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 <coopercc@users.sourceforge.net> 11 Copyright (c) 2000-2005 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> 12 Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> 13 Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> 14 Copyright (c) 2016-2024 Sebastian Pipping <sebastian@pipping.org> 15 Copyright (c) 2016 Cristian Rodríguez <crrodriguez@opensuse.org> 16 Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> 17 Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> 18 Copyright (c) 2022 Thijs Schreijer <thijs@thijsschreijer.nl> 19 Copyright (c) 2023 Hanno Böck <hanno@gentoo.org> 20 Copyright (c) 2023 Sony Corporation / Snild Dolkow <snild@sony.com> 21 Copyright (c) 2024 Taichi Haradaguchi <20001722@ymail.ne.jp> 22 Licensed under the MIT license: 23 24 Permission is hereby granted, free of charge, to any person obtaining 25 a copy of this software and associated documentation files (the 26 "Software"), to deal in the Software without restriction, including 27 without limitation the rights to use, copy, modify, merge, publish, 28 distribute, sublicense, and/or sell copies of the Software, and to permit 29 persons to whom the Software is furnished to do so, subject to the 30 following conditions: 31 32 The above copyright notice and this permission notice shall be included 33 in all copies or substantial portions of the Software. 34 35 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 36 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 37 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN 38 NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 39 DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 40 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 41 USE OR OTHER DEALINGS IN THE SOFTWARE. 42 */ 43 44 #ifndef Expat_INCLUDED 45 #define Expat_INCLUDED 1 46 47 #include <stdlib.h> 48 #include "expat_external.h" 49 50 #ifdef __cplusplus 51 extern "C" { 52 #endif 53 54 struct XML_ParserStruct; 55 typedef struct XML_ParserStruct *XML_Parser; 56 57 typedef unsigned char XML_Bool; 58 #define XML_TRUE ((XML_Bool)1) 59 #define XML_FALSE ((XML_Bool)0) 60 61 /* The XML_Status enum gives the possible return values for several 62 API functions. The preprocessor #defines are included so this 63 stanza can be added to code that still needs to support older 64 versions of Expat 1.95.x: 65 66 #ifndef XML_STATUS_OK 67 #define XML_STATUS_OK 1 68 #define XML_STATUS_ERROR 0 69 #endif 70 71 Otherwise, the #define hackery is quite ugly and would have been 72 dropped. 73 */ 74 enum XML_Status { 75 XML_STATUS_ERROR = 0, 76 #define XML_STATUS_ERROR XML_STATUS_ERROR 77 XML_STATUS_OK = 1, 78 #define XML_STATUS_OK XML_STATUS_OK 79 XML_STATUS_SUSPENDED = 2 80 #define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED 81 }; 82 83 enum XML_Error { 84 XML_ERROR_NONE, 85 XML_ERROR_NO_MEMORY, 86 XML_ERROR_SYNTAX, 87 XML_ERROR_NO_ELEMENTS, 88 XML_ERROR_INVALID_TOKEN, 89 XML_ERROR_UNCLOSED_TOKEN, 90 XML_ERROR_PARTIAL_CHAR, 91 XML_ERROR_TAG_MISMATCH, 92 XML_ERROR_DUPLICATE_ATTRIBUTE, 93 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 94 XML_ERROR_PARAM_ENTITY_REF, 95 XML_ERROR_UNDEFINED_ENTITY, 96 XML_ERROR_RECURSIVE_ENTITY_REF, 97 XML_ERROR_ASYNC_ENTITY, 98 XML_ERROR_BAD_CHAR_REF, 99 XML_ERROR_BINARY_ENTITY_REF, 100 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 101 XML_ERROR_MISPLACED_XML_PI, 102 XML_ERROR_UNKNOWN_ENCODING, 103 XML_ERROR_INCORRECT_ENCODING, 104 XML_ERROR_UNCLOSED_CDATA_SECTION, 105 XML_ERROR_EXTERNAL_ENTITY_HANDLING, 106 XML_ERROR_NOT_STANDALONE, 107 XML_ERROR_UNEXPECTED_STATE, 108 XML_ERROR_ENTITY_DECLARED_IN_PE, 109 XML_ERROR_FEATURE_REQUIRES_XML_DTD, 110 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 111 /* Added in 1.95.7. */ 112 XML_ERROR_UNBOUND_PREFIX, 113 /* Added in 1.95.8. */ 114 XML_ERROR_UNDECLARING_PREFIX, 115 XML_ERROR_INCOMPLETE_PE, 116 XML_ERROR_XML_DECL, 117 XML_ERROR_TEXT_DECL, 118 XML_ERROR_PUBLICID, 119 XML_ERROR_SUSPENDED, 120 XML_ERROR_NOT_SUSPENDED, 121 XML_ERROR_ABORTED, 122 XML_ERROR_FINISHED, 123 XML_ERROR_SUSPEND_PE, 124 /* Added in 2.0. */ 125 XML_ERROR_RESERVED_PREFIX_XML, 126 XML_ERROR_RESERVED_PREFIX_XMLNS, 127 XML_ERROR_RESERVED_NAMESPACE_URI, 128 /* Added in 2.2.1. */ 129 XML_ERROR_INVALID_ARGUMENT, 130 /* Added in 2.3.0. */ 131 XML_ERROR_NO_BUFFER, 132 /* Added in 2.4.0. */ 133 XML_ERROR_AMPLIFICATION_LIMIT_BREACH, 134 /* Added in 2.6.4. */ 135 XML_ERROR_NOT_STARTED, 136 }; 137 138 enum XML_Content_Type { 139 XML_CTYPE_EMPTY = 1, 140 XML_CTYPE_ANY, 141 XML_CTYPE_MIXED, 142 XML_CTYPE_NAME, 143 XML_CTYPE_CHOICE, 144 XML_CTYPE_SEQ 145 }; 146 147 enum XML_Content_Quant { 148 XML_CQUANT_NONE, 149 XML_CQUANT_OPT, 150 XML_CQUANT_REP, 151 XML_CQUANT_PLUS 152 }; 153 154 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 155 XML_CQUANT_NONE, and the other fields will be zero or NULL. 156 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 157 numchildren will contain number of elements that may be mixed in 158 and children point to an array of XML_Content cells that will be 159 all of XML_CTYPE_NAME type with no quantification. 160 161 If type == XML_CTYPE_NAME, then the name points to the name, and 162 the numchildren field will be zero and children will be NULL. The 163 quant fields indicates any quantifiers placed on the name. 164 165 CHOICE and SEQ will have name NULL, the number of children in 166 numchildren and children will point, recursively, to an array 167 of XML_Content cells. 168 169 The EMPTY, ANY, and MIXED types will only occur at top level. 170 */ 171 172 typedef struct XML_cp XML_Content; 173 174 struct XML_cp { 175 enum XML_Content_Type type; 176 enum XML_Content_Quant quant; 177 XML_Char *name; 178 unsigned int numchildren; 179 XML_Content *children; 180 }; 181 182 /* This is called for an element declaration. See above for 183 description of the model argument. It's the user code's responsibility 184 to free model when finished with it. See XML_FreeContentModel. 185 There is no need to free the model from the handler, it can be kept 186 around and freed at a later stage. 187 */ 188 typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, 189 const XML_Char *name, 190 XML_Content *model); 191 192 XMLPARSEAPI(void) 193 XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl); 194 195 /* The Attlist declaration handler is called for *each* attribute. So 196 a single Attlist declaration with multiple attributes declared will 197 generate multiple calls to this handler. The "default" parameter 198 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 199 keyword. The "isrequired" parameter will be true and the default 200 value will be NULL in the case of "#REQUIRED". If "isrequired" is 201 true and default is non-NULL, then this is a "#FIXED" default. 202 */ 203 typedef void(XMLCALL *XML_AttlistDeclHandler)( 204 void *userData, const XML_Char *elname, const XML_Char *attname, 205 const XML_Char *att_type, const XML_Char *dflt, int isrequired); 206 207 XMLPARSEAPI(void) 208 XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl); 209 210 /* The XML declaration handler is called for *both* XML declarations 211 and text declarations. The way to distinguish is that the version 212 parameter will be NULL for text declarations. The encoding 213 parameter may be NULL for XML declarations. The standalone 214 parameter will be -1, 0, or 1 indicating respectively that there 215 was no standalone parameter in the declaration, that it was given 216 as no, or that it was given as yes. 217 */ 218 typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData, 219 const XML_Char *version, 220 const XML_Char *encoding, 221 int standalone); 222 223 XMLPARSEAPI(void) 224 XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl); 225 226 typedef struct { 227 void *(*malloc_fcn)(size_t size); 228 void *(*realloc_fcn)(void *ptr, size_t size); 229 void (*free_fcn)(void *ptr); 230 } XML_Memory_Handling_Suite; 231 232 /* Constructs a new parser; encoding is the encoding specified by the 233 external protocol or NULL if there is none specified. 234 */ 235 XMLPARSEAPI(XML_Parser) 236 XML_ParserCreate(const XML_Char *encoding); 237 238 /* Constructs a new parser and namespace processor. Element type 239 names and attribute names that belong to a namespace will be 240 expanded; unprefixed attribute names are never expanded; unprefixed 241 element type names are expanded only if there is a default 242 namespace. The expanded name is the concatenation of the namespace 243 URI, the namespace separator character, and the local part of the 244 name. If the namespace separator is '\0' then the namespace URI 245 and the local part will be concatenated without any separator. 246 It is a programming error to use the separator '\0' with namespace 247 triplets (see XML_SetReturnNSTriplet). 248 If a namespace separator is chosen that can be part of a URI or 249 part of an XML name, splitting an expanded name back into its 250 1, 2 or 3 original parts on application level in the element handler 251 may end up vulnerable, so these are advised against; sane choices for 252 a namespace separator are e.g. '\n' (line feed) and '|' (pipe). 253 254 Note that Expat does not validate namespace URIs (beyond encoding) 255 against RFC 3986 today (and is not required to do so with regard to 256 the XML 1.0 namespaces specification) but it may start doing that 257 in future releases. Before that, an application using Expat must 258 be ready to receive namespace URIs containing non-URI characters. 259 */ 260 XMLPARSEAPI(XML_Parser) 261 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 262 263 /* Constructs a new parser using the memory management suite referred to 264 by memsuite. If memsuite is NULL, then use the standard library memory 265 suite. If namespaceSeparator is non-NULL it creates a parser with 266 namespace processing as described above. The character pointed at 267 will serve as the namespace separator. 268 269 All further memory operations used for the created parser will come from 270 the given suite. 271 */ 272 XMLPARSEAPI(XML_Parser) 273 XML_ParserCreate_MM(const XML_Char *encoding, 274 const XML_Memory_Handling_Suite *memsuite, 275 const XML_Char *namespaceSeparator); 276 277 /* Prepare a parser object to be reused. This is particularly 278 valuable when memory allocation overhead is disproportionately high, 279 such as when a large number of small documnents need to be parsed. 280 All handlers are cleared from the parser, except for the 281 unknownEncodingHandler. The parser's external state is re-initialized 282 except for the values of ns and ns_triplets. 283 284 Added in Expat 1.95.3. 285 */ 286 XMLPARSEAPI(XML_Bool) 287 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 288 289 /* atts is array of name/value pairs, terminated by 0; 290 names and values are 0 terminated. 291 */ 292 typedef void(XMLCALL *XML_StartElementHandler)(void *userData, 293 const XML_Char *name, 294 const XML_Char **atts); 295 296 typedef void(XMLCALL *XML_EndElementHandler)(void *userData, 297 const XML_Char *name); 298 299 /* s is not 0 terminated. */ 300 typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData, 301 const XML_Char *s, int len); 302 303 /* target and data are 0 terminated */ 304 typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, 305 const XML_Char *target, 306 const XML_Char *data); 307 308 /* data is 0 terminated */ 309 typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data); 310 311 typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData); 312 typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData); 313 314 /* This is called for any characters in the XML document for which 315 there is no applicable handler. This includes both characters that 316 are part of markup which is of a kind that is not reported 317 (comments, markup declarations), or characters that are part of a 318 construct which could be reported but for which no handler has been 319 supplied. The characters are passed exactly as they were in the XML 320 document except that they will be encoded in UTF-8 or UTF-16. 321 Line boundaries are not normalized. Note that a byte order mark 322 character is not passed to the default handler. There are no 323 guarantees about how characters are divided between calls to the 324 default handler: for example, a comment might be split between 325 multiple calls. 326 */ 327 typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s, 328 int len); 329 330 /* This is called for the start of the DOCTYPE declaration, before 331 any DTD or internal subset is parsed. 332 */ 333 typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, 334 const XML_Char *doctypeName, 335 const XML_Char *sysid, 336 const XML_Char *pubid, 337 int has_internal_subset); 338 339 /* This is called for the end of the DOCTYPE declaration when the 340 closing > is encountered, but after processing any external 341 subset. 342 */ 343 typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 344 345 /* This is called for entity declarations. The is_parameter_entity 346 argument will be non-zero if the entity is a parameter entity, zero 347 otherwise. 348 349 For internal entities (<!ENTITY foo "bar">), value will 350 be non-NULL and systemId, publicID, and notationName will be NULL. 351 The value string is NOT null-terminated; the length is provided in 352 the value_length argument. Since it is legal to have zero-length 353 values, do not use this argument to test for internal entities. 354 355 For external entities, value will be NULL and systemId will be 356 non-NULL. The publicId argument will be NULL unless a public 357 identifier was provided. The notationName argument will have a 358 non-NULL value only for unparsed entity declarations. 359 360 Note that is_parameter_entity can't be changed to XML_Bool, since 361 that would break binary compatibility. 362 */ 363 typedef void(XMLCALL *XML_EntityDeclHandler)( 364 void *userData, const XML_Char *entityName, int is_parameter_entity, 365 const XML_Char *value, int value_length, const XML_Char *base, 366 const XML_Char *systemId, const XML_Char *publicId, 367 const XML_Char *notationName); 368 369 XMLPARSEAPI(void) 370 XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler); 371 372 /* OBSOLETE -- OBSOLETE -- OBSOLETE 373 This handler has been superseded by the EntityDeclHandler above. 374 It is provided here for backward compatibility. 375 376 This is called for a declaration of an unparsed (NDATA) entity. 377 The base argument is whatever was set by XML_SetBase. The 378 entityName, systemId and notationName arguments will never be 379 NULL. The other arguments may be. 380 */ 381 typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)( 382 void *userData, const XML_Char *entityName, const XML_Char *base, 383 const XML_Char *systemId, const XML_Char *publicId, 384 const XML_Char *notationName); 385 386 /* This is called for a declaration of notation. The base argument is 387 whatever was set by XML_SetBase. The notationName will never be 388 NULL. The other arguments can be. 389 */ 390 typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData, 391 const XML_Char *notationName, 392 const XML_Char *base, 393 const XML_Char *systemId, 394 const XML_Char *publicId); 395 396 /* When namespace processing is enabled, these are called once for 397 each namespace declaration. The call to the start and end element 398 handlers occur between the calls to the start and end namespace 399 declaration handlers. For an xmlns attribute, prefix will be 400 NULL. For an xmlns="" attribute, uri will be NULL. 401 */ 402 typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, 403 const XML_Char *prefix, 404 const XML_Char *uri); 405 406 typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, 407 const XML_Char *prefix); 408 409 /* This is called if the document is not standalone, that is, it has an 410 external subset or a reference to a parameter entity, but does not 411 have standalone="yes". If this handler returns XML_STATUS_ERROR, 412 then processing will not continue, and the parser will return a 413 XML_ERROR_NOT_STANDALONE error. 414 If parameter entity parsing is enabled, then in addition to the 415 conditions above this handler will only be called if the referenced 416 entity was actually read. 417 */ 418 typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData); 419 420 /* This is called for a reference to an external parsed general 421 entity. The referenced entity is not automatically parsed. The 422 application can parse it immediately or later using 423 XML_ExternalEntityParserCreate. 424 425 The parser argument is the parser parsing the entity containing the 426 reference; it can be passed as the parser argument to 427 XML_ExternalEntityParserCreate. The systemId argument is the 428 system identifier as specified in the entity declaration; it will 429 not be NULL. 430 431 The base argument is the system identifier that should be used as 432 the base for resolving systemId if systemId was relative; this is 433 set by XML_SetBase; it may be NULL. 434 435 The publicId argument is the public identifier as specified in the 436 entity declaration, or NULL if none was specified; the whitespace 437 in the public identifier will have been normalized as required by 438 the XML spec. 439 440 The context argument specifies the parsing context in the format 441 expected by the context argument to XML_ExternalEntityParserCreate; 442 context is valid only until the handler returns, so if the 443 referenced entity is to be parsed later, it must be copied. 444 context is NULL only when the entity is a parameter entity. 445 446 The handler should return XML_STATUS_ERROR if processing should not 447 continue because of a fatal error in the handling of the external 448 entity. In this case the calling parser will return an 449 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 450 451 Note that unlike other handlers the first argument is the parser, 452 not userData. 453 */ 454 typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser, 455 const XML_Char *context, 456 const XML_Char *base, 457 const XML_Char *systemId, 458 const XML_Char *publicId); 459 460 /* This is called in two situations: 461 1) An entity reference is encountered for which no declaration 462 has been read *and* this is not an error. 463 2) An internal entity reference is read, but not expanded, because 464 XML_SetDefaultHandler has been called. 465 Note: skipped parameter entities in declarations and skipped general 466 entities in attribute values cannot be reported, because 467 the event would be out of sync with the reporting of the 468 declarations or attribute values 469 */ 470 typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData, 471 const XML_Char *entityName, 472 int is_parameter_entity); 473 474 /* This structure is filled in by the XML_UnknownEncodingHandler to 475 provide information to the parser about encodings that are unknown 476 to the parser. 477 478 The map[b] member gives information about byte sequences whose 479 first byte is b. 480 481 If map[b] is c where c is >= 0, then b by itself encodes the 482 Unicode scalar value c. 483 484 If map[b] is -1, then the byte sequence is malformed. 485 486 If map[b] is -n, where n >= 2, then b is the first byte of an 487 n-byte sequence that encodes a single Unicode scalar value. 488 489 The data member will be passed as the first argument to the convert 490 function. 491 492 The convert function is used to convert multibyte sequences; s will 493 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 494 convert function must return the Unicode scalar value represented 495 by this byte sequence or -1 if the byte sequence is malformed. 496 497 The convert function may be NULL if the encoding is a single-byte 498 encoding, that is if map[b] >= -1 for all bytes b. 499 500 When the parser is finished with the encoding, then if release is 501 not NULL, it will call release passing it the data member; once 502 release has been called, the convert function will not be called 503 again. 504 505 Expat places certain restrictions on the encodings that are supported 506 using this mechanism. 507 508 1. Every ASCII character that can appear in a well-formed XML document, 509 other than the characters 510 511 $@\^`{}~ 512 513 must be represented by a single byte, and that byte must be the 514 same byte that represents that character in ASCII. 515 516 2. No character may require more than 4 bytes to encode. 517 518 3. All characters encoded must have Unicode scalar values <= 519 0xFFFF, (i.e., characters that would be encoded by surrogates in 520 UTF-16 are not allowed). Note that this restriction doesn't 521 apply to the built-in support for UTF-8 and UTF-16. 522 523 4. No Unicode character may be encoded by more than one distinct 524 sequence of bytes. 525 */ 526 typedef struct { 527 int map[256]; 528 void *data; 529 int(XMLCALL *convert)(void *data, const char *s); 530 void(XMLCALL *release)(void *data); 531 } XML_Encoding; 532 533 /* This is called for an encoding that is unknown to the parser. 534 535 The encodingHandlerData argument is that which was passed as the 536 second argument to XML_SetUnknownEncodingHandler. 537 538 The name argument gives the name of the encoding as specified in 539 the encoding declaration. 540 541 If the callback can provide information about the encoding, it must 542 fill in the XML_Encoding structure, and return XML_STATUS_OK. 543 Otherwise it must return XML_STATUS_ERROR. 544 545 If info does not describe a suitable encoding, then the parser will 546 return an XML_ERROR_UNKNOWN_ENCODING error. 547 */ 548 typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, 549 const XML_Char *name, 550 XML_Encoding *info); 551 552 XMLPARSEAPI(void) 553 XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, 554 XML_EndElementHandler end); 555 556 XMLPARSEAPI(void) 557 XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler); 558 559 XMLPARSEAPI(void) 560 XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler); 561 562 XMLPARSEAPI(void) 563 XML_SetCharacterDataHandler(XML_Parser parser, 564 XML_CharacterDataHandler handler); 565 566 XMLPARSEAPI(void) 567 XML_SetProcessingInstructionHandler(XML_Parser parser, 568 XML_ProcessingInstructionHandler handler); 569 XMLPARSEAPI(void) 570 XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler); 571 572 XMLPARSEAPI(void) 573 XML_SetCdataSectionHandler(XML_Parser parser, 574 XML_StartCdataSectionHandler start, 575 XML_EndCdataSectionHandler end); 576 577 XMLPARSEAPI(void) 578 XML_SetStartCdataSectionHandler(XML_Parser parser, 579 XML_StartCdataSectionHandler start); 580 581 XMLPARSEAPI(void) 582 XML_SetEndCdataSectionHandler(XML_Parser parser, 583 XML_EndCdataSectionHandler end); 584 585 /* This sets the default handler and also inhibits expansion of 586 internal entities. These entity references will be passed to the 587 default handler, or to the skipped entity handler, if one is set. 588 */ 589 XMLPARSEAPI(void) 590 XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler); 591 592 /* This sets the default handler but does not inhibit expansion of 593 internal entities. The entity reference will not be passed to the 594 default handler. 595 */ 596 XMLPARSEAPI(void) 597 XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler); 598 599 XMLPARSEAPI(void) 600 XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, 601 XML_EndDoctypeDeclHandler end); 602 603 XMLPARSEAPI(void) 604 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 605 XML_StartDoctypeDeclHandler start); 606 607 XMLPARSEAPI(void) 608 XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end); 609 610 XMLPARSEAPI(void) 611 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 612 XML_UnparsedEntityDeclHandler handler); 613 614 XMLPARSEAPI(void) 615 XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler); 616 617 XMLPARSEAPI(void) 618 XML_SetNamespaceDeclHandler(XML_Parser parser, 619 XML_StartNamespaceDeclHandler start, 620 XML_EndNamespaceDeclHandler end); 621 622 XMLPARSEAPI(void) 623 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 624 XML_StartNamespaceDeclHandler start); 625 626 XMLPARSEAPI(void) 627 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 628 XML_EndNamespaceDeclHandler end); 629 630 XMLPARSEAPI(void) 631 XML_SetNotStandaloneHandler(XML_Parser parser, 632 XML_NotStandaloneHandler handler); 633 634 XMLPARSEAPI(void) 635 XML_SetExternalEntityRefHandler(XML_Parser parser, 636 XML_ExternalEntityRefHandler handler); 637 638 /* If a non-NULL value for arg is specified here, then it will be 639 passed as the first argument to the external entity ref handler 640 instead of the parser object. 641 */ 642 XMLPARSEAPI(void) 643 XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg); 644 645 XMLPARSEAPI(void) 646 XML_SetSkippedEntityHandler(XML_Parser parser, 647 XML_SkippedEntityHandler handler); 648 649 XMLPARSEAPI(void) 650 XML_SetUnknownEncodingHandler(XML_Parser parser, 651 XML_UnknownEncodingHandler handler, 652 void *encodingHandlerData); 653 654 /* This can be called within a handler for a start element, end 655 element, processing instruction or character data. It causes the 656 corresponding markup to be passed to the default handler. 657 */ 658 XMLPARSEAPI(void) 659 XML_DefaultCurrent(XML_Parser parser); 660 661 /* If do_nst is non-zero, and namespace processing is in effect, and 662 a name has a prefix (i.e. an explicit namespace qualifier) then 663 that name is returned as a triplet in a single string separated by 664 the separator character specified when the parser was created: URI 665 + sep + local_name + sep + prefix. 666 667 If do_nst is zero, then namespace information is returned in the 668 default manner (URI + sep + local_name) whether or not the name 669 has a prefix. 670 671 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 672 XML_ParseBuffer has no effect. 673 */ 674 675 XMLPARSEAPI(void) 676 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 677 678 /* This value is passed as the userData argument to callbacks. */ 679 XMLPARSEAPI(void) 680 XML_SetUserData(XML_Parser parser, void *userData); 681 682 /* Returns the last value set by XML_SetUserData or NULL. */ 683 #define XML_GetUserData(parser) (*(void **)(parser)) 684 685 /* This is equivalent to supplying an encoding argument to 686 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 687 zero otherwise. 688 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 689 has no effect and returns XML_STATUS_ERROR. 690 */ 691 XMLPARSEAPI(enum XML_Status) 692 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 693 694 /* If this function is called, then the parser will be passed as the 695 first argument to callbacks instead of userData. The userData will 696 still be accessible using XML_GetUserData. 697 */ 698 XMLPARSEAPI(void) 699 XML_UseParserAsHandlerArg(XML_Parser parser); 700 701 /* If useDTD == XML_TRUE is passed to this function, then the parser 702 will assume that there is an external subset, even if none is 703 specified in the document. In such a case the parser will call the 704 externalEntityRefHandler with a value of NULL for the systemId 705 argument (the publicId and context arguments will be NULL as well). 706 Note: For the purpose of checking WFC: Entity Declared, passing 707 useDTD == XML_TRUE will make the parser behave as if the document 708 had a DTD with an external subset. 709 Note: If this function is called, then this must be done before 710 the first call to XML_Parse or XML_ParseBuffer, since it will 711 have no effect after that. Returns 712 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 713 Note: If the document does not have a DOCTYPE declaration at all, 714 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 715 be called, despite an external subset being parsed. 716 Note: If XML_DTD is not defined when Expat is compiled, returns 717 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 718 Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. 719 */ 720 XMLPARSEAPI(enum XML_Error) 721 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 722 723 /* Sets the base to be used for resolving relative URIs in system 724 identifiers in declarations. Resolving relative identifiers is 725 left to the application: this value will be passed through as the 726 base argument to the XML_ExternalEntityRefHandler, 727 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 728 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 729 XML_STATUS_OK otherwise. 730 */ 731 XMLPARSEAPI(enum XML_Status) 732 XML_SetBase(XML_Parser parser, const XML_Char *base); 733 734 XMLPARSEAPI(const XML_Char *) 735 XML_GetBase(XML_Parser parser); 736 737 /* Returns the number of the attribute/value pairs passed in last call 738 to the XML_StartElementHandler that were specified in the start-tag 739 rather than defaulted. Each attribute/value pair counts as 2; thus 740 this corresponds to an index into the atts array passed to the 741 XML_StartElementHandler. Returns -1 if parser == NULL. 742 */ 743 XMLPARSEAPI(int) 744 XML_GetSpecifiedAttributeCount(XML_Parser parser); 745 746 /* Returns the index of the ID attribute passed in the last call to 747 XML_StartElementHandler, or -1 if there is no ID attribute or 748 parser == NULL. Each attribute/value pair counts as 2; thus this 749 corresponds to an index into the atts array passed to the 750 XML_StartElementHandler. 751 */ 752 XMLPARSEAPI(int) 753 XML_GetIdAttributeIndex(XML_Parser parser); 754 755 #ifdef XML_ATTR_INFO 756 /* Source file byte offsets for the start and end of attribute names and values. 757 The value indices are exclusive of surrounding quotes; thus in a UTF-8 source 758 file an attribute value of "blah" will yield: 759 info->valueEnd - info->valueStart = 4 bytes. 760 */ 761 typedef struct { 762 XML_Index nameStart; /* Offset to beginning of the attribute name. */ 763 XML_Index nameEnd; /* Offset after the attribute name's last byte. */ 764 XML_Index valueStart; /* Offset to beginning of the attribute value. */ 765 XML_Index valueEnd; /* Offset after the attribute value's last byte. */ 766 } XML_AttrInfo; 767 768 /* Returns an array of XML_AttrInfo structures for the attribute/value pairs 769 passed in last call to the XML_StartElementHandler that were specified 770 in the start-tag rather than defaulted. Each attribute/value pair counts 771 as 1; thus the number of entries in the array is 772 XML_GetSpecifiedAttributeCount(parser) / 2. 773 */ 774 XMLPARSEAPI(const XML_AttrInfo *) 775 XML_GetAttributeInfo(XML_Parser parser); 776 #endif 777 778 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 779 detected. The last call to XML_Parse must have isFinal true; len 780 may be zero for this call (or any other). 781 782 Though the return values for these functions has always been 783 described as a Boolean value, the implementation, at least for the 784 1.95.x series, has always returned exactly one of the XML_Status 785 values. 786 */ 787 XMLPARSEAPI(enum XML_Status) 788 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 789 790 XMLPARSEAPI(void *) 791 XML_GetBuffer(XML_Parser parser, int len); 792 793 XMLPARSEAPI(enum XML_Status) 794 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 795 796 /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 797 Must be called from within a call-back handler, except when aborting 798 (resumable = 0) an already suspended parser. Some call-backs may 799 still follow because they would otherwise get lost. Examples: 800 - endElementHandler() for empty elements when stopped in 801 startElementHandler(), 802 - endNameSpaceDeclHandler() when stopped in endElementHandler(), 803 and possibly others. 804 805 Can be called from most handlers, including DTD related call-backs, 806 except when parsing an external parameter entity and resumable != 0. 807 Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 808 Possible error codes: 809 - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 810 - XML_ERROR_FINISHED: when the parser has already finished. 811 - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 812 813 When resumable != 0 (true) then parsing is suspended, that is, 814 XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 815 Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 816 return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 817 818 *Note*: 819 This will be applied to the current parser instance only, that is, if 820 there is a parent parser then it will continue parsing when the 821 externalEntityRefHandler() returns. It is up to the implementation of 822 the externalEntityRefHandler() to call XML_StopParser() on the parent 823 parser (recursively), if one wants to stop parsing altogether. 824 825 When suspended, parsing can be resumed by calling XML_ResumeParser(). 826 */ 827 XMLPARSEAPI(enum XML_Status) 828 XML_StopParser(XML_Parser parser, XML_Bool resumable); 829 830 /* Resumes parsing after it has been suspended with XML_StopParser(). 831 Must not be called from within a handler call-back. Returns same 832 status codes as XML_Parse() or XML_ParseBuffer(). 833 Additional error code XML_ERROR_NOT_SUSPENDED possible. 834 835 *Note*: 836 This must be called on the most deeply nested child parser instance 837 first, and on its parent parser only after the child parser has finished, 838 to be applied recursively until the document entity's parser is restarted. 839 That is, the parent parser will not resume by itself and it is up to the 840 application to call XML_ResumeParser() on it at the appropriate moment. 841 */ 842 XMLPARSEAPI(enum XML_Status) 843 XML_ResumeParser(XML_Parser parser); 844 845 enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED }; 846 847 typedef struct { 848 enum XML_Parsing parsing; 849 XML_Bool finalBuffer; 850 } XML_ParsingStatus; 851 852 /* Returns status of parser with respect to being initialized, parsing, 853 finished, or suspended and processing the final buffer. 854 XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 855 XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 856 */ 857 XMLPARSEAPI(void) 858 XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 859 860 /* Creates an XML_Parser object that can parse an external general 861 entity; context is a '\0'-terminated string specifying the parse 862 context; encoding is a '\0'-terminated string giving the name of 863 the externally specified encoding, or NULL if there is no 864 externally specified encoding. The context string consists of a 865 sequence of tokens separated by formfeeds (\f); a token consisting 866 of a name specifies that the general entity of the name is open; a 867 token of the form prefix=uri specifies the namespace for a 868 particular prefix; a token of the form =uri specifies the default 869 namespace. This can be called at any point after the first call to 870 an ExternalEntityRefHandler so longer as the parser has not yet 871 been freed. The new parser is completely independent and may 872 safely be used in a separate thread. The handlers and userData are 873 initialized from the parser argument. Returns NULL if out of memory. 874 Otherwise returns a new XML_Parser object. 875 */ 876 XMLPARSEAPI(XML_Parser) 877 XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context, 878 const XML_Char *encoding); 879 880 enum XML_ParamEntityParsing { 881 XML_PARAM_ENTITY_PARSING_NEVER, 882 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 883 XML_PARAM_ENTITY_PARSING_ALWAYS 884 }; 885 886 /* Controls parsing of parameter entities (including the external DTD 887 subset). If parsing of parameter entities is enabled, then 888 references to external parameter entities (including the external 889 DTD subset) will be passed to the handler set with 890 XML_SetExternalEntityRefHandler. The context passed will be 0. 891 892 Unlike external general entities, external parameter entities can 893 only be parsed synchronously. If the external parameter entity is 894 to be parsed, it must be parsed during the call to the external 895 entity ref handler: the complete sequence of 896 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 897 XML_ParserFree calls must be made during this call. After 898 XML_ExternalEntityParserCreate has been called to create the parser 899 for the external parameter entity (context must be 0 for this 900 call), it is illegal to make any calls on the old parser until 901 XML_ParserFree has been called on the newly created parser. 902 If the library has been compiled without support for parameter 903 entity parsing (ie without XML_DTD being defined), then 904 XML_SetParamEntityParsing will return 0 if parsing of parameter 905 entities is requested; otherwise it will return non-zero. 906 Note: If XML_SetParamEntityParsing is called after XML_Parse or 907 XML_ParseBuffer, then it has no effect and will always return 0. 908 Note: If parser == NULL, the function will do nothing and return 0. 909 */ 910 XMLPARSEAPI(int) 911 XML_SetParamEntityParsing(XML_Parser parser, 912 enum XML_ParamEntityParsing parsing); 913 914 /* Sets the hash salt to use for internal hash calculations. 915 Helps in preventing DoS attacks based on predicting hash 916 function behavior. This must be called before parsing is started. 917 Returns 1 if successful, 0 when called after parsing has started. 918 Note: If parser == NULL, the function will do nothing and return 0. 919 */ 920 XMLPARSEAPI(int) 921 XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt); 922 923 /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 924 XML_GetErrorCode returns information about the error. 925 */ 926 XMLPARSEAPI(enum XML_Error) 927 XML_GetErrorCode(XML_Parser parser); 928 929 /* These functions return information about the current parse 930 location. They may be called from any callback called to report 931 some parse event; in this case the location is the location of the 932 first of the sequence of characters that generated the event. When 933 called from callbacks generated by declarations in the document 934 prologue, the location identified isn't as neatly defined, but will 935 be within the relevant markup. When called outside of the callback 936 functions, the position indicated will be just past the last parse 937 event (regardless of whether there was an associated callback). 938 939 They may also be called after returning from a call to XML_Parse 940 or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 941 the location is the location of the character at which the error 942 was detected; otherwise the location is the location of the last 943 parse event, as described above. 944 945 Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber 946 return 0 to indicate an error. 947 Note: XML_GetCurrentByteIndex returns -1 to indicate an error. 948 */ 949 XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); 950 XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); 951 XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); 952 953 /* Return the number of bytes in the current event. 954 Returns 0 if the event is in an internal entity. 955 */ 956 XMLPARSEAPI(int) 957 XML_GetCurrentByteCount(XML_Parser parser); 958 959 /* If XML_CONTEXT_BYTES is >=1, returns the input buffer, sets 960 the integer pointed to by offset to the offset within this buffer 961 of the current parse position, and sets the integer pointed to by size 962 to the size of this buffer (the number of input bytes). Otherwise 963 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 964 active. 965 966 NOTE: The character pointer returned should not be used outside 967 the handler that makes the call. 968 */ 969 XMLPARSEAPI(const char *) 970 XML_GetInputContext(XML_Parser parser, int *offset, int *size); 971 972 /* For backwards compatibility with previous versions. */ 973 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 974 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 975 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 976 977 /* Frees the content model passed to the element declaration handler */ 978 XMLPARSEAPI(void) 979 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 980 981 /* Exposing the memory handling functions used in Expat */ 982 XMLPARSEAPI(void *) 983 XML_ATTR_MALLOC 984 XML_ATTR_ALLOC_SIZE(2) 985 XML_MemMalloc(XML_Parser parser, size_t size); 986 987 XMLPARSEAPI(void *) 988 XML_ATTR_ALLOC_SIZE(3) 989 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 990 991 XMLPARSEAPI(void) 992 XML_MemFree(XML_Parser parser, void *ptr); 993 994 /* Frees memory used by the parser. */ 995 XMLPARSEAPI(void) 996 XML_ParserFree(XML_Parser parser); 997 998 /* Returns a string describing the error. */ 999 XMLPARSEAPI(const XML_LChar *) 1000 XML_ErrorString(enum XML_Error code); 1001 1002 /* Return a string containing the version number of this expat */ 1003 XMLPARSEAPI(const XML_LChar *) 1004 XML_ExpatVersion(void); 1005 1006 typedef struct { 1007 int major; 1008 int minor; 1009 int micro; 1010 } XML_Expat_Version; 1011 1012 /* Return an XML_Expat_Version structure containing numeric version 1013 number information for this version of expat. 1014 */ 1015 XMLPARSEAPI(XML_Expat_Version) 1016 XML_ExpatVersionInfo(void); 1017 1018 /* Added in Expat 1.95.5. */ 1019 enum XML_FeatureEnum { 1020 XML_FEATURE_END = 0, 1021 XML_FEATURE_UNICODE, 1022 XML_FEATURE_UNICODE_WCHAR_T, 1023 XML_FEATURE_DTD, 1024 XML_FEATURE_CONTEXT_BYTES, 1025 XML_FEATURE_MIN_SIZE, 1026 XML_FEATURE_SIZEOF_XML_CHAR, 1027 XML_FEATURE_SIZEOF_XML_LCHAR, 1028 XML_FEATURE_NS, 1029 XML_FEATURE_LARGE_SIZE, 1030 XML_FEATURE_ATTR_INFO, 1031 /* Added in Expat 2.4.0. */ 1032 XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, 1033 XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT, 1034 /* Added in Expat 2.6.0. */ 1035 XML_FEATURE_GE 1036 /* Additional features must be added to the end of this enum. */ 1037 }; 1038 1039 typedef struct { 1040 enum XML_FeatureEnum feature; 1041 const XML_LChar *name; 1042 long int value; 1043 } XML_Feature; 1044 1045 XMLPARSEAPI(const XML_Feature *) 1046 XML_GetFeatureList(void); 1047 1048 #if defined(XML_DTD) || (defined(XML_GE) && XML_GE == 1) 1049 /* Added in Expat 2.4.0 for XML_DTD defined and 1050 * added in Expat 2.6.0 for XML_GE == 1. */ 1051 XMLPARSEAPI(XML_Bool) 1052 XML_SetBillionLaughsAttackProtectionMaximumAmplification( 1053 XML_Parser parser, float maximumAmplificationFactor); 1054 1055 /* Added in Expat 2.4.0 for XML_DTD defined and 1056 * added in Expat 2.6.0 for XML_GE == 1. */ 1057 XMLPARSEAPI(XML_Bool) 1058 XML_SetBillionLaughsAttackProtectionActivationThreshold( 1059 XML_Parser parser, unsigned long long activationThresholdBytes); 1060 #endif 1061 1062 /* Added in Expat 2.6.0. */ 1063 XMLPARSEAPI(XML_Bool) 1064 XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled); 1065 1066 /* Expat follows the semantic versioning convention. 1067 See https://semver.org 1068 */ 1069 #define XML_MAJOR_VERSION 2 1070 #define XML_MINOR_VERSION 6 1071 #define XML_MICRO_VERSION 4 1072 1073 #ifdef __cplusplus 1074 } 1075 #endif 1076 1077 #endif /* not Expat_INCLUDED */ 1078