init

Author: Nathan Zylbersztejn

.idea/encodings.xml

@@ -0,0 +1 @@
+{}

.idea/fuzzy_matcher.iml

@@ -0,0 +1,5 @@
+[
+  "tests/test_fuzzy_matcher.py::test_partial_distance",
+  "tests/test_fuzzy_matcher.py::test_ratio",
+  "tests/test_fuzzy_matcher.py::test_partial_ratio"
+]

.pytest_cache/v/cache/lastfailed

@@ -0,0 +1 @@
+[]

.pytest_cache/v/cache/nodeids

@@ -0,0 +1,20 @@
+language: python
+python:
+- '2.7'
+- '3.4'
+- '3.5'
+- '3.6'
+- '3.7'
+install:
+- pip install -r requirements.txt
+script:
+- python -m pytest
+#deploy:
+#  provider: pypi
+#  distributions: sdist
+#  user: mrbot
+#  password:
+#    secure: 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
+#  on:
+#    tags: true
+#    python: 3.6

.pytest_cache/v/cache/stepwise

@@ -0,0 +1,23 @@
+# Fuzzy Matcher
+
+A super simple MIT licensed fuzzy matching library to be used as an MIT alternative to Fuzzy Wuzzy which is GPL licensed.
+It is much less featured as Fuzzy Wuzzy, so if GPL is not blocking you, you should probably use Fuzzy Wuzzy instead.
+
+## Usage
+
+```python
+from fuzzy_matcher import process
+query = "orange"
+val = ['blue', 'orange', 'brown', 'ornage', 'range', 'angel', 'gang', 'ang']
+fuzzy = process.extract(query, val, limit=3, scorer='ratio')
+```
+
+should output:
+```python
+[('orange', 100), ('range', 83), ('ornage', 66)]
+```
+
+### Supported scorers
+
+Only `ratio` and `partial_ratio` are supported at this time.
+Note that scores will not be the same as FuzzyWuzzy's. 

.travis.yml

@@ -0,0 +1,17 @@
+Metadata-Version: 2.1
+Name: fuzzy-matcher
+Version: 0.1.0
+Summary: A super simple MIT licensed fuzzy matching library
+Home-page: https://mrbot.ai
+Author: Nathan Zylbersztejn
+Author-email: human@mrbot.ai
+License: MIT
+Description: # Fuzzy Matcher
+        
+        A super simple MIT licensed fuzzy matching library. 
+        It's aiming at being an MIT alternative to Fuzzy Wuzzy which is GPL licensed.
+        It is much less featured as FuzzyWuzzy, so if the GPL is not blocking you, you should probably use it.
+        
+        
+Platform: UNKNOWN
+Description-Content-Type: text/markdown

README.md

@@ -0,0 +1,8 @@
+README.md
+fuzzy_matcher/__init__.py
+fuzzy_matcher/process.py
+fuzzy_matcher.egg-info/PKG-INFO
+fuzzy_matcher.egg-info/SOURCES.txt
+fuzzy_matcher.egg-info/dependency_links.txt
+fuzzy_matcher.egg-info/requires.txt
+fuzzy_matcher.egg-info/top_level.txt

__init__.py

@@ -0,0 +1 @@
+

fuzzy_matcher.egg-info/PKG-INFO

@@ -0,0 +1 @@
+editdistance

fuzzy_matcher.egg-info/SOURCES.txt

@@ -0,0 +1 @@
+fuzzy_matcher

fuzzy_matcher.egg-info/dependency_links.txt

@@ -0,0 +1,41 @@
+import editdistance
+import operator
+
+
+def distance(val1, val2):
+    return editdistance.eval(val1, val2)
+
+
+def ratio(val1, val2):
+    max_distance = max(len(val1), len(val2))
+    return int(100*(1 - distance(val1, val2) / max_distance))
+
+
+def partial_distance(val1, val2):
+    values = sorted([val1, val2], key=len, reverse=True)
+    distances = []
+    for i in range(0, len(values[0]) - len(values[1]) + 1):
+        distances.append(editdistance.eval(values[1], values[0][i:i + len(values[1])]))
+    return min(distances)
+
+
+def partial_ratio(val1, val2):
+    max_distance = len(val1)
+    return int(100*(1 - partial_distance(val1, val2) / max_distance))
+
+
+def _get_scorer(scorer_name):
+    if scorer_name == 'ratio':
+        return ratio
+    elif scorer_name == 'partial_ratio':
+        return partial_ratio
+
+
+def extract(value, choices=[], scorer='ratio', limit=5):
+    scorerfn = _get_scorer(scorer)
+    distances = [(choice, scorerfn(value, choice)) for choice in choices]
+    distances.sort(key=operator.itemgetter(1), reverse=True)
+    return distances[0:limit]
+
+
+

fuzzy_matcher.egg-info/requires.txt

@@ -0,0 +1 @@
+editdistance

fuzzy_matcher.egg-info/top_level.txt

@@ -0,0 +1,19 @@
+from setuptools import setup
+import os
+import io
+
+with io.open(os.path.join(os.path.abspath(os.path.dirname(__file__)), 'README.md'), encoding='utf-8') as f:
+    long_description = f.read()
+setup(
+    name='fuzzy_matcher',
+    version='0.1.0',
+    author='Nathan Zylbersztejn',
+    description="A super simple MIT licensed fuzzy matching library",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    install_requires=['editdistance', ],
+    licence='MIT',
+    url='https://mrbot.ai',
+    author_email='human@mrbot.ai',
+    packages=['fuzzy_matcher']
+)

fuzzy_matcher/__init__.py

@@ -0,0 +1,30 @@
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+
+
+from fuzzy_matcher import process
+
+
+def test_partial_distance():
+    query = "orange"
+    candidates = ['orangoutan', 'orange tango', 'olive martini', 'orangemartinin', 'martininorange']
+    partial_distances = [process.partial_distance(query, val) for val in candidates]
+    assert partial_distances == [1, 0, 5, 0, 0]
+
+
+def test_ratio():
+
+    query = "orange"
+    val = ['blue', 'orange', 'brown', 'ornage', 'range', 'angel', 'gang', 'ang']
+    fuzzy = process.extract(query, val, limit=3, scorer='ratio')
+    assert fuzzy == [('orange', 100), ('range', 83), ('ornage', 66)]
+
+
+def test_partial_ratio():
+    query = "orange"
+    val = ['blue tango', 'orange tango', 'brown tango']
+    fuzzy = process.extract(query, val, limit=3, scorer='partial_ratio')
+    assert fuzzy == [('orange tango', 100), ('blue tango', 50), ('brown tango', 50)]
+