|
1 /* |
|
2 * Copyright (c) 2009 Nokia Corporation and/or its subsidiary(-ies). |
|
3 * All rights reserved. |
|
4 * This component and the accompanying materials are made available |
|
5 * under the terms of "Eclipse Public License v1.0" |
|
6 * which accompanies this distribution, and is available |
|
7 * at the URL "http://www.eclipse.org/legal/epl-v10.html". |
|
8 * |
|
9 * Initial Contributors: |
|
10 * Nokia Corporation - initial contribution. |
|
11 * |
|
12 * Contributors: |
|
13 * |
|
14 * Description: |
|
15 * |
|
16 */ |
|
17 /* |
|
18 * Licensed to the Apache Software Foundation (ASF) under one or more |
|
19 * contributor license agreements. See the NOTICE file distributed with |
|
20 * this work for additional information regarding copyright ownership. |
|
21 * The ASF licenses this file to You under the Apache License, Version 2.0 |
|
22 * (the "License"); you may not use this file except in compliance with |
|
23 * the License. You may obtain a copy of the License at |
|
24 * |
|
25 * http://www.apache.org/licenses/LICENSE-2.0 |
|
26 * |
|
27 * Unless required by applicable law or agreed to in writing, software |
|
28 * distributed under the License is distributed on an "AS IS" BASIS, |
|
29 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
|
30 * See the License for the specific language governing permissions and |
|
31 * limitations under the License. |
|
32 */ |
|
33 |
|
34 /* |
|
35 * $Id: XMLStringTokenizer.hpp 568078 2007-08-21 11:43:25Z amassari $ |
|
36 */ |
|
37 |
|
38 #if !defined(XMLSTRINGTOKENIZER_HPP) |
|
39 #define XMLSTRINGTOKENIZER_HPP |
|
40 |
|
41 #include <xercesc/util/RefArrayVectorOf.hpp> |
|
42 #include <xercesc/util/XMLString.hpp> |
|
43 |
|
44 XERCES_CPP_NAMESPACE_BEGIN |
|
45 |
|
46 /** |
|
47 * The string tokenizer class breaks a string into tokens. |
|
48 * |
|
49 * The XMLStringTokenizer methods do not distinguish among identifiers, |
|
50 * numbers, and quoted strings, nor do they recognize and skip comments |
|
51 * |
|
52 * A XMLStringTokenizer object internally maintains a current position within |
|
53 * the string to be tokenized. Some operations advance this current position |
|
54 * past the characters processed. |
|
55 */ |
|
56 |
|
57 |
|
58 class XMLUTIL_EXPORT XMLStringTokenizer :public XMemory |
|
59 { |
|
60 public: |
|
61 // ----------------------------------------------------------------------- |
|
62 // Public Constructors |
|
63 // ----------------------------------------------------------------------- |
|
64 /** @name Constructors */ |
|
65 //@{ |
|
66 |
|
67 /** |
|
68 * Constructs a string tokenizer for the specified string. The tokenizer |
|
69 * uses the default delimiter set, which is "\t\n\r\f": the space |
|
70 * character, the tab character, the newline character, the |
|
71 * carriage-return character, and the form-feed character. Delimiter |
|
72 * characters themselves will not be treated as tokens. |
|
73 * |
|
74 * @param srcStr The string to be parsed. |
|
75 * @param manager Pointer to the memory manager to be used to |
|
76 * allocate objects. |
|
77 * |
|
78 */ |
|
79 XMLStringTokenizer(const XMLCh* const srcStr, |
|
80 MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager); |
|
81 |
|
82 /** |
|
83 * Constructs a string tokenizer for the specified string. The characters |
|
84 * in the delim argument are the delimiters for separating tokens. |
|
85 * Delimiter characters themselves will not be treated as tokens. |
|
86 * |
|
87 * @param srcStr The string to be parsed. |
|
88 * @param delim The set of delimiters. |
|
89 * @param manager Pointer to the memory manager to be used to |
|
90 * allocate objects. |
|
91 */ |
|
92 XMLStringTokenizer(const XMLCh* const srcStr |
|
93 , const XMLCh* const delim |
|
94 , MemoryManager* const manager = XMLPlatformUtils::fgMemoryManager); |
|
95 |
|
96 //@} |
|
97 |
|
98 // ----------------------------------------------------------------------- |
|
99 // Public Destructor |
|
100 // ----------------------------------------------------------------------- |
|
101 /** @name Destructor. */ |
|
102 //@{ |
|
103 |
|
104 ~XMLStringTokenizer(); |
|
105 |
|
106 //@} |
|
107 |
|
108 // ----------------------------------------------------------------------- |
|
109 // Management methods |
|
110 // ----------------------------------------------------------------------- |
|
111 /** @name Management Function */ |
|
112 //@{ |
|
113 |
|
114 /** |
|
115 * Tests if there are more tokens available from this tokenizer's string. |
|
116 * |
|
117 * Returns true if and only if there is at least one token in the string |
|
118 * after the current position; false otherwise. |
|
119 */ |
|
120 bool hasMoreTokens(); |
|
121 |
|
122 /** |
|
123 * Calculates the number of times that this tokenizer's nextToken method |
|
124 * can be called to return a valid token. The current position is not |
|
125 * advanced. |
|
126 * |
|
127 * Returns the number of tokens remaining in the string using the current |
|
128 * delimiter set. |
|
129 */ |
|
130 int countTokens(); |
|
131 |
|
132 /** |
|
133 * Returns the next token from this string tokenizer. |
|
134 * |
|
135 * Function allocated, function managed (fafm). The calling function |
|
136 * does not need to worry about deleting the returned pointer. |
|
137 */ |
|
138 XMLCh* nextToken(); |
|
139 |
|
140 //@} |
|
141 |
|
142 private: |
|
143 // ----------------------------------------------------------------------- |
|
144 // Unimplemented constructors and operators |
|
145 // ----------------------------------------------------------------------- |
|
146 XMLStringTokenizer(const XMLStringTokenizer&); |
|
147 XMLStringTokenizer& operator=(const XMLStringTokenizer&); |
|
148 |
|
149 // ----------------------------------------------------------------------- |
|
150 // CleanUp methods |
|
151 // ----------------------------------------------------------------------- |
|
152 void cleanUp(); |
|
153 |
|
154 // ----------------------------------------------------------------------- |
|
155 // Helper methods |
|
156 // ----------------------------------------------------------------------- |
|
157 bool isDelimeter(const XMLCh ch); |
|
158 |
|
159 // ----------------------------------------------------------------------- |
|
160 // Private data members |
|
161 // |
|
162 // fOffset |
|
163 // The current position in the parsed string. |
|
164 // |
|
165 // fStringLen |
|
166 // The length of the string parsed (for convenience). |
|
167 // |
|
168 // fString |
|
169 // The string to be parsed |
|
170 // |
|
171 // fDelimeters |
|
172 // A set of delimeter characters |
|
173 // |
|
174 // fTokens |
|
175 // A vector of the token strings |
|
176 // ----------------------------------------------------------------------- |
|
177 int fOffset; |
|
178 int fStringLen; |
|
179 XMLCh* fString; |
|
180 const XMLCh* fDelimeters; |
|
181 RefArrayVectorOf<XMLCh>* fTokens; |
|
182 MemoryManager* fMemoryManager; |
|
183 }; |
|
184 |
|
185 // --------------------------------------------------------------------------- |
|
186 // XMLStringTokenizer: Helper methods |
|
187 // --------------------------------------------------------------------------- |
|
188 inline bool XMLStringTokenizer::isDelimeter(const XMLCh ch) { |
|
189 |
|
190 return XMLString::indexOf(fDelimeters, ch) == -1 ? false : true; |
|
191 } |
|
192 |
|
193 |
|
194 // --------------------------------------------------------------------------- |
|
195 // XMLStringTokenizer: Management methods |
|
196 // --------------------------------------------------------------------------- |
|
197 inline int XMLStringTokenizer::countTokens() { |
|
198 |
|
199 if (fStringLen == 0) |
|
200 return 0; |
|
201 |
|
202 int tokCount = 0; |
|
203 bool inToken = false; |
|
204 |
|
205 for (int i= fOffset; i< fStringLen; i++) { |
|
206 |
|
207 if (isDelimeter(fString[i])) { |
|
208 |
|
209 if (inToken) { |
|
210 inToken = false; |
|
211 } |
|
212 |
|
213 continue; |
|
214 } |
|
215 |
|
216 if (!inToken) { |
|
217 |
|
218 tokCount++; |
|
219 inToken = true; |
|
220 } |
|
221 |
|
222 } // end for |
|
223 |
|
224 return tokCount; |
|
225 } |
|
226 |
|
227 XERCES_CPP_NAMESPACE_END |
|
228 |
|
229 #endif |
|
230 |
|
231 /** |
|
232 * End of file XMLStringTokenizer.hpp |
|
233 */ |
|
234 |