Mercurial > repos > shellac > sam_consensus_v3

comparison env/lib/python3.9/site-packages/chardet/cli/chardetect.py @ 0:4f3585e2f14b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 60cee0fc7c0cda8592644e1aad72851dec82c959"
author shellac
date Mon, 22 Mar 2021 18:12:50 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:4f3585e2f14b
1 """
2 Script which takes one or more file paths and reports on their detected
3 encodings
4
5 Example::
6
7 % chardetect somefile someotherfile
8 somefile: windows-1252 with confidence 0.5
9 someotherfile: ascii with confidence 1.0
10
11 If no paths are provided, it takes its input from stdin.
12
13 """
14
15 from __future__ import absolute_import, print_function, unicode_literals
16
17 import argparse
18 import sys
19
20 from chardet import __version__
21 from chardet.compat import PY2
22 from chardet.universaldetector import UniversalDetector
23
24
25 def description_of(lines, name='stdin'):
26 """
27 Return a string describing the probable encoding of a file or
28 list of strings.
29
30 :param lines: The lines to get the encoding of.
31 :type lines: Iterable of bytes
32 :param name: Name of file or collection of lines
33 :type name: str
34 """
35 u = UniversalDetector()
36 for line in lines:
37 line = bytearray(line)
38 u.feed(line)
39 # shortcut out of the loop to save reading further - particularly useful if we read a BOM.
40 if u.done:
41 break
42 u.close()
43 result = u.result
44 if PY2:
45 name = name.decode(sys.getfilesystemencoding(), 'ignore')
46 if result['encoding']:
47 return '{}: {} with confidence {}'.format(name, result['encoding'],
48 result['confidence'])
49 else:
50 return '{}: no result'.format(name)
51
52
53 def main(argv=None):
54 """
55 Handles command line arguments and gets things started.
56
57 :param argv: List of arguments, as if specified on the command-line.
58 If None, ``sys.argv[1:]`` is used instead.
59 :type argv: list of str
60 """
61 # Get command line arguments
62 parser = argparse.ArgumentParser(
63 description="Takes one or more file paths and reports their detected \
64 encodings")
65 parser.add_argument('input',
66 help='File whose encoding we would like to determine. \
67 (default: stdin)',
68 type=argparse.FileType('rb'), nargs='*',
69 default=[sys.stdin if PY2 else sys.stdin.buffer])
70 parser.add_argument('--version', action='version',
71 version='%(prog)s {}'.format(__version__))
72 args = parser.parse_args(argv)
73
74 for f in args.input:
75 if f.isatty():
76 print("You are running chardetect interactively. Press " +
77 "CTRL-D twice at the start of a blank line to signal the " +
78 "end of your input. If you want help, run chardetect " +
79 "--help\n", file=sys.stderr)
80 print(description_of(f, f.name))
81
82
83 if __name__ == '__main__':
84 main()