standardize exception classes across the repo (#583)

the purpose is to standardize exception classes across the repo and make
downstream services easier to handle exceptions. downstream services
only need to catch unstructured-ingest.error.UnstructuredIngestError,
because any exception thrown from ingest is a subclass of
UnstructuredIngestError. downstream services no longer need to
wrap_error

Author: bryan-unstructured

CHANGELOG.md

@@ -1,38 +1,42 @@
+## 1.2.10
+
+* **o11y: standardize exception classes across the repo**:
+
 ## 1.2.9
 
 **Fix**: enable s3fs cache_regions for bucket region detection
 
 ## 1.2.8
 
-**Fix**: Fix artifact url
+**Fix: Fix artifact url**
 
 ## 1.2.7
 
-**Fix**: Fix artifact url
+**Fix: Fix artifact url**
 
 ## 1.2.6
 
 **Publish to both pypi and artifacts**
 
 ## 1.2.5
 
-**Fix**: move S3 ambient_credentials out of AccessConfig
+**Fix: move S3 ambient_credentials out of AccessConfig**
 
 ## 1.2.4
 
-**Fix**: properly handle Together API 5xx errors as ProviderError instead of UserError
+**Fix: properly handle Together API 5xx errors as ProviderError instead of UserError**
 
 ## 1.2.3
 
-* **Feature**: allow environment credentials for S3
+* **Feature: allow environment credentials for S3**
 
 ## 1.2.2
 
-* **Fix**: prevent S3 path conflicts using tempfile for directory isolation
+* **Fix: prevent S3 path conflicts using tempfile for directory isolation**
 
 ## 1.2.1
 
-* **Fix**: Embeddings are properly assigned when embedding in batches
+* **Fix: Embeddings are properly assigned when embedding in batches**
 
 ## 1.2.0
 * **Drop Python 3.9 support**

test/integration/connectors/databricks/test_volumes_native.py

@@ -22,7 +22,7 @@
 )
 from test.integration.utils import requires_env
 from unstructured_ingest.data_types.file_data import FileData, SourceIdentifiers
-from unstructured_ingest.errors_v2 import UserAuthError, UserError
+from unstructured_ingest.error import UserAuthError, UserError
 from unstructured_ingest.processes.connectors.databricks.volumes_native import (
     CONNECTOR_TYPE,
     DatabricksNativeVolumesAccessConfig,

test/integration/connectors/discord/test_discord.py

@@ -13,7 +13,7 @@
     source_filedata_display_name_set_check,
 )
 from test.integration.utils import requires_env
-from unstructured_ingest.error import SourceConnectionError
+from unstructured_ingest.error import UserAuthError, ValueError
 from unstructured_ingest.processes.connectors.discord import (
     CONNECTOR_TYPE,
     DiscordAccessConfig,
@@ -76,7 +76,7 @@ def test_discord_source_precheck_fail_no_token():
 
     connection_config = DiscordConnectionConfig(access_config=DiscordAccessConfig(token=""))
     indexer = DiscordIndexer(connection_config=connection_config, index_config=indexer_config)
-    with pytest.raises(SourceConnectionError):
+    with pytest.raises(UserAuthError):
         indexer.precheck()
 
 
@@ -89,5 +89,5 @@ def test_discord_source_precheck_fail_no_channels():
         access_config=DiscordAccessConfig(token=get_env_data().token)
     )
     indexer = DiscordIndexer(connection_config=connection_config, index_config=indexer_config)
-    with pytest.raises(SourceConnectionError):
+    with pytest.raises(ValueError):
         indexer.precheck()

test/integration/connectors/test_s3.py

@@ -19,7 +19,7 @@
 )
 from test.integration.utils import requires_env
 from unstructured_ingest.data_types.file_data import FileData, SourceIdentifiers
-from unstructured_ingest.errors_v2 import UserAuthError, UserError
+from unstructured_ingest.error import UserAuthError, UserError
 from unstructured_ingest.processes.connectors.fsspec.s3 import (
     CONNECTOR_TYPE,
     S3AccessConfig,

test/integration/connectors/test_sharepoint.py

@@ -376,7 +376,7 @@ def _create_indexer(client_cred=None, site=None, path=None):
 )
 async def test_sharepoint_precheck_error_scenarios(indexer_factory, error_scenario, expected_error):
     """Parametrized test for different SharePoint precheck error scenarios."""
-    from unstructured_ingest.errors_v2 import UserAuthError, UserError
+    from unstructured_ingest.error import UserAuthError, UserError
 
     error_class_map = {"UserAuthError": UserAuthError, "UserError": UserError}
 
@@ -427,7 +427,7 @@ async def test_sharepoint_precheck_insufficient_permissions(
     base_sharepoint_config,
 ):
     """Test precheck with credentials that have insufficient permissions."""
-    from unstructured_ingest.errors_v2 import UserAuthError
+    from unstructured_ingest.error import UserAuthError
 
     access_config = SharepointAccessConfig(client_cred=insufficient_perms_config.client_cred)
     connection_config = SharepointConnectionConfig(

test/integration/connectors/test_zendesk.py

@@ -10,7 +10,7 @@
     source_filedata_display_name_set_check,
 )
 from test.integration.utils import requires_env
-from unstructured_ingest.errors_v2 import UserAuthError
+from unstructured_ingest.error import UserAuthError
 from unstructured_ingest.processes.connectors.zendesk.zendesk import (
     CONNECTOR_TYPE,
     ZendeskAccessConfig,

test/integration/connectors/utils/validation/source.py

@@ -168,14 +168,14 @@ def run_expected_download_files_validation(
 
 def run_directory_structure_validation(expected_output_dir: Path, download_files: list[str]):
     s3_keys_file = expected_output_dir / "expected_s3_keys.json"
-    
+
     if s3_keys_file.exists():
         with s3_keys_file.open("r") as f:
             s3_keys = json.load(f)["s3_keys"]
-        
+
         expected_filenames = {Path(s3_key).name for s3_key in s3_keys}
         actual_filenames = {Path(download_file).name for download_file in download_files}
-        
+
         assert expected_filenames == actual_filenames, (
             f"Expected filenames: {sorted(expected_filenames)}, "
             f"Got filenames: {sorted(actual_filenames)}"

test/integration/connectors/weaviate/test_cloud.py

@@ -1,7 +1,7 @@
 import pytest
-from pydantic import ValidationError
 
 from test.integration.connectors.utils.constants import DESTINATION_TAG, VECTOR_DB_TAG
+from unstructured_ingest.error import ValueError
 from unstructured_ingest.processes.connectors.weaviate.cloud import (
     CONNECTOR_TYPE,
     CloudWeaviateAccessConfig,
@@ -11,7 +11,7 @@
 
 @pytest.mark.tags(CONNECTOR_TYPE, DESTINATION_TAG, VECTOR_DB_TAG)
 def test_weaviate_failing_connection_config():
-    with pytest.raises(ValidationError):
+    with pytest.raises(ValueError):
         CloudWeaviateConnectionConfig(
             access_config=CloudWeaviateAccessConfig(api_key="my key", password="password"),
             username="username",

test/integration/embedders/test_bedrock.py

@@ -15,7 +15,7 @@
     BedrockEmbeddingConfig,
     BedrockEmbeddingEncoder,
 )
-from unstructured_ingest.errors_v2 import UserAuthError, UserError
+from unstructured_ingest.error import UserAuthError, UserError
 from unstructured_ingest.processes.embedder import Embedder, EmbedderConfig
 
 

test/integration/embedders/test_octoai.py

@@ -15,7 +15,7 @@
     OctoAiEmbeddingConfig,
     OctoAIEmbeddingEncoder,
 )
-from unstructured_ingest.errors_v2 import UserAuthError, UserError
+from unstructured_ingest.error import UserAuthError, UserError
 from unstructured_ingest.processes.embedder import Embedder, EmbedderConfig
 
 API_KEY = "OCTOAI_API_KEY"