[Zope3-checkins] CVS: Zope3/utilities - i18nextract.py:1.1 pygettext.py:1.1

Philipp von Weitershausen philikon at philikon.de
Wed Dec 17 02:59:35 EST 2003


Update of /cvs-repository/Zope3/utilities
In directory cvs.zope.org:/tmp/cvs-serv8160/utilities

Added Files:
	i18nextract.py pygettext.py 
Log Message:
Moved the i18n extract utility and the accompanying pygettext script to
the utilities directory. i18nextract will still write to CWD so in order
for it to generate the zope.pot file at the right place, it still has to
be executed from src/zope/app/translation_files.


=== Added File Zope3/utilities/i18nextract.py ===
#!/usr/bin/env python2.3
##############################################################################
#
# Copyright (c) 2003 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.
#
##############################################################################
"""Program to extract internationalization markup from Python Code,
Page Templates and ZCML.

This tool will extract all findable message strings from all
internationalizable files in your Zope 3 product. It only extracts
message ids of the specified domain. It defaults to the 'zope' domain
and the zope.app package.

Note: The Python Code extraction tool does not support domain
      registration, so that all message strings are returned for
      Python code.

Usage: i18nextract.py [options]
Options:
    -h / --help
        Print this message and exit.
    -d / --domain <domain>
        Specifies the domain that is supposed to be extracted (i.e. 'zope')
    -p / --path <path>
        Specifies the package that is supposed to be searched
        (i.e. 'zope/app')
    -o dir
        Specifies a directory, relative to the package in which to put the
        output translation template.

$Id: i18nextract.py,v 1.1 2003/12/17 07:59:34 philikon Exp $
"""

import os, sys, fnmatch
import getopt
import time
import tokenize
import traceback
from pygettext import safe_eval, normalize, make_escapes

__meta_class__ = type


pot_header = '''\
##############################################################################
#
# Copyright (c) 2003 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.
#
##############################################################################
msgid ""
msgstr ""
"Project-Id-Version: %(version)s\\n"
"POT-Creation-Date: %(time)s\\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\\n"
"Last-Translator: FULL NAME <EMAIL at ADDRESS>\\n"
"Language-Team: Zope 3 Developers <zope3-dev at zope.org>\\n"
"MIME-Version: 1.0\\n"
"Content-Type: text/plain; charset=CHARSET\\n"
"Content-Transfer-Encoding: ENCODING\\n"
"Generated-By: zope/app/translation_files/extract.py\\n"

'''

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

class POTEntry:
    """This class represents a single message entry in the POT file.
    """

    def __init__(self, msgid, comments=None):
        self.msgid = msgid
        self.comments = comments or ''

    def addComment(self, comment):
        self.comments += comment + '\n'

    def addLocationComment(self, filename, line):
        self.comments += '#: %s:%s\n' %(filename, line)

    def write(self, file):
        file.write(self.comments)
        from zope.i18n.messageid import MessageID
        if isinstance(self.msgid, MessageID) and \
               self.msgid != self.msgid.default:
            default = self.msgid.default.strip()
            file.write('# Default: %s\n' % normalize(default))
        file.write('msgid %s\n' % normalize(self.msgid))
        file.write('msgstr ""\n')
        file.write('\n')

    def __cmp__(self, other):
        return cmp(self.comments, other.comments)


class POTMaker:
    """This class inserts sets of strings into a POT file.
    """
    
    def __init__ (self, output_fn, path):
        self._output_filename = output_fn
        self.path = path
        self.catalog = {}

    def add(self, strings, base_dir=None):
        for msgid, locations in strings.items():
            if msgid == '':
                continue
            if msgid not in self.catalog:
                self.catalog[msgid] = POTEntry(msgid)

            for filename, lineno in locations:
                if base_dir is not None:
                    filename = filename.replace(base_dir, '')
                self.catalog[msgid].addLocationComment(filename, lineno)
                

    def _getProductVersion(self):
        # First, try to get the product version
        fn = os.path.join(self.path, 'version.txt')
        if os.path.exists(fn):
            return open(fn, 'r').read().strip()
        # Second, try to find a Zope version
        import zope
        fn = os.path.join(os.path.dirname(zope.__file__), 'version.txt')
        if os.path.exists(fn):
            return open(fn, 'r').read().strip()
        else:
            return 'Zope 3 (unknown version)'


    def write(self):
        file = open(self._output_filename, 'w')
        file.write(pot_header % {'time': time.ctime(),
                                 'version': self._getProductVersion()})
        
        # Sort the catalog entries by filename
        catalog = self.catalog.values()
        catalog.sort()

        # Write each entry to the file
        for entry in catalog:
            entry.write(file)
            
        file.close()


class TokenEater:
    """This is almost 100% taken from pygettext.py, except that I
    removed all option handling and output a dictionary.
    """
    
    def __init__(self):
        self.__messages = {}
        self.__state = self.__waiting
        self.__data = []
        self.__lineno = -1
        self.__freshmodule = 1
        self.__curfile = None

    def __call__(self, ttype, tstring, stup, etup, line):
        self.__state(ttype, tstring, stup[0])

    def __waiting(self, ttype, tstring, lineno):
        if ttype == tokenize.NAME and tstring in ['_']:
            self.__state = self.__keywordseen

    def __suiteseen(self, ttype, tstring, lineno):
        # ignore anything until we see the colon
        if ttype == tokenize.OP and tstring == ':':
            self.__state = self.__suitedocstring

    def __suitedocstring(self, ttype, tstring, lineno):

        # ignore any intervening noise
        if ttype == tokenize.STRING:
            self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
            self.__state = self.__waiting
        elif ttype not in (tokenize.NEWLINE, tokenize.INDENT,
                           tokenize.COMMENT):
            # there was no class docstring
            self.__state = self.__waiting

    def __keywordseen(self, ttype, tstring, lineno):
        if ttype == tokenize.OP and tstring == '(':
            self.__data = []
            self.__msgid = ''
            self.__lineno = lineno
            self.__state = self.__openseen
        else:
            self.__state = self.__waiting

    def __openseen(self, ttype, tstring, lineno):
        if ttype == tokenize.OP and tstring == ')':
            # We've seen the last of the translatable strings.  Record the
            # line number of the first line of the strings and update the list 
            # of messages seen.  Reset state for the next batch.  If there
            # were no strings inside _(), then just ignore this entry.
            if self.__data or self.__msgid:
                if self.__msgid:
                    msgid = self.__msgid
                    default = ''.join(self.__data)
                else:
                    msgid = ''.join(self.__data)
                    default = None
                self.__addentry(msgid, default)
            self.__state = self.__waiting
        elif ttype == tokenize.OP and tstring == ',':
            self.__msgid = ''.join(self.__data)
            self.__data = []
        elif ttype == tokenize.STRING:
            self.__data.append(safe_eval(tstring))

    def __addentry(self, msg, default=None, lineno=None, isdocstring=0):
        if lineno is None:
            lineno = self.__lineno

        if default is not None:
            from zope.i18n.messageid import MessageID
            msg = MessageID(msg, default=default)
        entry = (self.__curfile, lineno)
        self.__messages.setdefault(msg, {})[entry] = isdocstring

    def set_filename(self, filename):
        self.__curfile = filename
        self.__freshmodule = 1

    def getCatalog(self):
        catalog = {}
        # Sort the entries.  First sort each particular entry's keys, then
        # sort all the entries by their first item.
        reverse = {}
        for k, v in self.__messages.items():
            keys = v.keys()
            keys.sort()
            reverse.setdefault(tuple(keys), []).append((k, v))
        rkeys = reverse.keys()
        rkeys.sort()
        for rkey in rkeys:
            rentries = reverse[rkey]
            rentries.sort()
            for msgid, locations in rentries:
                catalog[msgid] = []
                
                locations = locations.keys()
                locations.sort()

                for filename, lineno in locations:
                    catalog[msgid].append((filename, lineno))

        return catalog

                    
def app_dir():
    try:
        import zope.app
    except ImportError:
        # Couldn't import zope.app, need to add something to the Python
        # path

        # Get the path of the src
        path = os.path.abspath(os.path.dirname(sys.argv[0]))
        while not path.endswith('src'):
            path = os.path.dirname(path)
        sys.path.insert(0, path)

        import zope.app

    return os.path.dirname(zope.app.__file__)


def find_files(dir, pattern, exclude=()):
    files = []

    def visit(files, dirname, names):
        files += [os.path.join(dirname, name)
                  for name in fnmatch.filter(names, pattern)
                  if name not in exclude]
        
    os.path.walk(dir, visit, files)

    return files


def py_strings(dir, domain="zope"):
    """Retrieve all Python messages from dir that are in the domain.
    """
    eater = TokenEater()
    make_escapes(0)
    for filename in find_files(dir, '*.py', 
                               exclude=('extract.py', 'pygettext.py')):
        fp = open(filename)
        try:
            eater.set_filename(filename)
            try:
                tokenize.tokenize(fp.readline, eater)
            except tokenize.TokenError, e:
                print >> sys.stderr, '%s: %s, line %d, column %d' % (
                    e[0], filename, e[1][0], e[1][1])
        finally:
            fp.close()            
    # XXX: No support for domains yet :(
    return eater.getCatalog()


def zcml_strings(dir, domain="zope"):
    """Retrieve all ZCML messages from dir that are in the domain.
    """
    from zope.app._app import config
    import zope
    dirname = os.path.dirname
    site_zcml = os.path.join(dirname(dirname(dirname(zope.__file__))),
                             "site.zcml")
    context = config(site_zcml, execute=False)
    return context.i18n_strings.get(domain, {})


def tal_strings(dir, domain="zope", include_default_domain=False):
    """Retrieve all TAL messages from dir that are in the domain.
    """
    # We import zope.tal.talgettext here because we can't rely on the
    # right sys path until app_dir has run
    from zope.tal.talgettext import POEngine, POTALInterpreter
    from zope.tal.htmltalparser import HTMLTALParser
    engine = POEngine()

    class Devnull:
        def write(self, s):
            pass

    for filename in find_files(dir, '*.pt'):
        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()

    # See whether anything in the domain was found
    if not engine.catalog.has_key(domain):
        return {}
    # We do not want column numbers.
    catalog = engine.catalog[domain].copy()
    # When the Domain is 'default', then this means that none was found;
    # Include these strings; yes or no?
    if include_default_domain:
        catalog.update(engine.catalog['default'])
    for msgid, locations in catalog.items():
        catalog[msgid] = map(lambda l: (l[0], l[1][0]), locations)
    return catalog


def main(argv=sys.argv):
    try:
        opts, args = getopt.getopt(
            sys.argv[1:],
            'hd:p:o:',
            ['help', 'domain=', 'path='])
    except getopt.error, msg:
        usage(1, msg)

    domain = 'zope'
    path = app_dir()
    include_default_domain = True
    output_dir = None
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-d', '--domain'):
            domain = arg
            include_default_domain = False
        elif opt in ('-o', ):
            output_dir = arg
        elif opt in ('-p', '--path'):
            if not os.path.exists(arg):
                usage(1, 'The specified path does not exist.')
            path = arg
            # We might not have an absolute path passed in.
            if not path == os.path.abspath(path):
                cwd = os.getcwd()
                # This is for symlinks. Thanks to Fred for this trick.
                if os.environ.has_key('PWD'):
                    cwd = os.environ['PWD']
                path = os.path.normpath(os.path.join(cwd, arg))

    # When generating the comments, we will not need the base directory info,
    # since it is specific to everyone's installation
    src_start = path.find('src')
    base_dir = path[:src_start]

    output_file = domain+'.pot'
    if output_dir:
        output_dir = os.path.join(path, output_dir)
        if not os.path.exists(output_dir):
            os.mkdir(output_dir)
        output_file = os.path.join(output_dir, output_file)
        

    maker = POTMaker(output_file, path)
    maker.add(py_strings(path, domain), base_dir)
    maker.add(zcml_strings(path, domain), base_dir)
    maker.add(tal_strings(path, domain, include_default_domain), base_dir)
    maker.write()


if __name__ == '__main__':
    main()


=== Added File Zope3/utilities/pygettext.py ===
#! /usr/bin/env python
# Originally written by Barry Warsaw <barry at zope.com>
#
# Minimally patched to make it even more xgettext compatible 
# by Peter Funk <pf at artcom-gmbh.de>

"""pygettext -- Python equivalent of xgettext(1)

Many systems (Solaris, Linux, Gnu) provide extensive tools that ease the
internationalization of C programs.  Most of these tools are independent of
the programming language and can be used from within Python programs.  Martin
von Loewis' work[1] helps considerably in this regard.

There's one problem though; xgettext is the program that scans source code
looking for message strings, but it groks only C (or C++).  Python introduces
a few wrinkles, such as dual quoting characters, triple quoted strings, and
raw strings.  xgettext understands none of this.

Enter pygettext, which uses Python's standard tokenize module to scan Python
source code, generating .pot files identical to what GNU xgettext[2] generates
for C and C++ code.  From there, the standard GNU tools can be used.

A word about marking Python strings as candidates for translation.  GNU
xgettext recognizes the following keywords: gettext, dgettext, dcgettext, and
gettext_noop.  But those can be a lot of text to include all over your code.
C and C++ have a trick: they use the C preprocessor.  Most internationalized C
source includes a #define for gettext() to _() so that what has to be written
in the source is much less.  Thus these are both translatable strings:

    gettext("Translatable String")
    _("Translatable String")

Python of course has no preprocessor so this doesn't work so well.  Thus,
pygettext searches only for _() by default, but see the -k/--keyword flag
below for how to augment this.

 [1] http://www.python.org/workshops/1997-10/proceedings/loewis.html
 [2] http://www.gnu.org/software/gettext/gettext.html

NOTE: pygettext attempts to be option and feature compatible with GNU xgettext
where ever possible.  However some options are still missing or are not fully
implemented.  Also, xgettext's use of command line switches with option
arguments is broken, and in these cases, pygettext just defines additional
switches.

Usage: pygettext [options] inputfile ...

Options:

    -a
    --extract-all
        Extract all strings.

    -d name
    --default-domain=name
        Rename the default output file from messages.pot to name.pot.

    -E
    --escape
        Replace non-ASCII characters with octal escape sequences.

    -D
    --docstrings
        Extract module, class, method, and function docstrings.  These do not
        need to be wrapped in _() markers, and in fact cannot be for Python to
        consider them docstrings. (See also the -X option).

    -h
    --help
        Print this help message and exit.

    -k word
    --keyword=word
        Keywords to look for in addition to the default set, which are:
        %(DEFAULTKEYWORDS)s

        You can have multiple -k flags on the command line.

    -K
    --no-default-keywords
        Disable the default set of keywords (see above).  Any keywords
        explicitly added with the -k/--keyword option are still recognized.

    --no-location
        Do not write filename/lineno location comments.

    -n
    --add-location
        Write filename/lineno location comments indicating where each
        extracted string is found in the source.  These lines appear before
        each msgid.  The style of comments is controlled by the -S/--style
        option.  This is the default.

    -o filename
    --output=filename
        Rename the default output file from messages.pot to filename.  If
        filename is `-' then the output is sent to standard out.

    -p dir
    --output-dir=dir
        Output files will be placed in directory dir.

    -S stylename
    --style stylename
        Specify which style to use for location comments.  Two styles are
        supported:

        Solaris  # File: filename, line: line-number
        GNU      #: filename:line

        The style name is case insensitive.  GNU style is the default.

    -v
    --verbose
        Print the names of the files being processed.

    -V
    --version
        Print the version of pygettext and exit.

    -w columns
    --width=columns
        Set width of output to columns.

    -x filename
    --exclude-file=filename
        Specify a file that contains a list of strings that are not be
        extracted from the input files.  Each string to be excluded must
        appear on a line by itself in the file.

    -X filename
    --no-docstrings=filename
        Specify a file that contains a list of files (one per line) that
        should not have their docstrings extracted.  This is only useful in
        conjunction with the -D option above.

If `inputfile' is -, standard input is read.
"""

import os
import sys
import time
import getopt
import tokenize
import operator

# for selftesting
try:
    import fintl
    _ = fintl.gettext
except ImportError:
    def _(s): return s

__version__ = '1.4'

default_keywords = ['_']
DEFAULTKEYWORDS = ', '.join(default_keywords)

EMPTYSTRING = ''



# The normal pot-file header. msgmerge and Emacs's po-mode work better if it's
# there.
pot_header = _('''\
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR ORGANIZATION
# FIRST AUTHOR <EMAIL at 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 at ADDRESS>\\n"
"Language-Team: LANGUAGE <LL at li.org>\\n"
"MIME-Version: 1.0\\n"
"Content-Type: text/plain; charset=CHARSET\\n"
"Content-Transfer-Encoding: ENCODING\\n"
"Generated-By: pygettext.py %(version)s\\n"

''')


def usage(code, msg=''):
    print >> sys.stderr, _(__doc__) % globals()
    if msg:
        print >> sys.stderr, msg
    sys.exit(code)



escapes = []

def make_escapes(pass_iso8859):
    global escapes
    if pass_iso8859:
        # Allow iso-8859 characters to pass through.  Otherwise we
        # escape any character outside the 32..126 range.
        mod = 128
    else:
        mod = 256
    for i in range(256):
        if 32 <= (i % mod) <= 126:
            escapes.append(chr(i))
        else:
            escapes.append("\\%03o" % i)
    escapes[ord('\\')] = '\\\\'
    escapes[ord('\t')] = '\\t'
    escapes[ord('\r')] = '\\r'
    escapes[ord('\n')] = '\\n'
    escapes[ord('\"')] = '\\"'


def escape(s):
    global escapes
    s = list(s)
    for i in range(len(s)):
        s[i] = escapes[ord(s[i])]
    return EMPTYSTRING.join(s)


def safe_eval(s):
    # unwrap quotes, safely
    return eval(s, {'__builtins__':{}}, {})


def normalize(s):
    # This converts the various Python string types into a format that is
    # appropriate for .po files, namely much closer to C style.
    lines = s.split('\n')
    if len(lines) == 1:
        s = '"' + escape(s) + '"'
    else:
        if not lines[-1]:
            del lines[-1]
            lines[-1] = lines[-1] + '\n'
        for i in range(len(lines)):
            lines[i] = escape(lines[i])
        lineterm = '\\n"\n"'
        s = '""\n"' + lineterm.join(lines) + '"'
    return s



class TokenEater:
    def __init__(self, options):
        self.__options = options
        self.__messages = {}
        self.__state = self.__waiting
        self.__data = []
        self.__lineno = -1
        self.__freshmodule = 1
        self.__curfile = None

    def __call__(self, ttype, tstring, stup, etup, line):
        # dispatch
##        import token
##        print >> sys.stderr, 'ttype:', token.tok_name[ttype], \
##              'tstring:', tstring
        self.__state(ttype, tstring, stup[0])

    def __waiting(self, ttype, tstring, lineno):
        opts = self.__options
        # Do docstring extractions, if enabled
        if opts.docstrings and not opts.nodocstrings.get(self.__curfile):
            # module docstring?
            if self.__freshmodule:
                if ttype == tokenize.STRING:
                    self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
                    self.__freshmodule = 0
                elif ttype not in (tokenize.COMMENT, tokenize.NL):
                    self.__freshmodule = 0
                return
            # class docstring?
            if ttype == tokenize.NAME and tstring in ('class', 'def'):
                self.__state = self.__suiteseen
                return
        if ttype == tokenize.NAME and tstring in opts.keywords:
            self.__state = self.__keywordseen

    def __suiteseen(self, ttype, tstring, lineno):
        # ignore anything until we see the colon
        if ttype == tokenize.OP and tstring == ':':
            self.__state = self.__suitedocstring

    def __suitedocstring(self, ttype, tstring, lineno):
        # ignore any intervening noise
        if ttype == tokenize.STRING:
            self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
            self.__state = self.__waiting
        elif ttype not in (tokenize.NEWLINE, tokenize.INDENT,
                           tokenize.COMMENT):
            # there was no class docstring
            self.__state = self.__waiting

    def __keywordseen(self, ttype, tstring, lineno):
        if ttype == tokenize.OP and tstring == '(':
            self.__data = []
            self.__lineno = lineno
            self.__state = self.__openseen
        else:
            self.__state = self.__waiting

    def __openseen(self, ttype, tstring, lineno):
        if ttype == tokenize.OP and tstring == ')':
            # We've seen the last of the translatable strings.  Record the
            # line number of the first line of the strings and update the list 
            # of messages seen.  Reset state for the next batch.  If there
            # were no strings inside _(), then just ignore this entry.
            if self.__data:
                self.__addentry(EMPTYSTRING.join(self.__data))
            self.__state = self.__waiting
        elif ttype == tokenize.STRING:
            self.__data.append(safe_eval(tstring))
        # TBD: should we warn if we seen anything else?

    def __addentry(self, msg, lineno=None, isdocstring=0):
        if lineno is None:
            lineno = self.__lineno
        if not msg in self.__options.toexclude:
            entry = (self.__curfile, lineno)
            self.__messages.setdefault(msg, {})[entry] = isdocstring

    def set_filename(self, filename):
        self.__curfile = filename
        self.__freshmodule = 1

    def write(self, fp):
        options = self.__options
        timestamp = time.ctime(time.time())
        # The time stamp in the header doesn't have the same format as that
        # generated by xgettext...
        print >> fp, pot_header % {'time': timestamp, 'version': __version__}
        # Sort the entries.  First sort each particular entry's keys, then
        # sort all the entries by their first item.
        reverse = {}
        for k, v in self.__messages.items():
            keys = v.keys()
            keys.sort()
            reverse.setdefault(tuple(keys), []).append((k, v))
        rkeys = reverse.keys()
        rkeys.sort()
        for rkey in rkeys:
            rentries = reverse[rkey]
            rentries.sort()
            for k, v in rentries:
                isdocstring = 0
                # If the entry was gleaned out of a docstring, then add a
                # comment stating so.  This is to aid translators who may wish
                # to skip translating some unimportant docstrings.
                if reduce(operator.__add__, v.values()):
                    isdocstring = 1
                # k is the message string, v is a dictionary-set of (filename,
                # lineno) tuples.  We want to sort the entries in v first by
                # file name and then by line number.
                v = v.keys()
                v.sort()
                if not options.writelocations:
                    pass
                # location comments are different b/w Solaris and GNU:
                elif options.locationstyle == options.SOLARIS:
                    for filename, lineno in v:
                        d = {'filename': filename, 'lineno': lineno}
                        print >>fp, _(
                            '# File: %(filename)s, line: %(lineno)d') % d
                elif options.locationstyle == options.GNU:
                    # fit as many locations on one line, as long as the
                    # resulting line length doesn't exceeds 'options.width'
                    locline = '#:'
                    for filename, lineno in v:
                        d = {'filename': filename, 'lineno': lineno}
                        s = _(' %(filename)s:%(lineno)d') % d
                        if len(locline) + len(s) <= options.width:
                            locline = locline + s
                        else:
                            print >> fp, locline
                            locline = "#:" + s
                    if len(locline) > 2:
                        print >> fp, locline
                if isdocstring:
                    print >> fp, '#, docstring'
                print >> fp, 'msgid', normalize(k)
                print >> fp, 'msgstr ""\n'



def main():
    global default_keywords
    try:
        opts, args = getopt.getopt(
            sys.argv[1:],
            'ad:DEhk:Kno:p:S:Vvw:x:X:',
            ['extract-all', 'default-domain=', 'escape', 'help',
             'keyword=', 'no-default-keywords',
             'add-location', 'no-location', 'output=', 'output-dir=',
             'style=', 'verbose', 'version', 'width=', 'exclude-file=',
             'docstrings', 'no-docstrings',
             ])
    except getopt.error, msg:
        usage(1, msg)

    # for holding option values
    class Options:
        # constants
        GNU = 1
        SOLARIS = 2
        # defaults
        extractall = 0 # FIXME: currently this option has no effect at all.
        escape = 0
        keywords = []
        outpath = ''
        outfile = 'messages.pot'
        writelocations = 1
        locationstyle = GNU
        verbose = 0
        width = 78
        excludefilename = ''
        docstrings = 0
        nodocstrings = {}

    options = Options()
    locations = {'gnu' : options.GNU,
                 'solaris' : options.SOLARIS,
                 }

    # parse options
    for opt, arg in opts:
        if opt in ('-h', '--help'):
            usage(0)
        elif opt in ('-a', '--extract-all'):
            options.extractall = 1
        elif opt in ('-d', '--default-domain'):
            options.outfile = arg + '.pot'
        elif opt in ('-E', '--escape'):
            options.escape = 1
        elif opt in ('-D', '--docstrings'):
            options.docstrings = 1
        elif opt in ('-k', '--keyword'):
            options.keywords.append(arg)
        elif opt in ('-K', '--no-default-keywords'):
            default_keywords = []
        elif opt in ('-n', '--add-location'):
            options.writelocations = 1
        elif opt in ('--no-location',):
            options.writelocations = 0
        elif opt in ('-S', '--style'):
            options.locationstyle = locations.get(arg.lower())
            if options.locationstyle is None:
                usage(1, _('Invalid value for --style: %s') % arg)
        elif opt in ('-o', '--output'):
            options.outfile = arg
        elif opt in ('-p', '--output-dir'):
            options.outpath = arg
        elif opt in ('-v', '--verbose'):
            options.verbose = 1
        elif opt in ('-V', '--version'):
            print _('pygettext.py (xgettext for Python) %s') % __version__
            sys.exit(0)
        elif opt in ('-w', '--width'):
            try:
                options.width = int(arg)
            except ValueError:
                usage(1, _('--width argument must be an integer: %s') % arg)
        elif opt in ('-x', '--exclude-file'):
            options.excludefilename = arg
        elif opt in ('-X', '--no-docstrings'):
            fp = open(arg)
            try:
                while 1:
                    line = fp.readline()
                    if not line:
                        break
                    options.nodocstrings[line[:-1]] = 1
            finally:
                fp.close()

    # calculate escapes
    make_escapes(options.escape)

    # calculate all keywords
    options.keywords.extend(default_keywords)

    # initialize list of strings to exclude
    if options.excludefilename:
        try:
            fp = open(options.excludefilename)
            options.toexclude = fp.readlines()
            fp.close()
        except IOError:
            print >> sys.stderr, _(
                "Can't read --exclude-file: %s") % options.excludefilename
            sys.exit(1)
    else:
        options.toexclude = []

    # slurp through all the files
    eater = TokenEater(options)
    for filename in args:
        if filename == '-':
            if options.verbose:
                print _('Reading standard input')
            fp = sys.stdin
            closep = 0
        else:
            if options.verbose:
                print _('Working on %s') % filename
            fp = open(filename)
            closep = 1
        try:
            eater.set_filename(filename)
            try:
                tokenize.tokenize(fp.readline, eater)
            except tokenize.TokenError, e:
                print >> sys.stderr, '%s: %s, line %d, column %d' % (
                    e[0], filename, e[1][0], e[1][1])
        finally:
            if closep:
                fp.close()

    # write the output
    if options.outfile == '-':
        fp = sys.stdout
        closep = 0
    else:
        if options.outpath:
            options.outfile = os.path.join(options.outpath, options.outfile)
        fp = open(options.outfile, 'w')
        closep = 1
    try:
        eater.write(fp)
    finally:
        if closep:
            fp.close()


if __name__ == '__main__':
    main()
    # some more test strings
    _(u'a unicode string')




More information about the Zope3-Checkins mailing list