ansible/files/scripts/create-filelist

#!/usr/bin/python
from __future__ import print_function

# A simple script to generate a file list in a format easily consumable by a
# shell script.

# Originally written by Jason Tibbitts <tibbs@math.uh.edu> in 2016.
# Donated to the public domain.  If you require a statement of license, please
# consider this work to be licensed as "CC0 Universal", any version you choose.

import argparse
import hashlib
import os
import sys
from scandir import scandir

# productmd is optional, needed only for the imagelist feature
try:
    from productmd.images import SUPPORTED_IMAGE_FORMATS
except ImportError:
    SUPPORTED_IMAGE_FORMATS = []


def get_ftype(entry):
    """Return a simple indicator of the file type."""
    if entry.is_symlink():
        return 'l'
    if entry.is_dir():
        return 'd'
    return 'f'


def sha1(fname):
    """Return the SHA1 checksum of a file in hex."""
    fh = open(fname, 'rb')
    sha1 = hashlib.sha1()
    block = fh.read(2 ** 16)
    while len(block) > 0:
        sha1.update(block)
        block = fh.read(2 ** 16)

    return sha1.hexdigest()


def recursedir(path='.', skip=[], alwaysskip=['.~tmp~']):
    """Just like scandir, but recursively.

    Will skip everything in the skip array, but only at the top level
    directory.
    """
    for entry in scandir(path):
        if entry.name in skip:
            continue
        if entry.name in alwaysskip:
            continue
        if entry.is_dir(follow_symlinks=False):
            # Don't pass skip here, because we only skip in the top level
            for rentry in recursedir(entry.path, alwaysskip=alwaysskip):
                yield rentry
        yield entry


def parseopts():
    null = open(os.devnull, 'w')
    p = argparse.ArgumentParser(
        description='Generate a list of files and times, suitable for consumption by quick-fedora-mirror, '
                    'and (optionally) a much smaller list of only files that match one of the productmd '
                    ' supported image types, for use by fedfind.')
    p.add_argument('-c', '--checksum', action='store_true',
                   help='Include checksums of all repomd.xml files in the file list.')
    p.add_argument('-C', '--checksum-file', action='append', dest='checksum_files',
                   help='Include checksums of all instances of the specified file.')
    p.add_argument('-s', '--skip', action='store_true',
                   help='Skip the file lists in the top directory')
    p.add_argument('-S', '--skip-file', action='append', dest='skip_files',
                   help='Skip the specified file in the top directory.')

    p.add_argument('-d', '--dir', help='Directory to scan (default: .).')

    p.add_argument('-t', '--timelist', type=argparse.FileType('w'), default=sys.stdout,
                   help='Filename of the file list with times (default: stdout).')
    p.add_argument('-f', '--filelist', type=argparse.FileType('w'), default=null,
                   help='Filename of the file list without times (default: no plain file list is generated).')
    p.add_argument('-i', '--imagelist', type=argparse.FileType('w'), default=null,
                   help='Filename of the image file list for fedfind (default: not generated). Requires '
                   'the productmd library.')

    opts = p.parse_args()

    if not opts.dir:
        opts.dir = '.'

    opts.checksum_files = opts.checksum_files or []
    if opts.checksum:
        opts.checksum_files += ['repomd.xml']

    opts.skip_files = opts.skip_files or []
    if opts.skip:
        if not opts.timelist.name == '<stdout>':
            opts.skip_files += [opts.timelist.name]
        if not opts.filelist.name == '<stdout>':
            opts.skip_files += [opts.filelist.name]

    return opts


def main():
    opts = parseopts()
    if opts.imagelist.name != os.devnull and not SUPPORTED_IMAGE_FORMATS:
        sys.exit("--imagelist requires the productmd library!")
    checksums = {}

    os.chdir(opts.dir)

    print('[Version]', file=opts.timelist)
    print('2', file=opts.timelist)
    print(file=opts.timelist)
    print('[Files]', file=opts.timelist)

    for entry in recursedir(skip=opts.skip_files):
        # opts.filelist.write(entry.path + '\n')
        print(entry.path, file=opts.filelist)
        # write to filtered list if appropriate
        imgs = ['.{0}'.format(form) for form in SUPPORTED_IMAGE_FORMATS]
        if any(entry.path.endswith(img) for img in imgs):
            print(entry.path, file=opts.imagelist)
        if entry.name in opts.checksum_files:
            checksums[entry.path[2:]] = True
        info = entry.stat(follow_symlinks=False)
        modtime = max(info.st_mtime, info.st_ctime)
        size = info.st_size
        ftype = get_ftype(entry)
        # opts.timelist.write('{0}\t{1}\t{2}\n'.format(modtime, ftype, entry.path[2:]))
        print('{0}\t{1}\t{2}\t{3}'.format(modtime, ftype, size, entry.path[2:]), file=opts.timelist)

    print('\n[Checksums SHA1]', file=opts.timelist)

    # It's OK if the checksum section is empty, but we should include it anyway
    # as the client expects it.
    for f in sorted(checksums):
        print('{0}\t{1}'.format(sha1(f), f), file=opts.timelist)

    print('\n[End]', file=opts.timelist)


if __name__ == '__main__':
        main()