/usr/lib/python3/dist-packages/decopy/parsers.py is in decopy 0.2.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | #!/usr/bin/env python3
# -*- coding: utf-8 -*- vim60:fdm=marker
#
# Copyright: 2016, Maximiliano Curia <maxy@debian.org>
#
# License: ISC
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
# .
# THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES WITH
# REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
# AND FITNESS. IN NO EVENT SHALL ISC BE LIABLE FOR ANY SPECIAL, DIRECT,
# INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
# LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
# OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
'''File Parsers'''
import functools
import logging
import shutil
import string
import subprocess
import tokenize
import xdg.Mime
# Local modules
from .datatypes import CopyrightHolder
from .matchers import find_licenses, parse_copyright, clean_comments, parse_holders
def generic_parser(filename):
content = ''
holders = []
with open(filename, 'rb') as f:
continuation = None
for raw_line in f:
try:
line = raw_line.decode('utf-8')
except UnicodeDecodeError:
if has_control_chars(raw_line):
# binary?
chars = (str(char) for char in raw_line
if char in PRINTABLE_BYTES)
line = ''.join(chars)
else:
line = raw_line.decode('latin1')
content += line
line = line.rstrip('\n')
copyrights, continuation = parse_copyright(line, continuation)
if not copyrights:
continue
for copyright_ in copyrights:
holder = CopyrightHolder.from_copyright(copyright_)
if holder:
holders.append(holder)
content = clean_comments(content)
licenses = find_licenses(content)
return holders, licenses
@functools.lru_cache()
def cmd_parser_factory(*cmd):
def _parser(filename):
fullcmd = cmd + (filename,)
try:
content = subprocess.check_output(fullcmd, universal_newlines=True,
stderr=subprocess.STDOUT)
except (subprocess.CalledProcessError, UnicodeDecodeError) as e:
logging.info('failed to parse %s with %s, ignoring (%s)',
filename, cmd, e)
content = ''
holders = parse_holders(content)
content = clean_comments(content)
licenses = find_licenses(content)
return holders, licenses
if shutil.which(cmd[0]) is None:
logging.warn('command %s not found, using generic parser as fallback',
cmd[0])
return generic_parser
return _parser
def python_parser(filename):
'''Extract comments and doc strings from a python file'''
lines = []
newline = True
with open(filename, 'rb') as f:
for token in tokenize.tokenize(f.readline):
if (token.type == tokenize.COMMENT) or \
(newline and token.type == tokenize.STRING):
lines.append(token.string)
elif token.type == tokenize.NEWLINE:
newline = True
elif newline and (token.type in {tokenize.INDENT, tokenize.NL}):
continue
else:
newline = False
content = '\n'.join(lines)
holders = parse_holders(content)
content = clean_comments(content)
licenses = find_licenses(content)
return holders, licenses
KNOWN_PARSERS = {
'application/gzip': cmd_parser_factory('zcat'),
'application/x-bzip': cmd_parser_factory('bzcat'),
'application/x-lzma': cmd_parser_factory('xzcat'),
'application/x-xz': cmd_parser_factory('xzcat'),
'text/x-python': python_parser,
'image/jpeg': cmd_parser_factory('exiv2'),
'image/png': cmd_parser_factory('exiv2'),
}
def has_control_chars(bytes_seq):
for i in bytes_seq:
# ascii control chars (C0), and delete (DEL)
if i < 32 or i == 127:
# except tab (HT), line feed (LF) and carriage return (CR)
if i in (9, 10, 13):
continue
return True
return False
PRINTABLE_BYTES = bytes(string.printable, encoding='ascii')
def parse_file(fullname, options):
'''Parses the received file with the matching parser.
Returns:
The list of copyrights and licenses obtained by the parser.
'''
if options.text:
parser = generic_parser
else:
xdg_type = xdg.Mime.get_type(fullname)
logging.debug('Type for %s is: %s', fullname, xdg_type)
parser = KNOWN_PARSERS.get(str(xdg_type), generic_parser)
copyrights, licenses = parser(fullname)
logging.debug('Parsed %s: %s, %s', fullname, copyrights, licenses)
return copyrights, licenses
|