Handle erroneous space in "Ph. D.", fix #43

Author: derek73

docs/release_log.rst

@@ -3,8 +3,8 @@ Release Log
 * 1.0.0 - August 30, 2018
     - Fix support for nicknames in single quotes (#74)
     - Change prefix handling to support prefixes on first names (#60)
-    - Fix prefix capitalization when not part of last name (#70)
-    - No other big changes, just bumping to v1 to indicate approprite project maturity
+    - Fix prefix capitalization when not part of lastname (#70)
+    - Handle erroneous space in "Ph. D." (#43)
 * 0.5.8 - August 19, 2018
     - Add "Junior" to suffixes (#76)
     - Add "dra" and "srta" to titles (#77)

nameparser/config/regexes.py

@@ -30,6 +30,7 @@
     ("no_vowels",re.compile(r'^[^aeyiuo]+$', re.I | re.U)),
     ("period_not_at_end",re.compile(r'.*\..+$', re.I | re.U)),
     ("emoji",re_emoji),
+    ("phd", re.compile(r'ph\.?\s+d\.?', re.I | re.U)),
 ])
 """
 All regular expressions used by the parser are precompiled and stored in the config.

nameparser/parser.py

@@ -361,17 +361,21 @@ def full_name(self, value):
 
     def collapse_whitespace(self, string):
         # collapse multiple spaces into single space
-        return self.C.regexes.spaces.sub(" ", string.strip())
-    
+        string =  self.C.regexes.spaces.sub(" ", string.strip())
+        if string.endswith(","):
+            string = string[:-1]
+        return string
+
     def pre_process(self):
         """
         
         This method happens at the beginning of the :py:func:`parse_full_name`
         before any other processing of the string aside from unicode
         normalization, so it's a good place to do any custom handling in a
-        subclass. Runs :py:func:`parse_nicknames`.
+        subclass. Runs :py:func:`parse_nicknames` and py:func:`squash_emoji`.
         
         """
+        self.fix_phd()
         self.parse_nicknames()
         self.squash_emoji()
 
@@ -382,6 +386,13 @@ def post_process(self):
         """
         self.handle_firstnames()
 
+    def fix_phd(self):
+        _re =  self.C.regexes.phd
+        match = _re.search(self._full_name)
+        if match:
+            self.suffix_list.append(match.group(0))
+            self._full_name = _re.sub('', self._full_name)
+
     def parse_nicknames(self):
         """
         The content of parenthesis or quotes in the name will be added to the 
@@ -780,7 +791,8 @@ def join_on_conjunctions(self, pieces, additional_parts_count=0):
     ### Capitalization Support
 
     def cap_word(self, word, attribute):
-        if (self.is_prefix(word) and attribute=='last') or self.is_conjunction(word):
+        if (self.is_prefix(word) and attribute in ('last','middle')) \
+                    or self.is_conjunction(word):
             return word.lower()
         exceptions = self.C.capitalization_exceptions
         if lc(word) in exceptions:

tests.py

@@ -1584,7 +1584,6 @@ def test_suffix_with_double_comma_format(self):
         self.m(hn.last, "Doe", hn)
         self.m(hn.suffix, "jr., MD", hn)
 
-    @unittest.expectedFailure
     def test_phd_with_erroneous_space(self):
         hn = HumanName("John Smith, Ph. D.")
         self.m(hn.first, "John", hn)