1 /*
2 * Copyright (c) 2003, 2020, 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 package build.tools.generatebreakiteratordata;
27
28 import java.util.Enumeration;
29 import java.util.ListResourceBundle;
30 import java.util.Locale;
31 import java.util.ResourceBundle;
32
33 /**
34 * Generates datafile for BreakIterator.
35 */
36 public class GenerateBreakIteratorData {
37
38 /**
39 * Directory where generated data files are put in.
40 */
41 private static String outputDir = "" ;
42
43 /**
44 * Unicode data file
45 */
46 private static String unicodeData = "UnicodeData.txt";
47
48 /**
49 * Locale data
50 */
51 private static String language = "";
52 private static String country = "";
53 private static String valiant = "";
54 private static String localeName = ""; /* _language_country_valiant */
55
56
57 public static void main(String[] args) {
58 /* Parse command-line options */
59 processArgs(args);
60
61 /* Make categoryMap from Unicode data */
62 CharacterCategory.makeCategoryMap(unicodeData);
63
64 /* Generate files */
65 try {
66 generateFiles();
67 } catch (Exception e) {
68 e.printStackTrace();
69 System.exit(1);
70 }
71 }
72
73 private static String localizedBundleName(String pkg, String clazz) {
74 if (language.length() > 0) {
75 return pkg + ".ext." + clazz + '_' + language;
76 } else {
77 return pkg + '.' + clazz;
78 }
79 }
80
81 /**
82 * Generate data files whose names are included in
83 * sun.text.resources.BreakIteratorInfo+<localeName>
84 */
85 private static void generateFiles() throws Exception {
86 String[] classNames;
87 ResourceBundle rules, info;
88
89 info = (ResourceBundle) Class.forName(
90 localizedBundleName("sun.text.resources", "BreakIteratorInfo")).getDeclaredConstructor().newInstance();
91
92 classNames = info.getStringArray("BreakIteratorClasses");
93
94 rules = (ResourceBundle) Class.forName(
95 localizedBundleName("sun.text.resources", "BreakIteratorRules")).getDeclaredConstructor().newInstance();
96
97 if (info.containsKey("CharacterData")) {
98 generateDataFile(info.getString("CharacterData"),
99 rules.getString("CharacterBreakRules"),
100 classNames[0]);
101 }
102 if (info.containsKey("WordData")) {
103 generateDataFile(info.getString("WordData"),
104 rules.getString("WordBreakRules"),
105 classNames[1]);
106 }
107 if (info.containsKey("LineData")) {
108 generateDataFile(info.getString("LineData"),
109 rules.getString("LineBreakRules"),
110 classNames[2]);
111 }
112 if (info.containsKey("SentenceData")) {
113 generateDataFile(info.getString("SentenceData"),
114 rules.getString("SentenceBreakRules"),
115 classNames[3]);
116 }
117 }
118
119 /**
120 * Generate a data file for break-iterator
121 */
122 private static void generateDataFile(String datafile, String rule, String builder) {
123 RuleBasedBreakIteratorBuilder bld;
124 if (builder.equals("RuleBasedBreakIterator")) {
125 bld = new RuleBasedBreakIteratorBuilder(rule);
126 } else if (builder.equals("DictionaryBasedBreakIterator")) {
127 bld = new DictionaryBasedBreakIteratorBuilder(rule);
128 } else {
129 throw new IllegalArgumentException("Invalid break iterator class \"" + builder + "\"");
130 }
131
132 bld.makeFile(datafile);
133 }
134
135 /**
136 * Parses the specified arguments and sets up the variables.
137 */
138 private static void processArgs(String[] args) {
139 for (int i = 0; i < args.length; i++) {
140 String arg = args[i];
141 if (arg.equals("-o")) {
142 outputDir = args[++i];
143 } else if (arg.equals("-spec")) {
144 unicodeData = args[++i];
145 } else if (arg.equals("-language")) {
146 language = args[++i];
147 } else if (arg.equals("-country")) {
148 country = args[++i];
149 } else if (arg.equals("-valiant")) {
150 valiant = args[++i];
151 } else {
152 usage();
153 }
154 }
155
156 // Set locale name
157 localeName = getLocaleName();
158 }
159
160 /**
161 * Make locale name ("_language_country_valiant")
162 */
163 private static String getLocaleName() {
164 if (language.equals("")) {
165 if (!country.equals("") || !valiant.equals("")) {
166 language = "en";
167 } else {
168 return "";
169 }
170 }
171
172 StringBuffer sb = new StringBuffer();
173 sb.append('_');
174 sb.append(language);
175 if (!country.equals("") || !valiant.equals("")) {
176 sb.append('_');
177 sb.append(country);
178 if (!valiant.equals("")) {
179 sb.append('_');
180 sb.append(valiant);
181 }
182 }
183
184 return sb.toString();
185 }
186
187 /**
188 * Usage: Displayed when an invalid command-line option is specified.
189 */
190 private static void usage() {
191 System.err.println("Usage: GenerateBreakIteratorData [options]\n" +
192 " -o outputDir output directory name\n" +
193 " -spec specname unicode text filename\n" +
194 " and locale data:\n" +
195 " -lang language target language name\n" +
196 " -country country target country name\n" +
197 " -valiant valiant target valiant name\n"
198 );
199 }
200
201 /**
202 * Return the path of output directory
203 */
204 static String getOutputDirectory() {
205 return outputDir;
206 }
207 }