Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 54f22ed

Browse files
committed
More trivial comment -> docstring transformations by Ka-Ping Yee,
who writes: Here is batch 2, as a big collection of CVS context diffs. Along with moving comments into docstrings, i've added a couple of missing docstrings and attempted to make sure more module docstrings begin with a one-line summary. I did not add docstrings to the methods in profile.py for fear of upsetting any careful optimizations there, though i did move class documentation into class docstrings. The convention i'm using is to leave credits/version/copyright type of stuff in # comments, and move the rest of the descriptive stuff about module usage into module docstrings. Hope this is okay.
1 parent 8b6323d commit 54f22ed

30 files changed

Lines changed: 1578 additions & 1823 deletions

Lib/dospath.py

Lines changed: 227 additions & 231 deletions
Large diffs are not rendered by default.

Lib/filecmp.py

Lines changed: 38 additions & 299 deletions
Original file line numberDiff line numberDiff line change
@@ -1,318 +1,57 @@
1-
"""Utilities for comparing files and directories.
1+
"""Compare files."""
22

3-
Classes:
4-
dircmp
5-
6-
Functions:
7-
cmp(f1, f2, shallow=1, use_statcache=0) -> int
8-
cmpfiles(a, b, common) -> ([], [], [])
9-
10-
"""
11-
12-
import os
13-
import stat
14-
import statcache
3+
import os, stat, statcache
154

165
_cache = {}
176
BUFSIZE=8*1024
187

19-
def cmp(f1, f2, shallow=1,use_statcache=0):
20-
"""Compare two files.
8+
def cmp(f1, f2, shallow=1,use_statcache=0):
9+
"""Compare two files.
2110
22-
Arguments:
11+
Arguments:
2312
24-
f1 -- First file name
13+
f1 -- First file name
2514
26-
f2 -- Second file name
15+
f2 -- Second file name
2716
28-
shallow -- Just check stat signature (do not read the files).
29-
defaults to 1.
17+
shallow -- Just check stat signature (do not read the files).
18+
defaults to 1.
3019
31-
use_statcache -- Do not stat() each file directly: go through
32-
the statcache module for more efficiency.
20+
use_statcache -- Do not stat() each file directly: go through
21+
the statcache module for more efficiency.
3322
34-
Return value:
23+
Return value:
3524
36-
integer -- 1 if the files are the same, 0 otherwise.
25+
integer -- 1 if the files are the same, 0 otherwise.
3726
38-
This function uses a cache for past comparisons and the results,
39-
with a cache invalidation mechanism relying on stale signatures.
40-
Of course, if 'use_statcache' is true, this mechanism is defeated,
41-
and the cache will never grow stale.
27+
This function uses a cache for past comparisons and the results,
28+
with a cache invalidation mechanism relying on stale signatures.
29+
Of course, if 'use_statcache' is true, this mechanism is defeated,
30+
and the cache will never grow stale.
4231
43-
"""
44-
stat_function = (os.stat, statcache.stat)[use_statcache]
45-
s1, s2 = _sig(stat_function(f1)), _sig(stat_function(f2))
46-
if s1[0]!=stat.S_IFREG or s2[0]!=stat.S_IFREG: return 0
47-
if shallow and s1 == s2: return 1
48-
if s1[1]!=s2[1]: return 0
32+
"""
33+
stat_function = (os.stat, statcache.stat)[use_statcache]
34+
s1, s2 = _sig(stat_function(f1)), _sig(stat_function(f2))
35+
if s1[0]!=stat.S_IFREG or s2[0]!=stat.S_IFREG: return 0
36+
if shallow and s1 == s2: return 1
37+
if s1[1]!=s2[1]: return 0
4938

50-
result = _cache.get((f1, f2))
51-
if result and (s1, s2)==result[:2]:
52-
return result[2]
53-
outcome = _do_cmp(f1, f2)
54-
_cache[f1, f2] = s1, s2, outcome
55-
return outcome
39+
result = _cache.get((f1, f2))
40+
if result and (s1, s2)==result[:2]:
41+
return result[2]
42+
outcome = _do_cmp(f1, f2)
43+
_cache[f1, f2] = s1, s2, outcome
44+
return outcome
5645

5746
def _sig(st):
58-
return (stat.S_IFMT(st[stat.ST_MODE]),
59-
st[stat.ST_SIZE],
60-
st[stat.ST_MTIME])
47+
return (stat.S_IFMT(st[stat.ST_MODE]),
48+
st[stat.ST_SIZE],
49+
st[stat.ST_MTIME])
6150

6251
def _do_cmp(f1, f2):
63-
bufsize = BUFSIZE
64-
fp1 , fp2 = open(f1, 'rb'), open(f2, 'rb')
65-
while 1:
66-
b1, b2 = fp1.read(bufsize), fp2.read(bufsize)
67-
if b1!=b2: return 0
68-
if not b1: return 1
69-
70-
# Directory comparison class.
71-
#
72-
class dircmp:
73-
"""A class that manages the comparison of 2 directories.
74-
75-
dircmp(a,b,ignore=None,hide=None)
76-
A and B are directories.
77-
IGNORE is a list of names to ignore,
78-
defaults to ['RCS', 'CVS', 'tags'].
79-
HIDE is a list of names to hide,
80-
defaults to [os.curdir, os.pardir].
81-
82-
High level usage:
83-
x = dircmp(dir1, dir2)
84-
x.report() -> prints a report on the differences between dir1 and dir2
85-
or
86-
x.report_partial_closure() -> prints report on differences between dir1
87-
and dir2, and reports on common immediate subdirectories.
88-
x.report_full_closure() -> like report_partial_closure,
89-
but fully recursive.
90-
91-
Attributes:
92-
left_list, right_list: The files in dir1 and dir2,
93-
filtered by hide and ignore.
94-
common: a list of names in both dir1 and dir2.
95-
left_only, right_only: names only in dir1, dir2.
96-
common_dirs: subdirectories in both dir1 and dir2.
97-
common_files: files in both dir1 and dir2.
98-
common_funny: names in both dir1 and dir2 where the type differs between
99-
dir1 and dir2, or the name is not stat-able.
100-
same_files: list of identical files.
101-
diff_files: list of filenames which differ.
102-
funny_files: list of files which could not be compared.
103-
subdirs: a dictionary of dircmp objects, keyed by names in common_dirs.
104-
"""
105-
106-
def __init__(self, a, b, ignore=None, hide=None): # Initialize
107-
self.left = a
108-
self.right = b
109-
if hide is None:
110-
self.hide = [os.curdir, os.pardir] # Names never to be shown
111-
else:
112-
self.hide = hide
113-
if ignore is None:
114-
self.ignore = ['RCS', 'CVS', 'tags'] # Names ignored in comparison
115-
else:
116-
self.ignore = ignore
117-
118-
def phase0(self): # Compare everything except common subdirectories
119-
self.left_list = _filter(os.listdir(self.left),
120-
self.hide+self.ignore)
121-
self.right_list = _filter(os.listdir(self.right),
122-
self.hide+self.ignore)
123-
self.left_list.sort()
124-
self.right_list.sort()
125-
126-
__p4_attrs = ('subdirs',)
127-
__p3_attrs = ('same_files', 'diff_files', 'funny_files')
128-
__p2_attrs = ('common_dirs', 'common_files', 'common_funny')
129-
__p1_attrs = ('common', 'left_only', 'right_only')
130-
__p0_attrs = ('left_list', 'right_list')
131-
132-
def __getattr__(self, attr):
133-
if attr in self.__p4_attrs:
134-
self.phase4()
135-
elif attr in self.__p3_attrs:
136-
self.phase3()
137-
elif attr in self.__p2_attrs:
138-
self.phase2()
139-
elif attr in self.__p1_attrs:
140-
self.phase1()
141-
elif attr in self.__p0_attrs:
142-
self.phase0()
143-
else:
144-
raise AttributeError, attr
145-
return getattr(self, attr)
146-
147-
def phase1(self): # Compute common names
148-
a_only, b_only = [], []
149-
common = {}
150-
b = {}
151-
for fnm in self.right_list:
152-
b[fnm] = 1
153-
for x in self.left_list:
154-
if b.get(x, 0):
155-
common[x] = 1
156-
else:
157-
a_only.append(x)
158-
for x in self.right_list:
159-
if common.get(x, 0):
160-
pass
161-
else:
162-
b_only.append(x)
163-
self.common = common.keys()
164-
self.left_only = a_only
165-
self.right_only = b_only
166-
167-
def phase2(self): # Distinguish files, directories, funnies
168-
self.common_dirs = []
169-
self.common_files = []
170-
self.common_funny = []
171-
172-
for x in self.common:
173-
a_path = os.path.join(self.left, x)
174-
b_path = os.path.join(self.right, x)
175-
176-
ok = 1
177-
try:
178-
a_stat = statcache.stat(a_path)
179-
except os.error, why:
180-
# print 'Can\'t stat', a_path, ':', why[1]
181-
ok = 0
182-
try:
183-
b_stat = statcache.stat(b_path)
184-
except os.error, why:
185-
# print 'Can\'t stat', b_path, ':', why[1]
186-
ok = 0
187-
188-
if ok:
189-
a_type = stat.S_IFMT(a_stat[stat.ST_MODE])
190-
b_type = stat.S_IFMT(b_stat[stat.ST_MODE])
191-
if a_type <> b_type:
192-
self.common_funny.append(x)
193-
elif stat.S_ISDIR(a_type):
194-
self.common_dirs.append(x)
195-
elif stat.S_ISREG(a_type):
196-
self.common_files.append(x)
197-
else:
198-
self.common_funny.append(x)
199-
else:
200-
self.common_funny.append(x)
201-
202-
def phase3(self): # Find out differences between common files
203-
xx = cmpfiles(self.left, self.right, self.common_files)
204-
self.same_files, self.diff_files, self.funny_files = xx
205-
206-
def phase4(self): # Find out differences between common subdirectories
207-
# A new dircmp object is created for each common subdirectory,
208-
# these are stored in a dictionary indexed by filename.
209-
# The hide and ignore properties are inherited from the parent
210-
self.subdirs = {}
211-
for x in self.common_dirs:
212-
a_x = os.path.join(self.left, x)
213-
b_x = os.path.join(self.right, x)
214-
self.subdirs[x] = dircmp(a_x, b_x, self.ignore, self.hide)
215-
216-
def phase4_closure(self): # Recursively call phase4() on subdirectories
217-
self.phase4()
218-
for x in self.subdirs.keys():
219-
self.subdirs[x].phase4_closure()
220-
221-
def report(self): # Print a report on the differences between a and b
222-
# Output format is purposely lousy
223-
print 'diff', self.left, self.right
224-
if self.left_only:
225-
self.left_only.sort()
226-
print 'Only in', self.left, ':', self.left_only
227-
if self.right_only:
228-
self.right_only.sort()
229-
print 'Only in', self.right, ':', self.right_only
230-
if self.same_files:
231-
self.same_files.sort()
232-
print 'Identical files :', self.same_files
233-
if self.diff_files:
234-
self.diff_files.sort()
235-
print 'Differing files :', self.diff_files
236-
if self.funny_files:
237-
self.funny_files.sort()
238-
print 'Trouble with common files :', self.funny_files
239-
if self.common_dirs:
240-
self.common_dirs.sort()
241-
print 'Common subdirectories :', self.common_dirs
242-
if self.common_funny:
243-
self.common_funny.sort()
244-
print 'Common funny cases :', self.common_funny
245-
246-
def report_partial_closure(self): # Print reports on self and on subdirs
247-
self.report()
248-
for x in self.subdirs.keys():
249-
print
250-
self.subdirs[x].report()
251-
252-
def report_full_closure(self): # Report on self and subdirs recursively
253-
self.report()
254-
for x in self.subdirs.keys():
255-
print
256-
self.subdirs[x].report_full_closure()
257-
258-
259-
# Compare common files in two directories.
260-
# Return:
261-
# - files that compare equal
262-
# - files that compare different
263-
# - funny cases (can't stat etc.)
264-
#
265-
def cmpfiles(a, b, common):
266-
"""Compare common files in two directories.
267-
268-
cmpfiles(a,b,common)
269-
A and B are directory names
270-
COMMON is a list of file names
271-
returns a tuple of three lists:
272-
files that compare equal
273-
files that are different
274-
filenames that aren't regular files."""
275-
276-
res = ([], [], [])
277-
for x in common:
278-
res[_cmp(os.path.join(a, x), os.path.join(b, x))].append(x)
279-
return res
280-
281-
282-
# Compare two files.
283-
# Return:
284-
# 0 for equal
285-
# 1 for different
286-
# 2 for funny cases (can't stat, etc.)
287-
#
288-
def _cmp(a, b):
289-
try:
290-
return not abs(cmp(a, b))
291-
except os.error:
292-
return 2
293-
294-
295-
# Return a copy with items that occur in skip removed.
296-
#
297-
def _filter(list, skip):
298-
result = []
299-
for item in list:
300-
if item not in skip: result.append(item)
301-
return result
302-
303-
304-
# Demonstration and testing.
305-
#
306-
def demo():
307-
import sys
308-
import getopt
309-
options, args = getopt.getopt(sys.argv[1:], 'r')
310-
if len(args) <> 2: raise getopt.error, 'need exactly two args'
311-
dd = dircmp(args[0], args[1])
312-
if ('-r', '') in options:
313-
dd.report_full_closure()
314-
else:
315-
dd.report()
316-
317-
if __name__ == '__main__':
318-
demo()
52+
bufsize = BUFSIZE
53+
fp1 , fp2 = open(f1, 'rb'), open(f2, 'rb')
54+
while 1:
55+
b1, b2 = fp1.read(bufsize), fp2.read(bufsize)
56+
if b1!=b2: return 0
57+
if not b1: return 1

0 commit comments

Comments
 (0)