From 53e6358e1346afd64bad261823f92ae9619b93d2 Mon Sep 17 00:00:00 2001
From: Chen Bin <chenbin.sh@gmail.com>
Date: Sun, 15 Apr 2018 02:20:29 +1000
Subject: [PATCH] add api string-distance

---
 etc/NEWS                |  2 ++
 src/fns.c               | 35 +++++++++++++++++++++++++++++++++++
 test/lisp/subr-tests.el | 10 ++++++++++
 3 files changed, 47 insertions(+)

diff --git a/etc/NEWS b/etc/NEWS
index 12b72eb..75cc92d 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -463,6 +463,8 @@ x-lost-selection-hooks, x-sent-selection-hooks
 +++
 ** New function assoc-delete-all.
 
+** New function string-distance to calculate Levenshtein distance between two strings.
+
 ** 'print-quoted' now defaults to t, so if you want to see
 (quote x) instead of 'x you will have to bind it to nil where applicable.
 
diff --git a/src/fns.c b/src/fns.c
index 94b9d98..f149001 100644
--- a/src/fns.c
+++ b/src/fns.c
@@ -153,6 +153,40 @@ 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 between STRING1 and STRING2.
+Case is significant, but text properties are ignored.
+Strings are treated as byte arrays when calculating distance. */)
+  (Lisp_Object string1, Lisp_Object string2)
+{
+  CHECK_STRING (string1);
+  CHECK_STRING (string2);
+
+  char *s1 = SSDATA (string1);
+  char *s2 = SSDATA (string2);
+
+  ptrdiff_t s1len, s2len, x, y, lastdiag, olddiag;
+  s1len = SBYTES (string1);
+  s2len = SBYTES (string2);
+
+  USE_SAFE_ALLOCA;
+  ptrdiff_t *column = SAFE_ALLOCA ((s1len + 1) * sizeof (ptrdiff_t));
+  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] = min (min (column[y] + 1, column[y-1] + 1), lastdiag + (s1[y-1] == s2[x-1] ? 0 : 1));
+          lastdiag = olddiag;
+        }
+    }
+  SAFE_FREE ();
+  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 +5260,7 @@ this variable.  */);
   defsubr (&Slength);
   defsubr (&Ssafe_length);
   defsubr (&Sstring_bytes);
+  defsubr (&Sstring_distance);
   defsubr (&Sstring_equal);
   defsubr (&Scompare_strings);
   defsubr (&Sstring_lessp);
diff --git a/test/lisp/subr-tests.el b/test/lisp/subr-tests.el
index 52b61d9..40a7727 100644
--- a/test/lisp/subr-tests.el
+++ b/test/lisp/subr-tests.el
@@ -281,6 +281,16 @@ subr-test--frames-1
   (should (equal (string-match-p "\\`[[:blank:]]\\'" "\u3000") 0))
   (should-not (string-match-p "\\`[[:blank:]]\\'" "\N{LINE SEPARATOR}")))
 
+(ert-deftest subr-tests--string-distance ()
+  "Test `string-distance' behavior."
+  (should (equal 1 (string-distance "heelo" "hello")))
+  (should (equal 2 (string-distance "aeelo" "hello")))
+  (should (equal 0 (string-distance "ab" "ab")))
+  (should (equal 1 (string-distance "ab" "abc")))
+  ;; string containing unicode character (Hanzi)
+  (should (equal 6 (string-distance "ab" "ab我她")))
+  (should (equal 3 (string-distance "我" "她"))))
+
 (ert-deftest subr-tests--dolist--wrong-number-of-args ()
   "Test that `dolist' doesn't accept wrong types or length of SPEC,
 cf. Bug#25477."
-- 
2.16.3