expansion(kRSGeneric): Fix double apostrophe values with kRSUnicode (…

…#304)
cihai · Dec 10, 2023 · f21e437 · f21e437
2 parents cd24cbc + 7a219a4
commit f21e437
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 2 deletions.
diff --git a/CHANGES b/CHANGES
@@ -19,6 +19,10 @@ $ pipx install --suffix=@next unihan-etl --pip-args '\--pre' --force
 
 <!-- Maintainers, insert changes / features for the next release here -->
 
+### Bug fix
+
+- Expansions: Fix loading of double apostrophe values via `kRSUnicode` via `kRSGeneric` (#304)
+
 ## unihan-etl 0.30.0post0 (2023-11-26)
 
 ### CI

diff --git a/src/unihan_etl/expansion.py b/src/unihan_etl/expansion.py
@@ -573,11 +573,18 @@ class kRSGenericDict(t.TypedDict):
 
 
 def _expand_kRSGeneric(value: t.List[str]) -> t.List[kRSGenericDict]:
-    """Expand kRSGeneric field."""
+    """Expand kRSGeneric field.
+
+    Examples
+    --------
+    >>> _expand_kRSGeneric(['5.10', "213''.0"])  # doctest: +NORMALIZE_WHITESPACE
+    [{'radical': 5, 'strokes': 10, 'simplified': False},
+    {'radical': 213, 'strokes': 0, 'simplified': False}]
+    """
     pattern = re.compile(
         r"""
         (?P<radical>[1-9][0-9]{0,2})
-        (?P<simplified>\'?)\.
+        (?P<simplified>\'{0,2})\.
         (?P<strokes>-?[0-9]{1,2})
     """,
         re.X,