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) 2016-2021 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 Licensed under the MIT license: 19 20 Permission is hereby granted, free of charge, to any person obtaining 21 a copy of this software and associated documentation files (the 22 "Software"), to deal in the Software without restriction, including 23 without limitation the rights to use, copy, modify, merge, publish, 24 distribute, sublicense, and/or sell copies of the Software, and to permit 25 persons to whom the Software is furnished to do so, subject to the 26 following conditions: 27 28 The above copyright notice and this permission notice shall be included 29 in all copies or substantial portions of the Software. 30 31 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 32 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 33 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN 34 NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 35 DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 36 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 37 USE OR OTHER DEALINGS IN THE SOFTWARE. 38 */ 39 40 #ifndef Expat_INCLUDED 41 #define Expat_INCLUDED 1 42 43 #include "vtk_expat_mangle.h" 44 45 #include <stdlib.h> 46 #include "expat_external.h" 47 48 #ifdef __cplusplus 49 extern "C" { 50 #endif 51 52 struct XML_ParserStruct; 53 typedef struct XML_ParserStruct *XML_Parser; 54 55 typedef unsigned char XML_Bool; 56 #define XML_TRUE ((XML_Bool)1) 57 #define XML_FALSE ((XML_Bool)0) 58 59 /* The XML_Status enum gives the possible return values for several 60 API functions. The preprocessor #defines are included so this 61 stanza can be added to code that still needs to support older 62 versions of Expat 1.95.x: 63 64 #ifndef XML_STATUS_OK 65 #define XML_STATUS_OK 1 66 #define XML_STATUS_ERROR 0 67 #endif 68 69 Otherwise, the #define hackery is quite ugly and would have been 70 dropped. 71 */ 72 enum XML_Status { 73 XML_STATUS_ERROR = 0, 74 #define XML_STATUS_ERROR XML_STATUS_ERROR 75 XML_STATUS_OK = 1, 76 #define XML_STATUS_OK XML_STATUS_OK 77 XML_STATUS_SUSPENDED = 2 78 #define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED 79 }; 80 81 enum XML_Error { 82 XML_ERROR_NONE, 83 XML_ERROR_NO_MEMORY, 84 XML_ERROR_SYNTAX, 85 XML_ERROR_NO_ELEMENTS, 86 XML_ERROR_INVALID_TOKEN, 87 XML_ERROR_UNCLOSED_TOKEN, 88 XML_ERROR_PARTIAL_CHAR, 89 XML_ERROR_TAG_MISMATCH, 90 XML_ERROR_DUPLICATE_ATTRIBUTE, 91 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 92 XML_ERROR_PARAM_ENTITY_REF, 93 XML_ERROR_UNDEFINED_ENTITY, 94 XML_ERROR_RECURSIVE_ENTITY_REF, 95 XML_ERROR_ASYNC_ENTITY, 96 XML_ERROR_BAD_CHAR_REF, 97 XML_ERROR_BINARY_ENTITY_REF, 98 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 99 XML_ERROR_MISPLACED_XML_PI, 100 XML_ERROR_UNKNOWN_ENCODING, 101 XML_ERROR_INCORRECT_ENCODING, 102 XML_ERROR_UNCLOSED_CDATA_SECTION, 103 XML_ERROR_EXTERNAL_ENTITY_HANDLING, 104 XML_ERROR_NOT_STANDALONE, 105 XML_ERROR_UNEXPECTED_STATE, 106 XML_ERROR_ENTITY_DECLARED_IN_PE, 107 XML_ERROR_FEATURE_REQUIRES_XML_DTD, 108 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 109 /* Added in 1.95.7. */ 110 XML_ERROR_UNBOUND_PREFIX, 111 /* Added in 1.95.8. */ 112 XML_ERROR_UNDECLARING_PREFIX, 113 XML_ERROR_INCOMPLETE_PE, 114 XML_ERROR_XML_DECL, 115 XML_ERROR_TEXT_DECL, 116 XML_ERROR_PUBLICID, 117 XML_ERROR_SUSPENDED, 118 XML_ERROR_NOT_SUSPENDED, 119 XML_ERROR_ABORTED, 120 XML_ERROR_FINISHED, 121 XML_ERROR_SUSPEND_PE, 122 /* Added in 2.0. */ 123 XML_ERROR_RESERVED_PREFIX_XML, 124 XML_ERROR_RESERVED_PREFIX_XMLNS, 125 XML_ERROR_RESERVED_NAMESPACE_URI, 126 /* Added in 2.2.1. */ 127 XML_ERROR_INVALID_ARGUMENT, 128 /* Added in 2.3.0. */ 129 XML_ERROR_NO_BUFFER, 130 /* Added in 2.4.0. */ 131 XML_ERROR_AMPLIFICATION_LIMIT_BREACH 132 }; 133 134 enum XML_Content_Type { 135 XML_CTYPE_EMPTY = 1, 136 XML_CTYPE_ANY, 137 XML_CTYPE_MIXED, 138 XML_CTYPE_NAME, 139 XML_CTYPE_CHOICE, 140 XML_CTYPE_SEQ 141 }; 142 143 enum XML_Content_Quant { 144 XML_CQUANT_NONE, 145 XML_CQUANT_OPT, 146 XML_CQUANT_REP, 147 XML_CQUANT_PLUS 148 }; 149 150 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 151 XML_CQUANT_NONE, and the other fields will be zero or NULL. 152 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 153 numchildren will contain number of elements that may be mixed in 154 and children point to an array of XML_Content cells that will be 155 all of XML_CTYPE_NAME type with no quantification. 156 157 If type == XML_CTYPE_NAME, then the name points to the name, and 158 the numchildren field will be zero and children will be NULL. The 159 quant fields indicates any quantifiers placed on the name. 160 161 CHOICE and SEQ will have name NULL, the number of children in 162 numchildren and children will point, recursively, to an array 163 of XML_Content cells. 164 165 The EMPTY, ANY, and MIXED types will only occur at top level. 166 */ 167 168 typedef struct XML_cp XML_Content; 169 170 struct XML_cp { 171 enum XML_Content_Type type; 172 enum XML_Content_Quant quant; 173 XML_Char *name; 174 unsigned int numchildren; 175 XML_Content *children; 176 }; 177 178 /* This is called for an element declaration. See above for 179 description of the model argument. It's the caller's responsibility 180 to free model when finished with it. 181 */ 182 typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, 183 const XML_Char *name, 184 XML_Content *model); 185 186 XMLPARSEAPI(void) 187 XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl); 188 189 /* The Attlist declaration handler is called for *each* attribute. So 190 a single Attlist declaration with multiple attributes declared will 191 generate multiple calls to this handler. The "default" parameter 192 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 193 keyword. The "isrequired" parameter will be true and the default 194 value will be NULL in the case of "#REQUIRED". If "isrequired" is 195 true and default is non-NULL, then this is a "#FIXED" default. 196 */ 197 typedef void(XMLCALL *XML_AttlistDeclHandler)( 198 void *userData, const XML_Char *elname, const XML_Char *attname, 199 const XML_Char *att_type, const XML_Char *dflt, int isrequired); 200 201 XMLPARSEAPI(void) 202 XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl); 203 204 /* The XML declaration handler is called for *both* XML declarations 205 and text declarations. The way to distinguish is that the version 206 parameter will be NULL for text declarations. The encoding 207 parameter may be NULL for XML declarations. The standalone 208 parameter will be -1, 0, or 1 indicating respectively that there 209 was no standalone parameter in the declaration, that it was given 210 as no, or that it was given as yes. 211 */ 212 typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData, 213 const XML_Char *version, 214 const XML_Char *encoding, 215 int standalone); 216 217 XMLPARSEAPI(void) 218 XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl); 219 220 typedef struct { 221 void *(*malloc_fcn)(size_t size); 222 void *(*realloc_fcn)(void *ptr, size_t size); 223 void (*free_fcn)(void *ptr); 224 } XML_Memory_Handling_Suite; 225 226 /* Constructs a new parser; encoding is the encoding specified by the 227 external protocol or NULL if there is none specified. 228 */ 229 XMLPARSEAPI(XML_Parser) 230 XML_ParserCreate(const XML_Char *encoding); 231 232 /* Constructs a new parser and namespace processor. Element type 233 names and attribute names that belong to a namespace will be 234 expanded; unprefixed attribute names are never expanded; unprefixed 235 element type names are expanded only if there is a default 236 namespace. The expanded name is the concatenation of the namespace 237 URI, the namespace separator character, and the local part of the 238 name. If the namespace separator is '\0' then the namespace URI 239 and the local part will be concatenated without any separator. 240 It is a programming error to use the separator '\0' with namespace 241 triplets (see XML_SetReturnNSTriplet). 242 */ 243 XMLPARSEAPI(XML_Parser) 244 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 245 246 /* Constructs a new parser using the memory management suite referred to 247 by memsuite. If memsuite is NULL, then use the standard library memory 248 suite. If namespaceSeparator is non-NULL it creates a parser with 249 namespace processing as described above. The character pointed at 250 will serve as the namespace separator. 251 252 All further memory operations used for the created parser will come from 253 the given suite. 254 */ 255 XMLPARSEAPI(XML_Parser) 256 XML_ParserCreate_MM(const XML_Char *encoding, 257 const XML_Memory_Handling_Suite *memsuite, 258 const XML_Char *namespaceSeparator); 259 260 /* Prepare a parser object to be re-used. This is particularly 261 valuable when memory allocation overhead is disproportionately high, 262 such as when a large number of small documnents need to be parsed. 263 All handlers are cleared from the parser, except for the 264 unknownEncodingHandler. The parser's external state is re-initialized 265 except for the values of ns and ns_triplets. 266 267 Added in Expat 1.95.3. 268 */ 269 XMLPARSEAPI(XML_Bool) 270 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 271 272 /* atts is array of name/value pairs, terminated by 0; 273 names and values are 0 terminated. 274 */ 275 typedef void(XMLCALL *XML_StartElementHandler)(void *userData, 276 const XML_Char *name, 277 const XML_Char **atts); 278 279 typedef void(XMLCALL *XML_EndElementHandler)(void *userData, 280 const XML_Char *name); 281 282 /* s is not 0 terminated. */ 283 typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData, 284 const XML_Char *s, int len); 285 286 /* target and data are 0 terminated */ 287 typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, 288 const XML_Char *target, 289 const XML_Char *data); 290 291 /* data is 0 terminated */ 292 typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data); 293 294 typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData); 295 typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData); 296 297 /* This is called for any characters in the XML document for which 298 there is no applicable handler. This includes both characters that 299 are part of markup which is of a kind that is not reported 300 (comments, markup declarations), or characters that are part of a 301 construct which could be reported but for which no handler has been 302 supplied. The characters are passed exactly as they were in the XML 303 document except that they will be encoded in UTF-8 or UTF-16. 304 Line boundaries are not normalized. Note that a byte order mark 305 character is not passed to the default handler. There are no 306 guarantees about how characters are divided between calls to the 307 default handler: for example, a comment might be split between 308 multiple calls. 309 */ 310 typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s, 311 int len); 312 313 /* This is called for the start of the DOCTYPE declaration, before 314 any DTD or internal subset is parsed. 315 */ 316 typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, 317 const XML_Char *doctypeName, 318 const XML_Char *sysid, 319 const XML_Char *pubid, 320 int has_internal_subset); 321 322 /* This is called for the start of the DOCTYPE declaration when the 323 closing > is encountered, but after processing any external 324 subset. 325 */ 326 typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 327 328 /* This is called for entity declarations. The is_parameter_entity 329 argument will be non-zero if the entity is a parameter entity, zero 330 otherwise. 331 332 For internal entities (<!ENTITY foo "bar">), value will 333 be non-NULL and systemId, publicID, and notationName will be NULL. 334 The value string is NOT null-terminated; the length is provided in 335 the value_length argument. Since it is legal to have zero-length 336 values, do not use this argument to test for internal entities. 337 338 For external entities, value will be NULL and systemId will be 339 non-NULL. The publicId argument will be NULL unless a public 340 identifier was provided. The notationName argument will have a 341 non-NULL value only for unparsed entity declarations. 342 343 Note that is_parameter_entity can't be changed to XML_Bool, since 344 that would break binary compatibility. 345 */ 346 typedef void(XMLCALL *XML_EntityDeclHandler)( 347 void *userData, const XML_Char *entityName, int is_parameter_entity, 348 const XML_Char *value, int value_length, const XML_Char *base, 349 const XML_Char *systemId, const XML_Char *publicId, 350 const XML_Char *notationName); 351 352 XMLPARSEAPI(void) 353 XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler); 354 355 /* OBSOLETE -- OBSOLETE -- OBSOLETE 356 This handler has been superseded by the EntityDeclHandler above. 357 It is provided here for backward compatibility. 358 359 This is called for a declaration of an unparsed (NDATA) entity. 360 The base argument is whatever was set by XML_SetBase. The 361 entityName, systemId and notationName arguments will never be 362 NULL. The other arguments may be. 363 */ 364 typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)( 365 void *userData, const XML_Char *entityName, const XML_Char *base, 366 const XML_Char *systemId, const XML_Char *publicId, 367 const XML_Char *notationName); 368 369 /* This is called for a declaration of notation. The base argument is 370 whatever was set by XML_SetBase. The notationName will never be 371 NULL. The other arguments can be. 372 */ 373 typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData, 374 const XML_Char *notationName, 375 const XML_Char *base, 376 const XML_Char *systemId, 377 const XML_Char *publicId); 378 379 /* When namespace processing is enabled, these are called once for 380 each namespace declaration. The call to the start and end element 381 handlers occur between the calls to the start and end namespace 382 declaration handlers. For an xmlns attribute, prefix will be 383 NULL. For an xmlns="" attribute, uri will be NULL. 384 */ 385 typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, 386 const XML_Char *prefix, 387 const XML_Char *uri); 388 389 typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, 390 const XML_Char *prefix); 391 392 /* This is called if the document is not standalone, that is, it has an 393 external subset or a reference to a parameter entity, but does not 394 have standalone="yes". If this handler returns XML_STATUS_ERROR, 395 then processing will not continue, and the parser will return a 396 XML_ERROR_NOT_STANDALONE error. 397 If parameter entity parsing is enabled, then in addition to the 398 conditions above this handler will only be called if the referenced 399 entity was actually read. 400 */ 401 typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData); 402 403 /* This is called for a reference to an external parsed general 404 entity. The referenced entity is not automatically parsed. The 405 application can parse it immediately or later using 406 XML_ExternalEntityParserCreate. 407 408 The parser argument is the parser parsing the entity containing the 409 reference; it can be passed as the parser argument to 410 XML_ExternalEntityParserCreate. The systemId argument is the 411 system identifier as specified in the entity declaration; it will 412 not be NULL. 413 414 The base argument is the system identifier that should be used as 415 the base for resolving systemId if systemId was relative; this is 416 set by XML_SetBase; it may be NULL. 417 418 The publicId argument is the public identifier as specified in the 419 entity declaration, or NULL if none was specified; the whitespace 420 in the public identifier will have been normalized as required by 421 the XML spec. 422 423 The context argument specifies the parsing context in the format 424 expected by the context argument to XML_ExternalEntityParserCreate; 425 context is valid only until the handler returns, so if the 426 referenced entity is to be parsed later, it must be copied. 427 context is NULL only when the entity is a parameter entity. 428 429 The handler should return XML_STATUS_ERROR if processing should not 430 continue because of a fatal error in the handling of the external 431 entity. In this case the calling parser will return an 432 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 433 434 Note that unlike other handlers the first argument is the parser, 435 not userData. 436 */ 437 typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser, 438 const XML_Char *context, 439 const XML_Char *base, 440 const XML_Char *systemId, 441 const XML_Char *publicId); 442 443 /* This is called in two situations: 444 1) An entity reference is encountered for which no declaration 445 has been read *and* this is not an error. 446 2) An internal entity reference is read, but not expanded, because 447 XML_SetDefaultHandler has been called. 448 Note: skipped parameter entities in declarations and skipped general 449 entities in attribute values cannot be reported, because 450 the event would be out of sync with the reporting of the 451 declarations or attribute values 452 */ 453 typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData, 454 const XML_Char *entityName, 455 int is_parameter_entity); 456 457 /* This structure is filled in by the XML_UnknownEncodingHandler to 458 provide information to the parser about encodings that are unknown 459 to the parser. 460 461 The map[b] member gives information about byte sequences whose 462 first byte is b. 463 464 If map[b] is c where c is >= 0, then b by itself encodes the 465 Unicode scalar value c. 466 467 If map[b] is -1, then the byte sequence is malformed. 468 469 If map[b] is -n, where n >= 2, then b is the first byte of an 470 n-byte sequence that encodes a single Unicode scalar value. 471 472 The data member will be passed as the first argument to the convert 473 function. 474 475 The convert function is used to convert multibyte sequences; s will 476 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 477 convert function must return the Unicode scalar value represented 478 by this byte sequence or -1 if the byte sequence is malformed. 479 480 The convert function may be NULL if the encoding is a single-byte 481 encoding, that is if map[b] >= -1 for all bytes b. 482 483 When the parser is finished with the encoding, then if release is 484 not NULL, it will call release passing it the data member; once 485 release has been called, the convert function will not be called 486 again. 487 488 Expat places certain restrictions on the encodings that are supported 489 using this mechanism. 490 491 1. Every ASCII character that can appear in a well-formed XML document, 492 other than the characters 493 494 $@\^`{}~ 495 496 must be represented by a single byte, and that byte must be the 497 same byte that represents that character in ASCII. 498 499 2. No character may require more than 4 bytes to encode. 500 501 3. All characters encoded must have Unicode scalar values <= 502 0xFFFF, (i.e., characters that would be encoded by surrogates in 503 UTF-16 are not allowed). Note that this restriction doesn't 504 apply to the built-in support for UTF-8 and UTF-16. 505 506 4. No Unicode character may be encoded by more than one distinct 507 sequence of bytes. 508 */ 509 typedef struct { 510 int map[256]; 511 void *data; 512 int(XMLCALL *convert)(void *data, const char *s); 513 void(XMLCALL *release)(void *data); 514 } XML_Encoding; 515 516 /* This is called for an encoding that is unknown to the parser. 517 518 The encodingHandlerData argument is that which was passed as the 519 second argument to XML_SetUnknownEncodingHandler. 520 521 The name argument gives the name of the encoding as specified in 522 the encoding declaration. 523 524 If the callback can provide information about the encoding, it must 525 fill in the XML_Encoding structure, and return XML_STATUS_OK. 526 Otherwise it must return XML_STATUS_ERROR. 527 528 If info does not describe a suitable encoding, then the parser will 529 return an XML_ERROR_UNKNOWN_ENCODING error. 530 */ 531 typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, 532 const XML_Char *name, 533 XML_Encoding *info); 534 535 XMLPARSEAPI(void) 536 XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, 537 XML_EndElementHandler end); 538 539 XMLPARSEAPI(void) 540 XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler); 541 542 XMLPARSEAPI(void) 543 XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler); 544 545 XMLPARSEAPI(void) 546 XML_SetCharacterDataHandler(XML_Parser parser, 547 XML_CharacterDataHandler handler); 548 549 XMLPARSEAPI(void) 550 XML_SetProcessingInstructionHandler(XML_Parser parser, 551 XML_ProcessingInstructionHandler handler); 552 XMLPARSEAPI(void) 553 XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler); 554 555 XMLPARSEAPI(void) 556 XML_SetCdataSectionHandler(XML_Parser parser, 557 XML_StartCdataSectionHandler start, 558 XML_EndCdataSectionHandler end); 559 560 XMLPARSEAPI(void) 561 XML_SetStartCdataSectionHandler(XML_Parser parser, 562 XML_StartCdataSectionHandler start); 563 564 XMLPARSEAPI(void) 565 XML_SetEndCdataSectionHandler(XML_Parser parser, 566 XML_EndCdataSectionHandler end); 567 568 /* This sets the default handler and also inhibits expansion of 569 internal entities. These entity references will be passed to the 570 default handler, or to the skipped entity handler, if one is set. 571 */ 572 XMLPARSEAPI(void) 573 XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler); 574 575 /* This sets the default handler but does not inhibit expansion of 576 internal entities. The entity reference will not be passed to the 577 default handler. 578 */ 579 XMLPARSEAPI(void) 580 XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler); 581 582 XMLPARSEAPI(void) 583 XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, 584 XML_EndDoctypeDeclHandler end); 585 586 XMLPARSEAPI(void) 587 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 588 XML_StartDoctypeDeclHandler start); 589 590 XMLPARSEAPI(void) 591 XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end); 592 593 XMLPARSEAPI(void) 594 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 595 XML_UnparsedEntityDeclHandler handler); 596 597 XMLPARSEAPI(void) 598 XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler); 599 600 XMLPARSEAPI(void) 601 XML_SetNamespaceDeclHandler(XML_Parser parser, 602 XML_StartNamespaceDeclHandler start, 603 XML_EndNamespaceDeclHandler end); 604 605 XMLPARSEAPI(void) 606 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 607 XML_StartNamespaceDeclHandler start); 608 609 XMLPARSEAPI(void) 610 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 611 XML_EndNamespaceDeclHandler end); 612 613 XMLPARSEAPI(void) 614 XML_SetNotStandaloneHandler(XML_Parser parser, 615 XML_NotStandaloneHandler handler); 616 617 XMLPARSEAPI(void) 618 XML_SetExternalEntityRefHandler(XML_Parser parser, 619 XML_ExternalEntityRefHandler handler); 620 621 /* If a non-NULL value for arg is specified here, then it will be 622 passed as the first argument to the external entity ref handler 623 instead of the parser object. 624 */ 625 XMLPARSEAPI(void) 626 XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg); 627 628 XMLPARSEAPI(void) 629 XML_SetSkippedEntityHandler(XML_Parser parser, 630 XML_SkippedEntityHandler handler); 631 632 XMLPARSEAPI(void) 633 XML_SetUnknownEncodingHandler(XML_Parser parser, 634 XML_UnknownEncodingHandler handler, 635 void *encodingHandlerData); 636 637 /* This can be called within a handler for a start element, end 638 element, processing instruction or character data. It causes the 639 corresponding markup to be passed to the default handler. 640 */ 641 XMLPARSEAPI(void) 642 XML_DefaultCurrent(XML_Parser parser); 643 644 /* If do_nst is non-zero, and namespace processing is in effect, and 645 a name has a prefix (i.e. an explicit namespace qualifier) then 646 that name is returned as a triplet in a single string separated by 647 the separator character specified when the parser was created: URI 648 + sep + local_name + sep + prefix. 649 650 If do_nst is zero, then namespace information is returned in the 651 default manner (URI + sep + local_name) whether or not the name 652 has a prefix. 653 654 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 655 XML_ParseBuffer has no effect. 656 */ 657 658 XMLPARSEAPI(void) 659 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 660 661 /* This value is passed as the userData argument to callbacks. */ 662 XMLPARSEAPI(void) 663 XML_SetUserData(XML_Parser parser, void *userData); 664 665 /* Returns the last value set by XML_SetUserData or NULL. */ 666 #define XML_GetUserData(parser) (*(void **)(parser)) 667 668 /* This is equivalent to supplying an encoding argument to 669 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 670 zero otherwise. 671 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 672 has no effect and returns XML_STATUS_ERROR. 673 */ 674 XMLPARSEAPI(enum XML_Status) 675 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 676 677 /* If this function is called, then the parser will be passed as the 678 first argument to callbacks instead of userData. The userData will 679 still be accessible using XML_GetUserData. 680 */ 681 XMLPARSEAPI(void) 682 XML_UseParserAsHandlerArg(XML_Parser parser); 683 684 /* If useDTD == XML_TRUE is passed to this function, then the parser 685 will assume that there is an external subset, even if none is 686 specified in the document. In such a case the parser will call the 687 externalEntityRefHandler with a value of NULL for the systemId 688 argument (the publicId and context arguments will be NULL as well). 689 Note: For the purpose of checking WFC: Entity Declared, passing 690 useDTD == XML_TRUE will make the parser behave as if the document 691 had a DTD with an external subset. 692 Note: If this function is called, then this must be done before 693 the first call to XML_Parse or XML_ParseBuffer, since it will 694 have no effect after that. Returns 695 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 696 Note: If the document does not have a DOCTYPE declaration at all, 697 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 698 be called, despite an external subset being parsed. 699 Note: If XML_DTD is not defined when Expat is compiled, returns 700 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 701 Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. 702 */ 703 XMLPARSEAPI(enum XML_Error) 704 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 705 706 /* Sets the base to be used for resolving relative URIs in system 707 identifiers in declarations. Resolving relative identifiers is 708 left to the application: this value will be passed through as the 709 base argument to the XML_ExternalEntityRefHandler, 710 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 711 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 712 XML_STATUS_OK otherwise. 713 */ 714 XMLPARSEAPI(enum XML_Status) 715 XML_SetBase(XML_Parser parser, const XML_Char *base); 716 717 XMLPARSEAPI(const XML_Char *) 718 XML_GetBase(XML_Parser parser); 719 720 /* Returns the number of the attribute/value pairs passed in last call 721 to the XML_StartElementHandler that were specified in the start-tag 722 rather than defaulted. Each attribute/value pair counts as 2; thus 723 this corresponds to an index into the atts array passed to the 724 XML_StartElementHandler. Returns -1 if parser == NULL. 725 */ 726 XMLPARSEAPI(int) 727 XML_GetSpecifiedAttributeCount(XML_Parser parser); 728 729 /* Returns the index of the ID attribute passed in the last call to 730 XML_StartElementHandler, or -1 if there is no ID attribute or 731 parser == NULL. Each attribute/value pair counts as 2; thus this 732 corresponds to an index into the atts array passed to the 733 XML_StartElementHandler. 734 */ 735 XMLPARSEAPI(int) 736 XML_GetIdAttributeIndex(XML_Parser parser); 737 738 #ifdef XML_ATTR_INFO 739 /* Source file byte offsets for the start and end of attribute names and values. 740 The value indices are exclusive of surrounding quotes; thus in a UTF-8 source 741 file an attribute value of "blah" will yield: 742 info->valueEnd - info->valueStart = 4 bytes. 743 */ 744 typedef struct { 745 XML_Index nameStart; /* Offset to beginning of the attribute name. */ 746 XML_Index nameEnd; /* Offset after the attribute name's last byte. */ 747 XML_Index valueStart; /* Offset to beginning of the attribute value. */ 748 XML_Index valueEnd; /* Offset after the attribute value's last byte. */ 749 } XML_AttrInfo; 750 751 /* Returns an array of XML_AttrInfo structures for the attribute/value pairs 752 passed in last call to the XML_StartElementHandler that were specified 753 in the start-tag rather than defaulted. Each attribute/value pair counts 754 as 1; thus the number of entries in the array is 755 XML_GetSpecifiedAttributeCount(parser) / 2. 756 */ 757 XMLPARSEAPI(const XML_AttrInfo *) 758 XML_GetAttributeInfo(XML_Parser parser); 759 #endif 760 761 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 762 detected. The last call to XML_Parse must have isFinal true; len 763 may be zero for this call (or any other). 764 765 Though the return values for these functions has always been 766 described as a Boolean value, the implementation, at least for the 767 1.95.x series, has always returned exactly one of the XML_Status 768 values. 769 */ 770 XMLPARSEAPI(enum XML_Status) 771 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 772 773 XMLPARSEAPI(void *) 774 XML_GetBuffer(XML_Parser parser, int len); 775 776 XMLPARSEAPI(enum XML_Status) 777 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 778 779 /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 780 Must be called from within a call-back handler, except when aborting 781 (resumable = 0) an already suspended parser. Some call-backs may 782 still follow because they would otherwise get lost. Examples: 783 - endElementHandler() for empty elements when stopped in 784 startElementHandler(), 785 - endNameSpaceDeclHandler() when stopped in endElementHandler(), 786 and possibly others. 787 788 Can be called from most handlers, including DTD related call-backs, 789 except when parsing an external parameter entity and resumable != 0. 790 Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 791 Possible error codes: 792 - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 793 - XML_ERROR_FINISHED: when the parser has already finished. 794 - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 795 796 When resumable != 0 (true) then parsing is suspended, that is, 797 XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 798 Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 799 return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 800 801 *Note*: 802 This will be applied to the current parser instance only, that is, if 803 there is a parent parser then it will continue parsing when the 804 externalEntityRefHandler() returns. It is up to the implementation of 805 the externalEntityRefHandler() to call XML_StopParser() on the parent 806 parser (recursively), if one wants to stop parsing altogether. 807 808 When suspended, parsing can be resumed by calling XML_ResumeParser(). 809 */ 810 XMLPARSEAPI(enum XML_Status) 811 XML_StopParser(XML_Parser parser, XML_Bool resumable); 812 813 /* Resumes parsing after it has been suspended with XML_StopParser(). 814 Must not be called from within a handler call-back. Returns same 815 status codes as XML_Parse() or XML_ParseBuffer(). 816 Additional error code XML_ERROR_NOT_SUSPENDED possible. 817 818 *Note*: 819 This must be called on the most deeply nested child parser instance 820 first, and on its parent parser only after the child parser has finished, 821 to be applied recursively until the document entity's parser is restarted. 822 That is, the parent parser will not resume by itself and it is up to the 823 application to call XML_ResumeParser() on it at the appropriate moment. 824 */ 825 XMLPARSEAPI(enum XML_Status) 826 XML_ResumeParser(XML_Parser parser); 827 828 enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED }; 829 830 typedef struct { 831 enum XML_Parsing parsing; 832 XML_Bool finalBuffer; 833 } XML_ParsingStatus; 834 835 /* Returns status of parser with respect to being initialized, parsing, 836 finished, or suspended and processing the final buffer. 837 XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 838 XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 839 */ 840 XMLPARSEAPI(void) 841 XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 842 843 /* Creates an XML_Parser object that can parse an external general 844 entity; context is a '\0'-terminated string specifying the parse 845 context; encoding is a '\0'-terminated string giving the name of 846 the externally specified encoding, or NULL if there is no 847 externally specified encoding. The context string consists of a 848 sequence of tokens separated by formfeeds (\f); a token consisting 849 of a name specifies that the general entity of the name is open; a 850 token of the form prefix=uri specifies the namespace for a 851 particular prefix; a token of the form =uri specifies the default 852 namespace. This can be called at any point after the first call to 853 an ExternalEntityRefHandler so longer as the parser has not yet 854 been freed. The new parser is completely independent and may 855 safely be used in a separate thread. The handlers and userData are 856 initialized from the parser argument. Returns NULL if out of memory. 857 Otherwise returns a new XML_Parser object. 858 */ 859 XMLPARSEAPI(XML_Parser) 860 XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context, 861 const XML_Char *encoding); 862 863 enum XML_ParamEntityParsing { 864 XML_PARAM_ENTITY_PARSING_NEVER, 865 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 866 XML_PARAM_ENTITY_PARSING_ALWAYS 867 }; 868 869 /* Controls parsing of parameter entities (including the external DTD 870 subset). If parsing of parameter entities is enabled, then 871 references to external parameter entities (including the external 872 DTD subset) will be passed to the handler set with 873 XML_SetExternalEntityRefHandler. The context passed will be 0. 874 875 Unlike external general entities, external parameter entities can 876 only be parsed synchronously. If the external parameter entity is 877 to be parsed, it must be parsed during the call to the external 878 entity ref handler: the complete sequence of 879 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 880 XML_ParserFree calls must be made during this call. After 881 XML_ExternalEntityParserCreate has been called to create the parser 882 for the external parameter entity (context must be 0 for this 883 call), it is illegal to make any calls on the old parser until 884 XML_ParserFree has been called on the newly created parser. 885 If the library has been compiled without support for parameter 886 entity parsing (ie without XML_DTD being defined), then 887 XML_SetParamEntityParsing will return 0 if parsing of parameter 888 entities is requested; otherwise it will return non-zero. 889 Note: If XML_SetParamEntityParsing is called after XML_Parse or 890 XML_ParseBuffer, then it has no effect and will always return 0. 891 Note: If parser == NULL, the function will do nothing and return 0. 892 */ 893 XMLPARSEAPI(int) 894 XML_SetParamEntityParsing(XML_Parser parser, 895 enum XML_ParamEntityParsing parsing); 896 897 /* Sets the hash salt to use for internal hash calculations. 898 Helps in preventing DoS attacks based on predicting hash 899 function behavior. This must be called before parsing is started. 900 Returns 1 if successful, 0 when called after parsing has started. 901 Note: If parser == NULL, the function will do nothing and return 0. 902 */ 903 XMLPARSEAPI(int) 904 XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt); 905 906 /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 907 XML_GetErrorCode returns information about the error. 908 */ 909 XMLPARSEAPI(enum XML_Error) 910 XML_GetErrorCode(XML_Parser parser); 911 912 /* These functions return information about the current parse 913 location. They may be called from any callback called to report 914 some parse event; in this case the location is the location of the 915 first of the sequence of characters that generated the event. When 916 called from callbacks generated by declarations in the document 917 prologue, the location identified isn't as neatly defined, but will 918 be within the relevant markup. When called outside of the callback 919 functions, the position indicated will be just past the last parse 920 event (regardless of whether there was an associated callback). 921 922 They may also be called after returning from a call to XML_Parse 923 or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 924 the location is the location of the character at which the error 925 was detected; otherwise the location is the location of the last 926 parse event, as described above. 927 928 Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber 929 return 0 to indicate an error. 930 Note: XML_GetCurrentByteIndex returns -1 to indicate an error. 931 */ 932 XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); 933 XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); 934 XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); 935 936 /* Return the number of bytes in the current event. 937 Returns 0 if the event is in an internal entity. 938 */ 939 XMLPARSEAPI(int) 940 XML_GetCurrentByteCount(XML_Parser parser); 941 942 /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets 943 the integer pointed to by offset to the offset within this buffer 944 of the current parse position, and sets the integer pointed to by size 945 to the size of this buffer (the number of input bytes). Otherwise 946 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 947 active. 948 949 NOTE: The character pointer returned should not be used outside 950 the handler that makes the call. 951 */ 952 XMLPARSEAPI(const char *) 953 XML_GetInputContext(XML_Parser parser, int *offset, int *size); 954 955 /* For backwards compatibility with previous versions. */ 956 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 957 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 958 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 959 960 /* Frees the content model passed to the element declaration handler */ 961 XMLPARSEAPI(void) 962 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 963 964 /* Exposing the memory handling functions used in Expat */ 965 XMLPARSEAPI(void *) 966 XML_ATTR_MALLOC 967 XML_ATTR_ALLOC_SIZE(2) 968 XML_MemMalloc(XML_Parser parser, size_t size); 969 970 XMLPARSEAPI(void *) 971 XML_ATTR_ALLOC_SIZE(3) 972 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 973 974 XMLPARSEAPI(void) 975 XML_MemFree(XML_Parser parser, void *ptr); 976 977 /* Frees memory used by the parser. */ 978 XMLPARSEAPI(void) 979 XML_ParserFree(XML_Parser parser); 980 981 /* Returns a string describing the error. */ 982 XMLPARSEAPI(const XML_LChar *) 983 XML_ErrorString(enum XML_Error code); 984 985 /* Return a string containing the version number of this expat */ 986 XMLPARSEAPI(const XML_LChar *) 987 XML_ExpatVersion(void); 988 989 typedef struct { 990 int major; 991 int minor; 992 int micro; 993 } XML_Expat_Version; 994 995 /* Return an XML_Expat_Version structure containing numeric version 996 number information for this version of expat. 997 */ 998 XMLPARSEAPI(XML_Expat_Version) 999 XML_ExpatVersionInfo(void); 1000 1001 /* Added in Expat 1.95.5. */ 1002 enum XML_FeatureEnum { 1003 XML_FEATURE_END = 0, 1004 XML_FEATURE_UNICODE, 1005 XML_FEATURE_UNICODE_WCHAR_T, 1006 XML_FEATURE_DTD, 1007 XML_FEATURE_CONTEXT_BYTES, 1008 XML_FEATURE_MIN_SIZE, 1009 XML_FEATURE_SIZEOF_XML_CHAR, 1010 XML_FEATURE_SIZEOF_XML_LCHAR, 1011 XML_FEATURE_NS, 1012 XML_FEATURE_LARGE_SIZE, 1013 XML_FEATURE_ATTR_INFO, 1014 /* Added in Expat 2.4.0. */ 1015 XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, 1016 XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT 1017 /* Additional features must be added to the end of this enum. */ 1018 }; 1019 1020 typedef struct { 1021 enum XML_FeatureEnum feature; 1022 const XML_LChar *name; 1023 long int value; 1024 } XML_Feature; 1025 1026 XMLPARSEAPI(const XML_Feature *) 1027 XML_GetFeatureList(void); 1028 1029 #ifdef XML_DTD 1030 /* Added in Expat 2.4.0. */ 1031 XMLPARSEAPI(XML_Bool) 1032 XML_SetBillionLaughsAttackProtectionMaximumAmplification( 1033 XML_Parser parser, float maximumAmplificationFactor); 1034 1035 /* Added in Expat 2.4.0. */ 1036 XMLPARSEAPI(XML_Bool) 1037 XML_SetBillionLaughsAttackProtectionActivationThreshold( 1038 XML_Parser parser, unsigned long long activationThresholdBytes); 1039 #endif 1040 1041 /* Expat follows the semantic versioning convention. 1042 See http://semver.org. 1043 */ 1044 #define XML_MAJOR_VERSION 2 1045 #define XML_MINOR_VERSION 4 1046 #define XML_MICRO_VERSION 1 1047 1048 #ifdef __cplusplus 1049 } 1050 #endif 1051 1052 #endif /* not Expat_INCLUDED */ 1053