Lots of new country and corporate type country coverage from the 'disco' fork

cleanco/classify.py

@@ -22,7 +22,7 @@
 
 
 def typesources():
-   "business types / abbreviations sorted by length of business type"
+   """business types / abbreviations sorted by length of business type"""
    types = []
    for business_type in terms_by_type:
        for item in terms_by_type[business_type]:
@@ -32,7 +32,7 @@ def typesources():
 
 
 def countrysources():
-   "business countries / type abbreviations sorted by length of type abbreviations"
+   """business countries / type abbreviations sorted by length of type abbreviations"""
    countries = []
    for country in terms_by_country:
        for item in terms_by_country[country]:
@@ -42,20 +42,20 @@ def countrysources():
 
 
 def matches(name, sources):
-    "get types or countries matching with the legal terms in name"
+    """get types or countries matching with the legal terms in name"""
 
     name = strip_tail(name)
     parts = name.split()
     nparts = [normalized(p) for p in parts]
-    matches = []
+    matched = []
     for classifier, term in sources:
         nterm = normalized(term)
         try:
             idx = nparts.index(nterm)
         except ValueError:
             pass
         else:
-            matches.append(classifier)
+            matched.append(classifier)
 
-    return matches
+    return matched
 

cleanco/clean.py

@@ -1,6 +1,6 @@
 """Functions to help clean & normalize business names.
 
-See http://www.unicode.org/reports/tr15/#Normalization_Forms_Table for details
+See https://www.unicode.org/reports/tr15/#Normalization_Forms_Table for details
 on Unicode normalization and the NFKD normalization used here.
 
 Basic usage:
@@ -13,17 +13,16 @@
 
 import functools
 import operator
-from collections import OrderedDict
 import re
 import unicodedata
 from .termdata import terms_by_type, terms_by_country
 from .non_nfkd_map import NON_NFKD_MAP
 
-tail_removal_rexp = re.compile(r"[^\.\w]+$", flags=re.UNICODE)
+tail_removal_rexp = re.compile(r"[^.\w]+$", flags=re.UNICODE)
 
 
 def get_unique_terms():
-    "retrieve all unique terms from termdata definitions"
+    """retrieve all unique terms from termdata definitions"""
     ts = functools.reduce(operator.iconcat, terms_by_type.values(), [])
     cs = functools.reduce(operator.iconcat, terms_by_country.values(), [])
     return set(ts + cs)
@@ -46,25 +45,25 @@ def strip_punct(t):
 
 
 def normalize_terms(terms):
-    "normalize terms"
+    """normalize terms"""
     return (strip_punct(remove_accents(t)) for t in terms)
 
 
 def strip_tail(name):
-    "get rid of all trailing non-letter symbols except the dot"
+    """get rid of all trailing non-letter symbols except the dot"""
     match = re.search(tail_removal_rexp, name)
     if match is not None:
         name = name[: match.span()[0]]
     return name
 
 
 def normalized(text):
-    "caseless Unicode normalization"
+    """caseless Unicode normalization"""
     return remove_accents(text)
 
 
 def prepare_default_terms():
-    "construct an optimized term structure for basename extraction"
+    """construct an optimized term structure for basename extraction"""
     terms = get_unique_terms()
     nterms = normalize_terms(terms)
     ntermparts = (t.split() for t in nterms)
@@ -74,7 +73,7 @@ def prepare_default_terms():
 
 
 def custom_basename(name, terms, suffix=True, prefix=False, middle=False, **kwargs):
-    "return cleaned base version of the business name"
+    """return cleaned base version of the business name"""
 
     name = strip_tail(name)
     nparts = name.split()