view roundup/cgi/TAL/talgettext.py @ 5096:e74c3611b138

- issue2550636, issue2550909: Added support for Whoosh indexer. Also adds new config.ini setting called indexer to select indexer. See ``doc/upgrading.txt`` for details. Initial patch done by David Wolever. Patch modified (see ticket or below for changes), docs updated and committed. I have an outstanding issue with test/test_indexer.py. I have to comment out all imports and tests for indexers I don't have (i.e. mysql, postgres) otherwise no tests run. With that change made, dbm, sqlite (rdbms), xapian and whoosh indexes are all passing the indexer tests. Changes summary: 1) support native back ends dbm and rdbms. (original patch only fell through to dbm) 2) Developed whoosh stopfilter to not index stopwords or words outside the the maxlength and minlength limits defined in index_common.py. Required to pass the extremewords test_indexer test. Also I removed a call to .lower on the input text as the tokenizer I chose automatically does the lowercase. 3) Added support for max/min length to find. This was needed to pass extremewords test. 4) Added back a call to save_index in add_text. This allowed all but two tests to pass. 5) Fixed a call to: results = searcher.search(query.Term("identifier", identifier)) which had an extra parameter that is an error under current whoosh. 6) Set limit=None in search call for find() otherwise it only return 10 items. This allowed it to pass manyresults test Also due to changes in the roundup code removed the call in indexer_whoosh to from roundup.anypy.sets_ import set since we use the python builtin set.
author John Rouillard <rouilj@ieee.org>
date Sat, 25 Jun 2016 20:10:03 -0400
parents 3a407f0d5dad
children 198b6e810c67
line wrap: on
line source

#!/usr/bin/env python
##############################################################################
#
# Copyright (c) 2002 Zope Corporation and Contributors.
# All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.0 (ZPL).  A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE.
#
##############################################################################
# Modifications for Roundup:
# 1. commented out ITALES references
# 2. escape quotes and line feeds in msgids
# 3. don't collect empty msgids

"""Program to extract internationalization markup from Page Templates.

Once you have marked up a Page Template file with i18n: namespace tags, use
this program to extract GNU gettext .po file entries.

Usage: talgettext.py [options] files
Options:
    -h / --help
        Print this message and exit.
    -o / --output <file>
        Output the translation .po file to <file>.
    -u / --update <file>
        Update the existing translation <file> with any new translation strings
        found.
"""

import sys
import time
import getopt
import traceback

from roundup import __version__
from roundup.cgi.TAL.HTMLTALParser import HTMLTALParser
from roundup.cgi.TAL.TALInterpreter import TALInterpreter
from roundup.cgi.TAL.DummyEngine import DummyEngine
#from ITALES import ITALESEngine
from roundup.cgi.TAL.TALDefs import TALESError

pot_header = '''\
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\\n"
"POT-Creation-Date: %(time)s\\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\\n"
"Language-Team: LANGUAGE <LL@li.org>\\n"
"MIME-Version: 1.0\\n"
"Content-Type: text/plain; charset=CHARSET\\n"
"Content-Transfer-Encoding: ENCODING\\n"
"Generated-By: talgettext.py %(version)s\\n"
'''

NLSTR = '"\n"'

try:
    True
except NameError:
    True=1
    False=0

def usage(code, msg=''):
    # Python 2.1 required
    print >> sys.stderr, __doc__
    if msg:
        print >> sys.stderr, msg
    sys.exit(code)


class POTALInterpreter(TALInterpreter):
    def translate(self, msgid, default, i18ndict=None, obj=None):
        # XXX is this right?
        if i18ndict is None:
            i18ndict = {}
        if obj:
            i18ndict.update(obj)
        # XXX Mmmh, it seems that sometimes the msgid is None; is that really
        # possible?
        if msgid is None:
            return None
        # XXX We need to pass in one of context or target_language
        return self.engine.translate(msgid, self.i18nContext.domain, i18ndict,
                                     position=self.position, default=default)


class POEngine(DummyEngine):
    #__implements__ = ITALESEngine

    def __init__(self, macros=None):
        self.catalog = {}
        DummyEngine.__init__(self, macros)

    def evaluate(*args):
        return '' # who cares

    def evaluatePathOrVar(*args):
        return '' # who cares

    def evaluateSequence(self, expr):
        return (0,) # dummy

    def evaluateBoolean(self, expr):
        return True # dummy

    def translate(self, msgid, domain=None, mapping=None, default=None,
                  # XXX position is not part of the ITALESEngine
                  #     interface
                  position=None):

        if not msgid: return 'x'

        if domain not in self.catalog:
            self.catalog[domain] = {}
        domain = self.catalog[domain]

        if msgid not in domain:
            domain[msgid] = []
        domain[msgid].append((self.file, position))
        return 'x'


class UpdatePOEngine(POEngine):
    """A slightly-less braindead POEngine which supports loading an existing
    .po file first."""

    def __init__ (self, macros=None, filename=None):
        POEngine.__init__(self, macros)

        self._filename = filename
        self._loadFile()
        self.base = self.catalog
        self.catalog = {}

    def __add(self, id, s, fuzzy):
        "Add a non-fuzzy translation to the dictionary."
        if not fuzzy and str:
            # check for multi-line values and munge them appropriately
            if '\n' in s:
                lines = s.rstrip().split('\n')
                s = NLSTR.join(lines)
            self.catalog[id] = s

    def _loadFile(self):
        # shamelessly cribbed from Python's Tools/i18n/msgfmt.py
        # 25-Mar-2003 Nathan R. Yergler (nathan@zope.org)
        # 14-Apr-2003 Hacked by Barry Warsaw (barry@zope.com)

        ID = 1
        STR = 2

        try:
            lines = open(self._filename).readlines()
        except IOError, msg:
            print >> sys.stderr, msg
            sys.exit(1)

        section = None
        fuzzy = False

        # Parse the catalog
        lno = 0
        for l in lines:
            lno += True
            # If we get a comment line after a msgstr, this is a new entry
            if l[0] == '#' and section == STR:
                self.__add(msgid, msgstr, fuzzy)
                section = None
                fuzzy = False
            # Record a fuzzy mark
            if l[:2] == '#,' and l.find('fuzzy'):
                fuzzy = True
            # Skip comments
            if l[0] == '#':
                continue
            # Now we are in a msgid section, output previous section
            if l.startswith('msgid'):
                if section == STR:
                    self.__add(msgid, msgstr, fuzzy)
                section = ID
                l = l[5:]
                msgid = msgstr = ''
            # Now we are in a msgstr section
            elif l.startswith('msgstr'):
                section = STR
                l = l[6:]
            # Skip empty lines
            if not l.strip():
                continue
            # XXX: Does this always follow Python escape semantics?
            l = eval(l)
            if section == ID:
                msgid += l
            elif section == STR:
                msgstr += '%s\n' % l
            else:
                print >> sys.stderr, 'Syntax error on %s:%d' % (infile, lno), \
                      'before:'
                print >> sys.stderr, l
                sys.exit(1)
        # Add last entry
        if section == STR:
            self.__add(msgid, msgstr, fuzzy)

    def evaluate(self, expression):
        try:
            return POEngine.evaluate(self, expression)
        except TALESError:
            pass

    def evaluatePathOrVar(self, expr):
        return 'who cares'

    def translate(self, msgid, domain=None, mapping=None, default=None,
                  position=None):
        if msgid not in self.base:
            POEngine.translate(self, msgid, domain, mapping, default, position)
        return 'x'


def main():
    try:
        opts, args = getopt.getopt(
            sys.argv[1:],
            'ho:u:',
            ['help', 'output=', 'update='])
    except getopt.error, msg:
        usage(1, msg)

    outfile = None
    engine = None
    update_mode = False
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-o', '--output'):
            outfile = arg
        elif opt in ('-u', '--update'):
            update_mode = True
            if outfile is None:
                outfile = arg
            engine = UpdatePOEngine(filename=arg)

    if not args:
        print 'nothing to do'
        return

    # We don't care about the rendered output of the .pt file
    class Devnull:
        def write(self, s):
            pass

    # check if we've already instantiated an engine;
    # if not, use the stupidest one available
    if not engine:
        engine = POEngine()

    # process each file specified
    for filename in args:
        try:
            engine.file = filename
            p = HTMLTALParser()
            p.parseFile(filename)
            program, macros = p.getCode()
            POTALInterpreter(program, macros, engine, stream=Devnull(),
                             metal=False)()
        except: # Hee hee, I love bare excepts!
            print 'There was an error processing', filename
            traceback.print_exc()

    # Now output the keys in the engine.  Write them to a file if --output or
    # --update was specified; otherwise use standard out.
    if (outfile is None):
        outfile = sys.stdout
    else:
        outfile = file(outfile, update_mode and "a" or "w")

    catalog = {}
    for domain in engine.catalog.keys():
        catalog.update(engine.catalog[domain])

    messages = catalog.copy()
    try:
        messages.update(engine.base)
    except AttributeError:
        pass
    if '' not in messages:
        print >> outfile, pot_header % {'time': time.ctime(),
                                        'version': __version__}

    msgids = catalog.keys()
    # XXX: You should not sort by msgid, but by filename and position. (SR)
    msgids.sort()
    for msgid in msgids:
        positions = catalog[msgid]
        for filename, position in positions:
            outfile.write('#: %s:%s\n' % (filename, position[0]))

        outfile.write('msgid "%s"\n'
            % msgid.replace('"', '\\"').replace("\n", '\\n"\n"'))
        outfile.write('msgstr ""\n')
        outfile.write('\n')


if __name__ == '__main__':
    main()

Roundup Issue Tracker: http://roundup-tracker.org/