X-Git-Url: https://git.kaliko.me/?a=blobdiff_plain;f=sima%2Flib%2Fsimastr.py;h=033a994e23f7bea76b99db648570426c8a62e4ad;hb=37dd60538984a3917354b794a5c96b0a025f8e95;hp=9dacc45d1ea3af6302a1f56b08c9e6049b117a9b;hpb=e73aeec41c2065c852294253a8ed85a5d0958f76;p=mpd-sima.git

diff --git a/sima/lib/simastr.py b/sima/lib/simastr.py
index 9dacc45..033a994 100644
--- a/sima/lib/simastr.py
+++ b/sima/lib/simastr.py
@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
-
 #
-# Copyright (c) 2009, 2010, 2013 Jack Kaliko <kaliko@azylum.org>
+# Copyright (c) 2009, 2010, 2013 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
@@ -18,7 +17,7 @@
 #  If not, see <http://www.gnu.org/licenses/>.
 #
 
-"""
+r"""
 SimaStr
 
 Special unicode() subclass to perform fuzzy match on specific strings with
@@ -70,7 +69,7 @@ __version__ = '0.4'
 
 # IMPORTS
 import unicodedata
-from re import (compile, U, I)
+from re import compile as re_compile, U, I
 
 from ..utils.leven import levenshtein_ratio
 
@@ -94,11 +93,11 @@ class SimaStr(str):
     # Trailing patterns: ! ? live
     # TODO: add "concert" key word
     #       add "Live at <somewhere>"
-    regexp_dict.update({'trail': '([- !?\.]|\(? ?[Ll]ive ?\)?)'})
+    regexp_dict.update({'trail': r'([- !?\.]|\(? ?[Ll]ive ?\)?)'})
 
-    reg_lead = compile('^(?P<lead>%(lead)s )(?P<root0>.*)$' % regexp_dict, I | U)
-    reg_midl = compile('^(?P<root0>.*)(?P<mid> %(mid)s )(?P<root1>.*)' % regexp_dict, U)
-    reg_trail = compile('^(?P<root0>.*?)(?P<trail>%(trail)s+$)' % regexp_dict, U)
+    reg_lead = re_compile('^(?P<lead>%(lead)s )(?P<root0>.*)$' % regexp_dict, I | U)
+    reg_midl = re_compile('^(?P<root0>.*)(?P<mid> %(mid)s )(?P<root1>.*)' % regexp_dict, U)
+    reg_trail = re_compile('^(?P<root0>.*?)(?P<trail>%(trail)s+$)' % regexp_dict, U)
 
     def __init__(self, fuzzstr):
         """
@@ -108,7 +107,7 @@ class SimaStr(str):
         # fuzzy computation
         self._get_root()
         if self.__class__.diafilter:
-           self.remove_diacritics()
+            self.remove_diacritics()
 
     def __new__(cls, fuzzstr):
         return super(SimaStr, cls).__new__(cls, fuzzstr)
@@ -119,21 +118,19 @@ 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):
+        """converting diacritics"""
         self.stripped = ''.join(x for x in
                                 unicodedata.normalize('NFKD', self.stripped)
                                 if unicodedata.category(x) != 'Mn')
@@ -156,40 +153,5 @@ 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