feat!: Docling v2 (#117)

---------

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

tests/test_legacy_format_transform.py

@@ -0,0 +1,52 @@
+import json
+from pathlib import Path
+
+import pytest
+
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.pipeline_options import PdfPipelineOptions
+from docling.document_converter import DocumentConverter, PdfFormatOption
+
+
+@pytest.fixture
+def test_doc_paths():
+    return [
+        Path("tests/data/wiki_duck.html"),
+        Path("tests/data/word_sample.docx"),
+        Path("tests/data/lorem_ipsum.docx"),
+        Path("tests/data/powerpoint_sample.pptx"),
+        Path("tests/data/2305.03393v1-pg9-img.png"),
+        Path("tests/data/2206.01062.pdf"),
+    ]
+
+
+def get_converter():
+
+    pipeline_options = PdfPipelineOptions()
+    pipeline_options.do_ocr = False
+
+    converter = DocumentConverter(
+        format_options={
+            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+        }
+    )
+
+    return converter
+
+
+def test_compare_legacy_output(test_doc_paths):
+    converter = get_converter()
+
+    res = converter.convert_all(test_doc_paths, raises_on_error=True)
+
+    for conv_res in res:
+        print(f"Results for {conv_res.input.file}")
+        print(
+            json.dumps(
+                conv_res.legacy_document.model_dump(
+                    mode="json", by_alias=True, exclude_none=True
+                )
+            )
+        )
+
+    # assert res.legacy_output == res.legacy_output_transformed