mdiff: reinstate new algorithm

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

mdiff: reinstate new algorithm

This unreverts the new algorithm with a fix from Chris (s/len/lena)
and adds some comments on what it's doing.

manifest hash: 75fc1acee1926e57d495f67a44cd88d9555f2356
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)

iD8DBQFCrf4UywK+sNU5EO8RAoRzAKCA2vpUAGNqTkDeba3YHo6XXht7VgCfXQK0
/j5yv5cucnsYezCdclpftOA=
=FNMD
-----END PGP SIGNATURE-----

mercurial/mdiff.py

@@ -1,99 +1,115 b''
 # mdiff.py - diff and patch routines for mercurial
 #
 # Copyright 2005 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import difflib, struct
 from mercurial.mpatch import *
 
 def unidiff(a, ad, b, bd, fn):
     if not a and not b: return ""
 
     if a == None:
         b = b.splitlines(1)
         l1 = "--- %s\t%s\n" % ("/dev/null", ad)
         l2 = "+++ %s\t%s\n" % ("b/" + fn, bd)
         l3 = "@@ -0,0 +1,%d @@\n" % len(b)
         l = [l1, l2, l3] + ["+" + e for e in b]
     elif b == None:
         a = a.splitlines(1)
         l1 = "--- %s\t%s\n" % ("a/" + fn, ad)
         l2 = "+++ %s\t%s\n" % ("/dev/null", bd)
         l3 = "@@ -1,%d +0,0 @@\n" % len(a)
         l = [l1, l2, l3] + ["-" + e for e in a]
     else:
         a = a.splitlines(1)
         b = b.splitlines(1)
         l = list(difflib.unified_diff(a, b, "a/" + fn, "b/" + fn))
         if not l: return ""
         # difflib uses a space, rather than a tab
         l[0] = l[0][:-2] + "\t" + ad + "\n"
         l[1] = l[1][:-2] + "\t" + bd + "\n"
 
     for ln in xrange(len(l)):
         if l[ln][-1] != '\n':
             l[ln] += "\n\ No newline at end of file\n"
 
     return "".join(l)
 
 def textdiff(a, b):
     return diff(a.splitlines(1), b.splitlines(1))
 
 def sortdiff(a, b):
     la = lb = 0
+    lena = len(a)
+    lenb = len(b)
 
     while 1:
-        if la >= len(a) or lb >= len(b): break
-        if b[lb] < a[la]:
-            si = lb
-            while lb < len(b) and b[lb] < a[la] : lb += 1
-            yield "insert", la, la, si, lb
-        elif a[la] < b[lb]:
-            si = la
-            while la < len(a) and a[la] < b[lb]: la += 1
-            yield "delete", si, la, lb, lb
-        else:
+        am, bm, = la, lb
+
+        # walk over matching lines
+        while lb < lenb and la < lenb and a[la] == b[lb] :
             la += 1
             lb += 1
 
-    if lb < len(b):
-        yield "insert", la, la, lb, len(b)
+        if la > am:
+            yield (am, bm, la - am) # return a match
+
+        # skip mismatched lines from b
+        while lb < lenb and b[lb] < a[la]:
+            lb += 1
 
-    if la < len(a):
-        yield "delete", la, len(a), lb, lb
+        if lb >= lenb:
+            break
+        
+        # skip mismatched lines from a
+        while la < lena and b[lb] > a[la]:
+            la += 1
+
+        if la >= lena:
+            break
+        
+    yield (lena, lenb, 0)
 
 def diff(a, b, sorted=0):
+    if not a:
+        s = "".join(b)
+        return s and (struct.pack(">lll", 0, 0, len(s)) + s)
+
     bin = []
     p = [0]
     for i in a: p.append(p[-1] + len(i))
 
     if sorted:
         try:
             d = sortdiff(a, b)
         except:
             print a, b
             raise
     else:
-        d = difflib.SequenceMatcher(None, a, b).get_opcodes()
-
-    for o, m, n, s, t in d:
-        if o == 'equal': continue
-        s = "".join(b[s:t])
-        bin.append(struct.pack(">lll", p[m], p[n], len(s)) + s)
+        d = difflib.SequenceMatcher(None, a, b).get_matching_blocks()
+    la = 0
+    lb = 0
+    for am, bm, size in d:
+        s = "".join(b[lb:bm])
+        if am > la or s:
+            bin.append(struct.pack(">lll", p[la], p[am], len(s)) + s)
+        la = am + size
+        lb = bm + size
 
     return "".join(bin)
 
 def patchtext(bin):
     pos = 0
     t = []
     while pos < len(bin):
         p1, p2, l = struct.unpack(">lll", bin[pos:pos + 12])
         pos += 12
         t.append(bin[pos:pos + l])
         pos += l
     return "".join(t)
 
 def patch(a, bin):
     return patches(a, [bin])