Roll ICU to icu52

The ICU update does the following among other things: - Update EUC-JP (no more JIS X 212 round-trip coverage) per WHATWG encoding spec. - Add CP866 - Add far better/more extensive support for plural, format, etc - Numerous locale data update - Khmer/Lao line/word-breaking support - More compact Chinese/Japanese dictionary (now a part of the upstream instead of our local patch) - Better plural support that we plan to use right away. - Update icu/BUILD.gn : file list update, new defines, etc. - Update tests a. icu_string_conversions_unittests : drop iscii (nobody uses it) and remove JIS X 212 code points from the round-trip test b. l10n_util_unittests: Display names for zh-*. c. ThaiSnippet's expected result. (due to a Unicode grapheme definition change). d. Update Expected results in file_manager_browsertest/test_util.js (see http://crbug.com/383930) - Update SpellcheckerWordIterator a. Add U+0027 back to MidNumLet b. Add Lao and Khmer scripts to the list of scripts requiring dictionary-based word-breaking. - l10n_util : alias 'tl' to 'fil' (Tagalog to Filipino) - Update IdentityInternalsSingleTokenWebUITest.verifyGetters (DateTimeFormat-Full has 'at' before time, which is not handled by Date.parse() - update license.py because we don't have a separate Chinese/Japanese dictionary any more. It's now a part of ICU BUG=132145,277023,136148,360433,364072 TEST=base_unittests:*ICU*, net_unittests:*IDN*, ui_unittests:*Lang*, browser_tests (encoding related, Iden*verifyGet*), unit_tests:Ext*L10*, unit_tests:*Lang*, component_tests:*Snipp*, layout tests (encoding, date/calendar, line breaking, and others), build 'base_i18n_nacl', GN build bots. Review URL: https://codereview.chromium.org/265613002 git-svn-id: svn://svn.chromium.org/chrome/trunk/src@277111 0039d316-1c4b-4281-b951-d872f2087c98
Denger-Network · Jun 13, 2014 · 6589d67 · 6589d67
1 parent 0823c68
commit 6589d67
Show file tree

Hide file tree

Showing 12 changed files with 202 additions and 184 deletions.
diff --git a/DEPS b/DEPS
@@ -117,7 +117,7 @@ deps = {
     "/external/w3c/csswg-test.git@bacbb4a8dca702cd86646761fde96793db13d4f1",
 
   "src/third_party/icu":
-    "/trunk/deps/third_party/icu46@262949",
+    "/trunk/deps/third_party/icu52@275893",
 
   "src/third_party/libexif/sources":
     "/trunk/deps/third_party/libexif/sources@265008",

diff --git a/base/i18n/icu_string_conversions_unittest.cc b/base/i18n/icu_string_conversions_unittest.cc
@@ -186,13 +186,6 @@ static const struct {
    true,
    L"\x05E9\x05C1\x05B8\x05DC\x05D5\x05B9\x05DD",
    NULL},
-  // Hindi Devanagari (ISCII)
-  {"iscii-dev",
-   "\xEF\x42" "\xC6\xCC\xD7\xE8\xB3\xDA\xCF",
-   OnStringConversionError::FAIL,
-   true,
-   L"\x0928\x092E\x0938\x094D\x0915\x093E\x0930",
-   NULL},
   // Korean (EUC)
   {"euc-kr",
    "\xBE\xC8\xB3\xE7\xC7\xCF\xBC\xBC\xBF\xE4",
@@ -202,10 +195,10 @@ static const struct {
    NULL},
   // Japanese (EUC)
   {"euc-jp",
-   "\xA4\xB3\xA4\xF3\xA4\xCB\xA4\xC1\xA4\xCF\xB0\xEC\x8F\xB0\xA1\x8E\xA6",
+   "\xA4\xB3\xA4\xF3\xA4\xCB\xA4\xC1\xA4\xCF\xB0\xEC\x8E\xA6",
    OnStringConversionError::FAIL,
    true,
-   L"\x3053\x3093\x306B\x3061\x306F\x4E00\x4E02\xFF66",
+   L"\x3053\x3093\x306B\x3061\x306F\x4E00\xFF66",
    NULL},
   // Japanese (ISO-2022)
   {"iso-2022-jp",
@@ -238,13 +231,6 @@ static const struct {
    L"\x0E2A\x0E27\x0E31\x0E2A\x0E14\x0E35"
    L"\x0E04\x0E23\x0e31\x0E1A",
    NULL},
-  // Empty text
-  {"iscii-dev",
-   "",
-   OnStringConversionError::FAIL,
-   true,
-   L"",
-   NULL},
 };
 
 TEST(ICUStringConversionsTest, ConvertBetweenCodepageAndWide) {

diff --git a/chrome/browser/translate/translate_manager_render_view_host_unittest.cc b/chrome/browser/translate/translate_manager_render_view_host_unittest.cc
@@ -6,6 +6,7 @@
 #include <set>
 #include <vector>
 
+#include "base/macros.h"
 #include "base/memory/scoped_ptr.h"
 #include "base/prefs/pref_change_registrar.h"
 #include "base/prefs/pref_service.h"
@@ -621,22 +622,24 @@ TEST_F(TranslateManagerRenderViewHostTest, TestLanguages) {
   }
 }
 
+// A list of languages to fake being returned by the translate server.
+// Use only langauges for which Chrome's copy of ICU has
+// display names in English locale. To save space, Chrome's copy of ICU
+// does not have the display name for a language unless it's in the
+// Accept-Language list.
+static const char* server_language_list[] =
+    {"ach", "ak", "af", "en-CA", "zh", "yi", "fr-FR", "tl", "iw", "in", "xx"};
+static const char* alpha_language_list[] = {"ach", "yi"};
+
 // Test the fetching of languages from the translate server
 TEST_F(TranslateManagerRenderViewHostTest, FetchLanguagesFromTranslateServer) {
   std::vector<std::string> server_languages;
-  // A list of languages to fake being returned by the translate server.
-  server_languages.push_back("aa");
-  server_languages.push_back("ak");
-  server_languages.push_back("ab");
-  server_languages.push_back("en-CA");
-  server_languages.push_back("zh");
-  server_languages.push_back("yi");
-  server_languages.push_back("fr-FR");
-  server_languages.push_back("xx");
+  for (size_t i = 0; i < arraysize(server_language_list); ++i)
+    server_languages.push_back(server_language_list[i]);
 
   std::vector<std::string> alpha_languages;
-  alpha_languages.push_back("aa");
-  alpha_languages.push_back("yi");
+  for (size_t i = 0; i < arraysize(alpha_language_list); ++i)
+    alpha_languages.push_back(alpha_language_list[i]);
 
   // First, get the default languages list. Note that calling
   // GetSupportedLanguages() invokes RequestLanguageList() internally.
@@ -672,11 +675,12 @@ TEST_F(TranslateManagerRenderViewHostTest, FetchLanguagesFromTranslateServer) {
     EXPECT_NE(current_supported_languages.end(),
               std::find(current_supported_languages.begin(),
                         current_supported_languages.end(),
-                        lang));
+                        lang)) << "lang=" << lang;
     bool is_alpha =
         std::find(alpha_languages.begin(), alpha_languages.end(), lang) !=
         alpha_languages.end();
-    EXPECT_EQ(TranslateDownloadManager::IsAlphaLanguage(lang), is_alpha);
+    EXPECT_EQ(TranslateDownloadManager::IsAlphaLanguage(lang),
+              is_alpha) << "lang=" << lang;
   }
 }
 
@@ -685,18 +689,12 @@ TEST_F(TranslateManagerRenderViewHostTest, FetchLanguagesFromTranslateServer) {
 TEST_F(TranslateManagerRenderViewHostTest,
        FetchLanguagesFromTranslateServerWithoutAlpha) {
   std::vector<std::string> server_languages;
-  server_languages.push_back("aa");
-  server_languages.push_back("ak");
-  server_languages.push_back("ab");
-  server_languages.push_back("en-CA");
-  server_languages.push_back("zh");
-  server_languages.push_back("yi");
-  server_languages.push_back("fr-FR");
-  server_languages.push_back("xx");
+  for (size_t i = 0; i < arraysize(server_language_list); ++i)
+    server_languages.push_back(server_language_list[i]);
 
   std::vector<std::string> alpha_languages;
-  alpha_languages.push_back("aa");
-  alpha_languages.push_back("yi");
+  for (size_t i = 0; i < arraysize(alpha_language_list); ++i)
+    alpha_languages.push_back(alpha_language_list[i]);
 
   // call GetSupportedLanguages to call RequestLanguageList internally.
   std::vector<std::string> default_supported_languages;
@@ -718,8 +716,9 @@ TEST_F(TranslateManagerRenderViewHostTest,
     EXPECT_NE(current_supported_languages.end(),
               std::find(current_supported_languages.begin(),
                         current_supported_languages.end(),
-                        lang));
-    EXPECT_FALSE(TranslateDownloadManager::IsAlphaLanguage(lang));
+                        lang)) << "lang=" << lang;
+    EXPECT_FALSE(TranslateDownloadManager::IsAlphaLanguage(lang)) <<
+        "lang=" << lang;
   }
 }
 

diff --git a/chrome/browser/ui/webui/identity_internals_ui_browsertest.js b/chrome/browser/ui/webui/identity_internals_ui_browsertest.js
@@ -43,8 +43,10 @@ BaseIdentityInternalsWebUITest.prototype = {
    * @return {Date} Expiration date of the token.
    */
   getExpirationTime: function(tokenEntry) {
+    // Full-date format has 'at' between date and time in en-US, but
+    // ECMAScript's Date.parse cannot grok it.
     return Date.parse(tokenEntry.querySelector('.expiration-time')
-        .innerText);
+        .innerText.replace(' at ', ' '));
   },
 
   /**
@@ -162,9 +164,11 @@ TEST_F('IdentityInternalsSingleTokenWebUITest', 'verifyGetters', function() {
       tokenListEntries[0].querySelector('.access-token').innerText);
   expectEquals(this.getTokenStatus(tokenListEntries[0]),
       tokenListEntries[0].querySelector('.token-status').innerText);
+  // Full-date format has 'at' between date and time in en-US, but
+  // ECMAScript's Date.parse cannot grok it.
   expectEquals(this.getExpirationTime(tokenListEntries[0]),
       Date.parse(tokenListEntries[0].querySelector('.expiration-time')
-          .innerText));
+          .innerText.replace(' at ', ' ')));
   var scopes = tokenListEntries[0].querySelector('.scope-list')
       .innerHTML.split('<br>');
   var actualScopes = this.getScopes(tokenListEntries[0]);

diff --git a/chrome/renderer/spellchecker/spellcheck_worditerator.cc b/chrome/renderer/spellchecker/spellcheck_worditerator.cc
@@ -67,7 +67,10 @@ void SpellcheckCharAttribute::CreateRuleSets(const std::string& language) {
       // better, but it leads to an empty set error in Thai.
       // "$ALetter   = [[\\p{script=%s}] & [\\p{Word_Break = ALetter}]];"
       "$ALetter      = [\\p{script=%s}%s];"
-      "$MidNumLet    = [\\p{Word_Break = MidNumLet}];"
+      // U+0027 (single quote/apostrophe) is not in MidNumLet any more
+      // in UAX 29 rev 21 or later. For our purpose, U+0027
+      // has to be treated as MidNumLet. ( http://crbug.com/364072 )
+      "$MidNumLet    = [\\p{Word_Break = MidNumLet} \\u0027];"
       "$MidLetter    = [\\p{Word_Break = MidLetter}%s];"
       "$MidNum       = [\\p{Word_Break = MidNum}];"
       "$Numeric      = [\\p{Word_Break = Numeric}];"
@@ -153,7 +156,8 @@ void SpellcheckCharAttribute::CreateRuleSets(const std::string& language) {
       "$ALetterPlus  = [$ALetter [$dictionary-$Extend-$Control]];";
   const char kWithoutDictionary[] = "$ALetterPlus  = $ALetter;";
   const char* aletter_plus = kWithoutDictionary;
-  if (script_code_ == USCRIPT_HANGUL || script_code_ == USCRIPT_THAI)
+  if (script_code_ == USCRIPT_HANGUL || script_code_ == USCRIPT_THAI ||
+      script_code_ == USCRIPT_LAO || script_code_ == USCRIPT_KHMER)
     aletter_plus = kWithDictionary;
 
   // Treat numbers as word characters except for Arabic and Hebrew.

diff --git a/chrome/test/data/extensions/api_test/file_manager_browsertest/test_util.js b/chrome/test/data/extensions/api_test/file_manager_browsertest/test_util.js
@@ -203,93 +203,93 @@ TestEntryInfo.prototype.getExpectedRow = function() {
 var ENTRIES = {
   hello: new TestEntryInfo(
       EntryType.FILE, 'text.txt', 'hello.txt',
-      'text/plain', SharedOption.NONE, 'Sep 4, 1998 12:34 PM',
+      'text/plain', SharedOption.NONE, 'Sep 4, 1998, 12:34 PM',
       'hello.txt', '51 bytes', 'Plain text'),
 
   world: new TestEntryInfo(
       EntryType.FILE, 'video.ogv', 'world.ogv',
-      'text/plain', SharedOption.NONE, 'Jul 4, 2012 10:35 AM',
+      'text/plain', SharedOption.NONE, 'Jul 4, 2012, 10:35 AM',
       'world.ogv', '59 KB', 'OGG video'),
 
   unsupported: new TestEntryInfo(
       EntryType.FILE, 'random.bin', 'unsupported.foo',
-      'application/x-foo', SharedOption.NONE, 'Jul 4, 2012 10:36 AM',
+      'application/x-foo', SharedOption.NONE, 'Jul 4, 2012, 10:36 AM',
       'unsupported.foo', '8 KB', 'FOO file'),
 
   desktop: new TestEntryInfo(
       EntryType.FILE, 'image.png', 'My Desktop Background.png',
-      'text/plain', SharedOption.NONE, 'Jan 18, 2038 1:02 AM',
+      'text/plain', SharedOption.NONE, 'Jan 18, 2038, 1:02 AM',
       'My Desktop Background.png', '272 bytes', 'PNG image'),
 
   image2: new TestEntryInfo(
       EntryType.FILE, 'image2.png', 'image2.png',
-      'image/png', SharedOption.NONE, 'Jan 18, 2038 1:02 AM',
+      'image/png', SharedOption.NONE, 'Jan 18, 2038, 1:02 AM',
       'image2.png', '272 bytes', 'PNG image'),
 
   image3: new TestEntryInfo(
       EntryType.FILE, 'image3.jpg', 'image3.jpg',
-      'image/jpg', SharedOption.NONE, 'Jan 18, 2038 1:02 AM',
+      'image/jpg', SharedOption.NONE, 'Jan 18, 2038, 1:02 AM',
       'image3.jpg', '272 bytes', 'JPEG image'),
 
   beautiful: new TestEntryInfo(
       EntryType.FILE, 'music.ogg', 'Beautiful Song.ogg',
-      'text/plain', SharedOption.NONE, 'Nov 12, 2086 12:00 PM',
+      'text/plain', SharedOption.NONE, 'Nov 12, 2086, 12:00 PM',
       'Beautiful Song.ogg', '14 KB', 'OGG audio'),
 
   photos: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'photos',
-      null, SharedOption.NONE, 'Jan 1, 1980 11:59 PM',
+      null, SharedOption.NONE, 'Jan 1, 1980, 11:59 PM',
       'photos', '--', 'Folder'),
 
   testDocument: new TestEntryInfo(
       EntryType.FILE, null, 'Test Document',
       'application/vnd.google-apps.document',
-      SharedOption.NONE, 'Apr 10, 2013 4:20 PM',
+      SharedOption.NONE, 'Apr 10, 2013, 4:20 PM',
       'Test Document.gdoc', '--', 'Google document'),
 
   testSharedDocument: new TestEntryInfo(
       EntryType.FILE, null, 'Test Shared Document',
       'application/vnd.google-apps.document',
-      SharedOption.SHARED, 'Mar 20, 2013 10:40 PM',
+      SharedOption.SHARED, 'Mar 20, 2013, 10:40 PM',
       'Test Shared Document.gdoc', '--', 'Google document'),
 
   newlyAdded: new TestEntryInfo(
       EntryType.FILE, 'music.ogg', 'newly added file.ogg',
-      'audio/ogg', SharedOption.NONE, 'Sep 4, 1998 12:00 AM',
+      'audio/ogg', SharedOption.NONE, 'Sep 4, 1998, 12:00 AM',
       'newly added file.ogg', '14 KB', 'OGG audio'),
 
   directoryA: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'A',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'A', '--', 'Folder'),
 
   directoryB: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'A/B',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'B', '--', 'Folder'),
 
   directoryC: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'A/B/C',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'C', '--', 'Folder'),
 
   directoryD: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'D',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'D', '--', 'Folder'),
 
   directoryE: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'D/E',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'E', '--', 'Folder'),
 
   directoryF: new TestEntryInfo(
       EntryType.DIRECTORY, null, 'D/E/F',
-      null, SharedOption.NONE, 'Jan 1, 2000 1:00 AM',
+      null, SharedOption.NONE, 'Jan 1, 2000, 1:00 AM',
       'F', '--', 'Folder'),
 
   zipArchive: new TestEntryInfo(
       EntryType.FILE, 'archive.zip', 'archive.zip',
-      'application/x-zip', SharedOption.NONE, 'Jan 1, 2014 1:00 AM',
+      'application/x-zip', SharedOption.NONE, 'Jan 1, 2014, 1:00 AM',
       'archive.zip', '533 bytes', 'Zip archive')
 };
diff --git a/components/query_parser/snippet.h b/components/query_parser/snippet.h
@@ -33,13 +33,13 @@ class Snippet {
   // with no overlapping elements.
   //
   // NOTE: the positions returned are in terms of UTF8 encoding. To convert the
-  // offsets to wide, use ConvertMatchPositionsToWide.
+  // offsets to UTF-16, use ConvertMatchPositionsToWide
   static void ExtractMatchPositions(const std::string& offsets_str,
                                     const std::string& column_num,
                                     MatchPositions* match_positions);
 
   // Converts match positions as returned from ExtractMatchPositions to be in
-  // terms of a wide string.
+  // terms of a UTF-16 2-byte code unit.
   static void ConvertMatchPositionsToWide(
       const std::string& utf8_string,
       Snippet::MatchPositions* match_positions);