Merge pull request #689 from lalinsky/py-astrcmp

Add pure Python fallback for astrcmp

picard/util/_astrcmp.c

@@ -180,7 +180,7 @@ static struct PyModuleDef AstrcmpModule =
 };
 
 PyMODINIT_FUNC 
-PyInit_astrcmp(void)
+PyInit__astrcmp(void)
 {
     return PyModule_Create(&AstrcmpModule);
-}
+}

picard/util/astrcmp.py

@@ -0,0 +1,40 @@
+# http://hetland.org/coding/python/levenshtein.py
+
+# This is a straightforward implementation of a well-known algorithm, and thus
+# probably shouldn't be covered by copyright to begin with. But in case it is,
+# the author (Magnus Lie Hetland) has, to the extent possible under law,
+# dedicated all copyright and related and neighboring rights to this software
+# to the public domain worldwide, by distributing it under the CC0 license,
+# version 1.0. This software is distributed without any warranty. For more
+# information, see <http://creativecommons.org/publicdomain/zero/1.0>
+
+
+def astrcmp_py(a,b):
+    "Calculates the Levenshtein distance between a and b."
+    n, m = len(a), len(b)
+    if n > m:
+        # Make sure n <= m, to use O(min(n,m)) space
+        a, b = b, a
+        n, m = m, n
+
+    if n == 0 or m == 0.0:
+        return 0.0
+
+    current = range(n+1)
+    for i in range(1, m+1):
+        previous, current = current, [i]+[0]*n
+        for j in range(1, n+1):
+            add, delete = previous[j]+1, current[j-1]+1
+            change = previous[j-1]
+            if a[j-1] != b[i-1]:
+                change = change + 1
+            current[j] = min(add, delete, change)
+
+    return 1.0 - current[n] / max(m, n)
+
+
+try:
+    from picard.util._astrcmp import astrcmp as astrcmp_c
+    astrcmp = astrcmp_c
+except ImportError:
+    astrcmp = astrcmp_py

setup.py

@@ -35,7 +35,7 @@ from distutils.dist import Distribution
 from distutils.spawn import find_executable
 
 ext_modules = [
-    Extension('picard.util.astrcmp', sources=['picard/util/astrcmp.c']),
+    Extension('picard.util._astrcmp', sources=['picard/util/_astrcmp.c']),
 ]
 
 py2app_exclude_modules = [

test/test_util_astrcmp.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+import os
+import os.path
+import unittest
+from picard.util.astrcmp import astrcmp_c, astrcmp_py
+
+
+class AstrcmpBase(object):
+    func = None
+
+    def test_astrcmp(self):
+        astrcmp = self.__class__.func
+        self.assertAlmostEqual(0.0, astrcmp(u"", u""))
+        self.assertAlmostEqual(0.0, astrcmp(u"a", u""))
+        self.assertAlmostEqual(0.0, astrcmp(u"", u"a"))
+        self.assertAlmostEqual(1.0, astrcmp(u"a", u"a"))
+        self.assertAlmostEqual(0.0, astrcmp(u"a", u"b"))
+        self.assertAlmostEqual(0.0, astrcmp(u"ab", u"ba"))
+        self.assertAlmostEqual(0.7083333333333333, astrcmp(u"The Great Gig in the Sky", u"Great Gig In The sky"))
+
+
+class AstrcmpCTest(AstrcmpBase, unittest.TestCase):
+    func = astrcmp_c
+
+
+class AstrcmpPyTest(AstrcmpBase, unittest.TestCase):
+    func = astrcmp_py