Index: Lib/filecmp.py =================================================================== --- Lib/filecmp.py (revision 0) +++ Lib/filecmp.py (revision 0) @@ -0,0 +1,304 @@ +"""Utilities for comparing files and directories. + +Classes: + dircmp + +Functions: + cmp(f1, f2, shallow=1) -> int + cmpfiles(a, b, common) -> ([], [], []) + +""" + +import os +import stat +import warnings +from itertools import ifilter, ifilterfalse, imap, izip + +__all__ = ["cmp","dircmp","cmpfiles"] + +_cache = {} +BUFSIZE=8*1024 + +def cmp(f1, f2, shallow=1): + """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. + + """ + from java.io import File + + s1 = _sig(os.stat(f1)) + s2 = _sig(os.stat(f2)) + file1 = File(f1) + file2 = File(f2) + + if (not file1.isFile()) or (not file2.isFile()): + 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 + fp1 = open(f1, 'rb') + fp2 = open(f2, 'rb') + 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. + + 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(izip(imap(os.path.normcase, self.left_list), self.left_list)) + b = dict(izip(imap(os.path.normcase, self.right_list), self.right_list)) + self.common = map(a.__getitem__, ifilter(b.has_key, a)) + self.left_only = map(a.__getitem__, ifilterfalse(b.has_key, a)) + self.right_only = map(b.__getitem__, ifilterfalse(a.has_key, 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, why: + # print 'Can\'t stat', a_path, ':', why[1] + ok = 0 + try: + b_stat = os.stat(b_path) + except os.error, why: + # print 'Can\'t stat', b_path, ':', why[1] + ok = 0 + + if ok: + from java.io import File + p1 = File(a_path) + p2 = File(b_path) + if (p1.isFile() and p2.isDirectory()) or (p2.isFile() and p1.isDirectory()): + self.common_funny.append(x) + elif p1.isDirectory(): + self.common_dirs.append(x) + elif p1.isFile(): + 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.itervalues(): + 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.itervalues(): + print + sd.report() + + def report_full_closure(self): # Report on self and subdirs recursively + self.report() + for sd in self.subdirs.itervalues(): + 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: + raise AttributeError, attr + self.methodmap[attr](self) + return getattr(self, attr) + +def cmpfiles(a, b, common, shallow=1): + """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: +# 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(ifilterfalse(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() Index: Lib/test/test_filecmp.py =================================================================== --- Lib/test/test_filecmp.py (revision 0) +++ Lib/test/test_filecmp.py (revision 0) @@ -0,0 +1,134 @@ + +import os, filecmp, shutil, tempfile, shutil +import unittest +from test import test_support + +class FileCompareTestCase(unittest.TestCase): + def setUp(self): + self.name = test_support.TESTFN + self.name_same = test_support.TESTFN + '-same' + self.name_diff = test_support.TESTFN + '-diff' + data = 'Contents of file go here.\n' + for name in [self.name, self.name_same, self.name_diff]: + output = open(name, 'w') + output.write(data) + output.close() + + output = open(self.name_diff, 'a+') + output.write('An extra line.\n') + output.close() + self.dir = tempfile.gettempdir() + + def tearDown(self): + os.unlink(self.name) + os.unlink(self.name_same) + os.unlink(self.name_diff) + + def test_matching(self): + self.failUnless(filecmp.cmp(self.name, self.name_same), + "Comparing file to itself fails") + self.failUnless(filecmp.cmp(self.name, self.name_same, shallow=False), + "Comparing file to itself fails") + self.failUnless(filecmp.cmp(self.name, self.name, shallow=False), + "Comparing file to identical file fails") + self.failUnless(filecmp.cmp(self.name, self.name), + "Comparing file to identical file fails") + + def test_different(self): + self.failIf(filecmp.cmp(self.name, self.name_diff), + "Mismatched files compare as equal") + self.failIf(filecmp.cmp(self.name, self.dir), + "File and directory compare as equal") + +class DirCompareTestCase(unittest.TestCase): + def setUp(self): + tmpdir = tempfile.gettempdir() + self.dir = os.path.join(tmpdir, 'dir') + self.dir_same = os.path.join(tmpdir, 'dir-same') + self.dir_diff = os.path.join(tmpdir, 'dir-diff') + self.caseinsensitive = os.path.normcase('A') == os.path.normcase('a') + data = 'Contents of file go here.\n' + for dir in [self.dir, self.dir_same, self.dir_diff]: + shutil.rmtree(dir, True) + os.mkdir(dir) + if self.caseinsensitive and dir is self.dir_same: + fn = 'FiLe' # Verify case-insensitive comparison + else: + fn = 'file' + output = open(os.path.join(dir, fn), 'w') + output.write(data) + output.close() + + output = open(os.path.join(self.dir_diff, 'file2'), 'w') + output.write('An extra file.\n') + output.close() + + def tearDown(self): + shutil.rmtree(self.dir) + shutil.rmtree(self.dir_same) + shutil.rmtree(self.dir_diff) + + def test_cmpfiles(self): + self.failUnless(filecmp.cmpfiles(self.dir, self.dir, ['file']) == + (['file'], [], []), + "Comparing directory to itself fails") + self.failUnless(filecmp.cmpfiles(self.dir, self.dir_same, ['file']) == + (['file'], [], []), + "Comparing directory to same fails") + + # Try it with shallow=False + self.failUnless(filecmp.cmpfiles(self.dir, self.dir, ['file'], + shallow=False) == + (['file'], [], []), + "Comparing directory to itself fails") + self.failUnless(filecmp.cmpfiles(self.dir, self.dir_same, ['file'], + shallow=False), + "Comparing directory to same fails") + + # Add different file2 + output = open(os.path.join(self.dir, 'file2'), 'w') + output.write('Different contents.\n') + output.close() + + self.failIf(filecmp.cmpfiles(self.dir, self.dir_same, + ['file', 'file2']) == + (['file'], ['file2'], []), + "Comparing mismatched directories fails") + + + def test_dircmp(self): + # Check attributes for comparison of two identical directories + d = filecmp.dircmp(self.dir, self.dir_same) + if self.caseinsensitive: + self.assertEqual([d.left_list, d.right_list],[['file'], ['FiLe']]) + else: + self.assertEqual([d.left_list, d.right_list],[['file'], ['file']]) + self.failUnless(d.common == ['file']) + self.failUnless(d.left_only == d.right_only == []) + self.failUnless(d.same_files == ['file']) + self.failUnless(d.diff_files == []) + + # Check attributes for comparison of two different directories + d = filecmp.dircmp(self.dir, self.dir_diff) + self.failUnless(d.left_list == ['file']) + self.failUnless(d.right_list == ['file', 'file2']) + self.failUnless(d.common == ['file']) + self.failUnless(d.left_only == []) + self.failUnless(d.right_only == ['file2']) + self.failUnless(d.same_files == ['file']) + self.failUnless(d.diff_files == []) + + # Add different file2 + output = open(os.path.join(self.dir, 'file2'), 'w') + output.write('Different contents.\n') + output.close() + d = filecmp.dircmp(self.dir, self.dir_diff) + self.failUnless(d.same_files == ['file']) + self.failUnless(d.diff_files == ['file2']) + + +def test_main(): + test_support.run_unittest(FileCompareTestCase, DirCompareTestCase) + +if __name__ == "__main__": + test_main()