fix: improve handling of disallowed formats (#429)

* fix: Fixes and tests for StopIteration on .convert()

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Remove unnecessary case handling

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: Other test fixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* improve handling of unsupported types

- Introduced new explicit exception types instead of `RuntimeError`
- Introduced new `ConversionStatus` value for unsupported formats
- Tidied up converter member typing & removed asserts

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* robustify & simplify format option resolution

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

* rename new status, populate ConversionResult errors

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

tests/test_interfaces.py

@@ -10,7 +10,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
 
 from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
 
-GENERATE = True
+GENERATE = False
 
 
 def get_pdf_path():

tests/test_invalid_input.py

@@ -0,0 +1,45 @@
+from io import BytesIO
+from pathlib import Path
+
+import pytest
+
+from docling.datamodel.base_models import ConversionStatus, DocumentStream
+from docling.document_converter import ConversionError, DocumentConverter
+
+
+def get_pdf_path():
+
+    pdf_path = Path("./tests/data/2305.03393v1-pg9.pdf")
+    return pdf_path
+
+
+@pytest.fixture
+def converter():
+    converter = DocumentConverter()
+
+    return converter
+
+
+def test_convert_unsupported_doc_format_wout_exception(converter: DocumentConverter):
+    result = converter.convert(
+        DocumentStream(name="input.xyz", stream=BytesIO(b"xyz")), raises_on_error=False
+    )
+    assert result.status == ConversionStatus.SKIPPED
+
+
+def test_convert_unsupported_doc_format_with_exception(converter: DocumentConverter):
+    with pytest.raises(ConversionError):
+        converter.convert(
+            DocumentStream(name="input.xyz", stream=BytesIO(b"xyz")),
+            raises_on_error=True,
+        )
+
+
+def test_convert_too_small_filesize_limit_wout_exception(converter: DocumentConverter):
+    result = converter.convert(get_pdf_path(), max_file_size=1, raises_on_error=False)
+    assert result.status == ConversionStatus.FAILURE
+
+
+def test_convert_too_small_filesize_limit_with_exception(converter: DocumentConverter):
+    with pytest.raises(ConversionError):
+        converter.convert(get_pdf_path(), max_file_size=1, raises_on_error=True)