castor-extractor 0.24.1__py3-none-any.whl → 0.24.4__py3-none-any.whl

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/commands/extract_tableau.py

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

castor_extractor/visualization/tableau/__init__.py

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

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

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

castor_extractor/visualization/tableau/client/__init__.py

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

castor_extractor/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/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/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

castor_extractor/warehouse/snowflake/queries/column.sql

@@ -47,7 +47,9 @@ FROM snowflake.account_usage.columns AS c
     JOIN snowflake.account_usage.tables AS t ON t.table_id = c.table_id
     JOIN tags_agg_columns ta ON c.column_id = ta.column_id
 WHERE TRUE
-    AND COALESCE(c.column_name, '') != ''
+    AND TRIM(COALESCE(c.column_name, '')) != ''
+    AND TRIM(COALESCE(t.table_name, '')) != ''
+    AND TRIM(COALESCE(s.schema_name, '')) != ''
     AND UPPER(c.table_catalog) NOT IN ('SNOWFLAKE', 'UTIL_DB')
     AND (
         c.deleted IS NULL

castor_extractor/warehouse/snowflake/queries/query.sql

@@ -51,20 +51,28 @@ WHERE TRUE
     AND HOUR(CONVERT_TIMEZONE('UTC', start_time)) BETWEEN :hour_min AND :hour_max
     AND execution_status = 'SUCCESS'
     AND query_text != 'SELECT 1'
+    AND TRIM(COALESCE(query_text, '')) != ''
     AND query_type NOT IN (
-        'SHOW',
-        'USE',
-        'ROLLBACK',
-        'DESCRIBE',
         'ALTER_SESSION',
-        'PUT_FILES',
+        'BEGIN_TRANSACTION',
+        'CALL',
+        'COMMENT',
+        'COMMIT',
         'CREATE', -- create objects: stage|function|schema|procedure|file|storage|pipe|notification integration
-        'SET',
+        'DESCRIBE',
+        'DROP',
+        'EXPLAIN',
+        'GET_FILES',
         'GRANT',
-        'COMMIT',
+        'PUT_FILES',
+        'REFRESH_DYNAMIC_TABLE_AT_REFRESH_VERSION',
+        'REMOVE_FILES',
+        'REVOKE',
+        'ROLLBACK',
+        'SET',
+        'SHOW',
+        'TRUNCATE_TABLE',
+        'UNDROP',
         'UNLOAD',
-        'GET_FILES',
-        'DROP',
-        'BEGIN_TRANSACTION',
-        'REMOVE_FILES'
+        'USE'
     )

castor_extractor/warehouse/snowflake/queries/schema.sql

@@ -16,6 +16,7 @@ WHERE TRUE
         deleted IS NULL
         OR deleted > CURRENT_TIMESTAMP - INTERVAL '1 day'
     )
+    AND TRIM(COALESCE(schema_name, '')) != ''
     {database_allowed}
     {database_blocked}
     AND CASE {has_fetch_transient} WHEN FALSE THEN NOT s.is_transient::BOOLEAN ELSE TRUE END

castor_extractor/warehouse/snowflake/queries/table.sql

@@ -41,8 +41,8 @@ FROM snowflake.account_usage.tables AS t
     JOIN snowflake.account_usage.schemata AS s ON s.schema_id = t.table_schema_id
     JOIN tags_agg_tables ta ON t.table_id = ta.table_id
 WHERE TRUE
-    AND t.table_name IS NOT NULL
-    AND t.table_name != ''
+    AND TRIM(COALESCE(t.table_name, '')) != ''
+    AND TRIM(COALESCE(s.schema_name, '')) != ''
     AND UPPER(t.table_catalog) NOT IN ('SNOWFLAKE', 'UTIL_DB')
     AND (
         t.deleted IS NULL

{castor_extractor-0.24.1.dist-info → castor_extractor-0.24.4.dist-info}/METADATA

@@ -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.dist-info → castor_extractor-0.24.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-CHANGELOG.md,sha256=uuXk7pDCrTLgVqMxD2SYWDXs3OzvaBfe592stOCjBdg,15815
+CHANGELOG.md,sha256=1Y5FmmQDspwZaOhKjnJosP2sNd898LeTOmVIMTBt9Bw,16387
 Dockerfile,sha256=xQ05-CFfGShT3oUqaiumaldwA288dj9Yb_pxofQpufg,301
 DockerfileUsage.md,sha256=2hkJQF-5JuuzfPZ7IOxgM6QgIQW7l-9oRMFVwyXC4gE,998
 LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
@@ -25,7 +25,7 @@ castor_extractor/commands/extract_salesforce_reporting.py,sha256=FdANTNiLkIPdm80
 castor_extractor/commands/extract_sigma.py,sha256=sxewHcZ1Doq35V2qnpX_zCKKXkrb1_9bYjUMg7BOW-k,643
 castor_extractor/commands/extract_snowflake.py,sha256=GwlrRxwEBjHqGs_3bs5vM9fzmv61_iwvBr1KcIgFgWM,2161
 castor_extractor/commands/extract_sqlserver.py,sha256=lwhbcNChaXHZgMgSOch3faVr7WJw-sDU6GHl3lzBt_0,1141
-castor_extractor/commands/extract_tableau.py,sha256=DGQaXS-61rV-uzBtqfvqtyQzjLtrLTzE1ViTXPG1eck,1379
+castor_extractor/commands/extract_tableau.py,sha256=xXlLKLN8Eu_a8Kt2F4E-C5D-gq8SUmvoxJcdR_thKKY,1365
 castor_extractor/commands/extract_thoughtspot.py,sha256=caAYJlH-vK7u5IUB6OKXxcaWfLgc7d_XqnFDWK6YNS4,639
 castor_extractor/commands/file_check.py,sha256=TJx76Ymd0QCECmq35zRJMkPE8DJtSInB28MuSXWk8Ao,2644
 castor_extractor/commands/upload.py,sha256=rLXp7gQ8zb1kLbho4FT87q8eJd8Gvo_TkyIynAaQ-4s,1342
@@ -260,27 +260,26 @@ castor_extractor/visualization/sigma/client/credentials.py,sha256=XddAuQSmCKpxJ7
 castor_extractor/visualization/sigma/client/endpoints.py,sha256=DBFphbgoH78_MZUGM_bKBAq28Nl7LWSZ6VRsbxrxtDg,1162
 castor_extractor/visualization/sigma/client/pagination.py,sha256=kNEhNq08tTGbypyMjxs0w4uvDtQc_iaWpOZweaa_FsU,690
 castor_extractor/visualization/sigma/extract.py,sha256=XIT1qsj6g6dgBWP8HPfj_medZexu48EaY9tUwi14gzM,2298
-castor_extractor/visualization/tableau_revamp/__init__.py,sha256=a3DGjQhaz17gBqW-E84TAgupKbqLC40y5Ajo1yn-ot4,156
-castor_extractor/visualization/tableau_revamp/assets.py,sha256=8sJsK6Qixao6xVmVaO1usvs16SjNub9sIx7o-adYV14,659
-castor_extractor/visualization/tableau_revamp/client/__init__.py,sha256=wmS9uLtUiqNYVloi0-DgD8d2qzu3RVZEAtWiaDp6G_M,90
-castor_extractor/visualization/tableau_revamp/client/client.py,sha256=Ju89lMDiLOZ2LjxylcFm5429WElxGxjc52bMIWoKCDA,7716
-castor_extractor/visualization/tableau_revamp/client/client_metadata_api.py,sha256=WdALsMGTji2C5oSDyRwFzq-f5HZDwX-m3W8Byx87Qh4,4357
-castor_extractor/visualization/tableau_revamp/client/client_rest_api.py,sha256=O2F4qfrElTHHuD5WRPfLufazSmZ65jmlzye1t5rVOaQ,4024
-castor_extractor/visualization/tableau_revamp/client/client_tsc.py,sha256=AzN8ytKmq6HUeApTJ118JQ7EBEPESqrg7u8n3GZXqZI,1874
-castor_extractor/visualization/tableau_revamp/client/credentials.py,sha256=qA-EaX-4rbQRsn8v4zWh5Kh784ndHLjJaoZwnkQgCyo,1905
-castor_extractor/visualization/tableau_revamp/client/errors.py,sha256=ecT8Tit5VtzrOBB9ykblA0nvd75j5-_QDFupjV48zJQ,300
-castor_extractor/visualization/tableau_revamp/client/gql_queries.py,sha256=uKNGRhYeoiKfJ8vxO50L0a2fHDpYQgEdG_eZfYSdHqM,2238
-castor_extractor/visualization/tableau_revamp/client/rest_fields.py,sha256=3kvaq48BCBLfm7GL-i5W53MpbmSSi-e0yt31dNOk8ac,948
-castor_extractor/visualization/tableau_revamp/constants.py,sha256=lHGB50FgVNO2nXeIhkvQKivD8ZFBIjDrflgD5cTXKJw,104
-castor_extractor/visualization/tableau_revamp/extract.py,sha256=Ud_lt1YDSyCBjR38sjtvINy_Ez_TnA_jtM2D-8LcxPA,1471
+castor_extractor/visualization/tableau/__init__.py,sha256=eFI_1hjdkxyUiAYiy3szwyuwn3yJ5C_KbpBU0ySJDcQ,138
+castor_extractor/visualization/tableau/assets.py,sha256=HbCRd8VCj1WBEeqg9jwnygnT7xOFJ6PQD7Lq7sV-XR0,635
+castor_extractor/visualization/tableau/client/__init__.py,sha256=P8RKFKOC63WkH5hdEytJOwHS9vzQ8GXreLfXZetmMP8,78
+castor_extractor/visualization/tableau/client/client.py,sha256=zzqhzIqKyJygo4ZNGk6cZh0e6Z9R1W5T0P9un52KC1M,7626
+castor_extractor/visualization/tableau/client/client_metadata_api.py,sha256=fIBsSbRTypBABsCoigO2dkKsw4Eu3GrsEPTDfjY8A80,4303
+castor_extractor/visualization/tableau/client/client_rest_api.py,sha256=x4dNw4PPJdalTlGowwkANwqiS2ZhGxzpQytkHq3KbpY,3988
+castor_extractor/visualization/tableau/client/client_tsc.py,sha256=VI_PJyd1ty3HSYXHHQjshmG2ziowIbrwJRonRPCHbks,1820
+castor_extractor/visualization/tableau/client/credentials.py,sha256=uQICIgeXmLZfOroTgZt7PuKNKTyqQllRGSTcOmIfrKU,1893
+castor_extractor/visualization/tableau/client/errors.py,sha256=ecT8Tit5VtzrOBB9ykblA0nvd75j5-_QDFupjV48zJQ,300
+castor_extractor/visualization/tableau/client/gql_queries.py,sha256=NISarYh33Ij7DhYxqjTdv681AHYpbft8kPwVUQbAZ7U,2190
+castor_extractor/visualization/tableau/client/rest_fields.py,sha256=ZKYYuMxg9PXhczVXaD4rXNk7dYyWJ1_bVM8FLEXju7s,888
+castor_extractor/visualization/tableau/constants.py,sha256=lHGB50FgVNO2nXeIhkvQKivD8ZFBIjDrflgD5cTXKJw,104
+castor_extractor/visualization/tableau/extract.py,sha256=FnjmmUdNA9MEf3S5Tw37x6ZXxVsK8R3YnVk1UVYbaZk,1423
 castor_extractor/visualization/thoughtspot/__init__.py,sha256=NhTGUk5Kdt54oCjHYoAt0cLBmVLys5lFYiRANL6wCmI,150
 castor_extractor/visualization/thoughtspot/assets.py,sha256=SAQWPKaD2NTSDg7-GSkcRSSEkKSws0MJfOVcHkdeTSg,276
 castor_extractor/visualization/thoughtspot/client/__init__.py,sha256=svrE2rMxR-OXctjPeAHMEPePlfcra-9KDevTMcHunAA,86
-castor_extractor/visualization/thoughtspot/client/client.py,sha256=mtwMCPI1-1tyZb1gSYYr-O2QZMTFQwNgillU6ycsOU4,5552
+castor_extractor/visualization/thoughtspot/client/client.py,sha256=lRNkigPV2MTozgBzFkij7mCXMMRqXzPtNs8EEi_f3tk,7127
 castor_extractor/visualization/thoughtspot/client/credentials.py,sha256=fp4YHiZy-dstWiLr5c4kFU9SyPK5rd2nCeh8k5sVRpM,462
-castor_extractor/visualization/thoughtspot/client/endpoints.py,sha256=u3FRkmG6j5OIMEeXWZcgRObP8JeC4EutIJEeitNV44c,330
-castor_extractor/visualization/thoughtspot/client/utils.py,sha256=3LgbIWoG1e39VW8rYaV4ot_0EFipziwf3rFAZKxrlEY,1072
-castor_extractor/visualization/thoughtspot/client/utils_test.py,sha256=2XysRU7a58KA2JgNwU2j4GPrN0rkN7Gvk8kQCJlYXVk,2469
+castor_extractor/visualization/thoughtspot/client/endpoints.py,sha256=XLDGs7v2e2S2VdJX8cQjMh80KNCHb_H5A9I8ejP1ZPs,342
+castor_extractor/visualization/thoughtspot/client/pagination.py,sha256=iosYUJ7ZMT1G_Jm6AXPwczYnXFzS6Yez-B9-tRFiV_w,619
 castor_extractor/visualization/thoughtspot/extract.py,sha256=mcXS0jGFpa50td98AVbbTqxchyI5wDCpB-v1o5iRc3g,1354
 castor_extractor/warehouse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 castor_extractor/warehouse/abstract/__init__.py,sha256=Fdfa026tgOo64MvzVRLHM_F2G-JmcehrF0mh3dHgb7s,419
@@ -380,16 +379,16 @@ castor_extractor/warehouse/snowflake/credentials.py,sha256=u0sZ6xPtcZmmvnUsAejJk
 castor_extractor/warehouse/snowflake/credentials_test.py,sha256=Lkc-DHXOvr50KrqAW4nt_x0IA0Mu_CsBVu6ATnzQB6I,673
 castor_extractor/warehouse/snowflake/extract.py,sha256=3yc9kcVtt2c1uWJOJJgeZchV4VmRr9EeYM3W6gl8zQQ,3201
 castor_extractor/warehouse/snowflake/queries/.sqlfluff,sha256=vttrwcr64JVIuvc7WIg9C54cbOkjg_VjXNR7YnTGOPE,31
-castor_extractor/warehouse/snowflake/queries/column.sql,sha256=Wy-arvS_3Dh0HFrzdpRmBsI58mMlN_5U097s5kMNluQ,1781
+castor_extractor/warehouse/snowflake/queries/column.sql,sha256=Ru-yC0s76I9LehOA4aCZ--xz6D9H1Hyr3OZdILOBHAw,1882
 castor_extractor/warehouse/snowflake/queries/column_lineage.sql,sha256=YKBiZ6zySSNcXLDXwm31EjGIIkkkZc0-S6hI1SRM80o,1179
 castor_extractor/warehouse/snowflake/queries/database.sql,sha256=ifZXoKUXtsrGOxml6AcNhA4yybIyatH5va7bcp-lgCU,483
 castor_extractor/warehouse/snowflake/queries/function.sql,sha256=8LRh0ybhd-RldJ8UZspWUm3yv52evq11O2uqIO4KqeQ,372
 castor_extractor/warehouse/snowflake/queries/grant_to_role.sql,sha256=O7AJ1LzoXGDFmiVvQ8EMJ5x8FSAnaxRPdmRyAlEmkUM,272
 castor_extractor/warehouse/snowflake/queries/grant_to_user.sql,sha256=7AalVajU5vRRpIiys1igSwmDXirbwpMTvJr2ihSz2NE,143
-castor_extractor/warehouse/snowflake/queries/query.sql,sha256=-OYcWUvdPBkpOfezkZaW7hrOdDz3JyoqjNdRm_88Rsk,1779
+castor_extractor/warehouse/snowflake/queries/query.sql,sha256=w4T6-TgwUozDgaF3Fk-qex7bDdEIHLkkB5XEe2VJXZQ,1992
 castor_extractor/warehouse/snowflake/queries/role.sql,sha256=D0VvGxLZMwug2SvefhAsNR9YIun0fZvcDWkz891xSYM,96
-castor_extractor/warehouse/snowflake/queries/schema.sql,sha256=HCDEw0Nj_GPHBNH3Ik_5BF4rkD5yBfSyeN9UaiFGrI4,730
-castor_extractor/warehouse/snowflake/queries/table.sql,sha256=qTwkAJ7-kM8vX03RP16U_5_euWW5ZTQAKuiLPsbj2hs,1438
+castor_extractor/warehouse/snowflake/queries/schema.sql,sha256=iLn6_y5rn63KigjE4GEAMp8ZuZZofhMXYGb8saPDGUc,776
+castor_extractor/warehouse/snowflake/queries/table.sql,sha256=CbSLfJAylyyyD3mkGPSLLE7BHrGjlY499kzO9RN0e4Y,1473
 castor_extractor/warehouse/snowflake/queries/user.sql,sha256=88V8eRj1NDaD_ufclsKOHHlqCtBMQHOV54yy6RKJaXk,570
 castor_extractor/warehouse/snowflake/queries/view_ddl.sql,sha256=eWsci_50cxiYIv3N7BKkbXVM3RoIzqSDtohqRnE5kg4,673
 castor_extractor/warehouse/snowflake/query.py,sha256=C2LTdPwBzMQ_zMncg0Kq4_WkoY7K9as5tvxBDrIOlwI,1763
@@ -404,8 +403,8 @@ 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-0.24.1.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
-castor_extractor-0.24.1.dist-info/METADATA,sha256=O-v3GkuQVqXbbr5DYt0Tm2uodPoXJd4f6ayR93ywA3M,22971
-castor_extractor-0.24.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-castor_extractor-0.24.1.dist-info/entry_points.txt,sha256=FQNShG4w4nRO95_bZnagh7FQ2oiZ-40bdt8ZdTW1-uI,1731
-castor_extractor-0.24.1.dist-info/RECORD,,
+castor_extractor-0.24.4.dist-info/LICENCE,sha256=sL-IGa4hweyya1HgzMskrRdybbIa2cktzxb5qmUgDg8,8254
+castor_extractor-0.24.4.dist-info/METADATA,sha256=eY2TPP3IDq9an2JJzoZcN-_rG5DJIGzbJOqEtGBhzd4,23543
+castor_extractor-0.24.4.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+castor_extractor-0.24.4.dist-info/entry_points.txt,sha256=FQNShG4w4nRO95_bZnagh7FQ2oiZ-40bdt8ZdTW1-uI,1731
+castor_extractor-0.24.4.dist-info/RECORD,,

castor_extractor/visualization/tableau_revamp/__init__.py

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

castor_extractor/visualization/tableau_revamp/client/__init__.py

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

castor_extractor/visualization/thoughtspot/client/utils.py

@@ -1,31 +0,0 @@
-import csv
-import re
-from collections.abc import Iterator
-from io import StringIO
-
-_END_OF_GENERATED_TEXT = r'^""$'
-
-
-def usage_liveboard_reader(usage_liveboard_csv: str) -> Iterator[dict]:
-    """
-    Converts a CSV string into an iterator of dictionaries after
-    ignoring the generated text that preceeds the actual CSV header row.
-    The generated block ends with a row containing only two double quotes.
-    Here is an example:
-
-        "Data extract produced by Castor on 09/19/2024 06:54"
-        "Filters applied on data :"
-        "User Action IN [pinboard_embed_view,pinboard_tspublic_no_runtime_filter,pinboard_tspublic_runtime_filter,pinboard_view]"
-        "Pinboard NOT IN [mlm - availability pinboard,null]"
-        "Timestamp >= 20240820 00:00:00 < 20240919 00:00:00"
-        "Timestamp >= 20240919 00:00:00 < 20240920 00:00:00"
-        ""
-
-    """
-    csv_file = StringIO(usage_liveboard_csv)
-
-    line = next(csv_file)
-    while not re.match(_END_OF_GENERATED_TEXT, line.strip()):
-        line = next(csv_file)
-
-    yield from csv.DictReader(csv_file)

castor_extractor/visualization/thoughtspot/client/utils_test.py

@@ -1,75 +0,0 @@
-from .utils import (
-    usage_liveboard_reader,
-)
-
-VALID_CSV_1 = '''"Data extract produced by Castor on 09/19/2024 06:54"
-"Filters applied on data :"
-"User Action IN [pinboard_embed_view,pinboard_tspublic_no_runtime_filter,pinboard_tspublic_runtime_filter,pinboard_view]"
-"Pinboard NOT IN [mlm - availability pinboard,null]"
-"Timestamp >= 20240820 00:00:00 < 20240919 00:00:00"
-"Timestamp >= 20240919 00:00:00 < 20240920 00:00:00"
-""
-"Pinboard","Pinboard Views","Unique Number of User"
-"Market Report","559","19"
-"Retailer report","204","14"
-"Second-hand market","72","6"
-"September test","25","2"'''
-
-
-VALID_CSV_2 = '''"Data extract produced by Castor on 01/07/2025 16:07"
-"Filters applied on data :"
-"Timestamp >= 20241208 00:00:00 < 20250107 00:00:00"
-""
-"Answer name","User name","Number of unique users","Count of object interactions"
-"toto","tata","1","666"'''
-
-# Invalid CSV input (missing data rows)
-INVALID_CSV = '''"Data extract produced by Castor on 09/19/2024 06:54"
-"Filters applied on data :"
-"User Action IN [pinboard_embed_view,pinboard_tspublic_no_runtime_filter,pinboard_tspublic_runtime_filter,pinboard_view]"
-"Pinboard NOT IN [mlm - availability pinboard,null]"
-"Timestamp >= 20240820 00:00:00 < 20240919 00:00:00"
-"Timestamp >= 20240919 00:00:00 < 20240920 00:00:00"
-""'''
-
-
-def test_usage_liveboard_reader():
-    expected_output_1 = [
-        {
-            "Pinboard": "Market Report",
-            "Pinboard Views": "559",
-            "Unique Number of User": "19",
-        },
-        {
-            "Pinboard": "Retailer report",
-            "Pinboard Views": "204",
-            "Unique Number of User": "14",
-        },
-        {
-            "Pinboard": "Second-hand market",
-            "Pinboard Views": "72",
-            "Unique Number of User": "6",
-        },
-        {
-            "Pinboard": "September test",
-            "Pinboard Views": "25",
-            "Unique Number of User": "2",
-        },
-    ]
-    expected_output_2 = [
-        {
-            "Answer name": "toto",
-            "User name": "tata",
-            "Number of unique users": "1",
-            "Count of object interactions": "666",
-        }
-    ]
-
-    result = list(usage_liveboard_reader(VALID_CSV_1))
-    assert result == expected_output_1
-
-    result = list(usage_liveboard_reader(VALID_CSV_2))
-    assert result == expected_output_2
-
-    result = list(usage_liveboard_reader(INVALID_CSV))
-    assert result == []  # Expect an empty result since there is no data