Test all backends, fixes

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

tests/test_code_formula.py

@@ -3,7 +3,7 @@ from pathlib import Path
 from docling_core.types.doc import CodeItem, TextItem
 from docling_core.types.doc.labels import CodeLanguageLabel, DocItemLabel
 
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.backend.docling_parse_v2_backend import DoclingParseV4DocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import PdfPipelineOptions
@@ -24,7 +24,6 @@ def get_converter():
     converter = DocumentConverter(
         format_options={
             InputFormat.PDF: PdfFormatOption(
-                backend=DoclingParseV2DocumentBackend,
                 pipeline_cls=StandardPdfPipeline,
                 pipeline_options=pipeline_options,
             )

tests/test_document_picture_classifier.py

@@ -2,7 +2,7 @@ from pathlib import Path
 
 from docling_core.types.doc import PictureClassificationData
 
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.backend.docling_parse_v2_backend import DoclingParseV4DocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import PdfPipelineOptions
@@ -26,7 +26,6 @@ def get_converter():
     converter = DocumentConverter(
         format_options={
             InputFormat.PDF: PdfFormatOption(
-                backend=DoclingParseV2DocumentBackend,
                 pipeline_cls=StandardPdfPipeline,
                 pipeline_options=pipeline_options,
             )

tests/test_e2e_conversion.py

@@ -34,7 +34,7 @@ def get_converter():
     converter = DocumentConverter(
         format_options={
             InputFormat.PDF: PdfFormatOption(
-                pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
+                pipeline_options=pipeline_options,
             )
         }
     )

tests/test_e2e_ocr_conversion.py

@@ -45,7 +45,6 @@ def get_converter(ocr_options: OcrOptions):
         format_options={
             InputFormat.PDF: PdfFormatOption(
                 pipeline_options=pipeline_options,
-                backend=DoclingParseV4DocumentBackend,
             )
         }
     )

tests/test_interfaces.py

@@ -31,7 +31,7 @@ def converter():
     converter = DocumentConverter(
         format_options={
             InputFormat.PDF: PdfFormatOption(
-                pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
+                pipeline_options=pipeline_options,
             )
         }
     )

tests/test_options.py

@@ -3,7 +3,10 @@ from pathlib import Path
 
 import pytest
 
+from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
+from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
 from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
+from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import ConversionStatus, InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
@@ -33,7 +36,6 @@ def get_converters_with_table_options():
                 format_options={
                     InputFormat.PDF: PdfFormatOption(
                         pipeline_options=pipeline_options,
-                        backend=DoclingParseV4DocumentBackend,
                     )
                 }
             )
@@ -137,3 +139,29 @@ def test_ocr_coverage_threshold(test_doc_path):
 
     # this should have generated no results, since we set a very high threshold
     assert len(doc_result.document.texts) == 0
+
+
+def test_parser_backends(test_doc_path):
+    pipeline_options = PdfPipelineOptions()
+    pipeline_options.do_ocr = False
+    pipeline_options.do_table_structure = False
+
+    for backend_t in [
+        DoclingParseV4DocumentBackend,
+        DoclingParseV2DocumentBackend,
+        DoclingParseDocumentBackend,
+        PyPdfiumDocumentBackend,
+    ]:
+        converter = DocumentConverter(
+            format_options={
+                InputFormat.PDF: PdfFormatOption(
+                    pipeline_options=pipeline_options,
+                    backend=backend_t,
+                )
+            }
+        )
+
+        test_doc_path = Path("./tests/data/pdf/code_and_formula.pdf")
+        doc_result: ConversionResult = converter.convert(test_doc_path)
+
+        assert doc_result.status == ConversionStatus.SUCCESS