cpython-withatomic / Lib / difflib.py

   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
#! /usr/bin/env python

from __future__ import generators

"""
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 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.

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.
"""

__all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher',
           'Differ', 'IS_CHARACTER_JUNK', 'IS_LINE_JUNK']

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 6 elements
    a[14] and b[23] match for 15 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[8:14] b[17:23]
     equal a[14:29] b[23:38]

    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
        # b2jhas
        #      b2j.has_key
        # 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 has_key method of a hidden dict.
        #      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 ...
    # 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
        self.b2j = b2j = {}
        self.b2jhas = b2jhas = b2j.has_key
        for i in xrange(len(b)):
            elt = b[i]
            if b2jhas(elt):
                b2j[elt].append(i)
            else:
                b2j[elt] = [i]

        # 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, junkdict = self.isjunk, {}
        if isjunk:
            for elt in b2j.keys():
                if isjunk(elt):
                    junkdict[elt] = 1   # value irrelevant; it's a set
                    del b2j[elt]

        # Now for x in b, isjunk(x) == junkdict.has_key(x), 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.has_key

    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)
        (0, 4, 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)
        (1, 0, 4)

        If no blocks match, return (alo, blo, 0).

        >>> s = SequenceMatcher(None, "ab", "c")
        >>> s.find_longest_match(0, 2, 0, 1)
        (0, 0, 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 xrange(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

        # 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 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.

        The last triple is a dummy, (len(a), len(b), 0), and is the only
        triple with n==0.

        >>> s = SequenceMatcher(None, "abxcd", "abcd")
        >>> s.get_matching_blocks()
        [(0, 0, 2), (3, 2, 2), (5, 4, 0)]
        """

        if self.matching_blocks is not None:
            return self.matching_blocks
        self.matching_blocks = []
        la, lb = len(self.a), len(self.b)
        self.__helper(0, la, 0, lb, self.matching_blocks)
        self.matching_blocks.append( (la, lb, 0) )
        return self.matching_blocks

    # builds list of matching blocks covering a[alo:ahi] and
    # b[blo:bhi], appending them in increasing order to answer

    def __helper(self, alo, ahi, blo, bhi, answer):
        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 alo < i and blo < j:
                self.__helper(alo, i, blo, j, answer)
            answer.append(x)
            if i+k < ahi and j+k < bhi:
                self.__helper(i+k, ahi, j+k, bhi, answer)

    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 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 = reduce(lambda sum, triple: sum + triple[-1],
                         self.get_matching_blocks(), 0)
        return 2.0 * 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.has_key, 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 2.0 * 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 2.0 * 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: " + `n`)
    if not 0.0 <= cutoff <= 1.0:
        raise ValueError("cutoff must be in [0.0, 1.0]: " + `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))
    # Sort by score.
    result.sort()
    # Retain only the best n.
    result = result[-n:]
    # Move best-scorer to head of list.
    result.reverse()
    # Strip scores.
    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),
        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 ('#').

        - `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!).
        """

        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))),
        - 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 ' + `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):
        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()
        >>> d._fancy_replace(['abcDefghiJkl\n'], 0, 1, ['abcdefGhijkl\n'], 0, 1)
        >>> print ''.join(d.results),
        - 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 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
                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 ' + `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()
        >>> d._qformat('\tabcDefghiJkl\n', '\t\tabcdefGhijkl\n',
        ...            '  ^ ^  ^      ', '+  ^ ^  ^      ')
        >>> for line in d.results: print repr(line)
        ...
        '- \tabcDefghiJkl\n'
        '? \t ^ ^  ^\n'
        '+ \t\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], " "))
        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')
    1
    >>> IS_LINE_JUNK('  #   \n')
    1
    >>> IS_LINE_JUNK('hello\n')
    0
    """

    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(' ')
    1
    >>> IS_CHARACTER_JUNK('\t')
    1
    >>> IS_CHARACTER_JUNK('\n')
    0
    >>> IS_CHARACTER_JUNK('x')
    0
    """

    return ch in ws

del re

def ndiff(a, b, linejunk=IS_LINE_JUNK, 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 module-level function
      IS_LINE_JUNK, which filters out lines without visible characters, except
      for at most one splat ('#').

    - 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),
    - one
    ?  ^
    + ore
    ?  ^
    - two
    - three
    ?  -
    + tree
    + emu
    """
    return Differ(linejunk, charjunk).compare(a, b)

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)),
    one
    two
    three
    >>> print ''.join(restore(diff, 2)),
    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()
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.