1 /* |
|
2 * Copyright (c) 2003, 2005, Oracle and/or its affiliates. All rights reserved. |
|
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. |
|
4 * |
|
5 * This code is free software; you can redistribute it and/or modify it |
|
6 * under the terms of the GNU General Public License version 2 only, as |
|
7 * published by the Free Software Foundation. Oracle designates this |
|
8 * particular file as subject to the "Classpath" exception as provided |
|
9 * by Oracle in the LICENSE file that accompanied this code. |
|
10 * |
|
11 * This code is distributed in the hope that it will be useful, but WITHOUT |
|
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or |
|
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License |
|
14 * version 2 for more details (a copy is included in the LICENSE file that |
|
15 * accompanied this code). |
|
16 * |
|
17 * You should have received a copy of the GNU General Public License version |
|
18 * 2 along with this work; if not, write to the Free Software Foundation, |
|
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. |
|
20 * |
|
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA |
|
22 * or visit www.oracle.com if you need additional information or have any |
|
23 * questions. |
|
24 */ |
|
25 |
|
26 /* |
|
27 ******************************************************************************* |
|
28 * (C) Copyright IBM Corp. 1996-2005 - All Rights Reserved * |
|
29 * * |
|
30 * The original version of this source code and documentation is copyrighted * |
|
31 * and owned by IBM, These materials are provided under terms of a License * |
|
32 * Agreement between IBM and Sun. This technology is protected by multiple * |
|
33 * US and International patents. This notice and attribution to IBM may not * |
|
34 * to removed. * |
|
35 ******************************************************************************* |
|
36 */ |
|
37 |
|
38 package sun.text.normalizer; |
|
39 |
|
40 import java.io.InputStream; |
|
41 import java.io.DataInputStream; |
|
42 import java.io.IOException; |
|
43 import java.util.Arrays; |
|
44 |
|
45 /** |
|
46 * Trie implementation which stores data in int, 32 bits. |
|
47 * @author synwee |
|
48 * @see com.ibm.icu.impl.Trie |
|
49 * @since release 2.1, Jan 01 2002 |
|
50 */ |
|
51 public class IntTrie extends Trie |
|
52 { |
|
53 // public constructors --------------------------------------------- |
|
54 |
|
55 /** |
|
56 * <p>Creates a new Trie with the settings for the trie data.</p> |
|
57 * <p>Unserialize the 32-bit-aligned input stream and use the data for the |
|
58 * trie.</p> |
|
59 * @param inputStream file input stream to a ICU data file, containing |
|
60 * the trie |
|
61 * @param datamanipulate object which provides methods to parse the char |
|
62 * data |
|
63 * @throws IOException thrown when data reading fails |
|
64 * @draft 2.1 |
|
65 */ |
|
66 public IntTrie(InputStream inputStream, DataManipulate datamanipulate) |
|
67 throws IOException |
|
68 { |
|
69 super(inputStream, datamanipulate); |
|
70 if (!isIntTrie()) { |
|
71 throw new IllegalArgumentException( |
|
72 "Data given does not belong to a int trie."); |
|
73 } |
|
74 } |
|
75 |
|
76 // public methods -------------------------------------------------- |
|
77 |
|
78 /** |
|
79 * Gets the value associated with the codepoint. |
|
80 * If no value is associated with the codepoint, a default value will be |
|
81 * returned. |
|
82 * @param ch codepoint |
|
83 * @return offset to data |
|
84 * @draft 2.1 |
|
85 */ |
|
86 public final int getCodePointValue(int ch) |
|
87 { |
|
88 int offset = getCodePointOffset(ch); |
|
89 return (offset >= 0) ? m_data_[offset] : m_initialValue_; |
|
90 } |
|
91 |
|
92 /** |
|
93 * Gets the value to the data which this lead surrogate character points |
|
94 * to. |
|
95 * Returned data may contain folding offset information for the next |
|
96 * trailing surrogate character. |
|
97 * This method does not guarantee correct results for trail surrogates. |
|
98 * @param ch lead surrogate character |
|
99 * @return data value |
|
100 * @draft 2.1 |
|
101 */ |
|
102 public final int getLeadValue(char ch) |
|
103 { |
|
104 return m_data_[getLeadOffset(ch)]; |
|
105 } |
|
106 |
|
107 /** |
|
108 * Get a value from a folding offset (from the value of a lead surrogate) |
|
109 * and a trail surrogate. |
|
110 * @param leadvalue the value of a lead surrogate that contains the |
|
111 * folding offset |
|
112 * @param trail surrogate |
|
113 * @return trie data value associated with the trail character |
|
114 * @draft 2.1 |
|
115 */ |
|
116 public final int getTrailValue(int leadvalue, char trail) |
|
117 { |
|
118 if (m_dataManipulate_ == null) { |
|
119 throw new NullPointerException( |
|
120 "The field DataManipulate in this Trie is null"); |
|
121 } |
|
122 int offset = m_dataManipulate_.getFoldingOffset(leadvalue); |
|
123 if (offset > 0) { |
|
124 return m_data_[getRawOffset(offset, |
|
125 (char)(trail & SURROGATE_MASK_))]; |
|
126 } |
|
127 return m_initialValue_; |
|
128 } |
|
129 |
|
130 // protected methods ----------------------------------------------- |
|
131 |
|
132 /** |
|
133 * <p>Parses the input stream and stores its trie content into a index and |
|
134 * data array</p> |
|
135 * @param inputStream data input stream containing trie data |
|
136 * @exception IOException thrown when data reading fails |
|
137 */ |
|
138 protected final void unserialize(InputStream inputStream) |
|
139 throws IOException |
|
140 { |
|
141 super.unserialize(inputStream); |
|
142 // one used for initial value |
|
143 m_data_ = new int[m_dataLength_]; |
|
144 DataInputStream input = new DataInputStream(inputStream); |
|
145 for (int i = 0; i < m_dataLength_; i ++) { |
|
146 m_data_[i] = input.readInt(); |
|
147 } |
|
148 m_initialValue_ = m_data_[0]; |
|
149 } |
|
150 |
|
151 /** |
|
152 * Gets the offset to the data which the surrogate pair points to. |
|
153 * @param lead lead surrogate |
|
154 * @param trail trailing surrogate |
|
155 * @return offset to data |
|
156 * @draft 2.1 |
|
157 */ |
|
158 protected final int getSurrogateOffset(char lead, char trail) |
|
159 { |
|
160 if (m_dataManipulate_ == null) { |
|
161 throw new NullPointerException( |
|
162 "The field DataManipulate in this Trie is null"); |
|
163 } |
|
164 // get fold position for the next trail surrogate |
|
165 int offset = m_dataManipulate_.getFoldingOffset(getLeadValue(lead)); |
|
166 |
|
167 // get the real data from the folded lead/trail units |
|
168 if (offset > 0) { |
|
169 return getRawOffset(offset, (char)(trail & SURROGATE_MASK_)); |
|
170 } |
|
171 |
|
172 // return -1 if there is an error, in this case we return the default |
|
173 // value: m_initialValue_ |
|
174 return -1; |
|
175 } |
|
176 |
|
177 /** |
|
178 * Gets the value at the argument index. |
|
179 * For use internally in TrieIterator |
|
180 * @param index value at index will be retrieved |
|
181 * @return 32 bit value |
|
182 * @see com.ibm.icu.impl.TrieIterator |
|
183 * @draft 2.1 |
|
184 */ |
|
185 protected final int getValue(int index) |
|
186 { |
|
187 return m_data_[index]; |
|
188 } |
|
189 |
|
190 /** |
|
191 * Gets the default initial value |
|
192 * @return 32 bit value |
|
193 * @draft 2.1 |
|
194 */ |
|
195 protected final int getInitialValue() |
|
196 { |
|
197 return m_initialValue_; |
|
198 } |
|
199 |
|
200 // package private methods ----------------------------------------- |
|
201 |
|
202 /** |
|
203 * Internal constructor for builder use |
|
204 * @param index the index array to be slotted into this trie |
|
205 * @param data the data array to be slotted into this trie |
|
206 * @param initialvalue the initial value for this trie |
|
207 * @param options trie options to use |
|
208 * @param datamanipulate folding implementation |
|
209 */ |
|
210 IntTrie(char index[], int data[], int initialvalue, int options, |
|
211 DataManipulate datamanipulate) |
|
212 { |
|
213 super(index, options, datamanipulate); |
|
214 m_data_ = data; |
|
215 m_dataLength_ = m_data_.length; |
|
216 m_initialValue_ = initialvalue; |
|
217 } |
|
218 |
|
219 // private data members -------------------------------------------- |
|
220 |
|
221 /** |
|
222 * Default value |
|
223 */ |
|
224 private int m_initialValue_; |
|
225 /** |
|
226 * Array of char data |
|
227 */ |
|
228 private int m_data_[]; |
|
229 } |
|