25
|
1 /* |
|
2 The contents of this file are subject to the Mozilla Public License |
|
3 Version 1.1 (the "License"); you may not use this file except in |
|
4 compliance with the License. You may obtain a copy of the License at |
|
5 http://www.mozilla.org/MPL/ |
|
6 |
|
7 Software distributed under the License is distributed on an "AS IS" |
|
8 basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the |
|
9 License for the specific language governing rights and limitations |
|
10 under the License. |
|
11 |
|
12 The Original Code is expat. |
|
13 |
|
14 The Initial Developer of the Original Code is James Clark. |
|
15 Portions created by James Clark are Copyright (C) 1998, 1999 |
|
16 James Clark. All Rights Reserved. |
|
17 |
|
18 Contributor(s): |
|
19 |
|
20 Alternatively, the contents of this file may be used under the terms |
|
21 of the GNU General Public License (the "GPL"), in which case the |
|
22 provisions of the GPL are applicable instead of those above. If you |
|
23 wish to allow use of your version of this file only under the terms of |
|
24 the GPL and not to allow others to use your version of this file under |
|
25 the MPL, indicate your decision by deleting the provisions above and |
|
26 replace them with the notice and other provisions required by the |
|
27 GPL. If you do not delete the provisions above, a recipient may use |
|
28 your version of this file under either the MPL or the GPL. |
|
29 */ |
|
30 |
|
31 #ifndef XmlParse_INCLUDED |
|
32 #define XmlParse_INCLUDED 1 |
|
33 |
|
34 #ifdef __cplusplus |
|
35 extern "C" { |
|
36 #endif |
|
37 |
|
38 #ifndef XMLPARSEAPI |
|
39 #define XMLPARSEAPI /* as nothing */ |
|
40 #endif |
|
41 |
|
42 typedef void *XML_Parser; |
|
43 |
|
44 #ifdef XML_UNICODE_WCHAR_T |
|
45 |
|
46 /* XML_UNICODE_WCHAR_T will work only if sizeof(wchar_t) == 2 and wchar_t |
|
47 uses Unicode. */ |
|
48 /* Information is UTF-16 encoded as wchar_ts */ |
|
49 |
|
50 #ifndef XML_UNICODE |
|
51 #define XML_UNICODE |
|
52 #endif |
|
53 |
|
54 #include <stddef.h> |
|
55 typedef wchar_t XML_Char; |
|
56 typedef wchar_t XML_LChar; |
|
57 |
|
58 #else /* not XML_UNICODE_WCHAR_T */ |
|
59 |
|
60 #ifdef XML_UNICODE |
|
61 |
|
62 /* Information is UTF-16 encoded as unsigned shorts */ |
|
63 typedef unsigned short XML_Char; |
|
64 typedef char XML_LChar; |
|
65 |
|
66 #else /* not XML_UNICODE */ |
|
67 |
|
68 /* Information is UTF-8 encoded. */ |
|
69 typedef char XML_Char; |
|
70 typedef char XML_LChar; |
|
71 |
|
72 #endif /* not XML_UNICODE */ |
|
73 |
|
74 #endif /* not XML_UNICODE_WCHAR_T */ |
|
75 |
|
76 |
|
77 /* Constructs a new parser; encoding is the encoding specified by the external |
|
78 protocol or null if there is none specified. */ |
|
79 |
|
80 XML_Parser XMLPARSEAPI |
|
81 XML_ParserCreate(const XML_Char *encoding); |
|
82 |
|
83 /* Constructs a new parser and namespace processor. Element type names |
|
84 and attribute names that belong to a namespace will be expanded; |
|
85 unprefixed attribute names are never expanded; unprefixed element type |
|
86 names are expanded only if there is a default namespace. The expanded |
|
87 name is the concatenation of the namespace URI, the namespace separator character, |
|
88 and the local part of the name. If the namespace separator is '\0' then |
|
89 the namespace URI and the local part will be concatenated without any |
|
90 separator. When a namespace is not declared, the name and prefix will be |
|
91 passed through without expansion. */ |
|
92 |
|
93 XML_Parser XMLPARSEAPI |
|
94 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); |
|
95 |
|
96 |
|
97 /* atts is array of name/value pairs, terminated by 0; |
|
98 names and values are 0 terminated. */ |
|
99 |
|
100 typedef void (*XML_StartElementHandler)(void *userData, |
|
101 const XML_Char *name, |
|
102 const XML_Char **atts); |
|
103 |
|
104 typedef void (*XML_EndElementHandler)(void *userData, |
|
105 const XML_Char *name); |
|
106 |
|
107 /* s is not 0 terminated. */ |
|
108 typedef void (*XML_CharacterDataHandler)(void *userData, |
|
109 const XML_Char *s, |
|
110 int len); |
|
111 |
|
112 /* target and data are 0 terminated */ |
|
113 typedef void (*XML_ProcessingInstructionHandler)(void *userData, |
|
114 const XML_Char *target, |
|
115 const XML_Char *data); |
|
116 |
|
117 /* data is 0 terminated */ |
|
118 typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data); |
|
119 |
|
120 typedef void (*XML_StartCdataSectionHandler)(void *userData); |
|
121 typedef void (*XML_EndCdataSectionHandler)(void *userData); |
|
122 |
|
123 /* This is called for any characters in the XML document for |
|
124 which there is no applicable handler. This includes both |
|
125 characters that are part of markup which is of a kind that is |
|
126 not reported (comments, markup declarations), or characters |
|
127 that are part of a construct which could be reported but |
|
128 for which no handler has been supplied. The characters are passed |
|
129 exactly as they were in the XML document except that |
|
130 they will be encoded in UTF-8. Line boundaries are not normalized. |
|
131 Note that a byte order mark character is not passed to the default handler. |
|
132 There are no guarantees about how characters are divided between calls |
|
133 to the default handler: for example, a comment might be split between |
|
134 multiple calls. */ |
|
135 |
|
136 typedef void (*XML_DefaultHandler)(void *userData, |
|
137 const XML_Char *s, |
|
138 int len); |
|
139 |
|
140 /* This is called for a declaration of an unparsed (NDATA) |
|
141 entity. The base argument is whatever was set by XML_SetBase. |
|
142 The entityName, systemId and notationName arguments will never be null. |
|
143 The other arguments may be. */ |
|
144 |
|
145 typedef void (*XML_UnparsedEntityDeclHandler)(void *userData, |
|
146 const XML_Char *entityName, |
|
147 const XML_Char *base, |
|
148 const XML_Char *systemId, |
|
149 const XML_Char *publicId, |
|
150 const XML_Char *notationName); |
|
151 |
|
152 /* This is called for a declaration of notation. |
|
153 The base argument is whatever was set by XML_SetBase. |
|
154 The notationName will never be null. The other arguments can be. */ |
|
155 |
|
156 typedef void (*XML_NotationDeclHandler)(void *userData, |
|
157 const XML_Char *notationName, |
|
158 const XML_Char *base, |
|
159 const XML_Char *systemId, |
|
160 const XML_Char *publicId); |
|
161 |
|
162 /* When namespace processing is enabled, these are called once for |
|
163 each namespace declaration. The call to the start and end element |
|
164 handlers occur between the calls to the start and end namespace |
|
165 declaration handlers. For an xmlns attribute, prefix will be null. |
|
166 For an xmlns="" attribute, uri will be null. */ |
|
167 |
|
168 typedef void (*XML_StartNamespaceDeclHandler)(void *userData, |
|
169 const XML_Char *prefix, |
|
170 const XML_Char *uri); |
|
171 |
|
172 typedef void (*XML_EndNamespaceDeclHandler)(void *userData, |
|
173 const XML_Char *prefix); |
|
174 |
|
175 /* This is called if the document is not standalone (it has an |
|
176 external subset or a reference to a parameter entity, but does not |
|
177 have standalone="yes"). If this handler returns 0, then processing |
|
178 will not continue, and the parser will return a |
|
179 XML_ERROR_NOT_STANDALONE error. */ |
|
180 |
|
181 typedef int (*XML_NotStandaloneHandler)(void *userData); |
|
182 |
|
183 /* This is called for a reference to an external parsed general entity. |
|
184 The referenced entity is not automatically parsed. |
|
185 The application can parse it immediately or later using |
|
186 XML_ExternalEntityParserCreate. |
|
187 The parser argument is the parser parsing the entity containing the reference; |
|
188 it can be passed as the parser argument to XML_ExternalEntityParserCreate. |
|
189 The systemId argument is the system identifier as specified in the entity declaration; |
|
190 it will not be null. |
|
191 The base argument is the system identifier that should be used as the base for |
|
192 resolving systemId if systemId was relative; this is set by XML_SetBase; |
|
193 it may be null. |
|
194 The publicId argument is the public identifier as specified in the entity declaration, |
|
195 or null if none was specified; the whitespace in the public identifier |
|
196 will have been normalized as required by the XML spec. |
|
197 The context argument specifies the parsing context in the format |
|
198 expected by the context argument to |
|
199 XML_ExternalEntityParserCreate; context is valid only until the handler |
|
200 returns, so if the referenced entity is to be parsed later, it must be copied. |
|
201 The handler should return 0 if processing should not continue because of |
|
202 a fatal error in the handling of the external entity. |
|
203 In this case the calling parser will return an XML_ERROR_EXTERNAL_ENTITY_HANDLING |
|
204 error. |
|
205 Note that unlike other handlers the first argument is the parser, not userData. */ |
|
206 |
|
207 typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser, |
|
208 const XML_Char *context, |
|
209 const XML_Char *base, |
|
210 const XML_Char *systemId, |
|
211 const XML_Char *publicId); |
|
212 |
|
213 /* This structure is filled in by the XML_UnknownEncodingHandler |
|
214 to provide information to the parser about encodings that are unknown |
|
215 to the parser. |
|
216 The map[b] member gives information about byte sequences |
|
217 whose first byte is b. |
|
218 If map[b] is c where c is >= 0, then b by itself encodes the Unicode scalar value c. |
|
219 If map[b] is -1, then the byte sequence is malformed. |
|
220 If map[b] is -n, where n >= 2, then b is the first byte of an n-byte |
|
221 sequence that encodes a single Unicode scalar value. |
|
222 The data member will be passed as the first argument to the convert function. |
|
223 The convert function is used to convert multibyte sequences; |
|
224 s will point to a n-byte sequence where map[(unsigned char)*s] == -n. |
|
225 The convert function must return the Unicode scalar value |
|
226 represented by this byte sequence or -1 if the byte sequence is malformed. |
|
227 The convert function may be null if the encoding is a single-byte encoding, |
|
228 that is if map[b] >= -1 for all bytes b. |
|
229 When the parser is finished with the encoding, then if release is not null, |
|
230 it will call release passing it the data member; |
|
231 once release has been called, the convert function will not be called again. |
|
232 |
|
233 Expat places certain restrictions on the encodings that are supported |
|
234 using this mechanism. |
|
235 |
|
236 1. Every ASCII character that can appear in a well-formed XML document, |
|
237 other than the characters |
|
238 |
|
239 $@\^`{}~ |
|
240 |
|
241 must be represented by a single byte, and that byte must be the |
|
242 same byte that represents that character in ASCII. |
|
243 |
|
244 2. No character may require more than 4 bytes to encode. |
|
245 |
|
246 3. All characters encoded must have Unicode scalar values <= 0xFFFF, |
|
247 (ie characters that would be encoded by surrogates in UTF-16 |
|
248 are not allowed). Note that this restriction doesn't apply to |
|
249 the built-in support for UTF-8 and UTF-16. |
|
250 |
|
251 4. No Unicode character may be encoded by more than one distinct sequence |
|
252 of bytes. */ |
|
253 |
|
254 typedef struct { |
|
255 int map[256]; |
|
256 void *data; |
|
257 int (*convert)(void *data, const char *s); |
|
258 void (*release)(void *data); |
|
259 } XML_Encoding; |
|
260 |
|
261 /* This is called for an encoding that is unknown to the parser. |
|
262 The encodingHandlerData argument is that which was passed as the |
|
263 second argument to XML_SetUnknownEncodingHandler. |
|
264 The name argument gives the name of the encoding as specified in |
|
265 the encoding declaration. |
|
266 If the callback can provide information about the encoding, |
|
267 it must fill in the XML_Encoding structure, and return 1. |
|
268 Otherwise it must return 0. |
|
269 If info does not describe a suitable encoding, |
|
270 then the parser will return an XML_UNKNOWN_ENCODING error. */ |
|
271 |
|
272 typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData, |
|
273 const XML_Char *name, |
|
274 XML_Encoding *info); |
|
275 |
|
276 void XMLPARSEAPI |
|
277 XML_SetElementHandler(XML_Parser parser, |
|
278 XML_StartElementHandler start, |
|
279 XML_EndElementHandler end); |
|
280 |
|
281 void XMLPARSEAPI |
|
282 XML_SetCharacterDataHandler(XML_Parser parser, |
|
283 XML_CharacterDataHandler handler); |
|
284 |
|
285 void XMLPARSEAPI |
|
286 XML_SetProcessingInstructionHandler(XML_Parser parser, |
|
287 XML_ProcessingInstructionHandler handler); |
|
288 void XMLPARSEAPI |
|
289 XML_SetCommentHandler(XML_Parser parser, |
|
290 XML_CommentHandler handler); |
|
291 |
|
292 void XMLPARSEAPI |
|
293 XML_SetCdataSectionHandler(XML_Parser parser, |
|
294 XML_StartCdataSectionHandler start, |
|
295 XML_EndCdataSectionHandler end); |
|
296 |
|
297 /* This sets the default handler and also inhibits expansion of internal entities. |
|
298 The entity reference will be passed to the default handler. */ |
|
299 |
|
300 void XMLPARSEAPI |
|
301 XML_SetDefaultHandler(XML_Parser parser, |
|
302 XML_DefaultHandler handler); |
|
303 |
|
304 /* This sets the default handler but does not inhibit expansion of internal entities. |
|
305 The entity reference will not be passed to the default handler. */ |
|
306 |
|
307 void XMLPARSEAPI |
|
308 XML_SetDefaultHandlerExpand(XML_Parser parser, |
|
309 XML_DefaultHandler handler); |
|
310 |
|
311 void XMLPARSEAPI |
|
312 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, |
|
313 XML_UnparsedEntityDeclHandler handler); |
|
314 |
|
315 void XMLPARSEAPI |
|
316 XML_SetNotationDeclHandler(XML_Parser parser, |
|
317 XML_NotationDeclHandler handler); |
|
318 |
|
319 void XMLPARSEAPI |
|
320 XML_SetNamespaceDeclHandler(XML_Parser parser, |
|
321 XML_StartNamespaceDeclHandler start, |
|
322 XML_EndNamespaceDeclHandler end); |
|
323 |
|
324 void XMLPARSEAPI |
|
325 XML_SetNotStandaloneHandler(XML_Parser parser, |
|
326 XML_NotStandaloneHandler handler); |
|
327 |
|
328 void XMLPARSEAPI |
|
329 XML_SetExternalEntityRefHandler(XML_Parser parser, |
|
330 XML_ExternalEntityRefHandler handler); |
|
331 |
|
332 /* If a non-null value for arg is specified here, then it will be passed |
|
333 as the first argument to the external entity ref handler instead |
|
334 of the parser object. */ |
|
335 void XMLPARSEAPI |
|
336 XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg); |
|
337 |
|
338 void XMLPARSEAPI |
|
339 XML_SetUnknownEncodingHandler(XML_Parser parser, |
|
340 XML_UnknownEncodingHandler handler, |
|
341 void *encodingHandlerData); |
|
342 |
|
343 /* This can be called within a handler for a start element, end element, |
|
344 processing instruction or character data. It causes the corresponding |
|
345 markup to be passed to the default handler. */ |
|
346 void XMLPARSEAPI XML_DefaultCurrent(XML_Parser parser); |
|
347 |
|
348 /* This value is passed as the userData argument to callbacks. */ |
|
349 void XMLPARSEAPI |
|
350 XML_SetUserData(XML_Parser parser, void *userData); |
|
351 |
|
352 /* Returns the last value set by XML_SetUserData or null. */ |
|
353 #define XML_GetUserData(parser) (*(void **)(parser)) |
|
354 |
|
355 /* This is equivalent to supplying an encoding argument |
|
356 to XML_CreateParser. It must not be called after XML_Parse |
|
357 or XML_ParseBuffer. */ |
|
358 |
|
359 int XMLPARSEAPI |
|
360 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); |
|
361 |
|
362 /* If this function is called, then the parser will be passed |
|
363 as the first argument to callbacks instead of userData. |
|
364 The userData will still be accessible using XML_GetUserData. */ |
|
365 |
|
366 void XMLPARSEAPI |
|
367 XML_UseParserAsHandlerArg(XML_Parser parser); |
|
368 |
|
369 /* Sets the base to be used for resolving relative URIs in system identifiers in |
|
370 declarations. Resolving relative identifiers is left to the application: |
|
371 this value will be passed through as the base argument to the |
|
372 XML_ExternalEntityRefHandler, XML_NotationDeclHandler |
|
373 and XML_UnparsedEntityDeclHandler. The base argument will be copied. |
|
374 Returns zero if out of memory, non-zero otherwise. */ |
|
375 |
|
376 int XMLPARSEAPI |
|
377 XML_SetBase(XML_Parser parser, const XML_Char *base); |
|
378 |
|
379 const XML_Char XMLPARSEAPI * |
|
380 XML_GetBase(XML_Parser parser); |
|
381 |
|
382 /* Returns the number of the attributes passed in last call to the |
|
383 XML_StartElementHandler that were specified in the start-tag rather |
|
384 than defaulted. */ |
|
385 |
|
386 int XMLPARSEAPI XML_GetSpecifiedAttributeCount(XML_Parser parser); |
|
387 |
|
388 /* Parses some input. Returns 0 if a fatal error is detected. |
|
389 The last call to XML_Parse must have isFinal true; |
|
390 len may be zero for this call (or any other). */ |
|
391 int XMLPARSEAPI |
|
392 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); |
|
393 |
|
394 void XMLPARSEAPI * |
|
395 XML_GetBuffer(XML_Parser parser, int len); |
|
396 |
|
397 int XMLPARSEAPI |
|
398 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); |
|
399 |
|
400 /* Creates an XML_Parser object that can parse an external general entity; |
|
401 context is a '\0'-terminated string specifying the parse context; |
|
402 encoding is a '\0'-terminated string giving the name of the externally specified encoding, |
|
403 or null if there is no externally specified encoding. |
|
404 The context string consists of a sequence of tokens separated by formfeeds (\f); |
|
405 a token consisting of a name specifies that the general entity of the name |
|
406 is open; a token of the form prefix=uri specifies the namespace for a particular |
|
407 prefix; a token of the form =uri specifies the default namespace. |
|
408 This can be called at any point after the first call to an ExternalEntityRefHandler |
|
409 so longer as the parser has not yet been freed. |
|
410 The new parser is completely independent and may safely be used in a separate thread. |
|
411 The handlers and userData are initialized from the parser argument. |
|
412 Returns 0 if out of memory. Otherwise returns a new XML_Parser object. */ |
|
413 XML_Parser XMLPARSEAPI |
|
414 XML_ExternalEntityParserCreate(XML_Parser parser, |
|
415 const XML_Char *context, |
|
416 const XML_Char *encoding); |
|
417 |
|
418 enum XML_Error { |
|
419 XML_ERROR_NONE, |
|
420 XML_ERROR_NO_MEMORY, |
|
421 XML_ERROR_SYNTAX, |
|
422 XML_ERROR_NO_ELEMENTS, |
|
423 XML_ERROR_INVALID_TOKEN, |
|
424 XML_ERROR_UNCLOSED_TOKEN, |
|
425 XML_ERROR_PARTIAL_CHAR, |
|
426 XML_ERROR_TAG_MISMATCH, |
|
427 XML_ERROR_DUPLICATE_ATTRIBUTE, |
|
428 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, |
|
429 XML_ERROR_PARAM_ENTITY_REF, |
|
430 XML_ERROR_UNDEFINED_ENTITY, |
|
431 XML_ERROR_RECURSIVE_ENTITY_REF, |
|
432 XML_ERROR_ASYNC_ENTITY, |
|
433 XML_ERROR_BAD_CHAR_REF, |
|
434 XML_ERROR_BINARY_ENTITY_REF, |
|
435 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, |
|
436 XML_ERROR_MISPLACED_XML_PI, |
|
437 XML_ERROR_UNKNOWN_ENCODING, |
|
438 XML_ERROR_INCORRECT_ENCODING, |
|
439 XML_ERROR_UNCLOSED_CDATA_SECTION, |
|
440 XML_ERROR_EXTERNAL_ENTITY_HANDLING, |
|
441 XML_ERROR_NOT_STANDALONE |
|
442 }; |
|
443 |
|
444 /* If XML_Parse or XML_ParseBuffer have returned 0, then XML_GetErrorCode |
|
445 returns information about the error. */ |
|
446 |
|
447 enum XML_Error XMLPARSEAPI XML_GetErrorCode(XML_Parser parser); |
|
448 |
|
449 /* These functions return information about the current parse location. |
|
450 They may be called when XML_Parse or XML_ParseBuffer return 0; |
|
451 in this case the location is the location of the character at which |
|
452 the error was detected. |
|
453 They may also be called from any other callback called to report |
|
454 some parse event; in this the location is the location of the first |
|
455 of the sequence of characters that generated the event. */ |
|
456 |
|
457 int XMLPARSEAPI XML_GetCurrentLineNumber(XML_Parser parser); |
|
458 int XMLPARSEAPI XML_GetCurrentColumnNumber(XML_Parser parser); |
|
459 long XMLPARSEAPI XML_GetCurrentByteIndex(XML_Parser parser); |
|
460 |
|
461 /* Return the number of bytes in the current event. |
|
462 Returns 0 if the event is in an internal entity. */ |
|
463 |
|
464 int XMLPARSEAPI XML_GetCurrentByteCount(XML_Parser parser); |
|
465 |
|
466 /* For backwards compatibility with previous versions. */ |
|
467 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber |
|
468 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber |
|
469 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex |
|
470 |
|
471 /* Frees memory used by the parser. */ |
|
472 void XMLPARSEAPI |
|
473 XML_ParserFree(XML_Parser parser); |
|
474 |
|
475 /* Returns a string describing the error. */ |
|
476 const XML_LChar XMLPARSEAPI *XML_ErrorString(int code); |
|
477 |
|
478 #ifdef __cplusplus |
|
479 } |
|
480 #endif |
|
481 |
|
482 #endif /* not XmlParse_INCLUDED */ |