Clean up third_party/cld.

1. Remove files we don't use that come from toolbar
2. Simplify the directory structure by removing the redundant
intermediary directories bar/toolbar/cld/i18n

This will bring CLD a step closer to where it can be open-sourced separately (or along with CED for encoding detection.). It's not there yet.


In addition to the clean-up, change |LanguageCode*| return 
'nb', 'he', 'fil' instead of 'no', 'iw', and 'tl'. 

Also, use LanguageCodeWithDialects instead of LanguageCode to get 'zh-CN' 
instead of 'zh'. This is to simplify the 3-way mapping between 
Chrome's UI locale code, CLD's language code and what's accepted by 
Google Translate. It's also another preparation for open-sourcing because
we'd better use the standard code rather than the obsolete code like 'iw'
when open-sourcing.

BUG=32759, 33613
TEST=third_party/cld builds on all platforms and pass the following tests:
- unit_tests: Extension*.DetectTabLanguage and CompactLangDetTest.* 
- browser_tests: ExtensionBrowserTest.Toolstrip


git-svn-id: svn://svn.chromium.org/chrome/trunk/src@38146 0039d316-1c4b-4281-b951-d872f2087c98

6 files changed, 9 insertions, 15 deletions

diff --git a/chrome/chrome_tests.gypi b/chrome/chrome_tests.gypi
index 066f627..10d4e45 100755
--- a/chrome/chrome_tests.gypi
+++ b/chrome/chrome_tests.gypi
@@ -875,7 +875,7 @@
         'test/v8_unit_test.cc',
         'test/v8_unit_test.h',
         'tools/convert_dict/convert_dict_unittest.cc',
-        '../third_party/cld/bar/toolbar/cld/i18n/encodings/compact_lang_det/compact_lang_det_unittest_small.cc',
+        '../third_party/cld/encodings/compact_lang_det/compact_lang_det_unittest_small.cc',
       ],
       'conditions': [
         ['chromeos==0', {
diff --git a/chrome/common/extensions/api/extension_api.json b/chrome/common/extensions/api/extension_api.json
index 75f8b9ca..00ef4ce 100755
--- a/chrome/common/extensions/api/extension_api.json
+++ b/chrome/common/extensions/api/extension_api.json
@@ -862,7 +862,7 @@
               {
                 "type": "string",
                 "name": "language",
-                "description": "An ISO language code such as <code>en</code> or <code>fr</code>. For a complete list of languages supported by this method, see the second column of <a href='http://src.chromium.org/viewvc/chrome/trunk/src/third_party/cld/bar/toolbar/cld/i18n/languages/internal/languages.cc'>kLanguageInfoTable</a>."
+                "description": "An ISO language code such as <code>en</code> or <code>fr</code>. For a complete list of languages supported by this method, see <a href='http://src.chromium.org/viewvc/chrome/trunk/src/third_party/cld/languages/internal/languages.cc'>kLanguageInfoTable</a>. The 2nd to 4th columns will be checked and the first non-NULL value will be returned except for Simplified Chinese for which zh-CN will be returned. For an unknown language, <code>und</code> will be returned."
               }
             ]
           }
diff --git a/chrome/common/extensions/docs/tabs.html b/chrome/common/extensions/docs/tabs.html
index cde0df3..82da463 100644
--- a/chrome/common/extensions/docs/tabs.html
+++ b/chrome/common/extensions/docs/tabs.html
@@ -1248,8 +1248,7 @@ For other examples and for help in viewing the source code, see
           <dd class="todo" style="display: none; ">
             Undocumented.
           </dd>
-          <dd>An ISO language code such as <code>en</code> or <code>fr</code>. For a complete list of languages supported by this method, see the second column of <a href="http://src.chromium.org/viewvc/chrome/trunk/src/third_party/cld/bar/toolbar/cld/i18n/languages/internal/languages.cc">kLanguageInfoTable</a>.</dd>
-
+          <dd>An ISO language code such as <code>en</code> or <code>fr</code>. For a complete list of languages supported by this method, see <a href='http://src.chromium.org/viewvc/chrome/trunk/src/third_party/cld/languages/internal/languages.cc'>kLanguageInfoTable</a>. The 2nd to 4th columns will be checked and the first non-NULL value will be returned except for Simplified Chinese for which zh-CN will be returned. For an unknown language, <code>und</code> will be returned.</dd>
           <!-- OBJECT PROPERTIES -->
           <dd style="display: none; ">
             <dl>
diff --git a/chrome/renderer/DEPS b/chrome/renderer/DEPS
index 35f9fb6..55936c2 100644
--- a/chrome/renderer/DEPS
+++ b/chrome/renderer/DEPS
@@ -12,7 +12,7 @@ include_rules = [
   "+webkit/glue",
   "+webkit/glue/plugins",
   "+v8/include",
-  "+third_party/cld/bar/toolbar/cld/i18n/encodings/compact_lang_det/win",
+  "+third_party/cld/encodings/compact_lang_det/win",
   "+third_party/npapi/bindings",
   "+third_party/sqlite/preprocessed",
   "+third_party/tcmalloc",
diff --git a/chrome/renderer/render_view.cc b/chrome/renderer/render_view.cc
index 872c518..cf74f81 100644
--- a/chrome/renderer/render_view.cc
+++ b/chrome/renderer/render_view.cc
@@ -67,7 +67,7 @@
 #include "net/base/net_errors.h"
 #include "skia/ext/bitmap_platform_device.h"
 #include "skia/ext/image_operations.h"
-#include "third_party/cld/bar/toolbar/cld/i18n/encodings/compact_lang_det/win/cld_unicodetext.h"
+#include "third_party/cld/encodings/compact_lang_det/win/cld_unicodetext.h"
 #include "third_party/WebKit/WebKit/chromium/public/WebAccessibilityCache.h"
 #include "third_party/WebKit/WebKit/chromium/public/WebAccessibilityObject.h"
 #include "third_party/WebKit/WebKit/chromium/public/WebCString.h"
diff --git a/chrome/renderer/render_view.h b/chrome/renderer/render_view.h
index c09bf32..7245df1 100644
--- a/chrome/renderer/render_view.h
+++ b/chrome/renderer/render_view.h
@@ -458,15 +458,10 @@ class RenderView : public RenderWidget,
 
   PageTranslator* page_translator() const { return page_translator_.get(); }
 
-  // Returns the ISO 639 language code of the current page (e.g. en, fr, zh).
-  // If ISO 639-1 code is not available for the language, ISO 639-2 3-letter code
-  // will be returned (e.g. kha for Khasi and und for undtermined). For traditional
-  // Chinse, 'zh-TW' will be returned while for simplified Chinse, 'zh' will be
-  // returned.
-  // TODO(jungshik): Make it return 'he' (the correct ISO 639 code for Hebrew)
-  // instead of the obsolete 'iw'. Perhaps, it's also better to return 'zh-Hans'
-  // (or 'zh-CN') for Simplified Chinese instead of 'zh' to be aligned with
-  // 'zh-TW' for Traditional Chinse.
+  // Returns the ISO 639 language code of the current page (e.g. en, fr).
+  // If ISO 639-1 code is not available for the language, ISO 639-2 3-letter
+  // code will be returned (e.g. fil for Filipino and und for undtermined). For
+  // traditional and simplified Chinse, 'zh-TW'  and 'zh-CN' will be returned.
   std::string DetectLanguage();
 
 #if defined(OS_MACOSX)