Mercurial > cpython-lru_cache-weakref
annotate Tools/scripts/ndiff.py @ 16413:8819867f14ef legacy-trunk
Patch derived from Trent's 101162: a Python/C API testing framework.
STILL NEEDS UNIX BUILD CHANGES.
| author | Tim Peters <tim.peters@gmail.com> |
|---|---|
| date | Fri, 02 Feb 2001 05:57:15 +0000 |
| parents | f3bf5f082a3f |
| children | 7de5043827f7 |
| 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 |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
3 # Module ndiff version 1.6.0 |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
4 # Released to the public domain 08-Dec-2000, |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
5 # by Tim Peters (tim.one@home.com). |
| 10486 | 6 |
| 7 # Provided as-is; use at your own risk; no warranty; no promises; enjoy! | |
| 8 | |
| 9 """ndiff [-q] file1 file2 | |
| 10487 | 10 or |
| 11 ndiff (-r1 | -r2) < ndiff_output > file1_or_file2 | |
| 10486 | 12 |
| 13 Print a human-friendly file difference report to stdout. Both inter- | |
| 10487 | 14 and intra-line differences are noted. In the second form, recreate file1 |
| 15 (-r1) or file2 (-r2) on stdout, from an ndiff report on stdin. | |
| 10486 | 16 |
| 10487 | 17 In the first form, if -q ("quiet") is not specified, the first two lines |
| 18 of output are | |
| 10486 | 19 |
| 20 -: file1 | |
| 21 +: file2 | |
| 22 | |
| 23 Each remaining line begins with a two-letter code: | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
24 |
| 10486 | 25 "- " line unique to file1 |
| 26 "+ " line unique to file2 | |
| 27 " " line common to both files | |
| 28 "? " line not present in either input file | |
| 29 | |
| 30 Lines beginning with "? " attempt to guide the eye to intraline | |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
31 differences, and were not present in either input file. These lines can be |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
32 confusing if the source files contain tab characters. |
| 10486 | 33 |
| 34 The first file can be recovered by retaining only lines that begin with | |
| 10487 | 35 " " or "- ", and deleting those 2-character prefixes; use ndiff with -r1. |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
36 |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
37 The second file can be recovered similarly, but by retaining only " " and |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
38 "+ " lines; use ndiff with -r2; or, on Unix, the second file can be |
| 10487 | 39 recovered by piping the output through |
| 40 | |
| 10486 | 41 sed -n '/^[+ ] /s/^..//p' |
| 42 | |
| 43 See module comments for details and programmatic interface. | |
| 44 """ | |
| 45 | |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
46 __version__ = 1, 5, 0 |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
47 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
48 # SequenceMatcher tries to compute a "human-friendly diff" between |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
49 # two sequences (chiefly picturing a file as a sequence of lines, |
| 10486 | 50 # and a line as a sequence of characters, here). Unlike e.g. UNIX(tm) |
| 51 # diff, the fundamental notion is the longest *contiguous* & junk-free | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
52 # matching subsequence. That's what catches peoples' eyes. The |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
53 # 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
|
54 # 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
|
55 # 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
|
56 # 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
|
57 # 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
|
58 # 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
|
59 # 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
|
60 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
61 # 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
|
62 # contrary, minimal diffs are often counter-intuitive, because they |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
63 # synch up anywhere possible, sometimes accidental matches 100 pages |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
64 # apart. Restricting synch points to contiguous matches preserves some |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
65 # 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
|
66 # |
| 10486 | 67 # With respect to junk, an earlier version of ndiff simply refused to |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
68 # *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
|
69 # before: private Thread currentThread; |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
70 # after: private volatile Thread currentThread; |
| 10486 | 71 # If you consider whitespace to be junk, the longest contiguous match |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
72 # 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
|
73 # 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
|
74 # 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
|
75 # 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
|
76 # 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
|
77 # 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
|
78 # 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
|
79 # 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
|
80 # that "volatile " was inserted before "Thread". The only quibble |
| 10486 | 81 # remaining is that perhaps it was really the case that " volatile" |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
82 # 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
|
83 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
84 # NOTE on junk: the module-level names |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
85 # IS_LINE_JUNK |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
86 # IS_CHARACTER_JUNK |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
87 # 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
|
88 # 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
|
89 # 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
|
90 # 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
|
91 # 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
|
92 # 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
|
93 # newline in this!). |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
94 # |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
95 # 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
|
96 # names of the files you want to compare. The difference report |
| 10486 | 97 # is sent to stdout. Or you can call main(args), passing what would |
| 98 # have been in sys.argv[1:] had the cmd-line form been used. | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
99 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
100 import string |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
101 TRACE = 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
102 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
103 # define what "junk" means |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
104 import re |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
105 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
106 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
|
107 return pat(line) is not None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
108 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
109 def IS_CHARACTER_JUNK(ch, ws=" \t"): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
110 return ch in ws |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
111 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
112 del re |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
113 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
114 class SequenceMatcher: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
115 def __init__(self, isjunk=None, a='', b=''): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
116 # Members: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
117 # a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
118 # first sequence |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
119 # b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
120 # second sequence; differences are computed as "what do |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
121 # 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
|
122 # b2j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
123 # 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
|
124 # at which x appears; junk elements do not appear |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
125 # b2jhas |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
126 # b2j.has_key |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
127 # fullbcount |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
128 # 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
|
129 # appears in b; only materialized if really needed (used |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
130 # only for computing quick_ratio()) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
131 # matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
132 # 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
|
133 # 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
|
134 # a dummy (len(a), len(b), 0) sentinel |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
135 # opcodes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
136 # 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
|
137 # one of |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
138 # '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
|
139 # 'delete' a[i1:i2] should be deleted |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
140 # 'insert' b[j1:j2] should be inserted |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
141 # 'equal' a[i1:i2] == b[j1:j2] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
142 # isjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
143 # a user-supplied function taking a sequence element and |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
144 # returning true iff the element is "junk" -- this has |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
145 # 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
|
146 # get around to writing up someday <0.9 wink>. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
147 # 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
|
148 # isbjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
149 # 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
|
150 # 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
|
151 # DOES NOT WORK for x in a! |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
152 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
153 self.isjunk = isjunk |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
154 self.a = self.b = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
155 self.set_seqs(a, b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
156 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
157 def set_seqs(self, a, b): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
158 self.set_seq1(a) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
159 self.set_seq2(b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
160 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
161 def set_seq1(self, a): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
162 if a is self.a: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
163 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
164 self.a = a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
165 self.matching_blocks = self.opcodes = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
166 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
167 def set_seq2(self, b): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
168 if b is self.b: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
169 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
170 self.b = b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
171 self.matching_blocks = self.opcodes = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
172 self.fullbcount = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
173 self.__chain_b() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
174 |
| 10486 | 175 # For each element x in b, set b2j[x] to a list of the indices in |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
176 # 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
|
177 # 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
|
178 # 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
|
179 # 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
|
180 # from starting any matching block at a junk element ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
181 # also creates the fast isbjunk function ... |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
182 # 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
|
183 # 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
|
184 # repeatedly |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
185 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
186 def __chain_b(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
187 # 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
|
188 # 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
|
189 # 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
|
190 # 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
|
191 # 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
|
192 # have guessed that. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
193 # 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
|
194 # 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
|
195 # 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
|
196 # from the start. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
197 b = self.b |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
198 self.b2j = b2j = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
199 self.b2jhas = b2jhas = b2j.has_key |
| 10486 | 200 for i in xrange(len(b)): |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
201 elt = b[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
202 if b2jhas(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
203 b2j[elt].append(i) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
204 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
205 b2j[elt] = [i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
206 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
207 # Now b2j.keys() contains elements uniquely, and especially when |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
208 # 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
|
209 # 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
|
210 # saved. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
211 isjunk, junkdict = self.isjunk, {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
212 if isjunk: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
213 for elt in b2j.keys(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
214 if isjunk(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
215 junkdict[elt] = 1 # value irrelevant; it's a set |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
216 del b2j[elt] |
|
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 # 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
|
219 # 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
|
220 # 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
|
221 # 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
|
222 # 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
|
223 self.isbjunk = junkdict.has_key |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
224 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
225 def find_longest_match(self, alo, ahi, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
226 """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
|
227 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
228 If isjunk is not defined: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
229 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
230 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
|
231 alo <= i <= i+k <= ahi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
232 blo <= j <= j+k <= bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
233 and for all (i',j',k') meeting those conditions, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
234 k >= k' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
235 i <= i' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
236 and if i == i', j <= j' |
| 10486 | 237 In other words, of all maximal matching blocks, return one |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
238 that starts earliest in a, and of all those maximal matching |
| 10486 | 239 blocks that start earliest in a, return the one that starts |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
240 earliest in b. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
241 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
242 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
|
243 determined as above, but with the additional restriction that |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
244 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
|
245 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
|
246 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
|
247 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
|
248 match. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
249 |
| 10486 | 250 If no blocks match, return (alo, blo, 0). |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
251 """ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
252 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
253 # CAUTION: stripping common prefix or suffix would be incorrect. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
254 # E.g., |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
255 # ab |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
256 # acab |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
257 # 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
|
258 # 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
|
259 # 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
|
260 # 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
|
261 # "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
|
262 # 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
|
263 # 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
|
264 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
265 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
|
266 besti, bestj, bestsize = alo, blo, 0 |
| 10486 | 267 # find longest junk-free match |
| 268 # during an iteration of the loop, j2len[j] = length of longest | |
| 269 # junk-free match ending with a[i-1] and b[j] | |
| 270 j2len = {} | |
| 271 nothing = [] | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
272 for i in xrange(alo, ahi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
273 # 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
|
274 # b2j has no junk keys, the loop is skipped if a[i] is junk |
| 10486 | 275 j2lenget = j2len.get |
| 276 newj2len = {} | |
| 277 for j in b2j.get(a[i], nothing): | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
278 # a[i] matches b[j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
279 if j < blo: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
280 continue |
| 10486 | 281 if j >= bhi: |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
282 break |
| 10486 | 283 k = newj2len[j] = j2lenget(j-1, 0) + 1 |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
284 if k > bestsize: |
| 10486 | 285 besti, bestj, bestsize = i-k+1, j-k+1, k |
| 286 j2len = newj2len | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
287 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
288 # 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
|
289 # 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
|
290 # 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
|
291 # saves post-processing the (possibly considerable) expense of |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
292 # 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
|
293 # 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
|
294 # 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
|
295 while besti > alo and bestj > blo and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
296 isbjunk(b[bestj-1]) and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
297 a[besti-1] == b[bestj-1]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
298 besti, bestj, bestsize = besti-1, bestj-1, bestsize+1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
299 while besti+bestsize < ahi and bestj+bestsize < bhi and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
300 isbjunk(b[bestj+bestsize]) and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
301 a[besti+bestsize] == b[bestj+bestsize]: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
302 bestsize = bestsize + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
303 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
304 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
305 print "get_matching_blocks", alo, ahi, blo, bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
306 print " returns", besti, bestj, bestsize |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
307 return besti, bestj, bestsize |
|
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 def get_matching_blocks(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
310 if self.matching_blocks is not None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
311 return self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
312 self.matching_blocks = [] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
313 la, lb = len(self.a), len(self.b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
314 self.__helper(0, la, 0, lb, self.matching_blocks) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
315 self.matching_blocks.append( (la, lb, 0) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
316 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
317 print '*** matching blocks', self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
318 return self.matching_blocks |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
319 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
320 # 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
|
321 # 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
|
322 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
323 def __helper(self, alo, ahi, blo, bhi, answer): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
324 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
|
325 # a[alo:i] vs b[blo:j] unknown |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
326 # 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
|
327 # 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
|
328 if k: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
329 if alo < i and blo < j: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
330 self.__helper(alo, i, blo, j, answer) |
| 10487 | 331 answer.append(x) |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
332 if i+k < ahi and j+k < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
333 self.__helper(i+k, ahi, j+k, bhi, answer) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
334 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
335 def ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
336 """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
|
337 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
338 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
|
339 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
|
340 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
|
341 they have nothing in common. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
342 """ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
343 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
344 matches = reduce(lambda sum, triple: sum + triple[-1], |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
345 self.get_matching_blocks(), 0) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
346 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
|
347 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
348 def quick_ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
349 """Return an upper bound on ratio() relatively quickly.""" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
350 # 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
|
351 # of their intersection; this counts the number of matches |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
352 # 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
|
353 if self.fullbcount is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
354 self.fullbcount = fullbcount = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
355 for elt in self.b: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
356 fullbcount[elt] = fullbcount.get(elt, 0) + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
357 fullbcount = self.fullbcount |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
358 # 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
|
359 # 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
|
360 avail = {} |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
361 availhas, matches = avail.has_key, 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
362 for elt in self.a: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
363 if availhas(elt): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
364 numb = avail[elt] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
365 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
366 numb = fullbcount.get(elt, 0) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
367 avail[elt] = numb - 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
368 if numb > 0: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
369 matches = matches + 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
370 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
|
371 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
372 def real_quick_ratio(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
373 """Return an upper bound on ratio() very quickly""" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
374 la, lb = len(self.a), len(self.b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
375 # 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
|
376 # shorter sequence |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
377 return 2.0 * min(la, lb) / (la + lb) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
378 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
379 def get_opcodes(self): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
380 if self.opcodes is not None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
381 return self.opcodes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
382 i = j = 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
383 self.opcodes = answer = [] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
384 for ai, bj, size in self.get_matching_blocks(): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
385 # invariant: we've pumped out correct diffs to change |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
386 # 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
|
387 # 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
|
388 # 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
|
389 # 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
|
390 tag = '' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
391 if i < ai and j < bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
392 tag = 'replace' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
393 elif i < ai: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
394 tag = 'delete' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
395 elif j < bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
396 tag = 'insert' |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
397 if tag: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
398 answer.append( (tag, i, ai, j, bj) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
399 i, j = ai+size, bj+size |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
400 # the list of matching blocks is terminated by a |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
401 # sentinel with size 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
402 if size: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
403 answer.append( ('equal', ai, i, bj, j) ) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
404 return 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 # meant for dumping lines |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
407 def dump(tag, x, lo, hi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
408 for i in xrange(lo, hi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
409 print tag, x[i], |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
410 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
411 def plain_replace(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
412 assert alo < ahi and blo < bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
413 # 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
|
414 # memory if the blocks are of very different sizes |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
415 if bhi - blo < ahi - alo: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
416 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
417 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
418 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
419 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
420 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
421 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
422 # 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
|
423 # 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
|
424 # 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
|
425 # 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
|
426 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
427 def fancy_replace(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
428 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
429 print '*** fancy_replace', alo, ahi, blo, bhi |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
430 dump('>', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
431 dump('<', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
432 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
433 # 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
|
434 # 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
|
435 best_ratio, cutoff = 0.74, 0.75 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
436 cruncher = SequenceMatcher(IS_CHARACTER_JUNK) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
437 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
|
438 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
439 # 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
|
440 # (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
|
441 # on junk -- unless we have to) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
442 for j in xrange(blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
443 bj = b[j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
444 cruncher.set_seq2(bj) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
445 for i in xrange(alo, ahi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
446 ai = a[i] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
447 if ai == bj: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
448 if eqi is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
449 eqi, eqj = i, j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
450 continue |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
451 cruncher.set_seq1(ai) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
452 # computing similarity is expensive, so use the quick |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
453 # upper bounds first -- have seen this speed up messy |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
454 # compares by a factor of 3. |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
455 # 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
|
456 # 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
|
457 # of the computation is cached by cruncher |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
458 if cruncher.real_quick_ratio() > best_ratio and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
459 cruncher.quick_ratio() > best_ratio and \ |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
460 cruncher.ratio() > best_ratio: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
461 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
|
462 if best_ratio < cutoff: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
463 # no non-identical "pretty close" pair |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
464 if eqi is None: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
465 # 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
|
466 plain_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
467 return |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
468 # 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
|
469 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
|
470 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
471 # 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
|
472 eqi = None |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
473 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
474 # 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
|
475 # identical |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
476 if TRACE: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
477 print '*** best_ratio', best_ratio, best_i, best_j |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
478 dump('>', a, best_i, best_i+1) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
479 dump('<', b, best_j, best_j+1) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
480 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
481 # pump out diffs from before the synch point |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
482 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
|
483 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
484 # do intraline marking on the synch pair |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
485 aelt, belt = a[best_i], b[best_j] |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
486 if eqi is None: |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
487 # pump out a '-', '?', '+', '?' quad for the synched lines |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
488 atags = btags = "" |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
489 cruncher.set_seqs(aelt, belt) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
490 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
|
491 la, lb = ai2 - ai1, bj2 - bj1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
492 if tag == 'replace': |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
493 atags += '^' * la |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
494 btags += '^' * lb |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
495 elif tag == 'delete': |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
496 atags += '-' * la |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
497 elif tag == 'insert': |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
498 btags += '+' * lb |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
499 elif tag == 'equal': |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
500 atags += ' ' * la |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
501 btags += ' ' * lb |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
502 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
503 raise ValueError, 'unknown tag ' + `tag` |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
504 printq(aelt, belt, atags, btags) |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
505 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
506 # the synch pair is identical |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
507 print ' ', aelt, |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
508 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
509 # pump out diffs from after the synch point |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
510 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
|
511 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
512 def fancy_helper(a, alo, ahi, b, blo, bhi): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
513 if alo < ahi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
514 if blo < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
515 fancy_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
516 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
517 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
518 elif blo < bhi: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
519 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
520 |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
521 # Crap to deal with leading tabs in "?" output. Can hurt, but will |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
522 # probably help most of the time. |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
523 |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
524 def printq(aline, bline, atags, btags): |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
525 common = min(count_leading(aline, "\t"), |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
526 count_leading(bline, "\t")) |
|
15497
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
527 common = min(common, count_leading(atags[:common], " ")) |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
528 print "-", aline, |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
529 if count_leading(atags, " ") < len(atags): |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
530 print "?", "\t" * common + atags[common:] |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
531 print "+", bline, |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
532 if count_leading(btags, " ") < len(btags): |
|
f3bf5f082a3f
SF bug 124051: ndiff "?" lines can be confusing. Well, they still can, but
Tim Peters <tim.peters@gmail.com>
parents:
15367
diff
changeset
|
533 print "?", "\t" * common + btags[common:] |
|
15367
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
534 |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
535 def count_leading(line, ch): |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
536 i, n = 0, len(line) |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
537 while i < n and line[i] == ch: |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
538 i += 1 |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
539 return i |
|
8275d8643e79
Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents:
10487
diff
changeset
|
540 |
| 10487 | 541 def fail(msg): |
| 542 import sys | |
| 543 out = sys.stderr.write | |
| 544 out(msg + "\n\n") | |
| 545 out(__doc__) | |
| 546 return 0 | |
| 547 | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
548 # 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
|
549 # couldn't be opened |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
550 def fopen(fname): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
551 try: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
552 return open(fname, 'r') |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
553 except IOError, detail: |
| 10487 | 554 return fail("couldn't open " + fname + ": " + str(detail)) |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
555 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
556 # 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
|
557 def fcompare(f1name, f2name): |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
558 f1 = fopen(f1name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
559 f2 = fopen(f2name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
560 if not f1 or not f2: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
561 return 0 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
562 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
563 a = f1.readlines(); f1.close() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
564 b = f2.readlines(); f2.close() |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
565 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
566 cruncher = SequenceMatcher(IS_LINE_JUNK, a, b) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
567 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
|
568 if tag == 'replace': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
569 fancy_replace(a, alo, ahi, b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
570 elif tag == 'delete': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
571 dump('-', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
572 elif tag == 'insert': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
573 dump('+', b, blo, bhi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
574 elif tag == 'equal': |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
575 dump(' ', a, alo, ahi) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
576 else: |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
577 raise ValueError, 'unknown tag ' + `tag` |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
578 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
579 return 1 |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
580 |
| 10486 | 581 # crack args (sys.argv[1:] is normal) & compare; |
| 582 # return false iff a problem | |
| 583 | |
| 584 def main(args): | |
| 585 import getopt | |
| 586 try: | |
| 10487 | 587 opts, args = getopt.getopt(args, "qr:") |
| 10486 | 588 except getopt.error, detail: |
| 10487 | 589 return fail(str(detail)) |
| 10486 | 590 noisy = 1 |
| 10487 | 591 qseen = rseen = 0 |
| 10486 | 592 for opt, val in opts: |
| 593 if opt == "-q": | |
| 10487 | 594 qseen = 1 |
| 10486 | 595 noisy = 0 |
| 10487 | 596 elif opt == "-r": |
| 597 rseen = 1 | |
| 598 whichfile = val | |
| 599 if qseen and rseen: | |
| 600 return fail("can't specify both -q and -r") | |
| 601 if rseen: | |
| 602 if args: | |
| 603 return fail("no args allowed with -r option") | |
| 604 if whichfile in "12": | |
| 605 restore(whichfile) | |
| 606 return 1 | |
| 607 return fail("-r value must be 1 or 2") | |
| 10486 | 608 if len(args) != 2: |
| 10487 | 609 return fail("need 2 filename args") |
| 10486 | 610 f1name, f2name = args |
| 611 if noisy: | |
| 612 print '-:', f1name | |
| 613 print '+:', f2name | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
614 return fcompare(f1name, f2name) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
615 |
| 10487 | 616 def restore(which): |
| 617 import sys | |
| 618 tag = {"1": "- ", "2": "+ "}[which] | |
| 619 prefixes = (" ", tag) | |
| 620 for line in sys.stdin.readlines(): | |
| 621 if line[:2] in prefixes: | |
| 622 print line[2:], | |
| 623 | |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
624 if __name__ == '__main__': |
| 10486 | 625 import sys |
| 626 args = sys.argv[1:] | |
| 10487 | 627 if "-profile" in args: |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
628 import profile, pstats |
| 10487 | 629 args.remove("-profile") |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
630 statf = "ndiff.pro" |
| 10486 | 631 profile.run("main(args)", statf) |
|
8228
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
632 stats = pstats.Stats(statf) |
|
9d642a735a13
Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff
changeset
|
633 stats.strip_dirs().sort_stats('time').print_stats() |
| 10487 | 634 else: |
| 635 main(args) |
