v1.0, fix support for nicknames in single quotes (#74)

Author: derek73

docs/release_log.rst

@@ -1,5 +1,8 @@
 Release Log
 ===========
+* 1.0.0 - August 30, 2018
+    - Fix support for nicknames in single quotes (#74)
+    - No other big changes, just bumping to v1 to indicate approprite project maturity
 * 0.5.8 - August 19, 2018
     - Add "Junior" to suffixes (#76)
     - Add "dra" and "srta" to titles (#77)

nameparser/__init__.py

@@ -1,4 +1,4 @@
-VERSION = (0, 5, 8)
+VERSION = (1, 0, 0)
 __version__ = '.'.join(map(str, VERSION))
 __author__ = "Derek Gulbranson"
 __author_email__ = 'derek73@gmail.com'

nameparser/config/regexes.py

@@ -23,7 +23,9 @@
     ("word", re.compile(r"(\w|\.)+", re.U)),
     ("mac", re.compile(r'^(ma?c)(\w{2,})', re.I | re.U)),
     ("initial", re.compile(r'^(\w\.|[A-Z])?$', re.U)),
-    ("nickname", re.compile(r'\s*?[\("](.+?)[\)"]', re.U)),
+    ("quoted_word", re.compile(r'\'([^\s]*?)\'', re.U)),
+    ("double_quotes", re.compile(r'\"(.*?)\"', re.U)),
+    ("parenthesis", re.compile(r'\((.*?)\)', re.U)),
     ("roman_numeral", re.compile(r'^(X|IX|IV|V?I{0,3})$', re.I | re.U)),
     ("no_vowels",re.compile(r'^[^aeyiuo]+$', re.I | re.U)),
     ("period_not_at_end",re.compile(r'.*\..+$', re.I | re.U)),

nameparser/parser.py

@@ -384,15 +384,25 @@ def post_process(self):
 
     def parse_nicknames(self):
         """
-        The content of parenthesis or double quotes in the name will
-        be treated as nicknames. This happens before any other
-        processing of the name.
-        """
-        # https://code.google.com/p/python-nameparser/issues/detail?id=33
-        re_nickname = self.C.regexes.nickname
-        if re_nickname.search(self._full_name):
-            self.nickname_list = re_nickname.findall(self._full_name)
-            self._full_name = re_nickname.sub('', self._full_name)
+        The content of parenthesis or quotes in the name will be added to the 
+        nicknames list. This happens before any other processing of the name.
+        
+        Single quotes cannot span white space characters to allow for single
+        quotes in names like O'Connor. Double quotes and parenthesis can span
+        white space.
+        
+        Loops through 3 :py:data:`~nameparser.config.regexes.REGEXES`; 
+        `quoted_word`, `double_quotes` and `parenthesis`.
+        """
+        
+        re_quoted_word = self.C.regexes.quoted_word
+        re_double_quotes = self.C.regexes.double_quotes
+        re_parenthesis = self.C.regexes.parenthesis
+
+        for _re in (re_quoted_word, re_double_quotes, re_parenthesis):
+            if _re.search(self._full_name):
+                self.nickname_list += [x for x in _re.findall(self._full_name)]
+                self._full_name = _re.sub('', self._full_name)
 
     def squash_emoji(self):
         """

tests.py

@@ -1365,6 +1365,20 @@ def test_nickname_in_parenthesis(self):
         self.m(hn.last, "Franklin", hn)
         self.m(hn.nickname, "Ben", hn)
 
+    def test_two_word_nickname_in_parenthesis(self):
+        hn = HumanName("Benjamin (Big Ben) Franklin")
+        self.m(hn.first, "Benjamin", hn)
+        self.m(hn.middle, "", hn)
+        self.m(hn.last, "Franklin", hn)
+        self.m(hn.nickname, "Big Ben", hn)
+
+    def test_two_words_in_quotes(self):
+        hn = HumanName('Benjamin "Big Ben" Franklin')
+        self.m(hn.first, "Benjamin", hn)
+        self.m(hn.middle, "", hn)
+        self.m(hn.last, "Franklin", hn)
+        self.m(hn.nickname, "Big Ben", hn)
+
     def test_nickname_in_parenthesis_with_comma(self):
         hn = HumanName("Franklin, Benjamin (Ben)")
         self.m(hn.first, "Benjamin", hn)
@@ -1380,9 +1394,6 @@ def test_nickname_in_parenthesis_with_comma_and_suffix(self):
         self.m(hn.suffix, "Jr.", hn)
         self.m(hn.nickname, "Ben", hn)
 
-    # it would be hard to support this without breaking some of the
-    # other examples with single quotes in the names.
-    @unittest.expectedFailure
     def test_nickname_in_single_quotes(self):
         hn = HumanName("Benjamin 'Ben' Franklin")
         self.m(hn.first, "Benjamin", hn)
@@ -1398,9 +1409,9 @@ def test_nickname_in_double_quotes(self):
         self.m(hn.nickname, "Ben", hn)
 
     def test_single_quotes_on_first_name_not_treated_as_nickname(self):
-        hn = HumanName("Brian O'connor")
+        hn = HumanName("Brian Andrew O'connor")
         self.m(hn.first, "Brian", hn)
-        self.m(hn.middle, "", hn)
+        self.m(hn.middle, "Andrew", hn)
         self.m(hn.last, "O'connor", hn)
         self.m(hn.nickname, "", hn)
 
@@ -1419,19 +1430,26 @@ def test_single_quotes_on_end_of_last_name_not_treated_as_nickname(self):
         self.m(hn.nickname, "", hn)
 
     # http://code.google.com/p/python-nameparser/issues/detail?id=17
-    def test_parenthesis_are_removed(self):
-        hn = HumanName("John Jones (Google Docs)")
+    def test_parenthesis_are_removed_from_name(self):
+        hn = HumanName("John Jones (Unknown)")
         self.m(hn.first, "John", hn)
         self.m(hn.last, "Jones", hn)
         # not testing the nicknames because we don't actually care
-        # about Google Docs.
-        
-    def test_parenthesis_are_removed2(self):
+        # about Google Docs here
+
+    def test_duplicate_parenthesis_are_removed_from_name(self):
         hn = HumanName("John Jones (Google Docs), Jr. (Unknown)")
         self.m(hn.first, "John", hn)
         self.m(hn.last, "Jones", hn)
         self.m(hn.suffix, "Jr.", hn)
 
+    def test_parenthesis_and_quotes_together(self):
+        hn = HumanName("Jennifer 'Jen' Jones (Duff)")
+        self.m(hn.first, "Jennifer", hn)
+        self.m(hn.last, "Jones", hn)
+        self.m(hn.nickname, "Jen Duff", hn)
+
+
 
 class PrefixesTestCase(HumanNameTestBase):