style(fabric,core): satisfy ruff for CI — imports, docstrings, line length

sandeep-jay · sandeep-jay · commit de4995f54b5c · 2026-05-31T23:38:50.000-07:00
Pre-existing lint debt on the Spark-native tier that would fail core-pr-tests:
- sort imports (I001) in orchestration assets/checks/sensors + two tests
- collections.abc.Callable over typing.Callable (UP035) in fabric registry
- add docstrings: 4 package __init__, FabricPlatform.__init__, 4 silver_clinical
  builders, ValidationResult.fail/ok, capture_lineage.main
- wrap two &gt;100-char lines (fabric platform read pattern, gold procedures coalesce)
No behavior change. ruff check core fabric clean; 128 passed / 1 skipped.
diff --git a/core/orchestration/__init__.py b/core/orchestration/__init__.py
@@ -0,0 +1 @@
+"""Dagster orchestration (LocalLite) — the medallion as a software-defined asset graph."""
diff --git a/core/orchestration/dagster/assets.py b/core/orchestration/dagster/assets.py
@@ -32,13 +32,13 @@
 )
 from core.ingest.bronze_landing import cohort_files
 from core.ingest.dicom_index import DicomIndex
-from core.surfaces.cli.pipeline import _parse_cohort
+from core.orchestration.dagster.partitions import cohort_partitions
+from core.orchestration.dagster.resources import PlatformResource
 from core.platform.base import LakehousePlatform
 from core.preview import bundle_summary_md, gold_encounter_card, sample_md, schema_md
+from core.surfaces.cli.pipeline import _parse_cohort
 from core.transforms.fhir_parser import FHIRBundleParser
 from core.transforms.registry import SILVER_TABLES
-from core.orchestration.dagster.partitions import cohort_partitions
-from core.orchestration.dagster.resources import PlatformResource
 
 
 def _bronze_root(platform: LakehousePlatform):
diff --git a/core/orchestration/dagster/checks.py b/core/orchestration/dagster/checks.py
@@ -14,9 +14,9 @@
 
 from dagster import AssetCheckExecutionContext, AssetCheckResult, MetadataValue, asset_check
 
+from core.orchestration.dagster.resources import PlatformResource
 from core.transforms.registry import SILVER_TABLES
 from core.validation.validate import ValidationResult, validate_table
-from core.orchestration.dagster.resources import PlatformResource
 
 
 def _render_rules_table(result: ValidationResult) -> str:
diff --git a/core/orchestration/dagster/sensors.py b/core/orchestration/dagster/sensors.py
@@ -25,9 +25,9 @@
 )
 
 from core.ingest.bronze_landing import cohort_labels
-from core.transforms.registry import SILVER_TABLES
 from core.orchestration.dagster.partitions import COHORT_PARTITIONS_NAME, cohort_partitions
 from core.orchestration.dagster.resources import PlatformResource
+from core.transforms.registry import SILVER_TABLES
 
 #: Assets the sensor materializes per cohort: Bronze + every Silver table.
 #: Sourced from :data:`core.transforms.registry.SILVER_TABLES` so the selection
diff --git a/core/surfaces/__init__.py b/core/surfaces/__init__.py
@@ -0,0 +1 @@
+"""Execution surfaces for the LocalLite tier (e.g. the CLI pipeline)."""
diff --git a/core/surfaces/cli/__init__.py b/core/surfaces/cli/__init__.py
@@ -0,0 +1 @@
+"""CLI execution surface — Bronze → Silver → Gold pipeline orchestration."""
diff --git a/core/tests/test_docs_generated.py b/core/tests/test_docs_generated.py
@@ -5,8 +5,8 @@
 never silently drift from the registry.
 """
 
-from core.transforms.registry import SILVER_TABLES
 from core.scripts.gen_data_dictionary import OUTPUT_PATH, render
+from core.transforms.registry import SILVER_TABLES
 
 
 def test_data_dictionary_is_current():
diff --git a/core/tests/test_gold_encounter_summary.py b/core/tests/test_gold_encounter_summary.py
@@ -21,8 +21,8 @@
     SILVER_SOURCES,
     build_encounter_summary,
 )
-from core.transforms.registry import SILVER_TABLES
 from core.scripts.gen_corpus_schema import OUTPUT_PATH, _serialize, render_schema
+from core.transforms.registry import SILVER_TABLES
 
 INGEST_TS = datetime(2026, 5, 27, tzinfo=UTC)
 CREATED_TS = datetime(2026, 5, 27, 12, 0, tzinfo=UTC)
diff --git a/fabric/__init__.py b/fabric/__init__.py
@@ -0,0 +1 @@
+"""Fabric tier — independent Spark-native medallion implementation (ADR-022)."""
diff --git a/fabric/gold/encounter_summary.py b/fabric/gold/encounter_summary.py
@@ -197,7 +197,9 @@ def build_encounter_summary(
         F.coalesce(F.col("recent_labs"), F.array().cast(ArrayType(LAB_STRUCT))).alias(
             "recent_labs"
         ),
-        F.coalesce(F.col("procedures"), F.array().cast(ArrayType(StringType()))).alias("procedures"),
+        F.coalesce(F.col("procedures"), F.array().cast(ArrayType(StringType()))).alias(
+            "procedures"
+        ),
         F.col("soap_note_text"),
         F.col("soap_note_id"),
         F.col("ecg_finding"),
diff --git a/fabric/platform.py b/fabric/platform.py
@@ -53,6 +53,7 @@ def __init__(
         lakehouse_name: str | None = None,
         spark: Any | None = None,
     ) -> None:
+        """Store explicit workspace/lakehouse IDs + Spark session; else resolved from Spark conf."""
         self._workspace_id = workspace_id
         self._lakehouse_id = lakehouse_id
         self._lakehouse_name = lakehouse_name
@@ -177,7 +178,9 @@ def read_bronze_bundles_spark(
             raise RuntimeError(msg)
 
         fhir_root = self.storage_path("bronze", "fhir")
-        pattern = f"{fhir_root}/cohort={cohort}/*.json" if cohort else f"{fhir_root}/cohort=*/*.json"
+        pattern = (
+            f"{fhir_root}/cohort={cohort}/*.json" if cohort else f"{fhir_root}/cohort=*/*.json"
+        )
         df = (
             spark.read.text(pattern, wholetext=True)
             .withColumn("path", F.input_file_name())
diff --git a/fabric/scripts/capture_lineage.py b/fabric/scripts/capture_lineage.py
@@ -9,6 +9,7 @@
 
 
 def main() -> None:
+    """Entry point — capture Fabric Lakehouse lineage (stub, pending Session 5)."""
     raise NotImplementedError("Fabric lineage capture pending Session 5")
 
 
diff --git a/fabric/transforms/registry.py b/fabric/transforms/registry.py
@@ -6,9 +6,10 @@
 
 from __future__ import annotations
 
+from collections.abc import Callable
 from dataclasses import dataclass
 from datetime import datetime
-from typing import TYPE_CHECKING, Callable
+from typing import TYPE_CHECKING
 
 from fabric.transforms import (
     silver_clinical,
diff --git a/fabric/transforms/silver_clinical.py b/fabric/transforms/silver_clinical.py
@@ -58,6 +58,7 @@ def _code_coding0(col: Column) -> Column:
 
 
 def build_condition(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
+    """Build the Silver ``condition`` table from FHIR ``Condition`` resources."""
     resources = parse_bundles_to_resources(bundles_df)
     cond = resources.filter(F.col("r.resourceType") == "Condition")
     code0 = _code_coding0(F.col("r.code"))
@@ -102,6 +103,7 @@ def build_condition(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
 
 
 def build_observation(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
+    """Build the Silver ``observation`` table from FHIR ``Observation`` resources."""
     resources = parse_bundles_to_resources(bundles_df)
     obs = resources.filter(F.col("r.resourceType") == "Observation")
     code0 = _code_coding0(F.col("r.code"))
@@ -153,6 +155,7 @@ def build_observation(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
 
 
 def build_medication_request(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
+    """Build the Silver ``medication_request`` table from FHIR ``MedicationRequest`` resources."""
     resources = parse_bundles_to_resources(bundles_df)
     meds = resources.filter(F.col("r.resourceType") == "MedicationRequest")
     code0 = _code_coding0(F.col("r.medicationCodeableConcept"))
@@ -195,6 +198,7 @@ def build_medication_request(bundles_df: DataFrame, ingest_ts: datetime) -> Data
 
 
 def build_procedure(bundles_df: DataFrame, ingest_ts: datetime) -> DataFrame:
+    """Build the Silver ``procedure`` table from FHIR ``Procedure`` resources."""
     resources = parse_bundles_to_resources(bundles_df)
     proc = resources.filter(F.col("r.resourceType") == "Procedure")
     code0 = _code_coding0(F.col("r.code"))
diff --git a/fabric/validation/validate.py b/fabric/validation/validate.py
@@ -59,11 +59,13 @@ class ValidationResult:
     checks: list[CheckOutcome] = field(default_factory=list)
 
     def fail(self, check: str, name: str | None = None) -> None:
+        """Record a failed check and mark the overall result failed."""
         self.passed = False
         self.failed_checks.append(check)
         self.checks.append(CheckOutcome(name=name or check, passed=False, detail=check))
 
     def ok(self, name: str, detail: str) -> None:
+        """Record a passing check with a human-readable detail string."""
         self.checks.append(CheckOutcome(name=name, passed=True, detail=detail))
 
 

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+"""Dagster orchestration (LocalLite) — the medallion as a software-defined asset graph."""`
Original file line number	Diff line number	Diff line change
`@@ -25,9 +25,9 @@`
`25`	`25`	`)`
`26`	`26`
`27`	`27`	`from core.ingest.bronze_landing import cohort_labels`
`28`		`-from core.transforms.registry import SILVER_TABLES`
`29`	`28`	`from core.orchestration.dagster.partitions import COHORT_PARTITIONS_NAME, cohort_partitions`
`30`	`29`	`from core.orchestration.dagster.resources import PlatformResource`
	`30`	`+from core.transforms.registry import SILVER_TABLES`
`31`	`31`
`32`	`32`	`#: Assets the sensor materializes per cohort: Bronze + every Silver table.`
`33`	`33`	#: Sourced from :data:`core.transforms.registry.SILVER_TABLES` so the selection
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+"""Execution surfaces for the LocalLite tier (e.g. the CLI pipeline)."""`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+"""CLI execution surface — Bronze → Silver → Gold pipeline orchestration."""`
Original file line number	Diff line number	Diff line change
`@@ -21,8 +21,8 @@`
`21`	`21`	`SILVER_SOURCES,`
`22`	`22`	`build_encounter_summary,`
`23`	`23`	`)`
`24`		`-from core.transforms.registry import SILVER_TABLES`
`25`	`24`	`from core.scripts.gen_corpus_schema import OUTPUT_PATH, _serialize, render_schema`
	`25`	`+from core.transforms.registry import SILVER_TABLES`
`26`	`26`
`27`	`27`	`INGEST_TS = datetime(2026, 5, 27, tzinfo=UTC)`
`28`	`28`	`CREATED_TS = datetime(2026, 5, 27, 12, 0, tzinfo=UTC)`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+"""Fabric tier — independent Spark-native medallion implementation (ADR-022)."""`