[2674] | 1 | /* |
---|
| 2 | * Licensed to the Apache Software Foundation (ASF) under one or more |
---|
| 3 | * contributor license agreements. See the NOTICE file distributed with |
---|
| 4 | * this work for additional information regarding copyright ownership. |
---|
| 5 | * The ASF licenses this file to You under the Apache License, Version 2.0 |
---|
| 6 | * (the "License"); you may not use this file except in compliance with |
---|
| 7 | * the License. You may obtain a copy of the License at |
---|
| 8 | * |
---|
| 9 | * http://www.apache.org/licenses/LICENSE-2.0 |
---|
| 10 | * |
---|
| 11 | * Unless required by applicable law or agreed to in writing, software |
---|
| 12 | * distributed under the License is distributed on an "AS IS" BASIS, |
---|
| 13 | * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
---|
| 14 | * See the License for the specific language governing permissions and |
---|
| 15 | * limitations under the License. |
---|
| 16 | */ |
---|
| 17 | |
---|
| 18 | /* |
---|
| 19 | * $Id: XMLDocumentHandler.hpp 568078 2007-08-21 11:43:25Z amassari $ |
---|
| 20 | */ |
---|
| 21 | |
---|
| 22 | |
---|
| 23 | #if !defined(XMLDOCUMENTHANDLER_HPP) |
---|
| 24 | #define XMLDOCUMENTHANDLER_HPP |
---|
| 25 | |
---|
| 26 | #include <xercesc/util/XercesDefs.hpp> |
---|
| 27 | #include <xercesc/util/RefVectorOf.hpp> |
---|
| 28 | #include <xercesc/framework/XMLAttr.hpp> |
---|
| 29 | |
---|
| 30 | XERCES_CPP_NAMESPACE_BEGIN |
---|
| 31 | |
---|
| 32 | class XMLElementDecl; |
---|
| 33 | class XMLEntityDecl; |
---|
| 34 | |
---|
| 35 | /** |
---|
| 36 | * This abstract class provides the interface for the scanner to return |
---|
| 37 | * XML document information up to the parser as it scans through the |
---|
| 38 | * document. |
---|
| 39 | * |
---|
| 40 | * The interface is very similar to org.sax.DocumentHandler, but |
---|
| 41 | * has some extra methods required to get all the data out. |
---|
| 42 | */ |
---|
| 43 | class XMLPARSER_EXPORT XMLDocumentHandler |
---|
| 44 | { |
---|
| 45 | public: |
---|
| 46 | // ----------------------------------------------------------------------- |
---|
| 47 | // Constructors are hidden, just the virtual destructor is exposed |
---|
| 48 | // ----------------------------------------------------------------------- |
---|
| 49 | /** @name Destructor */ |
---|
| 50 | //@{ |
---|
| 51 | virtual ~XMLDocumentHandler() |
---|
| 52 | { |
---|
| 53 | } |
---|
| 54 | //@} |
---|
| 55 | |
---|
| 56 | /** @name The document handler interface */ |
---|
| 57 | //@{ |
---|
| 58 | /** Receive notification of character data. |
---|
| 59 | * |
---|
| 60 | * <p>The scanner will call this method to report each chunk of |
---|
| 61 | * character data. The scanner may return all contiguous character |
---|
| 62 | * data in a single chunk, or they may split it into several |
---|
| 63 | * chunks; however, all of the characters in any single event |
---|
| 64 | * will come from the same external entity, so that the Locator |
---|
| 65 | * provides useful information.</p> |
---|
| 66 | * |
---|
| 67 | * <p>The parser must not attempt to read from the array |
---|
| 68 | * outside of the specified range.</p> |
---|
| 69 | * |
---|
| 70 | * @param chars The content (characters) between markup from the XML |
---|
| 71 | * document. |
---|
| 72 | * @param length The number of characters to read from the array. |
---|
| 73 | * @param cdataSection Indicates that this data is inside a CDATA |
---|
| 74 | * section. |
---|
| 75 | * @see #ignorableWhitespace |
---|
| 76 | * @see Locator |
---|
| 77 | */ |
---|
| 78 | virtual void docCharacters |
---|
| 79 | ( |
---|
| 80 | const XMLCh* const chars |
---|
| 81 | , const unsigned int length |
---|
| 82 | , const bool cdataSection |
---|
| 83 | ) = 0; |
---|
| 84 | |
---|
| 85 | /** Receive notification of comments in the XML content being parsed. |
---|
| 86 | * |
---|
| 87 | * This scanner will call this method for any comments found in the |
---|
| 88 | * content of the document. |
---|
| 89 | * |
---|
| 90 | * @param comment The text of the comment. |
---|
| 91 | */ |
---|
| 92 | virtual void docComment |
---|
| 93 | ( |
---|
| 94 | const XMLCh* const comment |
---|
| 95 | ) = 0; |
---|
| 96 | |
---|
| 97 | /** Receive notification of PI's parsed in the XML content. |
---|
| 98 | * |
---|
| 99 | * The scanner will call this method for any PIs it finds within the |
---|
| 100 | * content of the document. |
---|
| 101 | * |
---|
| 102 | * @param target The name of the PI. |
---|
| 103 | * @param data The body of the PI. This may be an empty string since |
---|
| 104 | * the body is optional. |
---|
| 105 | */ |
---|
| 106 | virtual void docPI |
---|
| 107 | ( |
---|
| 108 | const XMLCh* const target |
---|
| 109 | , const XMLCh* const data |
---|
| 110 | ) = 0; |
---|
| 111 | |
---|
| 112 | /** Receive notification after the scanner has parsed the end of the |
---|
| 113 | * document. |
---|
| 114 | * |
---|
| 115 | * The scanner will call this method when the current document has been |
---|
| 116 | * fully parsed. The handler may use this opportunity to do something with |
---|
| 117 | * the data, clean up temporary data, etc... |
---|
| 118 | */ |
---|
| 119 | virtual void endDocument() = 0; |
---|
| 120 | |
---|
| 121 | /** Receive notification of the end of an element. |
---|
| 122 | * |
---|
| 123 | * This method is called when scanner encounters the end of element tag. |
---|
| 124 | * There will be a corresponding startElement() event for every |
---|
| 125 | * endElement() event, but not necessarily the other way around. For |
---|
| 126 | * empty tags, there is only a startElement() call. |
---|
| 127 | * |
---|
| 128 | * @param elemDecl The name of the element whose end tag was just |
---|
| 129 | * parsed. |
---|
| 130 | * @param uriId The ID of the URI in the URI pool (only valid if |
---|
| 131 | * name spaces is enabled) |
---|
| 132 | * @param isRoot Indicates if this is the root element. |
---|
| 133 | * @param prefixName The string representing the prefix name |
---|
| 134 | */ |
---|
| 135 | virtual void endElement |
---|
| 136 | ( |
---|
| 137 | const XMLElementDecl& elemDecl |
---|
| 138 | , const unsigned int uriId |
---|
| 139 | , const bool isRoot |
---|
| 140 | , const XMLCh* const prefixName = 0 |
---|
| 141 | ) = 0; |
---|
| 142 | |
---|
| 143 | /** Receive notification when a referenced entity's content ends |
---|
| 144 | * |
---|
| 145 | * This method is called when scanner encounters the end of an entity |
---|
| 146 | * reference. |
---|
| 147 | * |
---|
| 148 | * @param entDecl The name of the entity reference just scanned. |
---|
| 149 | */ |
---|
| 150 | virtual void endEntityReference |
---|
| 151 | ( |
---|
| 152 | const XMLEntityDecl& entDecl |
---|
| 153 | ) = 0; |
---|
| 154 | |
---|
| 155 | /** Receive notification of ignorable whitespace in element content. |
---|
| 156 | * |
---|
| 157 | * <p>Validating Parsers must use this method to report each chunk |
---|
| 158 | * of ignorable whitespace (see the W3C XML 1.0 recommendation, |
---|
| 159 | * section 2.10): non-validating parsers may also use this method |
---|
| 160 | * if they are capable of parsing and using content models.</p> |
---|
| 161 | * |
---|
| 162 | * <p>The scanner may return all contiguous whitespace in a single |
---|
| 163 | * chunk, or it may split it into several chunks; however, all of |
---|
| 164 | * the characters in any single event will come from the same |
---|
| 165 | * external entity, so that the Locator provides useful |
---|
| 166 | * information.</p> |
---|
| 167 | * |
---|
| 168 | * <p>The parser must not attempt to read from the array |
---|
| 169 | * outside of the specified range.</p> |
---|
| 170 | * |
---|
| 171 | * @param chars The whitespace characters from the XML document. |
---|
| 172 | * @param length The number of characters to read from the array. |
---|
| 173 | * @param cdataSection Indicates that this data is inside a CDATA |
---|
| 174 | * section. |
---|
| 175 | * @see #characters |
---|
| 176 | */ |
---|
| 177 | virtual void ignorableWhitespace |
---|
| 178 | ( |
---|
| 179 | const XMLCh* const chars |
---|
| 180 | , const unsigned int length |
---|
| 181 | , const bool cdataSection |
---|
| 182 | ) = 0; |
---|
| 183 | |
---|
| 184 | /** Reset the document handler's state, if required |
---|
| 185 | * |
---|
| 186 | * This method is used to give the registered document handler a |
---|
| 187 | * chance to reset itself. Its called by the scanner at the start of |
---|
| 188 | * every parse. |
---|
| 189 | */ |
---|
| 190 | virtual void resetDocument() = 0; |
---|
| 191 | |
---|
| 192 | /** Receive notification of the start of a new document |
---|
| 193 | * |
---|
| 194 | * This method is the first callback called the scanner at the |
---|
| 195 | * start of every parse. This is before any content is parsed. |
---|
| 196 | */ |
---|
| 197 | virtual void startDocument() = 0; |
---|
| 198 | |
---|
| 199 | /** Receive notification of a new start tag |
---|
| 200 | * |
---|
| 201 | * This method is called when scanner encounters the start of an element tag. |
---|
| 202 | * All elements must always have a startElement() tag. Empty tags will |
---|
| 203 | * only have the startElement() tag and no endElement() tag. |
---|
| 204 | * |
---|
| 205 | * @param elemDecl The name of the element whose start tag was just |
---|
| 206 | * parsed. |
---|
| 207 | * @param uriId The ID of the URI in the URI pool (only valid if |
---|
| 208 | * name spaces is enabled) |
---|
| 209 | * @param prefixName The string representing the prefix name |
---|
| 210 | * @param attrList List of attributes in the element |
---|
| 211 | * @param attrCount Count of the attributes in the element |
---|
| 212 | * @param isEmpty Indicates if the element is empty, in which case |
---|
| 213 | * you should not expect an endElement() event. |
---|
| 214 | * @param isRoot Indicates if this is the root element. |
---|
| 215 | */ |
---|
| 216 | virtual void startElement |
---|
| 217 | ( |
---|
| 218 | const XMLElementDecl& elemDecl |
---|
| 219 | , const unsigned int uriId |
---|
| 220 | , const XMLCh* const prefixName |
---|
| 221 | , const RefVectorOf<XMLAttr>& attrList |
---|
| 222 | , const unsigned int attrCount |
---|
| 223 | , const bool isEmpty |
---|
| 224 | , const bool isRoot |
---|
| 225 | ) = 0; |
---|
| 226 | |
---|
| 227 | /** Receive notification when the scanner hits an entity reference. |
---|
| 228 | * |
---|
| 229 | * This is currently useful only to DOM parser configurations as SAX |
---|
| 230 | * does not provide any api to return this information. |
---|
| 231 | * |
---|
| 232 | * @param entDecl The name of the entity that was referenced. |
---|
| 233 | */ |
---|
| 234 | virtual void startEntityReference(const XMLEntityDecl& entDecl) = 0; |
---|
| 235 | |
---|
| 236 | /** Receive notification of an XML declaration |
---|
| 237 | * |
---|
| 238 | * Currently neither DOM nor SAX provide API's to return back this |
---|
| 239 | * information. |
---|
| 240 | * |
---|
| 241 | * @param versionStr The value of the <code>version</code> pseudoattribute |
---|
| 242 | * of the XML decl. |
---|
| 243 | * @param encodingStr The value of the <code>encoding</code> pseudoattribute |
---|
| 244 | * of the XML decl. |
---|
| 245 | * @param standaloneStr The value of the <code>standalone</code> |
---|
| 246 | * pseudoattribute of the XML decl. |
---|
| 247 | * @param autoEncodingStr The encoding string auto-detected by the |
---|
| 248 | * scanner. In absence of any 'encoding' attribute in the |
---|
| 249 | * XML decl, the XML standard specifies how a parser can |
---|
| 250 | * auto-detect. If there is no <code>encodingStr</code> |
---|
| 251 | * this is what will be used to try to decode the file. |
---|
| 252 | */ |
---|
| 253 | virtual void XMLDecl |
---|
| 254 | ( |
---|
| 255 | const XMLCh* const versionStr |
---|
| 256 | , const XMLCh* const encodingStr |
---|
| 257 | , const XMLCh* const standaloneStr |
---|
| 258 | , const XMLCh* const autoEncodingStr |
---|
| 259 | ) = 0; |
---|
| 260 | |
---|
| 261 | /** Receive notification of the name and namespace of the type that validated |
---|
| 262 | * the element corresponding to the most recent endElement event. |
---|
| 263 | * This event will be fired immediately after the |
---|
| 264 | * endElement() event that signifies the end of the element |
---|
| 265 | * to which it applies; no other events will intervene. |
---|
| 266 | * This method is <em>EXPERIMENTAL</em> and may change, disappear |
---|
| 267 | * or become pure virtual at any time. |
---|
| 268 | * |
---|
| 269 | * This corresponds to a part of the information required by DOM Core |
---|
| 270 | * level 3's TypeInfo interface. |
---|
| 271 | * |
---|
| 272 | * @param typeName local name of the type that actually validated |
---|
| 273 | * the content of the element corresponding to the |
---|
| 274 | * most recent endElement() callback |
---|
| 275 | * @param typeURI namespace of the type that actually validated |
---|
| 276 | * the content of the element corresponding to the |
---|
| 277 | * most recent endElement() callback |
---|
| 278 | * @deprecated |
---|
| 279 | */ |
---|
| 280 | virtual void elementTypeInfo |
---|
| 281 | ( |
---|
| 282 | const XMLCh* const /* typeName */ |
---|
| 283 | , const XMLCh* const /* typeURI */ |
---|
| 284 | ) { /* non pure virtual to permit backward compatibility of implementations. */ }; |
---|
| 285 | //@} |
---|
| 286 | |
---|
| 287 | |
---|
| 288 | |
---|
| 289 | protected : |
---|
| 290 | // ----------------------------------------------------------------------- |
---|
| 291 | // Hidden Constructors |
---|
| 292 | // ----------------------------------------------------------------------- |
---|
| 293 | XMLDocumentHandler() |
---|
| 294 | { |
---|
| 295 | } |
---|
| 296 | |
---|
| 297 | |
---|
| 298 | private: |
---|
| 299 | // ----------------------------------------------------------------------- |
---|
| 300 | // Unimplemented constructors and operators |
---|
| 301 | // ----------------------------------------------------------------------- |
---|
| 302 | XMLDocumentHandler(const XMLDocumentHandler&); |
---|
| 303 | XMLDocumentHandler& operator=(const XMLDocumentHandler&); |
---|
| 304 | }; |
---|
| 305 | |
---|
| 306 | XERCES_CPP_NAMESPACE_END |
---|
| 307 | |
---|
| 308 | #endif |
---|