diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_001.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_001.png new file mode 100644 index 00000000..747b1616 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_001.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_002.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_002.png new file mode 100644 index 00000000..c7bf77fc Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_002.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_003.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_003.png new file mode 100644 index 00000000..6093dcb9 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_003.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_004.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_004.png new file mode 100644 index 00000000..d2725d3c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_004.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_005.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_005.png new file mode 100644 index 00000000..e7aa343c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_005.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_006.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_006.png new file mode 100644 index 00000000..99ee59e1 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_006.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_007.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_007.png new file mode 100644 index 00000000..3136d38d Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_007.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_008.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_008.png new file mode 100644 index 00000000..c6dd058b Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_008.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_009.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_009.png new file mode 100644 index 00000000..9f5a546c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_009.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_010.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_010.png new file mode 100644 index 00000000..b1ffd453 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_010.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_011.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_011.png new file mode 100644 index 00000000..f3588721 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_011.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_012.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_012.png new file mode 100644 index 00000000..db71fe92 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_012.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_013.png b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_013.png new file mode 100644 index 00000000..29a5e7d0 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/A8E7SRVS/annotated_pages/page_013.png differ diff --git a/tests/fixtures/ocr_real_papers/A8E7SRVS/expectations.json b/tests/fixtures/ocr_real_papers/A8E7SRVS/expectations.json new file mode 100644 index 00000000..5cbc5ca5 --- /dev/null +++ b/tests/fixtures/ocr_real_papers/A8E7SRVS/expectations.json @@ -0,0 +1,30 @@ +{ + "pages": { + "5": { + "expected_object_ownership": [ + {"object_type": "figure", "figure_number": 1, "must_render_as_object": true}, + {"object_type": "figure", "figure_number": 2, "must_render_as_object": true}, + {"object_type": "figure", "figure_number": 3, "must_render_as_object": true}, + {"object_type": "figure", "figure_number": 4, "must_render_as_object": true} + ], + "expected_render_invariants": [ + {"type": "not_in_body", "text_contains": "Fig. 1"} + ] + }, + "6": { + "expected_consumption": [ + {"block_id_comment": "Fig.5 continuation sentence", "consumed_by_kind": "figure", "consumed_by_number": 5, "must_not_render_as_body": true} + ] + }, + "7": { + "expected_object_ownership": [ + {"object_type": "table", "table_number": 3, "must_render_as_object": true, "must_not_split_by_body_blocks": true} + ] + }, + "12": { + "expected_render_invariants": [ + {"type": "before_text", "before": "Conclusion", "after": "References", "layer": "render_order_markdown"} + ] + } + } +} diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_001.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_001.png new file mode 100644 index 00000000..b60cc2b5 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_001.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_002.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_002.png new file mode 100644 index 00000000..521baa3e Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_002.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_003.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_003.png new file mode 100644 index 00000000..fafb4ef5 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_003.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_004.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_004.png new file mode 100644 index 00000000..01ec2e62 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_004.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_005.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_005.png new file mode 100644 index 00000000..59c59b1a Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_005.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_006.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_006.png new file mode 100644 index 00000000..389d2a90 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_006.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_007.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_007.png new file mode 100644 index 00000000..7239e8e9 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_007.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_008.png b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_008.png new file mode 100644 index 00000000..86672497 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/CAQNW9Q2/annotated_pages/page_008.png differ diff --git a/tests/fixtures/ocr_real_papers/CAQNW9Q2/expectations.json b/tests/fixtures/ocr_real_papers/CAQNW9Q2/expectations.json new file mode 100644 index 00000000..dcf6de84 --- /dev/null +++ b/tests/fixtures/ocr_real_papers/CAQNW9Q2/expectations.json @@ -0,0 +1,26 @@ +{ + "document": { + "expected_reader_figure_count_min": 2, + "expected_reference_zone": true, + "expected_abstract_span": true + }, + "pages": { + "1": { + "expected_roles": [ + {"block_pattern": "Quantitative radiography", "role": "title_or_doc_title", "confidence": "medium"} + ], + "expected_non_body": [0, 1, 4, 5], + "expected_reference_rules": [ + {"block_id_comment": "no block on page 1 should be reference_item"} + ] + }, + "7": { + "expected_order_relations": [ + {"before_text": "Conclusion", "after_text": "References", "layer": "render_order_markdown"} + ], + "expected_reference_rules": [ + {"must_not_render_references_as_body": true} + ] + } + } +} diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_001.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_001.png new file mode 100644 index 00000000..72d671a3 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_001.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_002.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_002.png new file mode 100644 index 00000000..650055a0 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_002.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_003.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_003.png new file mode 100644 index 00000000..81e4500b Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_003.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_004.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_004.png new file mode 100644 index 00000000..584b653e Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_004.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_005.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_005.png new file mode 100644 index 00000000..aec83e3d Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_005.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_006.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_006.png new file mode 100644 index 00000000..da1104a5 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_006.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_007.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_007.png new file mode 100644 index 00000000..5d4efcc7 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_007.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_008.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_008.png new file mode 100644 index 00000000..669258d6 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_008.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_009.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_009.png new file mode 100644 index 00000000..acb650f9 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_009.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_010.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_010.png new file mode 100644 index 00000000..8a831b77 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_010.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_011.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_011.png new file mode 100644 index 00000000..29392634 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_011.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_012.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_012.png new file mode 100644 index 00000000..05653435 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_012.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_013.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_013.png new file mode 100644 index 00000000..7aad7e72 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_013.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_014.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_014.png new file mode 100644 index 00000000..8d6a0fcb Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_014.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_015.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_015.png new file mode 100644 index 00000000..8fcb4db4 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_015.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_016.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_016.png new file mode 100644 index 00000000..e1955a36 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_016.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_017.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_017.png new file mode 100644 index 00000000..9300844d Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_017.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_018.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_018.png new file mode 100644 index 00000000..c9ef3267 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_018.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_019.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_019.png new file mode 100644 index 00000000..536d8e80 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_019.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_020.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_020.png new file mode 100644 index 00000000..c6818f95 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_020.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_021.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_021.png new file mode 100644 index 00000000..e3242336 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_021.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_022.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_022.png new file mode 100644 index 00000000..21d16254 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_022.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_023.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_023.png new file mode 100644 index 00000000..baffebe7 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_023.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_024.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_024.png new file mode 100644 index 00000000..b52827aa Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_024.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_025.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_025.png new file mode 100644 index 00000000..4b374f70 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_025.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_026.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_026.png new file mode 100644 index 00000000..665d9aaa Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_026.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_027.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_027.png new file mode 100644 index 00000000..10b557d8 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_027.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_028.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_028.png new file mode 100644 index 00000000..b474ef5c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_028.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_029.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_029.png new file mode 100644 index 00000000..6a8f6cd7 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_029.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_030.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_030.png new file mode 100644 index 00000000..733c9b0c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_030.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_031.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_031.png new file mode 100644 index 00000000..c037b7a1 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_031.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_032.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_032.png new file mode 100644 index 00000000..e7a4886c Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_032.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_033.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_033.png new file mode 100644 index 00000000..2f820dee Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_033.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_034.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_034.png new file mode 100644 index 00000000..9996d551 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_034.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_035.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_035.png new file mode 100644 index 00000000..08d632d1 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_035.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_036.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_036.png new file mode 100644 index 00000000..acc43ebe Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_036.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_037.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_037.png new file mode 100644 index 00000000..b2b430cb Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_037.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_038.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_038.png new file mode 100644 index 00000000..b49dd578 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_038.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_039.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_039.png new file mode 100644 index 00000000..f2d382dd Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_039.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_040.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_040.png new file mode 100644 index 00000000..88dbc7f0 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_040.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_041.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_041.png new file mode 100644 index 00000000..48a07467 Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_041.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_042.png b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_042.png new file mode 100644 index 00000000..8ca2a4ea Binary files /dev/null and b/tests/fixtures/ocr_real_papers/DWQQK2YB/annotated_pages/page_042.png differ diff --git a/tests/fixtures/ocr_real_papers/DWQQK2YB/expectations.json b/tests/fixtures/ocr_real_papers/DWQQK2YB/expectations.json new file mode 100644 index 00000000..b4b8e04f --- /dev/null +++ b/tests/fixtures/ocr_real_papers/DWQQK2YB/expectations.json @@ -0,0 +1,22 @@ +{ + "document": { + "expected_reader_figure_count_min": 3, + "expected_reference_zone": true, + "expected_abstract_span": true + }, + "pages": { + "35": { + "expected_object_ownership": [ + { + "object_type": "figure", + "figure_number": 1, + "must_render_as_object": true, + "must_not_render_caption_blocks_as_body": true + } + ] + } + }, + "expected_render_invariants": [ + {"type": "no_duplicate_caption", "caption_regex": "Fig\\.\\s*1"} + ] +}