1 /* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd 2 See the file COPYING for copying permission. 3 */ 4 5 #ifndef XmlParse_INCLUDED 6 #define XmlParse_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 19 #if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) 20 #define XML_USE_MSC_EXTENSIONS 1 21 #endif 22 23 /* Expat tries very hard to make the API boundary very specifically 24 defined. There are two macros defined to control this boundary; 25 each of these can be defined before including this header to 26 achieve some different behavior, but doing so it not recommended or 27 tested frequently. 28 29 XMLCALL - The calling convention to use for all calls across the 30 "library boundary." This will default to cdecl, and 31 try really hard to tell the compiler that's what we 32 want. 33 34 XMLIMPORT - Whatever magic is needed to note that a function is 35 to be imported from a dynamically loaded library 36 (.dll, .so, or .sl, depending on your platform). 37 38 The XMLCALL macro was added in Expat 1.95.7. The only one which is 39 expected to be directly useful in client code is XMLCALL. 40 41 Note that on at least some Unix versions, the Expat library must be 42 compiled with the cdecl calling convention as the default since 43 system headers may assume the cdecl convention. 44 */ 45 #ifndef XMLCALL 46 #if defined(XML_USE_MSC_EXTENSIONS) 47 #define XMLCALL __cdecl 48 #elif defined(__GNUC__) 49 #define XMLCALL __attribute__((cdecl)) 50 #else 51 /* For any platform which uses this definition and supports more than 52 one calling convention, we need to extend this definition to 53 declare the convention used on that platform, if it's possible to 54 do so. 55 56 If this is the case for your platform, please file a bug report 57 with information on how to identify your platform via the C 58 pre-processor and how to specify the same calling convention as the 59 platform's malloc() implementation. 60 */ 61 #define XMLCALL 62 #endif 63 #endif /* not defined XMLCALL */ 64 65 66 #if !defined(XML_STATIC) && !defined(XMLIMPORT) 67 #ifndef XML_BUILDING_EXPAT 68 /* using Expat from an application */ 69 70 #ifdef XML_USE_MSC_EXTENSIONS 71 #define XMLIMPORT __declspec(dllimport) 72 #endif 73 74 #endif 75 #endif /* not defined XML_STATIC */ 76 77 /* If we didn't define it above, define it away: */ 78 #ifndef XMLIMPORT 79 #define XMLIMPORT 80 #endif 81 82 83 #define XMLPARSEAPI(type) XMLIMPORT type XMLCALL 84 85 #ifdef __cplusplus 86 extern "C" { 87 #endif 88 89 #ifdef XML_UNICODE_WCHAR_T 90 #define XML_UNICODE 91 #endif 92 93 struct XML_ParserStruct; 94 typedef struct XML_ParserStruct *XML_Parser; 95 96 #ifdef XML_UNICODE /* Information is UTF-16 encoded. */ 97 #ifdef XML_UNICODE_WCHAR_T 98 typedef wchar_t XML_Char; 99 typedef wchar_t XML_LChar; 100 #else 101 typedef unsigned short XML_Char; 102 typedef char XML_LChar; 103 #endif /* XML_UNICODE_WCHAR_T */ 104 #else /* Information is UTF-8 encoded. */ 105 typedef char XML_Char; 106 typedef char XML_LChar; 107 #endif /* XML_UNICODE */ 108 109 /* Should this be defined using stdbool.h when C99 is available? */ 110 typedef unsigned char XML_Bool; 111 #define XML_TRUE ((XML_Bool) 1) 112 #define XML_FALSE ((XML_Bool) 0) 113 114 /* The XML_Status enum gives the possible return values for several 115 API functions. The preprocessor #defines are included so this 116 stanza can be added to code that still needs to support older 117 versions of Expat 1.95.x: 118 119 #ifndef XML_STATUS_OK 120 #define XML_STATUS_OK 1 121 #define XML_STATUS_ERROR 0 122 #endif 123 124 Otherwise, the #define hackery is quite ugly and would have been 125 dropped. 126 */ 127 enum XML_Status { 128 XML_STATUS_ERROR = 0, 129 #define XML_STATUS_ERROR XML_STATUS_ERROR 130 XML_STATUS_OK = 1 131 #define XML_STATUS_OK XML_STATUS_OK 132 }; 133 134 enum XML_Error { 135 XML_ERROR_NONE, 136 XML_ERROR_NO_MEMORY, 137 XML_ERROR_SYNTAX, 138 XML_ERROR_NO_ELEMENTS, 139 XML_ERROR_INVALID_TOKEN, 140 XML_ERROR_UNCLOSED_TOKEN, 141 XML_ERROR_PARTIAL_CHAR, 142 XML_ERROR_TAG_MISMATCH, 143 XML_ERROR_DUPLICATE_ATTRIBUTE, 144 XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 145 XML_ERROR_PARAM_ENTITY_REF, 146 XML_ERROR_UNDEFINED_ENTITY, 147 XML_ERROR_RECURSIVE_ENTITY_REF, 148 XML_ERROR_ASYNC_ENTITY, 149 XML_ERROR_BAD_CHAR_REF, 150 XML_ERROR_BINARY_ENTITY_REF, 151 XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 152 XML_ERROR_MISPLACED_XML_PI, 153 XML_ERROR_UNKNOWN_ENCODING, 154 XML_ERROR_INCORRECT_ENCODING, 155 XML_ERROR_UNCLOSED_CDATA_SECTION, 156 XML_ERROR_EXTERNAL_ENTITY_HANDLING, 157 XML_ERROR_NOT_STANDALONE, 158 XML_ERROR_UNEXPECTED_STATE, 159 XML_ERROR_ENTITY_DECLARED_IN_PE, 160 XML_ERROR_FEATURE_REQUIRES_XML_DTD, 161 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 162 XML_ERROR_UNBOUND_PREFIX 163 }; 164 165 enum XML_Content_Type { 166 XML_CTYPE_EMPTY = 1, 167 XML_CTYPE_ANY, 168 XML_CTYPE_MIXED, 169 XML_CTYPE_NAME, 170 XML_CTYPE_CHOICE, 171 XML_CTYPE_SEQ 172 }; 173 174 enum XML_Content_Quant { 175 XML_CQUANT_NONE, 176 XML_CQUANT_OPT, 177 XML_CQUANT_REP, 178 XML_CQUANT_PLUS 179 }; 180 181 /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 182 XML_CQUANT_NONE, and the other fields will be zero or NULL. 183 If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 184 numchildren will contain number of elements that may be mixed in 185 and children point to an array of XML_Content cells that will be 186 all of XML_CTYPE_NAME type with no quantification. 187 188 If type == XML_CTYPE_NAME, then the name points to the name, and 189 the numchildren field will be zero and children will be NULL. The 190 quant fields indicates any quantifiers placed on the name. 191 192 CHOICE and SEQ will have name NULL, the number of children in 193 numchildren and children will point, recursively, to an array 194 of XML_Content cells. 195 196 The EMPTY, ANY, and MIXED types will only occur at top level. 197 */ 198 199 typedef struct XML_cp XML_Content; 200 201 struct XML_cp { 202 enum XML_Content_Type type; 203 enum XML_Content_Quant quant; 204 XML_Char * name; 205 unsigned int numchildren; 206 XML_Content * children; 207 }; 208 209 210 /* This is called for an element declaration. See above for 211 description of the model argument. It's the caller's responsibility 212 to free model when finished with it. 213 */ 214 typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, 215 const XML_Char *name, 216 XML_Content *model); 217 218 XMLPARSEAPI(void) 219 XML_SetElementDeclHandler(XML_Parser parser, 220 XML_ElementDeclHandler eldecl); 221 222 /* The Attlist declaration handler is called for *each* attribute. So 223 a single Attlist declaration with multiple attributes declared will 224 generate multiple calls to this handler. The "default" parameter 225 may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 226 keyword. The "isrequired" parameter will be true and the default 227 value will be NULL in the case of "#REQUIRED". If "isrequired" is 228 true and default is non-NULL, then this is a "#FIXED" default. 229 */ 230 typedef void (XMLCALL *XML_AttlistDeclHandler) ( 231 void *userData, 232 const XML_Char *elname, 233 const XML_Char *attname, 234 const XML_Char *att_type, 235 const XML_Char *dflt, 236 int isrequired); 237 238 XMLPARSEAPI(void) 239 XML_SetAttlistDeclHandler(XML_Parser parser, 240 XML_AttlistDeclHandler attdecl); 241 242 /* The XML declaration handler is called for *both* XML declarations 243 and text declarations. The way to distinguish is that the version 244 parameter will be NULL for text declarations. The encoding 245 parameter may be NULL for XML declarations. The standalone 246 parameter will be -1, 0, or 1 indicating respectively that there 247 was no standalone parameter in the declaration, that it was given 248 as no, or that it was given as yes. 249 */ 250 typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, 251 const XML_Char *version, 252 const XML_Char *encoding, 253 int standalone); 254 255 XMLPARSEAPI(void) 256 XML_SetXmlDeclHandler(XML_Parser parser, 257 XML_XmlDeclHandler xmldecl); 258 259 260 typedef struct { 261 void *(XMLCALL *malloc_fcn)(size_t size); 262 void *(XMLCALL *realloc_fcn)(void *ptr, size_t size); 263 void (XMLCALL *free_fcn)(void *ptr); 264 } XML_Memory_Handling_Suite; 265 266 /* Constructs a new parser; encoding is the encoding specified by the 267 external protocol or NULL if there is none specified. 268 */ 269 XMLPARSEAPI(XML_Parser) 270 XML_ParserCreate(const XML_Char *encoding); 271 272 /* Constructs a new parser and namespace processor. Element type 273 names and attribute names that belong to a namespace will be 274 expanded; unprefixed attribute names are never expanded; unprefixed 275 element type names are expanded only if there is a default 276 namespace. The expanded name is the concatenation of the namespace 277 URI, the namespace separator character, and the local part of the 278 name. If the namespace separator is '\0' then the namespace URI 279 and the local part will be concatenated without any separator. 280 When a namespace is not declared, the name and prefix will be 281 passed through without expansion. 282 */ 283 XMLPARSEAPI(XML_Parser) 284 XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 285 286 287 /* Constructs a new parser using the memory management suite referred to 288 by memsuite. If memsuite is NULL, then use the standard library memory 289 suite. If namespaceSeparator is non-NULL it creates a parser with 290 namespace processing as described above. The character pointed at 291 will serve as the namespace separator. 292 293 All further memory operations used for the created parser will come from 294 the given suite. 295 */ 296 XMLPARSEAPI(XML_Parser) 297 XML_ParserCreate_MM(const XML_Char *encoding, 298 const XML_Memory_Handling_Suite *memsuite, 299 const XML_Char *namespaceSeparator); 300 301 /* Prepare a parser object to be re-used. This is particularly 302 valuable when memory allocation overhead is disproportionatly high, 303 such as when a large number of small documnents need to be parsed. 304 All handlers are cleared from the parser, except for the 305 unknownEncodingHandler. The parser's external state is re-initialized 306 except for the values of ns and ns_triplets. 307 308 Added in Expat 1.95.3. 309 */ 310 XMLPARSEAPI(XML_Bool) 311 XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 312 313 /* atts is array of name/value pairs, terminated by 0; 314 names and values are 0 terminated. 315 */ 316 typedef void (XMLCALL *XML_StartElementHandler) (void *userData, 317 const XML_Char *name, 318 const XML_Char **atts); 319 320 typedef void (XMLCALL *XML_EndElementHandler) (void *userData, 321 const XML_Char *name); 322 323 324 /* s is not 0 terminated. */ 325 typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, 326 const XML_Char *s, 327 int len); 328 329 /* target and data are 0 terminated */ 330 typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( 331 void *userData, 332 const XML_Char *target, 333 const XML_Char *data); 334 335 /* data is 0 terminated */ 336 typedef void (XMLCALL *XML_CommentHandler) (void *userData, 337 const XML_Char *data); 338 339 typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); 340 typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); 341 342 /* This is called for any characters in the XML document for which 343 there is no applicable handler. This includes both characters that 344 are part of markup which is of a kind that is not reported 345 (comments, markup declarations), or characters that are part of a 346 construct which could be reported but for which no handler has been 347 supplied. The characters are passed exactly as they were in the XML 348 document except that they will be encoded in UTF-8 or UTF-16. 349 Line boundaries are not normalized. Note that a byte order mark 350 character is not passed to the default handler. There are no 351 guarantees about how characters are divided between calls to the 352 default handler: for example, a comment might be split between 353 multiple calls. 354 */ 355 typedef void (XMLCALL *XML_DefaultHandler) (void *userData, 356 const XML_Char *s, 357 int len); 358 359 /* This is called for the start of the DOCTYPE declaration, before 360 any DTD or internal subset is parsed. 361 */ 362 typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( 363 void *userData, 364 const XML_Char *doctypeName, 365 const XML_Char *sysid, 366 const XML_Char *pubid, 367 int has_internal_subset); 368 369 /* This is called for the start of the DOCTYPE declaration when the 370 closing > is encountered, but after processing any external 371 subset. 372 */ 373 typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 374 375 /* This is called for entity declarations. The is_parameter_entity 376 argument will be non-zero if the entity is a parameter entity, zero 377 otherwise. 378 379 For internal entities (<!ENTITY foo "bar">), value will 380 be non-NULL and systemId, publicID, and notationName will be NULL. 381 The value string is NOT nul-terminated; the length is provided in 382 the value_length argument. Since it is legal to have zero-length 383 values, do not use this argument to test for internal entities. 384 385 For external entities, value will be NULL and systemId will be 386 non-NULL. The publicId argument will be NULL unless a public 387 identifier was provided. The notationName argument will have a 388 non-NULL value only for unparsed entity declarations. 389 390 Note that is_parameter_entity can't be changed to XML_Bool, since 391 that would break binary compatibility. 392 */ 393 typedef void (XMLCALL *XML_EntityDeclHandler) ( 394 void *userData, 395 const XML_Char *entityName, 396 int is_parameter_entity, 397 const XML_Char *value, 398 int value_length, 399 const XML_Char *base, 400 const XML_Char *systemId, 401 const XML_Char *publicId, 402 const XML_Char *notationName); 403 404 XMLPARSEAPI(void) 405 XML_SetEntityDeclHandler(XML_Parser parser, 406 XML_EntityDeclHandler handler); 407 408 /* OBSOLETE -- OBSOLETE -- OBSOLETE 409 This handler has been superceded by the EntityDeclHandler above. 410 It is provided here for backward compatibility. 411 412 This is called for a declaration of an unparsed (NDATA) entity. 413 The base argument is whatever was set by XML_SetBase. The 414 entityName, systemId and notationName arguments will never be 415 NULL. The other arguments may be. 416 */ 417 typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( 418 void *userData, 419 const XML_Char *entityName, 420 const XML_Char *base, 421 const XML_Char *systemId, 422 const XML_Char *publicId, 423 const XML_Char *notationName); 424 425 /* This is called for a declaration of notation. The base argument is 426 whatever was set by XML_SetBase. The notationName will never be 427 NULL. The other arguments can be. 428 */ 429 typedef void (XMLCALL *XML_NotationDeclHandler) ( 430 void *userData, 431 const XML_Char *notationName, 432 const XML_Char *base, 433 const XML_Char *systemId, 434 const XML_Char *publicId); 435 436 /* When namespace processing is enabled, these are called once for 437 each namespace declaration. The call to the start and end element 438 handlers occur between the calls to the start and end namespace 439 declaration handlers. For an xmlns attribute, prefix will be 440 NULL. For an xmlns="" attribute, uri will be NULL. 441 */ 442 typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( 443 void *userData, 444 const XML_Char *prefix, 445 const XML_Char *uri); 446 447 typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( 448 void *userData, 449 const XML_Char *prefix); 450 451 /* This is called if the document is not standalone, that is, it has an 452 external subset or a reference to a parameter entity, but does not 453 have standalone="yes". If this handler returns XML_STATUS_ERROR, 454 then processing will not continue, and the parser will return a 455 XML_ERROR_NOT_STANDALONE error. 456 If parameter entity parsing is enabled, then in addition to the 457 conditions above this handler will only be called if the referenced 458 entity was actually read. 459 */ 460 typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); 461 462 /* This is called for a reference to an external parsed general 463 entity. The referenced entity is not automatically parsed. The 464 application can parse it immediately or later using 465 XML_ExternalEntityParserCreate. 466 467 The parser argument is the parser parsing the entity containing the 468 reference; it can be passed as the parser argument to 469 XML_ExternalEntityParserCreate. The systemId argument is the 470 system identifier as specified in the entity declaration; it will 471 not be NULL. 472 473 The base argument is the system identifier that should be used as 474 the base for resolving systemId if systemId was relative; this is 475 set by XML_SetBase; it may be NULL. 476 477 The publicId argument is the public identifier as specified in the 478 entity declaration, or NULL if none was specified; the whitespace 479 in the public identifier will have been normalized as required by 480 the XML spec. 481 482 The context argument specifies the parsing context in the format 483 expected by the context argument to XML_ExternalEntityParserCreate; 484 context is valid only until the handler returns, so if the 485 referenced entity is to be parsed later, it must be copied. 486 context is NULL only when the entity is a parameter entity. 487 488 The handler should return XML_STATUS_ERROR if processing should not 489 continue because of a fatal error in the handling of the external 490 entity. In this case the calling parser will return an 491 XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 492 493 Note that unlike other handlers the first argument is the parser, 494 not userData. 495 */ 496 typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( 497 XML_Parser parser, 498 const XML_Char *context, 499 const XML_Char *base, 500 const XML_Char *systemId, 501 const XML_Char *publicId); 502 503 /* This is called in two situations: 504 1) An entity reference is encountered for which no declaration 505 has been read *and* this is not an error. 506 2) An internal entity reference is read, but not expanded, because 507 XML_SetDefaultHandler has been called. 508 Note: skipped parameter entities in declarations and skipped general 509 entities in attribute values cannot be reported, because 510 the event would be out of sync with the reporting of the 511 declarations or attribute values 512 */ 513 typedef void (XMLCALL *XML_SkippedEntityHandler) ( 514 void *userData, 515 const XML_Char *entityName, 516 int is_parameter_entity); 517 518 /* This structure is filled in by the XML_UnknownEncodingHandler to 519 provide information to the parser about encodings that are unknown 520 to the parser. 521 522 The map[b] member gives information about byte sequences whose 523 first byte is b. 524 525 If map[b] is c where c is >= 0, then b by itself encodes the 526 Unicode scalar value c. 527 528 If map[b] is -1, then the byte sequence is malformed. 529 530 If map[b] is -n, where n >= 2, then b is the first byte of an 531 n-byte sequence that encodes a single Unicode scalar value. 532 533 The data member will be passed as the first argument to the convert 534 function. 535 536 The convert function is used to convert multibyte sequences; s will 537 point to a n-byte sequence where map[(unsigned char)*s] == -n. The 538 convert function must return the Unicode scalar value represented 539 by this byte sequence or -1 if the byte sequence is malformed. 540 541 The convert function may be NULL if the encoding is a single-byte 542 encoding, that is if map[b] >= -1 for all bytes b. 543 544 When the parser is finished with the encoding, then if release is 545 not NULL, it will call release passing it the data member; once 546 release has been called, the convert function will not be called 547 again. 548 549 Expat places certain restrictions on the encodings that are supported 550 using this mechanism. 551 552 1. Every ASCII character that can appear in a well-formed XML document, 553 other than the characters 554 555 $@\^`{}~ 556 557 must be represented by a single byte, and that byte must be the 558 same byte that represents that character in ASCII. 559 560 2. No character may require more than 4 bytes to encode. 561 562 3. All characters encoded must have Unicode scalar values <= 563 0xFFFF, (i.e., characters that would be encoded by surrogates in 564 UTF-16 are not allowed). Note that this restriction doesn't 565 apply to the built-in support for UTF-8 and UTF-16. 566 567 4. No Unicode character may be encoded by more than one distinct 568 sequence of bytes. 569 */ 570 typedef struct { 571 int map[256]; 572 void *data; 573 int (XMLCALL *convert)(void *data, const char *s); 574 void (XMLCALL *release)(void *data); 575 } XML_Encoding; 576 577 /* This is called for an encoding that is unknown to the parser. 578 579 The encodingHandlerData argument is that which was passed as the 580 second argument to XML_SetUnknownEncodingHandler. 581 582 The name argument gives the name of the encoding as specified in 583 the encoding declaration. 584 585 If the callback can provide information about the encoding, it must 586 fill in the XML_Encoding structure, and return XML_STATUS_OK. 587 Otherwise it must return XML_STATUS_ERROR. 588 589 If info does not describe a suitable encoding, then the parser will 590 return an XML_UNKNOWN_ENCODING error. 591 */ 592 typedef int (XMLCALL *XML_UnknownEncodingHandler) ( 593 void *encodingHandlerData, 594 const XML_Char *name, 595 XML_Encoding *info); 596 597 XMLPARSEAPI(void) 598 XML_SetElementHandler(XML_Parser parser, 599 XML_StartElementHandler start, 600 XML_EndElementHandler end); 601 602 XMLPARSEAPI(void) 603 XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler); 604 605 XMLPARSEAPI(void) 606 XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler); 607 608 XMLPARSEAPI(void) 609 XML_SetCharacterDataHandler(XML_Parser parser, 610 XML_CharacterDataHandler handler); 611 612 XMLPARSEAPI(void) 613 XML_SetProcessingInstructionHandler(XML_Parser parser, 614 XML_ProcessingInstructionHandler handler); 615 XMLPARSEAPI(void) 616 XML_SetCommentHandler(XML_Parser parser, 617 XML_CommentHandler handler); 618 619 XMLPARSEAPI(void) 620 XML_SetCdataSectionHandler(XML_Parser parser, 621 XML_StartCdataSectionHandler start, 622 XML_EndCdataSectionHandler end); 623 624 XMLPARSEAPI(void) 625 XML_SetStartCdataSectionHandler(XML_Parser parser, 626 XML_StartCdataSectionHandler start); 627 628 XMLPARSEAPI(void) 629 XML_SetEndCdataSectionHandler(XML_Parser parser, 630 XML_EndCdataSectionHandler end); 631 632 /* This sets the default handler and also inhibits expansion of 633 internal entities. These entity references will be passed to the 634 default handler, or to the skipped entity handler, if one is set. 635 */ 636 XMLPARSEAPI(void) 637 XML_SetDefaultHandler(XML_Parser parser, 638 XML_DefaultHandler handler); 639 640 /* This sets the default handler but does not inhibit expansion of 641 internal entities. The entity reference will not be passed to the 642 default handler. 643 */ 644 XMLPARSEAPI(void) 645 XML_SetDefaultHandlerExpand(XML_Parser parser, 646 XML_DefaultHandler handler); 647 648 XMLPARSEAPI(void) 649 XML_SetDoctypeDeclHandler(XML_Parser parser, 650 XML_StartDoctypeDeclHandler start, 651 XML_EndDoctypeDeclHandler end); 652 653 XMLPARSEAPI(void) 654 XML_SetStartDoctypeDeclHandler(XML_Parser parser, 655 XML_StartDoctypeDeclHandler start); 656 657 XMLPARSEAPI(void) 658 XML_SetEndDoctypeDeclHandler(XML_Parser parser, 659 XML_EndDoctypeDeclHandler end); 660 661 XMLPARSEAPI(void) 662 XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 663 XML_UnparsedEntityDeclHandler handler); 664 665 XMLPARSEAPI(void) 666 XML_SetNotationDeclHandler(XML_Parser parser, 667 XML_NotationDeclHandler handler); 668 669 XMLPARSEAPI(void) 670 XML_SetNamespaceDeclHandler(XML_Parser parser, 671 XML_StartNamespaceDeclHandler start, 672 XML_EndNamespaceDeclHandler end); 673 674 XMLPARSEAPI(void) 675 XML_SetStartNamespaceDeclHandler(XML_Parser parser, 676 XML_StartNamespaceDeclHandler start); 677 678 XMLPARSEAPI(void) 679 XML_SetEndNamespaceDeclHandler(XML_Parser parser, 680 XML_EndNamespaceDeclHandler end); 681 682 XMLPARSEAPI(void) 683 XML_SetNotStandaloneHandler(XML_Parser parser, 684 XML_NotStandaloneHandler handler); 685 686 XMLPARSEAPI(void) 687 XML_SetExternalEntityRefHandler(XML_Parser parser, 688 XML_ExternalEntityRefHandler handler); 689 690 /* If a non-NULL value for arg is specified here, then it will be 691 passed as the first argument to the external entity ref handler 692 instead of the parser object. 693 */ 694 XMLPARSEAPI(void) 695 XML_SetExternalEntityRefHandlerArg(XML_Parser, void *arg); 696 697 XMLPARSEAPI(void) 698 XML_SetSkippedEntityHandler(XML_Parser parser, 699 XML_SkippedEntityHandler handler); 700 701 XMLPARSEAPI(void) 702 XML_SetUnknownEncodingHandler(XML_Parser parser, 703 XML_UnknownEncodingHandler handler, 704 void *encodingHandlerData); 705 706 /* This can be called within a handler for a start element, end 707 element, processing instruction or character data. It causes the 708 corresponding markup to be passed to the default handler. 709 */ 710 XMLPARSEAPI(void) 711 XML_DefaultCurrent(XML_Parser parser); 712 713 /* If do_nst is non-zero, and namespace processing is in effect, and 714 a name has a prefix (i.e. an explicit namespace qualifier) then 715 that name is returned as a triplet in a single string separated by 716 the separator character specified when the parser was created: URI 717 + sep + local_name + sep + prefix. 718 719 If do_nst is zero, then namespace information is returned in the 720 default manner (URI + sep + local_name) whether or not the name 721 has a prefix. 722 723 Note: Calling XML_SetReturnNSTriplet after XML_Parse or 724 XML_ParseBuffer has no effect. 725 */ 726 727 XMLPARSEAPI(void) 728 XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 729 730 /* This value is passed as the userData argument to callbacks. */ 731 XMLPARSEAPI(void) 732 XML_SetUserData(XML_Parser parser, void *userData); 733 734 /* Returns the last value set by XML_SetUserData or NULL. */ 735 #define XML_GetUserData(parser) (*(void **)(parser)) 736 737 /* This is equivalent to supplying an encoding argument to 738 XML_ParserCreate. On success XML_SetEncoding returns non-zero, 739 zero otherwise. 740 Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 741 has no effect and returns XML_STATUS_ERROR. 742 */ 743 XMLPARSEAPI(enum XML_Status) 744 XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 745 746 /* If this function is called, then the parser will be passed as the 747 first argument to callbacks instead of userData. The userData will 748 still be accessible using XML_GetUserData. 749 */ 750 XMLPARSEAPI(void) 751 XML_UseParserAsHandlerArg(XML_Parser parser); 752 753 /* If useDTD == XML_TRUE is passed to this function, then the parser 754 will assume that there is an external subset, even if none is 755 specified in the document. In such a case the parser will call the 756 externalEntityRefHandler with a value of NULL for the systemId 757 argument (the publicId and context arguments will be NULL as well). 758 Note: If this function is called, then this must be done before 759 the first call to XML_Parse or XML_ParseBuffer, since it will 760 have no effect after that. Returns 761 XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 762 Note: If the document does not have a DOCTYPE declaration at all, 763 then startDoctypeDeclHandler and endDoctypeDeclHandler will not 764 be called, despite an external subset being parsed. 765 Note: If XML_DTD is not defined when Expat is compiled, returns 766 XML_ERROR_FEATURE_REQUIRES_XML_DTD. 767 */ 768 XMLPARSEAPI(enum XML_Error) 769 XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 770 771 772 /* Sets the base to be used for resolving relative URIs in system 773 identifiers in declarations. Resolving relative identifiers is 774 left to the application: this value will be passed through as the 775 base argument to the XML_ExternalEntityRefHandler, 776 XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 777 argument will be copied. Returns XML_STATUS_ERROR if out of memory, 778 XML_STATUS_OK otherwise. 779 */ 780 XMLPARSEAPI(enum XML_Status) 781 XML_SetBase(XML_Parser parser, const XML_Char *base); 782 783 XMLPARSEAPI(const XML_Char *) 784 XML_GetBase(XML_Parser parser); 785 786 /* Returns the number of the attribute/value pairs passed in last call 787 to the XML_StartElementHandler that were specified in the start-tag 788 rather than defaulted. Each attribute/value pair counts as 2; thus 789 this correspondds to an index into the atts array passed to the 790 XML_StartElementHandler. 791 */ 792 XMLPARSEAPI(int) 793 XML_GetSpecifiedAttributeCount(XML_Parser parser); 794 795 /* Returns the index of the ID attribute passed in the last call to 796 XML_StartElementHandler, or -1 if there is no ID attribute. Each 797 attribute/value pair counts as 2; thus this correspondds to an 798 index into the atts array passed to the XML_StartElementHandler. 799 */ 800 XMLPARSEAPI(int) 801 XML_GetIdAttributeIndex(XML_Parser parser); 802 803 /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 804 detected. The last call to XML_Parse must have isFinal true; len 805 may be zero for this call (or any other). 806 807 Though the return values for these functions has always been 808 described as a Boolean value, the implementation, at least for the 809 1.95.x series, has always returned exactly one of the XML_Status 810 values. 811 */ 812 XMLPARSEAPI(enum XML_Status) 813 XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 814 815 XMLPARSEAPI(void *) 816 XML_GetBuffer(XML_Parser parser, int len); 817 818 XMLPARSEAPI(enum XML_Status) 819 XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 820 821 /* Creates an XML_Parser object that can parse an external general 822 entity; context is a '\0'-terminated string specifying the parse 823 context; encoding is a '\0'-terminated string giving the name of 824 the externally specified encoding, or NULL if there is no 825 externally specified encoding. The context string consists of a 826 sequence of tokens separated by formfeeds (\f); a token consisting 827 of a name specifies that the general entity of the name is open; a 828 token of the form prefix=uri specifies the namespace for a 829 particular prefix; a token of the form =uri specifies the default 830 namespace. This can be called at any point after the first call to 831 an ExternalEntityRefHandler so longer as the parser has not yet 832 been freed. The new parser is completely independent and may 833 safely be used in a separate thread. The handlers and userData are 834 initialized from the parser argument. Returns NULL if out of memory. 835 Otherwise returns a new XML_Parser object. 836 */ 837 XMLPARSEAPI(XML_Parser) 838 XML_ExternalEntityParserCreate(XML_Parser parser, 839 const XML_Char *context, 840 const XML_Char *encoding); 841 842 enum XML_ParamEntityParsing { 843 XML_PARAM_ENTITY_PARSING_NEVER, 844 XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 845 XML_PARAM_ENTITY_PARSING_ALWAYS 846 }; 847 848 /* Controls parsing of parameter entities (including the external DTD 849 subset). If parsing of parameter entities is enabled, then 850 references to external parameter entities (including the external 851 DTD subset) will be passed to the handler set with 852 XML_SetExternalEntityRefHandler. The context passed will be 0. 853 854 Unlike external general entities, external parameter entities can 855 only be parsed synchronously. If the external parameter entity is 856 to be parsed, it must be parsed during the call to the external 857 entity ref handler: the complete sequence of 858 XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 859 XML_ParserFree calls must be made during this call. After 860 XML_ExternalEntityParserCreate has been called to create the parser 861 for the external parameter entity (context must be 0 for this 862 call), it is illegal to make any calls on the old parser until 863 XML_ParserFree has been called on the newly created parser. 864 If the library has been compiled without support for parameter 865 entity parsing (ie without XML_DTD being defined), then 866 XML_SetParamEntityParsing will return 0 if parsing of parameter 867 entities is requested; otherwise it will return non-zero. 868 Note: If XML_SetParamEntityParsing is called after XML_Parse or 869 XML_ParseBuffer, then it has no effect and will always return 0. 870 */ 871 XMLPARSEAPI(int) 872 XML_SetParamEntityParsing(XML_Parser parser, 873 enum XML_ParamEntityParsing parsing); 874 875 /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 876 XML_GetErrorCode returns information about the error. 877 */ 878 XMLPARSEAPI(enum XML_Error) 879 XML_GetErrorCode(XML_Parser parser); 880 881 /* These functions return information about the current parse 882 location. They may be called from any callback called to report 883 some parse event; in this case the location is the location of the 884 first of the sequence of characters that generated the event. When 885 called from callbacks generated by declarations in the document 886 prologue, the location identified isn't as neatly defined, but will 887 be within the relevant markup. When called outside of the callback 888 functions, the position indicated will be just past the last parse 889 event (regardless of whether there was an associated callback). 890 891 They may also be called after returning from a call to XML_Parse 892 or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 893 the location is the location of the character at which the error 894 was detected; otherwise the location is the location of the last 895 parse event, as described above. 896 */ 897 XMLPARSEAPI(int) XML_GetCurrentLineNumber(XML_Parser parser); 898 XMLPARSEAPI(int) XML_GetCurrentColumnNumber(XML_Parser parser); 899 XMLPARSEAPI(long) XML_GetCurrentByteIndex(XML_Parser parser); 900 901 /* Return the number of bytes in the current event. 902 Returns 0 if the event is in an internal entity. 903 */ 904 XMLPARSEAPI(int) 905 XML_GetCurrentByteCount(XML_Parser parser); 906 907 /* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets 908 the integer pointed to by offset to the offset within this buffer 909 of the current parse position, and sets the integer pointed to by size 910 to the size of this buffer (the number of input bytes). Otherwise 911 returns a NULL pointer. Also returns a NULL pointer if a parse isn't 912 active. 913 914 NOTE: The character pointer returned should not be used outside 915 the handler that makes the call. 916 */ 917 XMLPARSEAPI(const char *) 918 XML_GetInputContext(XML_Parser parser, 919 int *offset, 920 int *size); 921 922 /* For backwards compatibility with previous versions. */ 923 #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 924 #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 925 #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 926 927 /* Frees the content model passed to the element declaration handler */ 928 XMLPARSEAPI(void) 929 XML_FreeContentModel(XML_Parser parser, XML_Content *model); 930 931 /* Exposing the memory handling functions used in Expat */ 932 XMLPARSEAPI(void *) 933 XML_MemMalloc(XML_Parser parser, size_t size); 934 935 XMLPARSEAPI(void *) 936 XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 937 938 XMLPARSEAPI(void) 939 XML_MemFree(XML_Parser parser, void *ptr); 940 941 /* Frees memory used by the parser. */ 942 XMLPARSEAPI(void) 943 XML_ParserFree(XML_Parser parser); 944 945 /* Returns a string describing the error. */ 946 XMLPARSEAPI(const XML_LChar *) 947 XML_ErrorString(enum XML_Error code); 948 949 /* Return a string containing the version number of this expat */ 950 XMLPARSEAPI(const XML_LChar *) 951 XML_ExpatVersion(void); 952 953 typedef struct { 954 int major; 955 int minor; 956 int micro; 957 } XML_Expat_Version; 958 959 /* Return an XML_Expat_Version structure containing numeric version 960 number information for this version of expat. 961 */ 962 XMLPARSEAPI(XML_Expat_Version) 963 XML_ExpatVersionInfo(void); 964 965 /* Added in Expat 1.95.5. */ 966 enum XML_FeatureEnum { 967 XML_FEATURE_END = 0, 968 XML_FEATURE_UNICODE, 969 XML_FEATURE_UNICODE_WCHAR_T, 970 XML_FEATURE_DTD, 971 XML_FEATURE_CONTEXT_BYTES, 972 XML_FEATURE_MIN_SIZE, 973 XML_FEATURE_SIZEOF_XML_CHAR, 974 XML_FEATURE_SIZEOF_XML_LCHAR 975 /* Additional features must be added to the end of this enum. */ 976 }; 977 978 typedef struct { 979 enum XML_FeatureEnum feature; 980 const XML_LChar *name; 981 long int value; 982 } XML_Feature; 983 984 XMLPARSEAPI(const XML_Feature *) 985 XML_GetFeatureList(void); 986 987 988 /* Expat follows the GNU/Linux convention of odd number minor version for 989 beta/development releases and even number minor version for stable 990 releases. Micro is bumped with each release, and set to 0 with each 991 change to major or minor version. 992 */ 993 #define XML_MAJOR_VERSION 1 994 #define XML_MINOR_VERSION 95 995 #define XML_MICRO_VERSION 7 996 997 #ifdef __cplusplus 998 } 999 #endif 1000 1001 #endif /* not XmlParse_INCLUDED */ 1002