def slice_file(path, size, offset=0, whence=0, output_dir=None, slice_name=None, slice_ext=None):
"""Write a new file from a slice of an existing file
Args:
path (str): Path of existing file.
size (int): Read length in bytes.
offset (int): (optional) Offset from the whence position. Defaults to 0.
whence (int): (optional) Originating file seek position. 0 - Absolute, 1 - Current, 2 - End of file. Defaults to 0.
output_dir (str): (optional) Path to the directory where new file is saved.
slice_name (str): (optional) File name of the slice file. Defaults to the full file's name (with extension).
slice_ext (str): (optional) File extension of the slice file. Defaults to 'slice_oYYwXX' where YY and XX are the offset and whence respectively.
Returns:
str: File path of slice file.
"""
if not is_str_not_empty(path): raise ValueError("file path must be a string")
if not is_int_pos(size): raise ValueError("size must be a positive integer")
if not is_int_not_neg(offset): raise ValueError("offset must be a non negative integer")
if whence not in [0,1,2]: raise ValueError("whence must be 0 - Absolute, 1 - Current, 2 - End of file")
output_dir = os.path.abspath('.') if output_dir is None else os.path.abspath(output_dir)
ext = slice_ext if is_str_not_empty(slice_ext) else 'slice_o' + str(offset) + 'w' + str(whence)
name = slice_name if is_str_not_empty(slice_name) else os.path.split(path)[1]
slice_path = os.path.abspath(os.path.join(output_dir, name + '.' + ext))
write_file(slice_path, read_file(path, size, offset, whence))
return slice_path
def read_file(path, size=None, offset=0, whence=0):
"""Read a file in binary mode
Args:
path (str): Path of file.
size (int): Read length in bytes. Defaults to None.
offset (int): (optional) Offset from the whence position. Defaults to 0.
whence (int): (optional) Originating file seek position. 0 - Absolute, 1 - Current, 2 - End of file. Defaults to 0.
Returns:
str: Binary data.
"""
if not is_str_not_empty(path): raise ValueError("file path must be a string")
if not is_int_not_neg(offset): raise ValueError("offset must be a positive integer")
if whence not in [0,1,2]: raise ValueError("whence must be 0 - Absolute, 1 - Current, 2 - End of file")
f = open(path, 'rb')
f.seek(offset, whence)
if size is None:
data = f.read()
else:
data = f.read(size)
f.close()
return data
def list_dir(dir=".", recurse=True, depth=0, get_file=True, get_dir=True):
"""Search a directory for files and directories
Args:
dir (str): (optional) Directory to search. Suggestion: use absolute path. Defaults to current working directory.
recurse (bool): (optional) Recursive search flag. Defaults to True.
depth (int): (optional) Set the recursion depth. Defaults to 0, which has a max of Python's recursion limit.
get_dir (bool): (optional) Return entry for directory. Defaults to True.
get_file (bool): (optional) Return entry for file. Defaults to True.
Returns:
list: List of strings of paths for files and directories.
"""
if not is_str_not_empty(dir):
raise ValueError("dir must be a non empty string")
if not os.path.isdir(dir):
raise ValueError("dir must be a valid directory")
if not is_bool(recurse):
raise TypeError("recurse must be True or False")
if is_int_neg(depth):
raise ValueError("depth must be >= 0")
if not is_bool(get_file):
raise TypeError("get_file must be True or False")
if not is_bool(get_dir):
raise TypeError("get_dir must be True or False")
list = []
i = 0
if recurse == True:
os_walk = os.walk(dir, topdown=True)
for root, dirs, files in os_walk:
if get_file == True:
for name in files:
list.append(os.path.join(os.path.abspath(root), name))
if get_dir == True:
for name in dirs:
list.append(os.path.join(os.path.abspath(root), name))
i += 1
if depth == i:
break
else:
listdir = os.listdir(dir)
for name in listdir:
path = os.path.join(os.path.abspath(dir), name)
if get_dir == True and get_file == True:
list.append(path)
elif get_file == True and os.path.isfile(path) == True:
list.append(path)
elif get_dir == True and os.path.isdir(path) == True:
list.append(path)
return list
def hash_file(hash_name, path, size=None, offset=0, whence=0):
"""Return the hash of a file
Args:
hash_name (str): Hash algorithm name. See :py:mod:`hashlib`
path (str): Path of file.
size (int): (optional) Read length in bytes. Defaults to None.
offset (int): (optional) Offset from the whence position. Defaults to 0.
whence (int): (optional) Originating file seek position. 0 - Absolute, 1 - Current, 2 - End of file. Defaults to 0.
Returns:
str: Hash (hex) string.
"""
if not is_str_not_empty(hash_name): raise ValueError("hash_name must be a string")
if not is_str_not_empty(path): raise ValueError("file path must be a string")
if not is_int_not_neg(offset): raise ValueError("offset must be a positive integer")
if whence not in [0,1,2]: raise ValueError("whence must be 0 - Absolute, 1 - Current, 2 - End of file")
data = read_file(path, size, offset, whence)
alg = getattr(hash, hash_name.lower())
return alg(data)
def find_file(re_filter=None, branch=".", recurse=True, depth=0, get_file=True, get_dir=True, case_i=True):
"""Search a branch directory for files and / or directories whose name matches one or more of the filter patterns
Args:
branch (str): (optional) Directory to search. Suggestion: use absolute path. Defaults to current working directory.
re_filter (list): (optional) List of strings of wildcard patterns. Defaults to None, which skips any filtering.
recurse (bool): (optional) Recursive search flag. Defaults to True.
depth (int): (optional) Set the recursion depth. Defaults to 0, which has a max of Python's recursion limit.
get_file (bool): (optional) Return entry for file. Defaults to True.
get_dir (bool): (optional) Return entry for directory. Defaults to True.
case_i (bool): (optional) Case insensitive search. Defaults to True.
Returns:
list: List of strings with paths of files.
"""
if not is_str_not_empty(branch):
raise ValueError("branch must be a non empty string")
if not os.path.isdir(branch):
raise ValueError("branch must be a valid directory")
if not is_bool(recurse):
raise ValueError("recurse must be True or False")
if is_int_neg(depth):
raise ValueError("depth must be >= 0")
if not is_bool(get_file):
raise ValueError("get_file must be True or False")
if not is_bool(get_dir):
raise ValueError("get_dir must be True or False")
if not is_bool(case_i):
raise ValueError("case_i must be True or False")
search_results = list_dir(branch, recurse, depth, get_file, get_dir)
if re_filter is None or len(re_filter) < 1:
return search_results
elif re_filter == "*":
return search_results
elif is_list(re_filter) and "*" in re_filter:
return search_results
if is_str(re_filter):
re_filter = [re_filter]
re_flag = 0
if case_i:
re_flag = re.IGNORECASE
bre = partial(wildcard_re, wildcard="*", escape="\\")
return list_filter(map(bre, re_filter), search_results, re_flag)
def find_file_re(re_filter=None, branch=".", recurse=True, depth=0, get_file=True, get_dir=True, re_flag=0):
"""Search a branch directory for files and / or directories whose name matches one or more of the regex filter patterns
Args:
branch (str): (optional) Directory to search. Suggestion: use absolute path. Defaults to current working directory.
re_filter (list): (optional) List of strings of regular expression patterns. Defaults to None, which skips any filtering.
recurse (bool): (optional) Recursive search flag. Defaults to True.
depth (int): (optional) Set the recursion depth. Defaults to 0, which has a max of Python's recursion limit.
get_file (bool): (optional) Return entry for file. Defaults to True.
get_dir (bool): (optional) Return entry for directory. Defaults to True.
re_flag (int): (optional) See :py:mod:`re`
Returns:
list: List of strings with paths of files.
"""
if not is_str_not_empty(branch):
raise ValueError("branch must be a non empty string")
if not os.path.isdir(branch):
raise ValueError("branch must be a valid directory")
if not is_bool(recurse):
raise TypeError("recurse must be True or False")
if is_int_neg(depth):
raise ValueError("depth must be >= 0")
if not is_bool(get_file):
raise ValueError("get_file must be True or False")
if not is_bool(get_dir):
raise ValueError("get_dir must be True or False")
search_results = list_dir(branch, recurse, depth, get_file, get_dir)
if re_filter is None or len(re_filter) < 1:
return search_results
if is_str(re_filter):
re_filter = [re_filter]
return list_filter(re_filter, search_results, re_flag)
def write_file(path, data, mode='new', offset=0, whence=0):
"""Write a file in binary mode
Args:
path (str): Path of file.
data (str): Data to be written.
mode (str): (optional) 'new' for a new or replacement file. 'insert' for writing more data into a file. 'overwrite' for writing new data over a file. 'append' for adding to the end of a file. Defaults to 'new'.
offset (int): (optional) Offset from the whence position. Defaults to 0.
whence (int): (optional) Originating file seek position. 0 - Absolute, 1 - Current, 2 - End of file. Defaults to 0.
Returns:
str: File path to written file.
"""
if not is_str_not_empty(path): raise ValueError("file path must be a string")
if not is_str_not_empty(data): raise ValueError("data must be a string")
if mode not in ['new','insert','overwrite','append']: raise ValueError("mode must be 'new' or 'insert' or 'overwrite' or 'append'")
if not is_int_not_neg(offset): raise ValueError("offset must be a non negative integer")
if whence not in [0,1,2]: raise ValueError("whence must be 0 - Absolute, 1 - Current, 2 - End of file")
path = os.path.abspath(path)
#: create the directory path to the file if it doesn't exist
if not os.path.exists(os.path.split(path)[0]):
mode = 'new'
os.makedirs(os.path.split(path)[0])
#: stop an attempt to overwrite a directory
elif os.path.isdir(path) == True:
raise ValueError('may not write file over a directory: ' + path)
if mode == 'append':
offset = 0
whence = 2
if mode == 'insert' or mode == 'overwrite' or mode == 'append':
original_file_size = os.stat(path).st_size
original_file = open(path, 'rb')
#: determine the offset position for the write action
original_file.seek(offset, whence)
start_pos = original_file.tell()
original_file.seek(0, 0)
#: create a temporary file
temp_file = open(path + '.tmp', 'wb')
#: write any offset data
if start_pos > 0:
temp_file.write(original_file.read(start_pos))
#: write new data
temp_file.write(data)
temp_file.flush()
os.fsync(temp_file.fileno())
temp_file.close()
temp_file_size = os.stat(path + '.tmp').st_size
#: write any remaining data from the original file
if mode == 'overwrite' and temp_file_size < original_file_size:
temp_file = open(path + '.tmp', 'ab')
original_file.seek(temp_file_size, 0)
temp_file.write(original_file.read())
temp_file.flush()
os.fsync(temp_file.fileno())
temp_file.close()
elif mode == 'insert':
temp_file = open(path + '.tmp', 'ab')
original_file.seek(start_pos, 0)
temp_file.write(original_file.read())
temp_file.flush()
os.fsync(temp_file.fileno())
temp_file.close()
original_file.close()
#: replace the original file
os.rename(path + '.tmp', path)
elif mode == 'new':
f = open(path, 'wb')
f.write(data)
f.flush()
os.fsync(f.fileno())
f.close()
return path
