castor-extractor 0.24.1__tar.gz → 0.24.4__tar.gz

{castor_extractor-0.24.1 → castor_extractor-0.24.4}/CHANGELOG.md

@@ -1,5 +1,21 @@
 # Changelog
 
+## 0.24.4 - 2025-03-19
+
+* Snowflake:
+  * improve the list of ignored queries in the query history extraction
+    * ignore the following query types : CALL, COMMENT, EXPLAIN, REFRESH_DYNAMIC_TABLE_AT_REFRESH_VERSION, REVOKE, TRUNCATE_TABLE, UNDROP
+    * ignore queries with empty text
+  * filter out schemas with empty names
+
+## 0.24.3 - 2025-03-18
+
+* Replace ThoughtSpot endpoint `/api/rest/2.0/report/liveboard` with `/api/rest/2.0/metadata/liveboard/data` following the deprecation of the CSV option
+
+## 0.24.2 - 2025-03-17
+
+* Rename Revamped Tableau Connector classes
+
 ## 0.24.1 - 2025-03-14
 
 * Added support for Looker Studio

{castor_extractor-0.24.1 → castor_extractor-0.24.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: castor-extractor
-Version: 0.24.1
+Version: 0.24.4
 Summary: Extract your metadata assets.
 Home-page: https://www.castordoc.com/
 License: EULA
@@ -210,6 +210,22 @@ For any questions or bug report, contact us at [support@castordoc.com](mailto:su
 
 # Changelog
 
+## 0.24.4 - 2025-03-19
+
+* Snowflake:
+  * improve the list of ignored queries in the query history extraction
+    * ignore the following query types : CALL, COMMENT, EXPLAIN, REFRESH_DYNAMIC_TABLE_AT_REFRESH_VERSION, REVOKE, TRUNCATE_TABLE, UNDROP
+    * ignore queries with empty text
+  * filter out schemas with empty names
+
+## 0.24.3 - 2025-03-18
+
+* Replace ThoughtSpot endpoint `/api/rest/2.0/report/liveboard` with `/api/rest/2.0/metadata/liveboard/data` following the deprecation of the CSV option
+
+## 0.24.2 - 2025-03-17
+
+* Rename Revamped Tableau Connector classes
+
 ## 0.24.1 - 2025-03-14
 
 * Added support for Looker Studio

{castor_extractor-0.24.1 → castor_extractor-0.24.4}/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-0.24.4/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.4/castor_extractor/visualization/tableau/client/__init__.py

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

{castor_extractor-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1/castor_extractor/visualization/tableau_revamp → castor_extractor-0.24.4/castor_extractor/visualization/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-0.24.1 → castor_extractor-0.24.4}/castor_extractor/visualization/thoughtspot/client/client.py

@@ -1,13 +1,17 @@
+import logging
 from collections.abc import Iterator
-from typing import Optional
+from functools import partial
+from typing import Iterable, Optional
 
 import requests
+from requests import Response
 
 from ....utils import (
     APIClient,
     BearerAuth,
     RequestSafeMode,
     build_url,
+    fetch_all_pages,
     handle_response,
 )
 from ..assets import (
@@ -19,9 +23,7 @@ from .credentials import (
 from .endpoints import (
     ThoughtspotEndpointFactory,
 )
-from .utils import (
-    usage_liveboard_reader,
-)
+from .pagination import METADATA_BATCH_SIZE, ThoughtSpotPagination
 
 _AUTH_TIMEOUT_S = 60
 _THOUGHTSPOT_HEADERS = {
@@ -29,7 +31,6 @@ _THOUGHTSPOT_HEADERS = {
     "Accept": "application/json",
     "Content-Type": "application/json",
 }
-_METADATA_BATCH_SIZE = 100
 # https://docs.thoughtspot.com/cloud/latest/object-usage-liveboard
 _OBJECT_USAGE_LIVEBOARD = "Object Usage"
 _ANSWER_USAGE_VIZ = "Answer Usage, by User"
@@ -40,6 +41,9 @@ _LIVEBOARD_USAGE_VIZ = "Popular Liveboards Last 30 Days"
 THOUGHTSPOT_SAFE_MODE = RequestSafeMode()
 
 
+logger = logging.getLogger(__name__)
+
+
 class ThoughtspotBearerAuth(BearerAuth):
     def __init__(self, host: str, token_payload: dict[str, str]):
         auth_endpoint = ThoughtspotEndpointFactory.authentication()
@@ -86,7 +90,7 @@ class ThoughtspotClient(APIClient):
             search_filters = {
                 "metadata": [{"type": metadata_type}],
                 "include_details": True,
-                "record_size": _METADATA_BATCH_SIZE,
+                "record_size": METADATA_BATCH_SIZE,
                 "record_offset": offset,
             }
             if identifier:
@@ -100,9 +104,9 @@ class ThoughtspotClient(APIClient):
                 data=search_filters,
             )
             yield from metadata
-            if len(metadata) < _METADATA_BATCH_SIZE:
+            if len(metadata) < METADATA_BATCH_SIZE:
                 break
-            offset = offset + _METADATA_BATCH_SIZE
+            offset = offset + METADATA_BATCH_SIZE
 
     def _get_all_answers(self) -> Iterator[dict]:
         yield from self._metadata_search(metadata_type="ANSWER")
@@ -120,7 +124,7 @@ class ThoughtspotClient(APIClient):
         self,
         liveboard_name: str,
         visualization_name: str,
-    ) -> Iterator[dict]:
+    ) -> Iterator[list[list]]:
         """
         Yields the data of a given visualization in the given liveboard.
         ThoughtSpot maintains two system liveboards with stats about data usage,
@@ -133,29 +137,62 @@ class ThoughtspotClient(APIClient):
         )
         liveboard_id = usage_liveboard["metadata_id"]
 
-        data = self._post(
-            endpoint=ThoughtspotEndpointFactory.liveboard(),
-            headers={"Accept": "application/octet-stream"},
+        def handler(response: Response) -> dict:
+            response_dict = response.json()
+            contents = response_dict.get("contents", [])
+            if not contents:
+                logger.warning("No data found in response")
+                return dict()
+            return contents[0]
+
+        request = partial(
+            self._post,
+            endpoint=ThoughtspotEndpointFactory.liveboard_data(),
             data={
                 "metadata_identifier": liveboard_id,
-                "file_format": "CSV",
                 "visualization_identifiers": [visualization_name],
+                "record_offset": 0,
+                "record_size": METADATA_BATCH_SIZE,
             },
-            handler=lambda x: x.text,
+            handler=handler,
         )
-        yield from usage_liveboard_reader(data)
+        yield from fetch_all_pages(request, ThoughtSpotPagination)
 
     def _get_answer_usages(self) -> Iterator[dict]:
-        return self._get_usages(
+        """
+        Returns the usage data of saved Answers, which is found in a visualization
+        of the "Object Usage" liveboard.
+        Each data row returned by the API is transformed from a list into a dictionary.
+        The columns are explicitly listed here because in the API response,
+        there is a mismatch between the number of column names and the number
+        of values per data row.
+        """
+        data: Iterable[list[list]] = self._get_usages(
             liveboard_name=_OBJECT_USAGE_LIVEBOARD,
             visualization_name=_ANSWER_USAGE_VIZ,
         )
+        columns = (
+            "Answer name",
+            "Number of unique users",
+            "Count of object interactions",
+        )
+        for row in data:
+            yield dict(zip(columns, row))
 
     def _get_liveboards_usages(self) -> Iterator[dict]:
-        return self._get_usages(
+        """
+        Returns the usage data of Liveboards, which is found in a visualization
+        of the "User Adoption" liveboard.
+        Each data row returned by the API is transformed from a list into a dictionary.
+        See `_get_answer_usages` regarding the columns list.
+        """
+        data: Iterable[list[list]] = self._get_usages(
             liveboard_name=_USER_ADOPTION_LIVEBOARD,
             visualization_name=_LIVEBOARD_USAGE_VIZ,
         )
+        columns = ("Pinboard", "Unique Number of User", "Pinboard Views")
+        for row in data:
+            yield dict(zip(columns, row))
 
     def fetch(self, asset: ThoughtspotAsset) -> Iterator[dict]:
         if asset == ThoughtspotAsset.ANSWERS:

{castor_extractor-0.24.1 → castor_extractor-0.24.4}/castor_extractor/visualization/thoughtspot/client/endpoints.py

@@ -8,5 +8,5 @@ class ThoughtspotEndpointFactory:
         return "api/rest/2.0/metadata/search"
 
     @classmethod
-    def liveboard(cls) -> str:
-        return "api/rest/2.0/report/liveboard"
+    def liveboard_data(cls) -> str:
+        return "api/rest/2.0/metadata/liveboard/data"

castor_extractor-0.24.4/castor_extractor/visualization/thoughtspot/client/pagination.py

@@ -0,0 +1,25 @@
+from pydantic import ConfigDict, Field
+
+from ....utils import PaginationModel
+
+METADATA_BATCH_SIZE = 100
+
+
+class ThoughtSpotPagination(PaginationModel):
+    data_rows: list = Field(default_factory=list)
+    record_offset: int
+    record_size: int
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        from_attributes=True,
+    )
+
+    def is_last(self) -> bool:
+        return len(self.data_rows) < METADATA_BATCH_SIZE
+
+    def next_page_payload(self) -> dict:
+        return {"record_offset": self.record_offset + METADATA_BATCH_SIZE}
+
+    def page_results(self) -> list:
+        return self.data_rows