docling-core 2.11.0__py3-none-any.whl → 2.12.1__py3-none-any.whl

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/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/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/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/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.dist-info → docling_core-2.12.1.dist-info}/METADATA

@@ -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.dist-info → docling_core-2.12.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
 docling_core/__init__.py,sha256=D0afxif-BMUrgx2cYk1cwxiwATRYaGXsIMk_z4nw1Vs,90
 docling_core/cli/__init__.py,sha256=C63yWifzpA0IV7YWDatpAdrhoV8zjqxAKv0xMf09VdM,19
-docling_core/cli/view.py,sha256=bhxvPQWIJVo2g_pRL0GjQwjDw-jdiRXp1-BTbG849go,1746
+docling_core/cli/view.py,sha256=gwxSBYhGqwznMR8pdXaEuAh2bjFD5X_g11xFYSgFgtM,1764
 docling_core/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling_core/resources/schemas/doc/ANN.json,sha256=04U5j-PU9m5w7IagJ_rHcAx7qUtLkUuaWZO9GuYHnTA,4202
 docling_core/resources/schemas/doc/DOC.json,sha256=9tVKpCqDGGq3074Nn5qlUCdTN-5k1Q0ri_scJblwnLE,6686
@@ -24,8 +24,8 @@ docling_core/types/__init__.py,sha256=MVRSgsk5focwGyAplh_TRR3dEecIXpd98g_u3zZ5HX
 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=_ttU8QI8wXDTQRUnN5n7L6D9wYFVLSAibxlFoMbgAsk,4557
-docling_core/types/doc/document.py,sha256=9t6FPvrxT9gKtUaYMP_Kyhz_izo2p6TQX_LlG2Fj5hY,91593
-docling_core/types/doc/labels.py,sha256=4BG_wNG1qDc5E3qQHixPjM_IAxGjGo14hobNyfTycZw,1662
+docling_core/types/doc/document.py,sha256=2W4wZunI0K_EOxNtY5jbKeyw7bYWKKNLiljxfN8anHc,91844
+docling_core/types/doc/labels.py,sha256=Pc5avKtGM2fv-w7mXinoxs9BkhktmFaJ6ACsgFiAAm4,1702
 docling_core/types/doc/tokens.py,sha256=uU_MYW_p7ypf7eYICFBvxdnVaPZ7CQnvZmbJ6oPrtEA,6134
 docling_core/types/doc/utils.py,sha256=YDOh_ZD1Y7OmCEDdCLJ_MO5K3HA67nc_acfhOK6WztU,1439
 docling_core/types/gen/__init__.py,sha256=C6TuCfvpSnSL5XDOFMcYHUY2-i08vvfOGRcdu6Af0pI,124
@@ -36,7 +36,7 @@ docling_core/types/legacy_doc/base.py,sha256=aBKBunw6M6nvEq4lqP1cfFWK3GpGa6PXwNQ
 docling_core/types/legacy_doc/doc_ann.py,sha256=CIQHW8yzu70bsMR9gtu7dqe4oz603Tq2eDDt9sh-tYo,1203
 docling_core/types/legacy_doc/doc_ocr.py,sha256=FfFqHAyMSbFt5cKeE7QLcxS0qUweBilBJoN9CH2TsQs,1394
 docling_core/types/legacy_doc/doc_raw.py,sha256=LrvQ9DhNjBRy98p_F9PUyHZeTGAxMKWqJzY4WJ7v-xs,3895
-docling_core/types/legacy_doc/document.py,sha256=A_cTYOjx6pNIICpOUm09YsfwPrIGDEZTKdetb2fx4PM,24273
+docling_core/types/legacy_doc/document.py,sha256=AW8AIBM19k-HtTmXPsFKagqd6gi9THJdB4RsPb1C5F0,24534
 docling_core/types/legacy_doc/tokens.py,sha256=uU_MYW_p7ypf7eYICFBvxdnVaPZ7CQnvZmbJ6oPrtEA,6134
 docling_core/types/nlp/__init__.py,sha256=hGcztAeVK7xkRBqRRvc4zbY4PGeJ0r0QrEsetnSx9nI,119
 docling_core/types/nlp/qa.py,sha256=TyZjubqkEoREv0YzmuLKlq4WW_TnJNj7BoBY1_r2a1E,2731
@@ -54,10 +54,10 @@ docling_core/utils/file.py,sha256=GzX0pclvewwPoqHJSaVUuULzSJwJgkCUwgKgJ7G5ohQ,56
 docling_core/utils/generate_docs.py,sha256=BdKAoduWXOc7YMvcmlhjoJOFlUxij1ybxglj6LZDtC8,2290
 docling_core/utils/generate_jsonschema.py,sha256=uNX1O5XnjyB5nA66XqZXTt3YbGuR2tyi_OhHepHYtZg,1654
 docling_core/utils/legacy.py,sha256=xfp7U0JqjI60K3loWiNTk8w08_KfCUzTb2MNULBOIz4,24396
-docling_core/utils/validate.py,sha256=3FmnxnKTDZC5J9OGxCL3U3DGRl0t0bBV1NcySXswdas,2031
+docling_core/utils/validate.py,sha256=aQ11UbFyl8iD_N7yTTZmm_VVeXz8KcCyn3GLXgkfYRM,2049
 docling_core/utils/validators.py,sha256=azcrndLzhNkTWnbFSu9shJ5D3j_znnLrIFA5R8hzmGU,2798
-docling_core-2.11.0.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
-docling_core-2.11.0.dist-info/METADATA,sha256=4Xb7VqXg4dAxRWiT-KThSn4i_TiIsoIXdhyN8eZOWSk,5744
-docling_core-2.11.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling_core-2.11.0.dist-info/entry_points.txt,sha256=oClcdb2L2RKx4jdqUykY16Kum_f0_whwWhGzIodyidc,216
-docling_core-2.11.0.dist-info/RECORD,,
+docling_core-2.12.1.dist-info/LICENSE,sha256=2M9-6EoQ1sxFztTOkXGAtwUDJvnWaAHdB9BYWVwGkIw,1087
+docling_core-2.12.1.dist-info/METADATA,sha256=7GQuAsiJL6EGBIEjeiX-XQs7gELqhCGWsNeSrsGm5Kk,5744
+docling_core-2.12.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling_core-2.12.1.dist-info/entry_points.txt,sha256=oClcdb2L2RKx4jdqUykY16Kum_f0_whwWhGzIodyidc,216
+docling_core-2.12.1.dist-info/RECORD,,