acryl-datahub 1.0.0.3rc8__py3-none-any.whl → 1.0.0.3rc10__py3-none-any.whl

datahub/metadata/schema_classes.py

@@ -20,16 +20,16 @@ from datahub.utilities._custom_package_loader import get_custom_models_package
 _custom_package_path = get_custom_models_package()
 
 if TYPE_CHECKING or not _custom_package_path:
-    from ._schema_classes import *
+    from ._internal_schema_classes import *
 
     # Required explicitly because __all__ doesn't include _ prefixed names.
-    from ._schema_classes import __SCHEMA_TYPES
+    from ._internal_schema_classes import __SCHEMA_TYPES
 
     if IS_SPHINX_BUILD:
         # Set __module__ to the current module so that Sphinx will document the
         # classes as belonging to this module instead of the custom package.
         for _cls in list(globals().values()):
-            if hasattr(_cls, "__module__") and "datahub.metadata._schema_classes" in _cls.__module__:
+            if hasattr(_cls, "__module__") and "datahub.metadata._internal_schema_classes" in _cls.__module__:
                 _cls.__module__ = __name__
 else:
     _custom_package = importlib.import_module(_custom_package_path)

datahub/metadata/schemas/__init__.py

@@ -15,10 +15,10 @@ import pathlib
 def _load_schema(schema_name: str) -> str:
     return (pathlib.Path(__file__).parent / f"{schema_name}.avsc").read_text()
 
-def getMetadataChangeProposalSchema() -> str:
-    return _load_schema("MetadataChangeProposal")
-
 def getMetadataChangeEventSchema() -> str:
     return _load_schema("MetadataChangeEvent")
 
+def getMetadataChangeProposalSchema() -> str:
+    return _load_schema("MetadataChangeProposal")
+
 # fmt: on

datahub/specific/dataset.py

@@ -292,3 +292,15 @@ class DatasetPatchBuilder(
                 value=timestamp,
             )
         return self
+
+    def set_external_url(
+        self, external_url: Optional[str] = None
+    ) -> "DatasetPatchBuilder":
+        if external_url is not None:
+            self._add_patch(
+                DatasetProperties.ASPECT_NAME,
+                "add",
+                path=("externalUrl",),
+                value=external_url,
+            )
+        return self

datahub/testing/check_imports.py

@@ -9,7 +9,7 @@ def ensure_no_indirect_model_imports(dirs: List[pathlib.Path]) -> None:
     # If our needs become more complex, we should move to a proper linter.
     denied_imports = {
         "src.": "datahub.*",
-        "datahub.metadata._schema_classes": "datahub.metadata.schema_classes",
+        "datahub.metadata._internal_schema_classes": "datahub.metadata.schema_classes",
         "datahub.metadata._urns": "datahub.metadata.urns",
     }
     ignored_files = {

datahub/utilities/logging_manager.py

@@ -161,6 +161,7 @@ class _LogBuffer:
         self._buffer: Deque[str] = collections.deque(maxlen=maxlen)
 
     def write(self, line: str) -> None:
+        # We do not expect `line` to have a trailing newline.
         if len(line) > IN_MEMORY_LOG_BUFFER_MAX_LINE_LENGTH:
             line = line[:IN_MEMORY_LOG_BUFFER_MAX_LINE_LENGTH] + "[truncated]"
 
@@ -188,7 +189,13 @@ class _BufferLogHandler(logging.Handler):
             message = self.format(record)
         except TypeError as e:
             message = f"Error formatting log message: {e}\nMessage: {record.msg}, Args: {record.args}"
-        self._storage.write(message)
+
+        # For exception stack traces, the message is split over multiple lines,
+        # but we store it as a single string. Because we truncate based on line
+        # length, it's better for us to split it into multiple lines so that we
+        # don't lose any information on deeper stack traces.
+        for line in message.split("\n"):
+            self._storage.write(line)
 
 
 def _remove_all_handlers(logger: logging.Logger) -> None:

datahub/utilities/sqlalchemy_query_combiner.py

@@ -272,11 +272,10 @@ class SQLAlchemyQueryCombiner:
                     self.report.uncombined_queries_issued += 1
                     return _sa_execute_underlying_method(conn, query, *args, **kwargs)
 
-        with _sa_execute_method_patching_lock:
-            with unittest.mock.patch(
-                "sqlalchemy.engine.Connection.execute", _sa_execute_fake
-            ):
-                yield self
+        with _sa_execute_method_patching_lock, unittest.mock.patch(
+            "sqlalchemy.engine.Connection.execute", _sa_execute_fake
+        ):
+            yield self
 
     def run(self, method: Callable[[], None]) -> None:
         """

datahub/utilities/urn_encoder.py

@@ -4,7 +4,7 @@ from typing import List
 # NOTE: Frontend relies on encoding these three characters. Specifically, we decode and encode schema fields for column level lineage.
 # If this changes, make appropriate changes to datahub-web-react/src/app/lineage/utils/columnLineageUtils.ts
 # We also rely on encoding these exact three characters when generating schemaField urns in our graphQL layer. Update SchemaFieldUtils if this changes.
-# Also see https://datahubproject.io/docs/what/urn/#restrictions
+# Also see https://docs.datahub.com/docs/what/urn/#restrictions
 RESERVED_CHARS = {",", "(", ")", "␟"}
 RESERVED_CHARS_EXTENDED = RESERVED_CHARS.union({"%"})