Determine language code and type of format for address.

BuildComponents() in address_ui.h should take the UI language and
determine the following two questions.

(1) Whether to show UI components based on local or latinized address
    format.

If the UI language does not match the default language for the country,
and latinized address format is available, then use the latinized
format. All countries with a latinized address format also have the
default language specified.

(2) Which language code should be used to format the address after the
    user provides it.

If the UI language is one of the languages supported by the country,
then use the UI language. If the country lists supported languages, none
of which match the UI language, then pick the first supported language.
If the country does not have supported languages (e.g. Antarctica), then
use the UI language for formatting. If using the latinized format and
the UI language is not one of the supported languages, then the
formatting language is [country's default language] + "-latn".

BUG=354954

Review URL: https://codereview.chromium.org/208243005

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@259150 0039d316-1c4b-4281-b951-d872f2087c98

24 files changed, 675 insertions, 311 deletions

diff --git a/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_data.h b/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_data.h
index e9ca7a4..e101877 100644
--- a/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_data.h
+++ b/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_data.h
@@ -56,11 +56,6 @@ struct AddressData {
   // which comprises multiple fields.
   void SetFieldValue(AddressField field, const std::string& value);
 
-  // Guesses the BCP 47 language code to be used for formatting the address for
-  // display. For example, guesses "en" if the |country_code| is "US". Can
-  // return an empty string.
-  const std::string& GuessLanguageCode() const;
-
   // The BCP 47 language code used to guide how the address is formatted for
   // display. The same address may have different representations in different
   // languages.
diff --git a/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_ui.h b/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_ui.h
index 91d917b..eecbcd8a 100644
--- a/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_ui.h
+++ b/third_party/libaddressinput/chromium/cpp/include/libaddressinput/address_ui.h
@@ -28,9 +28,26 @@ struct AddressUiComponent;
 // Returns the list of supported CLDR region codes.
 const std::vector<std::string>& GetRegionCodes();
 
-// Returns the UI components for the CLDR |region_code|. Returns an empty vector
-// on error.
-std::vector<AddressUiComponent> BuildComponents(const std::string& region_code);
+// Returns the UI components for the CLDR |region_code|. These components
+// represent the address input and formatting rules for |region_code|.
+//
+// Sets the |components_language_code| to the BCP 47 language code that should
+// be used to format the address that the user entered via the UI components.
+// The |components_language_code| parameter can be NULL.
+//
+// If |region_code| has rules for latinized address format and the BCP 47
+// |ui_language_code| is not the primary language code used in the region, then
+// returns the latinized version of the UI components.
+//
+// If the UI language has a variation, then the function ignores the variation.
+// For example, the function does not distinguish among zh-hans, zh-hant, and
+// zh.
+//
+// Returns an empty vector on error.
+std::vector<AddressUiComponent> BuildComponents(
+    const std::string& region_code,
+    const std::string& ui_language_code,
+    std::string* components_language_code);
 
 // Returns the fields which are required for the CLDR |region_code|. Returns an
 // empty vector on error.
diff --git a/third_party/libaddressinput/chromium/cpp/libaddressinput.gyp b/third_party/libaddressinput/chromium/cpp/libaddressinput.gyp
index 6215898..8c44188 100644
--- a/third_party/libaddressinput/chromium/cpp/libaddressinput.gyp
+++ b/third_party/libaddressinput/chromium/cpp/libaddressinput.gyp
@@ -42,12 +42,10 @@
         'src/retriever.cc',
         'src/rule.cc',
         'src/ruleset.cc',
-        'src/time_to_string.cc',
         'src/util/canonicalize_string.cc',
         'src/util/json.cc',
         'src/util/md5.cc',
-        'src/util/string_compare.cc',
-        'src/util/string_split.cc',
+        'src/util/string_util.cc',
         'src/util/trie.cc',
       ],
       'defines': [
@@ -76,12 +74,11 @@
         'test/retriever_test.cc',
         'test/rule_test.cc',
         'test/storage_test_runner.cc',
-        'test/time_to_string.cc',
         'test/util/json_test.cc',
         'test/util/md5_unittest.cc',
         'test/util/scoped_ptr_unittest.cc',
         'test/util/stl_util_unittest.cc',
-        'test/util/string_split_unittest.cc',
+        'test/util/string_util_test.cc',
         'test/util/trie_test.cc',
       ],
       'defines': [
diff --git a/third_party/libaddressinput/chromium/cpp/src/address_data.cc b/third_party/libaddressinput/chromium/cpp/src/address_data.cc
index 51d36c6..08da6ca 100644
--- a/third_party/libaddressinput/chromium/cpp/src/address_data.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/address_data.cc
@@ -24,6 +24,7 @@
 
 #include "region_data_constants.h"
 #include "rule.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
@@ -65,7 +66,16 @@ void AddressData::FormatForDisplay(std::vector<std::string>* lines) const {
   rule.CopyFrom(Rule::GetDefault());
   rule.ParseSerializedRule(RegionDataConstants::GetRegionData(country_code));
 
-  const std::vector<std::vector<FormatElement> >& format = rule.GetFormat();
+  // If latinized rules are available and the |language_code| of this address is
+  // not the primary language code for the region, then use the latinized
+  // formatting rules.
+  const std::vector<std::vector<FormatElement> >& format =
+      rule.GetLatinFormat().empty() ||
+      language_code.empty() ||
+      NormalizeLanguageCode(language_code) ==
+          NormalizeLanguageCode(rule.GetLanguage())
+              ? rule.GetFormat() : rule.GetLatinFormat();
+
   for (size_t i = 0; i < format.size(); ++i) {
     std::string line;
     for (size_t j = 0; j < format[i].size(); ++j) {
@@ -107,28 +117,5 @@ void AddressData::SetFieldValue(AddressField field, const std::string& value) {
   }
 }
 
-const std::string& AddressData::GuessLanguageCode() const {
-  Rule rule;
-  rule.CopyFrom(Rule::GetDefault());
-  if (!rule.ParseSerializedRule(
-          RegionDataConstants::GetRegionData(country_code))) {
-    return language_code;
-  }
-
-  std::vector<std::string>::const_iterator lang_it =
-      std::find(rule.GetLanguages().begin(),
-                rule.GetLanguages().end(),
-                language_code);
-  if (lang_it != rule.GetLanguages().end()) {
-    return *lang_it;
-  }
-
-  if (!rule.GetLanguage().empty()) {
-    return rule.GetLanguage();
-  }
-
-  return language_code;
-}
-
 }  // namespace addressinput
 }  // namespace i18n
diff --git a/third_party/libaddressinput/chromium/cpp/src/address_ui.cc b/third_party/libaddressinput/chromium/cpp/src/address_ui.cc
index c4eeb99..b4337fd 100644
--- a/third_party/libaddressinput/chromium/cpp/src/address_ui.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/address_ui.cc
@@ -17,6 +17,9 @@
 #include <libaddressinput/address_field.h>
 #include <libaddressinput/address_ui_component.h>
 
+#include <algorithm>
+#include <cassert>
+#include <cstddef>
 #include <set>
 #include <string>
 #include <vector>
@@ -25,6 +28,7 @@
 #include "grit/libaddressinput_strings.h"
 #include "region_data_constants.h"
 #include "rule.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
@@ -58,6 +62,74 @@ int GetMessageIdForField(AddressField field,
   }
 }
 
+// Returns the BCP 47 language code that should be used to format the address
+// that the user entered.
+//
+// If the rule does not contain information about languages, then returns the
+// UI language.
+//
+// If the UI language is either the default language for the country, one of the
+// languages for rules, or one of the languages for address input, then returns
+// this UI language. If there're no matches, then picks one of the languages in
+// the rule and returns it.
+//
+// If latinized rules are available and the UI language code is not the primary
+// language code for this region, then returns the primary language with "-latn"
+// appended.
+std::string GetComponentsLanguageCode(const Rule& rule,
+                                      const std::string& ui_language_code) {
+  // Select the default language code for the region.
+  std::string default_language_code;
+  if (!rule.GetLanguage().empty()) {
+    default_language_code = rule.GetLanguage();
+  } else if (!rule.GetLanguages().empty()) {
+    default_language_code = rule.GetLanguages()[0];
+  } else if (!rule.GetInputLanguages().empty()) {
+    default_language_code = rule.GetInputLanguages()[0];
+  } else {
+    // Region does not have any language information (e.g. Antarctica). Use the
+    // UI language code as is.
+    return ui_language_code;
+  }
+
+  // If the UI language code is not set, then use default language code.
+  if (ui_language_code.empty()) {
+    return default_language_code;
+  }
+
+  const std::string& normalized_ui_language_code =
+      NormalizeLanguageCode(ui_language_code);
+  const std::string& normalized_default_language_code =
+      NormalizeLanguageCode(default_language_code);
+
+  // Check whether UI language code matches any language codes in the rule,
+  // normalized or as is.
+  if (normalized_default_language_code == normalized_ui_language_code ||
+      std::find(
+          rule.GetLanguages().begin(),
+          rule.GetLanguages().end(),
+          ui_language_code) != rule.GetLanguages().end() ||
+      std::find(
+          rule.GetLanguages().begin(),
+          rule.GetLanguages().end(),
+          normalized_ui_language_code) != rule.GetLanguages().end() ||
+      std::find(
+          rule.GetInputLanguages().begin(),
+          rule.GetInputLanguages().end(),
+          ui_language_code) != rule.GetInputLanguages().end() ||
+      std::find(
+          rule.GetInputLanguages().begin(),
+          rule.GetInputLanguages().end(),
+          normalized_ui_language_code) != rule.GetInputLanguages().end()) {
+    return ui_language_code;
+  }
+
+  // The UI language code does not match any language information in the rule.
+  return rule.GetLatinFormat().empty()
+             ? default_language_code
+             : normalized_default_language_code + "-latn";
+}
+
 }  // namespace
 
 const std::vector<std::string>& GetRegionCodes() {
@@ -65,7 +137,9 @@ const std::vector<std::string>& GetRegionCodes() {
 }
 
 std::vector<AddressUiComponent> BuildComponents(
-    const std::string& region_code) {
+    const std::string& region_code,
+    const std::string& ui_language_code,
+    std::string* components_language_code) {
   std::vector<AddressUiComponent> result;
 
   Rule rule;
@@ -75,13 +149,28 @@ std::vector<AddressUiComponent> BuildComponents(
     return result;
   }
 
+  if (components_language_code != NULL) {
+    *components_language_code =
+        GetComponentsLanguageCode(rule, ui_language_code);
+  }
+
   // For avoiding showing an input field twice, when the field is displayed
   // twice on an envelope.
   std::set<AddressField> fields;
 
+  // If latinized rules are available and the |ui_language_code| is not the
+  // primary language code for the region, then use the latinized formatting
+  // rules.
+  const std::vector<std::vector<FormatElement> >& format =
+      rule.GetLatinFormat().empty() ||
+      ui_language_code.empty() ||
+      NormalizeLanguageCode(ui_language_code) ==
+          NormalizeLanguageCode(rule.GetLanguage())
+              ? rule.GetFormat() : rule.GetLatinFormat();
+
   for (std::vector<std::vector<FormatElement> >::const_iterator
-           line_it = rule.GetFormat().begin();
-       line_it != rule.GetFormat().end();
+           line_it = format.begin();
+       line_it != format.end();
        ++line_it) {
     int num_fields_this_row = 0;
     for (std::vector<FormatElement>::const_iterator element_it =
diff --git a/third_party/libaddressinput/chromium/cpp/src/address_validator.cc b/third_party/libaddressinput/chromium/cpp/src/address_validator.cc
index 357cc16..3241d47 100644
--- a/third_party/libaddressinput/chromium/cpp/src/address_validator.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/address_validator.cc
@@ -40,7 +40,7 @@
 #include "rule.h"
 #include "ruleset.h"
 #include "util/stl_util.h"
-#include "util/string_compare.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
diff --git a/third_party/libaddressinput/chromium/cpp/src/region_data_constants.cc b/third_party/libaddressinput/chromium/cpp/src/region_data_constants.cc
index be60e54..9b80464 100644
--- a/third_party/libaddressinput/chromium/cpp/src/region_data_constants.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/region_data_constants.cc
@@ -17,8 +17,8 @@
 //
 // https://code.google.com/p/libaddressinput/source/browse/trunk/java/src/com/android/i18n/addressinput/RegionDataConstants.java?r=137
 //
-// The language-to-separator and country-to-language mapping is loosely based
-// on:
+// The language-to-separator mapping and primary input languages are loosely
+// based on:
 //
 // http://unicode.org/cldr/trac/browser/tags/release-24/common/supplemental/supplementalData.xml
 
@@ -41,39 +41,48 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"ANDORRA\","
       "\"lang\":\"ca\","
       "\"languages\":\"ca\","
+      "\"input_languages\":\"ca\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %S\","
       "\"require\":\"AS\","
       "\"state_name_type\":\"parish\""
       "}"));
   region_data.insert(std::make_pair("AE", "{"
       "\"name\":\"UNITED ARAB EMIRATES\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C\","
       "\"require\":\"AC\""
       "}"));
   region_data.insert(std::make_pair("AF", "{"
-      "\"name\":\"AFGHANISTAN\""
+      "\"name\":\"AFGHANISTAN\","
+      "\"input_languages\":\"fa~ps\""
       "}"));
   region_data.insert(std::make_pair("AG", "{"
       "\"name\":\"ANTIGUA AND BARBUDA\","
+      "\"input_languages\":\"en\","
       "\"require\":\"A\""
       "}"));
   region_data.insert(std::make_pair("AI", "{"
-      "\"name\":\"ANGUILLA\""
+      "\"name\":\"ANGUILLA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("AL", "{"
-      "\"name\":\"ALBANIA\""
+      "\"name\":\"ALBANIA\","
+      "\"input_languages\":\"sq\""
       "}"));
   region_data.insert(std::make_pair("AM", "{"
       "\"name\":\"ARMENIA\","
       "\"lang\":\"hy\","
       "\"languages\":\"hy\","
-      "\"fmt\":\"%N%n%O%n%A%n%Z%n%C%n%S\""
+      "\"input_languages\":\"hy\","
+      "\"fmt\":\"%N%n%O%n%A%n%Z%n%C%n%S\","
+      "\"lfmt\":\"%N%n%O%n%A%n%Z%n%C%n%S\""
       "}"));
   region_data.insert(std::make_pair("AN", "{"
       "\"name\":\"NETHERLANDS ANTILLES\""
       "}"));
   region_data.insert(std::make_pair("AO", "{"
-      "\"name\":\"ANGOLA\""
+      "\"name\":\"ANGOLA\","
+      "\"input_languages\":\"pt\""
       "}"));
   region_data.insert(std::make_pair("AQ", "{"
       "\"name\":\"ANTARCTICA\""
@@ -82,11 +91,13 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"ARGENTINA\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C%n%S\","
       "\"state_name_type\":\"state\""
       "}"));
   region_data.insert(std::make_pair("AS", "{"
       "\"name\":\"AMERICAN SAMOA\","
+      "\"input_languages\":\"en~sm\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -94,6 +105,7 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("AT", "{"
       "\"name\":\"AUSTRIA\","
+      "\"input_languages\":\"de\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
@@ -101,77 +113,95 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"AUSTRALIA\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%O%n%N%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"state\""
       "}"));
   region_data.insert(std::make_pair("AW", "{"
-      "\"name\":\"ARUBA\""
+      "\"name\":\"ARUBA\","
+      "\"input_languages\":\"nl~pap\""
       "}"));
   region_data.insert(std::make_pair("AX", "{"
       "\"name\":\"FINLAND\","
+      "\"input_languages\":\"sv\","
       "\"fmt\":\"%O%n%N%n%A%nAX-%Z %C%n\xC3\x85LAND\","  // \xC3\x85 is Å.
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("AZ", "{"
       "\"name\":\"AZERBAIJAN\","
+      "\"input_languages\":\"az\","
       "\"fmt\":\"%N%n%O%n%A%nAZ %Z %C\""
       "}"));
   region_data.insert(std::make_pair("BA", "{"
       "\"name\":\"BOSNIA AND HERZEGOVINA\","
+      "\"input_languages\":\"bs~hr~sr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("BB", "{"
       "\"name\":\"BARBADOS\","
+      "\"input_languages\":\"en\","
       "\"state_name_type\":\"parish\""
       "}"));
   region_data.insert(std::make_pair("BD", "{"
       "\"name\":\"BANGLADESH\","
+      "\"input_languages\":\"bn\","
       "\"fmt\":\"%N%n%O%n%A%n%C - %Z\""
       "}"));
   region_data.insert(std::make_pair("BE", "{"
       "\"name\":\"BELGIUM\","
+      "\"input_languages\":\"de~fr~nl\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("BF", "{"
       "\"name\":\"BURKINA FASO\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%A%n%C %X\""
       "}"));
   region_data.insert(std::make_pair("BG", "{"
       "\"name\":\"BULGARIA (REP.)\","
+      "\"input_languages\":\"bg\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("BH", "{"
       "\"name\":\"BAHRAIN\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("BI", "{"
-      "\"name\":\"BURUNDI\""
+      "\"name\":\"BURUNDI\","
+      "\"input_languages\":\"fr~rn\""
       "}"));
   region_data.insert(std::make_pair("BJ", "{"
-      "\"name\":\"BENIN\""
+      "\"name\":\"BENIN\","
+      "\"input_languages\":\"fr\""
       "}"));
   region_data.insert(std::make_pair("BL", "{"
       "\"name\":\"SAINT BARTHELEMY\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("BM", "{"
       "\"name\":\"BERMUDA\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("BN", "{"
       "\"name\":\"BRUNEI DARUSSALAM\","
+      "\"input_languages\":\"ms\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("BO", "{"
-      "\"name\":\"BOLIVIA\""
+      "\"name\":\"BOLIVIA\","
+      "\"input_languages\":\"ay~es~qu\""
       "}"));
   region_data.insert(std::make_pair("BR", "{"
       "\"name\":\"BRAZIL\","
       "\"lang\":\"pt\","
       "\"languages\":\"pt\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%O%n%N%n%A%n%C-%S%n%Z\","
       "\"require\":\"ASCZ\","
       "\"state_name_type\":\"state\""
@@ -180,84 +210,103 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"BAHAMAS\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("BT", "{"
-      "\"name\":\"BHUTAN\""
+      "\"name\":\"BHUTAN\","
+      "\"input_languages\":\"dz\""
       "}"));
   region_data.insert(std::make_pair("BV", "{"
       "\"name\":\"BOUVET ISLAND\""
       "}"));
   region_data.insert(std::make_pair("BW", "{"
-      "\"name\":\"BOTSWANA\""
+      "\"name\":\"BOTSWANA\","
+      "\"input_languages\":\"en~tn\""
       "}"));
   region_data.insert(std::make_pair("BY", "{"
       "\"name\":\"BELARUS\","
+      "\"input_languages\":\"be~ru\","
       "\"fmt\":\"%S%n%Z %C %X%n%A%n%O%n%N\""
       "}"));
   region_data.insert(std::make_pair("BZ", "{"
-      "\"name\":\"BELIZE\""
+      "\"name\":\"BELIZE\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("CA", "{"
       "\"name\":\"CANADA\","
       "\"lang\":\"en\","
       "\"languages\":\"en~fr\","
+      "\"input_languages\":\"en~fr\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\""
       "}"));
   region_data.insert(std::make_pair("CC", "{"
       "\"name\":\"COCOS (KEELING) ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%O%n%N%n%A%n%C %S %Z\""
       "}"));
   region_data.insert(std::make_pair("CD", "{"
       "\"name\":\"CONGO (DEM. REP.)\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%A%n%C %X\""
       "}"));
   region_data.insert(std::make_pair("CF", "{"
-      "\"name\":\"CENTRAL AFRICAN REPUBLIC\""
+      "\"name\":\"CENTRAL AFRICAN REPUBLIC\","
+      "\"input_languages\":\"fr~sg\""
       "}"));
   region_data.insert(std::make_pair("CG", "{"
-      "\"name\":\"CONGO (REP.)\""
+      "\"name\":\"CONGO (REP.)\","
+      "\"input_languages\":\"fr~ln\""
       "}"));
   region_data.insert(std::make_pair("CH", "{"
       "\"name\":\"SWITZERLAND\","
       "\"lang\":\"de\","
       "\"languages\":\"de~fr~it\","
+      "\"input_languages\":\"de~fr~gsw~it\","
       "\"fmt\":\"%O%n%N%n%A%nCH-%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("CI", "{"
       "\"name\":\"COTE D'IVOIRE\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%X %A %C %X\""
       "}"));
   region_data.insert(std::make_pair("CK", "{"
       "\"name\":\"COOK ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("CL", "{"
       "\"name\":\"CHILE\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C%n%S\","
       "\"state_name_type\":\"state\""
       "}"));
   region_data.insert(std::make_pair("CM", "{"
-      "\"name\":\"CAMEROON\""
+      "\"name\":\"CAMEROON\","
+      "\"input_languages\":\"en~fr\""
       "}"));
   region_data.insert(std::make_pair("CN", "{"
       "\"name\":\"P.R. CHINA\","
       "\"lang\":\"zh-hans\","
       "\"languages\":\"zh-hans\","
+      "\"input_languages\":\"zh\","
       "\"fmt\":\"%Z%n%S%C%D%n%A%n%O%n%N\","
+      "\"lfmt\":\"%N%n%O%n%A, %D%n%C%n%S, %Z\","
       "\"require\":\"ACSZ\""
       "}"));
   region_data.insert(std::make_pair("CO", "{"
       "\"name\":\"COLOMBIA\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S\""
       "}"));
   region_data.insert(std::make_pair("CR", "{"
       "\"name\":\"COSTA RICA\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("CS", "{"
@@ -268,89 +317,110 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"CAPE VERDE\","
       "\"lang\":\"pt\","
       "\"languages\":\"pt\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C%n%S\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("CX", "{"
       "\"name\":\"CHRISTMAS ISLAND\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%O%n%N%n%A%n%C %S %Z\""
       "}"));
   region_data.insert(std::make_pair("CY", "{"
       "\"name\":\"CYPRUS\","
+      "\"input_languages\":\"el~tr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("CZ", "{"
       "\"name\":\"CZECH REP.\","
+      "\"input_languages\":\"cs\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("DE", "{"
       "\"name\":\"GERMANY\","
+      "\"input_languages\":\"de\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("DJ", "{"
-      "\"name\":\"DJIBOUTI\""
+      "\"name\":\"DJIBOUTI\","
+      "\"input_languages\":\"ar~fr\""
       "}"));
   region_data.insert(std::make_pair("DK", "{"
       "\"name\":\"DENMARK\","
+      "\"input_languages\":\"da\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("DM", "{"
-      "\"name\":\"DOMINICA\""
+      "\"name\":\"DOMINICA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("DO", "{"
       "\"name\":\"DOMINICAN REP.\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("DZ", "{"
       "\"name\":\"ALGERIA\","
+      "\"input_languages\":\"ar~fr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("EC", "{"
       "\"name\":\"ECUADOR\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z%n%C\""
       "}"));
   region_data.insert(std::make_pair("EE", "{"
       "\"name\":\"ESTONIA\","
+      "\"input_languages\":\"et\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("EG", "{"
       "\"name\":\"EGYPT\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S%n%Z\""
       "}"));
   region_data.insert(std::make_pair("EH", "{"
-      "\"name\":\"WESTERN SAHARA\""
+      "\"name\":\"WESTERN SAHARA\","
+      "\"input_languages\":\"ar\""
       "}"));
   region_data.insert(std::make_pair("ER", "{"
-      "\"name\":\"ERITREA\""
+      "\"name\":\"ERITREA\","
+      "\"input_languages\":\"ar~en~ti\""
       "}"));
   region_data.insert(std::make_pair("ES", "{"
       "\"name\":\"SPAIN\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C %S\","
       "\"require\":\"ACSZ\""
       "}"));
   region_data.insert(std::make_pair("ET", "{"
       "\"name\":\"ETHIOPIA\","
+      "\"input_languages\":\"am\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("FI", "{"
       "\"name\":\"FINLAND\","
+      "\"input_languages\":\"fi~sv\","
       "\"fmt\":\"%O%n%N%n%A%nFI-%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("FJ", "{"
-      "\"name\":\"FIJI\""
+      "\"name\":\"FIJI\","
+      "\"input_languages\":\"en~fj\""
       "}"));
   region_data.insert(std::make_pair("FK", "{"
       "\"name\":\"FALKLAND ISLANDS (MALVINAS)\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("FM", "{"
       "\"name\":\"MICRONESIA (Federated State of)\","
+      "\"input_languages\":\"chk~en~kos~pon~uli~yap\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -358,69 +428,85 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("FO", "{"
       "\"name\":\"FAROE ISLANDS\","
+      "\"input_languages\":\"fo\","
       "\"fmt\":\"%N%n%O%n%A%nFO%Z %C\""
       "}"));
   region_data.insert(std::make_pair("FR", "{"
       "\"name\":\"FRANCE\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("GA", "{"
-      "\"name\":\"GABON\""
+      "\"name\":\"GABON\","
+      "\"input_languages\":\"fr\""
       "}"));
   region_data.insert(std::make_pair("GB", "{"
       "\"name\":\"UNITED KINGDOM\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S%n%Z\","
       "\"require\":\"ACZ\","
       "\"state_name_type\":\"county\""
       "}"));
   region_data.insert(std::make_pair("GD", "{"
-      "\"name\":\"GRENADA (WEST INDIES)\""
+      "\"name\":\"GRENADA (WEST INDIES)\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("GE", "{"
       "\"name\":\"GEORGIA\","
+      "\"input_languages\":\"ka\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("GF", "{"
       "\"name\":\"FRENCH GUIANA\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("GG", "{"
       "\"name\":\"CHANNEL ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%nGUERNSEY%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("GH", "{"
-      "\"name\":\"GHANA\""
+      "\"name\":\"GHANA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("GI", "{"
       "\"name\":\"GIBRALTAR\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A\","
       "\"require\":\"A\""
       "}"));
   region_data.insert(std::make_pair("GL", "{"
       "\"name\":\"GREENLAND\","
+      "\"input_languages\":\"da~kl\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("GM", "{"
-      "\"name\":\"GAMBIA\""
+      "\"name\":\"GAMBIA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("GN", "{"
       "\"name\":\"GUINEA\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%Z %A %C\""
       "}"));
   region_data.insert(std::make_pair("GP", "{"
       "\"name\":\"GUADELOUPE\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("GQ", "{"
-      "\"name\":\"EQUATORIAL GUINEA\""
+      "\"name\":\"EQUATORIAL GUINEA\","
+      "\"input_languages\":\"es~fr\""
       "}"));
   region_data.insert(std::make_pair("GR", "{"
       "\"name\":\"GREECE\","
+      "\"input_languages\":\"el\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
@@ -431,10 +517,12 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("GT", "{"
       "\"name\":\"GUATEMALA\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z- %C\""
       "}"));
   region_data.insert(std::make_pair("GU", "{"
       "\"name\":\"GUAM\","
+      "\"input_languages\":\"ch~en\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -442,16 +530,20 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("GW", "{"
       "\"name\":\"GUINEA-BISSAU\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("GY", "{"
-      "\"name\":\"GUYANA\""
+      "\"name\":\"GUYANA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("HK", "{"
       "\"name\":\"HONG KONG\","
       "\"lang\":\"zh\","
       "\"languages\":\"zh\","
+      "\"input_languages\":\"en~zh\","
       "\"fmt\":\"%S%n%A%n%O%n%N\","
+      "\"lfmt\":\"%N%n%O%n%A%n%S\","
       "\"require\":\"AS\","
       "\"state_name_type\":\"area\""
       "}"));
@@ -461,38 +553,46 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("HN", "{"
       "\"name\":\"HONDURAS\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S%n%Z\","
       "\"require\":\"ACS\""
       "}"));
   region_data.insert(std::make_pair("HR", "{"
       "\"name\":\"CROATIA\","
+      "\"input_languages\":\"hr\","
       "\"fmt\":\"%N%n%O%n%A%nHR-%Z %C\""
       "}"));
   region_data.insert(std::make_pair("HT", "{"
       "\"name\":\"HAITI\","
+      "\"input_languages\":\"fr~ht\","
       "\"fmt\":\"%N%n%O%n%A%nHT%Z %C %X\""
       "}"));
   region_data.insert(std::make_pair("HU", "{"
       "\"name\":\"HUNGARY (Rep.)\","
+      "\"input_languages\":\"hu\","
       "\"fmt\":\"%N%n%O%n%C%n%A%n%Z\""
       "}"));
   region_data.insert(std::make_pair("ID", "{"
       "\"name\":\"INDONESIA\","
+      "\"input_languages\":\"id~su\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z%n%S\""
       "}"));
   region_data.insert(std::make_pair("IE", "{"
       "\"name\":\"IRELAND\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en~ga\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S\","
       "\"state_name_type\":\"county\""
       "}"));
   region_data.insert(std::make_pair("IL", "{"
       "\"name\":\"ISRAEL\","
+      "\"input_languages\":\"ar~he\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("IM", "{"
       "\"name\":\"ISLE OF MAN\","
+      "\"input_languages\":\"en~gv\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
@@ -500,33 +600,39 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"INDIA\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en~hi\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z%n%S\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"state\""
       "}"));
   region_data.insert(std::make_pair("IO", "{"
       "\"name\":\"BRITISH INDIAN OCEAN TERRITORY\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("IQ", "{"
       "\"name\":\"IRAQ\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%O%n%N%n%A%n%C, %S%n%Z\","
       "\"require\":\"ACS\""
       "}"));
   region_data.insert(std::make_pair("IS", "{"
       "\"name\":\"ICELAND\","
+      "\"input_languages\":\"is\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("IT", "{"
       "\"name\":\"ITALY\","
       "\"lang\":\"it\","
       "\"languages\":\"it\","
+      "\"input_languages\":\"it\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C %S\","
       "\"require\":\"ACSZ\""
       "}"));
   region_data.insert(std::make_pair("JE", "{"
       "\"name\":\"CHANNEL ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%nJERSEY%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
@@ -534,46 +640,56 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"JAMAICA\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S %X\","
       "\"require\":\"ACS\","
       "\"state_name_type\":\"parish\""
       "}"));
   region_data.insert(std::make_pair("JO", "{"
       "\"name\":\"JORDAN\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("JP", "{"
       "\"name\":\"JAPAN\","
       "\"lang\":\"ja\","
       "\"languages\":\"ja\","
+      "\"input_languages\":\"ja\","
       "\"fmt\":\"\xE3\x80\x92%Z%n%S%C%n%A%n%O%n%N\","  // \xE3\x80\x92 is 〒.
+      "\"lfmt\":\"%N%n%O%n%A%n%C, %S%n%Z\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"prefecture\""
       "}"));
   region_data.insert(std::make_pair("KE", "{"
       "\"name\":\"KENYA\","
+      "\"input_languages\":\"en~sw\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%Z\""
       "}"));
   region_data.insert(std::make_pair("KG", "{"
       "\"name\":\"KYRGYZSTAN\","
+      "\"input_languages\":\"ky~ru\","
       "\"fmt\":\"%Z %C %X%n%A%n%O%n%N\""
       "}"));
   region_data.insert(std::make_pair("KH", "{"
       "\"name\":\"CAMBODIA\","
+      "\"input_languages\":\"km\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("KI", "{"
       "\"name\":\"KIRIBATI\","
+      "\"input_languages\":\"en~gil\","
       "\"fmt\":\"%N%n%O%n%A%n%S%n%C\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("KM", "{"
-      "\"name\":\"COMOROS\""
+      "\"name\":\"COMOROS\","
+      "\"input_languages\":\"ar~fr~zdj\""
       "}"));
   region_data.insert(std::make_pair("KN", "{"
       "\"name\":\"SAINT KITTS AND NEVIS\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S\","
       "\"require\":\"ACS\","
       "\"state_name_type\":\"island\""
@@ -582,97 +698,120 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"KOREA (REP.)\","
       "\"lang\":\"ko\","
       "\"languages\":\"ko\","
+      "\"input_languages\":\"ko\","
       "\"fmt\":\"%S %C%D%n%A%n%O%n%N%nSEOUL %Z\","
+      "\"lfmt\":\"%N%n%O%n%A%n%D%n%C%n%S%nSEOUL %Z\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"do_si\""
       "}"));
   region_data.insert(std::make_pair("KW", "{"
       "\"name\":\"KUWAIT\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("KY", "{"
       "\"name\":\"CAYMAN ISLANDS\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%S\","
       "\"require\":\"AS\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("KZ", "{"
       "\"name\":\"KAZAKHSTAN\","
+      "\"input_languages\":\"kk~ru\","
       "\"fmt\":\"%Z%n%S%n%C%n%A%n%O%n%N\""
       "}"));
   region_data.insert(std::make_pair("LA", "{"
       "\"name\":\"LAO (PEOPLE'S DEM. REP.)\","
+      "\"input_languages\":\"lo\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("LB", "{"
       "\"name\":\"LEBANON\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("LC", "{"
-      "\"name\":\"SAINT LUCIA\""
+      "\"name\":\"SAINT LUCIA\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("LI", "{"
       "\"name\":\"LIECHTENSTEIN\","
+      "\"input_languages\":\"de~gsw\","
       "\"fmt\":\"%O%n%N%n%A%nFL-%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("LK", "{"
       "\"name\":\"SRI LANKA\","
+      "\"input_languages\":\"si~ta\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%Z\""
       "}"));
   region_data.insert(std::make_pair("LR", "{"
       "\"name\":\"LIBERIA\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C %X\""
       "}"));
   region_data.insert(std::make_pair("LS", "{"
       "\"name\":\"LESOTHO\","
+      "\"input_languages\":\"en~st\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("LT", "{"
       "\"name\":\"LITHUANIA\","
+      "\"input_languages\":\"lt\","
       "\"fmt\":\"%O%n%N%n%A%nLT-%Z %C\""
       "}"));
   region_data.insert(std::make_pair("LU", "{"
       "\"name\":\"LUXEMBOURG\","
+      "\"input_languages\":\"de~fr~lb\","
       "\"fmt\":\"%O%n%N%n%A%nL-%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("LV", "{"
       "\"name\":\"LATVIA\","
+      "\"input_languages\":\"lv\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %Z\""
       "}"));
   region_data.insert(std::make_pair("LY", "{"
-      "\"name\":\"LIBYA\""
+      "\"name\":\"LIBYA\","
+      "\"input_languages\":\"ar\""
       "}"));
   region_data.insert(std::make_pair("MA", "{"
       "\"name\":\"MOROCCO\","
+      "\"input_languages\":\"ar~fr~tzm\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("MC", "{"
       "\"name\":\"MONACO\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%A%nMC-%Z %C %X\""
       "}"));
   region_data.insert(std::make_pair("MD", "{"
       "\"name\":\"Rep. MOLDOVA\","
+      "\"input_languages\":\"ro\","
       "\"fmt\":\"%N%n%O%n%A%nMD-%Z %C\""
       "}"));
   region_data.insert(std::make_pair("ME", "{"
       "\"name\":\"MONTENEGRO\","
+      "\"input_languages\":\"sr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("MF", "{"
       "\"name\":\"SAINT MARTIN\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("MG", "{"
       "\"name\":\"MADAGASCAR\","
+      "\"input_languages\":\"en~fr~mg\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("MH", "{"
       "\"name\":\"MARSHALL ISLANDS\","
+      "\"input_languages\":\"en~mh\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -680,24 +819,30 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("MK", "{"
       "\"name\":\"MACEDONIA\","
+      "\"input_languages\":\"mk~sq\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("ML", "{"
-      "\"name\":\"MALI\""
+      "\"name\":\"MALI\","
+      "\"input_languages\":\"fr\""
       "}"));
   region_data.insert(std::make_pair("MN", "{"
       "\"name\":\"MONGOLIA\","
+      "\"input_languages\":\"mn\","
       "\"fmt\":\"%N%n%O%n%A%n%S %C-%X%n%Z\""
       "}"));
   region_data.insert(std::make_pair("MO", "{"
       "\"name\":\"MACAO\","
       "\"lang\":\"zh-hant\","
       "\"languages\":\"zh-hant\","
+      "\"input_languages\":\"pt~zh\","
       "\"fmt\":\"%A%n%O%n%N\","
+      "\"lfmt\":\"%N%n%O%n%A\","
       "\"require\":\"A\""
       "}"));
   region_data.insert(std::make_pair("MP", "{"
       "\"name\":\"NORTHERN MARIANA ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -705,35 +850,43 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("MQ", "{"
       "\"name\":\"MARTINIQUE\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("MR", "{"
-      "\"name\":\"MAURITANIA\""
+      "\"name\":\"MAURITANIA\","
+      "\"input_languages\":\"ar\""
       "}"));
   region_data.insert(std::make_pair("MS", "{"
-      "\"name\":\"MONTSERRAT\""
+      "\"name\":\"MONTSERRAT\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("MT", "{"
       "\"name\":\"MALTA\","
+      "\"input_languages\":\"en~mt\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("MU", "{"
       "\"name\":\"MAURITIUS\","
+      "\"input_languages\":\"en~fr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z%n%C\""
       "}"));
   region_data.insert(std::make_pair("MV", "{"
       "\"name\":\"MALDIVES\","
+      "\"input_languages\":\"dv\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("MW", "{"
       "\"name\":\"MALAWI\","
+      "\"input_languages\":\"en~ny\","
       "\"fmt\":\"%N%n%O%n%A%n%C %X\""
       "}"));
   region_data.insert(std::make_pair("MX", "{"
       "\"name\":\"MEXICO\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C, %S\","
       "\"require\":\"ACZ\","
       "\"state_name_type\":\"state\""
@@ -742,34 +895,41 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"MALAYSIA\","
       "\"lang\":\"ms\","
       "\"languages\":\"ms\","
+      "\"input_languages\":\"ms\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C, %S\","
       "\"require\":\"ACZ\","
       "\"state_name_type\":\"state\""
       "}"));
   region_data.insert(std::make_pair("MZ", "{"
       "\"name\":\"MOZAMBIQUE\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%N%n%O%n%A%n%C\""
       "}"));
   region_data.insert(std::make_pair("NA", "{"
-      "\"name\":\"NAMIBIA\""
+      "\"name\":\"NAMIBIA\","
+      "\"input_languages\":\"af~en\""
       "}"));
   region_data.insert(std::make_pair("NC", "{"
       "\"name\":\"NEW CALEDONIA\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("NE", "{"
       "\"name\":\"NIGER\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("NF", "{"
       "\"name\":\"NORFOLK ISLAND\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%O%n%N%n%A%n%C %S %Z\""
       "}"));
   region_data.insert(std::make_pair("NG", "{"
       "\"name\":\"NIGERIA\","
       "\"lang\":\"fr\","
       "\"languages\":\"fr\","
+      "\"input_languages\":\"efi~en~ha~ig~yo\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z%n%S\","
       "\"state_name_type\":\"state\""
       "}"));
@@ -777,101 +937,122 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"NICARAGUA\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z%n%C, %S\","
       "\"state_name_type\":\"department\""
       "}"));
   region_data.insert(std::make_pair("NL", "{"
       "\"name\":\"NETHERLANDS\","
+      "\"input_languages\":\"nl\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("NO", "{"
       "\"name\":\"NORWAY\","
+      "\"input_languages\":\"nb~nn\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("NP", "{"
       "\"name\":\"NEPAL\","
+      "\"input_languages\":\"ne\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("NR", "{"
       "\"name\":\"NAURU CENTRAL PACIFIC\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en~na\","
       "\"fmt\":\"%N%n%O%n%A%n%S\","
       "\"require\":\"AS\","
       "\"state_name_type\":\"district\""
       "}"));
   region_data.insert(std::make_pair("NU", "{"
-      "\"name\":\"NIUE\""
+      "\"name\":\"NIUE\","
+      "\"input_languages\":\"en~niu\""
       "}"));
   region_data.insert(std::make_pair("NZ", "{"
       "\"name\":\"NEW ZEALAND\","
+      "\"input_languages\":\"en~mi\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("OM", "{"
       "\"name\":\"OMAN\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%Z%n%C\""
       "}"));
   region_data.insert(std::make_pair("PA", "{"
       "\"name\":\"PANAMA (REP.)\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S\""
       "}"));
   region_data.insert(std::make_pair("PE", "{"
-      "\"name\":\"PERU\""
+      "\"name\":\"PERU\","
+      "\"input_languages\":\"es~qu\""
       "}"));
   region_data.insert(std::make_pair("PF", "{"
       "\"name\":\"FRENCH POLYNESIA\","
+      "\"input_languages\":\"fr~ty\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C %S\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("PG", "{"
       "\"name\":\"PAPUA NEW GUINEA\","
+      "\"input_languages\":\"en~ho~tpi\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z %S\","
       "\"require\":\"ACS\""
       "}"));
   region_data.insert(std::make_pair("PH", "{"
       "\"name\":\"PHILIPPINES\","
+      "\"input_languages\":\"en~fil\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C%n%S\","
       "\"require\":\"AC\""
       "}"));
   region_data.insert(std::make_pair("PK", "{"
       "\"name\":\"PAKISTAN\","
+      "\"input_languages\":\"en~ur\","
       "\"fmt\":\"%N%n%O%n%A%n%C-%Z\""
       "}"));
   region_data.insert(std::make_pair("PL", "{"
       "\"name\":\"POLAND\","
+      "\"input_languages\":\"pl\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("PM", "{"
       "\"name\":\"ST. PIERRE AND MIQUELON\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("PN", "{"
       "\"name\":\"PITCAIRN\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("PR", "{"
       "\"name\":\"PUERTO RICO\","
+      "\"input_languages\":\"en~es\","
       "\"fmt\":\"%N%n%O%n%A%n%C PR %Z\","
       "\"require\":\"ACZ\","
       "\"zip_name_type\":\"zip\""
       "}"));
   region_data.insert(std::make_pair("PS", "{"
-      "\"name\":\"PALESTINIAN TERRITORY\""
+      "\"name\":\"PALESTINIAN TERRITORY\","
+      "\"input_languages\":\"ar\""
       "}"));
   region_data.insert(std::make_pair("PT", "{"
       "\"name\":\"PORTUGAL\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("PW", "{"
       "\"name\":\"PALAU\","
+      "\"input_languages\":\"en~pau\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -879,88 +1060,108 @@ std::map<std::string, std::string> InitRegionData() {
       "}"));
   region_data.insert(std::make_pair("PY", "{"
       "\"name\":\"PARAGUAY\","
+      "\"input_languages\":\"es~gn\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("QA", "{"
-      "\"name\":\"QATAR\""
+      "\"name\":\"QATAR\","
+      "\"input_languages\":\"ar\""
       "}"));
   region_data.insert(std::make_pair("RE", "{"
       "\"name\":\"REUNION\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("RO", "{"
       "\"name\":\"ROMANIA\","
+      "\"input_languages\":\"ro\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("RS", "{"
       "\"name\":\"REPUBLIC OF SERBIA\","
+      "\"input_languages\":\"sr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("RU", "{"
       "\"name\":\"RUSSIAN FEDERATION\","
+      "\"input_languages\":\"ru\","
       "\"fmt\":\"%Z %C  %n%A%n%O%n%N\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("RW", "{"
-      "\"name\":\"RWANDA\""
+      "\"name\":\"RWANDA\","
+      "\"input_languages\":\"en~fr~rw\""
       "}"));
   region_data.insert(std::make_pair("SA", "{"
       "\"name\":\"SAUDI ARABIA\","
+      "\"input_languages\":\"ar\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z\""
       "}"));
   region_data.insert(std::make_pair("SB", "{"
-      "\"name\":\"SOLOMON ISLANDS\""
+      "\"name\":\"SOLOMON ISLANDS\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("SC", "{"
       "\"name\":\"SEYCHELLES\","
+      "\"input_languages\":\"en~fr\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S\","
       "\"state_name_type\":\"island\""
       "}"));
   region_data.insert(std::make_pair("SE", "{"
       "\"name\":\"SWEDEN\","
+      "\"input_languages\":\"sv\","
       "\"fmt\":\"%O%n%N%n%A%nSE-%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("SG", "{"
       "\"name\":\"REP. OF SINGAPORE\","
+      "\"input_languages\":\"en~ms~ta~zh\","
       "\"fmt\":\"%N%n%O%n%A%nSINGAPORE %Z\","
       "\"require\":\"AZ\""
       "}"));
   region_data.insert(std::make_pair("SH", "{"
       "\"name\":\"SAINT HELENA\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("SI", "{"
       "\"name\":\"SLOVENIA\","
+      "\"input_languages\":\"sl\","
       "\"fmt\":\"%N%n%O%n%A%nSI- %Z %C\""
       "}"));
   region_data.insert(std::make_pair("SJ", "{"
       "\"name\":\"SVALBARD AND JAN MAYEN ISLANDS\","
+      "\"input_languages\":\"nb\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("SK", "{"
       "\"name\":\"SLOVAKIA\","
+      "\"input_languages\":\"sk\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("SL", "{"
-      "\"name\":\"SIERRA LEONE\""
+      "\"name\":\"SIERRA LEONE\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("SM", "{"
       "\"name\":\"SAN MARINO\","
+      "\"input_languages\":\"it\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"AZ\""
       "}"));
   region_data.insert(std::make_pair("SN", "{"
       "\"name\":\"SENEGAL\","
+      "\"input_languages\":\"fr~wo\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("SO", "{"
       "\"name\":\"SOMALIA\","
       "\"lang\":\"so\","
       "\"languages\":\"so\","
+      "\"input_languages\":\"ar~so\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S %Z\","
       "\"require\":\"ACS\""
       "}"));
@@ -968,76 +1169,94 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"SURINAME\","
       "\"lang\":\"nl\","
       "\"languages\":\"nl\","
+      "\"input_languages\":\"nl\","
       "\"fmt\":\"%N%n%O%n%A%n%C %X%n%S\""
       "}"));
   region_data.insert(std::make_pair("ST", "{"
       "\"name\":\"SAO TOME AND PRINCIPE\","
+      "\"input_languages\":\"pt\","
       "\"fmt\":\"%N%n%O%n%A%n%C %X\""
       "}"));
   region_data.insert(std::make_pair("SV", "{"
       "\"name\":\"EL SALVADOR\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z-%C%n%S\","
       "\"require\":\"ACS\""
       "}"));
   region_data.insert(std::make_pair("SZ", "{"
       "\"name\":\"SWAZILAND\","
+      "\"input_languages\":\"en~ss\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%Z\""
       "}"));
   region_data.insert(std::make_pair("TC", "{"
       "\"name\":\"TURKS AND CAICOS ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("TD", "{"
-      "\"name\":\"CHAD\""
+      "\"name\":\"CHAD\","
+      "\"input_languages\":\"ar~fr\""
       "}"));
   region_data.insert(std::make_pair("TF", "{"
       "\"name\":\"FRENCH SOUTHERN TERRITORIES\""
       "}"));
   region_data.insert(std::make_pair("TG", "{"
-      "\"name\":\"TOGO\""
+      "\"name\":\"TOGO\","
+      "\"input_languages\":\"fr\""
       "}"));
   region_data.insert(std::make_pair("TH", "{"
       "\"name\":\"THAILAND\","
       "\"lang\":\"th\","
       "\"languages\":\"th\","
-      "\"fmt\":\"%N%n%O%n%A%n%C%n%S %Z\""
+      "\"input_languages\":\"th\","
+      "\"fmt\":\"%N%n%O%n%A%n%C%n%S %Z\","
+      "\"lfmt\":\"%N%n%O%n%A%n%C%n%S %Z\""
       "}"));
   region_data.insert(std::make_pair("TJ", "{"
       "\"name\":\"TAJIKISTAN\","
+      "\"input_languages\":\"tg\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("TK", "{"
-      "\"name\":\"TOKELAU\""
+      "\"name\":\"TOKELAU\","
+      "\"input_languages\":\"en~tkl\""
       "}"));
   region_data.insert(std::make_pair("TL", "{"
-      "\"name\":\"TIMOR-LESTE\""
+      "\"name\":\"TIMOR-LESTE\","
+      "\"input_languages\":\"pt~tet\""
       "}"));
   region_data.insert(std::make_pair("TM", "{"
       "\"name\":\"TURKMENISTAN\","
+      "\"input_languages\":\"tk\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("TN", "{"
       "\"name\":\"TUNISIA\","
+      "\"input_languages\":\"ar~fr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("TO", "{"
-      "\"name\":\"TONGA\""
+      "\"name\":\"TONGA\","
+      "\"input_languages\":\"en~to\""
       "}"));
   region_data.insert(std::make_pair("TR", "{"
       "\"name\":\"TURKEY\","
+      "\"input_languages\":\"tr\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C/%S\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("TT", "{"
-      "\"name\":\"TRINIDAD AND TOBAGO\""
+      "\"name\":\"TRINIDAD AND TOBAGO\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("TV", "{"
       "\"name\":\"TUVALU\","
       "\"lang\":\"tyv\","
       "\"languages\":\"tyv\","
+      "\"input_languages\":\"en~tvl\","
       "\"fmt\":\"%N%n%O%n%A%n%X%n%C%n%S\","
       "\"state_name_type\":\"island\""
       "}"));
@@ -1045,24 +1264,30 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"TAIWAN\","
       "\"lang\":\"zh-hant\","
       "\"languages\":\"zh-hant\","
+      "\"input_languages\":\"zh\","
       "\"fmt\":\"%Z%n%S%C%n%A%n%O%n%N\","
+      "\"lfmt\":\"%N%n%O%n%A%n%C, %S %Z\","
       "\"require\":\"ACSZ\","
       "\"state_name_type\":\"county\""
       "}"));
   region_data.insert(std::make_pair("TZ", "{"
-      "\"name\":\"TANZANIA (UNITED REP.)\""
+      "\"name\":\"TANZANIA (UNITED REP.)\","
+      "\"input_languages\":\"en~sw\""
       "}"));
   region_data.insert(std::make_pair("UA", "{"
       "\"name\":\"UKRAINE\","
+      "\"input_languages\":\"ru~uk\","
       "\"fmt\":\"%Z %C%n%A%n%O%n%N\""
       "}"));
   region_data.insert(std::make_pair("UG", "{"
-      "\"name\":\"UGANDA\""
+      "\"name\":\"UGANDA\","
+      "\"input_languages\":\"en~sw\""
       "}"));
   // NOTE: The fmt value for UM and US differs from the i18napis fmt by the
   // insertion of a comma separating city and state.
   region_data.insert(std::make_pair("UM", "{"
       "\"name\":\"UNITED STATES MINOR OUTLYING ISLANDS\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S %Z\","
       "\"require\":\"ACS\","
       "\"zip_name_type\":\"zip\","
@@ -1072,6 +1297,7 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"UNITED STATES\","
       "\"lang\":\"en\","
       "\"languages\":\"en\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C, %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -1081,32 +1307,39 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"URUGUAY\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C %S\""
       "}"));
   region_data.insert(std::make_pair("UZ", "{"
       "\"name\":\"UZBEKISTAN\","
+      "\"input_languages\":\"uz\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C%n%S\""
       "}"));
   region_data.insert(std::make_pair("VA", "{"
       "\"name\":\"VATICAN\","
+      "\"input_languages\":\"la\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\""
       "}"));
   region_data.insert(std::make_pair("VC", "{"
-      "\"name\":\"SAINT VINCENT AND THE GRENADINES (ANTILLES)\""
+      "\"name\":\"SAINT VINCENT AND THE GRENADINES (ANTILLES)\","
+      "\"input_languages\":\"en\""
       "}"));
   region_data.insert(std::make_pair("VE", "{"
       "\"name\":\"VENEZUELA\","
       "\"lang\":\"es\","
       "\"languages\":\"es\","
+      "\"input_languages\":\"es\","
       "\"fmt\":\"%N%n%O%n%A%n%C %Z, %S\","
       "\"require\":\"ACS\""
       "}"));
   region_data.insert(std::make_pair("VG", "{"
       "\"name\":\"VIRGIN ISLANDS (BRITISH)\","
+      "\"input_languages\":\"en\","
       "\"require\":\"A\""
       "}"));
   region_data.insert(std::make_pair("VI", "{"
       "\"name\":\"VIRGIN ISLANDS (U.S.)\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%C %S %Z\","
       "\"require\":\"ACSZ\","
       "\"zip_name_type\":\"zip\","
@@ -1116,41 +1349,51 @@ std::map<std::string, std::string> InitRegionData() {
       "\"name\":\"VIET NAM\","
       "\"lang\":\"vi\","
       "\"languages\":\"vi\","
+      "\"input_languages\":\"vi\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%S\","
+      "\"lfmt\":\"%N%n%O%n%A%n%C%n%S\","
       "\"require\":\"AC\""
       "}"));
   region_data.insert(std::make_pair("VU", "{"
-      "\"name\":\"VANUATU\""
+      "\"name\":\"VANUATU\","
+      "\"input_languages\":\"bi~en~fr\""
       "}"));
   region_data.insert(std::make_pair("WF", "{"
       "\"name\":\"WALLIS AND FUTUNA ISLANDS\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("WS", "{"
-      "\"name\":\"SAMOA\""
+      "\"name\":\"SAMOA\","
+      "\"input_languages\":\"en~sm\""
       "}"));
   region_data.insert(std::make_pair("YE", "{"
       "\"name\":\"YEMEN\","
+      "\"input_languages\":\"ar\","
       "\"require\":\"AC\""
       "}"));
   region_data.insert(std::make_pair("YT", "{"
       "\"name\":\"MAYOTTE\","
+      "\"input_languages\":\"fr\","
       "\"fmt\":\"%O%n%N%n%A%n%Z %C %X\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("ZA", "{"
       "\"name\":\"SOUTH AFRICA\","
+      "\"input_languages\":\"af~en~nr~nso~ss~st~tn~ts~ve~xh~zu\","
       "\"fmt\":\"%N%n%O%n%A%n%C%n%Z\","
       "\"require\":\"ACZ\""
       "}"));
   region_data.insert(std::make_pair("ZM", "{"
       "\"name\":\"ZAMBIA\","
+      "\"input_languages\":\"en\","
       "\"fmt\":\"%N%n%O%n%A%n%Z %C\","
       "\"require\":\"AC\""
       "}"));
   region_data.insert(std::make_pair("ZW", "{"
-      "\"name\":\"ZIMBABWE\""
+      "\"name\":\"ZIMBABWE\","
+      "\"input_languages\":\"en~nd~sn\""
       "}"));
   return region_data;
 }
diff --git a/third_party/libaddressinput/chromium/cpp/src/retriever.cc b/third_party/libaddressinput/chromium/cpp/src/retriever.cc
index 7722ef2..90dfc24 100644
--- a/third_party/libaddressinput/chromium/cpp/src/retriever.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/retriever.cc
@@ -28,9 +28,9 @@
 #include <string>
 
 #include "fallback_data_store.h"
-#include "time_to_string.h"
 #include "util/md5.h"
 #include "util/stl_util.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
diff --git a/third_party/libaddressinput/chromium/cpp/src/rule.cc b/third_party/libaddressinput/chromium/cpp/src/rule.cc
index a94e44d..791ac9e 100644
--- a/third_party/libaddressinput/chromium/cpp/src/rule.cc
+++ b/third_party/libaddressinput/chromium/cpp/src/rule.cc
@@ -26,8 +26,7 @@
 #include "grit/libaddressinput_strings.h"
 #include "region_data_constants.h"
 #include "util/json.h"
-#include "util/string_compare.h"
-#include "util/string_split.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
@@ -219,11 +218,13 @@ Rule::Rule()
       name_(),
       latin_name_(),
       format_(),
+      latin_format_(),
       required_(),
       sub_keys_(),
       sub_names_(),
       sub_lnames_(),
       languages_(),
+      input_languages_(),
       language_(),
       postal_code_format_(),
       admin_area_name_message_id_(INVALID_MESSAGE_ID),
@@ -250,9 +251,11 @@ void Rule::CopyFrom(const Rule& rule) {
   name_ = rule.name_;
   latin_name_ = rule.latin_name_;
   format_ = rule.format_;
+  latin_format_ = rule.latin_format_;
   required_ = rule.required_;
   sub_keys_ = rule.sub_keys_;
   languages_ = rule.languages_;
+  input_languages_ = rule.input_languages_;
   language_ = rule.language_;
   sub_keys_ = rule.sub_keys_;
   sub_names_ = rule.sub_names_;
@@ -291,6 +294,10 @@ void Rule::ParseJsonRule(const Json& json_rule) {
     ParseAddressFieldsFormat(value, &format_);
   }
 
+  if (json_rule.GetStringValueForKey("lfmt", &value)) {
+    ParseAddressFieldsFormat(value, &latin_format_);
+  }
+
   if (json_rule.GetStringValueForKey("require", &value)) {
     ParseAddressFieldsRequired(value, &required_);
   }
@@ -316,6 +323,10 @@ void Rule::ParseJsonRule(const Json& json_rule) {
     SplitString(value, kSeparator, &languages_);
   }
 
+  if (json_rule.GetStringValueForKey("input_languages", &value)) {
+    SplitString(value, kSeparator, &input_languages_);
+  }
+
   if (json_rule.GetStringValueForKey("lang", &value)) {
     language_.swap(value);
   }
diff --git a/third_party/libaddressinput/chromium/cpp/src/rule.h b/third_party/libaddressinput/chromium/cpp/src/rule.h
index 80cc830..cc0a3d7 100644
--- a/third_party/libaddressinput/chromium/cpp/src/rule.h
+++ b/third_party/libaddressinput/chromium/cpp/src/rule.h
@@ -108,6 +108,12 @@ class Rule {
     return format_;
   }
 
+  // Returns the latinized format of the address as it should appear on an
+  // envelope.
+  const std::vector<std::vector<FormatElement> >& GetLatinFormat() const {
+    return latin_format_;
+  }
+
   // Returns the required fields for this rule.
   const std::vector<AddressField>& GetRequired() const { return required_; }
 
@@ -121,6 +127,12 @@ class Rule {
   // example ["de", "fr", "it"].
   const std::vector<std::string>& GetLanguages() const { return languages_; }
 
+  // Returns all of the languages codes for addresses that adhere to this rule,
+  // for example ["de", "fr", "gsw", "it"].
+  const std::vector<std::string>& GetInputLanguages() const {
+    return input_languages_;
+  }
+
   // Returns the language code of this rule, for example "de".
   const std::string& GetLanguage() const { return language_; }
 
@@ -168,12 +180,14 @@ class Rule {
   std::string name_;
   std::string latin_name_;
   std::vector<std::vector<FormatElement> > format_;
+  std::vector<std::vector<FormatElement> > latin_format_;
   std::vector<AddressField> required_;
   std::vector<std::string> sub_keys_;
   std::vector<std::string> sub_names_;
   // The Latin names (when |sub_names_| is not in Latin characters).
   std::vector<std::string> sub_lnames_;
   std::vector<std::string> languages_;
+  std::vector<std::string> input_languages_;
   std::string language_;
   std::string postal_code_format_;
   int admin_area_name_message_id_;
diff --git a/third_party/libaddressinput/chromium/cpp/src/time_to_string.cc b/third_party/libaddressinput/chromium/cpp/src/time_to_string.cc
deleted file mode 100644
index f1c2097..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/time_to_string.cc
+++ /dev/null
@@ -1,36 +0,0 @@
-// Copyright (C) 2014 Google Inc.
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#include "time_to_string.h"
-
-#include <cstdio>
-#include <ctime>
-#include <string>
-
-#ifdef _MSC_VER
-// http://msdn.microsoft.com/en-us/library/2ts7cx93%28v=vs.110%29.aspx
-#define snprintf _snprintf
-#endif  // _MSC_VER
-
-namespace i18n {
-namespace addressinput {
-
-std::string TimeToString(time_t time) {
-  char time_string[2 + 3 * sizeof time];
-  snprintf(time_string, sizeof time_string, "%ld", time);
-  return time_string;
-}
-
-}  // namespace addressinput
-}  // namespace i18n
diff --git a/third_party/libaddressinput/chromium/cpp/src/time_to_string.h b/third_party/libaddressinput/chromium/cpp/src/time_to_string.h
deleted file mode 100644
index ccd7ad9..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/time_to_string.h
+++ /dev/null
@@ -1,30 +0,0 @@
-// Copyright (C) 2014 Google Inc.
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#ifndef I18N_ADDRESSINPUT_TIME_TO_STRING_H_
-#define I18N_ADDRESSINPUT_TIME_TO_STRING_H_
-
-#include <ctime>
-#include <string>
-
-namespace i18n {
-namespace addressinput {
-
-// Returns |time| serialized into a string.
-std::string TimeToString(time_t time);
-
-}  // namespace addressinput
-}  // namespace i18n
-
-#endif  // I18N_ADDRESSINPUT_TIME_TO_STRING_H_
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_compare.cc b/third_party/libaddressinput/chromium/cpp/src/util/string_compare.cc
deleted file mode 100644
index d5f6a18..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/util/string_compare.cc
+++ /dev/null
@@ -1,31 +0,0 @@
-// Copyright (C) 2014 Google Inc.
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#include "string_compare.h"
-
-#include <libaddressinput/util/scoped_ptr.h>
-
-#include "canonicalize_string.h"
-
-namespace i18n {
-namespace addressinput {
-
-bool LooseStringCompare(const std::string& a, const std::string& b) {
-  scoped_ptr<StringCanonicalizer> canonicalizer(StringCanonicalizer::Build());
-  return canonicalizer->CanonicalizeString(a) ==
-         canonicalizer->CanonicalizeString(b);
-}
-
-}  // namespace addressinput
-}  // namespace i18n
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_compare.h b/third_party/libaddressinput/chromium/cpp/src/util/string_compare.h
deleted file mode 100644
index 4e0ecf7..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/util/string_compare.h
+++ /dev/null
@@ -1,30 +0,0 @@
-// Copyright (C) 2014 Google Inc.
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-// http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-#ifndef I18N_ADDRESSINPUT_UTIL_STRING_COMPARE_H_
-#define I18N_ADDRESSINPUT_UTIL_STRING_COMPARE_H_
-
-#include <string>
-
-namespace i18n {
-namespace addressinput {
-
-// Unicode (UTF-8) approximate string comparison. Designed for matching user
-// input against canonical data. Returns true for a match.
-bool LooseStringCompare(const std::string& a, const std::string& b);
-
-}  // namespace addressinput
-}  // namespace i18n
-
-#endif  // I18N_ADDRESSINPUT_UTIL_STRING_COMPARE_H_
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_split.cc b/third_party/libaddressinput/chromium/cpp/src/util/string_split.cc
deleted file mode 100644
index 114cd92..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/util/string_split.cc
+++ /dev/null
@@ -1,37 +0,0 @@
-// Copyright 2013 The Chromium Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file.
-//
-// The original source code is from:
-// http://src.chromium.org/viewvc/chrome/trunk/src/base/strings/string_split.cc?revision=216633
-
-#include "string_split.h"
-
-#include <cassert>
-#include <cstddef>
-#include <string>
-#include <vector>
-
-namespace i18n {
-namespace addressinput {
-
-void SplitString(const std::string& str, char s, std::vector<std::string>* r) {
-  assert(r != NULL);
-  r->clear();
-  size_t last = 0;
-  size_t c = str.size();
-  for (size_t i = 0; i <= c; ++i) {
-    if (i == c || str[i] == s) {
-      std::string tmp(str, last, i - last);
-      // Avoid converting an empty or all-whitespace source string into a vector
-      // of one empty string.
-      if (i != c || !r->empty() || !tmp.empty()) {
-        r->push_back(tmp);
-      }
-      last = i + 1;
-    }
-  }
-}
-
-}  // namespace addressinput
-}  // namespace i18n
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_split.h b/third_party/libaddressinput/chromium/cpp/src/util/string_split.h
deleted file mode 100644
index 6809296..0000000
--- a/third_party/libaddressinput/chromium/cpp/src/util/string_split.h
+++ /dev/null
@@ -1,34 +0,0 @@
-// Copyright 2013 The Chromium Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file.
-//
-// The original source code is from:
-// http://src.chromium.org/viewvc/chrome/trunk/src/base/strings/string_split.h?revision=236210
-//
-// Modifications from original:
-//   1) Supports only std::string type.
-//   2) Does not trim whitespace.
-
-#ifndef I18N_ADDRESSINPUT_UTIL_STRING_SPLIT_H_
-#define I18N_ADDRESSINPUT_UTIL_STRING_SPLIT_H_
-
-#include <string>
-#include <vector>
-
-namespace i18n {
-namespace addressinput {
-
-// Splits |str| into a vector of strings delimited by |c|, placing the results
-// in |r|. If several instances of |c| are contiguous, or if |str| begins with
-// or ends with |c|, then an empty string is inserted.
-//
-// |str| should not be in a multi-byte encoding like Shift-JIS or GBK in which
-// the trailing byte of a multi-byte character can be in the ASCII range.
-// UTF-8, and other single/multi-byte ASCII-compatible encodings are OK.
-// Note: |c| must be in the ASCII range.
-void SplitString(const std::string& str, char c, std::vector<std::string>* r);
-
-}  // namespace addressinput
-}  // namespace i18n
-
-#endif  // I18N_ADDRESSINPUT_UTIL_STRING_SPLIT_H_
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_util.cc b/third_party/libaddressinput/chromium/cpp/src/util/string_util.cc
new file mode 100644
index 0000000..ac10b10
--- /dev/null
+++ b/third_party/libaddressinput/chromium/cpp/src/util/string_util.cc
@@ -0,0 +1,80 @@
+// Copyright (C) 2014 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+#include "string_util.h"
+
+#include <libaddressinput/util/scoped_ptr.h>
+
+#include <cassert>
+#include <cstddef>
+#include <cstdio>
+#include <ctime>
+#include <string>
+#include <vector>
+
+#include "canonicalize_string.h"
+
+#ifdef _MSC_VER
+// http://msdn.microsoft.com/en-us/library/2ts7cx93%28v=vs.110%29.aspx
+#define snprintf _snprintf
+#endif  // _MSC_VER
+
+namespace i18n {
+namespace addressinput {
+
+std::string NormalizeLanguageCode(const std::string& language_code) {
+  std::string::size_type pos = language_code.find('-');
+  if (pos == std::string::npos) {
+    return language_code;
+  }
+  if (language_code.substr(pos) == "-latn") {
+    return language_code;
+  }
+  return language_code.substr(0, pos);
+}
+
+std::string TimeToString(time_t time) {
+  char time_string[2 + 3 * sizeof time];
+  snprintf(time_string, sizeof time_string, "%ld", time);
+  return time_string;
+}
+
+bool LooseStringCompare(const std::string& a, const std::string& b) {
+  scoped_ptr<StringCanonicalizer> canonicalizer(StringCanonicalizer::Build());
+  return canonicalizer->CanonicalizeString(a) ==
+         canonicalizer->CanonicalizeString(b);
+}
+
+// The original source code is from:
+// http://src.chromium.org/viewvc/chrome/trunk/src/base/strings/string_split.cc?revision=216633
+void SplitString(const std::string& str, char s, std::vector<std::string>* r) {
+  assert(r != NULL);
+  r->clear();
+  size_t last = 0;
+  size_t c = str.size();
+  for (size_t i = 0; i <= c; ++i) {
+    if (i == c || str[i] == s) {
+      std::string tmp(str, last, i - last);
+      // Avoid converting an empty or all-whitespace source string into a vector
+      // of one empty string.
+      if (i != c || !r->empty() || !tmp.empty()) {
+        r->push_back(tmp);
+      }
+      last = i + 1;
+    }
+  }
+}
+
+}  // namespace addressinput
+}  // namespace i18n
diff --git a/third_party/libaddressinput/chromium/cpp/src/util/string_util.h b/third_party/libaddressinput/chromium/cpp/src/util/string_util.h
new file mode 100644
index 0000000..7ebc630
--- /dev/null
+++ b/third_party/libaddressinput/chromium/cpp/src/util/string_util.h
@@ -0,0 +1,56 @@
+// Copyright (C) 2014 Google Inc.
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+#ifndef I18N_ADDRESSINPUT_UTIL_STRING_UTIL_H_
+#define I18N_ADDRESSINPUT_UTIL_STRING_UTIL_H_
+
+#include <string>
+#include <vector>
+
+namespace i18n {
+namespace addressinput {
+
+// Removes the language variation from |language_code|, unless the variation is
+// "latn". For example, returns "zh" for "zh-hans". Returns "zh-latn" for
+// "zh-latn".
+std::string NormalizeLanguageCode(const std::string& language_code);
+
+// Returns |time| serialized into a string.
+std::string TimeToString(time_t time);
+
+// Unicode (UTF-8) approximate string comparison. Designed for matching user
+// input against canonical data. Returns true for a match.
+bool LooseStringCompare(const std::string& a, const std::string& b);
+
+// Splits |str| into a vector of strings delimited by |c|, placing the results
+// in |r|. If several instances of |c| are contiguous, or if |str| begins with
+// or ends with |c|, then an empty string is inserted.
+//
+// |str| should not be in a multi-byte encoding like Shift-JIS or GBK in which
+// the trailing byte of a multi-byte character can be in the ASCII range.
+// UTF-8, and other single/multi-byte ASCII-compatible encodings are OK.
+// Note: |c| must be in the ASCII range.
+//
+// The original source code is from:
+// http://src.chromium.org/viewvc/chrome/trunk/src/base/strings/string_split.h?revision=236210
+//
+// Modifications from original:
+//   1) Supports only std::string type.
+//   2) Does not trim whitespace.
+void SplitString(const std::string& str, char c, std::vector<std::string>* r);
+
+}  // namespace addressinput
+}  // namespace i18n
+
+#endif  // I18N_ADDRESSINPUT_UTIL_STRING_UTIL_H_
diff --git a/third_party/libaddressinput/chromium/cpp/test/address_data_test.cc b/third_party/libaddressinput/chromium/cpp/test/address_data_test.cc
index a4d61c3..26659fa 100644
--- a/third_party/libaddressinput/chromium/cpp/test/address_data_test.cc
+++ b/third_party/libaddressinput/chromium/cpp/test/address_data_test.cc
@@ -85,6 +85,7 @@ TEST(AddressDataTest, FormatForDisplayAr) {
 TEST(AddressDataTest, FormatForDisplayJp) {
   AddressData address;
   address.country_code = "JP";
+  address.language_code = "ja";
   address.administrative_area = "東京都";
   address.locality = "渋谷区";
   address.postal_code = "150-8512";
@@ -108,6 +109,33 @@ TEST(AddressDataTest, FormatForDisplayJp) {
   EXPECT_EQ(expected, actual);
 }
 
+TEST(AddressDataTest, FormatForDisplayJpLatn) {
+  AddressData address;
+  address.country_code = "JP";
+  address.language_code = "ja-latn";
+  address.administrative_area = "Tokyo";
+  address.locality = "Shibuya-ku";
+  address.postal_code = "150-8512";
+  address.address_lines.push_back("26-1 Sakuragaoka-cho");
+  address.address_lines.push_back("Cerulean Tower 6F");
+  address.organization = "Google Japan Inc.";
+  address.recipient = "Miki Murakami";
+
+  std::vector<std::string> actual;
+  address.FormatForDisplay(&actual);
+
+  std::vector<std::string> expected;
+  expected.push_back(address.recipient);
+  expected.push_back(address.organization);
+  expected.insert(expected.end(),
+                  address.address_lines.begin(),
+                  address.address_lines.end());
+  expected.push_back(address.locality + ", "+ address.administrative_area);
+  expected.push_back(address.postal_code);
+
+  EXPECT_EQ(expected, actual);
+}
+
 TEST(AddressDataTest, FormatForDisplayWithStreetCi) {
   AddressData address;
   address.country_code = "CI";
diff --git a/third_party/libaddressinput/chromium/cpp/test/address_ui_test.cc b/third_party/libaddressinput/chromium/cpp/test/address_ui_test.cc
index 8fa508a..dadd8e7 100644
--- a/third_party/libaddressinput/chromium/cpp/test/address_ui_test.cc
+++ b/third_party/libaddressinput/chromium/cpp/test/address_ui_test.cc
@@ -75,7 +75,8 @@ TEST(AddressUiTest, RegionsAndComponentsAreValid) {
   for (size_t i = 0; i < region_codes.size(); ++i) {
     SCOPED_TRACE("Region code: " + region_codes[i]);
     EXPECT_EQ(2U, region_codes[i].size());
-    EXPECT_TRUE(ComponentsAreValid(BuildComponents(region_codes[i])));
+    EXPECT_TRUE(ComponentsAreValid(
+        BuildComponents(region_codes[i], std::string(), NULL)));
     EXPECT_FALSE(GetRequiredFields(region_codes[i]).empty());
   }
 }
@@ -83,7 +84,8 @@ TEST(AddressUiTest, RegionsAndComponentsAreValid) {
 // Verifies that BuildComponents() and GetRequiredFields() return an empty
 // vector for an invalid region code.
 TEST(AddressUiTest, InvalidRegionCodeReturnsEmptyVector) {
-  EXPECT_TRUE(BuildComponents("INVALID-REGION-CODE").empty());
+  EXPECT_TRUE(
+      BuildComponents("INVALID-REGION-CODE", std::string(), NULL).empty());
   EXPECT_TRUE(GetRequiredFields("INVALID-REGION-CODE").empty());
 }
 
@@ -119,6 +121,53 @@ INSTANTIATE_TEST_CASE_P(
         SeparatorData("th", " "),
         SeparatorData("en", ", ")));
 
+TEST(AddressUiTest, ComponentLanguageCodeTest) {
+  static const struct LanguageCodeData {
+    const char* region_code;
+    const char* ui_language_code;
+    const char* components_language_code;
+  } kLangugeCodes[] = {
+    {"AM", "", "hy"},
+    {"AM", "hy", "hy"},
+    {"AM", "en", "hy-latn"},
+    {"CN", "zh-hans", "zh-hans"},
+    {"CN", "zh-hant", "zh-hant"},
+    {"CN", "zh", "zh"},
+    {"CN", "zh-latn", "zh-latn"},
+    {"CN", "en", "zh-latn"},
+    {"CN", "ja", "zh-latn"},
+    {"CN", "ko", "zh-latn"},
+    {"HK", "zh", "zh"},
+    {"HK", "zh-hans", "zh-hans"},
+    {"HK", "zh-hant", "zh-hant"},
+    {"HK", "zh-latn", "zh-latn"},
+    {"HK", "en", "en"},
+    {"HK", "fr", "zh-latn"},
+    {"HK", "ja", "zh-latn"},
+    {"HK", "ko", "zh-latn"},
+    {"MO", "zh", "zh"},
+    {"MO", "pt", "pt"},
+    {"MO", "en", "zh-latn"},
+    {"AQ", "en", "en"},
+    {"AQ", "fr", "fr"},
+    {"AQ", "es", "es"},
+    {"AQ", "zh", "zh"}
+  };
+  static const size_t kArraySize =
+      sizeof kLangugeCodes / sizeof (LanguageCodeData);
+  for (size_t i = 0; i < kArraySize; ++i) {
+    SCOPED_TRACE(std::string("region code = ") +
+        kLangugeCodes[i].region_code + ", ui language code = " +
+        kLangugeCodes[i].ui_language_code + ", components language code = " +
+        kLangugeCodes[i].components_language_code);
+    std::string components_language_code;
+    EXPECT_FALSE(BuildComponents(kLangugeCodes[i].region_code,
+                                 kLangugeCodes[i].ui_language_code,
+                                 &components_language_code).empty());
+    EXPECT_EQ(
+        kLangugeCodes[i].components_language_code, components_language_code);
+  }
+}
 
 }  // namespace
 
diff --git a/third_party/libaddressinput/chromium/cpp/test/countryinfo_example_addresses_test.cc b/third_party/libaddressinput/chromium/cpp/test/countryinfo_example_addresses_test.cc
index 32a2deb..31ffefd5 100644
--- a/third_party/libaddressinput/chromium/cpp/test/countryinfo_example_addresses_test.cc
+++ b/third_party/libaddressinput/chromium/cpp/test/countryinfo_example_addresses_test.cc
@@ -32,7 +32,7 @@
 #include "fake_downloader.h"
 #include "fake_storage.h"
 #include "util/json.h"
-#include "util/string_split.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
diff --git a/third_party/libaddressinput/chromium/cpp/test/retriever_test.cc b/third_party/libaddressinput/chromium/cpp/test/retriever_test.cc
index 5caff83..90c9099 100644
--- a/third_party/libaddressinput/chromium/cpp/test/retriever_test.cc
+++ b/third_party/libaddressinput/chromium/cpp/test/retriever_test.cc
@@ -28,7 +28,7 @@
 #include "fake_downloader.h"
 #include "fake_storage.h"
 #include "region_data_constants.h"
-#include "time_to_string.h"
+#include "util/string_util.h"
 
 namespace i18n {
 namespace addressinput {
diff --git a/third_party/libaddressinput/chromium/cpp/test/util/string_split_unittest.cc b/third_party/libaddressinput/chromium/cpp/test/util/string_util_test.cc
index 73ca595..e5d4a1a 100644
--- a/third_party/libaddressinput/chromium/cpp/test/util/string_split_unittest.cc
+++ b/third_party/libaddressinput/chromium/cpp/test/util/string_util_test.cc
@@ -1,11 +1,11 @@
-// Copyright 2013 The Chromium Authors. All rights reserved.
+// Copyright 2014 The Chromium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 //
 // The original source code is from:
 // http://src.chromium.org/viewvc/chrome/trunk/src/base/strings/string_split_unittest.cc?revision=216633
 
-#include "util/string_split.h"
+#include "util/string_util.h"
 
 #include <string>
 #include <vector>
diff --git a/third_party/libaddressinput/libaddressinput.gyp b/third_party/libaddressinput/libaddressinput.gyp
index b0dfee2..3c89615 100644
--- a/third_party/libaddressinput/libaddressinput.gyp
+++ b/third_party/libaddressinput/libaddressinput.gyp
@@ -86,17 +86,13 @@
         '<(libaddressinput_dir)/cpp/src/rule.h',
         '<(libaddressinput_dir)/cpp/src/ruleset.cc',
         '<(libaddressinput_dir)/cpp/src/ruleset.h',
-        '<(libaddressinput_dir)/cpp/src/time_to_string.cc',
-        '<(libaddressinput_dir)/cpp/src/time_to_string.h',
+        '<(libaddressinput_dir)/cpp/src/util/canonicalize_string.h',
         '<(libaddressinput_dir)/cpp/src/util/json.h',
         '<(libaddressinput_dir)/cpp/src/util/md5.cc',
         '<(libaddressinput_dir)/cpp/src/util/md5.h',
         '<(libaddressinput_dir)/cpp/src/util/stl_util.h',
-        '<(libaddressinput_dir)/cpp/src/util/canonicalize_string.h',
-        '<(libaddressinput_dir)/cpp/src/util/string_compare.cc',
-        '<(libaddressinput_dir)/cpp/src/util/string_compare.h',
-        '<(libaddressinput_dir)/cpp/src/util/string_split.cc',
-        '<(libaddressinput_dir)/cpp/src/util/string_split.h',
+        '<(libaddressinput_dir)/cpp/src/util/string_util.cc',
+        '<(libaddressinput_dir)/cpp/src/util/string_util.h',
         '<(libaddressinput_dir)/cpp/src/util/trie.cc',
         '<(libaddressinput_dir)/cpp/src/util/trie.h',
       ],
@@ -155,7 +151,7 @@
         '<(libaddressinput_dir)/cpp/test/util/md5_unittest.cc',
         '<(libaddressinput_dir)/cpp/test/util/scoped_ptr_unittest.cc',
         '<(libaddressinput_dir)/cpp/test/util/stl_util_unittest.cc',
-        '<(libaddressinput_dir)/cpp/test/util/string_split_unittest.cc',
+        '<(libaddressinput_dir)/cpp/test/util/string_util_test.cc',
         '<(libaddressinput_dir)/cpp/test/util/trie_test.cc',
       ],
       'defines': [