unstructured-ingest 0.5.19__py3-none-any.whl → 0.5.20__py3-none-any.whl

test/unit/v2/connectors/ibm_watsonx/test_ibm_watsonx_s3.py

@@ -0,0 +1,459 @@
+import time
+from unittest.mock import MagicMock
+
+import pandas as pd
+import pytest
+from pydantic import Secret
+from pyiceberg.exceptions import CommitFailedException
+from pytest_mock import MockerFixture
+
+from unstructured_ingest.v2.errors import ProviderError, UserError
+from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
+from unstructured_ingest.v2.processes.connectors.ibm_watsonx import IBM_WATSONX_S3_CONNECTOR_TYPE
+from unstructured_ingest.v2.processes.connectors.ibm_watsonx.ibm_watsonx_s3 import (
+    IbmWatsonxAccessConfig,
+    IbmWatsonxConnectionConfig,
+    IbmWatsonxUploader,
+    IbmWatsonxUploaderConfig,
+)
+
+
+@pytest.fixture
+def file_data():
+    return FileData(
+        identifier="test_identifier",
+        connector_type=IBM_WATSONX_S3_CONNECTOR_TYPE,
+        source_identifiers=SourceIdentifiers(
+            filename="test_file.pdf", fullpath="/tmp/test_file.pdf"
+        ),
+    )
+
+
+@pytest.fixture
+def access_config():
+    return IbmWatsonxAccessConfig(
+        iam_api_key="test_iam_api_key",
+        access_key_id="test_access_key_id",
+        secret_access_key="test_secret_access_key",
+    )
+
+
+@pytest.fixture
+def connection_config(access_config: IbmWatsonxAccessConfig):
+    return IbmWatsonxConnectionConfig(
+        access_config=Secret(access_config),
+        iceberg_endpoint="test_iceberg_endpoint/",
+        object_storage_endpoint="test_object_storage_endpoint/",
+        object_storage_region="test_region",
+        catalog="test_catalog",
+    )
+
+
+@pytest.fixture
+def uploader_config():
+    return IbmWatsonxUploaderConfig(
+        namespace="test_namespace",
+        table="test_table",
+        record_id_key="test_record_id_key",
+    )
+
+
+@pytest.fixture
+def uploader(
+    connection_config: IbmWatsonxConnectionConfig, uploader_config: IbmWatsonxUploaderConfig
+):
+    return IbmWatsonxUploader(
+        connection_config=connection_config,
+        upload_config=uploader_config,
+    )
+
+
+@pytest.fixture
+def mock_catalog(mocker: MockerFixture):
+    mock_catalog = mocker.MagicMock()
+    mock_catalog.namespace_exists.return_value = True
+    mock_catalog.table_exists.return_value = True
+    return mock_catalog
+
+
+@pytest.fixture
+def mock_get_catalog(mocker: MockerFixture, mock_catalog: MagicMock):
+    mock_get_catalog = mocker.patch.context_manager(
+        IbmWatsonxConnectionConfig, "get_catalog", autospec=True
+    )
+    mock_get_catalog.return_value.__enter__.return_value = mock_catalog
+    return mock_get_catalog
+
+
+@pytest.fixture
+def mock_table(mocker: MockerFixture):
+    mock_table = mocker.MagicMock()
+    return mock_table
+
+
+@pytest.fixture
+def mock_get_table(mocker: MockerFixture, mock_table: MagicMock):
+    mock_get_table = mocker.patch.context_manager(IbmWatsonxUploader, "get_table", autospec=True)
+    mock_get_table.return_value.__enter__.return_value = mock_table
+    return mock_get_table
+
+
+@pytest.fixture
+def mock_transaction(mocker: MockerFixture, mock_table: MagicMock):
+    mock_transaction = mocker.MagicMock()
+    mock_table.transaction.return_value.__enter__.return_value = mock_transaction
+    return mock_transaction
+
+
+@pytest.fixture
+def mock_data_table(mocker: MockerFixture):
+    mock_data_table = mocker.MagicMock()
+    mock_data_table.schema = "schema"
+    return mock_data_table
+
+
+@pytest.fixture
+def mock_delete(mocker: MockerFixture):
+    return mocker.patch.object(IbmWatsonxUploader, "_delete")
+
+
+@pytest.fixture
+def test_df():
+    return pd.DataFrame(
+        {
+            "test_column_0": [True, False, True],
+            "test_column_1": [1, 2, 3],
+            "test_column_2": ["a", "b", "c"],
+        }
+    )
+
+
+@pytest.fixture
+def timestamp_now():
+    return int(time.time())
+
+
+def test_ibm_watsonx_connection_config_iceberg_url(
+    mocker: MockerFixture,
+    connection_config: IbmWatsonxConnectionConfig,
+):
+    mocker.patch(
+        "unstructured_ingest.v2.processes.connectors.ibm_watsonx.ibm_watsonx_s3.DEFAULT_ICEBERG_URI_PATH",  # noqa: E501
+        new="/mds/iceberg",
+    )
+    expected_url = "https://test_iceberg_endpoint/mds/iceberg"
+    assert connection_config.iceberg_url == expected_url
+
+
+def test_ibm_watsonx_connection_config_object_storage_url(
+    connection_config: IbmWatsonxConnectionConfig,
+):
+    expected_url = "https://test_object_storage_endpoint"
+    assert connection_config.object_storage_url == expected_url
+
+
+def test_ibm_watsonx_connection_config_bearer_token_new_token(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig, timestamp_now: int
+):
+    mock_generate_bearer_token = mocker.patch.object(
+        IbmWatsonxConnectionConfig,
+        "generate_bearer_token",
+        return_value={"access_token": "new_token", "expiration": timestamp_now + 3600},
+    )
+    token = connection_config.bearer_token
+    assert token == "new_token"
+    mock_generate_bearer_token.assert_called_once()
+
+
+def test_ibm_watsonx_connection_config_bearer_token_existing_token(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig, timestamp_now: int
+):
+    connection_config._bearer_token = {
+        "access_token": "existing_token",
+        "expiration": timestamp_now + 3600,
+    }
+    mock_generate_bearer_token = mocker.patch.object(
+        IbmWatsonxConnectionConfig, "generate_bearer_token"
+    )
+    token = connection_config.bearer_token
+    assert token == "existing_token"
+    mock_generate_bearer_token.assert_not_called()
+
+
+def test_ibm_watsonx_connection_config_bearer_token_expired_token(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig, timestamp_now: int
+):
+    connection_config._bearer_token = {
+        "access_token": "expired_token",
+        "expiration": timestamp_now - 3600,
+    }
+    mock_generate_bearer_token = mocker.patch.object(
+        IbmWatsonxConnectionConfig,
+        "generate_bearer_token",
+        return_value={"access_token": "new_token", "expiration": timestamp_now + 3600},
+    )
+    token = connection_config.bearer_token
+    assert token == "new_token"
+    mock_generate_bearer_token.assert_called_once()
+
+
+def test_ibm_watsonx_connection_config_bearer_token_soon_to_expire_token(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig, timestamp_now: int
+):
+    connection_config._bearer_token = {
+        "access_token": "soon_to_expire_token",
+        "expiration": timestamp_now + 60,
+    }
+    mock_generate_bearer_token = mocker.patch.object(
+        IbmWatsonxConnectionConfig,
+        "generate_bearer_token",
+        return_value={"access_token": "new_token", "expiration": timestamp_now + 3600},
+    )
+    token = connection_config.bearer_token
+    assert token == "new_token"
+    mock_generate_bearer_token.assert_called_once()
+
+
+def test_ibm_watsonx_connection_config_get_catalog_success(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig
+):
+    mocker.patch(
+        "unstructured_ingest.v2.processes.connectors.ibm_watsonx.ibm_watsonx_s3.DEFAULT_ICEBERG_URI_PATH",  # noqa: E501
+        new="/mds/iceberg",
+    )
+    mocker.patch.object(
+        IbmWatsonxConnectionConfig,
+        "bearer_token",
+        new="test_bearer_token",
+    )
+    mock_load_catalog = mocker.patch("pyiceberg.catalog.load_catalog")
+
+    with connection_config.get_catalog() as catalog:
+        assert catalog is not None
+    mock_load_catalog.assert_called_once_with(
+        **{
+            "name": "test_catalog",
+            "type": "rest",
+            "uri": "https://test_iceberg_endpoint/mds/iceberg",
+            "token": "test_bearer_token",
+            "warehouse": "test_catalog",
+            "s3.endpoint": "https://test_object_storage_endpoint",
+            "s3.access-key-id": "test_access_key_id",
+            "s3.secret-access-key": "test_secret_access_key",
+            "s3.region": "test_region",
+        }
+    )
+
+
+def test_ibm_watsonx_connection_config_get_catalog_failure(
+    mocker: MockerFixture, connection_config: IbmWatsonxConnectionConfig
+):
+    mocker.patch(
+        "pyiceberg.catalog.load_catalog",
+        side_effect=Exception("Connection error"),
+    )
+    mocker.patch.object(
+        IbmWatsonxConnectionConfig,
+        "bearer_token",
+        new="test_bearer_token",
+    )
+    with pytest.raises(ProviderError):
+        with connection_config.get_catalog():
+            pass
+
+
+def test_ibm_watsonx_uploader_precheck_namespace_exists_table_exists(
+    mock_get_catalog: MagicMock,
+    mock_catalog: MagicMock,
+    uploader: IbmWatsonxUploader,
+):
+    uploader.precheck()
+
+    mock_catalog.namespace_exists.assert_called_once_with("test_namespace")
+    mock_catalog.table_exists.assert_called_once_with(("test_namespace", "test_table"))
+
+
+def test_ibm_watsonx_uploader_precheck_namespace_does_not_exist(
+    mock_get_catalog: MagicMock,
+    mock_catalog: MagicMock,
+    uploader: IbmWatsonxUploader,
+):
+    mock_catalog.namespace_exists.return_value = False
+
+    with pytest.raises(UserError, match="Namespace 'test_namespace' does not exist"):
+        uploader.precheck()
+
+    mock_catalog.namespace_exists.assert_called_once_with("test_namespace")
+    mock_catalog.table_exists.assert_not_called()
+
+
+def test_ibm_watsonx_uploader_precheck_table_does_not_exist(
+    mock_get_catalog: MagicMock,
+    mock_catalog: MagicMock,
+    uploader: IbmWatsonxUploader,
+):
+    mock_catalog.table_exists.return_value = False
+
+    with pytest.raises(
+        UserError,
+        match="Table 'test_table' does not exist in namespace 'test_namespace'",
+    ):
+        uploader.precheck()
+
+    mock_catalog.namespace_exists.assert_called_once_with("test_namespace")
+    mock_catalog.table_exists.assert_called_once_with(("test_namespace", "test_table"))
+
+
+def test_ibm_watsonx_uploader_upload_data_table_success(
+    uploader: IbmWatsonxUploader,
+    mock_table: MagicMock,
+    mock_transaction: MagicMock,
+    mock_data_table: MagicMock,
+    mock_delete: MagicMock,
+    file_data: FileData,
+):
+    uploader.upload_data_table(mock_table, mock_data_table, file_data)
+
+    mock_delete.assert_called_once_with(mock_transaction, "test_identifier")
+    mock_transaction.append.assert_called_once_with(mock_data_table)
+
+
+def test_ibm_watsonx_uploader_upload_data_table_commit_exception(
+    uploader: IbmWatsonxUploader,
+    mock_table: MagicMock,
+    mock_transaction: MagicMock,
+    mock_data_table: MagicMock,
+    mock_delete: MagicMock,
+    file_data: FileData,
+):
+    mock_transaction.append.side_effect = CommitFailedException()
+
+    with pytest.raises(ProviderError):
+        uploader.upload_data_table(mock_table, mock_data_table, file_data)
+    assert mock_table.refresh.call_count == 5
+
+
+def test_ibm_watsonx_uploader_upload_data_table_exception(
+    uploader: IbmWatsonxUploader,
+    mock_table: MagicMock,
+    mock_transaction: MagicMock,
+    mock_data_table: MagicMock,
+    mock_delete: MagicMock,
+    file_data: FileData,
+):
+    mock_transaction.append.side_effect = Exception()
+
+    with pytest.raises(ProviderError):
+        uploader.upload_data_table(mock_table, mock_data_table, file_data)
+    assert mock_table.refresh.call_count == 0
+
+
+def test_ibm_watsonx_uploader_df_to_arrow_table(
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+    test_df: pd.DataFrame,
+):
+    mock_fit_to_schema = mocker.patch.object(
+        IbmWatsonxUploader, "_fit_to_schema", return_value=test_df
+    )
+
+    result = uploader._df_to_arrow_table(test_df)
+
+    mock_fit_to_schema.assert_called_once_with(test_df, add_missing_columns=False)
+    assert len(result.column_names) == 3
+    assert "test_column_0" in result.column_names
+    assert "test_column_1" in result.column_names
+    assert "test_column_2" in result.column_names
+
+
+def test_ibm_watsonx_uploader_can_delete_column_exists(
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+):
+    mocker.patch.object(
+        IbmWatsonxUploader, "get_table_columns", return_value=["test_record_id_key"]
+    )
+
+    assert uploader.can_delete() is True
+
+
+def test_ibm_watsonx_uploader_can_delete_column_does_not_exist(
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+):
+    mocker.patch.object(IbmWatsonxUploader, "get_table_columns", return_value=["other_column"])
+
+    assert uploader.can_delete() is False
+
+
+def test_ibm_watsonx_uploader_get_table_columns_cache(
+    uploader: IbmWatsonxUploader,
+):
+    uploader._columns = ["cached_column"]
+
+    result = uploader.get_table_columns()
+
+    assert result == ["cached_column"]
+
+
+def test_ibm_watsonx_uploader_get_table_columns_no_cache(
+    uploader: IbmWatsonxUploader,
+    mock_get_table: MagicMock,
+    mock_table: MagicMock,
+):
+    uploader._columns = None
+    mock_table.schema.return_value.column_names = ["column_1", "column_2"]
+
+    result = uploader.get_table_columns()
+
+    mock_get_table.assert_called_once()
+    assert result == ["column_1", "column_2"]
+    assert uploader._columns == ["column_1", "column_2"]
+
+
+def test_ibm_watsonx_uploader_upload_dataframe_success(
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+    test_df: pd.DataFrame,
+    mock_get_table: MagicMock,
+    mock_table: MagicMock,
+    mock_data_table: MagicMock,
+    file_data: FileData,
+):
+    mocker.patch.object(IbmWatsonxUploader, "_df_to_arrow_table", return_value=mock_data_table)
+    mock_upload_data_table = mocker.patch.object(IbmWatsonxUploader, "upload_data_table")
+
+    uploader.upload_dataframe(test_df, file_data)
+
+    mock_get_table.assert_called_once()
+    mock_upload_data_table.assert_called_once_with(mock_table, mock_data_table, file_data)
+
+
+def test_ibm_watsonx_uploader_delete_can_delete(
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+    mock_transaction: MagicMock,
+):
+    mocker.patch.object(IbmWatsonxUploader, "can_delete", return_value=True)
+    mock_equal_to = mocker.patch("pyiceberg.expressions.EqualTo")
+
+    uploader._delete(mock_transaction, "test_identifier")
+
+    mock_equal_to.assert_called_once_with("test_record_id_key", "test_identifier")
+    mock_transaction.delete.assert_called_once_with(delete_filter=mock_equal_to.return_value)
+
+
+def test_ibm_watsonx_uploader_delete_cannot_delete(
+    caplog: pytest.LogCaptureFixture,
+    mocker: MockerFixture,
+    uploader: IbmWatsonxUploader,
+    mock_transaction: MagicMock,
+):
+    mocker.patch.object(IbmWatsonxUploader, "can_delete", return_value=False)
+
+    uploader._delete(mock_transaction, "test_identifier")
+    mock_transaction.delete.assert_not_called()
+    assert (
+        "Table doesn't contain expected record id column test_record_id_key, skipping delete"
+        in caplog.text
+    )

test/unit/v2/connectors/sql/test_sql.py

@@ -1,10 +1,16 @@
 from pathlib import Path
 
+import pandas as pd
 import pytest
 from pytest_mock import MockerFixture
 
 from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
-from unstructured_ingest.v2.processes.connectors.sql.sql import SQLUploadStager
+from unstructured_ingest.v2.processes.connectors.sql.sql import (
+    SQLConnectionConfig,
+    SQLUploader,
+    SQLUploaderConfig,
+    SQLUploadStager,
+)
 
 
 @pytest.fixture
@@ -12,6 +18,17 @@ def mock_instance() -> SQLUploadStager:
     return SQLUploadStager()
 
 
+@pytest.fixture
+def mock_uploader(mocker: MockerFixture) -> SQLUploader:
+    mock_connection_config = mocker.Mock(spec=SQLConnectionConfig)
+    mock_upload_config = mocker.Mock(spec=SQLUploaderConfig)
+    return SQLUploader(
+        upload_config=mock_upload_config,
+        connection_config=mock_connection_config,
+        connector_type="sql_test",
+    )
+
+
 @pytest.mark.parametrize(
     ("input_filepath", "output_filename", "expected"),
     [
@@ -72,3 +89,64 @@ def test_run_output_filename_suffix(
         path=output_dir / expected, data=[{"key": "value"}, {"key": "value2"}]
     )
     assert result.name == expected
+
+
+def test_fit_to_schema_drop_columns(mocker: MockerFixture, mock_uploader: SQLUploader):
+    df = pd.DataFrame(
+        {
+            "col1": [1, 2],
+            "col2": [3, 4],
+            "col3": [5, 6],
+        }
+    )
+    mocker.patch.object(mock_uploader, "get_table_columns", return_value=["col1", "col2"])
+
+    result = mock_uploader._fit_to_schema(df)
+
+    assert "col3" not in result.columns
+    assert "col1" in result.columns
+    assert "col2" in result.columns
+
+
+def test_fit_to_schema_add_missing_columns(mocker: MockerFixture, mock_uploader: SQLUploader):
+    df = pd.DataFrame(
+        {
+            "col1": [1, 2],
+        }
+    )
+    mocker.patch.object(mock_uploader, "get_table_columns", return_value=["col1", "col2"])
+
+    result = mock_uploader._fit_to_schema(df)
+
+    assert "col2" in result.columns
+    assert result["col2"].isnull().all()
+
+
+def test_fit_to_schema_no_changes(mocker: MockerFixture, mock_uploader: SQLUploader):
+    df = pd.DataFrame(
+        {
+            "col1": [1, 2],
+            "col2": [3, 4],
+        }
+    )
+    mocker.patch.object(mock_uploader, "get_table_columns", return_value=["col1", "col2"])
+
+    result = mock_uploader._fit_to_schema(df)
+
+    assert "col1" in result.columns
+    assert "col2" in result.columns
+    assert result.equals(df)
+
+
+def test_fit_to_schema_no_add_missing_columns(mocker: MockerFixture, mock_uploader: SQLUploader):
+    df = pd.DataFrame(
+        {
+            "col1": [1, 2],
+        }
+    )
+    mocker.patch.object(mock_uploader, "get_table_columns", return_value=["col1", "col2"])
+
+    result = mock_uploader._fit_to_schema(df, add_missing_columns=False)
+
+    assert "col2" not in result.columns
+    assert "col1" in result.columns

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.19"  # pragma: no cover
+__version__ = "0.5.20"  # pragma: no cover

unstructured_ingest/v2/processes/connectors/__init__.py

@@ -4,6 +4,7 @@ import unstructured_ingest.v2.processes.connectors.databricks  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.duckdb  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.elasticsearch  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.fsspec  # noqa: F401
+import unstructured_ingest.v2.processes.connectors.ibm_watsonx  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.kafka  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.lancedb  # noqa: F401
 import unstructured_ingest.v2.processes.connectors.qdrant  # noqa: F401
@@ -121,4 +122,5 @@ add_source_entry(source_type=DISCORD_CONNECTOR_TYPE, entry=discord_source_entry)
 add_destination_entry(destination_type=REDIS_CONNECTOR_TYPE, entry=redis_destination_entry)
 
 add_source_entry(source_type=JIRA_CONNECTOR_TYPE, entry=jira_source_entry)
+
 add_source_entry(source_type=ZENDESK_CONNECTOR_TYPE, entry=zendesk_source_entry)

unstructured_ingest/v2/processes/connectors/ibm_watsonx/__init__.py

@@ -0,0 +1,10 @@
+from __future__ import annotations
+
+from unstructured_ingest.v2.processes.connector_registry import add_destination_entry
+
+from .ibm_watsonx_s3 import CONNECTOR_TYPE as IBM_WATSONX_S3_CONNECTOR_TYPE
+from .ibm_watsonx_s3 import ibm_watsonx_s3_destination_entry
+
+add_destination_entry(
+    destination_type=IBM_WATSONX_S3_CONNECTOR_TYPE, entry=ibm_watsonx_s3_destination_entry
+)

unstructured_ingest/v2/processes/connectors/ibm_watsonx/ibm_watsonx_s3.py

@@ -0,0 +1,301 @@
+import logging
+import time
+from contextlib import contextmanager
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import TYPE_CHECKING, Any, Generator, Optional, Tuple
+
+import pandas as pd
+from pydantic import Field, Secret
+
+from unstructured_ingest.utils.data_prep import get_data_df
+from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.v2.constants import RECORD_ID_LABEL
+from unstructured_ingest.v2.errors import ProviderError, UserAuthError, UserError
+from unstructured_ingest.v2.interfaces import (
+    AccessConfig,
+    ConnectionConfig,
+    FileData,
+    UploaderConfig,
+)
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.processes.connector_registry import (
+    DestinationRegistryEntry,
+)
+from unstructured_ingest.v2.processes.connectors.sql.sql import (
+    SQLUploader,
+    SQLUploadStager,
+    SQLUploadStagerConfig,
+)
+
+if TYPE_CHECKING:
+    from pyarrow import Table as ArrowTable
+    from pyiceberg.catalog.rest import RestCatalog
+    from pyiceberg.table import Table, Transaction
+
+CONNECTOR_TYPE = "ibm_watsonx_s3"
+
+DEFAULT_IBM_CLOUD_AUTH_URL = "https://iam.cloud.ibm.com/identity/token"
+DEFAULT_ICEBERG_URI_PATH = "/mds/iceberg"
+DEFAULT_ICEBERG_CATALOG_TYPE = "rest"
+
+
+class IcebergCommitFailedException(Exception):
+    """Failed to commit changes to the iceberg table."""
+
+
+class IbmWatsonxAccessConfig(AccessConfig):
+    iam_api_key: str = Field(description="IBM IAM API Key")
+    access_key_id: str = Field(description="Cloud Object Storage HMAC Access Key ID")
+    secret_access_key: str = Field(description="Cloud Object Storage HMAC Secret Access Key")
+
+
+class IbmWatsonxConnectionConfig(ConnectionConfig):
+    access_config: Secret[IbmWatsonxAccessConfig]
+    iceberg_endpoint: str = Field(description="Iceberg REST endpoint")
+    object_storage_endpoint: str = Field(description="Cloud Object Storage public endpoint")
+    object_storage_region: str = Field(description="Cloud Object Storage region")
+    catalog: str = Field(description="Catalog name")
+
+    _bearer_token: Optional[dict[str, Any]] = None
+
+    @property
+    def iceberg_url(self) -> str:
+        return f"https://{self.iceberg_endpoint.strip('/')}{DEFAULT_ICEBERG_URI_PATH}"
+
+    @property
+    def object_storage_url(self) -> str:
+        return f"https://{self.object_storage_endpoint.strip('/')}"
+
+    @property
+    def bearer_token(self) -> str:
+        # Add 60 seconds to deal with edge cases where the token expires before the request is made
+        timestamp = int(time.time()) + 60
+        if self._bearer_token is None or self._bearer_token.get("expiration", 0) <= timestamp:
+            self._bearer_token = self.generate_bearer_token()
+        return self._bearer_token["access_token"]
+
+    @requires_dependencies(["httpx"], extras="ibm-watsonx-s3")
+    def wrap_error(self, e: Exception) -> Exception:
+        import httpx
+
+        if not isinstance(e, httpx.HTTPStatusError):
+            logger.error(f"Unhandled exception from IBM watsonx.data connector: {e}", exc_info=True)
+            return e
+        url = e.request.url
+        response_code = e.response.status_code
+        if response_code == 401:
+            logger.error(
+                f"Failed to authenticate IBM watsonx.data user {url}, status code {response_code}"
+            )
+            return UserAuthError(e)
+        if response_code == 403:
+            logger.error(
+                f"Given IBM watsonx.data user is not authorized {url}, status code {response_code}"
+            )
+            return UserAuthError(e)
+        if 400 <= response_code < 500:
+            logger.error(
+                f"Request to {url} failed"
+                f"in IBM watsonx.data connector, status code {response_code}"
+            )
+            return UserError(e)
+        if response_code > 500:
+            logger.error(
+                f"Request to {url} failed"
+                f"in IBM watsonx.data connector, status code {response_code}"
+            )
+            return ProviderError(e)
+        logger.error(f"Unhandled exception from IBM watsonx.data connector: {e}", exc_info=True)
+        return e
+
+    @requires_dependencies(["httpx"], extras="ibm-watsonx-s3")
+    def generate_bearer_token(self) -> dict[str, Any]:
+        import httpx
+
+        headers = {
+            "Content-Type": "application/x-www-form-urlencoded",
+            "Accept": "application/json",
+        }
+        data = {
+            "grant_type": "urn:ibm:params:oauth:grant-type:apikey",
+            "apikey": self.access_config.get_secret_value().iam_api_key,
+        }
+
+        logger.info("Generating IBM IAM Bearer Token")
+        try:
+            response = httpx.post(DEFAULT_IBM_CLOUD_AUTH_URL, headers=headers, data=data)
+            response.raise_for_status()
+        except Exception as e:
+            raise self.wrap_error(e)
+        return response.json()
+
+    def get_catalog_config(self) -> dict[str, Any]:
+        return {
+            "name": self.catalog,
+            "type": DEFAULT_ICEBERG_CATALOG_TYPE,
+            "uri": self.iceberg_url,
+            "token": self.bearer_token,
+            "warehouse": self.catalog,
+            "s3.endpoint": self.object_storage_url,
+            "s3.access-key-id": self.access_config.get_secret_value().access_key_id,
+            "s3.secret-access-key": self.access_config.get_secret_value().secret_access_key,
+            "s3.region": self.object_storage_region,
+        }
+
+    @requires_dependencies(["pyiceberg"], extras="ibm-watsonx-s3")
+    @contextmanager
+    def get_catalog(self) -> Generator["RestCatalog", None, None]:
+        from pyiceberg.catalog import load_catalog
+
+        try:
+            catalog_config = self.get_catalog_config()
+            catalog = load_catalog(**catalog_config)
+        except Exception as e:
+            logger.error(f"Failed to connect to catalog '{self.catalog}': {e}", exc_info=True)
+            raise ProviderError(f"Failed to connect to catalog '{self.catalog}': {e}")
+
+        yield catalog
+
+
+@dataclass
+class IbmWatsonxUploadStagerConfig(SQLUploadStagerConfig):
+    pass
+
+
+@dataclass
+class IbmWatsonxUploadStager(SQLUploadStager):
+    upload_stager_config: IbmWatsonxUploadStagerConfig = field(
+        default_factory=IbmWatsonxUploadStagerConfig
+    )
+
+
+class IbmWatsonxUploaderConfig(UploaderConfig):
+    namespace: str = Field(description="Namespace name")
+    table: str = Field(description="Table name")
+    max_retries: int = Field(
+        default=5, description="Maximum number of retries to upload data", ge=2, le=10
+    )
+    record_id_key: str = Field(
+        default=RECORD_ID_LABEL,
+        description="Searchable key to find entries for the same record on previous runs",
+    )
+
+    @property
+    def table_identifier(self) -> Tuple[str, str]:
+        return (self.namespace, self.table)
+
+
+@dataclass
+class IbmWatsonxUploader(SQLUploader):
+    connection_config: IbmWatsonxConnectionConfig
+    upload_config: IbmWatsonxUploaderConfig
+    connector_type: str = CONNECTOR_TYPE
+
+    def precheck(self) -> None:
+        with self.connection_config.get_catalog() as catalog:
+            if not catalog.namespace_exists(self.upload_config.namespace):
+                raise UserError(f"Namespace '{self.upload_config.namespace}' does not exist")
+            if not catalog.table_exists(self.upload_config.table_identifier):
+                raise UserError(
+                    f"Table '{self.upload_config.table}' does not exist in namespace '{self.upload_config.namespace}'"  # noqa: E501
+                )
+
+    @contextmanager
+    def get_table(self) -> Generator["Table", None, None]:
+        with self.connection_config.get_catalog() as catalog:
+            table = catalog.load_table(self.upload_config.table_identifier)
+            yield table
+
+    def get_table_columns(self) -> list[str]:
+        if self._columns is None:
+            with self.get_table() as table:
+                self._columns = table.schema().column_names
+        return self._columns
+
+    def can_delete(self) -> bool:
+        return self.upload_config.record_id_key in self.get_table_columns()
+
+    @requires_dependencies(["pyarrow"], extras="ibm-watsonx-s3")
+    def _df_to_arrow_table(self, df: pd.DataFrame) -> "ArrowTable":
+        import pyarrow as pa
+
+        # Iceberg will automatically fill missing columns with nulls
+        # Iceberg will throw an error if the DataFrame column has only null values
+        # because it can't infer the type of the column and match it with the table schema
+        return pa.Table.from_pandas(self._fit_to_schema(df, add_missing_columns=False))
+
+    @requires_dependencies(["pyiceberg"], extras="ibm-watsonx-s3")
+    def _delete(self, transaction: "Transaction", identifier: str) -> None:
+        from pyiceberg.expressions import EqualTo
+
+        if self.can_delete():
+            transaction.delete(delete_filter=EqualTo(self.upload_config.record_id_key, identifier))
+        else:
+            logger.warning(
+                f"Table doesn't contain expected "
+                f"record id column "
+                f"{self.upload_config.record_id_key}, skipping delete"
+            )
+
+    @requires_dependencies(["pyiceberg", "tenacity"], extras="ibm-watsonx-s3")
+    def upload_data_table(
+        self, table: "Table", data_table: "ArrowTable", file_data: FileData
+    ) -> None:
+        from pyiceberg.exceptions import CommitFailedException
+        from tenacity import (
+            before_log,
+            retry,
+            retry_if_exception_type,
+            stop_after_attempt,
+            wait_random,
+        )
+
+        @retry(
+            stop=stop_after_attempt(self.upload_config.max_retries),
+            wait=wait_random(),
+            retry=retry_if_exception_type(IcebergCommitFailedException),
+            before=before_log(logger, logging.DEBUG),
+            reraise=True,
+        )
+        def _upload_data_table(table: "Table", data_table: "ArrowTable", file_data: FileData):
+            try:
+                with table.transaction() as transaction:
+                    self._delete(transaction, file_data.identifier)
+                    transaction.append(data_table)
+            except CommitFailedException as e:
+                table.refresh()
+                logger.debug(e)
+                raise IcebergCommitFailedException(e)
+            except Exception as e:
+                raise ProviderError(f"Failed to upload data to table: {e}")
+
+        try:
+            return _upload_data_table(table, data_table, file_data)
+        except ProviderError:
+            raise
+        except Exception as e:
+            raise ProviderError(f"Failed to upload data to table: {e}")
+
+    def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:
+        data_table = self._df_to_arrow_table(df)
+
+        with self.get_table() as table:
+            self.upload_data_table(table, data_table, file_data)
+
+    def run_data(self, data: list[dict], file_data: FileData, **kwargs: Any) -> None:
+        df = pd.DataFrame(data)
+        self.upload_dataframe(df=df, file_data=file_data)
+
+    def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
+        df = get_data_df(path=path)
+        self.upload_dataframe(df=df, file_data=file_data)
+
+
+ibm_watsonx_s3_destination_entry = DestinationRegistryEntry(
+    connection_config=IbmWatsonxConnectionConfig,
+    uploader=IbmWatsonxUploader,
+    uploader_config=IbmWatsonxUploaderConfig,
+    upload_stager=IbmWatsonxUploadStager,
+    upload_stager_config=IbmWatsonxUploadStagerConfig,
+)

unstructured_ingest/v2/processes/connectors/sql/sql.py

@@ -323,7 +323,7 @@ class SQLUploader(Uploader):
             output.append(tuple(parsed))
         return output
 
-    def _fit_to_schema(self, df: pd.DataFrame) -> pd.DataFrame:
+    def _fit_to_schema(self, df: pd.DataFrame, add_missing_columns: bool = True) -> pd.DataFrame:
         table_columns = self.get_table_columns()
         columns = set(df.columns)
         schema_fields = set(table_columns)
@@ -335,7 +335,7 @@ class SQLUploader(Uploader):
                 "Following columns will be dropped to match the table's schema: "
                 f"{', '.join(columns_to_drop)}"
             )
-        if missing_columns:
+        if missing_columns and add_missing_columns:
             logger.info(
                 "Following null filled columns will be added to match the table's schema:"
                 f" {', '.join(missing_columns)} "
@@ -343,8 +343,9 @@ class SQLUploader(Uploader):
 
         df = df.drop(columns=columns_to_drop)
 
-        for column in missing_columns:
-            df[column] = pd.Series()
+        if add_missing_columns:
+            for column in missing_columns:
+                df[column] = pd.Series()
         return df
 
     def upload_dataframe(self, df: pd.DataFrame, file_data: FileData) -> None:

{unstructured_ingest-0.5.19.dist-info → unstructured_ingest-0.5.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.19
+Version: 0.5.20
 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: dataclasses_json
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: pandas
 Requires-Dist: click
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: pydantic>=2.7
+Requires-Dist: pandas
 Requires-Dist: tqdm
+Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -66,16 +66,16 @@ Requires-Dist: pyairtable; extra == "airtable"
 Provides-Extra: astradb
 Requires-Dist: astrapy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: fsspec; extra == "azure"
 Requires-Dist: adlfs; extra == "azure"
+Requires-Dist: fsspec; 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"
+Requires-Dist: fsspec; extra == "box"
 Provides-Extra: chroma
 Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
@@ -86,8 +86,8 @@ Requires-Dist: atlassian-python-api; 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
@@ -98,19 +98,24 @@ Requires-Dist: duckdb; extra == "duckdb"
 Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
-Requires-Dist: gcsfs; extra == "gcs"
 Requires-Dist: bs4; extra == "gcs"
+Requires-Dist: gcsfs; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: requests; extra == "github"
 Requires-Dist: pygithub>1.58.0; extra == "github"
+Requires-Dist: requests; extra == "github"
 Provides-Extra: gitlab
 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: ibm-watsonx-s3
+Requires-Dist: httpx; extra == "ibm-watsonx-s3"
+Requires-Dist: pyarrow; extra == "ibm-watsonx-s3"
+Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
+Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
 Provides-Extra: jira
 Requires-Dist: atlassian-python-api; extra == "jira"
 Provides-Extra: kafka
@@ -125,22 +130,22 @@ Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
 Requires-Dist: networkx; extra == "neo4j"
-Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
-Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
+Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: bs4; extra == "onedrive"
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
 Provides-Extra: opensearch
 Requires-Dist: opensearch-py; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Provides-Extra: pinecone
 Requires-Dist: pinecone-client>=3.7.1; extra == "pinecone"
 Provides-Extra: postgres
@@ -155,18 +160,18 @@ Provides-Extra: s3
 Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: fsspec; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
 Provides-Extra: salesforce
 Requires-Dist: simple-salesforce; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: fsspec; extra == "sftp"
 Requires-Dist: paramiko; extra == "sftp"
+Requires-Dist: fsspec; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -178,17 +183,17 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
 Provides-Extra: vastdb
 Requires-Dist: pyarrow; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: ibis; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: bs4; extra == "zendesk"
-Requires-Dist: httpx; extra == "zendesk"
 Requires-Dist: aiofiles; extra == "zendesk"
+Requires-Dist: httpx; extra == "zendesk"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
@@ -204,8 +209,8 @@ Provides-Extra: openai
 Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: boto3; extra == "bedrock"
 Requires-Dist: aioboto3; extra == "bedrock"
+Requires-Dist: boto3; extra == "bedrock"
 Provides-Extra: togetherai
 Requires-Dist: together; extra == "togetherai"
 Dynamic: author

{unstructured_ingest-0.5.19.dist-info → unstructured_ingest-0.5.20.dist-info}/RECORD

@@ -93,10 +93,12 @@ test/unit/v2/connectors/test_confluence.py,sha256=lN6nnU5qOtmsjIGcz65roepm76w4vP
 test/unit/v2/connectors/test_jira.py,sha256=XEBBDSdNZWUVO5JbpiSsjazJYmbLsgXUOW-APqPRKLg,12113
 test/unit/v2/connectors/databricks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/connectors/databricks/test_volumes_table.py,sha256=-R_EJHqv1BseGRK9VRAZhF-2EXA64LAlhycoyIu556U,1078
+test/unit/v2/connectors/ibm_watsonx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+test/unit/v2/connectors/ibm_watsonx/test_ibm_watsonx_s3.py,sha256=gvgF9vCA_cPQVS_IC6VFvnP4ojFVKOH7eorM6k5VR84,14518
 test/unit/v2/connectors/motherduck/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/connectors/motherduck/test_base.py,sha256=f3W7hppEZ904_I_fKax-5LVDp-0yj04DjF1ccZ4k5O8,2503
 test/unit/v2/connectors/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-test/unit/v2/connectors/sql/test_sql.py,sha256=51-AKUBxw6ThO68bjenLopUUuxM88YZb2rMUV8L6YwY,2464
+test/unit/v2/connectors/sql/test_sql.py,sha256=wA5LvLtmaCi-8YDOd515j3YnP0_E4qi7z50NFXBn75g,4634
 test/unit/v2/embedders/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/embedders/test_bedrock.py,sha256=HMaweO_v_9Y1SE2m5QImXP73cb26vNTUfc1onTBa1-g,1074
 test/unit/v2/embedders/test_huggingface.py,sha256=TOHUKC7hAadl6XTotr8UqOCq28kbQxOIkPSrMxr2PLU,1546
@@ -111,7 +113,7 @@ test/unit/v2/partitioners/test_partitioner.py,sha256=iIYg7IpftV3LusoO4H8tr1IHY1U
 test/unit/v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/utils/data_generator.py,sha256=UoYVNjG4S4wlaA9gceQ82HIpF9_6I1UTHD1_GrQBHp0,973
 unstructured_ingest/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
-unstructured_ingest/__version__.py,sha256=YeBJuoTNGo0rz_5lKoO5e3ooyBOI71QLt4fdSp1KO_c,43
+unstructured_ingest/__version__.py,sha256=BCszjb86jsmMjfakEG2zLAZFKHpLYTR2k5TCe7RzaBc,43
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -426,7 +428,7 @@ unstructured_ingest/v2/processes/embedder.py,sha256=gvlCQDsbQVgcp-2f0Qq4RiFbcr8g
 unstructured_ingest/v2/processes/filter.py,sha256=kjUmMw2SDq2bme0JCAOxs6cJriIG6Ty09KOznS-xz08,2145
 unstructured_ingest/v2/processes/partitioner.py,sha256=HxopDSbovLh_1epeGeVtuWEX7v5KG35BowwKIJ_y4e8,9910
 unstructured_ingest/v2/processes/uncompress.py,sha256=Z_XfsITGdyaRwhtNUc7bMj5Y2jLuBge8KoK4nxhqKag,2425
-unstructured_ingest/v2/processes/connectors/__init__.py,sha256=ebLvZes84qRx4eS20SkvlVH6WIIM76hifyUgkUJ-dfg,6588
+unstructured_ingest/v2/processes/connectors/__init__.py,sha256=l4Xq4AuzRMTqUv5TU7cE1NbhGCka4SFJFZwG1FoVotE,6666
 unstructured_ingest/v2/processes/connectors/airtable.py,sha256=eeZJe-bBNxt5Sa-XEFCdcGeJCguJU5WN2Mv9kLp5dVQ,8917
 unstructured_ingest/v2/processes/connectors/astradb.py,sha256=5xc5pWFicE_-2BV38oK-nnzAMI2EzF-q8XAqQ3qPUR8,18249
 unstructured_ingest/v2/processes/connectors/azure_ai_search.py,sha256=ngPDpU0oZ6m5sxIlB6u5ebQpqCS_SJ-_amCC1KQ03EQ,11529
@@ -477,6 +479,8 @@ unstructured_ingest/v2/processes/connectors/fsspec/gcs.py,sha256=nlDSKHs8mbXCY5B
 unstructured_ingest/v2/processes/connectors/fsspec/s3.py,sha256=qO4WDZPoxmYMbUkaSvrxXaLn3UxzyMVhpj5wVyXqmi4,6623
 unstructured_ingest/v2/processes/connectors/fsspec/sftp.py,sha256=ZimcBJL-Har7GOESb9blzDb8pzPZcmh16YvvHYxYkJM,6373
 unstructured_ingest/v2/processes/connectors/fsspec/utils.py,sha256=jec_Qfe2hbfahBuY-u8FnvHuv933AI5HwPFjOL3kEEY,456
+unstructured_ingest/v2/processes/connectors/ibm_watsonx/__init__.py,sha256=EMG7lyThrYO8W7y3DIxGgNNXtbpdeAdvLd0m4tpO-Io,377
+unstructured_ingest/v2/processes/connectors/ibm_watsonx/ibm_watsonx_s3.py,sha256=zaj5MVsM-uf7IRgZGg7QwRtzjtTM1gCYuqji61TrqWk,11562
 unstructured_ingest/v2/processes/connectors/kafka/__init__.py,sha256=mQJ9Ex-QCfhz-BB5YWTfbPf7xGLd1i7FpjRr0ukbhNw,754
 unstructured_ingest/v2/processes/connectors/kafka/cloud.py,sha256=GdAeQ8Uz-6v1C5byBHtjfevVfbzW3obScBFFLRTb0ps,3441
 unstructured_ingest/v2/processes/connectors/kafka/kafka.py,sha256=UfS41jzV9VxekS6AwWHhURJmJ7RUAw5iiIrj75BWrXQ,10255
@@ -564,7 +568,7 @@ unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py,sha25
 unstructured_ingest/v2/processes/connectors/sql/postgres.py,sha256=BATfX1PQGT2kl8jAbdNKXTojYKJxh3pJV9-h3OBnHGo,5124
 unstructured_ingest/v2/processes/connectors/sql/singlestore.py,sha256=OPBDQ2c_5KjWHEFfqXxf3pQ2tWC-N4MtslMulMgP1Wc,5503
 unstructured_ingest/v2/processes/connectors/sql/snowflake.py,sha256=0hfiX_u7V38k_RfoeDmXJp8WIHZ19ilIHnrgZVSleKw,9270
-unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=F5PPUxt2W8JaAQGfz5Od0FvKqYa15RfwMIlnrdJu1nk,15317
+unstructured_ingest/v2/processes/connectors/sql/sql.py,sha256=wtVK6CHrQ4McwsPifUoa7KKaY-v0cjDZJetASSAaSIA,15415
 unstructured_ingest/v2/processes/connectors/sql/sqlite.py,sha256=PRjN_S7UQv0k4ZpSyclW1AJrsrugyxbR-GoOrHvBpks,5200
 unstructured_ingest/v2/processes/connectors/sql/vastdb.py,sha256=0rxrb1ByXIefB9umzMTEJbpvzdTttXHK5DjRY97-GG8,9618
 unstructured_ingest/v2/processes/connectors/weaviate/__init__.py,sha256=NMiwnVWan69KnzVELvaqX34tMhCytIa-C8EDsXVKsEo,856
@@ -577,9 +581,9 @@ unstructured_ingest/v2/processes/connectors/zendesk/client.py,sha256=DDAYQB7catK
 unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py,sha256=R8SXYkRhVUoWEHdGCt2CzcTxxuFundw_0GlGZ34YmbM,8987
 unstructured_ingest/v2/processes/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/processes/utils/blob_storage.py,sha256=EWvK4HRYubr9i1UyMhv5cU9u0UzVkCDC_BIm4Uxab7Y,964
-unstructured_ingest-0.5.19.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.5.19.dist-info/METADATA,sha256=6veKDuElp9klfZfEzZIFIwPCchckH6Mf04qCc0ogN7M,8465
-unstructured_ingest-0.5.19.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-unstructured_ingest-0.5.19.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.5.19.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.5.19.dist-info/RECORD,,
+unstructured_ingest-0.5.20.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.5.20.dist-info/METADATA,sha256=S2Yr62sVeW0csT-QRyonnokiHFvvH0FAwQ2x02BqAeM,8697
+unstructured_ingest-0.5.20.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+unstructured_ingest-0.5.20.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.5.20.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.5.20.dist-info/RECORD,,