[Python-checkins] CVS: python/dist/src/Lib difflib.py,1.4,1.5
Tim Peters
tim_one@users.sourceforge.net
Sat, 22 Sep 2001 14:30:24 -0700
Update of /cvsroot/python/python/dist/src/Lib
In directory usw-pr-cvs1:/tmp/cvs-serv24440/python/Lib
Modified Files:
difflib.py
Log Message:
Make difflib.ndiff() and difflib.Differ.compare() generators. This
restores the 2.1 ability of Tools/scripts/ndiff.py to start producing
output before the entire comparison is complete.
Index: difflib.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/difflib.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** difflib.py 2001/08/12 22:25:01 1.4
--- difflib.py 2001/09/22 21:30:22 1.5
***************
*** 1,4 ****
--- 1,6 ----
#! /usr/bin/env python
+ from __future__ import generators
+
"""
Module difflib -- helpers for computing deltas between objects.
***************
*** 23,28 ****
'Differ']
- TRACE = 0
-
class SequenceMatcher:
--- 25,28 ----
***************
*** 407,413 ****
bestsize = bestsize + 1
- if TRACE:
- print "get_matching_blocks", alo, ahi, blo, bhi
- print " returns", besti, bestj, bestsize
return besti, bestj, bestsize
--- 407,410 ----
***************
*** 433,438 ****
self.__helper(0, la, 0, lb, self.matching_blocks)
self.matching_blocks.append( (la, lb, 0) )
- if TRACE:
- print '*** matching blocks', self.matching_blocks
return self.matching_blocks
--- 430,433 ----
***************
*** 695,699 ****
Finally, we compare the two:
! >>> result = d.compare(text1, text2)
'result' is a list of strings, so let's pretty-print it:
--- 690,694 ----
Finally, we compare the two:
! >>> result = list(d.compare(text1, text2))
'result' is a list of strings, so let's pretty-print it:
***************
*** 732,736 ****
compare(a, b)
! Compare two sequences of lines; return the resulting delta (list).
"""
--- 727,731 ----
compare(a, b)
! Compare two sequences of lines; generate the resulting delta.
"""
***************
*** 754,767 ****
self.linejunk = linejunk
self.charjunk = charjunk
- self.results = []
def compare(self, a, b):
r"""
! Compare two sequences of lines; return the resulting delta (list).
Each sequence must contain individual single-line strings ending with
newlines. Such sequences can be obtained from the `readlines()` method
! of file-like objects. The list returned is also made up of
! newline-terminated strings, ready to be used with the `writelines()`
method of a file-like object.
--- 749,761 ----
self.linejunk = linejunk
self.charjunk = charjunk
def compare(self, a, b):
r"""
! Compare two sequences of lines; generate the resulting delta.
Each sequence must contain individual single-line strings ending with
newlines. Such sequences can be obtained from the `readlines()` method
! of file-like objects. The delta generated also consists of newline-
! terminated strings, ready to be printed as-is via the writeline()
method of a file-like object.
***************
*** 784,804 ****
for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
if tag == 'replace':
! self._fancy_replace(a, alo, ahi, b, blo, bhi)
elif tag == 'delete':
! self._dump('-', a, alo, ahi)
elif tag == 'insert':
! self._dump('+', b, blo, bhi)
elif tag == 'equal':
! self._dump(' ', a, alo, ahi)
else:
raise ValueError, 'unknown tag ' + `tag`
- results = self.results
- self.results = []
- return results
def _dump(self, tag, x, lo, hi):
! """Store comparison results for a same-tagged range."""
for i in xrange(lo, hi):
! self.results.append('%s %s' % (tag, x[i]))
def _plain_replace(self, a, alo, ahi, b, blo, bhi):
--- 778,798 ----
for tag, alo, ahi, blo, bhi in cruncher.get_opcodes():
if tag == 'replace':
! g = self._fancy_replace(a, alo, ahi, b, blo, bhi)
elif tag == 'delete':
! g = self._dump('-', a, alo, ahi)
elif tag == 'insert':
! g = self._dump('+', b, blo, bhi)
elif tag == 'equal':
! g = self._dump(' ', a, alo, ahi)
else:
raise ValueError, 'unknown tag ' + `tag`
+ for line in g:
+ yield line
+
def _dump(self, tag, x, lo, hi):
! """Generate comparison results for a same-tagged range."""
for i in xrange(lo, hi):
! yield '%s %s' % (tag, x[i])
def _plain_replace(self, a, alo, ahi, b, blo, bhi):
***************
*** 807,815 ****
# memory if the blocks are of very different sizes
if bhi - blo < ahi - alo:
! self._dump('+', b, blo, bhi)
! self._dump('-', a, alo, ahi)
else:
! self._dump('-', a, alo, ahi)
! self._dump('+', b, blo, bhi)
def _fancy_replace(self, a, alo, ahi, b, blo, bhi):
--- 801,813 ----
# memory if the blocks are of very different sizes
if bhi - blo < ahi - alo:
! first = self._dump('+', b, blo, bhi)
! second = self._dump('-', a, alo, ahi)
else:
! first = self._dump('-', a, alo, ahi)
! second = self._dump('+', b, blo, bhi)
!
! for g in first, second:
! for line in g:
! yield line
def _fancy_replace(self, a, alo, ahi, b, blo, bhi):
***************
*** 831,840 ****
"""
- if TRACE:
- self.results.append('*** _fancy_replace %s %s %s %s\n'
- % (alo, ahi, blo, bhi))
- self._dump('>', a, alo, ahi)
- self._dump('<', b, blo, bhi)
-
# don't synch up unless the lines have a similarity score of at
# least cutoff; best_ratio tracks the best score seen so far
--- 829,832 ----
***************
*** 870,874 ****
if eqi is None:
# no identical pair either -- treat it as a straight replace
! self._plain_replace(a, alo, ahi, b, blo, bhi)
return
# no close pair, but an identical pair -- synch up on that
--- 862,867 ----
if eqi is None:
# no identical pair either -- treat it as a straight replace
! for line in self._plain_replace(a, alo, ahi, b, blo, bhi):
! yield line
return
# no close pair, but an identical pair -- synch up on that
***************
*** 880,891 ****
# a[best_i] very similar to b[best_j]; eqi is None iff they're not
# identical
- if TRACE:
- self.results.append('*** best_ratio %s %s %s %s\n'
- % (best_ratio, best_i, best_j))
- self._dump('>', a, best_i, best_i+1)
- self._dump('<', b, best_j, best_j+1)
# pump out diffs from before the synch point
! self._fancy_helper(a, alo, best_i, b, blo, best_j)
# do intraline marking on the synch pair
--- 873,880 ----
# a[best_i] very similar to b[best_j]; eqi is None iff they're not
# identical
# pump out diffs from before the synch point
! for line in self._fancy_helper(a, alo, best_i, b, blo, best_j):
! yield line
# do intraline marking on the synch pair
***************
*** 909,929 ****
else:
raise ValueError, 'unknown tag ' + `tag`
! self._qformat(aelt, belt, atags, btags)
else:
# the synch pair is identical
! self.results.append(' ' + aelt)
# pump out diffs from after the synch point
! self._fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi)
def _fancy_helper(self, a, alo, ahi, b, blo, bhi):
if alo < ahi:
if blo < bhi:
! self._fancy_replace(a, alo, ahi, b, blo, bhi)
else:
! self._dump('-', a, alo, ahi)
elif blo < bhi:
! self._dump('+', b, blo, bhi)
def _qformat(self, aline, bline, atags, btags):
r"""
--- 898,924 ----
else:
raise ValueError, 'unknown tag ' + `tag`
! for line in self._qformat(aelt, belt, atags, btags):
! yield line
else:
# the synch pair is identical
! yield ' ' + aelt
# pump out diffs from after the synch point
! for line in self._fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi):
! yield line
def _fancy_helper(self, a, alo, ahi, b, blo, bhi):
+ g = []
if alo < ahi:
if blo < bhi:
! g = self._fancy_replace(a, alo, ahi, b, blo, bhi)
else:
! g = self._dump('-', a, alo, ahi)
elif blo < bhi:
! g = self._dump('+', b, blo, bhi)
+ for line in g:
+ yield line
+
def _qformat(self, aline, bline, atags, btags):
r"""
***************
*** 950,960 ****
btags = btags[common:].rstrip()
! self.results.append("- " + aline)
if atags:
! self.results.append("? %s%s\n" % ("\t" * common, atags))
! self.results.append("+ " + bline)
if btags:
! self.results.append("? %s%s\n" % ("\t" * common, btags))
# With respect to junk, an earlier version of ndiff simply refused to
--- 945,955 ----
btags = btags[common:].rstrip()
! yield "- " + aline
if atags:
! yield "? %s%s\n" % ("\t" * common, atags)
! yield "+ " + bline
if btags:
! yield "? %s%s\n" % ("\t" * common, btags)
# With respect to junk, an earlier version of ndiff simply refused to
***************
*** 1051,1055 ****
def restore(delta, which):
r"""
! Return one of the two sequences that generated a delta.
Given a `delta` produced by `Differ.compare()` or `ndiff()`, extract
--- 1046,1050 ----
def restore(delta, which):
r"""
! Generate one of the two sequences that generated a delta.
Given a `delta` produced by `Differ.compare()` or `ndiff()`, extract
***************
*** 1061,1064 ****
--- 1056,1060 ----
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))
+ >>> diff = list(diff)
>>> print ''.join(restore(diff, 1)),
one
***************
*** 1076,1084 ****
% which)
prefixes = (" ", tag)
- results = []
for line in delta:
if line[:2] in prefixes:
! results.append(line[2:])
! return results
def _test():
--- 1072,1078 ----
% which)
prefixes = (" ", tag)
for line in delta:
if line[:2] in prefixes:
! yield line[2:]
def _test():