Add script to remove unneeded info from .po files

Differential Revision: D4264
This was SVN commit r26123.

source/tools/i18n/cleanTranslationFiles.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+#
+# Copyright (C) 2021 Wildfire Games.
+# This file is part of 0 A.D.
+#
+# 0 A.D. is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 2 of the License, or
+# (at your option) any later version.
+#
+# 0 A.D. is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with 0 A.D.  If not, see <http://www.gnu.org/licenses/>.
+
+"""
+This file removes unneeded personal data from the translators. Most notably
+the e-mail addresses. We need to translators' nicks for the credits, but no
+more data is required.
+
+TODO: ideally we don't even pull the e-mail addresses in the .po files.
+However that needs to be fixed on the transifex side, see rP25896. For now
+strip the e-mails using this script.
+"""
+
+import sys, os, glob, re, fileinput
+
+from i18n_helper import l10nToolsDirectory, projectRootDirectory
+
+def main():
+    l10nFolderName = "l10n"
+    transifexClientFolder = ".tx"
+
+    # Prepare some regexes.
+    commentMatch = re.compile('#.*')
+    translatorMatch = re.compile("(# [^,<]*)(?: <.*>)?(?:, [0-9,-]{4,9})")
+    lastTranslatorMatch = re.compile("(\"Last-Translator: [^,<]*)(?: <.*>)?( ?\\\\n\")")
+
+    for root, folders, filenames in os.walk(projectRootDirectory):
+        for folder in folders:
+            if folder == l10nFolderName:
+                if os.path.exists(os.path.join(root, folder, transifexClientFolder)):
+                    path = os.path.join(root, folder, "*.po")
+                    files = glob.glob(path)
+                    for file in files:
+                        usernames = []
+                        reached = False
+                        for line in fileinput.input(file.replace("\\", "/"), inplace=1):
+                            if reached:
+                                if line == "# \n":
+                                   line = ""
+                                m = translatorMatch.match(line)
+                                if m:
+                                    if m.group(1) in usernames:
+                                        line = ""
+                                    else:
+                                        line = m.group(1) + "\n"
+                                        usernames.append(m.group(1))
+                                m2 = lastTranslatorMatch.match(line)
+                                if m2:
+                                    line = m2.group(1) + "\\n\"\n"
+                            elif line.strip() == "# Translators:":
+                                reached = True
+                            sys.stdout.write(line)
+
+if __name__ == "__main__":
+    main()

source/tools/i18n/creditTranslators.py

@@ -128,8 +128,7 @@ newJSONData = {'Title': 'Translators', 'Content': []}
 # Now go through the list of languages and search the .po files for people
 
 # Prepare some regexes
-commentMatch = re.compile('#.*')
-translatorMatch = re.compile('# ([^,<]*)(?: <.*>)?, [0-9,-]{4,9}')
+translatorMatch = re.compile('# (.*)')
 deletedUsernameMatch = re.compile('[0-9a-f]{32}')
 
 # Search
@@ -144,13 +143,13 @@ for lang in langs.keys():
             reached = False
             for line in poFile:
                 if reached:
-                    if not commentMatch.match(line):
-                        break
                     m = translatorMatch.match(line)
-                    if m:
-                        username = m.group(1)
-                        if not deletedUsernameMatch.match(username):
-                            langsLists[lang].append(m.group(1))
+                    if not m:
+                        break
+
+                    username = m.group(1)
+                    if not deletedUsernameMatch.match(username):
+                        langsLists[lang].append(username)
                 if line.strip() == '# Translators:':
                     reached = True
             poFile.close()

source/tools/i18n/maintenanceTasks.sh

@@ -20,6 +20,9 @@ python3 "${SCRIPT_PATH}/pullTranslations.py"
 
 # Pre-Commit Cleanup  #########################################################
 
+echo ":: Removing unneeded data from the .po files…"
+python3 "${SCRIPT_PATH}/cleanTranslationFiles.py"
+
 echo ":: Reverting unnecessary changes…"
 python3 "${SCRIPT_PATH}/checkDiff.py"