src/com/hughes/android/dictionary/engine/DictionaryBuilderMain.java

   1 // Copyright 2011 Google Inc. All Rights Reserved.
   2 //
   3 // Licensed under the Apache License, Version 2.0 (the "License");
   4 // you may not use this file except in compliance with the License.
   5 // You may obtain a copy of the License at
   6 //
   7 //     http://www.apache.org/licenses/LICENSE-2.0
   8 //
   9 // Unless required by applicable law or agreed to in writing, software
  10 // distributed under the License is distributed on an "AS IS" BASIS,
  11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  12 // See the License for the specific language governing permissions and
  13 // limitations under the License.
  14
  15 package com.hughes.android.dictionary.engine;
  16
  17 import java.io.File;
  18 import java.io.PrintWriter;
  19 import java.io.RandomAccessFile;
  20 import java.util.ArrayList;
  21 import java.util.Collections;
  22 import java.util.List;
  23
  24 import junit.framework.TestCase;
  25
  26 public class DictionaryBuilderMain extends TestCase {
  27
  28   static final String INPUTS = "../DictionaryData/inputs/";
  29   static final String STOPLISTS = "../DictionaryData/inputs/stoplists/";
  30   static final String OUTPUTS = "../DictionaryData/outputs/";
  31
  32   static class Lang {
  33     final String nameRegex;
  34     final String isoCode;
  35     final String wikiSplit;
  36     final String stoplistFile;
  37     public Lang(String nameRegex, String code, final String wikiSplit, final String stoplistFile) {
  38       this.nameRegex = nameRegex;
  39       this.isoCode = code;
  40       this.wikiSplit = wikiSplit;
  41       this.stoplistFile = stoplistFile;
  42     }
  43   }
  44
  45
  46   public static void main(final String[] args) throws Exception {
  47
  48     Lang[] langs1 = new Lang[] {
  49         new Lang("^English$", "EN", null, "en.txt"),
  50     };
  51     Lang[] langs2 = new Lang[] {
  52         //new Lang("^.*Italian.*$", "IT", "italian.data", "it.txt"),
  53         new Lang("^.*French.*$", "FR", "french.data", "empty.txt"),
  54         new Lang("^.*Spanish.*$", "ES", "spanish.data", "empty.txt"),
  55         new Lang("^.*Greek.*$", "EL", "greek.data", "empty.txt"),
  56         new Lang("^.*Japanese.*$", "JA", "japanese.data", "empty.txt"),
  57         new Lang("^.*Chinese.*$|^.*Mandarin.*$", "ZH", "mandarin.data", "empty.txt"),
  58         /*
  59         new Lang("^German$", "DE"),
  60         new Lang("^Afrikaans$", "AF"),
  61         new Lang("^Armenian$", "HY"),
  62         new Lang("^Arabic$", "AR"),
  63         new Lang("^Croation$", "HR"),
  64         new Lang("^Czech$", "CS"),
  65         new Lang("^Dutch$", "NL"),
  66         new Lang("^English$", "EN"),
  67         new Lang("^Finnish$", "FI"),
  68         new Lang("^Hebrew$", "HE"),
  69         new Lang("^Hindi$", "HI"),
  70         new Lang("^Icelandic$", "IS"),
  71         new Lang("^Irish$", "GA"),
  72         new Lang("^Korean$", "KO"),
  73         new Lang("^Kurdish$", "KU"),
  74         new Lang("^Lithuanian$", "LT"),
  75         new Lang("^Malay$", "MS"),
  76         new Lang("^Maori$", "MI"),
  77         new Lang("^Mongolian$", "MN"),
  78         new Lang("^Norwegian$", "NO"),
  79         new Lang("^Persian$", "FA"),
  80         new Lang("^Portuguese$", "PT"),
  81         new Lang("^Romanian$", "RO"),
  82         new Lang("^Russian$", "RU"),
  83         new Lang("^Sanskrit$", "SA"),
  84         new Lang("^Serbian$", "SR"),
  85         new Lang("^Somali$", "SO"),
  86         new Lang("^Sudanese$", "SU"),
  87         new Lang("^Swedish$", "SV"),
  88         new Lang("^Tajik$", "TG"),
  89         new Lang("^Thai$", "TH"),
  90         new Lang("^Tibetan$", "BO"),
  91         new Lang("^Turkish$", "TR"),
  92         new Lang("^Ukranian$", "UK"),
  93         new Lang("^Vietnamese$", "VI"),
  94         new Lang("^Welsh$", "CY"),
  95         new Lang("^Yiddish$", "YI"),
  96         new Lang("^Zulu$", "ZU"),*/
  97     };
  98
  99     for (final Lang lang1 : langs1) {
 100       for (final Lang lang2 : langs2) {
 101         if (lang1.nameRegex.equals(lang2.nameRegex)) {
 102           continue;
 103         }
 104
 105         int enIndex = -1;
 106         Lang nonEnglish = null;
 107         if (lang2.isoCode.equals("EN")) {
 108           enIndex = 2;
 109           nonEnglish = lang1;
 110         }
 111         if (lang1.isoCode.equals("EN")) {
 112           enIndex = 1;
 113           nonEnglish = lang2;
 114         }
 115         assert nonEnglish != null;
 116
 117         final String dictFile = String.format(OUTPUTS + "/%s-%s_enwiktionary.quickdic", lang1.isoCode, lang2.isoCode);
 118         System.out.println("building dictFile: " + dictFile);
 119         DictionaryBuilder.main(new String[] {
 120             String.format("--dictOut=%s", dictFile),
 121             String.format("--lang1=%s", lang1.isoCode),
 122             String.format("--lang2=%s", lang2.isoCode),
 123             String.format("--lang1Stoplist=%s", STOPLISTS + lang1.stoplistFile),
 124             String.format("--lang2Stoplist=%s", STOPLISTS + lang2.stoplistFile),
 125             String.format("--dictInfo=(EN)Wikitionary-based %s-%s dictionary", lang1.isoCode, lang2.isoCode),
 126
 127             "--input2=" + INPUTS + "enWikiSplit/" + nonEnglish.wikiSplit,
 128             "--input2Name=enwiktionary." + nonEnglish.wikiSplit,
 129             "--input2Format=enwiktionary",
 130             "--input2LangPattern=" + nonEnglish.nameRegex,
 131             "--input2LangCodePattern=" + nonEnglish.isoCode.toLowerCase(),
 132             "--input2EnIndex=" + enIndex,
 133
 134             "--input3=" + INPUTS + "enWikiSplit/english.data",
 135             "--input3Name=enwiktionary.english",
 136             "--input3Format=enwiktionary",
 137             "--input3LangPattern=" + nonEnglish.nameRegex,
 138             "--input3LangCodePattern=" + (enIndex == 1 ? lang2.isoCode : lang1.isoCode).toLowerCase(),
 139             "--input3EnIndex=" + enIndex,
 140
 141         });
 142
 143         // Print the entries for diffing.
 144         final RandomAccessFile raf = new RandomAccessFile(new File(dictFile), "r");
 145         final Dictionary dict = new Dictionary(raf);
 146         final PrintWriter textOut = new PrintWriter(new File(dictFile + ".text"));
 147         final List<PairEntry> sorted = new ArrayList<PairEntry>(dict.pairEntries);
 148         Collections.sort(sorted);
 149         for (final PairEntry pairEntry : sorted) {
 150           textOut.println(pairEntry.getRawText(false));
 151         }
 152         textOut.close();
 153         raf.close();
 154
 155       }  // langs2
 156     }  // langs1
 157
 158     DictionaryBuilder.main(new String[] {
 159         "--dictOut=" + OUTPUTS + "DE-EN_chemnitz.quickdic",
 160         "--lang1=DE",
 161         "--lang2=EN",
 162         "--dictInfo=@" + INPUTS + "de-en_chemnitz.info",
 163
 164         "--input1=" + INPUTS + "de-en_chemnitz.txt",
 165         "--input1Name=chemnitz",
 166         "--input1Charset=UTF8",
 167         "--input1Format=chemnitz",
 168     });
 169
 170     DictionaryBuilder.main(new String[] {
 171         "--dictOut=" + OUTPUTS + "de-en_all.quickdic",
 172         "--lang1=DE",
 173         "--lang2=EN",
 174         "--dictInfo=@" + INPUTS + "de-en_all.info",
 175
 176         "--input2=" + INPUTS + "de-en_chemnitz.txt",
 177         "--input2Name=dictcc",
 178         "--input2Charset=UTF8",
 179         "--input2Format=chemnitz",
 180
 181         "--input3=" + INPUTS + "/NONFREE/de-en_dictcc.txt",
 182         "--input3Name=dictcc",
 183         "--input3Charset=UTF8",
 184         "--input3Format=dictcc",
 185
 186         // TODO: wiktionary
 187     });
 188
 189   }
 190
 191 }