10a48773fSEric van Gyzen /* 20a48773fSEric van Gyzen __ __ _ 30a48773fSEric van Gyzen ___\ \/ /_ __ __ _| |_ 40a48773fSEric van Gyzen / _ \\ /| '_ \ / _` | __| 50a48773fSEric van Gyzen | __// \| |_) | (_| | |_ 60a48773fSEric van Gyzen \___/_/\_\ .__/ \__,_|\__| 70a48773fSEric van Gyzen |_| XML parser 80a48773fSEric van Gyzen 90a48773fSEric van Gyzen Copyright (c) 1997-2000 Thai Open Source Software Center Ltd 10cc68614dSXin LI Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net> 11cc68614dSXin LI Copyright (c) 2000-2005 Fred L. Drake, Jr. <fdrake@users.sourceforge.net> 12cc68614dSXin LI Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net> 13cc68614dSXin LI Copyright (c) 2002-2016 Karl Waclawek <karl@waclawek.net> 14*4543ef51SXin LI Copyright (c) 2016-2024 Sebastian Pipping <sebastian@pipping.org> 15cc68614dSXin LI Copyright (c) 2016 Cristian Rodríguez <crrodriguez@opensuse.org> 16cc68614dSXin LI Copyright (c) 2016 Thomas Beutlich <tc@tbeu.de> 17cc68614dSXin LI Copyright (c) 2017 Rhodri James <rhodri@wildebeest.org.uk> 187ed8e142SXin LI Copyright (c) 2022 Thijs Schreijer <thijs@thijsschreijer.nl> 19*4543ef51SXin LI Copyright (c) 2023 Hanno Böck <hanno@gentoo.org> 20*4543ef51SXin LI Copyright (c) 2023 Sony Corporation / Snild Dolkow <snild@sony.com> 210a48773fSEric van Gyzen Licensed under the MIT license: 220a48773fSEric van Gyzen 230a48773fSEric van Gyzen Permission is hereby granted, free of charge, to any person obtaining 240a48773fSEric van Gyzen a copy of this software and associated documentation files (the 250a48773fSEric van Gyzen "Software"), to deal in the Software without restriction, including 260a48773fSEric van Gyzen without limitation the rights to use, copy, modify, merge, publish, 270a48773fSEric van Gyzen distribute, sublicense, and/or sell copies of the Software, and to permit 280a48773fSEric van Gyzen persons to whom the Software is furnished to do so, subject to the 290a48773fSEric van Gyzen following conditions: 300a48773fSEric van Gyzen 310a48773fSEric van Gyzen The above copyright notice and this permission notice shall be included 320a48773fSEric van Gyzen in all copies or substantial portions of the Software. 330a48773fSEric van Gyzen 340a48773fSEric van Gyzen THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, 350a48773fSEric van Gyzen EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF 360a48773fSEric van Gyzen MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN 370a48773fSEric van Gyzen NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, 380a48773fSEric van Gyzen DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR 390a48773fSEric van Gyzen OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE 400a48773fSEric van Gyzen USE OR OTHER DEALINGS IN THE SOFTWARE. 415bb6a25fSPoul-Henning Kamp */ 425bb6a25fSPoul-Henning Kamp 43220ed979SColeman Kane #ifndef Expat_INCLUDED 44220ed979SColeman Kane #define Expat_INCLUDED 1 455bb6a25fSPoul-Henning Kamp 465bb6a25fSPoul-Henning Kamp #include <stdlib.h> 47220ed979SColeman Kane #include "expat_external.h" 485bb6a25fSPoul-Henning Kamp 495bb6a25fSPoul-Henning Kamp #ifdef __cplusplus 505bb6a25fSPoul-Henning Kamp extern "C" { 515bb6a25fSPoul-Henning Kamp #endif 525bb6a25fSPoul-Henning Kamp 535bb6a25fSPoul-Henning Kamp struct XML_ParserStruct; 545bb6a25fSPoul-Henning Kamp typedef struct XML_ParserStruct *XML_Parser; 555bb6a25fSPoul-Henning Kamp 565bb6a25fSPoul-Henning Kamp typedef unsigned char XML_Bool; 575bb6a25fSPoul-Henning Kamp #define XML_TRUE ((XML_Bool)1) 585bb6a25fSPoul-Henning Kamp #define XML_FALSE ((XML_Bool)0) 595bb6a25fSPoul-Henning Kamp 60220ed979SColeman Kane /* The XML_Status enum gives the possible return values for several 61220ed979SColeman Kane API functions. The preprocessor #defines are included so this 62220ed979SColeman Kane stanza can be added to code that still needs to support older 63220ed979SColeman Kane versions of Expat 1.95.x: 64220ed979SColeman Kane 65220ed979SColeman Kane #ifndef XML_STATUS_OK 66220ed979SColeman Kane #define XML_STATUS_OK 1 67220ed979SColeman Kane #define XML_STATUS_ERROR 0 68220ed979SColeman Kane #endif 69220ed979SColeman Kane 70220ed979SColeman Kane Otherwise, the #define hackery is quite ugly and would have been 71220ed979SColeman Kane dropped. 72220ed979SColeman Kane */ 73220ed979SColeman Kane enum XML_Status { 74220ed979SColeman Kane XML_STATUS_ERROR = 0, 75220ed979SColeman Kane #define XML_STATUS_ERROR XML_STATUS_ERROR 76220ed979SColeman Kane XML_STATUS_OK = 1, 77220ed979SColeman Kane #define XML_STATUS_OK XML_STATUS_OK 78220ed979SColeman Kane XML_STATUS_SUSPENDED = 2 79220ed979SColeman Kane #define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED 80220ed979SColeman Kane }; 81220ed979SColeman Kane 825bb6a25fSPoul-Henning Kamp enum XML_Error { 835bb6a25fSPoul-Henning Kamp XML_ERROR_NONE, 845bb6a25fSPoul-Henning Kamp XML_ERROR_NO_MEMORY, 855bb6a25fSPoul-Henning Kamp XML_ERROR_SYNTAX, 865bb6a25fSPoul-Henning Kamp XML_ERROR_NO_ELEMENTS, 875bb6a25fSPoul-Henning Kamp XML_ERROR_INVALID_TOKEN, 885bb6a25fSPoul-Henning Kamp XML_ERROR_UNCLOSED_TOKEN, 895bb6a25fSPoul-Henning Kamp XML_ERROR_PARTIAL_CHAR, 905bb6a25fSPoul-Henning Kamp XML_ERROR_TAG_MISMATCH, 915bb6a25fSPoul-Henning Kamp XML_ERROR_DUPLICATE_ATTRIBUTE, 925bb6a25fSPoul-Henning Kamp XML_ERROR_JUNK_AFTER_DOC_ELEMENT, 935bb6a25fSPoul-Henning Kamp XML_ERROR_PARAM_ENTITY_REF, 945bb6a25fSPoul-Henning Kamp XML_ERROR_UNDEFINED_ENTITY, 955bb6a25fSPoul-Henning Kamp XML_ERROR_RECURSIVE_ENTITY_REF, 965bb6a25fSPoul-Henning Kamp XML_ERROR_ASYNC_ENTITY, 975bb6a25fSPoul-Henning Kamp XML_ERROR_BAD_CHAR_REF, 985bb6a25fSPoul-Henning Kamp XML_ERROR_BINARY_ENTITY_REF, 995bb6a25fSPoul-Henning Kamp XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, 1005bb6a25fSPoul-Henning Kamp XML_ERROR_MISPLACED_XML_PI, 1015bb6a25fSPoul-Henning Kamp XML_ERROR_UNKNOWN_ENCODING, 1025bb6a25fSPoul-Henning Kamp XML_ERROR_INCORRECT_ENCODING, 1035bb6a25fSPoul-Henning Kamp XML_ERROR_UNCLOSED_CDATA_SECTION, 1045bb6a25fSPoul-Henning Kamp XML_ERROR_EXTERNAL_ENTITY_HANDLING, 1055bb6a25fSPoul-Henning Kamp XML_ERROR_NOT_STANDALONE, 1065bb6a25fSPoul-Henning Kamp XML_ERROR_UNEXPECTED_STATE, 1075bb6a25fSPoul-Henning Kamp XML_ERROR_ENTITY_DECLARED_IN_PE, 1085bb6a25fSPoul-Henning Kamp XML_ERROR_FEATURE_REQUIRES_XML_DTD, 109220ed979SColeman Kane XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, 110220ed979SColeman Kane /* Added in 1.95.7. */ 111220ed979SColeman Kane XML_ERROR_UNBOUND_PREFIX, 112220ed979SColeman Kane /* Added in 1.95.8. */ 113220ed979SColeman Kane XML_ERROR_UNDECLARING_PREFIX, 114220ed979SColeman Kane XML_ERROR_INCOMPLETE_PE, 115220ed979SColeman Kane XML_ERROR_XML_DECL, 116220ed979SColeman Kane XML_ERROR_TEXT_DECL, 117220ed979SColeman Kane XML_ERROR_PUBLICID, 118220ed979SColeman Kane XML_ERROR_SUSPENDED, 119220ed979SColeman Kane XML_ERROR_NOT_SUSPENDED, 120220ed979SColeman Kane XML_ERROR_ABORTED, 121220ed979SColeman Kane XML_ERROR_FINISHED, 122220ed979SColeman Kane XML_ERROR_SUSPEND_PE, 123220ed979SColeman Kane /* Added in 2.0. */ 124220ed979SColeman Kane XML_ERROR_RESERVED_PREFIX_XML, 125220ed979SColeman Kane XML_ERROR_RESERVED_PREFIX_XMLNS, 1260a48773fSEric van Gyzen XML_ERROR_RESERVED_NAMESPACE_URI, 1270a48773fSEric van Gyzen /* Added in 2.2.1. */ 128cc68614dSXin LI XML_ERROR_INVALID_ARGUMENT, 129cc68614dSXin LI /* Added in 2.3.0. */ 130cc68614dSXin LI XML_ERROR_NO_BUFFER, 131cc68614dSXin LI /* Added in 2.4.0. */ 132cc68614dSXin LI XML_ERROR_AMPLIFICATION_LIMIT_BREACH 1335bb6a25fSPoul-Henning Kamp }; 1345bb6a25fSPoul-Henning Kamp 1355bb6a25fSPoul-Henning Kamp enum XML_Content_Type { 1365bb6a25fSPoul-Henning Kamp XML_CTYPE_EMPTY = 1, 1375bb6a25fSPoul-Henning Kamp XML_CTYPE_ANY, 1385bb6a25fSPoul-Henning Kamp XML_CTYPE_MIXED, 1395bb6a25fSPoul-Henning Kamp XML_CTYPE_NAME, 1405bb6a25fSPoul-Henning Kamp XML_CTYPE_CHOICE, 1415bb6a25fSPoul-Henning Kamp XML_CTYPE_SEQ 1425bb6a25fSPoul-Henning Kamp }; 1435bb6a25fSPoul-Henning Kamp 1445bb6a25fSPoul-Henning Kamp enum XML_Content_Quant { 1455bb6a25fSPoul-Henning Kamp XML_CQUANT_NONE, 1465bb6a25fSPoul-Henning Kamp XML_CQUANT_OPT, 1475bb6a25fSPoul-Henning Kamp XML_CQUANT_REP, 1485bb6a25fSPoul-Henning Kamp XML_CQUANT_PLUS 1495bb6a25fSPoul-Henning Kamp }; 1505bb6a25fSPoul-Henning Kamp 1515bb6a25fSPoul-Henning Kamp /* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be 1525bb6a25fSPoul-Henning Kamp XML_CQUANT_NONE, and the other fields will be zero or NULL. 1535bb6a25fSPoul-Henning Kamp If type == XML_CTYPE_MIXED, then quant will be NONE or REP and 1545bb6a25fSPoul-Henning Kamp numchildren will contain number of elements that may be mixed in 1555bb6a25fSPoul-Henning Kamp and children point to an array of XML_Content cells that will be 1565bb6a25fSPoul-Henning Kamp all of XML_CTYPE_NAME type with no quantification. 1575bb6a25fSPoul-Henning Kamp 1585bb6a25fSPoul-Henning Kamp If type == XML_CTYPE_NAME, then the name points to the name, and 1595bb6a25fSPoul-Henning Kamp the numchildren field will be zero and children will be NULL. The 1605bb6a25fSPoul-Henning Kamp quant fields indicates any quantifiers placed on the name. 1615bb6a25fSPoul-Henning Kamp 1625bb6a25fSPoul-Henning Kamp CHOICE and SEQ will have name NULL, the number of children in 1635bb6a25fSPoul-Henning Kamp numchildren and children will point, recursively, to an array 1645bb6a25fSPoul-Henning Kamp of XML_Content cells. 1655bb6a25fSPoul-Henning Kamp 1665bb6a25fSPoul-Henning Kamp The EMPTY, ANY, and MIXED types will only occur at top level. 1675bb6a25fSPoul-Henning Kamp */ 1685bb6a25fSPoul-Henning Kamp 1695bb6a25fSPoul-Henning Kamp typedef struct XML_cp XML_Content; 1705bb6a25fSPoul-Henning Kamp 1715bb6a25fSPoul-Henning Kamp struct XML_cp { 1725bb6a25fSPoul-Henning Kamp enum XML_Content_Type type; 1735bb6a25fSPoul-Henning Kamp enum XML_Content_Quant quant; 1745bb6a25fSPoul-Henning Kamp XML_Char *name; 1755bb6a25fSPoul-Henning Kamp unsigned int numchildren; 1765bb6a25fSPoul-Henning Kamp XML_Content *children; 1775bb6a25fSPoul-Henning Kamp }; 1785bb6a25fSPoul-Henning Kamp 1795bb6a25fSPoul-Henning Kamp /* This is called for an element declaration. See above for 1807ed8e142SXin LI description of the model argument. It's the user code's responsibility 1817ed8e142SXin LI to free model when finished with it. See XML_FreeContentModel. 1827ed8e142SXin LI There is no need to free the model from the handler, it can be kept 1837ed8e142SXin LI around and freed at a later stage. 1845bb6a25fSPoul-Henning Kamp */ 185220ed979SColeman Kane typedef void(XMLCALL *XML_ElementDeclHandler)(void *userData, 1865bb6a25fSPoul-Henning Kamp const XML_Char *name, 1875bb6a25fSPoul-Henning Kamp XML_Content *model); 1885bb6a25fSPoul-Henning Kamp 1895bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 1906b2c1e49SXin LI XML_SetElementDeclHandler(XML_Parser parser, XML_ElementDeclHandler eldecl); 1915bb6a25fSPoul-Henning Kamp 1925bb6a25fSPoul-Henning Kamp /* The Attlist declaration handler is called for *each* attribute. So 1935bb6a25fSPoul-Henning Kamp a single Attlist declaration with multiple attributes declared will 1945bb6a25fSPoul-Henning Kamp generate multiple calls to this handler. The "default" parameter 1955bb6a25fSPoul-Henning Kamp may be NULL in the case of the "#IMPLIED" or "#REQUIRED" 1965bb6a25fSPoul-Henning Kamp keyword. The "isrequired" parameter will be true and the default 1975bb6a25fSPoul-Henning Kamp value will be NULL in the case of "#REQUIRED". If "isrequired" is 1985bb6a25fSPoul-Henning Kamp true and default is non-NULL, then this is a "#FIXED" default. 1995bb6a25fSPoul-Henning Kamp */ 200220ed979SColeman Kane typedef void(XMLCALL *XML_AttlistDeclHandler)( 2016b2c1e49SXin LI void *userData, const XML_Char *elname, const XML_Char *attname, 2026b2c1e49SXin LI const XML_Char *att_type, const XML_Char *dflt, int isrequired); 2035bb6a25fSPoul-Henning Kamp 2045bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 2056b2c1e49SXin LI XML_SetAttlistDeclHandler(XML_Parser parser, XML_AttlistDeclHandler attdecl); 2065bb6a25fSPoul-Henning Kamp 2075bb6a25fSPoul-Henning Kamp /* The XML declaration handler is called for *both* XML declarations 2085bb6a25fSPoul-Henning Kamp and text declarations. The way to distinguish is that the version 2095bb6a25fSPoul-Henning Kamp parameter will be NULL for text declarations. The encoding 2105bb6a25fSPoul-Henning Kamp parameter may be NULL for XML declarations. The standalone 2115bb6a25fSPoul-Henning Kamp parameter will be -1, 0, or 1 indicating respectively that there 2125bb6a25fSPoul-Henning Kamp was no standalone parameter in the declaration, that it was given 2135bb6a25fSPoul-Henning Kamp as no, or that it was given as yes. 2145bb6a25fSPoul-Henning Kamp */ 215220ed979SColeman Kane typedef void(XMLCALL *XML_XmlDeclHandler)(void *userData, 2165bb6a25fSPoul-Henning Kamp const XML_Char *version, 2175bb6a25fSPoul-Henning Kamp const XML_Char *encoding, 2185bb6a25fSPoul-Henning Kamp int standalone); 2195bb6a25fSPoul-Henning Kamp 2205bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 2216b2c1e49SXin LI XML_SetXmlDeclHandler(XML_Parser parser, XML_XmlDeclHandler xmldecl); 2225bb6a25fSPoul-Henning Kamp 2235bb6a25fSPoul-Henning Kamp typedef struct { 2245bb6a25fSPoul-Henning Kamp void *(*malloc_fcn)(size_t size); 2255bb6a25fSPoul-Henning Kamp void *(*realloc_fcn)(void *ptr, size_t size); 2265bb6a25fSPoul-Henning Kamp void (*free_fcn)(void *ptr); 2275bb6a25fSPoul-Henning Kamp } XML_Memory_Handling_Suite; 2285bb6a25fSPoul-Henning Kamp 2295bb6a25fSPoul-Henning Kamp /* Constructs a new parser; encoding is the encoding specified by the 2305bb6a25fSPoul-Henning Kamp external protocol or NULL if there is none specified. 2315bb6a25fSPoul-Henning Kamp */ 2325bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Parser) 2335bb6a25fSPoul-Henning Kamp XML_ParserCreate(const XML_Char *encoding); 2345bb6a25fSPoul-Henning Kamp 2355bb6a25fSPoul-Henning Kamp /* Constructs a new parser and namespace processor. Element type 2365bb6a25fSPoul-Henning Kamp names and attribute names that belong to a namespace will be 2375bb6a25fSPoul-Henning Kamp expanded; unprefixed attribute names are never expanded; unprefixed 2385bb6a25fSPoul-Henning Kamp element type names are expanded only if there is a default 2395bb6a25fSPoul-Henning Kamp namespace. The expanded name is the concatenation of the namespace 2405bb6a25fSPoul-Henning Kamp URI, the namespace separator character, and the local part of the 2415bb6a25fSPoul-Henning Kamp name. If the namespace separator is '\0' then the namespace URI 2425bb6a25fSPoul-Henning Kamp and the local part will be concatenated without any separator. 243220ed979SColeman Kane It is a programming error to use the separator '\0' with namespace 244220ed979SColeman Kane triplets (see XML_SetReturnNSTriplet). 2457ed8e142SXin LI If a namespace separator is chosen that can be part of a URI or 2467ed8e142SXin LI part of an XML name, splitting an expanded name back into its 2477ed8e142SXin LI 1, 2 or 3 original parts on application level in the element handler 2487ed8e142SXin LI may end up vulnerable, so these are advised against; sane choices for 2497ed8e142SXin LI a namespace separator are e.g. '\n' (line feed) and '|' (pipe). 2507ed8e142SXin LI 2517ed8e142SXin LI Note that Expat does not validate namespace URIs (beyond encoding) 2527ed8e142SXin LI against RFC 3986 today (and is not required to do so with regard to 2537ed8e142SXin LI the XML 1.0 namespaces specification) but it may start doing that 2547ed8e142SXin LI in future releases. Before that, an application using Expat must 2557ed8e142SXin LI be ready to receive namespace URIs containing non-URI characters. 2565bb6a25fSPoul-Henning Kamp */ 2575bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Parser) 2585bb6a25fSPoul-Henning Kamp XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); 2595bb6a25fSPoul-Henning Kamp 260220ed979SColeman Kane /* Constructs a new parser using the memory management suite referred to 2615bb6a25fSPoul-Henning Kamp by memsuite. If memsuite is NULL, then use the standard library memory 2625bb6a25fSPoul-Henning Kamp suite. If namespaceSeparator is non-NULL it creates a parser with 2635bb6a25fSPoul-Henning Kamp namespace processing as described above. The character pointed at 2645bb6a25fSPoul-Henning Kamp will serve as the namespace separator. 2655bb6a25fSPoul-Henning Kamp 2665bb6a25fSPoul-Henning Kamp All further memory operations used for the created parser will come from 2675bb6a25fSPoul-Henning Kamp the given suite. 2685bb6a25fSPoul-Henning Kamp */ 2695bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Parser) 2705bb6a25fSPoul-Henning Kamp XML_ParserCreate_MM(const XML_Char *encoding, 2715bb6a25fSPoul-Henning Kamp const XML_Memory_Handling_Suite *memsuite, 2725bb6a25fSPoul-Henning Kamp const XML_Char *namespaceSeparator); 2735bb6a25fSPoul-Henning Kamp 274*4543ef51SXin LI /* Prepare a parser object to be reused. This is particularly 2750a48773fSEric van Gyzen valuable when memory allocation overhead is disproportionately high, 2765bb6a25fSPoul-Henning Kamp such as when a large number of small documnents need to be parsed. 2775bb6a25fSPoul-Henning Kamp All handlers are cleared from the parser, except for the 2785bb6a25fSPoul-Henning Kamp unknownEncodingHandler. The parser's external state is re-initialized 2795bb6a25fSPoul-Henning Kamp except for the values of ns and ns_triplets. 2805bb6a25fSPoul-Henning Kamp 2815bb6a25fSPoul-Henning Kamp Added in Expat 1.95.3. 2825bb6a25fSPoul-Henning Kamp */ 2835bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Bool) 2845bb6a25fSPoul-Henning Kamp XML_ParserReset(XML_Parser parser, const XML_Char *encoding); 2855bb6a25fSPoul-Henning Kamp 2865bb6a25fSPoul-Henning Kamp /* atts is array of name/value pairs, terminated by 0; 2875bb6a25fSPoul-Henning Kamp names and values are 0 terminated. 2885bb6a25fSPoul-Henning Kamp */ 289220ed979SColeman Kane typedef void(XMLCALL *XML_StartElementHandler)(void *userData, 2905bb6a25fSPoul-Henning Kamp const XML_Char *name, 2915bb6a25fSPoul-Henning Kamp const XML_Char **atts); 2925bb6a25fSPoul-Henning Kamp 293220ed979SColeman Kane typedef void(XMLCALL *XML_EndElementHandler)(void *userData, 2945bb6a25fSPoul-Henning Kamp const XML_Char *name); 2955bb6a25fSPoul-Henning Kamp 2965bb6a25fSPoul-Henning Kamp /* s is not 0 terminated. */ 297220ed979SColeman Kane typedef void(XMLCALL *XML_CharacterDataHandler)(void *userData, 2986b2c1e49SXin LI const XML_Char *s, int len); 2995bb6a25fSPoul-Henning Kamp 3005bb6a25fSPoul-Henning Kamp /* target and data are 0 terminated */ 3016b2c1e49SXin LI typedef void(XMLCALL *XML_ProcessingInstructionHandler)(void *userData, 3025bb6a25fSPoul-Henning Kamp const XML_Char *target, 3035bb6a25fSPoul-Henning Kamp const XML_Char *data); 3045bb6a25fSPoul-Henning Kamp 3055bb6a25fSPoul-Henning Kamp /* data is 0 terminated */ 3066b2c1e49SXin LI typedef void(XMLCALL *XML_CommentHandler)(void *userData, const XML_Char *data); 3075bb6a25fSPoul-Henning Kamp 308220ed979SColeman Kane typedef void(XMLCALL *XML_StartCdataSectionHandler)(void *userData); 309220ed979SColeman Kane typedef void(XMLCALL *XML_EndCdataSectionHandler)(void *userData); 3105bb6a25fSPoul-Henning Kamp 3115bb6a25fSPoul-Henning Kamp /* This is called for any characters in the XML document for which 3125bb6a25fSPoul-Henning Kamp there is no applicable handler. This includes both characters that 3135bb6a25fSPoul-Henning Kamp are part of markup which is of a kind that is not reported 3145bb6a25fSPoul-Henning Kamp (comments, markup declarations), or characters that are part of a 3155bb6a25fSPoul-Henning Kamp construct which could be reported but for which no handler has been 3165bb6a25fSPoul-Henning Kamp supplied. The characters are passed exactly as they were in the XML 3175bb6a25fSPoul-Henning Kamp document except that they will be encoded in UTF-8 or UTF-16. 3185bb6a25fSPoul-Henning Kamp Line boundaries are not normalized. Note that a byte order mark 3195bb6a25fSPoul-Henning Kamp character is not passed to the default handler. There are no 3205bb6a25fSPoul-Henning Kamp guarantees about how characters are divided between calls to the 3215bb6a25fSPoul-Henning Kamp default handler: for example, a comment might be split between 3225bb6a25fSPoul-Henning Kamp multiple calls. 3235bb6a25fSPoul-Henning Kamp */ 3246b2c1e49SXin LI typedef void(XMLCALL *XML_DefaultHandler)(void *userData, const XML_Char *s, 3255bb6a25fSPoul-Henning Kamp int len); 3265bb6a25fSPoul-Henning Kamp 3275bb6a25fSPoul-Henning Kamp /* This is called for the start of the DOCTYPE declaration, before 3285bb6a25fSPoul-Henning Kamp any DTD or internal subset is parsed. 3295bb6a25fSPoul-Henning Kamp */ 3306b2c1e49SXin LI typedef void(XMLCALL *XML_StartDoctypeDeclHandler)(void *userData, 3315bb6a25fSPoul-Henning Kamp const XML_Char *doctypeName, 3325bb6a25fSPoul-Henning Kamp const XML_Char *sysid, 3335bb6a25fSPoul-Henning Kamp const XML_Char *pubid, 3345bb6a25fSPoul-Henning Kamp int has_internal_subset); 3355bb6a25fSPoul-Henning Kamp 3367ed8e142SXin LI /* This is called for the end of the DOCTYPE declaration when the 3375bb6a25fSPoul-Henning Kamp closing > is encountered, but after processing any external 3385bb6a25fSPoul-Henning Kamp subset. 3395bb6a25fSPoul-Henning Kamp */ 340220ed979SColeman Kane typedef void(XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); 3415bb6a25fSPoul-Henning Kamp 3425bb6a25fSPoul-Henning Kamp /* This is called for entity declarations. The is_parameter_entity 3435bb6a25fSPoul-Henning Kamp argument will be non-zero if the entity is a parameter entity, zero 3445bb6a25fSPoul-Henning Kamp otherwise. 3455bb6a25fSPoul-Henning Kamp 3465bb6a25fSPoul-Henning Kamp For internal entities (<!ENTITY foo "bar">), value will 3475bb6a25fSPoul-Henning Kamp be non-NULL and systemId, publicID, and notationName will be NULL. 348cc68614dSXin LI The value string is NOT null-terminated; the length is provided in 3495bb6a25fSPoul-Henning Kamp the value_length argument. Since it is legal to have zero-length 3505bb6a25fSPoul-Henning Kamp values, do not use this argument to test for internal entities. 3515bb6a25fSPoul-Henning Kamp 3525bb6a25fSPoul-Henning Kamp For external entities, value will be NULL and systemId will be 3535bb6a25fSPoul-Henning Kamp non-NULL. The publicId argument will be NULL unless a public 3545bb6a25fSPoul-Henning Kamp identifier was provided. The notationName argument will have a 3555bb6a25fSPoul-Henning Kamp non-NULL value only for unparsed entity declarations. 3565bb6a25fSPoul-Henning Kamp 3575bb6a25fSPoul-Henning Kamp Note that is_parameter_entity can't be changed to XML_Bool, since 3585bb6a25fSPoul-Henning Kamp that would break binary compatibility. 3595bb6a25fSPoul-Henning Kamp */ 360220ed979SColeman Kane typedef void(XMLCALL *XML_EntityDeclHandler)( 3616b2c1e49SXin LI void *userData, const XML_Char *entityName, int is_parameter_entity, 3626b2c1e49SXin LI const XML_Char *value, int value_length, const XML_Char *base, 3636b2c1e49SXin LI const XML_Char *systemId, const XML_Char *publicId, 3645bb6a25fSPoul-Henning Kamp const XML_Char *notationName); 3655bb6a25fSPoul-Henning Kamp 3665bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 3676b2c1e49SXin LI XML_SetEntityDeclHandler(XML_Parser parser, XML_EntityDeclHandler handler); 3685bb6a25fSPoul-Henning Kamp 3695bb6a25fSPoul-Henning Kamp /* OBSOLETE -- OBSOLETE -- OBSOLETE 370be8aff81SXin LI This handler has been superseded by the EntityDeclHandler above. 3715bb6a25fSPoul-Henning Kamp It is provided here for backward compatibility. 3725bb6a25fSPoul-Henning Kamp 3735bb6a25fSPoul-Henning Kamp This is called for a declaration of an unparsed (NDATA) entity. 3745bb6a25fSPoul-Henning Kamp The base argument is whatever was set by XML_SetBase. The 3755bb6a25fSPoul-Henning Kamp entityName, systemId and notationName arguments will never be 3765bb6a25fSPoul-Henning Kamp NULL. The other arguments may be. 3775bb6a25fSPoul-Henning Kamp */ 378220ed979SColeman Kane typedef void(XMLCALL *XML_UnparsedEntityDeclHandler)( 3796b2c1e49SXin LI void *userData, const XML_Char *entityName, const XML_Char *base, 3806b2c1e49SXin LI const XML_Char *systemId, const XML_Char *publicId, 3815bb6a25fSPoul-Henning Kamp const XML_Char *notationName); 3825bb6a25fSPoul-Henning Kamp 3835bb6a25fSPoul-Henning Kamp /* This is called for a declaration of notation. The base argument is 3845bb6a25fSPoul-Henning Kamp whatever was set by XML_SetBase. The notationName will never be 3855bb6a25fSPoul-Henning Kamp NULL. The other arguments can be. 3865bb6a25fSPoul-Henning Kamp */ 3876b2c1e49SXin LI typedef void(XMLCALL *XML_NotationDeclHandler)(void *userData, 3885bb6a25fSPoul-Henning Kamp const XML_Char *notationName, 3895bb6a25fSPoul-Henning Kamp const XML_Char *base, 3905bb6a25fSPoul-Henning Kamp const XML_Char *systemId, 3915bb6a25fSPoul-Henning Kamp const XML_Char *publicId); 3925bb6a25fSPoul-Henning Kamp 3935bb6a25fSPoul-Henning Kamp /* When namespace processing is enabled, these are called once for 3945bb6a25fSPoul-Henning Kamp each namespace declaration. The call to the start and end element 3955bb6a25fSPoul-Henning Kamp handlers occur between the calls to the start and end namespace 3965bb6a25fSPoul-Henning Kamp declaration handlers. For an xmlns attribute, prefix will be 3975bb6a25fSPoul-Henning Kamp NULL. For an xmlns="" attribute, uri will be NULL. 3985bb6a25fSPoul-Henning Kamp */ 3996b2c1e49SXin LI typedef void(XMLCALL *XML_StartNamespaceDeclHandler)(void *userData, 4005bb6a25fSPoul-Henning Kamp const XML_Char *prefix, 4015bb6a25fSPoul-Henning Kamp const XML_Char *uri); 4025bb6a25fSPoul-Henning Kamp 4036b2c1e49SXin LI typedef void(XMLCALL *XML_EndNamespaceDeclHandler)(void *userData, 4045bb6a25fSPoul-Henning Kamp const XML_Char *prefix); 4055bb6a25fSPoul-Henning Kamp 4065bb6a25fSPoul-Henning Kamp /* This is called if the document is not standalone, that is, it has an 4075bb6a25fSPoul-Henning Kamp external subset or a reference to a parameter entity, but does not 408220ed979SColeman Kane have standalone="yes". If this handler returns XML_STATUS_ERROR, 409220ed979SColeman Kane then processing will not continue, and the parser will return a 4105bb6a25fSPoul-Henning Kamp XML_ERROR_NOT_STANDALONE error. 4115bb6a25fSPoul-Henning Kamp If parameter entity parsing is enabled, then in addition to the 4125bb6a25fSPoul-Henning Kamp conditions above this handler will only be called if the referenced 4135bb6a25fSPoul-Henning Kamp entity was actually read. 4145bb6a25fSPoul-Henning Kamp */ 415220ed979SColeman Kane typedef int(XMLCALL *XML_NotStandaloneHandler)(void *userData); 4165bb6a25fSPoul-Henning Kamp 4175bb6a25fSPoul-Henning Kamp /* This is called for a reference to an external parsed general 4185bb6a25fSPoul-Henning Kamp entity. The referenced entity is not automatically parsed. The 4195bb6a25fSPoul-Henning Kamp application can parse it immediately or later using 4205bb6a25fSPoul-Henning Kamp XML_ExternalEntityParserCreate. 4215bb6a25fSPoul-Henning Kamp 4225bb6a25fSPoul-Henning Kamp The parser argument is the parser parsing the entity containing the 4235bb6a25fSPoul-Henning Kamp reference; it can be passed as the parser argument to 4245bb6a25fSPoul-Henning Kamp XML_ExternalEntityParserCreate. The systemId argument is the 4255bb6a25fSPoul-Henning Kamp system identifier as specified in the entity declaration; it will 4265bb6a25fSPoul-Henning Kamp not be NULL. 4275bb6a25fSPoul-Henning Kamp 4285bb6a25fSPoul-Henning Kamp The base argument is the system identifier that should be used as 4295bb6a25fSPoul-Henning Kamp the base for resolving systemId if systemId was relative; this is 4305bb6a25fSPoul-Henning Kamp set by XML_SetBase; it may be NULL. 4315bb6a25fSPoul-Henning Kamp 4325bb6a25fSPoul-Henning Kamp The publicId argument is the public identifier as specified in the 4335bb6a25fSPoul-Henning Kamp entity declaration, or NULL if none was specified; the whitespace 4345bb6a25fSPoul-Henning Kamp in the public identifier will have been normalized as required by 4355bb6a25fSPoul-Henning Kamp the XML spec. 4365bb6a25fSPoul-Henning Kamp 4375bb6a25fSPoul-Henning Kamp The context argument specifies the parsing context in the format 4385bb6a25fSPoul-Henning Kamp expected by the context argument to XML_ExternalEntityParserCreate; 4395bb6a25fSPoul-Henning Kamp context is valid only until the handler returns, so if the 4405bb6a25fSPoul-Henning Kamp referenced entity is to be parsed later, it must be copied. 441220ed979SColeman Kane context is NULL only when the entity is a parameter entity. 4425bb6a25fSPoul-Henning Kamp 443220ed979SColeman Kane The handler should return XML_STATUS_ERROR if processing should not 444220ed979SColeman Kane continue because of a fatal error in the handling of the external 445220ed979SColeman Kane entity. In this case the calling parser will return an 4465bb6a25fSPoul-Henning Kamp XML_ERROR_EXTERNAL_ENTITY_HANDLING error. 4475bb6a25fSPoul-Henning Kamp 4485bb6a25fSPoul-Henning Kamp Note that unlike other handlers the first argument is the parser, 4495bb6a25fSPoul-Henning Kamp not userData. 4505bb6a25fSPoul-Henning Kamp */ 4516b2c1e49SXin LI typedef int(XMLCALL *XML_ExternalEntityRefHandler)(XML_Parser parser, 4525bb6a25fSPoul-Henning Kamp const XML_Char *context, 4535bb6a25fSPoul-Henning Kamp const XML_Char *base, 4545bb6a25fSPoul-Henning Kamp const XML_Char *systemId, 4555bb6a25fSPoul-Henning Kamp const XML_Char *publicId); 4565bb6a25fSPoul-Henning Kamp 4575bb6a25fSPoul-Henning Kamp /* This is called in two situations: 4585bb6a25fSPoul-Henning Kamp 1) An entity reference is encountered for which no declaration 4595bb6a25fSPoul-Henning Kamp has been read *and* this is not an error. 4605bb6a25fSPoul-Henning Kamp 2) An internal entity reference is read, but not expanded, because 4615bb6a25fSPoul-Henning Kamp XML_SetDefaultHandler has been called. 4625bb6a25fSPoul-Henning Kamp Note: skipped parameter entities in declarations and skipped general 4635bb6a25fSPoul-Henning Kamp entities in attribute values cannot be reported, because 4645bb6a25fSPoul-Henning Kamp the event would be out of sync with the reporting of the 4655bb6a25fSPoul-Henning Kamp declarations or attribute values 4665bb6a25fSPoul-Henning Kamp */ 4676b2c1e49SXin LI typedef void(XMLCALL *XML_SkippedEntityHandler)(void *userData, 4685bb6a25fSPoul-Henning Kamp const XML_Char *entityName, 4695bb6a25fSPoul-Henning Kamp int is_parameter_entity); 4705bb6a25fSPoul-Henning Kamp 4715bb6a25fSPoul-Henning Kamp /* This structure is filled in by the XML_UnknownEncodingHandler to 4725bb6a25fSPoul-Henning Kamp provide information to the parser about encodings that are unknown 4735bb6a25fSPoul-Henning Kamp to the parser. 4745bb6a25fSPoul-Henning Kamp 4755bb6a25fSPoul-Henning Kamp The map[b] member gives information about byte sequences whose 4765bb6a25fSPoul-Henning Kamp first byte is b. 4775bb6a25fSPoul-Henning Kamp 4785bb6a25fSPoul-Henning Kamp If map[b] is c where c is >= 0, then b by itself encodes the 4795bb6a25fSPoul-Henning Kamp Unicode scalar value c. 4805bb6a25fSPoul-Henning Kamp 4815bb6a25fSPoul-Henning Kamp If map[b] is -1, then the byte sequence is malformed. 4825bb6a25fSPoul-Henning Kamp 4835bb6a25fSPoul-Henning Kamp If map[b] is -n, where n >= 2, then b is the first byte of an 4845bb6a25fSPoul-Henning Kamp n-byte sequence that encodes a single Unicode scalar value. 4855bb6a25fSPoul-Henning Kamp 4865bb6a25fSPoul-Henning Kamp The data member will be passed as the first argument to the convert 4875bb6a25fSPoul-Henning Kamp function. 4885bb6a25fSPoul-Henning Kamp 4895bb6a25fSPoul-Henning Kamp The convert function is used to convert multibyte sequences; s will 4905bb6a25fSPoul-Henning Kamp point to a n-byte sequence where map[(unsigned char)*s] == -n. The 4915bb6a25fSPoul-Henning Kamp convert function must return the Unicode scalar value represented 4925bb6a25fSPoul-Henning Kamp by this byte sequence or -1 if the byte sequence is malformed. 4935bb6a25fSPoul-Henning Kamp 4945bb6a25fSPoul-Henning Kamp The convert function may be NULL if the encoding is a single-byte 4955bb6a25fSPoul-Henning Kamp encoding, that is if map[b] >= -1 for all bytes b. 4965bb6a25fSPoul-Henning Kamp 4975bb6a25fSPoul-Henning Kamp When the parser is finished with the encoding, then if release is 4985bb6a25fSPoul-Henning Kamp not NULL, it will call release passing it the data member; once 4995bb6a25fSPoul-Henning Kamp release has been called, the convert function will not be called 5005bb6a25fSPoul-Henning Kamp again. 5015bb6a25fSPoul-Henning Kamp 5025bb6a25fSPoul-Henning Kamp Expat places certain restrictions on the encodings that are supported 5035bb6a25fSPoul-Henning Kamp using this mechanism. 5045bb6a25fSPoul-Henning Kamp 5055bb6a25fSPoul-Henning Kamp 1. Every ASCII character that can appear in a well-formed XML document, 5065bb6a25fSPoul-Henning Kamp other than the characters 5075bb6a25fSPoul-Henning Kamp 5085bb6a25fSPoul-Henning Kamp $@\^`{}~ 5095bb6a25fSPoul-Henning Kamp 5105bb6a25fSPoul-Henning Kamp must be represented by a single byte, and that byte must be the 5115bb6a25fSPoul-Henning Kamp same byte that represents that character in ASCII. 5125bb6a25fSPoul-Henning Kamp 5135bb6a25fSPoul-Henning Kamp 2. No character may require more than 4 bytes to encode. 5145bb6a25fSPoul-Henning Kamp 5155bb6a25fSPoul-Henning Kamp 3. All characters encoded must have Unicode scalar values <= 5165bb6a25fSPoul-Henning Kamp 0xFFFF, (i.e., characters that would be encoded by surrogates in 5175bb6a25fSPoul-Henning Kamp UTF-16 are not allowed). Note that this restriction doesn't 5185bb6a25fSPoul-Henning Kamp apply to the built-in support for UTF-8 and UTF-16. 5195bb6a25fSPoul-Henning Kamp 5205bb6a25fSPoul-Henning Kamp 4. No Unicode character may be encoded by more than one distinct 5215bb6a25fSPoul-Henning Kamp sequence of bytes. 5225bb6a25fSPoul-Henning Kamp */ 5235bb6a25fSPoul-Henning Kamp typedef struct { 5245bb6a25fSPoul-Henning Kamp int map[256]; 5255bb6a25fSPoul-Henning Kamp void *data; 526220ed979SColeman Kane int(XMLCALL *convert)(void *data, const char *s); 527220ed979SColeman Kane void(XMLCALL *release)(void *data); 5285bb6a25fSPoul-Henning Kamp } XML_Encoding; 5295bb6a25fSPoul-Henning Kamp 5305bb6a25fSPoul-Henning Kamp /* This is called for an encoding that is unknown to the parser. 5315bb6a25fSPoul-Henning Kamp 5325bb6a25fSPoul-Henning Kamp The encodingHandlerData argument is that which was passed as the 5335bb6a25fSPoul-Henning Kamp second argument to XML_SetUnknownEncodingHandler. 5345bb6a25fSPoul-Henning Kamp 5355bb6a25fSPoul-Henning Kamp The name argument gives the name of the encoding as specified in 5365bb6a25fSPoul-Henning Kamp the encoding declaration. 5375bb6a25fSPoul-Henning Kamp 5385bb6a25fSPoul-Henning Kamp If the callback can provide information about the encoding, it must 539220ed979SColeman Kane fill in the XML_Encoding structure, and return XML_STATUS_OK. 540220ed979SColeman Kane Otherwise it must return XML_STATUS_ERROR. 5415bb6a25fSPoul-Henning Kamp 5425bb6a25fSPoul-Henning Kamp If info does not describe a suitable encoding, then the parser will 543cc68614dSXin LI return an XML_ERROR_UNKNOWN_ENCODING error. 5445bb6a25fSPoul-Henning Kamp */ 5456b2c1e49SXin LI typedef int(XMLCALL *XML_UnknownEncodingHandler)(void *encodingHandlerData, 5465bb6a25fSPoul-Henning Kamp const XML_Char *name, 5475bb6a25fSPoul-Henning Kamp XML_Encoding *info); 5485bb6a25fSPoul-Henning Kamp 5495bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5506b2c1e49SXin LI XML_SetElementHandler(XML_Parser parser, XML_StartElementHandler start, 5515bb6a25fSPoul-Henning Kamp XML_EndElementHandler end); 5525bb6a25fSPoul-Henning Kamp 5535bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5546b2c1e49SXin LI XML_SetStartElementHandler(XML_Parser parser, XML_StartElementHandler handler); 5555bb6a25fSPoul-Henning Kamp 5565bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5576b2c1e49SXin LI XML_SetEndElementHandler(XML_Parser parser, XML_EndElementHandler handler); 5585bb6a25fSPoul-Henning Kamp 5595bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5605bb6a25fSPoul-Henning Kamp XML_SetCharacterDataHandler(XML_Parser parser, 5615bb6a25fSPoul-Henning Kamp XML_CharacterDataHandler handler); 5625bb6a25fSPoul-Henning Kamp 5635bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5645bb6a25fSPoul-Henning Kamp XML_SetProcessingInstructionHandler(XML_Parser parser, 5655bb6a25fSPoul-Henning Kamp XML_ProcessingInstructionHandler handler); 5665bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5676b2c1e49SXin LI XML_SetCommentHandler(XML_Parser parser, XML_CommentHandler handler); 5685bb6a25fSPoul-Henning Kamp 5695bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5705bb6a25fSPoul-Henning Kamp XML_SetCdataSectionHandler(XML_Parser parser, 5715bb6a25fSPoul-Henning Kamp XML_StartCdataSectionHandler start, 5725bb6a25fSPoul-Henning Kamp XML_EndCdataSectionHandler end); 5735bb6a25fSPoul-Henning Kamp 5745bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5755bb6a25fSPoul-Henning Kamp XML_SetStartCdataSectionHandler(XML_Parser parser, 5765bb6a25fSPoul-Henning Kamp XML_StartCdataSectionHandler start); 5775bb6a25fSPoul-Henning Kamp 5785bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5795bb6a25fSPoul-Henning Kamp XML_SetEndCdataSectionHandler(XML_Parser parser, 5805bb6a25fSPoul-Henning Kamp XML_EndCdataSectionHandler end); 5815bb6a25fSPoul-Henning Kamp 5825bb6a25fSPoul-Henning Kamp /* This sets the default handler and also inhibits expansion of 5835bb6a25fSPoul-Henning Kamp internal entities. These entity references will be passed to the 5845bb6a25fSPoul-Henning Kamp default handler, or to the skipped entity handler, if one is set. 5855bb6a25fSPoul-Henning Kamp */ 5865bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5876b2c1e49SXin LI XML_SetDefaultHandler(XML_Parser parser, XML_DefaultHandler handler); 5885bb6a25fSPoul-Henning Kamp 5895bb6a25fSPoul-Henning Kamp /* This sets the default handler but does not inhibit expansion of 5905bb6a25fSPoul-Henning Kamp internal entities. The entity reference will not be passed to the 5915bb6a25fSPoul-Henning Kamp default handler. 5925bb6a25fSPoul-Henning Kamp */ 5935bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5946b2c1e49SXin LI XML_SetDefaultHandlerExpand(XML_Parser parser, XML_DefaultHandler handler); 5955bb6a25fSPoul-Henning Kamp 5965bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 5976b2c1e49SXin LI XML_SetDoctypeDeclHandler(XML_Parser parser, XML_StartDoctypeDeclHandler start, 5985bb6a25fSPoul-Henning Kamp XML_EndDoctypeDeclHandler end); 5995bb6a25fSPoul-Henning Kamp 6005bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6015bb6a25fSPoul-Henning Kamp XML_SetStartDoctypeDeclHandler(XML_Parser parser, 6025bb6a25fSPoul-Henning Kamp XML_StartDoctypeDeclHandler start); 6035bb6a25fSPoul-Henning Kamp 6045bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6056b2c1e49SXin LI XML_SetEndDoctypeDeclHandler(XML_Parser parser, XML_EndDoctypeDeclHandler end); 6065bb6a25fSPoul-Henning Kamp 6075bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6085bb6a25fSPoul-Henning Kamp XML_SetUnparsedEntityDeclHandler(XML_Parser parser, 6095bb6a25fSPoul-Henning Kamp XML_UnparsedEntityDeclHandler handler); 6105bb6a25fSPoul-Henning Kamp 6115bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6126b2c1e49SXin LI XML_SetNotationDeclHandler(XML_Parser parser, XML_NotationDeclHandler handler); 6135bb6a25fSPoul-Henning Kamp 6145bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6155bb6a25fSPoul-Henning Kamp XML_SetNamespaceDeclHandler(XML_Parser parser, 6165bb6a25fSPoul-Henning Kamp XML_StartNamespaceDeclHandler start, 6175bb6a25fSPoul-Henning Kamp XML_EndNamespaceDeclHandler end); 6185bb6a25fSPoul-Henning Kamp 6195bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6205bb6a25fSPoul-Henning Kamp XML_SetStartNamespaceDeclHandler(XML_Parser parser, 6215bb6a25fSPoul-Henning Kamp XML_StartNamespaceDeclHandler start); 6225bb6a25fSPoul-Henning Kamp 6235bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6245bb6a25fSPoul-Henning Kamp XML_SetEndNamespaceDeclHandler(XML_Parser parser, 6255bb6a25fSPoul-Henning Kamp XML_EndNamespaceDeclHandler end); 6265bb6a25fSPoul-Henning Kamp 6275bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6285bb6a25fSPoul-Henning Kamp XML_SetNotStandaloneHandler(XML_Parser parser, 6295bb6a25fSPoul-Henning Kamp XML_NotStandaloneHandler handler); 6305bb6a25fSPoul-Henning Kamp 6315bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6325bb6a25fSPoul-Henning Kamp XML_SetExternalEntityRefHandler(XML_Parser parser, 6335bb6a25fSPoul-Henning Kamp XML_ExternalEntityRefHandler handler); 6345bb6a25fSPoul-Henning Kamp 6355bb6a25fSPoul-Henning Kamp /* If a non-NULL value for arg is specified here, then it will be 6365bb6a25fSPoul-Henning Kamp passed as the first argument to the external entity ref handler 6375bb6a25fSPoul-Henning Kamp instead of the parser object. 6385bb6a25fSPoul-Henning Kamp */ 6395bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6406b2c1e49SXin LI XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg); 6415bb6a25fSPoul-Henning Kamp 6425bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6435bb6a25fSPoul-Henning Kamp XML_SetSkippedEntityHandler(XML_Parser parser, 6445bb6a25fSPoul-Henning Kamp XML_SkippedEntityHandler handler); 6455bb6a25fSPoul-Henning Kamp 6465bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6475bb6a25fSPoul-Henning Kamp XML_SetUnknownEncodingHandler(XML_Parser parser, 6485bb6a25fSPoul-Henning Kamp XML_UnknownEncodingHandler handler, 6495bb6a25fSPoul-Henning Kamp void *encodingHandlerData); 6505bb6a25fSPoul-Henning Kamp 6515bb6a25fSPoul-Henning Kamp /* This can be called within a handler for a start element, end 6525bb6a25fSPoul-Henning Kamp element, processing instruction or character data. It causes the 6535bb6a25fSPoul-Henning Kamp corresponding markup to be passed to the default handler. 6545bb6a25fSPoul-Henning Kamp */ 6555bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6565bb6a25fSPoul-Henning Kamp XML_DefaultCurrent(XML_Parser parser); 6575bb6a25fSPoul-Henning Kamp 6585bb6a25fSPoul-Henning Kamp /* If do_nst is non-zero, and namespace processing is in effect, and 6595bb6a25fSPoul-Henning Kamp a name has a prefix (i.e. an explicit namespace qualifier) then 6605bb6a25fSPoul-Henning Kamp that name is returned as a triplet in a single string separated by 6615bb6a25fSPoul-Henning Kamp the separator character specified when the parser was created: URI 6625bb6a25fSPoul-Henning Kamp + sep + local_name + sep + prefix. 6635bb6a25fSPoul-Henning Kamp 6645bb6a25fSPoul-Henning Kamp If do_nst is zero, then namespace information is returned in the 6655bb6a25fSPoul-Henning Kamp default manner (URI + sep + local_name) whether or not the name 6665bb6a25fSPoul-Henning Kamp has a prefix. 6675bb6a25fSPoul-Henning Kamp 6685bb6a25fSPoul-Henning Kamp Note: Calling XML_SetReturnNSTriplet after XML_Parse or 6695bb6a25fSPoul-Henning Kamp XML_ParseBuffer has no effect. 6705bb6a25fSPoul-Henning Kamp */ 6715bb6a25fSPoul-Henning Kamp 6725bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6735bb6a25fSPoul-Henning Kamp XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); 6745bb6a25fSPoul-Henning Kamp 6755bb6a25fSPoul-Henning Kamp /* This value is passed as the userData argument to callbacks. */ 6765bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6775bb6a25fSPoul-Henning Kamp XML_SetUserData(XML_Parser parser, void *userData); 6785bb6a25fSPoul-Henning Kamp 6795bb6a25fSPoul-Henning Kamp /* Returns the last value set by XML_SetUserData or NULL. */ 6805bb6a25fSPoul-Henning Kamp #define XML_GetUserData(parser) (*(void **)(parser)) 6815bb6a25fSPoul-Henning Kamp 6825bb6a25fSPoul-Henning Kamp /* This is equivalent to supplying an encoding argument to 6835bb6a25fSPoul-Henning Kamp XML_ParserCreate. On success XML_SetEncoding returns non-zero, 6845bb6a25fSPoul-Henning Kamp zero otherwise. 6855bb6a25fSPoul-Henning Kamp Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer 686220ed979SColeman Kane has no effect and returns XML_STATUS_ERROR. 6875bb6a25fSPoul-Henning Kamp */ 688220ed979SColeman Kane XMLPARSEAPI(enum XML_Status) 6895bb6a25fSPoul-Henning Kamp XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); 6905bb6a25fSPoul-Henning Kamp 6915bb6a25fSPoul-Henning Kamp /* If this function is called, then the parser will be passed as the 6925bb6a25fSPoul-Henning Kamp first argument to callbacks instead of userData. The userData will 6935bb6a25fSPoul-Henning Kamp still be accessible using XML_GetUserData. 6945bb6a25fSPoul-Henning Kamp */ 6955bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 6965bb6a25fSPoul-Henning Kamp XML_UseParserAsHandlerArg(XML_Parser parser); 6975bb6a25fSPoul-Henning Kamp 6985bb6a25fSPoul-Henning Kamp /* If useDTD == XML_TRUE is passed to this function, then the parser 6995bb6a25fSPoul-Henning Kamp will assume that there is an external subset, even if none is 7005bb6a25fSPoul-Henning Kamp specified in the document. In such a case the parser will call the 7015bb6a25fSPoul-Henning Kamp externalEntityRefHandler with a value of NULL for the systemId 7025bb6a25fSPoul-Henning Kamp argument (the publicId and context arguments will be NULL as well). 703220ed979SColeman Kane Note: For the purpose of checking WFC: Entity Declared, passing 704220ed979SColeman Kane useDTD == XML_TRUE will make the parser behave as if the document 705220ed979SColeman Kane had a DTD with an external subset. 7065bb6a25fSPoul-Henning Kamp Note: If this function is called, then this must be done before 7075bb6a25fSPoul-Henning Kamp the first call to XML_Parse or XML_ParseBuffer, since it will 7085bb6a25fSPoul-Henning Kamp have no effect after that. Returns 7095bb6a25fSPoul-Henning Kamp XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. 7105bb6a25fSPoul-Henning Kamp Note: If the document does not have a DOCTYPE declaration at all, 7115bb6a25fSPoul-Henning Kamp then startDoctypeDeclHandler and endDoctypeDeclHandler will not 7125bb6a25fSPoul-Henning Kamp be called, despite an external subset being parsed. 7135bb6a25fSPoul-Henning Kamp Note: If XML_DTD is not defined when Expat is compiled, returns 7145bb6a25fSPoul-Henning Kamp XML_ERROR_FEATURE_REQUIRES_XML_DTD. 7150a48773fSEric van Gyzen Note: If parser == NULL, returns XML_ERROR_INVALID_ARGUMENT. 7165bb6a25fSPoul-Henning Kamp */ 7175bb6a25fSPoul-Henning Kamp XMLPARSEAPI(enum XML_Error) 7185bb6a25fSPoul-Henning Kamp XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); 7195bb6a25fSPoul-Henning Kamp 7205bb6a25fSPoul-Henning Kamp /* Sets the base to be used for resolving relative URIs in system 7215bb6a25fSPoul-Henning Kamp identifiers in declarations. Resolving relative identifiers is 7225bb6a25fSPoul-Henning Kamp left to the application: this value will be passed through as the 7235bb6a25fSPoul-Henning Kamp base argument to the XML_ExternalEntityRefHandler, 7245bb6a25fSPoul-Henning Kamp XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base 725220ed979SColeman Kane argument will be copied. Returns XML_STATUS_ERROR if out of memory, 726220ed979SColeman Kane XML_STATUS_OK otherwise. 7275bb6a25fSPoul-Henning Kamp */ 728220ed979SColeman Kane XMLPARSEAPI(enum XML_Status) 7295bb6a25fSPoul-Henning Kamp XML_SetBase(XML_Parser parser, const XML_Char *base); 7305bb6a25fSPoul-Henning Kamp 7315bb6a25fSPoul-Henning Kamp XMLPARSEAPI(const XML_Char *) 7325bb6a25fSPoul-Henning Kamp XML_GetBase(XML_Parser parser); 7335bb6a25fSPoul-Henning Kamp 7345bb6a25fSPoul-Henning Kamp /* Returns the number of the attribute/value pairs passed in last call 7355bb6a25fSPoul-Henning Kamp to the XML_StartElementHandler that were specified in the start-tag 7365bb6a25fSPoul-Henning Kamp rather than defaulted. Each attribute/value pair counts as 2; thus 737cc68614dSXin LI this corresponds to an index into the atts array passed to the 7380a48773fSEric van Gyzen XML_StartElementHandler. Returns -1 if parser == NULL. 7395bb6a25fSPoul-Henning Kamp */ 7405bb6a25fSPoul-Henning Kamp XMLPARSEAPI(int) 7415bb6a25fSPoul-Henning Kamp XML_GetSpecifiedAttributeCount(XML_Parser parser); 7425bb6a25fSPoul-Henning Kamp 7435bb6a25fSPoul-Henning Kamp /* Returns the index of the ID attribute passed in the last call to 7440a48773fSEric van Gyzen XML_StartElementHandler, or -1 if there is no ID attribute or 7450a48773fSEric van Gyzen parser == NULL. Each attribute/value pair counts as 2; thus this 746cc68614dSXin LI corresponds to an index into the atts array passed to the 7470a48773fSEric van Gyzen XML_StartElementHandler. 7485bb6a25fSPoul-Henning Kamp */ 7495bb6a25fSPoul-Henning Kamp XMLPARSEAPI(int) 7505bb6a25fSPoul-Henning Kamp XML_GetIdAttributeIndex(XML_Parser parser); 7515bb6a25fSPoul-Henning Kamp 752e3466a89SXin LI #ifdef XML_ATTR_INFO 753e3466a89SXin LI /* Source file byte offsets for the start and end of attribute names and values. 754e3466a89SXin LI The value indices are exclusive of surrounding quotes; thus in a UTF-8 source 755e3466a89SXin LI file an attribute value of "blah" will yield: 756e3466a89SXin LI info->valueEnd - info->valueStart = 4 bytes. 757e3466a89SXin LI */ 758e3466a89SXin LI typedef struct { 759e3466a89SXin LI XML_Index nameStart; /* Offset to beginning of the attribute name. */ 760e3466a89SXin LI XML_Index nameEnd; /* Offset after the attribute name's last byte. */ 761e3466a89SXin LI XML_Index valueStart; /* Offset to beginning of the attribute value. */ 762e3466a89SXin LI XML_Index valueEnd; /* Offset after the attribute value's last byte. */ 763e3466a89SXin LI } XML_AttrInfo; 764e3466a89SXin LI 765e3466a89SXin LI /* Returns an array of XML_AttrInfo structures for the attribute/value pairs 766e3466a89SXin LI passed in last call to the XML_StartElementHandler that were specified 767e3466a89SXin LI in the start-tag rather than defaulted. Each attribute/value pair counts 768e3466a89SXin LI as 1; thus the number of entries in the array is 769e3466a89SXin LI XML_GetSpecifiedAttributeCount(parser) / 2. 770e3466a89SXin LI */ 771e3466a89SXin LI XMLPARSEAPI(const XML_AttrInfo *) 772e3466a89SXin LI XML_GetAttributeInfo(XML_Parser parser); 773e3466a89SXin LI #endif 774e3466a89SXin LI 7755bb6a25fSPoul-Henning Kamp /* Parses some input. Returns XML_STATUS_ERROR if a fatal error is 7765bb6a25fSPoul-Henning Kamp detected. The last call to XML_Parse must have isFinal true; len 7775bb6a25fSPoul-Henning Kamp may be zero for this call (or any other). 7785bb6a25fSPoul-Henning Kamp 779220ed979SColeman Kane Though the return values for these functions has always been 780220ed979SColeman Kane described as a Boolean value, the implementation, at least for the 781220ed979SColeman Kane 1.95.x series, has always returned exactly one of the XML_Status 782220ed979SColeman Kane values. 7835bb6a25fSPoul-Henning Kamp */ 7845bb6a25fSPoul-Henning Kamp XMLPARSEAPI(enum XML_Status) 7855bb6a25fSPoul-Henning Kamp XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); 7865bb6a25fSPoul-Henning Kamp 7875bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void *) 7885bb6a25fSPoul-Henning Kamp XML_GetBuffer(XML_Parser parser, int len); 7895bb6a25fSPoul-Henning Kamp 7905bb6a25fSPoul-Henning Kamp XMLPARSEAPI(enum XML_Status) 7915bb6a25fSPoul-Henning Kamp XML_ParseBuffer(XML_Parser parser, int len, int isFinal); 7925bb6a25fSPoul-Henning Kamp 793220ed979SColeman Kane /* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. 794220ed979SColeman Kane Must be called from within a call-back handler, except when aborting 795220ed979SColeman Kane (resumable = 0) an already suspended parser. Some call-backs may 796220ed979SColeman Kane still follow because they would otherwise get lost. Examples: 797220ed979SColeman Kane - endElementHandler() for empty elements when stopped in 798220ed979SColeman Kane startElementHandler(), 799220ed979SColeman Kane - endNameSpaceDeclHandler() when stopped in endElementHandler(), 800220ed979SColeman Kane and possibly others. 801220ed979SColeman Kane 802220ed979SColeman Kane Can be called from most handlers, including DTD related call-backs, 803220ed979SColeman Kane except when parsing an external parameter entity and resumable != 0. 804220ed979SColeman Kane Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. 805220ed979SColeman Kane Possible error codes: 806220ed979SColeman Kane - XML_ERROR_SUSPENDED: when suspending an already suspended parser. 807220ed979SColeman Kane - XML_ERROR_FINISHED: when the parser has already finished. 808220ed979SColeman Kane - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. 809220ed979SColeman Kane 810220ed979SColeman Kane When resumable != 0 (true) then parsing is suspended, that is, 811220ed979SColeman Kane XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. 812220ed979SColeman Kane Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() 813220ed979SColeman Kane return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. 814220ed979SColeman Kane 815220ed979SColeman Kane *Note*: 816220ed979SColeman Kane This will be applied to the current parser instance only, that is, if 817220ed979SColeman Kane there is a parent parser then it will continue parsing when the 818220ed979SColeman Kane externalEntityRefHandler() returns. It is up to the implementation of 819220ed979SColeman Kane the externalEntityRefHandler() to call XML_StopParser() on the parent 820220ed979SColeman Kane parser (recursively), if one wants to stop parsing altogether. 821220ed979SColeman Kane 822220ed979SColeman Kane When suspended, parsing can be resumed by calling XML_ResumeParser(). 823220ed979SColeman Kane */ 824220ed979SColeman Kane XMLPARSEAPI(enum XML_Status) 825220ed979SColeman Kane XML_StopParser(XML_Parser parser, XML_Bool resumable); 826220ed979SColeman Kane 827220ed979SColeman Kane /* Resumes parsing after it has been suspended with XML_StopParser(). 828220ed979SColeman Kane Must not be called from within a handler call-back. Returns same 829220ed979SColeman Kane status codes as XML_Parse() or XML_ParseBuffer(). 830220ed979SColeman Kane Additional error code XML_ERROR_NOT_SUSPENDED possible. 831220ed979SColeman Kane 832220ed979SColeman Kane *Note*: 833220ed979SColeman Kane This must be called on the most deeply nested child parser instance 834220ed979SColeman Kane first, and on its parent parser only after the child parser has finished, 835220ed979SColeman Kane to be applied recursively until the document entity's parser is restarted. 836220ed979SColeman Kane That is, the parent parser will not resume by itself and it is up to the 837220ed979SColeman Kane application to call XML_ResumeParser() on it at the appropriate moment. 838220ed979SColeman Kane */ 839220ed979SColeman Kane XMLPARSEAPI(enum XML_Status) 840220ed979SColeman Kane XML_ResumeParser(XML_Parser parser); 841220ed979SColeman Kane 8426b2c1e49SXin LI enum XML_Parsing { XML_INITIALIZED, XML_PARSING, XML_FINISHED, XML_SUSPENDED }; 843220ed979SColeman Kane 844220ed979SColeman Kane typedef struct { 845220ed979SColeman Kane enum XML_Parsing parsing; 846220ed979SColeman Kane XML_Bool finalBuffer; 847220ed979SColeman Kane } XML_ParsingStatus; 848220ed979SColeman Kane 849220ed979SColeman Kane /* Returns status of parser with respect to being initialized, parsing, 850220ed979SColeman Kane finished, or suspended and processing the final buffer. 851220ed979SColeman Kane XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, 852220ed979SColeman Kane XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED 853220ed979SColeman Kane */ 854220ed979SColeman Kane XMLPARSEAPI(void) 855220ed979SColeman Kane XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); 856220ed979SColeman Kane 8575bb6a25fSPoul-Henning Kamp /* Creates an XML_Parser object that can parse an external general 8585bb6a25fSPoul-Henning Kamp entity; context is a '\0'-terminated string specifying the parse 8595bb6a25fSPoul-Henning Kamp context; encoding is a '\0'-terminated string giving the name of 8605bb6a25fSPoul-Henning Kamp the externally specified encoding, or NULL if there is no 8615bb6a25fSPoul-Henning Kamp externally specified encoding. The context string consists of a 8625bb6a25fSPoul-Henning Kamp sequence of tokens separated by formfeeds (\f); a token consisting 8635bb6a25fSPoul-Henning Kamp of a name specifies that the general entity of the name is open; a 8645bb6a25fSPoul-Henning Kamp token of the form prefix=uri specifies the namespace for a 8655bb6a25fSPoul-Henning Kamp particular prefix; a token of the form =uri specifies the default 8665bb6a25fSPoul-Henning Kamp namespace. This can be called at any point after the first call to 8675bb6a25fSPoul-Henning Kamp an ExternalEntityRefHandler so longer as the parser has not yet 8685bb6a25fSPoul-Henning Kamp been freed. The new parser is completely independent and may 8695bb6a25fSPoul-Henning Kamp safely be used in a separate thread. The handlers and userData are 870220ed979SColeman Kane initialized from the parser argument. Returns NULL if out of memory. 8715bb6a25fSPoul-Henning Kamp Otherwise returns a new XML_Parser object. 8725bb6a25fSPoul-Henning Kamp */ 8735bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Parser) 8746b2c1e49SXin LI XML_ExternalEntityParserCreate(XML_Parser parser, const XML_Char *context, 8755bb6a25fSPoul-Henning Kamp const XML_Char *encoding); 8765bb6a25fSPoul-Henning Kamp 8775bb6a25fSPoul-Henning Kamp enum XML_ParamEntityParsing { 8785bb6a25fSPoul-Henning Kamp XML_PARAM_ENTITY_PARSING_NEVER, 8795bb6a25fSPoul-Henning Kamp XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, 8805bb6a25fSPoul-Henning Kamp XML_PARAM_ENTITY_PARSING_ALWAYS 8815bb6a25fSPoul-Henning Kamp }; 8825bb6a25fSPoul-Henning Kamp 8835bb6a25fSPoul-Henning Kamp /* Controls parsing of parameter entities (including the external DTD 8845bb6a25fSPoul-Henning Kamp subset). If parsing of parameter entities is enabled, then 8855bb6a25fSPoul-Henning Kamp references to external parameter entities (including the external 8865bb6a25fSPoul-Henning Kamp DTD subset) will be passed to the handler set with 8875bb6a25fSPoul-Henning Kamp XML_SetExternalEntityRefHandler. The context passed will be 0. 8885bb6a25fSPoul-Henning Kamp 8895bb6a25fSPoul-Henning Kamp Unlike external general entities, external parameter entities can 8905bb6a25fSPoul-Henning Kamp only be parsed synchronously. If the external parameter entity is 8915bb6a25fSPoul-Henning Kamp to be parsed, it must be parsed during the call to the external 8925bb6a25fSPoul-Henning Kamp entity ref handler: the complete sequence of 8935bb6a25fSPoul-Henning Kamp XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and 8945bb6a25fSPoul-Henning Kamp XML_ParserFree calls must be made during this call. After 8955bb6a25fSPoul-Henning Kamp XML_ExternalEntityParserCreate has been called to create the parser 8965bb6a25fSPoul-Henning Kamp for the external parameter entity (context must be 0 for this 8975bb6a25fSPoul-Henning Kamp call), it is illegal to make any calls on the old parser until 8985bb6a25fSPoul-Henning Kamp XML_ParserFree has been called on the newly created parser. 8995bb6a25fSPoul-Henning Kamp If the library has been compiled without support for parameter 9005bb6a25fSPoul-Henning Kamp entity parsing (ie without XML_DTD being defined), then 9015bb6a25fSPoul-Henning Kamp XML_SetParamEntityParsing will return 0 if parsing of parameter 9025bb6a25fSPoul-Henning Kamp entities is requested; otherwise it will return non-zero. 9035bb6a25fSPoul-Henning Kamp Note: If XML_SetParamEntityParsing is called after XML_Parse or 9045bb6a25fSPoul-Henning Kamp XML_ParseBuffer, then it has no effect and will always return 0. 9050a48773fSEric van Gyzen Note: If parser == NULL, the function will do nothing and return 0. 9065bb6a25fSPoul-Henning Kamp */ 9075bb6a25fSPoul-Henning Kamp XMLPARSEAPI(int) 9085bb6a25fSPoul-Henning Kamp XML_SetParamEntityParsing(XML_Parser parser, 9095bb6a25fSPoul-Henning Kamp enum XML_ParamEntityParsing parsing); 9105bb6a25fSPoul-Henning Kamp 911e3466a89SXin LI /* Sets the hash salt to use for internal hash calculations. 912e3466a89SXin LI Helps in preventing DoS attacks based on predicting hash 913e3466a89SXin LI function behavior. This must be called before parsing is started. 914e3466a89SXin LI Returns 1 if successful, 0 when called after parsing has started. 9150a48773fSEric van Gyzen Note: If parser == NULL, the function will do nothing and return 0. 916e3466a89SXin LI */ 917e3466a89SXin LI XMLPARSEAPI(int) 9186b2c1e49SXin LI XML_SetHashSalt(XML_Parser parser, unsigned long hash_salt); 919e3466a89SXin LI 920220ed979SColeman Kane /* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then 9215bb6a25fSPoul-Henning Kamp XML_GetErrorCode returns information about the error. 9225bb6a25fSPoul-Henning Kamp */ 9235bb6a25fSPoul-Henning Kamp XMLPARSEAPI(enum XML_Error) 9245bb6a25fSPoul-Henning Kamp XML_GetErrorCode(XML_Parser parser); 9255bb6a25fSPoul-Henning Kamp 9265bb6a25fSPoul-Henning Kamp /* These functions return information about the current parse 927220ed979SColeman Kane location. They may be called from any callback called to report 928220ed979SColeman Kane some parse event; in this case the location is the location of the 929220ed979SColeman Kane first of the sequence of characters that generated the event. When 930220ed979SColeman Kane called from callbacks generated by declarations in the document 931220ed979SColeman Kane prologue, the location identified isn't as neatly defined, but will 932220ed979SColeman Kane be within the relevant markup. When called outside of the callback 933220ed979SColeman Kane functions, the position indicated will be just past the last parse 934220ed979SColeman Kane event (regardless of whether there was an associated callback). 9355bb6a25fSPoul-Henning Kamp 936220ed979SColeman Kane They may also be called after returning from a call to XML_Parse 937220ed979SColeman Kane or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then 938220ed979SColeman Kane the location is the location of the character at which the error 939220ed979SColeman Kane was detected; otherwise the location is the location of the last 940220ed979SColeman Kane parse event, as described above. 9410a48773fSEric van Gyzen 9420a48773fSEric van Gyzen Note: XML_GetCurrentLineNumber and XML_GetCurrentColumnNumber 9430a48773fSEric van Gyzen return 0 to indicate an error. 9440a48773fSEric van Gyzen Note: XML_GetCurrentByteIndex returns -1 to indicate an error. 9455bb6a25fSPoul-Henning Kamp */ 946220ed979SColeman Kane XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); 947220ed979SColeman Kane XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); 948220ed979SColeman Kane XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); 9495bb6a25fSPoul-Henning Kamp 9505bb6a25fSPoul-Henning Kamp /* Return the number of bytes in the current event. 9515bb6a25fSPoul-Henning Kamp Returns 0 if the event is in an internal entity. 9525bb6a25fSPoul-Henning Kamp */ 9535bb6a25fSPoul-Henning Kamp XMLPARSEAPI(int) 9545bb6a25fSPoul-Henning Kamp XML_GetCurrentByteCount(XML_Parser parser); 9555bb6a25fSPoul-Henning Kamp 956*4543ef51SXin LI /* If XML_CONTEXT_BYTES is >=1, returns the input buffer, sets 9575bb6a25fSPoul-Henning Kamp the integer pointed to by offset to the offset within this buffer 9585bb6a25fSPoul-Henning Kamp of the current parse position, and sets the integer pointed to by size 9595bb6a25fSPoul-Henning Kamp to the size of this buffer (the number of input bytes). Otherwise 9605bb6a25fSPoul-Henning Kamp returns a NULL pointer. Also returns a NULL pointer if a parse isn't 9615bb6a25fSPoul-Henning Kamp active. 9625bb6a25fSPoul-Henning Kamp 9635bb6a25fSPoul-Henning Kamp NOTE: The character pointer returned should not be used outside 9645bb6a25fSPoul-Henning Kamp the handler that makes the call. 9655bb6a25fSPoul-Henning Kamp */ 9665bb6a25fSPoul-Henning Kamp XMLPARSEAPI(const char *) 9676b2c1e49SXin LI XML_GetInputContext(XML_Parser parser, int *offset, int *size); 9685bb6a25fSPoul-Henning Kamp 9695bb6a25fSPoul-Henning Kamp /* For backwards compatibility with previous versions. */ 9705bb6a25fSPoul-Henning Kamp #define XML_GetErrorLineNumber XML_GetCurrentLineNumber 9715bb6a25fSPoul-Henning Kamp #define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber 9725bb6a25fSPoul-Henning Kamp #define XML_GetErrorByteIndex XML_GetCurrentByteIndex 9735bb6a25fSPoul-Henning Kamp 974220ed979SColeman Kane /* Frees the content model passed to the element declaration handler */ 975220ed979SColeman Kane XMLPARSEAPI(void) 976220ed979SColeman Kane XML_FreeContentModel(XML_Parser parser, XML_Content *model); 977220ed979SColeman Kane 978220ed979SColeman Kane /* Exposing the memory handling functions used in Expat */ 979220ed979SColeman Kane XMLPARSEAPI(void *) 980be8aff81SXin LI XML_ATTR_MALLOC 981be8aff81SXin LI XML_ATTR_ALLOC_SIZE(2) 982220ed979SColeman Kane XML_MemMalloc(XML_Parser parser, size_t size); 983220ed979SColeman Kane 984220ed979SColeman Kane XMLPARSEAPI(void *) 985be8aff81SXin LI XML_ATTR_ALLOC_SIZE(3) 986220ed979SColeman Kane XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); 987220ed979SColeman Kane 988220ed979SColeman Kane XMLPARSEAPI(void) 989220ed979SColeman Kane XML_MemFree(XML_Parser parser, void *ptr); 990220ed979SColeman Kane 9915bb6a25fSPoul-Henning Kamp /* Frees memory used by the parser. */ 9925bb6a25fSPoul-Henning Kamp XMLPARSEAPI(void) 9935bb6a25fSPoul-Henning Kamp XML_ParserFree(XML_Parser parser); 9945bb6a25fSPoul-Henning Kamp 9955bb6a25fSPoul-Henning Kamp /* Returns a string describing the error. */ 9965bb6a25fSPoul-Henning Kamp XMLPARSEAPI(const XML_LChar *) 9975bb6a25fSPoul-Henning Kamp XML_ErrorString(enum XML_Error code); 9985bb6a25fSPoul-Henning Kamp 9995bb6a25fSPoul-Henning Kamp /* Return a string containing the version number of this expat */ 10005bb6a25fSPoul-Henning Kamp XMLPARSEAPI(const XML_LChar *) 10015bb6a25fSPoul-Henning Kamp XML_ExpatVersion(void); 10025bb6a25fSPoul-Henning Kamp 10035bb6a25fSPoul-Henning Kamp typedef struct { 10045bb6a25fSPoul-Henning Kamp int major; 10055bb6a25fSPoul-Henning Kamp int minor; 10065bb6a25fSPoul-Henning Kamp int micro; 10075bb6a25fSPoul-Henning Kamp } XML_Expat_Version; 10085bb6a25fSPoul-Henning Kamp 10095bb6a25fSPoul-Henning Kamp /* Return an XML_Expat_Version structure containing numeric version 10105bb6a25fSPoul-Henning Kamp number information for this version of expat. 10115bb6a25fSPoul-Henning Kamp */ 10125bb6a25fSPoul-Henning Kamp XMLPARSEAPI(XML_Expat_Version) 10135bb6a25fSPoul-Henning Kamp XML_ExpatVersionInfo(void); 10145bb6a25fSPoul-Henning Kamp 10155bb6a25fSPoul-Henning Kamp /* Added in Expat 1.95.5. */ 10165bb6a25fSPoul-Henning Kamp enum XML_FeatureEnum { 10175bb6a25fSPoul-Henning Kamp XML_FEATURE_END = 0, 10185bb6a25fSPoul-Henning Kamp XML_FEATURE_UNICODE, 10195bb6a25fSPoul-Henning Kamp XML_FEATURE_UNICODE_WCHAR_T, 10205bb6a25fSPoul-Henning Kamp XML_FEATURE_DTD, 10215bb6a25fSPoul-Henning Kamp XML_FEATURE_CONTEXT_BYTES, 10225bb6a25fSPoul-Henning Kamp XML_FEATURE_MIN_SIZE, 10235bb6a25fSPoul-Henning Kamp XML_FEATURE_SIZEOF_XML_CHAR, 1024220ed979SColeman Kane XML_FEATURE_SIZEOF_XML_LCHAR, 1025220ed979SColeman Kane XML_FEATURE_NS, 1026e3466a89SXin LI XML_FEATURE_LARGE_SIZE, 1027cc68614dSXin LI XML_FEATURE_ATTR_INFO, 1028cc68614dSXin LI /* Added in Expat 2.4.0. */ 1029cc68614dSXin LI XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT, 1030*4543ef51SXin LI XML_FEATURE_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT, 1031*4543ef51SXin LI /* Added in Expat 2.6.0. */ 1032*4543ef51SXin LI XML_FEATURE_GE 10335bb6a25fSPoul-Henning Kamp /* Additional features must be added to the end of this enum. */ 10345bb6a25fSPoul-Henning Kamp }; 10355bb6a25fSPoul-Henning Kamp 10365bb6a25fSPoul-Henning Kamp typedef struct { 10375bb6a25fSPoul-Henning Kamp enum XML_FeatureEnum feature; 1038220ed979SColeman Kane const XML_LChar *name; 10395bb6a25fSPoul-Henning Kamp long int value; 10405bb6a25fSPoul-Henning Kamp } XML_Feature; 10415bb6a25fSPoul-Henning Kamp 10425bb6a25fSPoul-Henning Kamp XMLPARSEAPI(const XML_Feature *) 10435bb6a25fSPoul-Henning Kamp XML_GetFeatureList(void); 10445bb6a25fSPoul-Henning Kamp 1045*4543ef51SXin LI #if XML_GE == 1 1046*4543ef51SXin LI /* Added in Expat 2.4.0 for XML_DTD defined and 1047*4543ef51SXin LI * added in Expat 2.6.0 for XML_GE == 1. */ 1048cc68614dSXin LI XMLPARSEAPI(XML_Bool) 1049cc68614dSXin LI XML_SetBillionLaughsAttackProtectionMaximumAmplification( 1050cc68614dSXin LI XML_Parser parser, float maximumAmplificationFactor); 1051cc68614dSXin LI 1052*4543ef51SXin LI /* Added in Expat 2.4.0 for XML_DTD defined and 1053*4543ef51SXin LI * added in Expat 2.6.0 for XML_GE == 1. */ 1054cc68614dSXin LI XMLPARSEAPI(XML_Bool) 1055cc68614dSXin LI XML_SetBillionLaughsAttackProtectionActivationThreshold( 1056cc68614dSXin LI XML_Parser parser, unsigned long long activationThresholdBytes); 1057cc68614dSXin LI #endif 1058cc68614dSXin LI 1059*4543ef51SXin LI /* Added in Expat 2.6.0. */ 1060*4543ef51SXin LI XMLPARSEAPI(XML_Bool) 1061*4543ef51SXin LI XML_SetReparseDeferralEnabled(XML_Parser parser, XML_Bool enabled); 1062*4543ef51SXin LI 1063be8aff81SXin LI /* Expat follows the semantic versioning convention. 1064*4543ef51SXin LI See https://semver.org 10655bb6a25fSPoul-Henning Kamp */ 1066220ed979SColeman Kane #define XML_MAJOR_VERSION 2 1067*4543ef51SXin LI #define XML_MINOR_VERSION 6 1068dc58b3fcSXin LI #define XML_MICRO_VERSION 0 10695bb6a25fSPoul-Henning Kamp 10705bb6a25fSPoul-Henning Kamp #ifdef __cplusplus 10715bb6a25fSPoul-Henning Kamp } 10725bb6a25fSPoul-Henning Kamp #endif 10735bb6a25fSPoul-Henning Kamp 1074220ed979SColeman Kane #endif /* not Expat_INCLUDED */ 1075