feat: improve PDF validation error handling with FileValidationError … (#280)

…base class

Author: CyMule

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.37.3
+
+### Enhancements
+* Improve PDF validation error handling by introducing FileValidationError base class for better error abstraction
+
+### Features
+
+### Fixes
+* Replace RequestError with PDFValidationError for invalid PDF files to provide more accurate error context
+
 ## 0.37.0
 
 ### Enhancements

_test_unstructured_client/unit/test_split_pdf_hook.py

@@ -8,7 +8,6 @@
 from unittest.mock import MagicMock, patch
 
 import httpx
-from httpx import RequestError
 import pytest
 import requests
 from requests_toolbelt import MultipartDecoder
@@ -467,8 +466,8 @@ def test_unit_get_split_pdf_cache_tmp_data_dir_uses_dir_from_form_data(mock_path
     assert result == str(Path(mock_dir).resolve())
 
 
-def test_before_request_raises_request_error_when_pdf_check_fails():
-    """Test that before_request raises RequestError when pdf_utils.check_pdf throws PDFValidationError."""
+def test_before_request_raises_pdf_validation_error_when_pdf_check_fails():
+    """Test that before_request raises PDFValidationError when pdf_utils.check_pdf throws PDFValidationError."""
     hook = SplitPdfHook()
 
     # Initialize the hook with a mock client
@@ -514,13 +513,12 @@ def test_before_request_raises_request_error_when_pdf_check_fails():
         mock_check_pdf.side_effect = pdf_utils.PDFValidationError(error_message)
         mock_get_base_url.return_value = "http://localhost:8888"
 
-        # Call the method under test and verify it raises RequestError
-        with pytest.raises(RequestError) as exc_info:
+        # Call the method under test and verify it raises PDFValidationError
+        with pytest.raises(pdf_utils.PDFValidationError) as exc_info:
             hook.before_request(mock_hook_ctx, mock_request)
 
-        # Verify the exception has the correct message and request object
+        # Verify the exception has the correct message
         assert str(exc_info.value) == error_message
-        assert exc_info.value.request == mock_request
 
         # Verify that the mocked functions were called as expected
         mock_get_fields.assert_called_once_with(mock_request)

gen.yaml

@@ -14,7 +14,7 @@ generation:
     oAuth2ClientCredentialsEnabled: false
     oAuth2PasswordEnabled: false
 python:
-  version: 0.37.2
+  version: 0.37.3
   additionalDependencies:
     dev:
       deepdiff: '>=6.0'

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "unstructured-client"
-version = "0.37.2"
+version = "0.37.3"
 description = "Python Client SDK for Unstructured API"
 authors = [{ name = "Unstructured" },]
 readme = "README-PYPI.md"

src/unstructured_client/_hooks/custom/pdf_utils.py

@@ -8,6 +8,7 @@
 from pypdf.errors import FileNotDecryptedError, PdfReadError
 
 from unstructured_client._hooks.custom.common import UNSTRUCTURED_CLIENT_LOGGER_NAME
+from unstructured_client._hooks.custom.validation_errors import FileValidationError
 
 logger = logging.getLogger(UNSTRUCTURED_CLIENT_LOGGER_NAME)
 
@@ -17,12 +18,11 @@
 pdf_logger.setLevel(logging.ERROR)
 
 
-class PDFValidationError(Exception):
-    """Base exception for PDF validation errors."""
+class PDFValidationError(FileValidationError):
+    """Exception for PDF validation errors."""
 
     def __init__(self, message: str):
-        self.message = message
-        super().__init__(self.message)
+        super().__init__(message, file_type="PDF")
 
 
 def read_pdf(pdf_file: Union[BinaryIO, bytes]) -> Optional[PdfReader]:

src/unstructured_client/_hooks/custom/split_pdf_hook.py

@@ -16,7 +16,7 @@
 import aiofiles
 import httpx
 import nest_asyncio  # type: ignore
-from httpx import AsyncClient, RequestError
+from httpx import AsyncClient
 from pypdf import PdfReader, PdfWriter
 
 from unstructured_client._hooks.custom import form_utils, pdf_utils, request_utils
@@ -303,13 +303,7 @@ def before_request(
         if pdf is None:
             return request
 
-        try:
-            pdf = pdf_utils.check_pdf(pdf)
-        except pdf_utils.PDFValidationError as e:
-            raise RequestError(
-                message=e.message,
-                request=request,
-            ) from e
+        pdf = pdf_utils.check_pdf(pdf)
 
         starting_page_number = form_utils.get_starting_page_number(
             form_data,

src/unstructured_client/_hooks/custom/validation_errors.py

@@ -0,0 +1,16 @@
+"""File validation error classes for the Unstructured client."""
+
+from typing import Optional
+
+
+class FileValidationError(Exception):
+    """Base exception for file validation errors.
+    
+    This exception should be raised when a file fails validation
+    checks before being processed by the API.
+    """
+
+    def __init__(self, message: str, file_type: Optional[str] = None):
+        self.message: str = message
+        self.file_type: Optional[str] = file_type
+        super().__init__(self.message)