Use BCP47 compliant format for locale representation

base/android/java/src/org/chromium/base/LocaleUtils.java

Index: base/android/java/src/org/chromium/base/LocaleUtils.java
diff --git a/base/android/java/src/org/chromium/base/LocaleUtils.java b/base/android/java/src/org/chromium/base/LocaleUtils.java
index 35d04a9b73b8e337f8469420e4141343810b2ef3..d9014f1addd574ce642881daee637b7ef526a232 100644
--- a/base/android/java/src/org/chromium/base/LocaleUtils.java
+++ b/base/android/java/src/org/chromium/base/LocaleUtils.java
@@ -6,7 +6,10 @@ package org.chromium.base;
 
 import org.chromium.base.annotations.CalledByNative;
 
+import java.util.Collections;
+import java.util.HashMap;
 import java.util.Locale;
+import java.util.Map;
 
 /**
  * This class provides the locale related methods.
@@ -18,45 +21,91 @@ public class LocaleUtils {
     private LocaleUtils() {
     }
 
+    private static final Map<String, String> LANGUAGE_MAP;
+
+    static {
+        HashMap<String, String> map = new HashMap<>();
+        map.put("iw", "he"); // Hebrew
+        map.put("ji", "yi"); // Yiddish
+        map.put("in", "id"); // Indonesian
+        map.put("tl", "fil"); // Filipino
+        LANGUAGE_MAP = Collections.unmodifiableMap(map);
+    }
+
     /**
-     * @return The string for the given locale, translating Android deprecated language codes
-     *         into the modern ones used by Chromium.
+     * Handle the special cases in converting a language code/region code pair into an ISO-639-1
+     * language tag. When a language code used for Chromium is different from the language code
+     * in Android, update that language code for Chromium.
+     * @return a updated language code for Chromium if necessary.
+     **/
+    private static String updateLanguageForChromium(String language) {
+        String updatedLanguageCode = LANGUAGE_MAP.get(language);
+        return updatedLanguageCode == null ? language : updatedLanguageCode;
+    }
+
+    /**
+     * This function creates Locale object from xx-XX style string where xx is language code
+     * and XX is a country code.
+     * @return the locale that best represents the language tag.
      */
-    public static String getLocale(Locale locale) {
-        String language = getLanguage(locale);
-        String country = locale.getCountry();
+    public static Locale forLanguageTag(String languageTag) {
+        if (languageTag.length() == 0) {
+            return new Locale("");
+        }
+        String[] tag = languageTag.split("-");
+        String language = updateLanguageForChromium(tag[0]);
+        if (language.length() != 2 && language.length() != 3) {
+            return new Locale("");
+        }
+        if (tag.length == 1) {
+            return new Locale(language);
+        }
+        String country = tag[1];
+        if (country.length() != 2 && country.length() != 3) {
+            return new Locale(language);
+        }
+        return new Locale(language, country);
+    }
 
-        return country.isEmpty() ? language : language + "-" + country;
+    /**
+     * Android uses deprecated lanuages codes for Hebrew, Yiddish and Indonesian but
+     * Chromium uses the updated codes. Also, Android uses "tl" while Chromium uses "fil"
+     * for Tagalog/Filipino. So apply a mapping.
+     * See http://developer.android.com/reference/java/util/Locale.html
+     * @return a updated language code for Chromium with given locale.
+     */
+    public static String getLocaleLanguage(Locale locale) {
+        return updateLanguageForChromium(locale.getLanguage());
     }
 
     /**
-     * @return The language for the given locale, translating Android deprecated languages codes
-     *         into modern ones used by Chromium.
+     * Converts Locale object to the BC47 compliant string format.
+     *
+     * Java keeps deprecated language codes for Hebrew, Yiddish and Indonesian but Chromium uses
+     * updated ones. Similarly, Android uses "tl" while Chromium uses "fil" for Tagalog/Filipino.
+     * Note that we cannot use Locale.getLanguage() and Locale.toLanguageTag() for this purpose.
+     * Since Locale.getLanguage() returns deprecated language code even if the Locale object is
+     * constructed with updated language code. As for Locale.toLanguageTag(), it does a special
+     * conversion from deprecated language code to updated one, but it is not usable because this
+     * special conversion is not working Android M or before.
+     * @return a well-formed IETF BCP 47 language tag with language and country code that
+     *         represents this locale.
      */
-    public static String getLanguage(Locale locale) {
-        String language = locale.getLanguage();
+    public static String getLocaleString(Locale locale) {
+        String language = updateLanguageForChromium(locale.getLanguage());
+        String country = locale.getCountry();
 
-        // Android uses deprecated lanuages codes for Hebrew and Indonesian but Chromium uses the
-        // updated codes. Also, Android uses "tl" while Chromium uses "fil" for Tagalog/Filipino.
-        // So apply a mapping.
-        // See http://developer.android.com/reference/java/util/Locale.html
-        if ("iw".equals(language)) {
-            language = "he";
-        } else if ("in".equals(language)) {
-            language = "id";
-        } else if ("tl".equals(language)) {
-            language = "fil";
-        }
-        return language;
+        return country.isEmpty() ? language : language + "-" + country;
     }
 
     /**
-     * @return The default locale, translating Android deprecated language codes into the modern
-     *         ones used by Chromium.
+     * @return a well-formed IETF BCP 47 language tag with language and country code that
+     *         represents a default locale.
      */
     @CalledByNative
-    public static String getDefaultLocale() {
-        return getLocale(Locale.getDefault());
+    public static String getDefaultLocaleString() {
+        Locale locale = Locale.getDefault();
+        return getLocaleString(locale);
     }
 
     /**