Mercurial > cpython-lru_cache-weakref
annotate Tools/scripts/ndiff.py @ 8831:00a6bb65ff29 legacy-trunk
Getting rid of this ancient stuff.
| author | Guido van Rossum <guido@python.org> |
|---|---|
| date | Wed, 05 Aug 1998 21:10:09 +0000 |
| parents | 32bc17f7c77b |
| children | 30c94cd49a68 |
| rev | line source |
|---|---|
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
1 #! /usr/bin/env python |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
2 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
3 # Released to the public domain $JustDate: 3/16/98 $, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
4 # by Tim Peters (email tim_one@email.msn.com). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
5 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
6 # ndiff file1 file2 -- a human-friendly file differencer. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
7 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
8 # $Revision$ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
9 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
10 # SequenceMatcher tries to compute a "human-friendly diff" between |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
11 # two sequences (chiefly picturing a file as a sequence of lines, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
12 # and a line as a sequence of characters, here). Unlike UNIX(tm) diff, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
13 # e.g., the fundamental notion is the longest *contiguous* & junk-free |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
14 # matching subsequence. That's what catches peoples' eyes. The |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
15 # Windows(tm) windiff has another interesting notion, pairing up elements |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
16 # that appear uniquely in each sequence. That, and the method here, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
17 # appear to yield more intuitive difference reports than does diff. This |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
18 # method appears to be the least vulnerable to synching up on blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
19 # of "junk lines", though (like blank lines in ordinary text files, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
20 # or maybe "<P>" lines in HTML files). That may be because this is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
21 # the only method of the 3 that has a *concept* of "junk" <wink>. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
22 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
23 # Note that ndiff makes no claim to produce a *minimal* diff. To the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
24 # contrary, minimal diffs are often counter-intuitive, because they |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
25 # synch up anywhere possible, sometimes accidental matches 100 pages |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
26 # apart. Restricting synch points to contiguous matches preserves some |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
27 # notion of locality, at the occasional cost of producing a longer diff. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
28 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
29 # With respect to junk, an earlier verion of ndiff simply refused to |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
30 # *start* a match with a junk element. The result was cases like this: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
31 # before: private Thread currentThread; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
32 # after: private volatile Thread currentThread; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
33 # If you consider whitespace to be junk, the longest continguous match |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
34 # not starting with junk is "e Thread currentThread". So ndiff reported |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
35 # that "e volatil" was inserted between the 't' and the 'e' in "private". |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
36 # While an accurate view, to people that's absurd. The current version |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
37 # looks for matching blocks that are entirely junk-free, then extends the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
38 # longest one of those as far as possible but only with matching junk. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
39 # So now "currentThread" is matched, then extended to suck up the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
40 # preceding blank; then "private" is matched, and extended to suck up the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
41 # following blank; then "Thread" is matched; and finally ndiff reports |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
42 # that "volatile " was inserted before "Thread". The only quibble |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
43 # remaining is that perhaps it was really the case that " volative" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
44 # was inserted after "private". I can live with that <wink>. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
45 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
46 # NOTE on the output: From an ndiff report, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
47 # 1) The first file can be recovered by retaining only lines that begin |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
48 # with " " or "- ", and deleting those 2-character prefixes. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
49 # 2) The second file can be recovered similarly, but by retaining only |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
50 # " " and "+ " lines. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
51 # 3) Lines beginning with "? " attempt to guide the eye to intraline |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
52 # differences, and were not present in either input file. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
53 # |
|
8285
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
54 # COROLLARY: |
|
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
55 # On Unix, the second file can be recovered by piping the output through |
|
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
56 # sed -n '/^[+ ] /s/^..//p' |
|
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
57 # Modifications to recover the first file are left as an exercise for |
|
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
58 # the reader. |
|
32bc17f7c77b
Add the specific sed statement to recover the second output file to
Guido van Rossum <guido@python.org>
parents:
8228
diff
changeset
|
59 # |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
60 # NOTE on junk: the module-level names |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
61 # IS_LINE_JUNK |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
62 # IS_CHARACTER_JUNK |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
63 # can be set to any functions you like. The first one should accept |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
64 # a single string argument, and return true iff the string is junk. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
65 # The default is whether the regexp r"\s*#?\s*$" matches (i.e., a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
66 # line without visible characters, except for at most one splat). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
67 # The second should accept a string of length 1 etc. The default is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
68 # whether the character is a blank or tab (note: bad idea to include |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
69 # newline in this!). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
70 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
71 # After setting those, you can call fcompare(f1name, f2name) with the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
72 # names of the files you want to compare. The difference report |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
73 # is sent to stdout. Or you can call main(), which expects to find |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
74 # (exactly) the two file names in sys.argv. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
75 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
76 import string |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
77 TRACE = 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
78 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
79 # define what "junk" means |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
80 import re |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
81 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
82 def IS_LINE_JUNK(line, pat=re.compile(r"\s*#?\s*$").match): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
83 return pat(line) is not None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
84 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
85 def IS_CHARACTER_JUNK(ch, ws=" \t"): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
86 return ch in ws |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
87 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
88 del re |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
89 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
90 class SequenceMatcher: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
91 def __init__(self, isjunk=None, a='', b=''): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
92 # Members: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
93 # a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
94 # first sequence |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
95 # b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
96 # second sequence; differences are computed as "what do |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
97 # we need to do to 'a' to change it into 'b'?" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
98 # b2j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
99 # for x in b, b2j[x] is a list of the indices (into b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
100 # at which x appears; junk elements do not appear |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
101 # b2jhas |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
102 # b2j.has_key |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
103 # fullbcount |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
104 # for x in b, fullbcount[x] == the number of times x |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
105 # appears in b; only materialized if really needed (used |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
106 # only for computing quick_ratio()) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
107 # matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
108 # a list of (i, j, k) triples, where a[i:i+k] == b[j:j+k]; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
109 # ascending & non-overlapping in i and in j; terminated by |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
110 # a dummy (len(a), len(b), 0) sentinel |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
111 # opcodes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
112 # a list of (tag, i1, i2, j1, j2) tuples, where tag is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
113 # one of |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
114 # 'replace' a[i1:i2] should be replaced by b[j1:j2] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
115 # 'delete' a[i1:i2] should be deleted |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
116 # 'insert' b[j1:j2] should be inserted |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
117 # 'equal' a[i1:i2] == b[j1:j2] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
118 # isjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
119 # a user-supplied function taking a sequence element and |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
120 # returning true iff the element is "junk" -- this has |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
121 # subtle but helpful effects on the algorithm, which I'll |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
122 # get around to writing up someday <0.9 wink>. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
123 # DON'T USE! Only __chain_b uses this. Use isbjunk. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
124 # isbjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
125 # for x in b, isbjunk(x) == isjunk(x) but much faster; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
126 # it's really the has_key method of a hidden dict. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
127 # DOES NOT WORK for x in a! |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
128 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
129 self.isjunk = isjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
130 self.a = self.b = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
131 self.set_seqs(a, b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
132 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
133 def set_seqs(self, a, b): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
134 self.set_seq1(a) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
135 self.set_seq2(b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
136 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
137 def set_seq1(self, a): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
138 if a is self.a: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
139 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
140 self.a = a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
141 self.matching_blocks = self.opcodes = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
142 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
143 def set_seq2(self, b): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
144 if b is self.b: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
145 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
146 self.b = b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
147 self.matching_blocks = self.opcodes = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
148 self.fullbcount = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
149 self.__chain_b() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
150 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
151 # for each element x in b, set b2j[x] to a list of the indices in |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
152 # b where x appears; the indices are in increasing order; note that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
153 # the number of times x appears in b is len(b2j[x]) ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
154 # when self.isjunk is defined, junk elements don't show up in this |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
155 # map at all, which stops the central find_longest_match method |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
156 # from starting any matching block at a junk element ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
157 # also creates the fast isbjunk function ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
158 # note that this is only called when b changes; so for cross-product |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
159 # kinds of matches, it's best to call set_seq2 once, then set_seq1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
160 # repeatedly |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
161 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
162 def __chain_b(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
163 # Because isjunk is a user-defined (not C) function, and we test |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
164 # for junk a LOT, it's important to minimize the number of calls. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
165 # Before the tricks described here, __chain_b was by far the most |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
166 # time-consuming routine in the whole module! If anyone sees |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
167 # Jim Roskind, thank him again for profile.py -- I never would |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
168 # have guessed that. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
169 # The first trick is to build b2j ignoring the possibility |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
170 # of junk. I.e., we don't call isjunk at all yet. Throwing |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
171 # out the junk later is much cheaper than building b2j "right" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
172 # from the start. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
173 b = self.b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
174 self.b2j = b2j = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
175 self.b2jhas = b2jhas = b2j.has_key |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
176 for i in xrange(0, len(b)): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
177 elt = b[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
178 if b2jhas(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
179 b2j[elt].append(i) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
180 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
181 b2j[elt] = [i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
182 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
183 # Now b2j.keys() contains elements uniquely, and especially when |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
184 # the sequence is a string, that's usually a good deal smaller |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
185 # than len(string). The difference is the number of isjunk calls |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
186 # saved. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
187 isjunk, junkdict = self.isjunk, {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
188 if isjunk: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
189 for elt in b2j.keys(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
190 if isjunk(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
191 junkdict[elt] = 1 # value irrelevant; it's a set |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
192 del b2j[elt] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
193 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
194 # Now for x in b, isjunk(x) == junkdict.has_key(x), but the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
195 # latter is much faster. Note too that while there may be a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
196 # lot of junk in the sequence, the number of *unique* junk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
197 # elements is probably small. So the memory burden of keeping |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
198 # this dict alive is likely trivial compared to the size of b2j. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
199 self.isbjunk = junkdict.has_key |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
200 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
201 def find_longest_match(self, alo, ahi, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
202 """Find longest matching block in a[alo:ahi] and b[blo:bhi]. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
203 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
204 If isjunk is not defined: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
205 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
206 Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
207 alo <= i <= i+k <= ahi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
208 blo <= j <= j+k <= bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
209 and for all (i',j',k') meeting those conditions, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
210 k >= k' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
211 i <= i' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
212 and if i == i', j <= j' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
213 In other words, of all maximal matching blocks, returns one |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
214 that starts earliest in a, and of all those maximal matching |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
215 blocks that start earliest in a, returns the one that starts |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
216 earliest in b. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
217 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
218 If isjunk is defined, first the longest matching block is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
219 determined as above, but with the additional restriction that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
220 no junk element appears in the block. Then that block is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
221 extended as far as possible by matching (only) junk elements on |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
222 both sides. So the resulting block never matches on junk except |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
223 as identical junk happens to be adjacent to an "interesting" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
224 match. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
225 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
226 If no blocks match, returns (alo, blo, 0). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
227 """ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
228 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
229 # CAUTION: stripping common prefix or suffix would be incorrect. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
230 # E.g., |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
231 # ab |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
232 # acab |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
233 # Longest matching block is "ab", but if common prefix is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
234 # stripped, it's "a" (tied with "b"). UNIX(tm) diff does so |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
235 # strip, so ends up claiming that ab is changed to acab by |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
236 # inserting "ca" in the middle. That's minimal but unintuitive: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
237 # "it's obvious" that someone inserted "ac" at the front. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
238 # Windiff ends up at the same place as diff, but by pairing up |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
239 # the unique 'b's and then matching the first two 'a's. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
240 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
241 # find longest junk-free match |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
242 a, b, b2j, isbjunk = self.a, self.b, self.b2j, self.isbjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
243 besti, bestj, bestsize = alo, blo, 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
244 for i in xrange(alo, ahi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
245 # check for longest match starting at a[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
246 if i + bestsize >= ahi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
247 # we're too far right to get a new best |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
248 break |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
249 # look at all instances of a[i] in b; note that because |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
250 # b2j has no junk keys, the loop is skipped if a[i] is junk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
251 for j in b2j.get(a[i], []): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
252 # a[i] matches b[j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
253 if j < blo: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
254 continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
255 if j + bestsize >= bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
256 # we're too far right to get a new best, here or |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
257 # anywhere to the right |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
258 break |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
259 if a[i + bestsize] != b[j + bestsize]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
260 # can't be longer match; this test is not necessary |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
261 # for correctness, but is a huge win for efficiency |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
262 continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
263 # set k to length of match |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
264 k = 1 # a[i] == b[j] already known |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
265 while i + k < ahi and j + k < bhi and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
266 a[i+k] == b[j+k] and not isbjunk(b[j+k]): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
267 k = k + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
268 if k > bestsize: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
269 besti, bestj, bestsize = i, j, k |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
270 if i + bestsize >= ahi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
271 # only time in my life I really wanted a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
272 # labelled break <wink> -- we're done with |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
273 # both loops now |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
274 break |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
275 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
276 # Now that we have a wholly interesting match (albeit possibly |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
277 # empty!), we may as well suck up the matching junk on each |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
278 # side of it too. Can't think of a good reason not to, and it |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
279 # saves post-processing the (possibly considerable) expense of |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
280 # figuring out what to do with it. In the case of an empty |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
281 # interesting match, this is clearly the right thing to do, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
282 # because no other kind of match is possible in the regions. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
283 while besti > alo and bestj > blo and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
284 isbjunk(b[bestj-1]) and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
285 a[besti-1] == b[bestj-1]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
286 besti, bestj, bestsize = besti-1, bestj-1, bestsize+1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
287 while besti+bestsize < ahi and bestj+bestsize < bhi and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
288 isbjunk(b[bestj+bestsize]) and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
289 a[besti+bestsize] == b[bestj+bestsize]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
290 bestsize = bestsize + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
291 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
292 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
293 print "get_matching_blocks", alo, ahi, blo, bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
294 print " returns", besti, bestj, bestsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
295 return besti, bestj, bestsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
296 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
297 # A different implementation, using a binary doubling technique that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
298 # does far fewer element compares (trades 'em for integer compares), |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
299 # and has n*lg n worst-case behavior. Alas, the code is much harder |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
300 # to follow (the details are tricky!), and in most cases I've seen, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
301 # it takes at least 50% longer than the "clever dumb" method above; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
302 # probably due to creating layers of small dicts. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
303 # NOTE: this no longer matches the version above wrt junk; remains |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
304 # too unpromising to update it; someday, though ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
305 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
306 # def find_longest_match(self, alo, ahi, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
307 # """Find longest matching block in a[alo:ahi] and b[blo:bhi]. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
308 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
309 # Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
310 # alo <= i <= i+k <= ahi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
311 # blo <= j <= j+k <= bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
312 # and for all (i',j',k') meeting those conditions, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
313 # k >= k' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
314 # i <= i' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
315 # and if i == i', j <= j' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
316 # In other words, of all maximal matching blocks, returns one |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
317 # that starts earliest in a, and of all those maximal matching |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
318 # blocks that start earliest in a, returns the one that starts |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
319 # earliest in b. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
320 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
321 # If no blocks match, returns (alo, blo, 0). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
322 # """ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
323 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
324 # a, b2j = self.a, self.b2j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
325 # # alljs[size][i] is a set of all j's s.t. a[i:i+len] matches |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
326 # # b[j:j+len] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
327 # alljs = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
328 # alljs[1] = js = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
329 # ahits = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
330 # for i in xrange(alo, ahi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
331 # elt = a[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
332 # if ahits.has_key(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
333 # js[i] = ahits[elt] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
334 # continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
335 # if b2j.has_key(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
336 # in_range = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
337 # for j in b2j[elt]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
338 # if j >= blo: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
339 # if j >= bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
340 # break |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
341 # in_range[j] = 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
342 # if in_range: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
343 # ahits[elt] = js[i] = in_range |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
344 # del ahits |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
345 # size = 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
346 # while js: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
347 # oldsize = size |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
348 # size = size + size |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
349 # oldjs = js |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
350 # alljs[size] = js = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
351 # for i in oldjs.keys(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
352 # # i has matches of size oldsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
353 # if not oldjs.has_key(i + oldsize): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
354 # # can't double it |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
355 # continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
356 # second_js = oldjs[i + oldsize] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
357 # answer = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
358 # for j in oldjs[i].keys(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
359 # if second_js.has_key(j + oldsize): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
360 # answer[j] = 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
361 # if answer: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
362 # js[i] = answer |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
363 # del alljs[size] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
364 # size = size >> 1 # max power of 2 with a match |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
365 # if not size: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
366 # return alo, blo, 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
367 # besti, bestj, bestsize = alo, blo, 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
368 # fatis = alljs[size].keys() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
369 # fatis.sort() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
370 # for i in fatis: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
371 # # figure out longest match starting at a[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
372 # totalsize = halfsize = size |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
373 # # i has matches of len totalsize at the indices in js |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
374 # js = alljs[size][i].keys() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
375 # while halfsize > 1: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
376 # halfsize = halfsize >> 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
377 # # is there a match of len halfsize starting at |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
378 # # i + totalsize? |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
379 # newjs = [] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
380 # if alljs[halfsize].has_key(i + totalsize): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
381 # second_js = alljs[halfsize][i + totalsize] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
382 # for j in js: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
383 # if second_js.has_key(j + totalsize): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
384 # newjs.append(j) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
385 # if newjs: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
386 # totalsize = totalsize + halfsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
387 # js = newjs |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
388 # if totalsize > bestsize: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
389 # besti, bestj, bestsize = i, min(js), totalsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
390 # return besti, bestj, bestsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
391 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
392 def get_matching_blocks(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
393 if self.matching_blocks is not None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
394 return self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
395 self.matching_blocks = [] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
396 la, lb = len(self.a), len(self.b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
397 self.__helper(0, la, 0, lb, self.matching_blocks) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
398 self.matching_blocks.append( (la, lb, 0) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
399 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
400 print '*** matching blocks', self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
401 return self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
402 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
403 # builds list of matching blocks covering a[alo:ahi] and |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
404 # b[blo:bhi], appending them in increasing order to answer |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
405 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
406 def __helper(self, alo, ahi, blo, bhi, answer): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
407 i, j, k = x = self.find_longest_match(alo, ahi, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
408 # a[alo:i] vs b[blo:j] unknown |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
409 # a[i:i+k] same as b[j:j+k] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
410 # a[i+k:ahi] vs b[j+k:bhi] unknown |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
411 if k: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
412 if alo < i and blo < j: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
413 self.__helper(alo, i, blo, j, answer) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
414 answer.append( x ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
415 if i+k < ahi and j+k < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
416 self.__helper(i+k, ahi, j+k, bhi, answer) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
417 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
418 def ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
419 """Return a measure of the sequences' similarity (float in [0,1]). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
420 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
421 Where T is the total number of elements in both sequences, and |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
422 M is the number of matches, this is 2*M / T. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
423 Note that this is 1 if the sequences are identical, and 0 if |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
424 they have nothing in common. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
425 """ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
426 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
427 matches = reduce(lambda sum, triple: sum + triple[-1], |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
428 self.get_matching_blocks(), 0) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
429 return 2.0 * matches / (len(self.a) + len(self.b)) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
430 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
431 def quick_ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
432 """Return an upper bound on ratio() relatively quickly.""" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
433 # viewing a and b as multisets, set matches to the cardinality |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
434 # of their intersection; this counts the number of matches |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
435 # without regard to order, so is clearly an upper bound |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
436 if self.fullbcount is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
437 self.fullbcount = fullbcount = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
438 for elt in self.b: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
439 fullbcount[elt] = fullbcount.get(elt, 0) + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
440 fullbcount = self.fullbcount |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
441 # avail[x] is the number of times x appears in 'b' less the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
442 # number of times we've seen it in 'a' so far ... kinda |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
443 avail = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
444 availhas, matches = avail.has_key, 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
445 for elt in self.a: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
446 if availhas(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
447 numb = avail[elt] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
448 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
449 numb = fullbcount.get(elt, 0) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
450 avail[elt] = numb - 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
451 if numb > 0: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
452 matches = matches + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
453 return 2.0 * matches / (len(self.a) + len(self.b)) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
454 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
455 def real_quick_ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
456 """Return an upper bound on ratio() very quickly""" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
457 la, lb = len(self.a), len(self.b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
458 # can't have more matches than the number of elements in the |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
459 # shorter sequence |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
460 return 2.0 * min(la, lb) / (la + lb) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
461 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
462 def get_opcodes(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
463 if self.opcodes is not None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
464 return self.opcodes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
465 i = j = 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
466 self.opcodes = answer = [] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
467 for ai, bj, size in self.get_matching_blocks(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
468 # invariant: we've pumped out correct diffs to change |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
469 # a[:i] into b[:j], and the next matching block is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
470 # a[ai:ai+size] == b[bj:bj+size]. So we need to pump |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
471 # out a diff to change a[i:ai] into b[j:bj], pump out |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
472 # the matching block, and move (i,j) beyond the match |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
473 tag = '' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
474 if i < ai and j < bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
475 tag = 'replace' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
476 elif i < ai: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
477 tag = 'delete' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
478 elif j < bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
479 tag = 'insert' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
480 if tag: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
481 answer.append( (tag, i, ai, j, bj) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
482 i, j = ai+size, bj+size |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
483 # the list of matching blocks is terminated by a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
484 # sentinel with size 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
485 if size: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
486 answer.append( ('equal', ai, i, bj, j) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
487 return answer |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
488 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
489 # meant for dumping lines |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
490 def dump(tag, x, lo, hi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
491 for i in xrange(lo, hi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
492 print tag, x[i], |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
493 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
494 # figure out which mark to stick under characters in lines that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
495 # have changed (blank = same, - = deleted, + = inserted, ^ = replaced) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
496 _combine = { ' ': ' ', |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
497 '. ': '-', |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
498 ' .': '+', |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
499 '..': '^' } |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
500 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
501 def plain_replace(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
502 assert alo < ahi and blo < bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
503 # dump the shorter block first -- reduces the burden on short-term |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
504 # memory if the blocks are of very different sizes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
505 if bhi - blo < ahi - alo: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
506 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
507 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
508 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
509 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
510 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
511 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
512 # When replacing one block of lines with another, this guy searches |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
513 # the blocks for *similar* lines; the best-matching pair (if any) is |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
514 # used as a synch point, and intraline difference marking is done on |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
515 # the similar pair. Lots of work, but often worth it. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
516 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
517 def fancy_replace(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
518 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
519 print '*** fancy_replace', alo, ahi, blo, bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
520 dump('>', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
521 dump('<', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
522 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
523 # don't synch up unless the lines have a similarity score of at |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
524 # least cutoff; best_ratio tracks the best score seen so far |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
525 best_ratio, cutoff = 0.74, 0.75 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
526 cruncher = SequenceMatcher(IS_CHARACTER_JUNK) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
527 eqi, eqj = None, None # 1st indices of equal lines (if any) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
528 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
529 # search for the pair that matches best without being identical |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
530 # (identical lines must be junk lines, & we don't want to synch up |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
531 # on junk -- unless we have to) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
532 for j in xrange(blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
533 bj = b[j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
534 cruncher.set_seq2(bj) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
535 for i in xrange(alo, ahi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
536 ai = a[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
537 if ai == bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
538 if eqi is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
539 eqi, eqj = i, j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
540 continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
541 cruncher.set_seq1(ai) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
542 # computing similarity is expensive, so use the quick |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
543 # upper bounds first -- have seen this speed up messy |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
544 # compares by a factor of 3. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
545 # note that ratio() is only expensive to compute the first |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
546 # time it's called on a sequence pair; the expensive part |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
547 # of the computation is cached by cruncher |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
548 if cruncher.real_quick_ratio() > best_ratio and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
549 cruncher.quick_ratio() > best_ratio and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
550 cruncher.ratio() > best_ratio: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
551 best_ratio, best_i, best_j = cruncher.ratio(), i, j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
552 if best_ratio < cutoff: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
553 # no non-identical "pretty close" pair |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
554 if eqi is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
555 # no identical pair either -- treat it as a straight replace |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
556 plain_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
557 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
558 # no close pair, but an identical pair -- synch up on that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
559 best_i, best_j, best_ratio = eqi, eqj, 1.0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
560 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
561 # there's a close pair, so forget the identical pair (if any) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
562 eqi = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
563 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
564 # a[best_i] very similar to b[best_j]; eqi is None iff they're not |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
565 # identical |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
566 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
567 print '*** best_ratio', best_ratio, best_i, best_j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
568 dump('>', a, best_i, best_i+1) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
569 dump('<', b, best_j, best_j+1) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
570 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
571 # pump out diffs from before the synch point |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
572 fancy_helper(a, alo, best_i, b, blo, best_j) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
573 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
574 # do intraline marking on the synch pair |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
575 aelt, belt = a[best_i], b[best_j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
576 if eqi is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
577 # pump out a '-', '+', '?' triple for the synched lines; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
578 atags = btags = "" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
579 cruncher.set_seqs(aelt, belt) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
580 for tag, ai1, ai2, bj1, bj2 in cruncher.get_opcodes(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
581 la, lb = ai2 - ai1, bj2 - bj1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
582 if tag == 'replace': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
583 atags = atags + '.' * la |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
584 btags = btags + '.' * lb |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
585 elif tag == 'delete': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
586 atags = atags + '.' * la |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
587 elif tag == 'insert': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
588 btags = btags + '.' * lb |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
589 elif tag == 'equal': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
590 atags = atags + ' ' * la |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
591 btags = btags + ' ' * lb |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
592 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
593 raise ValueError, 'unknown tag ' + `tag` |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
594 la, lb = len(atags), len(btags) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
595 if la < lb: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
596 atags = atags + ' ' * (lb - la) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
597 elif lb < la: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
598 btags = btags + ' ' * (la - lb) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
599 combined = map(lambda x,y: _combine[x+y], atags, btags) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
600 print '-', aelt, '+', belt, '?', \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
601 string.rstrip(string.join(combined, '')) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
602 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
603 # the synch pair is identical |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
604 print ' ', aelt, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
605 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
606 # pump out diffs from after the synch point |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
607 fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
608 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
609 def fancy_helper(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
610 if alo < ahi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
611 if blo < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
612 fancy_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
613 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
614 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
615 elif blo < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
616 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
617 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
618 # open a file & return the file object; gripe and return 0 if it |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
619 # couldn't be opened |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
620 def fopen(fname): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
621 try: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
622 return open(fname, 'r') |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
623 except IOError, detail: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
624 print "couldn't open " + fname + ": " + `detail` |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
625 return 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
626 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
627 # open two files & spray the diff to stdout; return false iff a problem |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
628 def fcompare(f1name, f2name): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
629 f1 = fopen(f1name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
630 f2 = fopen(f2name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
631 if not f1 or not f2: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
632 return 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
633 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
634 a = f1.readlines(); f1.close() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
635 b = f2.readlines(); f2.close() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
636 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
637 cruncher = SequenceMatcher(IS_LINE_JUNK, a, b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
638 for tag, alo, ahi, blo, bhi in cruncher.get_opcodes(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
639 if tag == 'replace': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
640 fancy_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
641 elif tag == 'delete': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
642 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
643 elif tag == 'insert': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
644 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
645 elif tag == 'equal': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
646 dump(' ', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
647 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
648 raise ValueError, 'unknown tag ' + `tag` |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
649 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
650 return 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
651 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
652 # get file names from argv & compare; return false iff a problem |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
653 def main(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
654 from sys import argv |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
655 if len(argv) != 3: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
656 print 'need 2 args' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
657 return 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
658 [f1name, f2name] = argv[1:3] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
659 print '-:', f1name |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
660 print '+:', f2name |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
661 return fcompare(f1name, f2name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
662 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
663 if __name__ == '__main__': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
664 if 1: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
665 main() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
666 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
667 import profile, pstats |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
668 statf = "ndiff.pro" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
669 profile.run("main()", statf) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
670 stats = pstats.Stats(statf) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
671 stats.strip_dirs().sort_stats('time').print_stats() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
672 |
