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

   1 // Copyright 2011 Google Inc. All Rights Reserved.\r
   2 //\r
   3 // Licensed under the Apache License, Version 2.0 (the "License");\r
   4 // you may not use this file except in compliance with the License.\r
   5 // You may obtain a copy of the License at\r
   6 //\r
   7 //     http://www.apache.org/licenses/LICENSE-2.0\r
   8 //\r
   9 // Unless required by applicable law or agreed to in writing, software\r
  10 // distributed under the License is distributed on an "AS IS" BASIS,\r
  11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\r
  12 // See the License for the specific language governing permissions and\r
  13 // limitations under the License.\r
  14 \r
  15 package com.hughes.android.dictionary.engine;\r
  16 \r
  17 import com.hughes.android.dictionary.R;\r
  18 import com.ibm.icu.text.Collator;\r
  19 \r
  20 import java.util.ArrayList;\r
  21 import java.util.LinkedHashMap;\r
  22 import java.util.Locale;\r
  23 import java.util.Map;\r
  24 import java.util.regex.Pattern;\r
  25 \r
  26 public class Language {\r
  27   \r
  28   public static final class LanguageResources {\r
  29     public final String englishName;\r
  30     public final int nameId;\r
  31     public final int flagId;\r
  32     \r
  33     private LanguageResources(final String englishName, int nameId, int flagId) {\r
  34       this.englishName = englishName;\r
  35       this.nameId = nameId;\r
  36       this.flagId = flagId;\r
  37     }\r
  38 \r
  39     private LanguageResources(final String englishName, int nameId) {\r
  40       this(englishName, nameId, 0);\r
  41     }\r
  42   }\r
  43 \r
  44   // Useful:\r
  45   // http://www.loc.gov/standards/iso639-2/php/code_list.php\r
  46   public static final Map<String,LanguageResources> isoCodeToResources = new LinkedHashMap<String,LanguageResources>();\r
  47   static {\r
  48     isoCodeToResources.put("AF", new LanguageResources("Afrikaans", R.string.AF));\r
  49     isoCodeToResources.put("SQ", new LanguageResources("Albanian", R.string.SQ));\r
  50     isoCodeToResources.put("AR", new LanguageResources("Arabic", R.string.AR));\r
  51     isoCodeToResources.put("HY", new LanguageResources("Armenian", R.string.HY));\r
  52     isoCodeToResources.put("BE", new LanguageResources("Belarusian", R.string.BE));\r
  53     isoCodeToResources.put("BN", new LanguageResources("Bengali", R.string.BN));\r
  54     isoCodeToResources.put("BS", new LanguageResources("Bosnian", R.string.BS));\r
  55     isoCodeToResources.put("BG", new LanguageResources("Bulgarian", R.string.BG));\r
  56     isoCodeToResources.put("MY", new LanguageResources("Burmese", R.string.MY));\r
  57     isoCodeToResources.put("ZH", new LanguageResources("Chinese", R.string.ZH));\r
  58     isoCodeToResources.put("cmn", new LanguageResources("Mandarin", R.string.cmn));\r
  59     isoCodeToResources.put("yue", new LanguageResources("Cantonese", R.string.yue));\r
  60     isoCodeToResources.put("CA", new LanguageResources("Catalan", R.string.CA));\r
  61     isoCodeToResources.put("HR", new LanguageResources("Croatian", R.string.HR));\r
  62     isoCodeToResources.put("CS", new LanguageResources("Czech", R.string.CS));\r
  63     isoCodeToResources.put("DA", new LanguageResources("Danish", R.string.DA));\r
  64     isoCodeToResources.put("NL", new LanguageResources("Dutch", R.string.NL));\r
  65     isoCodeToResources.put("EN", new LanguageResources("English", R.string.EN));\r
  66     isoCodeToResources.put("EO", new LanguageResources("Esperanto", R.string.EO));\r
  67     isoCodeToResources.put("ET", new LanguageResources("Estonian", R.string.ET));\r
  68     isoCodeToResources.put("FI", new LanguageResources("Finnish", R.string.FI));\r
  69     isoCodeToResources.put("FR", new LanguageResources("French", R.string.FR));\r
  70     isoCodeToResources.put("DE", new LanguageResources("German", R.string.DE));\r
  71     isoCodeToResources.put("EL", new LanguageResources("Greek", R.string.EL));\r
  72     isoCodeToResources.put("grc", new LanguageResources("Ancient Greek", R.string.grc));\r
  73     isoCodeToResources.put("haw", new LanguageResources("Hawaiian", R.string.haw));\r
  74     isoCodeToResources.put("HE", new LanguageResources("Hebrew", R.string.HE));\r
  75     isoCodeToResources.put("HI", new LanguageResources("Hindi", R.string.HI));\r
  76     isoCodeToResources.put("HU", new LanguageResources("Hungarian", R.string.HU));\r
  77     isoCodeToResources.put("IS", new LanguageResources("Icelandic", R.string.IS));\r
  78     isoCodeToResources.put("ID", new LanguageResources("Indonesian", R.string.ID));\r
  79     isoCodeToResources.put("GA", new LanguageResources("Irish", R.string.GA));\r
  80     isoCodeToResources.put("GD", new LanguageResources("Scottish Gaelic", R.string.GD));\r
  81     isoCodeToResources.put("IT", new LanguageResources("Italian", R.string.IT));\r
  82     isoCodeToResources.put("LA", new LanguageResources("Latin", R.string.LA));\r
  83     isoCodeToResources.put("LV", new LanguageResources("Latvian", R.string.LV));\r
  84     isoCodeToResources.put("LT", new LanguageResources("Lithuanian", R.string.LT));\r
  85     isoCodeToResources.put("JA", new LanguageResources("Japanese", R.string.JA));\r
  86     isoCodeToResources.put("KO", new LanguageResources("Korean", R.string.KO));\r
  87     isoCodeToResources.put("KU", new LanguageResources("Kurdish", R.string.KU));\r
  88     isoCodeToResources.put("MS", new LanguageResources("Malay", R.string.MS));\r
  89     isoCodeToResources.put("MI", new LanguageResources("Maori", R.string.MI));\r
  90     isoCodeToResources.put("MN", new LanguageResources("Mongolian", R.string.MN));\r
  91     isoCodeToResources.put("NE", new LanguageResources("Nepali", R.string.NE));\r
  92     isoCodeToResources.put("NO", new LanguageResources("Norwegian", R.string.NO));\r
  93     isoCodeToResources.put("FA", new LanguageResources("Persian", R.string.FA));\r
  94     isoCodeToResources.put("PL", new LanguageResources("Polish", R.string.PL));\r
  95     isoCodeToResources.put("PT", new LanguageResources("Portuguese", R.string.PT));\r
  96     isoCodeToResources.put("PA", new LanguageResources("Punjabi", R.string.PA));\r
  97     isoCodeToResources.put("RO", new LanguageResources("Romanian", R.string.RO));\r
  98     isoCodeToResources.put("RU", new LanguageResources("Russian", R.string.RU));\r
  99     isoCodeToResources.put("SA", new LanguageResources("Sanskrit", R.string.SA));\r
 100     isoCodeToResources.put("SR", new LanguageResources("Serbian", R.string.SR));\r
 101     isoCodeToResources.put("SK", new LanguageResources("Slovak", R.string.SK));\r
 102     isoCodeToResources.put("SL", new LanguageResources("Slovenian", R.string.SL));\r
 103     isoCodeToResources.put("SO", new LanguageResources("Somali", R.string.SO));\r
 104     isoCodeToResources.put("ES", new LanguageResources("Spanish", R.string.ES));\r
 105     isoCodeToResources.put("SW", new LanguageResources("Swahili", R.string.SW));\r
 106     isoCodeToResources.put("SV", new LanguageResources("Swedish", R.string.SV));\r
 107     isoCodeToResources.put("TL", new LanguageResources("Tagalog", R.string.TL));\r
 108     isoCodeToResources.put("TG", new LanguageResources("Tajik", R.string.TG));\r
 109     isoCodeToResources.put("TH", new LanguageResources("Thai", R.string.TH));\r
 110     isoCodeToResources.put("BO", new LanguageResources("Tibetan", R.string.BO));\r
 111     isoCodeToResources.put("TR", new LanguageResources("Turkish", R.string.TR));\r
 112     isoCodeToResources.put("UK", new LanguageResources("Ukrainian", R.string.UK));\r
 113     isoCodeToResources.put("UR", new LanguageResources("Urdu", R.string.UR));\r
 114     isoCodeToResources.put("VI", new LanguageResources("Vietnamese", R.string.VI));\r
 115     isoCodeToResources.put("CI", new LanguageResources("Welsh", R.string.CI));\r
 116     isoCodeToResources.put("YI", new LanguageResources("Yiddish", R.string.YI));\r
 117     isoCodeToResources.put("ZU", new LanguageResources("Zulu", R.string.ZU));\r
 118     isoCodeToResources.put("AZ", new LanguageResources("Azeri", R.string.AZ));\r
 119     isoCodeToResources.put("EU", new LanguageResources("Basque", R.string.EU));\r
 120     isoCodeToResources.put("BR", new LanguageResources("Breton", R.string.BR));\r
 121     isoCodeToResources.put("MR", new LanguageResources("Burmese", R.string.MR));\r
 122     isoCodeToResources.put("FO", new LanguageResources("Faroese", R.string.FO));\r
 123     isoCodeToResources.put("GL", new LanguageResources("Galician", R.string.GL));\r
 124     isoCodeToResources.put("KA", new LanguageResources("Georgian", R.string.KA));\r
 125     isoCodeToResources.put("HT", new LanguageResources("Haitian Creole", R.string.HT));\r
 126     isoCodeToResources.put("LB", new LanguageResources("Luxembourgish", R.string.LB));\r
 127     isoCodeToResources.put("MK", new LanguageResources("Macedonian", R.string.MK));\r
 128     isoCodeToResources.put("LO", new LanguageResources("Lao", R.string.LO));\r
 129     isoCodeToResources.put("ML", new LanguageResources("Malayalam", R.string.ML));\r
 130     isoCodeToResources.put("SL", new LanguageResources("Slovenian", R.string.SL));\r
 131     isoCodeToResources.put("TA", new LanguageResources("Tamil", R.string.TA));\r
 132     isoCodeToResources.put("SH", new LanguageResources("Serbo-Croations", R.string.SH));\r
 133 \r
 134     // Hack to allow lower-case ISO codes to work:\r
 135     for (final String isoCode : new ArrayList<String>(isoCodeToResources.keySet())) {\r
 136       isoCodeToResources.put(isoCode.toLowerCase(), isoCodeToResources.get(isoCode));\r
 137     }\r
 138 \r
 139   }\r
 140 \r
 141 \r
 142   private static final Map<String, Language> registry = new LinkedHashMap<String, Language>();\r
 143 \r
 144   final String isoCode;\r
 145   final Locale locale;\r
 146   \r
 147   private Collator collator;\r
 148 \r
 149   private Language(final Locale locale, final String isoCode) {\r
 150     this.locale = locale;\r
 151     this.isoCode = isoCode;\r
 152 \r
 153     registry.put(isoCode.toLowerCase(), this);\r
 154   }\r
 155 \r
 156   @Override\r
 157   public String toString() {\r
 158     return locale.toString();\r
 159   }\r
 160   \r
 161   public String getIsoCode() {\r
 162     return isoCode;\r
 163   }\r
 164   \r
 165   public synchronized Collator getCollator() {\r
 166     // Don't think this is thread-safe...\r
 167 //    if (collator == null) {\r
 168       this.collator = Collator.getInstance(locale);\r
 169       this.collator.setStrength(Collator.IDENTICAL);\r
 170 //    }\r
 171     return collator;\r
 172   }\r
 173   \r
 174   public String getDefaultNormalizerRules() {\r
 175     return ":: Any-Latin; ' ' > ; :: Lower; :: NFD; :: [:Nonspacing Mark:] Remove; :: NFC ;";\r
 176   }\r
 177   \r
 178   /**\r
 179    * A practical pattern to identify strong RTL characters. This pattern is not\r
 180    * completely correct according to the Unicode standard. It is simplified for\r
 181    * performance and small code size.\r
 182    */\r
 183   private static final String rtlChars =\r
 184       "\u0591-\u07FF\uFB1D-\uFDFD\uFE70-\uFEFC";\r
 185 \r
 186   private static final String puncChars =\r
 187       "\\[\\]\\(\\)\\{\\}\\=";\r
 188 \r
 189   private static final Pattern RTL_LEFT_BOUNDARY = Pattern.compile("(["+ puncChars +"])([" + rtlChars + "])");\r
 190   private static final Pattern RTL_RIGHT_BOUNDARY = Pattern.compile("([" + rtlChars + "])(["+ puncChars +"])");\r
 191   \r
 192   public static String fixBidiText(String text) {\r
 193 //    text = RTL_LEFT_BOUNDARY.matcher(text).replaceAll("$1\u200e $2");\r
 194 //    text = RTL_RIGHT_BOUNDARY.matcher(text).replaceAll("$1 \u200e$2");\r
 195     return text;\r
 196   }\r
 197   \r
 198   // ----------------------------------------------------------------\r
 199 \r
 200   public static final Language en = new Language(Locale.ENGLISH, "EN");\r
 201   public static final Language fr = new Language(Locale.FRENCH, "FR");\r
 202   public static final Language it = new Language(Locale.ITALIAN, "IT");\r
 203 \r
 204   public static final Language de = new Language(Locale.GERMAN, "DE") {\r
 205     @Override\r
 206     public String getDefaultNormalizerRules() {\r
 207       return ":: Lower; 'ae' > 'ä'; 'oe' > 'ö'; 'ue' > 'ü'; 'ß' > 'ss'; ";\r
 208     }\r
 209   };\r
 210   \r
 211   // ----------------------------------------------------------------\r
 212 \r
 213   public static synchronized Language lookup(final String isoCode) {\r
 214     Language lang = registry.get(isoCode.toLowerCase());\r
 215     if (lang == null) {\r
 216       lang = new Language(new Locale(isoCode), isoCode);\r
 217     }\r
 218     return lang;\r
 219   }\r
 220 \r
 221 }\r