feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905)

* Add DoclingParseV3 backend implementation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use docling-core with docling-parse types Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes and test updates Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset tests Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test units Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add back DoclingParse v1 backend, pipeline options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update locks Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Ground-truth files updated Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update tests, use TextCell.from_ocr property Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Text fixes, new test data Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename docling backend to v4 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Test all backends, fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset all tests to use docling-parse v1 for now Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for DPv4 backend init, better test coverage Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * test_input_doc use default backend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-12-08 20:58:11 +00:00 · 2025-03-18 10:38:19 +01:00
parent 772487f9c9
commit 3960b199d6
126 changed files with 1138 additions and 709 deletions
--- a/tests/test_backend_docling_parse_v4.py
+++ b/tests/test_backend_docling_parse_v4.py
@@ -0,0 +1,76 @@
+from pathlib import Path
+
+import pytest
+
+from docling.backend.docling_parse_v4_backend import (
+    DoclingParseV4DocumentBackend,
+    DoclingParseV4PageBackend,
+)
+from docling.datamodel.base_models import BoundingBox, InputFormat
+from docling.datamodel.document import InputDocument
+
+
+@pytest.fixture
+def test_doc_path():
+    return Path("./tests/data/pdf/2206.01062.pdf")
+
+
+def _get_backend(pdf_doc):
+    in_doc = InputDocument(
+        path_or_stream=pdf_doc,
+        format=InputFormat.PDF,
+        backend=DoclingParseV4DocumentBackend,
+    )
+
+    doc_backend = in_doc._backend
+    return doc_backend
+
+
+def test_text_cell_counts():
+    pdf_doc = Path("./tests/data/pdf/redp5110_sampled.pdf")
+
+    doc_backend = _get_backend(pdf_doc)
+
+    for page_index in range(0, doc_backend.page_count()):
+        last_cell_count = None
+        for i in range(10):
+            page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
+            cells = list(page_backend.get_text_cells())
+
+            if last_cell_count is None:
+                last_cell_count = len(cells)
+
+            if len(cells) != last_cell_count:
+                assert (
+                    False
+                ), "Loading page multiple times yielded non-identical text cell counts"
+            last_cell_count = len(cells)
+
+
+def test_get_text_from_rect(test_doc_path):
+    doc_backend = _get_backend(test_doc_path)
+    page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
+
+    # Get the title text of the DocLayNet paper
+    textpiece = page_backend.get_text_in_rect(
+        bbox=BoundingBox(l=102, t=77, r=511, b=124)
+    )
+    ref = "DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis"
+
+    assert textpiece.strip() == ref
+
+
+def test_crop_page_image(test_doc_path):
+    doc_backend = _get_backend(test_doc_path)
+    page_backend: DoclingParseV4PageBackend = doc_backend.load_page(0)
+
+    # Crop out "Figure 1" from the DocLayNet paper
+    im = page_backend.get_page_image(
+        scale=2, cropbox=BoundingBox(l=317, t=246, r=574, b=527)
+    )
+    # im.show()
+
+
+def test_num_pages(test_doc_path):
+    doc_backend = _get_backend(test_doc_path)
+    doc_backend.page_count() == 9