Merge pull request #204 from derek73/simplify-1-3

Simplify pass over the changes since v1.2.1

Author: derek73

AGENTS.md

@@ -134,7 +134,7 @@ Add a dedicated `copy.deepcopy()` round-trip test for it too (see `test_regexes_
 
 **Cyrillic suffix regexes need `re.I` even when the pattern is suffix-only** — a Latin title-cased word (`Ivanovich`) keeps its suffix lowercase, so `re.I` seemed skippable; but an irregular Cyrillic suffix can be nearly the whole word (`ильич`), so title-casing capitalizes into the suffix itself (`Ильич`). `east_slavic_patronymic_cyrillic` shipped without `re.I` on the Latin reasoning and silently failed on capitalized irregular forms — don't assume Latin's title-case safety transfers to Cyrillic. (#185)
 
-**`suffix_not_acronyms` vs `is_an_initial` tension** — single-letter roman numeral suffixes (`i`, `v`) are in `suffix_not_acronyms` but also match the `is_an_initial` regex (single uppercase letter), so `is_suffix()` rejects them. Two separate code paths need context-aware workarounds: (1) suffix-comma detection uses `are_suffixes_after_comma()` which bypasses `is_suffix()` for `suffix_not_acronyms` members; (2) lastname-comma post-comma parsing uses `is_suffix_at_lastname_comma_end()` which only fires when `nxt is None` and `len(parts)==2` (no `parts[2]` suffix segment). See issues #136, #144.
+**`suffix_not_acronyms` vs `is_an_initial` tension** — single-letter roman numeral suffixes (`i`, `v`) are in `suffix_not_acronyms` but also match the `is_an_initial` regex (single uppercase letter), so `is_suffix()` rejects them. The lenient test lives in `is_suffix_lenient()`, which accepts `suffix_not_acronyms` members unconditionally and is only safe in unambiguous positions: (1) suffix-comma detection uses it via `are_suffixes_after_comma()`; (2) lastname-comma post-comma parsing uses it inline, only when `nxt is None` and `len(parts)==2` (no `parts[2]` suffix segment). See issues #136, #144.
 
 **Expected-failure tests use `@pytest.mark.xfail`** — the conftest parametrized fixture breaks `@unittest.expectedFailure`; always use `@pytest.mark.xfail` instead.
 

nameparser/config/__init__.py

@@ -140,40 +140,44 @@ def clear(self) -> Self:
 T = TypeVar('T')
 
 
+def _is_dunder(attr: str) -> bool:
+    # Dunder names are Python's protocol probes (copy looks up __deepcopy__,
+    # inspect.unwrap looks up __wrapped__, typing's GenericAlias.__call__ sets
+    # __orig_class__, ...), never config keys. The TupleManager attribute hooks
+    # all route dunders to normal object-attribute behavior so those probes
+    # work instead of being mistaken for dict entries.
+    return attr.startswith("__") and attr.endswith("__")
+
+
 class TupleManager(dict[str, T]):
     '''
-    A dictionary with dot.notation access. Subclass of ``dict``. Makes the tuple constants 
+    A dictionary with dot.notation access. Subclass of ``dict``. Makes the tuple constants
     more friendly.
     '''
 
     def __getattr__(self, attr: str) -> T | None:
-        # Dunder names are Python's protocol probes (copy looks up __deepcopy__,
-        # inspect.unwrap looks up __wrapped__, ...), never config keys. Report
-        # them as genuinely absent so hasattr() is honest and those probes work;
-        # otherwise the dict default is mistaken for a real protocol hook. See
-        # RegexTupleManager.__getattr__ for the concrete failure this prevents.
-        if attr.startswith("__") and attr.endswith("__"):
+        # Otherwise the dict default (None) is mistaken for a real protocol hook.
+        if _is_dunder(attr):
             raise AttributeError(attr)
         return self.get(attr)
 
     def __setattr__(self, attr: str, value: T) -> None:
-        # Dunder names are Python's protocol probes, not config keys -- same
-        # rationale as __getattr__ above. Concretely: constructing a
-        # subscripted generic, e.g. TupleManager[re.Pattern[str] | str](...),
-        # makes typing's GenericAlias.__call__ set `__orig_class__` on the new
-        # instance right after __init__ returns. Without this guard that
-        # assignment falls through to dict.__setitem__ and silently inserts a
-        # bogus '__orig_class__' entry into the dict itself, corrupting
-        # .values()/iteration. Fall back to normal object attribute storage
-        # for dunders; everything else keeps the dict-backed dot-notation
-        # behavior this class exists for.
-        if attr.startswith("__") and attr.endswith("__"):
+        # Fall back to normal object attribute storage for dunders; everything
+        # else keeps the dict-backed dot-notation behavior this class exists
+        # for. Concretely: constructing a subscripted generic, e.g.
+        # TupleManager[re.Pattern[str] | str](...), makes typing's
+        # GenericAlias.__call__ set `__orig_class__` on the new instance right
+        # after __init__ returns. Without this guard that assignment falls
+        # through to dict.__setitem__ and silently inserts a bogus
+        # '__orig_class__' entry into the dict itself, corrupting
+        # .values()/iteration.
+        if _is_dunder(attr):
             object.__setattr__(self, attr, value)
         else:
             self[attr] = value
 
     def __delattr__(self, attr: str) -> None:
-        if attr.startswith("__") and attr.endswith("__"):
+        if _is_dunder(attr):
             object.__delattr__(self, attr)
         else:
             del self[attr]
@@ -194,12 +198,9 @@ def __reduce__(self) -> tuple[type, tuple[()], Mapping[str, T]]:
 
 class RegexTupleManager(TupleManager[re.Pattern[str]]):
     def __getattr__(self, attr: str) -> re.Pattern[str]:
-        # Dunder names are Python's protocol probes (copy.deepcopy looks up
-        # __deepcopy__, inspect.unwrap looks up __wrapped__, ...), never regex
-        # keys. Report them as genuinely absent; otherwise the EMPTY_REGEX
-        # default is mistaken for a real protocol hook — e.g. copy.deepcopy
-        # tries to call the returned re.Pattern and raises TypeError.
-        if attr.startswith("__") and attr.endswith("__"):
+        # Otherwise EMPTY_REGEX is returned for a dunder probe; copy.deepcopy
+        # then tries to call the returned re.Pattern and raises TypeError.
+        if _is_dunder(attr):
             raise AttributeError(attr)
         return self.get(attr, EMPTY_REGEX)
 

nameparser/parser.py

@@ -663,43 +663,24 @@ def are_suffixes(self, pieces: Iterable[str]) -> bool:
                 return False
         return True
 
-    def are_suffixes_after_comma(self, pieces: Iterable[str]) -> bool:
-        """Like are_suffixes, but pieces found in suffix_not_acronyms are
-        accepted unconditionally without passing through is_suffix().
+    def is_suffix_lenient(self, piece: str) -> bool:
+        """Like is_suffix(), but suffix_not_acronyms members are accepted
+        unconditionally, bypassing is_suffix()'s is_an_initial() veto.
 
-        Used when detecting suffix-comma format (e.g. "John Ingram, V") where
-        the post-comma position is unambiguous. This covers all
-        suffix_not_acronyms members (i, ii, iii, iv, v, jr, sr, etc.),
-        case-insensitively, including single-letter entries that is_suffix()
-        would otherwise reject via is_an_initial().
+        This covers all suffix_not_acronyms members (i, ii, iii, iv, v, jr,
+        sr, etc.), case-insensitively, including single-letter entries that
+        is_suffix() would otherwise reject. Only safe for pieces in
+        unambiguous positions, e.g. after a comma ("John Ingram, V").
         """
-        for piece in pieces:
-            if lc(piece) in self.C.suffix_not_acronyms:
-                continue
-            if not self.is_suffix(piece):
-                return False
-        return True
-
-    def is_suffix_at_lastname_comma_end(self, piece: str, nxt: str | None, parts: list[str]) -> bool:
-        """True when ``piece`` is a suffix_not_acronyms member that should be
-        treated as a suffix at the end of ``parts[1]`` (the post-comma segment)
-        in a lastname-comma name, where ``parts`` is the full comma-split of the
-        name string.
-
-        Returns True only when all three conditions hold:
-        - ``nxt is None``: piece is the last token in the post-comma segment
-        - ``len(parts) == 2``: no ``parts[2]`` suffix segment exists
-        - ``lc(piece) in suffix_not_acronyms``
+        return lc(piece) in self.C.suffix_not_acronyms or self.is_suffix(piece)
 
-        When ``parts[2]`` exists the caller already declared an explicit suffix
-        via comma (e.g. 'Doe, Rev. John V, Jr.'), making the trailing token more
-        likely a middle initial; ``len(parts) == 2`` excludes that case.
-        Used as an OR alternative to ``is_suffix()`` for pieces that
-        ``is_suffix()`` would reject via ``is_an_initial()``.
+    def are_suffixes_after_comma(self, pieces: Iterable[str]) -> bool:
+        """Return True if all pieces are suffixes by the lenient
+        :py:func:`is_suffix_lenient` test. Used when detecting suffix-comma
+        format (e.g. "John Ingram, V") where the post-comma position is
+        unambiguous.
         """
-        return (nxt is None
-                and len(parts) == 2
-                and lc(piece) in self.C.suffix_not_acronyms)
+        return all(self.is_suffix_lenient(piece) for piece in pieces)
 
     def is_rootname(self, piece: str) -> bool:
         """
@@ -1147,7 +1128,16 @@ def parse_full_name(self) -> None:
                     if not self.first:
                         self.first_list.append(piece)
                         continue
-                    if self.is_suffix(piece) or self.is_suffix_at_lastname_comma_end(piece, nxt, parts):
+                    # A trailing token in a two-part lastname-comma name is
+                    # unambiguously positioned, so use the lenient test that
+                    # accepts suffix_not_acronyms members is_suffix() would
+                    # veto as initials. When parts[2] exists the caller
+                    # already declared an explicit suffix via comma (e.g.
+                    # 'Doe, Rev. John V, Jr.'), making the trailing token
+                    # more likely a middle initial.
+                    if self.is_suffix(piece) or \
+                            (nxt is None and len(parts) == 2
+                             and self.is_suffix_lenient(piece)):
                         self.suffix_list.append(piece)
                         continue
                     self.middle_list.append(piece)
@@ -1266,6 +1256,16 @@ def join_on_conjunctions(self, pieces: list[str], additional_parts_count: int =
         # refresh conjunction index locations
         conj_index = [i for i, piece in enumerate(pieces) if self.is_conjunction(piece)]
 
+        def register_joined_piece(new_piece: str, neighbor: str) -> None:
+            if self.is_title(neighbor):
+                # when joining to a title, make new_piece a title too
+                self.C.titles.add(new_piece)
+            if self.is_prefix(neighbor):
+                # when joining to a prefix, make new_piece a prefix too, so
+                # e.g. "von" + "und" bridges into "von und" and can still
+                # chain onto a following prefix/lastname (see "von und zu")
+                self.C.prefixes.add(new_piece)
+
         for i in conj_index:
             if len(pieces[i]) == 1 and total_length < 4 and pieces[i].isalpha():
                 # if there are only 3 total parts (minus known titles, suffixes
@@ -1276,14 +1276,7 @@ def join_on_conjunctions(self, pieces: list[str], additional_parts_count: int =
 
             if i == 0:
                 new_piece = " ".join(pieces[i:i+2])
-                if self.is_title(pieces[i+1]):
-                    # when joining to a title, make new_piece a title too
-                    self.C.titles.add(new_piece)
-                if self.is_prefix(pieces[i+1]):
-                    # when joining to a prefix, make new_piece a prefix too, so
-                    # e.g. "von" + "und" bridges into "von und" and can still
-                    # chain onto a following prefix/lastname (see "von und zu")
-                    self.C.prefixes.add(new_piece)
+                register_joined_piece(new_piece, pieces[i+1])
                 pieces[i] = new_piece
                 pieces.pop(i+1)
                 # subtract 1 from the index of all the remaining conjunctions
@@ -1293,14 +1286,7 @@ def join_on_conjunctions(self, pieces: list[str], additional_parts_count: int =
 
             else:
                 new_piece = " ".join(pieces[i-1:i+2])
-                if self.is_title(pieces[i-1]):
-                    # when joining to a title, make new_piece a title too
-                    self.C.titles.add(new_piece)
-                if self.is_prefix(pieces[i-1]):
-                    # when joining to a prefix, make new_piece a prefix too, so
-                    # e.g. "von" + "und" bridges into "von und" and can still
-                    # chain onto a following prefix/lastname (see "von und zu")
-                    self.C.prefixes.add(new_piece)
+                register_joined_piece(new_piece, pieces[i-1])
                 pieces[i-1] = new_piece
                 pieces.pop(i)
                 rm_count = 2
@@ -1372,10 +1358,10 @@ def cap_word(self, word: str, attribute: HumanNameAttributeT) -> str:
                 or self.is_conjunction(word):
             return word.lower()
         exceptions = self.C.capitalization_exceptions
-        if lc(word) in exceptions:
-            return exceptions[lc(word)]
-        if lc(word).replace('.', '') in exceptions:
-            return exceptions[lc(word).replace('.', '')]
+        key = lc(word)
+        for k in (key, key.replace('.', '')):
+            if k in exceptions:
+                return exceptions[k]
         mac_match = self.C.regexes.mac.match(word)
         if mac_match:
             def cap_after_mac(m: re.Match) -> str:

tests/base.py

@@ -1,6 +1,7 @@
-from typing import Generic, TypeVar
+from typing import Any, ClassVar, Generic, TypeVar
 
 from nameparser import HumanName
+from nameparser.config import Constants
 
 T = TypeVar('T')
 
@@ -51,3 +52,20 @@ def assertIsNone(self, expr: object, msg: object = None) -> None:
 
     def assertIsNotNone(self, expr: object, msg: object = None) -> None:
         assert expr is not None, msg or "unexpectedly None"
+
+
+class FlaggedConstantsTestBase(HumanNameTestBase[T]):
+    """Base for test classes that parse with a dedicated, flagged Constants.
+
+    Subclasses set ``constants_kwargs``; each test method gets a fresh
+    ``Constants(**constants_kwargs)`` via ``setup_method``, and ``hn()``
+    parses with it.
+    """
+
+    constants_kwargs: ClassVar[dict[str, Any]] = {}
+
+    def setup_method(self) -> None:
+        self.C = Constants(**self.constants_kwargs)
+
+    def hn(self, name: str) -> HumanName:
+        return HumanName(name, constants=self.C)

tests/test_east_slavic_patronymic_order.py

@@ -1,6 +1,6 @@
 from nameparser import HumanName
 from nameparser.config import Constants
-from tests.base import HumanNameTestBase
+from tests.base import FlaggedConstantsTestBase, HumanNameTestBase
 
 
 def test_latin_patronymic_matches() -> None:
@@ -49,14 +49,10 @@ def test_cyrillic_patronymic_rejects_non_patronymic() -> None:
     assert not C.regexes.east_slavic_patronymic_cyrillic.search("Иванов")
 
 
-class PatronymicNameOrderReorderTests(HumanNameTestBase):
+class PatronymicNameOrderReorderTests(FlaggedConstantsTestBase):
     """Names that SHOULD be rotated when the flag is on."""
 
-    def setup_method(self) -> None:
-        self.C = Constants(patronymic_name_order=True)
-
-    def hn(self, name: str) -> HumanName:
-        return HumanName(name, constants=self.C)
+    constants_kwargs = {"patronymic_name_order": True}
 
     def test_canonical_latin(self) -> None:
         n = self.hn("Ivanov Ivan Ivanovich")
@@ -121,14 +117,10 @@ def test_western_patronymic_surname_reordered_when_flag_on(self) -> None:
         assert n.last == "David"
 
 
-class PatronymicNameOrderGuardsTests(HumanNameTestBase):
+class PatronymicNameOrderGuardsTests(FlaggedConstantsTestBase):
     """Names that must NOT be reordered even when the flag is on."""
 
-    def setup_method(self) -> None:
-        self.C = Constants(patronymic_name_order=True)
-
-    def hn(self, name: str) -> HumanName:
-        return HumanName(name, constants=self.C)
+    constants_kwargs = {"patronymic_name_order": True}
 
     def test_already_correct_order(self) -> None:
         # middle is patronymic → already in Western order, do not rotate

tests/test_middle_name_as_last.py

@@ -1,6 +1,6 @@
 from nameparser import HumanName
 from nameparser.config import Constants
-from tests.base import HumanNameTestBase
+from tests.base import FlaggedConstantsTestBase, HumanNameTestBase
 
 
 class MiddleNameAsLastFlagTests(HumanNameTestBase):
@@ -20,13 +20,9 @@ def test_does_not_affect_other_instance(self) -> None:
         assert C2.middle_name_as_last is False
 
 
-class MiddleNameAsLastFoldTests(HumanNameTestBase):
+class MiddleNameAsLastFoldTests(FlaggedConstantsTestBase):
 
-    def setup_method(self) -> None:
-        self.C = Constants(middle_name_as_last=True)
-
-    def hn(self, name: str) -> HumanName:
-        return HumanName(name, constants=self.C)
+    constants_kwargs = {"middle_name_as_last": True}
 
     def test_fold_no_comma(self) -> None:
         n = self.hn("Mohamad Ahmad Ali Hassan")
@@ -98,17 +94,13 @@ def test_default_constants_unaffected(self) -> None:
         self.m(n.last, "Hassan", n)
 
 
-class MiddleNameAsLastWithPatronymicOrderTests(HumanNameTestBase):
+class MiddleNameAsLastWithPatronymicOrderTests(FlaggedConstantsTestBase):
     """Both localization flags on: patronymic reordering must settle
     first/middle/last before the fold collapses middle into last, per the
     design's stated ordering rationale (post_process() runs the patronymic
     hook before the middle_name_as_last hook)."""
 
-    def setup_method(self) -> None:
-        self.C = Constants(middle_name_as_last=True, patronymic_name_order=True)
-
-    def hn(self, name: str) -> HumanName:
-        return HumanName(name, constants=self.C)
+    constants_kwargs = {"middle_name_as_last": True, "patronymic_name_order": True}
 
     def test_rotate_then_fold_no_comma(self) -> None:
         # patronymic_name_order rotates "Ivanov Petr Sergeyevich" to

tests/test_prefixes.py

@@ -2,8 +2,7 @@
 
 from nameparser import HumanName
 from nameparser.config import CONSTANTS, Constants
-from nameparser.config.prefixes import PREFIXES, NON_FIRST_NAME_PREFIXES
-from nameparser.config.bound_first_names import BOUND_FIRST_NAMES
+from nameparser.config.prefixes import NON_FIRST_NAME_PREFIXES
 
 from tests.base import HumanNameTestBase
 
@@ -166,14 +165,9 @@ 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_bound_first_names(self) -> None:
-        # A word cannot be both "joins to the first name" and "never a first
-        # name" (e.g. 'abu' is a bound_first_name, so it is excluded here).
-        self.assertEqual(NON_FIRST_NAME_PREFIXES & BOUND_FIRST_NAMES, set())
+    # The subset-of-PREFIXES and disjoint-from-BOUND_FIRST_NAMES invariants
+    # are enforced by import-time asserts in nameparser/config/prefixes.py,
+    # so they are not repeated as tests here.
 
     def test_non_first_name_prefixes_expected_members(self) -> None:
         # 'abu' is in PREFIXES but excluded (it is a bound_first_name);

tests/test_suffixes.py

@@ -204,7 +204,8 @@ def test_roman_numeral_i_after_single_initial_lastname_comma_format(self) -> Non
     def test_roman_numeral_i_with_explicit_suffix_comma_known_limitation(self) -> None:
         # When an explicit suffix comma is present (len(parts)==3), the trailing 'I'
         # is conservatively left in middle to avoid misclassifying true initials.
-        # This is a known limitation of is_suffix_at_lastname_comma_end (issue #144).
+        # This is a known limitation of the lastname-comma lenient-suffix
+        # guard in parse_full_name (issue #144).
         hn = HumanName("Maier, Amy I, Jr.")
         self.m(hn.suffix, "I, Jr.", hn)