1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
|
#! /usr/bin/env python3
"""
Module difflib -- helpers for computing deltas between objects.
Function get_close_matches(word, possibilities, n=3, cutoff=0.6):
Use SequenceMatcher to return list of the best "good enough" matches.
Function context_diff(a, b):
For two lists of strings, return a delta in context diff format.
Function ndiff(a, b):
Return a delta: the difference between `a` and `b` (lists of strings).
Function restore(delta, which):
Return one of the two sequences that generated an ndiff delta.
Function unified_diff(a, b):
For two lists of strings, return a delta in unified diff format.
Class SequenceMatcher:
A flexible class for comparing pairs of sequences of any type.
Class Differ:
For producing human-readable deltas from sequences of lines of text.
Class HtmlDiff:
For producing HTML side by side comparison with change highlights.
"""
__all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher',
'Differ','IS_CHARACTER_JUNK', 'IS_LINE_JUNK', 'context_diff',
'unified_diff', 'HtmlDiff', 'Match']
import heapq
from collections import namedtuple as _namedtuple
Match = _namedtuple('Match', 'a b size')
def _calculate_ratio(matches, length):
if length:
return 2.0 * matches / length
return 1.0
class SequenceMatcher:
"""
SequenceMatcher is a flexible class for comparing pairs of sequences of
any type, so long as the sequence elements are hashable. The basic
algorithm predates, and is a little fancier than, an algorithm
published in the late 1980's by Ratcliff and Obershelp under the
hyperbolic name "gestalt pattern matching". The basic idea is to find
the longest contiguous matching subsequence that contains no "junk"
elements (R-O doesn't address junk). The same idea is then applied
recursively to the pieces of the sequences to the left and to the right
of the matching subsequence. This does not yield minimal edit
sequences, but does tend to yield matches that "look right" to people.
SequenceMatcher tries to compute a "human-friendly diff" between two
sequences. Unlike e.g. UNIX(tm) diff, the fundamental notion is the
longest *contiguous* & junk-free matching subsequence. That's what
catches peoples' eyes. The Windows(tm) windiff has another interesting
notion, pairing up elements that appear uniquely in each sequence.
That, and the method here, appear to yield more intuitive difference
reports than does diff. This method appears to be the least vulnerable
to synching up on blocks of "junk lines", though (like blank lines in
ordinary text files, or maybe "<P>" lines in HTML files). That may be
because this is the only method of the 3 that has a *concept* of
"junk" <wink>.
Example, comparing two strings, and considering blanks to be "junk":
>>> s = SequenceMatcher(lambda x: x == " ",
... "private Thread currentThread;",
... "private volatile Thread currentThread;")
>>>
.ratio() returns a float in [0, 1], measuring the "similarity" of the
sequences. As a rule of thumb, a .ratio() value over 0.6 means the
sequences are close matches:
>>> print(round(s.ratio(), 3))
0.866
>>>
If you're only interested in where the sequences match,
.get_matching_blocks() is handy:
>>> for block in s.get_matching_blocks():
... print("a[%d] and b[%d] match for %d elements" % block)
a[0] and b[0] match for 8 elements
a[8] and b[17] match for 21 elements
a[29] and b[38] match for 0 elements
Note that the last tuple returned by .get_matching_blocks() is always a
dummy, (len(a), len(b), 0), and this is the only case in which the last
tuple element (number of elements matched) is 0.
If you want to know how to change the first sequence into the second,
use .get_opcodes():
>>> for opcode in s.get_opcodes():
... print("%6s a[%d:%d] b[%d:%d]" % opcode)
equal a[0:8] b[0:8]
insert a[8:8] b[8:17]
equal a[8:29] b[17:38]
See the Differ class for a fancy human-friendly file differencer, which
uses SequenceMatcher both to compare sequences of lines, and to compare
sequences of characters within similar (near-matching) lines.
See also function get_close_matches() in this module, which shows how
simple code building on SequenceMatcher can be used to do useful work.
Timing: Basic R-O is cubic time worst case and quadratic time expected
case. SequenceMatcher is quadratic time for the worst case and has
expected-case behavior dependent in a complicated way on how many
elements the sequences have in common; best case time is linear.
Methods:
__init__(isjunk=None, a='', b='')
Construct a SequenceMatcher.
set_seqs(a, b)
Set the two sequences to be compared.
set_seq1(a)
Set the first sequence to be compared.
set_seq2(b)
Set the second sequence to be compared.
find_longest_match(alo, ahi, blo, bhi)
Find longest matching block in a[alo:ahi] and b[blo:bhi].
get_matching_blocks()
Return list of triples describing matching subsequences.
get_opcodes()
Return list of 5-tuples describing how to turn a into b.
ratio()
Return a measure of the sequences' similarity (float in [0,1]).
quick_ratio()
Return an upper bound on .ratio() relatively quickly.
real_quick_ratio()
Return an upper bound on ratio() very quickly.
"""
def __init__(self, isjunk=None, a='', b=''):
"""Construct a SequenceMatcher.
Optional arg isjunk is None (the default), or a one-argument
function that takes a sequence element and returns true iff the
element is junk. None is equivalent to passing "lambda x: 0", i.e.
no elements are considered to be junk. For example, pass
lambda x: x in " \\t"
if you're comparing lines as sequences of characters, and don't
want to synch up on blanks or hard tabs.
Optional arg a is the first of two sequences to be compared. By
default, an empty string. The elements of a must be hashable. See
also .set_seqs() and .set_seq1().
Optional arg b is the second of two sequences to be compared. By
default, an empty string. The elements of b must be hashable. See
also .set_seqs() and .set_seq2().
"""
# Members:
# a
# first sequence
# b
# second sequence; differences are computed as "what do
# we need to do to 'a' to change it into 'b'?"
# b2j
# for x in b, b2j[x] is a list of the indices (into b)
# at which x appears; junk elements do not appear
# fullbcount
# for x in b, fullbcount[x] == the number of times x
# appears in b; only materialized if really needed (used
# only for computing quick_ratio())
# matching_blocks
# a list of (i, j, k) triples, where a[i:i+k] == b[j:j+k];
# ascending & non-overlapping in i and in j; terminated by
# a dummy (len(a), len(b), 0) sentinel
# opcodes
# a list of (tag, i1, i2, j1, j2) tuples, where tag is
# one of
# 'replace' a[i1:i2] should be replaced by b[j1:j2]
# 'delete' a[i1:i2] should be deleted
# 'insert' b[j1:j2] should be inserted
# 'equal' a[i1:i2] == b[j1:j2]
# isjunk
# a user-supplied function taking a sequence element and
# returning true iff the element is "junk" -- this has
# subtle but helpful effects on the algorithm, which I'll
# get around to writing up someday <0.9 wink>.
# DON'T USE! Only __chain_b uses this. Use isbjunk.
# isbjunk
# for x in b, isbjunk(x) == isjunk(x) but much faster;
# it's really the __contains__ method of a hidden dict.
# DOES NOT WORK for x in a!
# isbpopular
# for x in b, isbpopular(x) is true iff b is reasonably long
# (at least 200 elements) and x accounts for more than 1% of
# its elements. DOES NOT WORK for x in a!
self.isjunk = isjunk
self.a = self.b = None
self.set_seqs(a, b)
def set_seqs(self, a, b):
"""Set the two sequences to be compared.
>>> s = SequenceMatcher()
>>> s.set_seqs("abcd", "bcde")
>>> s.ratio()
0.75
"""
self.set_seq1(a)
self.set_seq2(b)
def set_seq1(self, a):
"""Set the first sequence to be compared.
The second sequence to be compared is not changed.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.set_seq1("bcde")
>>> s.ratio()
1.0
>>>
SequenceMatcher computes and caches detailed information about the
second sequence, so if you want to compare one sequence S against
many sequences, use .set_seq2(S) once and call .set_seq1(x)
repeatedly for each of the other sequences.
See also set_seqs() and set_seq2().
"""
if a is self.a:
return
self.a = a
self.matching_blocks = self.opcodes = None
def set_seq2(self, b):
"""Set the second sequence to be compared.
The first sequence to be compared is not changed.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.set_seq2("abcd")
>>> s.ratio()
1.0
>>>
SequenceMatcher computes and caches detailed information about the
second sequence, so if you want to compare one sequence S against
many sequences, use .set_seq2(S) once and call .set_seq1(x)
repeatedly for each of the other sequences.
See also set_seqs() and set_seq1().
"""
if b is self.b:
return
self.b = b
self.matching_blocks = self.opcodes = None
self.fullbcount = None
self.__chain_b()
# For each element x in b, set b2j[x] to a list of the indices in
# b where x appears; the indices are in increasing order; note that
# the number of times x appears in b is len(b2j[x]) ...
# when self.isjunk is defined, junk elements don't show up in this
# map at all, which stops the central find_longest_match method
# from starting any matching block at a junk element ...
# also creates the fast isbjunk function ...
# b2j also does not contain entries for "popular" elements, meaning
# elements that account for more than 1% of the total elements, and
# when the sequence is reasonably large (>= 200 elements); this can
# be viewed as an adaptive notion of semi-junk, and yields an enormous
# speedup when, e.g., comparing program files with hundreds of
# instances of "return NULL;" ...
# note that this is only called when b changes; so for cross-product
# kinds of matches, it's best to call set_seq2 once, then set_seq1
# repeatedly
def __chain_b(self):
# Because isjunk is a user-defined (not C) function, and we test
# for junk a LOT, it's important to minimize the number of calls.
# Before the tricks described here, __chain_b was by far the most
# time-consuming routine in the whole module! If anyone sees
# Jim Roskind, thank him again for profile.py -- I never would
# have guessed that.
# The first trick is to build b2j ignoring the possibility
# of junk. I.e., we don't call isjunk at all yet. Throwing
# out the junk later is much cheaper than building b2j "right"
# from the start.
b = self.b
n = len(b)
self.b2j = b2j = {}
populardict = {}
for i, elt in enumerate(b):
if elt in b2j:
indices = b2j[elt]
if n >= 200 and len(indices) * 100 > n:
populardict[elt] = 1
del indices[:]
else:
indices.append(i)
else:
b2j[elt] = [i]
# Purge leftover indices for popular elements.
for elt in populardict:
del b2j[elt]
# Now b2j.keys() contains elements uniquely, and especially when
# the sequence is a string, that's usually a good deal smaller
# than len(string). The difference is the number of isjunk calls
# saved.
isjunk = self.isjunk
junkdict = {}
if isjunk:
for d in populardict, b2j:
for elt in list(d.keys()):
if isjunk(elt):
junkdict[elt] = 1
del d[elt]
# Now for x in b, isjunk(x) == x in junkdict, but the
# latter is much faster. Note too that while there may be a
# lot of junk in the sequence, the number of *unique* junk
# elements is probably small. So the memory burden of keeping
# this dict alive is likely trivial compared to the size of b2j.
self.isbjunk = junkdict.__contains__
self.isbpopular = populardict.__contains__
def find_longest_match(self, alo, ahi, blo, bhi):
"""Find longest matching block in a[alo:ahi] and b[blo:bhi].
If isjunk is not defined:
Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where
alo <= i <= i+k <= ahi
blo <= j <= j+k <= bhi
and for all (i',j',k') meeting those conditions,
k >= k'
i <= i'
and if i == i', j <= j'
In other words, of all maximal matching blocks, return one that
starts earliest in a, and of all those maximal matching blocks that
start earliest in a, return the one that starts earliest in b.
>>> s = SequenceMatcher(None, " abcd", "abcd abcd")
>>> s.find_longest_match(0, 5, 0, 9)
Match(a=0, b=4, size=5)
If isjunk is defined, first the longest matching block is
determined as above, but with the additional restriction that no
junk element appears in the block. Then that block is extended as
far as possible by matching (only) junk elements on both sides. So
the resulting block never matches on junk except as identical junk
happens to be adjacent to an "interesting" match.
Here's the same example as before, but considering blanks to be
junk. That prevents " abcd" from matching the " abcd" at the tail
end of the second sequence directly. Instead only the "abcd" can
match, and matches the leftmost "abcd" in the second sequence:
>>> s = SequenceMatcher(lambda x: x==" ", " abcd", "abcd abcd")
>>> s.find_longest_match(0, 5, 0, 9)
Match(a=1, b=0, size=4)
If no blocks match, return (alo, blo, 0).
>>> s = SequenceMatcher(None, "ab", "c")
>>> s.find_longest_match(0, 2, 0, 1)
Match(a=0, b=0, size=0)
"""
# CAUTION: stripping common prefix or suffix would be incorrect.
# E.g.,
# ab
# acab
# Longest matching block is "ab", but if common prefix is
# stripped, it's "a" (tied with "b"). UNIX(tm) diff does so
# strip, so ends up claiming that ab is changed to acab by
# inserting "ca" in the middle. That's minimal but unintuitive:
# "it's obvious" that someone inserted "ac" at the front.
# Windiff ends up at the same place as diff, but by pairing up
# the unique 'b's and then matching the first two 'a's.
a, b, b2j, isbjunk = self.a, self.b, self.b2j, self.isbjunk
besti, bestj, bestsize = alo, blo, 0
# find longest junk-free match
# during an iteration of the loop, j2len[j] = length of longest
# junk-free match ending with a[i-1] and b[j]
j2len = {}
nothing = []
for i in range(alo, ahi):
# look at all instances of a[i] in b; note that because
# b2j has no junk keys, the loop is skipped if a[i] is junk
j2lenget = j2len.get
newj2len = {}
for j in b2j.get(a[i], nothing):
# a[i] matches b[j]
if j < blo:
continue
if j >= bhi:
break
k = newj2len[j] = j2lenget(j-1, 0) + 1
if k > bestsize:
besti, bestj, bestsize = i-k+1, j-k+1, k
j2len = newj2len
# Extend the best by non-junk elements on each end. In particular,
# "popular" non-junk elements aren't in b2j, which greatly speeds
# the inner loop above, but also means "the best" match so far
# doesn't contain any junk *or* popular non-junk elements.
while besti > alo and bestj > blo and \
not isbjunk(b[bestj-1]) and \
a[besti-1] == b[bestj-1]:
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
while besti+bestsize < ahi and bestj+bestsize < bhi and \
not isbjunk(b[bestj+bestsize]) and \
a[besti+bestsize] == b[bestj+bestsize]:
bestsize += 1
# Now that we have a wholly interesting match (albeit possibly
# empty!), we may as well suck up the matching junk on each
# side of it too. Can't think of a good reason not to, and it
# saves post-processing the (possibly considerable) expense of
# figuring out what to do with it. In the case of an empty
# interesting match, this is clearly the right thing to do,
# because no other kind of match is possible in the regions.
while besti > alo and bestj > blo and \
isbjunk(b[bestj-1]) and \
a[besti-1] == b[bestj-1]:
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
while besti+bestsize < ahi and bestj+bestsize < bhi and \
isbjunk(b[bestj+bestsize]) and \
a[besti+bestsize] == b[bestj+bestsize]:
bestsize = bestsize + 1
return Match(besti, bestj, bestsize)
def get_matching_blocks(self):
"""Return list of triples describing matching subsequences.
Each triple is of the form (i, j, n), and means that
a[i:i+n] == b[j:j+n]. The triples are monotonically increasing in
i and in j. New in Python 2.5, it's also guaranteed that if
(i, j, n) and (i', j', n') are adjacent triples in the list, and
the second is not the last triple in the list, then i+n != i' or
j+n != j'. IOW, adjacent triples never describe adjacent equal
blocks.
The last triple is a dummy, (len(a), len(b), 0), and is the only
triple with n==0.
>>> s = SequenceMatcher(None, "abxcd", "abcd")
>>> list(s.get_matching_blocks())
[Match(a=0, b=0, size=2), Match(a=3, b=2, size=2), Match(a=5, b=4, size=0)]
"""
if self.matching_blocks is not None:
return self.matching_blocks
la, lb = len(self.a), len(self.b)
# This is most naturally expressed as a recursive algorithm, but
# at least one user bumped into extreme use cases that exceeded
# the recursion limit on their box. So, now we maintain a list
# ('queue`) of blocks we still need to look at, and append partial
# results to `matching_blocks` in a loop; the matches are sorted
# at the end.
queue = [(0, la, 0, lb)]
matching_blocks = []
while queue:
alo, ahi, blo, bhi = queue.pop()
i, j, k = x = self.find_longest_match(alo, ahi, blo, bhi)
# a[alo:i] vs b[blo:j] unknown
# a[i:i+k] same as b[j:j+k]
# a[i+k:ahi] vs b[j+k:bhi] unknown
if k: # if k is 0, there was no matching block
matching_blocks.append(x)
if alo < i and blo < j:
queue.append((alo, i, blo, j))
if i+k < ahi and j+k < bhi:
queue.append((i+k, ahi, j+k, bhi))
matching_blocks.sort()
# It's possible that we have adjacent equal blocks in the
# matching_blocks list now. Starting with 2.5, this code was added
# to collapse them.
i1 = j1 = k1 = 0
non_adjacent = []
for i2, j2, k2 in matching_blocks:
# Is this block adjacent to i1, j1, k1?
if i1 + k1 == i2 and j1 + k1 == j2:
# Yes, so collapse them -- this just increases the length of
# the first block by the length of the second, and the first
# block so lengthened remains the block to compare against.
k1 += k2
else:
# Not adjacent. Remember the first block (k1==0 means it's
# the dummy we started with), and make the second block the
# new block to compare against.
if k1:
non_adjacent.append((i1, j1, k1))
i1, j1, k1 = i2, j2, k2
if k1:
non_adjacent.append((i1, j1, k1))
non_adjacent.append( (la, lb, 0) )
self.matching_blocks = non_adjacent
return map(Match._make, self.matching_blocks)
def get_opcodes(self):
"""Return list of 5-tuples describing how to turn a into b.
Each tuple is of the form (tag, i1, i2, j1, j2). The first tuple
has i1 == j1 == 0, and remaining tuples have i1 == the i2 from the
tuple preceding it, and likewise for j1 == the previous j2.
The tags are strings, with these meanings:
'replace': a[i1:i2] should be replaced by b[j1:j2]
'delete': a[i1:i2] should be deleted.
Note that j1==j2 in this case.
'insert': b[j1:j2] should be inserted at a[i1:i1].
Note that i1==i2 in this case.
'equal': a[i1:i2] == b[j1:j2]
>>> a = "qabxcd"
>>> b = "abycdf"
>>> s = SequenceMatcher(None, a, b)
>>> for tag, i1, i2, j1, j2 in s.get_opcodes():
... print(("%7s a[%d:%d] (%s) b[%d:%d] (%s)" %
... (tag, i1, i2, a[i1:i2], j1, j2, b[j1:j2])))
delete a[0:1] (q) b[0:0] ()
equal a[1:3] (ab) b[0:2] (ab)
replace a[3:4] (x) b[2:3] (y)
equal a[4:6] (cd) b[3:5] (cd)
insert a[6:6] () b[5:6] (f)
"""
if self.opcodes is not None:
return self.opcodes
i = j = 0
self.opcodes = answer = []
for ai, bj, size in self.get_matching_blocks():
# invariant: we've pumped out correct diffs to change
# a[:i] into b[:j], and the next matching block is
# a[ai:ai+size] == b[bj:bj+size]. So we need to pump
# out a diff to change a[i:ai] into b[j:bj], pump out
# the matching block, and move (i,j) beyond the match
tag = ''
if i < ai and j < bj:
tag = 'replace'
elif i < ai:
tag = 'delete'
elif j < bj:
tag = 'insert'
if tag:
answer.append( (tag, i, ai, j, bj) )
i, j = ai+size, bj+size
# the list of matching blocks is terminated by a
# sentinel with size 0
if size:
answer.append( ('equal', ai, i, bj, j) )
return answer
def get_grouped_opcodes(self, n=3):
""" Isolate change clusters by eliminating ranges with no changes.
Return a generator of groups with upto n lines of context.
Each group is in the same format as returned by get_opcodes().
>>> from pprint import pprint
>>> a = list(map(str, range(1,40)))
>>> b = a[:]
>>> b[8:8] = ['i'] # Make an insertion
>>> b[20] += 'x' # Make a replacement
>>> b[23:28] = [] # Make a deletion
>>> b[30] += 'y' # Make another replacement
>>> pprint(list(SequenceMatcher(None,a,b).get_grouped_opcodes()))
[[('equal', 5, 8, 5, 8), ('insert', 8, 8, 8, 9), ('equal', 8, 11, 9, 12)],
[('equal', 16, 19, 17, 20),
('replace', 19, 20, 20, 21),
('equal', 20, 22, 21, 23),
('delete', 22, 27, 23, 23),
('equal', 27, 30, 23, 26)],
[('equal', 31, 34, 27, 30),
('replace', 34, 35, 30, 31),
('equal', 35, 38, 31, 34)]]
"""
codes = self.get_opcodes()
if not codes:
codes = [("equal", 0, 1, 0, 1)]
# Fixup leading and trailing groups if they show no changes.
if codes[0][0] == 'equal':
tag, i1, i2, j1, j2 = codes[0]
codes[0] = tag, max(i1, i2-n), i2, max(j1, j2-n), j2
if codes[-1][0] == 'equal':
tag, i1, i2, j1, j2 = codes[-1]
codes[-1] = tag, i1, min(i2, i1+n), j1, min(j2, j1+n)
nn = n + n
group = []
for tag, i1, i2, j1, j2 in codes:
# End the current group and start a new one whenever
# there is a large range with no changes.
if tag == 'equal' and i2-i1 > nn:
group.append((tag, i1, min(i2, i1+n), j1, min(j2, j1+n)))
yield group
group = []
i1, j1 = max(i1, i2-n), max(j1, j2-n)
group.append((tag, i1, i2, j1 ,j2))
if group and not (len(group)==1 and group[0][0] == 'equal'):
yield group
def ratio(self):
"""Return a measure of the sequences' similarity (float in [0,1]).
Where T is the total number of elements in both sequences, and
M is the number of matches, this is 2.0*M / T.
Note that this is 1 if the sequences are identical, and 0 if
they have nothing in common.
.ratio() is expensive to compute if you haven't already computed
.get_matching_blocks() or .get_opcodes(), in which case you may
want to try .quick_ratio() or .real_quick_ratio() first to get an
upper bound.
>>> s = SequenceMatcher(None, "abcd", "bcde")
>>> s.ratio()
0.75
>>> s.quick_ratio()
0.75
>>> s.real_quick_ratio()
1.0
"""
matches = sum(triple[-1] for triple in self.get_matching_blocks())
return _calculate_ratio(matches, len(self.a) + len(self.b))
def quick_ratio(self):
"""Return an upper bound on ratio() relatively quickly.
This isn't defined beyond that it is an upper bound on .ratio(), and
is faster to compute.
"""
# viewing a and b as multisets, set matches to the cardinality
# of their intersection; this counts the number of matches
# without regard to order, so is clearly an upper bound
if self.fullbcount is None:
self.fullbcount = fullbcount = {}
for elt in self.b:
fullbcount[elt] = fullbcount.get(elt, 0) + 1
fullbcount = self.fullbcount
# avail[x] is the number of times x appears in 'b' less the
# number of times we've seen it in 'a' so far ... kinda
avail = {}
availhas, matches = avail.__contains__, 0
for elt in self.a:
if availhas(elt):
numb = avail[elt]
else:
numb = fullbcount.get(elt, 0)
avail[elt] = numb - 1
if numb > 0:
matches = matches + 1
return _calculate_ratio(matches, len(self.a) + len(self.b))
def real_quick_ratio(self):
"""Return an upper bound on ratio() very quickly.
This isn't defined beyond that it is an upper bound on .ratio(), and
is faster to compute than either .ratio() or .quick_ratio().
"""
la, lb = len(self.a), len(self.b)
# can't have more matches than the number of elements in the
# shorter sequence
return _calculate_ratio(min(la, lb), la + lb)
def get_close_matches(word, possibilities, n=3, cutoff=0.6):
"""Use SequenceMatcher to return list of the best "good enough" matches.
word is a sequence for which close matches are desired (typically a
string).
possibilities is a list of sequences against which to match word
(typically a list of strings).
Optional arg n (default 3) is the maximum number of close matches to
return. n must be > 0.
Optional arg cutoff (default 0.6) is a float in [0, 1]. Possibilities
that don't score at least that similar to word are ignored.
The best (no more than n) matches among the possibilities are returned
in a list, sorted by similarity score, most similar first.
>>> get_close_matches("appel", ["ape", "apple", "peach", "puppy"])
['apple', 'ape']
>>> import keyword as _keyword
>>> get_close_matches("wheel", _keyword.kwlist)
['while']
>>> get_close_matches("Apple", _keyword.kwlist)
[]
>>> get_close_matches("accept", _keyword.kwlist)
['except']
"""
if not n > 0:
raise ValueError("n must be > 0: %r" % (n,))
if not 0.0 <= cutoff <= 1.0:
raise ValueError("cutoff must be in [0.0, 1.0]: %r" % (cutoff,))
result = []
s = SequenceMatcher()
s.set_seq2(word)
for x in possibilities:
s.set_seq1(x)
if s.real_quick_ratio() >= cutoff and \
s.quick_ratio() >= cutoff and \
s.ratio() >= cutoff:
result.append((s.ratio(), x))
# Move the best scorers to head of list
result = heapq.nlargest(n, result)
# Strip scores for the best n matches
return [x for score, x in result]
def _count_leading(line, ch):
"""
Return number of `ch` characters at the start of `line`.
Example:
>>> _count_leading(' abc', ' ')
3
"""
i, n = 0, len(line)
while i < n and line[i] == ch:
i += 1
return i
class Differ:
r"""
Differ is a class for comparing sequences of lines of text, and
producing human-readable differences or deltas. Differ uses
SequenceMatcher both to compare sequences of lines, and to compare
sequences of characters within similar (near-matching) lines.
Each line of a Differ delta begins with a two-letter code:
'- ' line unique to sequence 1
'+ ' line unique to sequence 2
' ' line common to both sequences
'? ' line not present in either input sequence
Lines beginning with '? ' attempt to guide the eye to intraline
differences, and were not present in either input sequence. These lines
can be confusing if the sequences contain tab characters.
Note that Differ makes no claim to produce a *minimal* diff. To the
contrary, minimal diffs are often counter-intuitive, because they synch
up anywhere possible, sometimes accidental matches 100 pages apart.
Restricting synch points to contiguous matches preserves some notion of
locality, at the occasional cost of producing a longer diff.
Example: Comparing two texts.
First we set up the texts, sequences of individual single-line strings
ending with newlines (such sequences can also be obtained from the
`readlines()` method of file-like objects):
>>> text1 = ''' 1. Beautiful is better than ugly.
... 2. Explicit is better than implicit.
... 3. Simple is better than complex.
... 4. Complex is better than complicated.
... '''.splitlines(1)
>>> len(text1)
4
>>> text1[0][-1]
'\n'
>>> text2 = ''' 1. Beautiful is better than ugly.
... 3. Simple is better than complex.
... 4. Complicated is better than complex.
... 5. Flat is better than nested.
... '''.splitlines(1)
Next we instantiate a Differ object:
>>> d = Differ()
Note that when instantiating a Differ object we may pass functions to
filter out line and character 'junk'. See Differ.__init__ for details.
Finally, we compare the two:
>>> result = list(d.compare(text1, text2))
'result' is a list of strings, so let's pretty-print it:
>>> from pprint import pprint as _pprint
>>> _pprint(result)
[' 1. Beautiful is better than ugly.\n',
'- 2. Explicit is better than implicit.\n',
'- 3. Simple is better than complex.\n',
'+ 3. Simple is better than complex.\n',
'? ++\n',
'- 4. Complex is better than complicated.\n',
'? ^ ---- ^\n',
'+ 4. Complicated is better than complex.\n',
'? ++++ ^ ^\n',
'+ 5. Flat is better than nested.\n']
As a single multi-line string it looks like this:
>>> print(''.join(result), end="")
1. Beautiful is better than ugly.
- 2. Explicit is better than implicit.
- 3. Simple is better than complex.
+ 3. Simple is better than complex.
? ++
- 4. Complex is better than complicated.
? ^ ---- ^
+ 4. Complicated is better than complex.
? ++++ ^ ^
+ 5. Flat is better than nested.
Methods:
__init__(linejunk=None, charjunk=None)
Construct a text differencer, with optional filters.
compare(a, b)
Compare two sequences of lines; generate the resulting delta.
"""
def __init__(self, linejunk=None, charjunk=None):
"""
Construct a text differencer, with optional filters.
The two optional keyword parameters are for filter functions:
- `linejunk`: A function that should accept a single string argument,
and return true iff the string is junk. The module-level function
`IS_LINE_JUNK` may be used to filter out lines without visible
characters, except for at most one splat ('#'). It is recommended
to leave linejunk None; as of Python 2.3, the underlying
SequenceMatcher class has grown an adaptive notion of "noise" lines
that's better than any static definition the author has ever been
able to craft.
- `charjunk`: A function that should accept a string of length 1. The
module-level function `IS_CHARACTER_JUNK` may be used to filter out
whitespace characters (a blank or tab; **note**: bad idea to include
newline in this!). Use of IS_CHARACTER_JUNK is recommended.
"""
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.
Example:
>>> print(''.join(Differ().compare('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))),
... end="")
- one
? ^
+ ore
? ^
- two
- three
? -
+ tree
+ emu
"""
cruncher = SequenceMatcher(self.linejunk, a, b)
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 %r' % (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 range(lo, hi):
yield '%s %s' % (tag, x[i])
def _plain_replace(self, a, alo, ahi, b, blo, bhi):
assert alo < ahi and blo < bhi
# dump the shorter block first -- reduces the burden on short-term
# 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):
r"""
When replacing one block of lines with another, search the blocks
for *similar* lines; the best-matching pair (if any) is used as a
synch point, and intraline difference marking is done on the
similar pair. Lots of work, but often worth it.
Example:
>>> d = Differ()
>>> results = d._fancy_replace(['abcDefghiJkl\n'], 0, 1,
... ['abcdefGhijkl\n'], 0, 1)
>>> print(''.join(results), end="")
- abcDefghiJkl
? ^ ^ ^
+ abcdefGhijkl
? ^ ^ ^
"""
# 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(self.charjunk)
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 range(blo, bhi):
bj = b[j]
cruncher.set_seq2(bj)
for i in range(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
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
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
# 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
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 += '^' * la
btags += '^' * lb
elif tag == 'delete':
atags += '-' * la
elif tag == 'insert':
btags += '+' * lb
elif tag == 'equal':
atags += ' ' * la
btags += ' ' * lb
else:
raise ValueError('unknown tag %r' % (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"""
Format "?" output and deal with leading tabs.
Example:
>>> d = Differ()
>>> results = d._qformat('\tabcDefghiJkl\n', '\tabcdefGhijkl\n',
... ' ^ ^ ^ ', ' ^ ^ ^ ')
>>> for line in results: print(repr(line))
...
'- \tabcDefghiJkl\n'
'? \t ^ ^ ^\n'
'+ \tabcdefGhijkl\n'
'? \t ^ ^ ^\n'
"""
# Can hurt, but will probably help most of the time.
common = min(_count_leading(aline, "\t"),
_count_leading(bline, "\t"))
common = min(common, _count_leading(atags[:common], " "))
common = min(common, _count_leading(btags[:common], " "))
atags = atags[common:].rstrip()
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
# *start* a match with a junk element. The result was cases like this:
# before: private Thread currentThread;
# after: private volatile Thread currentThread;
# If you consider whitespace to be junk, the longest contiguous match
# not starting with junk is "e Thread currentThread". So ndiff reported
# that "e volatil" was inserted between the 't' and the 'e' in "private".
# While an accurate view, to people that's absurd. The current version
# looks for matching blocks that are entirely junk-free, then extends the
# longest one of those as far as possible but only with matching junk.
# So now "currentThread" is matched, then extended to suck up the
# preceding blank; then "private" is matched, and extended to suck up the
# following blank; then "Thread" is matched; and finally ndiff reports
# that "volatile " was inserted before "Thread". The only quibble
# remaining is that perhaps it was really the case that " volatile"
# was inserted after "private". I can live with that <wink>.
import re
def IS_LINE_JUNK(line, pat=re.compile(r"\s*#?\s*$").match):
r"""
Return 1 for ignorable line: iff `line` is blank or contains a single '#'.
Examples:
>>> IS_LINE_JUNK('\n')
True
>>> IS_LINE_JUNK(' # \n')
True
>>> IS_LINE_JUNK('hello\n')
False
"""
return pat(line) is not None
def IS_CHARACTER_JUNK(ch, ws=" \t"):
r"""
Return 1 for ignorable character: iff `ch` is a space or tab.
Examples:
>>> IS_CHARACTER_JUNK(' ')
True
>>> IS_CHARACTER_JUNK('\t')
True
>>> IS_CHARACTER_JUNK('\n')
False
>>> IS_CHARACTER_JUNK('x')
False
"""
return ch in ws
def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
tofiledate='', n=3, lineterm='\n'):
r"""
Compare two sequences of lines; generate the delta as a unified diff.
Unified diffs are a compact way of showing line changes and a few
lines of context. The number of context lines is set by 'n' which
defaults to three.
By default, the diff control lines (those with ---, +++, or @@) are
created with a trailing newline. This is helpful so that inputs
created from file.readlines() result in diffs that are suitable for
file.writelines() since both the inputs and outputs have trailing
newlines.
For inputs that do not have trailing newlines, set the lineterm
argument to "" so that the output will be uniformly newline free.
The unidiff format normally has a header for filenames and modification
times. Any or all of these may be specified using strings for
'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'. The modification
times are normally expressed in the format returned by time.ctime().
Example:
>>> for line in unified_diff('one two three four'.split(),
... 'zero one tree four'.split(), 'Original', 'Current',
... 'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:20:52 2003',
... lineterm=''):
... print(line)
--- Original Sat Jan 26 23:30:50 1991
+++ Current Fri Jun 06 10:20:52 2003
@@ -1,4 +1,4 @@
+zero
one
-two
-three
+tree
four
"""
started = False
for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
if not started:
yield '--- %s %s%s' % (fromfile, fromfiledate, lineterm)
yield '+++ %s %s%s' % (tofile, tofiledate, lineterm)
started = True
i1, i2, j1, j2 = group[0][1], group[-1][2], group[0][3], group[-1][4]
yield "@@ -%d,%d +%d,%d @@%s" % (i1+1, i2-i1, j1+1, j2-j1, lineterm)
for tag, i1, i2, j1, j2 in group:
if tag == 'equal':
for line in a[i1:i2]:
yield ' ' + line
continue
if tag == 'replace' or tag == 'delete':
for line in a[i1:i2]:
yield '-' + line
if tag == 'replace' or tag == 'insert':
for line in b[j1:j2]:
yield '+' + line
# See http://www.unix.org/single_unix_specification/
def context_diff(a, b, fromfile='', tofile='',
fromfiledate='', tofiledate='', n=3, lineterm='\n'):
r"""
Compare two sequences of lines; generate the delta as a context diff.
Context diffs are a compact way of showing line changes and a few
lines of context. The number of context lines is set by 'n' which
defaults to three.
By default, the diff control lines (those with *** or ---) are
created with a trailing newline. This is helpful so that inputs
created from file.readlines() result in diffs that are suitable for
file.writelines() since both the inputs and outputs have trailing
newlines.
For inputs that do not have trailing newlines, set the lineterm
argument to "" so that the output will be uniformly newline free.
The context diff format normally has a header for filenames and
modification times. Any or all of these may be specified using
strings for 'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'.
The modification times are normally expressed in the format returned
by time.ctime(). If not specified, the strings default to blanks.
Example:
>>> print(''.join(context_diff('one\ntwo\nthree\nfour\n'.splitlines(1),
... 'zero\none\ntree\nfour\n'.splitlines(1), 'Original', 'Current',
... 'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:22:46 2003')),
... end="")
*** Original Sat Jan 26 23:30:50 1991
--- Current Fri Jun 06 10:22:46 2003
***************
*** 1,4 ****
one
! two
! three
four
--- 1,4 ----
+ zero
one
! tree
four
"""
started = False
prefixmap = {'insert':'+ ', 'delete':'- ', 'replace':'! ', 'equal':' '}
for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n):
if not started:
yield '*** %s %s%s' % (fromfile, fromfiledate, lineterm)
yield '--- %s %s%s' % (tofile, tofiledate, lineterm)
started = True
yield '***************%s' % (lineterm,)
if group[-1][2] - group[0][1] >= 2:
yield '*** %d,%d ****%s' % (group[0][1]+1, group[-1][2], lineterm)
else:
yield '*** %d ****%s' % (group[-1][2], lineterm)
visiblechanges = [e for e in group if e[0] in ('replace', 'delete')]
if visiblechanges:
for tag, i1, i2, _, _ in group:
if tag != 'insert':
for line in a[i1:i2]:
yield prefixmap[tag] + line
if group[-1][4] - group[0][3] >= 2:
yield '--- %d,%d ----%s' % (group[0][3]+1, group[-1][4], lineterm)
else:
yield '--- %d ----%s' % (group[-1][4], lineterm)
visiblechanges = [e for e in group if e[0] in ('replace', 'insert')]
if visiblechanges:
for tag, _, _, j1, j2 in group:
if tag != 'delete':
for line in b[j1:j2]:
yield prefixmap[tag] + line
def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK):
r"""
Compare `a` and `b` (lists of strings); return a `Differ`-style delta.
Optional keyword parameters `linejunk` and `charjunk` are for filter
functions (or None):
- linejunk: A function that should accept a single string argument, and
return true iff the string is junk. The default is None, and is
recommended; as of Python 2.3, an adaptive notion of "noise" lines is
used that does a good job on its own.
- charjunk: A function that should accept a string of length 1. The
default is module-level function IS_CHARACTER_JUNK, which filters out
whitespace characters (a blank or tab; note: bad idea to include newline
in this!).
Tools/scripts/ndiff.py is a command-line front-end to this function.
Example:
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))
>>> print(''.join(diff), end="")
- one
? ^
+ ore
? ^
- two
- three
? -
+ tree
+ emu
"""
return Differ(linejunk, charjunk).compare(a, b)
def _mdiff(fromlines, tolines, context=None, linejunk=None,
charjunk=IS_CHARACTER_JUNK):
r"""Returns generator yielding marked up from/to side by side differences.
Arguments:
fromlines -- list of text lines to compared to tolines
tolines -- list of text lines to be compared to fromlines
context -- number of context lines to display on each side of difference,
if None, all from/to text lines will be generated.
linejunk -- passed on to ndiff (see ndiff documentation)
charjunk -- passed on to ndiff (see ndiff documentation)
This function returns an interator which returns a tuple:
(from line tuple, to line tuple, boolean flag)
from/to line tuple -- (line num, line text)
line num -- integer or None (to indicate a context separation)
line text -- original line text with following markers inserted:
'\0+' -- marks start of added text
'\0-' -- marks start of deleted text
'\0^' -- marks start of changed text
'\1' -- marks end of added/deleted/changed text
boolean flag -- None indicates context separation, True indicates
either "from" or "to" line contains a change, otherwise False.
This function/iterator was originally developed to generate side by side
file difference for making HTML pages (see HtmlDiff class for example
usage).
Note, this function utilizes the ndiff function to generate the side by
side difference markup. Optional ndiff arguments may be passed to this
function and they in turn will be passed to ndiff.
"""
import re
# regular expression for finding intraline change indices
change_re = re.compile('(\++|\-+|\^+)')
# create the difference iterator to generate the differences
diff_lines_iterator = ndiff(fromlines,tolines,linejunk,charjunk)
def _make_line(lines, format_key, side, num_lines=[0,0]):
"""Returns line of text with user's change markup and line formatting.
lines -- list of lines from the ndiff generator to produce a line of
text from. When producing the line of text to return, the
lines used are removed from this list.
format_key -- '+' return first line in list with "add" markup around
the entire line.
'-' return first line in list with "delete" markup around
the entire line.
'?' return first line in list with add/delete/change
intraline markup (indices obtained from second line)
None return first line in list with no markup
side -- indice into the num_lines list (0=from,1=to)
num_lines -- from/to current line number. This is NOT intended to be a
passed parameter. It is present as a keyword argument to
maintain memory of the current line numbers between calls
of this function.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
num_lines[side] += 1
# Handle case where no user markup is to be added, just return line of
# text with user's line format to allow for usage of the line number.
if format_key is None:
return (num_lines[side],lines.pop(0)[2:])
# Handle case of intraline changes
if format_key == '?':
text, markers = lines.pop(0), lines.pop(0)
# find intraline changes (store change type and indices in tuples)
sub_info = []
def record_sub_info(match_object,sub_info=sub_info):
sub_info.append([match_object.group(1)[0],match_object.span()])
return match_object.group(1)
change_re.sub(record_sub_info,markers)
# process each tuple inserting our special marks that won't be
# noticed by an xml/html escaper.
for key,(begin,end) in sub_info[::-1]:
text = text[0:begin]+'\0'+key+text[begin:end]+'\1'+text[end:]
text = text[2:]
# Handle case of add/delete entire line
else:
text = lines.pop(0)[2:]
# if line of text is just a newline, insert a space so there is
# something for the user to highlight and see.
if not text:
text = ' '
# insert marks that won't be noticed by an xml/html escaper.
text = '\0' + format_key + text + '\1'
# Return line of text, first allow user's line formatter to do its
# thing (such as adding the line number) then replace the special
# marks with what the user's change markup.
return (num_lines[side],text)
def _line_iterator():
"""Yields from/to lines of text with a change indication.
This function is an iterator. It itself pulls lines from a
differencing iterator, processes them and yields them. When it can
it yields both a "from" and a "to" line, otherwise it will yield one
or the other. In addition to yielding the lines of from/to text, a
boolean flag is yielded to indicate if the text line(s) have
differences in them.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
lines = []
num_blanks_pending, num_blanks_to_yield = 0, 0
while True:
# Load up next 4 lines so we can look ahead, create strings which
# are a concatenation of the first character of each of the 4 lines
# so we can do some very readable comparisons.
while len(lines) < 4:
try:
lines.append(next(diff_lines_iterator))
except StopIteration:
lines.append('X')
s = ''.join([line[0] for line in lines])
if s.startswith('X'):
# When no more lines, pump out any remaining blank lines so the
# corresponding add/delete lines get a matching blank line so
# all line pairs get yielded at the next level.
num_blanks_to_yield = num_blanks_pending
elif s.startswith('-?+?'):
# simple intraline change
yield _make_line(lines,'?',0), _make_line(lines,'?',1), True
continue
elif s.startswith('--++'):
# in delete block, add block coming: we do NOT want to get
# caught up on blank lines yet, just process the delete line
num_blanks_pending -= 1
yield _make_line(lines,'-',0), None, True
continue
elif s.startswith(('--?+', '--+', '- ')):
# in delete block and see a intraline change or unchanged line
# coming: yield the delete line and then blanks
from_line,to_line = _make_line(lines,'-',0), None
num_blanks_to_yield,num_blanks_pending = num_blanks_pending-1,0
elif s.startswith('-+?'):
# intraline change
yield _make_line(lines,None,0), _make_line(lines,'?',1), True
continue
elif s.startswith('-?+'):
# intraline change
yield _make_line(lines,'?',0), _make_line(lines,None,1), True
continue
elif s.startswith('-'):
# delete FROM line
num_blanks_pending -= 1
yield _make_line(lines,'-',0), None, True
continue
elif s.startswith('+--'):
# in add block, delete block coming: we do NOT want to get
# caught up on blank lines yet, just process the add line
num_blanks_pending += 1
yield None, _make_line(lines,'+',1), True
continue
elif s.startswith(('+ ', '+-')):
# will be leaving an add block: yield blanks then add line
from_line, to_line = None, _make_line(lines,'+',1)
num_blanks_to_yield,num_blanks_pending = num_blanks_pending+1,0
elif s.startswith('+'):
# inside an add block, yield the add line
num_blanks_pending += 1
yield None, _make_line(lines,'+',1), True
continue
elif s.startswith(' '):
# unchanged text, yield it to both sides
yield _make_line(lines[:],None,0),_make_line(lines,None,1),False
continue
# Catch up on the blank lines so when we yield the next from/to
# pair, they are lined up.
while(num_blanks_to_yield < 0):
num_blanks_to_yield += 1
yield None,('','\n'),True
while(num_blanks_to_yield > 0):
num_blanks_to_yield -= 1
yield ('','\n'),None,True
if s.startswith('X'):
raise StopIteration
else:
yield from_line,to_line,True
def _line_pair_iterator():
"""Yields from/to lines of text with a change indication.
This function is an iterator. It itself pulls lines from the line
iterator. Its difference from that iterator is that this function
always yields a pair of from/to text lines (with the change
indication). If necessary it will collect single from/to lines
until it has a matching pair from/to pair to yield.
Note, this function is purposefully not defined at the module scope so
that data it needs from its parent function (within whose context it
is defined) does not need to be of module scope.
"""
line_iterator = _line_iterator()
fromlines,tolines=[],[]
while True:
# Collecting lines of text until we have a from/to pair
while (len(fromlines)==0 or len(tolines)==0):
from_line, to_line, found_diff = next(line_iterator)
if from_line is not None:
fromlines.append((from_line,found_diff))
if to_line is not None:
tolines.append((to_line,found_diff))
# Once we have a pair, remove them from the collection and yield it
from_line, fromDiff = fromlines.pop(0)
to_line, to_diff = tolines.pop(0)
yield (from_line,to_line,fromDiff or to_diff)
# Handle case where user does not want context differencing, just yield
# them up without doing anything else with them.
line_pair_iterator = _line_pair_iterator()
if context is None:
while True:
yield next(line_pair_iterator)
# Handle case where user wants context differencing. We must do some
# storage of lines until we know for sure that they are to be yielded.
else:
context += 1
lines_to_write = 0
while True:
# Store lines up until we find a difference, note use of a
# circular queue because we only need to keep around what
# we need for context.
index, contextLines = 0, [None]*(context)
found_diff = False
while(found_diff is False):
from_line, to_line, found_diff = next(line_pair_iterator)
i = index % context
contextLines[i] = (from_line, to_line, found_diff)
index += 1
# Yield lines that we have collected so far, but first yield
# the user's separator.
if index > context:
yield None, None, None
lines_to_write = context
else:
lines_to_write = index
index = 0
while(lines_to_write):
i = index % context
index += 1
yield contextLines[i]
lines_to_write -= 1
# Now yield the context lines after the change
lines_to_write = context-1
while(lines_to_write):
from_line, to_line, found_diff = next(line_pair_iterator)
# If another change within the context, extend the context
if found_diff:
lines_to_write = context-1
else:
lines_to_write -= 1
yield from_line, to_line, found_diff
_file_template = """
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
<html>
<head>
<meta http-equiv="Content-Type"
content="text/html; charset=ISO-8859-1" />
<title></title>
<style type="text/css">%(styles)s
</style>
</head>
<body>
%(table)s%(legend)s
</body>
</html>"""
_styles = """
table.diff {font-family:Courier; border:medium;}
.diff_header {background-color:#e0e0e0}
td.diff_header {text-align:right}
.diff_next {background-color:#c0c0c0}
.diff_add {background-color:#aaffaa}
.diff_chg {background-color:#ffff77}
.diff_sub {background-color:#ffaaaa}"""
_table_template = """
<table class="diff" id="difflib_chg_%(prefix)s_top"
cellspacing="0" cellpadding="0" rules="groups" >
<colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup>
<colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup>
%(header_row)s
<tbody>
%(data_rows)s </tbody>
</table>"""
_legend = """
<table class="diff" summary="Legends">
<tr> <th colspan="2"> Legends </th> </tr>
<tr> <td> <table border="" summary="Colors">
<tr><th> Colors </th> </tr>
<tr><td class="diff_add"> Added </td></tr>
<tr><td class="diff_chg">Changed</td> </tr>
<tr><td class="diff_sub">Deleted</td> </tr>
</table></td>
<td> <table border="" summary="Links">
<tr><th colspan="2"> Links </th> </tr>
<tr><td>(f)irst change</td> </tr>
<tr><td>(n)ext change</td> </tr>
<tr><td>(t)op</td> </tr>
</table></td> </tr>
</table>"""
class HtmlDiff(object):
"""For producing HTML side by side comparison with change highlights.
This class can be used to create an HTML table (or a complete HTML file
containing the table) showing a side by side, line by line comparison
of text with inter-line and intra-line change highlights. The table can
be generated in either full or contextual difference mode.
The following methods are provided for HTML generation:
make_table -- generates HTML for a single side by side table
make_file -- generates complete HTML file with a single side by side table
See tools/scripts/diff.py for an example usage of this class.
"""
_file_template = _file_template
_styles = _styles
_table_template = _table_template
_legend = _legend
_default_prefix = 0
def __init__(self,tabsize=8,wrapcolumn=None,linejunk=None,
charjunk=IS_CHARACTER_JUNK):
"""HtmlDiff instance initializer
Arguments:
tabsize -- tab stop spacing, defaults to 8.
wrapcolumn -- column number where lines are broken and wrapped,
defaults to None where lines are not wrapped.
linejunk,charjunk -- keyword arguments passed into ndiff() (used to by
HtmlDiff() to generate the side by side HTML differences). See
ndiff() documentation for argument default values and descriptions.
"""
self._tabsize = tabsize
self._wrapcolumn = wrapcolumn
self._linejunk = linejunk
self._charjunk = charjunk
def make_file(self,fromlines,tolines,fromdesc='',todesc='',context=False,
numlines=5):
"""Returns HTML file of side by side comparison with change highlights
Arguments:
fromlines -- list of "from" lines
tolines -- list of "to" lines
fromdesc -- "from" file column header string
todesc -- "to" file column header string
context -- set to True for contextual differences (defaults to False
which shows full differences).
numlines -- number of context lines. When context is set True,
controls number of lines displayed before and after the change.
When context is False, controls the number of lines to place
the "next" link anchors before the next change (so click of
"next" link jumps to just before the change).
"""
return self._file_template % dict(
styles = self._styles,
legend = self._legend,
table = self.make_table(fromlines,tolines,fromdesc,todesc,
context=context,numlines=numlines))
def _tab_newline_replace(self,fromlines,tolines):
"""Returns from/to line lists with tabs expanded and newlines removed.
Instead of tab characters being replaced by the number of spaces
needed to fill in to the next tab stop, this function will fill
the space with tab characters. This is done so that the difference
algorithms can identify changes in a file when tabs are replaced by
spaces and vice versa. At the end of the HTML generation, the tab
characters will be replaced with a nonbreakable space.
"""
def expand_tabs(line):
# hide real spaces
line = line.replace(' ','\0')
# expand tabs into spaces
line = line.expandtabs(self._tabsize)
# relace spaces from expanded tabs back into tab characters
# (we'll replace them with markup after we do differencing)
line = line.replace(' ','\t')
return line.replace('\0',' ').rstrip('\n')
fromlines = [expand_tabs(line) for line in fromlines]
tolines = [expand_tabs(line) for line in tolines]
return fromlines,tolines
def _split_line(self,data_list,line_num,text):
"""Builds list of text lines by splitting text lines at wrap point
This function will determine if the input text line needs to be
wrapped (split) into separate lines. If so, the first wrap point
will be determined and the first line appended to the output
text line list. This function is used recursively to handle
the second part of the split line to further split it.
"""
# if blank line or context separator, just add it to the output list
if not line_num:
data_list.append((line_num,text))
return
# if line text doesn't need wrapping, just add it to the output list
size = len(text)
max = self._wrapcolumn
if (size <= max) or ((size -(text.count('\0')*3)) <= max):
data_list.append((line_num,text))
return
# scan text looking for the wrap point, keeping track if the wrap
# point is inside markers
i = 0
n = 0
mark = ''
while n < max and i < size:
if text[i] == '\0':
i += 1
mark = text[i]
i += 1
elif text[i] == '\1':
i += 1
mark = ''
else:
i += 1
n += 1
# wrap point is inside text, break it up into separate lines
line1 = text[:i]
line2 = text[i:]
# if wrap point is inside markers, place end marker at end of first
# line and start marker at beginning of second line because each
# line will have its own table tag markup around it.
if mark:
line1 = line1 + '\1'
line2 = '\0' + mark + line2
# tack on first line onto the output list
data_list.append((line_num,line1))
# use this routine again to wrap the remaining text
self._split_line(data_list,'>',line2)
def _line_wrapper(self,diffs):
"""Returns iterator that splits (wraps) mdiff text lines"""
# pull from/to data and flags from mdiff iterator
for fromdata,todata,flag in diffs:
# check for context separators and pass them through
if flag is None:
yield fromdata,todata,flag
continue
(fromline,fromtext),(toline,totext) = fromdata,todata
# for each from/to line split it at the wrap column to form
# list of text lines.
fromlist,tolist = [],[]
self._split_line(fromlist,fromline,fromtext)
self._split_line(tolist,toline,totext)
# yield from/to line in pairs inserting blank lines as
# necessary when one side has more wrapped lines
while fromlist or tolist:
if fromlist:
fromdata = fromlist.pop(0)
else:
fromdata = ('',' ')
if tolist:
todata = tolist.pop(0)
else:
todata = ('',' ')
yield fromdata,todata,flag
def _collect_lines(self,diffs):
"""Collects mdiff output into separate lists
Before storing the mdiff from/to data into a list, it is converted
into a single line of text with HTML markup.
"""
fromlist,tolist,flaglist = [],[],[]
# pull from/to data and flags from mdiff style iterator
for fromdata,todata,flag in diffs:
try:
# store HTML markup of the lines into the lists
fromlist.append(self._format_line(0,flag,*fromdata))
tolist.append(self._format_line(1,flag,*todata))
except TypeError:
# exceptions occur for lines where context separators go
fromlist.append(None)
tolist.append(None)
flaglist.append(flag)
return fromlist,tolist,flaglist
def _format_line(self,side,flag,linenum,text):
"""Returns HTML markup of "from" / "to" text lines
side -- 0 or 1 indicating "from" or "to" text
flag -- indicates if difference on line
linenum -- line number (used for line number column)
text -- line text to be marked up
"""
try:
linenum = '%d' % linenum
id = ' id="%s%s"' % (self._prefix[side],linenum)
except TypeError:
# handle blank lines where linenum is '>' or ''
id = ''
# replace those things that would get confused with HTML symbols
text=text.replace("&","&").replace(">",">").replace("<","<")
# make space non-breakable so they don't get compressed or line wrapped
text = text.replace(' ',' ').rstrip()
return '<td class="diff_header"%s>%s</td><td nowrap="nowrap">%s</td>' \
% (id,linenum,text)
def _make_prefix(self):
"""Create unique anchor prefixes"""
# Generate a unique anchor prefix so multiple tables
# can exist on the same HTML page without conflicts.
fromprefix = "from%d_" % HtmlDiff._default_prefix
toprefix = "to%d_" % HtmlDiff._default_prefix
HtmlDiff._default_prefix += 1
# store prefixes so line format method has access
self._prefix = [fromprefix,toprefix]
def _convert_flags(self,fromlist,tolist,flaglist,context,numlines):
"""Makes list of "next" links"""
# all anchor names will be generated using the unique "to" prefix
toprefix = self._prefix[1]
# process change flags, generating middle column of next anchors/links
next_id = ['']*len(flaglist)
next_href = ['']*len(flaglist)
num_chg, in_change = 0, False
last = 0
for i,flag in enumerate(flaglist):
if flag:
if not in_change:
in_change = True
last = i
# at the beginning of a change, drop an anchor a few lines
# (the context lines) before the change for the previous
# link
i = max([0,i-numlines])
next_id[i] = ' id="difflib_chg_%s_%d"' % (toprefix,num_chg)
# at the beginning of a change, drop a link to the next
# change
num_chg += 1
next_href[last] = '<a href="#difflib_chg_%s_%d">n</a>' % (
toprefix,num_chg)
else:
in_change = False
# check for cases where there is no content to avoid exceptions
if not flaglist:
flaglist = [False]
next_id = ['']
next_href = ['']
last = 0
if context:
fromlist = ['<td></td><td> No Differences Found </td>']
tolist = fromlist
else:
fromlist = tolist = ['<td></td><td> Empty File </td>']
# if not a change on first line, drop a link
if not flaglist[0]:
next_href[0] = '<a href="#difflib_chg_%s_0">f</a>' % toprefix
# redo the last link to link to the top
next_href[last] = '<a href="#difflib_chg_%s_top">t</a>' % (toprefix)
return fromlist,tolist,flaglist,next_href,next_id
def make_table(self,fromlines,tolines,fromdesc='',todesc='',context=False,
numlines=5):
"""Returns HTML table of side by side comparison with change highlights
Arguments:
fromlines -- list of "from" lines
tolines -- list of "to" lines
fromdesc -- "from" file column header string
todesc -- "to" file column header string
context -- set to True for contextual differences (defaults to False
which shows full differences).
numlines -- number of context lines. When context is set True,
controls number of lines displayed before and after the change.
When context is False, controls the number of lines to place
the "next" link anchors before the next change (so click of
"next" link jumps to just before the change).
"""
# make unique anchor prefixes so that multiple tables may exist
# on the same page without conflict.
self._make_prefix()
# change tabs to spaces before it gets more difficult after we insert
# markkup
fromlines,tolines = self._tab_newline_replace(fromlines,tolines)
# create diffs iterator which generates side by side from/to data
if context:
context_lines = numlines
else:
context_lines = None
diffs = _mdiff(fromlines,tolines,context_lines,linejunk=self._linejunk,
charjunk=self._charjunk)
# set up iterator to wrap lines that exceed desired width
if self._wrapcolumn:
diffs = self._line_wrapper(diffs)
# collect up from/to lines and flags into lists (also format the lines)
fromlist,tolist,flaglist = self._collect_lines(diffs)
# process change flags, generating middle column of next anchors/links
fromlist,tolist,flaglist,next_href,next_id = self._convert_flags(
fromlist,tolist,flaglist,context,numlines)
s = []
fmt = ' <tr><td class="diff_next"%s>%s</td>%s' + \
'<td class="diff_next">%s</td>%s</tr>\n'
for i in range(len(flaglist)):
if flaglist[i] is None:
# mdiff yields None on separator lines skip the bogus ones
# generated for the first line
if i > 0:
s.append(' </tbody> \n <tbody>\n')
else:
s.append( fmt % (next_id[i],next_href[i],fromlist[i],
next_href[i],tolist[i]))
if fromdesc or todesc:
header_row = '<thead><tr>%s%s%s%s</tr></thead>' % (
'<th class="diff_next"><br /></th>',
'<th colspan="2" class="diff_header">%s</th>' % fromdesc,
'<th class="diff_next"><br /></th>',
'<th colspan="2" class="diff_header">%s</th>' % todesc)
else:
header_row = ''
table = self._table_template % dict(
data_rows=''.join(s),
header_row=header_row,
prefix=self._prefix[1])
return table.replace('\0+','<span class="diff_add">'). \
replace('\0-','<span class="diff_sub">'). \
replace('\0^','<span class="diff_chg">'). \
replace('\1','</span>'). \
replace('\t',' ')
del re
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
lines originating from file 1 or 2 (parameter `which`), stripping off line
prefixes.
Examples:
>>> diff = ndiff('one\ntwo\nthree\n'.splitlines(1),
... 'ore\ntree\nemu\n'.splitlines(1))
>>> diff = list(diff)
>>> print(''.join(restore(diff, 1)), end="")
one
two
three
>>> print(''.join(restore(diff, 2)), end="")
ore
tree
emu
"""
try:
tag = {1: "- ", 2: "+ "}[int(which)]
except KeyError:
raise ValueError('unknown delta choice (must be 1 or 2): %r'
% which)
prefixes = (" ", tag)
for line in delta:
if line[:2] in prefixes:
yield line[2:]
def _test():
import doctest, difflib
return doctest.testmod(difflib)
if __name__ == "__main__":
_test()
|