[prev in list] [next in list] [prev in thread] [next in thread] 

List:       kde-i18n-doc
Subject:    Patch for Scripty to process mimetypes xml files
From:       Burkhard =?ISO-8859-1?Q?L=FCck?= <lueck () hube-lueck ! de>
Date:       2014-04-15 12:06:28
Message-ID: 2103493.Rhxs38Cg2g () parodia
[Download RAW message or body]

Hi,

attached a patch for Scripty to process mimetypes xml files.

It consists of two parts:

* a python file with a simple class to read translations from a po file 
  the class is really simple, but should be sufficient for the task

* some modifications for the bash scripts extract-xml.sh + update_translations
  this needs heavy review, my bash skills and understanding is very limited

Thanks
-- 
Burkhard Lück

["patch-mimetypes-xml.diff" (patch-mimetypes-xml.diff)]

Index: l10n-kde4/scripts/po2mimetypexml.py
===================================================================
--- l10n-kde4/scripts/po2mimetypexml.py	(Revision 0)
+++ l10n-kde4/scripts/po2mimetypexml.py	(Revision 0)
@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys, os, glob, re, codecs
+
+class message_catalog_simple(): #no plurals, no ctxt, no prev, only msgid + msgstr + \
fuzzy status +    def __init__(self,filename):
+        self.filename=os.path.abspath(filename)
+        self.name=os.path.basename(filename)
+        self.load()
+    def load(self):
+        f=codecs.open(self.filename,"r","utf8").read()
+        f=f.rstrip()+'\n' # >1 whitespaces (newlines etc) at end of file
+        try: f,obsoletemsg=f.split('\n#~ ',1) #falsch für "\n\n#, fuzzy\n#~ msgid \
..."  "\n\n#, Tag foo\n#~ msgid ..." +        except: pass
+        s=re.split('\n[:space:]*\n+',f) #2 oder mehrere '\n\n' + `\n \n'
+        if s[-1]!='' and not('msgstr' in s[-1] and 'msgid' in s[-1]): #s[-1] = #, \
fuzzy oder # Tag foo für obsolete +            s=s[:-1]
+        self.comraw, self.msgstr, self.msgid = [], [], []
+        for i in s:
+            commsgid=i.split('\nmsgstr')[0]
+            msgraw =i.split('\nmsgstr')[1:]
+            com = commsgid.split('\nmsgid')[0]
+            self.comraw.append(com)
+            midraw = (commsgid.split('\nmsgid')[1:])
+            if midraw == []: midraw = (commsgid.split('msgid')[1:]) #für pos nur \
mit msgid+msgstr zeilen, ohne #-zeilen davor +            \
mid=''.join(midraw).lstrip() +            mid=mid.replace('\\"', "\\'")
+            mid=mid.replace('\n','').replace('"','')
+            mid=mid.replace("\\'", '\\"')
+            msg=''.join(msgraw).lstrip()
+            msg=msg.replace('\\"', "\\'")
+            msg=msg.replace('\n','').replace('"','')
+            msg=msg.replace("\\'", '\\"')
+            self.msgid.append(mid)
+            self.msgstr.append(msg)
+    def messagerange(self):
+        return range(1,len(self.comraw))
+    def is_fuzzy(self, nr):
+        if '#, fuzzy' in self.comraw[nr]:
+           return True
+        else:
+           return False
+    def get_msgstr(self, msgid):
+        msgstr=''
+        for nr in self.messagerange():
+          if self.msgid[nr]==msgid:
+	    if self.is_fuzzy(nr):
+	      msgstr=''
+	    else:
+              msgstr=self.msgstr[nr]
+        return msgstr  
+
+if len(sys.argv) != 5:
+  print '\nUsage: python %s path/to/xmlfile path/to/l10ndir/ l10nmodulename \
pofilename.po' %os.path.basename(sys.argv[0]) +else:
+  xmlfilepath, xmlfilename, l10ndirpath, l10nmodulename, pofilename = sys.argv[1], \
sys.argv[1].split("/")[-1], sys.argv[2], sys.argv[3], sys.argv[4] +  \
begincommenttag="<comment>" +  endcommenttag="</comment>"
+  begincommentlangtag='<comment xml:lang='
+
+  xmllines=codecs.open(xmlfilepath,"rb","utf8").readlines()
+  xmlwithtranslation=''
+  xmlpofilelist=glob.glob("%s/*/messages/%s/%s" %(l10ndirpath, l10nmodulename, \
pofilename)) +
+  pofiledict={}
+  for pofile in xmlpofilelist:
+    langcode=pofile.split(l10ndirpath)[1].split("/")[0]
+    if langcode != "x-test":
+      po=message_catalog_simple(pofile)
+      pofiledict[langcode]=po
+  
+  for line in xmllines:
+    if begincommenttag in line:
+      indentwidth=line.split(begincommenttag)[0]
+      xmlwithtranslation += line
+      msgid=line.split(begincommenttag)[1].split(endcommenttag)[0]
+      for lang, po in sorted(pofiledict.iteritems()):
+        msgstr=pofiledict[lang].get_msgstr(msgid)
+        if msgstr!='':
+          transline='%s%s"%s">%s%s\n' %(indentwidth, begincommentlangtag, lang, \
msgstr, endcommenttag) +          xmlwithtranslation += transline
+    elif begincommentlangtag in line:
+      pass
+    else:
+      xmlwithtranslation += line
+      
+  modifiedxml=codecs.open("%s" %xmlfilepath,"w","utf8") # how to check for valid \
xml? +  modifiedxml.write(xmlwithtranslation)
+  modifiedxml.close()
Index: l10n-kde4/scripts/extract-xml.sh
===================================================================
--- l10n-kde4/scripts/extract-xml.sh	(Revision 1384186)
+++ l10n-kde4/scripts/extract-xml.sh	(Arbeitskopie)
@@ -36,6 +36,8 @@
        else
          echo "$xml_podir exists!"
        fi
+     $PO2MIMETYPEXML $xml_po_list $L10NDIR $PACKAGE $xml_file_po
+     svn commit $SVNQUIETFLAG -m "update $xml_po_list" $xml_po_list
      done
    fi
    exit_code=$?
Index: l10n-kde4/scripts/update_translations
===================================================================
--- l10n-kde4/scripts/update_translations	(Revision 1384186)
+++ l10n-kde4/scripts/update_translations	(Arbeitskopie)
@@ -200,6 +200,8 @@
 
         ( XGETTEXT=`which xgettext` \
           PACKAGE=$mod \
+          PO2MIMETYPEXML="python $BASEDIR/$transmod/scripts/po2mimetypexml.py" \
+          L10NDIR=$BASEDIR/$transmod \
           bash $BASEDIR/$transmod/scripts/extract-xml.sh)
 
         ( XGETTEXT=`which xgettext` \



[prev in list] [next in list] [prev in thread] [next in thread]