statcatlib 0.16.1__tar.gz → 0.16.2__tar.gz

{statcatlib-0.16.1 → statcatlib-0.16.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: statcatlib
-Version: 0.16.1
+Version: 0.16.2
 Summary: Queryable open data catalog engine for DCAT-AP, StatDCAT-AP, CKAN, and SDMX
 Keywords: sdmx,dcat,open-data,catalog,duckdb,statistical-data,ckan
 Author: gabrielgellner

{statcatlib-0.16.1 → statcatlib-0.16.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "statcatlib"
-version = "0.16.1"
+version = "0.16.2"
 description = "Queryable open data catalog engine for DCAT-AP, StatDCAT-AP, CKAN, and SDMX"
 license = "Apache-2.0"
 license-files = ["LICENSE"]

{statcatlib-0.16.1 → statcatlib-0.16.2}/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "statcatlib"
-version = "0.16.1"
+version = "0.16.2"
 description = "Queryable open data catalog engine for DCAT-AP, StatDCAT-AP, CKAN, and SDMX"
 license = "Apache-2.0"
 license-files = ["LICENSE"]

{statcatlib-0.16.1 → statcatlib-0.16.2}/src/statcatlib/cli/EGM.md

@@ -39,7 +39,7 @@ Commands:
 | `statcat verify-catalog PATH` | `verify_catalog` | `diagnostics.verify_catalog(path)` | any finding, each printed as `FAIL <file>: <detail>`; exit 2 on `CatalogUnreadableError`. Each stale data edition prints as `STALE <StaleEdition>` and leaves the exit code alone |
 | `statcat doctor PATH` | `doctor` | `diagnostics.doctor(path)` | the report holds a warning (topic `stale data editions`: a stale embargoed data edition is one; a stale live edition is `info` and leaves the exit code alone; topic `partials with no structure home`: each item is one) |
 | `statcat prune PATH --older-than DAYS --reason TEXT [--apply]` | `prune` | `sc.CatalogAdmin.open(path).prune(older_than=timedelta(days=DAYS), reason=TEXT, dry_run=not apply)` | `catalog.json` is missing, the catalog cannot be opened, the retire commit is refused, or a deletion failed (each printed as `FAIL <path>: <error>`) |
-| `statcat upload EDITION_DIR AZ_URL [--release-at TIME]` | `upload` | `upload_edition(edition_dir, location, release_at=)` | a finding, each printed as `FAIL <file>: <detail>`, or a `ManifestError`, `BlobStoreError` or `ClientAuthenticationError`, printed as `ERROR <message>`; exit 2 on a usage error, a bad `AZ_URL`, `s3://`, no `AZURE_STORAGE_ACCOUNT_NAME`, a refused `obstore` variable set, even empty, in any spelling `obstore` reads (`_REFUSED_VARIABLES`, matched by `_refused_variables`: `AZURE_` then any case), a naive time, or a missing `blob` extra |
+| `statcat upload EDITION_DIR AZ_URL [--release-at TIME]` | `upload` | `upload_edition(edition_dir, location, release_at=)` | a finding, each printed as `FAIL <file>: <detail>`, or a `ManifestError`, `BlobStoreError` or `ClientAuthenticationError`, printed as `ERROR <message>`; exit 2 on a usage error, a bad `AZ_URL`, `s3://`, no `AZURE_STORAGE_ACCOUNT_NAME`, a refused `obstore` variable set, even empty, in any spelling `obstore` reads (`_REFUSED_VARIABLES`, matched by `_refused_variables`: `AZURE_` then any case), a naive time, a missing `blob` extra, or an environment value `obstore` cannot parse, such as `AZURE_DISABLE_TAGGING=junk` (`GenericError` from the store build, before any request) |
 
 `build-index` options and their `WorkingCopy.build_index` keyword:
 
@@ -78,8 +78,10 @@ Private helpers that tests and later commands rely on:
   `_refused_variables()` lists the environment's names that `obstore` would parse as a
   refused key, as spelled. `_azure_location(uri, account)` builds the store with `obstore.store.from_url`,
   `TokenIdentity(AzureCredentialProvider(DefaultAzureCredential()))` and the one-hour
-  timeout; `upload` is the only code in statcatlib that reads the environment for a
-  store.
+  timeout, and turns obstore's `GenericError` from that build into `_usage`, with the text from
+  `_store_build_message(exc)`: obstore's first line, and the `AZURE_DISABLE_TAGGING` spelling the
+  environment sets, since obstore 0.12.1's message omits the variable. `upload` is the only code in
+  statcatlib that reads the environment for a store.
 - `_parse_codelist_policy(raw)` — accepts only mode `fts_only`
   (`_ACCEPTED_CODELIST_MODES`); raises `typer.BadParameter` otherwise.
 - `_parse_reference_metadata_blend(raw)` — `max_chars` must be a positive

{statcatlib-0.16.1 → statcatlib-0.16.2}/src/statcatlib/cli/__init__.py

@@ -669,22 +669,49 @@ def _azure_account() -> str:
 
 
 def _azure_location(uri: str, account: str) -> BlobLocation:
-    """The catalog at *uri*, reached with `DefaultAzureCredential`; a missing ``blob`` extra exits 2."""
+    """The catalog at *uri*, reached with `DefaultAzureCredential`.
+
+    A missing ``blob`` extra exits 2, and so does an environment value `obstore` cannot parse, such as
+    ``AZURE_DISABLE_TAGGING=junk``: obstore 0.12.1 raises `GenericError` from the store build, before any request.
+    """
     try:
         from azure.identity import DefaultAzureCredential  # noqa: PLC0415
         from obstore.auth.azure import AzureCredentialProvider  # noqa: PLC0415
+        from obstore.exceptions import GenericError  # noqa: PLC0415
         from obstore.store import from_url  # noqa: PLC0415
     except ImportError:
         _usage("upload needs the blob extra: uv add 'statcatlib[blob]' (or pip install 'statcatlib[blob]')")
-    store = from_url(
-        uri.removesuffix("/"),
-        account_name=account,
-        credential_provider=TokenIdentity(AzureCredentialProvider(DefaultAzureCredential())),
-        client_options={"timeout": _UPLOAD_TIMEOUT},
-    )
+    credential = TokenIdentity(AzureCredentialProvider(DefaultAzureCredential()))
+    try:
+        store = from_url(
+            uri.removesuffix("/"),
+            account_name=account,
+            credential_provider=credential,
+            client_options={"timeout": _UPLOAD_TIMEOUT},
+        )
+    except GenericError as exc:
+        _usage(_store_build_message(exc))
     return BlobLocation(uri, store)
 
 
+def _store_build_message(exc: Exception) -> str:
+    """The exit-2 text for a store build that failed on the environment.
+
+    obstore 0.12.1's message names the value and omits the variable, so the text names
+    ``AZURE_DISABLE_TAGGING`` when the environment sets it, in any case after ``AZURE_``.
+    """
+    reason = str(exc).splitlines()[0] if str(exc) else type(exc).__name__
+    message = f"obstore cannot build the store from the environment ({reason})"
+    tagging = sorted(
+        name
+        for name in os.environ
+        if name.startswith("AZURE_") and name.isascii() and name.lower() == "azure_disable_tagging"
+    )
+    if tagging:
+        message += f"; {', '.join(tagging)} takes true or false"
+    return message
+
+
 @app.command("upload")
 def upload(
     edition_dir: Path = typer.Argument(
@@ -709,8 +736,10 @@ def upload(
     release job. It exits 0 when the edition is uploaded, or already registered
     with the same bytes; 1 on any finding, each printed as ``FAIL <file>: <detail>``,
     or on a store or credential failure, printed as ``ERROR <message>``; and 2 on
-    a usage error, a missing ``blob`` extra, or any of these variables set, even
-    empty: ``AZURE_STORAGE_ACCOUNT_KEY``, ``AZURE_STORAGE_ACCESS_KEY``,
+    a usage error, a missing ``blob`` extra, an environment value ``obstore``
+    cannot parse, such as ``AZURE_DISABLE_TAGGING=junk``, or any of these
+    variables set, even empty: ``AZURE_STORAGE_ACCOUNT_KEY``,
+    ``AZURE_STORAGE_ACCESS_KEY``,
     ``AZURE_STORAGE_MASTER_KEY``, ``AZURE_STORAGE_SAS_KEY``,
     ``AZURE_STORAGE_SAS_TOKEN``, ``AZURE_STORAGE_TOKEN``,
     ``AZURE_STORAGE_ENDPOINT``, ``AZURE_ENDPOINT``,