\r
package com.hughes.android.dictionary.engine;\r
\r
-import java.util.Arrays;\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
+import java.util.regex.Pattern;\r
\r
+import com.hughes.android.dictionary.R;\r
import com.ibm.icu.text.Collator;\r
\r
public class Language {\r
\r
- public static final Map<String,String> isoCodeToWikiName = new LinkedHashMap<String,String>();\r
+ public static final Map<String,Integer> isoCodeToResourceId = new LinkedHashMap<String,Integer>();\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", "Hebrew");\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
+ isoCodeToResourceId.put("AF", R.string.AF);\r
+ isoCodeToResourceId.put("SQ", R.string.SQ);\r
+ isoCodeToResourceId.put("AR", R.string.AR);\r
+ isoCodeToResourceId.put("HY", R.string.HY);\r
+ isoCodeToResourceId.put("BE", R.string.BE);\r
+ isoCodeToResourceId.put("BN", R.string.BN);\r
+ isoCodeToResourceId.put("BS", R.string.BS);\r
+ isoCodeToResourceId.put("BG", R.string.BG);\r
+ isoCodeToResourceId.put("CA", R.string.CA);\r
+ isoCodeToResourceId.put("HR", R.string.HR);\r
+ isoCodeToResourceId.put("CS", R.string.CS);\r
+ isoCodeToResourceId.put("ZH", R.string.ZH);\r
+ isoCodeToResourceId.put("DA", R.string.DA);\r
+ isoCodeToResourceId.put("NL", R.string.NL);\r
+ isoCodeToResourceId.put("EN", R.string.EN);\r
+ isoCodeToResourceId.put("EO", R.string.EO);\r
+ isoCodeToResourceId.put("ET", R.string.ET);\r
+ isoCodeToResourceId.put("FI", R.string.FI);\r
+ isoCodeToResourceId.put("FR", R.string.FR);\r
+ isoCodeToResourceId.put("DE", R.string.DE);\r
+ isoCodeToResourceId.put("EL", R.string.EL);\r
+ isoCodeToResourceId.put("haw", R.string.haw);\r
+ isoCodeToResourceId.put("HE", R.string.HE);\r
+ isoCodeToResourceId.put("HI", R.string.HI);\r
+ isoCodeToResourceId.put("HU", R.string.HU);\r
+ isoCodeToResourceId.put("IS", R.string.IS);\r
+ isoCodeToResourceId.put("ID", R.string.ID);\r
+ isoCodeToResourceId.put("GA", R.string.GA);\r
+ isoCodeToResourceId.put("IT", R.string.IT);\r
+ isoCodeToResourceId.put("LA", R.string.LA);\r
+ isoCodeToResourceId.put("LV", R.string.LV);\r
+ isoCodeToResourceId.put("LT", R.string.LT);\r
+ isoCodeToResourceId.put("JA", R.string.JA);\r
+ isoCodeToResourceId.put("KO", R.string.KO);\r
+ isoCodeToResourceId.put("KU", R.string.KU);\r
+ isoCodeToResourceId.put("MS", R.string.MS);\r
+ isoCodeToResourceId.put("MI", R.string.MI);\r
+ isoCodeToResourceId.put("MN", R.string.MN);\r
+ isoCodeToResourceId.put("NE", R.string.NE);\r
+ isoCodeToResourceId.put("NO", R.string.NO);\r
+ isoCodeToResourceId.put("FA", R.string.FA);\r
+ isoCodeToResourceId.put("PL", R.string.PL);\r
+ isoCodeToResourceId.put("PT", R.string.PT);\r
+ isoCodeToResourceId.put("PA", R.string.PA);\r
+ isoCodeToResourceId.put("RO", R.string.RO);\r
+ isoCodeToResourceId.put("RU", R.string.RU);\r
+ isoCodeToResourceId.put("SA", R.string.SA);\r
+ isoCodeToResourceId.put("SR", R.string.SR);\r
+ isoCodeToResourceId.put("SK", R.string.SK);\r
+ isoCodeToResourceId.put("SO", R.string.SO);\r
+ isoCodeToResourceId.put("ES", R.string.ES);\r
+ isoCodeToResourceId.put("SW", R.string.SW);\r
+ isoCodeToResourceId.put("SV", R.string.SV);\r
+ isoCodeToResourceId.put("TG", R.string.TG);\r
+ isoCodeToResourceId.put("TH", R.string.TH);\r
+ isoCodeToResourceId.put("BO", R.string.BO);\r
+ isoCodeToResourceId.put("TR", R.string.TR);\r
+ isoCodeToResourceId.put("UK", R.string.UK);\r
+ isoCodeToResourceId.put("UR", R.string.UR);\r
+ isoCodeToResourceId.put("VI", R.string.VI);\r
+ isoCodeToResourceId.put("CI", R.string.CI);\r
+ isoCodeToResourceId.put("YI", R.string.YI);\r
+ isoCodeToResourceId.put("ZU", R.string.ZU);\r
+ \r
+ // Hack to allow lower-case ISO codes to work:\r
+ for (final String isoCode : new ArrayList<String>(isoCodeToResourceId.keySet())) {\r
+ isoCodeToResourceId.put(isoCode.toLowerCase(), isoCodeToResourceId.get(isoCode));\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
}\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
+ private static final Pattern RTL_TOKEN = Pattern.compile("[" + rtlChars + "]");\r
+ \r
+ public static String fixBidiText(final String text) {\r
+ // TODO: fix me!, use me!\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