Remove obsolete Python 2 compatibility code

The changes are mostly related to unicode and conditional imports.

Author: v--

docs/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # Nameparser documentation build configuration file, created by
 # sphinx-quickstart on Fri May 16 01:29:58 2014.
@@ -49,8 +48,8 @@
 master_doc = 'index'
 
 # General information about the project.
-project = u'Nameparser'
-copyright = u'{:%Y}, Derek Gulbranson'.format(date.today())
+project = 'Nameparser'
+copyright = '{:%Y}, Derek Gulbranson'.format(date.today())
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
@@ -223,8 +222,8 @@
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-  ('index', 'Nameparser.tex', u'Nameparser Documentation',
-   u'Derek Gulbranson', 'manual'),
+  ('index', 'Nameparser.tex', 'Nameparser Documentation',
+   'Derek Gulbranson', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -253,8 +252,8 @@
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'nameparser', u'Nameparser Documentation',
-     [u'Derek Gulbranson'], 1)
+    ('index', 'nameparser', 'Nameparser Documentation',
+     ['Derek Gulbranson'], 1)
 ]
 
 # If true, show URL addresses after external links.
@@ -267,8 +266,8 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  ('index', 'Nameparser', u'Nameparser Documentation',
-   u'Derek Gulbranson', 'Nameparser', 'A simple python modules for parsing human names into components.',
+  ('index', 'Nameparser', 'Nameparser Documentation',
+   'Derek Gulbranson', 'Nameparser', 'A simple python modules for parsing human names into components.',
    'Miscellaneous'),
 ]
 

nameparser/config/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """
 The :py:mod:`nameparser.config` module manages the configuration of the
 nameparser. 
@@ -28,15 +27,9 @@
 ``hn.C`` will be a reference to the module config, possibly yielding 
 unexpected results. See `Customizing the Parser <customize.html>`_.
 """
-from __future__ import unicode_literals
 import sys
-try:
-    # Python 3.3+
-    from collections.abc import Set
-except ImportError:
-    from collections import Set
+from collections.abc import Set
 
-from nameparser.util import binary_type
 from nameparser.util import lc
 from nameparser.config.prefixes import PREFIXES
 from nameparser.config.capitalization import CAPITALIZATION_EXCEPTIONS
@@ -102,7 +95,7 @@ def add_with_encoding(self, s, encoding=None):
         if sys.stdin:
             stdin_encoding = sys.stdin.encoding
         encoding = encoding or stdin_encoding or DEFAULT_ENCODING
-        if type(s) == binary_type:
+        if isinstance(s, bytes):
             s = s.decode(encoding)
         self.elements.add(lc(s))
 
@@ -144,7 +137,7 @@ def __reduce__(self):
         return (TupleManager, (), self.__getstate__())
 
 
-class Constants(object):
+class Constants:
     """
     An instance of this class hold all of the configuration constants for the parser.
 

nameparser/config/capitalization.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 CAPITALIZATION_EXCEPTIONS = (
     ('ii', 'II'),
     ('iii', 'III'),
@@ -10,4 +7,4 @@
 )
 """
 Any pieces that are not capitalized by capitalizing the first letter.
-"""
+"""

nameparser/config/conjunctions.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 CONJUNCTIONS = set([
     '&',
     'and',
@@ -15,4 +12,4 @@
 Pieces that should join to their neighboring pieces, e.g. "and", "y" and "&".
 "of" and "the" are also include to facilitate joining multiple titles,
 e.g. "President of the United States".
-"""
+"""

nameparser/config/prefixes.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 #: Name pieces that appear before a last name. Prefixes join to the piece
 #: that follows them to make one new piece. They can be chained together, e.g
 #: "von der" and "de la". Because they only appear in middle or last names,

nameparser/config/regexes.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
 import re
 
 # emoji regex from https://stackoverflow.com/questions/26568722/remove-unicode-emoji-using-re-in-python

nameparser/config/suffixes.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 SUFFIX_NOT_ACRONYMS = set([
     'dr',
     'esq',

nameparser/config/titles.py

@@ -1,6 +1,3 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 FIRST_NAME_TITLES = set([
     'aunt',
     'auntie',

nameparser/parser.py

@@ -1,13 +1,8 @@
-# -*- coding: utf-8 -*-
-from __future__ import unicode_literals
-
 import sys
 import re
 from operator import itemgetter
 from itertools import groupby
 
-from nameparser.util import u
-from nameparser.util import text_types, binary_type
 from nameparser.util import lc
 from nameparser.util import log
 from nameparser.config import CONSTANTS
@@ -30,7 +25,7 @@ def group_contiguous_integers(data):
     return ranges
 
 
-class HumanName(object):
+class HumanName:
     """
     Parse a person's name into individual components.
 
@@ -123,10 +118,10 @@ def __eq__(self, other):
         HumanName instances are equal to other objects whose
         lower case unicode representation is the same.
         """
-        return (u(self)).lower() == (u(other)).lower()
+        return str(self).lower() == str(other).lower()
 
     def __ne__(self, other):
-        return not (u(self)).lower() == (u(other)).lower()
+        return str(self).lower() != str(other).lower()
 
     def __getitem__(self, key):
         if isinstance(key, slice):
@@ -152,7 +147,7 @@ def __next__(self):
             self._count = c + 1
             return getattr(self, self._members[c]) or next(self)
 
-    def __unicode__(self):
+    def __str__(self):
         if self.string_format:
             # string_format = "{title} {first} {middle} {last} {suffix} ({nickname})"
             _s = self.string_format.format(**self.as_dict())
@@ -164,27 +159,19 @@ def __unicode__(self):
     def __hash__(self):
         return hash(str(self))
 
-    def __str__(self):
-        if sys.version_info[0] >= 3:
-            return self.__unicode__()
-        return self.__unicode__().encode(self.encoding)
-
     def __repr__(self):
         if self.unparsable:
-            _string = "<%(class)s : [ Unparsable ] >" % {'class': self.__class__.__name__, }
-        else:
-            _string = "<%(class)s : [\n\ttitle: %(title)r \n\tfirst: %(first)r \n\tmiddle: %(middle)r \n\tlast: %(last)r \n\tsuffix: %(suffix)r\n\tnickname: %(nickname)r\n]>" % {
-                'class': self.__class__.__name__,
-                'title': self.title or '',
-                'first': self.first or '',
-                'middle': self.middle or '',
-                'last': self.last or '',
-                'suffix': self.suffix or '',
-                'nickname': self.nickname or '',
-            }
-        if sys.version_info[0] >= 3:
-            return _string
-        return _string.encode(self.encoding)
+            return "<%(class)s : [ Unparsable ] >" % {'class': self.__class__.__name__, }
+
+        return "<%(class)s : [\n\ttitle: %(title)r \n\tfirst: %(first)r \n\tmiddle: %(middle)r \n\tlast: %(last)r \n\tsuffix: %(suffix)r\n\tnickname: %(nickname)r\n]>" % {
+            'class': self.__class__.__name__,
+            'title': self.title or '',
+            'first': self.first or '',
+            'middle': self.middle or '',
+            'last': self.last or '',
+            'suffix': self.suffix or '',
+            'nickname': self.nickname or '',
+        }
 
     def as_dict(self, include_empty=True):
         """
@@ -361,14 +348,14 @@ def surnames(self):
     def _set_list(self, attr, value):
         if isinstance(value, list):
             val = value
-        elif isinstance(value, text_types):
+        elif isinstance(value, str | bytes):
             val = [value]
         elif value is None:
             val = []
         else:
             raise TypeError(
                 "Can only assign strings, lists or None to name attributes."
-                " Got {0}".format(type(value)))
+                f" Got {0}".format(type(value)))
         setattr(self, attr+"_list", self.parse_pieces(val))
 
     @title.setter
@@ -481,7 +468,7 @@ def full_name(self):
     def full_name(self, value):
         self.original = value
         self._full_name = value
-        if isinstance(value, binary_type):
+        if isinstance(value, bytes):
             self._full_name = value.decode(self.encoding)
         self.parse_full_name()
 
@@ -657,7 +644,7 @@ def parse_full_name(self):
 
                 self.suffix_list += parts[1:]
                 pieces = self.parse_pieces(parts[0].split(' '))
-                log.debug("pieces: %s", u(pieces))
+                log.debug("pieces: %s", str(pieces))
                 for i, piece in enumerate(pieces):
                     try:
                         nxt = pieces[i + 1]
@@ -686,7 +673,7 @@ def parse_full_name(self):
                 # last [suffix], title first middles[,] suffix [,suffix]
                 #      parts[0],      parts[1],              parts[2:...]
 
-                log.debug("post-comma pieces: %s", u(post_comma_pieces))
+                log.debug("post-comma pieces: %s", str(post_comma_pieces))
 
                 # lastname part may have suffixes in it
                 lastname_pieces = self.parse_pieces(parts[0].split(' '), 1)
@@ -747,9 +734,9 @@ def parse_pieces(self, parts, additional_parts_count=0):
 
         output = []
         for part in parts:
-            if not isinstance(part, text_types):
+            if not isinstance(part, str | bytes):
                 raise TypeError("Name parts must be strings. "
-                                "Got {0}".format(type(part)))
+                                f"Got {type(part)}")
             output += [x.strip(' ,') for x in part.split(' ')]
 
         # If part contains periods, check if it's multiple titles or suffixes
@@ -981,7 +968,7 @@ def capitalize(self, force=None):
             'Shirley MacLaine'
 
         """
-        name = u(self)
+        name = str(self)
         force = self.C.force_mixed_case_capitalization \
             if force is None else force
 

nameparser/util.py

@@ -1,37 +1,11 @@
 import logging
 
-# http://code.google.com/p/python-nameparser/issues/detail?id=10
+
 log = logging.getLogger('HumanName')
-try:
-    log.addHandler(logging.NullHandler())
-except AttributeError:
-    class NullHandler(logging.Handler):
-        def emit(self, record):
-            pass
-    log.addHandler(NullHandler())
+log.addHandler(logging.NullHandler())
 log.setLevel(logging.ERROR)
 
 
-import sys
-if sys.version_info[0] < 3:
-
-    text_type = unicode
-    binary_type = str
-
-    def u(x, encoding=None):
-        if encoding:
-            return unicode(x, encoding)
-        else:
-            return unicode(x)
-
-else:
-    text_type = str
-    binary_type = bytes
-
-    def u(x, encoding=None):
-        return text_type(x)
-
-text_types = (text_type, binary_type)
 def lc(value):
     """Lower case and remove any periods to normalize for comparison."""
     if not value: