annotate Tools/scripts/ndiff.py @ 17322:bd110eadc19a legacy-trunk

One-liner critical fix from Jim Fulton: Eric's string-method crusade got the order backwards in a line (for .find()).
author Tim Peters <tim.peters@gmail.com>
date Thu, 05 Apr 2001 22:26:23 +0000
parents 7de5043827f7
children 50fb4683a461
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
6
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
7 # Provided as-is; use at your own risk; no warranty; no promises; enjoy!
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
8
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
9 """ndiff [-q] file1 file2
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
10 or
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
11 ndiff (-r1 | -r2) < ndiff_output > file1_or_file2
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
12
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
13 Print a human-friendly file difference report to stdout. Both inter-
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
14 and intra-line differences are noted. In the second form, recreate file1
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
15 (-r1) or file2 (-r2) on stdout, from an ndiff report on stdin.
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
16
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
17 In the first form, if -q ("quiet") is not specified, the first two lines
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
18 of output are
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
19
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
20 -: file1
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
21 +: file2
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
22
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
25 "- " line unique to file1
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
26 "+ " line unique to file2
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
27 " " line common to both files
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
28 "? " line not present in either input file
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
29
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
33
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
34 The first file can be recovered by retaining only lines that begin with
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
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
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
39 recovered by piping the output through
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
40
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
41 sed -n '/^[+ ] /s/^..//p'
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
42
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
43 See module comments for details and programmatic interface.
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
44 """
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
50 # and a line as a sequence of characters, here). Unlike e.g. UNIX(tm)
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
97 # is sent to stdout. Or you can call main(args), passing what would
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
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
16551
7de5043827f7 Moved SequenceMatcher from ndiff into new std library module difflib.py.
Tim Peters <tim.peters@gmail.com>
parents: 15497
diff changeset
100 from difflib import SequenceMatcher
7de5043827f7 Moved SequenceMatcher from ndiff into new std library module difflib.py.
Tim Peters <tim.peters@gmail.com>
parents: 15497
diff changeset
101
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
102 import string
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
103 TRACE = 0
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
104
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
105 # define what "junk" means
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
106 import re
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
107
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
108 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
109 return pat(line) is not None
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
110
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
111 def IS_CHARACTER_JUNK(ch, ws=" \t"):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
112 return ch in ws
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 del re
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
115
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
116 # meant for dumping lines
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
117 def dump(tag, x, lo, hi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
118 for i in xrange(lo, hi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
119 print tag, x[i],
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
120
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
121 def plain_replace(a, alo, ahi, b, blo, bhi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
122 assert alo < ahi and blo < bhi
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
123 # 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
124 # memory if the blocks are of very different sizes
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
125 if bhi - blo < ahi - alo:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
126 dump('+', b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
127 dump('-', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
128 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
129 dump('-', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
130 dump('+', b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
131
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
132 # 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
133 # 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
134 # 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
135 # 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
136
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
137 def fancy_replace(a, alo, ahi, b, blo, bhi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
138 if TRACE:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
139 print '*** fancy_replace', alo, ahi, blo, bhi
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
140 dump('>', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
141 dump('<', b, blo, bhi)
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 # 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
144 # 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
145 best_ratio, cutoff = 0.74, 0.75
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
146 cruncher = SequenceMatcher(IS_CHARACTER_JUNK)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
147 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
148
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
149 # 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
150 # (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
151 # on junk -- unless we have to)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
152 for j in xrange(blo, bhi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
153 bj = b[j]
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
154 cruncher.set_seq2(bj)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
155 for i in xrange(alo, ahi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
156 ai = a[i]
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
157 if ai == bj:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
158 if eqi is None:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
159 eqi, eqj = i, j
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
160 continue
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
161 cruncher.set_seq1(ai)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
162 # computing similarity is expensive, so use the quick
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
163 # upper bounds first -- have seen this speed up messy
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
164 # compares by a factor of 3.
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
165 # 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
166 # 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
167 # of the computation is cached by cruncher
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
168 if cruncher.real_quick_ratio() > best_ratio and \
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
169 cruncher.quick_ratio() > best_ratio and \
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
170 cruncher.ratio() > best_ratio:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
171 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
172 if best_ratio < cutoff:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
173 # no non-identical "pretty close" pair
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
174 if eqi is None:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
175 # 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
176 plain_replace(a, alo, ahi, b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
177 return
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
178 # 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
179 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
180 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
181 # 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
182 eqi = None
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
183
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
184 # 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
185 # identical
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
186 if TRACE:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
187 print '*** best_ratio', best_ratio, best_i, best_j
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
188 dump('>', a, best_i, best_i+1)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
189 dump('<', b, best_j, best_j+1)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
190
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
191 # pump out diffs from before the synch point
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
192 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
193
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
194 # do intraline marking on the synch pair
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
195 aelt, belt = a[best_i], b[best_j]
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
196 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
197 # pump out a '-', '?', '+', '?' quad for the synched lines
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
198 atags = btags = ""
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
199 cruncher.set_seqs(aelt, belt)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
200 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
201 la, lb = ai2 - ai1, bj2 - bj1
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
202 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
203 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
204 btags += '^' * lb
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
205 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
206 atags += '-' * la
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
207 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
208 btags += '+' * lb
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
209 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
210 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
211 btags += ' ' * lb
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
212 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
213 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
214 printq(aelt, belt, atags, btags)
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
215 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
216 # the synch pair is identical
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
217 print ' ', aelt,
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
218
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
219 # pump out diffs from after the synch point
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
220 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
221
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
222 def fancy_helper(a, alo, ahi, b, blo, bhi):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
223 if alo < ahi:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
224 if blo < bhi:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
225 fancy_replace(a, alo, ahi, b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
226 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
227 dump('-', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
228 elif blo < bhi:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
229 dump('+', b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
230
15367
8275d8643e79 Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents: 10487
diff changeset
231 # 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
232 # 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
233
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
234 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
235 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
236 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
237 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
238 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
239 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
240 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
241 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
242 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
243 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
244
8275d8643e79 Hack ndiff to display lines w/ leading tabs more intuitively. This synchs
Tim Peters <tim.peters@gmail.com>
parents: 10487
diff changeset
245 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
246 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
247 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
248 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
249 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
250
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
251 def fail(msg):
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
252 import sys
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
253 out = sys.stderr.write
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
254 out(msg + "\n\n")
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
255 out(__doc__)
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
256 return 0
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
257
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
258 # 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
259 # couldn't be opened
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
260 def fopen(fname):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
261 try:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
262 return open(fname, 'r')
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
263 except IOError, detail:
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
264 return fail("couldn't open " + fname + ": " + str(detail))
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
265
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
266 # 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
267 def fcompare(f1name, f2name):
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
268 f1 = fopen(f1name)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
269 f2 = fopen(f2name)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
270 if not f1 or not f2:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
271 return 0
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
272
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
273 a = f1.readlines(); f1.close()
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
274 b = f2.readlines(); f2.close()
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 cruncher = SequenceMatcher(IS_LINE_JUNK, a, b)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
277 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
278 if tag == 'replace':
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
279 fancy_replace(a, alo, ahi, b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
280 elif tag == 'delete':
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
281 dump('-', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
282 elif tag == 'insert':
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
283 dump('+', b, blo, bhi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
284 elif tag == 'equal':
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
285 dump(' ', a, alo, ahi)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
286 else:
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
287 raise ValueError, 'unknown tag ' + `tag`
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
288
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
289 return 1
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
290
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
291 # crack args (sys.argv[1:] is normal) & compare;
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
292 # return false iff a problem
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
293
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
294 def main(args):
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
295 import getopt
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
296 try:
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
297 opts, args = getopt.getopt(args, "qr:")
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
298 except getopt.error, detail:
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
299 return fail(str(detail))
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
300 noisy = 1
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
301 qseen = rseen = 0
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
302 for opt, val in opts:
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
303 if opt == "-q":
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
304 qseen = 1
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
305 noisy = 0
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
306 elif opt == "-r":
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
307 rseen = 1
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
308 whichfile = val
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
309 if qseen and rseen:
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
310 return fail("can't specify both -q and -r")
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
311 if rseen:
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
312 if args:
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
313 return fail("no args allowed with -r option")
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
314 if whichfile in "12":
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
315 restore(whichfile)
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
316 return 1
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
317 return fail("-r value must be 1 or 2")
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
318 if len(args) != 2:
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
319 return fail("need 2 filename args")
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
320 f1name, f2name = args
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
321 if noisy:
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
322 print '-:', f1name
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
323 print '+:', f2name
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
324 return fcompare(f1name, f2name)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
325
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
326 def restore(which):
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
327 import sys
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
328 tag = {"1": "- ", "2": "+ "}[which]
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
329 prefixes = (" ", tag)
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
330 for line in sys.stdin.readlines():
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
331 if line[:2] in prefixes:
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
332 print line[2:],
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
333
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
334 if __name__ == '__main__':
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
335 import sys
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
336 args = sys.argv[1:]
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
337 if "-profile" in args:
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
338 import profile, pstats
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
339 args.remove("-profile")
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
340 statf = "ndiff.pro"
10486
30c94cd49a68 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 8285
diff changeset
341 profile.run("main(args)", statf)
8228
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
342 stats = pstats.Stats(statf)
9d642a735a13 Adding Tim Peters' ndiff utility.
Guido van Rossum <guido@python.org>
parents:
diff changeset
343 stats.strip_dirs().sort_stats('time').print_stats()
10487
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
344 else:
05e97f6a3638 Tim Peters writes:
Guido van Rossum <guido@python.org>
parents: 10486
diff changeset
345 main(args)