A new HTML backend that handles styled html (ignors it) as well as images.

- Updated unit tests
- Added documentation (Example notebook)

Note: MyPy fails.
Seems to be a known issue with BeautifulSoup:
https://github.com/python/typeshed/pull/13604

Signed-off-by: Alexander Vaagan <alexander.vaagan@gmail.com>
Signed-off-by: vaaale <2428222+vaaale@users.noreply.github.com>

docling/backend/html_backend.py

@@ -1,22 +1,24 @@
+import base64
 import logging
-import traceback
+import re
+from enum import Enum
 from io import BytesIO
 from pathlib import Path
-from typing import Final, Optional, Union, cast
+from typing import Optional, Union
 
-from bs4 import BeautifulSoup, NavigableString, PageElement, Tag
+import requests
-from bs4.element import PreformattedString
+from bs4 import BeautifulSoup, NavigableString, Tag
 from docling_core.types.doc import (
-    DocItem,
     DocItemLabel,
     DoclingDocument,
     DocumentOrigin,
-    GroupItem,
+    Size,
-    GroupLabel,
     TableCell,
     TableData,
 )
-from docling_core.types.doc.document import ContentLayer
+from docling_core.types.doc.document import ContentLayer, ImageRef
+from PIL import Image, UnidentifiedImageError
+from pydantic import AnyUrl, HttpUrl, ValidationError
 from typing_extensions import override
 
 from docling.backend.abstract_backend import DeclarativeDocumentBackend
@@ -25,56 +27,38 @@ from docling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 
-# tags that generate NodeItem elements
+# Tags that initiate distinct Docling items
-TAGS_FOR_NODE_ITEMS: Final = [
+_BLOCK_TAGS = {"h1", "h2", "h3", "h4", "h5", "h6", "p", "ul", "ol", "table"}
-    "address",
-    "details",
-    "h1",
-    "h2",
-    "h3",
-    "h4",
-    "h5",
-    "h6",
-    "p",
-    "pre",
-    "code",
-    "ul",
-    "ol",
-    "li",
-    "summary",
-    "table",
-    "figure",
-    "img",
-]
 
 
-class HTMLDocumentBackend(DeclarativeDocumentBackend):
+class ImageOptions(str, Enum):
+    """Image options for HTML backend."""
+
+    NONE = "none"
+    INLINE = "inline"
+    REFERENCED = "referenced"
+
+
+class BaseHTMLDocumentBackend(DeclarativeDocumentBackend):
     @override
-    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+    def __init__(
+        self,
+        in_doc: InputDocument,
+        path_or_stream: Union[BytesIO, Path],
+        image_options: Optional[ImageOptions] = ImageOptions.NONE,
+    ):
         super().__init__(in_doc, path_or_stream)
+        self.image_options = image_options
         self.soup: Optional[Tag] = None
-        # HTML file:
-        self.path_or_stream = path_or_stream
-        # Initialise the parents for the hierarchy
-        self.max_levels = 10
-        self.level = 0
-        self.parents: dict[int, Optional[Union[DocItem, GroupItem]]] = {}
-        for i in range(self.max_levels):
-            self.parents[i] = None
-
         try:
-            if isinstance(self.path_or_stream, BytesIO):
+            raw = (
-                text_stream = self.path_or_stream.getvalue()
+                path_or_stream.getvalue()
-                self.soup = BeautifulSoup(text_stream, "html.parser")
+                if isinstance(path_or_stream, BytesIO)
-            if isinstance(self.path_or_stream, Path):
+                else Path(path_or_stream).read_bytes()
-                with open(self.path_or_stream, "rb") as f:
+            )
-                    html_content = f.read()
+            self.soup = BeautifulSoup(raw, "html.parser")
-                    self.soup = BeautifulSoup(html_content, "html.parser")
         except Exception as e:
-            raise RuntimeError(
+            raise RuntimeError(f"Could not initialize HTML backend: {e}")
-                "Could not initialize HTML backend for file with "
-                f"hash {self.document_hash}."
-            ) from e
 
     @override
     def is_valid(self) -> bool:
@@ -89,7 +73,6 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
     def unload(self):
         if isinstance(self.path_or_stream, BytesIO):
             self.path_or_stream.close()
-
         self.path_or_stream = None
 
     @classmethod
@@ -99,490 +82,247 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
     @override
     def convert(self) -> DoclingDocument:
-        # access self.path_or_stream to load stuff
         origin = DocumentOrigin(
             filename=self.file.name or "file",
             mimetype="text/html",
             binary_hash=self.document_hash,
         )
-
         doc = DoclingDocument(name=self.file.stem or "file", origin=origin)
-        _log.debug("Trying to convert HTML...")
+        _log.debug("Starting HTML conversion...")
-
+        if not self.is_valid():
-        if self.is_valid():
+            raise RuntimeError("Invalid HTML document.")
         assert self.soup is not None
-            content = self.soup.body or self.soup
+
-            # Replace <br> tags with newline characters
+        # Remove all script/style content
-            # TODO: remove style to avoid losing text from tags like i, b, span, ...
+        for tag in self.soup.find_all(["script", "style"]):
-            for br in content("br"):
+            tag.decompose()
+
+        body = self.soup.body or self.soup
+        # Normalize <br> tags to newline strings
+        for br in body.find_all("br"):
             br.replace_with(NavigableString("\n"))
 
-            headers = content.find(["h1", "h2", "h3", "h4", "h5", "h6"])
+        # Decide content layer by presence of headers
+        headers = body.find(list(_BLOCK_TAGS))
         self.content_layer = (
             ContentLayer.BODY if headers is None else ContentLayer.FURNITURE
         )
-            self.walk(content, doc)
+
-        else:
+        # Walk the body to build the DoclingDocument
-            raise RuntimeError(
+        self._walk(body, doc, parent=doc.body)
-                f"Cannot convert doc with {self.document_hash} because the backend "
-                "failed to init."
-            )
         return doc
 
-    def walk(self, tag: Tag, doc: DoclingDocument) -> None:
+    def _walk(self, element: Tag, doc: DoclingDocument, parent) -> None:
-        # Iterate over elements in the body of the document
+        """
-        text: str = ""
+        Recursively walk element.contents, buffering inline text across tags like <b> or <span>,
-        for element in tag.children:
+        emitting text nodes only at block boundaries, and extracting images immediately.
-            if isinstance(element, Tag):
+        """
+        buffer: list[str] = []
+
+        def flush_buffer():
+            if not buffer:
+                return
+            text = "".join(buffer).strip()
+            buffer.clear()
+            if not text:
+                return
+            # Split on newlines for <br>
+            for part in text.split("\n"):
+                seg = part.strip()
+                if seg:
+                    doc.add_text(DocItemLabel.TEXT, seg, parent=parent)
+
+        for node in element.contents:
+            # Skip scripts/styles
+            if isinstance(node, Tag) and node.name.lower() in ("script", "style"):
+                continue
+            # Immediate image extraction
+            if isinstance(node, Tag) and node.name.lower() == "img":
+                flush_buffer()
+                self._emit_image(node, doc, parent)
+                continue
+            # Block-level element triggers flush + handle
+            if isinstance(node, Tag) and node.name.lower() in _BLOCK_TAGS:
+                flush_buffer()
+                self._handle_block(node, doc, parent)
+            # Inline tag with nested blocks: recurse
+            elif isinstance(node, Tag) and node.find(list(_BLOCK_TAGS)):
+                flush_buffer()
+                self._walk(node, doc, parent)
+            # Inline text
+            elif isinstance(node, Tag):
+                buffer.append(node.get_text())
+            elif isinstance(node, NavigableString):
+                buffer.append(str(node))
+
+        # Flush any remaining text
+        flush_buffer()
+
+    def _handle_block(self, tag: Tag, doc: DoclingDocument, parent) -> None:
+        tag_name = tag.name.lower()
+        if tag_name == "h1":
+            text = tag.get_text(strip=True)
+            if text:
+                doc.add_title(text, parent=parent)
+            for img_tag in tag.find_all("img", recursive=True):
+                self._emit_image(img_tag, doc, parent)
+        elif tag_name in {"h2", "h3", "h4", "h5", "h6"}:
+            level = int(tag_name[1])
+            text = tag.get_text(strip=True)
+            if text:
+                doc.add_heading(text, level=level, parent=parent)
+            for img_tag in tag.find_all("img", recursive=True):
+                self._emit_image(img_tag, doc, parent)
+        elif tag_name == "p":
+            for part in tag.get_text().split("\n"):
+                seg = part.strip()
+                if seg:
+                    doc.add_text(DocItemLabel.TEXT, seg, parent=parent)
+                for img_tag in tag.find_all("img", recursive=True):
+                    self._emit_image(img_tag, doc, parent)
+        elif tag_name in {"ul", "ol"}:
+            is_ordered = tag_name == "ol"
+            group = (
+                doc.add_ordered_list(parent=parent)
+                if is_ordered
+                else doc.add_unordered_list(parent=parent)
+            )
+            for li in tag.find_all("li", recursive=False):
+                li_text = li.get_text(separator=" ", strip=True)
+                li_item = doc.add_list_item(
+                    text=li_text, enumerated=is_ordered, parent=group
+                )
+                # Nested lists inside <li>
+                for sub in li.find_all(["ul", "ol"], recursive=False):
+                    self._handle_block(sub, doc, parent=group)
+                for img_tag in li.find_all("img", recursive=True):
+                    self._emit_image(img_tag, doc, li_item)
+        elif tag_name == "table":
+            # Add table item and extract nested images
+            data = self._parse_table(tag, doc, parent)
+            doc.add_table(data=data, parent=parent)
+
+    def _emit_image(self, img_tag: Tag, doc: DoclingDocument, parent) -> None:
+        """
+        Helper to create a PictureItem (with optional CAPTION) for an <img> tag.
+        """
+
+        if ImageOptions.NONE == self.image_options:
+            return
+
+        alt = (img_tag.get("alt") or "").strip()
+        caption_item = None
+        if alt:
+            caption_item = doc.add_text(DocItemLabel.CAPTION, alt, parent=parent)
+
+        src_url = img_tag.get("src")
+        width = img_tag.get("width", "128")
+        height = img_tag.get("height", "128")
+        img_ref = None
+        if ImageOptions.INLINE == self.image_options:
             try:
-                    self.analyze_tag(cast(Tag, element), doc)
+                if src_url.startswith("http"):
-                except Exception as exc_child:
+                    img = Image.open(requests.get(src_url, stream=True).raw)
-                    _log.error(
+                elif src_url.startswith("file:"):
-                        f"Error processing child from tag {tag.name}:\n{traceback.format_exc()}"
+                    img = Image.open(src_url)
+                elif src_url.startswith("data:"):
+                    image_data = re.sub("^data:image/.+;base64,", "", src_url)
+                    img = Image.open(BytesIO(base64.b64decode(image_data)))
+                else:
+                    return
+                img_ref = ImageRef.from_pil(img, dpi=int(img.info.get("dpi")[0]))
+            except (FileNotFoundError, UnidentifiedImageError) as ve:
+                _log.warning(f"Could not load image (src={src_url}): {ve}")
+                return
+        elif ImageOptions.REFERENCED == self.image_options:
+            try:
+                img_url = AnyUrl(src_url)
+                img_ref = ImageRef(
+                    uri=img_url,
+                    dpi=72,
+                    mimetype="image/png",
+                    size=Size(width=float(width), height=float(height)),
                 )
-                    raise exc_child
+            except ValidationError as ve:
-            elif isinstance(element, NavigableString) and not isinstance(
+                _log.warning(f"Could not load image (src={src_url}): {ve}")
-                element, PreformattedString
-            ):
-                # Floating text outside paragraphs or analyzed tags
-                text += element
-                siblings: list[Tag] = [
-                    item for item in element.next_siblings if isinstance(item, Tag)
-                ]
-                if element.next_sibling is None or any(
-                    item.name in TAGS_FOR_NODE_ITEMS for item in siblings
-                ):
-                    text = text.strip()
-                    if text and tag.name in ["div"]:
-                        doc.add_text(
-                            parent=self.parents[self.level],
-                            label=DocItemLabel.TEXT,
-                            text=text,
-                            content_layer=self.content_layer,
-                        )
-                    text = ""
-
                 return
 
-    def analyze_tag(self, tag: Tag, doc: DoclingDocument) -> None:
+        doc.add_picture(image=img_ref, caption=caption_item, parent=parent)
-        if tag.name in ["h1", "h2", "h3", "h4", "h5", "h6"]:
-            self.handle_header(tag, doc)
-        elif tag.name in ["p", "address", "summary"]:
-            self.handle_paragraph(tag, doc)
-        elif tag.name in ["pre", "code"]:
-            self.handle_code(tag, doc)
-        elif tag.name in ["ul", "ol"]:
-            self.handle_list(tag, doc)
-        elif tag.name in ["li"]:
-            self.handle_list_item(tag, doc)
-        elif tag.name == "table":
-            self.handle_table(tag, doc)
-        elif tag.name == "figure":
-            self.handle_figure(tag, doc)
-        elif tag.name == "img":
-            self.handle_image(tag, doc)
-        elif tag.name == "details":
-            self.handle_details(tag, doc)
-        else:
-            self.walk(tag, doc)
 
-    def get_text(self, item: PageElement) -> str:
+    def _parse_table(self, table_tag: Tag, doc: DoclingDocument, parent) -> TableData:
-        """Get the text content of a tag."""
+        """
-        parts: list[str] = self.extract_text_recursively(item)
+        Convert an HTML table into TableData, capturing cell spans and text,
-
+        and emitting any nested images as PictureItems.
-        return "".join(parts) + " "
+        """
-
+        # Build TableData
-    # Function to recursively extract text from all child nodes
+        rows = []
-    def extract_text_recursively(self, item: PageElement) -> list[str]:
+        for sec in ("thead", "tbody", "tfoot"):
-        result: list[str] = []
+            section = table_tag.find(sec)
-
+            if section:
-        if isinstance(item, NavigableString):
+                rows.extend(section.find_all("tr", recursive=False))
-            return [item]
+        if not rows:
-
+            rows = table_tag.find_all("tr", recursive=False)
-        tag = cast(Tag, item)
+        occupied: dict[tuple[int, int], bool] = {}
-        if tag.name not in ["ul", "ol"]:
+        cells: list[TableCell] = []
-            for child in tag:
+        max_cols = 0
-                # Recursively get the child's text content
+        for r, tr in enumerate(rows):
-                result.extend(self.extract_text_recursively(child))
+            c = 0
-
+            for cell_tag in tr.find_all(("td", "th"), recursive=False):
-        return ["".join(result) + " "]
+                while occupied.get((r, c)):
-
+                    c += 1
-    def handle_details(self, element: Tag, doc: DoclingDocument) -> None:
+                rs = int(cell_tag.get("rowspan", 1) or 1)
-        """Handle details tag (details) and its content."""
+                cs = int(cell_tag.get("colspan", 1) or 1)
-
+                txt = cell_tag.get_text(strip=True)
-        self.parents[self.level + 1] = doc.add_group(
+                cell = TableCell(
-            name="details",
+                    bbox=None,
-            label=GroupLabel.SECTION,
+                    row_span=rs,
-            parent=self.parents[self.level],
+                    col_span=cs,
-            content_layer=self.content_layer,
+                    start_row_offset_idx=r,
+                    end_row_offset_idx=r + rs,
+                    start_col_offset_idx=c,
+                    end_col_offset_idx=c + cs,
+                    text=txt,
+                    column_header=(cell_tag.name == "th"),
+                    row_header=False,
+                    row_section=False,
                 )
+                cells.append(cell)
+                for dr in range(rs):
+                    for dc in range(cs):
+                        occupied[(r + dr, c + dc)] = True
+                c += cs
+            max_cols = max(max_cols, c)
+        # Emit images inside this table
+        for img_tag in table_tag.find_all("img", recursive=True):
+            self._emit_image(img_tag, doc, parent)
+        return TableData(table_cells=cells, num_rows=len(rows), num_cols=max_cols)
 
-        self.level += 1
-        self.walk(element, doc)
-        self.parents[self.level + 1] = None
-        self.level -= 1
 
-    def handle_header(self, element: Tag, doc: DoclingDocument) -> None:
+class HTMLDocumentBackend(BaseHTMLDocumentBackend):
-        """Handles header tags (h1, h2, etc.)."""
+    @override
-        hlevel = int(element.name.replace("h", ""))
+    def __init__(
-        text = element.text.strip()
+        self,
-
+        in_doc: InputDocument,
-        self.content_layer = ContentLayer.BODY
+        path_or_stream: Union[BytesIO, Path],
-
-        if hlevel == 1:
-            for key in self.parents.keys():
-                self.parents[key] = None
-
-            self.level = 1
-            self.parents[self.level] = doc.add_text(
-                parent=self.parents[0],
-                label=DocItemLabel.TITLE,
-                text=text,
-                content_layer=self.content_layer,
-            )
-        else:
-            if hlevel > self.level:
-                # add invisible group
-                for i in range(self.level + 1, hlevel):
-                    self.parents[i] = doc.add_group(
-                        name=f"header-{i}",
-                        label=GroupLabel.SECTION,
-                        parent=self.parents[i - 1],
-                        content_layer=self.content_layer,
-                    )
-                self.level = hlevel
-
-            elif hlevel < self.level:
-                # remove the tail
-                for key in self.parents.keys():
-                    if key > hlevel:
-                        self.parents[key] = None
-                self.level = hlevel
-
-            self.parents[hlevel] = doc.add_heading(
-                parent=self.parents[hlevel - 1],
-                text=text,
-                level=hlevel - 1,
-                content_layer=self.content_layer,
-            )
-
-    def handle_code(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles monospace code snippets (pre)."""
-        if element.text is None:
-            return
-        text = element.text.strip()
-        if text:
-            doc.add_code(
-                parent=self.parents[self.level],
-                text=text,
-                content_layer=self.content_layer,
-            )
-
-    def handle_paragraph(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles paragraph tags (p) or equivalent ones."""
-        if element.text is None:
-            return
-        text = element.text.strip()
-        if text:
-            doc.add_text(
-                parent=self.parents[self.level],
-                label=DocItemLabel.TEXT,
-                text=text,
-                content_layer=self.content_layer,
-            )
-
-    def handle_list(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles list tags (ul, ol) and their list items."""
-
-        if element.name == "ul":
-            # create a list group
-            self.parents[self.level + 1] = doc.add_group(
-                parent=self.parents[self.level],
-                name="list",
-                label=GroupLabel.LIST,
-                content_layer=self.content_layer,
-            )
-        elif element.name == "ol":
-            start_attr = element.get("start")
-            start: int = (
-                int(start_attr)
-                if isinstance(start_attr, str) and start_attr.isnumeric()
-                else 1
-            )
-            # create a list group
-            self.parents[self.level + 1] = doc.add_group(
-                parent=self.parents[self.level],
-                name="ordered list" + (f" start {start}" if start != 1 else ""),
-                label=GroupLabel.ORDERED_LIST,
-                content_layer=self.content_layer,
-            )
-        self.level += 1
-
-        self.walk(element, doc)
-
-        self.parents[self.level + 1] = None
-        self.level -= 1
-
-    def handle_list_item(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles list item tags (li)."""
-        nested_list = element.find(["ul", "ol"])
-
-        parent = self.parents[self.level]
-        if parent is None:
-            _log.debug(f"list-item has no parent in DoclingDocument: {element}")
-            return
-        parent_label: str = parent.label
-        index_in_list = len(parent.children) + 1
-        if (
-            parent_label == GroupLabel.ORDERED_LIST
-            and isinstance(parent, GroupItem)
-            and parent.name
     ):
-            start_in_list: str = parent.name.split(" ")[-1]
+        super().__init__(in_doc, path_or_stream, image_options=ImageOptions.NONE)
-            start: int = int(start_in_list) if start_in_list.isnumeric() else 1
-            index_in_list += start - 1
 
-        if nested_list:
-            # Text in list item can be hidden within hierarchy, hence
-            # we need to extract it recursively
-            text: str = self.get_text(element)
-            # Flatten text, remove break lines:
-            text = text.replace("\n", "").replace("\r", "")
-            text = " ".join(text.split()).strip()
 
-            marker = ""
+class HTMLDocumentBackendImagesInline(BaseHTMLDocumentBackend):
-            enumerated = False
+    @override
-            if parent_label == GroupLabel.ORDERED_LIST:
+    def __init__(
-                marker = str(index_in_list)
+        self,
-                enumerated = True
+        in_doc: InputDocument,
-
+        path_or_stream: Union[BytesIO, Path],
-            if len(text) > 0:
-                # create a list-item
-                self.parents[self.level + 1] = doc.add_list_item(
-                    text=text,
-                    enumerated=enumerated,
-                    marker=marker,
-                    parent=parent,
-                    content_layer=self.content_layer,
-                )
-                self.level += 1
-                self.walk(element, doc)
-                self.parents[self.level + 1] = None
-                self.level -= 1
-            else:
-                self.walk(element, doc)
-
-        elif element.text.strip():
-            text = element.text.strip()
-
-            marker = ""
-            enumerated = False
-            if parent_label == GroupLabel.ORDERED_LIST:
-                marker = f"{index_in_list!s}."
-                enumerated = True
-            doc.add_list_item(
-                text=text,
-                enumerated=enumerated,
-                marker=marker,
-                parent=parent,
-                content_layer=self.content_layer,
-            )
-        else:
-            _log.debug(f"list-item has no text: {element}")
-
-    @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)
-                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:
-                    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):
-                    if html_cell.name == "td":
-                        col_header = False
-                        row_header = False
-                    elif html_cell.get("rowspan") is None:
-                        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 = 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
-                )
-                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
+        super().__init__(in_doc, path_or_stream, image_options=ImageOptions.INLINE)
-                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
+class HTMLDocumentBackendImagesReferenced(BaseHTMLDocumentBackend):
-
+    @override
-    def handle_table(self, element: Tag, doc: DoclingDocument) -> None:
+    def __init__(
-        """Handles table tags."""
+        self,
-
+        in_doc: InputDocument,
-        table_data = HTMLDocumentBackend.parse_table_data(element)
+        path_or_stream: Union[BytesIO, Path],
-
+    ):
-        if table_data is not None:
+        super().__init__(in_doc, path_or_stream, image_options=ImageOptions.REFERENCED)
-            doc.add_table(
-                data=table_data,
-                parent=self.parents[self.level],
-                content_layer=self.content_layer,
-            )
-
-    def get_list_text(self, list_element: Tag, level: int = 0) -> list[str]:
-        """Recursively extract text from <ul> or <ol> with proper indentation."""
-        result = []
-        bullet_char = "*"  # Default bullet character for unordered lists
-
-        if list_element.name == "ol":  # For ordered lists, use numbers
-            for i, li in enumerate(list_element("li", recursive=False), 1):
-                if not isinstance(li, Tag):
-                    continue
-                # Add numbering for ordered lists
-                result.append(f"{'    ' * level}{i}. {li.get_text(strip=True)}")
-                # Handle nested lists
-                nested_list = li.find(["ul", "ol"])
-                if isinstance(nested_list, Tag):
-                    result.extend(self.get_list_text(nested_list, level + 1))
-        elif list_element.name == "ul":  # For unordered lists, use bullet points
-            for li in list_element("li", recursive=False):
-                if not isinstance(li, Tag):
-                    continue
-                # Add bullet points for unordered lists
-                result.append(
-                    f"{'    ' * level}{bullet_char} {li.get_text(strip=True)}"
-                )
-                # Handle nested lists
-                nested_list = li.find(["ul", "ol"])
-                if isinstance(nested_list, Tag):
-                    result.extend(self.get_list_text(nested_list, level + 1))
-
-        return result
-
-    def handle_figure(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles image tags (img)."""
-
-        # Extract the image URI from the <img> tag
-        # image_uri = root.xpath('//figure//img/@src')[0]
-
-        contains_captions = element.find(["figcaption"])
-        if not isinstance(contains_captions, Tag):
-            doc.add_picture(
-                parent=self.parents[self.level],
-                caption=None,
-                content_layer=self.content_layer,
-            )
-        else:
-            texts = []
-            for item in contains_captions:
-                texts.append(item.text)
-
-            fig_caption = doc.add_text(
-                label=DocItemLabel.CAPTION,
-                text=("".join(texts)).strip(),
-                content_layer=self.content_layer,
-            )
-            doc.add_picture(
-                parent=self.parents[self.level],
-                caption=fig_caption,
-                content_layer=self.content_layer,
-            )
-
-    def handle_image(self, element: Tag, doc: DoclingDocument) -> None:
-        """Handles image tags (img)."""
-        _log.debug(f"ignoring <img> tags at the moment: {element}")
-
-        doc.add_picture(
-            parent=self.parents[self.level],
-            caption=None,
-            content_layer=self.content_layer,
-        )

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

@@ -1,12 +1,11 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Introduction
-    item-2 at level 2: text: This is the first paragraph of the introduction.
+  item-2 at level 1: text: This is the first paragraph of the introduction.
-    item-3 at level 2: section_header: Background
+  item-3 at level 1: section_header: Background
-      item-4 at level 3: text: Some background information here.
+  item-4 at level 1: text: Some background information here.
-      item-5 at level 3: picture
+  item-5 at level 1: list: group group
-      item-6 at level 3: list: group list
+    item-6 at level 2: list_item: First item in unordered list
-        item-7 at level 4: list_item: First item in unordered list
+    item-7 at level 2: list_item: Second item in unordered list
-        item-8 at level 4: list_item: Second item in unordered list
+  item-8 at level 1: ordered_list: group group
-      item-9 at level 3: ordered_list: group ordered list
+    item-9 at level 2: list_item: First item in ordered list
-        item-10 at level 4: list_item: First item in ordered list
+    item-10 at level 2: list_item: Second item in ordered list
-        item-11 at level 4: list_item: Second item in ordered list

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

@@ -19,6 +19,21 @@
     "children": [
       {
         "$ref": "#/texts/0"
+      },
+      {
+        "$ref": "#/texts/1"
+      },
+      {
+        "$ref": "#/texts/2"
+      },
+      {
+        "$ref": "#/texts/3"
+      },
+      {
+        "$ref": "#/groups/0"
+      },
+      {
+        "$ref": "#/groups/1"
       }
     ],
     "content_layer": "body",
@@ -29,7 +44,7 @@
     {
       "self_ref": "#/groups/0",
       "parent": {
-        "$ref": "#/texts/2"
+        "$ref": "#/body"
       },
       "children": [
         {
@@ -40,13 +55,13 @@
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/1",
       "parent": {
-        "$ref": "#/texts/2"
+        "$ref": "#/body"
       },
       "children": [
         {
@@ -57,7 +72,7 @@
         }
       ],
       "content_layer": "body",
-      "name": "ordered list",
+      "name": "group",
       "label": "ordered_list"
     }
   ],
@@ -67,14 +82,7 @@
       "parent": {
         "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/texts/1"
-        },
-        {
-          "$ref": "#/texts/2"
-        }
-      ],
       "content_layer": "body",
       "label": "title",
       "prov": [],
@@ -84,7 +92,7 @@
     {
       "self_ref": "#/texts/1",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -96,33 +104,20 @@
     {
       "self_ref": "#/texts/2",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/texts/3"
-        },
-        {
-          "$ref": "#/pictures/0"
-        },
-        {
-          "$ref": "#/groups/0"
-        },
-        {
-          "$ref": "#/groups/1"
-        }
-      ],
       "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "Background",
       "text": "Background",
-      "level": 1
+      "level": 2
     },
     {
       "self_ref": "#/texts/3",
       "parent": {
-        "$ref": "#/texts/2"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -171,7 +166,7 @@
       "orig": "First item in ordered list",
       "text": "First item in ordered list",
       "enumerated": true,
-      "marker": "1."
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/7",
@@ -185,25 +180,10 @@
       "orig": "Second item in ordered list",
       "text": "Second item in ordered list",
       "enumerated": true,
-      "marker": "2."
+      "marker": "-"
-    }
-  ],
-  "pictures": [
-    {
-      "self_ref": "#/pictures/0",
-      "parent": {
-        "$ref": "#/texts/2"
-      },
-      "children": [],
-      "content_layer": "body",
-      "label": "picture",
-      "prov": [],
-      "captions": [],
-      "references": [],
-      "footnotes": [],
-      "annotations": []
     }
   ],
+  "pictures": [],
   "tables": [],
   "key_value_items": [],
   "form_items": [],

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

@@ -2,12 +2,10 @@
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 
-<!-- image -->
-
 - First item in unordered list
 - Second item in unordered list
 

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

@@ -1,11 +1,11 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Introduction
-    item-2 at level 2: text: This is the first paragraph of the introduction.
+  item-2 at level 1: text: This is the first paragraph of the introduction.
-    item-3 at level 2: section_header: Background
+  item-3 at level 1: section_header: Background
-      item-4 at level 3: text: Some background information here.
+  item-4 at level 1: text: Some background information here.
-      item-5 at level 3: list: group list
+  item-5 at level 1: list: group group
-        item-6 at level 4: list_item: First item in unordered list
+    item-6 at level 2: list_item: First item in unordered list
-        item-7 at level 4: list_item: Second item in unordered list
+    item-7 at level 2: list_item: Second item in unordered list
-      item-8 at level 3: ordered_list: group ordered list
+  item-8 at level 1: ordered_list: group group
-        item-9 at level 4: list_item: First item in ordered list
+    item-9 at level 2: list_item: First item in ordered list
-        item-10 at level 4: list_item: Second item in ordered list
+    item-10 at level 2: list_item: Second item in ordered list

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

@@ -19,86 +19,13 @@
     "children": [
       {
         "$ref": "#/texts/0"
-      }
-    ],
-    "content_layer": "body",
-    "name": "_root_",
-    "label": "unspecified"
       },
-  "groups": [
-    {
-      "self_ref": "#/groups/0",
-      "parent": {
-        "$ref": "#/texts/2"
-      },
-      "children": [
-        {
-          "$ref": "#/texts/4"
-        },
-        {
-          "$ref": "#/texts/5"
-        }
-      ],
-      "content_layer": "body",
-      "name": "list",
-      "label": "list"
-    },
-    {
-      "self_ref": "#/groups/1",
-      "parent": {
-        "$ref": "#/texts/2"
-      },
-      "children": [
-        {
-          "$ref": "#/texts/6"
-        },
-        {
-          "$ref": "#/texts/7"
-        }
-      ],
-      "content_layer": "body",
-      "name": "ordered list",
-      "label": "ordered_list"
-    }
-  ],
-  "texts": [
-    {
-      "self_ref": "#/texts/0",
-      "parent": {
-        "$ref": "#/body"
-      },
-      "children": [
       {
         "$ref": "#/texts/1"
       },
       {
         "$ref": "#/texts/2"
-        }
-      ],
-      "content_layer": "body",
-      "label": "title",
-      "prov": [],
-      "orig": "Introduction",
-      "text": "Introduction"
       },
-    {
-      "self_ref": "#/texts/1",
-      "parent": {
-        "$ref": "#/texts/0"
-      },
-      "children": [],
-      "content_layer": "body",
-      "label": "text",
-      "prov": [],
-      "orig": "This is the first paragraph of the introduction.",
-      "text": "This is the first paragraph of the introduction."
-    },
-    {
-      "self_ref": "#/texts/2",
-      "parent": {
-        "$ref": "#/texts/0"
-      },
-      "children": [
       {
         "$ref": "#/texts/3"
       },
@@ -110,16 +37,87 @@
       }
     ],
     "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [
+    {
+      "self_ref": "#/groups/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/4"
+        },
+        {
+          "$ref": "#/texts/5"
+        }
+      ],
+      "content_layer": "body",
+      "name": "group",
+      "label": "list"
+    },
+    {
+      "self_ref": "#/groups/1",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [
+        {
+          "$ref": "#/texts/6"
+        },
+        {
+          "$ref": "#/texts/7"
+        }
+      ],
+      "content_layer": "body",
+      "name": "group",
+      "label": "ordered_list"
+    }
+  ],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Introduction",
+      "text": "Introduction"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "text",
+      "prov": [],
+      "orig": "This is the first paragraph of the introduction.",
+      "text": "This is the first paragraph of the introduction."
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "Background",
       "text": "Background",
-      "level": 1
+      "level": 2
     },
     {
       "self_ref": "#/texts/3",
       "parent": {
-        "$ref": "#/texts/2"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -168,7 +166,7 @@
       "orig": "First item in ordered list",
       "text": "First item in ordered list",
       "enumerated": true,
-      "marker": "1."
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/7",
@@ -182,7 +180,7 @@
       "orig": "Second item in ordered list",
       "text": "Second item in ordered list",
       "enumerated": true,
-      "marker": "2."
+      "marker": "-"
     }
   ],
   "pictures": [],

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

@@ -2,7 +2,7 @@
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 

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

@@ -1,20 +1,20 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Example Document
-    item-2 at level 2: section_header: Introduction
+  item-2 at level 1: section_header: Introduction
-      item-3 at level 3: text: This is the first paragraph of the introduction.
+  item-3 at level 1: text: This is the first paragraph of the introduction.
-    item-4 at level 2: section_header: Background
+  item-4 at level 1: section_header: Background
-      item-5 at level 3: text: Some background information here.
+  item-5 at level 1: text: Some background information here.
-      item-6 at level 3: list: group list
+  item-6 at level 1: list: group group
-        item-7 at level 4: list_item: First item in unordered list
+    item-7 at level 2: list_item: First item in unordered list Nested item 1 Nested item 2
-          item-8 at level 5: list: group list
+    item-8 at level 2: list: group group
-            item-9 at level 6: list_item: Nested item 1
+      item-9 at level 3: list_item: Nested item 1
-            item-10 at level 6: list_item: Nested item 2
+      item-10 at level 3: list_item: Nested item 2
-        item-11 at level 4: list_item: Second item in unordered list
+    item-11 at level 2: list_item: Second item in unordered list
-      item-12 at level 3: ordered_list: group ordered list
+  item-12 at level 1: ordered_list: group group
-        item-13 at level 4: list_item: First item in ordered list
+    item-13 at level 2: list_item: First item in ordered list Nested ordered item 1 Nested ordered item 2
-          item-14 at level 5: ordered_list: group ordered list
+    item-14 at level 2: ordered_list: group group
-            item-15 at level 6: list_item: Nested ordered item 1
+      item-15 at level 3: list_item: Nested ordered item 1
-            item-16 at level 6: list_item: Nested ordered item 2
+      item-16 at level 3: list_item: Nested ordered item 2
-        item-17 at level 4: list_item: Second item in ordered list
+    item-17 at level 2: list_item: Second item in ordered list
-    item-18 at level 2: section_header: Data Table
+  item-18 at level 1: section_header: Data Table
-      item-19 at level 3: table with [4x3]
+  item-19 at level 1: table with [4x3]

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

@@ -19,6 +19,30 @@
     "children": [
       {
         "$ref": "#/texts/0"
+      },
+      {
+        "$ref": "#/texts/1"
+      },
+      {
+        "$ref": "#/texts/2"
+      },
+      {
+        "$ref": "#/texts/3"
+      },
+      {
+        "$ref": "#/texts/4"
+      },
+      {
+        "$ref": "#/groups/0"
+      },
+      {
+        "$ref": "#/groups/2"
+      },
+      {
+        "$ref": "#/texts/13"
+      },
+      {
+        "$ref": "#/tables/0"
       }
     ],
     "content_layer": "body",
@@ -29,24 +53,27 @@
     {
       "self_ref": "#/groups/0",
       "parent": {
-        "$ref": "#/texts/3"
+        "$ref": "#/body"
       },
       "children": [
         {
           "$ref": "#/texts/5"
         },
+        {
+          "$ref": "#/groups/1"
+        },
         {
           "$ref": "#/texts/8"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/1",
       "parent": {
-        "$ref": "#/texts/5"
+        "$ref": "#/groups/0"
       },
       "children": [
         {
@@ -57,30 +84,33 @@
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/2",
       "parent": {
-        "$ref": "#/texts/3"
+        "$ref": "#/body"
       },
       "children": [
         {
           "$ref": "#/texts/9"
         },
+        {
+          "$ref": "#/groups/3"
+        },
         {
           "$ref": "#/texts/12"
         }
       ],
       "content_layer": "body",
-      "name": "ordered list",
+      "name": "group",
       "label": "ordered_list"
     },
     {
       "self_ref": "#/groups/3",
       "parent": {
-        "$ref": "#/texts/9"
+        "$ref": "#/groups/2"
       },
       "children": [
         {
@@ -91,7 +121,7 @@
         }
       ],
       "content_layer": "body",
-      "name": "ordered list",
+      "name": "group",
       "label": "ordered_list"
     }
   ],
@@ -101,17 +131,7 @@
       "parent": {
         "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/texts/1"
-        },
-        {
-          "$ref": "#/texts/3"
-        },
-        {
-          "$ref": "#/texts/13"
-        }
-      ],
       "content_layer": "body",
       "label": "title",
       "prov": [],
@@ -121,24 +141,20 @@
     {
       "self_ref": "#/texts/1",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/texts/2"
-        }
-      ],
       "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "Introduction",
       "text": "Introduction",
-      "level": 1
+      "level": 2
     },
     {
       "self_ref": "#/texts/2",
       "parent": {
-        "$ref": "#/texts/1"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -150,30 +166,20 @@
     {
       "self_ref": "#/texts/3",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/texts/4"
-        },
-        {
-          "$ref": "#/groups/0"
-        },
-        {
-          "$ref": "#/groups/2"
-        }
-      ],
       "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "Background",
       "text": "Background",
-      "level": 1
+      "level": 2
     },
     {
       "self_ref": "#/texts/4",
       "parent": {
-        "$ref": "#/texts/3"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -187,16 +193,12 @@
       "parent": {
         "$ref": "#/groups/0"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/1"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "First item in unordered list",
+      "orig": "First item in unordered list Nested item 1 Nested item 2",
-      "text": "First item in unordered list",
+      "text": "First item in unordered list Nested item 1 Nested item 2",
       "enumerated": false,
       "marker": "-"
     },
@@ -247,18 +249,14 @@
       "parent": {
         "$ref": "#/groups/2"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/3"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "First item in ordered list",
+      "orig": "First item in ordered list Nested ordered item 1 Nested ordered item 2",
-      "text": "First item in ordered list",
+      "text": "First item in ordered list Nested ordered item 1 Nested ordered item 2",
       "enumerated": true,
-      "marker": "1"
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/10",
@@ -272,7 +270,7 @@
       "orig": "Nested ordered item 1",
       "text": "Nested ordered item 1",
       "enumerated": true,
-      "marker": "1."
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/11",
@@ -286,7 +284,7 @@
       "orig": "Nested ordered item 2",
       "text": "Nested ordered item 2",
       "enumerated": true,
-      "marker": "2."
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/12",
@@ -300,24 +298,20 @@
       "orig": "Second item in ordered list",
       "text": "Second item in ordered list",
       "enumerated": true,
-      "marker": "2."
+      "marker": "-"
     },
     {
       "self_ref": "#/texts/13",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/tables/0"
-        }
-      ],
       "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "Data Table",
       "text": "Data Table",
-      "level": 1
+      "level": 2
     }
   ],
   "pictures": [],
@@ -325,7 +319,7 @@
     {
       "self_ref": "#/tables/0",
       "parent": {
-        "$ref": "#/texts/13"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",

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

@@ -1,24 +1,24 @@
 # Example Document
 
-## Introduction
+### Introduction
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 
-- First item in unordered list
+- First item in unordered list Nested item 1 Nested item 2
     - Nested item 1
     - Nested item 2
 - Second item in unordered list
 
-1. First item in ordered list
+1. First item in ordered list Nested ordered item 1 Nested ordered item 2
     1. Nested ordered item 1
     2. Nested ordered item 2
 2. Second item in ordered list
 
-## Data Table
+### Data Table
 
 | Header 1     | Header 2     | Header 3     |
 |--------------|--------------|--------------|

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

@@ -1,3 +1,3 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Data Table with Rowspan and Colspan
-    item-2 at level 2: table with [4x3]
+  item-2 at level 1: table with [4x3]

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

@@ -19,6 +19,9 @@
     "children": [
       {
         "$ref": "#/texts/0"
+      },
+      {
+        "$ref": "#/tables/0"
       }
     ],
     "content_layer": "body",
@@ -32,11 +35,7 @@
       "parent": {
         "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/tables/0"
-        }
-      ],
       "content_layer": "body",
       "label": "title",
       "prov": [],
@@ -49,7 +48,7 @@
     {
       "self_ref": "#/tables/0",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",

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

@@ -1,3 +1,3 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Omitted html and body tags
-    item-2 at level 2: table with [4x3]
+  item-2 at level 1: table with [4x3]

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

@@ -19,6 +19,9 @@
     "children": [
       {
         "$ref": "#/texts/0"
+      },
+      {
+        "$ref": "#/tables/0"
       }
     ],
     "content_layer": "body",
@@ -32,11 +35,7 @@
       "parent": {
         "$ref": "#/body"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/tables/0"
-        }
-      ],
       "content_layer": "body",
       "label": "title",
       "prov": [],
@@ -49,7 +48,7 @@
     {
       "self_ref": "#/tables/0",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",

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

@@ -5,6 +5,7 @@ This is another div with text.
 This is a regular paragraph.
 
 This is a third div
+
 with a new line.
 
 Heading for the details element

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

@@ -1,22 +1,24 @@
 item-0 at level 0: unspecified: group _root_
-  item-1 at level 1: list: group list
+  item-1 at level 1: list: group group
-    item-2 at level 2: list_item: Asia
+    item-2 at level 2: list_item: Asia China Japan Thailand
-      item-3 at level 3: list: group list
+    item-3 at level 2: list: group group
-        item-4 at level 4: list_item: China
+      item-4 at level 3: list_item: China
-        item-5 at level 4: list_item: Japan
+      item-5 at level 3: list_item: Japan
-        item-6 at level 4: list_item: Thailand
+      item-6 at level 3: list_item: Thailand
-    item-7 at level 2: list_item: Europe
+    item-7 at level 2: list_item: Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria
-      item-8 at level 3: list: group list
+    item-8 at level 2: list: group group
-        item-9 at level 4: list_item: UK
+      item-9 at level 3: list_item: UK
-        item-10 at level 4: list_item: Germany
+      item-10 at level 3: list_item: Germany
-        item-11 at level 4: list_item: Switzerland
+      item-11 at level 3: list_item: Switzerland Bern Aargau
-          item-12 at level 5: list: group list
+      item-12 at level 3: list: group group
-            item-13 at level 6: list: group list
+        item-13 at level 4: list_item: Bern Aargau
-              item-14 at level 7: list_item: Bern
+        item-14 at level 4: list: group group
-              item-15 at level 7: list_item: Aargau
+          item-15 at level 5: list_item: Bern
-        item-16 at level 4: list_item: Italy
+          item-16 at level 5: list_item: Aargau
-          item-17 at level 5: list: group list
+      item-17 at level 3: list_item: Italy Piedmont Liguria
-            item-18 at level 6: list: group list
+      item-18 at level 3: list: group group
-              item-19 at level 7: list_item: Piedmont
+        item-19 at level 4: list_item: Piedmont Liguria
-              item-20 at level 7: list_item: Liguria
+        item-20 at level 4: list: group group
-    item-21 at level 2: list_item: Africa
+          item-21 at level 5: list_item: Piedmont
+          item-22 at level 5: list_item: Liguria
+    item-23 at level 2: list_item: Africa

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

@@ -35,21 +35,27 @@
         {
           "$ref": "#/texts/0"
         },
+        {
+          "$ref": "#/groups/1"
+        },
         {
           "$ref": "#/texts/4"
         },
         {
-          "$ref": "#/texts/13"
+          "$ref": "#/groups/2"
+        },
+        {
+          "$ref": "#/texts/15"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/1",
       "parent": {
-        "$ref": "#/texts/0"
+        "$ref": "#/groups/0"
       },
       "children": [
         {
@@ -63,13 +69,13 @@
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/2",
       "parent": {
-        "$ref": "#/texts/4"
+        "$ref": "#/groups/0"
       },
       "children": [
         {
@@ -82,25 +88,34 @@
           "$ref": "#/texts/7"
         },
         {
-          "$ref": "#/texts/10"
+          "$ref": "#/groups/3"
+        },
+        {
+          "$ref": "#/texts/11"
+        },
+        {
+          "$ref": "#/groups/5"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/3",
       "parent": {
-        "$ref": "#/texts/7"
+        "$ref": "#/groups/2"
       },
       "children": [
+        {
+          "$ref": "#/texts/8"
+        },
         {
           "$ref": "#/groups/4"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
@@ -110,28 +125,31 @@
       },
       "children": [
         {
-          "$ref": "#/texts/8"
+          "$ref": "#/texts/9"
         },
         {
-          "$ref": "#/texts/9"
+          "$ref": "#/texts/10"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
       "self_ref": "#/groups/5",
       "parent": {
-        "$ref": "#/texts/10"
+        "$ref": "#/groups/2"
       },
       "children": [
+        {
+          "$ref": "#/texts/12"
+        },
         {
           "$ref": "#/groups/6"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     },
     {
@@ -141,14 +159,14 @@
       },
       "children": [
         {
-          "$ref": "#/texts/11"
+          "$ref": "#/texts/13"
         },
         {
-          "$ref": "#/texts/12"
+          "$ref": "#/texts/14"
         }
       ],
       "content_layer": "body",
-      "name": "list",
+      "name": "group",
       "label": "list"
     }
   ],
@@ -158,16 +176,12 @@
       "parent": {
         "$ref": "#/groups/0"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/1"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "Asia",
+      "orig": "Asia China Japan Thailand",
-      "text": "Asia",
+      "text": "Asia China Japan Thailand",
       "enumerated": false,
       "marker": "-"
     },
@@ -218,16 +232,12 @@
       "parent": {
         "$ref": "#/groups/0"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/2"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "Europe",
+      "orig": "Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria",
-      "text": "Europe",
+      "text": "Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria",
       "enumerated": false,
       "marker": "-"
     },
@@ -264,21 +274,31 @@
       "parent": {
         "$ref": "#/groups/2"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/3"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "Switzerland",
+      "orig": "Switzerland Bern Aargau",
-      "text": "Switzerland",
+      "text": "Switzerland Bern Aargau",
       "enumerated": false,
       "marker": "-"
     },
     {
       "self_ref": "#/texts/8",
+      "parent": {
+        "$ref": "#/groups/3"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Bern Aargau",
+      "text": "Bern Aargau",
+      "enumerated": false,
+      "marker": "-"
+    },
+    {
+      "self_ref": "#/texts/9",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -292,7 +312,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/9",
+      "self_ref": "#/texts/10",
       "parent": {
         "$ref": "#/groups/4"
       },
@@ -306,25 +326,35 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/10",
+      "self_ref": "#/texts/11",
       "parent": {
         "$ref": "#/groups/2"
       },
-      "children": [
+      "children": [],
-        {
-          "$ref": "#/groups/5"
-        }
-      ],
       "content_layer": "body",
       "label": "list_item",
       "prov": [],
-      "orig": "Italy",
+      "orig": "Italy Piedmont Liguria",
-      "text": "Italy",
+      "text": "Italy Piedmont Liguria",
       "enumerated": false,
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/11",
+      "self_ref": "#/texts/12",
+      "parent": {
+        "$ref": "#/groups/5"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "list_item",
+      "prov": [],
+      "orig": "Piedmont Liguria",
+      "text": "Piedmont Liguria",
+      "enumerated": false,
+      "marker": "-"
+    },
+    {
+      "self_ref": "#/texts/13",
       "parent": {
         "$ref": "#/groups/6"
       },
@@ -338,7 +368,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/12",
+      "self_ref": "#/texts/14",
       "parent": {
         "$ref": "#/groups/6"
       },
@@ -352,7 +382,7 @@
       "marker": "-"
     },
     {
-      "self_ref": "#/texts/13",
+      "self_ref": "#/texts/15",
       "parent": {
         "$ref": "#/groups/0"
       },

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

@@ -1,14 +1,16 @@
-- Asia
+- Asia China Japan Thailand
     - China
     - Japan
     - Thailand
-- Europe
+- Europe UK Germany Switzerland Bern Aargau Italy Piedmont Liguria
     - UK
     - Germany
-    - Switzerland
+    - Switzerland Bern Aargau
+        - Bern Aargau
             - Bern
             - Aargau
-    - Italy
+    - Italy Piedmont Liguria
+        - Piedmont Liguria
             - Piedmont
             - Liguria
 - Africa

tests/data/groundtruth/docling_v2/mixed.md.md

@@ -2,7 +2,7 @@
 
 Some text
 
-## Famous ducks
+### Famous ducks
 
 Here is a table:
 

tests/data/groundtruth/docling_v2/mixed_without_h1.md.md

@@ -1,8 +1,10 @@
-## Some heading
+Content before first heading
+
+### Some heading
+
+This is HTML
 
 - A. first
-    - subitem
 - B. second
-    1. strange
 
 The end!

tests/data/groundtruth/docling_v2/nested.md.md

@@ -3,29 +3,64 @@
 A list featuring nesting:
 
 - abc
-    - abc123
-        - abc1234
-            - abc12345
-                - a.
-                - b.
-        - abcd1234：
-            - abcd12345：
-                - a.
-                - b.
 - def：
-    - def1234：
-        - def12345。
 - after one empty line
-    - foo
 - afer two empty lines
-    - bar
 
 - changing symbol
 
 A nested HTML list:
 
 - First item
-- Second item with subitems:
+- Second item with subitems: Subitem 1 Subitem 2
     - Subitem 1
     - Subitem 2
 - Last list item
+
+Table nesting apparently not yet suported by HTML backend:
+
+<table>
+
+<tr>
+
+<td>Cell</td>
+
+<td>Nested Table
+
+<table>
+
+<tr>
+
+<td>Cell 1</td>
+
+<>
+
+</tr>
+
+<tr>
+
+<td>Cell 2</td>
+
+</tr>
+
+<tr>
+
+<td>Cell 3</td>
+
+</tr>
+
+<tr>
+
+<td>Cell 4</td>
+
+</tr>
+
+</table>
+
+</td>
+
+</tr>
+
+<tr><td>additional row</td></tr>
+
+</table>

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

@@ -1,9 +1,8 @@
 item-0 at level 0: unspecified: group _root_
   item-1 at level 1: title: Title
-    item-2 at level 2: section_header: section-1
+  item-2 at level 1: section_header: section-1
-      item-3 at level 3: section_header: section-1.1
+  item-3 at level 1: section_header: section-1.1
-    item-4 at level 2: section_header: section-2
+  item-4 at level 1: section_header: section-2
-      item-5 at level 3: section: group header-3
+  item-5 at level 1: section_header: section-2.0.1
-        item-6 at level 4: section_header: section-2.0.1
+  item-6 at level 1: section_header: section-2.2
-      item-7 at level 3: section_header: section-2.2
+  item-7 at level 1: section_header: section-2.3
-      item-8 at level 3: section_header: section-2.3

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

@@ -19,86 +19,18 @@
     "children": [
       {
         "$ref": "#/texts/0"
-      }
-    ],
-    "content_layer": "body",
-    "name": "_root_",
-    "label": "unspecified"
       },
-  "groups": [
-    {
-      "self_ref": "#/groups/0",
-      "parent": {
-        "$ref": "#/texts/3"
-      },
-      "children": [
-        {
-          "$ref": "#/texts/4"
-        }
-      ],
-      "content_layer": "body",
-      "name": "header-3",
-      "label": "section"
-    }
-  ],
-  "texts": [
-    {
-      "self_ref": "#/texts/0",
-      "parent": {
-        "$ref": "#/body"
-      },
-      "children": [
       {
         "$ref": "#/texts/1"
       },
-        {
-          "$ref": "#/texts/3"
-        }
-      ],
-      "content_layer": "body",
-      "label": "title",
-      "prov": [],
-      "orig": "Title",
-      "text": "Title"
-    },
-    {
-      "self_ref": "#/texts/1",
-      "parent": {
-        "$ref": "#/texts/0"
-      },
-      "children": [
       {
         "$ref": "#/texts/2"
-        }
-      ],
-      "content_layer": "body",
-      "label": "section_header",
-      "prov": [],
-      "orig": "section-1",
-      "text": "section-1",
-      "level": 1
       },
       {
-      "self_ref": "#/texts/2",
+        "$ref": "#/texts/3"
-      "parent": {
-        "$ref": "#/texts/1"
-      },
-      "children": [],
-      "content_layer": "body",
-      "label": "section_header",
-      "prov": [],
-      "orig": "section-1.1",
-      "text": "section-1.1",
-      "level": 2
       },
       {
-      "self_ref": "#/texts/3",
+        "$ref": "#/texts/4"
-      "parent": {
-        "$ref": "#/texts/0"
-      },
-      "children": [
-        {
-          "$ref": "#/groups/0"
       },
       {
         "$ref": "#/texts/5"
@@ -108,16 +40,66 @@
       }
     ],
     "content_layer": "body",
+    "name": "_root_",
+    "label": "unspecified"
+  },
+  "groups": [],
+  "texts": [
+    {
+      "self_ref": "#/texts/0",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "title",
+      "prov": [],
+      "orig": "Title",
+      "text": "Title"
+    },
+    {
+      "self_ref": "#/texts/1",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "section_header",
+      "prov": [],
+      "orig": "section-1",
+      "text": "section-1",
+      "level": 2
+    },
+    {
+      "self_ref": "#/texts/2",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
+      "label": "section_header",
+      "prov": [],
+      "orig": "section-1.1",
+      "text": "section-1.1",
+      "level": 3
+    },
+    {
+      "self_ref": "#/texts/3",
+      "parent": {
+        "$ref": "#/body"
+      },
+      "children": [],
+      "content_layer": "body",
       "label": "section_header",
       "prov": [],
       "orig": "section-2",
       "text": "section-2",
-      "level": 1
+      "level": 2
     },
     {
       "self_ref": "#/texts/4",
       "parent": {
-        "$ref": "#/groups/0"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -125,12 +107,12 @@
       "prov": [],
       "orig": "section-2.0.1",
       "text": "section-2.0.1",
-      "level": 3
+      "level": 4
     },
     {
       "self_ref": "#/texts/5",
       "parent": {
-        "$ref": "#/texts/3"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -138,12 +120,12 @@
       "prov": [],
       "orig": "section-2.2",
       "text": "section-2.2",
-      "level": 2
+      "level": 3
     },
     {
       "self_ref": "#/texts/6",
       "parent": {
-        "$ref": "#/texts/3"
+        "$ref": "#/body"
       },
       "children": [],
       "content_layer": "body",
@@ -151,7 +133,7 @@
       "prov": [],
       "orig": "section-2.3",
       "text": "section-2.3",
-      "level": 2
+      "level": 3
     }
   ],
   "pictures": [],

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

@@ -1,13 +1,13 @@
 # Title
 
-## section-1
+### section-1
 
-### section-1.1
+#### section-1.1
 
-## section-2
+### section-2
 
-#### section-2.0.1
+##### section-2.0.1
 
-### section-2.2
+#### section-2.2
 
-### section-2.3
+#### section-2.3

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

@@ -1,458 +1,517 @@
 item-0 at level 0: unspecified: group _root_
-  item-1 at level 1: section: group header-1
+  item-1 at level 1: text: Jump to content
-    item-2 at level 2: section_header: Contents
+  item-2 at level 1: text: Main menu
-      item-3 at level 3: list: group list
+  item-3 at level 1: text: Main menu
-        item-4 at level 4: list_item: (Top)
+  item-4 at level 1: text: move to sidebar
-        item-5 at level 4: list_item: 1 Etymology
+  item-5 at level 1: text: hide
-          item-6 at level 5: list: group list
+  item-6 at level 1: text: Navigation
-        item-7 at level 4: list_item: 2 Taxonomy
+  item-7 at level 1: list: group group
-          item-8 at level 5: list: group list
+    item-8 at level 2: list_item: Main page
-        item-9 at level 4: list_item: 3 Morphology
+    item-9 at level 2: list_item: Contents
-          item-10 at level 5: list: group list
+    item-10 at level 2: list_item: Current events
-        item-11 at level 4: list_item: 4 Distribution and habitat
+    item-11 at level 2: list_item: Random article
-          item-12 at level 5: list: group list
+    item-12 at level 2: list_item: About Wikipedia
-        item-13 at level 4: list_item: 5 Behaviour Toggle Behaviour subsection
+    item-13 at level 2: list_item: Contact us
-          item-14 at level 5: list: group list
+  item-14 at level 1: text: Contribute
-            item-15 at level 6: list_item: 5.1 Feeding
+  item-15 at level 1: list: group group
-              item-16 at level 7: list: group list
+    item-16 at level 2: list_item: Help
-            item-17 at level 6: list_item: 5.2 Breeding
+    item-17 at level 2: list_item: Learn to edit
-              item-18 at level 7: list: group list
+    item-18 at level 2: list_item: Community portal
-            item-19 at level 6: list_item: 5.3 Communication
+    item-19 at level 2: list_item: Recent changes
-              item-20 at level 7: list: group list
+    item-20 at level 2: list_item: Upload file
-            item-21 at level 6: list_item: 5.4 Predators
+  item-21 at level 1: text: Search
-              item-22 at level 7: list: group list
+  item-22 at level 1: text: Search
-        item-23 at level 4: list_item: 6 Relationship with humans Toggle Relationship with humans subsection
+  item-23 at level 1: list: group group
-          item-24 at level 5: list: group list
+  item-24 at level 1: list: group group
-            item-25 at level 6: list_item: 6.1 Hunting
+    item-25 at level 2: list_item: Donate
-              item-26 at level 7: list: group list
+  item-26 at level 1: text: Appearance
-            item-27 at level 6: list_item: 6.2 Domestication
+  item-27 at level 1: list: group group
-              item-28 at level 7: list: group list
+  item-28 at level 1: list: group group
-            item-29 at level 6: list_item: 6.3 Heraldry
+    item-29 at level 2: list_item: Create account
-              item-30 at level 7: list: group list
+    item-30 at level 2: list_item: Log in
-            item-31 at level 6: list_item: 6.4 Cultural references
+  item-31 at level 1: text: Personal tools
-              item-32 at level 7: list: group list
+  item-32 at level 1: list: group group
-        item-33 at level 4: list_item: 7 See also
+    item-33 at level 2: list_item: Create account
-          item-34 at level 5: list: group list
+    item-34 at level 2: list_item: Log in
-        item-35 at level 4: list_item: 8 Notes Toggle Notes subsection
+  item-35 at level 1: text: Pages for logged out editors learn more
-          item-36 at level 5: list: group list
+  item-36 at level 1: list: group group
-            item-37 at level 6: list_item: 8.1 Citations
+    item-37 at level 2: list_item: Contributions
-              item-38 at level 7: list: group list
+    item-38 at level 2: list_item: Talk
-            item-39 at level 6: list_item: 8.2 Sources
+  item-39 at level 1: section_header: Contents
-              item-40 at level 7: list: group list
+  item-40 at level 1: text: move to sidebar
-        item-41 at level 4: list_item: 9 External links
+  item-41 at level 1: text: hide
-          item-42 at level 5: list: group list
+  item-42 at level 1: list: group group
-  item-43 at level 1: title: Duck
+    item-43 at level 2: list_item: (Top)
-    item-44 at level 2: list: group list
+    item-44 at level 2: list_item: 1 Etymology
-      item-45 at level 3: list_item: Acèh
+    item-45 at level 2: list: group group
-      item-46 at level 3: list_item: Afrikaans
+    item-46 at level 2: list_item: 2 Taxonomy
-      item-47 at level 3: list_item: Alemannisch
+    item-47 at level 2: list: group group
-      item-48 at level 3: list_item: አማርኛ
+    item-48 at level 2: list_item: 3 Morphology
-      item-49 at level 3: list_item: Ænglisc
+    item-49 at level 2: list: group group
-      item-50 at level 3: list_item: العربية
+    item-50 at level 2: list_item: 4 Distribution and habitat
-      item-51 at level 3: list_item: Aragonés
+    item-51 at level 2: list: group group
-      item-52 at level 3: list_item: ܐܪܡܝܐ
+    item-52 at level 2: list_item: 5 Behaviour Toggle Behaviour sub ... eeding 5.3 Communication 5.4 Predators
-      item-53 at level 3: list_item: Armãneashti
+    item-53 at level 2: list: group group
-      item-54 at level 3: list_item: Asturianu
+      item-54 at level 3: list_item: 5.1 Feeding
-      item-55 at level 3: list_item: Atikamekw
+      item-55 at level 3: list: group group
-      item-56 at level 3: list_item: Авар
+      item-56 at level 3: list_item: 5.2 Breeding
-      item-57 at level 3: list_item: Aymar aru
+      item-57 at level 3: list: group group
-      item-58 at level 3: list_item: تۆرکجه
+      item-58 at level 3: list_item: 5.3 Communication
-      item-59 at level 3: list_item: Basa Bali
+      item-59 at level 3: list: group group
-      item-60 at level 3: list_item: বাংলা
+      item-60 at level 3: list_item: 5.4 Predators
-      item-61 at level 3: list_item: 閩南語 / Bân-lâm-gú
+      item-61 at level 3: list: group group
-      item-62 at level 3: list_item: Беларуская
+    item-62 at level 2: list_item: 6 Relationship with humans Toggl ... n 6.3 Heraldry 6.4 Cultural references
-      item-63 at level 3: list_item: Беларуская (тарашкевіца)
+    item-63 at level 2: list: group group
-      item-64 at level 3: list_item: Bikol Central
+      item-64 at level 3: list_item: 6.1 Hunting
-      item-65 at level 3: list_item: Български
+      item-65 at level 3: list: group group
-      item-66 at level 3: list_item: Brezhoneg
+      item-66 at level 3: list_item: 6.2 Domestication
-      item-67 at level 3: list_item: Буряад
+      item-67 at level 3: list: group group
-      item-68 at level 3: list_item: Català
+      item-68 at level 3: list_item: 6.3 Heraldry
-      item-69 at level 3: list_item: Чӑвашла
+      item-69 at level 3: list: group group
-      item-70 at level 3: list_item: Čeština
+      item-70 at level 3: list_item: 6.4 Cultural references
-      item-71 at level 3: list_item: ChiShona
+      item-71 at level 3: list: group group
-      item-72 at level 3: list_item: Cymraeg
+    item-72 at level 2: list_item: 7 See also
-      item-73 at level 3: list_item: Dagbanli
+    item-73 at level 2: list: group group
-      item-74 at level 3: list_item: Dansk
+    item-74 at level 2: list_item: 8 Notes Toggle Notes subsection 8.1 Citations 8.2 Sources
-      item-75 at level 3: list_item: Deitsch
+    item-75 at level 2: list: group group
-      item-76 at level 3: list_item: Deutsch
+      item-76 at level 3: list_item: 8.1 Citations
-      item-77 at level 3: list_item: डोटेली
+      item-77 at level 3: list: group group
-      item-78 at level 3: list_item: Ελληνικά
+      item-78 at level 3: list_item: 8.2 Sources
-      item-79 at level 3: list_item: Emiliàn e rumagnòl
+      item-79 at level 3: list: group group
-      item-80 at level 3: list_item: Español
+    item-80 at level 2: list_item: 9 External links
-      item-81 at level 3: list_item: Esperanto
+    item-81 at level 2: list: group group
-      item-82 at level 3: list_item: Euskara
+  item-82 at level 1: text: Toggle the table of contents
-      item-83 at level 3: list_item: فارسی
+  item-83 at level 1: title: Duck
-      item-84 at level 3: list_item: Français
+  item-84 at level 1: text: 136 languages
-      item-85 at level 3: list_item: Gaeilge
+  item-85 at level 1: list: group group
-      item-86 at level 3: list_item: Galego
+    item-86 at level 2: list_item: Acèh
-      item-87 at level 3: list_item: ГӀалгӀай
+    item-87 at level 2: list_item: Afrikaans
-      item-88 at level 3: list_item: 贛語
+    item-88 at level 2: list_item: Alemannisch
-      item-89 at level 3: list_item: گیلکی
+    item-89 at level 2: list_item: አማርኛ
-      item-90 at level 3: list_item: 𐌲𐌿𐍄𐌹𐍃𐌺
+    item-90 at level 2: list_item: Ænglisc
-      item-91 at level 3: list_item: गोंयची कोंकणी / Gõychi Konknni
+    item-91 at level 2: list_item: العربية
-      item-92 at level 3: list_item: 客家語 / Hak-kâ-ngî
+    item-92 at level 2: list_item: Aragonés
-      item-93 at level 3: list_item: 한국어
+    item-93 at level 2: list_item: ܐܪܡܝܐ
-      item-94 at level 3: list_item: Hausa
+    item-94 at level 2: list_item: Armãneashti
-      item-95 at level 3: list_item: Հայերեն
+    item-95 at level 2: list_item: Asturianu
-      item-96 at level 3: list_item: हिन्दी
+    item-96 at level 2: list_item: Atikamekw
-      item-97 at level 3: list_item: Hrvatski
+    item-97 at level 2: list_item: Авар
-      item-98 at level 3: list_item: Ido
+    item-98 at level 2: list_item: Aymar aru
-      item-99 at level 3: list_item: Bahasa Indonesia
+    item-99 at level 2: list_item: تۆرکجه
-      item-100 at level 3: list_item: Iñupiatun
+    item-100 at level 2: list_item: Basa Bali
-      item-101 at level 3: list_item: Íslenska
+    item-101 at level 2: list_item: বাংলা
-      item-102 at level 3: list_item: Italiano
+    item-102 at level 2: list_item: 閩南語 / Bân-lâm-gú
-      item-103 at level 3: list_item: עברית
+    item-103 at level 2: list_item: Беларуская
-      item-104 at level 3: list_item: Jawa
+    item-104 at level 2: list_item: Беларуская (тарашкевіца)
-      item-105 at level 3: list_item: ಕನ್ನಡ
+    item-105 at level 2: list_item: Bikol Central
-      item-106 at level 3: list_item: Kapampangan
+    item-106 at level 2: list_item: Български
-      item-107 at level 3: list_item: ქართული
+    item-107 at level 2: list_item: Brezhoneg
-      item-108 at level 3: list_item: कॉशुर / کٲشُر
+    item-108 at level 2: list_item: Буряад
-      item-109 at level 3: list_item: Қазақша
+    item-109 at level 2: list_item: Català
-      item-110 at level 3: list_item: Ikirundi
+    item-110 at level 2: list_item: Чӑвашла
-      item-111 at level 3: list_item: Kongo
+    item-111 at level 2: list_item: Čeština
-      item-112 at level 3: list_item: Kreyòl ayisyen
+    item-112 at level 2: list_item: ChiShona
-      item-113 at level 3: list_item: Кырык мары
+    item-113 at level 2: list_item: Cymraeg
-      item-114 at level 3: list_item: ລາວ
+    item-114 at level 2: list_item: Dagbanli
-      item-115 at level 3: list_item: Latina
+    item-115 at level 2: list_item: Dansk
-      item-116 at level 3: list_item: Latviešu
+    item-116 at level 2: list_item: Deitsch
-      item-117 at level 3: list_item: Lietuvių
+    item-117 at level 2: list_item: Deutsch
-      item-118 at level 3: list_item: Li Niha
+    item-118 at level 2: list_item: डोटेली
-      item-119 at level 3: list_item: Ligure
+    item-119 at level 2: list_item: Ελληνικά
-      item-120 at level 3: list_item: Limburgs
+    item-120 at level 2: list_item: Emiliàn e rumagnòl
-      item-121 at level 3: list_item: Lingála
+    item-121 at level 2: list_item: Español
-      item-122 at level 3: list_item: Malagasy
+    item-122 at level 2: list_item: Esperanto
-      item-123 at level 3: list_item: മലയാളം
+    item-123 at level 2: list_item: Euskara
-      item-124 at level 3: list_item: मराठी
+    item-124 at level 2: list_item: فارسی
-      item-125 at level 3: list_item: مازِرونی
+    item-125 at level 2: list_item: Français
-      item-126 at level 3: list_item: Bahasa Melayu
+    item-126 at level 2: list_item: Gaeilge
-      item-127 at level 3: list_item: ꯃꯤꯇꯩ ꯂꯣꯟ
+    item-127 at level 2: list_item: Galego
-      item-128 at level 3: list_item: 閩東語 / Mìng-dĕ̤ng-ngṳ̄
+    item-128 at level 2: list_item: ГӀалгӀай
-      item-129 at level 3: list_item: Мокшень
+    item-129 at level 2: list_item: 贛語
-      item-130 at level 3: list_item: Монгол
+    item-130 at level 2: list_item: گیلکی
-      item-131 at level 3: list_item: မြန်မာဘာသာ
+    item-131 at level 2: list_item: 𐌲𐌿𐍄𐌹𐍃𐌺
-      item-132 at level 3: list_item: Nederlands
+    item-132 at level 2: list_item: गोंयची कोंकणी / Gõychi Konknni
-      item-133 at level 3: list_item: Nedersaksies
+    item-133 at level 2: list_item: 客家語 / Hak-kâ-ngî
-      item-134 at level 3: list_item: नेपाली
+    item-134 at level 2: list_item: 한국어
-      item-135 at level 3: list_item: नेपाल भाषा
+    item-135 at level 2: list_item: Hausa
-      item-136 at level 3: list_item: 日本語
+    item-136 at level 2: list_item: Հայերեն
-      item-137 at level 3: list_item: Нохчийн
+    item-137 at level 2: list_item: हिन्दी
-      item-138 at level 3: list_item: Norsk nynorsk
+    item-138 at level 2: list_item: Hrvatski
-      item-139 at level 3: list_item: Occitan
+    item-139 at level 2: list_item: Ido
-      item-140 at level 3: list_item: Oromoo
+    item-140 at level 2: list_item: Bahasa Indonesia
-      item-141 at level 3: list_item: ਪੰਜਾਬੀ
+    item-141 at level 2: list_item: Iñupiatun
-      item-142 at level 3: list_item: Picard
+    item-142 at level 2: list_item: Íslenska
-      item-143 at level 3: list_item: Plattdüütsch
+    item-143 at level 2: list_item: Italiano
-      item-144 at level 3: list_item: Polski
+    item-144 at level 2: list_item: עברית
-      item-145 at level 3: list_item: Português
+    item-145 at level 2: list_item: Jawa
-      item-146 at level 3: list_item: Qırımtatarca
+    item-146 at level 2: list_item: ಕನ್ನಡ
-      item-147 at level 3: list_item: Română
+    item-147 at level 2: list_item: Kapampangan
-      item-148 at level 3: list_item: Русский
+    item-148 at level 2: list_item: ქართული
-      item-149 at level 3: list_item: Саха тыла
+    item-149 at level 2: list_item: कॉशुर / کٲشُر
-      item-150 at level 3: list_item: ᱥᱟᱱᱛᱟᱲᱤ
+    item-150 at level 2: list_item: Қазақша
-      item-151 at level 3: list_item: Sardu
+    item-151 at level 2: list_item: Ikirundi
-      item-152 at level 3: list_item: Scots
+    item-152 at level 2: list_item: Kongo
-      item-153 at level 3: list_item: Seeltersk
+    item-153 at level 2: list_item: Kreyòl ayisyen
-      item-154 at level 3: list_item: Shqip
+    item-154 at level 2: list_item: Кырык мары
-      item-155 at level 3: list_item: Sicilianu
+    item-155 at level 2: list_item: ລາວ
-      item-156 at level 3: list_item: සිංහල
+    item-156 at level 2: list_item: Latina
-      item-157 at level 3: list_item: Simple English
+    item-157 at level 2: list_item: Latviešu
-      item-158 at level 3: list_item: سنڌي
+    item-158 at level 2: list_item: Lietuvių
-      item-159 at level 3: list_item: کوردی
+    item-159 at level 2: list_item: Li Niha
-      item-160 at level 3: list_item: Српски / srpski
+    item-160 at level 2: list_item: Ligure
-      item-161 at level 3: list_item: Srpskohrvatski / српскохрватски
+    item-161 at level 2: list_item: Limburgs
-      item-162 at level 3: list_item: Sunda
+    item-162 at level 2: list_item: Lingála
-      item-163 at level 3: list_item: Svenska
+    item-163 at level 2: list_item: Malagasy
-      item-164 at level 3: list_item: Tagalog
+    item-164 at level 2: list_item: മലയാളം
-      item-165 at level 3: list_item: தமிழ்
+    item-165 at level 2: list_item: मराठी
-      item-166 at level 3: list_item: Taqbaylit
+    item-166 at level 2: list_item: مازِرونی
-      item-167 at level 3: list_item: Татарча / tatarça
+    item-167 at level 2: list_item: Bahasa Melayu
-      item-168 at level 3: list_item: ไทย
+    item-168 at level 2: list_item: ꯃꯤꯇꯩ ꯂꯣꯟ
-      item-169 at level 3: list_item: Türkçe
+    item-169 at level 2: list_item: 閩東語 / Mìng-dĕ̤ng-ngṳ̄
-      item-170 at level 3: list_item: Українська
+    item-170 at level 2: list_item: Мокшень
-      item-171 at level 3: list_item: ئۇيغۇرچە / Uyghurche
+    item-171 at level 2: list_item: Монгол
-      item-172 at level 3: list_item: Vahcuengh
+    item-172 at level 2: list_item: မြန်မာဘာသာ
-      item-173 at level 3: list_item: Tiếng Việt
+    item-173 at level 2: list_item: Nederlands
-      item-174 at level 3: list_item: Walon
+    item-174 at level 2: list_item: Nedersaksies
-      item-175 at level 3: list_item: 文言
+    item-175 at level 2: list_item: नेपाली
-      item-176 at level 3: list_item: Winaray
+    item-176 at level 2: list_item: नेपाल भाषा
-      item-177 at level 3: list_item: 吴语
+    item-177 at level 2: list_item: 日本語
-      item-178 at level 3: list_item: 粵語
+    item-178 at level 2: list_item: Нохчийн
-      item-179 at level 3: list_item: Žemaitėška
+    item-179 at level 2: list_item: Norsk nynorsk
-      item-180 at level 3: list_item: 中文
+    item-180 at level 2: list_item: Occitan
-    item-181 at level 2: list: group list
+    item-181 at level 2: list_item: Oromoo
-      item-182 at level 3: list_item: Article
+    item-182 at level 2: list_item: ਪੰਜਾਬੀ
-      item-183 at level 3: list_item: Talk
+    item-183 at level 2: list_item: Picard
-    item-184 at level 2: list: group list
+    item-184 at level 2: list_item: Plattdüütsch
-    item-185 at level 2: list: group list
+    item-185 at level 2: list_item: Polski
-      item-186 at level 3: list_item: Read
+    item-186 at level 2: list_item: Português
-      item-187 at level 3: list_item: View source
+    item-187 at level 2: list_item: Qırımtatarca
-      item-188 at level 3: list_item: View history
+    item-188 at level 2: list_item: Română
-    item-189 at level 2: text: Tools
+    item-189 at level 2: list_item: Русский
-    item-190 at level 2: text: Actions
+    item-190 at level 2: list_item: Саха тыла
-    item-191 at level 2: list: group list
+    item-191 at level 2: list_item: ᱥᱟᱱᱛᱟᱲᱤ
-      item-192 at level 3: list_item: Read
+    item-192 at level 2: list_item: Sardu
-      item-193 at level 3: list_item: View source
+    item-193 at level 2: list_item: Scots
-      item-194 at level 3: list_item: View history
+    item-194 at level 2: list_item: Seeltersk
-    item-195 at level 2: text: General
+    item-195 at level 2: list_item: Shqip
-    item-196 at level 2: list: group list
+    item-196 at level 2: list_item: Sicilianu
-      item-197 at level 3: list_item: What links here
+    item-197 at level 2: list_item: සිංහල
-      item-198 at level 3: list_item: Related changes
+    item-198 at level 2: list_item: Simple English
-      item-199 at level 3: list_item: Upload file
+    item-199 at level 2: list_item: سنڌي
-      item-200 at level 3: list_item: Special pages
+    item-200 at level 2: list_item: کوردی
-      item-201 at level 3: list_item: Permanent link
+    item-201 at level 2: list_item: Српски / srpski
-      item-202 at level 3: list_item: Page information
+    item-202 at level 2: list_item: Srpskohrvatski / српскохрватски
-      item-203 at level 3: list_item: Cite this page
+    item-203 at level 2: list_item: Sunda
-      item-204 at level 3: list_item: Get shortened URL
+    item-204 at level 2: list_item: Svenska
-      item-205 at level 3: list_item: Download QR code
+    item-205 at level 2: list_item: Tagalog
-      item-206 at level 3: list_item: Wikidata item
+    item-206 at level 2: list_item: தமிழ்
-    item-207 at level 2: text: Print/export
+    item-207 at level 2: list_item: Taqbaylit
-    item-208 at level 2: list: group list
+    item-208 at level 2: list_item: Татарча / tatarça
-      item-209 at level 3: list_item: Download as PDF
+    item-209 at level 2: list_item: ไทย
-      item-210 at level 3: list_item: Printable version
+    item-210 at level 2: list_item: Türkçe
-    item-211 at level 2: text: In other projects
+    item-211 at level 2: list_item: Українська
-    item-212 at level 2: list: group list
+    item-212 at level 2: list_item: ئۇيغۇرچە / Uyghurche
-      item-213 at level 3: list_item: Wikimedia Commons
+    item-213 at level 2: list_item: Vahcuengh
-      item-214 at level 3: list_item: Wikiquote
+    item-214 at level 2: list_item: Tiếng Việt
-    item-215 at level 2: text: Appearance
+    item-215 at level 2: list_item: Walon
-    item-216 at level 2: picture
+    item-216 at level 2: list_item: 文言
-    item-217 at level 2: text: From Wikipedia, the free encyclopedia
+    item-217 at level 2: list_item: Winaray
-    item-218 at level 2: text: Common name for many species of bird
+    item-218 at level 2: list_item: 吴语
-    item-219 at level 2: text: This article is about the bird.  ... as a food, see . For other uses, see .
+    item-219 at level 2: list_item: 粵語
-    item-220 at level 2: text: "Duckling" redirects here. For other uses, see .
+    item-220 at level 2: list_item: Žemaitėška
-    item-221 at level 2: table with [13x2]
+    item-221 at level 2: list_item: 中文
-    item-222 at level 2: text: Duck is the common name for nume ... und in both fresh water and sea water.
+  item-222 at level 1: text: Edit links
-    item-223 at level 2: text: Ducks are sometimes confused wit ...  divers, grebes, gallinules and coots.
+  item-223 at level 1: list: group group
-    item-224 at level 2: section_header: Etymology
+    item-224 at level 2: list_item: Article
-      item-225 at level 3: text: The word duck comes from Old Eng ... h duiken and German tauchen 'to dive'.
+    item-225 at level 2: list_item: Talk
-      item-226 at level 3: picture
+  item-226 at level 1: text: English
-        item-226 at level 4: caption: Pacific black duck displaying the characteristic upending "duck"
+  item-227 at level 1: list: group group
-      item-227 at level 3: text: This word replaced Old English e ... nskrit ātí 'water bird', among others.
+  item-228 at level 1: list: group group
-      item-228 at level 3: text: A duckling is a young duck in do ... , is sometimes labelled as a duckling.
+    item-229 at level 2: list_item: Read
-      item-229 at level 3: text: A male is called a drake and the ... a duck, or in ornithology a hen.[3][4]
+    item-230 at level 2: list_item: View source
-      item-230 at level 3: picture
+    item-231 at level 2: list_item: View history
-        item-230 at level 4: caption: Male mallard.
+  item-232 at level 1: text: Tools
-      item-231 at level 3: picture
+  item-233 at level 1: text: Tools
-        item-231 at level 4: caption: Wood ducks.
+  item-234 at level 1: text: move to sidebar
-    item-232 at level 2: section_header: Taxonomy
+  item-235 at level 1: text: hide
-      item-233 at level 3: text: All ducks belong to the biologic ... ationships between various species.[9]
+  item-236 at level 1: text: Actions
-      item-234 at level 3: picture
+  item-237 at level 1: list: group group
-        item-234 at level 4: caption: Mallard landing in approach
+    item-238 at level 2: list_item: Read
-      item-235 at level 3: text: In most modern classifications,  ... all size and stiff, upright tails.[14]
+    item-239 at level 2: list_item: View source
-      item-236 at level 3: text: A number of other species called ...  shelducks in the tribe Tadornini.[15]
+    item-240 at level 2: list_item: View history
-    item-237 at level 2: section_header: Morphology
+  item-241 at level 1: text: General
-      item-238 at level 3: picture
+  item-242 at level 1: list: group group
-        item-238 at level 4: caption: Male Mandarin duck
+    item-243 at level 2: list_item: What links here
-      item-239 at level 3: text: The overall body plan of ducks i ... is moult typically precedes migration.
+    item-244 at level 2: list_item: Related changes
-      item-240 at level 3: text: The drakes of northern species o ... rkscrew shaped vagina to prevent rape.
+    item-245 at level 2: list_item: Upload file
-    item-241 at level 2: section_header: Distribution and habitat
+    item-246 at level 2: list_item: Special pages
-      item-242 at level 3: picture
+    item-247 at level 2: list_item: Permanent link
-        item-242 at level 4: caption: Flying steamer ducks in Ushuaia, Argentina
+    item-248 at level 2: list_item: Page information
-      item-243 at level 3: text: Ducks have a cosmopolitan distri ... endemic to such far-flung islands.[21]
+    item-249 at level 2: list_item: Cite this page
-      item-244 at level 3: picture
+    item-250 at level 2: list_item: Get shortened URL
-        item-244 at level 4: caption: Female mallard in Cornwall, England
+    item-251 at level 2: list_item: Download QR code
-      item-245 at level 3: text: Some duck species, mainly those  ... t form after localised heavy rain.[23]
+    item-252 at level 2: list_item: Wikidata item
-    item-246 at level 2: section_header: Behaviour
+  item-253 at level 1: text: Print/export
-      item-247 at level 3: section_header: Feeding
+  item-254 at level 1: list: group group
-        item-248 at level 4: picture
+    item-255 at level 2: list_item: Download as PDF
-          item-248 at level 5: caption: Pecten along the bill
+    item-256 at level 2: list_item: Printable version
-        item-249 at level 4: picture
+  item-257 at level 1: text: In other projects
-          item-249 at level 5: caption: Mallard duckling preening
+  item-258 at level 1: list: group group
-        item-250 at level 4: text: Ducks eat food sources such as g ... amphibians, worms, and small molluscs.
+    item-259 at level 2: list_item: Wikimedia Commons
-        item-251 at level 4: text: Dabbling ducks feed on the surfa ... thers and to hold slippery food items.
+    item-260 at level 2: list_item: Wikiquote
-        item-252 at level 4: text: Diving ducks and sea ducks forag ... ave more difficulty taking off to fly.
+  item-261 at level 1: text: Appearance
-        item-253 at level 4: text: A few specialized species such a ... apted to catch and swallow large fish.
+  item-262 at level 1: text: move to sidebar
-        item-254 at level 4: text: The others have the characterist ... e nostrils come out through hard horn.
+  item-263 at level 1: text: hide
-        item-255 at level 4: text: The Guardian published an articl ...  the ducks and pollutes waterways.[25]
+  item-264 at level 1: text: From Wikipedia, the free encyclopedia
-      item-256 at level 3: section_header: Breeding
+  item-265 at level 1: text: (Redirected from Duckling)
-        item-257 at level 4: picture
+  item-266 at level 1: text: Common name for many species of bird
-          item-257 at level 5: caption: A Muscovy duckling
+  item-267 at level 1: text: This article is about the bird.  ... other uses, see Duck (disambiguation).
-        item-258 at level 4: text: Ducks generally only have one pa ... st and led her ducklings to water.[28]
+  item-268 at level 1: text: "Duckling" redirects here. For other uses, see Duckling (disambiguation).
-      item-259 at level 3: section_header: Communication
+  item-269 at level 1: table with [13x2]
-        item-260 at level 4: text: Female mallard ducks (as well as ... laying calls or quieter contact calls.
+  item-270 at level 1: text: Duck is the common name for nume ... und in both fresh water and sea water.
-        item-261 at level 4: text: A common urban legend claims tha ... annel television show MythBusters.[32]
+  item-271 at level 1: text: Ducks are sometimes confused wit ...  divers, grebes, gallinules and coots.
-      item-262 at level 3: section_header: Predators
+  item-272 at level 1: section_header: Etymology
-        item-263 at level 4: picture
+  item-273 at level 1: text: The word duck comes from Old Eng ... h duiken and German tauchen 'to dive'.
-          item-263 at level 5: caption: Ringed teal
+  item-274 at level 1: text: Pacific black duck displaying the characteristic upending "duck"
-        item-264 at level 4: text: Ducks have many predators. Duckl ... or large birds, such as hawks or owls.
+  item-275 at level 1: text: This word replaced Old English e ... nskrit ātí 'water bird', among others.
-        item-265 at level 4: text: Adult ducks are fast fliers, but ... its speed and strength to catch ducks.
+  item-276 at level 1: text: A duckling is a young duck in do ... , is sometimes labelled as a duckling.
-    item-266 at level 2: section_header: Relationship with humans
+  item-277 at level 1: text: A male is called a drake and the ... a duck, or in ornithology a hen.[3][4]
-      item-267 at level 3: section_header: Hunting
+  item-278 at level 1: text: Male mallard.
-        item-268 at level 4: text: Humans have hunted ducks since p ...  evidence of this is uncommon.[35][42]
+  item-279 at level 1: text: Wood ducks.
-        item-269 at level 4: text: In many areas, wild ducks (inclu ... inated by pollutants such as PCBs.[44]
+  item-280 at level 1: section_header: Taxonomy
-      item-270 at level 3: section_header: Domestication
+  item-281 at level 1: text: All ducks belong to the biologic ... ationships between various species.[9]
-        item-271 at level 4: picture
+  item-282 at level 1: text: Mallard landing in approach
-          item-271 at level 5: caption: Indian Runner ducks, a common breed of domestic ducks
+  item-283 at level 1: text: In most modern classifications,  ... all size and stiff, upright tails.[14]
-        item-272 at level 4: text: Ducks have many economic uses, b ... it weighs less than 1 kg (2.2 lb).[48]
+  item-284 at level 1: text: A number of other species called ...  shelducks in the tribe Tadornini.[15]
-      item-273 at level 3: section_header: Heraldry
+  item-285 at level 1: section_header: Morphology
-        item-274 at level 4: picture
+  item-286 at level 1: text: Male Mandarin duck
-          item-274 at level 5: caption: Three black-colored ducks in the coat of arms of Maaninka[49]
+  item-287 at level 1: text: The overall body plan of ducks i ... is moult typically precedes migration.
-        item-275 at level 4: text: Ducks appear on several coats of ... the coat of arms of Föglö (Åland).[51]
+  item-288 at level 1: text: The drakes of northern species o ... rkscrew shaped vagina to prevent rape.
-      item-276 at level 3: section_header: Cultural references
+  item-289 at level 1: section_header: Distribution and habitat
-        item-277 at level 4: text: In 2002, psychologist Richard Wi ... 54] and was made into a movie in 1986.
+  item-290 at level 1: text: See also: List of Anseriformes by population
-        item-278 at level 4: text: The 1992 Disney film The Mighty  ...  Ducks minor league baseball team.[55]
+  item-291 at level 1: text: Flying steamer ducks in Ushuaia, Argentina
-    item-279 at level 2: section_header: See also
+  item-292 at level 1: text: Ducks have a cosmopolitan distri ... endemic to such far-flung islands.[21]
-      item-280 at level 3: list: group list
+  item-293 at level 1: text: Female mallard in Cornwall, England
-        item-281 at level 4: list_item: Birds portal
+  item-294 at level 1: text: Some duck species, mainly those  ... t form after localised heavy rain.[23]
-      item-282 at level 3: list: group list
+  item-295 at level 1: section_header: Behaviour
-        item-283 at level 4: list_item: Domestic duck
+  item-296 at level 1: section_header: Feeding
-        item-284 at level 4: list_item: Duck as food
+  item-297 at level 1: text: Pecten along the bill
-        item-285 at level 4: list_item: Duck test
+  item-298 at level 1: text: Mallard duckling preening
-        item-286 at level 4: list_item: Duck breeds
+  item-299 at level 1: text: Ducks eat food sources such as g ... amphibians, worms, and small molluscs.
-        item-287 at level 4: list_item: Fictional ducks
+  item-300 at level 1: text: Dabbling ducks feed on the surfa ... thers and to hold slippery food items.
-        item-288 at level 4: list_item: Rubber duck
+  item-301 at level 1: text: Diving ducks and sea ducks forag ... ave more difficulty taking off to fly.
-    item-289 at level 2: section_header: Notes
+  item-302 at level 1: text: A few specialized species such a ... apted to catch and swallow large fish.
-      item-290 at level 3: section_header: Citations
+  item-303 at level 1: text: The others have the characterist ... e nostrils come out through hard horn.
-        item-291 at level 4: ordered_list: group ordered list
+  item-304 at level 1: text: The Guardian published an articl ...  the ducks and pollutes waterways.[25]
-          item-292 at level 5: list_item: ^ "Duckling". The American Herit ... n Company. 2006. Retrieved 2015-05-22.
+  item-305 at level 1: section_header: Breeding
-          item-293 at level 5: list_item: ^ "Duckling". Kernerman English  ...  Ltd. 2000–2006. Retrieved 2015-05-22.
+  item-306 at level 1: text: A Muscovy duckling
-          item-294 at level 5: list_item: ^ Dohner, Janet Vorwald (2001).  ... University Press. ISBN 978-0300138139.
+  item-307 at level 1: text: Ducks generally only have one pa ... st and led her ducklings to water.[28]
-          item-295 at level 5: list_item: ^ Visca, Curt; Visca, Kelley (20 ...  Publishing Group. ISBN 9780823961566.
+  item-308 at level 1: section_header: Communication
-          item-296 at level 5: list_item: ^ a b c d Carboneras 1992, p. 536.
+  item-309 at level 1: text: Female mallard ducks (as well as ... laying calls or quieter contact calls.
-          item-297 at level 5: list_item: ^ Livezey 1986, pp. 737–738.
+  item-310 at level 1: text: A common urban legend claims tha ... annel television show MythBusters.[32]
-          item-298 at level 5: list_item: ^ Madsen, McHugh & de Kloet 1988, p. 452.
+  item-311 at level 1: section_header: Predators
-          item-299 at level 5: list_item: ^ Donne-Goussé, Laudet & Hänni 2002, pp. 353–354.
+  item-312 at level 1: text: Ringed teal
-          item-300 at level 5: list_item: ^ a b c d e f Carboneras 1992, p. 540.
+  item-313 at level 1: text: Ducks have many predators. Duckl ... or large birds, such as hawks or owls.
-          item-301 at level 5: list_item: ^ Elphick, Dunning & Sibley 2001, p. 191.
+  item-314 at level 1: text: Adult ducks are fast fliers, but ... its speed and strength to catch ducks.
-          item-302 at level 5: list_item: ^ Kear 2005, p. 448.
+  item-315 at level 1: section_header: Relationship with humans
-          item-303 at level 5: list_item: ^ Kear 2005, p. 622–623.
+  item-316 at level 1: section_header: Hunting
-          item-304 at level 5: list_item: ^ Kear 2005, p. 686.
+  item-317 at level 1: text: Main article: Waterfowl hunting
-          item-305 at level 5: list_item: ^ Elphick, Dunning & Sibley 2001, p. 193.
+  item-318 at level 1: text: Humans have hunted ducks since p ...  evidence of this is uncommon.[35][42]
-          item-306 at level 5: list_item: ^ a b c d e f g Carboneras 1992, p. 537.
+  item-319 at level 1: text: In many areas, wild ducks (inclu ... inated by pollutants such as PCBs.[44]
-          item-307 at level 5: list_item: ^ American Ornithologists' Union 1998, p. xix.
+  item-320 at level 1: section_header: Domestication
-          item-308 at level 5: list_item: ^ American Ornithologists' Union 1998.
+  item-321 at level 1: text: Main article: Domestic duck
-          item-309 at level 5: list_item: ^ Carboneras 1992, p. 538.
+  item-322 at level 1: text: Indian Runner ducks, a common breed of domestic ducks
-          item-310 at level 5: list_item: ^ Christidis & Boles 2008, p. 62.
+  item-323 at level 1: text: Ducks have many economic uses, b ... it weighs less than 1 kg (2.2 lb).[48]
-          item-311 at level 5: list_item: ^ Shirihai 2008, pp. 239, 245.
+  item-324 at level 1: section_header: Heraldry
-          item-312 at level 5: list_item: ^ a b Pratt, Bruner & Berrett 1987, pp. 98–107.
+  item-325 at level 1: text: Three black-colored ducks in the coat of arms of Maaninka[49]
-          item-313 at level 5: list_item: ^ Fitter, Fitter & Hosking 2000, pp. 52–3.
+  item-326 at level 1: text: Ducks appear on several coats of ... the coat of arms of Föglö (Åland).[51]
-          item-314 at level 5: list_item: ^ "Pacific Black Duck". www.wiresnr.org. Retrieved 2018-04-27.
+  item-327 at level 1: section_header: Cultural references
-          item-315 at level 5: list_item: ^ Ogden, Evans. "Dabbling Ducks". CWE. Retrieved 2006-11-02.
+  item-328 at level 1: text: In 2002, psychologist Richard Wi ... 54] and was made into a movie in 1986.
-          item-316 at level 5: list_item: ^ Karl Mathiesen (16 March 2015) ...  Guardian. Retrieved 13 November 2016.
+  item-329 at level 1: text: The 1992 Disney film The Mighty  ...  Ducks minor league baseball team.[55]
-          item-317 at level 5: list_item: ^ Rohwer, Frank C.; Anderson, Mi ... 4615-6787-5_4. ISBN 978-1-4615-6789-9.
+  item-330 at level 1: section_header: See also
-          item-318 at level 5: list_item: ^ Smith, Cyndi M.; Cooke, Fred;  ... 093/condor/102.1.201. hdl:10315/13797.
+  item-331 at level 1: list: group group
-          item-319 at level 5: list_item: ^ "If You Find An Orphaned Duckl ... l on 2018-09-23. Retrieved 2018-12-22.
+    item-332 at level 2: list_item: Birds portal
-          item-320 at level 5: list_item: ^ Carver, Heather (2011). The Du ...  9780557901562.[self-published source]
+  item-333 at level 1: list: group group
-          item-321 at level 5: list_item: ^ Titlow, Budd (2013-09-03). Bir ... man & Littlefield. ISBN 9780762797707.
+    item-334 at level 2: list_item: Domestic duck
-          item-322 at level 5: list_item: ^ Amos, Jonathan (2003-09-08). " ... kers". BBC News. Retrieved 2006-11-02.
+    item-335 at level 2: list_item: Duck as food
-          item-323 at level 5: list_item: ^ "Mythbusters Episode 8". 12 December 2003.
+    item-336 at level 2: list_item: Duck test
-          item-324 at level 5: list_item: ^ Erlandson 1994, p. 171.
+    item-337 at level 2: list_item: Duck breeds
-          item-325 at level 5: list_item: ^ Jeffries 2008, pp. 168, 243.
+    item-338 at level 2: list_item: Fictional ducks
-          item-326 at level 5: list_item: ^ a b Sued-Badillo 2003, p. 65.
+    item-339 at level 2: list_item: Rubber duck
-          item-327 at level 5: list_item: ^ Thorpe 1996, p. 68.
+  item-340 at level 1: section_header: Notes
-          item-328 at level 5: list_item: ^ Maisels 1999, p. 42.
+  item-341 at level 1: section_header: Citations
-          item-329 at level 5: list_item: ^ Rau 1876, p. 133.
+  item-342 at level 1: ordered_list: group group
-          item-330 at level 5: list_item: ^ Higman 2012, p. 23.
+    item-343 at level 2: list_item: ^ "Duckling" . The American Heri ... Company. 2006 . Retrieved 2015-05-22 .
-          item-331 at level 5: list_item: ^ Hume 2012, p. 53.
+    item-344 at level 2: list_item: ^ "Duckling" . Kernerman English ... td. 2000–2006 . Retrieved 2015-05-22 .
-          item-332 at level 5: list_item: ^ Hume 2012, p. 52.
+    item-345 at level 2: list_item: ^ Dohner, Janet Vorwald (2001).  ... niversity Press. ISBN 978-0300138139 .
-          item-333 at level 5: list_item: ^ Fieldhouse 2002, p. 167.
+    item-346 at level 2: list_item: ^ Visca, Curt; Visca, Kelley (20 ... Publishing Group. ISBN 9780823961566 .
-          item-334 at level 5: list_item: ^ Livingston, A. D. (1998-01-01) ... Editions, Limited. ISBN 9781853263774.
+    item-347 at level 2: list_item: ^ a b c d Carboneras 1992 , p. 536.
-          item-335 at level 5: list_item: ^ "Study plan for waterfowl inju ...  on 2022-10-09. Retrieved 2 July 2019.
+    item-348 at level 2: list_item: ^ Livezey 1986 , pp. 737–738.
-          item-336 at level 5: list_item: ^ "FAOSTAT". www.fao.org. Retrieved 2019-10-25.
+    item-349 at level 2: list_item: ^ Madsen, McHugh & de Kloet 1988 , p. 452.
-          item-337 at level 5: list_item: ^ "Anas platyrhynchos, Domestic  ... . Digimorph.org. Retrieved 2012-12-23.
+    item-350 at level 2: list_item: ^ Donne-Goussé, Laudet & Hänni 2002 , pp. 353–354.
-          item-338 at level 5: list_item: ^ Sy Montgomery. "Mallard; Encyc ...  Britannica.com. Retrieved 2012-12-23.
+    item-351 at level 2: list_item: ^ a b c d e f Carboneras 1992 , p. 540.
-          item-339 at level 5: list_item: ^ Glenday, Craig (2014). Guinnes ... ited. pp. 135. ISBN 978-1-908843-15-9.
+    item-352 at level 2: list_item: ^ Elphick, Dunning & Sibley 2001 , p. 191.
-          item-340 at level 5: list_item: ^ Suomen kunnallisvaakunat (in F ... tto. 1982. p. 147. ISBN 951-773-085-3.
+    item-353 at level 2: list_item: ^ Kear 2005 , p. 448.
-          item-341 at level 5: list_item: ^ "Lubānas simbolika" (in Latvian). Retrieved September 9, 2021.
+    item-354 at level 2: list_item: ^ Kear 2005 , p. 622–623.
-          item-342 at level 5: list_item: ^ "Föglö" (in Swedish). Retrieved September 9, 2021.
+    item-355 at level 2: list_item: ^ Kear 2005 , p. 686.
-          item-343 at level 5: list_item: ^ Young, Emma. "World's funniest ... w Scientist. Retrieved 7 January 2019.
+    item-356 at level 2: list_item: ^ Elphick, Dunning & Sibley 2001 , p. 193.
-          item-344 at level 5: list_item: ^ "Howard the Duck (character)". Grand Comics Database.
+    item-357 at level 2: list_item: ^ a b c d e f g Carboneras 1992 , p. 537.
-          item-345 at level 5: list_item: ^ Sanderson, Peter; Gilbert, Lau ... luding this bad-tempered talking duck.
+    item-358 at level 2: list_item: ^ American Ornithologists' Union 1998 , p. xix.
-          item-346 at level 5: list_item: ^ "The Duck". University of Oregon Athletics. Retrieved 2022-01-20.
+    item-359 at level 2: list_item: ^ American Ornithologists' Union 1998 .
-      item-347 at level 3: section_header: Sources
+    item-360 at level 2: list_item: ^ Carboneras 1992 , p. 538.
-        item-348 at level 4: list: group list
+    item-361 at level 2: list_item: ^ Christidis & Boles 2008 , p. 62.
-          item-349 at level 5: list_item: American Ornithologists' Union ( ... (PDF) from the original on 2022-10-09.
+    item-362 at level 2: list_item: ^ Shirihai 2008 , pp. 239, 245.
-          item-350 at level 5: list_item: Carboneras, Carlos (1992). del H ... Lynx Edicions. ISBN 978-84-87334-10-8.
+    item-363 at level 2: list_item: ^ a b Pratt, Bruner & Berrett 1987 , pp. 98–107.
-          item-351 at level 5: list_item: Christidis, Les; Boles, Walter E ... ro Publishing. ISBN 978-0-643-06511-6.
+    item-364 at level 2: list_item: ^ Fitter, Fitter & Hosking 2000 , pp. 52–3.
-          item-352 at level 5: list_item: Donne-Goussé, Carole; Laudet, Vi ... /S1055-7903(02)00019-2. PMID 12099792.
+    item-365 at level 2: list_item: ^ "Pacific Black Duck" . www.wiresnr.org . Retrieved 2018-04-27 .
-          item-353 at level 5: list_item: Elphick, Chris; Dunning, John B. ... istopher Helm. ISBN 978-0-7136-6250-4.
+    item-366 at level 2: list_item: ^ Ogden, Evans. "Dabbling Ducks" . CWE . Retrieved 2006-11-02 .
-          item-354 at level 5: list_item: Erlandson, Jon M. (1994). Early  ... usiness Media. ISBN 978-1-4419-3231-0.
+    item-367 at level 2: list_item: ^ Karl Mathiesen (16 March 2015) ... uardian . Retrieved 13 November 2016 .
-          item-355 at level 5: list_item: Fieldhouse, Paul (2002). Food, F ... ara: ABC-CLIO. ISBN 978-1-61069-412-4.
+    item-368 at level 2: list_item: ^ Rohwer, Frank C.; Anderson, Mi ... 15-6787-5_4 . ISBN 978-1-4615-6789-9 .
-          item-356 at level 5: list_item: Fitter, Julian; Fitter, Daniel;  ... versity Press. ISBN 978-0-691-10295-5.
+    item-369 at level 2: list_item: ^ Smith, Cyndi M.; Cooke, Fred;  ... condor/102.1.201 . hdl : 10315/13797 .
-          item-357 at level 5: list_item: Higman, B. W. (2012). How Food M ...  Wiley & Sons. ISBN 978-1-4051-8947-7.
+    item-370 at level 2: list_item: ^ "If You Find An Orphaned Duckl ... on 2018-09-23 . Retrieved 2018-12-22 .
-          item-358 at level 5: list_item: Hume, Julian H. (2012). Extinct  ... istopher Helm. ISBN 978-1-4729-3744-5.
+    item-371 at level 2: list_item: ^ Carver, Heather (2011). The Du ... 0557901562 . [ self-published source ]
-          item-359 at level 5: list_item: Jeffries, Richard (2008). Holoce ... Alabama Press. ISBN 978-0-8173-1658-7.
+    item-372 at level 2: list_item: ^ Titlow, Budd (2013-09-03). Bir ... an & Littlefield. ISBN 9780762797707 .
-          item-360 at level 5: list_item: Kear, Janet, ed. (2005). Ducks,  ... versity Press. ISBN 978-0-19-861009-0.
+    item-373 at level 2: list_item: ^ Amos, Jonathan (2003-09-08). " ... s" . BBC News . Retrieved 2006-11-02 .
-          item-361 at level 5: list_item: Livezey, Bradley C. (October 198 ... (PDF) from the original on 2022-10-09.
+    item-374 at level 2: list_item: ^ "Mythbusters Episode 8" . 12 December 2003.
-          item-362 at level 5: list_item: Madsen, Cort S.; McHugh, Kevin P ... (PDF) from the original on 2022-10-09.
+    item-375 at level 2: list_item: ^ Erlandson 1994 , p. 171.
-          item-363 at level 5: list_item: Maisels, Charles Keith (1999). E ... on: Routledge. ISBN 978-0-415-10975-8.
+    item-376 at level 2: list_item: ^ Jeffries 2008 , pp. 168, 243.
-          item-364 at level 5: list_item: Pratt, H. Douglas; Bruner, Phill ...  University Press. ISBN 0-691-02399-9.
+    item-377 at level 2: list_item: ^ a b Sued-Badillo 2003 , p. 65.
-          item-365 at level 5: list_item: Rau, Charles (1876). Early Man i ... ork: Harper & Brothers. LCCN 05040168.
+    item-378 at level 2: list_item: ^ Thorpe 1996 , p. 68.
-          item-366 at level 5: list_item: Shirihai, Hadoram (2008). A Comp ... versity Press. ISBN 978-0-691-13666-0.
+    item-379 at level 2: list_item: ^ Maisels 1999 , p. 42.
-          item-367 at level 5: list_item: Sued-Badillo, Jalil (2003). Auto ... Paris: UNESCO. ISBN 978-92-3-103832-7.
+    item-380 at level 2: list_item: ^ Rau 1876 , p. 133.
-          item-368 at level 5: list_item: Thorpe, I. J. (1996). The Origin ... rk: Routledge. ISBN 978-0-415-08009-5.
+    item-381 at level 2: list_item: ^ Higman 2012 , p. 23.
-    item-369 at level 2: section_header: External links
+    item-382 at level 2: list_item: ^ Hume 2012 , p. 53.
-      item-370 at level 3: list: group list
+    item-383 at level 2: list_item: ^ Hume 2012 , p. 52.
-        item-371 at level 4: list_item: Definitions from Wiktionary
+    item-384 at level 2: list_item: ^ Fieldhouse 2002 , p. 167.
-        item-372 at level 4: list_item: Media from Commons
+    item-385 at level 2: list_item: ^ Livingston, A. D. (1998-01-01) ... ditions, Limited. ISBN 9781853263774 .
-        item-373 at level 4: list_item: Quotations from Wikiquote
+    item-386 at level 2: list_item: ^ "Study plan for waterfowl inju ... n 2022-10-09 . Retrieved 2 July 2019 .
-        item-374 at level 4: list_item: Recipes from Wikibooks
+    item-387 at level 2: list_item: ^ "FAOSTAT" . www.fao.org . Retrieved 2019-10-25 .
-        item-375 at level 4: list_item: Taxa from Wikispecies
+    item-388 at level 2: list_item: ^ "Anas platyrhynchos, Domestic  ... Digimorph.org . Retrieved 2012-12-23 .
-        item-376 at level 4: list_item: Data from Wikidata
+    item-389 at level 2: list_item: ^ Sy Montgomery. "Mallard; Encyc ... ritannica.com . Retrieved 2012-12-23 .
-      item-377 at level 3: list: group list
+    item-390 at level 2: list_item: ^ Glenday, Craig (2014). Guinnes ... ed. pp. 135 . ISBN 978-1-908843-15-9 .
-        item-378 at level 4: list_item: list of books (useful looking abstracts)
+    item-391 at level 2: list_item: ^ Suomen kunnallisvaakunat (in F ... to. 1982. p. 147. ISBN 951-773-085-3 .
-        item-379 at level 4: list_item: Ducks on postage stamps Archived 2013-05-13 at the Wayback Machine
+    item-392 at level 2: list_item: ^ "Lubānas simbolika" (in Latvian) . Retrieved September 9, 2021 .
-        item-380 at level 4: list_item: Ducks at a Distance, by Rob Hine ... uide to identification of US waterfowl
+    item-393 at level 2: list_item: ^ "Föglö" (in Swedish) . Retrieved September 9, 2021 .
-      item-381 at level 3: table with [3x2]
+    item-394 at level 2: list_item: ^ Young, Emma. "World's funniest ... Scientist . Retrieved 7 January 2019 .
-      item-382 at level 3: picture
+    item-395 at level 2: list_item: ^ "Howard the Duck (character)" . Grand Comics Database .
-      item-383 at level 3: text: Retrieved from ""
+    item-396 at level 2: list_item: ^ Sanderson, Peter ; Gilbert, La ... luding this bad-tempered talking duck.
-      item-384 at level 3: text: :
+    item-397 at level 2: list_item: ^ "The Duck" . University of Oregon Athletics . Retrieved 2022-01-20 .
-      item-385 at level 3: list: group list
+  item-398 at level 1: section_header: Sources
-        item-386 at level 4: list_item: Ducks
+  item-399 at level 1: list: group group
-        item-387 at level 4: list_item: Game birds
+    item-400 at level 2: list_item: American Ornithologists' Union ( ... (PDF) from the original on 2022-10-09.
-        item-388 at level 4: list_item: Bird common names
+    item-401 at level 2: list_item: Carboneras, Carlos (1992). del H ... ynx Edicions. ISBN 978-84-87334-10-8 .
-      item-389 at level 3: text: Hidden categories:
+    item-402 at level 2: list_item: Christidis, Les; Boles, Walter E ... o Publishing. ISBN 978-0-643-06511-6 .
-      item-390 at level 3: list: group list
+    item-403 at level 2: list_item: Donne-Goussé, Carole; Laudet, Vi ... 1055-7903(02)00019-2 . PMID 12099792 .
-        item-391 at level 4: list_item: All accuracy disputes
+    item-404 at level 2: list_item: Elphick, Chris; Dunning, John B. ... stopher Helm. ISBN 978-0-7136-6250-4 .
-        item-392 at level 4: list_item: Accuracy disputes from February 2020
+    item-405 at level 2: list_item: Erlandson, Jon M. (1994). Early  ... siness Media. ISBN 978-1-4419-3231-0 .
-        item-393 at level 4: list_item: CS1 Finnish-language sources (fi)
+    item-406 at level 2: list_item: Fieldhouse, Paul (2002). Food, F ... ra: ABC-CLIO. ISBN 978-1-61069-412-4 .
-        item-394 at level 4: list_item: CS1 Latvian-language sources (lv)
+    item-407 at level 2: list_item: Fitter, Julian; Fitter, Daniel;  ... ersity Press. ISBN 978-0-691-10295-5 .
-        item-395 at level 4: list_item: CS1 Swedish-language sources (sv)
+    item-408 at level 2: list_item: Higman, B. W. (2012). How Food M ... Wiley & Sons. ISBN 978-1-4051-8947-7 .
-        item-396 at level 4: list_item: Articles with short description
+    item-409 at level 2: list_item: Hume, Julian H. (2012). Extinct  ... stopher Helm. ISBN 978-1-4729-3744-5 .
-        item-397 at level 4: list_item: Short description is different from Wikidata
+    item-410 at level 2: list_item: Jeffries, Richard (2008). Holoce ... labama Press. ISBN 978-0-8173-1658-7 .
-        item-398 at level 4: list_item: Wikipedia indefinitely move-protected pages
+    item-411 at level 2: list_item: Kear, Janet, ed. (2005). Ducks,  ... ersity Press. ISBN 978-0-19-861009-0 .
-        item-399 at level 4: list_item: Wikipedia indefinitely semi-protected pages
+    item-412 at level 2: list_item: Livezey, Bradley C. (October 198 ... (PDF) from the original on 2022-10-09.
-        item-400 at level 4: list_item: Articles with 'species' microformats
+    item-413 at level 2: list_item: Madsen, Cort S.; McHugh, Kevin P ... (PDF) from the original on 2022-10-09.
-        item-401 at level 4: list_item: Articles containing Old English (ca. 450-1100)-language text
+    item-414 at level 2: list_item: Maisels, Charles Keith (1999). E ... n: Routledge. ISBN 978-0-415-10975-8 .
-        item-402 at level 4: list_item: Articles containing Dutch-language text
+    item-415 at level 2: list_item: Pratt, H. Douglas; Bruner, Phill ... University Press. ISBN 0-691-02399-9 .
-        item-403 at level 4: list_item: Articles containing German-language text
+    item-416 at level 2: list_item: Rau, Charles (1876). Early Man i ... rk: Harper & Brothers. LCCN 05040168 .
-        item-404 at level 4: list_item: Articles containing Norwegian-language text
+    item-417 at level 2: list_item: Shirihai, Hadoram (2008). A Comp ... ersity Press. ISBN 978-0-691-13666-0 .
-        item-405 at level 4: list_item: Articles containing Lithuanian-language text
+    item-418 at level 2: list_item: Sued-Badillo, Jalil (2003). Auto ... aris: UNESCO. ISBN 978-92-3-103832-7 .
-        item-406 at level 4: list_item: Articles containing Ancient Greek (to 1453)-language text
+    item-419 at level 2: list_item: Thorpe, I. J. (1996). The Origin ... k: Routledge. ISBN 978-0-415-08009-5 .
-        item-407 at level 4: list_item: All articles with self-published sources
+  item-420 at level 1: section_header: External links
-        item-408 at level 4: list_item: Articles with self-published sources from February 2020
+  item-421 at level 1: text: Duck  at Wikipedia's sister projects
-        item-409 at level 4: list_item: All articles with unsourced statements
+  item-422 at level 1: list: group group
-        item-410 at level 4: list_item: Articles with unsourced statements from January 2022
+    item-423 at level 2: list_item: Definitions from Wiktionary
-        item-411 at level 4: list_item: CS1: long volume value
+    item-424 at level 2: list_item: Media from Commons
-        item-412 at level 4: list_item: Pages using Sister project links with wikidata mismatch
+    item-425 at level 2: list_item: Quotations from Wikiquote
-        item-413 at level 4: list_item: Pages using Sister project links with hidden wikidata
+    item-426 at level 2: list_item: Recipes from Wikibooks
-        item-414 at level 4: list_item: Webarchive template wayback links
+    item-427 at level 2: list_item: Taxa from Wikispecies
-        item-415 at level 4: list_item: Articles with Project Gutenberg links
+    item-428 at level 2: list_item: Data from Wikidata
-        item-416 at level 4: list_item: Articles containing video clips
+  item-429 at level 1: list: group group
-      item-417 at level 3: list: group list
+    item-430 at level 2: list_item: list of books (useful looking abstracts)
-        item-418 at level 4: list_item: This page was last edited on 21 September 2024, at 12:11 (UTC).
+    item-431 at level 2: list_item: Ducks on postage stamps Archived 2013-05-13 at the Wayback Machine
-        item-419 at level 4: list_item: Text is available under the Crea ... tion, Inc., a non-profit organization.
+    item-432 at level 2: list_item: 
-      item-420 at level 3: list: group list
+    item-433 at level 2: list_item: Ducks at a Distance, by Rob Hine ... uide to identification of US waterfowl
-        item-421 at level 4: list_item: Privacy policy
+  item-434 at level 1: table with [3x2]
-        item-422 at level 4: list_item: About Wikipedia
+  item-435 at level 1: text: NewPP limit report
-        item-423 at level 4: list_item: Disclaimers
+  item-436 at level 1: text: Parsed by mw‐web.codfw.main‐5d5b97b956‐mw5gf
-        item-424 at level 4: list_item: Contact Wikipedia
+  item-437 at level 1: text: Cached time: 20241001035144
-        item-425 at level 4: list_item: Code of Conduct
+  item-438 at level 1: text: Cache expiry: 2592000
-        item-426 at level 4: list_item: Developers
+  item-439 at level 1: text: Reduced expiry: false
-        item-427 at level 4: list_item: Statistics
+  item-440 at level 1: text: Complications: [vary‐revision‐sha1, show‐toc]
-        item-428 at level 4: list_item: Cookie statement
+  item-441 at level 1: text: CPU time usage: 1.191 seconds
-        item-429 at level 4: list_item: Mobile view
+  item-442 at level 1: text: Real time usage: 1.452 seconds
-      item-430 at level 3: list: group list
+  item-443 at level 1: text: Preprocessor visited node count: 12444/1000000
-      item-431 at level 3: list: group list
+  item-444 at level 1: text: Post‐expand include size: 122530/2097152 bytes
-  item-432 at level 1: caption: Pacific black duck displaying the characteristic upending "duck"
+  item-445 at level 1: text: Template argument size: 9168/2097152 bytes
-  item-433 at level 1: caption: Male mallard.
+  item-446 at level 1: text: Highest expansion depth: 14/100
-  item-434 at level 1: caption: Wood ducks.
+  item-447 at level 1: text: Expensive parser function count: 14/500
-  item-435 at level 1: caption: Mallard landing in approach
+  item-448 at level 1: text: Unstrip recursion depth: 1/20
-  item-436 at level 1: caption: Male Mandarin duck
+  item-449 at level 1: text: Unstrip post‐expand size: 165576/5000000 bytes
-  item-437 at level 1: caption: Flying steamer ducks in Ushuaia, Argentina
+  item-450 at level 1: text: Lua time usage: 0.865/10.000 seconds
-  item-438 at level 1: caption: Female mallard in Cornwall, England
+  item-451 at level 1: text: Lua memory usage: 25093454/52428800 bytes
-  item-439 at level 1: caption: Pecten along the bill
+  item-452 at level 1: text: Number of Wikibase entities loaded: 1/400
-  item-440 at level 1: caption: Mallard duckling preening
+  item-453 at level 1: text: Transclusion expansion time report (%,ms,calls,template)
-  item-441 at level 1: caption: A Muscovy duckling
+  item-454 at level 1: text: 100.00% 1311.889      1 -total
-  item-442 at level 1: caption: Ringed teal
+  item-455 at level 1: text: 22.17%  290.786      1 Template:Automatic_taxobox
-  item-443 at level 1: caption: Indian Runner ducks, a common breed of domestic ducks
+  item-456 at level 1: text: 16.91%  221.802      1 Template:Reflist
-  item-444 at level 1: caption: Three black-colored ducks in the coat of arms of Maaninka[49]
+  item-457 at level 1: text: 10.86%  142.472     44 Template:Sfn
+  item-458 at level 1: text: 9.48%  124.344     15 Template:Lang
+  item-459 at level 1: text: 9.25%  121.312     15 Template:Cite_web
+  item-460 at level 1: text: 8.03%  105.346     26 Template:Cite_book
+  item-461 at level 1: text: 5.85%   76.725      1 Template:Short_description
+  item-462 at level 1: text: 5.74%   75.262      1 Template:Authority_control
+  item-463 at level 1: text: 4.50%   58.973      1 Template:Sisterlinks
+  item-464 at level 1: text: Saved in parser cache with key e ... ering was triggered because: page-view
+  item-465 at level 1: text: esi <esi:include src="/esitest-fa8a495983347898/content" />
+  item-466 at level 1: text: Retrieved from "https://en.wikip ... index.php?title=Duck&oldid=1246843351"
+  item-467 at level 1: text: Categories:
+  item-468 at level 1: list: group group
+    item-469 at level 2: list_item: Ducks
+    item-470 at level 2: list_item: Game birds
+    item-471 at level 2: list_item: Bird common names
+  item-472 at level 1: text: Hidden categories:
+  item-473 at level 1: list: group group
+    item-474 at level 2: list_item: All accuracy disputes
+    item-475 at level 2: list_item: Accuracy disputes from February 2020
+    item-476 at level 2: list_item: CS1 Finnish-language sources (fi)
+    item-477 at level 2: list_item: CS1 Latvian-language sources (lv)
+    item-478 at level 2: list_item: CS1 Swedish-language sources (sv)
+    item-479 at level 2: list_item: Articles with short description
+    item-480 at level 2: list_item: Short description is different from Wikidata
+    item-481 at level 2: list_item: Wikipedia indefinitely move-protected pages
+    item-482 at level 2: list_item: Wikipedia indefinitely semi-protected pages
+    item-483 at level 2: list_item: Articles with 'species' microformats
+    item-484 at level 2: list_item: Articles containing Old English (ca. 450-1100)-language text
+    item-485 at level 2: list_item: Articles containing Dutch-language text
+    item-486 at level 2: list_item: Articles containing German-language text
+    item-487 at level 2: list_item: Articles containing Norwegian-language text
+    item-488 at level 2: list_item: Articles containing Lithuanian-language text
+    item-489 at level 2: list_item: Articles containing Ancient Greek (to 1453)-language text
+    item-490 at level 2: list_item: All articles with self-published sources
+    item-491 at level 2: list_item: Articles with self-published sources from February 2020
+    item-492 at level 2: list_item: All articles with unsourced statements
+    item-493 at level 2: list_item: Articles with unsourced statements from January 2022
+    item-494 at level 2: list_item: CS1: long volume value
+    item-495 at level 2: list_item: Pages using Sister project links with wikidata mismatch
+    item-496 at level 2: list_item: Pages using Sister project links with hidden wikidata
+    item-497 at level 2: list_item: Webarchive template wayback links
+    item-498 at level 2: list_item: Articles with Project Gutenberg links
+    item-499 at level 2: list_item: Articles containing video clips
+  item-500 at level 1: list: group group
+    item-501 at level 2: list_item: This page was last edited on 21 September 2024, at 12:11 (UTC) .
+    item-502 at level 2: list_item: Text is available under the Crea ... ion, Inc. , a non-profit organization.
+  item-503 at level 1: list: group group
+    item-504 at level 2: list_item: Privacy policy
+    item-505 at level 2: list_item: About Wikipedia
+    item-506 at level 2: list_item: Disclaimers
+    item-507 at level 2: list_item: Contact Wikipedia
+    item-508 at level 2: list_item: Code of Conduct
+    item-509 at level 2: list_item: Developers
+    item-510 at level 2: list_item: Statistics
+    item-511 at level 2: list_item: Cookie statement
+    item-512 at level 2: list_item: Mobile view
+  item-513 at level 1: list: group group
+    item-514 at level 2: list_item: 
+    item-515 at level 2: list_item: 
+  item-516 at level 1: list: group group

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

@@ -1,28 +1,84 @@
-## Contents
+Jump to content
+
+Main menu
+
+Main menu
+
+move to sidebar
+
+hide
+
+Navigation
+
+- Main page
+- Contents
+- Current events
+- Random article
+- About Wikipedia
+- Contact us
+
+Contribute
+
+- Help
+- Learn to edit
+- Community portal
+- Recent changes
+- Upload file
+
+Search
+
+Search
+
+- Donate
+
+Appearance
+
+- Create account
+- Log in
+
+Personal tools
+
+- Create account
+- Log in
+
+Pages for logged out editors learn more
+
+- Contributions
+- Talk
+
+### Contents
+
+move to sidebar
+
+hide
 
 - (Top)
 - 1 Etymology
 - 2 Taxonomy
 - 3 Morphology
 - 4 Distribution and habitat
-- 5 Behaviour Toggle Behaviour subsection
+- 5 Behaviour Toggle Behaviour subsection 5.1 Feeding 5.2 Breeding 5.3 Communication 5.4 Predators
     - 5.1 Feeding
     - 5.2 Breeding
     - 5.3 Communication
     - 5.4 Predators
-- 6 Relationship with humans Toggle Relationship with humans subsection
+- 6 Relationship with humans Toggle Relationship with humans subsection 6.1 Hunting 6.2 Domestication 6.3 Heraldry 6.4 Cultural references
     - 6.1 Hunting
     - 6.2 Domestication
     - 6.3 Heraldry
     - 6.4 Cultural references
 - 7 See also
-- 8 Notes Toggle Notes subsection
+- 8 Notes Toggle Notes subsection 8.1 Citations 8.2 Sources
     - 8.1 Citations
     - 8.2 Sources
 - 9 External links
 
+Toggle the table of contents
+
 # Duck
 
+136 languages
+
 - Acèh
 - Afrikaans
 - Alemannisch
@@ -160,15 +216,25 @@
 - Žemaitėška
 - 中文
 
+Edit links
+
 - Article
 - Talk
 
+English
+
 - Read
 - View source
 - View history
 
 Tools
 
+Tools
+
+move to sidebar
+
+hide
+
 Actions
 
 - Read
@@ -200,18 +266,22 @@ In other projects
 
 Appearance
 
-<!-- image -->
+move to sidebar
+
+hide
 
 From Wikipedia, the free encyclopedia
 
+(Redirected from Duckling)
+
 Common name for many species of bird
 
-This article is about the bird. For duck as a food, see . For other uses, see .
+This article is about the bird. For duck as a food, see Duck as food. For other uses, see Duck (disambiguation).
 
-"Duckling" redirects here. For other uses, see .
+"Duckling" redirects here. For other uses, see Duckling (disambiguation).
 
 | Duck                          | Duck                          |
-|--------------------------------|--------------------------------|
+|-------------------------------|-------------------------------|
 |                               |                               |
 | Bufflehead(Bucephala albeola) | Bufflehead(Bucephala albeola) |
 | Scientific classification     | Scientific classification     |
@@ -229,14 +299,12 @@ Duck is the common name for numerous species of waterfowl in the family Anatidae
 
 Ducks are sometimes confused with several types of unrelated water birds with similar forms, such as loons or divers, grebes, gallinules and coots.
 
-## Etymology
+### Etymology
 
 The word duck comes from Old English dūce 'diver', a derivative of the verb *dūcan 'to duck, bend down low as if to get under something, or dive', because of the way many species in the dabbling duck group feed by upending; compare with Dutch duiken and German tauchen 'to dive'.
 
 Pacific black duck displaying the characteristic upending "duck"
 
-<!-- image -->
-
 This word replaced Old English ened /ænid 'duck', possibly to avoid confusion with other words, such as ende 'end' with similar forms. Other Germanic languages still have similar words for duck, for example, Dutch eend, German Ente and Norwegian and. The word ened /ænid was inherited from Proto-Indo-European; cf. Latin anas "duck", Lithuanian ántis 'duck', Ancient Greek νῆσσα /νῆττα (nēssa /nētta) 'duck', and Sanskrit ātí 'water bird', among others.
 
 A duckling is a young duck in downy plumage[1] or baby duck,[2] but in the food trade a young domestic duck which has just reached adult size and bulk and its meat is still fully tender, is sometimes labelled as a duckling.
@@ -245,60 +313,46 @@ A male is called a drake and the female is called a duck, or in ornithology a he
 
 Male mallard.
 
-<!-- image -->
-
 Wood ducks.
 
-<!-- image -->
+### Taxonomy
-
-## Taxonomy
 
 All ducks belong to the biological order Anseriformes, a group that contains the ducks, geese and swans, as well as the screamers, and the magpie goose.[5] All except the screamers belong to the biological family Anatidae.[5] Within the family, ducks are split into a variety of subfamilies and 'tribes'. The number and composition of these subfamilies and tribes is the cause of considerable disagreement among taxonomists.[5] Some base their decisions on morphological characteristics, others on shared behaviours or genetic studies.[6][7] The number of suggested subfamilies containing ducks ranges from two to five.[8][9] The significant level of hybridisation that occurs among wild ducks complicates efforts to tease apart the relationships between various species.[9]
 
 Mallard landing in approach
 
-<!-- image -->
-
 In most modern classifications, the so-called 'true ducks' belong to the subfamily Anatinae, which is further split into a varying number of tribes.[10] The largest of these, the Anatini, contains the 'dabbling' or 'river' ducks – named for their method of feeding primarily at the surface of fresh water.[11] The 'diving ducks', also named for their primary feeding method, make up the tribe Aythyini.[12] The 'sea ducks' of the tribe Mergini are diving ducks which specialise on fish and shellfish and spend a majority of their lives in saltwater.[13] The tribe Oxyurini contains the 'stifftails', diving ducks notable for their small size and stiff, upright tails.[14]
 
 A number of other species called ducks are not considered to be 'true ducks', and are typically placed in other subfamilies or tribes. The whistling ducks are assigned either to a tribe (Dendrocygnini) in the subfamily Anatinae or the subfamily Anserinae,[15] or to their own subfamily (Dendrocygninae) or family (Dendrocyganidae).[9][16] The freckled duck of Australia is either the sole member of the tribe Stictonettini in the subfamily Anserinae,[15] or in its own family, the Stictonettinae.[9] The shelducks make up the tribe Tadornini in the family Anserinae in some classifications,[15] and their own subfamily, Tadorninae, in others,[17] while the steamer ducks are either placed in the family Anserinae in the tribe Tachyerini[15] or lumped with the shelducks in the tribe Tadorini.[9] The perching ducks make up in the tribe Cairinini in the subfamily Anserinae in some classifications, while that tribe is eliminated in other classifications and its members assigned to the tribe Anatini.[9] The torrent duck is generally included in the subfamily Anserinae in the monotypic tribe Merganettini,[15] but is sometimes included in the tribe Tadornini.[18] The pink-eared duck is sometimes included as a true duck either in the tribe Anatini[15] or the tribe Malacorhynchini,[19] and other times is included with the shelducks in the tribe Tadornini.[15]
 
-## Morphology
+### Morphology
 
 Male Mandarin duck
 
-<!-- image -->
-
 The overall body plan of ducks is elongated and broad, and they are also relatively long-necked, albeit not as long-necked as the geese and swans. The body shape of diving ducks varies somewhat from this in being more rounded. The bill is usually broad and contains serrated pectens, which are particularly well defined in the filter-feeding species. In the case of some fishing species the bill is long and strongly serrated. The scaled legs are strong and well developed, and generally set far back on the body, more so in the highly aquatic species. The wings are very strong and are generally short and pointed, and the flight of ducks requires fast continuous strokes, requiring in turn strong wing muscles. Three species of steamer duck are almost flightless, however. Many species of duck are temporarily flightless while moulting; they seek out protected habitat with good food supplies during this period. This moult typically precedes migration.
 
 The drakes of northern species often have extravagant plumage, but that is moulted in summer to give a more female-like appearance, the "eclipse" plumage. Southern resident species typically show less sexual dimorphism, although there are exceptions such as the paradise shelduck of New Zealand, which is both strikingly sexually dimorphic and in which the female's plumage is brighter than that of the male. The plumage of juvenile birds generally resembles that of the female. Female ducks have evolved to have a corkscrew shaped vagina to prevent rape.
 
-## Distribution and habitat
+### Distribution and habitat
+
+See also: List of Anseriformes by population
 
 Flying steamer ducks in Ushuaia, Argentina
 
-<!-- image -->
-
 Ducks have a cosmopolitan distribution, and are found on every continent except Antarctica.[5] Several species manage to live on subantarctic islands, including South Georgia and the Auckland Islands.[20] Ducks have reached a number of isolated oceanic islands, including the Hawaiian Islands, Micronesia and the Galápagos Islands, where they are often vagrants and less often residents.[21][22] A handful are endemic to such far-flung islands.[21]
 
 Female mallard in Cornwall, England
 
-<!-- image -->
-
 Some duck species, mainly those breeding in the temperate and Arctic Northern Hemisphere, are migratory; those in the tropics are generally not. Some ducks, particularly in Australia where rainfall is erratic, are nomadic, seeking out the temporary lakes and pools that form after localised heavy rain.[23]
 
-## Behaviour
+### Behaviour
 
-### Feeding
+#### Feeding
 
 Pecten along the bill
 
-<!-- image -->
-
 Mallard duckling preening
 
-<!-- image -->
-
 Ducks eat food sources such as grasses, aquatic plants, fish, insects, small amphibians, worms, and small molluscs.
 
 Dabbling ducks feed on the surface of water or on land, or as deep as they can reach by up-ending without completely submerging.[24] Along the edge of the bill, there is a comb-like structure called a pecten. This strains the water squirting from the side of the bill and traps any food. The pecten is also used to preen feathers and to hold slippery food items.
@@ -311,61 +365,57 @@ The others have the characteristic wide flat bill adapted to dredging-type jobs
 
 The Guardian published an article advising that ducks should not be fed with bread because it damages the health of the ducks and pollutes waterways.[25]
 
-### Breeding
+#### Breeding
 
 A Muscovy duckling
 
-<!-- image -->
-
 Ducks generally only have one partner at a time, although the partnership usually only lasts one year.[26] Larger species and the more sedentary species (like fast-river specialists) tend to have pair-bonds that last numerous years.[27] Most duck species breed once a year, choosing to do so in favourable conditions (spring/summer or wet seasons). Ducks also tend to make a nest before breeding, and, after hatching, lead their ducklings to water. Mother ducks are very caring and protective of their young, but may abandon some of their ducklings if they are physically stuck in an area they cannot get out of (such as nesting in an enclosed courtyard) or are not prospering due to genetic defects or sickness brought about by hypothermia, starvation, or disease. Ducklings can also be orphaned by inconsistent late hatching where a few eggs hatch after the mother has abandoned the nest and led her ducklings to water.[28]
 
-### Communication
+#### Communication
 
 Female mallard ducks (as well as several other species in the genus Anas, such as the American and Pacific black ducks, spot-billed duck, northern pintail and common teal) make the classic "quack" sound while males make a similar but raspier sound that is sometimes written as "breeeeze",[29][self-published source?] but, despite widespread misconceptions, most species of duck do not "quack".[30] In general, ducks make a range of calls, including whistles, cooing, yodels and grunts. For example, the scaup – which are diving ducks – make a noise like "scaup" (hence their name). Calls may be loud displaying calls or quieter contact calls.
 
 A common urban legend claims that duck quacks do not echo; however, this has been proven to be false. This myth was first debunked by the Acoustics Research Centre at the University of Salford in 2003 as part of the British Association's Festival of Science.[31] It was also debunked in one of the earlier episodes of the popular Discovery Channel television show MythBusters.[32]
 
-### Predators
+#### Predators
 
 Ringed teal
 
-<!-- image -->
-
 Ducks have many predators. Ducklings are particularly vulnerable, since their inability to fly makes them easy prey not only for predatory birds but also for large fish like pike, crocodilians, predatory testudines such as the alligator snapping turtle, and other aquatic hunters, including fish-eating birds such as herons. Ducks' nests are raided by land-based predators, and brooding females may be caught unaware on the nest by mammals, such as foxes, or large birds, such as hawks or owls.
 
 Adult ducks are fast fliers, but may be caught on the water by large aquatic predators including big fish such as the North American muskie and the European pike. In flight, ducks are safe from all but a few predators such as humans and the peregrine falcon, which uses its speed and strength to catch ducks.
 
-## Relationship with humans
+### Relationship with humans
 
-### Hunting
+#### Hunting
+
+Main article: Waterfowl hunting
 
 Humans have hunted ducks since prehistoric times. Excavations of middens in California dating to 7800 – 6400 BP have turned up bones of ducks, including at least one now-extinct flightless species.[33] Ducks were captured in "significant numbers" by Holocene inhabitants of the lower Ohio River valley, suggesting they took advantage of the seasonal bounty provided by migrating waterfowl.[34] Neolithic hunters in locations as far apart as the Caribbean,[35] Scandinavia,[36] Egypt,[37] Switzerland,[38] and China relied on ducks as a source of protein for some or all of the year.[39] Archeological evidence shows that Māori people in New Zealand hunted the flightless Finsch's duck, possibly to extinction, though rat predation may also have contributed to its fate.[40] A similar end awaited the Chatham duck, a species with reduced flying capabilities which went extinct shortly after its island was colonised by Polynesian settlers.[41] It is probable that duck eggs were gathered by Neolithic hunter-gathers as well, though hard evidence of this is uncommon.[35][42]
 
 In many areas, wild ducks (including ducks farmed and released into the wild) are hunted for food or sport,[43] by shooting, or by being trapped using duck decoys. Because an idle floating duck or a duck squatting on land cannot react to fly or move quickly, "a sitting duck" has come to mean "an easy target". These ducks may be contaminated by pollutants such as PCBs.[44]
 
-### Domestication
+#### Domestication
+
+Main article: Domestic duck
 
 Indian Runner ducks, a common breed of domestic ducks
 
-<!-- image -->
-
 Ducks have many economic uses, being farmed for their meat, eggs, and feathers (particularly their down). Approximately 3 billion ducks are slaughtered each year for meat worldwide.[45] They are also kept and bred by aviculturists and often displayed in zoos. Almost all the varieties of domestic ducks are descended from the mallard (Anas platyrhynchos), apart from the Muscovy duck (Cairina moschata).[46][47] The Call duck is another example of a domestic duck breed. Its name comes from its original use established by hunters, as a decoy to attract wild mallards from the sky, into traps set for them on the ground. The call duck is the world's smallest domestic duck breed, as it weighs less than 1 kg (2.2 lb).[48]
 
-### Heraldry
+#### Heraldry
 
 Three black-colored ducks in the coat of arms of Maaninka[49]
 
-<!-- image -->
-
 Ducks appear on several coats of arms, including the coat of arms of Lubāna (Latvia)[50] and the coat of arms of Föglö (Åland).[51]
 
-### Cultural references
+#### Cultural references
 
 In 2002, psychologist Richard Wiseman and colleagues at the University of Hertfordshire, UK, finished a year-long LaughLab experiment, concluding that of all animals, ducks attract the most humor and silliness; he said, "If you're going to tell a joke involving an animal, make it a duck."[52] The word "duck" may have become an inherently funny word in many languages, possibly because ducks are seen as silly in their looks or behavior. Of the many ducks in fiction, many are cartoon characters, such as Walt Disney's Donald Duck, and Warner Bros.' Daffy Duck. Howard the Duck started as a comic book character in 1973[53][54] and was made into a movie in 1986.
 
 The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck as the mascot for the fictional youth hockey team who are protagonists of the movie, based on the duck being described as a fierce fighter. This led to the duck becoming the nickname and mascot for the eventual National Hockey League professional team of the Anaheim Ducks, who were founded with the name the Mighty Ducks of Anaheim.[citation needed] The duck is also the nickname of the University of Oregon sports teams as well as the Long Island Ducks minor league baseball team.[55]
 
-## See also
+### See also
 
 - Birds portal
 
@@ -376,14 +426,14 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 - Fictional ducks
 - Rubber duck
 
-## Notes
+### Notes
 
-### Citations
+#### Citations
 
 1. ^ "Duckling" . The American Heritage Dictionary of the English Language, Fourth Edition . Houghton Mifflin Company. 2006 . Retrieved 2015-05-22 .
 2. ^ "Duckling" . Kernerman English Multilingual Dictionary (Beta Version) . K. Dictionaries Ltd. 2000–2006 . Retrieved 2015-05-22 .
-3. ^ Dohner, Janet Vorwald (2001). The Encyclopedia of Historic and Endangered Livestock and Poultry Breeds. Yale University Press. ISBN 978-0300138139.
+3. ^ Dohner, Janet Vorwald (2001). The Encyclopedia of Historic and Endangered Livestock and Poultry Breeds . Yale University Press. ISBN 978-0300138139 .
-4. ^ Visca, Curt; Visca, Kelley (2003). How to Draw Cartoon Birds. The Rosen Publishing Group. ISBN 9780823961566.
+4. ^ Visca, Curt; Visca, Kelley (2003). How to Draw Cartoon Birds . The Rosen Publishing Group. ISBN 9780823961566 .
 5. ^ a b c d Carboneras 1992 , p. 536.
 6. ^ Livezey 1986 , pp. 737–738.
 7. ^ Madsen, McHugh &amp; de Kloet 1988 , p. 452.
@@ -405,11 +455,11 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 23. ^ "Pacific Black Duck" . www.wiresnr.org . Retrieved 2018-04-27 .
 24. ^ Ogden, Evans. "Dabbling Ducks" . CWE . Retrieved 2006-11-02 .
 25. ^ Karl Mathiesen (16 March 2015). "Don't feed the ducks bread, say conservationists" . The Guardian . Retrieved 13 November 2016 .
-26. ^ Rohwer, Frank C.; Anderson, Michael G. (1988). "Female-Biased Philopatry, Monogamy, and the Timing of Pair Formation in Migratory Waterfowl". Current Ornithology. pp. 187–221. doi:10.1007/978-1-4615-6787-5\_4. ISBN 978-1-4615-6789-9.
+26. ^ Rohwer, Frank C.; Anderson, Michael G. (1988). "Female-Biased Philopatry, Monogamy, and the Timing of Pair Formation in Migratory Waterfowl". Current Ornithology . pp. 187–221. doi : 10.1007/978-1-4615-6787-5\_4 . ISBN 978-1-4615-6789-9 .
 27. ^ Smith, Cyndi M.; Cooke, Fred; Robertson, Gregory J.; Goudie, R. Ian; Boyd, W. Sean (2000). "Long-Term Pair Bonds in Harlequin Ducks" . The Condor . 102 (1): 201–205. doi : 10.1093/condor/102.1.201 . hdl : 10315/13797 .
 28. ^ "If You Find An Orphaned Duckling - Wildlife Rehabber" . wildliferehabber.com . Archived from the original on 2018-09-23 . Retrieved 2018-12-22 .
-29. ^ Carver, Heather (2011). The Duck Bible. Lulu.com. ISBN 9780557901562.[self-published source]
+29. ^ Carver, Heather (2011). The Duck Bible . Lulu.com. ISBN 9780557901562 . [ self-published source ]
-30. ^ Titlow, Budd (2013-09-03). Bird Brains: Inside the Strange Minds of Our Fine Feathered Friends. Rowman &amp; Littlefield. ISBN 9780762797707.
+30. ^ Titlow, Budd (2013-09-03). Bird Brains: Inside the Strange Minds of Our Fine Feathered Friends . Rowman &amp; Littlefield. ISBN 9780762797707 .
 31. ^ Amos, Jonathan (2003-09-08). "Sound science is quackers" . BBC News . Retrieved 2006-11-02 .
 32. ^ "Mythbusters Episode 8" . 12 December 2003.
 33. ^ Erlandson 1994 , p. 171.
@@ -422,44 +472,46 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 40. ^ Hume 2012 , p. 53.
 41. ^ Hume 2012 , p. 52.
 42. ^ Fieldhouse 2002 , p. 167.
-43. ^ Livingston, A. D. (1998-01-01). Guide to Edible Plants and Animals. Wordsworth Editions, Limited. ISBN 9781853263774.
+43. ^ Livingston, A. D. (1998-01-01). Guide to Edible Plants and Animals . Wordsworth Editions, Limited. ISBN 9781853263774 .
 44. ^ "Study plan for waterfowl injury assessment: Determining PCB concentrations in Hudson river resident waterfowl" (PDF) . New York State Department of Environmental Conservation . US Department of Commerce. December 2008. p. 3. Archived (PDF) from the original on 2022-10-09 . Retrieved 2 July 2019 .
 45. ^ "FAOSTAT" . www.fao.org . Retrieved 2019-10-25 .
 46. ^ "Anas platyrhynchos, Domestic Duck; DigiMorph Staff - The University of Texas at Austin" . Digimorph.org . Retrieved 2012-12-23 .
 47. ^ Sy Montgomery. "Mallard; Encyclopædia Britannica" . Britannica.com . Retrieved 2012-12-23 .
-48. ^ Glenday, Craig (2014). Guinness World Records. Guinness World Records Limited. pp. 135. ISBN 978-1-908843-15-9.
+48. ^ Glenday, Craig (2014). Guinness World Records . Guinness World Records Limited. pp. 135 . ISBN 978-1-908843-15-9 .
-49. ^ Suomen kunnallisvaakunat (in Finnish). Suomen Kunnallisliitto. 1982. p. 147. ISBN 951-773-085-3.
+49. ^ Suomen kunnallisvaakunat (in Finnish). Suomen Kunnallisliitto. 1982. p. 147. ISBN 951-773-085-3 .
 50. ^ "Lubānas simbolika" (in Latvian) . Retrieved September 9, 2021 .
 51. ^ "Föglö" (in Swedish) . Retrieved September 9, 2021 .
 52. ^ Young, Emma. "World's funniest joke revealed" . New Scientist . Retrieved 7 January 2019 .
 53. ^ "Howard the Duck (character)" . Grand Comics Database .
-54. ^ Sanderson, Peter; Gilbert, Laura (2008). "1970s". Marvel Chronicle A Year by Year History. London, United Kingdom: Dorling Kindersley. p. 161. ISBN 978-0756641238. December saw the debut of the cigar-smoking Howard the Duck. In this story by writer Steve Gerber and artist Val Mayerik, various beings from different realities had begun turning up in the Man-Thing's Florida swamp, including this bad-tempered talking duck.
+54. ^ Sanderson, Peter ; Gilbert, Laura (2008). "1970s". Marvel Chronicle A Year by Year History . London, United Kingdom: Dorling Kindersley . p. 161. ISBN 978-0756641238 . December saw the debut of the cigar-smoking Howard the Duck. In this story by writer Steve Gerber and artist Val Mayerik, various beings from different realities had begun turning up in the Man-Thing's Florida swamp, including this bad-tempered talking duck.
 55. ^ "The Duck" . University of Oregon Athletics . Retrieved 2022-01-20 .
 
-### Sources
+#### Sources
 
-- American Ornithologists' Union (1998). Checklist of North American Birds (PDF). Washington, DC: American Ornithologists' Union. ISBN 978-1-891276-00-2. Archived (PDF) from the original on 2022-10-09.
+- American Ornithologists' Union (1998). Checklist of North American Birds (PDF) . Washington, DC: American Ornithologists' Union. ISBN 978-1-891276-00-2 . Archived (PDF) from the original on 2022-10-09.
-- Carboneras, Carlos (1992). del Hoyo, Josep; Elliott, Andrew; Sargatal, Jordi (eds.). Handbook of the Birds of the World. Vol. 1: Ostrich to Ducks. Barcelona: Lynx Edicions. ISBN 978-84-87334-10-8.
+- Carboneras, Carlos (1992). del Hoyo, Josep; Elliott, Andrew; Sargatal, Jordi (eds.). Handbook of the Birds of the World . Vol. 1: Ostrich to Ducks. Barcelona: Lynx Edicions. ISBN 978-84-87334-10-8 .
-- Christidis, Les; Boles, Walter E., eds. (2008). Systematics and Taxonomy of Australian Birds. Collingwood, VIC: Csiro Publishing. ISBN 978-0-643-06511-6.
+- Christidis, Les; Boles, Walter E., eds. (2008). Systematics and Taxonomy of Australian Birds . Collingwood, VIC: Csiro Publishing. ISBN 978-0-643-06511-6 .
-- Donne-Goussé, Carole; Laudet, Vincent; Hänni, Catherine (July 2002). "A molecular phylogeny of Anseriformes based on mitochondrial DNA analysis". Molecular Phylogenetics and Evolution. 23 (3): 339–356. Bibcode:2002MolPE..23..339D. doi:10.1016/S1055-7903(02)00019-2. PMID 12099792.
+- Donne-Goussé, Carole; Laudet, Vincent; Hänni, Catherine (July 2002). "A molecular phylogeny of Anseriformes based on mitochondrial DNA analysis". Molecular Phylogenetics and Evolution . 23 (3): 339–356. Bibcode : 2002MolPE..23..339D . doi : 10.1016/S1055-7903(02)00019-2 . PMID 12099792 .
-- Elphick, Chris; Dunning, John B. Jr.; Sibley, David, eds. (2001). The Sibley Guide to Bird Life and Behaviour. London: Christopher Helm. ISBN 978-0-7136-6250-4.
+- Elphick, Chris; Dunning, John B. Jr.; Sibley, David, eds. (2001). The Sibley Guide to Bird Life and Behaviour . London: Christopher Helm. ISBN 978-0-7136-6250-4 .
-- Erlandson, Jon M. (1994). Early Hunter-Gatherers of the California Coast. New York, NY: Springer Science &amp; Business Media. ISBN 978-1-4419-3231-0.
+- Erlandson, Jon M. (1994). Early Hunter-Gatherers of the California Coast . New York, NY: Springer Science &amp; Business Media. ISBN 978-1-4419-3231-0 .
-- Fieldhouse, Paul (2002). Food, Feasts, and Faith: An Encyclopedia of Food Culture in World Religions. Vol. I: A–K. Santa Barbara: ABC-CLIO. ISBN 978-1-61069-412-4.
+- Fieldhouse, Paul (2002). Food, Feasts, and Faith: An Encyclopedia of Food Culture in World Religions . Vol. I: A–K. Santa Barbara: ABC-CLIO. ISBN 978-1-61069-412-4 .
-- Fitter, Julian; Fitter, Daniel; Hosking, David (2000). Wildlife of the Galápagos. Princeton, NJ: Princeton University Press. ISBN 978-0-691-10295-5.
+- Fitter, Julian; Fitter, Daniel; Hosking, David (2000). Wildlife of the Galápagos . Princeton, NJ: Princeton University Press. ISBN 978-0-691-10295-5 .
-- Higman, B. W. (2012). How Food Made History. Chichester, UK: John Wiley &amp; Sons. ISBN 978-1-4051-8947-7.
+- Higman, B. W. (2012). How Food Made History . Chichester, UK: John Wiley &amp; Sons. ISBN 978-1-4051-8947-7 .
-- Hume, Julian H. (2012). Extinct Birds. London: Christopher Helm. ISBN 978-1-4729-3744-5.
+- Hume, Julian H. (2012). Extinct Birds . London: Christopher Helm. ISBN 978-1-4729-3744-5 .
-- Jeffries, Richard (2008). Holocene Hunter-Gatherers of the Lower Ohio River Valley. Tuscaloosa: University of Alabama Press. ISBN 978-0-8173-1658-7.
+- Jeffries, Richard (2008). Holocene Hunter-Gatherers of the Lower Ohio River Valley . Tuscaloosa: University of Alabama Press. ISBN 978-0-8173-1658-7 .
-- Kear, Janet, ed. (2005). Ducks, Geese and Swans: Species Accounts (Cairina to Mergus). Bird Families of the World. Oxford: Oxford University Press. ISBN 978-0-19-861009-0.
+- Kear, Janet, ed. (2005). Ducks, Geese and Swans: Species Accounts ( Cairina to Mergus ) . Bird Families of the World. Oxford: Oxford University Press. ISBN 978-0-19-861009-0 .
 - Livezey, Bradley C. (October 1986). "A phylogenetic analysis of recent Anseriform genera using morphological characters" (PDF) . The Auk . 103 (4): 737–754. doi : 10.1093/auk/103.4.737 . Archived (PDF) from the original on 2022-10-09.
 - Madsen, Cort S.; McHugh, Kevin P.; de Kloet, Siwo R. (July 1988). "A partial classification of waterfowl (Anatidae) based on single-copy DNA" (PDF) . The Auk . 105 (3): 452–459. doi : 10.1093/auk/105.3.452 . Archived (PDF) from the original on 2022-10-09.
-- Maisels, Charles Keith (1999). Early Civilizations of the Old World. London: Routledge. ISBN 978-0-415-10975-8.
+- Maisels, Charles Keith (1999). Early Civilizations of the Old World . London: Routledge. ISBN 978-0-415-10975-8 .
-- Pratt, H. Douglas; Bruner, Phillip L.; Berrett, Delwyn G. (1987). A Field Guide to the Birds of Hawaii and the Tropical Pacific. Princeton, NJ: Princeton University Press. ISBN 0-691-02399-9.
+- Pratt, H. Douglas; Bruner, Phillip L.; Berrett, Delwyn G. (1987). A Field Guide to the Birds of Hawaii and the Tropical Pacific . Princeton, NJ: Princeton University Press. ISBN 0-691-02399-9 .
-- Rau, Charles (1876). Early Man in Europe. New York: Harper &amp; Brothers. LCCN 05040168.
+- Rau, Charles (1876). Early Man in Europe . New York: Harper &amp; Brothers. LCCN 05040168 .
-- Shirihai, Hadoram (2008). A Complete Guide to Antarctic Wildlife. Princeton, NJ, US: Princeton University Press. ISBN 978-0-691-13666-0.
+- Shirihai, Hadoram (2008). A Complete Guide to Antarctic Wildlife . Princeton, NJ, US: Princeton University Press. ISBN 978-0-691-13666-0 .
-- Sued-Badillo, Jalil (2003). Autochthonous Societies. General History of the Caribbean. Paris: UNESCO. ISBN 978-92-3-103832-7.
+- Sued-Badillo, Jalil (2003). Autochthonous Societies . General History of the Caribbean. Paris: UNESCO. ISBN 978-92-3-103832-7 .
-- Thorpe, I. J. (1996). The Origins of Agriculture in Europe. New York: Routledge. ISBN 978-0-415-08009-5.
+- Thorpe, I. J. (1996). The Origins of Agriculture in Europe . New York: Routledge. ISBN 978-0-415-08009-5 .
 
-## External links
+### External links
+
+Duck  at Wikipedia's sister projects
 
 - Definitions from Wiktionary
 - Media from Commons
@@ -473,15 +525,75 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 - Ducks at a Distance, by Rob Hines at Project Gutenberg - A modern illustrated guide to identification of US waterfowl
 
 | Authority control databases   | Authority control databases                  |
-|--------------------------------|----------------------------------------------|
+|-------------------------------|----------------------------------------------|
 | National                      | United StatesFranceBnF dataJapanLatviaIsrael |
 | Other                         | IdRef                                        |
 
-<!-- image -->
+NewPP limit report
 
-Retrieved from ""
+Parsed by mw‐web.codfw.main‐5d5b97b956‐mw5gf
 
-:
+Cached time: 20241001035144
+
+Cache expiry: 2592000
+
+Reduced expiry: false
+
+Complications: [vary‐revision‐sha1, show‐toc]
+
+CPU time usage: 1.191 seconds
+
+Real time usage: 1.452 seconds
+
+Preprocessor visited node count: 12444/1000000
+
+Post‐expand include size: 122530/2097152 bytes
+
+Template argument size: 9168/2097152 bytes
+
+Highest expansion depth: 14/100
+
+Expensive parser function count: 14/500
+
+Unstrip recursion depth: 1/20
+
+Unstrip post‐expand size: 165576/5000000 bytes
+
+Lua time usage: 0.865/10.000 seconds
+
+Lua memory usage: 25093454/52428800 bytes
+
+Number of Wikibase entities loaded: 1/400
+
+Transclusion expansion time report (%,ms,calls,template)
+
+100.00% 1311.889      1 -total
+
+22.17%  290.786      1 Template:Automatic\_taxobox
+
+16.91%  221.802      1 Template:Reflist
+
+10.86%  142.472     44 Template:Sfn
+
+9.48%  124.344     15 Template:Lang
+
+9.25%  121.312     15 Template:Cite\_web
+
+8.03%  105.346     26 Template:Cite\_book
+
+5.85%   76.725      1 Template:Short\_description
+
+5.74%   75.262      1 Template:Authority\_control
+
+4.50%   58.973      1 Template:Sisterlinks
+
+Saved in parser cache with key enwiki:pcache:idhash:37674-0!canonical and timestamp 20241001035144 and revision id 1246843351. Rendering was triggered because: page-view
+
+esi &lt;esi:include src="/esitest-fa8a495983347898/content" /&gt;
+
+Retrieved from "https://en.wikipedia.org/w/index.php?title=Duck&amp;oldid=1246843351"
+
+Categories:
 
 - Ducks
 - Game birds
@@ -516,7 +628,7 @@ Hidden categories:
 - Articles with Project Gutenberg links
 - Articles containing video clips
 
-- This page was last edited on 21 September 2024, at 12:11 (UTC).
+- This page was last edited on 21 September 2024, at 12:11 (UTC) .
 - Text is available under the Creative Commons Attribution-ShareAlike License 4.0 ;
 additional terms may apply. By using this site, you agree to the Terms of Use and Privacy Policy . Wikipedia® is a registered trademark of the Wikimedia Foundation, Inc. , a non-profit organization.
 

tests/data/html/example_08.html

@@ -0,0 +1,21 @@
+<html>
+    <body>
+        <h1>Introduction to parsing HTML files with <img src="https://docling-project.github.io/docling/assets/logo.png" alt="Docling" height="64"> Docling</h1>
+        <p>Docling simplifies document processing, parsing diverse formats — including HTML — and providing seamless integrations with the gen AI ecosystem.</p>
+        <h2>Supported file formats</h2>
+        <p>Docling supports multiple file formats..</p>
+        <ul>
+            <li><img src="file://../assets/pdf.png" height="32" alt="PDF">Advanced PDF understanding</li>
+            <li><img src="file://../assets/docx.png" height="32" alt="DOCX">Microsoft Office DOCX</li>
+            <li><img src="file://../assets/html.png" height="32" alt="HTML">HTML files (with optional support for images)</li>
+        </ul>
+        <h3>Three backends for handling HTML files</h3>
+        <p>Docling has three backends for parsing HTML files:</p>
+        <ol>
+            <li><b>HTMLDocumentBackend</b> Ignores images</li>
+            <li><b>HTMLDocumentBackendImagesInline</b> Extracts images inline</li>
+            <li><b>HTMLDocumentBackendImagesReferenced</b> Extracts images as references</li>
+        </ol>
+    </body>
+</html>
+

tests/data/html/example_09.html

@@ -0,0 +1,21 @@
+<html>
+    <body>
+        <h1>Introduction to parsing HTML files with <img src="https://docling-project.github.io/docling/assets/logo.png" alt="Docling" height="64"> Docling</h1>
+        <p>Docling simplifies document processing, parsing diverse formats — including HTML — and providing seamless integrations with the gen AI ecosystem.</p>
+        <h2>Supported file formats</h2>
+        <p>Docling supports multiple file formats..</p>
+        <ul>
+            <li><img src="https://github.com/docling-project/docling/tree/main/docs/assets/pdf.png" height="32" alt="PDF">Advanced PDF understanding</li>
+            <li><img src="https://github.com/docling-project/docling/tree/main/docs/assets/docx.png" height="32" alt="DOCX">Microsoft Office DOCX</li>
+            <li><img src="https://github.com/docling-project/docling/tree/main/docs/assets/html.png" height="32" alt="HTML">HTML files (with optional support for images)</li>
+        </ul>
+        <h3>Three backends for handling HTML files</h3>
+        <p>Docling has three backends for parsing HTML files:</p>
+        <ol>
+            <li><b>HTMLDocumentBackend</b> Ignores images</li>
+            <li><b>HTMLDocumentBackendImagesInline</b> Extracts images inline</li>
+            <li><b>HTMLDocumentBackendImagesReferenced</b> Extracts images as references</li>
+        </ol>
+    </body>
+</html>
+

tests/test_backend_html.py

@@ -37,10 +37,10 @@ def test_heading_levels():
         if isinstance(item, SectionHeaderItem):
             if item.text == "Etymology":
                 found_lvl_1 = True
-                assert item.level == 1
+                assert item.level == 2
             elif item.text == "Feeding":
                 found_lvl_2 = True
-                assert item.level == 2
+                assert item.level == 3
     assert found_lvl_1 and found_lvl_2