File: archive_corpus.py

package info (click to toggle)
chromium 139.0.7258.127-1
  • links: PTS, VCS
  • area: main
  • in suites:
  • size: 6,122,068 kB
  • sloc: cpp: 35,100,771; ansic: 7,163,530; javascript: 4,103,002; python: 1,436,920; asm: 946,517; xml: 746,709; pascal: 187,653; perl: 88,691; sh: 88,436; objc: 79,953; sql: 51,488; cs: 44,583; fortran: 24,137; makefile: 22,147; tcl: 15,277; php: 13,980; yacc: 8,984; ruby: 7,485; awk: 3,720; lisp: 3,096; lex: 1,327; ada: 727; jsp: 228; sed: 36
file content (60 lines) | stat: -rwxr-xr-x 1,882 bytes parent folder | download | duplicates (9)
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
#!/usr/bin/env python3
#
# Copyright 2016 The Chromium Authors
# 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

SEED_CORPUS_LIMIT_MB = 100


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 = []
  seed_corpus_path = args.output

  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(seed_corpus_path, '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 os.path.getsize(seed_corpus_path) > SEED_CORPUS_LIMIT_MB * 1024 * 1024:
    print('Seed corpus %s exceeds maximum allowed size (%d MB).' %
          (seed_corpus_path, SEED_CORPUS_LIMIT_MB))
    sys.exit(-1)


if __name__ == '__main__':
  main()