New submission from Nate <[EMAIL PROTECTED]>:
The following code shows no matches though the strings clearly match.
from difflib import *
a =
'''39043203381559556628573221727792187279924711093861125152794523529732793117520068565885125032447020125028126531603069277213510312502702798781521250210814711252468946033191629862834564694482932523354428149539640297186717055152464370568794560959154441746654640262554157367545426801783736754129988985714104837148017837367541448283617148017837367541330684087148017837367541408596657148017837367541538510044714801783736754157158643714106907148017837367541474888907148017837362059576680178373675454488017831041705391546777051025363147367544777801783736754152171032271480178373675417378111377148017837367541727911516714801783736754176929952714801783736754175759835714801783736754173989658714801783104170550264677705512355737056879456095915445625329640826754157363006104258329145203115148103015957219995715478978791137801783736189510219832803777819819892374989136789814142131989249498926799891648825778109447511028842170482589787911378017831041705118365420736273279818012793603261597148017837361!
71798080178310415420736447510213871790638471586131412631592131012571210126718031314200414571314893700123874777987006697747115770067074789312578013869801783104120529166337056879456095918495136604565251349544838956219513495753741344870733943253617458316356794745831634651172458316348316144586052838244151360641656349118903581890331689038658903263218549028909605134957536316060'''
b =
'''46343203381559556628573221727792187279924711093861125152794523529732793117520068565885125032447020125028126531603069277213510312502702798781521250210814711252468946033191629862834564694482932523354428149539640297186717055152464370568794560959154441746654640262554157367545426801783736754129988985714104837148017837367541448283617148017837367541330684087148017837367541408596657148017837367541538510044714801783736754157158643714106907148017837367541474888907148017837362059576680178373675454488017831041705391546777051025363147367544777801783736754131821081171480178373675417378111377148017837367541727911516714801783736754176929952714801783736754175759835714801783736754173989658714801783104170550264677705512355737056879456095915445625329640826754157363006104258329145203115148103015957219995715478978791137801783736189510219832803777819819892374989136789814142131989249498926799891648825778109447511028842170482589787911378017831041705118365420736273279818012793603261597148017837361!
71798080178310415420736447510213871790638471412131420041457131485122165131466702097131466731723131466741536131466751581131466771649131466761975131467212090131467261974131467231858131467201556131467212538131467221553131467221943131467231748131466711452131467271787131412578013869801783104154307361718482280178373638585436251621338931320893185072980138084820801545115716861861152948618615002682261422349251058108327767521397977810837298017831041205291663370568794560959184951366045652513495448389562195134957537413448707339432536174583163'''
lst = [(a,b)]
for a, b in lst:
print "---------------------------"
s = SequenceMatcher(None, a, b)
print "length of a is %d" % len(a)
print "length of b is %d" % len(b)
print s.find_longest_match(0, len(a), 0, len(b))
print s.ratio()
for block in s.get_matching_blocks():
m = a[block[0]:block[0]+block[2]]
print "a[%d] and b[%d] match for %d elements and it is \"%s\"" %
(block[0], block[1], block[2], m)
----------
components: Extension Modules
messages: 67428
nosy: hagna
severity: normal
status: open
title: difflib.SequenceMatcher not matching long sequences
versions: Python 2.5
__________________________________
Tracker <[EMAIL PROTECTED]>
<http://bugs.python.org/issue2986>
__________________________________
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
