[188] | 1 | /*
|
---|
| 2 | * The Apache Software License, Version 1.1
|
---|
| 3 | *
|
---|
| 4 | * Copyright (c) 2001 The Apache Software Foundation. All rights
|
---|
| 5 | * reserved.
|
---|
| 6 | *
|
---|
| 7 | * Redistribution and use in source and binary forms, with or without
|
---|
| 8 | * modification, are permitted provided that the following conditions
|
---|
| 9 | * are met:
|
---|
| 10 | *
|
---|
| 11 | * 1. Redistributions of source code must retain the above copyright
|
---|
| 12 | * notice, this list of conditions and the following disclaimer.
|
---|
| 13 | *
|
---|
| 14 | * 2. Redistributions in binary form must reproduce the above copyright
|
---|
| 15 | * notice, this list of conditions and the following disclaimer in
|
---|
| 16 | * the documentation and/or other materials provided with the
|
---|
| 17 | * distribution.
|
---|
| 18 | *
|
---|
| 19 | * 3. The end-user documentation included with the redistribution,
|
---|
| 20 | * if any, must include the following acknowledgment:
|
---|
| 21 | * "This product includes software developed by the
|
---|
| 22 | * Apache Software Foundation (http://www.apache.org/)."
|
---|
| 23 | * Alternately, this acknowledgment may appear in the software itself,
|
---|
| 24 | * if and wherever such third-party acknowledgments normally appear.
|
---|
| 25 | *
|
---|
| 26 | * 4. The names "Xerces" and "Apache Software Foundation" must
|
---|
| 27 | * not be used to endorse or promote products derived from this
|
---|
| 28 | * software without prior written permission. For written
|
---|
| 29 | * permission, please contact apache\@apache.org.
|
---|
| 30 | *
|
---|
| 31 | * 5. Products derived from this software may not be called "Apache",
|
---|
| 32 | * nor may "Apache" appear in their name, without prior written
|
---|
| 33 | * permission of the Apache Software Foundation.
|
---|
| 34 | *
|
---|
| 35 | * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
|
---|
| 36 | * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
---|
| 37 | * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
---|
| 38 | * DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
|
---|
| 39 | * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
---|
| 40 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
---|
| 41 | * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
|
---|
| 42 | * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
---|
| 43 | * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
---|
| 44 | * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
|
---|
| 45 | * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
---|
| 46 | * SUCH DAMAGE.
|
---|
| 47 | * ====================================================================
|
---|
| 48 | *
|
---|
| 49 | * This software consists of voluntary contributions made by many
|
---|
| 50 | * individuals on behalf of the Apache Software Foundation, and was
|
---|
| 51 | * originally based on software copyright (c) 2001, International
|
---|
| 52 | * Business Machines, Inc., http://www.ibm.com . For more information
|
---|
| 53 | * on the Apache Software Foundation, please see
|
---|
| 54 | * <http://www.apache.org/>.
|
---|
| 55 | */
|
---|
| 56 |
|
---|
| 57 | /*
|
---|
| 58 | * $Id: XMLStringTokenizer.hpp,v 1.6 2004/01/29 11:48:47 cargilld Exp $
|
---|
| 59 | */
|
---|
| 60 |
|
---|
| 61 | #if !defined(XMLSTRINGTOKENIZER_HPP)
|
---|
| 62 | #define XMLSTRINGTOKENIZER_HPP
|
---|
| 63 |
|
---|
| 64 | #include <xercesc/util/RefArrayVectorOf.hpp>
|
---|
| 65 | #include <xercesc/util/XMLString.hpp>
|
---|
| 66 |
|
---|
| 67 | XERCES_CPP_NAMESPACE_BEGIN
|
---|
| 68 |
|
---|
| 69 | /**
|
---|
| 70 | * The string tokenizer class breaks a string into tokens.
|
---|
| 71 | *
|
---|
| 72 | * The XMLStringTokenizer methods do not distinguish among identifiers,
|
---|
| 73 | * numbers, and quoted strings, nor do they recognize and skip comments
|
---|
| 74 | *
|
---|
| 75 | * A XMLStringTokenizer object internally maintains a current position within
|
---|
| 76 | * the string to be tokenized. Some operations advance this current position
|
---|
| 77 | * past the characters processed.
|
---|
| 78 | */
|
---|
| 79 |
|
---|
| 80 |
|
---|
| 81 | class XMLUTIL_EXPORT XMLStringTokenizer :public XMemory
|
---|
| 82 | {
|
---|
| 83 | public:
|
---|
| 84 | // -----------------------------------------------------------------------
|
---|
| 85 | // Public Constructors
|
---|
| 86 | // -----------------------------------------------------------------------
|
---|
| 87 | /** @name Constructors */
|
---|
| 88 | //@{
|
---|
| 89 |
|
---|
| 90 | /**
|
---|
| 91 | * Constructs a string tokenizer for the specified string. The tokenizer
|
---|
| 92 | * uses the default delimiter set, which is "\t\n\r\f": the space
|
---|
| 93 | * character, the tab character, the newline character, the
|
---|
| 94 | * carriage-return character, and the form-feed character. Delimiter
|
---|
| 95 | * characters themselves will not be treated as tokens.
|
---|
| 96 | *
|
---|
| 97 | * @param srcStr The string to be parsed.
|
---|
| 98 | * @param manager Pointer to the memory manager to be used to
|
---|
| 99 | * allocate objects.
|
---|
| 100 | *
|
---|
| 101 | */
|
---|
| 102 | XMLStringTokenizer(const XMLCh* const srcStr,
|
---|
| 103 | MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager);
|
---|
| 104 |
|
---|
| 105 | /**
|
---|
| 106 | * Constructs a string tokenizer for the specified string. The characters
|
---|
| 107 | * in the delim argument are the delimiters for separating tokens.
|
---|
| 108 | * Delimiter characters themselves will not be treated as tokens.
|
---|
| 109 | *
|
---|
| 110 | * @param srcStr The string to be parsed.
|
---|
| 111 | * @param delim The set of delimiters.
|
---|
| 112 | * @param manager Pointer to the memory manager to be used to
|
---|
| 113 | * allocate objects.
|
---|
| 114 | */
|
---|
| 115 | XMLStringTokenizer(const XMLCh* const srcStr
|
---|
| 116 | , const XMLCh* const delim
|
---|
| 117 | , MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager);
|
---|
| 118 |
|
---|
| 119 | //@}
|
---|
| 120 |
|
---|
| 121 | // -----------------------------------------------------------------------
|
---|
| 122 | // Public Destructor
|
---|
| 123 | // -----------------------------------------------------------------------
|
---|
| 124 | /** @name Destructor. */
|
---|
| 125 | //@{
|
---|
| 126 |
|
---|
| 127 | ~XMLStringTokenizer();
|
---|
| 128 |
|
---|
| 129 | //@}
|
---|
| 130 |
|
---|
| 131 | // -----------------------------------------------------------------------
|
---|
| 132 | // Management methods
|
---|
| 133 | // -----------------------------------------------------------------------
|
---|
| 134 | /** @name Management Function */
|
---|
| 135 | //@{
|
---|
| 136 |
|
---|
| 137 | /**
|
---|
| 138 | * Tests if there are more tokens available from this tokenizer's string.
|
---|
| 139 | *
|
---|
| 140 | * Returns true if and only if there is at least one token in the string
|
---|
| 141 | * after the current position; false otherwise.
|
---|
| 142 | */
|
---|
| 143 | bool hasMoreTokens();
|
---|
| 144 |
|
---|
| 145 | /**
|
---|
| 146 | * Calculates the number of times that this tokenizer's nextToken method
|
---|
| 147 | * can be called to return a valid token. The current position is not
|
---|
| 148 | * advanced.
|
---|
| 149 | *
|
---|
| 150 | * Returns the number of tokens remaining in the string using the current
|
---|
| 151 | * delimiter set.
|
---|
| 152 | */
|
---|
| 153 | int countTokens();
|
---|
| 154 |
|
---|
| 155 | /**
|
---|
| 156 | * Returns the next token from this string tokenizer.
|
---|
| 157 | *
|
---|
| 158 | * Function allocated, function managed (fafm). The calling function
|
---|
| 159 | * does not need to worry about deleting the returned pointer.
|
---|
| 160 | */
|
---|
| 161 | XMLCh* nextToken();
|
---|
| 162 |
|
---|
| 163 | //@}
|
---|
| 164 |
|
---|
| 165 | private:
|
---|
| 166 | // -----------------------------------------------------------------------
|
---|
| 167 | // Unimplemented constructors and operators
|
---|
| 168 | // -----------------------------------------------------------------------
|
---|
| 169 | XMLStringTokenizer(const XMLStringTokenizer&);
|
---|
| 170 | XMLStringTokenizer& operator=(const XMLStringTokenizer&);
|
---|
| 171 |
|
---|
| 172 | // -----------------------------------------------------------------------
|
---|
| 173 | // CleanUp methods
|
---|
| 174 | // -----------------------------------------------------------------------
|
---|
| 175 | void cleanUp();
|
---|
| 176 |
|
---|
| 177 | // -----------------------------------------------------------------------
|
---|
| 178 | // Helper methods
|
---|
| 179 | // -----------------------------------------------------------------------
|
---|
| 180 | bool isDelimeter(const XMLCh ch);
|
---|
| 181 |
|
---|
| 182 | // -----------------------------------------------------------------------
|
---|
| 183 | // Private data members
|
---|
| 184 | //
|
---|
| 185 | // fOffset
|
---|
| 186 | // The current position in the parsed string.
|
---|
| 187 | //
|
---|
| 188 | // fStringLen
|
---|
| 189 | // The length of the string parsed (for convenience).
|
---|
| 190 | //
|
---|
| 191 | // fString
|
---|
| 192 | // The string to be parsed
|
---|
| 193 | //
|
---|
| 194 | // fDelimeters
|
---|
| 195 | // A set of delimeter characters
|
---|
| 196 | //
|
---|
| 197 | // fTokens
|
---|
| 198 | // A vector of the token strings
|
---|
| 199 | // -----------------------------------------------------------------------
|
---|
| 200 | int fOffset;
|
---|
| 201 | int fStringLen;
|
---|
| 202 | XMLCh* fString;
|
---|
| 203 | XMLCh* fDelimeters;
|
---|
| 204 | RefArrayVectorOf<XMLCh>* fTokens;
|
---|
| 205 | MemoryManager* fMemoryManager;
|
---|
| 206 | };
|
---|
| 207 |
|
---|
| 208 |
|
---|
| 209 | // ---------------------------------------------------------------------------
|
---|
| 210 | // XMLStringTokenizer: CleanUp methods
|
---|
| 211 | // ---------------------------------------------------------------------------
|
---|
| 212 | inline void XMLStringTokenizer::cleanUp() {
|
---|
| 213 |
|
---|
| 214 | fMemoryManager->deallocate(fString);//delete [] fString;
|
---|
| 215 | fMemoryManager->deallocate(fDelimeters);//delete [] fDelimeters;
|
---|
| 216 | delete fTokens;
|
---|
| 217 | }
|
---|
| 218 |
|
---|
| 219 | // ---------------------------------------------------------------------------
|
---|
| 220 | // XMLStringTokenizer: Helper methods
|
---|
| 221 | // ---------------------------------------------------------------------------
|
---|
| 222 | inline bool XMLStringTokenizer::isDelimeter(const XMLCh ch) {
|
---|
| 223 |
|
---|
| 224 | return XMLString::indexOf(fDelimeters, ch) == -1 ? false : true;
|
---|
| 225 | }
|
---|
| 226 |
|
---|
| 227 |
|
---|
| 228 | // ---------------------------------------------------------------------------
|
---|
| 229 | // XMLStringTokenizer: Management methods
|
---|
| 230 | // ---------------------------------------------------------------------------
|
---|
| 231 | inline int XMLStringTokenizer::countTokens() {
|
---|
| 232 |
|
---|
| 233 | if (fStringLen == 0)
|
---|
| 234 | return 0;
|
---|
| 235 |
|
---|
| 236 | int tokCount = 0;
|
---|
| 237 | bool inToken = false;
|
---|
| 238 |
|
---|
| 239 | for (int i= fOffset; i< fStringLen; i++) {
|
---|
| 240 |
|
---|
| 241 | if (isDelimeter(fString[i])) {
|
---|
| 242 |
|
---|
| 243 | if (inToken) {
|
---|
| 244 | inToken = false;
|
---|
| 245 | }
|
---|
| 246 |
|
---|
| 247 | continue;
|
---|
| 248 | }
|
---|
| 249 |
|
---|
| 250 | if (!inToken) {
|
---|
| 251 |
|
---|
| 252 | tokCount++;
|
---|
| 253 | inToken = true;
|
---|
| 254 | }
|
---|
| 255 |
|
---|
| 256 | } // end for
|
---|
| 257 |
|
---|
| 258 | return tokCount;
|
---|
| 259 | }
|
---|
| 260 |
|
---|
| 261 | XERCES_CPP_NAMESPACE_END
|
---|
| 262 |
|
---|
| 263 | #endif
|
---|
| 264 |
|
---|
| 265 | /**
|
---|
| 266 | * End of file XMLStringTokenizer.hpp
|
---|
| 267 | */
|
---|
| 268 |
|
---|