gen3-dataops-toolkit 5.0.0__tar.gz → 5.0.2__tar.gz

{gen3_dataops_toolkit-5.0.0 → gen3_dataops_toolkit-5.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gen3-dataops-toolkit
-Version: 5.0.0
+Version: 5.0.2
 Summary: Gen3 DataOps toolkit (g3dt): operate SSM-published Gen3 data pipeline environments
 License: Apache-2.0
 Author: JoshuaHarris391

{gen3_dataops_toolkit-5.0.0 → gen3_dataops_toolkit-5.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gen3-dataops-toolkit"
-version = "5.0.0"
+version = "5.0.2"
 description = "Gen3 DataOps toolkit (g3dt): operate SSM-published Gen3 data pipeline environments"
 authors = ["JoshuaHarris391 <harjo391@gmail.com>"]
 readme = "README.md"

{gen3_dataops_toolkit-5.0.0 → gen3_dataops_toolkit-5.0.2}/src/g3dt/cli/dict_cmds.py

@@ -37,6 +37,11 @@ def _version(env_cfg, override):
     return override or env_cfg.dictionary_version
 
 
+def _bare_version(v) -> str:
+    """``v1.2.0`` / ``1.2.0`` / ``V1.2.0`` -> ``1.2.0`` (None -> "")."""
+    return (v or "").strip().lstrip("vV")
+
+
 def warn_if_overridden(env_cfg, version: Optional[str]) -> None:
     """Say so, loudly, when the deployed version isn't the one SSM declares.
 
@@ -148,7 +153,9 @@ def status(
         stamp = deployed or "(no version stamp on the object)"
         when = uploaded.strftime("%Y-%m-%d %H:%M %Z") if hasattr(uploaded, "strftime") else uploaded
         typer.echo(f"deployed : {stamp}   (s3://{location}, uploaded {when})")
-        state = "in sync" if deployed == declared else "DRIFT"
+        # The S3 stamp is the JSON's _settings _dict_version (often "1.2.0")
+        # while the declared tag carries the git "v" prefix; the same version.
+        state = "in sync" if _bare_version(deployed) == _bare_version(declared) else "DRIFT"
     if state == "in sync":
         typer.secho("status   : in sync", fg=typer.colors.GREEN)
         return

{gen3_dataops_toolkit-5.0.0 → gen3_dataops_toolkit-5.0.2}/src/g3dt/utils/athena_utils.py

@@ -915,6 +915,28 @@ def write_gold_json_to_s3(
     logger.info(f"Object created at s3://{s3_bucket}/{s3_object_key}")
 
 
+def construct_data_import_order(s3_uri: str) -> list:
+    """Submission order (parents first) of the dictionary bundle at ``s3_uri``.
+
+    Kept for the aws-gen3-pipeline release-export Glue job
+    (``write_data_release_to_json.py``), which imports this name from here to
+    write each release's ``DataImportOrder.txt``. 5.0.0 moved the derivation
+    to :mod:`g3dt.import_order` and dropped the name, so any deployment with
+    ``toolkitVersion >= 5.0.0`` failed its release export with
+    ``ImportError: cannot import name 'construct_data_import_order'``.
+
+    Delegates to :func:`g3dt.import_order.derive_import_order` (a topological
+    sort of the raw bundle). Compared with the pre-5.0 gen3_validator order it
+    omits the unsubmittable ``program`` node and does not force
+    ``core_metadata_collection`` last; both are valid submission orders and
+    the upload only uses the file to sequence the node JSONs it finds.
+    """
+    from g3dt.import_order import derive_import_order
+    from g3dt.validate.validate import load_schema_from_s3_uri
+
+    return derive_import_order(load_schema_from_s3_uri(s3_uri))
+
+
 def write_release_jsons_to_s3(s3_bucket, release_id, study_id, table_name, json_data,
                               s3_client=None, key_prefix="release_jsons"):
     """