zzzutils.py

import sys
import os
import shutil
import hashlib


def query_yes_no(question):
    valid = {"yes": True, "y": True, "no": False, "n": False}

    while True:
        sys.stdout.write(question + " [y/n] ")
        choice = input().lower()
        if choice in valid:
            return valid[choice]
        else:
            sys.stdout.write("Please respond with 'yes' or 'no' " + "(or 'y' or 'n').\n")


def copyFile(src, dst, buffer_size=10485760, perserveFileDate=True):
    '''
    Copies a file to a new location. Much faster performance than Apache Commons due to use of larger buffer
    @param src:    Source File
    @param dst:    Destination File (not file path)
    @param buffer_size:    Buffer size to use during copy
    @param perserveFileDate:    Preserve the original file date
    '''
    #    Check to make sure destination directory exists. If it doesn't create the directory
    # dstParent, dstFileName = os.path.split(dst)
    # if(not(os.path.exists(dstParent))):
    #    os.makedirs(dstParent)

    #    Optimize the buffer for small files
    buffer_size = min(buffer_size, os.path.getsize(src))
    if (buffer_size == 0):
        buffer_size = 1024

    if shutil._samefile(src, dst):
        raise shutil.Error("`%s` and `%s` are the same file" % (src, dst))
    for fn in [src, dst]:
        try:
            st = os.stat(fn)
        except OSError:
            # File most likely does not exist
            pass
        else:
            # XXX What about other special files? (sockets, devices...)
            if shutil.stat.S_ISFIFO(st.st_mode):
                raise shutil.SpecialFileError("`%s` is a named pipe" % fn)
    with open(src, 'rb') as fsrc:
        with open(dst, 'wb') as fdst:
            shutil.copyfileobj(fsrc, fdst, buffer_size)

    if (perserveFileDate):
        shutil.copystat(src, dst)


def hashfile(afile, hasher, blocksize=65536):
    buf = afile.read(blocksize)
    while len(buf) > 0:
        hasher.update(buf)
        buf = afile.read(blocksize)
    return hasher.hexdigest()


def calc_hash_md5(file_name):
    return hashfile(open(file_name, 'rb'), hashlib.md5())