diff options
author | Ivo Hinkelmann <ihi@openoffice.org> | 2010-07-07 15:35:17 +0200 |
---|---|---|
committer | Ivo Hinkelmann <ihi@openoffice.org> | 2010-07-07 15:35:17 +0200 |
commit | fb9f27fc9881ad5670bfe4d9f96438bf2322b24d (patch) | |
tree | 74279553ba3c958297d104a9cbc4c935247ea497 /l10ntools/scripts | |
parent | bb7dd792818f8404d6e756505469d17350eebd83 (diff) |
l10ntxt: #i113008# add support for xtx files (single text files)
Diffstat (limited to 'l10ntools/scripts')
-rw-r--r-- | l10ntools/scripts/const.py | 39 | ||||
-rw-r--r-- | l10ntools/scripts/l10ntool.py | 188 | ||||
-rw-r--r-- | l10ntools/scripts/sdf.py | 240 | ||||
-rwxr-xr-x | l10ntools/scripts/xtxex | 47 | ||||
-rw-r--r-- | l10ntools/scripts/xtxex.py | 92 |
5 files changed, 606 insertions, 0 deletions
diff --git a/l10ntools/scripts/const.py b/l10ntools/scripts/const.py new file mode 100644 index 000000000000..2d514eabdab6 --- /dev/null +++ b/l10ntools/scripts/const.py @@ -0,0 +1,39 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org 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 Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + +# Pseudo const +class _const: + class ConstError(TypeError): pass + def __setattr__(self, name, value): + if self.__dict__.has_key(name): + raise self.ConstError, "Can't rebind const(%s)"%name + self.__dict__[name] = value + +import sys +sys.modules[__name__] = _const() + + diff --git a/l10ntools/scripts/l10ntool.py b/l10ntools/scripts/l10ntool.py new file mode 100644 index 000000000000..caa15b7efd17 --- /dev/null +++ b/l10ntools/scripts/l10ntool.py @@ -0,0 +1,188 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org 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 Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + +from optparse import OptionParser +from sdf import SdfData +import string , sys , os + +class abstractL10nTool: + _options = {} + _args = "" + _resource_type = "" + _source_language = "en-US" + + ##### Implement these abstract methods + + ##### Nameing scheme for the output files + def get_outputfile_format_str(self): + # filename,fileNoExt,language,extension,pathPrefix,pathPostFix,path + return "{path}/{fileNoExt}_{language}.{extension}" + + ################################# Merge single files ########################################### + + ##### Merge a single file + def merge_file(self, inputfilename, outputfilename, parsed_file_ref, lang, is_forced_lang, sdfdata): + pass + + ##### Helper for parse-once-use-often like parsing a xml file is needed implement it here + def parse_file(self, filename): + return None + + ################### Merge one big file containing all strings in all languages ################# + def merge_one_big_file(self, inputfile, outputfilename, parsed_file_ref, lang, sdfdata): + pass + + ################### Extract a single File ###################################################### + def extract_file(self, inputfile): + pass + + ################################################################################################ + + def format_outputfile(self, filename, language): + extension = filename[filename.rfind('.')+1:] + file = filename[:filename.rfind('.')] + return self.get_outputfile_format_str().format( + filename=filename, fileNoExt=file, language=language, extension=extension, path_prefix=self._options.path_prefix, + path_postfix=self._options.path_postfix, path=self.get_path()) + + def get_path(self): + if self._options.outputfile.find('/') == -1: + return "" + else: + return self._options.outputfile[:self._options.outputfile.rfind('/')] + + def merge(self, sdfdata): + langset,forcedset, foundset = set(), set() , set() + + if self._options.languages: langset = set(self._options.languages) + if self._options.forcedlanguages: forcedset = set(self._options.forcedlanguages) + if sdfdata.get_languages_found_in_sdf(): foundset = sdfdata.get_languages_found_in_sdf() + + if self.has_multi_inputfiles(): + filelist = self.read_inputfile_list() + else: + filelist = self._options.inputfile + + for inputfile in filelist: + ref = self.parse_file(inputfile) + # Don't write that files if there is no l10n present + if ((langset & foundset) - forcedset): # all langs given and found in sdf without enforced + [self.merge_file(inputfile,self.format_outputfile(inputfile, lang), ref, lang, False, sdfdata) for lang in ((langset & foundset) - forcedset)] + # Always write those files even if there is no l10n available + if forcedset: # all enforced langs + [self.merge_file(inputfile, self.format_outputfile(inputfile, lang), ref, lang, True, sdfdata) for lang in forcedset] + # In case a big file have to be written + if ((langset & foundset) | forcedset): # all langs given ,found in sdf and enforced ones + self.merge_one_big_file(inputfile, self.format_outputfile(inputfile, lang), ref, ((langset & foundset) | forcedset), sdfdata) + + def has_multi_inputfiles(self): + return self._options.inputfile[0] == '@' + + def extract(self): + try: + f = open(self._options.outputfile, "w+") + f.write(self.extract_file(self._options.inputfile)) + except IOError: + print "ERROR: Can not write file " + self._options.outputfile + else: + f.close() + + # Parse the common options + def parse_options(self): + parser = OptionParser() + parser.add_option("-i", "--inputfile", dest="inputfile", metavar="FILE", help="resource file to read" ) + parser.add_option("-o", "--outputfile", dest="outputfile", metavar="FILE", help="extracted sdf or merged file" ) + parser.add_option("-m", "--inputsdffile", dest="input_sdf_file", metavar="FILE", help="merge this sdf file" ) + parser.add_option("-x", "--pathprefix", dest="path_prefix", metavar="PATH", help="" ) + parser.add_option("-y", "--pathpostfix", dest="path_postfix", metavar="PATH", help="" ) + parser.add_option("-p", "--projectname", dest="project_name", metavar="NAME", help="" ) + parser.add_option("-r", "--projectroot", dest="project_root", metavar="PATH", help="" ) + parser.add_option("-f", "--forcedlanguages", dest="forcedlanguages", metavar="ISOCODE[,ISOCODE]", help="Always merge those langs even if no l10n is available for those langs" ) + parser.add_option("-l", "--languages", dest="languages", metavar="ISOCODE[,ISOCODE]", help="Merge those langs if l10n is found for each") + parser.add_option("-q", "--quiet", action="store_true", dest="quietmode", help="",default=False) + (self._options, self.args) = parser.parse_args() + + # -l "de,pr,pt-BR" => [ "de" , "pt" , "pt-BR" ] + parse_complex_arg = lambda arg: arg.split(",") + if self._options.forcedlanguages: self._options.forcedlanguages = parse_complex_arg(self._options.forcedlanguages) + if self._options.languages: self._options.languages = parse_complex_arg(self._options.languages) + self.test_options() + + def __init__(self): + self.parse_options() + if self._options.input_sdf_file != None and len(self._options.input_sdf_file): + sdfdata = SdfData(self._options.input_sdf_file) + sdfdata.read() + self.merge(sdfdata) + else: + self.extract() + + def make_dirs(self, filename): + dir = filename[:filename.rfind('/')] + if os.path.exists(dir): + if os.path.isfile(dir): + print "ERROR: There is a file '"+dir+"' where I want create a directory" + sys.exit(-1) + else: + return + else: + try: + print "DBG: make_dir " + str(dir) + os.makedirs(dir) + except IOError: + print "Error: Can not create dir " + dir + sys.exit(-1) + + def test_options(self): + opt = self._options + is_valid = lambda x: x != None and len(x) > 0 + return is_valid(opt.project_root) and is_valid(opt.project_name) and is_valid(opt.languages) and \ + ( is_valid(opt.inputfile) and (( is_valid(opt.path_prefix) and is_valid(opt.path_postfix) ) or is_valid(opt.outputfile)) and \ + ( ( is_valid(opt.input_sdf_file) and ( is_valid(opt.outputfile) or ( is_valid(opt.path_prefix) and is_valid(opt.path_postfix) ) or \ + ( is_valid(opt.inputfile) and is_valid(opt.outputFile)) )))) + print "Strange options ..." + sys.exit( -1 ) + + + def read_inputfile_list(self): + if self.has_multi_inputfiles(): + lines = [] + try: + f = open(self._options.inputfile[1:], "r") + lines = [line.strip('\n') for line in f.readlines()] + except IOError: + print "ERROR: Can not read file list " + self._options.inputfile[2:] + sys.exit(-1) + else: + f.close() + return lines + + def get_filename_string(self, inputfile): + absfile = os.path.realpath(os.path.abspath(inputfile)) + absroot = os.path.realpath(os.path.abspath(self._options.project_root)) + return absfile[len(absroot):].replace('/','\\') + diff --git a/l10ntools/scripts/sdf.py b/l10ntools/scripts/sdf.py new file mode 100644 index 000000000000..ce1077197622 --- /dev/null +++ b/l10ntools/scripts/sdf.py @@ -0,0 +1,240 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org 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 Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + +import string + +class MyOrderedDict(dict): + _keylist = [] + _valuelist = [] + + #correct?!? + def __init__(self, defaults={}): + dict.__init__(self) + for n,v in defaults.items(): + self[n] = v + #def __getitem__(self): + # pass + + def __setitem__(self, key, value): + self._keylist.append(key) + self._valuelist.append(value) + return dict.__setitem__(self, key, value) + + def __delattr__(self, key): + self._keylist.__delattr__(key) + self._valuelist.__delattr__(dict[key]) + return dict.__delattr__(self, key) + + def __delitem__(self, key): + self._keylist.__delitem__(key) + self._valuelist.__delitem__(dict[key]) + return dict.__delitem__(self, key) + + def __iter(self): + return zip(self._keylist, self._valuelist) + + def __iterkeys__(self): + return self._keylist + + def __iteritems__(self): + return self._valuelist + + def items(self): + return zip(self._keylist,self._valuelist) + + def keys(self): + return self._keylist + + def __keysattr__(self): + return self._keylist + + def pop(self, key): + self._keylist.pop(key) + self._valuelist.pop(key) + return dict.__pop__(self, key) + + def popitem(self): + raise NotImplementedError("popitem") + + def clear(self): + self._keylist.clear() + self._valuelist.clear() + return dict.clear() + + def copy(self): + # correct?!? + newobj = MyOrderedDict(self) + newobj._keylist = self._keylist + newobj._valuelist = self._valuelist + return newobj + +class SdfData: + _filename = ""; + _dict = MyOrderedDict() + #_dict = {} + _languages_found = []; + + def __init__ (self, filename=""): + self._filename = filename + + def __getitem__(self, key): + if self._dict.has_key(key): + return self._dict[key] + else: + return None + + def has_key(self, key): + return self._dict.has_key(key) + + def __setitem__(self, key, value): + self._dict[key] = value + + def get_languages_found_in_sdf(self): + return set(self._languages_found) + + def read(self): + try: + f = open(self._filename, "r") + lines = [line.rstrip('\n') for line in f.readlines()] + except IOError: + print "ERROR: Trying to read "+ self._filename + raise + else: + f.close() + for line in lines: + entity = SdfEntity() + entity.set_properties(line) + self._dict[entity.get_id()] = entity + self._languages_found.append(entity.langid) + + def write(self, filename): + try: + f = open(filename, "w+") + for value in self._dict.itervalues(): + #f.write( repr(value)+"\n" ) + f.write(value + "\n") + except IOError: + print "ERROR: Trying to write " + filename + raise + else: + f.close() + + + +import sys +class SdfEntity: + # Sdf format columns + project = "" + source_file = "" + dummy1 = "" + resource_type = "" + gid = "" + lid = "" + helpid = "" + platform = "" + dummy2 = "" + langid = "" + text = "" + helptext = "" + quickhelptext = "" + title = "" + date = "" + + import const + const._PROJECT_POS = 0 + const._SOURCE_FILE_POS = 1 + const._DUMMY1_POS = 2 + const._RESOURCE_TYPE_POS = 3 + const._GID_POS = 4 + const._LID_POS = 5 + const._HELPID_POS = 6 + const._PLATFORM_POS = 7 + const._DUMMY2_POS = 8 + const._LANGID_POS = 9 + const._TEXT_POS = 10 + const._HELPTEXT_POS = 11 + const._QUICKHELPTEXT_POS = 12 + const._TITLE_POS = 13 + const._DATE_POS = 14 + + + + def __init__(self, project="", source_file="", dummy1="", resource_type="", gid="", lid="", helpid="", platform="", dummy2="", langid="", + text="", helptext="", quickhelptext="", title="", date="2002-02-02 02:02:02"): + self.project = project; + self.source_file = source_file; + self.dummy1 = dummy1; + self.resource_type = resource_type; + self.gid = gid; + self.lid = lid; + self.helpid = helpid; + self.platform = platform; + self.dummy2 = dummy2; + self.langid = langid; + self.text = text; + self.helptext = helptext; + self.quickhelptext = quickhelptext; + self.title = title; + self.date = date; + + def set_properties(self, line): + splitted = line.split("\t") + if len(splitted) == 15: + self.project = splitted[ self.const._PROJECT_POS ] + self.source_file = splitted[ self.const._SOURCE_FILE_POS ] + self.dummy1 = splitted[ self.const._DUMMY1_POS ] + self.resource_type = splitted[ self.const._RESOURCE_TYPE_POS ] + self.gid = splitted[ self.const._GID_POS ] + self.lid = splitted[ self.const._LID_POS ] + self.helpid = splitted[ self.const._HELPID_POS ] + self.platform = splitted[ self.const._PLATFORM_POS ] + self.dummy2 = splitted[ self.const._DUMMY2_POS ] + self.langid = splitted[ self.const._LANGID_POS ] + self.text = splitted[ self.const._TEXT_POS ] + self.helptext = splitted[ self.const._HELPTEXT_POS ] + self.quickhelptext = splitted[ self.const._QUICKHELPTEXT_POS ] + self.title = splitted[ self.const._TITLE_POS ] + self.date = splitted[ self.const._DATE_POS ] + #else: + # print "Offending line '"+line+"'" + # print "ERROR: Something is broken here! Line has {0} tabs".format( len(splitted) ) + # sys.exit( -1 ) + + def get_file_id(self): + return self.project + "\\" + self.source_file + + def get_resource_path(self): + return self.source_file[0:self.source_file.rfind( "\\" )-1] + + #def __repr__(self): + def __str__(self): + return ''.join([self.project, "\t", self.source_file, "\t", self.dummy1, "\t", self.resource_type, "\t" , + self.gid, "\t", self.lid, "\t", self.helpid, "\t", self.platform, "\t", self.dummy2, "\t" , self.langid, + "\t", self.text, "\t", self.helptext, "\t", self.quickhelptext, "\t" , self.title, "\t", self.date ]) + + def get_id(self): + return ''.join([self.project, self.gid, self.lid, self.source_file, self.resource_type, self.platform, self.helpid, self.langid]) diff --git a/l10ntools/scripts/xtxex b/l10ntools/scripts/xtxex new file mode 100755 index 000000000000..cc9dac01fca2 --- /dev/null +++ b/l10ntools/scripts/xtxex @@ -0,0 +1,47 @@ +#!/bin/sh +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org 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 Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + +if [ x${SOLARENV}x = xx ]; then + echo No environment found, please use 'setsolar' +exit 1 +fi + +# localize.pl calls localize_sl in solver bin directory which depends on dynamic +# libraries in solver lib directory but has no correct RPATH (or equivalent): +if [ "${OS?}" = MACOSX ]; then + export DYLD_LIBRARY_PATH=${DYLD_LIBRARY_PATH+${DYLD_LIBRARY_PATH}:}${SOLARVERSION?}/${INPATH?}/lib${UPDMINOREXT} +else + export LD_LIBRARY_PATH=${LD_LIBRARY_PATH+${LD_LIBRARY_PATH}:}${SOLARVERSION?}/${INPATH?}/lib${UPDMINOREXT} +fi + +if [ x${SOLARVER}x = xx -o x${UPDMINOREXT}x = xx ]; then + exec python $SOLARVERSION/$INPATH/bin/xtxex.py "$@" +else + exec python $SOLARVERSION/$INPATH/bin$UPDMINOREXT/xtxex.py "$@" +fi + diff --git a/l10ntools/scripts/xtxex.py b/l10ntools/scripts/xtxex.py new file mode 100644 index 000000000000..98ec1e86b596 --- /dev/null +++ b/l10ntools/scripts/xtxex.py @@ -0,0 +1,92 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org 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 Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + +from l10ntool import abstractL10nTool +from sdf import SdfEntity +import sys +import shutil + +class xtxex(abstractL10nTool): + _resourceType = "xtx" + + def __init__(self): + abstractL10nTool.__init__(self) + + def merge_file(self, inputfilename, outputfilename, parsed_file_ref, lang,is_forced_lang, sdfdata): + print "merge_file lang " + lang +" file " + outputfilename + sdfline = self.prepare_sdf_line(inputfilename,lang) + if sdfdata.has_key(sdfline.get_id()): + line = sdfdata[sdfline.get_id()].text.replace("\\n", '\n') + self.make_dirs(outputfilename) + try: + f = open(outputfilename, "w+") + f.write(line) + except IOError: + print "ERROR: Can not write file " + outputfilename + sys.exit(-1) + else: + f.close() + return + if is_forced_lang: + try: + shutil.copy(inputfilename, outputfilename) + except IOError: + print "ERROR: Can not copy file '" + inputfilename + "' to " + "'" + outputfilename + "'" + sys.exit(-1) + + ##### Extract a single File + def extract_file(self, inputfile): + lines = [] + try: + f = open(inputfile, "r") + lines = f.readlines() + except IOError: + print "ERROR: Can not open file " + inputfile + sys.exit(-1) + else: + f.close() + # remove legal header + lines = [line for line in lines if len(line) > 0 and not line[0] == '#'] + # escape all returns + lines = [line.replace('\n', "\\n") for line in lines] + line = ''.join(lines) + sdf_entity = self.prepare_sdf_line(inputfile); + sdf_entity.text = line + return str(sdf_entity) + + ##### Nameing scheme for the output files + def get_outputfile_format_str(self): + # filename,fileNoExt,language,extension,pathPrefix,pathPostFix,path + return "{path}/{fileNoExt}_{language}.{extension}" + + def prepare_sdf_line(self, inputfile="", lang=""): + if lang == "": + lang = self._source_language + return SdfEntity(project=self._options.project_name, source_file=self.get_filename_string(inputfile), + resource_type=self._resource_type, gid="none", lid="none", langid=lang,text="") + +run = xtxex() |