mirror of
https://github.com/MCV-Software/TWBlue.git
synced 2024-11-22 11:18:08 -06:00
Updated Pygettext to Python 3.7.9
This commit is contained in:
parent
8a8f1998ac
commit
60a67947e6
@ -1,6 +1,6 @@
|
||||
#! /usr/bin/env python
|
||||
#! /usr/bin/env python3
|
||||
# -*- coding: iso-8859-1 -*-
|
||||
# Originally written by Barry Warsaw <barry@zope.com>
|
||||
# Originally written by Barry Warsaw <barry@python.org>
|
||||
#
|
||||
# Minimally patched to make it even more xgettext compatible
|
||||
# by Peter Funk <pf@artcom-gmbh.de>
|
||||
@ -156,14 +156,14 @@ If `inputfile' is -, standard input is read.
|
||||
""")
|
||||
|
||||
import os
|
||||
import imp
|
||||
import importlib.machinery
|
||||
import importlib.util
|
||||
import sys
|
||||
import glob
|
||||
import time
|
||||
import getopt
|
||||
import token
|
||||
import tokenize
|
||||
import operator
|
||||
|
||||
__version__ = '1.5'
|
||||
|
||||
@ -189,50 +189,51 @@ msgstr ""
|
||||
"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"
|
||||
"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 >> sys.stderr, __doc__ % globals()
|
||||
print(__doc__ % globals(), file=sys.stderr)
|
||||
if msg:
|
||||
print >> sys.stderr, msg
|
||||
print(msg, file=sys.stderr)
|
||||
sys.exit(code)
|
||||
|
||||
|
||||
|
||||
escapes = []
|
||||
|
||||
def make_escapes(pass_iso8859):
|
||||
global escapes
|
||||
if pass_iso8859:
|
||||
# Allow iso-8859 characters to pass through so that e.g. 'msgid
|
||||
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
|
||||
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('\"')] = '\\"'
|
||||
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(s):
|
||||
global escapes
|
||||
s = list(s)
|
||||
for i in range(len(s)):
|
||||
s[i] = escapes[ord(s[i])]
|
||||
return EMPTYSTRING.join(s)
|
||||
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):
|
||||
@ -240,18 +241,18 @@ def safe_eval(s):
|
||||
return eval(s, {'__builtins__':{}}, {})
|
||||
|
||||
|
||||
def normalize(s):
|
||||
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) + '"'
|
||||
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])
|
||||
lines[i] = escape(lines[i], encoding)
|
||||
lineterm = '\\n"\n"'
|
||||
s = '""\n"' + lineterm.join(lines) + '"'
|
||||
return s
|
||||
@ -262,64 +263,6 @@ def containsAny(str, set):
|
||||
return 1 in [c in str for c in set]
|
||||
|
||||
|
||||
def _visit_pyfiles(list, dirname, names):
|
||||
"""Helper for getFilesForName()."""
|
||||
# get extension for python source files
|
||||
if not globals().has_key('_py_ext'):
|
||||
global _py_ext
|
||||
_py_ext = [triple[0] for triple in imp.get_suffixes()
|
||||
if triple[2] == imp.PY_SOURCE][0]
|
||||
|
||||
# don't recurse into CVS directories
|
||||
if 'CVS' in names:
|
||||
names.remove('CVS')
|
||||
|
||||
# add all *.py files to list
|
||||
list.extend(
|
||||
[os.path.join(dirname, file) for file in names
|
||||
if os.path.splitext(file)[1] == _py_ext]
|
||||
)
|
||||
|
||||
|
||||
def _get_modpkg_path(dotted_name, pathlist=None):
|
||||
"""Get the filesystem path for a module or a package.
|
||||
|
||||
Return the file system path to a file for a module, and to a directory for
|
||||
a package. Return None if the name is not found, or is a builtin or
|
||||
extension module.
|
||||
"""
|
||||
# split off top-most name
|
||||
parts = dotted_name.split('.', 1)
|
||||
|
||||
if len(parts) > 1:
|
||||
# we have a dotted path, import top-level package
|
||||
try:
|
||||
file, pathname, description = imp.find_module(parts[0], pathlist)
|
||||
if file: file.close()
|
||||
except ImportError:
|
||||
return None
|
||||
|
||||
# check if it's indeed a package
|
||||
if description[2] == imp.PKG_DIRECTORY:
|
||||
# recursively handle the remaining name parts
|
||||
pathname = _get_modpkg_path(parts[1], [pathname])
|
||||
else:
|
||||
pathname = None
|
||||
else:
|
||||
# plain name
|
||||
try:
|
||||
file, pathname, description = imp.find_module(
|
||||
dotted_name, pathlist)
|
||||
if file:
|
||||
file.close()
|
||||
if description[2] not in [imp.PY_SOURCE, imp.PKG_DIRECTORY]:
|
||||
pathname = None
|
||||
except ImportError:
|
||||
pathname = None
|
||||
|
||||
return pathname
|
||||
|
||||
|
||||
def getFilesForName(name):
|
||||
"""Get a list of module files for a filename, a module or package name,
|
||||
or a directory.
|
||||
@ -334,14 +277,28 @@ def getFilesForName(name):
|
||||
return list
|
||||
|
||||
# try to find module or package
|
||||
name = _get_modpkg_path(name)
|
||||
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 = []
|
||||
os.path.walk(name, _visit_pyfiles, 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
|
||||
@ -359,12 +316,13 @@ class TokenEater:
|
||||
self.__lineno = -1
|
||||
self.__freshmodule = 1
|
||||
self.__curfile = None
|
||||
self.__enclosurecount = 0
|
||||
|
||||
def __call__(self, ttype, tstring, stup, etup, line):
|
||||
# dispatch
|
||||
## import token
|
||||
## print >> sys.stderr, 'ttype:', token.tok_name[ttype], \
|
||||
## 'tstring:', tstring
|
||||
## print('ttype:', token.tok_name[ttype], 'tstring:', tstring,
|
||||
## file=sys.stderr)
|
||||
self.__state(ttype, tstring, stup[0])
|
||||
|
||||
def __waiting(self, ttype, tstring, lineno):
|
||||
@ -373,13 +331,13 @@ class TokenEater:
|
||||
if opts.docstrings and not opts.nodocstrings.get(self.__curfile):
|
||||
# module docstring?
|
||||
if self.__freshmodule:
|
||||
if ttype == tokenize.STRING:
|
||||
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 docstring?
|
||||
# class or func/method docstring?
|
||||
if ttype == tokenize.NAME and tstring in ('class', 'def'):
|
||||
self.__state = self.__suiteseen
|
||||
return
|
||||
@ -387,13 +345,19 @@ class TokenEater:
|
||||
self.__state = self.__keywordseen
|
||||
|
||||
def __suiteseen(self, ttype, tstring, lineno):
|
||||
# ignore anything until we see the colon
|
||||
if ttype == tokenize.OP and tstring == ':':
|
||||
# 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:
|
||||
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,
|
||||
@ -418,18 +382,18 @@ class TokenEater:
|
||||
if self.__data:
|
||||
self.__addentry(EMPTYSTRING.join(self.__data))
|
||||
self.__state = self.__waiting
|
||||
elif ttype == tokenize.STRING:
|
||||
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 >> sys.stderr, _(
|
||||
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):
|
||||
@ -445,45 +409,41 @@ class TokenEater:
|
||||
|
||||
def write(self, fp):
|
||||
options = self.__options
|
||||
timestamp = time.strftime('%Y-%m-%d %H:%M+%Z')
|
||||
# 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__}
|
||||
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 = v.keys()
|
||||
keys.sort()
|
||||
keys = sorted(v.keys())
|
||||
reverse.setdefault(tuple(keys), []).append((k, v))
|
||||
rkeys = reverse.keys()
|
||||
rkeys.sort()
|
||||
rkeys = sorted(reverse.keys())
|
||||
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
|
||||
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 = v.keys()
|
||||
v.sort()
|
||||
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 >>fp, _(
|
||||
'# File: %(filename)s, line: %(lineno)d') % d
|
||||
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 exceeds 'options.width'
|
||||
# resulting line length doesn't exceed 'options.width'
|
||||
locline = '#:'
|
||||
for filename, lineno in v:
|
||||
d = {'filename': filename, 'lineno': lineno}
|
||||
@ -491,14 +451,14 @@ class TokenEater:
|
||||
if len(locline) + len(s) <= options.width:
|
||||
locline = locline + s
|
||||
else:
|
||||
print >> fp, locline
|
||||
print(locline, file=fp)
|
||||
locline = "#:" + s
|
||||
if len(locline) > 2:
|
||||
print >> fp, locline
|
||||
print(locline, file=fp)
|
||||
if isdocstring:
|
||||
print >> fp, '#, docstring'
|
||||
print >> fp, 'msgid', normalize(k)
|
||||
print >> fp, 'msgstr ""\n'
|
||||
print('#, docstring', file=fp)
|
||||
print('msgid', normalize(k, encoding), file=fp)
|
||||
print('msgstr ""\n', file=fp)
|
||||
|
||||
|
||||
|
||||
@ -514,7 +474,7 @@ def main():
|
||||
'style=', 'verbose', 'version', 'width=', 'exclude-file=',
|
||||
'docstrings', 'no-docstrings',
|
||||
])
|
||||
except getopt.error, msg:
|
||||
except getopt.error as msg:
|
||||
usage(1, msg)
|
||||
|
||||
# for holding option values
|
||||
@ -572,7 +532,7 @@ def main():
|
||||
elif opt in ('-v', '--verbose'):
|
||||
options.verbose = 1
|
||||
elif opt in ('-V', '--version'):
|
||||
print _('pygettext.py (xgettext for Python) %s') % __version__
|
||||
print(_('pygettext.py (xgettext for Python) %s') % __version__)
|
||||
sys.exit(0)
|
||||
elif opt in ('-w', '--width'):
|
||||
try:
|
||||
@ -593,7 +553,7 @@ def main():
|
||||
fp.close()
|
||||
|
||||
# calculate escapes
|
||||
make_escapes(options.escape)
|
||||
make_escapes(not options.escape)
|
||||
|
||||
# calculate all keywords
|
||||
options.keywords.extend(default_keywords)
|
||||
@ -605,8 +565,8 @@ def main():
|
||||
options.toexclude = fp.readlines()
|
||||
fp.close()
|
||||
except IOError:
|
||||
print >> sys.stderr, _(
|
||||
"Can't read --exclude-file: %s") % options.excludefilename
|
||||
print(_(
|
||||
"Can't read --exclude-file: %s") % options.excludefilename, file=sys.stderr)
|
||||
sys.exit(1)
|
||||
else:
|
||||
options.toexclude = []
|
||||
@ -625,21 +585,24 @@ def main():
|
||||
for filename in args:
|
||||
if filename == '-':
|
||||
if options.verbose:
|
||||
print _('Reading standard input')
|
||||
fp = sys.stdin
|
||||
print(_('Reading standard input'))
|
||||
fp = sys.stdin.buffer
|
||||
closep = 0
|
||||
else:
|
||||
if options.verbose:
|
||||
print _('Working on %s') % filename
|
||||
fp = open(filename)
|
||||
print(_('Working on %s') % filename)
|
||||
fp = open(filename, 'rb')
|
||||
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])
|
||||
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()
|
||||
@ -663,7 +626,6 @@ def main():
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
# some more test strings
|
||||
_(u'a unicode string')
|
||||
# this one creates a warning
|
||||
_('*** Seen unexpected token "%(token)s"') % {'token': 'test'}
|
||||
_('more' 'than' 'one' 'string')
|
||||
|
||||
Loading…
Reference in New Issue
Block a user