I was able to figure out something very close to what I wanted to do. It's slower than regular diff, though. Here's the entire code, from my project GitGate.
def unified_diff(to_file_path, from_file_path, context=1):
""" Returns a list of differences between two files based
on some context. This is probably over-complicated. """
pat_diff = re.compile(r'@@ (.[0-9]+\,[0-9]+) (.[0-9]+,[0-9]+) @@')
from_lines = []
if os.path.exists(from_file_path):
from_fh = open(from_file_path,'r')
from_lines = from_fh.readlines()
from_fh.close()
to_lines = []
if os.path.exists(to_file_path):
to_fh = open(to_file_path,'r')
to_lines = to_fh.readlines()
to_fh.close()
diff_lines = []
lines = difflib.unified_diff(to_lines, from_lines, n=context)
for line in lines:
if line.startswith('--') or line.startswith('++'):
continue
m = pat_diff.match(line)
if m:
left = m.group(1)
right = m.group(2)
lstart = left.split(',')[0][1:]
rstart = right.split(',')[0][1:]
diff_lines.append("@@ %s %s @@\n"%(left, right))
to_lnum = int(lstart)
from_lnum = int(rstart)
continue
code = line[0]
lnum = from_lnum
if code == '-':
lnum = to_lnum
diff_lines.append("%s%.4d: %s"%(code, lnum, line[1:]))
if code == '-':
to_lnum += 1
elif code == '+':
from_lnum += 1
else:
to_lnum += 1
from_lnum += 1
return diff_lines