refactor: remove unnecessary code in fast distance comparer, update v…

…ersion and changelog

CHANGELOG.md

@@ -1,6 +1,11 @@
 CHANGELOG <br>
 ==============
 
+## 6.7.4 (2021-11-29)
+---------------------
+- Update `editdistpy` dependency version
+- Update `LevenshteinFast` and `DamerauOsaFast` to match the functionality of the `editdistpy` library
+
 ## 6.7.3 (2021-11-27)
 ---------------------
 - Update `editdistpy` dependency version

symspellpy/__init__.py

@@ -19,7 +19,7 @@
 .. moduleauthor:: Wolf Garbe <wolf.garbe@faroo.com>
 """
 
-__version__ = "6.7.3"
+__version__ = "6.7.4"
 
 import logging
 import os

symspellpy/editdistance.py

@@ -445,21 +445,6 @@ def distance(self, string_1: str, string_2: str, max_distance: int) -> int:
                 are equivalent, otherwise a positive number whose magnitude
                 increases as difference between the strings increases.
         """
-        if string_1 is None or string_2 is None:
-            return helpers.null_distance_results(string_1, string_2, max_distance)
-        if max_distance <= 0:
-            return 0 if string_1 == string_2 else -1
-        max_distance = int(min(2 ** 31 - 1, max_distance))
-        # if strings of different lengths, ensure shorter string is in string_1.
-        # This can result in a little faster speed by spending more time spinning
-        # just the inner loop during the main processing.
-        len_1 = len(string_1)
-        len_2 = len(string_2)
-        if len_1 > len_2:
-            string_2, string_1 = string_1, string_2
-            len_2, len_1 = len_1, len_2
-        if len_2 - len_1 > max_distance:
-            return -1
         return levenshtein.distance(string_1, string_2, max_distance)
 
 
@@ -483,19 +468,4 @@ def distance(self, string_1: str, string_2: str, max_distance: int) -> int:
                 are equivalent, otherwise a positive number whose magnitude
                 increases as difference between the strings increases.
         """
-        if string_1 is None or string_2 is None:
-            return helpers.null_distance_results(string_1, string_2, max_distance)
-        if max_distance <= 0:
-            return 0 if string_1 == string_2 else -1
-        max_distance = int(min(2 ** 31 - 1, max_distance))
-        # if strings of different lengths, ensure shorter string is in string_1.
-        # This can result in a little faster speed by spending more time spinning
-        # just the inner loop during the main processing.
-        len_1 = len(string_1)
-        len_2 = len(string_2)
-        if len_1 > len_2:
-            string_2, string_1 = string_1, string_2
-            len_2, len_1 = len_1, len_2
-        if len_2 - len_1 > max_distance:
-            return -1
         return damerau_osa.distance(string_1, string_2, max_distance)

tests/benchmarks.ipynb

@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -106,17 +106,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "214 µs ± 770 ns per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
-      "130 µs ± 538 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n",
-      "192 µs ± 346 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n",
-      "130 µs ± 369 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
+      "219 µs ± 1.35 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
+      "130 µs ± 692 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n",
+      "195 µs ± 775 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n",
+      "130 µs ± 925 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)\n"
      ]
     }
    ],
@@ -129,17 +129,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "20.5 ms ± 175 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n",
-      "10.9 ms ± 217 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
-      "18 ms ± 67 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
-      "10.5 ms ± 125 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
+      "21.8 ms ± 207 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n",
+      "11 ms ± 223 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
+      "19.1 ms ± 64.2 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
+      "10.3 ms ± 49.9 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
      ]
     }
    ],
@@ -152,17 +152,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1.62 ms ± 2.94 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
-      "1.62 ms ± 7.84 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
-      "1.75 ms ± 90.7 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
-      "1.65 ms ± 12.4 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n"
+      "1.64 ms ± 23.4 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
+      "1.65 ms ± 19.9 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
+      "1.63 ms ± 4.87 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n",
+      "1.63 ms ± 3.91 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n"
      ]
     }
    ],