1
# Copyright (C) 2006 by Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
"""Utilities for distinguishing binary files from text files"""
19
from itertools import chain
21
from bzrlib.errors import BinaryFile
22
from bzrlib.iterablefile import IterableFile
23
from bzrlib.osutils import file_iterator
27
"""Produce a file iterator that is guaranteed to be text, without seeking.
28
BinaryFile is raised if the file contains a NUL in the first 1024 bytes.
30
first_chunk = input.read(1024)
31
if '\x00' in first_chunk:
33
return IterableFile(chain((first_chunk,), file_iterator(input)))
36
def check_text_lines(lines):
37
"""Raise BinaryFile if the supplied lines contain NULs.
38
Only the first 1024 characters are checked.
40
f = IterableFile(lines)
41
if '\x00' in f.read(1024):
45
def check_text_path(path):
46
"""Check whether the supplied path is a text, not binary file.
47
Raise BinaryFile if a NUL occurs in the first 1024 bytes.
49
text_file(open(path, 'rb'))