├── README.md
└── diff.py


/README.md:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/aaronsw/htmldiff/f3c99f794a7f83f8e1645d4e58a89948a1939e65/README.md


--------------------------------------------------------------------------------
/diff.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/python
 2 | """HTML Diff: http://www.aaronsw.com/2002/diff
 3 | Rough code, badly documented. Send me comments and patches."""
 4 | 
 5 | __author__ = 'Aaron Swartz <me@aaronsw.com>'
 6 | __copyright__ = '(C) 2003 Aaron Swartz. GNU GPL 2 or 3.'
 7 | __version__ = '0.22'
 8 | 
 9 | import difflib, string
10 | 
11 | def isTag(x): return x[0] == "<" and x[-1] == ">"
12 | 
13 | def textDiff(a, b):
14 | 	"""Takes in strings a and b and returns a human-readable HTML diff."""
15 | 
16 | 	out = []
17 | 	a, b = html2list(a), html2list(b)
18 | 	try: # autojunk can cause malformed HTML, but also speeds up processing.
19 | 		s = difflib.SequenceMatcher(None, a, b, autojunk=False)
20 | 	except TypeError:
21 | 		s = difflib.SequenceMatcher(None, a, b)
22 | 	for e in s.get_opcodes():
23 | 		if e[0] == "replace":
24 | 			# @@ need to do something more complicated here
25 | 			# call textDiff but not for html, but for some html... ugh
26 | 			# gonna cop-out for now
27 | 			out.append('<del class="diff modified">'+''.join(a[e[1]:e[2]]) + '</del><ins class="diff modified">'+''.join(b[e[3]:e[4]])+"</ins>")
28 | 		elif e[0] == "delete":
29 | 			out.append('<del class="diff">'+ ''.join(a[e[1]:e[2]]) + "</del>")
30 | 		elif e[0] == "insert":
31 | 			out.append('<ins class="diff">'+''.join(b[e[3]:e[4]]) + "</ins>")
32 | 		elif e[0] == "equal":
33 | 			out.append(''.join(b[e[3]:e[4]]))
34 | 		else: 
35 | 			raise "Um, something's broken. I didn't expect a '" + `e[0]` + "'."
36 | 	return ''.join(out)
37 | 
38 | def html2list(x, b=0):
39 | 	mode = 'char'
40 | 	cur = ''
41 | 	out = []
42 | 	for c in x:
43 | 		if mode == 'tag':
44 | 			if c == '>': 
45 | 				if b: cur += ']'
46 | 				else: cur += c
47 | 				out.append(cur); cur = ''; mode = 'char'
48 | 			else: cur += c
49 | 		elif mode == 'char':
50 | 			if c == '<': 
51 | 				out.append(cur)
52 | 				if b: cur = '['
53 | 				else: cur = c
54 | 				mode = 'tag'
55 | 			elif c in string.whitespace: out.append(cur+c); cur = ''
56 | 			else: cur += c
57 | 	out.append(cur)
58 | 	return filter(lambda x: x is not '', out)
59 | 
60 | if __name__ == '__main__':
61 | 	import sys
62 | 	try:
63 | 		a, b = sys.argv[1:3]
64 | 	except ValueError:
65 | 		print "htmldiff: highlight the differences between two html files"
66 | 		print "usage: " + sys.argv[0] + " a b"
67 | 		sys.exit(1)
68 | 	print textDiff(open(a).read(), open(b).read())
69 | 	
70 | 


--------------------------------------------------------------------------------