2 * Copyright (c) 2015 Apple Inc. All rights reserved.
4 * @APPLE_LICENSE_HEADER_START@
6 * This file contains Original Code and/or Modifications of Original Code
7 * as defined in and that are subject to the Apple Public Source License
8 * Version 2.0 (the 'License'). You may not use this file except in
9 * compliance with the License. Please obtain a copy of the License at
10 * http://www.opensource.apple.com/apsl/ and read it before using this
13 * The Original Code and all software distributed under the License are
14 * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
15 * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
16 * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
18 * Please see the License for the specific language governing rights and
19 * limitations under the License.
21 * @APPLE_LICENSE_HEADER_END@
25 Copyright (c) 1998-2014, Apple Inc. All rights reserved.
28 /* CFXMLParser is deprecated as of Mac OS X 10.8. The suggested replacements are the Foundation classes NSXMLParser and NSXMLDocument, or the libxml2 library. */
30 #if !defined(__COREFOUNDATION_CFXMLPARSER__)
31 #define __COREFOUNDATION_CFXMLPARSER__ 1
33 #include <CoreFoundation/CFBase.h>
34 #include <CoreFoundation/CFArray.h>
35 #include <CoreFoundation/CFData.h>
36 #include <CoreFoundation/CFDictionary.h>
37 #include <CoreFoundation/CFTree.h>
38 #include <CoreFoundation/CFURL.h>
39 #include <CoreFoundation/CFXMLNode.h>
41 CF_IMPLICIT_BRIDGING_ENABLED
44 typedef struct __CFXMLParser
* CFXMLParserRef
;
46 /* These are the various options you can configure the parser with. These are
47 chosen such that an option flag of 0 (kCFXMLParserNoOptions) leaves the XML
48 as "intact" as possible (reports all structures; performs no replacements).
49 Hence, to make the parser do the most work, returning only the pure element
50 tree, set the option flag to kCFXMLParserAllOptions.
52 kCFXMLParserValidateDocument -
53 validate the document against its grammar from the DTD, reporting any errors.
54 Currently not supported.
56 kCFXMLParserSkipMetaData -
57 silently skip over metadata constructs (the DTD and comments)
59 kCFXMLParserReplacePhysicalEntities -
60 replace declared entities like <. Note that other than the 5 predefined
61 entities (lt, gt, quot, amp, apos), these must be defined in the DTD.
62 Currently not supported.
64 kCFXMLParserSkipWhitespace -
65 skip over all whitespace that does not abut non-whitespace character data.
66 In other words, given <foo> <bar> blah </bar></foo>, the whitespace between
67 foo's open tag and bar's open tag would be suppressed, but the whitespace
68 around blah would be preserved.
70 kCFXMLParserAddImpliedAttributes -
71 where the DTD specifies implied attribute-value pairs for a particular element,
72 add those pairs to any occurances of the element in the element tree.
73 Currently not supported.
76 typedef CF_OPTIONS(CFOptionFlags
, CFXMLParserOptions
) {
77 kCFXMLParserValidateDocument
= (1UL << 0),
78 kCFXMLParserSkipMetaData
= (1UL << 1),
79 kCFXMLParserReplacePhysicalEntities
= (1UL << 2),
80 kCFXMLParserSkipWhitespace
= (1UL << 3),
81 kCFXMLParserResolveExternalEntities
= (1UL << 4),
82 kCFXMLParserAddImpliedAttributes
= (1UL << 5),
83 kCFXMLParserAllOptions
= 0x00FFFFFF,
84 kCFXMLParserNoOptions
= 0
87 /* This list is expected to grow */
88 typedef CF_OPTIONS(CFIndex
, CFXMLParserStatusCode
) {
89 kCFXMLStatusParseNotBegun
= -2,
90 kCFXMLStatusParseInProgress
= -1,
91 kCFXMLStatusParseSuccessful
= 0,
92 kCFXMLErrorUnexpectedEOF
= 1,
93 kCFXMLErrorUnknownEncoding
,
94 kCFXMLErrorEncodingConversionFailure
,
95 kCFXMLErrorMalformedProcessingInstruction
,
96 kCFXMLErrorMalformedDTD
,
97 kCFXMLErrorMalformedName
,
98 kCFXMLErrorMalformedCDSect
,
99 kCFXMLErrorMalformedCloseTag
,
100 kCFXMLErrorMalformedStartTag
,
101 kCFXMLErrorMalformedDocument
,
102 kCFXMLErrorElementlessDocument
,
103 kCFXMLErrorMalformedComment
,
104 kCFXMLErrorMalformedCharacterReference
,
105 kCFXMLErrorMalformedParsedCharacterData
,
110 /* These functions are called as a parse progresses.
113 called as new XML structures are encountered by the parser. May return NULL to indicate
114 that the given structure should be skipped; if NULL is returned for a given structure,
115 only minimal parsing is done for that structure (enough to correctly determine its end,
116 and to extract any data necessary for the remainder of the parse, such as Entity definitions).
117 createXMLStructure (or indeed, any of the tree-creation callbacks) will not be called for any
118 children of the skipped structure. The only exception is that the top-most element will always
119 be reported even if NULL was returned for the document as a whole. NOTE: for performance reasons,
120 the node passed to createXMLStructure cannot be safely retained by the client; the node as
121 a whole must be copied (via CFXMLNodeCreateCopy), or its contents must be extracted and copied.
124 called as children are parsed and are ready to be added to the tree. If createXMLStructure
125 returns NULL for a given structure, that structure is omitted entirely, and addChild will
126 NOT be called for either a NULL child or parent.
129 called once a structure (and all its children) are completely parsed. As elements are encountered,
130 createXMLStructure is called for them first, then addChild to add the new structure to its parent,
131 then addChild (potentially several times) to add the new structure's children to it, then finally
132 endXMLStructure to show that the structure has been fully parsed.
134 createXMLStructure, addChild, and endXMLStructure are all REQUIRED TO BE NON-NULL.
136 resolveExternalEntity -
137 called when external entities are referenced (NOT when they are simply defined). If the function
138 pointer is NULL, the parser uses its internal routines to try and resolve the entity. If the
139 function pointer is set, and the function returns NULL, a place holder for the external entity
140 is inserted into the tree. In this manner, the parser's client can prevent any external network
143 handleError - called as errors/warnings are encountered in the data stream. At some point, we will
144 have an enum of the expected errors, some of which will be fatal, others of which will not. If
145 the function pointer is NULL, the parser will silently attempt to recover. The
146 handleError function may always return false to force the parser to stop; if handleError returns
147 true, the parser will attempt to recover (fatal errors will still cause the parse to abort
151 typedef void * (*CFXMLParserCreateXMLStructureCallBack
)(CFXMLParserRef parser
, CFXMLNodeRef nodeDesc
, void *info
);
152 typedef void (*CFXMLParserAddChildCallBack
)(CFXMLParserRef parser
, void *parent
, void *child
, void *info
);
153 typedef void (*CFXMLParserEndXMLStructureCallBack
)(CFXMLParserRef parser
, void *xmlType
, void *info
);
154 typedef CFDataRef (*CFXMLParserResolveExternalEntityCallBack
)(CFXMLParserRef parser
, CFXMLExternalID
*extID
, void *info
);
155 typedef Boolean (*CFXMLParserHandleErrorCallBack
)(CFXMLParserRef parser
, CFXMLParserStatusCode error
, void *info
);
158 CFXMLParserCreateXMLStructureCallBack createXMLStructure
;
159 CFXMLParserAddChildCallBack addChild
;
160 CFXMLParserEndXMLStructureCallBack endXMLStructure
;
161 CFXMLParserResolveExternalEntityCallBack resolveExternalEntity
;
162 CFXMLParserHandleErrorCallBack handleError
;
163 } CFXMLParserCallBacks
;
165 typedef const void * (*CFXMLParserRetainCallBack
)(const void *info
);
166 typedef void (*CFXMLParserReleaseCallBack
)(const void *info
);
167 typedef CFStringRef (*CFXMLParserCopyDescriptionCallBack
)(const void *info
);
171 CFXMLParserRetainCallBack retain
;
172 CFXMLParserReleaseCallBack release
;
173 CFXMLParserCopyDescriptionCallBack copyDescription
;
174 } CFXMLParserContext
;
177 CFTypeID
CFXMLParserGetTypeID(void) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
179 /* Creates a parser which will parse the given data with the given options. xmlData may not be NULL.
180 dataSource should be the URL from which the data came, and may be NULL; it is used to resolve any
181 relative references found in xmlData. versionOfNodes determines which version CFXMLNodes are produced
182 by the parser; see CFXMLNode.h for more details. callBacks are the callbacks called by the parser as
183 the parse progresses; callBacks, callBacks->createXMLStructure, callBacks->addChild, and
184 callBacks->endXMLStructure must all be non-NULL. context determines what if any info pointer is
185 passed to the callbacks as the parse progresses; context may be NULL. */
187 CFXMLParserRef
CFXMLParserCreate(CFAllocatorRef allocator
, CFDataRef xmlData
, CFURLRef dataSource
, CFOptionFlags parseOptions
, CFIndex versionOfNodes
, CFXMLParserCallBacks
*callBacks
, CFXMLParserContext
*context
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
189 /* Arguments as above, except that the data to be parsed is loaded directly
190 from dataSource. dataSource may not be NULL. */
192 CFXMLParserRef
CFXMLParserCreateWithDataFromURL(CFAllocatorRef allocator
, CFURLRef dataSource
, CFOptionFlags parseOptions
, CFIndex versionOfNodes
, CFXMLParserCallBacks
*callBacks
, CFXMLParserContext
*context
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
195 void CFXMLParserGetContext(CFXMLParserRef parser
, CFXMLParserContext
*context
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
198 void CFXMLParserGetCallBacks(CFXMLParserRef parser
, CFXMLParserCallBacks
*callBacks
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
201 CFURLRef
CFXMLParserGetSourceURL(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
203 /* Returns the character index of the current parse location */
205 CFIndex
CFXMLParserGetLocation(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
207 /* Returns the line number of the current parse location */
209 CFIndex
CFXMLParserGetLineNumber(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
211 /* Returns the top-most object returned by the createXMLStructure callback */
213 void *CFXMLParserGetDocument(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
215 /* Get the status code or a user-readable description of the last error that occurred in a parse.
216 If no error has occurred, a null description string is returned. See the enum above for
217 possible status returns */
219 CFXMLParserStatusCode
CFXMLParserGetStatusCode(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
222 CFStringRef
CFXMLParserCopyErrorDescription(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
224 /* Cause any in-progress parse to abort with the given error code and description. errorCode
225 must be positive, and errorDescription may not be NULL. Cannot be called asynchronously
226 (i.e. must be called from within a parser callback) */
228 void CFXMLParserAbort(CFXMLParserRef parser
, CFXMLParserStatusCode errorCode
, CFStringRef errorDescription
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
230 /* Starts a parse of the data the parser was created with; returns success or failure.
231 Upon success, use CFXMLParserGetDocument() to get the product of the parse. Upon
232 failure, use CFXMLParserGetErrorCode() or CFXMLParserCopyErrorDescription() to get
233 information about the error. It is an error to call CFXMLParserParse() while a
234 parse is already underway. */
236 Boolean
CFXMLParserParse(CFXMLParserRef parser
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
238 /* These functions provide a higher-level interface. The XML data is parsed to a
239 special CFTree (an CFXMLTree) with known contexts and callbacks. See CFXMLNode.h
240 for full details on using an CFXMLTree and the CFXMLNodes contained therein.
242 /* Parse to an CFXMLTreeRef. parseOptions are as above. versionOfNodes determines
243 what version CFXMLNodes are used to populate the tree. */
245 CFXMLTreeRef
CFXMLTreeCreateFromData(CFAllocatorRef allocator
, CFDataRef xmlData
, CFURLRef dataSource
, CFOptionFlags parseOptions
, CFIndex versionOfNodes
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
247 /* As above, with the additional by-reference pass of a CFDictionaryRef containing
248 various error information (see below). The caller is responsible for releasing the
249 returned dictionary. If the error dictionary is not desired, pass NULL. */
251 CFXMLTreeRef
CFXMLTreeCreateFromDataWithError(CFAllocatorRef allocator
, CFDataRef xmlData
, CFURLRef dataSource
, CFOptionFlags parseOptions
, CFIndex versionOfNodes
, CFDictionaryRef
*errorDict
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
253 /* Loads the data to be parsed directly from dataSource. Arguments as above. */
255 CFXMLTreeRef
CFXMLTreeCreateWithDataFromURL(CFAllocatorRef allocator
, CFURLRef dataSource
, CFOptionFlags parseOptions
, CFIndex versionOfNodes
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
257 /* Generate the XMLData (ready to be written to whatever permanent storage is to be
258 used) from an CFXMLTree. Will NOT regenerate entity references (except those
259 required for syntactic correctness) if they were replaced at the parse time;
260 clients that wish this should walk the tree and re-insert any entity references
261 that should appear in the final output file. */
263 CFDataRef
CFXMLTreeCreateXMLData(CFAllocatorRef allocator
, CFXMLTreeRef xmlTree
) CF_DEPRECATED(10_0
, 10_8
, 2_0
, 6_0
);
265 /* Escaping and unescaping XML entities in CFStrings. The standard XML entities
266 are always replaced. */
267 /* Creates a CFString by replacing entities that appear in the entities dictionary.
268 Dictionary keys are the entities themselves, and the values should be CFStrings
269 containing the expansion. Pass NULL for entitiesDictionary to indicate no entities
270 other than the standard five. */
272 CFStringRef
CFXMLCreateStringByEscapingEntities(CFAllocatorRef allocator
, CFStringRef string
, CFDictionaryRef entitiesDictionary
);
275 CFStringRef
CFXMLCreateStringByUnescapingEntities(CFAllocatorRef allocator
, CFStringRef string
, CFDictionaryRef entitiesDictionary
);
277 /* CFXMLTreeCreateFromDataWithError error dictionary key constants. */
278 CF_EXPORT
const CFStringRef kCFXMLTreeErrorDescription
;
279 /* value is a CFString containing the readable error string. */
281 CF_EXPORT
const CFStringRef kCFXMLTreeErrorLineNumber
;
282 /* value is a CFNumber containing the line on which the error appears. */
284 CF_EXPORT
const CFStringRef kCFXMLTreeErrorLocation
;
285 /* value is a CFNumber containing the byte location at which the error occurred. */
287 CF_EXPORT
const CFStringRef kCFXMLTreeErrorStatusCode
;
288 /* value is a CFNumber containing the error status code. */
291 CF_IMPLICIT_BRIDGING_DISABLED
293 #endif /* ! __COREFOUNDATION_CFXMLPARSER__ */