Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
freebsd
GitHub Repository: freebsd/freebsd-src
Path: blob/main/contrib/expat/lib/expat.h
39478 views
1
/*
2
__ __ _
3
___\ \/ /_ __ __ _| |_
4
/ _ \\ /| '_ \ / _` | __|
5
| __// \| |_) | (_| | |_
6
\___/_/\_\ .__/ \__,_|\__|
7
|_| XML parser
8
9
Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
10
Copyright (c) 2000 Clark Cooper <[email protected]>
11
Copyright (c) 2000-2005 Fred L. Drake, Jr. <[email protected]>
12
Copyright (c) 2001-2002 Greg Stein <[email protected]>
13
Copyright (c) 2002-2016 Karl Waclawek <[email protected]>
14
Copyright (c) 2016-2025 Sebastian Pipping <[email protected]>
15
Copyright (c) 2016 Cristian Rodríguez <[email protected]>
16
Copyright (c) 2016 Thomas Beutlich <[email protected]>
17
Copyright (c) 2017 Rhodri James <[email protected]>
18
Copyright (c) 2022 Thijs Schreijer <[email protected]>
19
Copyright (c) 2023 Hanno Böck <[email protected]>
20
Copyright (c) 2023 Sony Corporation / Snild Dolkow <[email protected]>
21
Copyright (c) 2024 Taichi Haradaguchi <[email protected]>
22
Copyright (c) 2025 Matthew Fernandez <[email protected]>
23
Licensed under the MIT license:
24
25
Permission is hereby granted, free of charge, to any person obtaining
26
a copy of this software and associated documentation files (the
27
"Software"), to deal in the Software without restriction, including
28
without limitation the rights to use, copy, modify, merge, publish,
29
distribute, sublicense, and/or sell copies of the Software, and to permit
30
persons to whom the Software is furnished to do so, subject to the
31
following conditions:
32
33
The above copyright notice and this permission notice shall be included
34
in all copies or substantial portions of the Software.
35
36
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
37
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
38
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
39
NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
40
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
41
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
42
USE OR OTHER DEALINGS IN THE SOFTWARE.
43
*/
44
45
#ifndef Expat_INCLUDED
46
# define Expat_INCLUDED 1
47
48
# include <stdlib.h>
49
# include "expat_external.h"
50
51
# ifdef __cplusplus
52
extern "C" {
53
# endif
54
55
struct XML_ParserStruct;
56
typedef struct XML_ParserStruct *XML_Parser;
57
58
typedef unsigned char XML_Bool;
59
# define XML_TRUE ((XML_Bool)1)
60
# define XML_FALSE ((XML_Bool)0)
61
62
/* The XML_Status enum gives the possible return values for several
63
API functions. The preprocessor #defines are included so this
64
stanza can be added to code that still needs to support older
65
versions of Expat 1.95.x:
66
67
#ifndef XML_STATUS_OK
68
#define XML_STATUS_OK 1
69
#define XML_STATUS_ERROR 0
70
#endif
71
72
Otherwise, the #define hackery is quite ugly and would have been
73
dropped.
74
*/
75
enum XML_Status {
76
XML_STATUS_ERROR = 0,
77
# define XML_STATUS_ERROR XML_STATUS_ERROR
78
XML_STATUS_OK = 1,
79
# define XML_STATUS_OK XML_STATUS_OK
80
XML_STATUS_SUSPENDED = 2
81
# define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED
82
};
83
84
enum XML_Error {
85
XML_ERROR_NONE,
86
XML_ERROR_NO_MEMORY,
87
XML_ERROR_SYNTAX,
88
XML_ERROR_NO_ELEMENTS,
89
XML_ERROR_INVALID_TOKEN,
90
XML_ERROR_UNCLOSED_TOKEN,
91
XML_ERROR_PARTIAL_CHAR,
92
XML_ERROR_TAG_MISMATCH,
93
XML_ERROR_DUPLICATE_ATTRIBUTE,
94
XML_ERROR_JUNK_AFTER_DOC_ELEMENT,
95
XML_ERROR_PARAM_ENTITY_REF,
96
XML_ERROR_UNDEFINED_ENTITY,
97
XML_ERROR_RECURSIVE_ENTITY_REF,
98
XML_ERROR_ASYNC_ENTITY,
99
XML_ERROR_BAD_CHAR_REF,
100
XML_ERROR_BINARY_ENTITY_REF,
101
XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
102
XML_ERROR_MISPLACED_XML_PI,
103
XML_ERROR_UNKNOWN_ENCODING,
104
XML_ERROR_INCORRECT_ENCODING,
105
XML_ERROR_UNCLOSED_CDATA_SECTION,
106
XML_ERROR_EXTERNAL_ENTITY_HANDLING,
107
XML_ERROR_NOT_STANDALONE,
108
XML_ERROR_UNEXPECTED_STATE,
109
XML_ERROR_ENTITY_DECLARED_IN_PE,
110
XML_ERROR_FEATURE_REQUIRES_XML_DTD,
111
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING,
112
/* Added in 1.95.7. */
113
XML_ERROR_UNBOUND_PREFIX,
114
/* Added in 1.95.8. */
115
XML_ERROR_UNDECLARING_PREFIX,
116
XML_ERROR_INCOMPLETE_PE,
117
XML_ERROR_XML_DECL,
118
XML_ERROR_TEXT_DECL,
119
XML_ERROR_PUBLICID,
120
XML_ERROR_SUSPENDED,
121
XML_ERROR_NOT_SUSPENDED,
122
XML_ERROR_ABORTED,
123
XML_ERROR_FINISHED,
124
XML_ERROR_SUSPEND_PE,
125
/* Added in 2.0. */
126
XML_ERROR_RESERVED_PREFIX_XML,
127
XML_ERROR_RESERVED_PREFIX_XMLNS,
128
XML_ERROR_RESERVED_NAMESPACE_URI,
129
/* Added in 2.2.1. */
130
XML_ERROR_INVALID_ARGUMENT,
131
/* Added in 2.3.0. */
132
XML_ERROR_NO_BUFFER,
133
/* Added in 2.4.0. */
134
XML_ERROR_AMPLIFICATION_LIMIT_BREACH,
135
/* Added in 2.6.4. */
136
XML_ERROR_NOT_STARTED,
137
};
138
139
enum XML_Content_Type {
140
XML_CTYPE_EMPTY = 1,
141
XML_CTYPE_ANY,
142
XML_CTYPE_MIXED,
143
XML_CTYPE_NAME,
144
XML_CTYPE_CHOICE,
145
XML_CTYPE_SEQ
146
};
147
148
enum XML_Content_Quant {
149
XML_CQUANT_NONE,
150
XML_CQUANT_OPT,
151
XML_CQUANT_REP,
152
XML_CQUANT_PLUS
153
};
154
155
/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be
156
XML_CQUANT_NONE, and the other fields will be zero or NULL.
157
If type == XML_CTYPE_MIXED, then quant will be NONE or REP and
158
numchildren will contain number of elements that may be mixed in
159
and children point to an array of XML_Content cells that will be
160
all of XML_CTYPE_NAME type with no quantification.
161
162
If type == XML_CTYPE_NAME, then the name points to the name, and
163
the numchildren field will be zero and children will be NULL. The
164
quant fields indicates any quantifiers placed on the name.
165
166
CHOICE and SEQ will have name NULL, the number of children in
167
numchildren and children will point, recursively, to an array
168
of XML_Content cells.
169
170
The EMPTY, ANY, and MIXED types will only occur at top level.
171
*/
172
173
typedef struct XML_cp XML_Content;
174
175
struct XML_cp {
176
enum XML_Content_Type type;
177
enum XML_Content_Quant quant;
178
XML_Char *name;
179
unsigned int numchildren;
180
XML_Content *children;
181
};
182
183
/* This is called for an element declaration. See above for
184
description of the model argument. It's the user code's responsibility
185
to free model when finished with it. See XML_FreeContentModel.
186
There is no need to free the model from the handler, it can be kept
187
around and freed at a later stage.
188
*/
189
typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData,
190
const XML_Char *name,
191
XML_Content *model);
192
193
XMLPARSEAPI(void)
194
XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl);
195
196
/* The Attlist declaration handler is called for *each* attribute. So
197
a single Attlist declaration with multiple attributes declared will
198
generate multiple calls to this handler. The "default" parameter
199
may be NULL in the case of the "#IMPLIED" or "#REQUIRED"
200
keyword. The "isrequired" parameter will be true and the default
201
value will be NULL in the case of "#REQUIRED". If "isrequired" is
202
true and default is non-NULL, then this is a "#FIXED" default.
203
*/
204
typedef void(XMLCALL *XML_AttlistDeclHandler)(
205
void *userData, const XML_Char *elname, const XML_Char *attname,
206
const XML_Char *att_type, const XML_Char *dflt, int isrequired);
207
208
XMLPARSEAPI(void)
209
XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl);
210
211
/* The XML declaration handler is called for *both* XML declarations
212
and text declarations. The way to distinguish is that the version
213
parameter will be NULL for text declarations. The encoding
214
parameter may be NULL for XML declarations. The standalone
215
parameter will be -1, 0, or 1 indicating respectively that there
216
was no standalone parameter in the declaration, that it was given
217
as no, or that it was given as yes.
218
*/
219
typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData,
220
const XML_Char *version,
221
const XML_Char *encoding,
222
int standalone);
223
224
XMLPARSEAPI(void)
225
XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl);
226
227
typedef struct {
228
void *(*malloc_fcn)(size_t size);
229
void *(*realloc_fcn)(void *ptr, size_t size);
230
void (*free_fcn)(void *ptr);
231
} XML_Memory_Handling_Suite;
232
233
/* Constructs a new parser; encoding is the encoding specified by the
234
external protocol or NULL if there is none specified.
235
*/
236
XMLPARSEAPI(XML_Parser)
237
XML_ParserCreate(const XML_Char *encoding);
238
239
/* Constructs a new parser and namespace processor. Element type
240
names and attribute names that belong to a namespace will be
241
expanded; unprefixed attribute names are never expanded; unprefixed
242
element type names are expanded only if there is a default
243
namespace. The expanded name is the concatenation of the namespace
244
URI, the namespace separator character, and the local part of the
245
name. If the namespace separator is '\0' then the namespace URI
246
and the local part will be concatenated without any separator.
247
It is a programming error to use the separator '\0' with namespace
248
triplets (see XML_SetReturnNSTriplet).
249
If a namespace separator is chosen that can be part of a URI or
250
part of an XML name, splitting an expanded name back into its
251
1, 2 or 3 original parts on application level in the element handler
252
may end up vulnerable, so these are advised against; sane choices for
253
a namespace separator are e.g. '\n' (line feed) and '|' (pipe).
254
255
Note that Expat does not validate namespace URIs (beyond encoding)
256
against RFC 3986 today (and is not required to do so with regard to
257
the XML 1.0 namespaces specification) but it may start doing that
258
in future releases. Before that, an application using Expat must
259
be ready to receive namespace URIs containing non-URI characters.
260
*/
261
XMLPARSEAPI(XML_Parser)
262
XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);
263
264
/* Constructs a new parser using the memory management suite referred to
265
by memsuite. If memsuite is NULL, then use the standard library memory
266
suite. If namespaceSeparator is non-NULL it creates a parser with
267
namespace processing as described above. The character pointed at
268
will serve as the namespace separator.
269
270
All further memory operations used for the created parser will come from
271
the given suite.
272
*/
273
XMLPARSEAPI(XML_Parser)
274
XML_ParserCreate_MM(const XML_Char *encoding,
275
const XML_Memory_Handling_Suite *memsuite,
276
const XML_Char *namespaceSeparator);
277
278
/* Prepare a parser object to be reused. This is particularly
279
valuable when memory allocation overhead is disproportionately high,
280
such as when a large number of small documents need to be parsed.
281
All handlers are cleared from the parser, except for the
282
unknownEncodingHandler. The parser's external state is re-initialized
283
except for the values of ns and ns_triplets.
284
285
Added in Expat 1.95.3.
286
*/
287
XMLPARSEAPI(XML_Bool)
288
XML_ParserReset(XML_Parser parser, const XML_Char *encoding);
289
290
/* atts is array of name/value pairs, terminated by 0;
291
names and values are 0 terminated.
292
*/
293
typedef void(XMLCALL *XML_StartElementHandler)(void *userData,
294
const XML_Char *name,
295
const XML_Char **atts);
296
297
typedef void(XMLCALL *XML_EndElementHandler)(void *userData,
298
const XML_Char *name);
299
300
/* s is not 0 terminated. */
301
typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData,
302
const XML_Char *s, int len);
303
304
/* target and data are 0 terminated */
305
typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData,
306
const XML_Char *target,
307
const XML_Char *data);
308
309
/* data is 0 terminated */
310
typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data);
311
312
typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData);
313
typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData);
314
315
/* This is called for any characters in the XML document for which
316
there is no applicable handler. This includes both characters that
317
are part of markup which is of a kind that is not reported
318
(comments, markup declarations), or characters that are part of a
319
construct which could be reported but for which no handler has been
320
supplied. The characters are passed exactly as they were in the XML
321
document except that they will be encoded in UTF-8 or UTF-16.
322
Line boundaries are not normalized. Note that a byte order mark
323
character is not passed to the default handler. There are no
324
guarantees about how characters are divided between calls to the
325
default handler: for example, a comment might be split between
326
multiple calls.
327
*/
328
typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s,
329
int len);
330
331
/* This is called for the start of the DOCTYPE declaration, before
332
any DTD or internal subset is parsed.
333
*/
334
typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData,
335
const XML_Char *doctypeName,
336
const XML_Char *sysid,
337
const XML_Char *pubid,
338
int has_internal_subset);
339
340
/* This is called for the end of the DOCTYPE declaration when the
341
closing > is encountered, but after processing any external
342
subset.
343
*/
344
typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData);
345
346
/* This is called for entity declarations. The is_parameter_entity
347
argument will be non-zero if the entity is a parameter entity, zero
348
otherwise.
349
350
For internal entities (<!ENTITY foo "bar">), value will
351
be non-NULL and systemId, publicID, and notationName will be NULL.
352
The value string is NOT null-terminated; the length is provided in
353
the value_length argument. Since it is legal to have zero-length
354
values, do not use this argument to test for internal entities.
355
356
For external entities, value will be NULL and systemId will be
357
non-NULL. The publicId argument will be NULL unless a public
358
identifier was provided. The notationName argument will have a
359
non-NULL value only for unparsed entity declarations.
360
361
Note that is_parameter_entity can't be changed to XML_Bool, since
362
that would break binary compatibility.
363
*/
364
typedef void(XMLCALL *XML_EntityDeclHandler)(
365
void *userData, const XML_Char *entityName, int is_parameter_entity,
366
const XML_Char *value, int value_length, const XML_Char *base,
367
const XML_Char *systemId, const XML_Char *publicId,
368
const XML_Char *notationName);
369
370
XMLPARSEAPI(void)
371
XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler);
372
373
/* OBSOLETE -- OBSOLETE -- OBSOLETE
374
This handler has been superseded by the EntityDeclHandler above.
375
It is provided here for backward compatibility.
376
377
This is called for a declaration of an unparsed (NDATA) entity.
378
The base argument is whatever was set by XML_SetBase. The
379
entityName, systemId and notationName arguments will never be
380
NULL. The other arguments may be.
381
*/
382
typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)(
383
void *userData, const XML_Char *entityName, const XML_Char *base,
384
const XML_Char *systemId, const XML_Char *publicId,
385
const XML_Char *notationName);
386
387
/* This is called for a declaration of notation. The base argument is
388
whatever was set by XML_SetBase. The notationName will never be
389
NULL. The other arguments can be.
390
*/
391
typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData,
392
const XML_Char *notationName,
393
const XML_Char *base,
394
const XML_Char *systemId,
395
const XML_Char *publicId);
396
397
/* When namespace processing is enabled, these are called once for
398
each namespace declaration. The call to the start and end element
399
handlers occur between the calls to the start and end namespace
400
declaration handlers. For an xmlns attribute, prefix will be
401
NULL. For an xmlns="" attribute, uri will be NULL.
402
*/
403
typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData,
404
const XML_Char *prefix,
405
const XML_Char *uri);
406
407
typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData,
408
const XML_Char *prefix);
409
410
/* This is called if the document is not standalone, that is, it has an
411
external subset or a reference to a parameter entity, but does not
412
have standalone="yes". If this handler returns XML_STATUS_ERROR,
413
then processing will not continue, and the parser will return a
414
XML_ERROR_NOT_STANDALONE error.
415
If parameter entity parsing is enabled, then in addition to the
416
conditions above this handler will only be called if the referenced
417
entity was actually read.
418
*/
419
typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData);
420
421
/* This is called for a reference to an external parsed general
422
entity. The referenced entity is not automatically parsed. The
423
application can parse it immediately or later using
424
XML_ExternalEntityParserCreate.
425
426
The parser argument is the parser parsing the entity containing the
427
reference; it can be passed as the parser argument to
428
XML_ExternalEntityParserCreate. The systemId argument is the
429
system identifier as specified in the entity declaration; it will
430
not be NULL.
431
432
The base argument is the system identifier that should be used as
433
the base for resolving systemId if systemId was relative; this is
434
set by XML_SetBase; it may be NULL.
435
436
The publicId argument is the public identifier as specified in the
437
entity declaration, or NULL if none was specified; the whitespace
438
in the public identifier will have been normalized as required by
439
the XML spec.
440
441
The context argument specifies the parsing context in the format
442
expected by the context argument to XML_ExternalEntityParserCreate;
443
context is valid only until the handler returns, so if the
444
referenced entity is to be parsed later, it must be copied.
445
context is NULL only when the entity is a parameter entity.
446
447
The handler should return XML_STATUS_ERROR if processing should not
448
continue because of a fatal error in the handling of the external
449
entity. In this case the calling parser will return an
450
XML_ERROR_EXTERNAL_ENTITY_HANDLING error.
451
452
Note that unlike other handlers the first argument is the parser,
453
not userData.
454
*/
455
typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser,
456
const XML_Char *context,
457
const XML_Char *base,
458
const XML_Char *systemId,
459
const XML_Char *publicId);
460
461
/* This is called in two situations:
462
1) An entity reference is encountered for which no declaration
463
has been read *and* this is not an error.
464
2) An internal entity reference is read, but not expanded, because
465
XML_SetDefaultHandler has been called.
466
Note: skipped parameter entities in declarations and skipped general
467
entities in attribute values cannot be reported, because
468
the event would be out of sync with the reporting of the
469
declarations or attribute values
470
*/
471
typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData,
472
const XML_Char *entityName,
473
int is_parameter_entity);
474
475
/* This structure is filled in by the XML_UnknownEncodingHandler to
476
provide information to the parser about encodings that are unknown
477
to the parser.
478
479
The map[b] member gives information about byte sequences whose
480
first byte is b.
481
482
If map[b] is c where c is >= 0, then b by itself encodes the
483
Unicode scalar value c.
484
485
If map[b] is -1, then the byte sequence is malformed.
486
487
If map[b] is -n, where n >= 2, then b is the first byte of an
488
n-byte sequence that encodes a single Unicode scalar value.
489
490
The data member will be passed as the first argument to the convert
491
function.
492
493
The convert function is used to convert multibyte sequences; s will
494
point to a n-byte sequence where map[(unsigned char)*s] == -n. The
495
convert function must return the Unicode scalar value represented
496
by this byte sequence or -1 if the byte sequence is malformed.
497
498
The convert function may be NULL if the encoding is a single-byte
499
encoding, that is if map[b] >= -1 for all bytes b.
500
501
When the parser is finished with the encoding, then if release is
502
not NULL, it will call release passing it the data member; once
503
release has been called, the convert function will not be called
504
again.
505
506
Expat places certain restrictions on the encodings that are supported
507
using this mechanism.
508
509
1. Every ASCII character that can appear in a well-formed XML document,
510
other than the characters
511
512
$@\^`{}~
513
514
must be represented by a single byte, and that byte must be the
515
same byte that represents that character in ASCII.
516
517
2. No character may require more than 4 bytes to encode.
518
519
3. All characters encoded must have Unicode scalar values <=
520
0xFFFF, (i.e., characters that would be encoded by surrogates in
521
UTF-16 are not allowed). Note that this restriction doesn't
522
apply to the built-in support for UTF-8 and UTF-16.
523
524
4. No Unicode character may be encoded by more than one distinct
525
sequence of bytes.
526
*/
527
typedef struct {
528
int map[256];
529
void *data;
530
int(XMLCALL *convert)(void *data, const char *s);
531
void(XMLCALL *release)(void *data);
532
} XML_Encoding;
533
534
/* This is called for an encoding that is unknown to the parser.
535
536
The encodingHandlerData argument is that which was passed as the
537
second argument to XML_SetUnknownEncodingHandler.
538
539
The name argument gives the name of the encoding as specified in
540
the encoding declaration.
541
542
If the callback can provide information about the encoding, it must
543
fill in the XML_Encoding structure, and return XML_STATUS_OK.
544
Otherwise it must return XML_STATUS_ERROR.
545
546
If info does not describe a suitable encoding, then the parser will
547
return an XML_ERROR_UNKNOWN_ENCODING error.
548
*/
549
typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData,
550
const XML_Char *name,
551
XML_Encoding *info);
552
553
XMLPARSEAPI(void)
554
XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start,
555
XML_EndElementHandler end);
556
557
XMLPARSEAPI(void)
558
XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler);
559
560
XMLPARSEAPI(void)
561
XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler);
562
563
XMLPARSEAPI(void)
564
XML_SetCharacterDataHandler(XML_Parser parser,
565
XML_CharacterDataHandler handler);
566
567
XMLPARSEAPI(void)
568
XML_SetProcessingInstructionHandler(XML_Parser parser,
569
XML_ProcessingInstructionHandler handler);
570
XMLPARSEAPI(void)
571
XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler);
572
573
XMLPARSEAPI(void)
574
XML_SetCdataSectionHandler(XML_Parser parser,
575
XML_StartCdataSectionHandler start,
576
XML_EndCdataSectionHandler end);
577
578
XMLPARSEAPI(void)
579
XML_SetStartCdataSectionHandler(XML_Parser parser,
580
XML_StartCdataSectionHandler start);
581
582
XMLPARSEAPI(void)
583
XML_SetEndCdataSectionHandler(XML_Parser parser,
584
XML_EndCdataSectionHandler end);
585
586
/* This sets the default handler and also inhibits expansion of
587
internal entities. These entity references will be passed to the
588
default handler, or to the skipped entity handler, if one is set.
589
*/
590
XMLPARSEAPI(void)
591
XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler);
592
593
/* This sets the default handler but does not inhibit expansion of
594
internal entities. The entity reference will not be passed to the
595
default handler.
596
*/
597
XMLPARSEAPI(void)
598
XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler);
599
600
XMLPARSEAPI(void)
601
XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start,
602
XML_EndDoctypeDeclHandler end);
603
604
XMLPARSEAPI(void)
605
XML_SetStartDoctypeDeclHandler(XML_Parser parser,
606
XML_StartDoctypeDeclHandler start);
607
608
XMLPARSEAPI(void)
609
XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end);
610
611
XMLPARSEAPI(void)
612
XML_SetUnparsedEntityDeclHandler(XML_Parser parser,
613
XML_UnparsedEntityDeclHandler handler);
614
615
XMLPARSEAPI(void)
616
XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler);
617
618
XMLPARSEAPI(void)
619
XML_SetNamespaceDeclHandler(XML_Parser parser,
620
XML_StartNamespaceDeclHandler start,
621
XML_EndNamespaceDeclHandler end);
622
623
XMLPARSEAPI(void)
624
XML_SetStartNamespaceDeclHandler(XML_Parser parser,
625
XML_StartNamespaceDeclHandler start);
626
627
XMLPARSEAPI(void)
628
XML_SetEndNamespaceDeclHandler(XML_Parser parser,
629
XML_EndNamespaceDeclHandler end);
630
631
XMLPARSEAPI(void)
632
XML_SetNotStandaloneHandler(XML_Parser parser,
633
XML_NotStandaloneHandler handler);
634
635
XMLPARSEAPI(void)
636
XML_SetExternalEntityRefHandler(XML_Parser parser,
637
XML_ExternalEntityRefHandler handler);
638
639
/* If a non-NULL value for arg is specified here, then it will be
640
passed as the first argument to the external entity ref handler
641
instead of the parser object.
642
*/
643
XMLPARSEAPI(void)
644
XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg);
645
646
XMLPARSEAPI(void)
647
XML_SetSkippedEntityHandler(XML_Parser parser,
648
XML_SkippedEntityHandler handler);
649
650
XMLPARSEAPI(void)
651
XML_SetUnknownEncodingHandler(XML_Parser parser,
652
XML_UnknownEncodingHandler handler,
653
void *encodingHandlerData);
654
655
/* This can be called within a handler for a start element, end
656
element, processing instruction or character data. It causes the
657
corresponding markup to be passed to the default handler.
658
*/
659
XMLPARSEAPI(void)
660
XML_DefaultCurrent(XML_Parser parser);
661
662
/* If do_nst is non-zero, and namespace processing is in effect, and
663
a name has a prefix (i.e. an explicit namespace qualifier) then
664
that name is returned as a triplet in a single string separated by
665
the separator character specified when the parser was created: URI
666
+ sep + local_name + sep + prefix.
667
668
If do_nst is zero, then namespace information is returned in the
669
default manner (URI + sep + local_name) whether or not the name
670
has a prefix.
671
672
Note: Calling XML_SetReturnNSTriplet after XML_Parse or
673
XML_ParseBuffer has no effect.
674
*/
675
676
XMLPARSEAPI(void)
677
XML_SetReturnNSTriplet(XML_Parser parser, int do_nst);
678
679
/* This value is passed as the userData argument to callbacks. */
680
XMLPARSEAPI(void)
681
XML_SetUserData(XML_Parser parser, void *userData);
682
683
/* Returns the last value set by XML_SetUserData or NULL. */
684
# define XML_GetUserData(parser) (*(void **)(parser))
685
686
/* This is equivalent to supplying an encoding argument to
687
XML_ParserCreate. On success XML_SetEncoding returns non-zero,
688
zero otherwise.
689
Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer
690
has no effect and returns XML_STATUS_ERROR.
691
*/
692
XMLPARSEAPI(enum XML_Status)
693
XML_SetEncoding(XML_Parser parser, const XML_Char *encoding);
694
695
/* If this function is called, then the parser will be passed as the
696
first argument to callbacks instead of userData. The userData will
697
still be accessible using XML_GetUserData.
698
*/
699
XMLPARSEAPI(void)
700
XML_UseParserAsHandlerArg(XML_Parser parser);
701
702
/* If useDTD == XML_TRUE is passed to this function, then the parser
703
will assume that there is an external subset, even if none is
704
specified in the document. In such a case the parser will call the
705
externalEntityRefHandler with a value of NULL for the systemId
706
argument (the publicId and context arguments will be NULL as well).
707
Note: For the purpose of checking WFC: Entity Declared, passing
708
useDTD == XML_TRUE will make the parser behave as if the document
709
had a DTD with an external subset.
710
Note: If this function is called, then this must be done before
711
the first call to XML_Parse or XML_ParseBuffer, since it will
712
have no effect after that. Returns
713
XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING.
714
Note: If the document does not have a DOCTYPE declaration at all,
715
then startDoctypeDeclHandler and endDoctypeDeclHandler will not
716
be called, despite an external subset being parsed.
717
Note: If XML_DTD is not defined when Expat is compiled, returns
718
XML_ERROR_FEATURE_REQUIRES_XML_DTD.
719
Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT.
720
*/
721
XMLPARSEAPI(enum XML_Error)
722
XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD);
723
724
/* Sets the base to be used for resolving relative URIs in system
725
identifiers in declarations. Resolving relative identifiers is
726
left to the application: this value will be passed through as the
727
base argument to the XML_ExternalEntityRefHandler,
728
XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base
729
argument will be copied. Returns XML_STATUS_ERROR if out of memory,
730
XML_STATUS_OK otherwise.
731
*/
732
XMLPARSEAPI(enum XML_Status)
733
XML_SetBase(XML_Parser parser, const XML_Char *base);
734
735
XMLPARSEAPI(const XML_Char *)
736
XML_GetBase(XML_Parser parser);
737
738
/* Returns the number of the attribute/value pairs passed in last call
739
to the XML_StartElementHandler that were specified in the start-tag
740
rather than defaulted. Each attribute/value pair counts as 2; thus
741
this corresponds to an index into the atts array passed to the
742
XML_StartElementHandler. Returns -1 if parser == NULL.
743
*/
744
XMLPARSEAPI(int)
745
XML_GetSpecifiedAttributeCount(XML_Parser parser);
746
747
/* Returns the index of the ID attribute passed in the last call to
748
XML_StartElementHandler, or -1 if there is no ID attribute or
749
parser == NULL. Each attribute/value pair counts as 2; thus this
750
corresponds to an index into the atts array passed to the
751
XML_StartElementHandler.
752
*/
753
XMLPARSEAPI(int)
754
XML_GetIdAttributeIndex(XML_Parser parser);
755
756
# ifdef XML_ATTR_INFO
757
/* Source file byte offsets for the start and end of attribute names and values.
758
The value indices are exclusive of surrounding quotes; thus in a UTF-8 source
759
file an attribute value of "blah" will yield:
760
info->valueEnd - info->valueStart = 4 bytes.
761
*/
762
typedef struct {
763
XML_Index nameStart; /* Offset to beginning of the attribute name. */
764
XML_Index nameEnd; /* Offset after the attribute name's last byte. */
765
XML_Index valueStart; /* Offset to beginning of the attribute value. */
766
XML_Index valueEnd; /* Offset after the attribute value's last byte. */
767
} XML_AttrInfo;
768
769
/* Returns an array of XML_AttrInfo structures for the attribute/value pairs
770
passed in last call to the XML_StartElementHandler that were specified
771
in the start-tag rather than defaulted. Each attribute/value pair counts
772
as 1; thus the number of entries in the array is
773
XML_GetSpecifiedAttributeCount(parser) / 2.
774
*/
775
XMLPARSEAPI(const XML_AttrInfo *)
776
XML_GetAttributeInfo(XML_Parser parser);
777
# endif
778
779
/* Parses some input. Returns XML_STATUS_ERROR if a fatal error is
780
detected. The last call to XML_Parse must have isFinal true; len
781
may be zero for this call (or any other).
782
783
Though the return values for these functions has always been
784
described as a Boolean value, the implementation, at least for the
785
1.95.x series, has always returned exactly one of the XML_Status
786
values.
787
*/
788
XMLPARSEAPI(enum XML_Status)
789
XML_Parse(XML_Parser parser, const char *s, int len, int isFinal);
790
791
XMLPARSEAPI(void *)
792
XML_GetBuffer(XML_Parser parser, int len);
793
794
XMLPARSEAPI(enum XML_Status)
795
XML_ParseBuffer(XML_Parser parser, int len, int isFinal);
796
797
/* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return.
798
Must be called from within a call-back handler, except when aborting
799
(resumable = 0) an already suspended parser. Some call-backs may
800
still follow because they would otherwise get lost. Examples:
801
- endElementHandler() for empty elements when stopped in
802
startElementHandler(),
803
- endNameSpaceDeclHandler() when stopped in endElementHandler(),
804
and possibly others.
805
806
Can be called from most handlers, including DTD related call-backs,
807
except when parsing an external parameter entity and resumable != 0.
808
Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise.
809
Possible error codes:
810
- XML_ERROR_SUSPENDED: when suspending an already suspended parser.
811
- XML_ERROR_FINISHED: when the parser has already finished.
812
- XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE.
813
814
When resumable != 0 (true) then parsing is suspended, that is,
815
XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED.
816
Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer()
817
return XML_STATUS_ERROR with error code XML_ERROR_ABORTED.
818
819
*Note*:
820
This will be applied to the current parser instance only, that is, if
821
there is a parent parser then it will continue parsing when the
822
externalEntityRefHandler() returns. It is up to the implementation of
823
the externalEntityRefHandler() to call XML_StopParser() on the parent
824
parser (recursively), if one wants to stop parsing altogether.
825
826
When suspended, parsing can be resumed by calling XML_ResumeParser().
827
*/
828
XMLPARSEAPI(enum XML_Status)
829
XML_StopParser(XML_Parser parser, XML_Bool resumable);
830
831
/* Resumes parsing after it has been suspended with XML_StopParser().
832
Must not be called from within a handler call-back. Returns same
833
status codes as XML_Parse() or XML_ParseBuffer().
834
Additional error code XML_ERROR_NOT_SUSPENDED possible.
835
836
*Note*:
837
This must be called on the most deeply nested child parser instance
838
first, and on its parent parser only after the child parser has finished,
839
to be applied recursively until the document entity's parser is restarted.
840
That is, the parent parser will not resume by itself and it is up to the
841
application to call XML_ResumeParser() on it at the appropriate moment.
842
*/
843
XMLPARSEAPI(enum XML_Status)
844
XML_ResumeParser(XML_Parser parser);
845
846
enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED };
847
848
typedef struct {
849
enum XML_Parsing parsing;
850
XML_Bool finalBuffer;
851
} XML_ParsingStatus;
852
853
/* Returns status of parser with respect to being initialized, parsing,
854
finished, or suspended and processing the final buffer.
855
XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus,
856
XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED
857
*/
858
XMLPARSEAPI(void)
859
XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status);
860
861
/* Creates an XML_Parser object that can parse an external general
862
entity; context is a '\0'-terminated string specifying the parse
863
context; encoding is a '\0'-terminated string giving the name of
864
the externally specified encoding, or NULL if there is no
865
externally specified encoding. The context string consists of a
866
sequence of tokens separated by formfeeds (\f); a token consisting
867
of a name specifies that the general entity of the name is open; a
868
token of the form prefix=uri specifies the namespace for a
869
particular prefix; a token of the form =uri specifies the default
870
namespace. This can be called at any point after the first call to
871
an ExternalEntityRefHandler so longer as the parser has not yet
872
been freed. The new parser is completely independent and may
873
safely be used in a separate thread. The handlers and userData are
874
initialized from the parser argument. Returns NULL if out of memory.
875
Otherwise returns a new XML_Parser object.
876
*/
877
XMLPARSEAPI(XML_Parser)
878
XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context,
879
const XML_Char *encoding);
880
881
enum XML_ParamEntityParsing {
882
XML_PARAM_ENTITY_PARSING_NEVER,
883
XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE,
884
XML_PARAM_ENTITY_PARSING_ALWAYS
885
};
886
887
/* Controls parsing of parameter entities (including the external DTD
888
subset). If parsing of parameter entities is enabled, then
889
references to external parameter entities (including the external
890
DTD subset) will be passed to the handler set with
891
XML_SetExternalEntityRefHandler. The context passed will be 0.
892
893
Unlike external general entities, external parameter entities can
894
only be parsed synchronously. If the external parameter entity is
895
to be parsed, it must be parsed during the call to the external
896
entity ref handler: the complete sequence of
897
XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and
898
XML_ParserFree calls must be made during this call. After
899
XML_ExternalEntityParserCreate has been called to create the parser
900
for the external parameter entity (context must be 0 for this
901
call), it is illegal to make any calls on the old parser until
902
XML_ParserFree has been called on the newly created parser.
903
If the library has been compiled without support for parameter
904
entity parsing (ie without XML_DTD being defined), then
905
XML_SetParamEntityParsing will return 0 if parsing of parameter
906
entities is requested; otherwise it will return non-zero.
907
Note: If XML_SetParamEntityParsing is called after XML_Parse or
908
XML_ParseBuffer, then it has no effect and will always return 0.
909
Note: If parser == NULL, the function will do nothing and return 0.
910
*/
911
XMLPARSEAPI(int)
912
XML_SetParamEntityParsing(XML_Parser parser,
913
enum XML_ParamEntityParsing parsing);
914
915
/* Sets the hash salt to use for internal hash calculations.
916
Helps in preventing DoS attacks based on predicting hash
917
function behavior. This must be called before parsing is started.
918
Returns 1 if successful, 0 when called after parsing has started.
919
Note: If parser == NULL, the function will do nothing and return 0.
920
*/
921
XMLPARSEAPI(int)
922
XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt);
923
924
/* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then
925
XML_GetErrorCode returns information about the error.
926
*/
927
XMLPARSEAPI(enum XML_Error)
928
XML_GetErrorCode(XML_Parser parser);
929
930
/* These functions return information about the current parse
931
location. They may be called from any callback called to report
932
some parse event; in this case the location is the location of the
933
first of the sequence of characters that generated the event. When
934
called from callbacks generated by declarations in the document
935
prologue, the location identified isn't as neatly defined, but will
936
be within the relevant markup. When called outside of the callback
937
functions, the position indicated will be just past the last parse
938
event (regardless of whether there was an associated callback).
939
940
They may also be called after returning from a call to XML_Parse
941
or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then
942
the location is the location of the character at which the error
943
was detected; otherwise the location is the location of the last
944
parse event, as described above.
945
946
Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber
947
return 0 to indicate an error.
948
Note: XML_GetCurrentByteIndex returns -1 to indicate an error.
949
*/
950
XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser);
951
XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser);
952
XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser);
953
954
/* Return the number of bytes in the current event.
955
Returns 0 if the event is in an internal entity.
956
*/
957
XMLPARSEAPI(int)
958
XML_GetCurrentByteCount(XML_Parser parser);
959
960
/* If XML_CONTEXT_BYTES is >=1, returns the input buffer, sets
961
the integer pointed to by offset to the offset within this buffer
962
of the current parse position, and sets the integer pointed to by size
963
to the size of this buffer (the number of input bytes). Otherwise
964
returns a NULL pointer. Also returns a NULL pointer if a parse isn't
965
active.
966
967
NOTE: The character pointer returned should not be used outside
968
the handler that makes the call.
969
*/
970
XMLPARSEAPI(const char *)
971
XML_GetInputContext(XML_Parser parser, int *offset, int *size);
972
973
/* For backwards compatibility with previous versions. */
974
# define XML_GetErrorLineNumber XML_GetCurrentLineNumber
975
# define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber
976
# define XML_GetErrorByteIndex XML_GetCurrentByteIndex
977
978
/* Frees the content model passed to the element declaration handler */
979
XMLPARSEAPI(void)
980
XML_FreeContentModel(XML_Parser parser, XML_Content *model);
981
982
/* Exposing the memory handling functions used in Expat */
983
XMLPARSEAPI(void *)
984
XML_ATTR_MALLOC
985
XML_ATTR_ALLOC_SIZE(2)
986
XML_MemMalloc(XML_Parser parser, size_t size);
987
988
XMLPARSEAPI(void *)
989
XML_ATTR_ALLOC_SIZE(3)
990
XML_MemRealloc(XML_Parser parser, void *ptr, size_t size);
991
992
XMLPARSEAPI(void)
993
XML_MemFree(XML_Parser parser, void *ptr);
994
995
/* Frees memory used by the parser. */
996
XMLPARSEAPI(void)
997
XML_ParserFree(XML_Parser parser);
998
999
/* Returns a string describing the error. */
1000
XMLPARSEAPI(const XML_LChar *)
1001
XML_ErrorString(enum XML_Error code);
1002
1003
/* Return a string containing the version number of this expat */
1004
XMLPARSEAPI(const XML_LChar *)
1005
XML_ExpatVersion(void);
1006
1007
typedef struct {
1008
int major;
1009
int minor;
1010
int micro;
1011
} XML_Expat_Version;
1012
1013
/* Return an XML_Expat_Version structure containing numeric version
1014
number information for this version of expat.
1015
*/
1016
XMLPARSEAPI(XML_Expat_Version)
1017
XML_ExpatVersionInfo(void);
1018
1019
/* Added in Expat 1.95.5. */
1020
enum XML_FeatureEnum {
1021
XML_FEATURE_END = 0,
1022
XML_FEATURE_UNICODE,
1023
XML_FEATURE_UNICODE_WCHAR_T,
1024
XML_FEATURE_DTD,
1025
XML_FEATURE_CONTEXT_BYTES,
1026
XML_FEATURE_MIN_SIZE,
1027
XML_FEATURE_SIZEOF_XML_CHAR,
1028
XML_FEATURE_SIZEOF_XML_LCHAR,
1029
XML_FEATURE_NS,
1030
XML_FEATURE_LARGE_SIZE,
1031
XML_FEATURE_ATTR_INFO,
1032
/* Added in Expat 2.4.0. */
1033
XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT,
1034
XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT,
1035
/* Added in Expat 2.6.0. */
1036
XML_FEATURE_GE,
1037
/* Added in Expat 2.7.2. */
1038
XML_FEATURE_ALLOC_TRACKER_MAXIMUM_AMPLIFICATION_DEFAULT,
1039
XML_FEATURE_ALLOC_TRACKER_ACTIVATION_THRESHOLD_DEFAULT,
1040
/* Additional features must be added to the end of this enum. */
1041
};
1042
1043
typedef struct {
1044
enum XML_FeatureEnum feature;
1045
const XML_LChar *name;
1046
long int value;
1047
} XML_Feature;
1048
1049
XMLPARSEAPI(const XML_Feature *)
1050
XML_GetFeatureList(void);
1051
1052
# if defined(XML_DTD) || (defined(XML_GE) && XML_GE == 1)
1053
/* Added in Expat 2.4.0 for XML_DTD defined and
1054
* added in Expat 2.6.0 for XML_GE == 1. */
1055
XMLPARSEAPI(XML_Bool)
1056
XML_SetBillionLaughsAttackProtectionMaximumAmplification(
1057
XML_Parser parser, float maximumAmplificationFactor);
1058
1059
/* Added in Expat 2.4.0 for XML_DTD defined and
1060
* added in Expat 2.6.0 for XML_GE == 1. */
1061
XMLPARSEAPI(XML_Bool)
1062
XML_SetBillionLaughsAttackProtectionActivationThreshold(
1063
XML_Parser parser, unsigned long long activationThresholdBytes);
1064
1065
/* Added in Expat 2.7.2. */
1066
XMLPARSEAPI(XML_Bool)
1067
XML_SetAllocTrackerMaximumAmplification(XML_Parser parser,
1068
float maximumAmplificationFactor);
1069
1070
/* Added in Expat 2.7.2. */
1071
XMLPARSEAPI(XML_Bool)
1072
XML_SetAllocTrackerActivationThreshold(
1073
XML_Parser parser, unsigned long long activationThresholdBytes);
1074
# endif
1075
1076
/* Added in Expat 2.6.0. */
1077
XMLPARSEAPI(XML_Bool)
1078
XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled);
1079
1080
/* Expat follows the semantic versioning convention.
1081
See https://semver.org
1082
*/
1083
# define XML_MAJOR_VERSION 2
1084
# define XML_MINOR_VERSION 7
1085
# define XML_MICRO_VERSION 3
1086
1087
# ifdef __cplusplus
1088
}
1089
# endif
1090
1091
#endif /* not Expat_INCLUDED */
1092
1093