castor-extractor 0.16.6__py3-none-any.whl → 0.16.9__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,18 @@
 # Changelog
 
+## 0.16.9 - 2024-05-28
+
+* Tableau: extract only fields that are necessary
+
+## 0.16.8 - 2024-05-21
+
+* Add compatibility with python 3.12
+* Looker: Bump looker-sdk and refactor client
+
+## 0.16.7 - 2024-05-16
+
+* Databricks: allow no emails on user
+
 ## 0.16.6 - 2024-05-14
 
 * Introducing the revamped connector for Tableau

castor_extractor/utils/__init__.py

@@ -5,7 +5,7 @@ from .client import (
     SqlalchemyClient,
     uri_encode,
 )
-from .collection import group_by
+from .collection import group_by, mapping_from_rows
 from .constants import OUTPUT_DIR
 from .deprecate import deprecate_python
 from .env import from_env
@@ -32,6 +32,7 @@ from .time import (
     current_timestamp,
     date_after,
     past_date,
+    timestamp_ms,
 )
 from .type import Callback, Getter, JsonType, SerializedAsset
 from .validation import validate_baseurl

castor_extractor/utils/collection.py

@@ -12,3 +12,35 @@ def group_by(identifier: Getter, elements: Sequence) -> Dict[Any, List]:
         groups[key].append(element)
 
     return groups
+
+
+def mapping_from_rows(rows: List[Dict], key: Any, value: Any) -> Dict:
+    """
+    Create a dictionary mapping from a list of dictionaries using specified keys for mapping.
+
+    Args:
+        rows (list[dict]): A list of dictionaries from which to create the mapping.
+        key (Any): The key to use for the keys of the resulting dictionary.
+        value (Any): The key to use for the values of the resulting dictionary.
+
+    Returns:
+        dict: A dictionary where each key-value pair corresponds to the specified key and value
+              from each dictionary in the input list. Only dictionaries with both specified key
+              and value present are included in the result.
+
+    Example:
+        rows = [{'id': 1, 'name': 'Alice'}, {'id': 2, 'name': 'Bob'}]
+        mapping = mapping_from_rows(rows, 'id', 'name')
+        # mapping will be {1: 'Alice', 2: 'Bob'}
+    """
+    mapping = {}
+
+    for row in rows:
+        mapping_key = row.get(key)
+        mapping_value = row.get(value)
+
+        if not mapping_key or not mapping_value:
+            continue
+        mapping[mapping_key] = mapping_value
+
+    return mapping

castor_extractor/utils/collection_test.py

@@ -0,0 +1,60 @@
+import pytest
+
+from .collection import mapping_from_rows
+
+
+def test__mapping_from_rows__basic_mapping():
+    rows = [{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {1: "Alice", 2: "Bob"}
+    assert result == expected
+
+
+def test__mapping_from_rows__missing_key():
+    rows = [{"id": 1, "name": "Alice"}, {"name": "Bob"}]
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {1: "Alice"}
+    assert result == expected
+
+
+def test__mapping_from_rows__missing_value():
+    rows = [{"id": 1, "name": "Alice"}, {"id": 2}]
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {1: "Alice"}
+    assert result == expected
+
+
+def test__mapping_from_rows__empty_list():
+    rows = []
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {}
+    assert result == expected
+
+
+def test__mapping_from_rows__non_existent_key_value():
+    rows = [{"id": 1, "name": "Alice"}, {"id": 2, "name": "Bob"}]
+    result = mapping_from_rows(rows, "nonexistent_key", "nonexistent_value")
+    expected = {}
+    assert result == expected
+
+
+def test__mapping_from_rows__none_key_value():
+    rows = [
+        {"id": 1, "name": "Alice"},
+        {"id": None, "name": "Bob"},
+        {"id": 2, "name": None},
+    ]
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {1: "Alice"}
+    assert result == expected
+
+
+def test__mapping_from_rows__multiple_valid_rows():
+    rows = [
+        {"id": 1, "name": "Alice"},
+        {"id": 2, "name": "Bob"},
+        {"id": 3, "name": "Charlie"},
+    ]
+    result = mapping_from_rows(rows, "id", "name")
+    expected = {1: "Alice", 2: "Bob", 3: "Charlie"}
+    assert result == expected

castor_extractor/utils/time.py

@@ -15,7 +15,7 @@ def current_timestamp() -> int:
     """
     Returns the current timestamp from epoch (rounded to the nearest second)
     """
-    return int(datetime.timestamp(current_datetime()))
+    return int(current_datetime().timestamp())
 
 
 def _set_uct_timezone(ts: datetime) -> datetime:
@@ -24,6 +24,14 @@ def _set_uct_timezone(ts: datetime) -> datetime:
     return ts
 
 
+def timestamp_ms(ts: datetime) -> int:
+    """
+    Return ts timestamp in millisecond (rounded)
+    """
+    ts_utc = _set_uct_timezone(ts)
+    return int(ts_utc.timestamp() * 1000)
+
+
 def now(tz: bool = False) -> datetime:
     """
     provide current time

castor_extractor/utils/time_test.py

@@ -1,6 +1,6 @@
 from datetime import date, datetime
 
-from .time import at_midnight, date_after
+from .time import at_midnight, date_after, timestamp_ms
 
 
 def test_at_midnight():
@@ -10,3 +10,10 @@ def test_at_midnight():
 def test_date_after():
     day = date(1999, 12, 31)
     assert date_after(day, 3) == date(2000, 1, 3)
+
+
+def test_timestamp_ms():
+    dt = datetime(1991, 4, 3, 0, 0)
+    result = timestamp_ms(dt)
+    expected = 670636800000
+    assert result == expected

castor_extractor/visualization/domo/client/client.py

@@ -1,10 +1,11 @@
 import logging
-from datetime import date, datetime, timedelta
+from datetime import datetime, timedelta
 from http import HTTPStatus
 from typing import Iterator, List, Optional, Set, Tuple
 
 import requests
 
+from ....utils import at_midnight, current_date, past_date, retry, timestamp_ms
 from ..assets import DomoAsset
 from .credentials import DomoCredentials
 from .endpoints import Endpoint, EndpointFactory
@@ -13,8 +14,7 @@ from .pagination import Pagination
 RawData = Iterator[dict]
 
 DOMO_PUBLIC_URL = "https://api.domo.com"
-FORMAT = "%Y-%m-%d %I:%M:%S %p"
-DEFAULT_TIMEOUT = 500
+DEFAULT_TIMEOUT = 120
 TOKEN_EXPIRATION_SECONDS = timedelta(seconds=3000)  # auth token lasts 1 hour
 
 IGNORED_ERROR_CODES = (
@@ -23,12 +23,14 @@ IGNORED_ERROR_CODES = (
 )
 ERROR_TPL = "Request failed with status code {status_code} and reason {reason}"
 
-logger = logging.getLogger(__name__)
-
+_RETRY_EXCEPTIONS = [
+    requests.exceptions.ConnectTimeout,
+    requests.exceptions.ReadTimeout,
+]
+_RETRY_COUNT = 2
+_RETRY_BASE_MS = 10 * 60 * 1000  # 10 minutes
 
-def _at_midnight(date_: date) -> datetime:
-    """convert date into datetime at midnight: 00:00:00"""
-    return datetime.combine(date_, datetime.min.time())
+logger = logging.getLogger(__name__)
 
 
 def _handle_response(response: requests.Response) -> requests.Response:
@@ -36,21 +38,6 @@ def _handle_response(response: requests.Response) -> requests.Response:
     return response
 
 
-def _is_expired(last_result: dict) -> bool:
-    """
-    Checks if the date given is expired
-    i.e. date < yesterday (00:00 AM)
-    """
-
-    last_timestamp = datetime.strptime(last_result["time"], FORMAT)
-    logger.info(f"Last audit input has timestamp: {last_timestamp}")
-    yesterday = date.today() - timedelta(days=1)
-    threshold = _at_midnight(yesterday)
-    if last_timestamp < threshold:
-        return True
-    return False
-
-
 def _ignore_or_raise(
     error: requests.RequestException,
     ignore_error_codes: Optional[Tuple[int, ...]],
@@ -82,6 +69,7 @@ class DomoClient:
     def __init__(self, credentials: DomoCredentials):
         self._authentication = credentials.authentication
         self._bearer_headers: Optional[dict] = None
+        self._session = requests.session()
         self._token_creation_time: datetime = datetime.min
         self._endpoint_factory = EndpointFactory(credentials.base_url)
         self._private_headers = credentials.private_headers
@@ -102,7 +90,7 @@ class DomoClient:
         basic_authentication = self._authentication
         endpoint = self._endpoint_factory.authentication
 
-        response = requests.get(
+        response = self._session.get(
             endpoint.url(),
             auth=basic_authentication,
             timeout=self._timeout,
@@ -115,6 +103,11 @@ class DomoClient:
 
         return self._bearer_headers
 
+    @retry(
+        exceptions=_RETRY_EXCEPTIONS,
+        max_retries=_RETRY_COUNT,
+        base_ms=_RETRY_BASE_MS,
+    )
     def _get(
         self,
         endpoint: Endpoint,
@@ -124,12 +117,14 @@ class DomoClient:
         params = params if params else {}
         is_private = endpoint.is_private
         headers = self._private_headers if is_private else self._bearer_auth()
-        response = requests.get(
+
+        response = self._session.get(
             url=endpoint.url(asset_id),
             headers=headers,
             params=params,
             timeout=self._timeout,
         )
+
         if response.status_code != HTTPStatus.OK:
             logger.warning(
                 ERROR_TPL.format(
@@ -165,28 +160,14 @@ class DomoClient:
         """Used when the response is paginated and need iterations"""
         pagination = Pagination()
         all_results: List[dict] = []
+
         while pagination.needs_increment:
-            results = self._get_many(
-                endpoint=endpoint,
-                params={
-                    "offset": pagination.offset,
-                    "limit": pagination.per_page,
-                },
-            )
+            params = {**pagination.params, **endpoint.params}
+            results = self._get_many(endpoint=endpoint, params=params)
             all_results.extend(results)
             number_of_items = len(results)
             pagination.increment_offset(number_of_items)
 
-            if endpoint == self._endpoint_factory.audit:
-                last_result = results[-1]
-                # We decided to fetch audits until the audit is prior to a particular date
-                # defined in _is_expired function. To be more precise, we could have instead use
-                # params start and end of the audit endpoint (timestamp in milliseconds).
-                # https://developer.domo.com/portal/a4e18ca6a0c0b-retrieve-activity-log-entries
-                # But we need then to manage properly the timezone conversion of the results
-                # which adds more complexity than benefits
-                if _is_expired(last_result):
-                    pagination.should_stop = True
         return all_results
 
     def _datasources(self, page_id: str) -> RawData:
@@ -300,7 +281,11 @@ class DomoClient:
             )
 
     def _audit(self) -> RawData:
-        yield from self._get_paginated(self._endpoint_factory.audit)
+        yesterday = timestamp_ms(at_midnight(past_date(1)))
+        today = timestamp_ms(at_midnight(current_date()))
+        yield from self._get_paginated(
+            self._endpoint_factory.audit(yesterday, today)
+        )
 
     def _dataflows(self) -> RawData:
         dataflows = self._get_many(self._endpoint_factory.dataflows)

castor_extractor/visualization/domo/client/client_test.py

@@ -1,33 +1,11 @@
-from datetime import date, datetime, timedelta
 from unittest.mock import patch
 
 import pytest
 import requests
 
-from .client import (
-    FORMAT,
-    DomoClient,
-    DomoCredentials,
-    _at_midnight,
-    _is_expired,
-)
+from .client import DomoClient, DomoCredentials
 from .endpoints import EndpointFactory
 
-NEVER_EXPIRING_DATE = datetime.max
-TODAY_DATE = _at_midnight(date.today())
-EXPIRED_DATE = _at_midnight(date.today() - timedelta(days=2))
-
-
-def test__is_expired():
-    test_datetimes = (
-        ({"time": NEVER_EXPIRING_DATE.strftime(FORMAT)}, False),
-        ({"time": TODAY_DATE.strftime(FORMAT)}, False),
-        ({"time": EXPIRED_DATE.strftime(FORMAT)}, True),
-    )
-
-    for test_datetime, is_expired in test_datetimes:
-        assert _is_expired(test_datetime) == is_expired
-
 
 class FakeResponse:
     """

castor_extractor/visualization/domo/client/endpoints.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from typing import Optional
 
 _DOMO_PUBLIC_URL = "https://api.domo.com"
@@ -13,6 +13,7 @@ class Endpoint:
 
     base_url: str
     is_private: bool = False
+    params: dict = field(default_factory=dict)
 
     def url(self, asset_id: Optional[str] = None):
         return f"{self.base_url}/{asset_id}" if asset_id else self.base_url
@@ -40,10 +41,6 @@ class EndpointFactory:
     def users(self) -> Endpoint:
         return Endpoint(f"{_DOMO_PUBLIC_URL}/v1/users")
 
-    @property
-    def audit(self) -> Endpoint:
-        return Endpoint(f"{_DOMO_PUBLIC_URL}/v1/audit")
-
     @property
     def dataflows(self) -> Endpoint:
         return Endpoint(
@@ -51,6 +48,16 @@ class EndpointFactory:
             is_private=True,
         )
 
+    def audit(self, start: int, end: int) -> Endpoint:
+        """
+        start and end are timestamps since epoch in milliseconds
+        See [documentation](https://developer.domo.com/portal/a4e18ca6a0c0b-retrieve-activity-log-entries)
+        """
+        return Endpoint(
+            base_url=f"{_DOMO_PUBLIC_URL}/v1/audit",
+            params={"start": start, "end": end},
+        )
+
     def lineage(self, dataflow_id: str) -> Endpoint:
         return Endpoint(
             base_url=f"{self.base_url}/api/data/v1/lineage/DATAFLOW/{dataflow_id}",
@@ -65,6 +72,6 @@ class EndpointFactory:
 
     def page_content(self, page_id: str) -> Endpoint:
         return Endpoint(
-            f"{self.base_url}/api/content/v3/stacks/{page_id}/cards?parts=datasources",
+            base_url=f"{self.base_url}/api/content/v3/stacks/{page_id}/cards?parts=datasources",
             is_private=True,
         )

castor_extractor/visualization/domo/client/pagination.py

@@ -23,6 +23,10 @@ class Pagination:
 
         return True
 
+    @property
+    def params(self) -> dict:
+        return {"offset": self.offset, "limit": self.per_page}
+
     def increment_offset(self, number_results: int) -> None:
         self.offset += number_results
         self.number_results = number_results

castor_extractor/visualization/looker/api/client.py

@@ -4,7 +4,22 @@ from datetime import date, timedelta
 from typing import Callable, Iterator, List, Optional, Sequence, Tuple
 
 from dateutil.utils import today
-from looker_sdk.sdk.api40.models import ContentView, UserAttribute
+from looker_sdk import init40
+from looker_sdk.sdk.api40.models import (
+    ContentView,
+    Dashboard,
+    DBConnection,
+    Folder,
+    GroupHierarchy,
+    GroupSearch,
+    Look,
+    LookmlModel,
+    LookmlModelExplore,
+    Project,
+    User,
+    UserAttribute,
+)
+from looker_sdk.sdk.constants import sdk_version
 
 from ....utils import Pager, PagerLogger, SafeMode, past_date, safe_mode
 from ..env import page_size
@@ -24,21 +39,7 @@ from .constants import (
     USER_FIELDS,
     USERS_ATTRIBUTES_FIELDS,
 )
-from .sdk import (
-    Credentials,
-    Dashboard,
-    DBConnection,
-    Folder,
-    GroupHierarchy,
-    GroupSearch,
-    Look,
-    LookmlModel,
-    LookmlModelExplore,
-    Project,
-    User,
-    has_admin_permissions,
-    init40,
-)
+from .sdk import CastorApiSettings, Credentials, has_admin_permissions
 
 logger = logging.getLogger(__name__)
 
@@ -81,7 +82,10 @@ class ApiClient:
         on_api_call: OnApiCall = lambda: None,
         safe_mode: Optional[SafeMode] = None,
     ):
-        sdk = init40(credentials)
+        settings = CastorApiSettings(
+            credentials=credentials, sdk_version=sdk_version
+        )
+        sdk = init40(config_settings=settings)
         if not has_admin_permissions(sdk):
             raise PermissionError("User does not have admin access.")
         else:

castor_extractor/visualization/looker/api/sdk.py

@@ -4,35 +4,9 @@ This file is a proxy to Looker SDK functions using Castor ApiSettings.
 
 from typing import Optional
 
-from looker_sdk.error import SDKError
-from looker_sdk.rtl import (
-    auth_session,
-    requests_transport,
-    serialize,
-    transport,
-)
-from looker_sdk.rtl.api_settings import PApiSettings, SettingsConfig
-from looker_sdk.sdk import constants
+from looker_sdk.rtl import transport
+from looker_sdk.rtl.api_settings import ApiSettings, SettingsConfig
 from looker_sdk.sdk.api40 import methods as methods40
-from looker_sdk.sdk.api40.models import (
-    Dashboard,
-    DashboardElement,
-    DBConnection,
-    Folder,
-    GroupHierarchy,
-    GroupSearch,
-    Look,
-    LookmlModel,
-    LookmlModelExplore,
-    LookmlModelExploreField,
-    LookmlModelExploreFieldset,
-    LookmlModelExploreJoins,
-    LookmlModelNavExplore,
-    Project,
-    Query,
-    User,
-)
-from typing_extensions import Protocol
 
 from ..env import timeout_second
 
@@ -76,46 +50,24 @@ def has_admin_permissions(sdk_: methods40.Looker40SDK) -> bool:
     )
 
 
-def init40(config: Credentials) -> methods40.Looker40SDK:
-    """Default dependency configuration"""
-    settings = ApiSettings(config=config, sdk_version=constants.sdk_version)
-    settings.is_configured()
-    transport = requests_transport.RequestsTransport.configure(settings)
-    return methods40.Looker40SDK(
-        auth=auth_session.AuthSession(
-            settings,
-            transport,
-            serialize.deserialize40,
-            "4.0",
-        ),
-        deserialize=serialize.deserialize40,
-        serialize=serialize.serialize40,
-        transport=transport,
-        api_version="4.0",
-    )
-
-
-class CastorApiSettings(PApiSettings):
-    """This is an intermediate class that is meant to be extended (for typing purpose)"""
-
-    def read_config(self) -> SettingsConfig:
-        raise NotImplementedError()
-
-
-class ApiSettings(CastorApiSettings):
+class CastorApiSettings(ApiSettings):
     """SDK settings with initialisation using a credential object instead of a path to a .ini file"""
 
-    def __init__(self, config: Credentials, sdk_version: Optional[str] = ""):
+    def __init__(
+        self, credentials: Credentials, sdk_version: Optional[str] = ""
+    ):
         """Configure using a config dict"""
-        self.config = config.to_settings_config()
+        self.config = credentials.to_settings_config()
         self.verify_ssl = True
         self.base_url = self.config.get("base_url", "")
-        self.timeout = config.timeout
+        self.timeout = credentials.timeout
         self.headers = {"Content-Type": "application/json"}
         self.agent_tag = f"{transport.AGENT_PREFIX}"
         if sdk_version:
             self.agent_tag += f" {sdk_version}"
 
+        super().__init__()
+
     def read_config(self) -> SettingsConfig:
         """Returns a serialization of the credentials"""
         return self.config

castor_extractor/visualization/looker/api/utils.py

@@ -1,6 +1,6 @@
 from typing import Iterable, Set, Tuple
 
-from .sdk import LookmlModel
+from looker_sdk.sdk.api40.models import LookmlModel
 
 
 def lookml_explore_names(

castor_extractor/visualization/looker/extract.py

@@ -1,6 +1,8 @@
 import logging
 from typing import Iterable, Optional, Set, Tuple, Union
 
+from looker_sdk.sdk.api40.models import LookmlModel
+
 from ...logger import add_logging_file_handler, set_stream_handler_to_stdout
 from ...utils import (
     SafeMode,
@@ -12,7 +14,6 @@ from ...utils import (
     write_summary,
 )
 from .api import ApiClient, Credentials, lookml_explore_names
-from .api.sdk import LookmlModel
 from .assets import LookerAsset
 from .multithreading import MultithreadingFetcher
 from .parameters import get_parameters

castor_extractor/visualization/looker/multithreading.py

@@ -4,11 +4,11 @@ from concurrent.futures import ThreadPoolExecutor
 from functools import partial
 from typing import Iterable, List, Set
 
+from looker_sdk.error import SDKError
 from tqdm import tqdm  # type: ignore
 
 from ...utils import RetryStrategy, deep_serialize, retry
 from . import ApiClient
-from .api.sdk import SDKError
 from .assets import LookerAsset
 
 logger = logging.getLogger(__name__)

castor_extractor/visualization/tableau_revamp/client/client.py

@@ -2,6 +2,7 @@ import logging
 from typing import Dict, Iterator, List, Optional
 
 import tableauserverclient as TSC  # type: ignore
+from tableauserverclient import Pager
 
 from ....utils import SerializedAsset
 from ..assets import TableauRevampAsset
@@ -12,7 +13,7 @@ from ..constants import (
 )
 from .credentials import TableauRevampCredentials
 from .errors import TableauApiError
-from .gql_queries import GQL_QUERIES, QUERY_TEMPLATE
+from .gql_queries import FIELDS_QUERIES, GQL_QUERIES, QUERY_TEMPLATE
 from .tsc_fields import TSC_FIELDS
 
 logger = logging.getLogger(__name__)
@@ -27,13 +28,15 @@ _TSC_ASSETS = (
     TableauRevampAsset.USAGE,
 )
 
+# speed up extraction: fields and columns are smaller but volumes are bigger
 _CUSTOM_PAGE_SIZE: Dict[TableauRevampAsset, int] = {
     TableauRevampAsset.FIELD: 1000,
+    TableauRevampAsset.COLUMN: 1000,
 }
 
 
 def _pick_fields(
-    data: SerializedAsset,
+    data: Pager,
     asset: TableauRevampAsset,
 ) -> SerializedAsset:
     fields = TSC_FIELDS[asset]
@@ -44,7 +47,7 @@ def _pick_fields(
     return [_pick(row) for row in data]
 
 
-def _enrich_with_tsc(
+def _enrich_datasources_with_tsc(
     datasources: SerializedAsset,
     tsc_datasources: SerializedAsset,
 ) -> SerializedAsset:
@@ -69,6 +72,32 @@ def _enrich_with_tsc(
     return datasources
 
 
+def _enrich_workbooks_with_tsc(
+    workbooks: SerializedAsset,
+    tsc_workbooks: SerializedAsset,
+) -> SerializedAsset:
+    """
+    Enrich workbooks with fields coming from TableauServerClient:
+    - project_luid
+    """
+
+    mapping = {row["id"]: row for row in tsc_workbooks}
+
+    for workbook in workbooks:
+        luid = workbook["luid"]
+        tsc_workbook = mapping.get(luid)
+        if not tsc_workbook:
+            # it happens that a workbook is in Metadata API but not in TSC
+            # in this case, we push the workbook with default project
+            logger.warning(f"Workbook {luid} was not found in TSC")
+            workbook["projectLuid"] = None
+            continue
+
+        workbook["projectLuid"] = tsc_workbook["project_id"]
+
+    return workbooks
+
+
 def gql_query_scroll(
     server,
     query: str,
@@ -176,29 +205,32 @@ class TableauRevampClient:
         asset: TableauRevampAsset,
     ) -> SerializedAsset:
 
-        if asset == TableauRevampAsset.USER:
-            data = TSC.Pager(self._server.users)
+        if asset == TableauRevampAsset.DATASOURCE:
+            data = TSC.Pager(self._server.datasources)
 
         elif asset == TableauRevampAsset.PROJECT:
             data = TSC.Pager(self._server.projects)
 
-        elif asset == TableauRevampAsset.DATASOURCE:
-            data = TSC.Pager(self._server.datasources)
-
         elif asset == TableauRevampAsset.USAGE:
             data = TSC.Pager(self._server.views, usage=True)
 
+        elif asset == TableauRevampAsset.USER:
+            data = TSC.Pager(self._server.users)
+
+        elif asset == TableauRevampAsset.WORKBOOK:
+            data = TSC.Pager(self._server.workbooks)
+
         else:
             raise AssertionError(f"Fetching from TSC not supported for {asset}")
 
         return _pick_fields(data, asset)
 
-    def _fetch_from_metadata_api(
+    def _run_graphql_query(
         self,
-        asset: TableauRevampAsset,
+        resource: str,
+        fields: str,
+        page_size: int = DEFAULT_PAGE_SIZE,
     ) -> SerializedAsset:
-        resource, fields = GQL_QUERIES[asset]
-        page_size = _CUSTOM_PAGE_SIZE.get(asset) or DEFAULT_PAGE_SIZE
         query = QUERY_TEMPLATE.format(
             resource=resource,
             fields=fields,
@@ -207,13 +239,40 @@ class TableauRevampClient:
         result_pages = gql_query_scroll(self._server, query, resource)
         return [asset for page in result_pages for asset in page]
 
+    def _fetch_fields(self) -> SerializedAsset:
+        result: SerializedAsset = []
+        page_size = _CUSTOM_PAGE_SIZE[TableauRevampAsset.FIELD]
+        for resource, fields in FIELDS_QUERIES:
+            current = self._run_graphql_query(resource, fields, page_size)
+            result.extend(current)
+        return result
+
+    def _fetch_from_metadata_api(
+        self,
+        asset: TableauRevampAsset,
+    ) -> SerializedAsset:
+        if asset == TableauRevampAsset.FIELD:
+            return self._fetch_fields()
+
+        page_size = _CUSTOM_PAGE_SIZE.get(asset) or DEFAULT_PAGE_SIZE
+        resource, fields = GQL_QUERIES[asset]
+        return self._run_graphql_query(resource, fields, page_size)
+
     def _fetch_datasources(self) -> SerializedAsset:
         asset = TableauRevampAsset.DATASOURCE
 
         datasources = self._fetch_from_metadata_api(asset)
         datasource_projects = self._fetch_from_tsc(asset)
 
-        return _enrich_with_tsc(datasources, datasource_projects)
+        return _enrich_datasources_with_tsc(datasources, datasource_projects)
+
+    def _fetch_workbooks(self) -> SerializedAsset:
+        asset = TableauRevampAsset.WORKBOOK
+
+        workbooks = self._fetch_from_metadata_api(asset)
+        workbook_projects = self._fetch_from_tsc(asset)
+
+        return _enrich_workbooks_with_tsc(workbooks, workbook_projects)
 
     def fetch(
         self,
@@ -226,6 +285,10 @@ class TableauRevampClient:
             # both APIs are required to extract datasources
             return self._fetch_datasources()
 
+        if asset == TableauRevampAsset.WORKBOOK:
+            # both APIs are required to extract workbooks
+            return self._fetch_workbooks()
+
         if asset in _TSC_ASSETS:
             # some assets can only be extracted via TSC
             return self._fetch_from_tsc(asset)

castor_extractor/visualization/tableau_revamp/client/gql_queries.py

@@ -37,12 +37,10 @@ workbook { id }
 
 _DATASOURCES_QUERY = """
 __typename
-createdAt
 downstreamDashboards { id }
 downstreamWorkbooks { id }
 id
 name
-updatedAt
 ... on PublishedDatasource {
     description
     luid
@@ -64,7 +62,6 @@ name
     connectionType
     fullName
     schema
-    tableType
 }
 ... on CustomSQLTable {
     query
@@ -80,7 +77,6 @@ id
 luid
 name
 owner { luid }
-projectLuid
 site { name }
 tags { name }
 updatedAt
@@ -96,16 +92,17 @@ downstreamWorkbooks { id }
 folderName
 id
 name
-... on DataField {
-    dataType
-    role
-}
-... on ColumnField {
-    columns {
-        name
-        table { name }
-    }
-}
+dataType
+role
+"""
+
+
+_FIELDS_QUERY_WITH_COLUMNS = f"""
+{_FIELDS_QUERY}
+columns {{
+    name
+   table {{ name }}
+}}
 """
 
 _SHEETS_QUERY = """
@@ -124,8 +121,14 @@ GQL_QUERIES: Dict[TableauRevampAsset, Tuple[str, str]] = {
     TableauRevampAsset.COLUMN: ("columns", _COLUMNS_QUERY),
     TableauRevampAsset.DASHBOARD: ("dashboards", _DASHBOARDS_QUERY),
     TableauRevampAsset.DATASOURCE: ("datasources", _DATASOURCES_QUERY),
-    TableauRevampAsset.FIELD: ("fields", _FIELDS_QUERY),
     TableauRevampAsset.SHEET: ("sheets", _SHEETS_QUERY),
     TableauRevampAsset.TABLE: ("tables", _TABLES_QUERY),
     TableauRevampAsset.WORKBOOK: ("workbooks", _WORKBOOKS_QUERY),
 }
+
+FIELDS_QUERIES = (
+    ("binFields", _FIELDS_QUERY),
+    ("calculatedFields", _FIELDS_QUERY),
+    ("columnFields", _FIELDS_QUERY_WITH_COLUMNS),
+    ("groupFields", _FIELDS_QUERY),
+)

castor_extractor/visualization/tableau_revamp/client/tsc_fields.py

@@ -27,4 +27,8 @@ TSC_FIELDS: Dict[TableauRevampAsset, Set[str]] = {
         "name",
         "site_role",
     },
+    TableauRevampAsset.WORKBOOK: {
+        "id",
+        "project_id",
+    },
 }

castor_extractor/warehouse/databricks/client.py

@@ -3,7 +3,7 @@ from datetime import date
 from functools import partial
 from typing import Any, Dict, List, Optional, Set
 
-from ...utils import at_midnight, date_after
+from ...utils import at_midnight, date_after, mapping_from_rows
 from ...utils.client.api import APIClient
 from ...utils.pager import PagerOnToken
 from ..abstract.time_filter import TimeFilter
@@ -88,15 +88,22 @@ class DatabricksClient(APIClient):
         )
 
     @staticmethod
-    def _match_table_with_user(table: dict, user_id_by_email: dict) -> dict:
+    def _match_table_with_user(table: dict, user_mapping: dict) -> dict:
         table_owner_email = table.get("owner_email")
         if not table_owner_email:
             return table
-        owner_external_id = user_id_by_email.get(table_owner_email)
+        owner_external_id = user_mapping.get(table_owner_email)
         if not owner_external_id:
             return table
         return {**table, "owner_external_id": owner_external_id}
 
+    @staticmethod
+    def _get_user_mapping(users: List[dict]) -> dict:
+        return {
+            **mapping_from_rows(users, "email", "id"),
+            **mapping_from_rows(users, "user_name", "id"),
+        }
+
     def tables_and_columns(
         self, schemas: List[dict], users: List[dict]
     ) -> TablesColumns:
@@ -105,11 +112,11 @@ class DatabricksClient(APIClient):
         """
         tables: List[dict] = []
         columns: List[dict] = []
-        user_id_by_email = {user.get("email"): user.get("id") for user in users}
+        user_mapping = self._get_user_mapping(users)
         for schema in schemas:
             t_to_add, c_to_add = self._tables_columns_of_schema(schema)
             t_with_owner = [
-                self._match_table_with_user(table, user_id_by_email)
+                self._match_table_with_user(table, user_mapping)
                 for table in t_to_add
             ]
             tables.extend(t_with_owner)

castor_extractor/warehouse/databricks/client_test.py

@@ -66,15 +66,34 @@ def test_DatabricksClient__keep_catalog():
     assert not client._keep_catalog("something_unknown")
 
 
+def test_DatabricksClient__get_user_mapping():
+    client = MockDatabricksClient()
+    users = [
+        {"id": "both", "email": "hello@world.com", "user_name": "hello world"},
+        {"id": "no_email", "email": "", "user_name": "no email"},
+        {"id": "no_name", "email": "no@name.fr", "user_name": ""},
+        {"id": "no_both", "email": "", "user_name": ""},
+        {"id": "", "email": "no@id.com", "user_name": "no id"},
+    ]
+    expected = {
+        "hello@world.com": "both",
+        "hello world": "both",
+        "no@name.fr": "no_name",
+        "no email": "no_email",
+    }
+    mapping = client._get_user_mapping(users)
+    assert mapping == expected
+
+
 def test_DatabricksClient__match_table_with_user():
     client = MockDatabricksClient()
-    users_by_email = {"bob@castordoc.com": 3}
+    user_mapping = {"bob@castordoc.com": 3}
 
     table = {"id": 1, "owner_email": "bob@castordoc.com"}
-    table_with_owner = client._match_table_with_user(table, users_by_email)
+    table_with_owner = client._match_table_with_user(table, user_mapping)
 
     assert table_with_owner == {**table, "owner_external_id": 3}
 
     table_without_owner = {"id": 1, "owner_email": None}
-    actual = client._match_table_with_user(table_without_owner, users_by_email)
+    actual = client._match_table_with_user(table_without_owner, user_mapping)
     assert actual == table_without_owner

castor_extractor/warehouse/databricks/format.py

@@ -127,13 +127,17 @@ class DatabricksFormatter:
                 return email["value"]
         return emails[0]["value"]
 
+    def _email(self, user: dict) -> Optional[str]:
+        emails = user.get("emails")
+        return self._primary(emails) if emails else None
+
     def format_user(self, raw_users: List[dict]) -> List[dict]:
         users = []
         for user in raw_users:
             users.append(
                 {
                     "id": user["id"],
-                    "email": self._primary(user["emails"]),
+                    "email": self._email(user),
                     "first_name": None,
                     "last_name": user.get("displayName") or user["userName"],
                     "user_name": user["userName"],

{castor_extractor-0.16.6.dist-info → castor_extractor-0.16.9.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.16.6
+Version: 0.16.9
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
 Author: Castor
 Author-email: support@castordoc.com
-Requires-Python: >=3.8,<3.12
+Requires-Python: >=3.8,<3.13
 Classifier: License :: Other/Proprietary License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
@@ -14,6 +14,7 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Provides-Extra: all
 Provides-Extra: bigquery
 Provides-Extra: dbt
@@ -34,8 +35,10 @@ Requires-Dist: google-cloud-core (>=2.1.0,<3.0.0)
 Requires-Dist: google-cloud-storage (>=2,<3)
 Requires-Dist: google-resumable-media (>=2.0.3,<3.0.0)
 Requires-Dist: googleapis-common-protos (>=1.53.0,<2.0.0)
-Requires-Dist: looker-sdk (>=22.4.0,<=23.0.0) ; extra == "looker" or extra == "all"
+Requires-Dist: looker-sdk (>=23.0.0) ; extra == "looker" or extra == "all"
 Requires-Dist: msal (>=1.20.0,<2.0.0) ; extra == "powerbi" or extra == "all"
+Requires-Dist: numpy (<1.25) ; python_version >= "3.8" and python_version < "3.9"
+Requires-Dist: numpy (>=1.26,<2) ; python_version >= "3.12" and python_version < "3.13"
 Requires-Dist: psycopg2-binary (>=2.0.0,<3.0.0) ; extra == "metabase" or extra == "postgres" or extra == "redshift" or extra == "all"
 Requires-Dist: pycryptodome (>=3.0.0,<4.0.0) ; extra == "metabase" or extra == "all"
 Requires-Dist: pydantic (>=2.6,<3.0)

{castor_extractor-0.16.6.dist-info → castor_extractor-0.16.9.dist-info}/RECORD

@@ -1,4 +1,4 @@
-CHANGELOG.md,sha256=5zI5Mielu8ZXyckh7x2A_iXPW3qXjEhH_8THWOZVY0c,10191
+CHANGELOG.md,sha256=WwEWPQQuGqVnWLhPtEh3SuOlBrNgHyHcLsYuvahpN7E,10437
 Dockerfile,sha256=HcX5z8OpeSvkScQsN-Y7CNMUig_UB6vTMDl7uqzuLGE,303
 LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
 README.md,sha256=uF6PXm9ocPITlKVSh9afTakHmpLx3TvawLf-CbMP3wM,3578
@@ -44,7 +44,7 @@ castor_extractor/uploader/env_test.py,sha256=ClCWWtwd2N-5ClIDUxVMeKkWfhhOTxpppsX
 castor_extractor/uploader/upload.py,sha256=5Aj3UOx8cpSVvzjYRz7S6nLk249IqUiCia70utU_970,3363
 castor_extractor/uploader/upload_test.py,sha256=BfGjAYEEDBmEcUS6_b3SlKyiQNR1iRf6-qmADDirTJI,328
 castor_extractor/uploader/utils.py,sha256=NCe0tkB28BVhqzOaDhDjaSfODjjcPWB17X6chnvyCWs,478
-castor_extractor/utils/__init__.py,sha256=cZbvEJ4G2IcJR2BzHwi3oOwDLqJsBx0J9gD71lWE1BQ,1149
+castor_extractor/utils/__init__.py,sha256=bmzAOc-PKsVreMJtF7DGpPQeHrVqxWel_BblRftt6Ag,1186
 castor_extractor/utils/client/__init__.py,sha256=CRE-xJKm6fVV9dB8ljzB5YoOxX4I1sCD1KSgqs3Y8_Y,161
 castor_extractor/utils/client/abstract.py,sha256=aA5Qcb9TwWDSMq8WpXbGkOB20hehwX2VTpqQAwV76wk,2048
 castor_extractor/utils/client/api.py,sha256=tHa7eC11sS_eOCXhlnvUa2haRfOLENmjKgjB09Ijt0s,1664
@@ -53,7 +53,8 @@ castor_extractor/utils/client/postgres.py,sha256=n6ulaT222WWPY0_6qAZ0MHF0m91HtI9
 castor_extractor/utils/client/query.py,sha256=O6D5EjD1KmBlwa786Uw4D4kzxx97_HH50xIIeSWt0B8,205
 castor_extractor/utils/client/uri.py,sha256=jmP9hY-6PRqdc3-vAOdtll_U6q9VCqSqmBAN6QRs3ZI,150
 castor_extractor/utils/client/uri_test.py,sha256=1XKF6qSseCeD4G4ckaNO07JXfGbt7XUVinOZdpEYrDQ,259
-castor_extractor/utils/collection.py,sha256=uenJvfamphxV5ZFt12BgfsRs99pWffYJIMjAD_Laz2Q,417
+castor_extractor/utils/collection.py,sha256=L4KLCjpgYBEwC7lSPFWBkiUzeLOTv5e-X6c-nibdnmQ,1555
+castor_extractor/utils/collection_test.py,sha256=I9xLnBUPiAGj7UDqEd0G6pcgqjcNHJ5DYXbmTXVhBM8,1713
 castor_extractor/utils/constants.py,sha256=qBQprS9U66mS-RIBXiLujdTSV3WvGv40Bc0khP4Abdk,39
 castor_extractor/utils/dbt/__init__.py,sha256=LHQROlMqYWCc7tcmhdjXtROFpJqUvCg9jPC8avHgD4I,107
 castor_extractor/utils/dbt/assets.py,sha256=JY1nKEGySZ84wNoe7dnizwAYw2q0t8NVaIfqhB2rSw0,148
@@ -92,8 +93,8 @@ castor_extractor/utils/salesforce/credentials_test.py,sha256=FQRyNk2Jsh6KtYiW20o
 castor_extractor/utils/store.py,sha256=D_pVaPsu1MKAJC0K47O_vYTs-Afl6oejravAJdvjmGc,2040
 castor_extractor/utils/string.py,sha256=aW6bbjqEGnh9kT5KZBnMlV6fhdgOJ0ENCkCTDon1xA0,2377
 castor_extractor/utils/string_test.py,sha256=OmRVCJUXMcCTwY-QJDhUViYpxkvQQgNRJLCaXY0iUnk,2535
-castor_extractor/utils/time.py,sha256=a9AChz_rlmPwLxQvoC0tF_fNUJvBVCTLQSdJLtN107w,1210
-castor_extractor/utils/time_test.py,sha256=W51zOsYNu_BNzsl3EWeT0Pgn2lUbT_weT8bM5rTrIQk,283
+castor_extractor/utils/time.py,sha256=Rll1KJVDZdCKjWuiXA_BuB9OHeEfb_f6Z637Kkxnobs,1385
+castor_extractor/utils/time_test.py,sha256=pEwpcHI7wGPnfgwrH1DNHEbPz3HEAryNF5yPL7Dqkp8,448
 castor_extractor/utils/type.py,sha256=87t32cTctEjX-_BqZLtPLWu-M9OVvw_lFU4DbaQ6V0U,313
 castor_extractor/utils/validation.py,sha256=NNMkdyvMzConslnyCM3gmciEtPPvefW0vAT2gNsMhvE,1909
 castor_extractor/utils/validation_test.py,sha256=aSetitOCkH_K-Wto9ISOVGso5jGfTUOBLm3AZnvavO8,1181
@@ -102,29 +103,29 @@ castor_extractor/visualization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5
 castor_extractor/visualization/domo/__init__.py,sha256=_mAYVfoVLizfLGF_f6ZiwBhdPpvoJY_diySf33dt3Jo,127
 castor_extractor/visualization/domo/assets.py,sha256=bK1urFR2tnlWkVkkhR32mAKMoKbESNlop-CNGx-65PY,206
 castor_extractor/visualization/domo/client/__init__.py,sha256=UDszV3IXNC9Wp_j55NZ-6ey2INo0TYtAg2QNIJOjglE,88
-castor_extractor/visualization/domo/client/client.py,sha256=ZJJh0ZWuh1X4_uW6FEcZUUAxgRRVFh9vWUtS5aJly4Q,11075
-castor_extractor/visualization/domo/client/client_test.py,sha256=qGGmpJHnm-o2Ybko5J31nSM9xev5YS0yXjVNM9E92b4,2378
+castor_extractor/visualization/domo/client/client.py,sha256=8bQgK6TFJcEvSH19ZzVNlsyz86jgIypOAheOCXLORVU,10203
+castor_extractor/visualization/domo/client/client_test.py,sha256=pEIL8AALixq9a7sckW-TVqaz1k4oKUtfGUjGpTPOJi0,1790
 castor_extractor/visualization/domo/client/credentials.py,sha256=CksQ9W9X6IGjTlYN0okwGAmURMRJKAjctxODAvAJUAo,1148
-castor_extractor/visualization/domo/client/endpoints.py,sha256=_D_gq99d77am4KHeRCkITM_XyYuAOscHagC7t3adscY,2019
-castor_extractor/visualization/domo/client/pagination.py,sha256=E3WMK9Uw-u5qt9LCUzwKdKh9oSzyFEC0GgnRMFgxgrs,713
+castor_extractor/visualization/domo/client/endpoints.py,sha256=6UI5psMYaIa1Pq_Gulb4cNna7NZ16xMotScX7yg5TRQ,2367
+castor_extractor/visualization/domo/client/pagination.py,sha256=ukVkHVzoH4mfZ29H9YcnC2YrdVolP10wv25J6Q3ehRw,821
 castor_extractor/visualization/domo/client/pagination_test.py,sha256=nV4yZWfus13QFCr-tlBUgwva21VqfpF6P-0ks_Awwis,581
 castor_extractor/visualization/domo/constants.py,sha256=AriJZPrCY5Z3HRUANrMu-4U0b7hQK_jRDcxiB-hbrQ4,233
 castor_extractor/visualization/domo/extract.py,sha256=GWWRfPEMt4SgzBGFaTcoOabsoOqLRFIEFAtgXwb8LDI,2567
 castor_extractor/visualization/looker/__init__.py,sha256=Xu5bJ3743kaP8szMMp2NXCgvM1EdOQgtic4utUlO9Cc,145
 castor_extractor/visualization/looker/api/__init__.py,sha256=rN03VMucxIqc0yfd17dIe3ZNFpcg5CA09epn1fKJg90,99
-castor_extractor/visualization/looker/api/client.py,sha256=R-hnVK1TYaCPYaJ1wvpVUwa_AqQPu2RAcZz0kOK4l58,9582
+castor_extractor/visualization/looker/api/client.py,sha256=tfV-zx5FAtPCtu_NFIxfSFiQ1AtxxIeAj1sHT5Vug3I,9790
 castor_extractor/visualization/looker/api/client_test.py,sha256=wsi20-neBXHaahDqf4nwCp8Ew5fRFCmVHG3OqrePKFs,1868
 castor_extractor/visualization/looker/api/constants.py,sha256=pZpq09tqcGi2Vh8orXxn9eil8ewfPUOLKfVuqgV2W-A,4126
-castor_extractor/visualization/looker/api/sdk.py,sha256=hSNcRsCoFae3zmjWFGsMrhQCIP57TcMJ2SorMPYJwn4,3553
+castor_extractor/visualization/looker/api/sdk.py,sha256=RiCb-3BAL59iGqLfPEO9490cM05LRv-xGoo-AM-Z4No,2251
 castor_extractor/visualization/looker/api/sdk_test.py,sha256=NHtKZTflPhqzBFHs1TyAQaubgxfzLLwYKFT8rEqR55I,1742
-castor_extractor/visualization/looker/api/utils.py,sha256=NpP90CA-SwdUjHhaWFBsKpJz0Z9BXgDOahIqfc3R9tk,565
+castor_extractor/visualization/looker/api/utils.py,sha256=TJqq9UBVFtS33VB1zHzT6kU8f9MOyqXsUcr57ZurJy4,588
 castor_extractor/visualization/looker/assets.py,sha256=K08nV6MMIpfF9r91TmCO7_62smHzGRv3gR4aIOootMQ,827
 castor_extractor/visualization/looker/constant.py,sha256=JvmAfbyAg-LQIoI48Slg9k5T0mYggs_76D_6vD-mP88,695
 castor_extractor/visualization/looker/env.py,sha256=vPqirdeGKm3as2T-tBTjbpulQe8W7-3UE2j-Z57wFXk,1174
-castor_extractor/visualization/looker/extract.py,sha256=vOIP8Hoxv05MiRa-l79YKOCHahuNiSW9uSKjwQQQQKs,5112
+castor_extractor/visualization/looker/extract.py,sha256=Y7ZsiUO3uaAkBX0inhjMcEXX4nyBTo9ewthtLfbQhzU,5132
 castor_extractor/visualization/looker/fields.py,sha256=WmiSehmczWTufCLg4r2Ozq2grUpzxDNvIAHyGuOoGs4,636
 castor_extractor/visualization/looker/fields_test.py,sha256=7Cwq8Qky6aTZg8nCHp1gmPJtd9pGNB4QeMIRRWdHo5w,782
-castor_extractor/visualization/looker/multithreading.py,sha256=WtsJlwSarE27qSLO6nc2Tudv15lZqXV5B4NmO0nqxFE,2602
+castor_extractor/visualization/looker/multithreading.py,sha256=6CrMOy9kMBfhHnZI7XrpNNyBiYYCO3CE4AuIjQVlLH0,2610
 castor_extractor/visualization/looker/parameters.py,sha256=Nk2hfrg3L9twU-51Q7Wdp9uaxy8M2_juEebWoLfIMPc,2427
 castor_extractor/visualization/metabase/__init__.py,sha256=hSIoVgPzhQh-9H8XRUzga4EZSOYejGdH-qY_hBNGbyw,125
 castor_extractor/visualization/metabase/assets.py,sha256=47fMax7QjFKyjEuH2twsjd-l9EM4RJutAZb4GbASdkU,2836
@@ -243,11 +244,11 @@ castor_extractor/visualization/tableau/usage.py,sha256=LlFwlbEr-EnYUJjKZha99CRCR
 castor_extractor/visualization/tableau_revamp/__init__.py,sha256=a3DGjQhaz17gBqW-E84TAgupKbqLC40y5Ajo1yn-ot4,156
 castor_extractor/visualization/tableau_revamp/assets.py,sha256=owlwaI2E4UKk1YhkaHgaAXx6gu3Op6EqZ7bjp0tHI6s,351
 castor_extractor/visualization/tableau_revamp/client/__init__.py,sha256=wmS9uLtUiqNYVloi0-DgD8d2qzu3RVZEAtWiaDp6G_M,90
-castor_extractor/visualization/tableau_revamp/client/client.py,sha256=PsU7OOAYeTBF4dcT-Tl7RwJGD8o_S6vmGhUk_lYNhDw,7288
+castor_extractor/visualization/tableau_revamp/client/client.py,sha256=8BO7J-HFM2j6_f-Hjj3uSWip11eKeZ0cjhxGEqMTPRA,9428
 castor_extractor/visualization/tableau_revamp/client/credentials.py,sha256=fHG32egq6ll2U4BNazalMof_plzfCMQjrN9WOs6kezk,3014
 castor_extractor/visualization/tableau_revamp/client/errors.py,sha256=dTe1shqmWmAXpDpCz-E24m8dGYjt6rvIGV9qQb4jnvI,150
-castor_extractor/visualization/tableau_revamp/client/gql_queries.py,sha256=SiKTbl-lblV6GCajikPXrDh4BaTmi0wN_HtGQhVDV3o,2041
-castor_extractor/visualization/tableau_revamp/client/tsc_fields.py,sha256=Nl_CM2OEzgh3eL8Szcv9Fbiu9wGRkcaYlerUYTJrZLQ,610
+castor_extractor/visualization/tableau_revamp/client/gql_queries.py,sha256=jBxvjQnOIWfFjMJpr7S_ZPnQhdzabxoO3jyEKi8A8ns,2112
+castor_extractor/visualization/tableau_revamp/client/tsc_fields.py,sha256=WsDliPCo-XsQ7wN-j0gpW9bdxCHvgH-aePywiltzfbU,688
 castor_extractor/visualization/tableau_revamp/constants.py,sha256=PcdudAogQhi3e-knalhgliMKjy5ahN0em_-7XSLrnxM,87
 castor_extractor/visualization/tableau_revamp/extract.py,sha256=2SLUxp5okM4AcEJJ61ZgcC2ikfZZl9MH17CEXMXmgl0,1450
 castor_extractor/warehouse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -276,11 +277,11 @@ castor_extractor/warehouse/bigquery/queries/view_ddl.sql,sha256=obCm-IN9V8_YSZTw
 castor_extractor/warehouse/bigquery/query.py,sha256=hrFfjd5jW2oQnZ6ozlkn-gDe6sCIzu5zSX19T9W6fIk,4162
 castor_extractor/warehouse/bigquery/types.py,sha256=LZVWSmE57lOemNbB5hBRyYmDk9bFAU4nbRaJWALl6N8,140
 castor_extractor/warehouse/databricks/__init__.py,sha256=bTvDxjGQGM2J3hOnVhfNmFP1y8DK0tySiD_EXe5_xWE,200
-castor_extractor/warehouse/databricks/client.py,sha256=FIqHjlGN5EN2dvcZD2941zPAomOye91JmkgPlxGDk0g,8078
-castor_extractor/warehouse/databricks/client_test.py,sha256=ctOQnUXosuuFjWGJKgkxjUcV4vQUBWt2BQ_f0Tyzqe4,2717
+castor_extractor/warehouse/databricks/client.py,sha256=FsHlpHZ9JTG92Rf_8Z7277o9HBaAD0CKxSEHiujOgXg,8271
+castor_extractor/warehouse/databricks/client_test.py,sha256=Y-LBveZFRVaaL49Lo2MwbcJReBcYLNRdHtR_w7xWNWQ,3381
 castor_extractor/warehouse/databricks/credentials.py,sha256=PpGv5_GP320UQjV_gvaxSpOw58AmqSznmjGhGfe6bdU,655
 castor_extractor/warehouse/databricks/extract.py,sha256=-vJhAIxSu1lD_xGl-GXZYTmc5BGu0aXM3l-U0UghREM,5773
-castor_extractor/warehouse/databricks/format.py,sha256=LiPGCTPzL3gQQMMl1v6DvpcTk7BWxZFq03jnHdoYnuU,4968
+castor_extractor/warehouse/databricks/format.py,sha256=Nd5L89yWhpIl0OEMV7WK1H3JYUa9WGPC0c-NUOT_uXM,5101
 castor_extractor/warehouse/databricks/format_test.py,sha256=iPmdJof43fBYL1Sa_fBrCWDQHCHgm7IWCZag1kWkj9E,1970
 castor_extractor/warehouse/databricks/types.py,sha256=T2SyLy9pY_olLtstdC77moPxIiikVsuQLMxh92YMJQo,78
 castor_extractor/warehouse/mysql/__init__.py,sha256=2KFDogo9GNbApHqw3Vm5t_uNmIRjdp76nmP_WQQMfQY,116
@@ -367,8 +368,8 @@ castor_extractor/warehouse/synapse/queries/schema.sql,sha256=aX9xNrBD_ydwl-znGSF
 castor_extractor/warehouse/synapse/queries/table.sql,sha256=mCE8bR1Vb7j7SwZW2gafcXidQ2fo1HwxcybA8wP2Kfs,1049
 castor_extractor/warehouse/synapse/queries/user.sql,sha256=sTb_SS7Zj3AXW1SggKPLNMCd0qoTpL7XI_BJRMaEpBg,67
 castor_extractor/warehouse/synapse/queries/view_ddl.sql,sha256=3EVbp5_yTgdByHFIPLHmnoOnqqLE77SrjAwFDvu4e54,249
-castor_extractor-0.16.6.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
-castor_extractor-0.16.6.dist-info/METADATA,sha256=yDrJkKrR_JGhxTHdorJu_IcuH_d3qd7VLoLwQPEdclo,6370
-castor_extractor-0.16.6.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-castor_extractor-0.16.6.dist-info/entry_points.txt,sha256=SbyPk58Gh-FRztfCNnUZQ6w7SatzNJFZ6GIJLNsy7tI,1427
-castor_extractor-0.16.6.dist-info/RECORD,,
+castor_extractor-0.16.9.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
+castor_extractor-0.16.9.dist-info/METADATA,sha256=qRP78w8BztI4N8IyOLoESkFdhKWByXf7PQQjFLTvu6A,6582
+castor_extractor-0.16.9.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+castor_extractor-0.16.9.dist-info/entry_points.txt,sha256=SbyPk58Gh-FRztfCNnUZQ6w7SatzNJFZ6GIJLNsy7tI,1427
+castor_extractor-0.16.9.dist-info/RECORD,,