mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(html): put parsed item in body if doc has no header

Browse Source 
In case an HTML does not have any header tag, all parsed items are placed in
DoclingDocument's body content layer.
HTML paragraphs ('p' tags) are parsed as text items with paragraph label.
Update test ground truth accoring to the changes above.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis 2025-02-28 18:03:58 +01:00
parent 70e6b942e1
commit 38d622f22c
4 changed files with 502 additions and 632 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
docling/backend/html_backend.py
View File

@ -67,7 +67,8 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
self.soup = BeautifulSoup(html_content, "html.parser") self.soup = BeautifulSoup(html_content, "html.parser")
except Exception as e: except Exception as e:
raise RuntimeError( raise RuntimeError(
f"Could not initialize HTML backend for file with hash {self.document_hash}." "Could not initialize HTML backend for file with "
f"hash {self.document_hash}."
) from e ) from e
@override @override
@ -104,18 +105,22 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
_log.debug("Trying to convert HTML...") _log.debug("Trying to convert HTML...")
if self.is_valid(): if self.is_valid():
self.content_layer = ContentLayer.FURNITURE
assert self.soup is not None assert self.soup is not None
content = self.soup.body or self.soup content = self.soup.body or self.soup
# Replace <br> tags with newline characters # Replace <br> tags with newline characters
# TODO: remove style to avoid losing text from tags like i, b, span, ... # TODO: remove style to avoid losing text from tags like i, b, span, ...
for br in content("br"): for br in content("br"):
br.replace_with(NavigableString("\n")) br.replace_with(NavigableString("\n"))
headers = content.find(["h1", "h2", "h3", "h4", "h5", "h6"])
self.content_layer = (
ContentLayer.BODY if headers is None else ContentLayer.FURNITURE
)
self.walk(content, doc) self.walk(content, doc)
else: else:
raise RuntimeError( raise RuntimeError(
f"Cannot convert doc with {self.document_hash} because the backend failed to init." f"Cannot convert doc with {self.document_hash} because the backend "
"failed to init."
) )
return doc return doc
@ -147,7 +152,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
if text and tag.name in ["div"]: if text and tag.name in ["div"]:
doc.add_text( doc.add_text(
parent=self.parents[self.level], parent=self.parents[self.level],
label=DocItemLabel.TEXT, label=DocItemLabel.PARAGRAPH,
text=text, text=text,
content_layer=self.content_layer, content_layer=self.content_layer,
) )
@ -259,11 +264,10 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
if element.text is None: if element.text is None:
return return
text = element.text.strip() text = element.text.strip()
label = DocItemLabel.TEXT
if text: if text:
doc.add_text( doc.add_text(
parent=self.parents[self.level], parent=self.parents[self.level],
label=label, label=DocItemLabel.PARAGRAPH,
text=text, text=text,
content_layer=self.content_layer, content_layer=self.content_layer,
) )
@ -533,7 +537,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
def handle_image(self, element: Tag, doc: DoclingDocument) -> None: def handle_image(self, element: Tag, doc: DoclingDocument) -> None:
"""Handles image tags (img).""" """Handles image tags (img)."""
_log.warning(f"ignoring <img> tags at the moment: {element}") _log.debug(f"ignoring <img> tags at the moment: {element}")
doc.add_picture( doc.add_picture(
parent=self.parents[self.level], parent=self.parents[self.level],

905
tests/data/groundtruth/docling_v2/wiki_duck.html.itxt
View File

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

150
tests/data/groundtruth/docling_v2/wiki_duck.html.json
View File

@ -138,7 +138,7 @@
"$ref": "#/texts/7" "$ref": "#/texts/7"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -164,7 +164,7 @@
"$ref": "#/texts/13" "$ref": "#/texts/13"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -174,7 +174,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -188,7 +188,7 @@
"$ref": "#/texts/14" "$ref": "#/texts/14"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -198,7 +198,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -215,7 +215,7 @@
"$ref": "#/texts/16" "$ref": "#/texts/16"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -232,7 +232,7 @@
"$ref": "#/texts/18" "$ref": "#/texts/18"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -249,7 +249,7 @@
"$ref": "#/texts/21" "$ref": "#/texts/21"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -263,7 +263,7 @@
"$ref": "#/texts/22" "$ref": "#/texts/22"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "header-1", "name": "header-1",
"label": "section" "label": "section"
}, },
@ -304,7 +304,7 @@
"$ref": "#/texts/42" "$ref": "#/texts/42"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -314,7 +314,7 @@
"$ref": "#/texts/24" "$ref": "#/texts/24"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -324,7 +324,7 @@
"$ref": "#/texts/25" "$ref": "#/texts/25"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -334,7 +334,7 @@
"$ref": "#/texts/26" "$ref": "#/texts/26"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -344,7 +344,7 @@
"$ref": "#/texts/27" "$ref": "#/texts/27"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -367,7 +367,7 @@
"$ref": "#/texts/32" "$ref": "#/texts/32"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -377,7 +377,7 @@
"$ref": "#/texts/29" "$ref": "#/texts/29"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -387,7 +387,7 @@
"$ref": "#/texts/30" "$ref": "#/texts/30"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -397,7 +397,7 @@
"$ref": "#/texts/31" "$ref": "#/texts/31"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -407,7 +407,7 @@
"$ref": "#/texts/32" "$ref": "#/texts/32"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -430,7 +430,7 @@
"$ref": "#/texts/37" "$ref": "#/texts/37"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -440,7 +440,7 @@
"$ref": "#/texts/34" "$ref": "#/texts/34"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -450,7 +450,7 @@
"$ref": "#/texts/35" "$ref": "#/texts/35"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -460,7 +460,7 @@
"$ref": "#/texts/36" "$ref": "#/texts/36"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -470,7 +470,7 @@
"$ref": "#/texts/37" "$ref": "#/texts/37"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -480,7 +480,7 @@
"$ref": "#/texts/38" "$ref": "#/texts/38"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -497,7 +497,7 @@
"$ref": "#/texts/41" "$ref": "#/texts/41"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -507,7 +507,7 @@
"$ref": "#/texts/40" "$ref": "#/texts/40"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -517,7 +517,7 @@
"$ref": "#/texts/41" "$ref": "#/texts/41"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -527,7 +527,7 @@
"$ref": "#/texts/42" "$ref": "#/texts/42"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"name": "list", "name": "list",
"label": "list" "label": "list"
}, },
@ -1623,7 +1623,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "paragraph", "label": "paragraph",
"prov": [], "prov": [],
"orig": "Main menu", "orig": "Main menu",
@ -1635,7 +1635,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "paragraph", "label": "paragraph",
"prov": [], "prov": [],
"orig": "Navigation", "orig": "Navigation",
@ -1647,7 +1647,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Main page", "orig": "Main page",
@ -1661,7 +1661,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Contents", "orig": "Contents",
@ -1675,7 +1675,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Current events", "orig": "Current events",
@ -1689,7 +1689,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Random article", "orig": "Random article",
@ -1703,7 +1703,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "About Wikipedia", "orig": "About Wikipedia",
@ -1717,7 +1717,7 @@
"$ref": "#/groups/0" "$ref": "#/groups/0"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Contact us", "orig": "Contact us",
@ -1731,7 +1731,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "paragraph", "label": "paragraph",
"prov": [], "prov": [],
"orig": "Contribute", "orig": "Contribute",
@ -1743,7 +1743,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Help", "orig": "Help",
@ -1757,7 +1757,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Learn to edit", "orig": "Learn to edit",
@ -1771,7 +1771,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Community portal", "orig": "Community portal",
@ -1785,7 +1785,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Recent changes", "orig": "Recent changes",
@ -1799,7 +1799,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Upload file", "orig": "Upload file",
@ -1813,7 +1813,7 @@
"$ref": "#/groups/3" "$ref": "#/groups/3"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Donate", "orig": "Donate",
@ -1827,7 +1827,7 @@
"$ref": "#/groups/5" "$ref": "#/groups/5"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Create account", "orig": "Create account",
@ -1841,7 +1841,7 @@
"$ref": "#/groups/5" "$ref": "#/groups/5"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Log in", "orig": "Log in",
@ -1855,7 +1855,7 @@
"$ref": "#/groups/6" "$ref": "#/groups/6"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Create account", "orig": "Create account",
@ -1869,7 +1869,7 @@
"$ref": "#/groups/6" "$ref": "#/groups/6"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Log in", "orig": "Log in",
@ -1883,7 +1883,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "paragraph", "label": "paragraph",
"prov": [], "prov": [],
"orig": "Pages for logged out editors", "orig": "Pages for logged out editors",
@ -1895,7 +1895,7 @@
"$ref": "#/groups/7" "$ref": "#/groups/7"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Contributions", "orig": "Contributions",
@ -1909,7 +1909,7 @@
"$ref": "#/groups/7" "$ref": "#/groups/7"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "Talk", "orig": "Talk",
@ -1927,7 +1927,7 @@
"$ref": "#/groups/9" "$ref": "#/groups/9"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "section_header", "label": "section_header",
"prov": [], "prov": [],
"orig": "Contents", "orig": "Contents",
@ -1940,7 +1940,7 @@
"$ref": "#/groups/9" "$ref": "#/groups/9"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "(Top)", "orig": "(Top)",
@ -1958,7 +1958,7 @@
"$ref": "#/groups/10" "$ref": "#/groups/10"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "1 Etymology", "orig": "1 Etymology",
@ -1976,7 +1976,7 @@
"$ref": "#/groups/11" "$ref": "#/groups/11"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "2 Taxonomy", "orig": "2 Taxonomy",
@ -1994,7 +1994,7 @@
"$ref": "#/groups/12" "$ref": "#/groups/12"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "3 Morphology", "orig": "3 Morphology",
@ -2012,7 +2012,7 @@
"$ref": "#/groups/13" "$ref": "#/groups/13"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "4 Distribution and habitat", "orig": "4 Distribution and habitat",
@ -2030,7 +2030,7 @@
"$ref": "#/groups/14" "$ref": "#/groups/14"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "5 Behaviour Toggle Behaviour subsection", "orig": "5 Behaviour Toggle Behaviour subsection",
@ -2048,7 +2048,7 @@
"$ref": "#/groups/15" "$ref": "#/groups/15"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "5.1 Feeding", "orig": "5.1 Feeding",
@ -2066,7 +2066,7 @@
"$ref": "#/groups/16" "$ref": "#/groups/16"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "5.2 Breeding", "orig": "5.2 Breeding",
@ -2084,7 +2084,7 @@
"$ref": "#/groups/17" "$ref": "#/groups/17"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "5.3 Communication", "orig": "5.3 Communication",
@ -2102,7 +2102,7 @@
"$ref": "#/groups/18" "$ref": "#/groups/18"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "5.4 Predators", "orig": "5.4 Predators",
@ -2120,7 +2120,7 @@
"$ref": "#/groups/19" "$ref": "#/groups/19"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "6 Relationship with humans Toggle Relationship with humans subsection", "orig": "6 Relationship with humans Toggle Relationship with humans subsection",
@ -2138,7 +2138,7 @@
"$ref": "#/groups/20" "$ref": "#/groups/20"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "6.1 Hunting", "orig": "6.1 Hunting",
@ -2156,7 +2156,7 @@
"$ref": "#/groups/21" "$ref": "#/groups/21"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "6.2 Domestication", "orig": "6.2 Domestication",
@ -2174,7 +2174,7 @@
"$ref": "#/groups/22" "$ref": "#/groups/22"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "6.3 Heraldry", "orig": "6.3 Heraldry",
@ -2192,7 +2192,7 @@
"$ref": "#/groups/23" "$ref": "#/groups/23"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "6.4 Cultural references", "orig": "6.4 Cultural references",
@ -2210,7 +2210,7 @@
"$ref": "#/groups/24" "$ref": "#/groups/24"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "7 See also", "orig": "7 See also",
@ -2228,7 +2228,7 @@
"$ref": "#/groups/25" "$ref": "#/groups/25"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "8 Notes Toggle Notes subsection", "orig": "8 Notes Toggle Notes subsection",
@ -2246,7 +2246,7 @@
"$ref": "#/groups/26" "$ref": "#/groups/26"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "8.1 Citations", "orig": "8.1 Citations",
@ -2264,7 +2264,7 @@
"$ref": "#/groups/27" "$ref": "#/groups/27"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "8.2 Sources", "orig": "8.2 Sources",
@ -2282,7 +2282,7 @@
"$ref": "#/groups/28" "$ref": "#/groups/28"
} }
], ],
"content_layer": "body", "content_layer": "furniture",
"label": "list_item", "label": "list_item",
"prov": [], "prov": [],
"orig": "9 External links", "orig": "9 External links",
@ -7592,7 +7592,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "picture", "label": "picture",
"prov": [], "prov": [],
"captions": [], "captions": [],
@ -7606,7 +7606,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "picture", "label": "picture",
"prov": [], "prov": [],
"captions": [], "captions": [],
@ -7620,7 +7620,7 @@
"$ref": "#/body" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "furniture",
"label": "picture", "label": "picture",
"prov": [], "prov": [],
"captions": [], "captions": [],

59
tests/data/groundtruth/docling_v2/wiki_duck.html.md
View File

@ -1,62 +1,3 @@
Main menu
Navigation
- Main page
- Contents
- Current events
- Random article
- About Wikipedia
- Contact us
Contribute
- Help
- Learn to edit
- Community portal
- Recent changes
- Upload file
<!-- image -->
<!-- image -->
<!-- image -->
- Donate
- Create account
- Log in
- Create account
- Log in
Pages for logged out editors
- Contributions
- Talk
## Contents
- (Top)
- 1 Etymology
- 2 Taxonomy
- 3 Morphology
- 4 Distribution and habitat
- 5 Behaviour Toggle Behaviour subsection
- 5.1 Feeding
- 5.2 Breeding
- 5.3 Communication
- 5.4 Predators
- 6 Relationship with humans Toggle Relationship with humans subsection
- 6.1 Hunting
- 6.2 Domestication
- 6.3 Heraldry
- 6.4 Cultural references
- 7 See also
- 8 Notes Toggle Notes subsection
- 8.1 Citations
- 8.2 Sources
- 9 External links
# Duck # Duck
- Acèh - Acèh