mostlyright-data 0.16.2__tar.gz → 0.16.3__tar.gz

{mostlyright_data-0.16.2 → mostlyright_data-0.16.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mostlyright-data
-Version: 0.16.2
+Version: 0.16.3
 Summary: Mostly Right CLI for reproducible, reviewed Parquet datasets
 Project-URL: Homepage, https://mostlyright.md/
 Project-URL: Documentation, https://mostlyright.md/docs/guides/cli/

{mostlyright_data-0.16.2 → mostlyright_data-0.16.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mostlyright-data"
-version = "0.16.2"
+version = "0.16.3"
 description = "Mostly Right CLI for reproducible, reviewed Parquet datasets"
 readme = "README.md"
 requires-python = ">=3.13,<3.14"

{mostlyright_data-0.16.2 → mostlyright_data-0.16.3}/src/mostlyright/data_harness/acquisition/parsing.py

@@ -47,6 +47,7 @@ _FORBIDDEN_REFERENCE_KEYS = frozenset(
 _SAFE_COLUMN = re.compile(r"^[^\x00-\x1f\x7f]{1,256}$")
 _ISO_DATE = re.compile(r"\d{4}-\d{2}-\d{2}\Z")
 _ISO_TIMESTAMP = re.compile(r"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:\.\d{1,6})?Z\Z")
+_ISO_SPACE_MINUTE_TIMESTAMP = re.compile(r"\d{4}-\d{2}-\d{2} \d{2}:\d{2}\Z")
 _MAX_REUSABLE_CSV_ROW_BYTES = 256 * 1024
 _STREAMING_ROW_HASH_BATCH_ROWS = 1_024
 # One input character can become a six-byte JSON escape; the per-row estimate also includes the
@@ -1084,17 +1085,25 @@ def _partition_key_and_date(value: str, *, encoding: str) -> tuple[str, datetime
         raise AcquisitionSecurityError(
             "WINDOW_STREAM_PARTITION", "partition value is not a canonical date"
         )
-    if encoding == "iso_date_prefix" and value != key and _ISO_TIMESTAMP.fullmatch(value) is None:
-        raise AcquisitionSecurityError(
-            "WINDOW_STREAM_PARTITION", "partition value is not canonical"
-        )
     if encoding == "iso_date_prefix" and value != key:
-        try:
-            datetime.datetime.fromisoformat(value)
-        except ValueError:
+        if _ISO_TIMESTAMP.fullmatch(value) is not None:
+            try:
+                datetime.datetime.fromisoformat(value)
+            except ValueError:
+                raise AcquisitionSecurityError(
+                    "WINDOW_STREAM_PARTITION", "partition timestamp is not real"
+                ) from None
+        elif _ISO_SPACE_MINUTE_TIMESTAMP.fullmatch(value) is not None:
+            try:
+                datetime.datetime.strptime(value, "%Y-%m-%d %H:%M")
+            except ValueError:
+                raise AcquisitionSecurityError(
+                    "WINDOW_STREAM_PARTITION", "partition timestamp is not real"
+                ) from None
+        else:
             raise AcquisitionSecurityError(
-                "WINDOW_STREAM_PARTITION", "partition timestamp is not real"
-            ) from None
+                "WINDOW_STREAM_PARTITION", "partition value is not canonical"
+            )
     return (key, parsed_date)
 
 

{mostlyright_data-0.16.2 → mostlyright_data-0.16.3}/src/mostlyright/data_harness/hosted_run_worker.py

@@ -8660,7 +8660,14 @@ def _run_source_collection(
         )
     artifact_id = artifact_id_for(job, "source_bundle", collection.collection_id)
     payload = ArtifactPayload(
-        "source_bundle", SOURCE_BUNDLE_MEDIA_TYPE, artifact_id, content=bundle
+        "source_bundle",
+        SOURCE_BUNDLE_MEDIA_TYPE,
+        artifact_id,
+        content=bundle,
+        # Studio reserves every source bundle under the final canonical USTAR digest.
+        # This is the bundle reservation key, not the collection id used to derive the
+        # artifact id above.
+        part_key=sha256_bytes(bundle),
     )
     stage.set("persist")
     measure_phase_call(

{mostlyright_data-0.16.2 → mostlyright_data-0.16.3}/src/mostlyright/data_harness/hosted_worker.py

@@ -3105,8 +3105,8 @@ class ArtifactPayload:
     #: rather than derived here so a part is not hashed twice: the sink hashed it as it closed it.
     path_digest: str = ""
     path_size_bytes: int = 0
-    #: The key that makes this artifact one of many of its kind within a run. Empty for every
-    #: kind but ``table_part``.
+    #: The key that makes a repeatable artifact unique within a run. Empty except for
+    #: ``table_part`` and ``source_bundle``.
     part_key: str = ""
     part_stats: Mapping[str, Any] | None = None