Question

I’d like to recursively walk a directory, but I want python to break from any single listdir if it encounters a directory with greater than 100 files. Basically, I’m searching for a (.TXT) file, but I want to avoid directories with large DPX image sequences (usually 10,000 files). Since DPXs live in directories by themselves with no sub directories, I’d like to break that loop ASAP.

So long story short, if python encounters a file matching “.DPX$” it stops listing the sub-directory, backs out, skips that sub-directory and continues the walk in other sub-directories.

Is this possible to break a directory listing loop before all the list results are returned?

Answer 1

The right way to avoid allocating the list of names using the os.listdir is to use the os level function as @Charles Duffy said.

Inspired from this other post: List files in a folder as a stream to begin process immediately

I added how to solve the specific OP question and used the re-entrant version of the function.

from ctypes import CDLL, c_char_p, c_int, c_long, c_ushort, c_byte, c_char, Structure, POINTER, byref, cast, sizeof, get_errno
from ctypes.util import find_library

class c_dir(Structure):
    """Opaque type for directory entries, corresponds to struct DIR"""
    pass

class c_dirent(Structure):
    """Directory entry"""
    # FIXME not sure these are the exactly correct types!
    _fields_ = (
        ('d_ino', c_long), # inode number
        ('d_off', c_long), # offset to the next dirent
        ('d_reclen', c_ushort), # length of this record
        ('d_type', c_byte), # type of file; not supported by all file system types
        ('d_name', c_char * 4096) # filename
        )
c_dirent_p = POINTER(c_dirent)
c_dirent_pp = POINTER(c_dirent_p)
c_dir_p = POINTER(c_dir)

c_lib = CDLL(find_library("c"))
opendir = c_lib.opendir
opendir.argtypes = [c_char_p]
opendir.restype = c_dir_p

readdir_r = c_lib.readdir_r
readdir_r.argtypes = [c_dir_p, c_dirent_p, c_dirent_pp]
readdir_r.restype = c_int

closedir = c_lib.closedir
closedir.argtypes = [c_dir_p]
closedir.restype = c_int

import errno

def listdirx(path):
    """
    A generator to return the names of files in the directory passed in
    """
    dir_p = opendir(path)

    if not dir_p:
        raise IOError()

    entry_p = cast(c_lib.malloc(sizeof(c_dirent)), c_dirent_p)

    try:
        while True:
            res = readdir_r(dir_p, entry_p, byref(entry_p))
            if res:
                raise IOError()
            if not entry_p:
                break
            name = entry_p.contents.d_name
            if name not in (".", ".."):
                yield name
    finally:
        if dir_p:
            closedir(dir_p)
        if entry_p:
            c_lib.free(entry_p)

if __name__ == '__main__':
    import sys
    path = sys.argv[1]
    max_per_dir = int(sys.argv[2])
    for idx, entry in enumerate(listdirx(path)):
        if idx >= max_per_dir:
            break
        print entry