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 "expatemboss.h" 19 #include "expat_external.h" 20 21 #ifdef __cplusplus 22 extern "C" { 23 #endif 24 25 struct XML_ParserStruct; 26 typedef struct XML_ParserStruct *XML_Parser; 27 28 /* Should this be defined using stdbool.h when C99 is available? */ 29 typedef unsigned char XML_Bool; 30 #define XML_TRUE ((XML_Bool) 1) 31 #define XML_FALSE ((XML_Bool) 0) 32 33 /* The XML_Status enum gives the possible return values for several 34 API functions. The preprocessor #defines are included so this 35 stanza can be added to code that still needs to support older 36 versions of Expat 1.95.x: 37 38 #ifndef XML_STATUS_OK 39 #define XML_STATUS_OK 1 40 #define XML_STATUS_ERROR 0 41 #endif 42 43 Otherwise, the #define hackery is quite ugly and would have been 44 dropped. 45 */ 46 enum XML_Status { 47 XML_STATUS_ERROR = 0, 48 #define XML_STATUS_ERROR XML_STATUS_ERROR 49 XML_STATUS_OK = 1, 50 #define XML_STATUS_OK XML_STATUS_OK 51 XML_STATUS_SUSPENDED = 2 52 #define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED 53 }; 54 55 enum XML_Error { 56 XML_ERROR_NONE, 57 XML_ERROR_NO_MEMORY, 58 XML_ERROR_SYNTAX, 59 XML_ERROR_NO_ELEMENTS, 60 XML_ERROR_INVALID_TOKEN, 61 XML_ERROR_UNCLOSED_TOKEN, 62 XML_ERROR_PARTIAL_CHAR, 63 XML_ERROR_TAG_MISMATCH, 64 XML_ERROR_DUPLICATE_ATTRIBUTE, 65 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 66 XML_ERROR_PARAM_ENTITY_REF, 67 XML_ERROR_UNDEFINED_ENTITY, 68 XML_ERROR_RECURSIVE_ENTITY_REF, 69 XML_ERROR_ASYNC_ENTITY, 70 XML_ERROR_BAD_CHAR_REF, 71 XML_ERROR_BINARY_ENTITY_REF, 72 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 73 XML_ERROR_MISPLACED_XML_PI, 74 XML_ERROR_UNKNOWN_ENCODING, 75 XML_ERROR_INCORRECT_ENCODING, 76 XML_ERROR_UNCLOSED_CDATA_SECTION, 77 XML_ERROR_EXTERNAL_ENTITY_HANDLING, 78 XML_ERROR_NOT_STANDALONE, 79 XML_ERROR_UNEXPECTED_STATE, 80 XML_ERROR_ENTITY_DECLARED_IN_PE, 81 XML_ERROR_FEATURE_REQUIRES_XML_DTD, 82 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 83 /* Added in 1.95.7. */ 84 XML_ERROR_UNBOUND_PREFIX, 85 /* Added in 1.95.8. */ 86 XML_ERROR_UNDECLARING_PREFIX, 87 XML_ERROR_INCOMPLETE_PE, 88 XML_ERROR_XML_DECL, 89 XML_ERROR_TEXT_DECL, 90 XML_ERROR_PUBLICID, 91 XML_ERROR_SUSPENDED, 92 XML_ERROR_NOT_SUSPENDED, 93 XML_ERROR_ABORTED, 94 XML_ERROR_FINISHED, 95 XML_ERROR_SUSPEND_PE, 96 /* Added in 2.0. */ 97 XML_ERROR_RESERVED_PREFIX_XML, 98 XML_ERROR_RESERVED_PREFIX_XMLNS, 99 XML_ERROR_RESERVED_NAMESPACE_URI 100 }; 101 102 enum XML_Content_Type { 103 XML_CTYPE_EMPTY = 1, 104 XML_CTYPE_ANY, 105 XML_CTYPE_MIXED, 106 XML_CTYPE_NAME, 107 XML_CTYPE_CHOICE, 108 XML_CTYPE_SEQ 109 }; 110 111 enum XML_Content_Quant { 112 XML_CQUANT_NONE, 113 XML_CQUANT_OPT, 114 XML_CQUANT_REP, 115 XML_CQUANT_PLUS 116 }; 117 118 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 119 XML_CQUANT_NONE, and the other fields will be zero or NULL. 120 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 121 numchildren will contain number of elements that may be mixed in 122 and children point to an array of XML_Content cells that will be 123 all of XML_CTYPE_NAME type with no quantification. 124 125 If type == XML_CTYPE_NAME, then the name points to the name, and 126 the numchildren field will be zero and children will be NULL. The 127 quant fields indicates any quantifiers placed on the name. 128 129 CHOICE and SEQ will have name NULL, the number of children in 130 numchildren and children will point, recursively, to an array 131 of XML_Content cells. 132 133 The EMPTY, ANY, and MIXED types will only occur at top level. 134 */ 135 136 typedef struct XML_cp XML_Content; 137 138 struct XML_cp { 139 enum XML_Content_Type type; 140 enum XML_Content_Quant quant; 141 XML_Char * name; 142 unsigned int numchildren; 143 XML_Content * children; 144 }; 145 146 147 /* This is called for an element declaration. See above for 148 description of the model argument. It's the caller's responsibility 149 to free model when finished with it. 150 */ 151 typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, 152 const XML_Char *name, 153 XML_Content *model); 154 155 XMLPARSEAPI(void) 156 XML_SetElementDeclHandler(XML_Parser parser, 157 XML_ElementDeclHandler eldecl); 158 159 /* The Attlist declaration handler is called for *each* attribute. So 160 a single Attlist declaration with multiple attributes declared will 161 generate multiple calls to this handler. The "default" parameter 162 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 163 keyword. The "isrequired" parameter will be true and the default 164 value will be NULL in the case of "#REQUIRED". If "isrequired" is 165 true and default is non-NULL, then this is a "#FIXED" default. 166 */ 167 typedef void (XMLCALL *XML_AttlistDeclHandler) ( 168 void *userData, 169 const XML_Char *elname, 170 const XML_Char *attname, 171 const XML_Char *att_type, 172 const XML_Char *dflt, 173 int isrequired); 174 175 XMLPARSEAPI(void) 176 XML_SetAttlistDeclHandler(XML_Parser parser, 177 XML_AttlistDeclHandler attdecl); 178 179 /* The XML declaration handler is called for *both* XML declarations 180 and text declarations. The way to distinguish is that the version 181 parameter will be NULL for text declarations. The encoding 182 parameter may be NULL for XML declarations. The standalone 183 parameter will be -1, 0, or 1 indicating respectively that there 184 was no standalone parameter in the declaration, that it was given 185 as no, or that it was given as yes. 186 */ 187 typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, 188 const XML_Char *version, 189 const XML_Char *encoding, 190 int standalone); 191 192 XMLPARSEAPI(void) 193 XML_SetXmlDeclHandler(XML_Parser parser, 194 XML_XmlDeclHandler xmldecl); 195 196 197 typedef struct { 198 void *(*malloc_fcn)(size_t size); 199 void *(*realloc_fcn)(void *ptr, size_t size); 200 void (*free_fcn)(void *ptr); 201 } XML_Memory_Handling_Suite; 202 203 /* Constructs a new parser; encoding is the encoding specified by the 204 external protocol or NULL if there is none specified. 205 */ 206 XMLPARSEAPI(XML_Parser) 207 XML_ParserCreate(const XML_Char *encoding); 208 209 /* Constructs a new parser and namespace processor. Element type 210 names and attribute names that belong to a namespace will be 211 expanded; unprefixed attribute names are never expanded; unprefixed 212 element type names are expanded only if there is a default 213 namespace. The expanded name is the concatenation of the namespace 214 URI, the namespace separator character, and the local part of the 215 name. If the namespace separator is '\0' then the namespace URI 216 and the local part will be concatenated without any separator. 217 It is a programming error to use the separator '\0' with namespace 218 triplets (see XML_SetReturnNSTriplet). 219 */ 220 XMLPARSEAPI(XML_Parser) 221 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 222 223 224 /* Constructs a new parser using the memory management suite referred to 225 by memsuite. If memsuite is NULL, then use the standard library memory 226 suite. If namespaceSeparator is non-NULL it creates a parser with 227 namespace processing as described above. The character pointed at 228 will serve as the namespace separator. 229 230 All further memory operations used for the created parser will come from 231 the given suite. 232 */ 233 XMLPARSEAPI(XML_Parser) 234 XML_ParserCreate_MM(const XML_Char *encoding, 235 const XML_Memory_Handling_Suite *memsuite, 236 const XML_Char *namespaceSeparator); 237 238 /* Prepare a parser object to be re-used. This is particularly 239 valuable when memory allocation overhead is disproportionatly high, 240 such as when a large number of small documnents need to be parsed. 241 All handlers are cleared from the parser, except for the 242 unknownEncodingHandler. The parser's external state is re-initialized 243 except for the values of ns and ns_triplets. 244 245 Added in Expat 1.95.3. 246 */ 247 XMLPARSEAPI(XML_Bool) 248 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 249 250 /* atts is array of name/value pairs, terminated by 0; 251 names and values are 0 terminated. 252 */ 253 typedef void (XMLCALL *XML_StartElementHandler) (void *userData, 254 const XML_Char *name, 255 const XML_Char **atts); 256 257 typedef void (XMLCALL *XML_EndElementHandler) (void *userData, 258 const XML_Char *name); 259 260 261 /* s is not 0 terminated. */ 262 typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, 263 const XML_Char *s, 264 int len); 265 266 /* target and data are 0 terminated */ 267 typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( 268 void *userData, 269 const XML_Char *target, 270 const XML_Char *data); 271 272 /* data is 0 terminated */ 273 typedef void (XMLCALL *XML_CommentHandler) (void *userData, 274 const XML_Char *data); 275 276 typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); 277 typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); 278 279 /* This is called for any characters in the XML document for which 280 there is no applicable handler. This includes both characters that 281 are part of markup which is of a kind that is not reported 282 (comments, markup declarations), or characters that are part of a 283 construct which could be reported but for which no handler has been 284 supplied. The characters are passed exactly as they were in the XML 285 document except that they will be encoded in UTF-8 or UTF-16. 286 Line boundaries are not normalized. Note that a byte order mark 287 character is not passed to the default handler. There are no 288 guarantees about how characters are divided between calls to the 289 default handler: for example, a comment might be split between 290 multiple calls. 291 */ 292 typedef void (XMLCALL *XML_DefaultHandler) (void *userData, 293 const XML_Char *s, 294 int len); 295 296 /* This is called for the start of the DOCTYPE declaration, before 297 any DTD or internal subset is parsed. 298 */ 299 typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( 300 void *userData, 301 const XML_Char *doctypeName, 302 const XML_Char *sysid, 303 const XML_Char *pubid, 304 int has_internal_subset); 305 306 /* This is called for the start of the DOCTYPE declaration when the 307 closing > is encountered, but after processing any external 308 subset. 309 */ 310 typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 311 312 /* This is called for entity declarations. The is_parameter_entity 313 argument will be non-zero if the entity is a parameter entity, zero 314 otherwise. 315 316 For internal entities (<!ENTITY foo "bar">), value will 317 be non-NULL and systemId, publicID, and notationName will be NULL. 318 The value string is NOT nul-terminated; the length is provided in 319 the value_length argument. Since it is legal to have zero-length 320 values, do not use this argument to test for internal entities. 321 322 For external entities, value will be NULL and systemId will be 323 non-NULL. The publicId argument will be NULL unless a public 324 identifier was provided. The notationName argument will have a 325 non-NULL value only for unparsed entity declarations. 326 327 Note that is_parameter_entity can't be changed to XML_Bool, since 328 that would break binary compatibility. 329 */ 330 typedef void (XMLCALL *XML_EntityDeclHandler) ( 331 void *userData, 332 const XML_Char *entityName, 333 int is_parameter_entity, 334 const XML_Char *value, 335 int value_length, 336 const XML_Char *base, 337 const XML_Char *systemId, 338 const XML_Char *publicId, 339 const XML_Char *notationName); 340 341 XMLPARSEAPI(void) 342 XML_SetEntityDeclHandler(XML_Parser parser, 343 XML_EntityDeclHandler handler); 344 345 /* OBSOLETE -- OBSOLETE -- OBSOLETE 346 This handler has been superceded by the EntityDeclHandler above. 347 It is provided here for backward compatibility. 348 349 This is called for a declaration of an unparsed (NDATA) entity. 350 The base argument is whatever was set by XML_SetBase. The 351 entityName, systemId and notationName arguments will never be 352 NULL. The other arguments may be. 353 */ 354 typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( 355 void *userData, 356 const XML_Char *entityName, 357 const XML_Char *base, 358 const XML_Char *systemId, 359 const XML_Char *publicId, 360 const XML_Char *notationName); 361 362 /* This is called for a declaration of notation. The base argument is 363 whatever was set by XML_SetBase. The notationName will never be 364 NULL. The other arguments can be. 365 */ 366 typedef void (XMLCALL *XML_NotationDeclHandler) ( 367 void *userData, 368 const XML_Char *notationName, 369 const XML_Char *base, 370 const XML_Char *systemId, 371 const XML_Char *publicId); 372 373 /* When namespace processing is enabled, these are called once for 374 each namespace declaration. The call to the start and end element 375 handlers occur between the calls to the start and end namespace 376 declaration handlers. For an xmlns attribute, prefix will be 377 NULL. For an xmlns="" attribute, uri will be NULL. 378 */ 379 typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( 380 void *userData, 381 const XML_Char *prefix, 382 const XML_Char *uri); 383 384 typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( 385 void *userData, 386 const XML_Char *prefix); 387 388 /* This is called if the document is not standalone, that is, it has an 389 external subset or a reference to a parameter entity, but does not 390 have standalone="yes". If this handler returns XML_STATUS_ERROR, 391 then processing will not continue, and the parser will return a 392 XML_ERROR_NOT_STANDALONE error. 393 If parameter entity parsing is enabled, then in addition to the 394 conditions above this handler will only be called if the referenced 395 entity was actually read. 396 */ 397 typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); 398 399 /* This is called for a reference to an external parsed general 400 entity. The referenced entity is not automatically parsed. The 401 application can parse it immediately or later using 402 XML_ExternalEntityParserCreate. 403 404 The parser argument is the parser parsing the entity containing the 405 reference; it can be passed as the parser argument to 406 XML_ExternalEntityParserCreate. The systemId argument is the 407 system identifier as specified in the entity declaration; it will 408 not be NULL. 409 410 The base argument is the system identifier that should be used as 411 the base for resolving systemId if systemId was relative; this is 412 set by XML_SetBase; it may be NULL. 413 414 The publicId argument is the public identifier as specified in the 415 entity declaration, or NULL if none was specified; the whitespace 416 in the public identifier will have been normalized as required by 417 the XML spec. 418 419 The context argument specifies the parsing context in the format 420 expected by the context argument to XML_ExternalEntityParserCreate; 421 context is valid only until the handler returns, so if the 422 referenced entity is to be parsed later, it must be copied. 423 context is NULL only when the entity is a parameter entity. 424 425 The handler should return XML_STATUS_ERROR if processing should not 426 continue because of a fatal error in the handling of the external 427 entity. In this case the calling parser will return an 428 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 429 430 Note that unlike other handlers the first argument is the parser, 431 not userData. 432 */ 433 typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( 434 XML_Parser parser, 435 const XML_Char *context, 436 const XML_Char *base, 437 const XML_Char *systemId, 438 const XML_Char *publicId); 439 440 /* This is called in two situations: 441 1) An entity reference is encountered for which no declaration 442 has been read *and* this is not an error. 443 2) An internal entity reference is read, but not expanded, because 444 XML_SetDefaultHandler has been called. 445 Note: skipped parameter entities in declarations and skipped general 446 entities in attribute values cannot be reported, because 447 the event would be out of sync with the reporting of the 448 declarations or attribute values 449 */ 450 typedef void (XMLCALL *XML_SkippedEntityHandler) ( 451 void *userData, 452 const XML_Char *entityName, 453 int is_parameter_entity); 454 455 /* This structure is filled in by the XML_UnknownEncodingHandler to 456 provide information to the parser about encodings that are unknown 457 to the parser. 458 459 The map[b] member gives information about byte sequences whose 460 first byte is b. 461 462 If map[b] is c where c is >= 0, then b by itself encodes the 463 Unicode scalar value c. 464 465 If map[b] is -1, then the byte sequence is malformed. 466 467 If map[b] is -n, where n >= 2, then b is the first byte of an 468 n-byte sequence that encodes a single Unicode scalar value. 469 470 The data member will be passed as the first argument to the convert 471 function. 472 473 The convert function is used to convert multibyte sequences; s will 474 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 475 convert function must return the Unicode scalar value represented 476 by this byte sequence or -1 if the byte sequence is malformed. 477 478 The convert function may be NULL if the encoding is a single-byte 479 encoding, that is if map[b] >= -1 for all bytes b. 480 481 When the parser is finished with the encoding, then if release is 482 not NULL, it will call release passing it the data member; once 483 release has been called, the convert function will not be called 484 again. 485 486 Expat places certain restrictions on the encodings that are supported 487 using this mechanism. 488 489 1. Every ASCII character that can appear in a well-formed XML document, 490 other than the characters 491 492 $@\^`{}~ 493 494 must be represented by a single byte, and that byte must be the 495 same byte that represents that character in ASCII. 496 497 2. No character may require more than 4 bytes to encode. 498 499 3. All characters encoded must have Unicode scalar values <= 500 0xFFFF, (i.e., characters that would be encoded by surrogates in 501 UTF-16 are not allowed). Note that this restriction doesn't 502 apply to the built-in support for UTF-8 and UTF-16. 503 504 4. No Unicode character may be encoded by more than one distinct 505 sequence of bytes. 506 */ 507 typedef struct { 508 int map[256]; 509 void *data; 510 int (XMLCALL *convert)(void *data, const char *s); 511 void (XMLCALL *release)(void *data); 512 } XML_Encoding; 513 514 /* This is called for an encoding that is unknown to the parser. 515 516 The encodingHandlerData argument is that which was passed as the 517 second argument to XML_SetUnknownEncodingHandler. 518 519 The name argument gives the name of the encoding as specified in 520 the encoding declaration. 521 522 If the callback can provide information about the encoding, it must 523 fill in the XML_Encoding structure, and return XML_STATUS_OK. 524 Otherwise it must return XML_STATUS_ERROR. 525 526 If info does not describe a suitable encoding, then the parser will 527 return an XML_UNKNOWN_ENCODING error. 528 */ 529 typedef int (XMLCALL *XML_UnknownEncodingHandler) ( 530 void *encodingHandlerData, 531 const XML_Char *name, 532 XML_Encoding *info); 533 534 XMLPARSEAPI(void) 535 XML_SetElementHandler(XML_Parser parser, 536 XML_StartElementHandler start, 537 XML_EndElementHandler end); 538 539 XMLPARSEAPI(void) 540 XML_SetStartElementHandler(XML_Parser parser, 541 XML_StartElementHandler handler); 542 543 XMLPARSEAPI(void) 544 XML_SetEndElementHandler(XML_Parser parser, 545 XML_EndElementHandler handler); 546 547 XMLPARSEAPI(void) 548 XML_SetCharacterDataHandler(XML_Parser parser, 549 XML_CharacterDataHandler handler); 550 551 XMLPARSEAPI(void) 552 XML_SetProcessingInstructionHandler(XML_Parser parser, 553 XML_ProcessingInstructionHandler handler); 554 XMLPARSEAPI(void) 555 XML_SetCommentHandler(XML_Parser parser, 556 XML_CommentHandler handler); 557 558 XMLPARSEAPI(void) 559 XML_SetCdataSectionHandler(XML_Parser parser, 560 XML_StartCdataSectionHandler start, 561 XML_EndCdataSectionHandler end); 562 563 XMLPARSEAPI(void) 564 XML_SetStartCdataSectionHandler(XML_Parser parser, 565 XML_StartCdataSectionHandler start); 566 567 XMLPARSEAPI(void) 568 XML_SetEndCdataSectionHandler(XML_Parser parser, 569 XML_EndCdataSectionHandler end); 570 571 /* This sets the default handler and also inhibits expansion of 572 internal entities. These entity references will be passed to the 573 default handler, or to the skipped entity handler, if one is set. 574 */ 575 XMLPARSEAPI(void) 576 XML_SetDefaultHandler(XML_Parser parser, 577 XML_DefaultHandler handler); 578 579 /* This sets the default handler but does not inhibit expansion of 580 internal entities. The entity reference will not be passed to the 581 default handler. 582 */ 583 XMLPARSEAPI(void) 584 XML_SetDefaultHandlerExpand(XML_Parser parser, 585 XML_DefaultHandler handler); 586 587 XMLPARSEAPI(void) 588 XML_SetDoctypeDeclHandler(XML_Parser parser, 589 XML_StartDoctypeDeclHandler start, 590 XML_EndDoctypeDeclHandler end); 591 592 XMLPARSEAPI(void) 593 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 594 XML_StartDoctypeDeclHandler start); 595 596 XMLPARSEAPI(void) 597 XML_SetEndDoctypeDeclHandler(XML_Parser parser, 598 XML_EndDoctypeDeclHandler end); 599 600 XMLPARSEAPI(void) 601 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 602 XML_UnparsedEntityDeclHandler handler); 603 604 XMLPARSEAPI(void) 605 XML_SetNotationDeclHandler(XML_Parser parser, 606 XML_NotationDeclHandler handler); 607 608 XMLPARSEAPI(void) 609 XML_SetNamespaceDeclHandler(XML_Parser parser, 610 XML_StartNamespaceDeclHandler start, 611 XML_EndNamespaceDeclHandler end); 612 613 XMLPARSEAPI(void) 614 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 615 XML_StartNamespaceDeclHandler start); 616 617 XMLPARSEAPI(void) 618 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 619 XML_EndNamespaceDeclHandler end); 620 621 XMLPARSEAPI(void) 622 XML_SetNotStandaloneHandler(XML_Parser parser, 623 XML_NotStandaloneHandler handler); 624 625 XMLPARSEAPI(void) 626 XML_SetExternalEntityRefHandler(XML_Parser parser, 627 XML_ExternalEntityRefHandler handler); 628 629 /* If a non-NULL value for arg is specified here, then it will be 630 passed as the first argument to the external entity ref handler 631 instead of the parser object. 632 */ 633 XMLPARSEAPI(void) 634 XML_SetExternalEntityRefHandlerArg(XML_Parser parser, 635 void *arg); 636 637 XMLPARSEAPI(void) 638 XML_SetSkippedEntityHandler(XML_Parser parser, 639 XML_SkippedEntityHandler handler); 640 641 XMLPARSEAPI(void) 642 XML_SetUnknownEncodingHandler(XML_Parser parser, 643 XML_UnknownEncodingHandler handler, 644 void *encodingHandlerData); 645 646 /* This can be called within a handler for a start element, end 647 element, processing instruction or character data. It causes the 648 corresponding markup to be passed to the default handler. 649 */ 650 XMLPARSEAPI(void) 651 XML_DefaultCurrent(XML_Parser parser); 652 653 /* If do_nst is non-zero, and namespace processing is in effect, and 654 a name has a prefix (i.e. an explicit namespace qualifier) then 655 that name is returned as a triplet in a single string separated by 656 the separator character specified when the parser was created: URI 657 + sep + local_name + sep + prefix. 658 659 If do_nst is zero, then namespace information is returned in the 660 default manner (URI + sep + local_name) whether or not the name 661 has a prefix. 662 663 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 664 XML_ParseBuffer has no effect. 665 */ 666 667 XMLPARSEAPI(void) 668 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 669 670 /* This value is passed as the userData argument to callbacks. */ 671 XMLPARSEAPI(void) 672 XML_SetUserData(XML_Parser parser, void *userData); 673 674 /* Returns the last value set by XML_SetUserData or NULL. */ 675 #define XML_GetUserData(parser) (*(void **)(parser)) 676 677 /* This is equivalent to supplying an encoding argument to 678 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 679 zero otherwise. 680 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 681 has no effect and returns XML_STATUS_ERROR. 682 */ 683 XMLPARSEAPI(enum XML_Status) 684 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 685 686 /* If this function is called, then the parser will be passed as the 687 first argument to callbacks instead of userData. The userData will 688 still be accessible using XML_GetUserData. 689 */ 690 XMLPARSEAPI(void) 691 XML_UseParserAsHandlerArg(XML_Parser parser); 692 693 /* If useDTD == XML_TRUE is passed to this function, then the parser 694 will assume that there is an external subset, even if none is 695 specified in the document. In such a case the parser will call the 696 externalEntityRefHandler with a value of NULL for the systemId 697 argument (the publicId and context arguments will be NULL as well). 698 Note: For the purpose of checking WFC: Entity Declared, passing 699 useDTD == XML_TRUE will make the parser behave as if the document 700 had a DTD with an external subset. 701 Note: If this function is called, then this must be done before 702 the first call to XML_Parse or XML_ParseBuffer, since it will 703 have no effect after that. Returns 704 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 705 Note: If the document does not have a DOCTYPE declaration at all, 706 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 707 be called, despite an external subset being parsed. 708 Note: If XML_DTD is not defined when Expat is compiled, returns 709 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 710 */ 711 XMLPARSEAPI(enum XML_Error) 712 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 713 714 715 /* Sets the base to be used for resolving relative URIs in system 716 identifiers in declarations. Resolving relative identifiers is 717 left to the application: this value will be passed through as the 718 base argument to the XML_ExternalEntityRefHandler, 719 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 720 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 721 XML_STATUS_OK otherwise. 722 */ 723 XMLPARSEAPI(enum XML_Status) 724 XML_SetBase(XML_Parser parser, const XML_Char *base); 725 726 XMLPARSEAPI(const XML_Char *) 727 XML_GetBase(XML_Parser parser); 728 729 /* Returns the number of the attribute/value pairs passed in last call 730 to the XML_StartElementHandler that were specified in the start-tag 731 rather than defaulted. Each attribute/value pair counts as 2; thus 732 this correspondds to an index into the atts array passed to the 733 XML_StartElementHandler. 734 */ 735 XMLPARSEAPI(int) 736 XML_GetSpecifiedAttributeCount(XML_Parser parser); 737 738 /* Returns the index of the ID attribute passed in the last call to 739 XML_StartElementHandler, or -1 if there is no ID attribute. Each 740 attribute/value pair counts as 2; thus this correspondds to an 741 index into the atts array passed to the XML_StartElementHandler. 742 */ 743 XMLPARSEAPI(int) 744 XML_GetIdAttributeIndex(XML_Parser parser); 745 746 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 747 detected. The last call to XML_Parse must have isFinal true; len 748 may be zero for this call (or any other). 749 750 Though the return values for these functions has always been 751 described as a Boolean value, the implementation, at least for the 752 1.95.x series, has always returned exactly one of the XML_Status 753 values. 754 */ 755 XMLPARSEAPI(enum XML_Status) 756 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 757 758 XMLPARSEAPI(void *) 759 XML_GetBuffer(XML_Parser parser, int len); 760 761 XMLPARSEAPI(enum XML_Status) 762 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 763 764 /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 765 Must be called from within a call-back handler, except when aborting 766 (resumable = 0) an already suspended parser. Some call-backs may 767 still follow because they would otherwise get lost. Examples: 768 - endElementHandler() for empty elements when stopped in 769 startElementHandler(), 770 - endNameSpaceDeclHandler() when stopped in endElementHandler(), 771 and possibly others. 772 773 Can be called from most handlers, including DTD related call-backs, 774 except when parsing an external parameter entity and resumable != 0. 775 Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 776 Possible error codes: 777 - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 778 - XML_ERROR_FINISHED: when the parser has already finished. 779 - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 780 781 When resumable != 0 (true) then parsing is suspended, that is, 782 XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 783 Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 784 return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 785 786 *Note*: 787 This will be applied to the current parser instance only, that is, if 788 there is a parent parser then it will continue parsing when the 789 externalEntityRefHandler() returns. It is up to the implementation of 790 the externalEntityRefHandler() to call XML_StopParser() on the parent 791 parser (recursively), if one wants to stop parsing altogether. 792 793 When suspended, parsing can be resumed by calling XML_ResumeParser(). 794 */ 795 XMLPARSEAPI(enum XML_Status) 796 XML_StopParser(XML_Parser parser, XML_Bool resumable); 797 798 /* Resumes parsing after it has been suspended with XML_StopParser(). 799 Must not be called from within a handler call-back. Returns same 800 status codes as XML_Parse() or XML_ParseBuffer(). 801 Additional error code XML_ERROR_NOT_SUSPENDED possible. 802 803 *Note*: 804 This must be called on the most deeply nested child parser instance 805 first, and on its parent parser only after the child parser has finished, 806 to be applied recursively until the document entity's parser is restarted. 807 That is, the parent parser will not resume by itself and it is up to the 808 application to call XML_ResumeParser() on it at the appropriate moment. 809 */ 810 XMLPARSEAPI(enum XML_Status) 811 XML_ResumeParser(XML_Parser parser); 812 813 enum XML_Parsing { 814 XML_INITIALIZED, 815 XML_PARSING, 816 XML_FINISHED, 817 XML_SUSPENDED 818 }; 819 820 typedef struct { 821 enum XML_Parsing parsing; 822 XML_Bool finalBuffer; 823 } XML_ParsingStatus; 824 825 /* Returns status of parser with respect to being initialized, parsing, 826 finished, or suspended and processing the final buffer. 827 XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 828 XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 829 */ 830 XMLPARSEAPI(void) 831 XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 832 833 /* Creates an XML_Parser object that can parse an external general 834 entity; context is a '\0'-terminated string specifying the parse 835 context; encoding is a '\0'-terminated string giving the name of 836 the externally specified encoding, or NULL if there is no 837 externally specified encoding. The context string consists of a 838 sequence of tokens separated by formfeeds (\f); a token consisting 839 of a name specifies that the general entity of the name is open; a 840 token of the form prefix=uri specifies the namespace for a 841 particular prefix; a token of the form =uri specifies the default 842 namespace. This can be called at any point after the first call to 843 an ExternalEntityRefHandler so longer as the parser has not yet 844 been freed. The new parser is completely independent and may 845 safely be used in a separate thread. The handlers and userData are 846 initialized from the parser argument. Returns NULL if out of memory. 847 Otherwise returns a new XML_Parser object. 848 */ 849 XMLPARSEAPI(XML_Parser) 850 XML_ExternalEntityParserCreate(XML_Parser parser, 851 const XML_Char *context, 852 const XML_Char *encoding); 853 854 enum XML_ParamEntityParsing { 855 XML_PARAM_ENTITY_PARSING_NEVER, 856 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 857 XML_PARAM_ENTITY_PARSING_ALWAYS 858 }; 859 860 /* Controls parsing of parameter entities (including the external DTD 861 subset). If parsing of parameter entities is enabled, then 862 references to external parameter entities (including the external 863 DTD subset) will be passed to the handler set with 864 XML_SetExternalEntityRefHandler. The context passed will be 0. 865 866 Unlike external general entities, external parameter entities can 867 only be parsed synchronously. If the external parameter entity is 868 to be parsed, it must be parsed during the call to the external 869 entity ref handler: the complete sequence of 870 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 871 XML_ParserFree calls must be made during this call. After 872 XML_ExternalEntityParserCreate has been called to create the parser 873 for the external parameter entity (context must be 0 for this 874 call), it is illegal to make any calls on the old parser until 875 XML_ParserFree has been called on the newly created parser. 876 If the library has been compiled without support for parameter 877 entity parsing (ie without XML_DTD being defined), then 878 XML_SetParamEntityParsing will return 0 if parsing of parameter 879 entities is requested; otherwise it will return non-zero. 880 Note: If XML_SetParamEntityParsing is called after XML_Parse or 881 XML_ParseBuffer, then it has no effect and will always return 0. 882 */ 883 XMLPARSEAPI(int) 884 XML_SetParamEntityParsing(XML_Parser parser, 885 enum XML_ParamEntityParsing parsing); 886 887 /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 888 XML_GetErrorCode returns information about the error. 889 */ 890 XMLPARSEAPI(enum XML_Error) 891 XML_GetErrorCode(XML_Parser parser); 892 893 /* These functions return information about the current parse 894 location. They may be called from any callback called to report 895 some parse event; in this case the location is the location of the 896 first of the sequence of characters that generated the event. When 897 called from callbacks generated by declarations in the document 898 prologue, the location identified isn't as neatly defined, but will 899 be within the relevant markup. When called outside of the callback 900 functions, the position indicated will be just past the last parse 901 event (regardless of whether there was an associated callback). 902 903 They may also be called after returning from a call to XML_Parse 904 or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 905 the location is the location of the character at which the error 906 was detected; otherwise the location is the location of the last 907 parse event, as described above. 908 */ 909 XMLPARSEAPI(XML_Size) 910 XML_GetCurrentLineNumber(XML_Parser parser); 911 912 XMLPARSEAPI(XML_Size) 913 XML_GetCurrentColumnNumber(XML_Parser parser); 914 915 XMLPARSEAPI(XML_Index) 916 XML_GetCurrentByteIndex(XML_Parser parser); 917 918 /* Return the number of bytes in the current event. 919 Returns 0 if the event is in an internal entity. 920 */ 921 XMLPARSEAPI(int) 922 XML_GetCurrentByteCount(XML_Parser parser); 923 924 /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets 925 the integer pointed to by offset to the offset within this buffer 926 of the current parse position, and sets the integer pointed to by size 927 to the size of this buffer (the number of input bytes). Otherwise 928 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 929 active. 930 931 NOTE: The character pointer returned should not be used outside 932 the handler that makes the call. 933 */ 934 XMLPARSEAPI(const char *) 935 XML_GetInputContext(XML_Parser parser, 936 int *offset, 937 int *size); 938 939 /* For backwards compatibility with previous versions. */ 940 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 941 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 942 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 943 944 /* Frees the content model passed to the element declaration handler */ 945 XMLPARSEAPI(void) 946 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 947 948 /* Exposing the memory handling functions used in Expat */ 949 XMLPARSEAPI(void *) 950 XML_MemMalloc(XML_Parser parser, size_t size); 951 952 XMLPARSEAPI(void *) 953 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 954 955 XMLPARSEAPI(void) 956 XML_MemFree(XML_Parser parser, void *ptr); 957 958 /* Frees memory used by the parser. */ 959 XMLPARSEAPI(void) 960 XML_ParserFree(XML_Parser parser); 961 962 /* Returns a string describing the error. */ 963 XMLPARSEAPI(const XML_LChar *) 964 XML_ErrorString(enum XML_Error code); 965 966 /* Return a string containing the version number of this expat */ 967 XMLPARSEAPI(const XML_LChar *) 968 XML_ExpatVersion(void); 969 970 typedef struct { 971 int major; 972 int minor; 973 int micro; 974 } XML_Expat_Version; 975 976 /* Return an XML_Expat_Version structure containing numeric version 977 number information for this version of expat. 978 */ 979 XMLPARSEAPI(XML_Expat_Version) 980 XML_ExpatVersionInfo(void); 981 982 /* Added in Expat 1.95.5. */ 983 enum XML_FeatureEnum { 984 XML_FEATURE_END = 0, 985 XML_FEATURE_UNICODE, 986 XML_FEATURE_UNICODE_WCHAR_T, 987 XML_FEATURE_DTD, 988 XML_FEATURE_CONTEXT_BYTES, 989 XML_FEATURE_MIN_SIZE, 990 XML_FEATURE_SIZEOF_XML_CHAR, 991 XML_FEATURE_SIZEOF_XML_LCHAR, 992 XML_FEATURE_NS, 993 XML_FEATURE_LARGE_SIZE 994 /* Additional features must be added to the end of this enum. */ 995 }; 996 997 typedef struct { 998 enum XML_FeatureEnum feature; 999 const XML_LChar *name; 1000 long int value; 1001 } XML_Feature; 1002 1003 XMLPARSEAPI(const XML_Feature *) 1004 XML_GetFeatureList(void); 1005 1006 1007 /* Expat follows the GNU/Linux convention of odd number minor version for 1008 beta/development releases and even number minor version for stable 1009 releases. Micro is bumped with each release, and set to 0 with each 1010 change to major or minor version. 1011 */ 1012 #define XML_MAJOR_VERSION 2 1013 #define XML_MINOR_VERSION 0 1014 #define XML_MICRO_VERSION 1 1015 1016 #ifdef __cplusplus 1017 } 1018 #endif 1019 1020 #endif /* not Expat_INCLUDED */ 1021