ner.fast tests

Author: sidxz

.github/workflows/ci.yml

@@ -19,7 +19,7 @@ jobs:
         run: uv python install 3.12
 
       - name: Install dependencies
-        run: uv sync --dev
+        run: uv sync --dev --extra fast --extra dataframe
 
       - name: Lint
         run: uv run ruff check structflo/ tests/

structflo/ner/fast/_loader.py

@@ -6,8 +6,6 @@
 import re
 from pathlib import Path
 
-import yaml
-
 from structflo.ner._entities import _ENTITY_CLASS_MAP
 
 logger = logging.getLogger(__name__)
@@ -41,6 +39,8 @@ def load_gazetteer(path: Path) -> tuple[str, list[str]]:
         Tuple of (entity_type, list_of_terms) where entity_type is derived
         from the filename stem.
     """
+    import yaml  # noqa: PLC0415
+
     entity_type = path.stem
     with open(path) as f:
         terms = yaml.safe_load(f)

structflo/ner/fast/_matcher.py

@@ -5,8 +5,6 @@
 import re
 from dataclasses import dataclass
 
-from rapidfuzz import fuzz
-
 from structflo.ner.fast._normalize import expand_variants, normalize
 
 
@@ -180,6 +178,8 @@ def _regex_match(self, text: str, occupied: set[int]) -> list[Match]:
 
     def _fuzzy_match(self, text: str, occupied: set[int]) -> list[Match]:
         """Phase 2: Fuzzy matching on unmatched tokens."""
+        from rapidfuzz import fuzz  # noqa: PLC0415
+
         matches: list[Match] = []
 
         for token_match in _TOKEN_RE.finditer(text):

tests/test_fast.py

@@ -7,7 +7,10 @@
 
 import pytest
 
-from structflo.ner._entities import (
+pytest.importorskip("rapidfuzz", reason="rapidfuzz required for fast NER tests")
+pytest.importorskip("yaml", reason="PyYAML required for fast NER tests")
+
+from structflo.ner._entities import (  # noqa: E402
     AccessionEntity,
     ChemicalEntity,
     DiseaseEntity,