fix(markdown): fix single-formatted headings & list items (#1820)
* fix(markdown): fix formatting & inline edge cases (show behavior before change) Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * add change and updated test data Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * update lock Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> * improve test case Signed-off-by: Panos Vagenas <pva@zurich.ibm.com> --------- Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
GitHub
parent
41e8cae26b
commit
7c5614a37a
@ -2,9 +2,10 @@ import logging
|
||||
import re
|
||||
import warnings
|
||||
from copy import deepcopy
|
||||
from enum import Enum
|
||||
from io import BytesIO
|
||||
from pathlib import Path
|
||||
from typing import List, Optional, Set, Union
|
||||
from typing import List, Literal, Optional, Set, Union
|
||||
|
||||
import marko
|
||||
import marko.element
|
||||
@ -21,7 +22,8 @@ from docling_core.types.doc import (
|
||||
)
|
||||
from docling_core.types.doc.document import Formatting, OrderedList, UnorderedList
|
||||
from marko import Markdown
|
||||
from pydantic import AnyUrl, TypeAdapter
|
||||
from pydantic import AnyUrl, BaseModel, Field, TypeAdapter
|
||||
from typing_extensions import Annotated
|
||||
|
||||
from docling.backend.abstract_backend import DeclarativeDocumentBackend
|
||||
from docling.backend.html_backend import HTMLDocumentBackend
|
||||
@ -35,6 +37,31 @@ _START_MARKER = f"#_#_{_MARKER_BODY}_START_#_#"
|
||||
_STOP_MARKER = f"#_#_{_MARKER_BODY}_STOP_#_#"
|
||||
|
||||
|
||||
class _PendingCreationType(str, Enum):
|
||||
"""CoordOrigin."""
|
||||
|
||||
HEADING = "heading"
|
||||
LIST_ITEM = "list_item"
|
||||
|
||||
|
||||
class _HeadingCreationPayload(BaseModel):
|
||||
kind: Literal["heading"] = "heading"
|
||||
level: int
|
||||
|
||||
|
||||
class _ListItemCreationPayload(BaseModel):
|
||||
kind: Literal["list_item"] = "list_item"
|
||||
|
||||
|
||||
_CreationPayload = Annotated[
|
||||
Union[
|
||||
_HeadingCreationPayload,
|
||||
_ListItemCreationPayload,
|
||||
],
|
||||
Field(discriminator="kind"),
|
||||
]
|
||||
|
||||
|
||||
class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
def _shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
|
||||
# This regex will match any sequence of underscores
|
||||
@ -155,6 +182,52 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
doc.add_table(data=table_data)
|
||||
return
|
||||
|
||||
def _create_list_item(
|
||||
self,
|
||||
doc: DoclingDocument,
|
||||
parent_item: Optional[NodeItem],
|
||||
text: str,
|
||||
formatting: Optional[Formatting] = None,
|
||||
hyperlink: Optional[Union[AnyUrl, Path]] = None,
|
||||
):
|
||||
if not isinstance(parent_item, (OrderedList, UnorderedList)):
|
||||
_log.warning("ListItem would have not had a list parent, adding one.")
|
||||
parent_item = doc.add_unordered_list(parent=parent_item)
|
||||
item = doc.add_list_item(
|
||||
text=text,
|
||||
enumerated=(isinstance(parent_item, OrderedList)),
|
||||
parent=parent_item,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
return item
|
||||
|
||||
def _create_heading_item(
|
||||
self,
|
||||
doc: DoclingDocument,
|
||||
parent_item: Optional[NodeItem],
|
||||
text: str,
|
||||
level: int,
|
||||
formatting: Optional[Formatting] = None,
|
||||
hyperlink: Optional[Union[AnyUrl, Path]] = None,
|
||||
):
|
||||
if level == 1:
|
||||
item = doc.add_title(
|
||||
text=text,
|
||||
parent=parent_item,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
else:
|
||||
item = doc.add_heading(
|
||||
text=text,
|
||||
level=level - 1,
|
||||
parent=parent_item,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
return item
|
||||
|
||||
def _iterate_elements( # noqa: C901
|
||||
self,
|
||||
*,
|
||||
@ -162,6 +235,9 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
depth: int,
|
||||
doc: DoclingDocument,
|
||||
visited: Set[marko.element.Element],
|
||||
creation_stack: list[
|
||||
_CreationPayload
|
||||
], # stack for lazy item creation triggered deep in marko's AST (on RawText)
|
||||
parent_item: Optional[NodeItem] = None,
|
||||
formatting: Optional[Formatting] = None,
|
||||
hyperlink: Optional[Union[AnyUrl, Path]] = None,
|
||||
@ -177,28 +253,17 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
f" - Heading level {element.level}, content: {element.children[0].children}" # type: ignore
|
||||
)
|
||||
|
||||
if len(element.children) == 1:
|
||||
child = element.children[0]
|
||||
snippet_text = str(child.children) # type: ignore
|
||||
visited.add(child)
|
||||
else:
|
||||
snippet_text = "" # inline group will be created
|
||||
|
||||
if element.level == 1:
|
||||
parent_item = doc.add_title(
|
||||
text=snippet_text,
|
||||
parent=parent_item,
|
||||
if len(element.children) > 1: # inline group will be created further down
|
||||
parent_item = self._create_heading_item(
|
||||
doc=doc,
|
||||
parent_item=parent_item,
|
||||
text="",
|
||||
level=element.level,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
else:
|
||||
parent_item = doc.add_heading(
|
||||
text=snippet_text,
|
||||
level=element.level - 1,
|
||||
parent=parent_item,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
creation_stack.append(_HeadingCreationPayload(level=element.level))
|
||||
|
||||
elif isinstance(element, marko.block.List):
|
||||
has_non_empty_list_items = False
|
||||
@ -224,22 +289,16 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
self._close_table(doc)
|
||||
_log.debug(" - List item")
|
||||
|
||||
if len(child.children) == 1:
|
||||
snippet_text = str(child.children[0].children) # type: ignore
|
||||
visited.add(child)
|
||||
if len(child.children) > 1: # inline group will be created further down
|
||||
parent_item = self._create_list_item(
|
||||
doc=doc,
|
||||
parent_item=parent_item,
|
||||
text="",
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
else:
|
||||
snippet_text = "" # inline group will be created
|
||||
is_numbered = isinstance(parent_item, OrderedList)
|
||||
if not isinstance(parent_item, (OrderedList, UnorderedList)):
|
||||
_log.warning("ListItem would have not had a list parent, adding one.")
|
||||
parent_item = doc.add_unordered_list(parent=parent_item)
|
||||
parent_item = doc.add_list_item(
|
||||
enumerated=is_numbered,
|
||||
parent=parent_item,
|
||||
text=snippet_text,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
creation_stack.append(_ListItemCreationPayload())
|
||||
|
||||
elif isinstance(element, marko.inline.Image):
|
||||
self._close_table(doc)
|
||||
@ -285,13 +344,38 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
self.md_table_buffer.append(snippet_text)
|
||||
elif snippet_text:
|
||||
self._close_table(doc)
|
||||
doc.add_text(
|
||||
label=DocItemLabel.TEXT,
|
||||
parent=parent_item,
|
||||
text=snippet_text,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
|
||||
if creation_stack:
|
||||
while len(creation_stack) > 0:
|
||||
to_create = creation_stack.pop()
|
||||
if isinstance(to_create, _ListItemCreationPayload):
|
||||
parent_item = self._create_list_item(
|
||||
doc=doc,
|
||||
parent_item=parent_item,
|
||||
text=snippet_text,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
elif isinstance(to_create, _HeadingCreationPayload):
|
||||
# not keeping as parent_item as logic for correctly tracking
|
||||
# that not implemented yet (section components not captured
|
||||
# as heading children in marko)
|
||||
self._create_heading_item(
|
||||
doc=doc,
|
||||
parent_item=parent_item,
|
||||
text=snippet_text,
|
||||
level=to_create.level,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
else:
|
||||
doc.add_text(
|
||||
label=DocItemLabel.TEXT,
|
||||
parent=parent_item,
|
||||
text=snippet_text,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
)
|
||||
|
||||
elif isinstance(element, marko.inline.CodeSpan):
|
||||
self._close_table(doc)
|
||||
@ -353,7 +437,6 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
parent_item = doc.add_inline_group(parent=parent_item)
|
||||
|
||||
processed_block_types = (
|
||||
# marko.block.Heading,
|
||||
marko.block.CodeBlock,
|
||||
marko.block.FencedCode,
|
||||
marko.inline.RawText,
|
||||
@ -369,6 +452,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
depth=depth + 1,
|
||||
doc=doc,
|
||||
visited=visited,
|
||||
creation_stack=creation_stack,
|
||||
parent_item=parent_item,
|
||||
formatting=formatting,
|
||||
hyperlink=hyperlink,
|
||||
@ -412,6 +496,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
|
||||
doc=doc,
|
||||
parent_item=None,
|
||||
visited=set(),
|
||||
creation_stack=[],
|
||||
)
|
||||
self._close_table(doc=doc) # handle any last hanging table
|
||||
|
||||
|
||||
@ -2705,7 +2705,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -2745,7 +2745,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
@ -13641,7 +13641,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -13687,7 +13687,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
@ -26499,7 +26499,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -26545,7 +26545,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
|
||||
116
tests/data/groundtruth/docling_v2/2203.01017v2.json
vendored
116
tests/data/groundtruth/docling_v2/2203.01017v2.json
vendored
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "2203.01017v2",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
@ -17863,7 +17863,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -18753,7 +18754,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -20117,7 +20119,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/3",
|
||||
@ -22266,7 +22269,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/4",
|
||||
@ -22927,7 +22931,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/5",
|
||||
@ -24050,7 +24055,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/6",
|
||||
@ -26307,7 +26313,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/7",
|
||||
@ -27600,7 +27607,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/8",
|
||||
@ -27635,7 +27643,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/9",
|
||||
@ -27670,7 +27679,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/10",
|
||||
@ -27705,7 +27715,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/11",
|
||||
@ -27740,7 +27751,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/12",
|
||||
@ -27783,7 +27795,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/13",
|
||||
@ -27818,7 +27831,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/14",
|
||||
@ -27853,7 +27867,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/15",
|
||||
@ -27888,7 +27903,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/16",
|
||||
@ -27931,7 +27947,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/17",
|
||||
@ -27966,7 +27983,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/18",
|
||||
@ -28001,7 +28019,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/19",
|
||||
@ -28036,7 +28055,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/20",
|
||||
@ -28071,7 +28091,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/21",
|
||||
@ -28106,7 +28127,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/22",
|
||||
@ -28141,7 +28163,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/23",
|
||||
@ -28176,7 +28199,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/24",
|
||||
@ -28211,7 +28235,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/25",
|
||||
@ -28246,7 +28271,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/26",
|
||||
@ -28281,7 +28307,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/27",
|
||||
@ -28324,7 +28351,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/28",
|
||||
@ -28359,7 +28387,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/29",
|
||||
@ -28394,7 +28423,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/30",
|
||||
@ -28429,7 +28459,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/31",
|
||||
@ -28464,7 +28495,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/32",
|
||||
@ -28499,7 +28531,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/33",
|
||||
@ -28542,7 +28575,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/34",
|
||||
@ -28577,7 +28611,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/35",
|
||||
@ -28612,7 +28647,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/36",
|
||||
@ -28647,7 +28683,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/37",
|
||||
@ -28682,7 +28719,8 @@
|
||||
"num_rows": 0,
|
||||
"num_cols": 0,
|
||||
"grid": []
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "2206.01062",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
@ -23491,7 +23491,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -26654,7 +26655,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -29187,7 +29189,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/3",
|
||||
@ -31574,7 +31577,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/4",
|
||||
@ -34177,7 +34181,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "2305.03393v1-pg9",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
@ -2104,7 +2104,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -2705,7 +2705,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -2745,7 +2745,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
@ -13641,7 +13641,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -13687,7 +13687,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
@ -26499,7 +26499,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.9373534917831421,
|
||||
"confidence": 0.9373533725738525,
|
||||
"cells": [
|
||||
{
|
||||
"index": 0,
|
||||
@ -26545,7 +26545,7 @@
|
||||
"b": 102.78223000000003,
|
||||
"coord_origin": "TOPLEFT"
|
||||
},
|
||||
"confidence": 0.8858680725097656,
|
||||
"confidence": 0.8858679533004761,
|
||||
"cells": [
|
||||
{
|
||||
"index": 1,
|
||||
|
||||
@ -60,6 +60,8 @@
|
||||
<page_header><loc_159><loc_59><loc_366><loc_64>Optimized Table Tokenization for Table Structure Recognition</page_header>
|
||||
<page_header><loc_389><loc_59><loc_393><loc_64>7</page_header>
|
||||
<picture><loc_135><loc_103><loc_367><loc_177><caption><loc_110><loc_79><loc_393><loc_98>Fig. 3. OTSL description of table structure: A - table example; B - graphical representation of table structure; C - mapping structure on a grid; D - OTSL structure encoding; E - explanation on cell encoding</caption></picture>
|
||||
<unordered_list><list_item><loc_273><loc_172><loc_349><loc_176>4 - 2d merges: "C", "L", "U", "X"</list_item>
|
||||
</unordered_list>
|
||||
<section_header_level_1><loc_110><loc_193><loc_202><loc_198>4.2 Language Syntax</section_header_level_1>
|
||||
<text><loc_110><loc_205><loc_297><loc_211>The OTSL representation follows these syntax rules:</text>
|
||||
<unordered_list><list_item><loc_114><loc_219><loc_393><loc_232>1. Left-looking cell rule : The left neighbour of an "L" cell must be either another "L" cell or a "C" cell.</list_item>
|
||||
|
||||
894
tests/data/groundtruth/docling_v2/2305.03393v1.json
vendored
894
tests/data/groundtruth/docling_v2/2305.03393v1.json
vendored
File diff suppressed because it is too large
Load Diff
@ -84,6 +84,8 @@ Fig. 3. OTSL description of table structure: A - table example; B - graphical re
|
||||
|
||||
<!-- image -->
|
||||
|
||||
- 4 - 2d merges: "C", "L", "U", "X"
|
||||
|
||||
## 4.2 Language Syntax
|
||||
|
||||
The OTSL representation follows these syntax rules:
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "amt_handbook_sample",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "code_and_formula",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-comma-in-cell",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -538,7 +538,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-comma",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -1788,7 +1788,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-inconsistent-header",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -526,7 +526,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-pipe",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -1788,7 +1788,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-semicolon",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -1788,7 +1788,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-tab",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -1788,7 +1788,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-too-few-columns",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -526,7 +526,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "csv-too-many-columns",
|
||||
"origin": {
|
||||
"mimetype": "text/csv",
|
||||
@ -610,7 +610,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "equations",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -250,7 +250,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -280,7 +281,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -322,7 +324,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -436,7 +439,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -466,7 +470,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -520,7 +525,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -634,7 +640,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_01",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_02",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_03",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
@ -637,7 +637,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_04",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
@ -325,7 +325,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_05",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
@ -325,7 +325,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_06",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_07",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "example_08",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
@ -661,7 +661,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -1330,7 +1331,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -1999,7 +2001,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -11,10 +11,13 @@ Create your feature branch: `git checkout -b feature/AmazingFeature` .
|
||||
3. Commit your changes ( `git commit -m 'Add some AmazingFeature'` )
|
||||
4. Push to the branch ( `git push origin feature/AmazingFeature` )
|
||||
5. Open a Pull Request
|
||||
6. **Whole list item has same formatting**
|
||||
7. List item has *mixed or partial* formatting
|
||||
|
||||
##
|
||||
# *Whole heading is italic*
|
||||
|
||||
*Second* section
|
||||
Some *`formatted_code`*
|
||||
|
||||
- **First** : Lorem ipsum.
|
||||
- **Second** : Dolor `sit` amet.
|
||||
## *Partially formatted* heading to\_escape `not_to_escape`
|
||||
|
||||
[$$E=mc^2$$](https://en.wikipedia.org/wiki/Albert_Einstein)
|
||||
|
||||
@ -5,8 +5,10 @@ body:
|
||||
- $ref: '#/groups/0'
|
||||
- $ref: '#/groups/1'
|
||||
- $ref: '#/groups/2'
|
||||
- $ref: '#/texts/27'
|
||||
- $ref: '#/texts/32'
|
||||
- $ref: '#/groups/8'
|
||||
- $ref: '#/texts/35'
|
||||
- $ref: '#/texts/39'
|
||||
content_layer: body
|
||||
label: unspecified
|
||||
name: _root_
|
||||
@ -47,6 +49,8 @@ groups:
|
||||
- $ref: '#/texts/18'
|
||||
- $ref: '#/texts/22'
|
||||
- $ref: '#/texts/26'
|
||||
- $ref: '#/texts/27'
|
||||
- $ref: '#/texts/28'
|
||||
content_layer: body
|
||||
label: ordered_list
|
||||
name: list
|
||||
@ -94,47 +98,38 @@ groups:
|
||||
$ref: '#/texts/22'
|
||||
self_ref: '#/groups/6'
|
||||
- children:
|
||||
- $ref: '#/texts/28'
|
||||
- $ref: '#/texts/29'
|
||||
- $ref: '#/texts/30'
|
||||
- $ref: '#/texts/31'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/27'
|
||||
$ref: '#/texts/28'
|
||||
self_ref: '#/groups/7'
|
||||
- children:
|
||||
- $ref: '#/texts/30'
|
||||
- $ref: '#/texts/33'
|
||||
- $ref: '#/texts/34'
|
||||
content_layer: body
|
||||
label: list
|
||||
name: list
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
self_ref: '#/groups/8'
|
||||
- children:
|
||||
- $ref: '#/texts/31'
|
||||
- $ref: '#/texts/32'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/30'
|
||||
self_ref: '#/groups/9'
|
||||
- children:
|
||||
- $ref: '#/texts/34'
|
||||
- $ref: '#/texts/35'
|
||||
- $ref: '#/texts/36'
|
||||
- $ref: '#/texts/37'
|
||||
- $ref: '#/texts/38'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/33'
|
||||
self_ref: '#/groups/10'
|
||||
$ref: '#/texts/35'
|
||||
self_ref: '#/groups/9'
|
||||
key_value_items: []
|
||||
name: inline_and_formatting
|
||||
origin:
|
||||
binary_hash: 9342273634728023910
|
||||
binary_hash: 16409076955457599155
|
||||
filename: inline_and_formatting.md
|
||||
mimetype: text/markdown
|
||||
pages: {}
|
||||
@ -174,6 +169,7 @@ texts:
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
@ -188,6 +184,7 @@ texts:
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
@ -202,6 +199,7 @@ texts:
|
||||
formatting:
|
||||
bold: true
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
@ -277,6 +275,7 @@ texts:
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
hyperlink: https://github.com/docling-project/docling
|
||||
@ -436,130 +435,167 @@ texts:
|
||||
prov: []
|
||||
self_ref: '#/texts/26'
|
||||
text: Open a Pull Request
|
||||
- children: []
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: Whole list item has same formatting
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/27'
|
||||
text: Whole list item has same formatting
|
||||
- children:
|
||||
- $ref: '#/groups/7'
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/28'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: List item has
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/29'
|
||||
text: List item has
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: mixed or partial
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/30'
|
||||
text: mixed or partial
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: formatting
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/31'
|
||||
text: formatting
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: title
|
||||
orig: Whole heading is italic
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/32'
|
||||
text: Whole heading is italic
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Some
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
self_ref: '#/texts/33'
|
||||
text: Some
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: code
|
||||
orig: formatted_code
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/34'
|
||||
text: formatted_code
|
||||
- children:
|
||||
- $ref: '#/groups/9'
|
||||
content_layer: body
|
||||
label: section_header
|
||||
level: 1
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/27'
|
||||
self_ref: '#/texts/35'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
script: baseline
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: Second
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/28'
|
||||
text: Second
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: section
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/29'
|
||||
text: section
|
||||
- children:
|
||||
- $ref: '#/groups/9'
|
||||
content_layer: body
|
||||
enumerated: false
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
self_ref: '#/texts/30'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: First
|
||||
orig: Partially formatted
|
||||
parent:
|
||||
$ref: '#/groups/9'
|
||||
prov: []
|
||||
self_ref: '#/texts/31'
|
||||
text: First
|
||||
self_ref: '#/texts/36'
|
||||
text: Partially formatted
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: ': Lorem ipsum.'
|
||||
orig: heading to_escape
|
||||
parent:
|
||||
$ref: '#/groups/9'
|
||||
prov: []
|
||||
self_ref: '#/texts/32'
|
||||
text: ': Lorem ipsum.'
|
||||
- children:
|
||||
- $ref: '#/groups/10'
|
||||
content_layer: body
|
||||
enumerated: false
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
self_ref: '#/texts/33'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: Second
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
self_ref: '#/texts/34'
|
||||
text: Second
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: ': Dolor'
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
self_ref: '#/texts/35'
|
||||
text: ': Dolor'
|
||||
self_ref: '#/texts/37'
|
||||
text: heading to_escape
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: sit
|
||||
orig: not_to_escape
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
$ref: '#/groups/9'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/36'
|
||||
text: sit
|
||||
self_ref: '#/texts/38'
|
||||
text: not_to_escape
|
||||
- children: []
|
||||
content_layer: body
|
||||
hyperlink: https://en.wikipedia.org/wiki/Albert_Einstein
|
||||
label: text
|
||||
orig: amet.
|
||||
orig: $$E=mc^2$$
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/37'
|
||||
text: amet.
|
||||
version: 1.3.0
|
||||
self_ref: '#/texts/39'
|
||||
text: $$E=mc^2$$
|
||||
version: 1.4.0
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ipa20180000016.xml",
|
||||
"origin": {
|
||||
"mimetype": "application/xml",
|
||||
@ -6005,7 +6005,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ipa20200022300.xml",
|
||||
"origin": {
|
||||
"mimetype": "application/xml",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "lorem_ipsum",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -66,7 +66,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -96,7 +97,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -126,7 +128,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -156,7 +159,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -186,7 +190,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
}
|
||||
],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "multi_page",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "pa20010031492.xml",
|
||||
"origin": {
|
||||
"mimetype": "application/xml",
|
||||
@ -2127,7 +2127,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "pftaps057006474.txt",
|
||||
"origin": {
|
||||
"mimetype": "text/plain",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "pg06442728.xml",
|
||||
"origin": {
|
||||
"mimetype": "application/xml",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "picture_classification",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "powerpoint_bad_text",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.ms-powerpoint",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "powerpoint_sample",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.ms-powerpoint",
|
||||
@ -2199,7 +2199,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "powerpoint_with_image",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.ms-powerpoint",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "redp5110_sampled",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
@ -12471,7 +12471,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -13096,7 +13097,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -15356,7 +15358,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/3",
|
||||
@ -15713,7 +15716,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/4",
|
||||
@ -16918,7 +16922,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "right_to_left_01",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "right_to_left_02",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "right_to_left_03",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "sample_sales_data",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
|
||||
@ -2136,7 +2136,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "tablecell",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -78,7 +78,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -98,7 +99,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -130,7 +132,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -172,7 +175,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
}
|
||||
],
|
||||
@ -419,7 +423,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "test-01",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
|
||||
@ -681,7 +681,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -1599,7 +1600,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -2005,7 +2007,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/3",
|
||||
@ -2411,7 +2414,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/4",
|
||||
@ -2893,7 +2897,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/5",
|
||||
@ -3375,7 +3380,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "test_emf_docx",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -60,7 +60,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -78,7 +79,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -96,7 +98,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -114,7 +117,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
}
|
||||
],
|
||||
|
||||
117
tests/data/groundtruth/docling_v2/textbox.docx.itxt
vendored
117
tests/data/groundtruth/docling_v2/textbox.docx.itxt
vendored
@ -11,83 +11,82 @@ item-0 at level 0: unspecified: group _root_
|
||||
＊ Blisters
|
||||
＊ Headache
|
||||
＊ Sore throat
|
||||
item-9 at level 1: list_item:
|
||||
item-9 at level 1: paragraph:
|
||||
item-10 at level 1: paragraph:
|
||||
item-11 at level 1: paragraph:
|
||||
item-12 at level 1: section: group textbox
|
||||
item-13 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms
|
||||
item-11 at level 1: section: group textbox
|
||||
item-12 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms
|
||||
item-13 at level 1: paragraph:
|
||||
item-14 at level 1: paragraph:
|
||||
item-15 at level 1: paragraph:
|
||||
item-16 at level 1: paragraph:
|
||||
item-17 at level 1: paragraph:
|
||||
item-18 at level 1: section: group textbox
|
||||
item-19 at level 2: paragraph: Yes
|
||||
item-17 at level 1: section: group textbox
|
||||
item-18 at level 2: paragraph: Yes
|
||||
item-19 at level 1: paragraph:
|
||||
item-20 at level 1: paragraph:
|
||||
item-21 at level 1: paragraph:
|
||||
item-22 at level 1: section: group textbox
|
||||
item-23 at level 2: list: group list
|
||||
item-24 at level 3: list_item: A report must be submitted withi ... saster Prevention Information Network.
|
||||
item-25 at level 3: list_item: A report must also be submitted ... d Infectious Disease Reporting System.
|
||||
item-26 at level 2: paragraph:
|
||||
item-27 at level 1: list: group list
|
||||
item-28 at level 2: list_item:
|
||||
item-21 at level 1: section: group textbox
|
||||
item-22 at level 2: list: group list
|
||||
item-23 at level 3: list_item: A report must be submitted withi ... saster Prevention Information Network.
|
||||
item-24 at level 3: list_item: A report must also be submitted ... d Infectious Disease Reporting System.
|
||||
item-25 at level 2: paragraph:
|
||||
item-26 at level 1: list: group list
|
||||
item-27 at level 2: list_item:
|
||||
item-28 at level 1: paragraph:
|
||||
item-29 at level 1: paragraph:
|
||||
item-30 at level 1: paragraph:
|
||||
item-31 at level 1: paragraph:
|
||||
item-32 at level 1: paragraph:
|
||||
item-33 at level 1: paragraph:
|
||||
item-34 at level 1: section: group textbox
|
||||
item-35 at level 2: paragraph: Health Bureau:
|
||||
item-36 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control.
|
||||
item-37 at level 2: list: group list
|
||||
item-38 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection.
|
||||
item-39 at level 3: list_item: Implement appropriate epidemic p ... the Communicable Disease Control Act.
|
||||
item-40 at level 2: paragraph:
|
||||
item-41 at level 1: list: group list
|
||||
item-42 at level 2: list_item:
|
||||
item-43 at level 1: paragraph:
|
||||
item-44 at level 1: section: group textbox
|
||||
item-45 at level 2: paragraph: Department of Education:
|
||||
item-33 at level 1: section: group textbox
|
||||
item-34 at level 2: paragraph: Health Bureau:
|
||||
item-35 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control.
|
||||
item-36 at level 2: list: group list
|
||||
item-37 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection.
|
||||
item-38 at level 3: list_item: Implement appropriate epidemic p ... the Communicable Disease Control Act.
|
||||
item-39 at level 2: paragraph:
|
||||
item-40 at level 1: list: group list
|
||||
item-41 at level 2: list_item:
|
||||
item-42 at level 1: paragraph:
|
||||
item-43 at level 1: section: group textbox
|
||||
item-44 at level 2: paragraph: Department of Education:
|
||||
Collabo ... vention measures at all school levels.
|
||||
item-45 at level 1: paragraph:
|
||||
item-46 at level 1: paragraph:
|
||||
item-47 at level 1: paragraph:
|
||||
item-48 at level 1: paragraph:
|
||||
item-49 at level 1: paragraph:
|
||||
item-50 at level 1: paragraph:
|
||||
item-51 at level 1: paragraph:
|
||||
item-52 at level 1: paragraph:
|
||||
item-53 at level 1: section: group textbox
|
||||
item-54 at level 2: inline: group group
|
||||
item-55 at level 3: paragraph: The Health Bureau will handle
|
||||
item-56 at level 3: paragraph: reporting and specimen collection
|
||||
item-57 at level 3: paragraph: .
|
||||
item-58 at level 2: paragraph:
|
||||
item-52 at level 1: section: group textbox
|
||||
item-53 at level 2: inline: group group
|
||||
item-54 at level 3: paragraph: The Health Bureau will handle
|
||||
item-55 at level 3: paragraph: reporting and specimen collection
|
||||
item-56 at level 3: paragraph: .
|
||||
item-57 at level 2: paragraph:
|
||||
item-58 at level 1: paragraph:
|
||||
item-59 at level 1: paragraph:
|
||||
item-60 at level 1: paragraph:
|
||||
item-61 at level 1: paragraph:
|
||||
item-62 at level 1: section: group textbox
|
||||
item-63 at level 2: paragraph: Whether the epidemic has eased.
|
||||
item-64 at level 2: paragraph:
|
||||
item-65 at level 1: paragraph:
|
||||
item-66 at level 1: section: group textbox
|
||||
item-67 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease.
|
||||
item-68 at level 2: paragraph: No
|
||||
item-61 at level 1: section: group textbox
|
||||
item-62 at level 2: paragraph: Whether the epidemic has eased.
|
||||
item-63 at level 2: paragraph:
|
||||
item-64 at level 1: paragraph:
|
||||
item-65 at level 1: section: group textbox
|
||||
item-66 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease.
|
||||
item-67 at level 2: paragraph: No
|
||||
item-68 at level 1: paragraph:
|
||||
item-69 at level 1: paragraph:
|
||||
item-70 at level 1: paragraph:
|
||||
item-71 at level 1: section: group textbox
|
||||
item-72 at level 2: paragraph: Yes
|
||||
item-73 at level 1: paragraph:
|
||||
item-74 at level 1: section: group textbox
|
||||
item-75 at level 2: paragraph: Yes
|
||||
item-70 at level 1: section: group textbox
|
||||
item-71 at level 2: paragraph: Yes
|
||||
item-72 at level 1: paragraph:
|
||||
item-73 at level 1: section: group textbox
|
||||
item-74 at level 2: paragraph: Yes
|
||||
item-75 at level 1: paragraph:
|
||||
item-76 at level 1: paragraph:
|
||||
item-77 at level 1: paragraph:
|
||||
item-78 at level 1: section: group textbox
|
||||
item-79 at level 2: paragraph: Case closed.
|
||||
item-80 at level 2: paragraph:
|
||||
item-81 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary.
|
||||
item-82 at level 1: paragraph:
|
||||
item-83 at level 1: section: group textbox
|
||||
item-84 at level 2: paragraph: No
|
||||
item-77 at level 1: section: group textbox
|
||||
item-78 at level 2: paragraph: Case closed.
|
||||
item-79 at level 2: paragraph:
|
||||
item-80 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary.
|
||||
item-81 at level 1: paragraph:
|
||||
item-82 at level 1: section: group textbox
|
||||
item-83 at level 2: paragraph: No
|
||||
item-84 at level 1: paragraph:
|
||||
item-85 at level 1: paragraph:
|
||||
item-86 at level 1: paragraph:
|
||||
item-87 at level 1: paragraph:
|
||||
item-86 at level 1: paragraph:
|
||||
433
tests/data/groundtruth/docling_v2/textbox.docx.json
vendored
433
tests/data/groundtruth/docling_v2/textbox.docx.json
vendored
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "textbox",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -36,10 +36,10 @@
|
||||
"$ref": "#/texts/7"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/2"
|
||||
"$ref": "#/texts/9"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/10"
|
||||
@ -50,17 +50,14 @@
|
||||
{
|
||||
"$ref": "#/texts/12"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/13"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/15"
|
||||
"$ref": "#/texts/14"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/16"
|
||||
"$ref": "#/texts/15"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/4"
|
||||
@ -68,6 +65,9 @@
|
||||
{
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/20"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/21"
|
||||
},
|
||||
@ -80,9 +80,6 @@
|
||||
{
|
||||
"$ref": "#/texts/24"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/25"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -90,11 +87,14 @@
|
||||
"$ref": "#/groups/9"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/32"
|
||||
"$ref": "#/texts/31"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/10"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/33"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/34"
|
||||
},
|
||||
@ -114,10 +114,10 @@
|
||||
"$ref": "#/texts/39"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/40"
|
||||
"$ref": "#/groups/11"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/11"
|
||||
"$ref": "#/texts/44"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/45"
|
||||
@ -125,56 +125,53 @@
|
||||
{
|
||||
"$ref": "#/texts/46"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/47"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/13"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/50"
|
||||
"$ref": "#/texts/49"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/14"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/53"
|
||||
"$ref": "#/texts/52"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/54"
|
||||
"$ref": "#/texts/53"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/15"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/56"
|
||||
"$ref": "#/texts/55"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/16"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/58"
|
||||
"$ref": "#/texts/57"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/59"
|
||||
"$ref": "#/texts/58"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/17"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/63"
|
||||
"$ref": "#/texts/62"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/18"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/64"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/65"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/66"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/67"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -223,7 +220,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/9"
|
||||
"$ref": "#/texts/8"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -237,7 +234,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/14"
|
||||
"$ref": "#/texts/13"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -254,7 +251,7 @@
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/19"
|
||||
"$ref": "#/texts/18"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -268,10 +265,10 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/17"
|
||||
"$ref": "#/texts/16"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/18"
|
||||
"$ref": "#/texts/17"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -285,7 +282,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/20"
|
||||
"$ref": "#/texts/19"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -299,16 +296,16 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/26"
|
||||
"$ref": "#/texts/25"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/27"
|
||||
"$ref": "#/texts/26"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/8"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/30"
|
||||
"$ref": "#/texts/29"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -322,10 +319,10 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/28"
|
||||
"$ref": "#/texts/27"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/29"
|
||||
"$ref": "#/texts/28"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -339,7 +336,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/31"
|
||||
"$ref": "#/texts/30"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -353,7 +350,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/33"
|
||||
"$ref": "#/texts/32"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -370,7 +367,7 @@
|
||||
"$ref": "#/groups/12"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/44"
|
||||
"$ref": "#/texts/43"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -383,14 +380,14 @@
|
||||
"$ref": "#/groups/11"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/40"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/41"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/42"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/43"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -404,10 +401,10 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/48"
|
||||
"$ref": "#/texts/47"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/49"
|
||||
"$ref": "#/texts/48"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -421,10 +418,10 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/51"
|
||||
"$ref": "#/texts/50"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/52"
|
||||
"$ref": "#/texts/51"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -438,7 +435,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/55"
|
||||
"$ref": "#/texts/54"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -452,7 +449,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/57"
|
||||
"$ref": "#/texts/56"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -465,14 +462,14 @@
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/59"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/60"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/61"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/62"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -486,7 +483,7 @@
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/64"
|
||||
"$ref": "#/texts/63"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
@ -510,7 +507,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -528,7 +526,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -558,7 +557,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -588,7 +588,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -600,12 +601,10 @@
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": "",
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/7",
|
||||
@ -621,18 +620,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/8",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
@ -646,9 +633,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/10",
|
||||
"parent": {
|
||||
@ -687,18 +687,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/13",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/14",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
@ -712,9 +700,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/14",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/15",
|
||||
"parent": {
|
||||
@ -729,18 +730,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/16",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/17",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
@ -754,13 +743,14 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/18",
|
||||
"self_ref": "#/texts/17",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
@ -774,13 +764,14 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/19",
|
||||
"self_ref": "#/texts/18",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
@ -792,7 +783,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/20",
|
||||
"self_ref": "#/texts/19",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
@ -805,6 +796,18 @@
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/20",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/21",
|
||||
"parent": {
|
||||
@ -855,18 +858,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/25",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/26",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -880,11 +871,12 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/27",
|
||||
"self_ref": "#/texts/26",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -898,11 +890,12 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/28",
|
||||
"self_ref": "#/texts/27",
|
||||
"parent": {
|
||||
"$ref": "#/groups/8"
|
||||
},
|
||||
@ -916,13 +909,14 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/29",
|
||||
"self_ref": "#/texts/28",
|
||||
"parent": {
|
||||
"$ref": "#/groups/8"
|
||||
},
|
||||
@ -936,13 +930,14 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/30",
|
||||
"self_ref": "#/texts/29",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
@ -954,7 +949,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/31",
|
||||
"self_ref": "#/texts/30",
|
||||
"parent": {
|
||||
"$ref": "#/groups/9"
|
||||
},
|
||||
@ -968,7 +963,7 @@
|
||||
"marker": "-"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/32",
|
||||
"self_ref": "#/texts/31",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
@ -980,7 +975,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/33",
|
||||
"self_ref": "#/texts/32",
|
||||
"parent": {
|
||||
"$ref": "#/groups/10"
|
||||
},
|
||||
@ -994,9 +989,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/33",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/34",
|
||||
"parent": {
|
||||
@ -1071,18 +1079,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/40",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/41",
|
||||
"parent": {
|
||||
"$ref": "#/groups/12"
|
||||
},
|
||||
@ -1096,11 +1092,12 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/42",
|
||||
"self_ref": "#/texts/41",
|
||||
"parent": {
|
||||
"$ref": "#/groups/12"
|
||||
},
|
||||
@ -1114,11 +1111,12 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/43",
|
||||
"self_ref": "#/texts/42",
|
||||
"parent": {
|
||||
"$ref": "#/groups/12"
|
||||
},
|
||||
@ -1132,13 +1130,26 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/43",
|
||||
"parent": {
|
||||
"$ref": "#/groups/11"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/44",
|
||||
"parent": {
|
||||
"$ref": "#/groups/11"
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
@ -1173,18 +1184,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/47",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/48",
|
||||
"parent": {
|
||||
"$ref": "#/groups/13"
|
||||
},
|
||||
@ -1198,11 +1197,12 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/49",
|
||||
"self_ref": "#/texts/48",
|
||||
"parent": {
|
||||
"$ref": "#/groups/13"
|
||||
},
|
||||
@ -1214,7 +1214,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/50",
|
||||
"self_ref": "#/texts/49",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
@ -1226,7 +1226,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/51",
|
||||
"self_ref": "#/texts/50",
|
||||
"parent": {
|
||||
"$ref": "#/groups/14"
|
||||
},
|
||||
@ -1240,11 +1240,12 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/52",
|
||||
"self_ref": "#/texts/51",
|
||||
"parent": {
|
||||
"$ref": "#/groups/14"
|
||||
},
|
||||
@ -1258,9 +1259,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/52",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/53",
|
||||
"parent": {
|
||||
@ -1275,18 +1289,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/54",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/55",
|
||||
"parent": {
|
||||
"$ref": "#/groups/15"
|
||||
},
|
||||
@ -1300,11 +1302,12 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/56",
|
||||
"self_ref": "#/texts/55",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
@ -1316,7 +1319,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/57",
|
||||
"self_ref": "#/texts/56",
|
||||
"parent": {
|
||||
"$ref": "#/groups/16"
|
||||
},
|
||||
@ -1330,9 +1333,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/57",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/58",
|
||||
"parent": {
|
||||
@ -1347,18 +1363,6 @@
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/59",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/60",
|
||||
"parent": {
|
||||
"$ref": "#/groups/17"
|
||||
},
|
||||
@ -1372,11 +1376,12 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/61",
|
||||
"self_ref": "#/texts/60",
|
||||
"parent": {
|
||||
"$ref": "#/groups/17"
|
||||
},
|
||||
@ -1388,7 +1393,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/62",
|
||||
"self_ref": "#/texts/61",
|
||||
"parent": {
|
||||
"$ref": "#/groups/17"
|
||||
},
|
||||
@ -1402,11 +1407,12 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/63",
|
||||
"self_ref": "#/texts/62",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
@ -1418,7 +1424,7 @@
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/64",
|
||||
"self_ref": "#/texts/63",
|
||||
"parent": {
|
||||
"$ref": "#/groups/18"
|
||||
},
|
||||
@ -1432,9 +1438,22 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/64",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/65",
|
||||
"parent": {
|
||||
@ -1458,18 +1477,6 @@
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/67",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "paragraph",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": ""
|
||||
}
|
||||
],
|
||||
"pictures": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "unit_test_01",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "unit_test_formatting",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -182,7 +182,8 @@
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -200,7 +201,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -218,7 +220,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": true,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -236,7 +239,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"hyperlink": "https:/github.com/DS4SD/docling"
|
||||
},
|
||||
@ -255,7 +259,8 @@
|
||||
"bold": true,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"hyperlink": "https:/github.com/DS4SD/docling"
|
||||
},
|
||||
@ -274,7 +279,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -292,7 +298,8 @@
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -310,7 +317,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -328,7 +336,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": true,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -346,7 +355,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -364,7 +374,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"hyperlink": "https:/github.com/DS4SD/docling"
|
||||
},
|
||||
@ -383,7 +394,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -413,7 +425,8 @@
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -433,7 +446,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -453,7 +467,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": true,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -491,7 +506,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -509,7 +525,8 @@
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -527,7 +544,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -545,7 +563,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": true,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -581,7 +600,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -599,7 +619,8 @@
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -617,7 +638,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "unit_test_headers",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -138,7 +138,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -168,7 +169,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -239,7 +241,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -269,7 +272,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -343,7 +347,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -373,7 +378,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -447,7 +453,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -477,7 +484,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -566,7 +574,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -596,7 +605,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -667,7 +677,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -697,7 +708,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -771,7 +783,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -801,7 +814,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "unit_test_headers_numbered",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -214,7 +214,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -244,7 +245,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -315,7 +317,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -345,7 +348,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -419,7 +423,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -449,7 +454,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -523,7 +529,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -553,7 +560,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -620,7 +628,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -650,7 +659,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -721,7 +731,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -751,7 +762,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -825,7 +837,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -855,7 +868,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "unit_test_lists",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -370,7 +370,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -400,7 +401,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -450,7 +452,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -470,7 +473,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -490,7 +494,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -542,7 +547,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -562,7 +568,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -582,7 +589,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -634,7 +642,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -654,7 +663,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -674,7 +684,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -694,7 +705,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -714,7 +726,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -734,7 +747,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -786,7 +800,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -806,7 +821,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -826,7 +842,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -878,7 +895,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -898,7 +916,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -918,7 +937,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -938,7 +958,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -996,7 +1017,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -1016,7 +1038,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -1036,7 +1059,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -1056,7 +1080,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -1076,7 +1101,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -1096,7 +1122,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "wiki_duck",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
@ -8489,7 +8489,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -8648,7 +8649,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "word_image_anchors",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -101,7 +101,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -119,7 +120,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -137,7 +139,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -155,7 +158,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -185,7 +189,8 @@
|
||||
"bold": true,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -203,7 +208,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "word_sample",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -106,7 +106,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -149,7 +150,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -167,7 +169,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -217,7 +220,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -235,7 +239,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -255,7 +260,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -275,7 +281,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -295,7 +302,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -313,7 +321,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -333,7 +342,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -353,7 +363,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -373,7 +384,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -426,7 +438,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -444,7 +457,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -462,7 +476,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -492,7 +507,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -510,7 +526,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -530,7 +547,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -550,7 +568,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
},
|
||||
"enumerated": false,
|
||||
"marker": "-"
|
||||
@ -897,7 +916,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "word_tables",
|
||||
"origin": {
|
||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||
@ -119,7 +119,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -149,7 +150,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -179,7 +181,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -209,7 +212,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -239,7 +243,8 @@
|
||||
"bold": false,
|
||||
"italic": false,
|
||||
"underline": false,
|
||||
"strikethrough": false
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
@ -510,7 +515,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/1",
|
||||
@ -729,7 +735,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/2",
|
||||
@ -1020,7 +1027,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/3",
|
||||
@ -1387,7 +1395,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/tables/4",
|
||||
@ -2398,7 +2407,8 @@
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
},
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"key_value_items": [],
|
||||
|
||||
11
tests/data/md/inline_and_formatting.md
vendored
11
tests/data/md/inline_and_formatting.md
vendored
@ -11,8 +11,13 @@ Create your feature branch: `git checkout -b feature/AmazingFeature`.
|
||||
3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
|
||||
4. Push to the branch (`git push origin feature/AmazingFeature`)
|
||||
5. Open a Pull Request
|
||||
6. **Whole list item has same formatting**
|
||||
7. List item has *mixed or partial* formatting
|
||||
|
||||
## *Second* section <!-- inline groups in headings not yet supported by serializers -->
|
||||
# *Whole heading is italic*
|
||||
|
||||
- **First**: Lorem ipsum.
|
||||
- **Second**: Dolor `sit` amet.
|
||||
Some *`formatted_code`*
|
||||
|
||||
## *Partially formatted* heading to_escape `not_to_escape`
|
||||
|
||||
[$$E=mc^2$$](https://en.wikipedia.org/wiki/Albert_Einstein)
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "webp-test",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ocr_test",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ocr_test_rotated_180",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ocr_test_rotated_270",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.3.0",
|
||||
"version": "1.4.0",
|
||||
"name": "ocr_test_rotated_90",
|
||||
"origin": {
|
||||
"mimetype": "application/pdf",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user