admin/createFileHash.py

   1 #! /usr/bin/env python
   2 # This file is part of the GROMACS molecular simulation package.
   3 #
   4 # Copyright (c) 2019, by the GROMACS development team, led by
   5 # Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
   6 # and including many others, as listed in the AUTHORS file in the
   7 # top-level source directory and at http://www.gromacs.org.
   8 #
   9 # GROMACS is free software; you can redistribute it and/or
  10 # modify it under the terms of the GNU Lesser General Public License
  11 # as published by the Free Software Foundation; either version 2.1
  12 # of the License, or (at your option) any later version.
  13 #
  14 # GROMACS is distributed in the hope that it will be useful,
  15 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  16 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  17 # Lesser General Public License for more details.
  18 #
  19 # You should have received a copy of the GNU Lesser General Public
  20 # License along with GROMACS; if not, see
  21 # http://www.gnu.org/licenses, or write to the Free Software Foundation,
  22 # Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA.
  23 #
  24 # If you want to redistribute modifications to GROMACS, please
  25 # consider that scientific software is very special. Version
  26 # control is crucial - bugs must be traceable. We will be happy to
  27 # consider code for inclusion in the official distribution, but
  28 # derived work must not be called official GROMACS. Details are found
  29 # in the README & COPYING files - if they are missing, get the
  30 # official version at http://www.gromacs.org.
  31 #
  32 # To help us fund GROMACS development, we humbly ask that you cite
  33 # the research papers on the package. Check out http://www.gromacs.org.
  34 import hashlib, hmac, os, stat, sys, re
  35 from re import search
  36
  37 """
  38 Calculate hash of files in build tree to allow checking against
  39 stored hashes in case of the tree not being in git (e.g. if the
  40 program is build from a release tarball.
  41
  42 Based on example script found here:
  43     https://unix.stackexchange.com/a/35847
  44 """
  45
  46 def is_in_whitelist(name):
  47     """Return true if file is white listed to be included in hash calculation."""
  48     in_whitelist = False
  49     whitelist = ["\.cpp$", "\.h$", "\.cuh$", "\.cu$", "\.clh$", "CMakeList.txt$", "\.cmake$", "\.in$", "\.cmakein$", "\.py$"]
  50     for item in whitelist:
  51         if search(item, name):
  52             in_whitelist = True
  53             break
  54
  55     return in_whitelist
  56
  57 def is_blacklisted(name):
  58     """Return if a file has been explicitly blacklisted.
  59
  60     """
  61     is_blacklisted = False
  62     blacklist = ["gmx-completion"]
  63     for item in blacklist:
  64         if search(item, name):
  65             is_blacklisted = True
  66             break
  67
  68     return is_blacklisted
  69
  70 def file_hash(name):
  71     """Return the hash of the contents of the specified file, as a hex string
  72
  73     Reads file in chunks of 16384 bytes and calculates the hash of the complete
  74     file afterwards.
  75     The hashing algorithm used is sha256, to avoid accidental clashes when using
  76     a more simple algorithm such as md5.
  77     """
  78     f = open(name, 'rb')
  79     h = hashlib.sha256()
  80     while True:
  81         buf = f.read(16384)
  82         if len(buf) == 0: break
  83         h.update(buf)
  84     f.close()
  85     return h.hexdigest()
  86
  87 def traverse(h, path, original_path):
  88     """Recursive function to traverse a file path until a regular file is found.
  89     Walks down the path given as the input and updates the hash function with
  90     information of new files that are found on bottom of the list.
  91
  92     Information used to calculate the hash are the name and the contents of the file.
  93     Uses both absolute and relative path to make sure only the relative path is used
  94     to calculate the hash.
  95
  96     Ignores files that are not in the white-list and also skips files that are
  97     explicitly blacklisted.
  98     Other things that are ignored are symlinks and all kinds of special files.
  99     """
 100     rs = os.lstat(path)
 101     quoted_name = repr(os.path.relpath(path, original_path))
 102     if stat.S_ISDIR(rs.st_mode):
 103         for entry in sorted(os.listdir(path)):
 104             traverse(h, os.path.join(path, entry), original_path)
 105     elif stat.S_ISREG(rs.st_mode):
 106         # Only test files that actually take part in building GROMACS
 107         if (is_in_whitelist(path) and not is_blacklisted(path)):
 108             fullname = 'reg ' + quoted_name + ' '
 109             fullname += str(rs.st_size) + ' '
 110             fullname += file_hash(path) + '\n'
 111             h.update(fullname.encode('utf-8'))
 112     else: pass # silently symlinks and other special files
 113
 114 def main():
 115     """Run the hashing script.
 116
 117     Takes single directory to hash files in.
 118
 119     """
 120     import os
 121     import sys
 122     import argparse
 123
 124     parser = argparse.ArgumentParser(description='Hash all white listed files in a single directory')
 125     parser.add_argument('-s',
 126             '--source-root',
 127             help='Source tree directory, can be specified multiple times to get several directories hashed',
 128             nargs='*',
 129             required=True)
 130     parser.add_argument('-o',
 131             '--output-file',
 132             help='File to write hash to.',
 133             default='hashresult')
 134
 135     args = parser.parse_args()
 136
 137     outfile_path = args.output_file
 138     h = hashlib.sha256()
 139     for input_sources in args.source_root:
 140         traverse(h, input_sources, input_sources)
 141
 142     end = 'end\n'
 143     h.update(end.encode('utf-8'))
 144     outputfile = open(outfile_path, 'w')
 145     outputfile.write(h.hexdigest())
 146
 147 if __name__ == '__main__':
 148     main()
 149