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