[PATCH] add 'string-distance' to calculate Levenshtein distance

[Chen Bin]

Hello,
Attached patch implemented 'string-distance' is much faster then
existing Lisp implementation like 'org-babel-edit-distance'.

I benchmarked by below snippet:

  (setq s1 "projs1/emacs/etc/imeees/icon/emacs-document.svg")
  (setq s2 "projs2/test/etc/images/icons/emacs-document23.svg")
  (let* ((gc-cons-threshold most-positive-fixnum))
    (message "%S vs %S"
             (benchmark-run-compiled 100
               (org-babel-edit-distance s1 s2))
             (benchmark-run-compiled 100
               (string-distance s1 s2))))

Got:
(0.506494223 0 0.0) vs (0.001317414 0 0.0)

>From bb32afb18bd06e6843921205987b23641145f51a Mon Sep 17 00:00:00 2001
From: Chen Bin <address@hidden>
Date: Sat, 14 Apr 2018 10:33:44 +1000
Subject: [PATCH] add api string-distance

---
 src/fns.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/src/fns.c b/src/fns.c
index 94b9d98..b63d4f4 100644
--- a/src/fns.c
+++ b/src/fns.c
@@ -41,6 +41,8 @@ along with GNU Emacs.  If not, see 
<https://www.gnu.org/licenses/>.  */
 # define gnutls_rnd w32_gnutls_rnd
 #endif
 
+#define min3(a, b, c) ((a) < (b) ? ((a) < (c) ? (a) : (c)) : ((b) < (c) ? (b) 
: (c)))
+
 static void sort_vector_copy (Lisp_Object, ptrdiff_t,
                              Lisp_Object *restrict, Lisp_Object *restrict);
 enum equal_kind { EQUAL_NO_QUIT, EQUAL_PLAIN, EQUAL_INCLUDING_PROPERTIES };
@@ -153,6 +155,33 @@ If STRING is multibyte, this may be greater than the 
length of STRING.  */)
   return make_number (SBYTES (string));
 }
 
+DEFUN ("string-distance", Fstring_distance, Sstring_distance, 2, 2, 0,
+       doc: /* Return Levenshtein distance of two strings.
+Case is significant, but text properties are ignored. */)
+  (register Lisp_Object string1, Lisp_Object string2)
+{
+  CHECK_STRING (string1);
+  CHECK_STRING (string2);
+
+  char *s1 = SSDATA (string1);
+  char *s2 = SSDATA (string2);
+  unsigned int s1len, s2len, x, y, lastdiag, olddiag;
+  s1len = strlen(s1);
+  s2len = strlen(s2);
+  unsigned int column[s1len+1];
+  for (y = 1; y <= s1len; y++)
+    column[y] = y;
+  for (x = 1; x <= s2len; x++) {
+    column[0] = x;
+    for (y = 1, lastdiag = x-1; y <= s1len; y++) {
+      olddiag = column[y];
+      column[y] = min3(column[y] + 1, column[y-1] + 1, lastdiag + (s1[y-1] == 
s2[x-1] ? 0 : 1));
+      lastdiag = olddiag;
+    }
+  }
+  return make_number(column[s1len]);
+}
+
 DEFUN ("string-equal", Fstring_equal, Sstring_equal, 2, 2, 0,
        doc: /* Return t if two strings have identical contents.
 Case is significant, but text properties are ignored.
@@ -5226,6 +5255,7 @@ this variable.  */);
   defsubr (&Slength);
   defsubr (&Ssafe_length);
   defsubr (&Sstring_bytes);
+  defsubr (&Sstring_distance);
   defsubr (&Sstring_equal);
   defsubr (&Scompare_strings);
   defsubr (&Sstring_lessp);
-- 
2.16.3

-- 
Best Regards,
Chen Bin

--
Help me, help you