databricks-schema 0.6.0__tar.gz → 0.6.1__tar.gz

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/.gitignore

@@ -10,4 +10,7 @@ wheels/
 .venv
 
 # Tests
-.test_output/
+.test_output/
+
+# Claude Code
+.claude/

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: databricks-schema
-Version: 0.6.0
+Version: 0.6.1
 Summary: Databricks Unity Catalog schema extractor
 Project-URL: Repository, https://github.com/frizzleqq/databricks-schema
 Project-URL: Issues, https://github.com/frizzleqq/databricks-schema/issues

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/databricks_schema/extractor.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import logging
 from collections.abc import Iterator
 from concurrent.futures import ThreadPoolExecutor
+from urllib.parse import quote
 
 from databricks.sdk import WorkspaceClient
 from databricks.sdk.errors import NotFound
@@ -22,7 +23,10 @@ class CatalogExtractor:
     def _fetch_tags(self, entity_type: str, entity_name: str) -> dict[str, str]:
         tags: dict[str, str] = {}
         try:
-            for assignment in self.client.entity_tag_assignments.list(entity_type, entity_name):
+            # Percent-encode entity_name so special characters (e.g. slashes in column names)
+            # don't break URL path routing. Dots are safe — they're the UC name separators.
+            encoded_name = quote(entity_name, safe=".")
+            for assignment in self.client.entity_tag_assignments.list(entity_type, encoded_name):
                 key = getattr(assignment, "tag_key", None)
                 value = getattr(assignment, "tag_value", None)
                 if key is not None:

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/pyproject.toml

@@ -7,7 +7,7 @@ packages = ["databricks_schema"]
 
 [project]
 name = "databricks-schema"
-version = "0.6.0"
+version = "0.6.1"
 description = "Databricks Unity Catalog schema extractor"
 readme = "README.md"
 requires-python = ">=3.11"

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/tests/test_extractor.py

@@ -398,6 +398,33 @@ class TestCatalogExtractor:
 
         client.tables.get.assert_not_called()
 
+    def test_column_tags_slash_in_name(self):
+        """Column names containing slashes must be percent-encoded before tag lookup."""
+        extractor, client = self._extractor()
+        sdk_catalog = MagicMock()
+        sdk_catalog.comment = None
+        client.catalogs.get.return_value = sdk_catalog
+
+        s = MagicMock()
+        s.name = "main"
+        s.comment = None
+        s.owner = None
+        client.schemas.list.return_value = [s]
+
+        col = _make_col("/example/column", position=1, type_text="STRING")
+        sdk_table = _make_sdk_table("orders", columns=[col])
+        client.tables.list.return_value = [sdk_table]
+
+        def mock_list(entity_type, entity_name):
+            if entity_type == "columns" and entity_name == "mycat.main.orders.%2Fexample%2Fcolumn":
+                return [_make_tag("sensitivity", "high")]
+            return []
+
+        client.entity_tag_assignments.list.side_effect = mock_list
+
+        catalog = extractor.extract_catalog("mycat")
+        assert catalog.schemas[0].tables[0].columns[0].tags == {"sensitivity": "high"}
+
     def test_parallel_extraction(self):
         """With max_workers > 1, all tables are still extracted correctly."""
         extractor, client = self._extractor(max_workers=4)

{databricks_schema-0.6.0 → databricks_schema-0.6.1}/uv.lock

@@ -233,7 +233,7 @@ wheels = [
 
 [[package]]
 name = "databricks-schema"
-version = "0.6.0"
+version = "0.6.1"
 source = { editable = "." }
 dependencies = [
     { name = "databricks-sdk" },