From 57196e643ad1854726a670850744b9c82fbeff06 Mon Sep 17 00:00:00 2001
From: Tom Jaspers <tomjaspers@gmail.com>
Date: Tue, 31 Mar 2015 14:02:58 +0200
Subject: [PATCH] Use Levenshtein distance from Jellyfish library

Its about two orders of magnitude faster than current 'handrolled' one

See #646
---
 beets/autotag/hooks.py |  4 ++--
 beets/util/__init__.py | 23 -----------------------
 setup.py               |  1 +
 tox.ini                |  1 +
 4 files changed, 4 insertions(+), 25 deletions(-)

diff --git a/beets/autotag/hooks.py b/beets/autotag/hooks.py
index 3a4f96548..fa2dad9d6 100644
--- a/beets/autotag/hooks.py
+++ b/beets/autotag/hooks.py
@@ -23,7 +23,7 @@ from beets import logging
 from beets import plugins
 from beets import config
 from beets.autotag import mb
-from beets.util import levenshtein
+from jellyfish import levenshtein_distance
 from unidecode import unidecode
 
 log = logging.getLogger('beets')
@@ -209,7 +209,7 @@ def _string_dist_basic(str1, str2):
     str2 = re.sub(r'[^a-z0-9]', '', str2.lower())
     if not str1 and not str2:
         return 0.0
-    return levenshtein(str1, str2) / float(max(len(str1), len(str2)))
+    return levenshtein_distance(str1, str2) / float(max(len(str1), len(str2)))
 
 
 def string_dist(str1, str2):
diff --git a/beets/util/__init__.py b/beets/util/__init__.py
index a3b57eea6..ca06962b7 100644
--- a/beets/util/__init__.py
+++ b/beets/util/__init__.py
@@ -564,29 +564,6 @@ def as_string(value):
         return unicode(value)
 
 
-def levenshtein(s1, s2):
-    """A nice DP edit distance implementation from Wikibooks:
-    http://en.wikibooks.org/wiki/Algorithm_implementation/Strings/
-    Levenshtein_distance#Python
-    """
-    if len(s1) < len(s2):
-        return levenshtein(s2, s1)
-    if not s1:
-        return len(s2)
-
-    previous_row = xrange(len(s2) + 1)
-    for i, c1 in enumerate(s1):
-        current_row = [i + 1]
-        for j, c2 in enumerate(s2):
-            insertions = previous_row[j + 1] + 1
-            deletions = current_row[j] + 1
-            substitutions = previous_row[j] + (c1 != c2)
-            current_row.append(min(insertions, deletions, substitutions))
-        previous_row = current_row
-
-    return previous_row[-1]
-
-
 def plurality(objs):
     """Given a sequence of comparable objects, returns the object that
     is most common in the set and the frequency of that object. The
diff --git a/setup.py b/setup.py
index 78937b39e..e702c8faa 100755
--- a/setup.py
+++ b/setup.py
@@ -82,6 +82,7 @@ setup(
         'unidecode',
         'musicbrainzngs>=0.4',
         'pyyaml',
+        'jellyfish',
     ] + (['colorama'] if (sys.platform == 'win32') else []) +
         (['ordereddict'] if sys.version_info < (2, 7, 0) else []),
 
diff --git a/tox.ini b/tox.ini
index 57ef435c4..42529d390 100644
--- a/tox.ini
+++ b/tox.ini
@@ -18,6 +18,7 @@ deps =
     responses
     pathlib
     pyxdg
+    jellyfish
 commands =
     nosetests {posargs}