gen3-dataops-toolkit 3.7.1__tar.gz → 3.7.3__tar.gz

{gen3_dataops_toolkit-3.7.1 → gen3_dataops_toolkit-3.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gen3-dataops-toolkit
-Version: 3.7.1
+Version: 3.7.3
 Summary: Gen3 DataOps toolkit (g3dt): operate SSM-published Gen3 data pipeline environments
 License: Apache-2.0
 Author: JoshuaHarris391

{gen3_dataops_toolkit-3.7.1 → gen3_dataops_toolkit-3.7.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gen3-dataops-toolkit"
-version = "3.7.1"
+version = "3.7.3"
 description = "Gen3 DataOps toolkit (g3dt): operate SSM-published Gen3 data pipeline environments"
 authors = ["JoshuaHarris391 <harjo391@gmail.com>"]
 readme = "README.md"

{gen3_dataops_toolkit-3.7.1 → gen3_dataops_toolkit-3.7.3}/src/g3dt/cli/synth.py

@@ -503,7 +503,11 @@ def delete(
 
 @app.command(name="install-simulator")
 def install_simulator() -> None:
-    """Install the gen3-metadata-simulator generator (the 'synth' extra)."""
+    """Install or upgrade the gen3-metadata-simulator generator (the 'synth' extra)."""
     import sys
 
-    runner.run([sys.executable, "-m", "pip", "install", "gen3-metadata-simulator"])
+    # --upgrade so re-running after a simulator release actually updates it;
+    # without it pip leaves an existing (stale) install untouched.
+    runner.run(
+        [sys.executable, "-m", "pip", "install", "--upgrade", "gen3-metadata-simulator"]
+    )

{gen3_dataops_toolkit-3.7.1 → gen3_dataops_toolkit-3.7.3}/src/g3dt/services/synthetic_data/upload_synth_metadata_sheepdog.py

@@ -13,6 +13,19 @@ DEFAULT_REGION = "ap-southeast-2"
 DEFAULT_PROFILE = None  # ambient credentials unless --aws-profile is given
 DEFAULT_SUBMISSION_SIZE_KB = 50
 
+# Nodes never submitted from a synthetic batch. The first four are the
+# structural nodes MetadataSubmitter always excludes; core_metadata_collection
+# is excluded here too because the simulator fills its date-time fields with
+# random words, which Sheepdog rejects (400) — and synthetic data has no use
+# for it anyway.
+EXCLUDE_NODES = [
+    "program",
+    "project",
+    "acknowledgement",
+    "publication",
+    "core_metadata_collection",
+]
+
 def submit_synthetic_metadata(
     base_dir,
     project_id,
@@ -57,6 +70,7 @@ def submit_synthetic_metadata(
             table=None,
             athena_s3_output=None,
             max_size_kb=max_submission_size_kb,
+            exclude_nodes=EXCLUDE_NODES,
             aws_profile=aws_profile,
             upload_to_database=False,
         )