1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
|
#!/usr/bin/python2.2
"""HTML Diff: http://www.aaronsw.com/2002/diff
Rough code, badly documented. Send me comments and patches."""
__author__ = 'Aaron Swartz <me@aaronsw.com>'
__copyright__ = '(C) 2003 Aaron Swartz. GNU GPL 2.'
__version__ = '0.22'
import difflib, string
def isTag(x): return x[0] == "<" and x[-1] == ">"
def textDiff(a, b):
"""Takes in strings a and b and returns a human-readable HTML diff."""
out = []
a, b = html2list(a), html2list(b)
s = difflib.SequenceMatcher(None, a, b)
for e in s.get_opcodes():
if e[0] == "replace":
# @@ need to do something more complicated here
# call textDiff but not for html, but for some html... ugh
# gonna cop-out for now
out.append('<del>'+''.join(a[e[1]:e[2]]) + '</del><ins>'+''.join(b[e[3]:e[4]])+"</ins>")
elif e[0] == "delete":
out.append('<del >'+ ''.join(a[e[1]:e[2]]) + "</del>")
elif e[0] == "insert":
out.append('<ins >'+''.join(b[e[3]:e[4]]) + "</ins>")
elif e[0] == "equal":
out.append(''.join(b[e[3]:e[4]]))
else:
raise "Um, something's broken. I didn't expect a '" + `e[0]` + "'."
return ''.join(out)
def html2list(x, b=0):
mode = 'char'
cur = ''
out = []
for c in x:
if mode == 'tag':
if c == '>':
if b: cur += ']'
else: cur += c
out.append(cur); cur = ''; mode = 'char'
else: cur += c
elif mode == 'char':
if c == '<':
out.append(cur)
if b: cur = '['
else: cur = c
mode = 'tag'
elif c in string.whitespace: out.append(cur+c); cur = ''
else: cur += c
out.append(cur)
return filter(lambda x: x is not '', out)
if __name__ == '__main__':
import sys
try:
a, b = sys.argv[1:3]
except ValueError:
print "htmldiff: highlight the differences between two html files"
print "usage: " + sys.argv[0] + " a b"
sys.exit(1)
print textDiff(open(a).read(), open(b).read())
|
