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