\r
package com.hughes.android.dictionary.engine;\r
\r
-import java.util.Arrays;\r
+import com.hughes.android.dictionary.R;\r
+import com.ibm.icu.text.Collator;\r
+\r
+import java.util.ArrayList;\r
import java.util.LinkedHashMap;\r
-import java.util.List;\r
import java.util.Locale;\r
import java.util.Map;\r
-\r
-import com.ibm.icu.text.Collator;\r
+import java.util.regex.Pattern;\r
\r
public class Language {\r
+ \r
+ public static final class LanguageResources {\r
+ public final String englishName;\r
+ public final int nameId;\r
+ public final int flagId;\r
+ \r
+ private LanguageResources(final String englishName, int nameId, int flagId) {\r
+ this.englishName = englishName;\r
+ this.nameId = nameId;\r
+ this.flagId = flagId;\r
+ }\r
\r
- public static final Map<String,String> isoCodeToWikiName = new LinkedHashMap<String,String>();\r
+ private LanguageResources(final String englishName, int nameId) {\r
+ this(englishName, nameId, 0);\r
+ }\r
+}\r
+\r
+ public static final Map<String,LanguageResources> isoCodeToResources = new LinkedHashMap<String,LanguageResources>();\r
static {\r
-// Albanian\r
-// Armenian\r
-// Belarusian\r
-// Bengali\r
-// Bosnian\r
-// Bulgarian\r
-// Catalan\r
-// Esperanto\r
-// Estonian\r
-// Hungarian\r
-// Indonesian\r
-// Kurdish\r
-// Latin\r
-// Lithuanian\r
-// Nepali\r
-// Punjabi\r
-// Swahili\r
- isoCodeToWikiName.put("AF", "Afrikaans");\r
- isoCodeToWikiName.put("AR", "Arabic");\r
- isoCodeToWikiName.put("HY", "Armenian");\r
- isoCodeToWikiName.put("HR", "Croation");\r
- isoCodeToWikiName.put("CS", "Czech");\r
- isoCodeToWikiName.put("ZH", "Chinese|Mandarin|Cantonese");\r
- isoCodeToWikiName.put("DA", "Danish");\r
- isoCodeToWikiName.put("NL", "Dutch");\r
- isoCodeToWikiName.put("EN", "English");\r
- isoCodeToWikiName.put("FI", "Finish");\r
- isoCodeToWikiName.put("FR", "French");\r
- isoCodeToWikiName.put("DE", "German");\r
- isoCodeToWikiName.put("EL", "Greek");\r
- isoCodeToWikiName.put("haw", "Hawaiian");\r
- isoCodeToWikiName.put("HE", "Hewbrew");\r
- isoCodeToWikiName.put("HI", "Hindi");\r
- isoCodeToWikiName.put("IS", "Icelandic");\r
- isoCodeToWikiName.put("GA", "Irish");\r
- isoCodeToWikiName.put("IT", "Italian");\r
- isoCodeToWikiName.put("LT", "Lithuanian");\r
- isoCodeToWikiName.put("JA", "Japanese");\r
- isoCodeToWikiName.put("KO", "Korean");\r
- isoCodeToWikiName.put("KU", "Kurdish");\r
- isoCodeToWikiName.put("MS", "Malay");\r
- isoCodeToWikiName.put("MI", "Maori");\r
- isoCodeToWikiName.put("MN", "Mongolian");\r
- isoCodeToWikiName.put("NO", "Norwegian");\r
- isoCodeToWikiName.put("FA", "Persian");\r
- isoCodeToWikiName.put("PT", "Portuguese");\r
- isoCodeToWikiName.put("RO", "Romanian");\r
- isoCodeToWikiName.put("RU", "Russian");\r
- isoCodeToWikiName.put("SA", "Sanskrit");\r
- isoCodeToWikiName.put("SR", "Serbian");\r
- isoCodeToWikiName.put("SO", "Somali");\r
- isoCodeToWikiName.put("ES", "Spanish");\r
- isoCodeToWikiName.put("SU", "Sudanese");\r
- isoCodeToWikiName.put("SV", "Swedish");\r
- isoCodeToWikiName.put("TG", "Tajik");\r
- isoCodeToWikiName.put("TH", "Thai");\r
- isoCodeToWikiName.put("BO", "Tibetan");\r
- isoCodeToWikiName.put("TR", "Turkish");\r
- isoCodeToWikiName.put("UK", "Ukranian");\r
- isoCodeToWikiName.put("VI", "Vietnamese");\r
- isoCodeToWikiName.put("CI", "Welsh");\r
- isoCodeToWikiName.put("YI", "Yiddish");\r
- isoCodeToWikiName.put("ZU", "Zulu");\r
+ isoCodeToResources.put("AF", new LanguageResources("Afrikaans", R.string.AF));\r
+ isoCodeToResources.put("SQ", new LanguageResources("Albanian", R.string.SQ));\r
+ isoCodeToResources.put("AR", new LanguageResources("Arabic", R.string.AR));\r
+ isoCodeToResources.put("HY", new LanguageResources("Armenian", R.string.HY));\r
+ isoCodeToResources.put("BE", new LanguageResources("Belarusian", R.string.BE));\r
+ isoCodeToResources.put("BN", new LanguageResources("Bengali", R.string.BN));\r
+ isoCodeToResources.put("BS", new LanguageResources("Bosnian", R.string.BS));\r
+ isoCodeToResources.put("BG", new LanguageResources("Bulgarian", R.string.BG));\r
+ isoCodeToResources.put("MY", new LanguageResources("Burmese", R.string.MY));\r
+ isoCodeToResources.put("ZH", new LanguageResources("Chinese", R.string.ZH));\r
+ isoCodeToResources.put("cmn", new LanguageResources("Mandarin", R.string.cmn));\r
+ isoCodeToResources.put("yue", new LanguageResources("Cantonese", R.string.yue));\r
+ isoCodeToResources.put("CA", new LanguageResources("Catalan", R.string.CA));\r
+ isoCodeToResources.put("HR", new LanguageResources("Croatian", R.string.HR));\r
+ isoCodeToResources.put("CS", new LanguageResources("Czech", R.string.CS));\r
+ isoCodeToResources.put("DA", new LanguageResources("Danish", R.string.DA));\r
+ isoCodeToResources.put("NL", new LanguageResources("Dutch", R.string.NL));\r
+ isoCodeToResources.put("EN", new LanguageResources("English", R.string.EN));\r
+ isoCodeToResources.put("EO", new LanguageResources("Esperanto", R.string.EO));\r
+ isoCodeToResources.put("ET", new LanguageResources("Estonian", R.string.ET));\r
+ isoCodeToResources.put("FI", new LanguageResources("Finnish", R.string.FI));\r
+ isoCodeToResources.put("FR", new LanguageResources("French", R.string.FR));\r
+ isoCodeToResources.put("DE", new LanguageResources("German", R.string.DE));\r
+ isoCodeToResources.put("EL", new LanguageResources("Greek", R.string.EL));\r
+ isoCodeToResources.put("grc", new LanguageResources("Ancient Greek", R.string.grc));\r
+ isoCodeToResources.put("haw", new LanguageResources("Hawaiian", R.string.haw));\r
+ isoCodeToResources.put("HE", new LanguageResources("Hebrew", R.string.HE));\r
+ isoCodeToResources.put("HI", new LanguageResources("Hindi", R.string.HI));\r
+ isoCodeToResources.put("HU", new LanguageResources("Hungarian", R.string.HU));\r
+ isoCodeToResources.put("IS", new LanguageResources("Icelandic", R.string.IS));\r
+ isoCodeToResources.put("ID", new LanguageResources("Indonesian", R.string.ID));\r
+ isoCodeToResources.put("GA", new LanguageResources("Irish", R.string.GA));\r
+ isoCodeToResources.put("GD", new LanguageResources("Scottish Gaelic", R.string.GD));\r
+ isoCodeToResources.put("IT", new LanguageResources("Italian", R.string.IT));\r
+ isoCodeToResources.put("LA", new LanguageResources("Latin", R.string.LA));\r
+ isoCodeToResources.put("LV", new LanguageResources("Latvian", R.string.LV));\r
+ isoCodeToResources.put("LT", new LanguageResources("Lithuanian", R.string.LT));\r
+ isoCodeToResources.put("JA", new LanguageResources("Japanese", R.string.JA));\r
+ isoCodeToResources.put("KO", new LanguageResources("Korean", R.string.KO));\r
+ isoCodeToResources.put("KU", new LanguageResources("Kurdish", R.string.KU));\r
+ isoCodeToResources.put("MS", new LanguageResources("Malay", R.string.MS));\r
+ isoCodeToResources.put("MI", new LanguageResources("Maori", R.string.MI));\r
+ isoCodeToResources.put("MN", new LanguageResources("Mongolian", R.string.MN));\r
+ isoCodeToResources.put("NE", new LanguageResources("Nepali", R.string.NE));\r
+ isoCodeToResources.put("NO", new LanguageResources("Norwegian", R.string.NO));\r
+ isoCodeToResources.put("FA", new LanguageResources("Persian", R.string.FA));\r
+ isoCodeToResources.put("PL", new LanguageResources("Polish", R.string.PL));\r
+ isoCodeToResources.put("PT", new LanguageResources("Portuguese", R.string.PT));\r
+ isoCodeToResources.put("PA", new LanguageResources("Punjabi", R.string.PA));\r
+ isoCodeToResources.put("RO", new LanguageResources("Romanian", R.string.RO));\r
+ isoCodeToResources.put("RU", new LanguageResources("Russian", R.string.RU));\r
+ isoCodeToResources.put("SA", new LanguageResources("Sanskrit", R.string.SA));\r
+ isoCodeToResources.put("SR", new LanguageResources("Serbian", R.string.SR));\r
+ isoCodeToResources.put("SK", new LanguageResources("Slovak", R.string.SK));\r
+ isoCodeToResources.put("SL", new LanguageResources("Slovenian", R.string.SL));\r
+ isoCodeToResources.put("SO", new LanguageResources("Somali", R.string.SO));\r
+ isoCodeToResources.put("ES", new LanguageResources("Spanish", R.string.ES));\r
+ isoCodeToResources.put("SW", new LanguageResources("Swahili", R.string.SW));\r
+ isoCodeToResources.put("SV", new LanguageResources("Swedish", R.string.SV));\r
+ isoCodeToResources.put("TL", new LanguageResources("Tagalog", R.string.TL));\r
+ isoCodeToResources.put("TG", new LanguageResources("Tajik", R.string.TG));\r
+ isoCodeToResources.put("TH", new LanguageResources("Thai", R.string.TH));\r
+ isoCodeToResources.put("BO", new LanguageResources("Tibetan", R.string.BO));\r
+ isoCodeToResources.put("TR", new LanguageResources("Turkish", R.string.TR));\r
+ isoCodeToResources.put("UK", new LanguageResources("Ukrainian", R.string.UK));\r
+ isoCodeToResources.put("UR", new LanguageResources("Urdu", R.string.UR));\r
+ isoCodeToResources.put("VI", new LanguageResources("Vietnamese", R.string.VI));\r
+ isoCodeToResources.put("CI", new LanguageResources("Welsh", R.string.CI));\r
+ isoCodeToResources.put("YI", new LanguageResources("Yiddish", R.string.YI));\r
+ isoCodeToResources.put("ZU", new LanguageResources("Zulu", R.string.ZU));\r
+ isoCodeToResources.put("AZ", new LanguageResources("Azeri", R.string.AZ));\r
+ isoCodeToResources.put("EU", new LanguageResources("Basque", R.string.EU));\r
+ isoCodeToResources.put("BR", new LanguageResources("Breton", R.string.BR));\r
+ isoCodeToResources.put("MR", new LanguageResources("Burmese", R.string.MR));\r
+ isoCodeToResources.put("FO", new LanguageResources("Faroese", R.string.FO));\r
+ isoCodeToResources.put("GL", new LanguageResources("Galician", R.string.GL));\r
+ isoCodeToResources.put("KA", new LanguageResources("Georgian", R.string.KA));\r
+ isoCodeToResources.put("HT", new LanguageResources("Haitian Creole", R.string.HT));\r
+ isoCodeToResources.put("LB", new LanguageResources("Luxembourgish", R.string.LB));\r
+ isoCodeToResources.put("MK", new LanguageResources("Macedonian", R.string.MK));\r
+ isoCodeToResources.put("LO", new LanguageResources("Lao", R.string.LO));\r
+ isoCodeToResources.put("ML", new LanguageResources("Malayalam", R.string.ML));\r
+ isoCodeToResources.put("SL", new LanguageResources("Slovenian", R.string.SL));\r
+ isoCodeToResources.put("TA", new LanguageResources("Tamil", R.string.TA));\r
+ isoCodeToResources.put("SH", new LanguageResources("Serbo-Croations", R.string.SH));\r
+\r
+ // Hack to allow lower-case ISO codes to work:\r
+ for (final String isoCode : new ArrayList<String>(isoCodeToResources.keySet())) {\r
+ isoCodeToResources.put(isoCode.toLowerCase(), isoCodeToResources.get(isoCode));\r
+ }\r
+\r
}\r
\r
- static final List<String> ISO_CODES_WITH_DICTS = Arrays.asList();\r
\r
- static final Map<String, Language> symbolToLangauge = new LinkedHashMap<String, Language>();\r
+ private static final Map<String, Language> registry = new LinkedHashMap<String, Language>();\r
\r
- final String symbol;\r
+ final String isoCode;\r
final Locale locale;\r
\r
private Collator collator;\r
\r
- public Language(final Locale locale) {\r
- this.symbol = locale.getLanguage();\r
+ private Language(final Locale locale, final String isoCode) {\r
this.locale = locale;\r
+ this.isoCode = isoCode;\r
\r
- symbolToLangauge.put(symbol.toLowerCase(), this);\r
+ registry.put(isoCode.toLowerCase(), this);\r
}\r
\r
@Override\r
return locale.toString();\r
}\r
\r
- public String getSymbol() {\r
- return symbol;\r
+ public String getIsoCode() {\r
+ return isoCode;\r
}\r
\r
public synchronized Collator getCollator() {\r
- if (collator == null) {\r
+ // Don't think this is thread-safe...\r
+// if (collator == null) {\r
this.collator = Collator.getInstance(locale);\r
this.collator.setStrength(Collator.IDENTICAL);\r
- }\r
+// }\r
return collator;\r
}\r
\r
public String getDefaultNormalizerRules() {\r
- return ":: Any-Latin; :: Lower; :: NFD; :: [:Nonspacing Mark:] Remove; :: NFC ;";\r
+ return ":: Any-Latin; ' ' > ; :: Lower; :: NFD; :: [:Nonspacing Mark:] Remove; :: NFC ;";\r
}\r
+ \r
+ /**\r
+ * A practical pattern to identify strong RTL characters. This pattern is not\r
+ * completely correct according to the Unicode standard. It is simplified for\r
+ * performance and small code size.\r
+ */\r
+ private static final String rtlChars =\r
+ "\u0591-\u07FF\uFB1D-\uFDFD\uFE70-\uFEFC";\r
+\r
+ private static final String puncChars =\r
+ "\\[\\]\\(\\)\\{\\}\\=";\r
+\r
+ private static final Pattern RTL_LEFT_BOUNDARY = Pattern.compile("(["+ puncChars +"])([" + rtlChars + "])");\r
+ private static final Pattern RTL_RIGHT_BOUNDARY = Pattern.compile("([" + rtlChars + "])(["+ puncChars +"])");\r
+ \r
+ public static String fixBidiText(String text) {\r
+// text = RTL_LEFT_BOUNDARY.matcher(text).replaceAll("$1\u200e $2");\r
+// text = RTL_RIGHT_BOUNDARY.matcher(text).replaceAll("$1 \u200e$2");\r
+ return text;\r
+ }\r
+ \r
// ----------------------------------------------------------------\r
\r
- public static final Language en = new Language(Locale.ENGLISH);\r
- public static final Language fr = new Language(Locale.FRENCH);\r
- public static final Language it = new Language(Locale.ITALIAN);\r
+ public static final Language en = new Language(Locale.ENGLISH, "EN");\r
+ public static final Language fr = new Language(Locale.FRENCH, "FR");\r
+ public static final Language it = new Language(Locale.ITALIAN, "IT");\r
\r
- public static final Language de = new Language(Locale.GERMAN) {\r
+ public static final Language de = new Language(Locale.GERMAN, "DE") {\r
@Override\r
public String getDefaultNormalizerRules() {\r
return ":: Lower; 'ae' > 'ä'; 'oe' > 'ö'; 'ue' > 'ü'; 'ß' > 'ss'; ";\r
\r
// ----------------------------------------------------------------\r
\r
- public static synchronized Language lookup(final String symbol) {\r
- Language lang = symbolToLangauge.get(symbol.toLowerCase());\r
+ public static synchronized Language lookup(final String isoCode) {\r
+ Language lang = registry.get(isoCode.toLowerCase());\r
if (lang == null) {\r
- lang = new Language(new Locale(symbol));\r
+ lang = new Language(new Locale(isoCode), isoCode);\r
}\r
return lang;\r
}\r
projects / Dictionary.git / blobdiff