unstructured-ingest 0.5.3__tar.gz → 0.5.4__tar.gz

{unstructured_ingest-0.5.3/unstructured_ingest.egg-info → unstructured_ingest-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.3
+Version: 0.5.4
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -23,12 +23,12 @@ Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: python-dateutil
+Requires-Dist: click
+Requires-Dist: dataclasses_json
 Requires-Dist: opentelemetry-sdk
+Requires-Dist: pydantic>=2.7
 Requires-Dist: tqdm
 Requires-Dist: pandas
-Requires-Dist: click
-Requires-Dist: pydantic>=2.7
-Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
 Provides-Extra: csv
@@ -66,13 +66,13 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: requests; extra == "biomed"
 Requires-Dist: bs4; extra == "biomed"
+Requires-Dist: requests; extra == "biomed"
 Provides-Extra: box
 Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
@@ -86,21 +86,21 @@ Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: deltalake; extra == "delta-table"
 Requires-Dist: boto3; extra == "delta-table"
+Requires-Dist: deltalake; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: fsspec; extra == "dropbox"
 Requires-Dist: dropboxdrivefs; extra == "dropbox"
+Requires-Dist: fsspec; extra == "dropbox"
 Provides-Extra: duckdb
 Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
 Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
@@ -109,8 +109,8 @@ Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
 Requires-Dist: google-api-python-client; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: urllib3; extra == "hubspot"
 Requires-Dist: hubspot-api-client; extra == "hubspot"
+Requires-Dist: urllib3; extra == "hubspot"
 Provides-Extra: jira
 Requires-Dist: atlassian-python-api; extra == "jira"
 Provides-Extra: kafka
@@ -128,10 +128,10 @@ Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
+Requires-Dist: htmlBuilder; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
@@ -165,8 +165,8 @@ Requires-Dist: paramiko; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Requires-Dist: psycopg2-binary; extra == "snowflake"
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -178,18 +178,18 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
+Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
-Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -197,11 +197,11 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

unstructured_ingest-0.5.4/test/integration/connectors/test_sharepoint.py

@@ -0,0 +1,222 @@
+import os
+
+import pytest
+
+from test.integration.connectors.utils.constants import BLOB_STORAGE_TAG, SOURCE_TAG
+from test.integration.connectors.utils.validation.source import (
+    SourceValidationConfigs,
+    source_connector_validation,
+)
+from test.integration.utils import requires_env
+from unstructured_ingest.v2.processes.connectors.sharepoint import (
+    CONNECTOR_TYPE,
+    SharepointAccessConfig,
+    SharepointConnectionConfig,
+    SharepointDownloader,
+    SharepointDownloaderConfig,
+    SharepointIndexer,
+    SharepointIndexerConfig,
+)
+
+
+def sharepoint_config():
+    class SharepointTestConfig:
+        def __init__(self):
+            self.client_id = os.environ["SHAREPOINT_CLIENT_ID"]
+            self.client_cred = os.environ["SHAREPOINT_CRED"]
+            self.user_pname = os.environ["MS_USER_PNAME"]
+            self.tenant = os.environ["MS_TENANT_ID"]
+
+    return SharepointTestConfig()
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_source(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True)
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint1",
+            expected_num_files=4,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_source_with_path(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="Folder1")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint2",
+            expected_num_files=2,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_root_with_path(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="e2e-test-folder")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint3",
+            expected_num_files=1,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
+@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
+async def test_sharepoint_shared_documents(temp_dir):
+    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
+    config = sharepoint_config()
+
+    # Create connection and indexer configurations
+    access_config = SharepointAccessConfig(client_cred=config.client_cred)
+    connection_config = SharepointConnectionConfig(
+        client_id=config.client_id,
+        site=site,
+        tenant=config.tenant,
+        user_pname=config.user_pname,
+        access_config=access_config,
+    )
+    index_config = SharepointIndexerConfig(recursive=True, path="Shared Documents")
+
+    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
+
+    # Instantiate indexer and downloader
+    indexer = SharepointIndexer(
+        connection_config=connection_config,
+        index_config=index_config,
+    )
+    downloader = SharepointDownloader(
+        connection_config=connection_config,
+        download_config=download_config,
+    )
+
+    # Run the source connector validation
+    await source_connector_validation(
+        indexer=indexer,
+        downloader=downloader,
+        configs=SourceValidationConfigs(
+            test_id="sharepoint4",
+            expected_num_files=4,
+            validate_downloaded_files=True,
+            exclude_fields_extend=[
+                "metadata.date_created",
+                "metadata.date_modified",
+                "additional_metadata.LastModified",
+                "additional_metadata.@microsoft.graph.downloadUrl",
+            ],
+        ),
+    )

unstructured_ingest-0.5.4/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.5.4"  # pragma: no cover

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.4}/unstructured_ingest/v2/processes/connectors/sharepoint.py

@@ -31,6 +31,7 @@ if TYPE_CHECKING:
     from office365.onedrive.driveitems.driveItem import DriveItem
 
 CONNECTOR_TYPE = "sharepoint"
+LEGACY_DEFAULT_PATH = "Shared Documents"
 
 
 class SharepointAccessConfig(OnedriveAccessConfig):
@@ -76,10 +77,14 @@ class SharepointIndexer(OnedriveIndexer):
         except ClientRequestException:
             logger.info("Site not found")
 
-        drive_items = await self.list_objects(
-            folder=site_drive_item, recursive=self.index_config.recursive
-        )
-        for drive_item in drive_items:
+        path = self.index_config.path
+        # Deprecated sharepoint sdk needed a default path. Microsoft Graph SDK does not.
+        if path and path != LEGACY_DEFAULT_PATH:
+            site_drive_item = site_drive_item.get_by_path(path).get().execute_query()
+
+        for drive_item in site_drive_item.get_files(
+            recursive=self.index_config.recursive
+        ).execute_query():
             file_data = await self.drive_item_to_file_data(drive_item=drive_item)
             yield file_data
 

{unstructured_ingest-0.5.3 → unstructured_ingest-0.5.4/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.3
+Version: 0.5.4
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -23,12 +23,12 @@ Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: python-dateutil
+Requires-Dist: click
+Requires-Dist: dataclasses_json
 Requires-Dist: opentelemetry-sdk
+Requires-Dist: pydantic>=2.7
 Requires-Dist: tqdm
 Requires-Dist: pandas
-Requires-Dist: click
-Requires-Dist: pydantic>=2.7
-Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.26.1; extra == "remote"
 Provides-Extra: csv
@@ -66,13 +66,13 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Provides-Extra: azure-ai-search
 Requires-Dist: azure-search-documents; extra == "azure-ai-search"
 Provides-Extra: biomed
-Requires-Dist: requests; extra == "biomed"
 Requires-Dist: bs4; extra == "biomed"
+Requires-Dist: requests; extra == "biomed"
 Provides-Extra: box
 Requires-Dist: fsspec; extra == "box"
 Requires-Dist: boxfs; extra == "box"
@@ -86,21 +86,21 @@ Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
-Requires-Dist: deltalake; extra == "delta-table"
 Requires-Dist: boto3; extra == "delta-table"
+Requires-Dist: deltalake; extra == "delta-table"
 Provides-Extra: discord
 Requires-Dist: discord.py; extra == "discord"
 Provides-Extra: dropbox
-Requires-Dist: fsspec; extra == "dropbox"
 Requires-Dist: dropboxdrivefs; extra == "dropbox"
+Requires-Dist: fsspec; extra == "dropbox"
 Provides-Extra: duckdb
 Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Provides-Extra: github
 Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
@@ -109,8 +109,8 @@ Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
 Requires-Dist: google-api-python-client; extra == "google-drive"
 Provides-Extra: hubspot
-Requires-Dist: urllib3; extra == "hubspot"
 Requires-Dist: hubspot-api-client; extra == "hubspot"
+Requires-Dist: urllib3; extra == "hubspot"
 Provides-Extra: jira
 Requires-Dist: atlassian-python-api; extra == "jira"
 Provides-Extra: kafka
@@ -128,10 +128,10 @@ Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
-Requires-Dist: backoff; extra == "notion"
 Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
+Requires-Dist: htmlBuilder; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
@@ -165,8 +165,8 @@ Requires-Dist: paramiko; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Requires-Dist: psycopg2-binary; extra == "snowflake"
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -178,18 +178,18 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
+Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
-Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -197,11 +197,11 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

unstructured_ingest-0.5.3/test/integration/connectors/test_sharepoint.py

@@ -1,71 +0,0 @@
-import os
-
-import pytest
-
-from test.integration.connectors.utils.constants import BLOB_STORAGE_TAG, SOURCE_TAG
-from test.integration.connectors.utils.validation.source import (
-    SourceValidationConfigs,
-    source_connector_validation,
-)
-from test.integration.utils import requires_env
-from unstructured_ingest.v2.processes.connectors.sharepoint import (
-    CONNECTOR_TYPE,
-    SharepointAccessConfig,
-    SharepointConnectionConfig,
-    SharepointDownloader,
-    SharepointDownloaderConfig,
-    SharepointIndexer,
-    SharepointIndexerConfig,
-)
-
-
-@pytest.mark.asyncio
-@pytest.mark.tags(CONNECTOR_TYPE, SOURCE_TAG, BLOB_STORAGE_TAG)
-@requires_env("SHAREPOINT_CLIENT_ID", "SHAREPOINT_CRED", "MS_TENANT_ID", "MS_USER_PNAME")
-async def test_sharepoint_source(temp_dir):
-    # Retrieve environment variables
-    site = "https://unstructuredio.sharepoint.com/sites/utic-platform-test-source"
-    client_id = os.environ["SHAREPOINT_CLIENT_ID"]
-    client_cred = os.environ["SHAREPOINT_CRED"]
-    user_pname = os.environ["MS_USER_PNAME"]
-    tenant = os.environ["MS_TENANT_ID"]
-
-    # Create connection and indexer configurations
-    access_config = SharepointAccessConfig(client_cred=client_cred)
-    connection_config = SharepointConnectionConfig(
-        client_id=client_id,
-        site=site,
-        tenant=tenant,
-        user_pname=user_pname,
-        access_config=access_config,
-    )
-    index_config = SharepointIndexerConfig(recursive=True)
-
-    download_config = SharepointDownloaderConfig(download_dir=temp_dir)
-
-    # Instantiate indexer and downloader
-    indexer = SharepointIndexer(
-        connection_config=connection_config,
-        index_config=index_config,
-    )
-    downloader = SharepointDownloader(
-        connection_config=connection_config,
-        download_config=download_config,
-    )
-
-    # Run the source connector validation
-    await source_connector_validation(
-        indexer=indexer,
-        downloader=downloader,
-        configs=SourceValidationConfigs(
-            test_id="sharepoint",
-            expected_num_files=4,
-            validate_downloaded_files=True,
-            exclude_fields_extend=[
-                "metadata.date_created",
-                "metadata.date_modified",
-                "additional_metadata.LastModified",
-                "additional_metadata.@microsoft.graph.downloadUrl",
-            ],
-        ),
-    )

unstructured_ingest-0.5.3/unstructured_ingest/__version__.py

@@ -1 +0,0 @@
-__version__ = "0.5.3"  # pragma: no cover