Modularize Compact Language Detector 2 (CLD2) data sources

build/common.gypi

 # Copyright (c) 2012 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.
 
 # IMPORTANT:
 # Please don't directly include this file if you are building via gyp_chromium,
 # since gyp_chromium is automatically forcing its inclusion.
 {
   # Variables expected to be overriden on the GYP command line (-D) or by
   # ~/.gyp/include.gypi.
@@ skipping 431 matching lines @@
 
       # For CLD2, the size of the tables that should be included in the build
       # Only evaluated if cld_version == 2 or if building the CLD2 dynamic data
       # tool explicitly.
       # See third_party/cld_2/cld_2.gyp for more information.
       #   0: Small tables, lower accuracy
       #   1: Medium tables, medium accuracy
       #   2: Large tables, high accuracy
       'cld2_table_size%': 2,
 
-      # Set the way CLD is compiled. Only evaluated if cld_version == 2.
-      #   0: static, language scoring tables compiled into the binary
-      #   1: dynamic, language scoring tables live in a data file that must
-      #      be loaded at runtime.
-      'cld2_dynamic%': 0,
-
-      # Whether CLD2 is a component. Only evaluated if cld_version == 2 and
-      # cld2_dynamic == 1.
-      #   0: Not a component. If cld2_dynamic == 1, it is up to the distribution
-      #      to ensure that the data file is provided if desired.
-      #   1: Componentized. CLD data should be obtained via the Component
-      #      Updater.
-      'cld2_is_component%': 0,
+      # The data acquisition mode for CLD2. Possible values are:
+      #   static:     CLD2 data is statically linked to the executable.
+      #   standalone: CLD2 data is provided in a standalone file that is
+      #               bundled with the executable.
+      #   component:  CLD2 data is provided as a Chrome "component" and is
+      #               downloaded via the component updater.
+      'cld2_data_source': 'static',
 
       # Enable spell checker.
       'enable_spellcheck%': 1,
 
       # Webrtc compilation is enabled by default. Set to 0 to disable.
       'enable_webrtc%': 1,
 
       # Enables use of the session service, which is enabled by default.
       # Support for disabling depends on the platform.
       'enable_session_service%': 1,
@@ skipping 203 matching lines @@
         }],
 
         ['OS=="win" or OS=="mac" or (OS=="linux" and chromeos==0)', {
           'enable_one_click_signin%': 1,
         }],
 
         ['OS=="android"', {
           'enable_extensions%': 0,
           'enable_google_now%': 0,
           'cld_version%': 1,
-          'cld2_dynamic%': 0,
-          'cld2_is_component%': 0,
           'enable_spellcheck%': 0,
           'enable_themes%': 0,
           'remoting%': 0,
           'arm_neon%': 0,
           'arm_neon_optional%': 1,
           'native_discardable_memory%': 1,
           'native_memory_pressure_signals%': 1,
           'enable_printing%': 2,
           'enable_task_manager%':0,
            # Set to 1 once we have a notification system for Android.
@@ skipping 29 matching lines @@
 
         ['OS=="android"', {
           'enable_webrtc%': 1,
         }],
 
         ['OS=="ios"', {
           'disable_ftp_support%': 1,
           'enable_extensions%': 0,
           'enable_google_now%': 0,
           'cld_version%': 1,
-          'cld2_dynamic%': 0,
           'enable_printing%': 0,
           'enable_session_service%': 0,
           'enable_themes%': 0,
           'enable_webrtc%': 0,
           'notifications%': 0,
           'remoting%': 0,
           'safe_browsing%': 0,
           'enable_managed_users%': 0,
           'enable_task_manager%': 0,
         }],
@@ skipping 334 matching lines @@
     'use_canvas_skia%': '<(use_canvas_skia)',
     'test_isolation_mode%': '<(test_isolation_mode)',
     'test_isolation_outdir%': '<(test_isolation_outdir)',
     'test_isolation_fail_on_missing': '<(test_isolation_fail_on_missing)',
     'enable_printing%': '<(enable_printing)',
     'win_pdf_metafile_for_printing%': '<(win_pdf_metafile_for_printing)',
     'enable_spellcheck%': '<(enable_spellcheck)',
     'enable_google_now%': '<(enable_google_now)',
     'cld_version%': '<(cld_version)',
     'cld2_table_size%': '<(cld2_table_size)',
-    'cld2_dynamic%': '<(cld2_dynamic)',
-    'cld2_is_component%': '<(cld2_is_component)',
+    'cld2_data_source%': '<(cld2_data_source)',
     'enable_captive_portal_detection%': '<(enable_captive_portal_detection)',
     'disable_file_support%': '<(disable_file_support)',
     'disable_ftp_support%': '<(disable_ftp_support)',
     'use_icu_alternatives_on_android%': '<(use_icu_alternatives_on_android)',
     'enable_task_manager%': '<(enable_task_manager)',
     'sas_dll_path%': '<(sas_dll_path)',
     'wix_path%': '<(wix_path)',
     'use_libjpeg_turbo%': '<(use_libjpeg_turbo)',
     'use_system_libjpeg%': '<(use_system_libjpeg)',
     'android_webview_build%': '<(android_webview_build)',
@@ skipping 1583 matching lines @@
       }],
       ['enable_background==1', {
         'defines': ['ENABLE_BACKGROUND=1'],
       }],
       ['enable_google_now==1', {
         'defines': ['ENABLE_GOOGLE_NOW=1'],
       }],
       ['cld_version!=0', {
         'defines': ['CLD_VERSION=<(cld_version)'],
       }],
-      ['cld2_dynamic!=0', {
-        'defines': ['CLD2_DYNAMIC_MODE=1'],
+      ['cld2_data_source=="static"', {
+        'defines': ['CLD_DATA_FROM_STATIC'],
+      }, {
+        # This is for CLD2 itself, which uses this check to enable dynamic mode
+        # during compilation. Don't check this flag in Chromium.
+        'defines': ['CLD2_DYNAMIC_MODE'],

[Takashi Toyoshima, 2014/06/23 08:49:59]

Would it be safe to move this CLD2_DYNAMIC_MODE definition inside cld_2.gyp?

[Andrew Hayden (chromium.org), 2014/06/23 13:20:34]

Almost, but not quite. The forward declarations of "loadDataFromRawAddress" and
"isDataLoaded" methods in CLD2 header files are guarded by the preprocessor
check, and these files are included in both the cld_2 compile as well as the
translate component compile. The linker complains that it can't locate the
symbols if the define is only done in cld_2.

To fix this we'd have to expose the methods in CLD2 directly. Not necessarily a
bad idea - we could have the ifdefs inside the methods instead, and declare them
unconditionally. I'll ping Dick Sites about this, but let's skip this change for
now unless you strongly object. Agree it would be nicer to do it that way.

[Takashi Toyoshima, 2014/06/24 02:09:47]

OK. Current approach sounds reasonable.

       }],
-      ['cld2_is_component!=0', {
-        'defines': ['CLD2_IS_COMPONENT=1'],
+      ['cld2_data_source=="standalone"', {
+        'defines': ['CLD_DATA_FROM_STANDALONE'],
+      }],
+      ['cld2_data_source=="component"', {
+        'defines': ['CLD_DATA_FROM_COMPONENT'],
       }],
       ['enable_printing==1', {
         'defines': ['ENABLE_FULL_PRINTING=1', 'ENABLE_PRINTING=1'],
       }],
       ['enable_printing==2', {
         'defines': ['ENABLE_PRINTING=1'],
       }],
       ['OS=="win" and win_pdf_metafile_for_printing==1', {
         'defines': ['WIN_PDF_METAFILE_FOR_PRINTING=1'],
       }],
@@ skipping 2759 matching lines @@
     # settings in target dicts.  SYMROOT is a special case, because many other
     # Xcode variables depend on it, including variables such as
     # PROJECT_DERIVED_FILE_DIR.  When a source group corresponding to something
     # like PROJECT_DERIVED_FILE_DIR is added to a project, in order for the
     # files to appear (when present) in the UI as actual files and not red
     # red "missing file" proxies, the correct path to PROJECT_DERIVED_FILE_DIR,
     # and therefore SYMROOT, needs to be set at the project level.
     'SYMROOT': '<(DEPTH)/xcodebuild',
   },
 }