
---|
411 | typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser, |
---|
412 | const XML_Char *context, |
---|
413 | const XML_Char *base, |
---|
414 | const XML_Char *systemId, |
---|
415 | const XML_Char *publicId); |
---|
416 | |
---|
417 | /* This is called in two situations: |
---|
418 | 1) An entity reference is encountered for which no declaration |
---|
419 | has been read *and* this is not an error. |
---|
420 | 2) An internal entity reference is read, but not expanded, because |
---|
421 | XML_SetDefaultHandler has been called. |
---|
422 | Note: skipped parameter entities in declarations and skipped general |
---|
423 | entities in attribute values cannot be reported, because |
---|
424 | the event would be out of sync with the reporting of the |
---|
425 | declarations or attribute values |
---|
426 | */ |
---|
427 | typedef void (*XML_SkippedEntityHandler)(void *userData, |
---|
428 | const XML_Char *entityName, |
---|
429 | int is_parameter_entity); |
---|
430 | |
---|
431 | /* This structure is filled in by the XML_UnknownEncodingHandler to |
---|
432 | provide information to the parser about encodings that are unknown |
---|
433 | to the parser. |
---|
434 | |
---|
435 | The map[b] member gives information about byte sequences whose |
---|
436 | first byte is b. |
---|
437 | |
---|
438 | If map[b] is c where c is >= 0, then b by itself encodes the |
---|
439 | Unicode scalar value c. |
---|
440 | |
---|
441 | If map[b] is -1, then the byte sequence is malformed. |
---|
442 | |
---|
443 | If map[b] is -n, where n >= 2, then b is the first byte of an |
---|
444 | n-byte sequence that encodes a single Unicode scalar value. |
---|
445 | |
---|
446 | The data member will be passed as the first argument to the convert |
---|
447 | function. |
---|
448 | |
---|
449 | The convert function is used to convert multibyte sequences; s will |
---|
450 | point to a n-byte sequence where map[(unsigned char)*s] == -n. The |
---|
451 | convert function must return the Unicode scalar value represented |
---|
452 | by this byte sequence or -1 if the byte sequence is malformed. |
---|
453 | |
---|
454 | The convert function may be NULL if the encoding is a single-byte |
---|
455 | encoding, that is if map[b] >= -1 for all bytes b. |
---|
456 | |
---|
457 | When the parser is finished with the encoding, then if release is |
---|
458 | not NULL, it will call release passing it the data member; once |
---|
459 | release has been called, the convert function will not be called |
---|
460 | again. |
---|
461 | |
---|
462 | Expat places certain restrictions on the encodings that are supported |
---|
463 | using this mechanism. |
---|
464 | |
---|
465 | 1. Every ASCII character that can appear in a well-formed XML document, |
---|
466 | other than the characters |
---|
467 | |
---|
468 | $@\^`{}~ |
---|
469 | |
---|
470 | must be represented by a single byte, and that byte must be the |
---|
471 | same byte that represents that character in ASCII. |
---|
472 | |
---|
473 | 2. No character may require more than 4 bytes to encode. |
---|
474 | |
---|
475 | 3. All characters encoded must have Unicode scalar values <= |
---|
476 | 0xFFFF, (i.e., characters that would be encoded by surrogates in |
---|
477 | UTF-16 are not allowed). Note that this restriction doesn't |
---|
478 | apply to the built-in support for UTF-8 and UTF-16. |
---|
479 | |
---|
480 | 4. No Unicode character may be encoded by more than one distinct |
---|
481 | sequence of bytes. |
---|
482 | */ |
---|
483 | typedef struct { |
---|
484 | int map[256]; |
---|
485 | void *data; |
---|
486 | int (*convert)(void *data, const char *s); |
---|
487 | void (*release)(void *data); |
---|
488 | } XML_Encoding; |
---|
489 | |
---|
490 | /* This is called for an encoding that is unknown to the parser. |
---|
491 | |
---|
492 | The encodingHandlerData argument is that which was passed as the |
---|
493 | second argument to XML_SetUnknownEncodingHandler. |
---|
494 | |
---|
495 | The name argument gives the name of the encoding as specified in |
---|
496 | the encoding declaration. |
---|
497 | |
---|
498 | If the callback can provide information about the encoding, it must |
---|
499 | fill in the XML_Encoding structure, and return 1. Otherwise it |
---|
500 | must return 0. |
---|
501 | |
---|
502 | If info does not describe a suitable encoding, then the parser will |
---|
503 | return an XML_UNKNOWN_ENCODING error. |
---|
504 | */ |
---|
505 | typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData, |
---|
506 | const XML_Char *name, |
---|
507 | XML_Encoding *info); |
---|
508 | |
---|
509 | XMLPARSEAPI(void) |
---|
510 | XML_SetElementHandler(XML_Parser parser, |
---|
511 | XML_StartElementHandler start, |
---|
512 | XML_EndElementHandler end); |
---|
513 | |
---|
514 | XMLPARSEAPI(void) |
---|
515 | XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler); |
---|
516 | |
---|
517 | XMLPARSEAPI(void) |
---|
518 | XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler); |
---|
519 | |
---|
520 | XMLPARSEAPI(void) |
---|
521 | XML_SetCharacterDataHandler(XML_Parser parser, |
---|
522 | XML_CharacterDataHandler handler); |
---|
523 | |
---|
524 | XMLPARSEAPI(void) |
---|
525 | XML_SetProcessingInstructionHandler(XML_Parser parser, |
---|
526 | XML_ProcessingInstructionHandler handler); |
---|
527 | XMLPARSEAPI(void) |
---|
528 | XML_SetCommentHandler(XML_Parser parser, |
---|
529 | XML_CommentHandler handler); |
---|
530 | |
---|
531 | XMLPARSEAPI(void) |
---|
532 | XML_SetCdataSectionHandler(XML_Parser parser, |
---|
533 | XML_StartCdataSectionHandler start, |
---|
534 | XML_EndCdataSectionHandler end); |
---|
535 | |
---|
536 | XMLPARSEAPI(void) |
---|
537 | XML_SetStartCdataSectionHandler(XML_Parser parser, |
---|
538 | XML_StartCdataSectionHandler start); |
---|
539 | |
---|
540 | XMLPARSEAPI(void) |
---|
541 | XML_SetEndCdataSectionHandler(XML_Parser parser, |
---|
542 | XML_EndCdataSectionHandler end); |
---|
543 | |
---|
544 | /* This sets the default handler and also inhibits expansion of |
---|
545 | internal entities. These entity references will be passed to the |
---|
546 | default handler, or to the skipped entity handler, if one is set. |
---|
547 | */ |
---|
548 | XMLPARSEAPI(void) |
---|
549 | XML_SetDefaultHandler(XML_Parser parser, |
---|
550 | XML_DefaultHandler handler); |
---|
551 | |
---|
552 | /* This sets the default handler but does not inhibit expansion of |
---|
553 | internal entities. The entity reference will not be passed to the |
---|
554 | default handler. |
---|
555 | */ |
---|
556 | XMLPARSEAPI(void) |
---|
557 | XML_SetDefaultHandlerExpand(XML_Parser parser, |
---|
558 | XML_DefaultHandler handler); |
---|
559 | |
---|
560 | XMLPARSEAPI(void) |
---|
561 | XML_SetDoctypeDeclHandler(XML_Parser parser, |
---|
562 | XML_StartDoctypeDeclHandler start, |
---|
563 | XML_EndDoctypeDeclHandler end); |
---|
564 | |
---|
565 | XMLPARSEAPI(void) |
---|
566 | XML_SetStartDoctypeDeclHandler(XML_Parser parser, |
---|
567 | XML_StartDoctypeDeclHandler start); |
---|
568 | |
---|
569 | XMLPARSEAPI(void) |
---|
570 | XML_SetEndDoctypeDeclHandler(XML_Parser parser, |
---|
571 | XML_EndDoctypeDeclHandler end); |
---|
572 | |
---|
573 | XMLPARSEAPI(void) |
---|
574 | XML_SetUnparsedEntityDeclHandler(XML_Parser parser, |
---|
575 | XML_UnparsedEntityDeclHandler handler); |
---|
576 | |
---|
577 | XMLPARSEAPI(void) |
---|
578 | XML_SetNotationDeclHandler(XML_Parser parser, |
---|
579 | XML_NotationDeclHandler handler); |
---|
580 | |
---|
581 | XMLPARSEAPI(void) |
---|
582 | XML_SetNamespaceDeclHandler(XML_Parser parser, |
---|
583 | XML_StartNamespaceDeclHandler start, |
---|
584 | XML_EndNamespaceDeclHandler end); |
---|
585 | |
---|
586 | XMLPARSEAPI(void) |
---|
587 | XML_SetStartNamespaceDeclHandler(XML_Parser parser, |
---|
588 | XML_StartNamespaceDeclHandler start); |
---|
589 | |
---|
590 | XMLPARSEAPI(void) |
---|
591 | XML_SetEndNamespaceDeclHandler(XML_Parser parser, |
---|
592 | XML_EndNamespaceDeclHandler end); |
---|
593 | |
---|
594 | XMLPARSEAPI(void) |
---|
595 | XML_SetNotStandaloneHandler(XML_Parser parser, |
---|
596 | XML_NotStandaloneHandler handler); |
---|
597 | |
---|
598 | XMLPARSEAPI(void) |
---|
599 | XML_SetExternalEntityRefHandler(XML_Parser parser, |
---|
600 | XML_ExternalEntityRefHandler handler); |
---|
601 | |
---|
602 | /* If a non-NULL value for arg is specified here, then it will be |
---|
603 | passed as the first argument to the external entity ref handler |
---|
604 | instead of the parser object. |
---|
605 | */ |
---|
606 | XMLPARSEAPI(void) |
---|
607 | XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg); |
---|
608 | |
---|
609 | XMLPARSEAPI(void) |
---|
610 | XML_SetSkippedEntityHandler(XML_Parser parser, |
---|
611 | XML_SkippedEntityHandler handler); |
---|
612 | |
---|
613 | XMLPARSEAPI(void) |
---|
614 | XML_SetUnknownEncodingHandler(XML_Parser parser, |
---|
615 | XML_UnknownEncodingHandler handler, |
---|
616 | void *encodingHandlerData); |
---|
617 | |
---|
618 | /* This can be called within a handler for a start element, end |
---|
619 | element, processing instruction or character data. It causes the |
---|
620 | corresponding markup to be passed to the default handler. |
---|
621 | */ |
---|
622 | XMLPARSEAPI(void) |
---|
623 | XML_DefaultCurrent(XML_Parser parser); |
---|
624 | |
---|
625 | /* If do_nst is non-zero, and namespace processing is in effect, and |
---|
626 | a name has a prefix (i.e. an explicit namespace qualifier) then |
---|
627 | that name is returned as a triplet in a single string separated by |
---|
628 | the separator character specified when the parser was created: URI |
---|
629 | + sep + local_name + sep + prefix. |
---|
630 | |
---|
631 | If do_nst is zero, then namespace information is returned in the |
---|
632 | default manner (URI + sep + local_name) whether or not the name |
---|
633 | has a prefix. |
---|
634 | |
---|
635 | Note: Calling XML_SetReturnNSTriplet after XML_Parse or |
---|
636 | XML_ParseBuffer has no effect. |
---|
637 | */ |
---|
638 | |
---|
639 | XMLPARSEAPI(void) |
---|
640 | XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); |
---|
641 | |
---|
642 | /* This value is passed as the userData argument to callbacks. */ |
---|
643 | XMLPARSEAPI(void) |
---|
644 | XML_SetUserData(XML_Parser parser, void *userData); |
---|
645 | |
---|
646 | /* Returns the last value set by XML_SetUserData or NULL. */ |
---|
647 | #define XML_GetUserData(parser) (*(void **)(parser)) |
---|
648 | |
---|
649 | /* This is equivalent to supplying an encoding argument to |
---|
650 | XML_ParserCreate. On success XML_SetEncoding returns non-zero, |
---|
651 | zero otherwise. |
---|
652 | Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer |
---|
653 | has no effect and returns zero. |
---|
654 | */ |
---|
655 | XMLPARSEAPI(int) |
---|
656 | XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); |
---|
657 | |
---|
658 | /* If this function is called, then the parser will be passed as the |
---|
659 | first argument to callbacks instead of userData. The userData will |
---|
660 | still be accessible using XML_GetUserData. |
---|
661 | */ |
---|
662 | XMLPARSEAPI(void) |
---|
663 | XML_UseParserAsHandlerArg(XML_Parser parser); |
---|
664 | |
---|
665 | /* If useDTD == XML_TRUE is passed to this function, then the parser |
---|
666 | will assume that there is an external subset, even if none is |
---|
667 | specified in the document. In such a case the parser will call the |
---|
668 | externalEntityRefHandler with a value of NULL for the systemId |
---|
669 | argument (the publicId and context arguments will be NULL as well). |
---|
670 | Note: If this function is called, then this must be done before |
---|
671 | the first call to XML_Parse or XML_ParseBuffer, since it will |
---|
672 | have no effect after that. Returns |
---|
673 | XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. |
---|
674 | Note: If the document does not have a DOCTYPE declaration at all, |
---|
675 | then startDoctypeDeclHandler and endDoctypeDeclHandler will not |
---|
676 | be called, despite an external subset being parsed. |
---|
677 | Note: If XML_DTD is not defined when Expat is compiled, returns |
---|
678 | XML_ERROR_FEATURE_REQUIRES_XML_DTD. |
---|
679 | */ |
---|
680 | XMLPARSEAPI(enum XML_Error) |
---|
681 | XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); |
---|
682 | |
---|
683 | |
---|
684 | /* Sets the base to be used for resolving relative URIs in system |
---|
685 | identifiers in declarations. Resolving relative identifiers is |
---|
686 | left to the application: this value will be passed through as the |
---|
687 | base argument to the XML_ExternalEntityRefHandler, |
---|
688 | XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base |
---|
689 | argument will be copied. Returns zero if out of memory, non-zero |
---|
690 | otherwise. |
---|
691 | */ |
---|
692 | XMLPARSEAPI(int) |
---|
693 | XML_SetBase(XML_Parser parser, const XML_Char *base); |
---|
694 | |
---|
695 | XMLPARSEAPI(const XML_Char *) |
---|
696 | XML_GetBase(XML_Parser parser); |
---|
697 | |
---|
698 | /* Returns the number of the attribute/value pairs passed in last call |
---|
699 | to the XML_StartElementHandler that were specified in the start-tag |
---|
700 | rather than defaulted. Each attribute/value pair counts as 2; thus |
---|
701 | this correspondds to an index into the atts array passed to the |
---|
702 | XML_StartElementHandler. |
---|
703 | */ |
---|
704 | XMLPARSEAPI(int) |
---|
705 | XML_GetSpecifiedAttributeCount(XML_Parser parser); |
---|
706 | |
---|
707 | /* Returns the index of the ID attribute passed in the last call to |
---|
708 | XML_StartElementHandler, or -1 if there is no ID attribute. Each |
---|
709 | attribute/value pair counts as 2; thus this correspondds to an |
---|
710 | index into the atts array passed to the XML_StartElementHandler. |
---|
711 | */ |
---|
712 | XMLPARSEAPI(int) |
---|
713 | XML_GetIdAttributeIndex(XML_Parser parser); |
---|
714 | |
---|
715 | /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is |
---|
716 | detected. The last call to XML_Parse must have isFinal true; len |
---|
717 | may be zero for this call (or any other). |
---|
718 | |
---|
719 | The XML_Status enum gives the possible return values for the |
---|
720 | XML_Parse and XML_ParseBuffer functions. Though the return values |
---|
721 | for these functions has always been described as a Boolean value, |
---|
722 | the implementation, at least for the 1.95.x series, has always |
---|
723 | returned exactly one of these values. The preprocessor #defines |
---|
724 | are included so this stanza can be added to code that still needs |
---|
725 | to support older versions of Expat 1.95.x: |
---|
726 | |
---|
727 | #ifndef XML_STATUS_OK |
---|
728 | #define XML_STATUS_OK 1 |
---|
729 | #define XML_STATUS_ERROR 0 |
---|
730 | #endif |
---|
731 | |
---|
732 | Otherwise, the #define hackery is quite ugly and would have been dropped. |
---|
733 | */ |
---|
734 | enum XML_Status { |
---|
735 | XML_STATUS_ERROR = 0, |
---|
736 | #define XML_STATUS_ERROR XML_STATUS_ERROR |
---|
737 | XML_STATUS_OK = 1 |
---|
738 | #define XML_STATUS_OK XML_STATUS_OK |
---|
739 | }; |
---|
740 | |
---|
741 | XMLPARSEAPI(enum XML_Status) |
---|
742 | XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); |
---|
743 | |
---|
744 | XMLPARSEAPI(void *) |
---|
745 | XML_GetBuffer(XML_Parser parser, int len); |
---|
746 | |
---|
747 | XMLPARSEAPI(enum XML_Status) |
---|
748 | XML_ParseBuffer(XML_Parser parser, int len, int isFinal); |
---|
749 | |
---|
750 | /* Creates an XML_Parser object that can parse an external general |
---|
751 | entity; context is a '\0'-terminated string specifying the parse |
---|
752 | context; encoding is a '\0'-terminated string giving the name of |
---|
753 | the externally specified encoding, or NULL if there is no |
---|
754 | externally specified encoding. The context string consists of a |
---|
755 | sequence of tokens separated by formfeeds (\f); a token consisting |
---|
756 | of a name specifies that the general entity of the name is open; a |
---|
757 | token of the form prefix=uri specifies the namespace for a |
---|
758 | particular prefix; a token of the form =uri specifies the default |
---|
759 | namespace. This can be called at any point after the first call to |
---|
760 | an ExternalEntityRefHandler so longer as the parser has not yet |
---|
761 | been freed. The new parser is completely independent and may |
---|
762 | safely be used in a separate thread. The handlers and userData are |
---|
763 | initialized from the parser argument. Returns 0 if out of memory. |
---|
764 | Otherwise returns a new XML_Parser object. |
---|
765 | */ |
---|
766 | XMLPARSEAPI(XML_Parser) |
---|
767 | XML_ExternalEntityParserCreate(XML_Parser parser, |
---|
768 | const XML_Char *context, |
---|
769 | const XML_Char *encoding); |
---|
770 | |
---|
771 | enum XML_ParamEntityParsing { |
---|
772 | XML_PARAM_ENTITY_PARSING_NEVER, |
---|
773 | XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, |
---|
774 | XML_PARAM_ENTITY_PARSING_ALWAYS |
---|
775 | }; |
---|
776 | |
---|
777 | /* Controls parsing of parameter entities (including the external DTD |
---|
778 | subset). If parsing of parameter entities is enabled, then |
---|
779 | references to external parameter entities (including the external |
---|
780 | DTD subset) will be passed to the handler set with |
---|
781 | XML_SetExternalEntityRefHandler. The context passed will be 0. |
---|
782 | |
---|
783 | Unlike external general entities, external parameter entities can |
---|
784 | only be parsed synchronously. If the external parameter entity is |
---|
785 | to be parsed, it must be parsed during the call to the external |
---|
786 | entity ref handler: the complete sequence of |
---|
787 | XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and |
---|
788 | XML_ParserFree calls must be made during this call. After |
---|
789 | XML_ExternalEntityParserCreate has been called to create the parser |
---|
790 | for the external parameter entity (context must be 0 for this |
---|
791 | call), it is illegal to make any calls on the old parser until |
---|
792 | XML_ParserFree has been called on the newly created parser. |
---|
793 | If the library has been compiled without support for parameter |
---|
794 | entity parsing (ie without XML_DTD being defined), then |
---|
795 | XML_SetParamEntityParsing will return 0 if parsing of parameter |
---|
796 | entities is requested; otherwise it will return non-zero. |
---|
797 | Note: If XML_SetParamEntityParsing is called after XML_Parse or |
---|
798 | XML_ParseBuffer, then it has no effect and will always return 0. |
---|
799 | */ |
---|
800 | XMLPARSEAPI(int) |
---|
801 | XML_SetParamEntityParsing(XML_Parser parser, |
---|
802 | enum XML_ParamEntityParsing parsing); |
---|
803 | |
---|
804 | /* If XML_Parse or XML_ParseBuffer have returned 0, then |
---|
805 | XML_GetErrorCode returns information about the error. |
---|
806 | */ |
---|
807 | XMLPARSEAPI(enum XML_Error) |
---|
808 | XML_GetErrorCode(XML_Parser parser); |
---|
809 | |
---|
810 | /* These functions return information about the current parse |
---|
811 | location. They may be called when XML_Parse or XML_ParseBuffer |
---|
812 | return 0; in this case the location is the location of the |
---|
813 | character at which the error was detected. |
---|
814 | |
---|
815 | They may also be called from any other callback called to report |
---|
816 | some parse event; in this the location is the location of the first |
---|
817 | of the sequence of characters that generated the event. |
---|
818 | */ |
---|
819 | XMLPARSEAPI(int) XML_GetCurrentLineNumber(XML_Parser parser); |
---|
820 | XMLPARSEAPI(int) XML_GetCurrentColumnNumber(XML_Parser parser); |
---|
821 | XMLPARSEAPI(long) XML_GetCurrentByteIndex(XML_Parser parser); |
---|
822 | |
---|
823 | /* Return the number of bytes in the current event. |
---|
824 | Returns 0 if the event is in an internal entity. |
---|
825 | */ |
---|
826 | XMLPARSEAPI(int) |
---|
827 | XML_GetCurrentByteCount(XML_Parser parser); |
---|
828 | |
---|
829 | /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets |
---|
830 | the integer pointed to by offset to the offset within this buffer |
---|
831 | of the current parse position, and sets the integer pointed to by size |
---|
832 | to the size of this buffer (the number of input bytes). Otherwise |
---|
833 | returns a NULL pointer. Also returns a NULL pointer if a parse isn't |
---|
834 | active. |
---|
835 | |
---|
836 | NOTE: The character pointer returned should not be used outside |
---|
837 | the handler that makes the call. |
---|
838 | */ |
---|
839 | XMLPARSEAPI(const char *) |
---|
840 | XML_GetInputContext(XML_Parser parser, |
---|
841 | int *offset, |
---|
842 | int *size); |
---|
843 | |
---|
844 | /* For backwards compatibility with previous versions. */ |
---|
845 | #define XML_GetErrorLineNumber XML_GetCurrentLineNumber |
---|
846 | #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber |
---|
847 | #define XML_GetErrorByteIndex XML_GetCurrentByteIndex |
---|
848 | |
---|
849 | /* Frees memory used by the parser. */ |
---|
850 | XMLPARSEAPI(void) |
---|
851 | XML_ParserFree(XML_Parser parser); |
---|
852 | |
---|
853 | /* Returns a string describing the error. */ |
---|
854 | XMLPARSEAPI(const XML_LChar *) |
---|
855 | XML_ErrorString(enum XML_Error code); |
---|
856 | |
---|
857 | /* Return a string containing the version number of this expat */ |
---|
858 | XMLPARSEAPI(const XML_LChar *) |
---|
859 | XML_ExpatVersion(void); |
---|
860 | |
---|
861 | typedef struct { |
---|
862 | int major; |
---|
863 | int minor; |
---|
864 | int micro; |
---|
865 | } XML_Expat_Version; |
---|
866 | |
---|
867 | /* Return an XML_Expat_Version structure containing numeric version |
---|
868 | number information for this version of expat. |
---|
869 | */ |
---|
870 | XMLPARSEAPI(XML_Expat_Version) |
---|
871 | XML_ExpatVersionInfo(void); |
---|
872 | |
---|
873 | /* Added in Expat 1.95.5. */ |
---|
874 | enum XML_FeatureEnum { |
---|
875 | XML_FEATURE_END = 0, |
---|
876 | XML_FEATURE_UNICODE, |
---|
877 | XML_FEATURE_UNICODE_WCHAR_T, |
---|
878 | XML_FEATURE_DTD, |
---|
879 | XML_FEATURE_CONTEXT_BYTES, |
---|
880 | XML_FEATURE_MIN_SIZE, |
---|
881 | XML_FEATURE_SIZEOF_XML_CHAR, |
---|
882 | XML_FEATURE_SIZEOF_XML_LCHAR |
---|
883 | /* Additional features must be added to the end of this enum. */ |
---|
884 | }; |
---|
885 | |
---|
886 | typedef struct { |
---|
887 | enum XML_FeatureEnum feature; |
---|
888 | XML_LChar *name; |
---|
889 | long int value; |
---|
890 | } XML_Feature; |
---|
891 | |
---|
892 | XMLPARSEAPI(const XML_Feature *) |
---|
893 | XML_GetFeatureList(void); |
---|
894 | |
---|
895 | |
---|
896 | /* Expat follows the GNU/Linux convention of odd number minor version for |
---|
897 | beta/development releases and even number minor version for stable |
---|
898 | releases. Micro is bumped with each release, and set to 0 with each |
---|
899 | change to major or minor version. |
---|
900 | */ |
---|
901 | #define XML_MAJOR_VERSION 1 |
---|
902 | #define XML_MINOR_VERSION 95 |
---|
903 | #define XML_MICRO_VERSION 5 |
---|
904 | |
---|
905 | #ifdef __cplusplus |
---|
906 | } |
---|
907 | #endif |
---|
908 | |
---|
909 | #endif /* not XmlParse_INCLUDED */ |
---|