dapla-toolbelt-metadata 0.4.2__tar.gz → 0.6.0__tar.gz

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/PKG-INFO

@@ -1,34 +1,34 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: dapla-toolbelt-metadata
-Version: 0.4.2
+Version: 0.6.0
 Summary: Dapla Toolbelt Metadata
-Home-page: https://github.com/statisticsnorway/dapla-toolbelt-metadata
 License: MIT
 Author: Team Metadata
 Author-email: metadata@ssb.no
-Requires-Python: >=3.10,<4.0
+Requires-Python: >=3.11,<4.0
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 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: pandas (>=1.4.2)
+Requires-Dist: google-auth (>=2.38.0)
+Requires-Dist: lxml (>=5.3.1)
 Requires-Dist: pyarrow (>=8.0.0)
 Requires-Dist: pydantic (>=2.5.2)
 Requires-Dist: pyjwt (>=2.8.0)
 Requires-Dist: python-dotenv (>=1.0.1)
 Requires-Dist: requests (>=2.31.0)
+Requires-Dist: ruamel-yaml (>=0.18.10)
 Requires-Dist: ssb-datadoc-model (>=6.0.0,<7.0.0)
-Requires-Dist: ssb-klass-python (>=0.0.9)
+Requires-Dist: ssb-klass-python (>=1.0.1)
 Requires-Dist: typing-extensions (>=4.12.2)
 Project-URL: Changelog, https://github.com/statisticsnorway/dapla-toolbelt-metadata/releases
 Project-URL: Documentation, https://statisticsnorway.github.io/dapla-toolbelt-metadata
+Project-URL: Homepage, https://github.com/statisticsnorway/dapla-toolbelt-metadata
 Project-URL: Repository, https://github.com/statisticsnorway/dapla-toolbelt-metadata
 Description-Content-Type: text/markdown
 
@@ -45,7 +45,6 @@ Description-Content-Type: text/markdown
 [![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=statisticsnorway_dapla-toolbelt-metadata&metric=alert_status&token=ee0a4d273db2bf811222fca5dffccd4592e3d536)][sonarquality]
 
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)][pre-commit]
-[![Black](https://img.shields.io/badge/code%20style-black-000000.svg)][black]
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)][poetry]
 
@@ -56,7 +55,6 @@ Description-Content-Type: text/markdown
 [sonarcov]: https://sonarcloud.io/summary/overall?id=statisticsnorway_dapla-toolbelt-metadata
 [sonarquality]: https://sonarcloud.io/summary/overall?id=statisticsnorway_dapla-toolbelt-metadata
 [pre-commit]: https://github.com/pre-commit/pre-commit
-[black]: https://github.com/psf/black
 [poetry]: https://python-poetry.org/
 
 Tools and clients for working with the Dapla Metadata system.

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/README.md

@@ -11,7 +11,6 @@
 [![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=statisticsnorway_dapla-toolbelt-metadata&metric=alert_status&token=ee0a4d273db2bf811222fca5dffccd4592e3d536)][sonarquality]
 
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)][pre-commit]
-[![Black](https://img.shields.io/badge/code%20style-black-000000.svg)][black]
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)][poetry]
 
@@ -22,7 +21,6 @@
 [sonarcov]: https://sonarcloud.io/summary/overall?id=statisticsnorway_dapla-toolbelt-metadata
 [sonarquality]: https://sonarcloud.io/summary/overall?id=statisticsnorway_dapla-toolbelt-metadata
 [pre-commit]: https://github.com/pre-commit/pre-commit
-[black]: https://github.com/psf/black
 [poetry]: https://python-poetry.org/
 
 Tools and clients for working with the Dapla Metadata system.

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dapla-toolbelt-metadata"
-version = "0.4.2"
+version = "0.6.0"
 description = "Dapla Toolbelt Metadata"
 authors = ["Team Metadata <metadata@ssb.no>"]
 license = "MIT"
@@ -16,23 +16,23 @@ packages = [{ include = "dapla_metadata", from = "src" }]
 Changelog = "https://github.com/statisticsnorway/dapla-toolbelt-metadata/releases"
 
 [tool.poetry.dependencies]
-python = ">=3.10,<4.0"
+python = ">=3.11,<4.0"
 pyarrow = ">=8.0.0"
 pydantic = ">=2.5.2"
-pandas = ">=1.4.2"
-dapla-toolbelt = ">=3.0.1"
 arrow = ">=1.3.0"
 python-dotenv = ">=1.0.1"
 requests = ">=2.31.0"
 beautifulsoup4 = ">=4.12.3"
 cloudpathlib = { extras = ["gs"], version = ">=0.17.0" }
 pyjwt = ">=2.8.0"
-ssb-klass-python = ">=0.0.9"
+ssb-klass-python = ">=1.0.1"
 ssb-datadoc-model = "^6.0.0"
 typing-extensions = ">=4.12.2"
+ruamel-yaml = ">=0.18.10"
+google-auth = ">=2.38.0"
+lxml = ">=5.3.1"
 
 [tool.poetry.group.dev.dependencies]
-black = ">=24.8.0"
 pygments = ">=2.18.0"
 coverage = { extras = ["toml"], version = ">=6.2" }
 faker = ">=26.1.0"
@@ -48,8 +48,8 @@ typeguard = ">=2.13.3"
 xdoctest = { extras = ["colors"], version = ">=0.15.10" }
 myst-parser = { version = ">=0.16.1" }
 mypy = ">=0.950"
+pandas = ">=1.4.2"
 pytest-cov = ">=3.0.0"
-nbstripout = "^0.8.1"
 python-kacl = "*"
 pytest-mock = ">=3.14.0"
 deptry = ">=0.12.0"
@@ -59,11 +59,13 @@ requests-mock = ">=1.12.1"
 types-Pygments = "*"
 types-colorama = "*"
 types-setuptools = "*"
+types-requests = "*"
 types-beautifulsoup4 = ">=4.12.0.20240511"
 ipykernel = "^6.29.5"
 rich = "^13.9.4"
 bpython = "^0.24"
 testcontainers = { version = "^4.8.2", extras = ["generic"] }
+pytest-asyncio = "^0.26.0"
 
 [tool.pytest.ini_options]
 pythonpath = ["src"]
@@ -78,19 +80,14 @@ source = ["dapla_metadata"]
 omit = [
     "tests/*",
     "__init__.py",
-    "*/dapla_metadata/variable_definitions/generated/*",
+    "*/dapla_metadata/variable_definitions/_generated/*",
 ]
 relative_files = true
 
 [tool.coverage.report]
 show_missing = true
 fail_under = 80
-omit = ["*/dapla_metadata/variable_definitions/generated/*"]
-
-[tool.black]
-# We don't want to format generated files because it creates large diffs
-# when generated code is updated.
-extend-exclude = "/generated/"
+omit = ["*/dapla_metadata/variable_definitions/_generated/*"]
 
 [tool.mypy]
 plugins = ["pydantic.mypy"]
@@ -100,10 +97,10 @@ pretty = true
 show_column_numbers = true
 show_error_context = true
 # Generated code is not high quality, just ignore the problems there
-exclude = "generated/vardef_client/.*"
+exclude = "_generated/vardef_client/.*"
 
 [[tool.mypy.overrides]]
-module = ["dapla_metadata.variable_definitions.generated.vardef_client.*"]
+module = ["dapla_metadata.variable_definitions._generated.vardef_client.*"]
 warn_unreachable = false
 ignore_errors = true
 disable_error_code = ["unreachable"]
@@ -121,8 +118,8 @@ module = [
     "datadoc_model.model",
     "pytest_mock",
     "testcontainers.*",
-    "yaml",
     "httpx",
+    "ruamel.*",
 ]
 ignore_missing_imports = true
 
@@ -141,7 +138,7 @@ disable_error_code = [
 force-exclude = true # Apply excludes to pre-commit
 show-fixes = true
 src = ["src", "tests"]
-target-version = "py310" # Minimum Python version supported
+target-version = "py311" # Minimum Python version supported
 include = ["*.py", "*.pyi", "**/pyproject.toml", "*.ipynb"]
 extend-exclude = [
     "__pycache__",
@@ -149,19 +146,23 @@ extend-exclude = [
     ".ipynb_checkpoints",
     "noxfile.py",
     "docs/conf.py",
+    "_generated/",
 ]
 
 # Ruff rules may be customized as desired: https://docs.astral.sh/ruff/rules/
 [tool.ruff.lint]
 select = ["ALL"]
 ignore = [
-    "ANN101", # Supress missing-type-self.
-    "ANN102", # Supress missing-type-cls.
-    "ANN202", # Don't requiere return type annotation for private functions.
-    "ANN401", # Allow type annotation with type Any.
-    "D100",   # Supress undocumented-public-module. Only doc of public api required.
-    "E402",   # Supress module-import-not-at-top-of-file, needed in jupyter notebooks.
-    "E501",   # Supress line-too-long warnings: trust black's judgement on this one.
+    "ANN202",  # Don't requiere return type annotation for private functions.
+    "ANN401",  # Allow type annotation with type Any.
+    "COM812",  # Suggested to ignore when using ruff format
+    "D100",    # Supress undocumented-public-module. Only doc of public api required.
+    "FBT001",  # Allow boolean positional arguments in a function.
+    "FBT002",  # Allow boolean default positional arguments in a function.
+    "FIX002",  # Don't fail on TODO as long as it's documented correctly.
+    "E402",    # Supress module-import-not-at-top-of-file, needed in jupyter notebooks.
+    "E501",    # Supress line-too-long warnings: trust black's judgement on this one.
+    "PLR2004", # Allow to compare with unnamed numerical constants.
 ]
 
 [tool.ruff.lint.isort]
@@ -176,6 +177,9 @@ convention = "google" # You can also use "numpy".
 [tool.ruff.lint.flake8-pytest-style]
 fixture-parentheses = false
 
+[tool.ruff.lint.pylint]
+max-args = 8
+
 [tool.ruff.lint.pep8-naming]
 classmethod-decorators = [
     "classmethod",

dapla_toolbelt_metadata-0.6.0/src/dapla_metadata/__init__.py

@@ -0,0 +1,15 @@
+"""Tools and clients for working with the Dapla Metadata system."""
+
+import warnings
+
+warnings.filterwarnings(
+    "ignore",
+    message="As the c extension couldn't be imported, `google-crc32c` is using a pure python implementation that is significantly slower.",
+)
+
+import datadoc_model.model as datadoc_model
+
+from . import dapla
+from . import datasets
+from . import standards
+from . import variable_definitions

dapla_toolbelt_metadata-0.6.0/src/dapla_metadata/dapla/__init__.py

@@ -0,0 +1,4 @@
+"""Expose information specific to the Dapla platform."""
+
+from .user_info import DaplaLabUserInfo
+from .user_info import UserInfo

{dapla_toolbelt_metadata-0.4.2/src/dapla_metadata/_shared → dapla_toolbelt_metadata-0.6.0/src/dapla_metadata/dapla}/user_info.py

@@ -13,9 +13,6 @@ from dapla_metadata._shared.enums import DaplaService
 logger = logging.getLogger(__name__)
 
 
-PLACEHOLDER_EMAIL_ADDRESS = "default_user@ssb.no"
-
-
 class UserInfo(Protocol):
     """Information about the current user.
 
@@ -27,6 +24,16 @@ class UserInfo(Protocol):
         """Get the short email address."""
         ...
 
+    @property
+    def current_group(self) -> str:
+        """Get the group which the user is currently representing."""
+        ...
+
+    @property
+    def current_team(self) -> str:
+        """Get the team which the user is currently representing."""
+        ...
+
 
 class UnknownUserInfo:
     """Fallback when no implementation is found."""
@@ -36,14 +43,38 @@ class UnknownUserInfo:
         """Unknown email address."""
         return None
 
+    @property
+    def current_group(self) -> str:
+        """Get the group which the user is currently representing."""
+        return ""
+
+    @property
+    def current_team(self) -> str:
+        """Get the team which the user is currently representing."""
+        return ""
+
 
 class TestUserInfo:
     """Information about the current user for local development and testing."""
 
+    PLACEHOLDER_EMAIL_ADDRESS = "default_user@ssb.no"
+    PLACEHOLDER_GROUP = "default-team-developers"
+    PLACEHOLDER_TEAM = "default-team"
+
     @property
     def short_email(self) -> str | None:
         """Get the short email address."""
-        return PLACEHOLDER_EMAIL_ADDRESS
+        return TestUserInfo.PLACEHOLDER_EMAIL_ADDRESS
+
+    @property
+    def current_group(self) -> str | None:
+        """Get the group which the user is currently representing."""
+        return TestUserInfo.PLACEHOLDER_GROUP
+
+    @property
+    def current_team(self) -> str | None:
+        """Get the team which the user is currently representing."""
+        return TestUserInfo.PLACEHOLDER_TEAM
 
 
 class DaplaLabUserInfo:
@@ -65,6 +96,19 @@ class DaplaLabUserInfo:
         )
         return None
 
+    @property
+    def current_group(self) -> str:
+        """Get the group which the user is currently representing."""
+        if group := config.get_dapla_group_context():
+            return group
+        msg = "DAPLA_GROUP_CONTEXT environment variable not found"
+        raise OSError(msg)
+
+    @property
+    def current_team(self) -> str:
+        """Get the team which the user is currently representing."""
+        return parse_team_name(self.current_group)
+
 
 class JupyterHubUserInfo:
     """Information about the current user when running on JupyterHub."""
@@ -74,6 +118,16 @@ class JupyterHubUserInfo:
         """Get the short email address."""
         return config.get_jupyterhub_user()
 
+    @property
+    def current_group(self) -> str:
+        """Get the group which the user is currently representing."""
+        raise NotImplementedError
+
+    @property
+    def current_team(self) -> str:
+        """Get the team which the user is currently representing."""
+        raise NotImplementedError
+
 
 def get_user_info_for_current_platform() -> UserInfo:
     """Return the correct implementation of UserInfo for the current platform."""
@@ -88,28 +142,20 @@ def get_user_info_for_current_platform() -> UserInfo:
         return UnknownUserInfo()
 
 
-def get_owner() -> str:
-    """Returns the owner read from the GROUP_CONTEXT environment variable."""
-    if group := config.get_dapla_group_context():
-        return parse_team_name(group)
-    msg = "DAPLA_GROUP_CONTEXT environment variable not found"
-    raise OSError(msg)
-
-
 def parse_team_name(group: str) -> str:
     """Parses the group to get the current team.
 
-    >>> parse_team_name(dapla-metadata-developers)
-    (dapla-metadata)
+    >>> parse_team_name("dapla-metadata-developers")
+    'dapla-metadata'
 
-    >>> parse_team_name(dapla-metadata-data-admins)
-    (dapla-metadata)
+    >>> parse_team_name("dapla-metadata-data-admins")
+    'dapla-metadata'
 
-    >>> parse_team_name(dapla-metadata)
-    (dapla)
+    >>> parse_team_name("dapla-metadata")
+    'dapla'
 
-    >>> parse_team_name(dapla-metadata-not-real-name)
-    (dapla-metadata-not-real)
+    >>> parse_team_name("dapla-metadata-not-real-name")
+    'dapla-metadata-not-real'
     """
     parts = group.split("-")
     return "-".join(parts[:-2] if group.endswith("data-admins") else parts[:-1])

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/src/dapla_metadata/datasets/code_list.py

@@ -127,7 +127,7 @@ class CodeList(GetExternalSource):
                     .get_codes()
                     .data
                 )
-            except Exception:  # noqa: PERF203
+            except Exception:
                 logger.exception(
                     "Exception while getting classifications from Klass",
                 )

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/src/dapla_metadata/datasets/core.py

@@ -14,7 +14,7 @@ from datadoc_model import model
 from datadoc_model.model import DataSetStatus
 
 from dapla_metadata._shared import config
-from dapla_metadata._shared import user_info
+from dapla_metadata.dapla import user_info
 from dapla_metadata.datasets.dapla_dataset_path_info import DaplaDatasetPathInfo
 from dapla_metadata.datasets.dataset_parser import DatasetParser
 from dapla_metadata.datasets.model_backwards_compatibility import (

{dapla_toolbelt_metadata-0.4.2 → dapla_toolbelt_metadata-0.6.0}/src/dapla_metadata/datasets/dapla_dataset_path_info.py

@@ -478,7 +478,7 @@ class DaplaDatasetPathInfo:
         """Extract the bucket name from the dataset path.
 
         Returns:
-            The bucket name or None if the dataset path is not a GCS path.
+            The bucket name or None if the dataset path is not a GCS path nor ssb bucketeer path.
 
         Examples:
             >>> DaplaDatasetPathInfo('gs://ssb-staging-dapla-felles-data-delt/datadoc/utdata/person_data_p2021_v2.parquet').bucket_name
@@ -492,17 +492,35 @@ class DaplaDatasetPathInfo:
 
             >>> DaplaDatasetPathInfo('ssb-staging-dapla-felles-data-delt/datadoc/utdata/person_data_p2021_v2.parquet').bucket_name
             None
+
+            >>> DaplaDatasetPathInfo('ssb-staging-dapla-felles-data-delt/datadoc/utdata/person_data_p2021_v2.parquet').bucket_name
+            None
+
+            >>> DaplaDatasetPathInfo('buckets/ssb-staging-dapla-felles-data-delt/stat/utdata/person_data_p2021_v2.parquet').bucket_name
+            ssb-staging-dapla-felles-data-delt
+
+            >>> DaplaDatasetPathInfo('buckets/ssb-staging-dapla-felles-data-delt/person_data_p2021_v2.parquet').bucket_name
+            ssb-staging-dapla-felles-data-delt
+
+            >>> DaplaDatasetPathInfo('home/work/buckets/ssb-staging-dapla-felles-produkt/stat/utdata/person_data_p2021_v2.parquet').bucket_name
+            ssb-staging-dapla-felles-produkt
         """
         prefix: str | None = None
-        if self.dataset_string.startswith(GSPath.cloud_prefix):
+        dataset_string = str(self.dataset_string)
+        if GSPath.cloud_prefix in self.dataset_string:
             prefix = GSPath.cloud_prefix
-        elif self.dataset_string.startswith(GS_PREFIX_FROM_PATHLIB):
+            _, bucket_and_rest = dataset_string.split(prefix, 1)
+        elif GS_PREFIX_FROM_PATHLIB in self.dataset_string:
             prefix = GS_PREFIX_FROM_PATHLIB
+            _, bucket_and_rest = self.dataset_string.split(prefix, 1)
+        elif "buckets/" in self.dataset_string:
+            prefix = "buckets/"
+            _, bucket_and_rest = self.dataset_string.split(prefix, 1)
         else:
             return None
 
         return pathlib.Path(
-            self.dataset_string.removeprefix(prefix),
+            bucket_and_rest,
         ).parts[0]
 
     @property
@@ -528,6 +546,15 @@ class DaplaDatasetPathInfo:
 
             >>> DaplaDatasetPathInfo('my_data/simple_dataset_name.parquet').dataset_short_name
             simple_dataset_name
+
+            >>> DaplaDatasetPathInfo('gs:/ssb-staging-dapla-felles-data-delt/datadoc/utdata/person_data_p2021_v2.parquet').dataset_short_name
+            person_data
+
+            >>> DaplaDatasetPathInfo('buckets/ssb-staging-dapla-felles-data-delt/stat/utdata/folk_data_p2021_v2.parquet').dataset_short_name
+            folk_data
+
+            >>> DaplaDatasetPathInfo('buckets/ssb-staging-dapla-felles-data-delt/stat/utdata/dapla/bus_p2021_v2.parquet').dataset_short_name
+            bus
         """
         if self.contains_data_from or self.contains_data_until:
             short_name_sections = self.dataset_name_sections[
@@ -601,6 +628,9 @@ class DaplaDatasetPathInfo:
             >>> DaplaDatasetPathInfo('utdata/min_statistikk/person_data_v1.parquet').dataset_state
             <DataSetState.OUTPUT_DATA: 'OUTPUT_DATA'>
 
+            >>> DaplaDatasetPathInfo('buckets/bucket_name/stat_name/inndata/min_statistikk/person_data_v1.parquet').dataset_state
+            <DataSetState.INPUT_DATA: 'INPUT_DATA'>
+
             >>> DaplaDatasetPathInfo('my_special_data/person_data_v1.parquet').dataset_state
             None
         """
@@ -632,6 +662,12 @@ class DaplaDatasetPathInfo:
 
             >>> DaplaDatasetPathInfo('person_data.parquet').dataset_version
             None
+
+            >>> DaplaDatasetPathInfo('buckets/bucket_name/stat_name/inndata/min_statistikk/person_data_v1.parquet').dataset_version
+            '1'
+
+            >>> DaplaDatasetPathInfo('buckets/bucket_name/stat_name/inndata/min_statistikk/person_data.parquet').dataset_version
+            None
         """
         minimum_elements_in_file_name: Final[int] = 2
         minimum_characters_in_version_string: Final[int] = 2
@@ -645,13 +681,37 @@ class DaplaDatasetPathInfo:
                 return last_filename_element[1:]
         return None
 
+    def _get_left_parts(
+        self,
+        dataset_path_parts: list[str],
+        state_index: int,
+    ) -> list[str]:
+        """Retrieve the path parts before the dataset state, considering bucket prefixes."""
+        bucket_prefix = {"gs:", "buckets"}
+        left_parts = dataset_path_parts[:state_index]
+
+        # Stop checking beyond the bucket prefix
+        prefix_intersection = bucket_prefix & set(left_parts)
+        if prefix_intersection:
+            first_prefix = min(
+                left_parts.index(prefix) for prefix in prefix_intersection
+            )
+            left_parts = left_parts[first_prefix:]
+
+        return (
+            []
+            if left_parts == ["/"]
+            or (left_parts[0] in bucket_prefix and len(left_parts) <= 2)
+            else left_parts
+        )
+
     @property
     def statistic_short_name(
         self,
     ) -> str | None:
         """Extract the statistical short name from the filepath.
 
-        Extract the statistical short name from the filepath right before the
+        Extract the statistical short name from the filepath either after bucket name or right before the
         dataset state based on the Dapla filepath naming convention.
 
         Returns:
@@ -662,21 +722,75 @@ class DaplaDatasetPathInfo:
             >>> DaplaDatasetPathInfo('prosjekt/befolkning/klargjorte_data/person_data_v1.parquet').statistic_short_name
             befolkning
 
+            >>> DaplaDatasetPathInfo('buckets/prosjekt/befolkning/person_data_v1.parquet').statistic_short_name
+            befolkning
+
             >>> DaplaDatasetPathInfo('befolkning/inndata/person_data_v1.parquet').statistic_short_name
             befolkning
 
+            >>> DaplaDatasetPathInfo('buckets/bucket_name/stat_name/inndata/min_statistikk/person_data.parquet').statistic_short_name
+            stat_name
+
+            >>> DaplaDatasetPathInfo('buckets/stat_name/utdata/person_data.parquet').statistic_short_name
+            None
+
             >>> DaplaDatasetPathInfo('befolkning/person_data.parquet').statistic_short_name
             None
+
+            >>> DaplaDatasetPathInfo('buckets/produkt/befolkning/utdata/person_data.parquet').statistic_short_name
+            befolkning
+
+            >>> DaplaDatasetPathInfo('resources/buckets/produkt/befolkning/utdata/person_data.parquet').statistic_short_name
+            befolkning
+
+            >>> DaplaDatasetPathInfo('gs://statistikk/produkt/klargjorte-data/persondata_p1990-Q1_p2023-Q4_v1/aar=2019/data.parquet').statistic_short_name
+            produkt
+
+            >>> DaplaDatasetPathInfo('gs://statistikk/produkt/persondata_p1990-Q1_p2023-Q4_v1/aar=2019/data.parquet').statistic_short_name
+            None
+
+            >>> DaplaDatasetPathInfo('buckets/ssb-staging-dapla-felles-data-delt/person_data_p2021_v2.parquet').statistic_short_name
+            None
         """
-        dataset_state = self.dataset_state
-        if dataset_state is not None:
-            dataset_state_names = self._extract_norwegian_dataset_state_path_part(
-                dataset_state,
-            )
-            dataset_path_parts = list(self.dataset_path.parts)
-            for i in dataset_state_names:
-                if i in dataset_path_parts and dataset_path_parts.index(i) != 0:
-                    return dataset_path_parts[dataset_path_parts.index(i) - 1]
+        if not self.dataset_state:
+            if self.bucket_name:
+                parts = self.dataset_path.parent.parts
+
+                if self.bucket_name not in parts:
+                    return None
+
+                # Find the index of bucket_name in the path
+                bucket_name_index = self.dataset_path.parent.parts.index(
+                    self.bucket_name,
+                )
+
+                # If there are parts after bucket_name, return the part immediately after it
+                if len(self.dataset_path.parent.parts) > bucket_name_index + 1:
+                    return self.dataset_path.parent.parts[bucket_name_index + 1]
+
+            return None
+
+        dataset_state_names = self._extract_norwegian_dataset_state_path_part(
+            self.dataset_state,
+        )
+        dataset_path_parts = list(self.dataset_path.parts)
+
+        for state in dataset_state_names:
+            if state not in dataset_path_parts:
+                continue
+
+            index = dataset_path_parts.index(state)
+
+            if index == 0:
+                continue
+
+            left_parts = self._get_left_parts(dataset_path_parts, index)
+
+            if not left_parts:
+                return None
+
+            return dataset_path_parts[index - 1]
+
         return None
 
     def path_complies_with_naming_standard(self) -> bool: