dapla-toolbelt-metadata 0.2.3__tar.gz → 0.2.5__tar.gz

{dapla_toolbelt_metadata-0.2.3 → dapla_toolbelt_metadata-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dapla-toolbelt-metadata
-Version: 0.2.3
+Version: 0.2.5
 Summary: Dapla Toolbelt Metadata
 Home-page: https://github.com/statisticsnorway/dapla-toolbelt-metadata
 License: MIT
@@ -17,7 +17,6 @@ Requires-Dist: arrow (>=1.3.0)
 Requires-Dist: beautifulsoup4 (>=4.12.3)
 Requires-Dist: cloudpathlib[gs] (>=0.17.0)
 Requires-Dist: dapla-toolbelt (>=3.0.1)
-Requires-Dist: google-auth-stubs (>=0.3.0,<0.4.0)
 Requires-Dist: pandas (>=1.4.2)
 Requires-Dist: pyarrow (>=8.0.0)
 Requires-Dist: pydantic (>=2.5.2)

{dapla_toolbelt_metadata-0.2.3 → dapla_toolbelt_metadata-0.2.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dapla-toolbelt-metadata"
-version = "0.2.3"
+version = "0.2.5"
 description = "Dapla Toolbelt Metadata"
 authors = ["Team Metadata <metadata@ssb.no>"]
 license = "MIT"
@@ -30,7 +30,6 @@ pyjwt = ">=2.8.0"
 ssb-klass-python = ">=0.0.9"
 ssb-datadoc-model = "^6.0.0"
 typing-extensions = ">=4.12.2"
-google-auth-stubs = "^0.3.0"
 
 [tool.poetry.group.dev.dependencies]
 black = ">=24.8.0"

{dapla_toolbelt_metadata-0.2.3 → dapla_toolbelt_metadata-0.2.5}/src/dapla_metadata/datasets/dapla_dataset_path_info.py

@@ -141,6 +141,9 @@ class SsbDateFormat(DateFormat):
 
             >>> SSB_BIMESTER.get_floor("2003B4")
             datetime.date(2003, 7, 1)
+
+            >>> SSB_BIMESTER.get_floor("2003-B4")
+            datetime.date(2003, 7, 1)
         """
         try:
             year = period_string[:4]
@@ -170,6 +173,9 @@ class SsbDateFormat(DateFormat):
 
             >>> SSB_HALF_YEAR.get_ceil("2024H1")
             datetime.date(2024, 6, 30)
+
+            >>> SSB_HALF_YEAR.get_ceil("2024-H1")
+            datetime.date(2024, 6, 30)
         """
         try:
             year = period_string[:4]
@@ -182,7 +188,7 @@ class SsbDateFormat(DateFormat):
 
 SSB_BIMESTER = SsbDateFormat(
     name="SSB_BIMESTER",
-    regex_pattern=r"^\d{4}[B]\d{1}$",
+    regex_pattern=r"^\d{4}-?[B]\d{1}$",
     arrow_pattern="YYYYMM",
     timeframe="month",
     ssb_dates={
@@ -215,7 +221,7 @@ SSB_BIMESTER = SsbDateFormat(
 
 SSB_QUARTERLY = SsbDateFormat(
     name="SSB_QUARTERLY",
-    regex_pattern=r"^\d{4}[Q]\d{1}$",
+    regex_pattern=r"^\d{4}-?[Q]\d{1}$",
     arrow_pattern="YYYYMM",
     timeframe="month",
     ssb_dates={
@@ -240,7 +246,7 @@ SSB_QUARTERLY = SsbDateFormat(
 
 SSB_TRIANNUAL = SsbDateFormat(
     name="SSB_TRIANNUAL",
-    regex_pattern=r"^\d{4}[T]\d{1}$",
+    regex_pattern=r"^\d{4}-?[T]\d{1}$",
     arrow_pattern="YYYYMM",
     timeframe="month",
     ssb_dates={
@@ -260,7 +266,7 @@ SSB_TRIANNUAL = SsbDateFormat(
 )
 SSB_HALF_YEAR = SsbDateFormat(
     name="SSB_HALF_YEAR",
-    regex_pattern=r"^\d{4}[H]\d{1}$",
+    regex_pattern=r"^\d{4}-?[H]\d{1}$",
     arrow_pattern="YYYYMM",
     timeframe="month",
     ssb_dates={
@@ -413,6 +419,9 @@ class DaplaDatasetPathInfo:
             >>> DaplaDatasetPathInfo._extract_period_strings(['p1990Q1', 'kommune', 'v1'])
             ['1990Q1']
 
+            >>> DaplaDatasetPathInfo._extract_period_strings(['p1990-Q1', 'kommune', 'v1'])
+            ['1990-Q1']
+
             >>> DaplaDatasetPathInfo._extract_period_strings(['varehandel','v1'])
             []
         """
@@ -586,6 +595,9 @@ class DaplaDatasetPathInfo:
             >>> DaplaDatasetPathInfo('klargjorte_data/person_data_v1.parquet').dataset_state
             <DataSetState.PROCESSED_DATA: 'PROCESSED_DATA'>
 
+            >>> DaplaDatasetPathInfo('klargjorte-data/person_data_v1.parquet').dataset_state
+            <DataSetState.PROCESSED_DATA: 'PROCESSED_DATA'>
+
             >>> DaplaDatasetPathInfo('utdata/min_statistikk/person_data_v1.parquet').dataset_state
             <DataSetState.OUTPUT_DATA: 'OUTPUT_DATA'>
 

{dapla_toolbelt_metadata-0.2.3 → dapla_toolbelt_metadata-0.2.5}/src/dapla_metadata/datasets/dataset_parser.py

@@ -179,11 +179,11 @@ class DatasetParserParquet(DatasetParser):
     def get_fields(self) -> list[Variable]:
         """Extract the fields from this dataset."""
         with self.dataset.open(mode="rb") as f:
-            schema: pa.Schema = pq.read_schema(f)  # type: ignore [arg-type]
+            schema: pa.Schema = pq.read_schema(f)  # type: ignore [arg-type, assignment]
         return [
             Variable(
                 short_name=data_field.name.strip(),
-                data_type=self.transform_data_type(str(data_field.type)),
+                data_type=self.transform_data_type(str(data_field.type)),  # type: ignore [attr-defined]
             )
             for data_field in schema
             if data_field.name

{dapla_toolbelt_metadata-0.2.3 → dapla_toolbelt_metadata-0.2.5}/src/dapla_metadata/datasets/utility/utils.py

@@ -5,7 +5,6 @@ import logging
 import pathlib
 import uuid
 
-import google.auth
 from cloudpathlib import CloudPath
 from cloudpathlib import GSClient
 from cloudpathlib import GSPath
@@ -52,11 +51,7 @@ def normalize_path(path: str) -> pathlib.Path | CloudPath:
         Pathlib compatible object.
     """
     if path.startswith(GSPath.cloud_prefix):
-        try:
-            credentials, _ = google.auth.default()
-            client = GSClient(credentials=credentials)
-        except google.auth.exceptions.DefaultCredentialsError:
-            client = GSClient(credentials=AuthClient.fetch_google_credentials())
+        client = GSClient(credentials=AuthClient.fetch_google_credentials())
         return GSPath(path, client=client)
     return pathlib.Path(path)