castor-extractor 0.24.29__py3-none-any.whl → 0.24.33__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## 0.24.33 - 2025-07-10
+
+* Tableau - Add an option to skip fields ingestion
+
+## 0.24.32 - 2025-07-02
+
+* Salesforce reporting - extract report's metadata
+
+## 0.24.31 - 2025-07-02
+
+* Looker Studio: add option to list users via a provided JSON file
+
+## 0.24.30 - 2025-06-26
+
+* Sigma: remove retry on timeout, decrease pagination for queries
+
 ## 0.24.29 - 2025-06-24
 
 * Strategy: skip descriptions on ValueErrors

castor_extractor/commands/extract_looker_studio.py

@@ -30,6 +30,14 @@ def main():
         default=False,
         help="Skips the extraction of activity logs",
     )
+    parser.add_argument(
+        "--users-file-path",
+        help=(
+            "Optional path to a JSON file with user email addresses "
+            'as a list of strings (e.g. ["foo@bar.com", "fee@bar.com"]). '
+            "If provided, only extracts assets owned by the specified users."
+        ),
+    )
 
     parser.add_argument("-o", "--output", help="Directory to write to")
 

castor_extractor/commands/extract_tableau.py

@@ -28,6 +28,13 @@ def main():
         help="Option to avoid extracting Tableau columns, default to False",
     )
 
+    parser.add_argument(
+        "--skip-fields",
+        dest="skip_fields",
+        action="store_true",
+        help="Option to avoid extracting Tableau fields, default to False",
+    )
+
     parser.add_argument(
         "--with-pulse",
         dest="with_pulse",
@@ -41,6 +48,14 @@ def main():
         required=False,
     )
 
+    parser.add_argument(
+        "-ie",
+        "--ignore-errors",
+        action="store_true",
+        dest="ignore_errors",
+        help="Allow partial extraction of Fields and Columns: skip batch in case of Timeout errors",
+    )
+
     parser.add_argument("-o", "--output", help="Directory to write to")
 
     tableau.extract_all(**parse_filled_arguments(parser))

castor_extractor/visualization/looker_studio/client/client.py

@@ -36,23 +36,40 @@ class LookerStudioClient:
         self,
         credentials: LookerStudioCredentials,
         bigquery_credentials: Optional[dict] = None,
+        user_emails: Optional[list[str]] = None,
     ):
         self.admin_sdk_client = AdminSDKClient(credentials)
         self.looker_studio_client = LookerStudioAPIClient(credentials)
+        self.user_emails = user_emails
 
         self.bigquery_client: Optional[BigQueryClient] = None
         if bigquery_credentials:
             self.bigquery_client = BigQueryClient(bigquery_credentials)
 
-    def _get_assets(self) -> Iterator[dict]:
+    def _list_user_emails(self) -> Iterator[str]:
         """
-        Extracts reports and data sources user by user.
+        Lists user emails either from a provided JSON file or via the Admin SDK API.
+
+        Using all Google Workspace users can be inefficient for large clients -
+        the client might spend hours checking thousands of users for Looker Studio
+        assets when only a handful actually own any. A JSON file allows
+        targeting known owners instead.
         """
-        users = self.admin_sdk_client.list_users()
+        if self.user_emails is not None:
+            yield from self.user_emails
+            return
+
+        for user in self.admin_sdk_client.list_users():
+            yield user[USER_EMAIL_FIELD]
 
-        for user in users:
-            email = user[USER_EMAIL_FIELD]
-            yield from self.looker_studio_client.fetch_user_assets(email)
+    def _get_assets(self) -> Iterator[dict]:
+        """
+        Extracts reports and data sources user by user. The loop is necessary
+        because the Looker Studio API can only retrieve the assets owned by a
+        single user.
+        """
+        for user_email in self._list_user_emails():
+            yield from self.looker_studio_client.fetch_user_assets(user_email)
 
     def _get_source_queries(self) -> Iterator[dict]:
         """

castor_extractor/visualization/looker_studio/extract.py

@@ -70,21 +70,53 @@ def _bigquery_credentials_or_none(params: dict) -> Optional[dict]:
         return cast(dict, json.load(file))
 
 
+def _validate_user_emails(user_emails: list[str]):
+    """
+    Raises an error if the user emails are not in the expected format (list of strings),
+    or if the list is empty.
+    """
+    if not isinstance(user_emails, list):
+        raise TypeError("The users file must be a list")
+
+    if len(user_emails) == 0:
+        raise ValueError("The users file must contain at least one user email")
+
+    if not all(isinstance(email, str) for email in user_emails):
+        raise TypeError("All items in users list must be strings")
+
+
+def _read_optional_user_emails(
+    users_file_path: Optional[str],
+) -> Optional[list[str]]:
+    """Loads the user emails from a file, if it was provided."""
+    if not users_file_path:
+        return None
+
+    with open(users_file_path, "r") as file:
+        user_emails = json.load(file)
+
+    _validate_user_emails(user_emails)
+    return user_emails
+
+
 def extract_all(**kwargs) -> None:
     """
     Extracts data from Looker Studio and stores the output files locally under
     the given output_directory.
     """
+    users_file_path = kwargs.get("users_file_path")
     output_directory = kwargs.get("output") or from_env(OUTPUT_DIR)
 
     credentials = _credentials(kwargs)
     has_view_activity_logs = bool(credentials.has_view_activity_logs)
+    user_emails = _read_optional_user_emails(users_file_path)
 
     bigquery_credentials = _bigquery_credentials_or_none(kwargs)
 
     client = LookerStudioClient(
         credentials=credentials,
         bigquery_credentials=bigquery_credentials,
+        user_emails=user_emails,
     )
     ts = current_timestamp()
 

castor_extractor/visualization/looker_studio/extract_test.py

@@ -0,0 +1,19 @@
+import pytest
+
+from .extract import _validate_user_emails
+
+
+def test__validate_user_emails():
+    with pytest.raises(TypeError):
+        _validate_user_emails("toto@tata.com")
+
+    with pytest.raises(TypeError):
+        _validate_user_emails({"not": "the", "right": "format"})
+
+    with pytest.raises(ValueError):
+        _validate_user_emails([])
+
+    with pytest.raises(TypeError):
+        _validate_user_emails([1, 2, 3, 4])
+
+    _validate_user_emails(["admin@toto.com", "tata@toto.com"])

castor_extractor/visualization/salesforce_reporting/assets.py

@@ -8,4 +8,5 @@ class SalesforceReportingAsset(ExternalAsset):
     DASHBOARD_COMPONENTS = "dashboard_components"
     FOLDERS = "folders"
     REPORTS = "reports"
+    REPORTS_METADATA = "reports_metadata"
     USERS = "users"

castor_extractor/visualization/salesforce_reporting/client/rest.py

@@ -1,7 +1,10 @@
 import logging
 from collections.abc import Iterator
+from concurrent.futures import ThreadPoolExecutor
 from typing import Optional
 
+import requests
+
 from ....utils import build_url
 from ....utils.salesforce import SalesforceBaseClient
 from ..assets import SalesforceReportingAsset
@@ -15,6 +18,8 @@ REQUIRING_URL_ASSETS = (
     SalesforceReportingAsset.FOLDERS,
 )
 
+_CONCURRENT_THREADS = 50
+
 
 class SalesforceReportingClient(SalesforceBaseClient):
     """
@@ -50,6 +55,50 @@ class SalesforceReportingClient(SalesforceBaseClient):
             url = self._get_asset_url(asset_type, asset)
             yield {**asset, "Url": url}
 
+    def _metadata(self, report_id: str) -> Optional[dict]:
+        url = f"services/data/v60.0/analytics/reports/{report_id}/describe"
+        try:
+            metadata = self._get(url, retry_on_timeout=False)
+            # pick only what we need to build the lineage
+            columns = metadata["reportExtendedMetadata"]["detailColumnInfo"]
+            return {
+                "reportId": report_id,
+                "detailColumnInfo": columns or dict(),
+            }
+        except (requests.HTTPError, requests.RequestException) as ex:
+            # Extracting column metadata is used only for lineage purposes
+            # and is non-critical. API errors are common during this step,
+            # so we choose to skip them rather than fail the process. The same
+            # rows consistently fail, and retries have proven ineffective.
+            logger.info(ex)
+            return None
+
+    def _fetch_reports_metadata(self) -> Iterator[dict]:
+        """
+        Use the "describe" endpoint to extract report metadata.
+        Keep only the detailColumnInfo, which is required for building the lineage.
+
+        More info here:
+        https://developer.salesforce.com/docs/atlas.en-us.api_analytics.meta/api_analytics/sforce_analytics_rest_api_getbasic_reportmetadata.htm
+        https://www.notion.so/castordoc/Salesforce-Lineage-216a1c3d458580859888cf4ca2d7fa51?source=copy_link
+        """
+        # The "describe" endpoint requires report_ids. To avoid introducing
+        # task dependencies, we opted to re-extract the reports.
+        # It is fast anyway, since it's running a SQL query
+        reports = self.fetch(SalesforceReportingAsset.REPORTS)
+        report_ids = [report["Id"] for report in reports]
+
+        # Calling "describe" on each report individually can be slow,
+        # especially for accounts with thousands of reports. That's why
+        # we use multithreading here — it significantly improves performance.
+        with ThreadPoolExecutor(max_workers=_CONCURRENT_THREADS) as executor:
+            fetch_results = executor.map(self._metadata, report_ids)
+
+            for metadata in fetch_results:
+                if not metadata:
+                    continue
+                yield metadata
+
     def fetch(self, asset: SalesforceReportingAsset) -> list[dict]:
         """
         Fetch Salesforce Reporting assets
@@ -59,4 +108,7 @@ class SalesforceReportingClient(SalesforceBaseClient):
         if asset in REQUIRING_URL_ASSETS:
             return list(self._fetch_and_add_url(asset))
 
+        if asset == SalesforceReportingAsset.REPORTS_METADATA:
+            return list(self._fetch_reports_metadata())
+
         return list(self._query_all(queries[asset]))

castor_extractor/visualization/sigma/client/client.py

@@ -2,7 +2,7 @@ from collections.abc import Iterator
 from concurrent.futures import ThreadPoolExecutor
 from functools import partial
 from http import HTTPStatus
-from typing import Callable, Optional
+from typing import Callable, Iterable, Optional
 
 import requests
 from pydantic import BaseModel
@@ -19,7 +19,11 @@ from ....utils import (
 from ..assets import SigmaAsset
 from .credentials import SigmaCredentials
 from .endpoints import SigmaEndpointFactory
-from .pagination import SIGMA_API_LIMIT, SigmaPagination
+from .pagination import (
+    SIGMA_API_LIMIT,
+    SIGMA_QUERIES_PAGINATION_LIMIT,
+    SigmaPagination,
+)
 
 _CONTENT_TYPE = "application/x-www-form-urlencoded"
 
@@ -101,9 +105,27 @@ class SigmaClient(APIClient):
             safe_mode=safe_mode or SIGMA_SAFE_MODE,
         )
 
-    def _get_paginated(self, endpoint: str) -> Callable:
+    def _get_paginated(
+        self,
+        endpoint: str,
+        limit: int = SIGMA_API_LIMIT,
+    ) -> Callable:
+        """
+        Sigma’s API does not experience random timeouts, unlike some other APIs.
+        However, extracting queries from certain workbooks can take a
+        significant amount of time.
+        Previously, when a timeout occurred, the system would retry multiple
+        times — even though we knew it would eventually fail due to the inherent
+        slowness of the operation.
+        These retries only delayed the inevitable failure without adding value.
+        To address this, we've disabled retries on timeout and instead adjusted
+        the page size when extracting queries.
+        """
         return partial(
-            self._get, endpoint=endpoint, params={"limit": SIGMA_API_LIMIT}
+            self._get,
+            retry_on_timeout=False,  # explained in the docstring
+            endpoint=endpoint,
+            params={"limit": limit},
         )
 
     def _get_all_datasets(self) -> Iterator[dict]:
@@ -200,16 +222,34 @@ class SigmaClient(APIClient):
                 "element_id": lineage.context.element_id,
             }
 
+    @staticmethod
+    def _yield_deduplicated_queries(
+        queries: Iterable[dict], workbook_id: str
+    ) -> Iterator[dict]:
+        """
+        Returns unique queries for a workbook. This is necessary because the API
+        unfortunately returns duplicate entries for some workbook elements.
+        """
+        seen_elements = set()
+
+        for query in queries:
+            element_id = query["elementId"]
+            if element_id in seen_elements:
+                continue
+
+            seen_elements.add(element_id)
+            yield {**query, "workbook_id": workbook_id}
+
     def _get_all_queries(self, workbooks: list[dict]) -> Iterator[dict]:
         for workbook in workbooks:
             workbook_id = workbook["workbookId"]
             request = self._get_paginated(
-                SigmaEndpointFactory.queries(workbook_id)
+                SigmaEndpointFactory.queries(workbook_id),
+                limit=SIGMA_QUERIES_PAGINATION_LIMIT,
             )
             queries = fetch_all_pages(request, SigmaPagination)
 
-            for query in queries:
-                yield {**query, "workbook_id": workbook_id}
+            yield from self._yield_deduplicated_queries(queries, workbook_id)
 
     def fetch(
         self,

castor_extractor/visualization/sigma/client/client_test.py

@@ -0,0 +1,19 @@
+from .client import SigmaClient
+
+
+def test_SigmaClient__yield_deduplicated_queries():
+    workbook_id = "workbook1"
+    mock_queries = [
+        {"elementId": "element1", "name": "Query 1"},
+        {"elementId": "element2", "name": "Query 2"},
+        {"elementId": "element1", "name": "Query 1"},  # Duplicate
+        {"elementId": "element3", "name": "Query 3"},
+    ]
+
+    queries = list(
+        SigmaClient._yield_deduplicated_queries(mock_queries, workbook_id)
+    )
+
+    assert len(queries) == 3
+    for query in queries:
+        assert query["workbook_id"] == workbook_id

castor_extractor/visualization/sigma/client/pagination.py

@@ -6,6 +6,7 @@ from pydantic.alias_generators import to_camel
 from ....utils import PaginationModel
 
 SIGMA_API_LIMIT = 200  # default number of records per page
+SIGMA_QUERIES_PAGINATION_LIMIT = 50
 
 
 class SigmaPagination(PaginationModel):

castor_extractor/visualization/tableau/client/client.py

@@ -122,13 +122,17 @@ class TableauClient:
         credentials: TableauCredentials,
         timeout_sec: int = DEFAULT_TIMEOUT_SECONDS,
         with_columns: bool = True,
+        with_fields: bool = True,
         with_pulse: bool = False,
         override_page_size: Optional[int] = None,
+        ignore_errors: bool = False,
     ):
         self._credentials = credentials
         self._server = _server(credentials.server_url, timeout_sec)
         self._with_columns = with_columns
+        self._with_fields = with_fields
         self._with_pulse = with_pulse
+        self._ignore_errors = ignore_errors
 
         self._client_metadata = TableauClientMetadataApi(
             server=self._server,
@@ -221,6 +225,10 @@ class TableauClient:
             logger.info(f"Skipping asset {asset} - deactivated columns")
             return []
 
+        if asset == TableauAsset.FIELD and not self._with_fields:
+            logger.info(f"Skipping asset {asset} - deactivated fields")
+            return []
+
         logger.info(f"Extracting {asset.name}...")
 
         if asset == TableauAsset.DATASOURCE:
@@ -240,4 +248,4 @@ class TableauClient:
             return self._client_rest.fetch(asset)
 
         # other assets can be extracted via Metadata API
-        return self._client_metadata.fetch(asset)
+        return self._client_metadata.fetch(asset, self._ignore_errors)

castor_extractor/visualization/tableau/client/client_metadata_api.py

@@ -2,6 +2,7 @@ import logging
 from collections.abc import Iterator
 from typing import Optional
 
+import requests
 import tableauserverclient as TSC  # type: ignore
 
 from ....utils import SerializedAsset, retry
@@ -12,6 +13,13 @@ from .gql_queries import FIELDS_QUERIES, GQL_QUERIES, QUERY_TEMPLATE
 
 logger = logging.getLogger(__name__)
 
+# These assets are known to be error-prone, so it's acceptable if a few are missed.
+# If errors occur, skip the current batch.
+_SAFE_MODE_ASSETS = (
+    TableauAsset.COLUMN,
+    TableauAsset.FIELD,
+)
+
 # increase the value when extraction is too slow
 # decrease the value when timeouts arise
 _CUSTOM_PAGE_SIZE: dict[TableauAsset, int] = {
@@ -92,6 +100,7 @@ def gql_query_scroll(
     resource: str,
     fields: str,
     page_size: int,
+    skip_batch: bool,
 ) -> Iterator[SerializedAsset]:
     """
     Iterate over GQL query results, handling pagination and cursor
@@ -119,15 +128,22 @@ def gql_query_scroll(
 
     current_offset = 0
     while True:
-        payload = _call(first=page_size, offset=current_offset)
-        yield payload["nodes"]
+        try:
+            payload = _call(first=page_size, offset=current_offset)
+            yield payload["nodes"]
+
+            current_offset += len(payload["nodes"])
+            total = payload["totalCount"]
+            logger.info(f"Extracted {current_offset}/{total} {resource}")
 
-        current_offset += len(payload["nodes"])
-        total = payload["totalCount"]
-        logger.info(f"Extracted {current_offset}/{total} {resource}")
+            if not payload["pageInfo"]["hasNextPage"]:
+                break
+        except requests.exceptions.ReadTimeout:
+            if not skip_batch:
+                raise
 
-        if not payload["pageInfo"]["hasNextPage"]:
-            break
+            logger.warning("Skipping batch because of TableauServer Timeout")
+            current_offset += page_size
 
 
 def _deduplicate(result_pages: Iterator[SerializedAsset]) -> SerializedAsset:
@@ -177,12 +193,14 @@ class TableauClientMetadataApi:
         resource: str,
         fields: str,
         page_size: int = DEFAULT_PAGE_SIZE,
+        skip_batch: bool = False,
     ) -> SerializedAsset:
         result_pages = gql_query_scroll(
             self._server,
             resource=resource,
             fields=fields,
             page_size=page_size,
+            skip_batch=skip_batch,
         )
         return _deduplicate(result_pages)
 
@@ -193,21 +211,41 @@ class TableauClientMetadataApi:
             or DEFAULT_PAGE_SIZE
         )
 
-    def _fetch_fields(self) -> SerializedAsset:
+    def _fetch_fields(self, skip_batch: bool = False) -> SerializedAsset:
         result: SerializedAsset = []
         page_size = self._page_size(TableauAsset.FIELD)
         for resource, fields in FIELDS_QUERIES:
-            current = self._call(resource, fields, page_size)
+            current = self._call(
+                resource,
+                fields,
+                page_size,
+                skip_batch=skip_batch,
+            )
             result.extend(current)
         return result
 
+    @staticmethod
+    def _should_skip_batch_with_timeout(
+        asset: TableauAsset,
+        ignore_metadata_errors: bool = False,
+    ) -> bool:
+        return asset in _SAFE_MODE_ASSETS and ignore_metadata_errors
+
     def fetch(
         self,
         asset: TableauAsset,
+        ignore_errors: bool = False,
     ) -> SerializedAsset:
+        skip_batch = self._should_skip_batch_with_timeout(asset, ignore_errors)
+
         if asset == TableauAsset.FIELD:
-            return self._fetch_fields()
+            return self._fetch_fields(skip_batch=skip_batch)
 
         page_size = self._page_size(asset)
         resource, fields = GQL_QUERIES[asset]
-        return self._call(resource, fields, page_size)
+        return self._call(
+            resource=resource,
+            fields=fields,
+            page_size=page_size,
+            skip_batch=skip_batch,
+        )

castor_extractor/visualization/tableau/extract.py

@@ -33,16 +33,20 @@ def extract_all(**kwargs) -> None:
     """
     output_directory = kwargs.get("output") or from_env(OUTPUT_DIR)
     with_columns = not kwargs.get("skip_columns")
+    with_fields = not kwargs.get("skip_fields")
     with_pulse = kwargs.get("with_pulse") or False
     page_size = kwargs.get("page_size")
+    ignore_errors = kwargs.get("ignore_errors") or False
     timestamp = current_timestamp()
 
     credentials = TableauCredentials(**kwargs)
     client = TableauClient(
         credentials,
         with_columns=with_columns,
+        with_fields=with_fields,
         with_pulse=with_pulse,
         override_page_size=page_size,
+        ignore_errors=ignore_errors,
     )
     client.login()
 

castor_extractor/warehouse/databricks/sql_client.py

@@ -1,7 +1,6 @@
 import logging
 from collections import defaultdict
 from datetime import date
-from typing import Optional
 
 from databricks import sql  # type: ignore
 
@@ -17,7 +16,7 @@ _INFORMATION_SCHEMA_SQL = "SELECT * FROM system.information_schema"
 
 _LINEAGE_SQL_TPL = """
 SELECT * FROM system.access.{table_name}
-WHERE event_date = :day
+WHERE event_date = DATE('{day}')
 """
 
 
@@ -34,11 +33,7 @@ class DatabricksSQLClient:
         self._host = credentials.host
         self._token = credentials.token
 
-    def execute_sql(
-        self,
-        query: str,
-        params: Optional[dict] = None,
-    ):
+    def execute_sql(self, query: str):
         """
         Execute a SQL query on Databricks system tables and return the results.
         https://docs.databricks.com/en/dev-tools/python-sql-connector.html
@@ -52,7 +47,7 @@ class DatabricksSQLClient:
             access_token=self._token,
         ) as connection:
             with connection.cursor() as cursor:
-                cursor.execute(query, params)
+                cursor.execute(query)
                 return cursor.fetchall()
 
     def _needs_extraction(self, entity: TagEntity) -> bool:
@@ -89,16 +84,23 @@ class DatabricksSQLClient:
         return mapping
 
     def get_lineage(
-        self, lineage_entity: LineageEntity, day: date
+        self,
+        lineage_entity: LineageEntity,
+        day: date,
     ) -> list[dict]:
         """
         Fetch {TABLE|COLUMN} lineage of the given day, via system tables
         https://docs.databricks.com/en/admin/system-tables/lineage.html
+
+        Unfortunately, passing parameters is not always supported. We have to
+        format the query beforehand and pass it as plain text for execution.
         """
         table_name = f"{lineage_entity.value.lower()}_lineage"
-        query = _LINEAGE_SQL_TPL.format(table_name=table_name)
-        params = {"day": day}
-        result = self.execute_sql(query, params)
+        query = _LINEAGE_SQL_TPL.format(
+            table_name=table_name,
+            day=day,
+        )
+        result = self.execute_sql(query)
         data = []
         for row in result:
             data.append(row.asDict())

{castor_extractor-0.24.29.dist-info → castor_extractor-0.24.33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.24.29
+Version: 0.24.33
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
@@ -215,6 +215,22 @@ For any questions or bug report, contact us at [support@coalesce.io](mailto:supp
 
 # Changelog
 
+## 0.24.33 - 2025-07-10
+
+* Tableau - Add an option to skip fields ingestion
+
+## 0.24.32 - 2025-07-02
+
+* Salesforce reporting - extract report's metadata
+
+## 0.24.31 - 2025-07-02
+
+* Looker Studio: add option to list users via a provided JSON file
+
+## 0.24.30 - 2025-06-26
+
+* Sigma: remove retry on timeout, decrease pagination for queries
+
 ## 0.24.29 - 2025-06-24
 
 * Strategy: skip descriptions on ValueErrors

{castor_extractor-0.24.29.dist-info → castor_extractor-0.24.33.dist-info}/RECORD

@@ -1,4 +1,4 @@
-CHANGELOG.md,sha256=GanHBv0C_fiKSfPSLzumCuBYUIQy4ZRLbA9BAXZYFAg,18440
+CHANGELOG.md,sha256=jKQMJGiDeDEZG-753wDrtfOoOYa5Db5Liy0AsATdsuc,18779
 Dockerfile,sha256=xQ05-CFfGShT3oUqaiumaldwA288dj9Yb_pxofQpufg,301
 DockerfileUsage.md,sha256=2hkJQF-5JuuzfPZ7IOxgM6QgIQW7l-9oRMFVwyXC4gE,998
 LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
@@ -10,7 +10,7 @@ castor_extractor/commands/extract_confluence.py,sha256=blYcnDqywXNKRQ1aZAD9FclhL
 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=M7wx8XZScLizCI2vq80aj88vYrdiHChiCiebrrChlZY,1090
+castor_extractor/commands/extract_looker_studio.py,sha256=YFQWabmBEaWZFCquMNZw_iq6TF95KBVGdemcYiJMhk8,1399
 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
@@ -26,7 +26,7 @@ castor_extractor/commands/extract_sigma.py,sha256=sxewHcZ1Doq35V2qnpX_zCKKXkrb1_
 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_strategy.py,sha256=Q-pUymatPrBFGXobhyUPzFph0-t774-XOpjdCFF1dYo,821
-castor_extractor/commands/extract_tableau.py,sha256=ngujGYohWOqOK1qjIP1Hh951jr0KNKNSeOyoaOnO450,1558
+castor_extractor/commands/extract_tableau.py,sha256=LNtI29LbVk1vp4RNrn89GmdW6R_7QBYunRmkowDhbco,1982
 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
@@ -191,14 +191,15 @@ castor_extractor/visualization/looker_studio/__init__.py,sha256=GccG-GJXoNhjXFPk
 castor_extractor/visualization/looker_studio/assets.py,sha256=rI73rbVrfwkkepqZr0zPouP2lPUfJxSi21RKtOTHtAA,308
 castor_extractor/visualization/looker_studio/client/__init__.py,sha256=YkQaVDJa-7KSwdOLjtgKJMRiafbGNKC_46YVx0hYZ1Q,129
 castor_extractor/visualization/looker_studio/client/admin_sdk_client.py,sha256=HIeyT9JTW1TPwVzD2Q-VfJ99jMP80Z-4CznKAnTnp2w,3493
-castor_extractor/visualization/looker_studio/client/client.py,sha256=6sTfLRUhuxhkqDjC2ZBEaw6YnR6ze8-_VW2rc1u9Ksk,3191
+castor_extractor/visualization/looker_studio/client/client.py,sha256=N4AtFMAPhLoe2i2rVhCbqEVIoxzcBKFh29V9LjRcdH0,3969
 castor_extractor/visualization/looker_studio/client/credentials.py,sha256=F4ISI8Ua_HJsMuGhYql28o3hKYR4sL_uzkrUkRiekRo,1347
 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=Phq378VEaFLD-nyP2_A1wge6HUP45jSthhlNjD7aqSg,4085
 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/extract.py,sha256=uNpvg4wtFflmpkqXFfo_9Nm12AEKXBOCKKajIggySho,3026
+castor_extractor/visualization/looker_studio/extract.py,sha256=NU48xQ83UtRW3jXKJcvofzqgEM2lHGjtTzjbKOSB50A,4059
+castor_extractor/visualization/looker_studio/extract_test.py,sha256=ZckAxUMuoEjJ9RWkfRvt9M8SxblkQvsq-Grb8GSs-y0,492
 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
@@ -264,18 +265,19 @@ castor_extractor/visualization/qlik/client/rest.py,sha256=x_Vx0xjRvj4D5FPm2CzBH_
 castor_extractor/visualization/qlik/client/rest_test.py,sha256=yfiUht6BcpBYS2uGdaKCH-tYe0fQ-joM4MbitKwOf24,1799
 castor_extractor/visualization/qlik/extract.py,sha256=CkJ2UELZmADUxdB84VGH5-qd1tz9Dh_ywoLULTkbrII,2186
 castor_extractor/visualization/salesforce_reporting/__init__.py,sha256=MvArD0GKNIpCDvLIYcpKrjMjFLhMyDETK6i3k0Fb6Tk,124
-castor_extractor/visualization/salesforce_reporting/assets.py,sha256=2J-iAmJGGDufOcJUgE47M3-dEcjYXcVyVUNcmHrj79w,271
+castor_extractor/visualization/salesforce_reporting/assets.py,sha256=m9UnyaocyzSYZh-NkiyjAyk9D1OMBwyP9gqAJrSIwMg,313
 castor_extractor/visualization/salesforce_reporting/client/__init__.py,sha256=DIA6f_vNJZqT89qVYxg98Le7QeDn2y0Qew03V3J9t9o,44
-castor_extractor/visualization/salesforce_reporting/client/rest.py,sha256=-wKDSsAvc38EU5vYmH9pHAJRMNSsICLx_KvPnFEUDFg,1881
+castor_extractor/visualization/salesforce_reporting/client/rest.py,sha256=AqL1DTOpRy9KToJTlZohqUaRR5q-Xta79exi8odh2uE,4333
 castor_extractor/visualization/salesforce_reporting/client/soql.py,sha256=ytZnX6zE-NoS_Kz12KghMcCM4ukPwhMj6U0rQZ_8Isk,1621
 castor_extractor/visualization/salesforce_reporting/extract.py,sha256=ScStilebLGf4HDTFqhVTQAvv_OrKxc8waycfBKdsVAc,1359
 castor_extractor/visualization/sigma/__init__.py,sha256=GINql4yJLtjfOJgjHaWNpE13cMtnKNytiFRomwav27Q,114
 castor_extractor/visualization/sigma/assets.py,sha256=JZ1Cpxnml8P3mIJoTUM57hvylB18ErECQXaP5FF63O4,268
 castor_extractor/visualization/sigma/client/__init__.py,sha256=YQv06FBBQHvBMFg_tN0nUcmUp2NCL2s-eFTXG8rXaBg,74
-castor_extractor/visualization/sigma/client/client.py,sha256=d9CpE7vRZAPGzck0jFn37LY_6E_Njz9D1sCnFVGJSWk,8006
+castor_extractor/visualization/sigma/client/client.py,sha256=ZE44k5klBVnc5lld3tpjuKGeSdFmlJ0wr5DOB4pEfco,9446
+castor_extractor/visualization/sigma/client/client_test.py,sha256=ae0ZOvKutCm44jnrJ-0_A5Y6ZGyDkMf9Ml3eEP8dNkY,581
 castor_extractor/visualization/sigma/client/credentials.py,sha256=XddAuQSmCKpxJ70TQgRnOj0vMPYVtiStk_lMMQ1AiNM,693
 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/client/pagination.py,sha256=2bFA7GiBUUasFtHJKA90516d283p7Pg50-4zw6Fwt8I,726
 castor_extractor/visualization/sigma/extract.py,sha256=XIT1qsj6g6dgBWP8HPfj_medZexu48EaY9tUwi14gzM,2298
 castor_extractor/visualization/strategy/__init__.py,sha256=HOMv4JxqF5ZmViWi-pDE-PSXJRLTdXal_jtpHG_rlR8,123
 castor_extractor/visualization/strategy/assets.py,sha256=yFXF_dX01patC0HQ1eU7Jo_4DZ4m6IJEg0uCB71tMoI,480
@@ -287,8 +289,8 @@ castor_extractor/visualization/strategy/extract.py,sha256=2fBuvS2xiOGXRpxXnZsE_C
 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=iJ3Y-vwPvmPyAUTs1PqFJEZelPGiLvsiwXpTI3b5THc,7867
-castor_extractor/visualization/tableau/client/client_metadata_api.py,sha256=ryRq4_qUok8vvWGhj5CNWXtwR2JlUsu1qjsov2KhQTE,6286
+castor_extractor/visualization/tableau/client/client.py,sha256=QV-GFS4nEq976JLji57pIfsw2ZZaGTvfCFqy6_HOWMg,8204
+castor_extractor/visualization/tableau/client/client_metadata_api.py,sha256=eAq9rjrB_2ZCQy9NwREHBOTXZffWdkwtwhzswm1pEfk,7449
 castor_extractor/visualization/tableau/client/client_metadata_api_test.py,sha256=rikyQKDLFYHLJhHJTF3LwWhKJ80svtTsYp5n7n9oTU8,2665
 castor_extractor/visualization/tableau/client/client_rest_api.py,sha256=x4dNw4PPJdalTlGowwkANwqiS2ZhGxzpQytkHq3KbpY,3988
 castor_extractor/visualization/tableau/client/client_tsc.py,sha256=VI_PJyd1ty3HSYXHHQjshmG2ziowIbrwJRonRPCHbks,1820
@@ -297,7 +299,7 @@ castor_extractor/visualization/tableau/client/errors.py,sha256=ecT8Tit5VtzrOBB9y
 castor_extractor/visualization/tableau/client/gql_queries.py,sha256=XJAfhpMZ5S7-AhfpOaoHMHCAdil-l5e5xB-CH4NC38M,2177
 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=hGVr1BZVsHlIgNXOFusRN2YwUUhXvF3reOeN8g1CTEo,1508
+castor_extractor/visualization/tableau/extract.py,sha256=9mSHFJ2DGlW-cDYiRZlJafAgj4_ObACxO0l9vBBfjUw,1683
 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
@@ -345,7 +347,7 @@ castor_extractor/warehouse/databricks/format_test.py,sha256=ls0IcOElqp_qecAzNbK0
 castor_extractor/warehouse/databricks/lineage.py,sha256=jwiRXrgqBAtzQt5EgErYrN8YRyviEEHmyrSbw8TSPq4,2105
 castor_extractor/warehouse/databricks/lineage_test.py,sha256=PyBn1eAoxLm4Bz5M0F4zmaxFX2mXRTM_uug5OKbQPQs,2684
 castor_extractor/warehouse/databricks/pagination.py,sha256=sM1G0sN1pf1TPpI0Y3Oew378UGEKVkMRc2Mlu9tDjLo,545
-castor_extractor/warehouse/databricks/sql_client.py,sha256=5isGsRL0MW1lu_E_xTyCvSj_rwaJ2nh-kPlhvTvDy_w,3566
+castor_extractor/warehouse/databricks/sql_client.py,sha256=BchHMNqHPtZsJWhj2XYq3QVVTj3XfKhzhhPTJng8vXo,3656
 castor_extractor/warehouse/databricks/types.py,sha256=-TFX4jS6_c3wQLOpJTKpLeGS21YIPjKDjISnzeUPdCc,46
 castor_extractor/warehouse/databricks/utils.py,sha256=5CKn6Me1Tus97H_qDEz_5tkhd4ARmwk2qiC3GndjyCc,1969
 castor_extractor/warehouse/databricks/utils_test.py,sha256=_guTuzRWRTZdDY7ils0X1K8jhI9T877MEtw3x_YDg9I,2415
@@ -428,8 +430,8 @@ 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-0.24.29.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
-castor_extractor-0.24.29.dist-info/METADATA,sha256=0aRiXGPqFGxNnPoSmsuE1BkgRCalVbEotI17_Vv2VDo,25893
-castor_extractor-0.24.29.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-castor_extractor-0.24.29.dist-info/entry_points.txt,sha256=_F-qeZCybjoMkNb9ErEhnyqXuG6afHIFQhakdBHZsr4,1803
-castor_extractor-0.24.29.dist-info/RECORD,,
+castor_extractor-0.24.33.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
+castor_extractor-0.24.33.dist-info/METADATA,sha256=vCEpwDM8sngoUEfrGtRPSjtCjTw6zxJGiJrnmj4eq_Y,26232
+castor_extractor-0.24.33.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+castor_extractor-0.24.33.dist-info/entry_points.txt,sha256=_F-qeZCybjoMkNb9ErEhnyqXuG6afHIFQhakdBHZsr4,1803
+castor_extractor-0.24.33.dist-info/RECORD,,