unstructured-ingest 0.6.0__py3-none-any.whl → 0.6.2__py3-none-any.whl

unstructured_ingest/__version__.py

@@ -1 +1 @@
-__version__ = "0.6.0"  # pragma: no cover
+__version__ = "0.6.2"  # pragma: no cover

unstructured_ingest/v2/processes/chunker.py

@@ -6,6 +6,7 @@ from typing import Any, Optional
 from pydantic import BaseModel, Field, SecretStr
 
 from unstructured_ingest.utils.chunking import assign_and_map_hash_ids
+from unstructured_ingest.utils.data_prep import get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.interfaces.process import BaseProcess
 from unstructured_ingest.v2.logger import logger
@@ -92,9 +93,11 @@ class Chunker(BaseProcess, ABC):
     @requires_dependencies(dependencies=["unstructured"])
     def run(self, elements_filepath: Path, **kwargs: Any) -> list[dict]:
         from unstructured.chunking import dispatch
-        from unstructured.staging.base import elements_from_json
+        from unstructured.staging.base import elements_from_dicts
 
-        elements = elements_from_json(filename=str(elements_filepath))
+        element_dicts = get_json_data(elements_filepath)
+
+        elements = elements_from_dicts(element_dicts=element_dicts)
         if not elements:
             return [e.to_dict() for e in elements]
         local_chunking_strategies = ("basic", "by_title")

unstructured_ingest/v2/processes/connectors/assets/databricks_delta_table_schema.sql

@@ -0,0 +1,10 @@
+CREATE TABLE elements (
+    id STRING NOT NULL PRIMARY KEY,
+    record_id STRING NOT NULL,
+    element_id STRING NOT NULL,
+    text STRING,
+    embeddings ARRAY<FLOAT>,
+    type STRING,
+    metadata VARIANT
+);
+

unstructured_ingest/v2/processes/connectors/databricks/volumes.py

@@ -5,7 +5,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generator, Optional
 from uuid import NAMESPACE_DNS, uuid5
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, Secret
 
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.errors import (
@@ -61,12 +61,14 @@ class DatabricksVolumesAccessConfig(AccessConfig):
 
 
 class DatabricksVolumesConnectionConfig(ConnectionConfig, ABC):
+    access_config: Secret[DatabricksVolumesAccessConfig]
     host: Optional[str] = Field(
         default=None,
         description="The Databricks host URL for either the "
         "Databricks workspace endpoint or the "
         "Databricks accounts endpoint.",
     )
+    user_agent: str = "unstructuredio_oss"
 
     def wrap_error(self, e: Exception) -> Exception:
         from databricks.sdk.errors.base import DatabricksError
@@ -94,11 +96,14 @@ class DatabricksVolumesConnectionConfig(ConnectionConfig, ABC):
     @requires_dependencies(dependencies=["databricks.sdk"], extras="databricks-volumes")
     def get_client(self) -> "WorkspaceClient":
         from databricks.sdk import WorkspaceClient
+        from databricks.sdk.core import Config
 
-        return WorkspaceClient(
+        config = Config(
             host=self.host,
             **self.access_config.get_secret_value().model_dump(),
-        )
+        ).with_user_agent_extra("PyDatabricksSdk", self.user_agent)
+
+        return WorkspaceClient(config=config)
 
 
 class DatabricksVolumesIndexerConfig(IndexerConfig, DatabricksPathMixin):

unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py

@@ -1,14 +1,20 @@
+import json
 import os
-import tempfile
 from contextlib import contextmanager
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Generator, Optional
 
 from pydantic import Field
 
-from unstructured_ingest.utils.data_prep import get_data_df, write_data
-from unstructured_ingest.v2.interfaces import Uploader, UploaderConfig
+from unstructured_ingest.utils.data_prep import get_json_data, write_data
+from unstructured_ingest.v2.constants import RECORD_ID_LABEL
+from unstructured_ingest.v2.interfaces import (
+    Uploader,
+    UploaderConfig,
+    UploadStager,
+    UploadStagerConfig,
+)
 from unstructured_ingest.v2.logger import logger
 from unstructured_ingest.v2.processes.connector_registry import (
     DestinationRegistryEntry,
@@ -16,28 +22,50 @@ from unstructured_ingest.v2.processes.connector_registry import (
 from unstructured_ingest.v2.processes.connectors.databricks.volumes import DatabricksPathMixin
 from unstructured_ingest.v2.processes.connectors.sql.databricks_delta_tables import (
     DatabricksDeltaTablesConnectionConfig,
-    DatabricksDeltaTablesUploadStager,
     DatabricksDeltaTablesUploadStagerConfig,
 )
 from unstructured_ingest.v2.types.file_data import FileData
+from unstructured_ingest.v2.utils import get_enhanced_element_id
 
 CONNECTOR_TYPE = "databricks_volume_delta_tables"
 
 if TYPE_CHECKING:
-    from pandas import DataFrame
+    pass
 
 
 class DatabricksVolumeDeltaTableUploaderConfig(UploaderConfig, DatabricksPathMixin):
     database: str = Field(description="Database name", default="default")
-    table_name: str = Field(description="Table name")
+    table_name: Optional[str] = Field(description="Table name", default=None)
+
+
+class DatabricksVolumeDeltaTableStagerConfig(UploadStagerConfig):
+    pass
 
 
 @dataclass
-class DatabricksVolumeDeltaTableStager(DatabricksDeltaTablesUploadStager):
-    def write_output(self, output_path: Path, data: list[dict]) -> Path:
+class DatabricksVolumeDeltaTableStager(UploadStager):
+    upload_stager_config: DatabricksVolumeDeltaTableStagerConfig = field(
+        default_factory=DatabricksVolumeDeltaTableStagerConfig
+    )
+
+    def run(
+        self,
+        elements_filepath: Path,
+        output_dir: Path,
+        output_filename: str,
+        file_data: FileData,
+        **kwargs: Any,
+    ) -> Path:
         # To avoid new line issues when migrating from volumes into delta tables, omit indenting
         # and always write it as a json file
+        output_dir.mkdir(exist_ok=True, parents=True)
+        output_path = output_dir / output_filename
         final_output_path = output_path.with_suffix(".json")
+        data = get_json_data(path=elements_filepath)
+        for element in data:
+            element["id"] = get_enhanced_element_id(element_dict=element, file_data=file_data)
+            element[RECORD_ID_LABEL] = file_data.identifier
+            element["metadata"] = json.dumps(element.get("metadata", {}))
         write_data(path=final_output_path, data=data, indent=None)
         return final_output_path
 
@@ -49,6 +77,29 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
     connector_type: str = CONNECTOR_TYPE
     _columns: Optional[dict[str, str]] = None
 
+    def init(self, **kwargs: Any) -> None:
+        self.create_destination(**kwargs)
+
+    def create_destination(
+        self, destination_name: str = "unstructuredautocreated", **kwargs: Any
+    ) -> bool:
+        table_name = self.upload_config.table_name or destination_name
+        self.upload_config.table_name = table_name
+        connectors_dir = Path(__file__).parents[1]
+        collection_config_file = connectors_dir / "assets" / "databricks_delta_table_schema.sql"
+        with self.get_cursor() as cursor:
+            cursor.execute("SHOW TABLES")
+            table_names = [r[1] for r in cursor.fetchall()]
+            if table_name in table_names:
+                return False
+            with collection_config_file.open() as schema_file:
+                data_lines = schema_file.readlines()
+            data_lines[0] = data_lines[0].replace("elements", table_name)
+            destination_schema = "".join([line.strip() for line in data_lines])
+            logger.info(f"creating table {table_name} for user")
+            cursor.execute(destination_schema)
+            return True
+
     def precheck(self) -> None:
         with self.connection_config.get_cursor() as cursor:
             cursor.execute("SHOW CATALOGS")
@@ -68,14 +119,6 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
                         self.upload_config.database, ", ".join(databases)
                     )
                 )
-            cursor.execute(f"SHOW TABLES IN {self.upload_config.database}")
-            table_names = [r[1] for r in cursor.fetchall()]
-            if self.upload_config.table_name not in table_names:
-                raise ValueError(
-                    "Table {} not found in {}".format(
-                        self.upload_config.table_name, ", ".join(table_names)
-                    )
-                )
 
     def get_output_path(self, file_data: FileData, suffix: str = ".json") -> str:
         filename = Path(file_data.source_identifiers.filename)
@@ -98,51 +141,42 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
                 self._columns = {desc[0]: desc[1] for desc in cursor.description}
         return self._columns
 
-    def _fit_to_schema(self, df: "DataFrame", add_missing_columns: bool = True) -> "DataFrame":
-        import pandas as pd
-
-        table_columns = self.get_table_columns()
-        columns = set(df.columns)
-        schema_fields = set(table_columns.keys())
-        columns_to_drop = columns - schema_fields
-        missing_columns = schema_fields - columns
-
-        if columns_to_drop:
-            logger.info(
-                "Following columns will be dropped to match the table's schema: "
-                f"{', '.join(columns_to_drop)}"
-            )
-        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)} "
+    def can_delete(self) -> bool:
+        existing_columns = self.get_table_columns()
+        return RECORD_ID_LABEL in existing_columns
+
+    def delete_previous_content(self, file_data: FileData) -> None:
+        logger.debug(
+            f"deleting any content with metadata "
+            f"{RECORD_ID_LABEL}={file_data.identifier} "
+            f"from delta table: {self.upload_config.table_name}"
+        )
+        with self.get_cursor() as cursor:
+            cursor.execute(
+                f"DELETE FROM {self.upload_config.table_name} WHERE {RECORD_ID_LABEL} = '{file_data.identifier}'"  # noqa: E501
             )
-
-        df = df.drop(columns=columns_to_drop)
-
-        if add_missing_columns:
-            for column in missing_columns:
-                df[column] = pd.Series()
-        return df
+            results = cursor.fetchall()
+            deleted_rows = results[0][0]
+            logger.debug(f"deleted {deleted_rows} rows from table {self.upload_config.table_name}")
 
     def run(self, path: Path, file_data: FileData, **kwargs: Any) -> None:
-        with tempfile.TemporaryDirectory() as temp_dir:
-            df = get_data_df()
-            df = self._fit_to_schema(df=df)
-            temp_path = Path(temp_dir) / path.name
-            df.to_json(temp_path, orient="records", lines=False)
-            with self.get_cursor(staging_allowed_local_path=temp_dir) as cursor:
-                catalog_path = self.get_output_path(file_data=file_data)
-                logger.debug(f"uploading {path.as_posix()} to {catalog_path}")
-                cursor.execute(f"PUT '{temp_path.as_posix()}' INTO '{catalog_path}' OVERWRITE")
-                logger.debug(
-                    f"migrating content from {catalog_path} to "
-                    f"table {self.upload_config.table_name}"
-                )
-                columns = list(df.columns)
-                column_str = ", ".join(columns)
-                sql_statment = f"INSERT INTO `{self.upload_config.table_name}` ({column_str}) SELECT {column_str} FROM json.`{catalog_path}`"  # noqa: E501
-                cursor.execute(sql_statment)
+        if self.can_delete():
+            self.delete_previous_content(file_data=file_data)
+        with self.get_cursor(staging_allowed_local_path=path.parent.as_posix()) as cursor:
+            catalog_path = self.get_output_path(file_data=file_data)
+            logger.debug(f"uploading {path.as_posix()} to {catalog_path}")
+            cursor.execute(f"PUT '{path.as_posix()}' INTO '{catalog_path}' OVERWRITE")
+            logger.debug(
+                f"migrating content from {catalog_path} to "
+                f"table {self.upload_config.table_name}"
+            )
+            data = get_json_data(path=path)
+            columns = data[0].keys()
+            select_columns = ["PARSE_JSON(metadata)" if c == "metadata" else c for c in columns]
+            column_str = ", ".join(columns)
+            select_column_str = ", ".join(select_columns)
+            sql_statment = f"INSERT INTO `{self.upload_config.table_name}` ({column_str}) SELECT {select_column_str} FROM json.`{catalog_path}`"  # noqa: E501
+            cursor.execute(sql_statment)
 
 
 databricks_volumes_delta_tables_destination_entry = DestinationRegistryEntry(

{unstructured_ingest-0.6.0.dist-info → unstructured_ingest-0.6.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.6.0
+Version: 0.6.2
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,12 +22,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: opentelemetry-sdk
+Requires-Dist: click
+Requires-Dist: python-dateutil
 Requires-Dist: dataclasses_json
 Requires-Dist: pydantic>=2.7
-Requires-Dist: python-dateutil
-Requires-Dist: click
 Requires-Dist: tqdm
+Requires-Dist: opentelemetry-sdk
 Requires-Dist: pandas
 Requires-Dist: numpy
 Provides-Extra: remote
@@ -103,8 +103,8 @@ Requires-Dist: astrapy; extra == "astradb"
 Requires-Dist: pandas; extra == "astradb"
 Requires-Dist: numpy; extra == "astradb"
 Provides-Extra: azure
-Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: fsspec; extra == "azure"
+Requires-Dist: adlfs; extra == "azure"
 Requires-Dist: pandas; extra == "azure"
 Requires-Dist: numpy; extra == "azure"
 Provides-Extra: azure-ai-search
@@ -117,8 +117,8 @@ Requires-Dist: bs4; extra == "biomed"
 Requires-Dist: pandas; extra == "biomed"
 Requires-Dist: numpy; extra == "biomed"
 Provides-Extra: box
-Requires-Dist: boxfs; extra == "box"
 Requires-Dist: fsspec; extra == "box"
+Requires-Dist: boxfs; extra == "box"
 Requires-Dist: pandas; extra == "box"
 Requires-Dist: numpy; extra == "box"
 Provides-Extra: chroma
@@ -130,8 +130,8 @@ Requires-Dist: clarifai; extra == "clarifai"
 Requires-Dist: pandas; extra == "clarifai"
 Requires-Dist: numpy; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: requests; extra == "confluence"
 Requires-Dist: atlassian-python-api; extra == "confluence"
+Requires-Dist: requests; extra == "confluence"
 Requires-Dist: pandas; extra == "confluence"
 Requires-Dist: numpy; extra == "confluence"
 Provides-Extra: couchbase
@@ -161,14 +161,14 @@ Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Requires-Dist: pandas; extra == "elasticsearch"
 Requires-Dist: numpy; 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"
 Requires-Dist: pandas; extra == "gcs"
 Requires-Dist: numpy; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: requests; extra == "github"
+Requires-Dist: pygithub>1.58.0; extra == "github"
 Requires-Dist: pandas; extra == "github"
 Requires-Dist: numpy; extra == "github"
 Provides-Extra: gitlab
@@ -185,10 +185,10 @@ Requires-Dist: urllib3; extra == "hubspot"
 Requires-Dist: pandas; extra == "hubspot"
 Requires-Dist: numpy; extra == "hubspot"
 Provides-Extra: ibm-watsonx-s3
-Requires-Dist: httpx; extra == "ibm-watsonx-s3"
+Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
 Requires-Dist: pyarrow; extra == "ibm-watsonx-s3"
 Requires-Dist: pyiceberg; extra == "ibm-watsonx-s3"
-Requires-Dist: tenacity; extra == "ibm-watsonx-s3"
+Requires-Dist: httpx; extra == "ibm-watsonx-s3"
 Requires-Dist: pandas; extra == "ibm-watsonx-s3"
 Requires-Dist: numpy; extra == "ibm-watsonx-s3"
 Provides-Extra: jira
@@ -216,21 +216,21 @@ Requires-Dist: pymongo; extra == "mongodb"
 Requires-Dist: pandas; extra == "mongodb"
 Requires-Dist: numpy; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
-Requires-Dist: cymple; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
+Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: pandas; extra == "neo4j"
 Requires-Dist: numpy; extra == "neo4j"
 Provides-Extra: notion
 Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
 Requires-Dist: pandas; extra == "notion"
 Requires-Dist: numpy; extra == "notion"
 Provides-Extra: onedrive
-Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
+Requires-Dist: msal; extra == "onedrive"
 Requires-Dist: bs4; extra == "onedrive"
 Requires-Dist: pandas; extra == "onedrive"
 Requires-Dist: numpy; extra == "onedrive"
@@ -239,8 +239,8 @@ Requires-Dist: opensearch-py; extra == "opensearch"
 Requires-Dist: pandas; extra == "opensearch"
 Requires-Dist: numpy; extra == "opensearch"
 Provides-Extra: outlook
-Requires-Dist: msal; extra == "outlook"
 Requires-Dist: Office365-REST-Python-Client; extra == "outlook"
+Requires-Dist: msal; extra == "outlook"
 Requires-Dist: pandas; extra == "outlook"
 Requires-Dist: numpy; extra == "outlook"
 Provides-Extra: pinecone
@@ -269,8 +269,8 @@ Requires-Dist: s3fs; extra == "s3"
 Requires-Dist: pandas; extra == "s3"
 Requires-Dist: numpy; extra == "s3"
 Provides-Extra: sharepoint
-Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: Office365-REST-Python-Client; extra == "sharepoint"
+Requires-Dist: msal; extra == "sharepoint"
 Requires-Dist: pandas; extra == "sharepoint"
 Requires-Dist: numpy; extra == "sharepoint"
 Provides-Extra: salesforce
@@ -278,8 +278,8 @@ Requires-Dist: simple-salesforce; extra == "salesforce"
 Requires-Dist: pandas; extra == "salesforce"
 Requires-Dist: numpy; extra == "salesforce"
 Provides-Extra: sftp
-Requires-Dist: fsspec; extra == "sftp"
 Requires-Dist: paramiko; extra == "sftp"
+Requires-Dist: fsspec; extra == "sftp"
 Requires-Dist: pandas; extra == "sftp"
 Requires-Dist: numpy; extra == "sftp"
 Provides-Extra: slack
@@ -287,8 +287,8 @@ Requires-Dist: slack_sdk[optional]; extra == "slack"
 Requires-Dist: pandas; extra == "slack"
 Requires-Dist: numpy; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: pandas; extra == "snowflake"
 Requires-Dist: numpy; extra == "snowflake"
 Provides-Extra: wikipedia
@@ -312,21 +312,21 @@ Requires-Dist: singlestoredb; extra == "singlestore"
 Requires-Dist: pandas; extra == "singlestore"
 Requires-Dist: numpy; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: requests; extra == "vectara"
+Requires-Dist: httpx; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
 Requires-Dist: pandas; extra == "vectara"
 Requires-Dist: numpy; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: vastdb; extra == "vastdb"
 Requires-Dist: pandas; extra == "vastdb"
 Requires-Dist: numpy; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: httpx; extra == "zendesk"
-Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: bs4; extra == "zendesk"
+Requires-Dist: aiofiles; extra == "zendesk"
 Requires-Dist: pandas; extra == "zendesk"
 Requires-Dist: numpy; extra == "zendesk"
 Provides-Extra: embed-huggingface
@@ -356,8 +356,8 @@ Requires-Dist: tiktoken; extra == "openai"
 Requires-Dist: pandas; extra == "openai"
 Requires-Dist: numpy; extra == "openai"
 Provides-Extra: bedrock
-Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"
+Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: pandas; extra == "bedrock"
 Requires-Dist: numpy; extra == "bedrock"
 Provides-Extra: togetherai

{unstructured_ingest-0.6.0.dist-info → unstructured_ingest-0.6.2.dist-info}/RECORD

@@ -91,8 +91,6 @@ test/unit/v2/chunkers/test_chunkers.py,sha256=HSr3_lsoMw1nkDhkjO0-NOTEomRdR9oxCr
 test/unit/v2/connectors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 test/unit/v2/connectors/test_confluence.py,sha256=lN6nnU5qOtmsjIGcz65roepm76w4vPF7AmSzi9vqV78,1919
 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=WKpDKvEGalh8LYRqN9xA7CfMPOPHo_VcZbnCXdkVjho,14513
 test/unit/v2/connectors/motherduck/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -113,7 +111,7 @@ 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=i3sYvJ7iKJXkLBzcGwrQbcRp0S3NVhrYt6MAMPjU-ss,42
+unstructured_ingest/__version__.py,sha256=UDy7drjkPUljex5sEiDR3ZALQNnlcrCXwJShdKZ37Ek,42
 unstructured_ingest/error.py,sha256=qDncnJgbf5ils956RcO2CGlAKYDT5OaEM9Clv1JVTNc,1448
 unstructured_ingest/interfaces.py,sha256=7DOnDpGvUNlCoFR7UPRGmOarqH5sFtuUOO5vf8X3oTM,31489
 unstructured_ingest/logger.py,sha256=S5nSqGcABoQyeicgRnBQFjDScCaTvFVivOCvbo-laL0,4479
@@ -421,7 +419,7 @@ unstructured_ingest/v2/pipeline/steps/stage.py,sha256=_0BN2i273y_fZyvSUPOOeXv4kL
 unstructured_ingest/v2/pipeline/steps/uncompress.py,sha256=I9TyqMCUSxlf2kdPADjeH4TrUTSe0FMTlARp9QD6TsE,1763
 unstructured_ingest/v2/pipeline/steps/upload.py,sha256=6x8SUdnydR76K6cR3nUVupOACIx-XsRV3vXRlebolqg,1996
 unstructured_ingest/v2/processes/__init__.py,sha256=FaHWSCGyc7GWVnAsNEUUj7L8hT8gCVY3_hUE2VzWtUg,462
-unstructured_ingest/v2/processes/chunker.py,sha256=31-7ojsM2coIt2rMR0KOb82IxLVJfNHbqYUOsDkhxN8,5491
+unstructured_ingest/v2/processes/chunker.py,sha256=O5FN8KWym79H0dtKZvW7ABgn4bwKtaeUO8meGdjM2Yo,5609
 unstructured_ingest/v2/processes/connector_registry.py,sha256=vkEe6jpgdYtZCxMj59s5atWGgmPuxAEXRUoTt-MJ7wc,2198
 unstructured_ingest/v2/processes/embedder.py,sha256=gvlCQDsbQVgcp-2f0Qq4RiFbcr8gJwIS-imgloE-UOc,7887
 unstructured_ingest/v2/processes/filter.py,sha256=E1MLxk-XeCm3mZIuM49lJToVcSgOivmTFIZApqOEFs8,2150
@@ -454,14 +452,15 @@ unstructured_ingest/v2/processes/connectors/slack.py,sha256=vbBVCYEd741-n2v6eAXL
 unstructured_ingest/v2/processes/connectors/utils.py,sha256=TAd0hb1f291N-q7-TUe6JKSCGkhqDyo7Ij8zmliBZUc,2071
 unstructured_ingest/v2/processes/connectors/vectara.py,sha256=KUqgZ6D2KUOrW596ms-EekvQYDh-fXqBTa7KG-leXoo,12301
 unstructured_ingest/v2/processes/connectors/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+unstructured_ingest/v2/processes/connectors/assets/databricks_delta_table_schema.sql,sha256=dUZZDNkyvQXKqoAThRz3ek7zaUE2l_LAQimlG5WZhH4,211
 unstructured_ingest/v2/processes/connectors/assets/weaviate_collection_config.json,sha256=SJlIO0kXxy866tWQ8bEzvwLwflsoUMIS-OKlxMvHIuE,504
 unstructured_ingest/v2/processes/connectors/databricks/__init__.py,sha256=Oh8SwTWi66gO8BsNF6vRMoQVuegyBPPCpVozkOHEf3A,2136
-unstructured_ingest/v2/processes/connectors/databricks/volumes.py,sha256=8fg11-32If4iQGZTT9MEl1DOWZ5s3Qgj1OOzMVaHldU,7749
+unstructured_ingest/v2/processes/connectors/databricks/volumes.py,sha256=EghKdkt4nGacGxulSpjhToHOl5BRLbb3xNZpJzpWNX8,8002
 unstructured_ingest/v2/processes/connectors/databricks/volumes_aws.py,sha256=h6qDxQhWlT7H4K1CEfKag1stTiD1o97VckJZERsofqU,2970
 unstructured_ingest/v2/processes/connectors/databricks/volumes_azure.py,sha256=gjICJJwhDHBLt_L-LrMlvJ3DL1DYtwFpyMLb_zYvOIg,3755
 unstructured_ingest/v2/processes/connectors/databricks/volumes_gcp.py,sha256=Uss3XPPaq1AsqJOEy4RJgBJw2-bTjrXH2PgtVNYd2w0,3006
 unstructured_ingest/v2/processes/connectors/databricks/volumes_native.py,sha256=g1qYnIrML4TjN7rmC0MGrD5JzAprb6SymBHlEdOumz0,3113
-unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=5BArD1FkLC6wRJC0LxjXxQmYfmtF7r9Zrd8CtaGgWls,6855
+unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py,sha256=LiSb66039idaRtMnTuHjR5ZqvdmmIu3ByUgFQ1a3iZQ,8264
 unstructured_ingest/v2/processes/connectors/duckdb/__init__.py,sha256=5sVvJCWhU-YkjHIwk4W6BZCanFYK5W4xTpWtQ8xzeB4,561
 unstructured_ingest/v2/processes/connectors/duckdb/base.py,sha256=VCoQ3h289BO4A2kJKZXUVB0QOcaQif-HeRgg-xXzn10,2976
 unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py,sha256=DM4pygQAnP-dtuFEFAVeBfGt0pzrfkltteCai0GKnG0,4439
@@ -582,9 +581,9 @@ unstructured_ingest/v2/processes/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JC
 unstructured_ingest/v2/processes/utils/blob_storage.py,sha256=_I3OMdpUElQdIwVs7W9ORU1kncNaZ_nr6lbxeKE8uaU,1014
 unstructured_ingest/v2/types/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 unstructured_ingest/v2/types/file_data.py,sha256=kowOhvYy0q_-khX3IuR111AfjkdQezEfxjzK6QDH7oA,3836
-unstructured_ingest-0.6.0.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
-unstructured_ingest-0.6.0.dist-info/METADATA,sha256=NWCm69UvgcHT7J8owHmQCYkXmdfkfyCJNcW6slNzANA,14998
-unstructured_ingest-0.6.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-unstructured_ingest-0.6.0.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
-unstructured_ingest-0.6.0.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
-unstructured_ingest-0.6.0.dist-info/RECORD,,
+unstructured_ingest-0.6.2.dist-info/LICENSE.md,sha256=SxkKP_62uIAKb9mb1eH7FH4Kn2aYT09fgjKpJt5PyTk,11360
+unstructured_ingest-0.6.2.dist-info/METADATA,sha256=yUMpJD0UXDhUG1cIIpHkjn-VU2AScEaA12wLmISmG-A,14998
+unstructured_ingest-0.6.2.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+unstructured_ingest-0.6.2.dist-info/entry_points.txt,sha256=gUAAFnjFPnBgThJSEbw0N5ZjxtaKlT1s9e05_arQrNw,70
+unstructured_ingest-0.6.2.dist-info/top_level.txt,sha256=DMuDMHZRMdeay8v8Kdi855muIv92F0OkutvBCaBEW6M,25
+unstructured_ingest-0.6.2.dist-info/RECORD,,

test/unit/v2/connectors/databricks/test_volumes_table.py

@@ -1,44 +0,0 @@
-from pathlib import Path
-
-import pytest
-from pytest_mock import MockerFixture
-
-from unstructured_ingest.v2.processes.connectors.databricks.volumes_table import (
-    DatabricksVolumeDeltaTableStager,
-)
-
-
-@pytest.fixture
-def stager():
-    return DatabricksVolumeDeltaTableStager()
-
-
-@pytest.mark.parametrize(
-    ("output_path", "called_output_path"),
-    [
-        (
-            Path("/fake/path/output"),
-            Path("/fake/path/output.json"),
-        ),
-        (
-            Path("/fake/path/output.ndjson"),
-            Path("/fake/path/output.json"),
-        ),
-    ],
-)
-def test_write_output(
-    mocker: MockerFixture,
-    stager: DatabricksVolumeDeltaTableStager,
-    output_path: Path,
-    called_output_path: Path,
-):
-    data = [{"key1": "value1", "key2": "value2"}]
-
-    mock_get_data = mocker.patch(
-        "unstructured_ingest.v2.processes.connectors.databricks.volumes_table.write_data",
-        return_value=None,
-    )
-
-    stager.write_output(output_path, data)
-
-    mock_get_data.assert_called_once_with(path=called_output_path, data=data, indent=None)