added three test-files for right-to-left

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
DS4SD · Feb 4, 2025 · d7c9874 · d7c9874
1 parent 5db82d5
commit d7c9874
Show file tree

Hide file tree

Showing 6 changed files with 117 additions and 146 deletions.
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -29,7 +29,8 @@ pydantic = "^2.0.0"
 docling-core = {extras = ["chunking"], version = "^2.17.0"}
 docling-ibm-models = "^3.3.0"
 deepsearch-glm = "^1.0.0"
-docling-parse = "^3.1.0"
+# docling-parse = "^3.1.0"
+docling-parse = { git = "https://github.com/DS4SD/docling-parse.git", rev = "93e281576e740345d0161ad5da1b1fff815df8e4"}
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"

diff --git a/tests/data/pdf/right_to_left_01.pdf b/tests/data/pdf/right_to_left_01.pdf
diff --git a/tests/data/pdf/right_to_left_02.pdf b/tests/data/pdf/right_to_left_02.pdf
diff --git a/tests/data/pdf/right_to_left_03.pdf b/tests/data/pdf/right_to_left_03.pdf
diff --git a/tests/verify_utils.py b/tests/verify_utils.py
@@ -248,13 +248,14 @@ def verify_conversion_result_v1(
         doc_pred_md = doc_result.legacy_document.export_to_markdown()
         doc_pred_dt = doc_result.legacy_document.export_to_document_tokens()
 
-
     engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"
-    
+
     gt_subpath = input_path.parent / "groundtruth" / "docling_v1" / input_path.name
     if str(input_path.parent).endswith("pdf"):
-        gt_subpath = input_path.parent.parent / "groundtruth" / "docling_v1" / input_path.name
-
+        gt_subpath = (
+            input_path.parent.parent / "groundtruth" / "docling_v1" / input_path.name
+        )
+
     pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json")
     json_path = gt_subpath.with_suffix(f"{engine_suffix}.json")
     md_path = gt_subpath.with_suffix(f"{engine_suffix}.md")
@@ -333,8 +334,10 @@ def verify_conversion_result_v2(
 
     gt_subpath = input_path.parent / "groundtruth" / "docling_v2" / input_path.name
     if str(input_path.parent).endswith("pdf"):
-        gt_subpath = input_path.parent.parent / "groundtruth" / "docling_v2" / input_path.name
-
+        gt_subpath = (
+            input_path.parent.parent / "groundtruth" / "docling_v2" / input_path.name
+        )
+
     pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json")
     json_path = gt_subpath.with_suffix(f"{engine_suffix}.json")
     md_path = gt_subpath.with_suffix(f"{engine_suffix}.md")