1 /* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd 2 See the file COPYING for copying permission. 3 */ 4 5 #ifndef Expat_INCLUDED 6 #define Expat_INCLUDED 1 7 8 #ifdef __VMS 9 /* 0 1 2 3 0 1 2 3 10 1234567890123456789012345678901 1234567890123456789012345678901 */ 11 #define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler 12 #define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler 13 #define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler 14 #define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg 15 #endif 16 17 #include <stdlib.h> 18 #include "expat_external.h" 19 20 #ifdef __cplusplus 21 extern "C" { 22 #endif 23 24 struct XML_ParserStruct; 25 typedef struct XML_ParserStruct *XML_Parser; 26 27 /* Should this be defined using stdbool.h when C99 is available? */ 28 typedef unsigned char XML_Bool; 29 #define XML_TRUE ((XML_Bool) 1) 30 #define XML_FALSE ((XML_Bool) 0) 31 32 /* The XML_Status enum gives the possible return values for several 33 API functions. The preprocessor #defines are included so this 34 stanza can be added to code that still needs to support older 35 versions of Expat 1.95.x: 36 37 #ifndef XML_STATUS_OK 38 #define XML_STATUS_OK 1 39 #define XML_STATUS_ERROR 0 40 #endif 41 42 Otherwise, the #define hackery is quite ugly and would have been 43 dropped. 44 */ 45 enum XML_Status { 46 XML_STATUS_ERROR = 0, 47 #define XML_STATUS_ERROR XML_STATUS_ERROR 48 XML_STATUS_OK = 1, 49 #define XML_STATUS_OK XML_STATUS_OK 50 XML_STATUS_SUSPENDED = 2 51 #define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED 52 }; 53 54 enum XML_Error { 55 XML_ERROR_NONE, 56 XML_ERROR_NO_MEMORY, 57 XML_ERROR_SYNTAX, 58 XML_ERROR_NO_ELEMENTS, 59 XML_ERROR_INVALID_TOKEN, 60 XML_ERROR_UNCLOSED_TOKEN, 61 XML_ERROR_PARTIAL_CHAR, 62 XML_ERROR_TAG_MISMATCH, 63 XML_ERROR_DUPLICATE_ATTRIBUTE, 64 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 65 XML_ERROR_PARAM_ENTITY_REF, 66 XML_ERROR_UNDEFINED_ENTITY, 67 XML_ERROR_RECURSIVE_ENTITY_REF, 68 XML_ERROR_ASYNC_ENTITY, 69 XML_ERROR_BAD_CHAR_REF, 70 XML_ERROR_BINARY_ENTITY_REF, 71 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 72 XML_ERROR_MISPLACED_XML_PI, 73 XML_ERROR_UNKNOWN_ENCODING, 74 XML_ERROR_INCORRECT_ENCODING, 75 XML_ERROR_UNCLOSED_CDATA_SECTION, 76 XML_ERROR_EXTERNAL_ENTITY_HANDLING, 77 XML_ERROR_NOT_STANDALONE, 78 XML_ERROR_UNEXPECTED_STATE, 79 XML_ERROR_ENTITY_DECLARED_IN_PE, 80 XML_ERROR_FEATURE_REQUIRES_XML_DTD, 81 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 82 /* Added in 1.95.7. */ 83 XML_ERROR_UNBOUND_PREFIX, 84 /* Added in 1.95.8. */ 85 XML_ERROR_UNDECLARING_PREFIX, 86 XML_ERROR_INCOMPLETE_PE, 87 XML_ERROR_XML_DECL, 88 XML_ERROR_TEXT_DECL, 89 XML_ERROR_PUBLICID, 90 XML_ERROR_SUSPENDED, 91 XML_ERROR_NOT_SUSPENDED, 92 XML_ERROR_ABORTED, 93 XML_ERROR_FINISHED, 94 XML_ERROR_SUSPEND_PE, 95 /* Added in 2.0. */ 96 XML_ERROR_RESERVED_PREFIX_XML, 97 XML_ERROR_RESERVED_PREFIX_XMLNS, 98 XML_ERROR_RESERVED_NAMESPACE_URI 99 }; 100 101 enum XML_Content_Type { 102 XML_CTYPE_EMPTY = 1, 103 XML_CTYPE_ANY, 104 XML_CTYPE_MIXED, 105 XML_CTYPE_NAME, 106 XML_CTYPE_CHOICE, 107 XML_CTYPE_SEQ 108 }; 109 110 enum XML_Content_Quant { 111 XML_CQUANT_NONE, 112 XML_CQUANT_OPT, 113 XML_CQUANT_REP, 114 XML_CQUANT_PLUS 115 }; 116 117 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 118 XML_CQUANT_NONE, and the other fields will be zero or NULL. 119 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 120 numchildren will contain number of elements that may be mixed in 121 and children point to an array of XML_Content cells that will be 122 all of XML_CTYPE_NAME type with no quantification. 123 124 If type == XML_CTYPE_NAME, then the name points to the name, and 125 the numchildren field will be zero and children will be NULL. The 126 quant fields indicates any quantifiers placed on the name. 127 128 CHOICE and SEQ will have name NULL, the number of children in 129 numchildren and children will point, recursively, to an array 130 of XML_Content cells. 131 132 The EMPTY, ANY, and MIXED types will only occur at top level. 133 */ 134 135 typedef struct XML_cp XML_Content; 136 137 struct XML_cp { 138 enum XML_Content_Type type; 139 enum XML_Content_Quant quant; 140 XML_Char * name; 141 unsigned int numchildren; 142 XML_Content * children; 143 }; 144 145 146 /* This is called for an element declaration. See above for 147 description of the model argument. It's the caller's responsibility 148 to free model when finished with it. 149 */ 150 typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, 151 const XML_Char *name, 152 XML_Content *model); 153 154 XMLPARSEAPI(void) 155 XML_SetElementDeclHandler(XML_Parser parser, 156 XML_ElementDeclHandler eldecl); 157 158 /* The Attlist declaration handler is called for *each* attribute. So 159 a single Attlist declaration with multiple attributes declared will 160 generate multiple calls to this handler. The "default" parameter 161 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 162 keyword. The "isrequired" parameter will be true and the default 163 value will be NULL in the case of "#REQUIRED". If "isrequired" is 164 true and default is non-NULL, then this is a "#FIXED" default. 165 */ 166 typedef void (XMLCALL *XML_AttlistDeclHandler) ( 167 void *userData, 168 const XML_Char *elname, 169 const XML_Char *attname, 170 const XML_Char *att_type, 171 const XML_Char *dflt, 172 int isrequired); 173 174 XMLPARSEAPI(void) 175 XML_SetAttlistDeclHandler(XML_Parser parser, 176 XML_AttlistDeclHandler attdecl); 177 178 /* The XML declaration handler is called for *both* XML declarations 179 and text declarations. The way to distinguish is that the version 180 parameter will be NULL for text declarations. The encoding 181 parameter may be NULL for XML declarations. The standalone 182 parameter will be -1, 0, or 1 indicating respectively that there 183 was no standalone parameter in the declaration, that it was given 184 as no, or that it was given as yes. 185 */ 186 typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, 187 const XML_Char *version, 188 const XML_Char *encoding, 189 int standalone); 190 191 XMLPARSEAPI(void) 192 XML_SetXmlDeclHandler(XML_Parser parser, 193 XML_XmlDeclHandler xmldecl); 194 195 196 typedef struct { 197 void *(*malloc_fcn)(size_t size); 198 void *(*realloc_fcn)(void *ptr, size_t size); 199 void (*free_fcn)(void *ptr); 200 } XML_Memory_Handling_Suite; 201 202 /* Constructs a new parser; encoding is the encoding specified by the 203 external protocol or NULL if there is none specified. 204 */ 205 XMLPARSEAPI(XML_Parser) 206 XML_ParserCreate(const XML_Char *encoding); 207 208 /* Constructs a new parser and namespace processor. Element type 209 names and attribute names that belong to a namespace will be 210 expanded; unprefixed attribute names are never expanded; unprefixed 211 element type names are expanded only if there is a default 212 namespace. The expanded name is the concatenation of the namespace 213 URI, the namespace separator character, and the local part of the 214 name. If the namespace separator is '\0' then the namespace URI 215 and the local part will be concatenated without any separator. 216 It is a programming error to use the separator '\0' with namespace 217 triplets (see XML_SetReturnNSTriplet). 218 */ 219 XMLPARSEAPI(XML_Parser) 220 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 221 222 223 /* Constructs a new parser using the memory management suite referred to 224 by memsuite. If memsuite is NULL, then use the standard library memory 225 suite. If namespaceSeparator is non-NULL it creates a parser with 226 namespace processing as described above. The character pointed at 227 will serve as the namespace separator. 228 229 All further memory operations used for the created parser will come from 230 the given suite. 231 */ 232 XMLPARSEAPI(XML_Parser) 233 XML_ParserCreate_MM(const XML_Char *encoding, 234 const XML_Memory_Handling_Suite *memsuite, 235 const XML_Char *namespaceSeparator); 236 237 /* Prepare a parser object to be re-used. This is particularly 238 valuable when memory allocation overhead is disproportionatly high, 239 such as when a large number of small documnents need to be parsed. 240 All handlers are cleared from the parser, except for the 241 unknownEncodingHandler. The parser's external state is re-initialized 242 except for the values of ns and ns_triplets. 243 244 Added in Expat 1.95.3. 245 */ 246 XMLPARSEAPI(XML_Bool) 247 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 248 249 /* atts is array of name/value pairs, terminated by 0; 250 names and values are 0 terminated. 251 */ 252 typedef void (XMLCALL *XML_StartElementHandler) (void *userData, 253 const XML_Char *name, 254 const XML_Char **atts); 255 256 typedef void (XMLCALL *XML_EndElementHandler) (void *userData, 257 const XML_Char *name); 258 259 260 /* s is not 0 terminated. */ 261 typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, 262 const XML_Char *s, 263 int len); 264 265 /* target and data are 0 terminated */ 266 typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( 267 void *userData, 268 const XML_Char *target, 269 const XML_Char *data); 270 271 /* data is 0 terminated */ 272 typedef void (XMLCALL *XML_CommentHandler) (void *userData, 273 const XML_Char *data); 274 275 typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); 276 typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); 277 278 /* This is called for any characters in the XML document for which 279 there is no applicable handler. This includes both characters that 280 are part of markup which is of a kind that is not reported 281 (comments, markup declarations), or characters that are part of a 282 construct which could be reported but for which no handler has been 283 supplied. The characters are passed exactly as they were in the XML 284 document except that they will be encoded in UTF-8 or UTF-16. 285 Line boundaries are not normalized. Note that a byte order mark 286 character is not passed to the default handler. There are no 287 guarantees about how characters are divided between calls to the 288 default handler: for example, a comment might be split between 289 multiple calls. 290 */ 291 typedef void (XMLCALL *XML_DefaultHandler) (void *userData, 292 const XML_Char *s, 293 int len); 294 295 /* This is called for the start of the DOCTYPE declaration, before 296 any DTD or internal subset is parsed. 297 */ 298 typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( 299 void *userData, 300 const XML_Char *doctypeName, 301 const XML_Char *sysid, 302 const XML_Char *pubid, 303 int has_internal_subset); 304 305 /* This is called for the start of the DOCTYPE declaration when the 306 closing > is encountered, but after processing any external 307 subset. 308 */ 309 typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 310 311 /* This is called for entity declarations. The is_parameter_entity 312 argument will be non-zero if the entity is a parameter entity, zero 313 otherwise. 314 315 For internal entities (<!ENTITY foo "bar">), value will 316 be non-NULL and systemId, publicID, and notationName will be NULL. 317 The value string is NOT nul-terminated; the length is provided in 318 the value_length argument. Since it is legal to have zero-length 319 values, do not use this argument to test for internal entities. 320 321 For external entities, value will be NULL and systemId will be 322 non-NULL. The publicId argument will be NULL unless a public 323 identifier was provided. The notationName argument will have a 324 non-NULL value only for unparsed entity declarations. 325 326 Note that is_parameter_entity can't be changed to XML_Bool, since 327 that would break binary compatibility. 328 */ 329 typedef void (XMLCALL *XML_EntityDeclHandler) ( 330 void *userData, 331 const XML_Char *entityName, 332 int is_parameter_entity, 333 const XML_Char *value, 334 int value_length, 335 const XML_Char *base, 336 const XML_Char *systemId, 337 const XML_Char *publicId, 338 const XML_Char *notationName); 339 340 XMLPARSEAPI(void) 341 XML_SetEntityDeclHandler(XML_Parser parser, 342 XML_EntityDeclHandler handler); 343 344 /* OBSOLETE -- OBSOLETE -- OBSOLETE 345 This handler has been superceded by the EntityDeclHandler above. 346 It is provided here for backward compatibility. 347 348 This is called for a declaration of an unparsed (NDATA) entity. 349 The base argument is whatever was set by XML_SetBase. The 350 entityName, systemId and notationName arguments will never be 351 NULL. The other arguments may be. 352 */ 353 typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( 354 void *userData, 355 const XML_Char *entityName, 356 const XML_Char *base, 357 const XML_Char *systemId, 358 const XML_Char *publicId, 359 const XML_Char *notationName); 360 361 /* This is called for a declaration of notation. The base argument is 362 whatever was set by XML_SetBase. The notationName will never be 363 NULL. The other arguments can be. 364 */ 365 typedef void (XMLCALL *XML_NotationDeclHandler) ( 366 void *userData, 367 const XML_Char *notationName, 368 const XML_Char *base, 369 const XML_Char *systemId, 370 const XML_Char *publicId); 371 372 /* When namespace processing is enabled, these are called once for 373 each namespace declaration. The call to the start and end element 374 handlers occur between the calls to the start and end namespace 375 declaration handlers. For an xmlns attribute, prefix will be 376 NULL. For an xmlns="" attribute, uri will be NULL. 377 */ 378 typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( 379 void *userData, 380 const XML_Char *prefix, 381 const XML_Char *uri); 382 383 typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( 384 void *userData, 385 const XML_Char *prefix); 386 387 /* This is called if the document is not standalone, that is, it has an 388 external subset or a reference to a parameter entity, but does not 389 have standalone="yes". If this handler returns XML_STATUS_ERROR, 390 then processing will not continue, and the parser will return a 391 XML_ERROR_NOT_STANDALONE error. 392 If parameter entity parsing is enabled, then in addition to the 393 conditions above this handler will only be called if the referenced 394 entity was actually read. 395 */ 396 typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); 397 398 /* This is called for a reference to an external parsed general 399 entity. The referenced entity is not automatically parsed. The 400 application can parse it immediately or later using 401 XML_ExternalEntityParserCreate. 402 403 The parser argument is the parser parsing the entity containing the 404 reference; it can be passed as the parser argument to 405 XML_ExternalEntityParserCreate. The systemId argument is the 406 system identifier as specified in the entity declaration; it will 407 not be NULL. 408 409 The base argument is the system identifier that should be used as 410 the base for resolving systemId if systemId was relative; this is 411 set by XML_SetBase; it may be NULL. 412 413 The publicId argument is the public identifier as specified in the 414 entity declaration, or NULL if none was specified; the whitespace 415 in the public identifier will have been normalized as required by 416 the XML spec. 417 418 The context argument specifies the parsing context in the format 419 expected by the context argument to XML_ExternalEntityParserCreate; 420 context is valid only until the handler returns, so if the 421 referenced entity is to be parsed later, it must be copied. 422 context is NULL only when the entity is a parameter entity. 423 424 The handler should return XML_STATUS_ERROR if processing should not 425 continue because of a fatal error in the handling of the external 426 entity. In this case the calling parser will return an 427 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 428 429 Note that unlike other handlers the first argument is the parser, 430 not userData. 431 */ 432 typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( 433 XML_Parser parser, 434 const XML_Char *context, 435 const XML_Char *base, 436 const XML_Char *systemId, 437 const XML_Char *publicId); 438 439 /* This is called in two situations: 440 1) An entity reference is encountered for which no declaration 441 has been read *and* this is not an error. 442 2) An internal entity reference is read, but not expanded, because 443 XML_SetDefaultHandler has been called. 444 Note: skipped parameter entities in declarations and skipped general 445 entities in attribute values cannot be reported, because 446 the event would be out of sync with the reporting of the 447 declarations or attribute values 448 */ 449 typedef void (XMLCALL *XML_SkippedEntityHandler) ( 450 void *userData, 451 const XML_Char *entityName, 452 int is_parameter_entity); 453 454 /* This structure is filled in by the XML_UnknownEncodingHandler to 455 provide information to the parser about encodings that are unknown 456 to the parser. 457 458 The map[b] member gives information about byte sequences whose 459 first byte is b. 460 461 If map[b] is c where c is >= 0, then b by itself encodes the 462 Unicode scalar value c. 463 464 If map[b] is -1, then the byte sequence is malformed. 465 466 If map[b] is -n, where n >= 2, then b is the first byte of an 467 n-byte sequence that encodes a single Unicode scalar value. 468 469 The data member will be passed as the first argument to the convert 470 function. 471 472 The convert function is used to convert multibyte sequences; s will 473 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 474 convert function must return the Unicode scalar value represented 475 by this byte sequence or -1 if the byte sequence is malformed. 476 477 The convert function may be NULL if the encoding is a single-byte 478 encoding, that is if map[b] >= -1 for all bytes b. 479 480 When the parser is finished with the encoding, then if release is 481 not NULL, it will call release passing it the data member; once 482 release has been called, the convert function will not be called 483 again. 484 485 Expat places certain restrictions on the encodings that are supported 486 using this mechanism. 487 488 1. Every ASCII character that can appear in a well-formed XML document, 489 other than the characters 490 491 $@\^`{}~ 492 493 must be represented by a single byte, and that byte must be the 494 same byte that represents that character in ASCII. 495 496 2. No character may require more than 4 bytes to encode. 497 498 3. All characters encoded must have Unicode scalar values <= 499 0xFFFF, (i.e., characters that would be encoded by surrogates in 500 UTF-16 are not allowed). Note that this restriction doesn't 501 apply to the built-in support for UTF-8 and UTF-16. 502 503 4. No Unicode character may be encoded by more than one distinct 504 sequence of bytes. 505 */ 506 typedef struct { 507 int map[256]; 508 void *data; 509 int (XMLCALL *convert)(void *data, const char *s); 510 void (XMLCALL *release)(void *data); 511 } XML_Encoding; 512 513 /* This is called for an encoding that is unknown to the parser. 514 515 The encodingHandlerData argument is that which was passed as the 516 second argument to XML_SetUnknownEncodingHandler. 517 518 The name argument gives the name of the encoding as specified in 519 the encoding declaration. 520 521 If the callback can provide information about the encoding, it must 522 fill in the XML_Encoding structure, and return XML_STATUS_OK. 523 Otherwise it must return XML_STATUS_ERROR. 524 525 If info does not describe a suitable encoding, then the parser will 526 return an XML_UNKNOWN_ENCODING error. 527 */ 528 typedef int (XMLCALL *XML_UnknownEncodingHandler) ( 529 void *encodingHandlerData, 530 const XML_Char *name, 531 XML_Encoding *info); 532 533 XMLPARSEAPI(void) 534 XML_SetElementHandler(XML_Parser parser, 535 XML_StartElementHandler start, 536 XML_EndElementHandler end); 537 538 XMLPARSEAPI(void) 539 XML_SetStartElementHandler(XML_Parser parser, 540 XML_StartElementHandler handler); 541 542 XMLPARSEAPI(void) 543 XML_SetEndElementHandler(XML_Parser parser, 544 XML_EndElementHandler handler); 545 546 XMLPARSEAPI(void) 547 XML_SetCharacterDataHandler(XML_Parser parser, 548 XML_CharacterDataHandler handler); 549 550 XMLPARSEAPI(void) 551 XML_SetProcessingInstructionHandler(XML_Parser parser, 552 XML_ProcessingInstructionHandler handler); 553 XMLPARSEAPI(void) 554 XML_SetCommentHandler(XML_Parser parser, 555 XML_CommentHandler handler); 556 557 XMLPARSEAPI(void) 558 XML_SetCdataSectionHandler(XML_Parser parser, 559 XML_StartCdataSectionHandler start, 560 XML_EndCdataSectionHandler end); 561 562 XMLPARSEAPI(void) 563 XML_SetStartCdataSectionHandler(XML_Parser parser, 564 XML_StartCdataSectionHandler start); 565 566 XMLPARSEAPI(void) 567 XML_SetEndCdataSectionHandler(XML_Parser parser, 568 XML_EndCdataSectionHandler end); 569 570 /* This sets the default handler and also inhibits expansion of 571 internal entities. These entity references will be passed to the 572 default handler, or to the skipped entity handler, if one is set. 573 */ 574 XMLPARSEAPI(void) 575 XML_SetDefaultHandler(XML_Parser parser, 576 XML_DefaultHandler handler); 577 578 /* This sets the default handler but does not inhibit expansion of 579 internal entities. The entity reference will not be passed to the 580 default handler. 581 */ 582 XMLPARSEAPI(void) 583 XML_SetDefaultHandlerExpand(XML_Parser parser, 584 XML_DefaultHandler handler); 585 586 XMLPARSEAPI(void) 587 XML_SetDoctypeDeclHandler(XML_Parser parser, 588 XML_StartDoctypeDeclHandler start, 589 XML_EndDoctypeDeclHandler end); 590 591 XMLPARSEAPI(void) 592 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 593 XML_StartDoctypeDeclHandler start); 594 595 XMLPARSEAPI(void) 596 XML_SetEndDoctypeDeclHandler(XML_Parser parser, 597 XML_EndDoctypeDeclHandler end); 598 599 XMLPARSEAPI(void) 600 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 601 XML_UnparsedEntityDeclHandler handler); 602 603 XMLPARSEAPI(void) 604 XML_SetNotationDeclHandler(XML_Parser parser, 605 XML_NotationDeclHandler handler); 606 607 XMLPARSEAPI(void) 608 XML_SetNamespaceDeclHandler(XML_Parser parser, 609 XML_StartNamespaceDeclHandler start, 610 XML_EndNamespaceDeclHandler end); 611 612 XMLPARSEAPI(void) 613 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 614 XML_StartNamespaceDeclHandler start); 615 616 XMLPARSEAPI(void) 617 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 618 XML_EndNamespaceDeclHandler end); 619 620 XMLPARSEAPI(void) 621 XML_SetNotStandaloneHandler(XML_Parser parser, 622 XML_NotStandaloneHandler handler); 623 624 XMLPARSEAPI(void) 625 XML_SetExternalEntityRefHandler(XML_Parser parser, 626 XML_ExternalEntityRefHandler handler); 627 628 /* If a non-NULL value for arg is specified here, then it will be 629 passed as the first argument to the external entity ref handler 630 instead of the parser object. 631 */ 632 XMLPARSEAPI(void) 633 XML_SetExternalEntityRefHandlerArg(XML_Parser parser, 634 void *arg); 635 636 XMLPARSEAPI(void) 637 XML_SetSkippedEntityHandler(XML_Parser parser, 638 XML_SkippedEntityHandler handler); 639 640 XMLPARSEAPI(void) 641 XML_SetUnknownEncodingHandler(XML_Parser parser, 642 XML_UnknownEncodingHandler handler, 643 void *encodingHandlerData); 644 645 /* This can be called within a handler for a start element, end 646 element, processing instruction or character data. It causes the 647 corresponding markup to be passed to the default handler. 648 */ 649 XMLPARSEAPI(void) 650 XML_DefaultCurrent(XML_Parser parser); 651 652 /* If do_nst is non-zero, and namespace processing is in effect, and 653 a name has a prefix (i.e. an explicit namespace qualifier) then 654 that name is returned as a triplet in a single string separated by 655 the separator character specified when the parser was created: URI 656 + sep + local_name + sep + prefix. 657 658 If do_nst is zero, then namespace information is returned in the 659 default manner (URI + sep + local_name) whether or not the name 660 has a prefix. 661 662 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 663 XML_ParseBuffer has no effect. 664 */ 665 666 XMLPARSEAPI(void) 667 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 668 669 /* This value is passed as the userData argument to callbacks. */ 670 XMLPARSEAPI(void) 671 XML_SetUserData(XML_Parser parser, void *userData); 672 673 /* Returns the last value set by XML_SetUserData or NULL. */ 674 #define XML_GetUserData(parser) (*(void **)(parser)) 675 676 /* This is equivalent to supplying an encoding argument to 677 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 678 zero otherwise. 679 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 680 has no effect and returns XML_STATUS_ERROR. 681 */ 682 XMLPARSEAPI(enum XML_Status) 683 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 684 685 /* If this function is called, then the parser will be passed as the 686 first argument to callbacks instead of userData. The userData will 687 still be accessible using XML_GetUserData. 688 */ 689 XMLPARSEAPI(void) 690 XML_UseParserAsHandlerArg(XML_Parser parser); 691 692 /* If useDTD == XML_TRUE is passed to this function, then the parser 693 will assume that there is an external subset, even if none is 694 specified in the document. In such a case the parser will call the 695 externalEntityRefHandler with a value of NULL for the systemId 696 argument (the publicId and context arguments will be NULL as well). 697 Note: For the purpose of checking WFC: Entity Declared, passing 698 useDTD == XML_TRUE will make the parser behave as if the document 699 had a DTD with an external subset. 700 Note: If this function is called, then this must be done before 701 the first call to XML_Parse or XML_ParseBuffer, since it will 702 have no effect after that. Returns 703 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 704 Note: If the document does not have a DOCTYPE declaration at all, 705 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 706 be called, despite an external subset being parsed. 707 Note: If XML_DTD is not defined when Expat is compiled, returns 708 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 709 */ 710 XMLPARSEAPI(enum XML_Error) 711 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 712 713 714 /* Sets the base to be used for resolving relative URIs in system 715 identifiers in declarations. Resolving relative identifiers is 716 left to the application: this value will be passed through as the 717 base argument to the XML_ExternalEntityRefHandler, 718 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 719 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 720 XML_STATUS_OK otherwise. 721 */ 722 XMLPARSEAPI(enum XML_Status) 723 XML_SetBase(XML_Parser parser, const XML_Char *base); 724 725 XMLPARSEAPI(const XML_Char *) 726 XML_GetBase(XML_Parser parser); 727 728 /* Returns the number of the attribute/value pairs passed in last call 729 to the XML_StartElementHandler that were specified in the start-tag 730 rather than defaulted. Each attribute/value pair counts as 2; thus 731 this correspondds to an index into the atts array passed to the 732 XML_StartElementHandler. 733 */ 734 XMLPARSEAPI(int) 735 XML_GetSpecifiedAttributeCount(XML_Parser parser); 736 737 /* Returns the index of the ID attribute passed in the last call to 738 XML_StartElementHandler, or -1 if there is no ID attribute. Each 739 attribute/value pair counts as 2; thus this correspondds to an 740 index into the atts array passed to the XML_StartElementHandler. 741 */ 742 XMLPARSEAPI(int) 743 XML_GetIdAttributeIndex(XML_Parser parser); 744 745 #ifdef XML_ATTR_INFO 746 /* Source file byte offsets for the start and end of attribute names and values. 747 The value indices are exclusive of surrounding quotes; thus in a UTF-8 source 748 file an attribute value of "blah" will yield: 749 info->valueEnd - info->valueStart = 4 bytes. 750 */ 751 typedef struct { 752 XML_Index nameStart; /* Offset to beginning of the attribute name. */ 753 XML_Index nameEnd; /* Offset after the attribute name's last byte. */ 754 XML_Index valueStart; /* Offset to beginning of the attribute value. */ 755 XML_Index valueEnd; /* Offset after the attribute value's last byte. */ 756 } XML_AttrInfo; 757 758 /* Returns an array of XML_AttrInfo structures for the attribute/value pairs 759 passed in last call to the XML_StartElementHandler that were specified 760 in the start-tag rather than defaulted. Each attribute/value pair counts 761 as 1; thus the number of entries in the array is 762 XML_GetSpecifiedAttributeCount(parser) / 2. 763 */ 764 XMLPARSEAPI(const XML_AttrInfo *) 765 XML_GetAttributeInfo(XML_Parser parser); 766 #endif 767 768 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 769 detected. The last call to XML_Parse must have isFinal true; len 770 may be zero for this call (or any other). 771 772 Though the return values for these functions has always been 773 described as a Boolean value, the implementation, at least for the 774 1.95.x series, has always returned exactly one of the XML_Status 775 values. 776 */ 777 XMLPARSEAPI(enum XML_Status) 778 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 779 780 XMLPARSEAPI(void *) 781 XML_GetBuffer(XML_Parser parser, int len); 782 783 XMLPARSEAPI(enum XML_Status) 784 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 785 786 /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 787 Must be called from within a call-back handler, except when aborting 788 (resumable = 0) an already suspended parser. Some call-backs may 789 still follow because they would otherwise get lost. Examples: 790 - endElementHandler() for empty elements when stopped in 791 startElementHandler(), 792 - endNameSpaceDeclHandler() when stopped in endElementHandler(), 793 and possibly others. 794 795 Can be called from most handlers, including DTD related call-backs, 796 except when parsing an external parameter entity and resumable != 0. 797 Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 798 Possible error codes: 799 - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 800 - XML_ERROR_FINISHED: when the parser has already finished. 801 - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 802 803 When resumable != 0 (true) then parsing is suspended, that is, 804 XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 805 Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 806 return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 807 808 *Note*: 809 This will be applied to the current parser instance only, that is, if 810 there is a parent parser then it will continue parsing when the 811 externalEntityRefHandler() returns. It is up to the implementation of 812 the externalEntityRefHandler() to call XML_StopParser() on the parent 813 parser (recursively), if one wants to stop parsing altogether. 814 815 When suspended, parsing can be resumed by calling XML_ResumeParser(). 816 */ 817 XMLPARSEAPI(enum XML_Status) 818 XML_StopParser(XML_Parser parser, XML_Bool resumable); 819 820 /* Resumes parsing after it has been suspended with XML_StopParser(). 821 Must not be called from within a handler call-back. Returns same 822 status codes as XML_Parse() or XML_ParseBuffer(). 823 Additional error code XML_ERROR_NOT_SUSPENDED possible. 824 825 *Note*: 826 This must be called on the most deeply nested child parser instance 827 first, and on its parent parser only after the child parser has finished, 828 to be applied recursively until the document entity's parser is restarted. 829 That is, the parent parser will not resume by itself and it is up to the 830 application to call XML_ResumeParser() on it at the appropriate moment. 831 */ 832 XMLPARSEAPI(enum XML_Status) 833 XML_ResumeParser(XML_Parser parser); 834 835 enum XML_Parsing { 836 XML_INITIALIZED, 837 XML_PARSING, 838 XML_FINISHED, 839 XML_SUSPENDED 840 }; 841 842 typedef struct { 843 enum XML_Parsing parsing; 844 XML_Bool finalBuffer; 845 } XML_ParsingStatus; 846 847 /* Returns status of parser with respect to being initialized, parsing, 848 finished, or suspended and processing the final buffer. 849 XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 850 XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 851 */ 852 XMLPARSEAPI(void) 853 XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 854 855 /* Creates an XML_Parser object that can parse an external general 856 entity; context is a '\0'-terminated string specifying the parse 857 context; encoding is a '\0'-terminated string giving the name of 858 the externally specified encoding, or NULL if there is no 859 externally specified encoding. The context string consists of a 860 sequence of tokens separated by formfeeds (\f); a token consisting 861 of a name specifies that the general entity of the name is open; a 862 token of the form prefix=uri specifies the namespace for a 863 particular prefix; a token of the form =uri specifies the default 864 namespace. This can be called at any point after the first call to 865 an ExternalEntityRefHandler so longer as the parser has not yet 866 been freed. The new parser is completely independent and may 867 safely be used in a separate thread. The handlers and userData are 868 initialized from the parser argument. Returns NULL if out of memory. 869 Otherwise returns a new XML_Parser object. 870 */ 871 XMLPARSEAPI(XML_Parser) 872 XML_ExternalEntityParserCreate(XML_Parser parser, 873 const XML_Char *context, 874 const XML_Char *encoding); 875 876 enum XML_ParamEntityParsing { 877 XML_PARAM_ENTITY_PARSING_NEVER, 878 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 879 XML_PARAM_ENTITY_PARSING_ALWAYS 880 }; 881 882 /* Controls parsing of parameter entities (including the external DTD 883 subset). If parsing of parameter entities is enabled, then 884 references to external parameter entities (including the external 885 DTD subset) will be passed to the handler set with 886 XML_SetExternalEntityRefHandler. The context passed will be 0. 887 888 Unlike external general entities, external parameter entities can 889 only be parsed synchronously. If the external parameter entity is 890 to be parsed, it must be parsed during the call to the external 891 entity ref handler: the complete sequence of 892 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 893 XML_ParserFree calls must be made during this call. After 894 XML_ExternalEntityParserCreate has been called to create the parser 895 for the external parameter entity (context must be 0 for this 896 call), it is illegal to make any calls on the old parser until 897 XML_ParserFree has been called on the newly created parser. 898 If the library has been compiled without support for parameter 899 entity parsing (ie without XML_DTD being defined), then 900 XML_SetParamEntityParsing will return 0 if parsing of parameter 901 entities is requested; otherwise it will return non-zero. 902 Note: If XML_SetParamEntityParsing is called after XML_Parse or 903 XML_ParseBuffer, then it has no effect and will always return 0. 904 */ 905 XMLPARSEAPI(int) 906 XML_SetParamEntityParsing(XML_Parser parser, 907 enum XML_ParamEntityParsing parsing); 908 909 /* Sets the hash salt to use for internal hash calculations. 910 Helps in preventing DoS attacks based on predicting hash 911 function behavior. This must be called before parsing is started. 912 Returns 1 if successful, 0 when called after parsing has started. 913 */ 914 XMLPARSEAPI(int) 915 XML_SetHashSalt(XML_Parser parser, 916 unsigned long hash_salt); 917 918 #define XML_HAS_SET_HASH_SALT /* Python Only: Defined for pyexpat.c. */ 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 XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); 943 XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); 944 XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); 945 946 /* Return the number of bytes in the current event. 947 Returns 0 if the event is in an internal entity. 948 */ 949 XMLPARSEAPI(int) 950 XML_GetCurrentByteCount(XML_Parser parser); 951 952 /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets 953 the integer pointed to by offset to the offset within this buffer 954 of the current parse position, and sets the integer pointed to by size 955 to the size of this buffer (the number of input bytes). Otherwise 956 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 957 active. 958 959 NOTE: The character pointer returned should not be used outside 960 the handler that makes the call. 961 */ 962 XMLPARSEAPI(const char *) 963 XML_GetInputContext(XML_Parser parser, 964 int *offset, 965 int *size); 966 967 /* For backwards compatibility with previous versions. */ 968 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 969 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 970 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 971 972 /* Frees the content model passed to the element declaration handler */ 973 XMLPARSEAPI(void) 974 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 975 976 /* Exposing the memory handling functions used in Expat */ 977 XMLPARSEAPI(void *) 978 XML_MemMalloc(XML_Parser parser, size_t size); 979 980 XMLPARSEAPI(void *) 981 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 982 983 XMLPARSEAPI(void) 984 XML_MemFree(XML_Parser parser, void *ptr); 985 986 /* Frees memory used by the parser. */ 987 XMLPARSEAPI(void) 988 XML_ParserFree(XML_Parser parser); 989 990 /* Returns a string describing the error. */ 991 XMLPARSEAPI(const XML_LChar *) 992 XML_ErrorString(enum XML_Error code); 993 994 /* Return a string containing the version number of this expat */ 995 XMLPARSEAPI(const XML_LChar *) 996 XML_ExpatVersion(void); 997 998 typedef struct { 999 int major; 1000 int minor; 1001 int micro; 1002 } XML_Expat_Version; 1003 1004 /* Return an XML_Expat_Version structure containing numeric version 1005 number information for this version of expat. 1006 */ 1007 XMLPARSEAPI(XML_Expat_Version) 1008 XML_ExpatVersionInfo(void); 1009 1010 /* Added in Expat 1.95.5. */ 1011 enum XML_FeatureEnum { 1012 XML_FEATURE_END = 0, 1013 XML_FEATURE_UNICODE, 1014 XML_FEATURE_UNICODE_WCHAR_T, 1015 XML_FEATURE_DTD, 1016 XML_FEATURE_CONTEXT_BYTES, 1017 XML_FEATURE_MIN_SIZE, 1018 XML_FEATURE_SIZEOF_XML_CHAR, 1019 XML_FEATURE_SIZEOF_XML_LCHAR, 1020 XML_FEATURE_NS, 1021 XML_FEATURE_LARGE_SIZE, 1022 XML_FEATURE_ATTR_INFO 1023 /* Additional features must be added to the end of this enum. */ 1024 }; 1025 1026 typedef struct { 1027 enum XML_FeatureEnum feature; 1028 const XML_LChar *name; 1029 long int value; 1030 } XML_Feature; 1031 1032 XMLPARSEAPI(const XML_Feature *) 1033 XML_GetFeatureList(void); 1034 1035 1036 /* Expat follows the GNU/Linux convention of odd number minor version for 1037 beta/development releases and even number minor version for stable 1038 releases. Micro is bumped with each release, and set to 0 with each 1039 change to major or minor version. 1040 */ 1041 #define XML_MAJOR_VERSION 2 1042 #define XML_MINOR_VERSION 1 1043 #define XML_MICRO_VERSION 0 1044 1045 #ifdef __cplusplus 1046 } 1047 #endif 1048 1049 #endif /* not Expat_INCLUDED */ 1050