docling-core 2.44.2__tar.gz → 2.46.0__tar.gz

{docling_core-2.44.2 → docling_core-2.46.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling-core
-Version: 2.44.2
+Version: 2.46.0
 Summary: A python library to define and validate data types in Docling.
 Author-email: Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
 Maintainer-email: Panos Vagenas <pva@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>

{docling_core-2.44.2 → docling_core-2.46.0}/docling_core/transforms/serializer/common.py

@@ -359,6 +359,7 @@ class DocSerializer(BaseModel, BaseDocSerializer):
                 item=item,
                 doc_serializer=self,
                 doc=self.doc,
+                visited=my_visited,
                 **my_kwargs,
             )
         elif isinstance(item, PictureItem):

{docling_core-2.44.2 → docling_core-2.46.0}/docling_core/transforms/serializer/doctags.py

@@ -157,6 +157,7 @@ class DocTagsTableSerializer(BaseTableSerializer):
         item: TableItem,
         doc_serializer: BaseDocSerializer,
         doc: DoclingDocument,
+        visited: Optional[set[str]] = None,
         **kwargs: Any,
     ) -> SerializationResult:
         """Serializes the passed item."""
@@ -179,6 +180,7 @@ class DocTagsTableSerializer(BaseTableSerializer):
                 add_cell_text=params.add_table_cell_text,
                 xsize=params.xsize,
                 ysize=params.ysize,
+                visited=visited,
             )
             res_parts.append(create_ser_result(text=otsl_text, span_source=item))
 

{docling_core-2.44.2 → docling_core-2.46.0}/docling_core/transforms/serializer/html.py

@@ -65,8 +65,8 @@ from docling_core.types.doc.document import (
     PictureItem,
     PictureMoleculeData,
     PictureTabularChartData,
+    RichTableCell,
     SectionHeaderItem,
-    TableCell,
     TableItem,
     TextItem,
     TitleItem,
@@ -346,9 +346,6 @@ class HTMLTableSerializer(BaseTableSerializer):
         **kwargs: Any,
     ) -> SerializationResult:
         """Serializes the passed table item to HTML."""
-        nrows = item.data.num_rows
-        ncols = item.data.num_cols
-
         res_parts: list[SerializationResult] = []
         cap_res = doc_serializer.serialize_captions(item=item, tag="caption", **kwargs)
         if cap_res.text:
@@ -356,11 +353,11 @@ class HTMLTableSerializer(BaseTableSerializer):
 
         if item.self_ref not in doc_serializer.get_excluded_refs(**kwargs):
             body = ""
+            span_source: Union[DocItem, list[SerializationResult]] = []
 
-            for i in range(nrows):
+            for i, row in enumerate(item.data.grid):
                 body += "<tr>"
-                for j in range(ncols):
-                    cell: TableCell = item.data.grid[i][j]
+                for j, cell in enumerate(row):
 
                     rowspan, rowstart = (
                         cell.row_span,
@@ -376,7 +373,16 @@ class HTMLTableSerializer(BaseTableSerializer):
                     if colstart != j:
                         continue
 
-                    content = html.escape(cell.text.strip())
+                    if isinstance(cell, RichTableCell):
+                        ser_res = doc_serializer.serialize(
+                            item=cell.ref.resolve(doc=doc), **kwargs
+                        )
+                        content = ser_res.text
+                        span_source = [ser_res]
+                    else:
+                        content = html.escape(cell.text.strip())
+                        span_source = item
+
                     celltag = "td"
                     if cell.column_header or cell.row_header or cell.row_section:
                         celltag = "th"
@@ -389,14 +395,14 @@ class HTMLTableSerializer(BaseTableSerializer):
 
                     text_dir = get_text_direction(content)
                     if text_dir == "rtl":
-                        opening_tag += f' dir="{dir}"'
+                        opening_tag += f' dir="{text_dir}"'
 
                     body += f"<{opening_tag}>{content}</{celltag}>"
                 body += "</tr>"
 
             if body:
                 body = f"<tbody>{body}</tbody>"
-                res_parts.append(create_ser_result(text=body, span_source=item))
+                res_parts.append(create_ser_result(text=body, span_source=span_source))
 
         text_res = "".join([r.text for r in res_parts])
         text_res = f"<table>{text_res}</table>" if text_res else ""
@@ -1057,7 +1063,7 @@ class HTMLDocSerializer(DocSerializer):
         if self.params.html_head is not None:
             return self.params.html_head
 
-        head_parts = ["<head>", '<meta charset="UTF-8">']
+        head_parts = ["<head>", '<meta charset="UTF-8"/>']
 
         # Add metadata if requested
         if params.add_document_metadata:
@@ -1067,7 +1073,7 @@ class HTMLDocSerializer(DocSerializer):
                 head_parts.append("<title>Docling Document</title>")
 
             head_parts.append(
-                '<meta name="generator" content="Docling HTML Serializer">'
+                '<meta name="generator" content="Docling HTML Serializer"/>'
             )
 
         # Add default styles or custom CSS

{docling_core-2.44.2 → docling_core-2.46.0}/docling_core/transforms/serializer/markdown.py

@@ -55,6 +55,7 @@ from docling_core.types.doc.document import (
     PictureItem,
     PictureMoleculeData,
     PictureTabularChartData,
+    RichTableCell,
     SectionHeaderItem,
     TableItem,
     TextItem,
@@ -320,7 +321,13 @@ class MarkdownTableSerializer(BaseTableSerializer):
                 [
                     # make sure that md tables are not broken
                     # due to newline chars in the text
-                    col.text.replace("\n", " ")
+                    (
+                        doc_serializer.serialize(
+                            item=col.ref.resolve(doc=doc), **kwargs
+                        ).text
+                        if isinstance(col, RichTableCell)
+                        else col.text
+                    ).replace("\n", " ")
                     for col in row
                 ]
                 for row in item.data.grid

{docling_core-2.44.2 → docling_core-2.46.0}/docling_core/types/doc/__init__.py

@@ -7,6 +7,7 @@
 
 from .base import BoundingBox, CoordOrigin, ImageRefMode, Size
 from .document import (
+    AnyTableCell,
     BaseAnnotation,
     ChartBar,
     ChartLine,
@@ -52,6 +53,7 @@ from .document import (
     PictureTabularChartData,
     ProvenanceItem,
     RefItem,
+    RichTableCell,
     Script,
     SectionHeaderItem,
     TableCell,