docling-core 2.11.0__tar.gz → 2.12.1__tar.gz

{docling_core-2.11.0 → docling_core-2.12.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.11.0
+Version: 2.12.1
 Summary: A python library to define and validate data types in Docling.
 Home-page: https://ds4sd.github.io/
 License: MIT

{docling_core-2.11.0 → docling_core-2.12.1}/docling_core/cli/view.py

@@ -57,7 +57,7 @@ def view(
     doc = DoclingDocument.load_from_json(filename=path)
     target_path = Path(tempfile.mkdtemp()) / "out.html"
     html_output = doc.export_to_html(image_mode=ImageRefMode.EMBEDDED)
-    with open(target_path, "w") as f:
+    with open(target_path, "w", encoding="utf-8") as f:
         f.write(html_output)
     webbrowser.open(url=f"file://{target_path.absolute().resolve()}")
 

{docling_core-2.11.0 → docling_core-2.12.1}/docling_core/types/doc/document.py

@@ -1884,7 +1884,7 @@ class DoclingDocument(BaseModel):
         )
 
         out = new_doc.export_to_dict()
-        with open(filename, "w") as fw:
+        with open(filename, "w", encoding="utf-8") as fw:
             json.dump(out, fw, indent=indent)
 
     @classmethod
@@ -1898,7 +1898,7 @@ class DoclingDocument(BaseModel):
         :rtype: DoclingDocument
 
         """
-        with open(filename, "r") as f:
+        with open(filename, "r", encoding="utf-8") as f:
             return cls.model_validate_json(f.read())
 
     def save_as_yaml(
@@ -1919,7 +1919,7 @@ class DoclingDocument(BaseModel):
         )
 
         out = new_doc.export_to_dict()
-        with open(filename, "w") as fw:
+        with open(filename, "w", encoding="utf-8") as fw:
             yaml.dump(out, fw, default_flow_style=default_flow_style)
 
     def export_to_dict(
@@ -1971,7 +1971,7 @@ class DoclingDocument(BaseModel):
             page_no=page_no,
         )
 
-        with open(filename, "w") as fw:
+        with open(filename, "w", encoding="utf-8") as fw:
             fw.write(md_out)
 
     def export_to_markdown(  # noqa: C901
@@ -2038,6 +2038,9 @@ class DoclingDocument(BaseModel):
             if ix < from_element or to_element <= ix:
                 continue  # skip as many items as you want
 
+            if (isinstance(item, DocItem)) and (item.label not in labels):
+                continue  # skip any label that is not whitelisted
+
             # Handle newlines between different types of content
             if (
                 len(mdtexts) > 0
@@ -2224,7 +2227,7 @@ class DoclingDocument(BaseModel):
             html_head=html_head,
         )
 
-        with open(filename, "w") as fw:
+        with open(filename, "w", encoding="utf-8") as fw:
             fw.write(html_out)
 
     def _get_output_paths(
@@ -2462,7 +2465,7 @@ class DoclingDocument(BaseModel):
             with_groups=with_groups,
         )
 
-        with open(filename, "w") as fw:
+        with open(filename, "w", encoding="utf-8") as fw:
             fw.write(out)
 
     def export_to_document_tokens(

{docling_core-2.11.0 → docling_core-2.12.1}/docling_core/types/doc/labels.py

@@ -48,6 +48,7 @@ class GroupLabel(str, Enum):
     SLIDE = "slide"
     FORM_AREA = "form_area"
     KEY_VALUE_AREA = "key_value_area"
+    COMMENT_SECTION = "comment_section"
 
     def __str__(self):
         """Get string value."""

{docling_core-2.11.0 → docling_core-2.12.1}/docling_core/types/legacy_doc/document.py

@@ -550,17 +550,18 @@ class ExportedCCSDocument(
 
                 elif (
                     isinstance(item, Table)
-                    and item.data
+                    and (item.data or item.text)
                     and item_type in main_text_labels
                 ):
 
                     md_table = ""
                     table = []
-                    for row in item.data:
-                        tmp = []
-                        for col in row:
-                            tmp.append(col.text)
-                        table.append(tmp)
+                    if item.data is not None:
+                        for row in item.data:
+                            tmp = []
+                            for col in row:
+                                tmp.append(col.text)
+                            table.append(tmp)
 
                     if len(table) > 1 and len(table[0]) > 0:
                         try:
@@ -579,7 +580,9 @@ class ExportedCCSDocument(
                     if item.text:
                         markdown_text = item.text
                     if not strict_text:
-                        markdown_text += "\n\n" + md_table
+                        markdown_text += (
+                            "\n\n" if len(markdown_text) > 0 else ""
+                        ) + md_table
 
                 elif isinstance(item, Figure) and item_type in main_text_labels:
 
@@ -587,7 +590,9 @@ class ExportedCCSDocument(
                     if item.text:
                         markdown_text = item.text
                     if not strict_text:
-                        markdown_text += f"\n{image_placeholder}"
+                        markdown_text += (
+                            "\n" if len(markdown_text) > 0 else ""
+                        ) + image_placeholder
 
                 if markdown_text:
                     md_texts.append(markdown_text)

{docling_core-2.11.0 → docling_core-2.12.1}/docling_core/utils/validate.py

@@ -38,7 +38,7 @@ def run():
     """Run the validation of a file containing a Document."""
     file_format, input_file = parse_arguments()
 
-    with open(input_file, "r") as fd:
+    with open(input_file, "r", encoding="utf-8") as fd:
         file_ = json.load(fd)
 
     result = (False, "Empty result")

{docling_core-2.11.0 → docling_core-2.12.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-core"
-version = "2.11.0"
+version = "2.12.1"
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 authors = [