fix: fix HTML table parser and JATS backend bugs (#1948)

Fix a bug in parsing HTML tables in HTML backend.
Fix a bug in test file that prevented JATS backend tests.
Ensure that the JATS backend creates headings with the right level.
Remove unnecessary data files for testing JATS backend.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

docling/backend/html_backend.py

@@ -379,6 +379,25 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         else:
             _log.debug(f"list-item has no text: {element}")
 
+    @staticmethod
+    def _get_cell_spans(cell: Tag) -> tuple[int, int]:
+        """Extract colspan and rowspan values from a table cell tag.
+
+        This function retrieves the 'colspan' and 'rowspan' attributes from a given
+        table cell tag.
+        If the attribute does not exist or it is not numeric, it defaults to 1.
+        """
+        raw_spans: tuple[str, str] = (
+            str(cell.get("colspan", "1")),
+            str(cell.get("rowspan", "1")),
+        )
+        int_spans: tuple[int, int] = (
+            int(raw_spans[0]) if raw_spans[0].isnumeric() else 1,
+            int(raw_spans[1]) if raw_spans[0].isnumeric() else 1,
+        )
+
+        return int_spans
+
     @staticmethod
     def parse_table_data(element: Tag) -> Optional[TableData]:  # noqa: C901
         nested_tables = element.find("table")
@@ -398,10 +417,9 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 if not isinstance(row, Tag):
                     continue
                 cell_tag = cast(Tag, cell)
-                val = cell_tag.get("colspan", "1")
-                colspan = int(val) if (isinstance(val, str) and val.isnumeric()) else 1
-                col_count += colspan
-                if cell_tag.name == "td" or cell_tag.get("rowspan") is None:
+                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:
@@ -428,10 +446,11 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
             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 html_cell.get("rowspan") is None:
+                    elif row_span == 1:
                         row_header = False
             if not row_header:
                 row_idx += 1
@@ -456,18 +475,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
                 text = html_cell.text
 
                 # label = html_cell.name
-                col_val = html_cell.get("colspan", "1")
-                col_span = (
-                    int(col_val)
-                    if isinstance(col_val, str) and col_val.isnumeric()
-                    else 1
-                )
-                row_val = html_cell.get("rowspan", "1")
-                row_span = (
-                    int(row_val)
-                    if isinstance(row_val, str) and row_val.isnumeric()
-                    else 1
-                )
+                col_span, row_span = HTMLDocumentBackend._get_cell_spans(html_cell)
                 if row_header:
                     row_span -= 1
                 while (

docling/backend/xml/jats_backend.py

@@ -93,8 +93,8 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
 
         # Initialize the root of the document hierarchy
         self.root: Optional[NodeItem] = None
-
-        self.valid = False
+        self.hlevel: int = 0
+        self.valid: bool = False
         try:
             if isinstance(self.path_or_stream, BytesIO):
                 self.path_or_stream.seek(0)
@@ -147,6 +147,7 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
                 binary_hash=self.document_hash,
             )
             doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
+            self.hlevel = 0
 
             # Get metadata XML components
             xml_components: XMLComponents = self._parse_metadata()
@@ -304,7 +305,9 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
             title: str = abstract["label"] or DEFAULT_HEADER_ABSTRACT
             if not text:
                 continue
-            parent = doc.add_heading(parent=self.root, text=title)
+            parent = doc.add_heading(
+                parent=self.root, text=title, level=self.hlevel + 1
+            )
             doc.add_text(
                 parent=parent,
                 text=text,
@@ -637,7 +640,10 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
                 elif child.tag == "ack":
                     text = DEFAULT_HEADER_ACKNOWLEDGMENTS
                 if text:
-                    new_parent = doc.add_heading(text=text, parent=parent)
+                    self.hlevel += 1
+                    new_parent = doc.add_heading(
+                        text=text, parent=parent, level=self.hlevel
+                    )
             elif child.tag == "list":
                 new_parent = doc.add_group(
                     label=GroupLabel.LIST, name="list", parent=parent
@@ -694,6 +700,8 @@ class JatsDocumentBackend(DeclarativeDocumentBackend):
                 new_text = self._walk_linear(doc, new_parent, child)
                 if not (node.getparent().tag == "p" and node.tag in flush_tags):
                     node_text += new_text
+                if child.tag in ("sec", "ack") and text:
+                    self.hlevel -= 1
 
             # pick up the tail text
             node_text += child.tail.replace("\n", " ") if child.tail else ""