1 package org.apache.lucene.analysis.icu;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.text.DateFormat;
21 import java.util.Date;
22 import java.util.HashMap;
23 import java.util.Locale;
24 import java.util.TimeZone;
26 import com.ibm.icu.text.UnicodeSet;
27 import com.ibm.icu.text.UnicodeSetIterator;
28 import com.ibm.icu.util.VersionInfo;
30 /** creates a macro to augment jflex's unicode wordbreak support for > BMP */
31 public class GenerateJFlexSupplementaryMacros {
32 private static final UnicodeSet BMP = new UnicodeSet("[\u0000-\uFFFF]");
33 private static final String NL = System.getProperty("line.separator");
34 private static final DateFormat DATE_FORMAT = DateFormat.getDateTimeInstance
35 (DateFormat.FULL, DateFormat.FULL, Locale.US);
37 DATE_FORMAT.setTimeZone(TimeZone.getTimeZone("UTC"));
40 private static final String APACHE_LICENSE
42 + " * Copyright 2010 The Apache Software Foundation." + NL
44 + " * Licensed under the Apache License, Version 2.0 (the \"License\");" + NL
45 + " * you may not use this file except in compliance with the License." + NL
46 + " * You may obtain a copy of the License at" + NL
48 + " * http://www.apache.org/licenses/LICENSE-2.0" + NL
50 + " * Unless required by applicable law or agreed to in writing, software" + NL
51 + " * distributed under the License is distributed on an \"AS IS\" BASIS," + NL
52 + " * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied." + NL
53 + " * See the License for the specific language governing permissions and" + NL
54 + " * limitations under the License." + NL
58 public static void main(String args[]) throws Exception {
60 outputMacro("ALetterSupp", "[:WordBreak=ALetter:]");
61 outputMacro("FormatSupp", "[:WordBreak=Format:]");
62 outputMacro("ExtendSupp", "[:WordBreak=Extend:]");
63 outputMacro("NumericSupp", "[:WordBreak=Numeric:]");
64 outputMacro("KatakanaSupp", "[:WordBreak=Katakana:]");
65 outputMacro("MidLetterSupp", "[:WordBreak=MidLetter:]");
66 outputMacro("MidNumSupp", "[:WordBreak=MidNum:]");
67 outputMacro("MidNumLetSupp", "[:WordBreak=MidNumLet:]");
68 outputMacro("ExtendNumLetSupp", "[:WordBreak=ExtendNumLet:]");
69 outputMacro("ExtendNumLetSupp", "[:WordBreak=ExtendNumLet:]");
70 outputMacro("ComplexContextSupp", "[:LineBreak=Complex_Context:]");
71 outputMacro("HanSupp", "[:Script=Han:]");
72 outputMacro("HiraganaSupp", "[:Script=Hiragana:]");
75 static void outputHeader() {
76 System.out.print(APACHE_LICENSE);
77 System.out.print("// Generated using ICU4J " + VersionInfo.ICU_VERSION.toString() + " on ");
78 System.out.println(DATE_FORMAT.format(new Date()));
79 System.out.println("// by " + GenerateJFlexSupplementaryMacros.class.getName());
80 System.out.print(NL + NL);
83 // we have to carefully output the possibilities as compact utf-16
84 // range expressions, or jflex will OOM!
85 static void outputMacro(String name, String pattern) {
86 UnicodeSet set = new UnicodeSet(pattern);
88 System.out.println(name + " = (");
89 // if the set is empty, we have to do this or jflex will barf
91 System.out.println("\t []");
94 HashMap<Character,UnicodeSet> utf16ByLead = new HashMap<Character,UnicodeSet>();
95 for (UnicodeSetIterator it = new UnicodeSetIterator(set); it.next();) {
96 char utf16[] = Character.toChars(it.codepoint);
97 UnicodeSet trails = utf16ByLead.get(utf16[0]);
99 trails = new UnicodeSet();
100 utf16ByLead.put(utf16[0], trails);
102 trails.add(utf16[1]);
105 boolean isFirst = true;
106 for (Character c : utf16ByLead.keySet()) {
107 UnicodeSet trail = utf16ByLead.get(c);
108 System.out.print( isFirst ? "\t " : "\t| ");
110 System.out.println("([\\u" + Integer.toHexString(c) + "]" + trail.getRegexEquivalent() + ")");
112 System.out.println(")");