File: archive_corpus.py

package info (click to toggle)
chromium 73.0.3683.75-1~deb9u1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 1,792,156 kB
  • sloc: cpp: 13,473,466; ansic: 1,577,080; python: 898,539; javascript: 655,737; xml: 341,883; asm: 306,070; java: 289,969; perl: 80,911; objc: 67,198; sh: 43,184; cs: 27,853; makefile: 12,092; php: 11,064; yacc: 10,373; tcl: 8,875; ruby: 3,941; lex: 1,800; pascal: 1,473; lisp: 812; awk: 41; jsp: 39; sed: 19; sql: 3
file content (50 lines) | stat: -rwxr-xr-x 1,555 bytes parent folder | download | duplicates (3)
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
#!/usr/bin/python2
#
# Copyright 2016 The Chromium Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.

"""Archive corpus file into zip and generate .d depfile.

Invoked by GN from fuzzer_test.gni.
"""

from __future__ import print_function
import argparse
import os
import sys
import warnings
import zipfile


def main():
  parser = argparse.ArgumentParser(description="Generate fuzzer config.")
  parser.add_argument('corpus_directories', metavar='corpus_dir', type=str,
                      nargs='+')
  parser.add_argument('--output', metavar='output_archive_name.zip',
                      required=True)
  args = parser.parse_args()

  corpus_files = []

  for directory in args.corpus_directories:
    if not os.path.exists(directory):
      raise Exception('The given seed_corpus directory (%s) does not exist.' %
                      directory)
    for (dirpath, _, filenames) in os.walk(directory):
      for filename in filenames:
        full_filename = os.path.join(dirpath, filename)
        corpus_files.append(full_filename)

  with zipfile.ZipFile(args.output, 'w') as z:
    # Turn warnings into errors to interrupt the build: crbug.com/653920.
    with warnings.catch_warnings():
      warnings.simplefilter("error")
      for i, corpus_file in enumerate(corpus_files):
        # To avoid duplication of filenames inside the archive, use numbers.
        arcname = '%016d' % i
        z.write(corpus_file, arcname)


if __name__ == '__main__':
  main()