#! /usr/bin/env python# Backported to Python 1.5.2 for the ViewCVS project by pf@artcom-gmbh.de# 24-Dec-2001, original version "stolen" from Python-2.1.1"""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.    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    >>> get_close_matches("wheel", keyword.kwlist)    ['while']    >>> get_close_matches("apple", keyword.kwlist)    []    >>> get_close_matches("accept", keyword.kwlist)    ['except']Class SequenceMatcherSequenceMatcher is a flexible class for comparing pairs of sequences of anytype, so long as the sequence elements are hashable.  The basic algorithmpredates, and is a little fancier than, an algorithm published in the late1980's by Ratcliff and Obershelp under the hyperbolic name "gestalt patternmatching".  The basic idea is to find the longest contiguous matchingsubsequence that contains no "junk" elements (R-O doesn't address junk).The same idea is then applied recursively to the pieces of the sequences tothe left and to the right of the matching subsequence.  This does not yieldminimal edit sequences, but does tend to yield matches that "look right"to people.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 thesequences.  As a rule of thumb, a .ratio() value over 0.6 means thesequences 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" % blocka[0] and b[0] match for 8 elementsa[8] and b[17] match for 6 elementsa[14] and b[23] match for 15 elementsa[29] and b[38] match for 0 elementsNote that the last tuple returned by .get_matching_blocks() is always adummy, (len(a), len(b), 0), and this is the only case in which the lasttuple 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 Tools/scripts/ndiff.py for a fancy human-friendly file differencer,which uses SequenceMatcher both to view files as sequences of lines, andlines as sequences of characters.See also function get_close_matches() in this module, which shows howsimple code building on SequenceMatcher can be used to do useful work.Timing:  Basic R-O is cubic time worst case and quadratic time expectedcase.  SequenceMatcher is quadratic time for the worst case and hasexpected-case behavior dependent in a complicated way on how manyelements the sequences have in common; best case time is linear.SequenceMatcher methods:__init__(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.    Optional arg b is the second of two sequences to be compared.  By    default, an empty string.  The elements of b must be hashable.set_seqs(a, b)    Set the two sequences to be compared.    >>> s = SequenceMatcher()    >>> s.set_seqs("abcd", "bcde")    >>> s.ratio()    0.75set_seq1(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().set_seq2(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().find_longest_match(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)get_matching_blocks()    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)]get_opcodes()    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)ratio()    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()    1.0quick_ratio()    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.real_quick_ratio():    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()."""TRACE = 0class SequenceMatcher:    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")