Merge pull request #48 from Machine-Learning-for-Medical-Language/mikix/expose-bsv-paths

feat: add filesystem.covid_symptoms_path to get bsv path directly

Author: mikix

.gitignore

@@ -1,5 +1,6 @@
 # Project specific
 
+/.idea/
 example-output/
 example-phi-build/
 
@@ -233,4 +234,4 @@ fabric.properties
 .idea/httpRequests
 
 # Android studio 3.1+ serialized cache file
-.idea/caches/build_file_checksums.ser
+.idea/caches/build_file_checksums.ser

.pylintrc

@@ -432,6 +432,6 @@ valid-metaclass-classmethod-first-arg=mcs
 
 # Exceptions that will emit a warning when being caught. Defaults to
 # "Exception"
-overgeneral-exceptions=StandardError,
-                       Exception,
-                       BaseException
+overgeneral-exceptions=builtins.StandardError,
+                       builtins.Exception,
+                       builtins.BaseException

ctakesclient/__init__.py

@@ -1,6 +1,6 @@
 """Public API"""
 
-__version__ = "2.0.0"
+__version__ = "2.1.0"
 
 from . import client
 from . import filesystem

ctakesclient/filesystem.py

@@ -218,9 +218,19 @@ def _resource_file(filename: str) -> str:
     return os.path.join(os.path.dirname(__file__), "resources", filename)
 
 
+def covid_symptoms_path() -> str:
+    """Returns the path to a bsv file of covid symptoms"""
+    return _resource_file("covid_symptoms.bsv")
+
+
 def covid_symptoms() -> List[BsvConcept]:
     """Returns a list of known covid symptoms"""
-    return list_bsv_concept(_resource_file("covid_symptoms.bsv"))
+    return list_bsv_concept(covid_symptoms_path())
+
+
+def umls_semantic_groups_path() -> str:
+    """Returns the path to a bsv file of UMLS semantic groups"""
+    return _resource_file("SemGroups_2018.bsv")
 
 
 def umls_semantic_groups() -> List[BsvSemanticType]:
@@ -229,4 +239,4 @@ def umls_semantic_groups() -> List[BsvSemanticType]:
 
     See https://lhncbc.nlm.nih.gov/ii/tools/MetaMap/documentation/SemanticTypesAndGroups.html
     """
-    return list_bsv_semantics(_resource_file("SemGroups_2018.bsv"))
+    return list_bsv_semantics(umls_semantic_groups_path())

ctakesclient/text2fhir.py

@@ -237,7 +237,7 @@ def _nlp_polarity(polarity: Polarity) -> Extension:
 
 
 def _nlp_derivation_span(docref_id, span: Span) -> Extension:
-    return _nlp_derivation(docref_id=docref_id, offset=span.begin, length=(span.end - span.begin))
+    return _nlp_derivation(docref_id=docref_id, offset=span.begin, length=span.end - span.begin)
 
 
 def _nlp_derivation(docref_id, offset=None, length=None) -> Extension:

ctakesclient/typesystem.py

@@ -137,7 +137,7 @@ def parse_polarity(polarity) -> Polarity:
         elif polarity == 0:
             return Polarity.pos
         else:
-            raise Exception(f"polarity unknown: {polarity}")
+            raise ValueError(f"polarity unknown: {polarity}")
 
     @staticmethod
     def parse_mention(mention: str) -> UmlsTypeMention:

tests/test_filesystem.py

@@ -1,14 +1,30 @@
 """Tests for the filesystem module"""
 
+import os
 import unittest
 
+import ddt
+
 from ctakesclient import filesystem
 from tests.test_resources import PathResource
 
 
+@ddt.ddt
 class TestCovidSymptomsBSV(unittest.TestCase):
     """Test case for files loaded from bsv"""
 
+    @ddt.data(
+        filesystem.covid_symptoms_path,
+        filesystem.umls_semantic_groups_path,
+    )
+    def test_path_methods(self, method):
+        """Verify we hand out a bsv path correctly"""
+        path = method()
+        self.assertIsInstance(path, str)
+        self.assertTrue(path.endswith(".bsv"))
+        self.assertTrue(os.path.isabs(path))
+        self.assertTrue(os.path.isfile(path))
+
     def test_covid_symptom_concepts(self):
         """
         Symptoms of COVID-19