cpython/Lib/filecmp.py

297 lines
9.3 KiB
Python
Raw Normal View History

"""Utilities for comparing files and directories.
Classes:
dircmp
Functions:
2009-05-17 09:19:44 -03:00
cmp(f1, f2, shallow=True) -> int
cmpfiles(a, b, common) -> ([], [], [])
"""
import os
import stat
Merged revisions 70342,70385-70387,70389-70390,70392-70393,70395,70400,70405-70406,70418,70438,70464,70468 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r70342 | georg.brandl | 2009-03-13 14:03:58 -0500 (Fri, 13 Mar 2009) | 1 line #5486: typos. ........ r70385 | benjamin.peterson | 2009-03-15 09:38:55 -0500 (Sun, 15 Mar 2009) | 1 line fix tuple.index() error message #5495 ........ r70386 | georg.brandl | 2009-03-15 16:32:06 -0500 (Sun, 15 Mar 2009) | 1 line #5496: fix docstring of lookup(). ........ r70387 | georg.brandl | 2009-03-15 16:37:16 -0500 (Sun, 15 Mar 2009) | 1 line #5493: clarify __nonzero__ docs. ........ r70389 | georg.brandl | 2009-03-15 16:43:38 -0500 (Sun, 15 Mar 2009) | 1 line Fix a small nit in the error message if bool() falls back on __len__ and it returns the wrong type: it would tell the user that __nonzero__ should return bool or int. ........ r70390 | georg.brandl | 2009-03-15 16:44:43 -0500 (Sun, 15 Mar 2009) | 1 line #5491: clarify nested() semantics. ........ r70392 | georg.brandl | 2009-03-15 16:46:00 -0500 (Sun, 15 Mar 2009) | 1 line #5488: add missing struct member. ........ r70393 | georg.brandl | 2009-03-15 16:47:42 -0500 (Sun, 15 Mar 2009) | 1 line #5478: fix copy-paste oversight in function signature. ........ r70395 | georg.brandl | 2009-03-15 16:51:48 -0500 (Sun, 15 Mar 2009) | 1 line #5276: document IDLESTARTUP and .Idle.py. ........ r70400 | georg.brandl | 2009-03-15 16:59:37 -0500 (Sun, 15 Mar 2009) | 3 lines Fix markup in re docs and give a mail address in regex howto, so that the recommendation to send suggestions to the author can be followed. ........ r70405 | georg.brandl | 2009-03-15 17:11:07 -0500 (Sun, 15 Mar 2009) | 7 lines Move the previously local import of threading to module level. This is cleaner and avoids lockups in obscure cases where a Queue is instantiated while the import lock is already held by another thread. OKed by Tim Peters. ........ r70406 | hirokazu.yamamoto | 2009-03-15 17:43:14 -0500 (Sun, 15 Mar 2009) | 1 line Added skip for old MSVC. ........ r70418 | georg.brandl | 2009-03-16 14:42:03 -0500 (Mon, 16 Mar 2009) | 1 line Add token markup. ........ r70438 | benjamin.peterson | 2009-03-17 15:29:51 -0500 (Tue, 17 Mar 2009) | 1 line I thought this was begging for an example ........ r70464 | benjamin.peterson | 2009-03-18 15:58:09 -0500 (Wed, 18 Mar 2009) | 1 line a much better example ........ r70468 | benjamin.peterson | 2009-03-18 22:04:31 -0500 (Wed, 18 Mar 2009) | 1 line close files after comparing them ........
2009-03-21 14:31:58 -03:00
import contextlib
from itertools import filterfalse
2009-05-17 09:19:44 -03:00
__all__ = ["cmp", "dircmp", "cmpfiles"]
2001-01-20 19:34:12 -04:00
_cache = {}
2009-05-17 09:19:44 -03:00
BUFSIZE = 8*1024
2009-05-17 09:19:44 -03:00
def cmp(f1, f2, shallow=True):
"""Compare two files.
Arguments:
f1 -- First file name
f2 -- Second file name
shallow -- Just check stat signature (do not read the files).
defaults to 1.
Return value:
True if the files are the same, False otherwise.
This function uses a cache for past comparisons and the results,
with a cache invalidation mechanism relying on stale signatures.
"""
s1 = _sig(os.stat(f1))
s2 = _sig(os.stat(f2))
if s1[0] != stat.S_IFREG or s2[0] != stat.S_IFREG:
return False
if shallow and s1 == s2:
return True
if s1[1] != s2[1]:
return False
result = _cache.get((f1, f2))
if result and (s1, s2) == result[:2]:
return result[2]
outcome = _do_cmp(f1, f2)
_cache[f1, f2] = s1, s2, outcome
return outcome
def _sig(st):
return (stat.S_IFMT(st.st_mode),
st.st_size,
st.st_mtime)
def _do_cmp(f1, f2):
bufsize = BUFSIZE
Merged revisions 70342,70385-70387,70389-70390,70392-70393,70395,70400,70405-70406,70418,70438,70464,70468 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r70342 | georg.brandl | 2009-03-13 14:03:58 -0500 (Fri, 13 Mar 2009) | 1 line #5486: typos. ........ r70385 | benjamin.peterson | 2009-03-15 09:38:55 -0500 (Sun, 15 Mar 2009) | 1 line fix tuple.index() error message #5495 ........ r70386 | georg.brandl | 2009-03-15 16:32:06 -0500 (Sun, 15 Mar 2009) | 1 line #5496: fix docstring of lookup(). ........ r70387 | georg.brandl | 2009-03-15 16:37:16 -0500 (Sun, 15 Mar 2009) | 1 line #5493: clarify __nonzero__ docs. ........ r70389 | georg.brandl | 2009-03-15 16:43:38 -0500 (Sun, 15 Mar 2009) | 1 line Fix a small nit in the error message if bool() falls back on __len__ and it returns the wrong type: it would tell the user that __nonzero__ should return bool or int. ........ r70390 | georg.brandl | 2009-03-15 16:44:43 -0500 (Sun, 15 Mar 2009) | 1 line #5491: clarify nested() semantics. ........ r70392 | georg.brandl | 2009-03-15 16:46:00 -0500 (Sun, 15 Mar 2009) | 1 line #5488: add missing struct member. ........ r70393 | georg.brandl | 2009-03-15 16:47:42 -0500 (Sun, 15 Mar 2009) | 1 line #5478: fix copy-paste oversight in function signature. ........ r70395 | georg.brandl | 2009-03-15 16:51:48 -0500 (Sun, 15 Mar 2009) | 1 line #5276: document IDLESTARTUP and .Idle.py. ........ r70400 | georg.brandl | 2009-03-15 16:59:37 -0500 (Sun, 15 Mar 2009) | 3 lines Fix markup in re docs and give a mail address in regex howto, so that the recommendation to send suggestions to the author can be followed. ........ r70405 | georg.brandl | 2009-03-15 17:11:07 -0500 (Sun, 15 Mar 2009) | 7 lines Move the previously local import of threading to module level. This is cleaner and avoids lockups in obscure cases where a Queue is instantiated while the import lock is already held by another thread. OKed by Tim Peters. ........ r70406 | hirokazu.yamamoto | 2009-03-15 17:43:14 -0500 (Sun, 15 Mar 2009) | 1 line Added skip for old MSVC. ........ r70418 | georg.brandl | 2009-03-16 14:42:03 -0500 (Mon, 16 Mar 2009) | 1 line Add token markup. ........ r70438 | benjamin.peterson | 2009-03-17 15:29:51 -0500 (Tue, 17 Mar 2009) | 1 line I thought this was begging for an example ........ r70464 | benjamin.peterson | 2009-03-18 15:58:09 -0500 (Wed, 18 Mar 2009) | 1 line a much better example ........ r70468 | benjamin.peterson | 2009-03-18 22:04:31 -0500 (Wed, 18 Mar 2009) | 1 line close files after comparing them ........
2009-03-21 14:31:58 -03:00
with contextlib.nested(open(f1, 'rb'), open(f2, 'rb')) as (fp1, fp2):
while True:
b1 = fp1.read(bufsize)
b2 = fp2.read(bufsize)
if b1 != b2:
return False
if not b1:
return True
# Directory comparison class.
#
class dircmp:
"""A class that manages the comparison of 2 directories.
2009-05-17 09:19:44 -03:00
dircmp(a, b, ignore=None, hide=None)
A and B are directories.
IGNORE is a list of names to ignore,
defaults to ['RCS', 'CVS', 'tags'].
HIDE is a list of names to hide,
defaults to [os.curdir, os.pardir].
High level usage:
x = dircmp(dir1, dir2)
x.report() -> prints a report on the differences between dir1 and dir2
or
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,
but fully recursive.
Attributes:
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.left = a
self.right = b
if hide is None:
self.hide = [os.curdir, os.pardir] # Names never to be shown
else:
self.hide = hide
if ignore is None:
self.ignore = ['RCS', 'CVS', 'tags'] # Names ignored in comparison
else:
self.ignore = ignore
def phase0(self): # Compare everything except common subdirectories
self.left_list = _filter(os.listdir(self.left),
self.hide+self.ignore)
self.right_list = _filter(os.listdir(self.right),
self.hide+self.ignore)
self.left_list.sort()
self.right_list.sort()
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
self.common_dirs = []
self.common_files = []
self.common_funny = []
for x in self.common:
a_path = os.path.join(self.left, x)
b_path = os.path.join(self.right, x)
ok = 1
try:
a_stat = os.stat(a_path)
except os.error as why:
2008-01-06 17:13:42 -04:00
# print('Can\'t stat', a_path, ':', why.args[1])
ok = 0
try:
b_stat = os.stat(b_path)
except os.error as why:
2008-01-06 17:13:42 -04:00
# print('Can\'t stat', b_path, ':', why.args[1])
ok = 0
if ok:
a_type = stat.S_IFMT(a_stat.st_mode)
b_type = stat.S_IFMT(b_stat.st_mode)
if a_type != b_type:
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)
else:
self.common_funny.append(x)
else:
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
self.subdirs = {}
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
self.phase4()
for sd in self.subdirs.values():
sd.phase4_closure()
def report(self): # Print a report on the differences between a and b
# Output format is purposely lousy
print('diff', self.left, self.right)
if self.left_only:
self.left_only.sort()
print('Only in', self.left, ':', self.left_only)
if self.right_only:
self.right_only.sort()
print('Only in', self.right, ':', self.right_only)
if self.same_files:
self.same_files.sort()
print('Identical files :', self.same_files)
if self.diff_files:
self.diff_files.sort()
print('Differing files :', self.diff_files)
if self.funny_files:
self.funny_files.sort()
print('Trouble with common files :', self.funny_files)
if self.common_dirs:
self.common_dirs.sort()
print('Common subdirectories :', self.common_dirs)
if self.common_funny:
self.common_funny.sort()
print('Common funny cases :', self.common_funny)
def report_partial_closure(self): # Print reports on self and on subdirs
self.report()
for sd in self.subdirs.values():
print()
sd.report()
def report_full_closure(self): # Report on self and subdirs recursively
self.report()
for sd in self.subdirs.values():
print()
sd.report_full_closure()
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:
2007-08-29 22:19:48 -03:00
raise AttributeError(attr)
self.methodmap[attr](self)
return getattr(self, attr)
2009-05-17 09:19:44 -03:00
def cmpfiles(a, b, common, shallow=True):
"""Compare common files in two directories.
a, b -- directory names
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:
files that compare equal
files that are different
filenames that aren't regular files.
"""
res = ([], [], [])
for x in common:
ax = os.path.join(a, x)
bx = os.path.join(b, x)
res[_cmp(ax, bx, shallow)].append(x)
return res
# Compare two files.
# Return:
2001-01-14 19:36:06 -04:00
# 0 for equal
# 1 for different
# 2 for funny cases (can't stat, etc.)
#
def _cmp(a, b, sh, abs=abs, cmp=cmp):
try:
return not abs(cmp(a, b, sh))
except os.error:
return 2
# Return a copy with items that occur in skip removed.
#
def _filter(flist, skip):
return list(filterfalse(skip.__contains__, flist))
# Demonstration and testing.
#
def demo():
import sys
import getopt
options, args = getopt.getopt(sys.argv[1:], 'r')
if len(args) != 2:
raise getopt.GetoptError('need exactly two args', None)
dd = dircmp(args[0], args[1])
if ('-r', '') in options:
dd.report_full_closure()
else:
dd.report()
if __name__ == '__main__':
demo()