Issue 2625 - [cms] Crowdin synchronisation script

cms/bin/translate.py

 # coding: utf-8
 
 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2015 Eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus is distributed in the hope that it will be useful,
@@ skipping 23 matching lines @@
 logger = logging.getLogger("cms.bin.translate")
 
 class CrowdinAPI:
   FILES_PER_REQUEST = 20
 
   def __init__(self, api_key, project_name):
     self.api_key = api_key
     self.project_name = project_name
     self.connection = urllib3.connection_from_url("https://api.crowdin.com/")
 
+  def raw_request(self, request_method, api_endpoint, query_params=(), **kwargs):
+    url = "/api/project/%s/%s?%s" % (
+      urllib.quote(self.project_name),
+      urllib.quote(api_endpoint),
+      urllib.urlencode((("key", self.api_key),) + query_params)
+    )
+    try:
+      response = self.connection.request(
+        request_method, str(url), **kwargs
+      )
+    except urllib3.exceptions.HTTPError:
+      logger.error("Connection to API endpoint %s failed", url)
+      raise
+    if response.status < 200 or response.status >= 300:
+      logger.error("API call to %s failed:\n%s", url, response.data)
+      raise urllib3.exceptions.HTTPError(response.status)
+    return response
+
   def request(self, request_method, api_endpoint, data=None, files=None):
-    url = "/api/project/%s/%s?%s" % (
-      urllib.quote(self.project_name), urllib.quote(api_endpoint),
-      urllib.urlencode([("key", self.api_key), ("json", "1")])
-    )
-
     fields = []
     if data:
       for name, value in data.iteritems():
         if isinstance(value, basestring):
           fields.append((name, value))
         else:
           fields.extend((name + "[]", v) for v in value)
     if files:
       fields.extend(("files[%s]" % f[0], f) for f in files)
 
+    response = self.raw_request(
+      request_method, api_endpoint, (("json", "1"),),
+      fields=fields, preload_content=False
+    )
+
     try:
-      response = self.connection.request(
-        request_method, str(url), fields=fields,
-        timeout=urllib3.Timeout(connect=5)
-      )
-      if response.status < 200 or response.status >= 300:
-        raise urllib3.exceptions.HTTPError(response.status)
-    except urllib3.exceptions.HTTPError:
-      logger.error("API call to %s failed:\n%s", url, response.data)
-      raise
-
-    try:
-      return json.loads(response.data)
+      return json.load(response)
     except ValueError:
       logger.error("Invalid response returned by API endpoint %s", url)
       raise
 
 
 def grouper(iterable, n):
   iterator = iter(iterable)
   while True:
     chunk = tuple(itertools.islice(iterator, n))
     if not chunk:
@@ skipping 97 matching lines @@
 
 def update_existing_files(crowdin_api, existing_files, page_strings):
   add_update_files(crowdin_api, "update-file", "Updating %d existing pages...",
                    existing_files, page_strings)
 
 def upload_translations(crowdin_api, source_dir, new_files, required_locales):
   def open_locale_files(locale, files):
     for file_name in files:
       path = os.path.join(source_dir, "locales", locale, file_name)
       if os.path.isfile(path):
-        with open(path, "r") as f:

[Sebastian Noack, 2015/07/14 14:39:28]

Nit: mode="rb" for compatibility with Windows.

[kzar, 2015/07/15 09:51:24]

Done.

+        with open(path, "rb") as f:
           yield (file_name, f.read(), "application/json")
 
   if new_files:
     for locale in required_locales:
       for files in grouper(open_locale_files(locale, new_files),
                            crowdin_api.FILES_PER_REQUEST):
         logger.info("Uploading %d existing translation "
                     "files for locale %s...", len(files), locale)
         crowdin_api.request("POST", "upload-translation", files=files,
                             data={"language": locale})
 
 def remove_old_files(crowdin_api, old_files):
   for file_name in old_files:
     logger.info("Removing old file %s", file_name)
     crowdin_api.request("POST", "delete-file", data={"file": file_name})
 
 def remove_old_directories(crowdin_api, old_directories):
   for directory in reversed(sorted(old_directories, key=len)):
     logger.info("Removing old directory %s", directory)
     crowdin_api.request("POST", "delete-directory", data={"name": directory})
 
 def download_translations(crowdin_api, source_dir, required_locales):
   logger.info("Requesting generation of fresh translations archive...")
   result = crowdin_api.request("GET", "export")
   if result.get("success", {}).get("status") == "skipped":
     logger.warning("Archive generation skipped, either "
                    "no changes or API usage excessive")
 
   logger.info("Downloading translations archive...")
-  response = crowdin_api.connection.request(
-    "GET",
-    "/api/project/%s/download/all.zip?%s" % (
-      urllib.quote(crowdin_api.project_name),
-      urllib.urlencode([("key", crowdin_api.api_key)])
-    ), preload_content = False
-  )
-  if response.status < 200 or response.status >= 300:
-    raise urllib3.exceptions.HTTPError(response.status, response.data)
+  response = crowdin_api.raw_request("GET", "download/all.zip")
 

[Sebastian Noack, 2015/07/14 14:39:28]

The logic above is duplicated in CrowdInApi.request(). Perhaps moving the common
code into another method?

[kzar, 2015/07/15 09:51:25]

Done.

   logger.info("Extracting translations archive...")
   with zipfile.ZipFile(io.BytesIO(response.data), "r") as archive:
     locale_path = os.path.join(source_dir, "locales")
     # First clear existing translation files
     for root, dirs, files in os.walk(locale_path, topdown=True):
       if root == locale_path:
         dirs[:] = [d for d in dirs if d in required_locales]
       for f in files:
-        if f.endswith(".json"):
+        if f.lower().endswith(".json"):
           os.remove(os.path.join(root, f))
     # Then extract the new ones in place
     for member in archive.namelist():
       path, file_name = posixpath.split(member)
       ext = posixpath.splitext(file_name)[1]
       locale = path.split(posixpath.sep)[0]
-      if ext == ".json" and locale in required_locales:

[Sebastian Noack, 2015/07/14 14:39:29]

Nit: I think we should match the file extension case-insensitive.

[kzar, 2015/07/15 09:51:25]

Done.

+      if ext.lower() == ".json" and locale in required_locales:
         archive.extract(member, locale_path)
 
 def crowdin_sync(source_dir, crowdin_api_key):
   with FileSource(source_dir) as source:
     config = source.read_config()
     defaultlocale = config.get("general", "defaultlocale")
     crowdin_project_name = config.get("general", "crowdin-project-name")
 
     crowdin_api = CrowdinAPI(crowdin_api_key, crowdin_project_name)
 
@@ skipping 36 matching lines @@
 if __name__ == "__main__":
   if len(sys.argv) < 3:
     print >>sys.stderr, "Usage: python -m cms.bin.translate www_directory crowdin_project_api_key [logging_level]"
     sys.exit(1)
 
   logging.basicConfig()
   logger.setLevel(sys.argv[3] if len(sys.argv) > 3 else logging.INFO)
 
   source_dir, crowdin_api_key = sys.argv[1:3]
   crowdin_sync(source_dir, crowdin_api_key)