1 /* 2 __ __ _ 3 ___\ \/ /_ __ __ _| |_ 4 / _ \\ /| '_ \ / _` | __| 5 | __// \| |_) | (_| | |_ 6 \___/_/\_\ .__/ \__,_|\__| 7 |_| XML parser 8 9 Copyright (c) 1997-2000 Thai Open Source Software Center Ltd 10 Copyright (c) 2000-2017 Expat development team 11 Licensed under the MIT license: 12 13 Permission is hereby granted, free of charge, to any person obtaining 14 a copy of this software and associated documentation files (the 15 "Software"), to deal in the Software without restriction, including 16 without limitation the rights to use, copy, modify, merge, publish, 17 distribute, sublicense, and/or sell copies of the Software, and to permit 18 persons to whom the Software is furnished to do so, subject to the 19 following conditions: 20 21 The above copyright notice and this permission notice shall be included 22 in all copies or substantial portions of the Software. 23 24 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 25 EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 26 MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN 27 NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 28 DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 29 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 30 USE OR OTHER DEALINGS IN THE SOFTWARE. 31 */ 32 33 #ifndef Expat_INCLUDED 34 #define Expat_INCLUDED 1 35 36 #ifdef __VMS 37 /* 0 1 2 3 0 1 2 3 38 1234567890123456789012345678901 1234567890123456789012345678901 */ 39 #define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler 40 #define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler 41 #define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler 42 #define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg 43 #endif 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 }; 129 130 enum XML_Content_Type { 131 XML_CTYPE_EMPTY = 1, 132 XML_CTYPE_ANY, 133 XML_CTYPE_MIXED, 134 XML_CTYPE_NAME, 135 XML_CTYPE_CHOICE, 136 XML_CTYPE_SEQ 137 }; 138 139 enum XML_Content_Quant { 140 XML_CQUANT_NONE, 141 XML_CQUANT_OPT, 142 XML_CQUANT_REP, 143 XML_CQUANT_PLUS 144 }; 145 146 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 147 XML_CQUANT_NONE, and the other fields will be zero or NULL. 148 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 149 numchildren will contain number of elements that may be mixed in 150 and children point to an array of XML_Content cells that will be 151 all of XML_CTYPE_NAME type with no quantification. 152 153 If type == XML_CTYPE_NAME, then the name points to the name, and 154 the numchildren field will be zero and children will be NULL. The 155 quant fields indicates any quantifiers placed on the name. 156 157 CHOICE and SEQ will have name NULL, the number of children in 158 numchildren and children will point, recursively, to an array 159 of XML_Content cells. 160 161 The EMPTY, ANY, and MIXED types will only occur at top level. 162 */ 163 164 typedef struct XML_cp XML_Content; 165 166 struct XML_cp { 167 enum XML_Content_Type type; 168 enum XML_Content_Quant quant; 169 XML_Char * name; 170 unsigned int numchildren; 171 XML_Content * children; 172 }; 173 174 175 /* This is called for an element declaration. See above for 176 description of the model argument. It's the caller's responsibility 177 to free model when finished with it. 178 */ 179 typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, 180 const XML_Char *name, 181 XML_Content *model); 182 183 XMLPARSEAPI(void) 184 XML_SetElementDeclHandler(XML_Parser parser, 185 XML_ElementDeclHandler eldecl); 186 187 /* The Attlist declaration handler is called for *each* attribute. So 188 a single Attlist declaration with multiple attributes declared will 189 generate multiple calls to this handler. The "default" parameter 190 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 191 keyword. The "isrequired" parameter will be true and the default 192 value will be NULL in the case of "#REQUIRED". If "isrequired" is 193 true and default is non-NULL, then this is a "#FIXED" default. 194 */ 195 typedef void (XMLCALL *XML_AttlistDeclHandler) ( 196 void *userData, 197 const XML_Char *elname, 198 const XML_Char *attname, 199 const XML_Char *att_type, 200 const XML_Char *dflt, 201 int isrequired); 202 203 XMLPARSEAPI(void) 204 XML_SetAttlistDeclHandler(XML_Parser parser, 205 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, 222 XML_XmlDeclHandler xmldecl); 223 224 225 typedef struct { 226 void *(*malloc_fcn)(size_t size); 227 void *(*realloc_fcn)(void *ptr, size_t size); 228 void (*free_fcn)(void *ptr); 229 } XML_Memory_Handling_Suite; 230 231 /* Constructs a new parser; encoding is the encoding specified by the 232 external protocol or NULL if there is none specified. 233 */ 234 XMLPARSEAPI(XML_Parser) 235 XML_ParserCreate(const XML_Char *encoding); 236 237 /* Constructs a new parser and namespace processor. Element type 238 names and attribute names that belong to a namespace will be 239 expanded; unprefixed attribute names are never expanded; unprefixed 240 element type names are expanded only if there is a default 241 namespace. The expanded name is the concatenation of the namespace 242 URI, the namespace separator character, and the local part of the 243 name. If the namespace separator is '\0' then the namespace URI 244 and the local part will be concatenated without any separator. 245 It is a programming error to use the separator '\0' with namespace 246 triplets (see XML_SetReturnNSTriplet). 247 */ 248 XMLPARSEAPI(XML_Parser) 249 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 250 251 252 /* Constructs a new parser using the memory management suite referred to 253 by memsuite. If memsuite is NULL, then use the standard library memory 254 suite. If namespaceSeparator is non-NULL it creates a parser with 255 namespace processing as described above. The character pointed at 256 will serve as the namespace separator. 257 258 All further memory operations used for the created parser will come from 259 the given suite. 260 */ 261 XMLPARSEAPI(XML_Parser) 262 XML_ParserCreate_MM(const XML_Char *encoding, 263 const XML_Memory_Handling_Suite *memsuite, 264 const XML_Char *namespaceSeparator); 265 266 /* Prepare a parser object to be re-used. This is particularly 267 valuable when memory allocation overhead is disproportionately high, 268 such as when a large number of small documnents need to be parsed. 269 All handlers are cleared from the parser, except for the 270 unknownEncodingHandler. The parser's external state is re-initialized 271 except for the values of ns and ns_triplets. 272 273 Added in Expat 1.95.3. 274 */ 275 XMLPARSEAPI(XML_Bool) 276 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 277 278 /* atts is array of name/value pairs, terminated by 0; 279 names and values are 0 terminated. 280 */ 281 typedef void (XMLCALL *XML_StartElementHandler) (void *userData, 282 const XML_Char *name, 283 const XML_Char **atts); 284 285 typedef void (XMLCALL *XML_EndElementHandler) (void *userData, 286 const XML_Char *name); 287 288 289 /* s is not 0 terminated. */ 290 typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, 291 const XML_Char *s, 292 int len); 293 294 /* target and data are 0 terminated */ 295 typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( 296 void *userData, 297 const XML_Char *target, 298 const XML_Char *data); 299 300 /* data is 0 terminated */ 301 typedef void (XMLCALL *XML_CommentHandler) (void *userData, 302 const XML_Char *data); 303 304 typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); 305 typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); 306 307 /* This is called for any characters in the XML document for which 308 there is no applicable handler. This includes both characters that 309 are part of markup which is of a kind that is not reported 310 (comments, markup declarations), or characters that are part of a 311 construct which could be reported but for which no handler has been 312 supplied. The characters are passed exactly as they were in the XML 313 document except that they will be encoded in UTF-8 or UTF-16. 314 Line boundaries are not normalized. Note that a byte order mark 315 character is not passed to the default handler. There are no 316 guarantees about how characters are divided between calls to the 317 default handler: for example, a comment might be split between 318 multiple calls. 319 */ 320 typedef void (XMLCALL *XML_DefaultHandler) (void *userData, 321 const XML_Char *s, 322 int len); 323 324 /* This is called for the start of the DOCTYPE declaration, before 325 any DTD or internal subset is parsed. 326 */ 327 typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( 328 void *userData, 329 const XML_Char *doctypeName, 330 const XML_Char *sysid, 331 const XML_Char *pubid, 332 int has_internal_subset); 333 334 /* This is called for the start of the DOCTYPE declaration when the 335 closing > is encountered, but after processing any external 336 subset. 337 */ 338 typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 339 340 /* This is called for entity declarations. The is_parameter_entity 341 argument will be non-zero if the entity is a parameter entity, zero 342 otherwise. 343 344 For internal entities (<!ENTITY foo "bar">), value will 345 be non-NULL and systemId, publicID, and notationName will be NULL. 346 The value string is NOT nul-terminated; the length is provided in 347 the value_length argument. Since it is legal to have zero-length 348 values, do not use this argument to test for internal entities. 349 350 For external entities, value will be NULL and systemId will be 351 non-NULL. The publicId argument will be NULL unless a public 352 identifier was provided. The notationName argument will have a 353 non-NULL value only for unparsed entity declarations. 354 355 Note that is_parameter_entity can't be changed to XML_Bool, since 356 that would break binary compatibility. 357 */ 358 typedef void (XMLCALL *XML_EntityDeclHandler) ( 359 void *userData, 360 const XML_Char *entityName, 361 int is_parameter_entity, 362 const XML_Char *value, 363 int value_length, 364 const XML_Char *base, 365 const XML_Char *systemId, 366 const XML_Char *publicId, 367 const XML_Char *notationName); 368 369 XMLPARSEAPI(void) 370 XML_SetEntityDeclHandler(XML_Parser parser, 371 XML_EntityDeclHandler handler); 372 373 /* OBSOLETE -- OBSOLETE -- OBSOLETE 374 This handler has been superseded by the EntityDeclHandler above. 375 It is provided here for backward compatibility. 376 377 This is called for a declaration of an unparsed (NDATA) entity. 378 The base argument is whatever was set by XML_SetBase. The 379 entityName, systemId and notationName arguments will never be 380 NULL. The other arguments may be. 381 */ 382 typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( 383 void *userData, 384 const XML_Char *entityName, 385 const XML_Char *base, 386 const XML_Char *systemId, 387 const XML_Char *publicId, 388 const XML_Char *notationName); 389 390 /* This is called for a declaration of notation. The base argument is 391 whatever was set by XML_SetBase. The notationName will never be 392 NULL. The other arguments can be. 393 */ 394 typedef void (XMLCALL *XML_NotationDeclHandler) ( 395 void *userData, 396 const XML_Char *notationName, 397 const XML_Char *base, 398 const XML_Char *systemId, 399 const XML_Char *publicId); 400 401 /* When namespace processing is enabled, these are called once for 402 each namespace declaration. The call to the start and end element 403 handlers occur between the calls to the start and end namespace 404 declaration handlers. For an xmlns attribute, prefix will be 405 NULL. For an xmlns="" attribute, uri will be NULL. 406 */ 407 typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( 408 void *userData, 409 const XML_Char *prefix, 410 const XML_Char *uri); 411 412 typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( 413 void *userData, 414 const XML_Char *prefix); 415 416 /* This is called if the document is not standalone, that is, it has an 417 external subset or a reference to a parameter entity, but does not 418 have standalone="yes". If this handler returns XML_STATUS_ERROR, 419 then processing will not continue, and the parser will return a 420 XML_ERROR_NOT_STANDALONE error. 421 If parameter entity parsing is enabled, then in addition to the 422 conditions above this handler will only be called if the referenced 423 entity was actually read. 424 */ 425 typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); 426 427 /* This is called for a reference to an external parsed general 428 entity. The referenced entity is not automatically parsed. The 429 application can parse it immediately or later using 430 XML_ExternalEntityParserCreate. 431 432 The parser argument is the parser parsing the entity containing the 433 reference; it can be passed as the parser argument to 434 XML_ExternalEntityParserCreate. The systemId argument is the 435 system identifier as specified in the entity declaration; it will 436 not be NULL. 437 438 The base argument is the system identifier that should be used as 439 the base for resolving systemId if systemId was relative; this is 440 set by XML_SetBase; it may be NULL. 441 442 The publicId argument is the public identifier as specified in the 443 entity declaration, or NULL if none was specified; the whitespace 444 in the public identifier will have been normalized as required by 445 the XML spec. 446 447 The context argument specifies the parsing context in the format 448 expected by the context argument to XML_ExternalEntityParserCreate; 449 context is valid only until the handler returns, so if the 450 referenced entity is to be parsed later, it must be copied. 451 context is NULL only when the entity is a parameter entity. 452 453 The handler should return XML_STATUS_ERROR if processing should not 454 continue because of a fatal error in the handling of the external 455 entity. In this case the calling parser will return an 456 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 457 458 Note that unlike other handlers the first argument is the parser, 459 not userData. 460 */ 461 typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( 462 XML_Parser parser, 463 const XML_Char *context, 464 const XML_Char *base, 465 const XML_Char *systemId, 466 const XML_Char *publicId); 467 468 /* This is called in two situations: 469 1) An entity reference is encountered for which no declaration 470 has been read *and* this is not an error. 471 2) An internal entity reference is read, but not expanded, because 472 XML_SetDefaultHandler has been called. 473 Note: skipped parameter entities in declarations and skipped general 474 entities in attribute values cannot be reported, because 475 the event would be out of sync with the reporting of the 476 declarations or attribute values 477 */ 478 typedef void (XMLCALL *XML_SkippedEntityHandler) ( 479 void *userData, 480 const XML_Char *entityName, 481 int is_parameter_entity); 482 483 /* This structure is filled in by the XML_UnknownEncodingHandler to 484 provide information to the parser about encodings that are unknown 485 to the parser. 486 487 The map[b] member gives information about byte sequences whose 488 first byte is b. 489 490 If map[b] is c where c is >= 0, then b by itself encodes the 491 Unicode scalar value c. 492 493 If map[b] is -1, then the byte sequence is malformed. 494 495 If map[b] is -n, where n >= 2, then b is the first byte of an 496 n-byte sequence that encodes a single Unicode scalar value. 497 498 The data member will be passed as the first argument to the convert 499 function. 500 501 The convert function is used to convert multibyte sequences; s will 502 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 503 convert function must return the Unicode scalar value represented 504 by this byte sequence or -1 if the byte sequence is malformed. 505 506 The convert function may be NULL if the encoding is a single-byte 507 encoding, that is if map[b] >= -1 for all bytes b. 508 509 When the parser is finished with the encoding, then if release is 510 not NULL, it will call release passing it the data member; once 511 release has been called, the convert function will not be called 512 again. 513 514 Expat places certain restrictions on the encodings that are supported 515 using this mechanism. 516 517 1. Every ASCII character that can appear in a well-formed XML document, 518 other than the characters 519 520 $@\^`{}~ 521 522 must be represented by a single byte, and that byte must be the 523 same byte that represents that character in ASCII. 524 525 2. No character may require more than 4 bytes to encode. 526 527 3. All characters encoded must have Unicode scalar values <= 528 0xFFFF, (i.e., characters that would be encoded by surrogates in 529 UTF-16 are not allowed). Note that this restriction doesn't 530 apply to the built-in support for UTF-8 and UTF-16. 531 532 4. No Unicode character may be encoded by more than one distinct 533 sequence of bytes. 534 */ 535 typedef struct { 536 int map[256]; 537 void *data; 538 int (XMLCALL *convert)(void *data, const char *s); 539 void (XMLCALL *release)(void *data); 540 } XML_Encoding; 541 542 /* This is called for an encoding that is unknown to the parser. 543 544 The encodingHandlerData argument is that which was passed as the 545 second argument to XML_SetUnknownEncodingHandler. 546 547 The name argument gives the name of the encoding as specified in 548 the encoding declaration. 549 550 If the callback can provide information about the encoding, it must 551 fill in the XML_Encoding structure, and return XML_STATUS_OK. 552 Otherwise it must return XML_STATUS_ERROR. 553 554 If info does not describe a suitable encoding, then the parser will 555 return an XML_UNKNOWN_ENCODING error. 556 */ 557 typedef int (XMLCALL *XML_UnknownEncodingHandler) ( 558 void *encodingHandlerData, 559 const XML_Char *name, 560 XML_Encoding *info); 561 562 XMLPARSEAPI(void) 563 XML_SetElementHandler(XML_Parser parser, 564 XML_StartElementHandler start, 565 XML_EndElementHandler end); 566 567 XMLPARSEAPI(void) 568 XML_SetStartElementHandler(XML_Parser parser, 569 XML_StartElementHandler handler); 570 571 XMLPARSEAPI(void) 572 XML_SetEndElementHandler(XML_Parser parser, 573 XML_EndElementHandler handler); 574 575 XMLPARSEAPI(void) 576 XML_SetCharacterDataHandler(XML_Parser parser, 577 XML_CharacterDataHandler handler); 578 579 XMLPARSEAPI(void) 580 XML_SetProcessingInstructionHandler(XML_Parser parser, 581 XML_ProcessingInstructionHandler handler); 582 XMLPARSEAPI(void) 583 XML_SetCommentHandler(XML_Parser parser, 584 XML_CommentHandler handler); 585 586 XMLPARSEAPI(void) 587 XML_SetCdataSectionHandler(XML_Parser parser, 588 XML_StartCdataSectionHandler start, 589 XML_EndCdataSectionHandler end); 590 591 XMLPARSEAPI(void) 592 XML_SetStartCdataSectionHandler(XML_Parser parser, 593 XML_StartCdataSectionHandler start); 594 595 XMLPARSEAPI(void) 596 XML_SetEndCdataSectionHandler(XML_Parser parser, 597 XML_EndCdataSectionHandler end); 598 599 /* This sets the default handler and also inhibits expansion of 600 internal entities. These entity references will be passed to the 601 default handler, or to the skipped entity handler, if one is set. 602 */ 603 XMLPARSEAPI(void) 604 XML_SetDefaultHandler(XML_Parser parser, 605 XML_DefaultHandler handler); 606 607 /* This sets the default handler but does not inhibit expansion of 608 internal entities. The entity reference will not be passed to the 609 default handler. 610 */ 611 XMLPARSEAPI(void) 612 XML_SetDefaultHandlerExpand(XML_Parser parser, 613 XML_DefaultHandler handler); 614 615 XMLPARSEAPI(void) 616 XML_SetDoctypeDeclHandler(XML_Parser parser, 617 XML_StartDoctypeDeclHandler start, 618 XML_EndDoctypeDeclHandler end); 619 620 XMLPARSEAPI(void) 621 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 622 XML_StartDoctypeDeclHandler start); 623 624 XMLPARSEAPI(void) 625 XML_SetEndDoctypeDeclHandler(XML_Parser parser, 626 XML_EndDoctypeDeclHandler end); 627 628 XMLPARSEAPI(void) 629 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 630 XML_UnparsedEntityDeclHandler handler); 631 632 XMLPARSEAPI(void) 633 XML_SetNotationDeclHandler(XML_Parser parser, 634 XML_NotationDeclHandler handler); 635 636 XMLPARSEAPI(void) 637 XML_SetNamespaceDeclHandler(XML_Parser parser, 638 XML_StartNamespaceDeclHandler start, 639 XML_EndNamespaceDeclHandler end); 640 641 XMLPARSEAPI(void) 642 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 643 XML_StartNamespaceDeclHandler start); 644 645 XMLPARSEAPI(void) 646 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 647 XML_EndNamespaceDeclHandler end); 648 649 XMLPARSEAPI(void) 650 XML_SetNotStandaloneHandler(XML_Parser parser, 651 XML_NotStandaloneHandler handler); 652 653 XMLPARSEAPI(void) 654 XML_SetExternalEntityRefHandler(XML_Parser parser, 655 XML_ExternalEntityRefHandler handler); 656 657 /* If a non-NULL value for arg is specified here, then it will be 658 passed as the first argument to the external entity ref handler 659 instead of the parser object. 660 */ 661 XMLPARSEAPI(void) 662 XML_SetExternalEntityRefHandlerArg(XML_Parser parser, 663 void *arg); 664 665 XMLPARSEAPI(void) 666 XML_SetSkippedEntityHandler(XML_Parser parser, 667 XML_SkippedEntityHandler handler); 668 669 XMLPARSEAPI(void) 670 XML_SetUnknownEncodingHandler(XML_Parser parser, 671 XML_UnknownEncodingHandler handler, 672 void *encodingHandlerData); 673 674 /* This can be called within a handler for a start element, end 675 element, processing instruction or character data. It causes the 676 corresponding markup to be passed to the default handler. 677 */ 678 XMLPARSEAPI(void) 679 XML_DefaultCurrent(XML_Parser parser); 680 681 /* If do_nst is non-zero, and namespace processing is in effect, and 682 a name has a prefix (i.e. an explicit namespace qualifier) then 683 that name is returned as a triplet in a single string separated by 684 the separator character specified when the parser was created: URI 685 + sep + local_name + sep + prefix. 686 687 If do_nst is zero, then namespace information is returned in the 688 default manner (URI + sep + local_name) whether or not the name 689 has a prefix. 690 691 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 692 XML_ParseBuffer has no effect. 693 */ 694 695 XMLPARSEAPI(void) 696 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 697 698 /* This value is passed as the userData argument to callbacks. */ 699 XMLPARSEAPI(void) 700 XML_SetUserData(XML_Parser parser, void *userData); 701 702 /* Returns the last value set by XML_SetUserData or NULL. */ 703 #define XML_GetUserData(parser) (*(void **)(parser)) 704 705 /* This is equivalent to supplying an encoding argument to 706 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 707 zero otherwise. 708 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 709 has no effect and returns XML_STATUS_ERROR. 710 */ 711 XMLPARSEAPI(enum XML_Status) 712 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 713 714 /* If this function is called, then the parser will be passed as the 715 first argument to callbacks instead of userData. The userData will 716 still be accessible using XML_GetUserData. 717 */ 718 XMLPARSEAPI(void) 719 XML_UseParserAsHandlerArg(XML_Parser parser); 720 721 /* If useDTD == XML_TRUE is passed to this function, then the parser 722 will assume that there is an external subset, even if none is 723 specified in the document. In such a case the parser will call the 724 externalEntityRefHandler with a value of NULL for the systemId 725 argument (the publicId and context arguments will be NULL as well). 726 Note: For the purpose of checking WFC: Entity Declared, passing 727 useDTD == XML_TRUE will make the parser behave as if the document 728 had a DTD with an external subset. 729 Note: If this function is called, then this must be done before 730 the first call to XML_Parse or XML_ParseBuffer, since it will 731 have no effect after that. Returns 732 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 733 Note: If the document does not have a DOCTYPE declaration at all, 734 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 735 be called, despite an external subset being parsed. 736 Note: If XML_DTD is not defined when Expat is compiled, returns 737 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 738 Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. 739 */ 740 XMLPARSEAPI(enum XML_Error) 741 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 742 743 744 /* Sets the base to be used for resolving relative URIs in system 745 identifiers in declarations. Resolving relative identifiers is 746 left to the application: this value will be passed through as the 747 base argument to the XML_ExternalEntityRefHandler, 748 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 749 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 750 XML_STATUS_OK otherwise. 751 */ 752 XMLPARSEAPI(enum XML_Status) 753 XML_SetBase(XML_Parser parser, const XML_Char *base); 754 755 XMLPARSEAPI(const XML_Char *) 756 XML_GetBase(XML_Parser parser); 757 758 /* Returns the number of the attribute/value pairs passed in last call 759 to the XML_StartElementHandler that were specified in the start-tag 760 rather than defaulted. Each attribute/value pair counts as 2; thus 761 this correspondds to an index into the atts array passed to the 762 XML_StartElementHandler. Returns -1 if parser == NULL. 763 */ 764 XMLPARSEAPI(int) 765 XML_GetSpecifiedAttributeCount(XML_Parser parser); 766 767 /* Returns the index of the ID attribute passed in the last call to 768 XML_StartElementHandler, or -1 if there is no ID attribute or 769 parser == NULL. Each attribute/value pair counts as 2; thus this 770 correspondds to an index into the atts array passed to the 771 XML_StartElementHandler. 772 */ 773 XMLPARSEAPI(int) 774 XML_GetIdAttributeIndex(XML_Parser parser); 775 776 #ifdef XML_ATTR_INFO 777 /* Source file byte offsets for the start and end of attribute names and values. 778 The value indices are exclusive of surrounding quotes; thus in a UTF-8 source 779 file an attribute value of "blah" will yield: 780 info->valueEnd - info->valueStart = 4 bytes. 781 */ 782 typedef struct { 783 XML_Index nameStart; /* Offset to beginning of the attribute name. */ 784 XML_Index nameEnd; /* Offset after the attribute name's last byte. */ 785 XML_Index valueStart; /* Offset to beginning of the attribute value. */ 786 XML_Index valueEnd; /* Offset after the attribute value's last byte. */ 787 } XML_AttrInfo; 788 789 /* Returns an array of XML_AttrInfo structures for the attribute/value pairs 790 passed in last call to the XML_StartElementHandler that were specified 791 in the start-tag rather than defaulted. Each attribute/value pair counts 792 as 1; thus the number of entries in the array is 793 XML_GetSpecifiedAttributeCount(parser) / 2. 794 */ 795 XMLPARSEAPI(const XML_AttrInfo *) 796 XML_GetAttributeInfo(XML_Parser parser); 797 #endif 798 799 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 800 detected. The last call to XML_Parse must have isFinal true; len 801 may be zero for this call (or any other). 802 803 Though the return values for these functions has always been 804 described as a Boolean value, the implementation, at least for the 805 1.95.x series, has always returned exactly one of the XML_Status 806 values. 807 */ 808 XMLPARSEAPI(enum XML_Status) 809 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 810 811 XMLPARSEAPI(void *) 812 XML_GetBuffer(XML_Parser parser, int len); 813 814 XMLPARSEAPI(enum XML_Status) 815 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 816 817 /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 818 Must be called from within a call-back handler, except when aborting 819 (resumable = 0) an already suspended parser. Some call-backs may 820 still follow because they would otherwise get lost. Examples: 821 - endElementHandler() for empty elements when stopped in 822 startElementHandler(), 823 - endNameSpaceDeclHandler() when stopped in endElementHandler(), 824 and possibly others. 825 826 Can be called from most handlers, including DTD related call-backs, 827 except when parsing an external parameter entity and resumable != 0. 828 Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 829 Possible error codes: 830 - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 831 - XML_ERROR_FINISHED: when the parser has already finished. 832 - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 833 834 When resumable != 0 (true) then parsing is suspended, that is, 835 XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 836 Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 837 return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 838 839 *Note*: 840 This will be applied to the current parser instance only, that is, if 841 there is a parent parser then it will continue parsing when the 842 externalEntityRefHandler() returns. It is up to the implementation of 843 the externalEntityRefHandler() to call XML_StopParser() on the parent 844 parser (recursively), if one wants to stop parsing altogether. 845 846 When suspended, parsing can be resumed by calling XML_ResumeParser(). 847 */ 848 XMLPARSEAPI(enum XML_Status) 849 XML_StopParser(XML_Parser parser, XML_Bool resumable); 850 851 /* Resumes parsing after it has been suspended with XML_StopParser(). 852 Must not be called from within a handler call-back. Returns same 853 status codes as XML_Parse() or XML_ParseBuffer(). 854 Additional error code XML_ERROR_NOT_SUSPENDED possible. 855 856 *Note*: 857 This must be called on the most deeply nested child parser instance 858 first, and on its parent parser only after the child parser has finished, 859 to be applied recursively until the document entity's parser is restarted. 860 That is, the parent parser will not resume by itself and it is up to the 861 application to call XML_ResumeParser() on it at the appropriate moment. 862 */ 863 XMLPARSEAPI(enum XML_Status) 864 XML_ResumeParser(XML_Parser parser); 865 866 enum XML_Parsing { 867 XML_INITIALIZED, 868 XML_PARSING, 869 XML_FINISHED, 870 XML_SUSPENDED 871 }; 872 873 typedef struct { 874 enum XML_Parsing parsing; 875 XML_Bool finalBuffer; 876 } XML_ParsingStatus; 877 878 /* Returns status of parser with respect to being initialized, parsing, 879 finished, or suspended and processing the final buffer. 880 XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 881 XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 882 */ 883 XMLPARSEAPI(void) 884 XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 885 886 /* Creates an XML_Parser object that can parse an external general 887 entity; context is a '\0'-terminated string specifying the parse 888 context; encoding is a '\0'-terminated string giving the name of 889 the externally specified encoding, or NULL if there is no 890 externally specified encoding. The context string consists of a 891 sequence of tokens separated by formfeeds (\f); a token consisting 892 of a name specifies that the general entity of the name is open; a 893 token of the form prefix=uri specifies the namespace for a 894 particular prefix; a token of the form =uri specifies the default 895 namespace. This can be called at any point after the first call to 896 an ExternalEntityRefHandler so longer as the parser has not yet 897 been freed. The new parser is completely independent and may 898 safely be used in a separate thread. The handlers and userData are 899 initialized from the parser argument. Returns NULL if out of memory. 900 Otherwise returns a new XML_Parser object. 901 */ 902 XMLPARSEAPI(XML_Parser) 903 XML_ExternalEntityParserCreate(XML_Parser parser, 904 const XML_Char *context, 905 const XML_Char *encoding); 906 907 enum XML_ParamEntityParsing { 908 XML_PARAM_ENTITY_PARSING_NEVER, 909 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 910 XML_PARAM_ENTITY_PARSING_ALWAYS 911 }; 912 913 /* Controls parsing of parameter entities (including the external DTD 914 subset). If parsing of parameter entities is enabled, then 915 references to external parameter entities (including the external 916 DTD subset) will be passed to the handler set with 917 XML_SetExternalEntityRefHandler. The context passed will be 0. 918 919 Unlike external general entities, external parameter entities can 920 only be parsed synchronously. If the external parameter entity is 921 to be parsed, it must be parsed during the call to the external 922 entity ref handler: the complete sequence of 923 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 924 XML_ParserFree calls must be made during this call. After 925 XML_ExternalEntityParserCreate has been called to create the parser 926 for the external parameter entity (context must be 0 for this 927 call), it is illegal to make any calls on the old parser until 928 XML_ParserFree has been called on the newly created parser. 929 If the library has been compiled without support for parameter 930 entity parsing (ie without XML_DTD being defined), then 931 XML_SetParamEntityParsing will return 0 if parsing of parameter 932 entities is requested; otherwise it will return non-zero. 933 Note: If XML_SetParamEntityParsing is called after XML_Parse or 934 XML_ParseBuffer, then it has no effect and will always return 0. 935 Note: If parser == NULL, the function will do nothing and return 0. 936 */ 937 XMLPARSEAPI(int) 938 XML_SetParamEntityParsing(XML_Parser parser, 939 enum XML_ParamEntityParsing parsing); 940 941 /* Sets the hash salt to use for internal hash calculations. 942 Helps in preventing DoS attacks based on predicting hash 943 function behavior. This must be called before parsing is started. 944 Returns 1 if successful, 0 when called after parsing has started. 945 Note: If parser == NULL, the function will do nothing and return 0. 946 */ 947 XMLPARSEAPI(int) 948 XML_SetHashSalt(XML_Parser parser, 949 unsigned long hash_salt); 950 951 /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 952 XML_GetErrorCode returns information about the error. 953 */ 954 XMLPARSEAPI(enum XML_Error) 955 XML_GetErrorCode(XML_Parser parser); 956 957 /* These functions return information about the current parse 958 location. They may be called from any callback called to report 959 some parse event; in this case the location is the location of the 960 first of the sequence of characters that generated the event. When 961 called from callbacks generated by declarations in the document 962 prologue, the location identified isn't as neatly defined, but will 963 be within the relevant markup. When called outside of the callback 964 functions, the position indicated will be just past the last parse 965 event (regardless of whether there was an associated callback). 966 967 They may also be called after returning from a call to XML_Parse 968 or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 969 the location is the location of the character at which the error 970 was detected; otherwise the location is the location of the last 971 parse event, as described above. 972 973 Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber 974 return 0 to indicate an error. 975 Note: XML_GetCurrentByteIndex returns -1 to indicate an error. 976 */ 977 XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); 978 XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); 979 XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); 980 981 /* Return the number of bytes in the current event. 982 Returns 0 if the event is in an internal entity. 983 */ 984 XMLPARSEAPI(int) 985 XML_GetCurrentByteCount(XML_Parser parser); 986 987 /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets 988 the integer pointed to by offset to the offset within this buffer 989 of the current parse position, and sets the integer pointed to by size 990 to the size of this buffer (the number of input bytes). Otherwise 991 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 992 active. 993 994 NOTE: The character pointer returned should not be used outside 995 the handler that makes the call. 996 */ 997 XMLPARSEAPI(const char *) 998 XML_GetInputContext(XML_Parser parser, 999 int *offset, 1000 int *size); 1001 1002 /* For backwards compatibility with previous versions. */ 1003 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 1004 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 1005 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 1006 1007 /* Frees the content model passed to the element declaration handler */ 1008 XMLPARSEAPI(void) 1009 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 1010 1011 /* Exposing the memory handling functions used in Expat */ 1012 XMLPARSEAPI(void *) 1013 XML_ATTR_MALLOC 1014 XML_ATTR_ALLOC_SIZE(2) 1015 XML_MemMalloc(XML_Parser parser, size_t size); 1016 1017 XMLPARSEAPI(void *) 1018 XML_ATTR_ALLOC_SIZE(3) 1019 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 1020 1021 XMLPARSEAPI(void) 1022 XML_MemFree(XML_Parser parser, void *ptr); 1023 1024 /* Frees memory used by the parser. */ 1025 XMLPARSEAPI(void) 1026 XML_ParserFree(XML_Parser parser); 1027 1028 /* Returns a string describing the error. */ 1029 XMLPARSEAPI(const XML_LChar *) 1030 XML_ErrorString(enum XML_Error code); 1031 1032 /* Return a string containing the version number of this expat */ 1033 XMLPARSEAPI(const XML_LChar *) 1034 XML_ExpatVersion(void); 1035 1036 typedef struct { 1037 int major; 1038 int minor; 1039 int micro; 1040 } XML_Expat_Version; 1041 1042 /* Return an XML_Expat_Version structure containing numeric version 1043 number information for this version of expat. 1044 */ 1045 XMLPARSEAPI(XML_Expat_Version) 1046 XML_ExpatVersionInfo(void); 1047 1048 /* Added in Expat 1.95.5. */ 1049 enum XML_FeatureEnum { 1050 XML_FEATURE_END = 0, 1051 XML_FEATURE_UNICODE, 1052 XML_FEATURE_UNICODE_WCHAR_T, 1053 XML_FEATURE_DTD, 1054 XML_FEATURE_CONTEXT_BYTES, 1055 XML_FEATURE_MIN_SIZE, 1056 XML_FEATURE_SIZEOF_XML_CHAR, 1057 XML_FEATURE_SIZEOF_XML_LCHAR, 1058 XML_FEATURE_NS, 1059 XML_FEATURE_LARGE_SIZE, 1060 XML_FEATURE_ATTR_INFO 1061 /* Additional features must be added to the end of this enum. */ 1062 }; 1063 1064 typedef struct { 1065 enum XML_FeatureEnum feature; 1066 const XML_LChar *name; 1067 long int value; 1068 } XML_Feature; 1069 1070 XMLPARSEAPI(const XML_Feature *) 1071 XML_GetFeatureList(void); 1072 1073 1074 /* Expat follows the semantic versioning convention. 1075 See http://semver.org. 1076 */ 1077 #define XML_MAJOR_VERSION 2 1078 #define XML_MINOR_VERSION 2 1079 #define XML_MICRO_VERSION 6 1080 1081 #ifdef __cplusplus 1082 } 1083 #endif 1084 1085 #endif /* not Expat_INCLUDED */ 1086