def fcompare(f1name, f2name): f1 = fopen(f1name) f2 = fopen(f2name) if not f1 or not f2: return 0 a = f1.readlines() f1.close() b = f2.readlines() f2.close() cruncher = SequenceMatcher(IS_LINE_JUNK, a, b) for tag, alo, ahi, blo, bhi in cruncher.get_opcodes(): if tag == 'replace': fancy_replace(a, alo, ahi, b, blo, bhi) elif tag == 'delete': dump('-', a, alo, ahi) elif tag == 'insert': dump('+', b, blo, bhi) elif tag == 'equal': dump(' ', a, alo, ahi) else: raise ValueError, 'unknown tag ' + ` tag ` return 1
def fcompare(f1name, f2name): f1 = fopen(f1name) f2 = fopen(f2name) if not f1 or not f2: return 0 a = f1.readlines(); f1.close() b = f2.readlines(); f2.close() cruncher = SequenceMatcher(IS_LINE_JUNK, a, b) for tag, alo, ahi, blo, bhi in cruncher.get_opcodes(): if tag == 'replace': fancy_replace(a, alo, ahi, b, blo, bhi) elif tag == 'delete': dump('-', a, alo, ahi) elif tag == 'insert': dump('+', b, blo, bhi) elif tag == 'equal': dump(' ', a, alo, ahi) else: raise ValueError, 'unknown tag ' + `tag` return 1
def fancy_replace(a, alo, ahi, b, blo, bhi): if TRACE: print '*** fancy_replace', alo, ahi, blo, bhi dump('>', a, alo, ahi) 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 best_ratio, cutoff = 0.74, 0.75 cruncher = SequenceMatcher(IS_CHARACTER_JUNK) eqi, eqj = None, None # 1st indices of equal lines (if any) # search for the pair that matches best without being identical # (identical lines must be junk lines, & we don't want to synch up # on junk -- unless we have to) for j in xrange(blo, bhi): bj = b[j] cruncher.set_seq2(bj) for i in xrange(alo, ahi): ai = a[i] if ai == bj: if eqi is None: eqi, eqj = i, j continue cruncher.set_seq1(ai) # computing similarity is expensive, so use the quick # upper bounds first -- have seen this speed up messy # compares by a factor of 3. # note that ratio() is only expensive to compute the first # time it's called on a sequence pair; the expensive part # of the computation is cached by cruncher if cruncher.real_quick_ratio() > best_ratio and \ cruncher.quick_ratio() > best_ratio and \ cruncher.ratio() > best_ratio: best_ratio, best_i, best_j = cruncher.ratio(), i, j if best_ratio < cutoff: # no non-identical "pretty close" pair if eqi is None: # no identical pair either -- treat it as a straight replace plain_replace(a, alo, ahi, b, blo, bhi) return # no close pair, but an identical pair -- synch up on that best_i, best_j, best_ratio = eqi, eqj, 1.0 else: # there's a close pair, so forget the identical pair (if any) eqi = None # a[best_i] very similar to b[best_j]; eqi is None iff they're not # identical if TRACE: print '*** best_ratio', best_ratio, best_i, best_j dump('>', a, best_i, best_i+1) dump('<', b, best_j, best_j+1) # pump out diffs from before the synch point fancy_helper(a, alo, best_i, b, blo, best_j) # do intraline marking on the synch pair aelt, belt = a[best_i], b[best_j] if eqi is None: # pump out a '-', '?', '+', '?' quad for the synched lines atags = btags = "" cruncher.set_seqs(aelt, belt) for tag, ai1, ai2, bj1, bj2 in cruncher.get_opcodes(): la, lb = ai2 - ai1, bj2 - bj1 if tag == 'replace': atags = atags + '^' * la btags = btags + '^' * lb elif tag == 'delete': atags = atags + '-' * la elif tag == 'insert': btags = btags + '+' * lb elif tag == 'equal': atags = atags + ' ' * la btags = btags + ' ' * lb else: raise ValueError, 'unknown tag ' + `tag` printq(aelt, belt, atags, btags) else: # the synch pair is identical print ' ', aelt, # pump out diffs from after the synch point fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi)
def fancy_replace(a, alo, ahi, b, blo, bhi): if TRACE: print '*** fancy_replace', alo, ahi, blo, bhi dump('>', a, alo, ahi) 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 best_ratio, cutoff = 0.74, 0.75 cruncher = SequenceMatcher(IS_CHARACTER_JUNK) eqi, eqj = None, None # 1st indices of equal lines (if any) # search for the pair that matches best without being identical # (identical lines must be junk lines, & we don't want to synch up # on junk -- unless we have to) for j in xrange(blo, bhi): bj = b[j] cruncher.set_seq2(bj) for i in xrange(alo, ahi): ai = a[i] if ai == bj: if eqi is None: eqi, eqj = i, j continue cruncher.set_seq1(ai) # computing similarity is expensive, so use the quick # upper bounds first -- have seen this speed up messy # compares by a factor of 3. # note that ratio() is only expensive to compute the first # time it's called on a sequence pair; the expensive part # of the computation is cached by cruncher if cruncher.real_quick_ratio() > best_ratio and \ cruncher.quick_ratio() > best_ratio and \ cruncher.ratio() > best_ratio: best_ratio, best_i, best_j = cruncher.ratio(), i, j if best_ratio < cutoff: # no non-identical "pretty close" pair if eqi is None: # no identical pair either -- treat it as a straight replace plain_replace(a, alo, ahi, b, blo, bhi) return # no close pair, but an identical pair -- synch up on that best_i, best_j, best_ratio = eqi, eqj, 1.0 else: # there's a close pair, so forget the identical pair (if any) eqi = None # a[best_i] very similar to b[best_j]; eqi is None iff they're not # identical if TRACE: print '*** best_ratio', best_ratio, best_i, best_j dump('>', a, best_i, best_i + 1) dump('<', b, best_j, best_j + 1) # pump out diffs from before the synch point fancy_helper(a, alo, best_i, b, blo, best_j) # do intraline marking on the synch pair aelt, belt = a[best_i], b[best_j] if eqi is None: # pump out a '-', '?', '+', '?' quad for the synched lines atags = btags = "" cruncher.set_seqs(aelt, belt) for tag, ai1, ai2, bj1, bj2 in cruncher.get_opcodes(): la, lb = ai2 - ai1, bj2 - bj1 if tag == 'replace': atags = atags + '^' * la btags = btags + '^' * lb elif tag == 'delete': atags = atags + '-' * la elif tag == 'insert': btags = btags + '+' * lb elif tag == 'equal': atags = atags + ' ' * la btags = btags + ' ' * lb else: raise ValueError, 'unknown tag ' + ` tag ` printq(aelt, belt, atags, btags) else: # the synch pair is identical print ' ', aelt, # pump out diffs from after the synch point fancy_helper(a, best_i + 1, ahi, b, best_j + 1, bhi)