X-Git-Url: https://git.kaliko.me/?a=blobdiff_plain;f=sima%2Flib%2Fsimastr.py;h=ec82d91510bd57c724e829ff968ff34bb9e27e3e;hb=HEAD;hp=56edbb4d7e68b82a816ad2d30cb6a99698d78864;hpb=78a694ddcd2a6ecc8b2b1fd3c74ee2d938707305;p=mpd-sima.git

diff --git a/sima/lib/simastr.py b/sima/lib/simastr.py
index 56edbb4..ec82d91 100644
--- a/sima/lib/simastr.py
+++ b/sima/lib/simastr.py
@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (c) 2009, 2010, 2013 Jack Kaliko <kaliko@azylum.org>
+# Copyright (c) 2009, 2010, 2013, 2021 kaliko <kaliko@azylum.org>
 #
 #  This program is free software; you can redistribute it and/or modify
 #  it under the terms of the GNU General Public License as
@@ -81,7 +81,7 @@ class SimaStr(str):
     """
     diafilter = True
     leven_ratio = 0.82
-    regexp_dict = dict()
+    regexp_dict = {}
 
     # Leading patterns: The Le Les
     # case-insensitive matching for this RE
@@ -102,6 +102,7 @@ class SimaStr(str):
     def __init__(self, fuzzstr):
         """
         """
+        super().__init__()
         self.orig = str(fuzzstr)
         self.stripped = str(fuzzstr.strip())
         # fuzzy computation
@@ -118,18 +119,15 @@ class SimaStr(str):
         """
         sea = SimaStr.reg_lead.search(self.stripped)
         if sea:
-            #print sea.groupdict()
             self.stripped = sea.group('root0')
 
         sea = SimaStr.reg_midl.search(self.stripped)
         if sea:
-            #print sea.groupdict()
             self.stripped = str().join([sea.group('root0'), ' ',
                                         sea.group('root1')])
 
         sea = SimaStr.reg_trail.search(self.stripped)
         if sea:
-            #print sea.groupdict()
             self.stripped = sea.group('root0')
 
     def remove_diacritics(self):
@@ -156,40 +154,5 @@ class SimaStr(str):
         return hash(self) != hash(other)
 
 
-# Script starts here
-if __name__ == "__main__":
-    import time
-    print(SimaStr('Kétanoue'))
-    #from leven import levenshtein_ratio
-    CASES_LIST = list([
-        dict({
-                    'got': 'Guns N\' Roses (live)!! !',
-                'look for': 'Guns And Roses'}),
-        dict({
-                     'got': 'Jesus & Mary Chains',
-                'look for': 'The Jesus and Mary Chains - live'}),
-        dict({
-                         'got': 'Desert sessions',
-                    'look for': 'The Desert Sessions'}),
-        dict({
-                         'got': 'Têtes Raides',
-                    'look for': 'Les Têtes Raides'}),
-        dict({
-                         'got': 'Noir Désir',
-                    'look for': 'Noir Désir'}),
-        dict({
-                         'got': 'No Future',
-                    'look for': 'Future'})])
-
-    for case in CASES_LIST[:]:
-        str0 = case.get('got')
-        str1 = case.get('look for')
-        fz_str0 = SimaStr(str0)
-        fz_str1 = SimaStr(str1)
-        print(fz_str0, '\n', fz_str1)
-        print(fz_str0.stripped == fz_str1.stripped)
-        #print levenshtein_ratio(fz_str0.lower(), fz_str1.lower())
-        time.sleep(1)
-
 # VIM MODLINE
 # vim: ai ts=4 sw=4 sts=4 expandtab