0  0$lad*j"Tځz@ؔţ &'("""Utilities for comparing files and directories. Classes: dircmp Functions: cmp(f1, f2, shallow=True) -> int cmpfiles(a, b, common) -> ([], [], []) clear_cache() """ import os import stat from itertools import filterfalse from types import GenericAlias __all__ = ['clear_cache', 'cmp', 'dircmp', 'cmpfiles', 'DEFAULT_IGNORES'] _cache = {} BUFSIZE = 8*1024 DEFAULT_IGNORES = [ 'RCS', 'CVS', 'tags', '.git', '.hg', '.bzr', '_darcs', '__pycache__'] def clear_cache(): """Clear the filecmp cache.""" _cache.clear() def cmp(f1, f2, shallow=True): """Compare two files. Arguments: f1 -- First file name f2 -- Second file name shallow -- treat files as identical if their stat signatures (type, size, mtime) are identical. Otherwise, files are considered different if their sizes or contents differ. [default: True] Return value: 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(). """ 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 outcome = _cache.get((f1, f2, s1, s2)) if outcome is None: outcome = _do_cmp(f1, f2) if len(_cache) > 100: # limit the maximum size of the cache clear_cache() _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 with open(f1, 'rb') as fp1, open(f2, 'rb') as 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. dircmp(a, b, ignore=None, hide=None) A and B are directories. 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]. 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 = DEFAULT_IGNORES else: self.ignore = ignore def phase0(self): # Compare everything except common subdirectories self.left_list = _filter(os.listdir(self.left), self.hide+self