001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.commons.lang3;
018
019import java.util.ArrayList;
020import java.util.Arrays;
021import java.util.Collections;
022import java.util.HashSet;
023import java.util.List;
024import java.util.Locale;
025import java.util.Set;
026import java.util.concurrent.ConcurrentHashMap;
027import java.util.concurrent.ConcurrentMap;
028
029/**
030 * <p>Operations to assist when working with a {@link Locale}.</p>
031 *
032 * <p>This class tries to handle {@code null} input gracefully.
033 * An exception will not be thrown for a {@code null} input.
034 * Each method documents its behaviour in more detail.</p>
035 *
036 * @since 2.2
037 */
038public class LocaleUtils {
039
040    /** Concurrent map of language locales by country. */
041    private static final ConcurrentMap<String, List<Locale>> cLanguagesByCountry =
042        new ConcurrentHashMap<>();
043
044    /** Concurrent map of country locales by language. */
045    private static final ConcurrentMap<String, List<Locale>> cCountriesByLanguage =
046        new ConcurrentHashMap<>();
047
048    /**
049     * <p>{@code LocaleUtils} instances should NOT be constructed in standard programming.
050     * Instead, the class should be used as {@code LocaleUtils.toLocale("en_GB");}.</p>
051     *
052     * <p>This constructor is public to permit tools that require a JavaBean instance
053     * to operate.</p>
054     */
055    public LocaleUtils() {
056      super();
057    }
058
059    //-----------------------------------------------------------------------
060    /**
061     * <p>Converts a String to a Locale.</p>
062     *
063     * <p>This method takes the string format of a locale and creates the
064     * locale object from it.</p>
065     *
066     * <pre>
067     *   LocaleUtils.toLocale("")           = new Locale("", "")
068     *   LocaleUtils.toLocale("en")         = new Locale("en", "")
069     *   LocaleUtils.toLocale("en_GB")      = new Locale("en", "GB")
070     *   LocaleUtils.toLocale("en_001")     = new Locale("en", "001")
071     *   LocaleUtils.toLocale("en_GB_xxx")  = new Locale("en", "GB", "xxx")   (#)
072     * </pre>
073     *
074     * <p>(#) The behaviour of the JDK variant constructor changed between JDK1.3 and JDK1.4.
075     * In JDK1.3, the constructor upper cases the variant, in JDK1.4, it doesn't.
076     * Thus, the result from getVariant() may vary depending on your JDK.</p>
077     *
078     * <p>This method validates the input strictly.
079     * The language code must be lowercase.
080     * The country code must be uppercase.
081     * The separator must be an underscore.
082     * The length must be correct.
083     * </p>
084     *
085     * @param str  the locale String to convert, null returns null
086     * @return a Locale, null if null input
087     * @throws IllegalArgumentException if the string is an invalid format
088     * @see Locale#forLanguageTag(String)
089     */
090    public static Locale toLocale(final String str) {
091        if (str == null) {
092            return null;
093        }
094        if (str.isEmpty()) { // LANG-941 - JDK 8 introduced an empty locale where all fields are blank
095            return new Locale(StringUtils.EMPTY, StringUtils.EMPTY);
096        }
097        if (str.contains("#")) { // LANG-879 - Cannot handle Java 7 script & extensions
098            throw new IllegalArgumentException("Invalid locale format: " + str);
099        }
100        final int len = str.length();
101        if (len < 2) {
102            throw new IllegalArgumentException("Invalid locale format: " + str);
103        }
104        final char ch0 = str.charAt(0);
105        if (ch0 == '_') {
106            if (len < 3) {
107                throw new IllegalArgumentException("Invalid locale format: " + str);
108            }
109            final char ch1 = str.charAt(1);
110            final char ch2 = str.charAt(2);
111            if (!Character.isUpperCase(ch1) || !Character.isUpperCase(ch2)) {
112                throw new IllegalArgumentException("Invalid locale format: " + str);
113            }
114            if (len == 3) {
115                return new Locale(StringUtils.EMPTY, str.substring(1, 3));
116            }
117            if (len < 5) {
118                throw new IllegalArgumentException("Invalid locale format: " + str);
119            }
120            if (str.charAt(3) != '_') {
121                throw new IllegalArgumentException("Invalid locale format: " + str);
122            }
123            return new Locale(StringUtils.EMPTY, str.substring(1, 3), str.substring(4));
124        }
125
126        return parseLocale(str);
127    }
128
129    /**
130     * Tries to parse a locale from the given String.
131     *
132     * @param str the String to parse a locale from.
133     * @return a Locale instance parsed from the given String.
134     * @throws IllegalArgumentException if the given String can not be parsed.
135     */
136    private static Locale parseLocale(final String str) {
137        if (isISO639LanguageCode(str)) {
138            return new Locale(str);
139        }
140
141        final String[] segments = str.split("_", -1);
142        final String language = segments[0];
143        if (segments.length == 2) {
144            final String country = segments[1];
145            if (isISO639LanguageCode(language) && isISO3166CountryCode(country) ||
146                    isNumericAreaCode(country)) {
147                return new Locale(language, country);
148            }
149        } else if (segments.length == 3) {
150            final String country = segments[1];
151            final String variant = segments[2];
152            if (isISO639LanguageCode(language) &&
153                    (country.length() == 0 || isISO3166CountryCode(country) || isNumericAreaCode(country)) &&
154                    variant.length() > 0) {
155                return new Locale(language, country, variant);
156            }
157        }
158        throw new IllegalArgumentException("Invalid locale format: " + str);
159    }
160
161    /**
162     * Checks whether the given String is a ISO 639 compliant language code.
163     *
164     * @param str the String to check.
165     * @return true, if the given String is a ISO 639 compliant language code.
166     */
167    private static boolean isISO639LanguageCode(final String str) {
168        return StringUtils.isAllLowerCase(str) && (str.length() == 2 || str.length() == 3);
169    }
170
171    /**
172     * Checks whether the given String is a ISO 3166 alpha-2 country code.
173     *
174     * @param str the String to check
175     * @return true, is the given String is a ISO 3166 compliant country code.
176     */
177    private static boolean isISO3166CountryCode(final String str) {
178        return StringUtils.isAllUpperCase(str) && str.length() == 2;
179    }
180
181    /**
182     * Checks whether the given String is a UN M.49 numeric area code.
183     *
184     * @param str the String to check
185     * @return true, is the given String is a UN M.49 numeric area code.
186     */
187    private static boolean isNumericAreaCode(final String str) {
188        return StringUtils.isNumeric(str) && str.length() == 3;
189    }
190
191    //-----------------------------------------------------------------------
192    /**
193     * <p>Obtains the list of locales to search through when performing
194     * a locale search.</p>
195     *
196     * <pre>
197     * localeLookupList(Locale("fr","CA","xxx"))
198     *   = [Locale("fr","CA","xxx"), Locale("fr","CA"), Locale("fr")]
199     * </pre>
200     *
201     * @param locale  the locale to start from
202     * @return the unmodifiable list of Locale objects, 0 being locale, not null
203     */
204    public static List<Locale> localeLookupList(final Locale locale) {
205        return localeLookupList(locale, locale);
206    }
207
208    //-----------------------------------------------------------------------
209    /**
210     * <p>Obtains the list of locales to search through when performing
211     * a locale search.</p>
212     *
213     * <pre>
214     * localeLookupList(Locale("fr", "CA", "xxx"), Locale("en"))
215     *   = [Locale("fr","CA","xxx"), Locale("fr","CA"), Locale("fr"), Locale("en"]
216     * </pre>
217     *
218     * <p>The result list begins with the most specific locale, then the
219     * next more general and so on, finishing with the default locale.
220     * The list will never contain the same locale twice.</p>
221     *
222     * @param locale  the locale to start from, null returns empty list
223     * @param defaultLocale  the default locale to use if no other is found
224     * @return the unmodifiable list of Locale objects, 0 being locale, not null
225     */
226    public static List<Locale> localeLookupList(final Locale locale, final Locale defaultLocale) {
227        final List<Locale> list = new ArrayList<>(4);
228        if (locale != null) {
229            list.add(locale);
230            if (locale.getVariant().length() > 0) {
231                list.add(new Locale(locale.getLanguage(), locale.getCountry()));
232            }
233            if (locale.getCountry().length() > 0) {
234                list.add(new Locale(locale.getLanguage(), StringUtils.EMPTY));
235            }
236            if (list.contains(defaultLocale) == false) {
237                list.add(defaultLocale);
238            }
239        }
240        return Collections.unmodifiableList(list);
241    }
242
243    //-----------------------------------------------------------------------
244    /**
245     * <p>Obtains an unmodifiable list of installed locales.</p>
246     *
247     * <p>This method is a wrapper around {@link Locale#getAvailableLocales()}.
248     * It is more efficient, as the JDK method must create a new array each
249     * time it is called.</p>
250     *
251     * @return the unmodifiable list of available locales
252     */
253    public static List<Locale> availableLocaleList() {
254        return SyncAvoid.AVAILABLE_LOCALE_LIST;
255    }
256
257    //-----------------------------------------------------------------------
258    /**
259     * <p>Obtains an unmodifiable set of installed locales.</p>
260     *
261     * <p>This method is a wrapper around {@link Locale#getAvailableLocales()}.
262     * It is more efficient, as the JDK method must create a new array each
263     * time it is called.</p>
264     *
265     * @return the unmodifiable set of available locales
266     */
267    public static Set<Locale> availableLocaleSet() {
268        return SyncAvoid.AVAILABLE_LOCALE_SET;
269    }
270
271    //-----------------------------------------------------------------------
272    /**
273     * <p>Checks if the locale specified is in the list of available locales.</p>
274     *
275     * @param locale the Locale object to check if it is available
276     * @return true if the locale is a known locale
277     */
278    public static boolean isAvailableLocale(final Locale locale) {
279        return availableLocaleList().contains(locale);
280    }
281
282    //-----------------------------------------------------------------------
283    /**
284     * <p>Obtains the list of languages supported for a given country.</p>
285     *
286     * <p>This method takes a country code and searches to find the
287     * languages available for that country. Variant locales are removed.</p>
288     *
289     * @param countryCode  the 2 letter country code, null returns empty
290     * @return an unmodifiable List of Locale objects, not null
291     */
292    public static List<Locale> languagesByCountry(final String countryCode) {
293        if (countryCode == null) {
294            return Collections.emptyList();
295        }
296        List<Locale> langs = cLanguagesByCountry.get(countryCode);
297        if (langs == null) {
298            langs = new ArrayList<>();
299            final List<Locale> locales = availableLocaleList();
300            for (int i = 0; i < locales.size(); i++) {
301                final Locale locale = locales.get(i);
302                if (countryCode.equals(locale.getCountry()) &&
303                        locale.getVariant().isEmpty()) {
304                    langs.add(locale);
305                }
306            }
307            langs = Collections.unmodifiableList(langs);
308            cLanguagesByCountry.putIfAbsent(countryCode, langs);
309            langs = cLanguagesByCountry.get(countryCode);
310        }
311        return langs;
312    }
313
314    //-----------------------------------------------------------------------
315    /**
316     * <p>Obtains the list of countries supported for a given language.</p>
317     *
318     * <p>This method takes a language code and searches to find the
319     * countries available for that language. Variant locales are removed.</p>
320     *
321     * @param languageCode  the 2 letter language code, null returns empty
322     * @return an unmodifiable List of Locale objects, not null
323     */
324    public static List<Locale> countriesByLanguage(final String languageCode) {
325        if (languageCode == null) {
326            return Collections.emptyList();
327        }
328        List<Locale> countries = cCountriesByLanguage.get(languageCode);
329        if (countries == null) {
330            countries = new ArrayList<>();
331            final List<Locale> locales = availableLocaleList();
332            for (int i = 0; i < locales.size(); i++) {
333                final Locale locale = locales.get(i);
334                if (languageCode.equals(locale.getLanguage()) &&
335                        locale.getCountry().length() != 0 &&
336                        locale.getVariant().isEmpty()) {
337                    countries.add(locale);
338                }
339            }
340            countries = Collections.unmodifiableList(countries);
341            cCountriesByLanguage.putIfAbsent(languageCode, countries);
342            countries = cCountriesByLanguage.get(languageCode);
343        }
344        return countries;
345    }
346
347    //-----------------------------------------------------------------------
348    // class to avoid synchronization (Init on demand)
349    static class SyncAvoid {
350        /** Unmodifiable list of available locales. */
351        private static final List<Locale> AVAILABLE_LOCALE_LIST;
352        /** Unmodifiable set of available locales. */
353        private static final Set<Locale> AVAILABLE_LOCALE_SET;
354
355        static {
356            final List<Locale> list = new ArrayList<>(Arrays.asList(Locale.getAvailableLocales()));  // extra safe
357            AVAILABLE_LOCALE_LIST = Collections.unmodifiableList(list);
358            AVAILABLE_LOCALE_SET = Collections.unmodifiableSet(new HashSet<>(list));
359        }
360    }
361
362}