Add scripts for web pages lang templates conversion to POT/PO files and vice versa

3 files changed, 200 insertions, 0 deletions

diff --git a/websites/README b/websites/README
new file mode 100644
index 00000000..b4d89a49
--- /dev/null
+++ b/websites/README
@@ -0,0 +1,51 @@
+For some reasons usual conversion scripts for .lang files from Translate Toolkit
+do not work as expected.
+
+Nevertheless, the attached script may be useful for those who want to
+organize sustainable translation process of web pages translation.
+
+Prerequisites:
+
+Installed python-polib package:
+
+# urpmi python-polib
+
+I langpo.py:
+
+Usage:
+
+1. Copy the script into the folder with English .lang files.
+2. Run
+  python langpo.py
+3. Script will create .pot's for all .lang's in the folder. Translate pot's and
+   rename the translations into <lang_code>.po
+4. Run
+  python langpo.py
+   once more to create lang's for your language.
+
+If you ever need to update something (.lang's were updated or you found a typo,
+etc.) just run
+  python langpo.py
+
+Limitations:
+The script is useful only for Unicode translations.
+
+II translated_converter.py is a one-time converter for existing
+translations.
+
+Run it as
+
+python translated_converter.py -l <lang_code>
+
+(Ex.: python translated_converter.py -l el)
+
+in a folder of translations. Then copy po's with their folders into /en folder
+and run
+
+python langpo.py
+
+  * Both of these files are free software. They come without any warranty, to
+  * the extent permitted by applicable law. You can redistribute it
+  * and/or modify them under the terms of the Do What The Fuck You Want
+  * To Public License, Version 2, as published by Sam Hocevar. See
+  * http://sam.zoy.org/wtfpl/COPYING for more details.
diff --git a/websites/langpo.py b/websites/langpo.py
new file mode 100644
index 00000000..703635b6
--- /dev/null
+++ b/websites/langpo.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import errno, glob, polib, re, os
+from time import strftime
+
+for langfile in glob.glob('*.en.lang'):
+  langfilename = langfile.replace('.en.lang', '')
+  # Create localization directories if needed
+  podir = langfilename + '/po'
+  try:
+    os.makedirs(podir)
+  except OSError, e:
+    if e.errno != errno.EEXIST:
+        raise
+  #open lang file
+  text = open(langfile,"r").read()
+  newtext = text.split('\n\n',1)[0]
+
+  # Write POT file
+  pot = polib.POFile()
+  potcreationtime = strftime('%Y-%m-%d %H:%M%z')
+  pot.metadata = {
+    'Project-Id-Version': langfile,
+    'Report-Msgid-Bugs-To': 'mageia-i18n@mageia.org',
+    'POT-Creation-Date': potcreationtime,
+    'PO-Revision-Date': 'YEAR-MO-DA HO:MI+ZONE',
+    'Last-Translator': 'FULL NAME <EMAIL@ADDRESS>',
+    'Language-Team': 'LANGUAGE <LL@li.org>',
+    'MIME-Version': '1.0',
+    'Content-Type': 'text/plain; charset=CHARSET',
+    'Content-Transfer-Encoding': '8bit',
+    }
+
+  # Parse contents and add them to POT
+  messagetemplate='\n\n#\ .*?\n\n'
+  mpattern=re.compile(messagetemplate,re.DOTALL)
+  for mblock in mpattern.findall(text):
+    mblock_stripped = mblock.strip('\n')
+    message_comment, message_text = mblock.strip('\n').split('\n',1)
+    # Strip '# ' from comments
+    message_comment = message_comment.lstrip('# ')
+    message_id, message_str = message_text.split('\n',1)
+    # Strip ';' from msgid
+    message_id = message_id.lstrip(';')
+    potentry = polib.POEntry(
+      msgctxt = message_comment,
+      msgid = message_id.decode('utf-8'),
+      msgstr = '',
+	  occurrences=[(langfile,'')]
+	  )
+    pot.append(potentry)
+  potfilename = langfilename + '/po/' + langfilename + '.pot'
+  pot.save(potfilename)
+
+  # Parse PO files
+  for pofile in glob.glob(podir + '/*.po'):
+    lang = pofile[:-3].rsplit('/',1)[1]
+    pofilename = pofile
+    po = polib.pofile(pofilename)
+    po.merge(pot)
+    po.save(pofilename)
+    content = newtext + '\n\n'
+    for entry in po.translated_entries():
+      content = content + ('# ' + entry.msgctxt + '\n;' + entry.msgid + '\n' + entry.msgstr).encode('utf-8')
+      if entry.msgid == entry.msgstr:
+	content = content + ' {ok}'
+      content = content + '\n\n'
+    translatedlang = open(langfile.rstrip('.en.lang') + '.' + lang + '.lang', "w")
+    translatedlang.write(content)
+    translatedlang.close()
+
diff --git a/websites/translated_converter.py b/websites/translated_converter.py
new file mode 100644
index 00000000..14c17f32
--- /dev/null
+++ b/websites/translated_converter.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import errno, glob, polib, re, os, getopt, sys
+from time import strftime
+
+def usage():
+    print '\nUsage: python %s [OPTION]' %os.path.basename(sys.argv[0])
+    print '       generates po file for existing lang translations'
+    print 'Options: -h, --help                         : usage'
+    print '         -l lang_code, --language lang_code : code of the translation language'
+    sys.exit(2)
+try:
+    opts, args = getopt.getopt(sys.argv[1:], "hl:", ["help", "language="])
+except getopt.GetoptError:
+    usage() # print help information and exit
+
+language=''
+for o,a in opts:
+    if o in ("-h", "--help"):
+        usage()
+    if o in ("-l", "--language"):
+        lang_code=a
+
+if lang_code == '':
+    sys.exit('Empty language code')
+
+file_extension = '.' + lang_code + '.lang'
+file_mask = '*' + file_extension
+for langfile in glob.glob(file_mask):
+  langfilename = langfile.replace(file_extension, '')
+  # Create localization directories if needed
+  podir = langfilename + '/po'
+  try:
+    os.makedirs(podir)
+  except OSError, e:
+    if e.errno != errno.EEXIST:
+        raise
+  #open lang file
+  text = open(langfile,"r").read()
+  newtext = text.split('\n\n',1)[0]
+
+  # Write PO file
+  po = polib.POFile()
+  pocreationtime = strftime('%Y-%m-%d %H:%M%z')
+  po.metadata = {
+    'Project-Id-Version': langfile,
+    'Report-Msgid-Bugs-To': 'mageia-i18n@mageia.org',
+    'POT-Creation-Date': pocreationtime,
+    'PO-Revision-Date': pocreationtime,
+    'Last-Translator': 'Duffy Duck <d_duck@nowher.net>',
+    'Language-Team': lang_code + ' <mageia-' + lang_code + '@mageia.org>',
+    'MIME-Version': '1.0',
+    'Content-Type': 'text/plain; charset=UTF-8',
+    'Content-Transfer-Encoding': '8bit',
+    }
+
+  # Parse contents and add them to POT
+  messagetemplate='\n\n#\ .*?\n\n'
+  mpattern=re.compile(messagetemplate,re.DOTALL)
+  for mblock in mpattern.findall(text):
+    mblock_stripped = mblock.strip('\n')
+    message_comment, message_text = mblock.strip('\n').split('\n',1)
+    # Strip '# ' from comments
+    message_comment = message_comment.lstrip('# ')
+    message_id, message_str = message_text.split('\n',1)
+    # Strip ';' from msgid
+    message_id = message_id.lstrip(';')
+    potentry = polib.POEntry(
+      msgctxt = message_comment,
+      msgid = message_id.decode('utf-8'),
+      msgstr = message_str.decode('utf-8'),
+	  occurrences=[(langfile,'')]
+	  )
+    po.append(potentry)
+  pofilename = langfilename + '/po/' + lang_code + '.po'
+  po.save(pofilename)