castor-extractor 0.24.0__py3-none-any.whl → 0.24.2__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.24.2 - 2025-03-17
+
+* Rename Revamped Tableau Connector classes
+
+## 0.24.1 - 2025-03-14
+
+* Added support for Looker Studio
+
 ## 0.24.0 - 2025-03-10
 
 * Remove legacy Tableau Connector

README.md

@@ -104,7 +104,9 @@ Depending on your use case, you can also install one of the following `extras`:
 
 ```bash
 pip install castor-extractor[bigquery]
+pip install castor-extractor[databricks]
 pip install castor-extractor[looker]
+pip install castor-extractor[lookerstudio]
 pip install castor-extractor[metabase]
 pip install castor-extractor[mysql]
 pip install castor-extractor[powerbi]

castor_extractor/commands/extract_looker_studio.py

@@ -0,0 +1,30 @@
+from argparse import ArgumentParser
+
+from castor_extractor.utils import parse_filled_arguments  # type: ignore
+from castor_extractor.visualization import looker_studio  # type: ignore
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument(
+        "-c",
+        "--credentials",
+        help="File path to Service Account credentials with Looker Studio access",
+    )
+    parser.add_argument(
+        "-a",
+        "--admin-email",
+        help="Email of a Google Workspace user with admin access",
+    )
+    parser.add_argument(
+        "-b",
+        "--bigquery-credentials",
+        help=(
+            "Optional: file path to Service Account credentials with BigQuery access. "
+            "This can be the same file path as for Looker Studio."
+        ),
+    )
+
+    parser.add_argument("-o", "--output", help="Directory to write to")
+
+    looker_studio.extract_all(**parse_filled_arguments(parser))

castor_extractor/commands/extract_tableau.py

@@ -2,7 +2,7 @@ import logging
 from argparse import ArgumentParser
 
 from castor_extractor.utils import parse_filled_arguments  # type: ignore
-from castor_extractor.visualization import tableau_revamp  # type: ignore
+from castor_extractor.visualization import tableau  # type: ignore
 
 logging.basicConfig(level=logging.INFO, format="%(levelname)s - %(message)s")
 
@@ -36,4 +36,4 @@ def main():
 
     parser.add_argument("-o", "--output", help="Directory to write to")
 
-    tableau_revamp.extract_all(**parse_filled_arguments(parser))
+    tableau.extract_all(**parse_filled_arguments(parser))

castor_extractor/visualization/looker_studio/__init__.py

@@ -4,3 +4,4 @@ from .client import (
     LookerStudioClient,
     LookerStudioCredentials,
 )
+from .extract import extract_all

castor_extractor/visualization/looker_studio/assets.py

@@ -3,4 +3,5 @@ from ...types import ExternalAsset
 
 class LookerStudioAsset(ExternalAsset):
     ASSETS = "assets"
+    SOURCE_QUERIES = "source_queries"
     VIEW_ACTIVITY = "view_activity"

castor_extractor/visualization/looker_studio/client/client.py

@@ -1,21 +1,49 @@
-from typing import Iterator
+from typing import Iterator, Optional
 
+from ....utils import empty_iterator
+from ....warehouse.abstract import WarehouseAsset
+from ....warehouse.bigquery import BigQueryClient, BigQueryQueryBuilder
 from .. import LookerStudioAsset
 from .admin_sdk_client import USER_EMAIL_FIELD, AdminSDKClient
 from .credentials import LookerStudioCredentials
 from .looker_studio_api_client import LookerStudioAPIClient
 
 
+class LookerStudioQueryBuilder(BigQueryQueryBuilder):
+    def job_history_queries(self) -> list:
+        """
+        This class and method are a convenient workaround to build the
+        ExtractionQueries which retrieve BigQuery's job history, but filtered on
+        Looker Studio only.
+
+        Compared to the generic BigQuery query history, only the SQL "template"
+        changes. By defining this class here, this will pick the SQL file
+        `queries/query.sql` located in the same directory as this file.
+        """
+        return super().build(WarehouseAsset.QUERY)  # type: ignore
+
+
 class LookerStudioClient:
     """
     Acts as a wrapper class to fetch Looker Studio assets, which requires
     coordinating calls between the Admin SDK API and the Looker Studio API.
+
+    If the BigQuery credentials are provided, it can also fetch the source queries
+    of BigQuery data sources.
     """
 
-    def __init__(self, credentials: LookerStudioCredentials):
+    def __init__(
+        self,
+        credentials: LookerStudioCredentials,
+        bigquery_credentials: Optional[dict] = None,
+    ):
         self.admin_sdk_client = AdminSDKClient(credentials)
         self.looker_studio_client = LookerStudioAPIClient(credentials)
 
+        self.bigquery_client: Optional[BigQueryClient] = None
+        if bigquery_credentials:
+            self.bigquery_client = BigQueryClient(bigquery_credentials)
+
     def _get_assets(self) -> Iterator[dict]:
         """
         Extracts reports and data sources user by user.
@@ -26,12 +54,34 @@ class LookerStudioClient:
             email = user[USER_EMAIL_FIELD]
             yield from self.looker_studio_client.fetch_user_assets(email)
 
-    def fetch(self, asset: LookerStudioAsset) -> Iterator[dict]:
-        if asset == LookerStudioAsset.VIEW_ACTIVITY:
-            yield from self.admin_sdk_client.list_view_events()
+    def _get_source_queries(self) -> Iterator[dict]:
+        """
+        Extracts the BigQuery jobs triggered by Looker Studio. The last job
+        per data source is returned.
+        """
+        if not self.bigquery_client:
+            return empty_iterator()
+
+        query_builder = LookerStudioQueryBuilder(
+            regions=self.bigquery_client.get_regions(),
+            datasets=self.bigquery_client.get_datasets(),
+            extended_regions=self.bigquery_client.get_extended_regions(),
+        )
+
+        queries = query_builder.job_history_queries()
+
+        for query in queries:
+            yield from self.bigquery_client.execute(query)
 
-        elif asset == LookerStudioAsset.ASSETS:
+    def fetch(self, asset: LookerStudioAsset) -> Iterator[dict]:
+        if asset == LookerStudioAsset.ASSETS:
             yield from self._get_assets()
 
+        elif asset == LookerStudioAsset.SOURCE_QUERIES:
+            yield from self._get_source_queries()
+
+        elif asset == LookerStudioAsset.VIEW_ACTIVITY:
+            yield from self.admin_sdk_client.list_view_events()
+
         else:
             raise ValueError(f"The asset {asset}, is not supported")

castor_extractor/visualization/looker_studio/client/credentials.py

@@ -2,6 +2,11 @@ from pydantic import BaseModel, SecretStr, field_serializer
 
 
 class LookerStudioCredentials(BaseModel):
+    """
+    Looker Studio Credentials match the Service Account credentials JSON
+    but with an additional admin_email field.
+    """
+
     admin_email: str
     auth_provider_x509_cert_url: str
     auth_uri: str

castor_extractor/visualization/looker_studio/client/queries/query.sql

@@ -0,0 +1,52 @@
+/*
+Gets the query jobs triggered by Looker Studio when refreshing a BigQuery data source. Only the latest query per
+data source is selected.
+
+The `labels` column should indicate the `looker_studio_datasource_id` that triggered the job. In some cases, it also
+contains a `looker_studio_report_id` value, which gives us a link between the data source and a report.
+*/
+WITH ranked_by_datasource AS (
+    SELECT
+        creation_time,
+        project_id AS database_name,
+        user_email,
+        query AS query_text,
+        referenced_tables,
+        labels,
+        ROW_NUMBER() OVER (
+            PARTITION BY (
+                SELECT
+                    label.value
+                FROM
+                    UNNEST(labels) AS label
+                WHERE
+                    label.key = 'looker_studio_datasource_id'
+            )
+            ORDER BY
+                creation_time DESC
+        ) AS row_num
+    FROM
+        `{project}.region-{region}.INFORMATION_SCHEMA.JOBS_BY_PROJECT`
+    WHERE
+        job_type = 'QUERY'
+        AND EXISTS (
+            SELECT
+                1
+            FROM
+                UNNEST(labels) AS label
+            WHERE
+                label.key = 'requestor'
+                AND label.value = 'looker_studio'
+        )
+)
+SELECT
+    creation_time,
+    database_name,
+    user_email,
+    query_text,
+    referenced_tables,
+    labels
+FROM
+    ranked_by_datasource
+WHERE
+    row_num = 1;

castor_extractor/visualization/looker_studio/extract.py

@@ -0,0 +1,84 @@
+import json
+import logging
+from collections.abc import Iterable
+from typing import Optional, Union, cast
+
+from ...utils import (
+    OUTPUT_DIR,
+    current_timestamp,
+    deep_serialize,
+    from_env,
+    get_output_filename,
+    write_json,
+    write_summary,
+)
+from .assets import LookerStudioAsset
+from .client import LookerStudioClient, LookerStudioCredentials
+
+logger = logging.getLogger(__name__)
+
+APPLICATION_CREDENTIALS = "GOOGLE_APPLICATION_CREDENTIALS"
+LOOKER_STUDIO_ADMIN_EMAIL = "CASTOR_LOOKER_STUDIO_ADMIN_EMAIL"
+
+
+def iterate_all_data(
+    client: LookerStudioClient,
+) -> Iterable[tuple[LookerStudioAsset, Union[list, dict]]]:
+    for asset in LookerStudioAsset:
+        logger.info(f"Extracting {asset.name} from API")
+        data = list(deep_serialize(client.fetch(asset)))
+        yield asset, data
+        logger.info(f"Extracted {len(data)} {asset.name} from API")
+
+
+def _credentials(params: dict) -> LookerStudioCredentials:
+    """
+    Builds the Looker Studio credentials by combining the Service Account
+    credentials with the admin email.
+    """
+    path = params.get("credentials") or from_env(APPLICATION_CREDENTIALS)
+    logger.info(f"Looker Studio credentials loaded from {path}")
+    with open(path) as file:
+        credentials = cast(dict, json.load(file))
+
+    admin_email = params.get("admin_email") or from_env(
+        LOOKER_STUDIO_ADMIN_EMAIL
+    )
+    credentials["admin_email"] = admin_email
+    return LookerStudioCredentials(**credentials)
+
+
+def _bigquery_credentials_or_none(params: dict) -> Optional[dict]:
+    """Extracts optional GCP credentials to access BigQuery"""
+    path = params.get("bigquery_credentials") or from_env(
+        APPLICATION_CREDENTIALS,
+        allow_missing=True,
+    )
+    if not path:
+        return None
+
+    logger.info(f"BigQuery credentials loaded from {path}")
+    with open(path) as file:
+        return cast(dict, json.load(file))
+
+
+def extract_all(**kwargs) -> None:
+    """
+    Extracts data from Looker Studio and stores the output files locally under
+    the given output_directory.
+    """
+    output_directory = kwargs.get("output") or from_env(OUTPUT_DIR)
+    credentials = _credentials(kwargs)
+    bigquery_credentials = _bigquery_credentials_or_none(kwargs)
+
+    client = LookerStudioClient(
+        credentials=credentials,
+        bigquery_credentials=bigquery_credentials,
+    )
+    ts = current_timestamp()
+
+    for key, data in iterate_all_data(client):
+        filename = get_output_filename(key.name.lower(), output_directory, ts)
+        write_json(filename, data)
+
+    write_summary(output_directory, ts)

castor_extractor/visualization/tableau/__init__.py

@@ -0,0 +1,3 @@
+from .assets import TableauAsset
+from .client import TableauClient, TableauCredentials
+from .extract import extract_all, iterate_all_data

castor_extractor/visualization/{tableau_revamp → tableau}/assets.py

@@ -1,7 +1,7 @@
 from ...types import ExternalAsset
 
 
-class TableauRevampAsset(ExternalAsset):
+class TableauAsset(ExternalAsset):
     """
     Tableau assets
     """
@@ -23,7 +23,7 @@ class TableauRevampAsset(ExternalAsset):
 
 # assets that are only available for clients using Tableau Pulse
 TABLEAU_PULSE_ASSETS = (
-    TableauRevampAsset.METRIC,
-    TableauRevampAsset.METRIC_DEFINITION,
-    TableauRevampAsset.SUBSCRIPTION,
+    TableauAsset.METRIC,
+    TableauAsset.METRIC_DEFINITION,
+    TableauAsset.SUBSCRIPTION,
 )

castor_extractor/visualization/tableau/client/__init__.py

@@ -0,0 +1,2 @@
+from .client import TableauClient
+from .credentials import TableauCredentials

castor_extractor/visualization/{tableau_revamp → tableau}/client/client.py

@@ -4,31 +4,31 @@ from typing import Optional
 import tableauserverclient as TSC  # type: ignore
 
 from ....utils import SerializedAsset
-from ..assets import TABLEAU_PULSE_ASSETS, TableauRevampAsset
+from ..assets import TABLEAU_PULSE_ASSETS, TableauAsset
 from ..constants import CREDENTIALS_SITE_ID_KEY, DEFAULT_TIMEOUT_SECONDS
 from .client_metadata_api import TableauClientMetadataApi
 from .client_rest_api import TableauClientRestApi
 from .client_tsc import TableauClientTSC
-from .credentials import TableauRevampCredentials
+from .credentials import TableauCredentials
 
 logger = logging.getLogger(__name__)
 
 # these assets must be extracted via TableauServerClient (TSC)
 _TSC_ASSETS = (
     # projects are not available in Metadata API
-    TableauRevampAsset.PROJECT,
+    TableauAsset.PROJECT,
     # view count are not available in Metadata API
-    TableauRevampAsset.USAGE,
+    TableauAsset.USAGE,
     # only users who published content can be extracted from MetadataAPI
-    TableauRevampAsset.USER,
+    TableauAsset.USER,
 )
 
 # these assets must be extracted via the REST API
 _REST_API_ASSETS = (
     # Tableau Pulse assets are only available in REST API
-    TableauRevampAsset.METRIC,
-    TableauRevampAsset.METRIC_DEFINITION,
-    TableauRevampAsset.SUBSCRIPTION,
+    TableauAsset.METRIC,
+    TableauAsset.METRIC_DEFINITION,
+    TableauAsset.SUBSCRIPTION,
 )
 
 logging.getLogger("tableau.endpoint").setLevel(logging.WARNING)
@@ -109,7 +109,7 @@ def _server(
     return server
 
 
-class TableauRevampClient:
+class TableauClient:
     """
     Connect to Tableau's API and extract assets.
 
@@ -119,7 +119,7 @@ class TableauRevampClient:
 
     def __init__(
         self,
-        credentials: TableauRevampCredentials,
+        credentials: TableauCredentials,
         timeout_sec: int = DEFAULT_TIMEOUT_SECONDS,
         with_pulse: bool = False,
         override_page_size: Optional[int] = None,
@@ -186,7 +186,7 @@ class TableauRevampClient:
         )
 
     def _fetch_datasources(self) -> SerializedAsset:
-        asset = TableauRevampAsset.DATASOURCE
+        asset = TableauAsset.DATASOURCE
 
         datasources = self._client_metadata.fetch(asset)
         tsc_datasources = self._client_tsc.fetch(asset)
@@ -194,7 +194,7 @@ class TableauRevampClient:
         return _merge_datasources(datasources, tsc_datasources)
 
     def _fetch_workbooks(self) -> SerializedAsset:
-        asset = TableauRevampAsset.WORKBOOK
+        asset = TableauAsset.WORKBOOK
 
         site_id = self._credentials.site_id
         workbooks = self._client_metadata.fetch(asset)
@@ -206,7 +206,7 @@ class TableauRevampClient:
 
     def fetch(
         self,
-        asset: TableauRevampAsset,
+        asset: TableauAsset,
     ) -> SerializedAsset:
         """
         Extract the given Tableau Asset
@@ -217,11 +217,11 @@ class TableauRevampClient:
 
         logger.info(f"Extracting {asset.name}...")
 
-        if asset == TableauRevampAsset.DATASOURCE:
+        if asset == TableauAsset.DATASOURCE:
             # two APIs are required to extract datasources
             return self._fetch_datasources()
 
-        if asset == TableauRevampAsset.WORKBOOK:
+        if asset == TableauAsset.WORKBOOK:
             # two APIs are required to extract workbooks
             return self._fetch_workbooks()
 

castor_extractor/visualization/{tableau_revamp → tableau}/client/client_metadata_api.py

@@ -4,21 +4,21 @@ from typing import Optional
 import tableauserverclient as TSC  # type: ignore
 
 from ....utils import SerializedAsset, retry
-from ..assets import TableauRevampAsset
+from ..assets import TableauAsset
 from ..constants import DEFAULT_PAGE_SIZE
 from .errors import TableauApiError, TableauApiTimeout
 from .gql_queries import FIELDS_QUERIES, GQL_QUERIES, QUERY_TEMPLATE
 
 # increase the value when extraction is too slow
 # decrease the value when timeouts arise
-_CUSTOM_PAGE_SIZE: dict[TableauRevampAsset, int] = {
+_CUSTOM_PAGE_SIZE: dict[TableauAsset, int] = {
     # for some clients, extraction of columns tend to hit the node limit
     # https://community.tableau.com/s/question/0D54T00000YuK60SAF/metadata-query-nodelimitexceeded-error
     # the workaround is to reduce pagination
-    TableauRevampAsset.COLUMN: 50,
+    TableauAsset.COLUMN: 50,
     # fields are light but volumes are bigger
-    TableauRevampAsset.FIELD: 1000,
-    TableauRevampAsset.TABLE: 50,
+    TableauAsset.FIELD: 1000,
+    TableauAsset.TABLE: 50,
 }
 
 _TIMEOUT_MESSAGE = (
@@ -115,7 +115,7 @@ class TableauClientMetadataApi:
         result_pages = gql_query_scroll(self._server, query, resource)
         return [asset for page in result_pages for asset in page]
 
-    def _page_size(self, asset: TableauRevampAsset) -> int:
+    def _page_size(self, asset: TableauAsset) -> int:
         return (
             self._override_page_size
             or _CUSTOM_PAGE_SIZE.get(asset)
@@ -124,7 +124,7 @@ class TableauClientMetadataApi:
 
     def _fetch_fields(self) -> SerializedAsset:
         result: SerializedAsset = []
-        page_size = self._page_size(TableauRevampAsset.FIELD)
+        page_size = self._page_size(TableauAsset.FIELD)
         for resource, fields in FIELDS_QUERIES:
             current = self._call(resource, fields, page_size)
             result.extend(current)
@@ -132,9 +132,9 @@ class TableauClientMetadataApi:
 
     def fetch(
         self,
-        asset: TableauRevampAsset,
+        asset: TableauAsset,
     ) -> SerializedAsset:
-        if asset == TableauRevampAsset.FIELD:
+        if asset == TableauAsset.FIELD:
             return self._fetch_fields()
 
         page_size = self._page_size(asset)

castor_extractor/visualization/{tableau_revamp → tableau}/client/client_rest_api.py

@@ -5,7 +5,7 @@ import requests
 import tableauserverclient as TSC  # type: ignore
 
 from ....utils import SerializedAsset, deduplicate
-from ..assets import TableauRevampAsset
+from ..assets import TableauAsset
 from .rest_fields import REST_FIELDS
 
 logger = logging.getLogger(__name__)
@@ -17,7 +17,7 @@ _METRICS_DEFINITION_URL = "{base}/pulse/site/{site}/{definition_id}"
 
 def _pick(
     data: SerializedAsset,
-    asset: TableauRevampAsset,
+    asset: TableauAsset,
 ) -> SerializedAsset:
     keys = REST_FIELDS[asset]
     return [{key: row[key] for key in keys} for row in data]
@@ -107,18 +107,18 @@ class TableauClientRestApi:
 
     def fetch(
         self,
-        asset: TableauRevampAsset,
+        asset: TableauAsset,
     ) -> SerializedAsset:
-        if asset == TableauRevampAsset.SUBSCRIPTION:
+        if asset == TableauAsset.SUBSCRIPTION:
             # https://help.tableau.com/current/api/rest_api/en-us/REST/rest_api_ref_pulse.htm#PulseSubscriptionService_ListSubscriptions
             data = self._call(path=_PULSE_API, target="subscriptions")
 
-        elif asset == TableauRevampAsset.METRIC_DEFINITION:
+        elif asset == TableauAsset.METRIC_DEFINITION:
             # https://help.tableau.com/current/api/rest_api/en-us/REST/rest_api_ref_pulse.htm#MetricQueryService_ListDefinitions
             data = self._call(path=_PULSE_API, target="definitions")
             self._compute_metric_url(data)
 
-        elif asset == TableauRevampAsset.METRIC:
+        elif asset == TableauAsset.METRIC:
             # https://help.tableau.com/current/api/rest_api/en-us/REST/rest_api_ref_pulse.htm#MetricQueryService_ListMetrics
             definitions = self._call(path=_PULSE_API, target="definitions")
             data = self._fetch_metrics(definitions)

castor_extractor/visualization/{tableau_revamp → tableau}/client/client_tsc.py

@@ -4,7 +4,7 @@ from typing import Any
 import tableauserverclient as TSC  # type: ignore
 
 from ....utils import JsonType, SerializedAsset
-from ..assets import TableauRevampAsset
+from ..assets import TableauAsset
 from .rest_fields import REST_FIELDS
 
 
@@ -30,13 +30,13 @@ class TableauClientTSC:
     def _pick_fields(
         self,
         data: Iterable,
-        asset: TableauRevampAsset,
+        asset: TableauAsset,
     ) -> Iterator[dict]:
         keys = REST_FIELDS[asset]
 
         for row in data:
             fields = {key: _pick(row, key) for key in keys}
-            if asset == TableauRevampAsset.USER:
+            if asset == TableauAsset.USER:
                 self._server.users.populate_groups(row)
                 fields["group_ids"] = [group.id for group in row.groups]
 
@@ -44,21 +44,21 @@ class TableauClientTSC:
 
     def fetch(
         self,
-        asset: TableauRevampAsset,
+        asset: TableauAsset,
     ) -> SerializedAsset:
-        if asset == TableauRevampAsset.DATASOURCE:
+        if asset == TableauAsset.DATASOURCE:
             data = TSC.Pager(self._server.datasources)
 
-        elif asset == TableauRevampAsset.PROJECT:
+        elif asset == TableauAsset.PROJECT:
             data = TSC.Pager(self._server.projects)
 
-        elif asset == TableauRevampAsset.USAGE:
+        elif asset == TableauAsset.USAGE:
             data = TSC.Pager(self._server.views, usage=True)
 
-        elif asset == TableauRevampAsset.USER:
+        elif asset == TableauAsset.USER:
             data = TSC.Pager(self._server.users)
 
-        elif asset == TableauRevampAsset.WORKBOOK:
+        elif asset == TableauAsset.WORKBOOK:
             data = TSC.Pager(self._server.workbooks)
 
         else:

castor_extractor/visualization/{tableau_revamp → tableau}/client/credentials.py

@@ -15,7 +15,7 @@ _DEFAULT_SITE_ID_USER_INPUT = "default"
 TABLEAU_ENV_PREFIX = "CASTOR_TABLEAU_"
 
 
-class TableauRevampCredentials(BaseSettings):
+class TableauCredentials(BaseSettings):
     """
     Tableau's credentials to connect to both APIs (REST and GRAPHQL)
     """
@@ -42,7 +42,7 @@ class TableauRevampCredentials(BaseSettings):
         return site_id
 
     @model_validator(mode="after")
-    def _check_user_xor_pat_login(self) -> "TableauRevampCredentials":
+    def _check_user_xor_pat_login(self) -> "TableauCredentials":
         """
         Checks that credentials are correctly input, it means either:
         - User and password are filled

castor_extractor/visualization/{tableau_revamp → tableau}/client/gql_queries.py

@@ -1,4 +1,4 @@
-from ..assets import TableauRevampAsset
+from ..assets import TableauAsset
 
 QUERY_TEMPLATE = """
 {{
@@ -128,13 +128,13 @@ workbook { id }
 """
 
 
-GQL_QUERIES: dict[TableauRevampAsset, tuple[str, str]] = {
-    TableauRevampAsset.COLUMN: ("columns", _COLUMNS_QUERY),
-    TableauRevampAsset.DASHBOARD: ("dashboards", _DASHBOARDS_QUERY),
-    TableauRevampAsset.DATASOURCE: ("datasources", _DATASOURCES_QUERY),
-    TableauRevampAsset.SHEET: ("sheets", _SHEETS_QUERY),
-    TableauRevampAsset.TABLE: ("tables", _TABLES_QUERY),
-    TableauRevampAsset.WORKBOOK: ("workbooks", _WORKBOOKS_QUERY),
+GQL_QUERIES: dict[TableauAsset, tuple[str, str]] = {
+    TableauAsset.COLUMN: ("columns", _COLUMNS_QUERY),
+    TableauAsset.DASHBOARD: ("dashboards", _DASHBOARDS_QUERY),
+    TableauAsset.DATASOURCE: ("datasources", _DATASOURCES_QUERY),
+    TableauAsset.SHEET: ("sheets", _SHEETS_QUERY),
+    TableauAsset.TABLE: ("tables", _TABLES_QUERY),
+    TableauAsset.WORKBOOK: ("workbooks", _WORKBOOKS_QUERY),
 }
 
 FIELDS_QUERIES = (

castor_extractor/visualization/{tableau_revamp → tableau}/client/rest_fields.py

@@ -1,44 +1,44 @@
-from ..assets import TableauRevampAsset
+from ..assets import TableauAsset
 
 # list of fields to pick in REST API or TSC responses
-REST_FIELDS: dict[TableauRevampAsset, set[str]] = {
-    TableauRevampAsset.DATASOURCE: {
+REST_FIELDS: dict[TableauAsset, set[str]] = {
+    TableauAsset.DATASOURCE: {
         "id",
         "project_id",
         "webpage_url",
     },
-    TableauRevampAsset.METRIC: {
+    TableauAsset.METRIC: {
         "id",
         "definition_id",
     },
-    TableauRevampAsset.METRIC_DEFINITION: {
+    TableauAsset.METRIC_DEFINITION: {
         "metadata",
         "specification",
     },
-    TableauRevampAsset.PROJECT: {
+    TableauAsset.PROJECT: {
         "description",
         "id",
         "name",
         "parent_id",
     },
-    TableauRevampAsset.SUBSCRIPTION: {
+    TableauAsset.SUBSCRIPTION: {
         "follower",
         "id",
         "metric_id",
     },
-    TableauRevampAsset.USAGE: {
+    TableauAsset.USAGE: {
         "name",
         "total_views",
         "workbook_id",
     },
-    TableauRevampAsset.USER: {
+    TableauAsset.USER: {
         "email",
         "fullname",
         "id",
         "name",
         "site_role",
     },
-    TableauRevampAsset.WORKBOOK: {
+    TableauAsset.WORKBOOK: {
         "id",
         "project_id",
     },

castor_extractor/visualization/{tableau_revamp → tableau}/extract.py

@@ -10,18 +10,18 @@ from ...utils import (
     write_json,
     write_summary,
 )
-from .assets import TableauRevampAsset
-from .client import TableauRevampClient, TableauRevampCredentials
+from .assets import TableauAsset
+from .client import TableauClient, TableauCredentials
 
 logger = logging.getLogger(__name__)
 
 
 def iterate_all_data(
-    client: TableauRevampClient,
-) -> Iterable[tuple[TableauRevampAsset, list]]:
+    client: TableauClient,
+) -> Iterable[tuple[TableauAsset, list]]:
     """Iterate over the extracted Data from Tableau"""
 
-    for asset in TableauRevampAsset:
+    for asset in TableauAsset:
         data = client.fetch(asset)
         yield asset, deep_serialize(data)
 
@@ -36,8 +36,8 @@ def extract_all(**kwargs) -> None:
     page_size = kwargs.get("page_size")
     timestamp = current_timestamp()
 
-    credentials = TableauRevampCredentials(**kwargs)
-    client = TableauRevampClient(
+    credentials = TableauCredentials(**kwargs)
+    client = TableauClient(
         credentials,
         with_pulse=with_pulse,
         override_page_size=page_size,

{castor_extractor-0.24.0.dist-info → castor_extractor-0.24.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.24.0
+Version: 0.24.2
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
@@ -170,7 +170,9 @@ Depending on your use case, you can also install one of the following `extras`:
 
 ```bash
 pip install castor-extractor[bigquery]
+pip install castor-extractor[databricks]
 pip install castor-extractor[looker]
+pip install castor-extractor[lookerstudio]
 pip install castor-extractor[metabase]
 pip install castor-extractor[mysql]
 pip install castor-extractor[powerbi]
@@ -208,6 +210,14 @@ For any questions or bug report, contact us at [support@castordoc.com](mailto:su
 
 # Changelog
 
+## 0.24.2 - 2025-03-17
+
+* Rename Revamped Tableau Connector classes
+
+## 0.24.1 - 2025-03-14
+
+* Added support for Looker Studio
+
 ## 0.24.0 - 2025-03-10
 
 * Remove legacy Tableau Connector

{castor_extractor-0.24.0.dist-info → castor_extractor-0.24.2.dist-info}/RECORD

@@ -1,8 +1,8 @@
-CHANGELOG.md,sha256=Ud6kiuDEyG_gu0YAVlp9-oXxriLibyma98FDrlajJJE,15756
+CHANGELOG.md,sha256=8iEypB0lozhyFumiedys3lbpowlX3HXCPnK-3QvjueE,15884
 Dockerfile,sha256=xQ05-CFfGShT3oUqaiumaldwA288dj9Yb_pxofQpufg,301
 DockerfileUsage.md,sha256=2hkJQF-5JuuzfPZ7IOxgM6QgIQW7l-9oRMFVwyXC4gE,998
 LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
-README.md,sha256=j8oiToTvFY4eozLUJo4rs0LEqan-G3_eOSP98KFfxfM,3634
+README.md,sha256=GlhxZBs3fkeyYUPjrB4_EGDY8_E0vvnftsaqtgv08vs,3718
 castor_extractor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 castor_extractor/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 castor_extractor/commands/extract_bigquery.py,sha256=dU4OiYO1V0n32orvZnMh1_xtFKF_VxHNXcVsH3otY-g,1269
@@ -10,6 +10,7 @@ castor_extractor/commands/extract_confluence.py,sha256=xQjC0VZdz8jFHnugqQ0fQGjzG
 castor_extractor/commands/extract_databricks.py,sha256=SVKyoa-BBUQAM6HRHf1Wdg9-tpICic2yyvXQwHcNBhA,1264
 castor_extractor/commands/extract_domo.py,sha256=jvAawUsUTHrwCn_koK6StmQr4n_b5GyvJi6uu6WS0SM,1061
 castor_extractor/commands/extract_looker.py,sha256=cySLiolLCgrREJ9d0kMrJ7P8K3efHTBTzShalWVfI3A,1214
+castor_extractor/commands/extract_looker_studio.py,sha256=e79gbyTtCexRz5pg_Pp55GWkXJZWjm6NvVclmvcR0lM,916
 castor_extractor/commands/extract_metabase_api.py,sha256=NXctea4GT_1iRDitY92nV3TKSqhjEUwYSxwPJMRS3iw,786
 castor_extractor/commands/extract_metabase_db.py,sha256=tYIhTPPgj1mN-07LyWcL6e-YoGp7HCWda58-5Ukyg_I,1255
 castor_extractor/commands/extract_mode.py,sha256=Q4iO-VAKMg4zFPejhAO-foZibL5Ht3jsnhWKwJ0oqUU,823
@@ -24,7 +25,7 @@ castor_extractor/commands/extract_salesforce_reporting.py,sha256=FdANTNiLkIPdm80
 castor_extractor/commands/extract_sigma.py,sha256=sxewHcZ1Doq35V2qnpX_zCKKXkrb1_9bYjUMg7BOW-k,643
 castor_extractor/commands/extract_snowflake.py,sha256=GwlrRxwEBjHqGs_3bs5vM9fzmv61_iwvBr1KcIgFgWM,2161
 castor_extractor/commands/extract_sqlserver.py,sha256=lwhbcNChaXHZgMgSOch3faVr7WJw-sDU6GHl3lzBt_0,1141
-castor_extractor/commands/extract_tableau.py,sha256=DGQaXS-61rV-uzBtqfvqtyQzjLtrLTzE1ViTXPG1eck,1379
+castor_extractor/commands/extract_tableau.py,sha256=xXlLKLN8Eu_a8Kt2F4E-C5D-gq8SUmvoxJcdR_thKKY,1365
 castor_extractor/commands/extract_thoughtspot.py,sha256=caAYJlH-vK7u5IUB6OKXxcaWfLgc7d_XqnFDWK6YNS4,639
 castor_extractor/commands/file_check.py,sha256=TJx76Ymd0QCECmq35zRJMkPE8DJtSInB28MuSXWk8Ao,2644
 castor_extractor/commands/upload.py,sha256=rLXp7gQ8zb1kLbho4FT87q8eJd8Gvo_TkyIynAaQ-4s,1342
@@ -168,17 +169,19 @@ castor_extractor/visualization/looker/extract.py,sha256=O_hzRftww3Cw1cgijL-K-8gh
 castor_extractor/visualization/looker/fields.py,sha256=7oC7p-3Wp7XHBP_FT_D1wH3kINFRnc_qGVeH1a4UNZY,623
 castor_extractor/visualization/looker/fields_test.py,sha256=7Cwq8Qky6aTZg8nCHp1gmPJtd9pGNB4QeMIRRWdHo5w,782
 castor_extractor/visualization/looker/multithreading.py,sha256=Muuh3usBLqtv3sfHoyPYJ6jJ7V5ajR6N9ZJ_F-bNc60,2608
-castor_extractor/visualization/looker_studio/__init__.py,sha256=p3mTWz7Yk1_m9vYohxCqwxnuE7SUYbU--TH2ezhf734,142
-castor_extractor/visualization/looker_studio/assets.py,sha256=_ir4L2RTmGDb1WetAm6-EZ6W4tPXxi0kNppNBlmy9QE,135
+castor_extractor/visualization/looker_studio/__init__.py,sha256=GccG-GJXoNhjXFPkw-rHHZ0SXVQTFKjqkMIYHVeu3T4,175
+castor_extractor/visualization/looker_studio/assets.py,sha256=lFIqr8EB6eK-Mf80R_x2qAscCyX7ZUcOcHVef1CM9B0,173
 castor_extractor/visualization/looker_studio/client/__init__.py,sha256=YkQaVDJa-7KSwdOLjtgKJMRiafbGNKC_46YVx0hYZ1Q,129
 castor_extractor/visualization/looker_studio/client/admin_sdk_client.py,sha256=hYKdU6TlWKkXx07r6HsZ4Wbxhasx8DP_jO6iDCjHjgk,3508
-castor_extractor/visualization/looker_studio/client/client.py,sha256=AYdR46NOdn_ITK_wPAASROW0gJjx-iA0Gi43QeuU5BU,1302
-castor_extractor/visualization/looker_studio/client/credentials.py,sha256=yzTaiJQ5cArTnbybUPF6fZZXbX9XQ0SBq-jVI2ECovA,521
+castor_extractor/visualization/looker_studio/client/client.py,sha256=6sTfLRUhuxhkqDjC2ZBEaw6YnR6ze8-_VW2rc1u9Ksk,3191
+castor_extractor/visualization/looker_studio/client/credentials.py,sha256=QImJPh8VctkrGt65UiU5hM12JI4WdCMSUFt88aiOoLw,657
 castor_extractor/visualization/looker_studio/client/endpoints.py,sha256=5eY-ffqNDdlDBOOpiF7LpjyHMrzeClJktidCr1pTDUs,669
 castor_extractor/visualization/looker_studio/client/enums.py,sha256=fHgemTaQpnwee8cw1YQVDsVnH--vTyFwT4Px8aVYYHQ,167
 castor_extractor/visualization/looker_studio/client/looker_studio_api_client.py,sha256=oySC6rsppj67RSifxwSCw4bFrz1Irx6IFJhX7tc_v1E,4087
 castor_extractor/visualization/looker_studio/client/pagination.py,sha256=9HQ3Rkdiz2VB6AvYtZ0F-WouiD0pMmdZyAmkv-3wh08,783
+castor_extractor/visualization/looker_studio/client/queries/query.sql,sha256=Ub4rdrJ5WTPWKI-eVmXrNMv0Ktmti4b-93zZBr0xEB0,1426
 castor_extractor/visualization/looker_studio/client/scopes.py,sha256=824cqqgZuGq4L-rPNoHJe0ibXsxkRwB0CLG_kqw9Q0g,256
+castor_extractor/visualization/looker_studio/extract.py,sha256=cHyroNZ1fKoBTvIbEebnKDrU3xpkcEgIPJy75ljCL70,2607
 castor_extractor/visualization/metabase/__init__.py,sha256=3E36cmkMyEgBB6Ot5rWk-N75i0G-7k24QTlc-Iol4pM,193
 castor_extractor/visualization/metabase/assets.py,sha256=nu3FwQBU_hdS2DBvgXAwQlEEi76QiNK2tMKEtMyctaY,2874
 castor_extractor/visualization/metabase/client/__init__.py,sha256=KBvaPMofBRV3m_sZAnKNCrJGr-Z88EbpdzEzWPQ_uBk,99
@@ -257,19 +260,19 @@ castor_extractor/visualization/sigma/client/credentials.py,sha256=XddAuQSmCKpxJ7
 castor_extractor/visualization/sigma/client/endpoints.py,sha256=DBFphbgoH78_MZUGM_bKBAq28Nl7LWSZ6VRsbxrxtDg,1162
 castor_extractor/visualization/sigma/client/pagination.py,sha256=kNEhNq08tTGbypyMjxs0w4uvDtQc_iaWpOZweaa_FsU,690
 castor_extractor/visualization/sigma/extract.py,sha256=XIT1qsj6g6dgBWP8HPfj_medZexu48EaY9tUwi14gzM,2298
-castor_extractor/visualization/tableau_revamp/__init__.py,sha256=a3DGjQhaz17gBqW-E84TAgupKbqLC40y5Ajo1yn-ot4,156
-castor_extractor/visualization/tableau_revamp/assets.py,sha256=8sJsK6Qixao6xVmVaO1usvs16SjNub9sIx7o-adYV14,659
-castor_extractor/visualization/tableau_revamp/client/__init__.py,sha256=wmS9uLtUiqNYVloi0-DgD8d2qzu3RVZEAtWiaDp6G_M,90
-castor_extractor/visualization/tableau_revamp/client/client.py,sha256=Ju89lMDiLOZ2LjxylcFm5429WElxGxjc52bMIWoKCDA,7716
-castor_extractor/visualization/tableau_revamp/client/client_metadata_api.py,sha256=WdALsMGTji2C5oSDyRwFzq-f5HZDwX-m3W8Byx87Qh4,4357
-castor_extractor/visualization/tableau_revamp/client/client_rest_api.py,sha256=O2F4qfrElTHHuD5WRPfLufazSmZ65jmlzye1t5rVOaQ,4024
-castor_extractor/visualization/tableau_revamp/client/client_tsc.py,sha256=AzN8ytKmq6HUeApTJ118JQ7EBEPESqrg7u8n3GZXqZI,1874
-castor_extractor/visualization/tableau_revamp/client/credentials.py,sha256=qA-EaX-4rbQRsn8v4zWh5Kh784ndHLjJaoZwnkQgCyo,1905
-castor_extractor/visualization/tableau_revamp/client/errors.py,sha256=ecT8Tit5VtzrOBB9ykblA0nvd75j5-_QDFupjV48zJQ,300
-castor_extractor/visualization/tableau_revamp/client/gql_queries.py,sha256=uKNGRhYeoiKfJ8vxO50L0a2fHDpYQgEdG_eZfYSdHqM,2238
-castor_extractor/visualization/tableau_revamp/client/rest_fields.py,sha256=3kvaq48BCBLfm7GL-i5W53MpbmSSi-e0yt31dNOk8ac,948
-castor_extractor/visualization/tableau_revamp/constants.py,sha256=lHGB50FgVNO2nXeIhkvQKivD8ZFBIjDrflgD5cTXKJw,104
-castor_extractor/visualization/tableau_revamp/extract.py,sha256=Ud_lt1YDSyCBjR38sjtvINy_Ez_TnA_jtM2D-8LcxPA,1471
+castor_extractor/visualization/tableau/__init__.py,sha256=eFI_1hjdkxyUiAYiy3szwyuwn3yJ5C_KbpBU0ySJDcQ,138
+castor_extractor/visualization/tableau/assets.py,sha256=HbCRd8VCj1WBEeqg9jwnygnT7xOFJ6PQD7Lq7sV-XR0,635
+castor_extractor/visualization/tableau/client/__init__.py,sha256=P8RKFKOC63WkH5hdEytJOwHS9vzQ8GXreLfXZetmMP8,78
+castor_extractor/visualization/tableau/client/client.py,sha256=zzqhzIqKyJygo4ZNGk6cZh0e6Z9R1W5T0P9un52KC1M,7626
+castor_extractor/visualization/tableau/client/client_metadata_api.py,sha256=fIBsSbRTypBABsCoigO2dkKsw4Eu3GrsEPTDfjY8A80,4303
+castor_extractor/visualization/tableau/client/client_rest_api.py,sha256=x4dNw4PPJdalTlGowwkANwqiS2ZhGxzpQytkHq3KbpY,3988
+castor_extractor/visualization/tableau/client/client_tsc.py,sha256=VI_PJyd1ty3HSYXHHQjshmG2ziowIbrwJRonRPCHbks,1820
+castor_extractor/visualization/tableau/client/credentials.py,sha256=uQICIgeXmLZfOroTgZt7PuKNKTyqQllRGSTcOmIfrKU,1893
+castor_extractor/visualization/tableau/client/errors.py,sha256=ecT8Tit5VtzrOBB9ykblA0nvd75j5-_QDFupjV48zJQ,300
+castor_extractor/visualization/tableau/client/gql_queries.py,sha256=NISarYh33Ij7DhYxqjTdv681AHYpbft8kPwVUQbAZ7U,2190
+castor_extractor/visualization/tableau/client/rest_fields.py,sha256=ZKYYuMxg9PXhczVXaD4rXNk7dYyWJ1_bVM8FLEXju7s,888
+castor_extractor/visualization/tableau/constants.py,sha256=lHGB50FgVNO2nXeIhkvQKivD8ZFBIjDrflgD5cTXKJw,104
+castor_extractor/visualization/tableau/extract.py,sha256=FnjmmUdNA9MEf3S5Tw37x6ZXxVsK8R3YnVk1UVYbaZk,1423
 castor_extractor/visualization/thoughtspot/__init__.py,sha256=NhTGUk5Kdt54oCjHYoAt0cLBmVLys5lFYiRANL6wCmI,150
 castor_extractor/visualization/thoughtspot/assets.py,sha256=SAQWPKaD2NTSDg7-GSkcRSSEkKSws0MJfOVcHkdeTSg,276
 castor_extractor/visualization/thoughtspot/client/__init__.py,sha256=svrE2rMxR-OXctjPeAHMEPePlfcra-9KDevTMcHunAA,86
@@ -401,8 +404,8 @@ castor_extractor/warehouse/sqlserver/queries/table.sql,sha256=kbBQP-TdG5px1IVgyx
 castor_extractor/warehouse/sqlserver/queries/user.sql,sha256=gOrZsMVypusR2dc4vwVs4E1a-CliRsr_UjnD2EbXs-A,94
 castor_extractor/warehouse/sqlserver/query.py,sha256=g0hPT-RmeGi2DyenAi3o72cTlQsLToXIFYojqc8E5fQ,533
 castor_extractor/warehouse/synapse/queries/column.sql,sha256=lNcFoIW3Y0PFOqoOzJEXmPvZvfAsY0AP63Mu2LuPzPo,1351
-castor_extractor-0.24.0.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
-castor_extractor-0.24.0.dist-info/METADATA,sha256=HWTKSDx_akRg3FK_dMP5mRxlLg9Oc55uGUYgt2NmYaQ,22828
-castor_extractor-0.24.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-castor_extractor-0.24.0.dist-info/entry_points.txt,sha256=7aVSxc-_2dicp28Ow-S4y0p4wGoTm9zGmVptMvfLdw8,1649
-castor_extractor-0.24.0.dist-info/RECORD,,
+castor_extractor-0.24.2.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
+castor_extractor-0.24.2.dist-info/METADATA,sha256=FNJlgmFPbgSmHoVwHx-hXj9rvHYw2wctlcEXeGck52I,23040
+castor_extractor-0.24.2.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+castor_extractor-0.24.2.dist-info/entry_points.txt,sha256=FQNShG4w4nRO95_bZnagh7FQ2oiZ-40bdt8ZdTW1-uI,1731
+castor_extractor-0.24.2.dist-info/RECORD,,

{castor_extractor-0.24.0.dist-info → castor_extractor-0.24.2.dist-info}/entry_points.txt

@@ -4,6 +4,7 @@ castor-extract-confluence=castor_extractor.commands.extract_confluence:main
 castor-extract-databricks=castor_extractor.commands.extract_databricks:main
 castor-extract-domo=castor_extractor.commands.extract_domo:main
 castor-extract-looker=castor_extractor.commands.extract_looker:main
+castor-extract-looker-studio=castor_extractor.commands.extract_looker_studio:main
 castor-extract-metabase-api=castor_extractor.commands.extract_metabase_api:main
 castor-extract-metabase-db=castor_extractor.commands.extract_metabase_db:main
 castor-extract-mode=castor_extractor.commands.extract_mode:main

castor_extractor/visualization/tableau_revamp/__init__.py

@@ -1,3 +0,0 @@
-from .assets import TableauRevampAsset
-from .client import TableauRevampClient, TableauRevampCredentials
-from .extract import extract_all, iterate_all_data

castor_extractor/visualization/tableau_revamp/client/__init__.py

@@ -1,2 +0,0 @@
-from .client import TableauRevampClient
-from .credentials import TableauRevampCredentials