"""Utilities for comparing files and directories.
cmp(f1, f2, shallow=True) -> int
cmpfiles(a, b, common) -> ([], [], [])
from itertools import filterfalse
__all__ = ['clear_cache', 'cmp', 'dircmp', 'cmpfiles', 'DEFAULT_IGNORES']
'RCS', 'CVS', 'tags', '.git', '.hg', '.bzr', '_darcs', '__pycache__']
"""Clear the filecmp cache."""
def cmp(f1, f2, shallow=True):
shallow -- Just check stat signature (do not read the files).
True if the files are the same, False otherwise.
This function uses a cache for past comparisons and the results,
with cache entries invalidated if their stat information
changes. The cache may be cleared by calling clear_cache().
if s1[0] != stat.S_IFREG or s2[0] != stat.S_IFREG:
outcome = _cache.get((f1, f2, s1, s2))
outcome = _do_cmp(f1, f2)
if len(_cache) > 100: # limit the maximum size of the cache
_cache[f1, f2, s1, s2] = outcome
return (stat.S_IFMT(st.st_mode),
with open(f1, 'rb') as fp1, open(f2, 'rb') as fp2:
# Directory comparison class.
"""A class that manages the comparison of 2 directories.
dircmp(a, b, ignore=None, hide=None)
IGNORE is a list of names to ignore,
defaults to DEFAULT_IGNORES.
HIDE is a list of names to hide,
defaults to [os.curdir, os.pardir].
x.report() -> prints a report on the differences between dir1 and dir2
x.report_partial_closure() -> prints report on differences between dir1
and dir2, and reports on common immediate subdirectories.
x.report_full_closure() -> like report_partial_closure,
left_list, right_list: The files in dir1 and dir2,
filtered by hide and ignore.
common: a list of names in both dir1 and dir2.
left_only, right_only: names only in dir1, dir2.
common_dirs: subdirectories in both dir1 and dir2.
common_files: files in both dir1 and dir2.
common_funny: names in both dir1 and dir2 where the type differs between
dir1 and dir2, or the name is not stat-able.
same_files: list of identical files.
diff_files: list of filenames which differ.
funny_files: list of files which could not be compared.
subdirs: a dictionary of dircmp objects, keyed by names in common_dirs.
def __init__(self, a, b, ignore=None, hide=None): # Initialize
self.hide = [os.curdir, os.pardir] # Names never to be shown
self.ignore = DEFAULT_IGNORES
def phase0(self): # Compare everything except common subdirectories
self.left_list = _filter(os.listdir(self.left),
self.right_list = _filter(os.listdir(self.right),
def phase1(self): # Compute common names
a = dict(zip(map(os.path.normcase, self.left_list), self.left_list))
b = dict(zip(map(os.path.normcase, self.right_list), self.right_list))
self.common = list(map(a.__getitem__, filter(b.__contains__, a)))
self.left_only = list(map(a.__getitem__, filterfalse(b.__contains__, a)))
self.right_only = list(map(b.__getitem__, filterfalse(a.__contains__, b)))
def phase2(self): # Distinguish files, directories, funnies
a_path = os.path.join(self.left, x)
b_path = os.path.join(self.right, x)
# print('Can\'t stat', a_path, ':', why.args[1])
# print('Can\'t stat', b_path, ':', why.args[1])
a_type = stat.S_IFMT(a_stat.st_mode)
b_type = stat.S_IFMT(b_stat.st_mode)
self.common_funny.append(x)
elif stat.S_ISDIR(a_type):
self.common_dirs.append(x)
elif stat.S_ISREG(a_type):
self.common_files.append(x)
self.common_funny.append(x)
self.common_funny.append(x)
def phase3(self): # Find out differences between common files
xx = cmpfiles(self.left, self.right, self.common_files)
self.same_files, self.diff_files, self.funny_files = xx
def phase4(self): # Find out differences between common subdirectories
# A new dircmp object is created for each common subdirectory,
# these are stored in a dictionary indexed by filename.
# The hide and ignore properties are inherited from the parent
for x in self.common_dirs:
a_x = os.path.join(self.left, x)
b_x = os.path.join(self.right, x)
self.subdirs[x] = dircmp(a_x, b_x, self.ignore, self.hide)
def phase4_closure(self): # Recursively call phase4() on subdirectories
for sd in self.subdirs.values():
def report(self): # Print a report on the differences between a and b
# Output format is purposely lousy
print('diff', self.left, self.right)
print('Only in', self.left, ':', self.left_only)
print('Only in', self.right, ':', self.right_only)
print('Identical files :', self.same_files)
print('Differing files :', self.diff_files)
print('Trouble with common files :', self.funny_files)
print('Common subdirectories :', self.common_dirs)
print('Common funny cases :', self.common_funny)
def report_partial_closure(self): # Print reports on self and on subdirs
for sd in self.subdirs.values():
def report_full_closure(self): # Report on self and subdirs recursively
for sd in self.subdirs.values():
methodmap = dict(subdirs=phase4,
same_files=phase3, diff_files=phase3, funny_files=phase3,
common_dirs = phase2, common_files=phase2, common_funny=phase2,
common=phase1, left_only=phase1, right_only=phase1,
left_list=phase0, right_list=phase0)
def __getattr__(self, attr):
if attr not in self.methodmap:
raise AttributeError(attr)
self.methodmap[attr](self)
return getattr(self, attr)
def cmpfiles(a, b, common, shallow=True):
"""Compare common files in two directories.
common -- list of file names found in both directories
shallow -- if true, do comparison based solely on stat() information
Returns a tuple of three lists:
filenames that aren't regular files.
res[_cmp(ax, bx, shallow)].append(x)
# 2 for funny cases (can't stat, etc.)
def _cmp(a, b, sh, abs=abs, cmp=cmp):
return not abs(cmp(a, b, sh))
# Return a copy with items that occur in skip removed.
def _filter(flist, skip):
return list(filterfalse(skip.__contains__, flist))
# Demonstration and testing.
options, args = getopt.getopt(sys.argv[1:], 'r')
raise getopt.GetoptError('need exactly two args', None)
dd = dircmp(args[0], args[1])
if ('-r', '') in options:
if __name__ == '__main__':
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
