docling-core 2.2.0__tar.gz → 2.2.2__tar.gz

{docling_core-2.2.0 → docling_core-2.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling-core
-Version: 2.2.0
+Version: 2.2.2
 Summary: A python library to define and validate data types in Docling.
 Home-page: https://ds4sd.github.io/
 License: MIT

{docling_core-2.2.0 → docling_core-2.2.2}/docling_core/transforms/chunker/hierarchical_chunker.py

@@ -129,8 +129,8 @@ class HierarchicalChunker(BaseChunker):
         table_df.index = table_df.index + 1
         table_df = table_df.sort_index()
 
-        rows = [item.strip() for item in table_df.iloc[:, 0].to_list()]
-        cols = [item.strip() for item in table_df.iloc[0, :].to_list()]
+        rows = [str(item).strip() for item in table_df.iloc[:, 0].to_list()]
+        cols = [str(item).strip() for item in table_df.iloc[0, :].to_list()]
 
         nrows = table_df.shape[0]
         ncols = table_df.shape[1]

{docling_core-2.2.0 → docling_core-2.2.2}/docling_core/types/doc/document.py

@@ -1291,6 +1291,18 @@ class DoclingDocument(BaseModel):
         mdtext = re.sub(
             r"\n\n\n+", "\n\n", mdtext
         )  # remove cases of double or more empty lines.
+
+        # Our export markdown doesn't contain any emphasis styling:
+        # Bold, Italic, or Bold-Italic
+        # Hence, any underscore that we print into Markdown is coming from document text
+        # That means we need to escape it, to properly reflect content in the markdown
+        def escape_underscores(text):
+            # Replace "_" with "\_" only if it's not already escaped
+            escaped_text = re.sub(r"(?<!\\)_", r"\_", text)
+            return escaped_text
+
+        mdtext = escape_underscores(mdtext)
+
         return mdtext
 
     def export_to_text(  # noqa: C901

{docling_core-2.2.0 → docling_core-2.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling-core"
-version = "2.2.0"
+version = "2.2.2"
 description = "A python library to define and validate data types in Docling."
 license = "MIT"
 authors = [