feat: Add option to define page range (#852)

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

tests/test_input_doc.py

@@ -4,6 +4,7 @@ from pathlib import Path
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import DocumentStream, InputFormat
 from docling.datamodel.document import InputDocument, _DocumentConversionInput
+from docling.datamodel.settings import DocumentLimits
 
 
 def test_in_doc_from_valid_path():
@@ -39,6 +40,40 @@ def test_in_doc_from_invalid_buf():
     assert doc.valid == False
 
 
+def test_in_doc_with_page_range():
+    test_doc_path = Path("./tests/data/2206.01062.pdf")
+    limits = DocumentLimits()
+    limits.page_range = (1, 10)
+
+    doc = InputDocument(
+        path_or_stream=test_doc_path,
+        format=InputFormat.PDF,
+        backend=PyPdfiumDocumentBackend,
+        limits=limits,
+    )
+    assert doc.valid == True
+
+    limits.page_range = (9, 9)
+
+    doc = InputDocument(
+        path_or_stream=test_doc_path,
+        format=InputFormat.PDF,
+        backend=PyPdfiumDocumentBackend,
+        limits=limits,
+    )
+    assert doc.valid == True
+
+    limits.page_range = (11, 12)
+
+    doc = InputDocument(
+        path_or_stream=test_doc_path,
+        format=InputFormat.PDF,
+        backend=PyPdfiumDocumentBackend,
+        limits=limits,
+    )
+    assert doc.valid == False
+
+
 def test_guess_format(tmp_path):
     """Test docling.datamodel.document._DocumentConversionInput.__guess_format"""
     dci = _DocumentConversionInput(path_or_stream_iterator=[])

tests/test_options.py

@@ -105,6 +105,20 @@ def test_e2e_conversions(test_doc_path):
         assert doc_result.status == ConversionStatus.SUCCESS
 
 
+def test_page_range(test_doc_path):
+    converter = DocumentConverter()
+    doc_result: ConversionResult = converter.convert(test_doc_path, page_range=(9, 9))
+
+    assert doc_result.status == ConversionStatus.SUCCESS
+    assert doc_result.input.page_count == 9
+    assert doc_result.document.num_pages() == 1
+
+    doc_result: ConversionResult = converter.convert(
+        test_doc_path, page_range=(10, 10), raises_on_error=False
+    )
+    assert doc_result.status == ConversionStatus.FAILURE
+
+
 def test_ocr_coverage_threshold(test_doc_path):
     pipeline_options = PdfPipelineOptions()
     pipeline_options.do_ocr = True