def image_hash_tree(dirs, exts=None, processfunc=None):
tree = BKTree(hamming_distance)
map = defaultdict(list)
exts = exts or fileextensions.images
for dir in dirs:
for entry in scandir_rec(dir, dirs=True, follow_symlinks=False, allow_skip=True):
if entry.is_dir() and entry.name in IGNORE_DIRNAMES:
logging.debug("Skipped: %s", entry.path)
entry.follow = False
elif entry.is_file():
ext = entrysuffix(entry)[1:].lower()
if ext in exts:
try:
img = Image.open(entry.path, "r")
except OSError:
logging.warning("Cannot open image: %s", entry.path)
else:
hash = phash_blockmean(img)
tree.add(hash)
map[hash].append(entry.path)
if processfunc:
processfunc((entry.path, hash))
return tree, map
def iter_size_path(dirs):
for dir in dirs:
for entry in scandir_rec(dir, dirs=True, follow_symlinks=False, allow_skip=True):
if entry.is_dir() and entry.name in IGNORE_DIRNAMES:
logging.debug("Skipped: %s", entry.path)
entry.follow = False
elif entry.is_file():
filesize = entry.stat().st_size
yield filesize, entry.path
def convert_filenames_to_ascii(path, follow_symlinks=False, rec=False):
# type: (PathType, bool, bool) -> None
""" convert all files in `path` to a ascii representation using unidecode """
for entry in scandir_rec(path,
files=True,
dirs=False,
rec=rec,
follow_symlinks=follow_symlinks):
filepath = entry.path
base, name = os.path.split(filepath)
os.rename(filepath, os.path.join(base, unidecode(name)))
def from_fs(cls, dirpath, hashcls=hashlib.sha1):
# type: (PathType, HashCls) -> DirHasher
""" Creates a DirHasher instance for a filesystem folder.
"""
paths = [
entry.path
for entry in sorted(scandir_rec(dirpath, files=True, dirs=False),
key=lambda x: x.path)
]
hashes = (hash_file(path, hashcls).digest() for path in paths)
return cls(paths, CachedIterable(hashes), fspath(dirpath))
def do(paths, yes):
# type: (Iterable[str], bool) -> None
for path in paths:
for entry in scandir_rec(path, dirs=False, files=True):
stats = entry.stat()
try:
if not is_writeable(stats):
if yes or confirm("Make {} writeable?".format(entry.path)):
make_writeable(entry.path, stats)
if yes:
print("Made {} writeable".format(entry.path))
except Exception as e:
logging.exception(entry.path)
nargs=2,
type=float,
help="Change the rate from x fps to y fps")
group.add_argument("--delay", type=float, help="Delay by +x or -x seconds")
args = parser.parse_args()
if args.inpath.is_file() == args.outpath.is_file():
errorquit("inpath and outpath must be both files or both directories")
if args.inpath == args.outpath:
errorquit("inpath is not allowed to equal outpath")
if args.fps:
func = lambda x: x * args.fps[0] / args.fps[1]
elif args.delay:
func = lambda x: x + args.delay
if args.inpath.is_dir():
for infile in scandir_rec(args.inpath, dirs=False, relative=True):
outfile = args.outpath / infile.relpath
print("In file: " + infile)
print("Out file: " + outfile)
try:
sync_srt(infile.path, outfile, func)
except MalformedFileException as e:
print("error: file is malformed")
else:
print("In file: " + args.inpath)
print("Out file: " + args.outpath)
sync_srt(args.inpath, args.outpath, func)
from __future__ import generator_stop
from argparse import ArgumentParser
from genutility.file import is_all_byte
from genutility.filesystem import scandir_rec
parser = ArgumentParser()
parser.add_argument("path")
args = parser.parse_args()
for entry in scandir_rec(args.path, dirs=False, files=True):
if entry.stat().st_size != 0:
with open(entry.path, "rb") as fr:
if is_all_byte(fr, b"\x00"):
print(entry.path)