1 | /*
|
---|
2 | * Copyright 1999-2004 The Apache Software Foundation.
|
---|
3 | *
|
---|
4 | * Licensed under the Apache License, Version 2.0 (the "License");
|
---|
5 | * you may not use this file except in compliance with the License.
|
---|
6 | * You may obtain a copy of the License at
|
---|
7 | *
|
---|
8 | * http://www.apache.org/licenses/LICENSE-2.0
|
---|
9 | *
|
---|
10 | * Unless required by applicable law or agreed to in writing, software
|
---|
11 | * distributed under the License is distributed on an "AS IS" BASIS,
|
---|
12 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
---|
13 | * See the License for the specific language governing permissions and
|
---|
14 | * limitations under the License.
|
---|
15 | */
|
---|
16 |
|
---|
17 | /*
|
---|
18 | * $Log: XMLValidator.hpp,v $
|
---|
19 | * Revision 1.10 2004/09/08 13:55:59 peiyongz
|
---|
20 | * Apache License Version 2.0
|
---|
21 | *
|
---|
22 | * Revision 1.9 2003/05/15 18:26:07 knoaman
|
---|
23 | * Partial implementation of the configurable memory manager.
|
---|
24 | *
|
---|
25 | * Revision 1.8 2003/03/07 18:08:10 tng
|
---|
26 | * Return a reference instead of void for operator=
|
---|
27 | *
|
---|
28 | * Revision 1.7 2002/11/07 21:59:22 tng
|
---|
29 | * Pass elemDecl to XMLValidator::validateAttrValue so that we can include element name in error message.
|
---|
30 | *
|
---|
31 | * Revision 1.6 2002/11/04 15:00:21 tng
|
---|
32 | * C++ Namespace Support.
|
---|
33 | *
|
---|
34 | * Revision 1.5 2002/09/04 18:17:55 tng
|
---|
35 | * Do not set IDREF to used during prevalidation.
|
---|
36 | *
|
---|
37 | * Revision 1.4 2002/08/20 16:54:11 tng
|
---|
38 | * [Bug 6251] Info during compilation.
|
---|
39 | *
|
---|
40 | * Revision 1.3 2002/07/11 18:55:44 knoaman
|
---|
41 | * Add a flag to the preContentValidation method to indicate whether to validate
|
---|
42 | * default/fixed attributes or not.
|
---|
43 | *
|
---|
44 | * Revision 1.2 2002/02/20 18:17:01 tng
|
---|
45 | * [Bug 5977] Warnings on generating apiDocs.
|
---|
46 | *
|
---|
47 | * Revision 1.1.1.1 2002/02/01 22:21:52 peiyongz
|
---|
48 | * sane_include
|
---|
49 | *
|
---|
50 | * Revision 1.17 2001/11/30 22:18:18 peiyongz
|
---|
51 | * cleanUp function made member function
|
---|
52 | * cleanUp object moved to file scope
|
---|
53 | * double mutex lock removed
|
---|
54 | *
|
---|
55 | * Revision 1.16 2001/11/13 13:24:46 tng
|
---|
56 | * Deprecate function XMLValidator::checkRootElement.
|
---|
57 | *
|
---|
58 | * Revision 1.15 2001/10/24 23:46:52 peiyongz
|
---|
59 | * [Bug 4342] fix the leak.
|
---|
60 | *
|
---|
61 | * Revision 1.14 2001/06/05 16:51:17 knoaman
|
---|
62 | * Add 'const' to getGrammar - submitted by Peter A. Volchek.
|
---|
63 | *
|
---|
64 | * Revision 1.13 2001/05/11 13:25:33 tng
|
---|
65 | * Copyright update.
|
---|
66 | *
|
---|
67 | * Revision 1.12 2001/05/03 20:34:22 tng
|
---|
68 | * Schema: SchemaValidator update
|
---|
69 | *
|
---|
70 | * Revision 1.11 2001/04/19 18:16:53 tng
|
---|
71 | * Schema: SchemaValidator update, and use QName in Content Model
|
---|
72 | *
|
---|
73 | * Revision 1.10 2001/03/21 21:56:03 tng
|
---|
74 | * Schema: Add Schema Grammar, Schema Validator, and split the DTDValidator into DTDValidator, DTDScanner, and DTDGrammar.
|
---|
75 | *
|
---|
76 | * Revision 1.9 2001/02/26 19:21:33 tng
|
---|
77 | * Schema: add parameter prefix in findElem and findAttr.
|
---|
78 | *
|
---|
79 | * Revision 1.8 2000/12/14 18:49:58 tng
|
---|
80 | * Fix API document generation warning: "Warning: end of member group without matching begin"
|
---|
81 | *
|
---|
82 | * Revision 1.7 2000/08/09 22:09:09 jpolast
|
---|
83 | * added const XMLCh* getURIText()
|
---|
84 | * allows parsers to use const URIs instead of appending
|
---|
85 | * to a XMLBuffer.
|
---|
86 | *
|
---|
87 | * Revision 1.6 2000/03/02 19:54:25 roddey
|
---|
88 | * This checkin includes many changes done while waiting for the
|
---|
89 | * 1.1.0 code to be finished. I can't list them all here, but a list is
|
---|
90 | * available elsewhere.
|
---|
91 | *
|
---|
92 | * Revision 1.5 2000/02/24 20:00:24 abagchi
|
---|
93 | * Swat for removing Log from API docs
|
---|
94 | *
|
---|
95 | * Revision 1.4 2000/02/15 23:59:07 roddey
|
---|
96 | * More updated documentation of Framework classes.
|
---|
97 | *
|
---|
98 | * Revision 1.3 2000/02/15 01:21:31 roddey
|
---|
99 | * Some initial documentation improvements. More to come...
|
---|
100 | *
|
---|
101 | * Revision 1.2 2000/02/06 07:47:49 rahulj
|
---|
102 | * Year 2K copyright swat.
|
---|
103 | *
|
---|
104 | * Revision 1.1.1.1 1999/11/09 01:08:38 twl
|
---|
105 | * Initial checkin
|
---|
106 | *
|
---|
107 | * Revision 1.4 1999/11/08 20:44:41 rahul
|
---|
108 | * Swat for adding in Product name and CVS comment log variable.
|
---|
109 | *
|
---|
110 | */
|
---|
111 |
|
---|
112 |
|
---|
113 | #if !defined(XMLVALIDATOR_HPP)
|
---|
114 | #define XMLVALIDATOR_HPP
|
---|
115 |
|
---|
116 | #include <xercesc/framework/XMLAttr.hpp>
|
---|
117 | #include <xercesc/framework/XMLValidityCodes.hpp>
|
---|
118 |
|
---|
119 | XERCES_CPP_NAMESPACE_BEGIN
|
---|
120 |
|
---|
121 | class ReaderMgr;
|
---|
122 | class XMLBufferMgr;
|
---|
123 | class XMLElementDecl;
|
---|
124 | class XMLScanner;
|
---|
125 | class Grammar;
|
---|
126 |
|
---|
127 |
|
---|
128 | /**
|
---|
129 | * This abstract class provides the interface for all validators. This is
|
---|
130 | * the simple amount of API that all validators must honor, in order for
|
---|
131 | * the scanner to use them to do validation. All validators will actually
|
---|
132 | * contain much more functionality than is accessible via this common API,
|
---|
133 | * but that functionality requires that you know what type of validator you
|
---|
134 | * are dealing with.
|
---|
135 | *
|
---|
136 | * Basically, at this level, the primary concern is to be able to query
|
---|
137 | * core information about elements and attributes. Adding decls to the
|
---|
138 | * validator requires that you go through the derived interface because they
|
---|
139 | * all have their own decl types. At this level, we can return information
|
---|
140 | * via the base decl classes, from which each validator derives its own
|
---|
141 | * decl classes.
|
---|
142 | */
|
---|
143 | class XMLPARSER_EXPORT XMLValidator : public XMemory
|
---|
144 | {
|
---|
145 | public:
|
---|
146 | // -----------------------------------------------------------------------
|
---|
147 | // Constructors are hidden, just the virtual destructor is exposed
|
---|
148 | // -----------------------------------------------------------------------
|
---|
149 |
|
---|
150 | /** @name Destructor */
|
---|
151 | //@{
|
---|
152 |
|
---|
153 | /**
|
---|
154 | * The derived class should clean up its allocated data, then this class
|
---|
155 | * will do the same for data allocated at this level.
|
---|
156 | */
|
---|
157 | virtual ~XMLValidator()
|
---|
158 | {
|
---|
159 | }
|
---|
160 | //@}
|
---|
161 |
|
---|
162 |
|
---|
163 | // -----------------------------------------------------------------------
|
---|
164 | // The virtual validator interface
|
---|
165 | // -----------------------------------------------------------------------
|
---|
166 |
|
---|
167 | /** @name Virtual validator interface */
|
---|
168 | //@{
|
---|
169 |
|
---|
170 | /**
|
---|
171 | * The derived class should look up its declaration of the passed element
|
---|
172 | * from its element pool. It should then use the content model description
|
---|
173 | * contained in that element declaration to validate that the passed list
|
---|
174 | * of child elements are valid for that content model. The count can be
|
---|
175 | * zero, indicating no child elements.
|
---|
176 | *
|
---|
177 | * Note that whitespace and text content are not validated here. Those are
|
---|
178 | * handled by the scanner. So only element ids are provided here.
|
---|
179 | *
|
---|
180 | * @param elemDecl The element whose content is to be checked.
|
---|
181 | *
|
---|
182 | * @param children An array of element QName which represent the elements
|
---|
183 | * found within the parent element, i.e. the content
|
---|
184 | * to be validated.
|
---|
185 | *
|
---|
186 | * @param childCount The number of elements in the childIds array. It can
|
---|
187 | * be zero if the element had none.
|
---|
188 | */
|
---|
189 | virtual int checkContent
|
---|
190 | (
|
---|
191 | XMLElementDecl* const elemDecl
|
---|
192 | , QName** const children
|
---|
193 | , const unsigned int childCount
|
---|
194 | ) = 0;
|
---|
195 |
|
---|
196 | /**
|
---|
197 | * The derived class should fault in the passed XMLAttr value. It should
|
---|
198 | * use the passeed attribute definition (which is passed via the base
|
---|
199 | * type so it must often be downcast to the appropriate type for the
|
---|
200 | * derived validator class), to fill in the passed attribute. This is done
|
---|
201 | * as a performance enhancement since the derived class has more direct
|
---|
202 | * access to the information.
|
---|
203 | */
|
---|
204 | virtual void faultInAttr
|
---|
205 | (
|
---|
206 | XMLAttr& toFill
|
---|
207 | , const XMLAttDef& attDef
|
---|
208 | ) const = 0;
|
---|
209 |
|
---|
210 | /**
|
---|
211 | * This method is called by the scanner after a Grammar is scanned.
|
---|
212 | */
|
---|
213 | virtual void preContentValidation(bool reuseGrammar,
|
---|
214 | bool validateDefAttr = false) = 0;
|
---|
215 |
|
---|
216 | /**
|
---|
217 | * This method is called by the scanner after the parse has completed. It
|
---|
218 | * gives the validator a chance to check certain things that can only be
|
---|
219 | * checked after the whole document has been parsed, such as referential
|
---|
220 | * integrity of ID/IDREF pairs and so forth. The validator should just
|
---|
221 | * issue errors for any problems it finds.
|
---|
222 | */
|
---|
223 | virtual void postParseValidation() = 0;
|
---|
224 |
|
---|
225 | /**
|
---|
226 | * This method is called by the scanner before a new document is about
|
---|
227 | * to start. It gives the validator a change to reset itself in preperation
|
---|
228 | * for another validation pass.
|
---|
229 | */
|
---|
230 | virtual void reset() = 0;
|
---|
231 |
|
---|
232 | /**
|
---|
233 | * The derived class should return a boolean that indicates whether it
|
---|
234 | * requires namespace processing or not. Some do and some allow it to be
|
---|
235 | * optional. This flag is used to control whether the client code's
|
---|
236 | * requests to disable namespace processing can be honored or not.
|
---|
237 | */
|
---|
238 | virtual bool requiresNamespaces() const = 0;
|
---|
239 |
|
---|
240 | /**
|
---|
241 | * The derived class should apply any rules to the passed attribute value
|
---|
242 | * that are above and beyond those defined by XML 1.0. The scanner itself
|
---|
243 | * will impose XML 1.0 rules, based on the type of the attribute. This
|
---|
244 | * will generally be used to check things such as range checks and other
|
---|
245 | * datatype related validation.
|
---|
246 | *
|
---|
247 | * If the value breaks any rules as defined by the derived class, it
|
---|
248 | * should just issue errors as usual.
|
---|
249 | */
|
---|
250 | virtual void validateAttrValue
|
---|
251 | (
|
---|
252 | const XMLAttDef* attDef
|
---|
253 | , const XMLCh* const attrValue
|
---|
254 | , bool preValidation = false
|
---|
255 | , const XMLElementDecl* elemDecl = 0
|
---|
256 | ) = 0;
|
---|
257 |
|
---|
258 | /**
|
---|
259 | * The derived class should apply any rules to the passed element decl
|
---|
260 | * that are above and beyond those defined by XML 1.0.
|
---|
261 | *
|
---|
262 | * If the value breaks any rules as defined by the derived class, it
|
---|
263 | * should just issue errors as usual.
|
---|
264 | */
|
---|
265 | virtual void validateElement
|
---|
266 | (
|
---|
267 | const XMLElementDecl* elemDef
|
---|
268 | ) = 0;
|
---|
269 |
|
---|
270 | /**
|
---|
271 | * Retrieve the Grammar used
|
---|
272 | */
|
---|
273 | virtual Grammar* getGrammar() const =0;
|
---|
274 |
|
---|
275 | /**
|
---|
276 | * Set the Grammar
|
---|
277 | */
|
---|
278 | virtual void setGrammar(Grammar* aGrammar) =0;
|
---|
279 |
|
---|
280 |
|
---|
281 | //@}
|
---|
282 |
|
---|
283 | // -----------------------------------------------------------------------
|
---|
284 | // Virtual DTD handler interface.
|
---|
285 | // -----------------------------------------------------------------------
|
---|
286 |
|
---|
287 | /** @name Virtual DTD handler interface */
|
---|
288 | //@{
|
---|
289 |
|
---|
290 | /**
|
---|
291 | * This method allows the scanner to ask the validator if it handles
|
---|
292 | * DTDs or not.
|
---|
293 | */
|
---|
294 | virtual bool handlesDTD() const = 0;
|
---|
295 |
|
---|
296 | // -----------------------------------------------------------------------
|
---|
297 | // Virtual Schema handler interface.
|
---|
298 | // -----------------------------------------------------------------------
|
---|
299 |
|
---|
300 | /** @name Virtual Schema handler interface */
|
---|
301 |
|
---|
302 | /**
|
---|
303 | * This method allows the scanner to ask the validator if it handles
|
---|
304 | * Schema or not.
|
---|
305 | */
|
---|
306 | virtual bool handlesSchema() const = 0;
|
---|
307 |
|
---|
308 | //@}
|
---|
309 |
|
---|
310 | // -----------------------------------------------------------------------
|
---|
311 | // Setter methods
|
---|
312 | //
|
---|
313 | // setScannerInfo() is called by the scanner to tell the validator
|
---|
314 | // about the stuff it needs to have access to.
|
---|
315 | // -----------------------------------------------------------------------
|
---|
316 |
|
---|
317 | /** @name Setter methods */
|
---|
318 | //@{
|
---|
319 |
|
---|
320 | /**
|
---|
321 | * @param owningScanner This is a pointer to the scanner to which the
|
---|
322 | * validator belongs. The validator will often
|
---|
323 | * need to query state data from the scanner.
|
---|
324 | *
|
---|
325 | * @param readerMgr This is a pointer to the reader manager that is
|
---|
326 | * being used by the scanner.
|
---|
327 | *
|
---|
328 | * @param bufMgr This is the buffer manager of the scanner. This
|
---|
329 | * is provided as a convenience so that the validator
|
---|
330 | * doesn't have to create its own buffer manager
|
---|
331 | * during the parse process.
|
---|
332 | */
|
---|
333 | void setScannerInfo
|
---|
334 | (
|
---|
335 | XMLScanner* const owningScanner
|
---|
336 | , ReaderMgr* const readerMgr
|
---|
337 | , XMLBufferMgr* const bufMgr
|
---|
338 | );
|
---|
339 |
|
---|
340 | /**
|
---|
341 | * This method is called to set an error reporter on the validator via
|
---|
342 | * which it will report any errors it sees during parsing or validation.
|
---|
343 | * This is generally called by the owning scanner.
|
---|
344 | *
|
---|
345 | * @param errorReporter A pointer to the error reporter to use. This
|
---|
346 | * is not adopted, just referenced so the caller
|
---|
347 | * remains responsible for its cleanup, if any.
|
---|
348 | */
|
---|
349 | void setErrorReporter
|
---|
350 | (
|
---|
351 | XMLErrorReporter* const errorReporter
|
---|
352 | );
|
---|
353 |
|
---|
354 | //@}
|
---|
355 |
|
---|
356 |
|
---|
357 | // -----------------------------------------------------------------------
|
---|
358 | // Error emitter methods
|
---|
359 | // -----------------------------------------------------------------------
|
---|
360 |
|
---|
361 | /** @name Error emittor methods */
|
---|
362 | //@{
|
---|
363 |
|
---|
364 | /**
|
---|
365 | * This call is a convenience by which validators can emit errors. Most
|
---|
366 | * of the grunt work of loading the text, getting the current source
|
---|
367 | * location, ect... is handled here.
|
---|
368 | *
|
---|
369 | * If the loaded text has replacement parameters, then text strings can be
|
---|
370 | * passed. These will be used to replace the tokens {0}, {1}, {2}, and {3}
|
---|
371 | * in the order passed. So text1 will replace {0}, text2 will replace {1},
|
---|
372 | * and so forth.
|
---|
373 | *
|
---|
374 | * textX Up to four replacement parameters. They can be provided
|
---|
375 | * as either XMLCh strings, or local code page strings which
|
---|
376 | * will be transcoded internally.
|
---|
377 | *
|
---|
378 | * @param toEmit The error code to emit. it must be one of the defined
|
---|
379 | * validator error codes.
|
---|
380 | *
|
---|
381 | */
|
---|
382 | void emitError(const XMLValid::Codes toEmit);
|
---|
383 | void emitError
|
---|
384 | (
|
---|
385 | const XMLValid::Codes toEmit
|
---|
386 | , const XMLCh* const text1
|
---|
387 | , const XMLCh* const text2 = 0
|
---|
388 | , const XMLCh* const text3 = 0
|
---|
389 | , const XMLCh* const text4 = 0
|
---|
390 | );
|
---|
391 | void emitError
|
---|
392 | (
|
---|
393 | const XMLValid::Codes toEmit
|
---|
394 | , const char* const text1
|
---|
395 | , const char* const text2 = 0
|
---|
396 | , const char* const text3 = 0
|
---|
397 | , const char* const text4 = 0
|
---|
398 | );
|
---|
399 |
|
---|
400 | //@}
|
---|
401 |
|
---|
402 | // -----------------------------------------------------------------------
|
---|
403 | // Deprecated XMLValidator interface
|
---|
404 | // -----------------------------------------------------------------------
|
---|
405 | /**
|
---|
406 | *
|
---|
407 | * DEPRECATED.
|
---|
408 | * For those validators that contrain the possible root elements of a
|
---|
409 | * document to only particular elements, they should use this call to
|
---|
410 | * validate that the passed root element id is a legal root element.
|
---|
411 | */
|
---|
412 | bool checkRootElement
|
---|
413 | (
|
---|
414 | const unsigned int
|
---|
415 | ) { return true;};
|
---|
416 |
|
---|
417 | // -----------------------------------------------------------------------
|
---|
418 | // Notification that lazy data has been deleted
|
---|
419 | // -----------------------------------------------------------------------
|
---|
420 | static void reinitMsgMutex();
|
---|
421 |
|
---|
422 | static void reinitMsgLoader();
|
---|
423 |
|
---|
424 | protected :
|
---|
425 | // -----------------------------------------------------------------------
|
---|
426 | // Hidden constructors
|
---|
427 | // -----------------------------------------------------------------------
|
---|
428 | XMLValidator
|
---|
429 | (
|
---|
430 | XMLErrorReporter* const errReporter = 0
|
---|
431 | );
|
---|
432 |
|
---|
433 |
|
---|
434 | // -----------------------------------------------------------------------
|
---|
435 | // Protected getters
|
---|
436 | // -----------------------------------------------------------------------
|
---|
437 | const XMLBufferMgr* getBufMgr() const;
|
---|
438 | XMLBufferMgr* getBufMgr();
|
---|
439 | const ReaderMgr* getReaderMgr() const;
|
---|
440 | ReaderMgr* getReaderMgr();
|
---|
441 | const XMLScanner* getScanner() const;
|
---|
442 | XMLScanner* getScanner();
|
---|
443 |
|
---|
444 |
|
---|
445 | private :
|
---|
446 | // -----------------------------------------------------------------------
|
---|
447 | // Unimplemented Constructors and Operators
|
---|
448 | // -----------------------------------------------------------------------
|
---|
449 | XMLValidator(const XMLValidator&);
|
---|
450 | XMLValidator& operator=(const XMLValidator&);
|
---|
451 |
|
---|
452 |
|
---|
453 | // -----------------------------------------------------------------------
|
---|
454 | // Private data members
|
---|
455 | //
|
---|
456 | // fErrorReporter
|
---|
457 | // The error reporter we are to use, if any.
|
---|
458 | //
|
---|
459 | // -----------------------------------------------------------------------
|
---|
460 | XMLBufferMgr* fBufMgr;
|
---|
461 | XMLErrorReporter* fErrorReporter;
|
---|
462 | ReaderMgr* fReaderMgr;
|
---|
463 | XMLScanner* fScanner;
|
---|
464 | };
|
---|
465 |
|
---|
466 |
|
---|
467 | // -----------------------------------------------------------------------
|
---|
468 | // Setter methods
|
---|
469 | // -----------------------------------------------------------------------
|
---|
470 | inline void
|
---|
471 | XMLValidator::setScannerInfo(XMLScanner* const owningScanner
|
---|
472 | , ReaderMgr* const readerMgr
|
---|
473 | , XMLBufferMgr* const bufMgr)
|
---|
474 | {
|
---|
475 | // We don't own any of these, we just reference them
|
---|
476 | fScanner = owningScanner;
|
---|
477 | fReaderMgr = readerMgr;
|
---|
478 | fBufMgr = bufMgr;
|
---|
479 | }
|
---|
480 |
|
---|
481 | inline void
|
---|
482 | XMLValidator::setErrorReporter(XMLErrorReporter* const errorReporter)
|
---|
483 | {
|
---|
484 | fErrorReporter = errorReporter;
|
---|
485 | }
|
---|
486 |
|
---|
487 |
|
---|
488 | // ---------------------------------------------------------------------------
|
---|
489 | // XMLValidator: Protected getter
|
---|
490 | // ---------------------------------------------------------------------------
|
---|
491 | inline const XMLBufferMgr* XMLValidator::getBufMgr() const
|
---|
492 | {
|
---|
493 | return fBufMgr;
|
---|
494 | }
|
---|
495 |
|
---|
496 | inline XMLBufferMgr* XMLValidator::getBufMgr()
|
---|
497 | {
|
---|
498 | return fBufMgr;
|
---|
499 | }
|
---|
500 |
|
---|
501 | inline const ReaderMgr* XMLValidator::getReaderMgr() const
|
---|
502 | {
|
---|
503 | return fReaderMgr;
|
---|
504 | }
|
---|
505 |
|
---|
506 | inline ReaderMgr* XMLValidator::getReaderMgr()
|
---|
507 | {
|
---|
508 | return fReaderMgr;
|
---|
509 | }
|
---|
510 |
|
---|
511 | inline const XMLScanner* XMLValidator::getScanner() const
|
---|
512 | {
|
---|
513 | return fScanner;
|
---|
514 | }
|
---|
515 |
|
---|
516 | inline XMLScanner* XMLValidator::getScanner()
|
---|
517 | {
|
---|
518 | return fScanner;
|
---|
519 | }
|
---|
520 |
|
---|
521 | XERCES_CPP_NAMESPACE_END
|
---|
522 |
|
---|
523 | #endif
|
---|