• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1 /*
2  * Copyright (c) 1996, 2000, 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  * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved
28  * (C) Copyright IBM Corp. 1996, 1997 - All Rights Reserved
29  *
30  *   The original version of this source code and documentation is copyrighted
31  * and owned by Taligent, Inc., a wholly-owned subsidiary of IBM. These
32  * materials are provided under terms of a License Agreement between Taligent
33  * and Sun. This technology is protected by multiple US and International
34  * patents. This notice and attribution to Taligent may not be removed.
35  *   Taligent is a registered trademark of Taligent, Inc.
36  *
37  */
38 
39 package java.text;
40 
41 import java.lang.Character;
42 
43 /**
44  * Utility class for normalizing and merging patterns for collation.
45  * This is to be used with MergeCollation for adding patterns to an
46  * existing rule table.
47  * @see        MergeCollation
48  * @author     Mark Davis, Helena Shih
49  */
50 
51 class PatternEntry {
52     /**
53      * Gets the current extension, quoted
54      */
appendQuotedExtension(StringBuffer toAddTo)55     public void appendQuotedExtension(StringBuffer toAddTo) {
56         appendQuoted(extension,toAddTo);
57     }
58 
59     /**
60      * Gets the current chars, quoted
61      */
appendQuotedChars(StringBuffer toAddTo)62     public void appendQuotedChars(StringBuffer toAddTo) {
63         appendQuoted(chars,toAddTo);
64     }
65 
66     /**
67      * WARNING this is used for searching in a Vector.
68      * Because Vector.indexOf doesn't take a comparator,
69      * this method is ill-defined and ignores strength.
70      */
equals(Object obj)71     public boolean equals(Object obj) {
72         if (obj == null) return false;
73         PatternEntry other = (PatternEntry) obj;
74         boolean result = chars.equals(other.chars);
75         return result;
76     }
77 
hashCode()78     public int hashCode() {
79         return chars.hashCode();
80     }
81 
82     /**
83      * For debugging.
84      */
toString()85     public String toString() {
86         StringBuffer result = new StringBuffer();
87         addToBuffer(result, true, false, null);
88         return result.toString();
89     }
90 
91     /**
92      * Gets the strength of the entry.
93      */
getStrength()94     final int getStrength() {
95         return strength;
96     }
97 
98     /**
99      * Gets the expanding characters of the entry.
100      */
getExtension()101     final String getExtension() {
102         return extension;
103     }
104 
105     /**
106      * Gets the core characters of the entry.
107      */
getChars()108     final String getChars() {
109         return chars;
110     }
111 
112     // ===== privates =====
113 
addToBuffer(StringBuffer toAddTo, boolean showExtension, boolean showWhiteSpace, PatternEntry lastEntry)114     void addToBuffer(StringBuffer toAddTo,
115                      boolean showExtension,
116                      boolean showWhiteSpace,
117                      PatternEntry lastEntry)
118     {
119         if (showWhiteSpace && toAddTo.length() > 0)
120             if (strength == Collator.PRIMARY || lastEntry != null)
121                 toAddTo.append('\n');
122             else
123                 toAddTo.append(' ');
124         if (lastEntry != null) {
125             toAddTo.append('&');
126             if (showWhiteSpace)
127                 toAddTo.append(' ');
128             lastEntry.appendQuotedChars(toAddTo);
129             appendQuotedExtension(toAddTo);
130             if (showWhiteSpace)
131                 toAddTo.append(' ');
132         }
133         var c = switch (strength) {
134             case Collator.IDENTICAL -> '=';
135             case Collator.TERTIARY  -> ',';
136             case Collator.SECONDARY -> ';';
137             case Collator.PRIMARY   -> '<';
138             case RESET              -> '&';
139             case UNSET              -> '?';
140 
141             default -> throw new IllegalStateException("Unexpected value: " + strength);
142         };
143         toAddTo.append(c);
144 
145         if (showWhiteSpace)
146             toAddTo.append(' ');
147         appendQuoted(chars,toAddTo);
148         if (showExtension && !extension.isEmpty()) {
149             toAddTo.append('/');
150             appendQuoted(extension,toAddTo);
151         }
152     }
153 
appendQuoted(String chars, StringBuffer toAddTo)154     static void appendQuoted(String chars, StringBuffer toAddTo) {
155         boolean inQuote = false;
156         char ch = chars.charAt(0);
157         if (Character.isSpaceChar(ch)) {
158             inQuote = true;
159             toAddTo.append('\'');
160         } else {
161           if (PatternEntry.isSpecialChar(ch)) {
162                 inQuote = true;
163                 toAddTo.append('\'');
164             } else {
165                 switch (ch) {
166                     case 0x0010: case '\f': case '\r':
167                     case '\t': case '\n':  case '@':
168                     inQuote = true;
169                     toAddTo.append('\'');
170                     break;
171                 case '\'':
172                     inQuote = true;
173                     toAddTo.append('\'');
174                     break;
175                 default:
176                     if (inQuote) {
177                         inQuote = false; toAddTo.append('\'');
178                     }
179                     break;
180                 }
181            }
182         }
183         toAddTo.append(chars);
184         if (inQuote)
185             toAddTo.append('\'');
186     }
187 
188     //========================================================================
189     // Parsing a pattern into a list of PatternEntries....
190     //========================================================================
191 
PatternEntry(int strength, StringBuffer chars, StringBuffer extension)192     PatternEntry(int strength,
193                  StringBuffer chars,
194                  StringBuffer extension)
195     {
196         this.strength = strength;
197         this.chars = chars.toString();
198         this.extension = (extension.length() > 0) ? extension.toString()
199                                                   : "";
200     }
201 
202     static class Parser {
203         private String pattern;
204         private int i;
205 
Parser(String pattern)206         public Parser(String pattern) {
207             this.pattern = pattern;
208             this.i = 0;
209         }
210 
next()211         public PatternEntry next() throws ParseException {
212             int newStrength = UNSET;
213 
214             newChars.setLength(0);
215             newExtension.setLength(0);
216 
217             boolean inChars = true;
218             boolean inQuote = false;
219         mainLoop:
220             while (i < pattern.length()) {
221                 char ch = pattern.charAt(i);
222                 if (inQuote) {
223                     if (ch == '\'') {
224                         inQuote = false;
225                     } else {
226                         if (newChars.length() == 0) newChars.append(ch);
227                         else if (inChars) newChars.append(ch);
228                         else newExtension.append(ch);
229                     }
230                 } else switch (ch) {
231                 case '=': if (newStrength != UNSET) break mainLoop;
232                     newStrength = Collator.IDENTICAL; break;
233                 case ',': if (newStrength != UNSET) break mainLoop;
234                     newStrength = Collator.TERTIARY; break;
235                 case ';': if (newStrength != UNSET) break mainLoop;
236                     newStrength = Collator.SECONDARY; break;
237                 case '<': if (newStrength != UNSET) break mainLoop;
238                     newStrength = Collator.PRIMARY; break;
239                 case '&': if (newStrength != UNSET) break mainLoop;
240                     newStrength = RESET; break;
241                 case '\t':
242                 case '\n':
243                 case '\f':
244                 case '\r':
245                 case ' ': break; // skip whitespace TODO use Character
246                 case '/': inChars = false; break;
247                 case '\'':
248                     inQuote = true;
249                     ch = pattern.charAt(++i);
250                     if (newChars.length() == 0) newChars.append(ch);
251                     else if (inChars) newChars.append(ch);
252                     else newExtension.append(ch);
253                     break;
254                 default:
255                     if (newStrength == UNSET) {
256                         throw new ParseException
257                             ("missing char (=,;<&) : " +
258                              pattern.substring(i,
259                                 (i+10 < pattern.length()) ?
260                                  i+10 : pattern.length()),
261                              i);
262                     }
263                     if (PatternEntry.isSpecialChar(ch) && (inQuote == false))
264                         throw new ParseException
265                             ("Unquoted punctuation character : " + Integer.toString(ch, 16), i);
266                     if (inChars) {
267                         newChars.append(ch);
268                     } else {
269                         newExtension.append(ch);
270                     }
271                     break;
272                 }
273                 i++;
274             }
275             if (newStrength == UNSET)
276                 return null;
277             if (newChars.length() == 0) {
278                 throw new ParseException
279                     ("missing chars (=,;<&): " +
280                       pattern.substring(i,
281                           (i+10 < pattern.length()) ?
282                            i+10 : pattern.length()),
283                      i);
284             }
285 
286             return new PatternEntry(newStrength, newChars, newExtension);
287         }
288 
289         // We re-use these objects in order to improve performance
290         private StringBuffer newChars = new StringBuffer();
291         private StringBuffer newExtension = new StringBuffer();
292 
293     }
294 
isSpecialChar(char ch)295     static boolean isSpecialChar(char ch) {
296         return ((ch == '\u0020') ||
297                 ((ch <= '\u002F') && (ch >= '\u0022')) ||
298                 ((ch <= '\u003F') && (ch >= '\u003A')) ||
299                 ((ch <= '\u0060') && (ch >= '\u005B')) ||
300                 ((ch <= '\u007E') && (ch >= '\u007B')));
301     }
302 
303 
304     static final int RESET = -2;
305     static final int UNSET = -1;
306 
307     int strength = UNSET;
308     String chars = "";
309     String extension = "";
310 }
311