docling-core 2.2.0__py3-none-any.whl → 2.2.2__py3-none-any.whl

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/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.dist-info → docling_core-2.2.2.dist-info}/METADATA

@@ -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.dist-info → docling_core-2.2.2.dist-info}/RECORD

@@ -16,12 +16,12 @@ docling_core/search/package.py,sha256=Lz2ml2eDy5t0ZimnGTq-DXHAn-f18w0bn4H5xrhs75
 docling_core/transforms/__init__.py,sha256=P81y_oqkiTN4Ld5crh1gQ6BbHqqR6C6nBt9ACDd57ds,106
 docling_core/transforms/chunker/__init__.py,sha256=sSSTnt7ZCt8Og1e0jhApNTtA0pyyHyzwcl8yXFLb2J8,292
 docling_core/transforms/chunker/base.py,sha256=iPouZOJ3cYWvai4P0Gpd3QmsTKQuY5fFUXzTMk_XNmE,1571
-docling_core/transforms/chunker/hierarchical_chunker.py,sha256=-wZrQAPMiROb9yKiSN3eGqtD13tjcDVAiDUz971Q8PI,8087
+docling_core/transforms/chunker/hierarchical_chunker.py,sha256=uG7nNoUCFqWeQAKydQg731JYJ9sayUe4J48nMF0VHE8,8097
 docling_core/types/__init__.py,sha256=MVRSgsk5focwGyAplh_TRR3dEecIXpd98g_u3zZ5HXo,260
 docling_core/types/base.py,sha256=PusJskRVL19y-hq0BgXr5e8--QEqSqLnFNJ8UbOqW88,8318
 docling_core/types/doc/__init__.py,sha256=bEL4zKVOG7Wxm6xQrgF58mu-Teds9aSavuEAKVNhrTU,639
 docling_core/types/doc/base.py,sha256=zvx631U_yQCcJam83hNdDanXEYnO3eN-CCw9vDr6S-I,4442
-docling_core/types/doc/document.py,sha256=RMG_iCgKJm71TFVRBrRKzST-Nb9DCgluji9O0BhPt4M,51373
+docling_core/types/doc/document.py,sha256=SrOXpO6iCIYFkhWW-pksd4C4PeJ2jubKI5m34K_lTac,51902
 docling_core/types/doc/labels.py,sha256=mzmSd072A-qW3IThswHxwIHV8IoyTCbHHlNOrisinRA,1335
 docling_core/types/gen/__init__.py,sha256=C6TuCfvpSnSL5XDOFMcYHUY2-i08vvfOGRcdu6Af0pI,124
 docling_core/types/gen/generic.py,sha256=l4CZ4_Lb8ONG36WNJWbKX5hGKvTh_yU-hXp5hsm7uVU,844
@@ -49,8 +49,8 @@ docling_core/utils/generate_docs.py,sha256=BdKAoduWXOc7YMvcmlhjoJOFlUxij1ybxglj6
 docling_core/utils/generate_jsonschema.py,sha256=uNX1O5XnjyB5nA66XqZXTt3YbGuR2tyi_OhHepHYtZg,1654
 docling_core/utils/validate.py,sha256=3FmnxnKTDZC5J9OGxCL3U3DGRl0t0bBV1NcySXswdas,2031
 docling_core/utils/validators.py,sha256=azcrndLzhNkTWnbFSu9shJ5D3j_znnLrIFA5R8hzmGU,2798
-docling_core-2.2.0.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
-docling_core-2.2.0.dist-info/METADATA,sha256=3iAaT-ENDYeRWqBtefYohekCqiiXM-AFkJw3lFi3s8o,5432
-docling_core-2.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_core-2.2.0.dist-info/entry_points.txt,sha256=jIxlWv3tnO04irlZc0zfhqJIgz1bg9Hha4AkaLWSdUA,177
-docling_core-2.2.0.dist-info/RECORD,,
+docling_core-2.2.2.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
+docling_core-2.2.2.dist-info/METADATA,sha256=680OW3ffU0R_QL5UdvoUASJBOyLj7YKlfeDcftd3Kkw,5432
+docling_core-2.2.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_core-2.2.2.dist-info/entry_points.txt,sha256=jIxlWv3tnO04irlZc0zfhqJIgz1bg9Hha4AkaLWSdUA,177
+docling_core-2.2.2.dist-info/RECORD,,