feat: Rich tables support for HTML backend (#2324)

* Rich tables support for HTML backend

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Decoupling JATS backend from HTML backend, ways of creating tables changed significantly

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* updated and added tests

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Refactored parse_table_data in html_backend into few smaller functions

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Changing scope of few functions in html_backend.py, making them static, when possible

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fix for HTML tables that have tbody and/or thead, now these tables are also properly supported

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>

docling/backend/html_backend.py

@@ -17,8 +17,11 @@ from docling_core.types.doc import (
     DocumentOrigin,
     GroupItem,
     GroupLabel,
+    RefItem,
+    RichTableCell,
     TableCell,
     TableData,
+    TableItem,
     TextItem,
 )
 from docling_core.types.doc.document import ContentLayer, Formatting, Script
@@ -276,10 +279,175 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         # reset context
         self.ctx = _Context()
         self._walk(content, doc)
-
         return doc
 
-    def _walk(self, element: Tag, doc: DoclingDocument) -> None:
+    @staticmethod
+    def group_cell_elements(
+        group_name: str,
+        doc: DoclingDocument,
+        provs_in_cell: list[RefItem],
+        docling_table: TableItem,
+    ) -> RefItem:
+        group_element = doc.add_group(
+            label=GroupLabel.UNSPECIFIED,
+            name=group_name,
+            parent=docling_table,
+        )
+        for prov in provs_in_cell:
+            group_element.children.append(prov)
+            pr_item = prov.resolve(doc)
+            item_parent = pr_item.parent.resolve(doc)
+            if pr_item.get_ref() in item_parent.children:
+                item_parent.children.remove(pr_item.get_ref())
+            pr_item.parent = group_element.get_ref()
+        ref_for_rich_cell = group_element.get_ref()
+        return ref_for_rich_cell
+
+    @staticmethod
+    def process_rich_table_cells(
+        provs_in_cell: list[RefItem],
+        group_name: str,
+        doc: DoclingDocument,
+        docling_table: TableItem,
+    ) -> tuple[bool, RefItem]:
+        rich_table_cell = False
+        ref_for_rich_cell = provs_in_cell[0]
+        if len(provs_in_cell) > 1:
+            # Cell has multiple elements, we need to group them
+            rich_table_cell = True
+            ref_for_rich_cell = HTMLDocumentBackend.group_cell_elements(
+                group_name, doc, provs_in_cell, docling_table
+            )
+        elif len(provs_in_cell) == 1:
+            item_ref = provs_in_cell[0]
+            pr_item = item_ref.resolve(doc)
+            if isinstance(pr_item, TextItem):
+                # Cell has only one element and it's just a text
+                rich_table_cell = False
+                doc.delete_items(node_items=[pr_item])
+            else:
+                rich_table_cell = True
+                ref_for_rich_cell = HTMLDocumentBackend.group_cell_elements(
+                    group_name, doc, provs_in_cell, docling_table
+                )
+
+        return rich_table_cell, ref_for_rich_cell
+
+    def parse_table_data(
+        self,
+        element: Tag,
+        doc: DoclingDocument,
+        docling_table: TableItem,
+        num_rows: int,
+        num_cols: int,
+    ) -> Optional[TableData]:
+        for t in cast(list[Tag], element.find_all(["thead", "tbody"], recursive=False)):
+            t.unwrap()
+
+        _log.debug(f"The table has {num_rows} rows and {num_cols} cols.")
+        grid: list = [[None for _ in range(num_cols)] for _ in range(num_rows)]
+        data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])
+
+        # Iterate over the rows in the table
+        start_row_span = 0
+        row_idx = -1
+
+        # We don't want this recursive to support nested tables
+        for row in element("tr", recursive=False):
+            if not isinstance(row, Tag):
+                continue
+            # For each row, find all the column cells (both <td> and <th>)
+            # We don't want this recursive to support nested tables
+            cells = row(["td", "th"], recursive=False)
+            # Check if cell is in a column header or row header
+            col_header = True
+            row_header = True
+            for html_cell in cells:
+                if isinstance(html_cell, Tag):
+                    _, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
+                    if html_cell.name == "td":
+                        col_header = False
+                        row_header = False
+                    elif row_span == 1:
+                        row_header = False
+            if not row_header:
+                row_idx += 1
+                start_row_span = 0
+            else:
+                start_row_span += 1
+
+            # Extract the text content of each cell
+            col_idx = 0
+            for html_cell in cells:
+                if not isinstance(html_cell, Tag):
+                    continue
+
+                # extract inline formulas
+                for formula in html_cell("inline-formula"):
+                    math_parts = formula.text.split("$$")
+                    if len(math_parts) == 3:
+                        math_formula = f"$${math_parts[1]}$$"
+                        formula.replace_with(NavigableString(math_formula))
+
+                provs_in_cell: list[RefItem] = []
+                # Parse table cell sub-tree for Rich Cells content:
+                provs_in_cell = self._walk(html_cell, doc)
+
+                rich_table_cell = False
+                ref_for_rich_cell = None
+                if len(provs_in_cell) > 0:
+                    group_name = f"rich_cell_group_{len(doc.tables)}_{col_idx}_{start_row_span + row_idx}"
+                    rich_table_cell, ref_for_rich_cell = (
+                        HTMLDocumentBackend.process_rich_table_cells(
+                            provs_in_cell, group_name, doc, docling_table
+                        )
+                    )
+
+                # Extracting text
+                text = self.get_text(html_cell).strip()
+                col_span, row_span = self._get_cell_spans(html_cell)
+                if row_header:
+                    row_span -= 1
+                while (
+                    col_idx < num_cols
+                    and grid[row_idx + start_row_span][col_idx] is not None
+                ):
+                    col_idx += 1
+                for r in range(start_row_span, start_row_span + row_span):
+                    for c in range(col_span):
+                        if row_idx + r < num_rows and col_idx + c < num_cols:
+                            grid[row_idx + r][col_idx + c] = text
+
+                if rich_table_cell:
+                    rich_cell = RichTableCell(
+                        text=text,
+                        row_span=row_span,
+                        col_span=col_span,
+                        start_row_offset_idx=start_row_span + row_idx,
+                        end_row_offset_idx=start_row_span + row_idx + row_span,
+                        start_col_offset_idx=col_idx,
+                        end_col_offset_idx=col_idx + col_span,
+                        column_header=col_header,
+                        row_header=((not col_header) and html_cell.name == "th"),
+                        ref=ref_for_rich_cell,  # points to an artificial group around children
+                    )
+                    doc.add_table_cell(table_item=docling_table, cell=rich_cell)
+                else:
+                    simple_cell = TableCell(
+                        text=text,
+                        row_span=row_span,
+                        col_span=col_span,
+                        start_row_offset_idx=start_row_span + row_idx,
+                        end_row_offset_idx=start_row_span + row_idx + row_span,
+                        start_col_offset_idx=col_idx,
+                        end_col_offset_idx=col_idx + col_span,
+                        column_header=col_header,
+                        row_header=((not col_header) and html_cell.name == "th"),
+                    )
+                    doc.add_table_cell(table_item=docling_table, cell=simple_cell)
+        return data
+
+    def _walk(self, element: Tag, doc: DoclingDocument) -> list[RefItem]:
         """Parse an XML tag by recursively walking its content.
 
         While walking, the method buffers inline text across tags like <b> or <span>,
@@ -289,17 +457,18 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             element: The XML tag to parse.
             doc: The Docling document to be updated with the parsed content.
         """
+        added_refs: list[RefItem] = []
         buffer: AnnotatedTextList = AnnotatedTextList()
 
         def flush_buffer():
             if not buffer:
-                return
+                return added_refs
             annotated_text_list: AnnotatedTextList = buffer.simplify_text_elements()
             parts = annotated_text_list.split_by_newline()
             buffer.clear()
 
             if not "".join([el.text for el in annotated_text_list]):
-                return
+                return added_refs
 
             for annotated_text_list in parts:
                 with self._use_inline_group(annotated_text_list, doc):
@@ -309,15 +478,16 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                                 annotated_text.text.strip()
                             )
                             if annotated_text.code:
-                                doc.add_code(
+                                docling_code2 = doc.add_code(
                                     parent=self.parents[self.level],
                                     text=seg_clean,
                                     content_layer=self.content_layer,
                                     formatting=annotated_text.formatting,
                                     hyperlink=annotated_text.hyperlink,
                                 )
+                                added_refs.append(docling_code2.get_ref())
                             else:
-                                doc.add_text(
+                                docling_text2 = doc.add_text(
                                     parent=self.parents[self.level],
                                     label=DocItemLabel.TEXT,
                                     text=seg_clean,
@@ -325,25 +495,31 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                                     formatting=annotated_text.formatting,
                                     hyperlink=annotated_text.hyperlink,
                                 )
+                                added_refs.append(docling_text2.get_ref())
 
         for node in element.contents:
             if isinstance(node, Tag):
                 name = node.name.lower()
                 if name == "img":
                     flush_buffer()
-                    self._emit_image(node, doc)
+                    im_ref3 = self._emit_image(node, doc)
+                    added_refs.append(im_ref3)
                 elif name in _FORMAT_TAG_MAP:
                     with self._use_format([name]):
-                        self._walk(node, doc)
+                        wk = self._walk(node, doc)
+                        added_refs.extend(wk)
                 elif name == "a":
                     with self._use_hyperlink(node):
-                        self._walk(node, doc)
+                        wk2 = self._walk(node, doc)
+                        added_refs.extend(wk2)
                 elif name in _BLOCK_TAGS:
                     flush_buffer()
-                    self._handle_block(node, doc)
+                    blk = self._handle_block(node, doc)
+                    added_refs.extend(blk)
                 elif node.find(_BLOCK_TAGS):
                     flush_buffer()
-                    self._walk(node, doc)
+                    wk3 = self._walk(node, doc)
+                    added_refs.extend(wk3)
                 else:
                     buffer.extend(
                         self._extract_text_and_hyperlink_recursively(
@@ -363,6 +539,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     )
 
         flush_buffer()
+        return added_refs
 
     @staticmethod
     def _collect_parent_format_tags(item: PageElement) -> list[str]:
@@ -581,7 +758,8 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             self.level -= 1
             self.content_layer = current_layer
 
-    def _handle_heading(self, tag: Tag, doc: DoclingDocument) -> None:
+    def _handle_heading(self, tag: Tag, doc: DoclingDocument) -> list[RefItem]:
+        added_ref = []
         tag_name = tag.name.lower()
         # set default content layer to BODY as soon as we encounter a heading
         self.content_layer = ContentLayer.BODY
@@ -596,12 +774,13 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             for key in self.parents.keys():
                 self.parents[key] = None
             self.level = 0
-            self.parents[self.level + 1] = doc.add_title(
+            docling_title = self.parents[self.level + 1] = doc.add_title(
                 text_clean,
                 content_layer=self.content_layer,
                 formatting=annotated_text.formatting,
                 hyperlink=annotated_text.hyperlink,
             )
+            added_ref = [docling_title.get_ref()]
         # the other levels need to be lowered by 1 if a title was set
         else:
             level -= 1
@@ -623,7 +802,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                         _log.debug(f"Remove the tail of level {key}")
                         self.parents[key] = None
                 self.level = level
-            self.parents[self.level + 1] = doc.add_heading(
+            docling_heading = self.parents[self.level + 1] = doc.add_heading(
                 parent=self.parents[self.level],
                 text=text_clean,
                 orig=annotated_text.text,
@@ -632,12 +811,15 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 formatting=annotated_text.formatting,
                 hyperlink=annotated_text.hyperlink,
             )
+            added_ref = [docling_heading.get_ref()]
         self.level += 1
         for img_tag in tag("img"):
             if isinstance(img_tag, Tag):
-                self._emit_image(img_tag, doc)
+                im_ref = self._emit_image(img_tag, doc)
+                added_ref.append(im_ref)
+        return added_ref
 
-    def _handle_list(self, tag: Tag, doc: DoclingDocument) -> None:
+    def _handle_list(self, tag: Tag, doc: DoclingDocument) -> RefItem:
         tag_name = tag.name.lower()
         start: Optional[int] = None
         name: str = ""
@@ -765,20 +947,50 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
         self.parents[self.level + 1] = None
         self.level -= 1
+        return list_group.get_ref()
 
-    def _handle_block(self, tag: Tag, doc: DoclingDocument) -> None:
+    @staticmethod
+    def get_html_table_row_col(tag: Tag) -> tuple[int, int]:
+        for t in cast(list[Tag], tag.find_all(["thead", "tbody"], recursive=False)):
+            t.unwrap()
+        # Find the number of rows and columns (taking into account spans)
+        num_rows: int = 0
+        num_cols: int = 0
+        for row in tag("tr", recursive=False):
+            col_count = 0
+            is_row_header = True
+            if not isinstance(row, Tag):
+                continue
+            for cell in row(["td", "th"], recursive=False):
+                if not isinstance(row, Tag):
+                    continue
+                cell_tag = cast(Tag, cell)
+                col_span, row_span = HTMLDocumentBackend._get_cell_spans(cell_tag)
+                col_count += col_span
+                if cell_tag.name == "td" or row_span == 1:
+                    is_row_header = False
+            num_cols = max(num_cols, col_count)
+            if not is_row_header:
+                num_rows += 1
+        return num_rows, num_cols
+
+    def _handle_block(self, tag: Tag, doc: DoclingDocument) -> list[RefItem]:
+        added_refs = []
         tag_name = tag.name.lower()
 
         if tag_name == "figure":
             img_tag = tag.find("img")
             if isinstance(img_tag, Tag):
-                self._emit_image(img_tag, doc)
+                im_ref = self._emit_image(img_tag, doc)
+                added_refs.append(im_ref)
 
         elif tag_name in {"h1", "h2", "h3", "h4", "h5", "h6"}:
-            self._handle_heading(tag, doc)
+            heading_refs = self._handle_heading(tag, doc)
+            added_refs.extend(heading_refs)
 
         elif tag_name in {"ul", "ol"}:
-            self._handle_list(tag, doc)
+            list_ref = self._handle_list(tag, doc)
+            added_refs.append(list_ref)
 
         elif tag_name in {"p", "address", "summary"}:
             text_list = self._extract_text_and_hyperlink_recursively(
@@ -791,15 +1003,16 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                         if seg := annotated_text.text.strip():
                             seg_clean = HTMLDocumentBackend._clean_unicode(seg)
                             if annotated_text.code:
-                                doc.add_code(
+                                docling_code = doc.add_code(
                                     parent=self.parents[self.level],
                                     text=seg_clean,
                                     content_layer=self.content_layer,
                                     formatting=annotated_text.formatting,
                                     hyperlink=annotated_text.hyperlink,
                                 )
+                                added_refs.append(docling_code.get_ref())
                             else:
-                                doc.add_text(
+                                docling_text = doc.add_text(
                                     parent=self.parents[self.level],
                                     label=DocItemLabel.TEXT,
                                     text=seg_clean,
@@ -807,22 +1020,27 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                                     formatting=annotated_text.formatting,
                                     hyperlink=annotated_text.hyperlink,
                                 )
+                                added_refs.append(docling_text.get_ref())
 
             for img_tag in tag("img"):
                 if isinstance(img_tag, Tag):
                     self._emit_image(img_tag, doc)
 
         elif tag_name == "table":
-            data = HTMLDocumentBackend.parse_table_data(tag)
+            num_rows, num_cols = self.get_html_table_row_col(tag)
+            data_e = TableData(num_rows=num_rows, num_cols=num_cols)
+            docling_table = doc.add_table(
+                data=data_e,
+                parent=self.parents[self.level],
+                content_layer=self.content_layer,
+            )
+            added_refs.append(docling_table.get_ref())
+            self.parse_table_data(tag, doc, docling_table, num_rows, num_cols)
+
             for img_tag in tag("img"):
                 if isinstance(img_tag, Tag):
-                    self._emit_image(tag, doc)
+                    im_ref2 = self._emit_image(tag, doc)
-            if data is not None:
+                    added_refs.append(im_ref2)
-                doc.add_table(
-                    data=data,
-                    parent=self.parents[self.level],
-                    content_layer=self.content_layer,
-                )
 
         elif tag_name in {"pre"}:
             # handle monospace code snippets (pre).
@@ -835,13 +1053,14 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                     text_clean = HTMLDocumentBackend._clean_unicode(
                         annotated_text.text.strip()
                     )
-                    doc.add_code(
+                    docling_code2 = doc.add_code(
                         parent=self.parents[self.level],
                         text=text_clean,
                         content_layer=self.content_layer,
                         formatting=annotated_text.formatting,
                         hyperlink=annotated_text.hyperlink,
                     )
+                    added_refs.append(docling_code2.get_ref())
 
         elif tag_name == "footer":
             with self._use_footer(tag, doc):
@@ -850,8 +1069,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         elif tag_name == "details":
             with self._use_details(tag, doc):
                 self._walk(tag, doc)
+        return added_refs
 
-    def _emit_image(self, img_tag: Tag, doc: DoclingDocument) -> None:
+    def _emit_image(self, img_tag: Tag, doc: DoclingDocument) -> RefItem:
         figure = img_tag.find_parent("figure")
         caption: AnnotatedTextList = AnnotatedTextList()
 
@@ -894,11 +1114,12 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 hyperlink=caption_anno_text.hyperlink,
             )
 
-        doc.add_picture(
+        docling_pic = doc.add_picture(
             caption=caption_item,
             parent=self.parents[self.level],
             content_layer=self.content_layer,
         )
+        return docling_pic.get_ref()
 
     @staticmethod
     def get_text(item: PageElement) -> str:
@@ -996,106 +1217,3 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         )
 
         return int_spans
-
-    @staticmethod
-    def parse_table_data(element: Tag) -> Optional[TableData]:  # noqa: C901
-        nested_tables = element.find("table")
-        if nested_tables is not None:
-            _log.debug("Skipping nested table.")
-            return None
-
-        # Find the number of rows and columns (taking into account spans)
-        num_rows = 0
-        num_cols = 0
-        for row in element("tr"):
-            col_count = 0
-            is_row_header = True
-            if not isinstance(row, Tag):
-                continue
-            for cell in row(["td", "th"]):
-                if not isinstance(row, Tag):
-                    continue
-                cell_tag = cast(Tag, cell)
-                col_span, row_span = HTMLDocumentBackend._get_cell_spans(cell_tag)
-                col_count += col_span
-                if cell_tag.name == "td" or row_span == 1:
-                    is_row_header = False
-            num_cols = max(num_cols, col_count)
-            if not is_row_header:
-                num_rows += 1
-
-        _log.debug(f"The table has {num_rows} rows and {num_cols} cols.")
-
-        grid: list = [[None for _ in range(num_cols)] for _ in range(num_rows)]
-
-        data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])
-
-        # Iterate over the rows in the table
-        start_row_span = 0
-        row_idx = -1
-        for row in element("tr"):
-            if not isinstance(row, Tag):
-                continue
-
-            # For each row, find all the column cells (both <td> and <th>)
-            cells = row(["td", "th"])
-
-            # Check if cell is in a column header or row header
-            col_header = True
-            row_header = True
-            for html_cell in cells:
-                if isinstance(html_cell, Tag):
-                    _, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
-                    if html_cell.name == "td":
-                        col_header = False
-                        row_header = False
-                    elif row_span == 1:
-                        row_header = False
-            if not row_header:
-                row_idx += 1
-                start_row_span = 0
-            else:
-                start_row_span += 1
-
-            # Extract the text content of each cell
-            col_idx = 0
-            for html_cell in cells:
-                if not isinstance(html_cell, Tag):
-                    continue
-
-                # extract inline formulas
-                for formula in html_cell("inline-formula"):
-                    math_parts = formula.text.split("$$")
-                    if len(math_parts) == 3:
-                        math_formula = f"$${math_parts[1]}$$"
-                        formula.replace_with(NavigableString(math_formula))
-
-                # TODO: extract content correctly from table-cells with lists
-                text = HTMLDocumentBackend.get_text(html_cell).strip()
-                col_span, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
-                if row_header:
-                    row_span -= 1
-                while (
-                    col_idx < num_cols
-                    and grid[row_idx + start_row_span][col_idx] is not None
-                ):
-                    col_idx += 1
-                for r in range(start_row_span, start_row_span + row_span):
-                    for c in range(col_span):
-                        if row_idx + r < num_rows and col_idx + c < num_cols:
-                            grid[row_idx + r][col_idx + c] = text
-
-                table_cell = TableCell(
-                    text=text,
-                    row_span=row_span,
-                    col_span=col_span,
-                    start_row_offset_idx=start_row_span + row_idx,
-                    end_row_offset_idx=start_row_span + row_idx + row_span,
-                    start_col_offset_idx=col_idx,
-                    end_col_offset_idx=col_idx + col_span,
-                    column_header=col_header,
-                    row_header=((not col_header) and html_cell.name == "th"),
-                )
-                data.table_cells.append(table_cell)
-
-        return data

docling/backend/xml/jats_backend.py

@@ -2,9 +2,9 @@ import logging
 import traceback
 from io import BytesIO
 from pathlib import Path
-from typing import Final, Optional, Union
+from typing import Final, Optional, Union, cast
 
-from bs4 import BeautifulSoup, Tag
+from bs4 import BeautifulSoup, NavigableString, Tag
 from docling_core.types.doc import (
     DocItemLabel,
     DoclingDocument,
@@ -12,6 +12,8 @@ from docling_core.types.doc import (
     GroupItem,
     GroupLabel,
     NodeItem,
+    TableCell,
+    TableData,
     TextItem,
 )
 from lxml import etree
@@ -535,6 +537,110 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
 
         return
 
+    @staticmethod
+    def parse_table_data(element: Tag) -> Optional[TableData]:  # noqa: C901
+        # TODO, see how to implement proper support for rich tables from HTML backend
+        nested_tables = element.find("table")
+        if nested_tables is not None:
+            _log.debug("Skipping nested table.")
+            return None
+
+        # Find the number of rows and columns (taking into account spans)
+        num_rows = 0
+        num_cols = 0
+        for row in element("tr"):
+            col_count = 0
+            is_row_header = True
+            if not isinstance(row, Tag):
+                continue
+            for cell in row(["td", "th"]):
+                if not isinstance(row, Tag):
+                    continue
+                cell_tag = cast(Tag, cell)
+                col_span, row_span = HTMLDocumentBackend._get_cell_spans(cell_tag)
+                col_count += col_span
+                if cell_tag.name == "td" or row_span == 1:
+                    is_row_header = False
+            num_cols = max(num_cols, col_count)
+            if not is_row_header:
+                num_rows += 1
+
+        _log.debug(f"The table has {num_rows} rows and {num_cols} cols.")
+
+        grid: list = [[None for _ in range(num_cols)] for _ in range(num_rows)]
+
+        data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=[])
+
+        # Iterate over the rows in the table
+        start_row_span = 0
+        row_idx = -1
+        for row in element("tr"):
+            if not isinstance(row, Tag):
+                continue
+
+            # For each row, find all the column cells (both <td> and <th>)
+            cells = row(["td", "th"])
+
+            # Check if cell is in a column header or row header
+            col_header = True
+            row_header = True
+            for html_cell in cells:
+                if isinstance(html_cell, Tag):
+                    _, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
+                    if html_cell.name == "td":
+                        col_header = False
+                        row_header = False
+                    elif row_span == 1:
+                        row_header = False
+            if not row_header:
+                row_idx += 1
+                start_row_span = 0
+            else:
+                start_row_span += 1
+
+            # Extract the text content of each cell
+            col_idx = 0
+            for html_cell in cells:
+                if not isinstance(html_cell, Tag):
+                    continue
+
+                # extract inline formulas
+                for formula in html_cell("inline-formula"):
+                    math_parts = formula.text.split("$$")
+                    if len(math_parts) == 3:
+                        math_formula = f"$${math_parts[1]}$$"
+                        formula.replace_with(NavigableString(math_formula))
+
+                # TODO: extract content correctly from table-cells with lists
+                text = HTMLDocumentBackend.get_text(html_cell).strip()
+                col_span, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
+                if row_header:
+                    row_span -= 1
+                while (
+                    col_idx < num_cols
+                    and grid[row_idx + start_row_span][col_idx] is not None
+                ):
+                    col_idx += 1
+                for r in range(start_row_span, start_row_span + row_span):
+                    for c in range(col_span):
+                        if row_idx + r < num_rows and col_idx + c < num_cols:
+                            grid[row_idx + r][col_idx + c] = text
+
+                table_cell = TableCell(
+                    text=text,
+                    row_span=row_span,
+                    col_span=col_span,
+                    start_row_offset_idx=start_row_span + row_idx,
+                    end_row_offset_idx=start_row_span + row_idx + row_span,
+                    start_col_offset_idx=col_idx,
+                    end_col_offset_idx=col_idx + col_span,
+                    column_header=col_header,
+                    row_header=((not col_header) and html_cell.name == "th"),
+                )
+                data.table_cells.append(table_cell)
+
+        return data
+
     def _add_table(
         self, doc: DoclingDocument, parent: NodeItem, table_xml_component: Table
     ) -> None:
@@ -543,8 +649,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
         if not isinstance(table_tag, Tag):
             return
 
-        data = HTMLDocumentBackend.parse_table_data(table_tag)
+        data = JatsDocumentBackend.parse_table_data(table_tag)
-
         # TODO: format label vs caption once styling is supported
         label = table_xml_component["label"]
         caption = table_xml_component["caption"]
@@ -554,7 +659,6 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
             if table_text
             else None
         )
-
         if data is not None:
             doc.add_table(data=data, parent=parent, caption=table_caption)
 

tests/data/groundtruth/docling_v2/example_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_02.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_02",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_03.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_03",
   "origin": {
     "mimetype": "text/html",
@@ -346,7 +346,8 @@
             "text": "Header 1",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -358,7 +359,8 @@
             "text": "Header 2",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -370,7 +372,8 @@
             "text": "Header 3",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -382,7 +385,8 @@
             "text": "Row 1, Col 1",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -394,7 +398,8 @@
             "text": "Row 1, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -406,7 +411,8 @@
             "text": "Row 1, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -418,7 +424,8 @@
             "text": "Row 2, Col 1",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -430,7 +437,8 @@
             "text": "Row 2, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -442,7 +450,8 @@
             "text": "Row 2, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -454,7 +463,8 @@
             "text": "Row 3, Col 1",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -466,7 +476,8 @@
             "text": "Row 3, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -478,7 +489,8 @@
             "text": "Row 3, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           }
         ],
         "num_rows": 4,
@@ -495,7 +507,8 @@
               "text": "Header 1",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -507,7 +520,8 @@
               "text": "Header 2",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -519,7 +533,8 @@
               "text": "Header 3",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -533,7 +548,8 @@
               "text": "Row 1, Col 1",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -545,7 +561,8 @@
               "text": "Row 1, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -557,7 +574,8 @@
               "text": "Row 1, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -571,7 +589,8 @@
               "text": "Row 2, Col 1",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -583,7 +602,8 @@
               "text": "Row 2, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -595,7 +615,8 @@
               "text": "Row 2, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -609,7 +630,8 @@
               "text": "Row 3, Col 1",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -621,7 +643,8 @@
               "text": "Row 3, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -633,7 +656,8 @@
               "text": "Row 3, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ]
         ]

tests/data/groundtruth/docling_v2/example_04.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_04",
   "origin": {
     "mimetype": "text/html",
@@ -70,7 +70,8 @@
             "text": "Header 1",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -82,7 +83,8 @@
             "text": "Header 2 & 3 (colspan)",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 2,
@@ -94,7 +96,8 @@
             "text": "Row 1 & 2, Col 1 (rowspan)",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -106,7 +109,8 @@
             "text": "Row 1, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -118,7 +122,8 @@
             "text": "Row 1, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -130,7 +135,8 @@
             "text": "Row 2, Col 2 & 3 (colspan)",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -142,7 +148,8 @@
             "text": "Row 3, Col 1",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -154,7 +161,8 @@
             "text": "Row 3, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -166,7 +174,8 @@
             "text": "Row 3, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           }
         ],
         "num_rows": 4,
@@ -183,7 +192,8 @@
               "text": "Header 1",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -195,7 +205,8 @@
               "text": "Header 2 & 3 (colspan)",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -207,7 +218,8 @@
               "text": "Header 2 & 3 (colspan)",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -221,7 +233,8 @@
               "text": "Row 1 & 2, Col 1 (rowspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -233,7 +246,8 @@
               "text": "Row 1, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -245,7 +259,8 @@
               "text": "Row 1, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -259,7 +274,8 @@
               "text": "Row 1 & 2, Col 1 (rowspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -271,7 +287,8 @@
               "text": "Row 2, Col 2 & 3 (colspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -283,7 +300,8 @@
               "text": "Row 2, Col 2 & 3 (colspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -297,7 +315,8 @@
               "text": "Row 3, Col 1",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -309,7 +328,8 @@
               "text": "Row 3, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -321,7 +341,8 @@
               "text": "Row 3, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ]
         ]

tests/data/groundtruth/docling_v2/example_05.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_05",
   "origin": {
     "mimetype": "text/html",
@@ -70,7 +70,8 @@
             "text": "Header 1",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -82,7 +83,8 @@
             "text": "Header 2 & 3 (colspan)",
             "column_header": true,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 2,
@@ -94,7 +96,8 @@
             "text": "Row 1 & 2, Col 1 (rowspan)",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -106,7 +109,8 @@
             "text": "Row 1, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -118,7 +122,8 @@
             "text": "Row 1, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -130,7 +135,8 @@
             "text": "Row 2, Col 2 & 3 (colspan)",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -142,7 +148,8 @@
             "text": "Row 3, Col 1",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -154,7 +161,8 @@
             "text": "Row 3, Col 2",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           },
           {
             "row_span": 1,
@@ -166,7 +174,8 @@
             "text": "Row 3, Col 3",
             "column_header": false,
             "row_header": false,
-            "row_section": false
+            "row_section": false,
+            "fillable": false
           }
         ],
         "num_rows": 4,
@@ -183,7 +192,8 @@
               "text": "Header 1",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -195,7 +205,8 @@
               "text": "Header 2 & 3 (colspan)",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -207,7 +218,8 @@
               "text": "Header 2 & 3 (colspan)",
               "column_header": true,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -221,7 +233,8 @@
               "text": "Row 1 & 2, Col 1 (rowspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -233,7 +246,8 @@
               "text": "Row 1, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -245,7 +259,8 @@
               "text": "Row 1, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -259,7 +274,8 @@
               "text": "Row 1 & 2, Col 1 (rowspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -271,7 +287,8 @@
               "text": "Row 2, Col 2 & 3 (colspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -283,7 +300,8 @@
               "text": "Row 2, Col 2 & 3 (colspan)",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ],
           [
@@ -297,7 +315,8 @@
               "text": "Row 3, Col 1",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -309,7 +328,8 @@
               "text": "Row 3, Col 2",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             },
             {
               "row_span": 1,
@@ -321,7 +341,8 @@
               "text": "Row 3, Col 3",
               "column_header": false,
               "row_header": false,
-              "row_section": false
+              "row_section": false,
+              "fillable": false
             }
           ]
         ]

tests/data/groundtruth/docling_v2/example_06.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_06",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_07.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_07",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_09.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "example_09",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/formatting.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "formatting",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/html_code_snippets.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "html_code_snippets",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/hyperlink_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "hyperlink_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/hyperlink_02.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "hyperlink_02",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/hyperlink_03.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "hyperlink_03",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/hyperlink_04.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "hyperlink_04",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/hyperlink_05.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "hyperlink_05",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/table_01.html.itxt

@@ -0,0 +1,5 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+    item-4 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_01.html.json

@@ -0,0 +1,213 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_01",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 8899613932804813807,
+    "filename": "table_01.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/2"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "1...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "1...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_01.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A    | B    |
+|------|------|
+| 1... | 2... |
+
+After table

tests/data/groundtruth/docling_v2/table_02.html.itxt

@@ -0,0 +1,9 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+      item-4 at level 3: unspecified: group rich_cell_group_1_0_1
+        item-5 at level 4: text: First Paragraph
+        item-6 at level 4: text: Second Paragraph
+        item-7 at level 4: text: Third Paragraph
+    item-8 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_02.html.json

@@ -0,0 +1,277 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_02",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 13259165361873975426,
+    "filename": "table_02.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/tables/0"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/2"
+        },
+        {
+          "$ref": "#/texts/3"
+        },
+        {
+          "$ref": "#/texts/4"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_1_0_1",
+      "label": "unspecified"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/5"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "First Paragraph",
+      "text": "First Paragraph"
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "Second Paragraph",
+      "text": "Second Paragraph"
+    },
+    {
+      "self_ref": "#/texts/4",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "Third Paragraph",
+      "text": "Third Paragraph"
+    },
+    {
+      "self_ref": "#/texts/5",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/0"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "First Paragraph\nSecond Paragraph\nThird Paragraph",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/0"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "First Paragraph\nSecond Paragraph\nThird Paragraph",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_02.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A                                                  | B    |
+|----------------------------------------------------|------|
+| First Paragraph  Second Paragraph  Third Paragraph | 2... |
+
+After table

tests/data/groundtruth/docling_v2/table_03.html.itxt

@@ -0,0 +1,10 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+      item-4 at level 3: unspecified: group rich_cell_group_1_0_1
+        item-5 at level 4: list: group list
+          item-6 at level 5: list_item: First item
+          item-7 at level 5: list_item: Second item
+          item-8 at level 5: list_item: Third item
+    item-9 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_03.html.json

@@ -0,0 +1,297 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_03",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 3098300110939273317,
+    "filename": "table_03.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/groups/1"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/2"
+        },
+        {
+          "$ref": "#/texts/3"
+        },
+        {
+          "$ref": "#/texts/4"
+        }
+      ],
+      "content_layer": "body",
+      "name": "list",
+      "label": "list"
+    },
+    {
+      "self_ref": "#/groups/1",
+      "parent": {
+        "$ref": "#/tables/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/0"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_1_0_1",
+      "label": "unspecified"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/5"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "First item",
+      "text": "First item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Second item",
+      "text": "Second item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/4",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Third item",
+      "text": "Third item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/5",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/1"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "First item Second item Third item",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/1"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "First item Second item Third item",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_03.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A                                       | B    |
+|-----------------------------------------|------|
+| - First item - Second item - Third item | 2... |
+
+After table

tests/data/groundtruth/docling_v2/table_04.html.itxt

@@ -0,0 +1,11 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+      item-4 at level 3: unspecified: group rich_cell_group_1_0_1
+        item-5 at level 4: text: Some text before list
+        item-6 at level 4: list: group list
+          item-7 at level 5: list_item: First item
+          item-8 at level 5: list_item: Second item
+          item-9 at level 5: list_item: Third item
+    item-10 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_04.html.json

@@ -0,0 +1,312 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_04",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 2569676747034209441,
+    "filename": "table_04.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/groups/1"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/3"
+        },
+        {
+          "$ref": "#/texts/4"
+        },
+        {
+          "$ref": "#/texts/5"
+        }
+      ],
+      "content_layer": "body",
+      "name": "list",
+      "label": "list"
+    },
+    {
+      "self_ref": "#/groups/1",
+      "parent": {
+        "$ref": "#/tables/0"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/2"
+        },
+        {
+          "$ref": "#/groups/0"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_1_0_1",
+      "label": "unspecified"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/6"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/groups/1"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "Some text before list",
+      "text": "Some text before list"
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "First item",
+      "text": "First item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/4",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Second item",
+      "text": "Second item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/5",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Third item",
+      "text": "Third item",
+      "enumerated": false,
+      "marker": ""
+    },
+    {
+      "self_ref": "#/texts/6",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/1"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "Some text before list\n                \nFirst item Second item Third item",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/1"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "Some text before list\n                \nFirst item Second item Third item",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_04.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A                                                              | B    |
+|----------------------------------------------------------------|------|
+| Some text before list  - First item - Second item - Third item | 2... |
+
+After table

tests/data/groundtruth/docling_v2/table_05.html.itxt

@@ -0,0 +1,7 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+      item-4 at level 3: unspecified: group rich_cell_group_2_0_1
+        item-5 at level 4: table with [2x3]
+    item-6 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_05.html.json

@@ -0,0 +1,417 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_05",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 12827430000043968589,
+    "filename": "table_05.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/tables/0"
+      },
+      "children": [
+        {
+          "$ref": "#/tables/1"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_2_0_1",
+      "label": "unspecified"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/2"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/0"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A1B1C1\n\n\nD1E1F1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/0"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A1B1C1\n\n\nD1E1F1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    },
+    {
+      "self_ref": "#/tables/1",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "C1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "D1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "E1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "F1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 3,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "C1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "D1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "E1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "F1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_05.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A                                                                    | B    |
+|----------------------------------------------------------------------|------|
+| | A1   | B1   | C1   | |------|------|------| | D1   | E1   | F1   | | 2... |
+
+After table

tests/data/groundtruth/docling_v2/table_06.html.itxt

@@ -0,0 +1,11 @@
+item-0 at level 0: unspecified: group _root_
+  item-1 at level 1: title: Header
+    item-2 at level 2: text: This is the first paragraph.
+    item-3 at level 2: table with [2x2]
+      item-4 at level 3: unspecified: group rich_cell_group_4_0_1
+        item-5 at level 4: table with [2x3]
+          item-6 at level 5: unspecified: group rich_cell_group_4_0_1
+            item-7 at level 6: table with [4x2]
+              item-8 at level 7: unspecified: group rich_cell_group_4_0_2
+                item-9 at level 8: table with [2x2]
+    item-10 at level 2: text: After table

tests/data/groundtruth/docling_v2/table_06.html.json

@@ -0,0 +1,827 @@
+{
+  "schema_name": "DoclingDocument",
+  "version": "1.7.0",
+  "name": "table_06",
+  "origin": {
+    "mimetype": "text/html",
+    "binary_hash": 3950001743588145047,
+    "filename": "table_06.html"
+  },
+  "furniture": {
+    "self_ref": "#/furniture",
+    "children": [],
+    "content_layer": "furniture",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "body": {
+    "self_ref": "#/body",
+    "children": [
+      {
+        "$ref": "#/texts/0"
+      }
+    ],
+    "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/tables/2"
+      },
+      "children": [
+        {
+          "$ref": "#/tables/3"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_4_0_2",
+      "label": "unspecified"
+    },
+    {
+      "self_ref": "#/groups/1",
+      "parent": {
+        "$ref": "#/tables/1"
+      },
+      "children": [
+        {
+          "$ref": "#/tables/2"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_4_0_1",
+      "label": "unspecified"
+    },
+    {
+      "self_ref": "#/groups/2",
+      "parent": {
+        "$ref": "#/tables/0"
+      },
+      "children": [
+        {
+          "$ref": "#/tables/1"
+        }
+      ],
+      "content_layer": "body",
+      "name": "rich_cell_group_4_0_1",
+      "label": "unspecified"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/1"
+        },
+        {
+          "$ref": "#/tables/0"
+        },
+        {
+          "$ref": "#/texts/2"
+        }
+      ],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Header",
+      "text": "Header"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph.",
+      "text": "This is the first paragraph."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "After table",
+      "text": "After table"
+    }
+  ],
+  "pictures": [],
+  "tables": [
+    {
+      "self_ref": "#/tables/0",
+      "parent": {
+        "$ref": "#/texts/0"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/2"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A1B1C1\n\n\nD1\n\n\n\nIII\n\n\nIIIIV\n\n\nV\n\n\n\nE1E2\n\n\nE3E4\n\n\n\n\n\nVIIVIII\n\n\n\nF1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/2"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "2...",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A1B1C1\n\n\nD1\n\n\n\nIII\n\n\nIIIIV\n\n\nV\n\n\n\nE1E2\n\n\nE3E4\n\n\n\n\n\nVIIVIII\n\n\n\nF1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "2...",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    },
+    {
+      "self_ref": "#/tables/1",
+      "parent": {
+        "$ref": "#/groups/2"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/1"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "A1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "B1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "C1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "D1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "III\n\n\nIIIIV\n\n\nV\n\n\n\nE1E2\n\n\nE3E4\n\n\n\n\n\nVIIVIII",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/1"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 2,
+            "end_col_offset_idx": 3,
+            "text": "F1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 3,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "A1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "B1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "C1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "D1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "III\n\n\nIIIIV\n\n\nV\n\n\n\nE1E2\n\n\nE3E4\n\n\n\n\n\nVIIVIII",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 2,
+              "end_col_offset_idx": 3,
+              "text": "F1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    },
+    {
+      "self_ref": "#/tables/2",
+      "parent": {
+        "$ref": "#/groups/1"
+      },
+      "children": [
+        {
+          "$ref": "#/groups/0"
+        }
+      ],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "I",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "II",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "III",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "IV",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "V",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 2,
+            "end_row_offset_idx": 3,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "E1E2\n\n\nE3E4",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false,
+            "ref": {
+              "$ref": "#/groups/0"
+            }
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "VII",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 3,
+            "end_row_offset_idx": 4,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "VIII",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 4,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "I",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "II",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "III",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "IV",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "V",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 2,
+              "end_row_offset_idx": 3,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "E1E2\n\n\nE3E4",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "VII",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 3,
+              "end_row_offset_idx": 4,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "VIII",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    },
+    {
+      "self_ref": "#/tables/3",
+      "parent": {
+        "$ref": "#/groups/0"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "table",
+      "prov": [],
+      "captions": [],
+      "references": [],
+      "footnotes": [],
+      "data": {
+        "table_cells": [
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "E1",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 0,
+            "end_row_offset_idx": 1,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "E2",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 0,
+            "end_col_offset_idx": 1,
+            "text": "E3",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          },
+          {
+            "row_span": 1,
+            "col_span": 1,
+            "start_row_offset_idx": 1,
+            "end_row_offset_idx": 2,
+            "start_col_offset_idx": 1,
+            "end_col_offset_idx": 2,
+            "text": "E4",
+            "column_header": false,
+            "row_header": false,
+            "row_section": false,
+            "fillable": false
+          }
+        ],
+        "num_rows": 2,
+        "num_cols": 2,
+        "grid": [
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "E1",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 0,
+              "end_row_offset_idx": 1,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "E2",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ],
+          [
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 0,
+              "end_col_offset_idx": 1,
+              "text": "E3",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            },
+            {
+              "row_span": 1,
+              "col_span": 1,
+              "start_row_offset_idx": 1,
+              "end_row_offset_idx": 2,
+              "start_col_offset_idx": 1,
+              "end_col_offset_idx": 2,
+              "text": "E4",
+              "column_header": false,
+              "row_header": false,
+              "row_section": false,
+              "fillable": false
+            }
+          ]
+        ]
+      },
+      "annotations": []
+    }
+  ],
+  "key_value_items": [],
+  "form_items": [],
+  "pages": {}
+}

tests/data/groundtruth/docling_v2/table_06.html.md

@@ -0,0 +1,9 @@
+# Header
+
+This is the first paragraph.
+
+| A                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | B    |
+|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------|
+| | A1   | B1                                                                                                                                                                                                                                                                                                | C1   | |------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------| | D1   | | I   | II                                              | |-----|-------------------------------------------------| | III | IV                                              | | V   | | E1   | E2   | |------|------| | E3   | E4   | | | VII | VIII                                            | | F1   | | 2... |
+
+After table

tests/data/groundtruth/docling_v2/unit_test_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.6.0",
+  "version": "1.7.0",
   "name": "unit_test_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/wiki_duck.html.md

@@ -232,24 +232,24 @@ This article is about the bird. For duck as a food, see [Duck as food](/wiki/Duc
 
 "Duckling" redirects here. For other uses, see [Duckling (disambiguation)](/wiki/Duckling_(disambiguation)) .
 
-<!-- image -->
+| Duck                                                     | Duck                      |
+|----------------------------------------------------------|---------------------------|
+|                                                          |                           |
+| [Bufflehead](/wiki/Bufflehead)  *Bucephala albeola*  ( ) |                           |
+| Scientific classification                                | Scientific classification |
+| Domain:                                                  | Eukaryota                 |
+| Kingdom:                                                 | Animalia                  |
+| Phylum:                                                  | Chordata                  |
+| Class:                                                   | Aves                      |
+| Order:                                                   | Anseriformes              |
+| Superfamily:                                             | Anatoidea                 |
+| Family:                                                  | Anatidae                  |
+| Subfamilies                                              | Subfamilies               |
+| See text                                                 | See text                  |
 
 <!-- image -->
 
-| Duck                           | Duck                           |
+<!-- image -->
-|--------------------------------|--------------------------------|
-|                                |                                |
-| Bufflehead (Bucephala albeola) | Bufflehead (Bucephala albeola) |
-| Scientific classification      | Scientific classification      |
-| Domain:                        | Eukaryota                      |
-| Kingdom:                       | Animalia                       |
-| Phylum:                        | Chordata                       |
-| Class:                         | Aves                           |
-| Order:                         | Anseriformes                   |
-| Superfamily:                   | Anatoidea                      |
-| Family:                        | Anatidae                       |
-| Subfamilies                    | Subfamilies                    |
-| See text                       | See text                       |
 
 **Duck** is the common name for numerous species of [waterfowl](/wiki/Waterfowl) in the [family](/wiki/Family_(biology)) [Anatidae](/wiki/Anatidae) . Ducks are generally smaller and shorter-necked than [swans](/wiki/Swan) and [geese](/wiki/Goose) , which are members of the same family. Divided among several subfamilies, they are a [form taxon](/wiki/Form_taxon) ; they do not represent a [monophyletic group](/wiki/Monophyletic_group) (the group of all descendants of a single common ancestral species), since swans and geese are not considered ducks. Ducks are mostly [aquatic birds](/wiki/Aquatic_bird) , and may be found in both fresh water and sea water.
 
@@ -509,12 +509,12 @@ The 1992 Disney film [*The Mighty Ducks*](/wiki/The_Mighty_Ducks_(film)) , starr
 - [Ducks on postage stamps](http://www.stampsbook.org/subject/Duck.html) [Archived](https://web.archive.org/web/20130513022903/http://www.stampsbook.org/subject/Duck.html) 2013-05-13 at the [Wayback Machine](/wiki/Wayback_Machine)
 - [*Ducks at a Distance, by Rob Hines*](https://gutenberg.org/ebooks/18884) at [Project Gutenberg](/wiki/Project_Gutenberg) - A modern illustrated guide to identification of US waterfowl
 
-<!-- image -->
+| Authority control databases   | Authority control databases                                                                                                                                                                                                                                                                                                                                                                                                                              |
+|-------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| National                      | - [United States](https://id.loc.gov/authorities/sh85039879) - [France](https://catalogue.bnf.fr/ark:/12148/cb119761481) - [BnF data](https://data.bnf.fr/ark:/12148/cb119761481) - [Japan](https://id.ndl.go.jp/auth/ndlna/00564819) - [Latvia](https://kopkatalogs.lv/F?func=direct&local_base=lnc10&doc_number=000090751&P_CON_LNG=ENG) - [Israel](http://olduli.nli.org.il/F/?func=find-b&local_base=NLX10&find_code=UID&request=987007565486205171) |
+| Other                         | - [IdRef](https://www.idref.fr/027796124)                                                                                                                                                                                                                                                                                                                                                                                                                |
 
-| Authority control databases   | Authority control databases                       |
+<!-- image -->
-|-------------------------------|---------------------------------------------------|
-| National                      | United States France BnF data Japan Latvia Israel |
-| Other                         | IdRef                                             |
 
 Retrieved from " [https://en.wikipedia.org/w/index.php?title=Duck&amp;oldid=1246843351](https://en.wikipedia.org/w/index.php?title=Duck&oldid=1246843351) "
 

tests/data/html/table_01.html

@@ -0,0 +1,24 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>1...</td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>

tests/data/html/table_02.html

@@ -0,0 +1,24 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>First Paragraph<br>Second Paragraph<br>Third Paragraph</td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>

tests/data/html/table_03.html

@@ -0,0 +1,28 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>
+                <ul>
+                <li>First item</li><li>Second item</li><li>Third item</li>
+                </ul>
+                </td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>

tests/data/html/table_04.html

@@ -0,0 +1,29 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>
+                Some text before list
+                <ul>
+                <li>First item</li><li>Second item</li><li>Third item</li>
+                </ul>
+                </td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>

tests/data/html/table_05.html

@@ -0,0 +1,33 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>
+                    <table>
+                        <tr>
+                            <td>A1</td><td>B1</td><td>C1</td>
+                        </tr>
+                        <tr>
+                            <td>D1</td><td>E1</td><td>F1</td>
+                        </tr>
+                    </table>
+                </td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>

tests/data/html/table_06.html

@@ -0,0 +1,60 @@
+<html>
+    <head>
+        <style>
+            table, th, td {border: 1px solid black; border-collapse: collapse;}
+            td {padding:30px;}
+            table {margin: 30px;}
+        </style>
+    </head>
+    <body>
+        <h1>Header</h1>
+        <p>This is the first paragraph.</p>
+        <table>
+            <tr>
+                <td>A</td>
+                <td>B</td>
+            </tr>
+            <tr>
+                <td>
+                    <table>
+                        <tr>
+                            <td>A1</td><td>B1</td><td>C1</td>
+                        </tr>
+                        <tr>
+                            <td>D1</td>
+                                <td>
+                                    <table>
+                                        <tr>
+                                            <td>I</td><td>II</td>                                            
+                                        </tr>
+                                        <tr>
+                                            <td>III</td><td>IV</td>                                            
+                                        </tr>
+                                        <tr>
+                                            <td>V</td>
+                                            <td>
+                                                <table>
+                                                    <tr>
+                                                        <td>E1</td><td>E2</td>
+                                                    </tr>
+                                                    <tr>
+                                                        <td>E3</td><td>E4</td>
+                                                    </tr>
+                                                </table>
+                                            </td>                                            
+                                        </tr>
+                                        <tr>
+                                            <td>VII</td><td>VIII</td>                                            
+                                        </tr>
+                                    </table>
+                                </td>
+                            <td>F1</td>
+                        </tr>
+                    </table>
+                </td>
+                <td>2...</td>
+            </tr>
+        </table>
+        After table
+    </body>
+</html>