mirrors/cosmopolitan
1
0
Fork 0
mirror of https://github.com/jart/cosmopolitan.git synced 2025-05-25 14:52:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

python-3.6.zip added from Github

Browse source 
README.cosmo contains the necessary links.
This commit is contained in:
ahgamut 2021-08-08 09:38:33 +05:30 • committed by Justine Tunney
parent 75fc601ff5
commit 0c4c56ff39
4219 changed files with 1968626 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

150
third_party/python/Tools/i18n/makelocalealias.py vendored Executable file
View file

@ -0,0 +1,150 @@
#!/usr/bin/env python3
"""
Convert the X11 locale.alias file into a mapping dictionary suitable
for locale.py.
Written by Marc-Andre Lemburg <mal@genix.com>, 2004-12-10.
"""
import locale
import sys
_locale = locale
# Location of the X11 alias file.
LOCALE_ALIAS = '/usr/share/X11/locale/locale.alias'
# Location of the glibc SUPPORTED locales file.
SUPPORTED = '/usr/share/i18n/SUPPORTED'
def parse(filename):
with open(filename, encoding='latin1') as f:
lines = list(f)
data = {}
for line in lines:
line = line.strip()
if not line:
continue
if line[:1] == '#':
continue
locale, alias = line.split()
# Fix non-standard locale names, e.g. ks_IN@devanagari.UTF-8
if '@' in alias:
alias_lang, _, alias_mod = alias.partition('@')
if '.' in alias_mod:
alias_mod, _, alias_enc = alias_mod.partition('.')
alias = alias_lang + '.' + alias_enc + '@' + alias_mod
# Strip ':'
if locale[-1] == ':':
locale = locale[:-1]
# Lower-case locale
locale = locale.lower()
# Ignore one letter locale mappings (except for 'c')
if len(locale) == 1 and locale != 'c':
continue
# Normalize encoding, if given
if '.' in locale:
lang, encoding = locale.split('.')[:2]
encoding = encoding.replace('-', '')
encoding = encoding.replace('_', '')
locale = lang + '.' + encoding
data[locale] = alias
return data
def parse_glibc_supported(filename):
with open(filename, encoding='latin1') as f:
lines = list(f)
data = {}
for line in lines:
line = line.strip()
if not line:
continue
if line[:1] == '#':
continue
line = line.replace('/', ' ').strip()
line = line.rstrip('\\').rstrip()
words = line.split()
if len(words) != 2:
continue
alias, alias_encoding = words
# Lower-case locale
locale = alias.lower()
# Normalize encoding, if given
if '.' in locale:
lang, encoding = locale.split('.')[:2]
encoding = encoding.replace('-', '')
encoding = encoding.replace('_', '')
locale = lang + '.' + encoding
# Add an encoding to alias
alias, _, modifier = alias.partition('@')
alias = _locale._replace_encoding(alias, alias_encoding)
if modifier and not (modifier == 'euro' and alias_encoding == 'ISO-8859-15'):
alias += '@' + modifier
data[locale] = alias
return data
def pprint(data):
items = sorted(data.items())
for k, v in items:
print(' %-40s%a,' % ('%a:' % k, v))
def print_differences(data, olddata):
items = sorted(olddata.items())
for k, v in items:
if k not in data:
print('# removed %a' % k)
elif olddata[k] != data[k]:
print('# updated %a -> %a to %a' % \
(k, olddata[k], data[k]))
# Additions are not mentioned
def optimize(data):
locale_alias = locale.locale_alias
locale.locale_alias = data.copy()
for k, v in data.items():
del locale.locale_alias[k]
if locale.normalize(k) != v:
locale.locale_alias[k] = v
newdata = locale.locale_alias
errors = check(data)
locale.locale_alias = locale_alias
if errors:
sys.exit(1)
return newdata
def check(data):
# Check that all alias definitions from the X11 file
# are actually mapped to the correct alias locales.
errors = 0
for k, v in data.items():
if locale.normalize(k) != v:
print('ERROR: %a -> %a != %a' % (k, locale.normalize(k), v),
file=sys.stderr)
errors += 1
return errors
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--locale-alias', default=LOCALE_ALIAS,
help='location of the X11 alias file '
'(default: %a)' % LOCALE_ALIAS)
parser.add_argument('--glibc-supported', default=SUPPORTED,
help='location of the glibc SUPPORTED locales file '
'(default: %a)' % SUPPORTED)
args = parser.parse_args()
data = locale.locale_alias.copy()
data.update(parse_glibc_supported(args.glibc_supported))
data.update(parse(args.locale_alias))
while True:
# Repeat optimization while the size is decreased.
n = len(data)
data = optimize(data)
if len(data) == n:
break
print_differences(data, locale.locale_alias)
print()
print('locale_alias = {')
pprint(data)
print('}')

238
third_party/python/Tools/i18n/msgfmt.py vendored Executable file
View file

@ -0,0 +1,238 @@
#! /usr/bin/env python3
# Written by Martin v. Löwis <loewis@informatik.hu-berlin.de>
"""Generate binary message catalog from textual translation description.
This program converts a textual Uniforum-style message catalog (.po file) into
a binary GNU catalog (.mo file). This is essentially the same function as the
GNU msgfmt program, however, it is a simpler implementation.
Usage: msgfmt.py [OPTIONS] filename.po
Options:
-o file
--output-file=file
Specify the output file to write to. If omitted, output will go to a
file named filename.mo (based off the input file name).
-h
--help
Print this message and exit.
-V
--version
Display version information and exit.
"""
import os
import sys
import ast
import getopt
import struct
import array
from email.parser import HeaderParser
__version__ = "1.1"
MESSAGES = {}
def usage(code, msg=''):
print(__doc__, file=sys.stderr)
if msg:
print(msg, file=sys.stderr)
sys.exit(code)
def add(id, str, fuzzy):
"Add a non-fuzzy translation to the dictionary."
global MESSAGES
if not fuzzy and str:
MESSAGES[id] = str
def generate():
"Return the generated output."
global MESSAGES
# the keys are sorted in the .mo file
keys = sorted(MESSAGES.keys())
offsets = []
ids = strs = b''
for id in keys:
# For each string, we need size and file offset. Each string is NUL
# terminated; the NUL does not count into the size.
offsets.append((len(ids), len(id), len(strs), len(MESSAGES[id])))
ids += id + b'\0'
strs += MESSAGES[id] + b'\0'
output = ''
# The header is 7 32-bit unsigned integers. We don't use hash tables, so
# the keys start right after the index tables.
# translated string.
keystart = 7*4+16*len(keys)
# and the values start after the keys
valuestart = keystart + len(ids)
koffsets = []
voffsets = []
# The string table first has the list of keys, then the list of values.
# Each entry has first the size of the string, then the file offset.
for o1, l1, o2, l2 in offsets:
koffsets += [l1, o1+keystart]
voffsets += [l2, o2+valuestart]
offsets = koffsets + voffsets
output = struct.pack("Iiiiiii",
0x950412de, # Magic
0, # Version
len(keys), # # of entries
7*4, # start of key index
7*4+len(keys)*8, # start of value index
0, 0) # size and offset of hash table
output += array.array("i", offsets).tobytes()
output += ids
output += strs
return output
def make(filename, outfile):
ID = 1
STR = 2
# Compute .mo name from .po name and arguments
if filename.endswith('.po'):
infile = filename
else:
infile = filename + '.po'
if outfile is None:
outfile = os.path.splitext(infile)[0] + '.mo'
try:
with open(infile, 'rb') as f:
lines = f.readlines()
except IOError as msg:
print(msg, file=sys.stderr)
sys.exit(1)
section = None
fuzzy = 0
# Start off assuming Latin-1, so everything decodes without failure,
# until we know the exact encoding
encoding = 'latin-1'
# Parse the catalog
lno = 0
for l in lines:
l = l.decode(encoding)
lno += 1
# If we get a comment line after a msgstr, this is a new entry
if l[0] == '#' and section == STR:
add(msgid, msgstr, fuzzy)
section = None
fuzzy = 0
# Record a fuzzy mark
if l[:2] == '#,' and 'fuzzy' in l:
fuzzy = 1
# Skip comments
if l[0] == '#':
continue
# Now we are in a msgid section, output previous section
if l.startswith('msgid') and not l.startswith('msgid_plural'):
if section == STR:
add(msgid, msgstr, fuzzy)
if not msgid:
# See whether there is an encoding declaration
p = HeaderParser()
charset = p.parsestr(msgstr.decode(encoding)).get_content_charset()
if charset:
encoding = charset
section = ID
l = l[5:]
msgid = msgstr = b''
is_plural = False
# This is a message with plural forms
elif l.startswith('msgid_plural'):
if section != ID:
print('msgid_plural not preceded by msgid on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l[12:]
msgid += b'\0' # separator of singular and plural
is_plural = True
# Now we are in a msgstr section
elif l.startswith('msgstr'):
section = STR
if l.startswith('msgstr['):
if not is_plural:
print('plural without msgid_plural on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l.split(']', 1)[1]
if msgstr:
msgstr += b'\0' # Separator of the various plural forms
else:
if is_plural:
print('indexed msgstr required for plural on %s:%d' % (infile, lno),
file=sys.stderr)
sys.exit(1)
l = l[6:]
# Skip empty lines
l = l.strip()
if not l:
continue
l = ast.literal_eval(l)
if section == ID:
msgid += l.encode(encoding)
elif section == STR:
msgstr += l.encode(encoding)
else:
print('Syntax error on %s:%d' % (infile, lno), \
'before:', file=sys.stderr)
print(l, file=sys.stderr)
sys.exit(1)
# Add last entry
if section == STR:
add(msgid, msgstr, fuzzy)
# Compute output
output = generate()
try:
with open(outfile,"wb") as f:
f.write(output)
except IOError as msg:
print(msg, file=sys.stderr)
def main():
try:
opts, args = getopt.getopt(sys.argv[1:], 'hVo:',
['help', 'version', 'output-file='])
except getopt.error as msg:
usage(1, msg)
outfile = None
# parse options
for opt, arg in opts:
if opt in ('-h', '--help'):
usage(0)
elif opt in ('-V', '--version'):
print("msgfmt.py", __version__)
sys.exit(0)
elif opt in ('-o', '--output-file'):
outfile = arg
# do it
if not args:
print('No input file given', file=sys.stderr)
print("Try `msgfmt --help' for more information.", file=sys.stderr)
return
for filename in args:
make(filename, outfile)
if __name__ == '__main__':
main()

631
third_party/python/Tools/i18n/pygettext.py vendored Executable file
View file

@ -0,0 +1,631 @@
#! /usr/bin/env python3
# -*- coding: iso-8859-1 -*-
# Originally written by Barry Warsaw <barry@python.org>
#
# Minimally patched to make it even more xgettext compatible
# by Peter Funk <pf@artcom-gmbh.de>
#
# 2002-11-22 Jürgen Hermann <jh@web.de>
# Added checks that _() only contains string literals, and
# command line args are resolved to module lists, i.e. you
# can now pass a filename, a module or package name, or a
# directory (including globbing chars, important for Win32).
# Made docstring fit in 80 chars wide displays using pydoc.
#
# for selftesting
try:
import fintl
_ = fintl.gettext
except ImportError:
_ = lambda s: s
__doc__ = _("""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 importlib.machinery
import importlib.util
import sys
import glob
import time
import getopt
import token
import tokenize
__version__ = '1.5'
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@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)s\\n"
"Content-Transfer-Encoding: %(encoding)s\\n"
"Generated-By: pygettext.py %(version)s\\n"
''')
def usage(code, msg=''):
print(__doc__ % globals(), file=sys.stderr)
if msg:
print(msg, file=sys.stderr)
sys.exit(code)
def make_escapes(pass_nonascii):
global escapes, escape
if pass_nonascii:
# Allow non-ascii characters to pass through so that e.g. 'msgid
# "Höhe"' would result not result in 'msgid "H\366he"'. Otherwise we
# escape any character outside the 32..126 range.
mod = 128
escape = escape_ascii
else:
mod = 256
escape = escape_nonascii
escapes = [r"\%03o" % i for i in range(mod)]
for i in range(32, 127):
escapes[i] = chr(i)
escapes[ord('\\')] = r'\\'
escapes[ord('\t')] = r'\t'
escapes[ord('\r')] = r'\r'
escapes[ord('\n')] = r'\n'
escapes[ord('\"')] = r'\"'
def escape_ascii(s, encoding):
return ''.join(escapes[ord(c)] if ord(c) < 128 else c for c in s)
def escape_nonascii(s, encoding):
return ''.join(escapes[b] for b in s.encode(encoding))
def is_literal_string(s):
return s[0] in '\'"' or (s[0] in 'rRuU' and s[1] in '\'"')
def safe_eval(s):
# unwrap quotes, safely
return eval(s, {'__builtins__':{}}, {})
def normalize(s, encoding):
# 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, encoding) + '"'
else:
if not lines[-1]:
del lines[-1]
lines[-1] = lines[-1] + '\n'
for i in range(len(lines)):
lines[i] = escape(lines[i], encoding)
lineterm = '\\n"\n"'
s = '""\n"' + lineterm.join(lines) + '"'
return s
def containsAny(str, set):
"""Check whether 'str' contains ANY of the chars in 'set'"""
return 1 in [c in str for c in set]
def getFilesForName(name):
"""Get a list of module files for a filename, a module or package name,
or a directory.
"""
if not os.path.exists(name):
# check for glob chars
if containsAny(name, "*?[]"):
files = glob.glob(name)
list = []
for file in files:
list.extend(getFilesForName(file))
return list
# try to find module or package
try:
spec = importlib.util.find_spec(name)
name = spec.origin
except ImportError:
name = None
if not name:
return []
if os.path.isdir(name):
# find all python files in directory
list = []
# get extension for python source files
_py_ext = importlib.machinery.SOURCE_SUFFIXES[0]
for root, dirs, files in os.walk(name):
# don't recurse into CVS directories
if 'CVS' in dirs:
dirs.remove('CVS')
# add all *.py files to list
list.extend(
[os.path.join(root, file) for file in files
if os.path.splitext(file)[1] == _py_ext]
)
return list
elif os.path.exists(name):
# a single file
return [name]
return []
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
self.__enclosurecount = 0
def __call__(self, ttype, tstring, stup, etup, line):
# dispatch
## import token
## print('ttype:', token.tok_name[ttype], 'tstring:', tstring,
## file=sys.stderr)
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 and is_literal_string(tstring):
self.__addentry(safe_eval(tstring), lineno, isdocstring=1)
self.__freshmodule = 0
elif ttype not in (tokenize.COMMENT, tokenize.NL):
self.__freshmodule = 0
return
# class or func/method 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):
# skip over any enclosure pairs until we see the colon
if ttype == tokenize.OP:
if tstring == ':' and self.__enclosurecount == 0:
# we see a colon and we're not in an enclosure: end of def
self.__state = self.__suitedocstring
elif tstring in '([{':
self.__enclosurecount += 1
elif tstring in ')]}':
self.__enclosurecount -= 1
def __suitedocstring(self, ttype, tstring, lineno):
# ignore any intervening noise
if ttype == tokenize.STRING and is_literal_string(tstring):
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 and is_literal_string(tstring):
self.__data.append(safe_eval(tstring))
elif ttype not in [tokenize.COMMENT, token.INDENT, token.DEDENT,
token.NEWLINE, tokenize.NL]:
# warn if we see anything else than STRING or whitespace
print(_(
'*** %(file)s:%(lineno)s: Seen unexpected token "%(token)s"'
) % {
'token': tstring,
'file': self.__curfile,
'lineno': self.__lineno
}, file=sys.stderr)
self.__state = self.__waiting
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.strftime('%Y-%m-%d %H:%M%z')
encoding = fp.encoding if fp.encoding else 'UTF-8'
print(pot_header % {'time': timestamp, 'version': __version__,
'charset': encoding,
'encoding': '8bit'}, file=fp)
# 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 = sorted(v.keys())
reverse.setdefault(tuple(keys), []).append((k, v))
rkeys = sorted(reverse.keys())
for rkey in rkeys:
rentries = reverse[rkey]
rentries.sort()
for k, v in rentries:
# 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.
isdocstring = any(v.values())
# 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 = sorted(v.keys())
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(_(
'# File: %(filename)s, line: %(lineno)d') % d, file=fp)
elif options.locationstyle == options.GNU:
# fit as many locations on one line, as long as the
# resulting line length doesn't exceed '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(locline, file=fp)
locline = "#:" + s
if len(locline) > 2:
print(locline, file=fp)
if isdocstring:
print('#, docstring', file=fp)
print('msgid', normalize(k, encoding), file=fp)
print('msgstr ""\n', file=fp)
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 as 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(not 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(_(
"Can't read --exclude-file: %s") % options.excludefilename, file=sys.stderr)
sys.exit(1)
else:
options.toexclude = []
# resolve args to module lists
expanded = []
for arg in args:
if arg == '-':
expanded.append(arg)
else:
expanded.extend(getFilesForName(arg))
args = expanded
# slurp through all the files
eater = TokenEater(options)
for filename in args:
if filename == '-':
if options.verbose:
print(_('Reading standard input'))
fp = sys.stdin.buffer
closep = 0
else:
if options.verbose:
print(_('Working on %s') % filename)
fp = open(filename, 'rb')
closep = 1
try:
eater.set_filename(filename)
try:
tokens = tokenize.tokenize(fp.readline)
for _token in tokens:
eater(*_token)
except tokenize.TokenError as e:
print('%s: %s, line %d, column %d' % (
e.args[0], filename, e.args[1][0], e.args[1][1]),
file=sys.stderr)
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
# this one creates a warning
_('*** Seen unexpected token "%(token)s"') % {'token': 'test'}
_('more' 'than' 'one' 'string')