/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd

   See the file COPYING for copying permission.

   Portion Copyright © 2009 Nokia Corporation and/or its subsidiary(-ies). All rights reserved. 

*/

#ifndef XmlParse_INCLUDED

#define XmlParse_INCLUDED 1

#ifdef __VMS

/*      0        1         2         3      0        1         2         3

        1234567890123456789012345678901     1234567890123456789012345678901 */

#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler   

#define XML_SetUnparsedEntityDeclHandler    XML_SetUnparsedEntDeclHandler   

#define XML_SetStartNamespaceDeclHandler    XML_SetStartNamespcDeclHandler  

#define XML_SetExternalEntityRefHandlerArg  XML_SetExternalEntRefHandlerArg 

#endif

#include <stdlib.h>

#ifndef XMLPARSEAPI

#define XMLPARSEAPI(type) type

#endif  /* not defined XMLPARSEAPI */

#ifdef __cplusplus

extern "C" {

#endif

#ifdef XML_UNICODE_WCHAR_T 

#define XML_UNICODE

#endif

struct XML_ParserStruct;

typedef struct XML_ParserStruct *XML_Parser;

#ifdef XML_UNICODE     /* Information is UTF-16 encoded. */

#ifdef XML_UNICODE_WCHAR_T

typedef wchar_t XML_Char;

typedef wchar_t XML_LChar;

#else

typedef unsigned short XML_Char;

typedef char XML_LChar;

#endif /* XML_UNICODE_WCHAR_T */

#else                  /* Information is UTF-8 encoded. */

typedef char XML_Char;

typedef char XML_LChar;

#endif /* XML_UNICODE */

/* Should this be defined using stdbool.h when C99 is available? */

typedef unsigned char XML_Bool;

#define XML_TRUE   ((XML_Bool) 1)

#define XML_FALSE  ((XML_Bool) 0)

enum XML_Error {

  XML_ERROR_NONE,

  XML_ERROR_NO_MEMORY,

  XML_ERROR_SYNTAX,

  XML_ERROR_NO_ELEMENTS,

  XML_ERROR_INVALID_TOKEN,

  XML_ERROR_UNCLOSED_TOKEN,

  XML_ERROR_PARTIAL_CHAR,

  XML_ERROR_TAG_MISMATCH,

  XML_ERROR_DUPLICATE_ATTRIBUTE,

  XML_ERROR_JUNK_AFTER_DOC_ELEMENT,

  XML_ERROR_PARAM_ENTITY_REF,

  XML_ERROR_UNDEFINED_ENTITY,

  XML_ERROR_RECURSIVE_ENTITY_REF,

  XML_ERROR_ASYNC_ENTITY,

  XML_ERROR_BAD_CHAR_REF,

  XML_ERROR_BINARY_ENTITY_REF,

  XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,

  XML_ERROR_MISPLACED_XML_PI,

  XML_ERROR_UNKNOWN_ENCODING,

  XML_ERROR_INCORRECT_ENCODING,

  XML_ERROR_UNCLOSED_CDATA_SECTION,

  XML_ERROR_EXTERNAL_ENTITY_HANDLING,

  XML_ERROR_NOT_STANDALONE,

  XML_ERROR_UNEXPECTED_STATE,

  XML_ERROR_ENTITY_DECLARED_IN_PE,

  XML_ERROR_FEATURE_REQUIRES_XML_DTD,

  XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING

};

enum XML_Content_Type {

  XML_CTYPE_EMPTY = 1,

  XML_CTYPE_ANY,

  XML_CTYPE_MIXED,

  XML_CTYPE_NAME,

  XML_CTYPE_CHOICE,

  XML_CTYPE_SEQ

};

enum XML_Content_Quant {

  XML_CQUANT_NONE,

  XML_CQUANT_OPT,

  XML_CQUANT_REP,

  XML_CQUANT_PLUS

};

/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be

   XML_CQUANT_NONE, and the other fields will be zero or NULL.

   If type == XML_CTYPE_MIXED, then quant will be NONE or REP and

   numchildren will contain number of elements that may be mixed in

   and children point to an array of XML_Content cells that will be

   all of XML_CTYPE_NAME type with no quantification.

   If type == XML_CTYPE_NAME, then the name points to the name, and

   the numchildren field will be zero and children will be NULL. The

   quant fields indicates any quantifiers placed on the name.

   CHOICE and SEQ will have name NULL, the number of children in

   numchildren and children will point, recursively, to an array

   of XML_Content cells.

   The EMPTY, ANY, and MIXED types will only occur at top level.

*/

typedef struct XML_cp XML_Content;

struct XML_cp {

  enum XML_Content_Type         type;

  enum XML_Content_Quant        quant;

  XML_Char *                    name;

  unsigned int                  numchildren;

  XML_Content *                 children;

};

/* This is called for an element declaration. See above for

   description of the model argument. It's the caller's responsibility

   to free model when finished with it.

*/

typedef void (*XML_ElementDeclHandler) (void *userData,

                                        const XML_Char *name,

                                        XML_Content *model);

XMLPARSEAPI(void)

XML_SetElementDeclHandler(XML_Parser parser,

                          XML_ElementDeclHandler eldecl);

/* The Attlist declaration handler is called for *each* attribute. So

   a single Attlist declaration with multiple attributes declared will

   generate multiple calls to this handler. The "default" parameter

   may be NULL in the case of the "#IMPLIED" or "#REQUIRED"

   keyword. The "isrequired" parameter will be true and the default

   value will be NULL in the case of "#REQUIRED". If "isrequired" is

   true and default is non-NULL, then this is a "#FIXED" default.

*/

typedef void (*XML_AttlistDeclHandler) (void           *userData,

                                        const XML_Char *elname,

                                        const XML_Char *attname,

                                        const XML_Char *att_type,

                                        const XML_Char *dflt,

                                        int             isrequired);

XMLPARSEAPI(void)

XML_SetAttlistDeclHandler(XML_Parser parser,

                          XML_AttlistDeclHandler attdecl);

/* The XML declaration handler is called for *both* XML declarations

   and text declarations. The way to distinguish is that the version

   parameter will be NULL for text declarations. The encoding

   parameter may be NULL for XML declarations. The standalone

   parameter will be -1, 0, or 1 indicating respectively that there

   was no standalone parameter in the declaration, that it was given

   as no, or that it was given as yes.

*/

typedef void (*XML_XmlDeclHandler) (void                *userData,

                                    const XML_Char      *version,

                                    const XML_Char      *encoding,

                                    int                  standalone);

XMLPARSEAPI(void)

XML_SetXmlDeclHandler(XML_Parser parser,

                      XML_XmlDeclHandler xmldecl);

typedef struct {

  void *(*malloc_fcn)(void *userData, size_t size);

  void *(*realloc_fcn)(void *userData, void *ptr, size_t size);

  void (*free_fcn)(void *userData, void *ptr);

  void *allocData;

} XML_Memory_Handling_Suite;

/* Constructs a new parser; encoding is the encoding specified by the

   external protocol or NULL if there is none specified.

*/

XMLPARSEAPI(XML_Parser)

XML_ParserCreate(const XML_Char *encoding);

/* Constructs a new parser and namespace processor.  Element type

   names and attribute names that belong to a namespace will be

   expanded; unprefixed attribute names are never expanded; unprefixed

   element type names are expanded only if there is a default

   namespace. The expanded name is the concatenation of the namespace

   URI, the namespace separator character, and the local part of the

   name.  If the namespace separator is '\0' then the namespace URI

   and the local part will be concatenated without any separator.

   When a namespace is not declared, the name and prefix will be

   passed through without expansion.

*/

XMLPARSEAPI(XML_Parser)

XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator);

/* Constructs a new parser using the memory management suit referred to

   by memsuite. If memsuite is NULL, then use the standard library memory

   suite. If namespaceSeparator is non-NULL it creates a parser with

   namespace processing as described above. The character pointed at

   will serve as the namespace separator.

   All further memory operations used for the created parser will come from

   the given suite.

*/

XMLPARSEAPI(XML_Parser)

XML_ParserCreate_MM(const XML_Char *encoding,

                    const XML_Memory_Handling_Suite *memsuite,

                    const XML_Char *namespaceSeparator);

/* Prepare a parser object to be re-used.  This is particularly

   valuable when memory allocation overhead is disproportionatly high,

   such as when a large number of small documnents need to be parsed.

   All handlers are cleared from the parser, except for the 

   unknownEncodingHandler. The parser's external state is re-initialized

   except for the values of ns and ns_triplets.

   Added in Expat 1.95.3.

*/

XMLPARSEAPI(XML_Bool)

XML_ParserReset(XML_Parser parser, const XML_Char *encoding);

/* atts is array of name/value pairs, terminated by 0;

   names and values are 0 terminated.

*/

typedef void (*XML_StartElementHandler)(void *userData,

                                        const XML_Char *name,

                                        const XML_Char **atts);

typedef void (*XML_EndElementHandler)(void *userData,

                                      const XML_Char *name);

/* s is not 0 terminated. */

typedef void (*XML_CharacterDataHandler)(void *userData,

                                         const XML_Char *s,

                                         int len);

/* target and data are 0 terminated */

typedef void (*XML_ProcessingInstructionHandler)(void *userData,

                                                 const XML_Char *target,

                                                 const XML_Char *data);

/* data is 0 terminated */

typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data);

typedef void (*XML_StartCdataSectionHandler)(void *userData);

typedef void (*XML_EndCdataSectionHandler)(void *userData);

/* This is called for any characters in the XML document for which

   there is no applicable handler.  This includes both characters that

   are part of markup which is of a kind that is not reported

   (comments, markup declarations), or characters that are part of a

   construct which could be reported but for which no handler has been

   supplied. The characters are passed exactly as they were in the XML

   document except that they will be encoded in UTF-8 or UTF-16. 

   Line boundaries are not normalized. Note that a byte order mark

   character is not passed to the default handler. There are no

   guarantees about how characters are divided between calls to the

   default handler: for example, a comment might be split between

   multiple calls.

*/

typedef void (*XML_DefaultHandler)(void *userData,

                                   const XML_Char *s,

                                   int len);

/* This is called for the start of the DOCTYPE declaration, before

   any DTD or internal subset is parsed.

*/

typedef void (*XML_StartDoctypeDeclHandler)(void *userData,

                                            const XML_Char *doctypeName,

                                            const XML_Char *sysid,

                                            const XML_Char *pubid,

                                            int has_internal_subset);

/* This is called for the start of the DOCTYPE declaration when the

   closing > is encountered, but after processing any external

   subset.

*/

typedef void (*XML_EndDoctypeDeclHandler)(void *userData);

/* This is called for entity declarations. The is_parameter_entity

   argument will be non-zero if the entity is a parameter entity, zero

   otherwise.

   For internal entities (<!ENTITY foo "bar">), value will

   be non-NULL and systemId, publicID, and notationName will be NULL.

   The value string is NOT nul-terminated; the length is provided in

   the value_length argument. Since it is legal to have zero-length

   values, do not use this argument to test for internal entities.

   For external entities, value will be NULL and systemId will be

   non-NULL. The publicId argument will be NULL unless a public

   identifier was provided. The notationName argument will have a

   non-NULL value only for unparsed entity declarations.

   Note that is_parameter_entity can't be changed to XML_Bool, since

   that would break binary compatibility.

*/

typedef void (*XML_EntityDeclHandler) (void *userData,

                                       const XML_Char *entityName,

                                       int is_parameter_entity,

                                       const XML_Char *value,

                                       int value_length,

                                       const XML_Char *base,

                                       const XML_Char *systemId,

                                       const XML_Char *publicId,

                                       const XML_Char *notationName);

XMLPARSEAPI(void)

XML_SetEntityDeclHandler(XML_Parser parser,

                         XML_EntityDeclHandler handler);

/* OBSOLETE -- OBSOLETE -- OBSOLETE

   This handler has been superceded by the EntityDeclHandler above.

   It is provided here for backward compatibility.

   This is called for a declaration of an unparsed (NDATA) entity.

   The base argument is whatever was set by XML_SetBase. The

   entityName, systemId and notationName arguments will never be

   NULL. The other arguments may be.

*/

typedef void (*XML_UnparsedEntityDeclHandler)(void *userData,

                                              const XML_Char *entityName,

                                              const XML_Char *base,

                                              const XML_Char *systemId,

                                              const XML_Char *publicId,

                                              const XML_Char *notationName);

/* This is called for a declaration of notation.  The base argument is

   whatever was set by XML_SetBase. The notationName will never be

   NULL.  The other arguments can be.

*/

typedef void (*XML_NotationDeclHandler)(void *userData,

                                        const XML_Char *notationName,

                                        const XML_Char *base,

                                        const XML_Char *systemId,

                                        const XML_Char *publicId);

/* When namespace processing is enabled, these are called once for

   each namespace declaration. The call to the start and end element

   handlers occur between the calls to the start and end namespace

   declaration handlers. For an xmlns attribute, prefix will be

   NULL.  For an xmlns="" attribute, uri will be NULL.

*/

typedef void (*XML_StartNamespaceDeclHandler)(void *userData,

                                              const XML_Char *prefix,

                                              const XML_Char *uri);

typedef void (*XML_EndNamespaceDeclHandler)(void *userData,

                                            const XML_Char *prefix);

/* This is called if the document is not standalone, that is, it has an

   external subset or a reference to a parameter entity, but does not

   have standalone="yes". If this handler returns 0, then processing

   will not continue, and the parser will return a

   XML_ERROR_NOT_STANDALONE error.

   If parameter entity parsing is enabled, then in addition to the

   conditions above this handler will only be called if the referenced

   entity was actually read.

*/

typedef int (*XML_NotStandaloneHandler)(void *userData);

/* This is called for a reference to an external parsed general

   entity.  The referenced entity is not automatically parsed.  The

   application can parse it immediately or later using

   XML_ExternalEntityParserCreate.

   The parser argument is the parser parsing the entity containing the

   reference; it can be passed as the parser argument to

   XML_ExternalEntityParserCreate.  The systemId argument is the

   system identifier as specified in the entity declaration; it will

   not be NULL.

   The base argument is the system identifier that should be used as

   the base for resolving systemId if systemId was relative; this is

   set by XML_SetBase; it may be NULL.

   The publicId argument is the public identifier as specified in the

   entity declaration, or NULL if none was specified; the whitespace

   in the public identifier will have been normalized as required by

   the XML spec.

   The context argument specifies the parsing context in the format

   expected by the context argument to XML_ExternalEntityParserCreate;

   context is valid only until the handler returns, so if the

   referenced entity is to be parsed later, it must be copied.

   The handler should return 0 if processing should not continue

   because of a fatal error in the handling of the external entity.

   In this case the calling parser will return an

   XML_ERROR_EXTERNAL_ENTITY_HANDLING error.

   Note that unlike other handlers the first argument is the parser,

   not userData.

*/

// // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // //

// Changed to allow entity name reporting for subsequent diversion to skipped entity handler

// 11/9/03

typedef int (*XML_ExternalEntityRefHandler)(void *userData, const XML_Char *name);

/*

Original form:

typedef int (*XML_ExternalEntityRefHandler)(XML_Parser parser,

                                            const XML_Char *context,

                                            const XML_Char *base,

                                            const XML_Char *systemId,

                                            const XML_Char *publicId);

*/

// // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // // //

/* This is called in two situations:

   1) An entity reference is encountered for which no declaration

      has been read *and* this is not an error.

   2) An internal entity reference is read, but not expanded, because

      XML_SetDefaultHandler has been called.

   Note: skipped parameter entities in declarations and skipped general

         entities in attribute values cannot be reported, because

         the event would be out of sync with the reporting of the

         declarations or attribute values

*/

typedef void (*XML_SkippedEntityHandler)(void *userData,

                                         const XML_Char *entityName,

                                         int is_parameter_entity);

/* This structure is filled in by the XML_UnknownEncodingHandler to

   provide information to the parser about encodings that are unknown

   to the parser.

   The map[b] member gives information about byte sequences whose

   first byte is b.

   If map[b] is c where c is >= 0, then b by itself encodes the

   Unicode scalar value c.

   If map[b] is -1, then the byte sequence is malformed.

   If map[b] is -n, where n >= 2, then b is the first byte of an

   n-byte sequence that encodes a single Unicode scalar value.

   The data member will be passed as the first argument to the convert

   function.

   The convert function is used to convert multibyte sequences; s will

   point to a n-byte sequence where map[(unsigned char)*s] == -n.  The

   convert function must return the Unicode scalar value represented

   by this byte sequence or -1 if the byte sequence is malformed.

   The convert function may be NULL if the encoding is a single-byte

   encoding, that is if map[b] >= -1 for all bytes b.

   When the parser is finished with the encoding, then if release is

   not NULL, it will call release passing it the data member; once

   release has been called, the convert function will not be called

   again.

   Expat places certain restrictions on the encodings that are supported

   using this mechanism.

   1. Every ASCII character that can appear in a well-formed XML document,

      other than the characters

      $@\^`{}~

      must be represented by a single byte, and that byte must be the

      same byte that represents that character in ASCII.

   2. No character may require more than 4 bytes to encode.

   3. All characters encoded must have Unicode scalar values <=

      0xFFFF, (i.e., characters that would be encoded by surrogates in

      UTF-16 are  not allowed).  Note that this restriction doesn't

      apply to the built-in support for UTF-8 and UTF-16.

   4. No Unicode character may be encoded by more than one distinct

      sequence of bytes.

*/

typedef struct {

  int map[256];

  void *data;

  int (*convert)(void *data, const char *s);

  void (*release)(void *data);

} XML_Encoding;

/* This is called for an encoding that is unknown to the parser.

   The encodingHandlerData argument is that which was passed as the

   second argument to XML_SetUnknownEncodingHandler.

   The name argument gives the name of the encoding as specified in

   the encoding declaration.

   If the callback can provide information about the encoding, it must

   fill in the XML_Encoding structure, and return 1.  Otherwise it

   must return 0.

   If info does not describe a suitable encoding, then the parser will

   return an XML_UNKNOWN_ENCODING error.

*/

typedef int (*XML_UnknownEncodingHandler)(void *encodingHandlerData,

                                          const XML_Char *name,

                                          XML_Encoding *info);

XMLPARSEAPI(void)

XML_SetElementHandler(XML_Parser parser,

                      XML_StartElementHandler start,

                      XML_EndElementHandler end);

XMLPARSEAPI(void)

XML_SetStartElementHandler(XML_Parser, XML_StartElementHandler);

XMLPARSEAPI(void)

XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler);

XMLPARSEAPI(void)

XML_SetCharacterDataHandler(XML_Parser parser,

                            XML_CharacterDataHandler handler);

XMLPARSEAPI(void)

XML_SetProcessingInstructionHandler(XML_Parser parser,