Issue 1166 - Import strings from ABP for Firefox

import_locales.py

Index: import_locales.py
===================================================================
new file mode 100755
--- /dev/null
+++ b/import_locales.py
@@ -0,0 +1,115 @@
+#!/usr/bin/env python
+
+import codecs
+from ConfigParser import ConfigParser

[Wladimir Palant, 2014/08/06 06:09:04]

We generally use SafeConfigParser

+import os
+
+from buildtools import localeTools
+
+ie_locales = [
+  "ar",
+  "bg",
+  "ca",
+  "cs",
+  "da",
+  "de",
+  "el",
+  "en",
+  "es-ES",
+  "et",
+  "fi",
+  "fil",
+  "fr",
+  "he",
+  "hi",
+  "hr",
+  "hu",
+  "it",
+  "ja",
+  "kn",
+  "mr",
+  "ms",
+  "nb",
+  "nl",
+  "nn-NO",
+  "pl",
+  "pt-BR",
+  "pt-PT",
+  "ro",
+  "ru",
+  "sk",
+  "sv-SE",
+  "th",
+  "tr",
+  "uk",
+  "ur-PK",
+  "zh-CN",
+  "zh-TW"
+]

[Felix Dahlke, 2014/08/06 10:32:08]

Yes, I just took the list of locales we currently have, since I wasn't sure
where to get the others.

On second thought, I suppose I can just use the codes we use on Crowding for
these? Anything supported by IE but missing from Crowding should probably be
added there too, right?

+
+locale_mapping = {
+  "en": "en-US",
+  "hi": "hi-IN",
+  "nb": "nb-NO"

[Felix Dahlke, 2014/08/06 10:32:08]

Here's a follow-up for that:
https://issues.adblockplus.org/ticket/1177

+}
+
+strings_to_import = {
+  "firstRun.properties/firstRun_acceptableAdsHeadline": "first-run/first-run-aa-title",
+  "firstRun.properties/firstRun_acceptableAdsExplanation": "first-run/first-run-aa-text",
+  "filters.dtd/acceptableAds2.label": "settings/settings-acceptable-ads"
+}
+
+def read_gecko_locale_strings(locale):
+  locale_base_path = "libadblockplus/adblockplus/chrome/locale"
+  locale_files = ["firstRun.properties", "filters.dtd"]
+  locale_strings = {}
+  for locale_file in locale_files:
+    locale_file_path = "%s/%s/%s" % (
+      locale_base_path, locale, locale_file)
+    if os.path.exists(locale_file_path):
+      locale_strings[locale_file] = localeTools.readFile(locale_file_path)
+    else:
+      locale_strings[locale_file] = {}
+  return locale_strings
+
+# This is to keep the locale file format largely intact - ConfigParser.write()
+# puts spaces around equal signs.
+def write_ini(config, file):
+  for index, section in enumerate(config.sections()):
+    if index > 0:
+      file.write("\n")
+    file.write("[%s]\n" % section)
+    items = config.items(section)
+    for item in items:
+      file.write("%s=%s\n" % item)

[Felix Dahlke, 2014/08/06 10:32:08]

Done.

+
+def import_locale(ie_locale):
+  if ie_locale in locale_mapping:
+    gecko_locale = locale_mapping[ie_locale]
+  else:
+    gecko_locale = ie_locale
+  gecko_locale_strings = read_gecko_locale_strings(gecko_locale)
+
+  ie_locale_path = "locales/%s.ini" % ie_locale
+  config = ConfigParser()
+  config.optionxform = str
+  with codecs.open(ie_locale_path, "r", "utf-8") as ie_locale_file:
+    config.readfp(ie_locale_file)
+
+  for source, target in strings_to_import.iteritems():
+    source_section, source_key = source.split("/")
+    target_section, target_key = target.split("/")
+    if source_key in gecko_locale_strings[source_section]:
+      value = gecko_locale_strings[source_section][source_key]
+      value = value.replace("&", "")

[Wladimir Palant, 2014/08/06 06:11:04]

This won't do the job for CJK locales. The strings there use Latin access keys
like this: "blablabla (&x)". You need to remove " (&x)" at the end of the string
and not just &. 

+      config.set(target_section, target_key, value)
+
+  with codecs.open(ie_locale_path, "w", "utf-8") as ie_locale_file:
+    write_ini(config, ie_locale_file)
+
+def import_locales():
+  for ie_locale in ie_locales:
+    import_locale(ie_locale)
+
+if __name__ == "__main__":
+  import_locales()