cpython/Lib/dircmp.py

204 lines
5.0 KiB
Python
Raw Normal View History

1990-10-13 16:23:40 -03:00
# Module 'dirmp'
#
# Defines a class to build directory diff tools on.
1992-03-31 14:55:40 -04:00
import os
1990-10-13 16:23:40 -03:00
import dircache
import cmpcache
import statcache
from stat import *
1990-10-13 16:23:40 -03:00
# Directory comparison class.
#
1991-12-26 09:03:23 -04:00
class dircmp:
1990-10-13 16:23:40 -03:00
#
def new(self, a, b): # Initialize
self.a = a
self.b = b
# Properties that caller may change before calling self.run():
self.hide = [os.curdir, os.pardir] # Names never to be shown
self.ignore = ['RCS', 'tags'] # Names ignored in comparison
1990-10-13 16:23:40 -03:00
#
return self
1990-10-13 16:23:40 -03:00
#
def run(self): # Compare everything except common subdirectories
self.a_list = filter(dircache.listdir(self.a), self.hide)
self.b_list = filter(dircache.listdir(self.b), self.hide)
self.a_list.sort()
self.b_list.sort()
self.phase1()
self.phase2()
self.phase3()
1990-10-13 16:23:40 -03:00
#
def phase1(self): # Compute common names
self.a_only = []
self.common = []
for x in self.a_list:
if x in self.b_list:
self.common.append(x)
1990-10-13 16:23:40 -03:00
else:
self.a_only.append(x)
1990-10-13 16:23:40 -03:00
#
self.b_only = []
for x in self.b_list:
if x not in self.common:
self.b_only.append(x)
1990-10-13 16:23:40 -03:00
#
def phase2(self): # Distinguish files, directories, funnies
self.common_dirs = []
self.common_files = []
self.common_funny = []
1990-10-13 16:23:40 -03:00
#
for x in self.common:
a_path = os.path.join(self.a, x)
b_path = os.path.join(self.b, x)
1990-10-13 16:23:40 -03:00
#
ok = 1
try:
a_stat = statcache.stat(a_path)
1992-03-31 14:55:40 -04:00
except os.error, why:
1990-10-13 16:23:40 -03:00
# print 'Can\'t stat', a_path, ':', why[1]
ok = 0
try:
b_stat = statcache.stat(b_path)
1992-03-31 14:55:40 -04:00
except os.error, why:
1990-10-13 16:23:40 -03:00
# print 'Can\'t stat', b_path, ':', why[1]
ok = 0
#
if ok:
a_type = S_IFMT(a_stat[ST_MODE])
b_type = S_IFMT(b_stat[ST_MODE])
1990-10-13 16:23:40 -03:00
if a_type <> b_type:
self.common_funny.append(x)
elif S_ISDIR(a_type):
self.common_dirs.append(x)
elif S_ISREG(a_type):
self.common_files.append(x)
1990-10-13 16:23:40 -03:00
else:
self.common_funny.append(x)
1990-10-13 16:23:40 -03:00
else:
self.common_funny.append(x)
1990-10-13 16:23:40 -03:00
#
def phase3(self): # Find out differences between common files
xx = cmpfiles(self.a, self.b, self.common_files)
self.same_files, self.diff_files, self.funny_files = xx
1990-10-13 16:23:40 -03:00
#
def phase4(self): # Find out differences between common subdirectories
1990-10-13 16:23:40 -03:00
# 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.a, x)
b_x = os.path.join(self.b, x)
self.subdirs[x] = newdd = dircmp().new(a_x, b_x)
newdd.hide = self.hide
newdd.ignore = self.ignore
1990-10-13 16:23:40 -03:00
newdd.run()
#
def phase4_closure(self): # Recursively call phase4() on subdirectories
self.phase4()
for x in self.subdirs.keys():
self.subdirs[x].phase4_closure()
1990-10-13 16:23:40 -03:00
#
def report(self): # Print a report on the differences between a and b
1990-10-13 16:23:40 -03:00
# Assume that phases 1 to 3 have been executed
# Output format is purposely lousy
print 'diff', self.a, self.b
if self.a_only:
print 'Only in', self.a, ':', self.a_only
if self.b_only:
print 'Only in', self.b, ':', self.b_only
if self.same_files:
print 'Identical files :', self.same_files
if self.diff_files:
print 'Differing files :', self.diff_files
if self.funny_files:
print 'Trouble with common files :', self.funny_files
if self.common_dirs:
print 'Common subdirectories :', self.common_dirs
if self.common_funny:
print 'Common funny cases :', self.common_funny
1990-10-13 16:23:40 -03:00
#
def report_closure(self): # Print reports on self and on subdirs
1990-10-13 16:23:40 -03:00
# If phase 4 hasn't been done, no subdir reports are printed
self.report()
1990-10-13 16:23:40 -03:00
try:
x = self.subdirs
1991-12-26 09:03:23 -04:00
except AttributeError:
1990-10-13 16:23:40 -03:00
return # No subdirectories computed
for x in self.subdirs.keys():
1990-10-13 16:23:40 -03:00
print
self.subdirs[x].report_closure()
1990-10-13 16:23:40 -03:00
#
def report_phase4_closure(self): # Report and do phase 4 recursively
self.report()
self.phase4()
for x in self.subdirs.keys():
1990-10-13 16:23:40 -03:00
print
self.subdirs[x].report_phase4_closure()
1990-10-13 16:23:40 -03:00
# Compare common files in two directories.
# Return:
# - files that compare equal
# - files that compare different
# - funny cases (can't stat etc.)
#
def cmpfiles(a, b, common):
res = ([], [], [])
for x in common:
1992-03-31 14:55:40 -04:00
res[cmp(os.path.join(a, x), os.path.join(b, x))].append(x)
1990-10-13 16:23:40 -03:00
return res
# Compare two files.
# Return:
# 0 for equal
# 1 for different
# 2 for funny cases (can't stat, etc.)
#
def cmp(a, b):
try:
if cmpcache.cmp(a, b): return 0
return 1
1992-03-31 14:55:40 -04:00
except os.error:
1990-10-13 16:23:40 -03:00
return 2
# Remove a list item.
# NB: This modifies the list argument.
#
def remove(list, item):
for i in range(len(list)):
1992-01-01 15:35:13 -04:00
if list[i] == item:
1990-10-13 16:23:40 -03:00
del list[i]
break
# Return a copy with items that occur in skip removed.
#
def filter(list, skip):
result = []
for item in list:
if item not in skip: result.append(item)
return result
# Demonstration and testing.
#
def demo():
import sys
import getopt
options, args = getopt.getopt(sys.argv[1:], 'r')
if len(args) <> 2: raise getopt.error, 'need exactly two args'
dd = dircmp().new(args[0], args[1])
dd.run()
if ('-r', '') in options:
dd.report_phase4_closure()
else:
dd.report()
# demo()