Add NON_FIRST_NAME_PREFIXES as a static subset of PREFIXES (#121)

Author: derek73

nameparser/config/prefixes.py

@@ -1,3 +1,37 @@
+#: The sub-set of :py:data:`PREFIXES` that are *never* a standalone first name.
+#: A name that *starts* with one of these has no first name -- the whole thing
+#: is a surname (e.g. "de Mesnil" -> last name "de Mesnil"). Curated to exclude
+#: anything that can be a given name in some culture (`al`, `van`, `von`,
+#: `della`, `di`, `del`, `da`, `vander`, ...) and anything that is also a first
+#: name prefix (`abu`). When unsure, leave a word out: a missing member just
+#: means that name is not auto-fixed, whereas a wrong member misparses a real
+#: person. Must stay a subset of :py:data:`PREFIXES` and disjoint from
+#: :py:data:`~nameparser.config.first_name_prefixes.FIRST_NAME_PREFIXES`.
+NON_FIRST_NAME_PREFIXES = set([
+    "'t",
+    'af',
+    'auf',
+    'av',
+    'bint',
+    'de',
+    "de'",
+    'degli',
+    'dei',
+    'delle',
+    'delli',
+    'dello',
+    'dem',
+    'der',
+    'dos',
+    'het',
+    'ibn',
+    'op',
+    'ter',
+    'vd',
+    'vom',
+    'zu',
+])
+
 #: 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,
@@ -7,64 +41,47 @@
 #: appear after a prefixes. So in "pennie von bergen wessels MD", "von" will
 #: join with all following name pieces until the suffix "MD", resulting in the
 #: correct parsing of the last name "von bergen wessels".
-PREFIXES = set([
-    "'t",
+#:
+#: Defined as a static union so every :py:data:`NON_FIRST_NAME_PREFIXES` member
+#: is guaranteed to also be a prefix (and still join forward), with no drift --
+#: mirroring ``TITLES = FIRST_NAME_TITLES | {...}`` in
+#: :py:mod:`nameparser.config.titles`.
+PREFIXES = NON_FIRST_NAME_PREFIXES | set([
     'aan',
     'aen',
     'abu',
-    'af',
     'al',
-    'auf',
-    'av',
     'bar',
     'bat',
     'bin',
-    'bint',
     'bon',
     'da',
     'dal',
-    'de',
-    "de'",
-    'degli',
-    'dei',
     'del',
     'dela',
     'della',
-    'delle',
-    'delli',
-    'dello',
-    'dem',
     'den',
-    'der',
     'di',
     'dí',
     'do',
-    'dos',
     'du',
     'freiherr',
     'freiherrin',
     'heer',
-    'het',
-    'ibn',
     'la',
     'le',
     'mac',
     'mc',
-    'op',
     'san',
     'santa',
     'st',
     'ste',
     'te',
-    'ter',
     'tho',
     'thoe',
     'van',
     'vande',
     'vander',
-    'vd',
     'vel',
-    'vom',
     'von',
-    'zu',
 ])

tests/test_prefixes.py

@@ -1,6 +1,8 @@
 import pytest
 
 from nameparser import HumanName
+from nameparser.config.prefixes import PREFIXES, NON_FIRST_NAME_PREFIXES
+from nameparser.config.first_name_prefixes import FIRST_NAME_PREFIXES
 
 from tests.base import HumanNameTestBase
 
@@ -163,6 +165,25 @@ def test_comma_three_conjunctions(self) -> None:
         self.m(hn.middle, "Q. Xavier", hn)
         self.m(hn.suffix, "III", hn)
 
+    def test_non_first_name_prefixes_subset_of_prefixes(self) -> None:
+        # Every non-first-name prefix must still be a prefix so it joins forward.
+        self.assertTrue(NON_FIRST_NAME_PREFIXES <= PREFIXES)
+
+    def test_non_first_name_prefixes_disjoint_from_first_name_prefixes(self) -> None:
+        # A word cannot be both "joins to the first name" and "never a first
+        # name" (e.g. 'abu' is a first_name_prefix, so it is excluded here).
+        self.assertEqual(NON_FIRST_NAME_PREFIXES & FIRST_NAME_PREFIXES, set())
+
+    def test_non_first_name_prefixes_expected_members(self) -> None:
+        # 'abu' is in PREFIXES but excluded (it is a first_name_prefix);
+        # 'von'/'van'/'della'/'di'/'del' are excluded (they can be first names).
+        self.assertIn('de', NON_FIRST_NAME_PREFIXES)
+        self.assertIn('dos', NON_FIRST_NAME_PREFIXES)
+        self.assertNotIn('abu', NON_FIRST_NAME_PREFIXES)
+        self.assertNotIn('von', NON_FIRST_NAME_PREFIXES)
+        self.assertNotIn('van', NON_FIRST_NAME_PREFIXES)
+        self.assertNotIn('della', NON_FIRST_NAME_PREFIXES)
+
 
 class LastNamePrefixSplitTestCase(HumanNameTestBase):