NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add content_layer property to items to address body, furniture and other roles (#735)

Browse Source 
* feat: Pass predicted page-headers and page-footers through to DoclingDocument furniture

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* chore: Update all test GT

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update all test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update all test cases again

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update lock

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update lock to final docling-core

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-10 12:07:49 +01:00 committed by GitHub
parent 3e26597995
commit cf78d5b7b9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
43 changed files with 2082 additions and 198 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
docling/models/ds_glm_model.py
View File

@ -4,7 +4,12 @@ from pathlib import Path
from typing import List, Union
from deepsearch_glm.andromeda_nlp import nlp_model
from docling_core.types.doc import BoundingBox, CoordOrigin, DoclingDocument
from docling_core.types.doc import (
BoundingBox,
CoordOrigin,
DocItemLabel,
DoclingDocument,
)
from docling_core.types.legacy_doc.base import BoundingBox as DsBoundingBox
from docling_core.types.legacy_doc.base import (
Figure,
@ -71,12 +76,15 @@ class GlmModel:
)
main_text: List[Union[Ref, BaseText]] = []
page_headers: List[Union[Ref, BaseText]] = []
page_footers: List[Union[Ref, BaseText]] = []
tables: List[DsSchemaTable] = []
figures: List[Figure] = []
page_no_to_page = {p.page_no: p for p in conv_res.pages}
for element in conv_res.assembled.elements:
for element in conv_res.assembled.body:
# Convert bboxes to lower-left origin.
target_bbox = DsBoundingBox(
element.cluster.bbox.to_bottom_left_origin(
@ -238,6 +246,53 @@ class GlmModel:
)
)
# We can throw in headers and footers at the end of the legacy doc
# since the reading-order will re-sort it later.
for element in conv_res.assembled.headers:
# Convert bboxes to lower-left origin.
target_bbox = DsBoundingBox(
element.cluster.bbox.to_bottom_left_origin(
page_no_to_page[element.page_no].size.height
).as_tuple()
)
if isinstance(element, TextElement):
tel = BaseText(
text=element.text,
obj_type=layout_label_to_ds_type.get(element.label),
name=element.label,
prov=[
Prov(
bbox=target_bbox,
page=element.page_no + 1,
span=[0, len(element.text)],
)
],
)
if element.label == DocItemLabel.PAGE_HEADER:
index = len(page_headers)
ref_str = f"#/page-headers/{index}"
main_text.append(
Ref(
name=element.label,
obj_type=layout_label_to_ds_type.get(element.label),
ref=ref_str,
),
)
page_headers.append(tel)
elif element.label == DocItemLabel.PAGE_FOOTER:
index = len(page_footers)
ref_str = f"#/page-footers/{index}"
main_text.append(
Ref(
name=element.label,
obj_type=layout_label_to_ds_type.get(element.label),
ref=ref_str,
),
)
page_footers.append(tel)
page_dimensions = [
PageDimensions(page=p.page_no + 1, height=p.size.height, width=p.size.width)
for p in conv_res.pages
@ -252,6 +307,8 @@ class GlmModel:
tables=tables,
figures=figures,
page_dimensions=page_dimensions,
page_headers=page_headers,
page_footers=page_footers,
)
return ds_doc
@ -264,6 +321,7 @@ class GlmModel:
glm_doc = self.model.apply_on_doc(ds_doc_dict)
docling_doc: DoclingDocument = to_docling_document(glm_doc) # Experimental
1 == 1
# DEBUG code:
def draw_clusters_and_cells(ds_document, page_no, show: bool = False):

10
docling/utils/glm_utils.py
View File

@ -15,6 +15,7 @@ from docling_core.types.doc import (
TableCell,
TableData,
)
from docling_core.types.doc.document import ContentLayer
def resolve_item(paths, obj):
@ -311,6 +312,15 @@ def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
current_list = None
doc.add_text(label=DocItemLabel.FORMULA, text="", orig=text, prov=prov)
elif label in [DocItemLabel.PAGE_HEADER, DocItemLabel.PAGE_FOOTER]:
current_list = None
doc.add_text(
label=DocItemLabel(name_label),
text=text,
prov=prov,
content_layer=ContentLayer.FURNITURE,
)
else:
current_list = None

312
poetry.lock generated
View File

@ -1,14 +1,14 @@
# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
[[package]]
name = "aiohappyeyeballs"
version = "2.4.4"
version = "2.4.6"
description = "Happy Eyeballs for asyncio"
optional = false
python-versions = ">=3.8"
python-versions = ">=3.9"
files = [
{file = "aiohappyeyeballs-2.4.4-py3-none-any.whl", hash = "sha256:a980909d50efcd44795c4afeca523296716d50cd756ddca6af8c65b996e27de8"},
{file = "aiohappyeyeballs-2.4.4.tar.gz", hash = "sha256:5fdd7d87889c63183afc18ce9271f9b0a7d32c2303e394468dd45d514a757745"},
{file = "aiohappyeyeballs-2.4.6-py3-none-any.whl", hash = "sha256:147ec992cf873d74f5062644332c539fcd42956dc69453fe5204195e560517e1"},
{file = "aiohappyeyeballs-2.4.6.tar.gz", hash = "sha256:9b05052f9042985d32ecbe4b59a77ae19c006a78f1344d7fdad69d28ded3d0b0"},
]
[[package]]
@ -866,13 +866,13 @@ files = [
[[package]]
name = "docling-core"
version = "2.17.2"
version = "2.18.0"
description = "A python library to define and validate data types in Docling."
optional = false
python-versions = "<4.0,>=3.9"
files = [
{file = "docling_core-2.17.2-py3-none-any.whl", hash = "sha256:9d344ebe39ca3714b38aa7d9c62e361a4fdbbdad4cda9b5177dcd524045dc679"},
{file = "docling_core-2.17.2.tar.gz", hash = "sha256:8d6e6213eb78b421c7e75fff00902d11a0e8dec0717321ca3ed1c5e529f95c91"},
{file = "docling_core-2.18.0-py3-none-any.whl", hash = "sha256:9dee0084cef3d6d742686629f538653e332ee8b7541ad7581c98c8ddc28149b3"},
{file = "docling_core-2.18.0.tar.gz", hash = "sha256:e8623b8cf4b1e19d5c05c4e3446ac7835afb178997b91c8d11ce8e504a09ec43"},
]
[package.dependencies]
@ -1542,13 +1542,13 @@ pyreadline3 = {version = "*", markers = "sys_platform == \"win32\" and python_ve
[[package]]
name = "identify"
version = "2.6.6"
version = "2.6.7"
description = "File identification library for Python"
optional = false
python-versions = ">=3.9"
files = [
{file = "identify-2.6.6-py2.py3-none-any.whl", hash = "sha256:cbd1810bce79f8b671ecb20f53ee0ae8e86ae84b557de31d89709dc2a48ba881"},
{file = "identify-2.6.6.tar.gz", hash = "sha256:7bec12768ed44ea4761efb47806f0a41f86e7c0a5fdf5950d4648c90eca7e251"},
{file = "identify-2.6.7-py2.py3-none-any.whl", hash = "sha256:155931cb617a401807b09ecec6635d6c692d180090a1cedca8ef7d58ba5b6aa0"},
{file = "identify-2.6.7.tar.gz", hash = "sha256:3fa266b42eba321ee0b2bb0936a6a6b9e36a1351cbb69055b3082f4193035684"},
]
[package.extras]
@ -2251,157 +2251,157 @@ files = [
[[package]]
name = "lxml"
version = "5.3.0"
version = "5.3.1"
description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
optional = false
python-versions = ">=3.6"
files = [
{file = "lxml-5.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:dd36439be765e2dde7660212b5275641edbc813e7b24668831a5c8ac91180656"},
{file = "lxml-5.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ae5fe5c4b525aa82b8076c1a59d642c17b6e8739ecf852522c6321852178119d"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:501d0d7e26b4d261fca8132854d845e4988097611ba2531408ec91cf3fd9d20a"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb66442c2546446944437df74379e9cf9e9db353e61301d1a0e26482f43f0dd8"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9e41506fec7a7f9405b14aa2d5c8abbb4dbbd09d88f9496958b6d00cb4d45330"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f7d4a670107d75dfe5ad080bed6c341d18c4442f9378c9f58e5851e86eb79965"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:41ce1f1e2c7755abfc7e759dc34d7d05fd221723ff822947132dc934d122fe22"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:44264ecae91b30e5633013fb66f6ddd05c006d3e0e884f75ce0b4755b3e3847b"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:3c174dc350d3ec52deb77f2faf05c439331d6ed5e702fc247ccb4e6b62d884b7"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:2dfab5fa6a28a0b60a20638dc48e6343c02ea9933e3279ccb132f555a62323d8"},
{file = "lxml-5.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:b1c8c20847b9f34e98080da785bb2336ea982e7f913eed5809e5a3c872900f32"},
{file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2c86bf781b12ba417f64f3422cfc302523ac9cd1d8ae8c0f92a1c66e56ef2e86"},
{file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:c162b216070f280fa7da844531169be0baf9ccb17263cf5a8bf876fcd3117fa5"},
{file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:36aef61a1678cb778097b4a6eeae96a69875d51d1e8f4d4b491ab3cfb54b5a03"},
{file = "lxml-5.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:f65e5120863c2b266dbcc927b306c5b78e502c71edf3295dfcb9501ec96e5fc7"},
{file = "lxml-5.3.0-cp310-cp310-win32.whl", hash = "sha256:ef0c1fe22171dd7c7c27147f2e9c3e86f8bdf473fed75f16b0c2e84a5030ce80"},
{file = "lxml-5.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:052d99051e77a4f3e8482c65014cf6372e61b0a6f4fe9edb98503bb5364cfee3"},
{file = "lxml-5.3.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:74bcb423462233bc5d6066e4e98b0264e7c1bed7541fff2f4e34fe6b21563c8b"},
{file = "lxml-5.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a3d819eb6f9b8677f57f9664265d0a10dd6551d227afb4af2b9cd7bdc2ccbf18"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b8f5db71b28b8c404956ddf79575ea77aa8b1538e8b2ef9ec877945b3f46442"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c3406b63232fc7e9b8783ab0b765d7c59e7c59ff96759d8ef9632fca27c7ee4"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ecdd78ab768f844c7a1d4a03595038c166b609f6395e25af9b0f3f26ae1230f"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:168f2dfcfdedf611eb285efac1516c8454c8c99caf271dccda8943576b67552e"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa617107a410245b8660028a7483b68e7914304a6d4882b5ff3d2d3eb5948d8c"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:69959bd3167b993e6e710b99051265654133a98f20cec1d9b493b931942e9c16"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:bd96517ef76c8654446fc3db9242d019a1bb5fe8b751ba414765d59f99210b79"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:ab6dd83b970dc97c2d10bc71aa925b84788c7c05de30241b9e96f9b6d9ea3080"},
{file = "lxml-5.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:eec1bb8cdbba2925bedc887bc0609a80e599c75b12d87ae42ac23fd199445654"},
{file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6a7095eeec6f89111d03dabfe5883a1fd54da319c94e0fb104ee8f23616b572d"},
{file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:6f651ebd0b21ec65dfca93aa629610a0dbc13dbc13554f19b0113da2e61a4763"},
{file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:f422a209d2455c56849442ae42f25dbaaba1c6c3f501d58761c619c7836642ec"},
{file = "lxml-5.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:62f7fdb0d1ed2065451f086519865b4c90aa19aed51081979ecd05a21eb4d1be"},
{file = "lxml-5.3.0-cp311-cp311-win32.whl", hash = "sha256:c6379f35350b655fd817cd0d6cbeef7f265f3ae5fedb1caae2eb442bbeae9ab9"},
{file = "lxml-5.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:9c52100e2c2dbb0649b90467935c4b0de5528833c76a35ea1a2691ec9f1ee7a1"},
{file = "lxml-5.3.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:e99f5507401436fdcc85036a2e7dc2e28d962550afe1cbfc07c40e454256a859"},
{file = "lxml-5.3.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:384aacddf2e5813a36495233b64cb96b1949da72bef933918ba5c84e06af8f0e"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:874a216bf6afaf97c263b56371434e47e2c652d215788396f60477540298218f"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65ab5685d56914b9a2a34d67dd5488b83213d680b0c5d10b47f81da5a16b0b0e"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aac0bbd3e8dd2d9c45ceb82249e8bdd3ac99131a32b4d35c8af3cc9db1657179"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b369d3db3c22ed14c75ccd5af429086f166a19627e84a8fdade3f8f31426e52a"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c24037349665434f375645fa9d1f5304800cec574d0310f618490c871fd902b3"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:62d172f358f33a26d6b41b28c170c63886742f5b6772a42b59b4f0fa10526cb1"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:c1f794c02903c2824fccce5b20c339a1a14b114e83b306ff11b597c5f71a1c8d"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:5d6a6972b93c426ace71e0be9a6f4b2cfae9b1baed2eed2006076a746692288c"},
{file = "lxml-5.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:3879cc6ce938ff4eb4900d901ed63555c778731a96365e53fadb36437a131a99"},
{file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:74068c601baff6ff021c70f0935b0c7bc528baa8ea210c202e03757c68c5a4ff"},
{file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ecd4ad8453ac17bc7ba3868371bffb46f628161ad0eefbd0a855d2c8c32dd81a"},
{file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:7e2f58095acc211eb9d8b5771bf04df9ff37d6b87618d1cbf85f92399c98dae8"},
{file = "lxml-5.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e63601ad5cd8f860aa99d109889b5ac34de571c7ee902d6812d5d9ddcc77fa7d"},
{file = "lxml-5.3.0-cp312-cp312-win32.whl", hash = "sha256:17e8d968d04a37c50ad9c456a286b525d78c4a1c15dd53aa46c1d8e06bf6fa30"},
{file = "lxml-5.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:c1a69e58a6bb2de65902051d57fde951febad631a20a64572677a1052690482f"},
{file = "lxml-5.3.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8c72e9563347c7395910de6a3100a4840a75a6f60e05af5e58566868d5eb2d6a"},
{file = "lxml-5.3.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:e92ce66cd919d18d14b3856906a61d3f6b6a8500e0794142338da644260595cd"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1d04f064bebdfef9240478f7a779e8c5dc32b8b7b0b2fc6a62e39b928d428e51"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c2fb570d7823c2bbaf8b419ba6e5662137f8166e364a8b2b91051a1fb40ab8b"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0c120f43553ec759f8de1fee2f4794452b0946773299d44c36bfe18e83caf002"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:562e7494778a69086f0312ec9689f6b6ac1c6b65670ed7d0267e49f57ffa08c4"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:423b121f7e6fa514ba0c7918e56955a1d4470ed35faa03e3d9f0e3baa4c7e492"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:c00f323cc00576df6165cc9d21a4c21285fa6b9989c5c39830c3903dc4303ef3"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:1fdc9fae8dd4c763e8a31e7630afef517eab9f5d5d31a278df087f307bf601f4"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:658f2aa69d31e09699705949b5fc4719cbecbd4a97f9656a232e7d6c7be1a367"},
{file = "lxml-5.3.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:1473427aff3d66a3fa2199004c3e601e6c4500ab86696edffdbc84954c72d832"},
{file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a87de7dd873bf9a792bf1e58b1c3887b9264036629a5bf2d2e6579fe8e73edff"},
{file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:0d7b36afa46c97875303a94e8f3ad932bf78bace9e18e603f2085b652422edcd"},
{file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:cf120cce539453ae086eacc0130a324e7026113510efa83ab42ef3fcfccac7fb"},
{file = "lxml-5.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:df5c7333167b9674aa8ae1d4008fa4bc17a313cc490b2cca27838bbdcc6bb15b"},
{file = "lxml-5.3.0-cp313-cp313-win32.whl", hash = "sha256:c802e1c2ed9f0c06a65bc4ed0189d000ada8049312cfeab6ca635e39c9608957"},
{file = "lxml-5.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:406246b96d552e0503e17a1006fd27edac678b3fcc9f1be71a2f94b4ff61528d"},
{file = "lxml-5.3.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:8f0de2d390af441fe8b2c12626d103540b5d850d585b18fcada58d972b74a74e"},
{file = "lxml-5.3.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1afe0a8c353746e610bd9031a630a95bcfb1a720684c3f2b36c4710a0a96528f"},
{file = "lxml-5.3.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56b9861a71575f5795bde89256e7467ece3d339c9b43141dbdd54544566b3b94"},
{file = "lxml-5.3.0-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:9fb81d2824dff4f2e297a276297e9031f46d2682cafc484f49de182aa5e5df99"},
{file = "lxml-5.3.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2c226a06ecb8cdef28845ae976da407917542c5e6e75dcac7cc33eb04aaeb237"},
{file = "lxml-5.3.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:7d3d1ca42870cdb6d0d29939630dbe48fa511c203724820fc0fd507b2fb46577"},
{file = "lxml-5.3.0-cp36-cp36m-win32.whl", hash = "sha256:094cb601ba9f55296774c2d57ad68730daa0b13dc260e1f941b4d13678239e70"},
{file = "lxml-5.3.0-cp36-cp36m-win_amd64.whl", hash = "sha256:eafa2c8658f4e560b098fe9fc54539f86528651f61849b22111a9b107d18910c"},
{file = "lxml-5.3.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:cb83f8a875b3d9b458cada4f880fa498646874ba4011dc974e071a0a84a1b033"},
{file = "lxml-5.3.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:25f1b69d41656b05885aa185f5fdf822cb01a586d1b32739633679699f220391"},
{file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23e0553b8055600b3bf4a00b255ec5c92e1e4aebf8c2c09334f8368e8bd174d6"},
{file = "lxml-5.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9ada35dd21dc6c039259596b358caab6b13f4db4d4a7f8665764d616daf9cc1d"},
{file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:81b4e48da4c69313192d8c8d4311e5d818b8be1afe68ee20f6385d0e96fc9512"},
{file = "lxml-5.3.0-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:2bc9fd5ca4729af796f9f59cd8ff160fe06a474da40aca03fcc79655ddee1a8b"},
{file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:07da23d7ee08577760f0a71d67a861019103e4812c87e2fab26b039054594cc5"},
{file = "lxml-5.3.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:ea2e2f6f801696ad7de8aec061044d6c8c0dd4037608c7cab38a9a4d316bfb11"},
{file = "lxml-5.3.0-cp37-cp37m-win32.whl", hash = "sha256:5c54afdcbb0182d06836cc3d1be921e540be3ebdf8b8a51ee3ef987537455f84"},
{file = "lxml-5.3.0-cp37-cp37m-win_amd64.whl", hash = "sha256:f2901429da1e645ce548bf9171784c0f74f0718c3f6150ce166be39e4dd66c3e"},
{file = "lxml-5.3.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c56a1d43b2f9ee4786e4658c7903f05da35b923fb53c11025712562d5cc02753"},
{file = "lxml-5.3.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ee8c39582d2652dcd516d1b879451500f8db3fe3607ce45d7c5957ab2596040"},
{file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fdf3a3059611f7585a78ee10399a15566356116a4288380921a4b598d807a22"},
{file = "lxml-5.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:146173654d79eb1fc97498b4280c1d3e1e5d58c398fa530905c9ea50ea849b22"},
{file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0a7056921edbdd7560746f4221dca89bb7a3fe457d3d74267995253f46343f15"},
{file = "lxml-5.3.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:9e4b47ac0f5e749cfc618efdf4726269441014ae1d5583e047b452a32e221920"},
{file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:f914c03e6a31deb632e2daa881fe198461f4d06e57ac3d0e05bbcab8eae01945"},
{file = "lxml-5.3.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:213261f168c5e1d9b7535a67e68b1f59f92398dd17a56d934550837143f79c42"},
{file = "lxml-5.3.0-cp38-cp38-win32.whl", hash = "sha256:218c1b2e17a710e363855594230f44060e2025b05c80d1f0661258142b2add2e"},
{file = "lxml-5.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:315f9542011b2c4e1d280e4a20ddcca1761993dda3afc7a73b01235f8641e903"},
{file = "lxml-5.3.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1ffc23010330c2ab67fac02781df60998ca8fe759e8efde6f8b756a20599c5de"},
{file = "lxml-5.3.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2b3778cb38212f52fac9fe913017deea2fdf4eb1a4f8e4cfc6b009a13a6d3fcc"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4b0c7a688944891086ba192e21c5229dea54382f4836a209ff8d0a660fac06be"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:747a3d3e98e24597981ca0be0fd922aebd471fa99d0043a3842d00cdcad7ad6a"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:86a6b24b19eaebc448dc56b87c4865527855145d851f9fc3891673ff97950540"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b11a5d918a6216e521c715b02749240fb07ae5a1fefd4b7bf12f833bc8b4fe70"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68b87753c784d6acb8a25b05cb526c3406913c9d988d51f80adecc2b0775d6aa"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:109fa6fede314cc50eed29e6e56c540075e63d922455346f11e4d7a036d2b8cf"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:02ced472497b8362c8e902ade23e3300479f4f43e45f4105c85ef43b8db85229"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:6b038cc86b285e4f9fea2ba5ee76e89f21ed1ea898e287dc277a25884f3a7dfe"},
{file = "lxml-5.3.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:7437237c6a66b7ca341e868cda48be24b8701862757426852c9b3186de1da8a2"},
{file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:7f41026c1d64043a36fda21d64c5026762d53a77043e73e94b71f0521939cc71"},
{file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:482c2f67761868f0108b1743098640fbb2a28a8e15bf3f47ada9fa59d9fe08c3"},
{file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:1483fd3358963cc5c1c9b122c80606a3a79ee0875bcac0204149fa09d6ff2727"},
{file = "lxml-5.3.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:2dec2d1130a9cda5b904696cec33b2cfb451304ba9081eeda7f90f724097300a"},
{file = "lxml-5.3.0-cp39-cp39-win32.whl", hash = "sha256:a0eabd0a81625049c5df745209dc7fcef6e2aea7793e5f003ba363610aa0a3ff"},
{file = "lxml-5.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:89e043f1d9d341c52bf2af6d02e6adde62e0a46e6755d5eb60dc6e4f0b8aeca2"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7b1cd427cb0d5f7393c31b7496419da594fe600e6fdc4b105a54f82405e6626c"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51806cfe0279e06ed8500ce19479d757db42a30fd509940b1701be9c86a5ff9a"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ee70d08fd60c9565ba8190f41a46a54096afa0eeb8f76bd66f2c25d3b1b83005"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:8dc2c0395bea8254d8daebc76dcf8eb3a95ec2a46fa6fae5eaccee366bfe02ce"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6ba0d3dcac281aad8a0e5b14c7ed6f9fa89c8612b47939fc94f80b16e2e9bc83"},
{file = "lxml-5.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:6e91cf736959057f7aac7adfc83481e03615a8e8dd5758aa1d95ea69e8931dba"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:94d6c3782907b5e40e21cadf94b13b0842ac421192f26b84c45f13f3c9d5dc27"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c300306673aa0f3ed5ed9372b21867690a17dba38c68c44b287437c362ce486b"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78d9b952e07aed35fe2e1a7ad26e929595412db48535921c5013edc8aa4a35ce"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:01220dca0d066d1349bd6a1726856a78f7929f3878f7e2ee83c296c69495309e"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2d9b8d9177afaef80c53c0a9e30fa252ff3036fb1c6494d427c066a4ce6a282f"},
{file = "lxml-5.3.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:20094fc3f21ea0a8669dc4c61ed7fa8263bd37d97d93b90f28fc613371e7a875"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ace2c2326a319a0bb8a8b0e5b570c764962e95818de9f259ce814ee666603f19"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:92e67a0be1639c251d21e35fe74df6bcc40cba445c2cda7c4a967656733249e2"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd5350b55f9fecddc51385463a4f67a5da829bc741e38cf689f38ec9023f54ab"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:4c1fefd7e3d00921c44dc9ca80a775af49698bbfd92ea84498e56acffd4c5469"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:71a8dd38fbd2f2319136d4ae855a7078c69c9a38ae06e0c17c73fd70fc6caad8"},
{file = "lxml-5.3.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:97acf1e1fd66ab53dacd2c35b319d7e548380c2e9e8c54525c6e76d21b1ae3b1"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:68934b242c51eb02907c5b81d138cb977b2129a0a75a8f8b60b01cb8586c7b21"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b710bc2b8292966b23a6a0121f7a6c51d45d2347edcc75f016ac123b8054d3f2"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18feb4b93302091b1541221196a2155aa296c363fd233814fa11e181adebc52f"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3eb44520c4724c2e1a57c0af33a379eee41792595023f367ba3952a2d96c2aab"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:609251a0ca4770e5a8768ff902aa02bf636339c5a93f9349b48eb1f606f7f3e9"},
{file = "lxml-5.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:516f491c834eb320d6c843156440fe7fc0d50b33e44387fcec5b02f0bc118a4c"},
{file = "lxml-5.3.0.tar.gz", hash = "sha256:4e109ca30d1edec1ac60cdbe341905dc3b8f55b16855e03a54aaf59e51ec8c6f"},
{file = "lxml-5.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a4058f16cee694577f7e4dd410263cd0ef75644b43802a689c2b3c2a7e69453b"},
{file = "lxml-5.3.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:364de8f57d6eda0c16dcfb999af902da31396949efa0e583e12675d09709881b"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:528f3a0498a8edc69af0559bdcf8a9f5a8bf7c00051a6ef3141fdcf27017bbf5"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db4743e30d6f5f92b6d2b7c86b3ad250e0bad8dee4b7ad8a0c44bfb276af89a3"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:17b5d7f8acf809465086d498d62a981fa6a56d2718135bb0e4aa48c502055f5c"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:928e75a7200a4c09e6efc7482a1337919cc61fe1ba289f297827a5b76d8969c2"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a997b784a639e05b9d4053ef3b20c7e447ea80814a762f25b8ed5a89d261eac"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:7b82e67c5feb682dbb559c3e6b78355f234943053af61606af126df2183b9ef9"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:f1de541a9893cf8a1b1db9bf0bf670a2decab42e3e82233d36a74eda7822b4c9"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:de1fc314c3ad6bc2f6bd5b5a5b9357b8c6896333d27fdbb7049aea8bd5af2d79"},
{file = "lxml-5.3.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:7c0536bd9178f754b277a3e53f90f9c9454a3bd108b1531ffff720e082d824f2"},
{file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:68018c4c67d7e89951a91fbd371e2e34cd8cfc71f0bb43b5332db38497025d51"},
{file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:aa826340a609d0c954ba52fd831f0fba2a4165659ab0ee1a15e4aac21f302406"},
{file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:796520afa499732191e39fc95b56a3b07f95256f2d22b1c26e217fb69a9db5b5"},
{file = "lxml-5.3.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3effe081b3135237da6e4c4530ff2a868d3f80be0bda027e118a5971285d42d0"},
{file = "lxml-5.3.1-cp310-cp310-win32.whl", hash = "sha256:a22f66270bd6d0804b02cd49dae2b33d4341015545d17f8426f2c4e22f557a23"},
{file = "lxml-5.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:0bcfadea3cdc68e678d2b20cb16a16716887dd00a881e16f7d806c2138b8ff0c"},
{file = "lxml-5.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:e220f7b3e8656ab063d2eb0cd536fafef396829cafe04cb314e734f87649058f"},
{file = "lxml-5.3.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0f2cfae0688fd01f7056a17367e3b84f37c545fb447d7282cf2c242b16262607"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:67d2f8ad9dcc3a9e826bdc7802ed541a44e124c29b7d95a679eeb58c1c14ade8"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db0c742aad702fd5d0c6611a73f9602f20aec2007c102630c06d7633d9c8f09a"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:198bb4b4dd888e8390afa4f170d4fa28467a7eaf857f1952589f16cfbb67af27"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d2a3e412ce1849be34b45922bfef03df32d1410a06d1cdeb793a343c2f1fd666"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2b8969dbc8d09d9cd2ae06362c3bad27d03f433252601ef658a49bd9f2b22d79"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:5be8f5e4044146a69c96077c7e08f0709c13a314aa5315981185c1f00235fe65"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:133f3493253a00db2c870d3740bc458ebb7d937bd0a6a4f9328373e0db305709"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:52d82b0d436edd6a1d22d94a344b9a58abd6c68c357ed44f22d4ba8179b37629"},
{file = "lxml-5.3.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:1b6f92e35e2658a5ed51c6634ceb5ddae32053182851d8cad2a5bc102a359b33"},
{file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:203b1d3eaebd34277be06a3eb880050f18a4e4d60861efba4fb946e31071a295"},
{file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:155e1a5693cf4b55af652f5c0f78ef36596c7f680ff3ec6eb4d7d85367259b2c"},
{file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:22ec2b3c191f43ed21f9545e9df94c37c6b49a5af0a874008ddc9132d49a2d9c"},
{file = "lxml-5.3.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:7eda194dd46e40ec745bf76795a7cccb02a6a41f445ad49d3cf66518b0bd9cff"},
{file = "lxml-5.3.1-cp311-cp311-win32.whl", hash = "sha256:fb7c61d4be18e930f75948705e9718618862e6fc2ed0d7159b2262be73f167a2"},
{file = "lxml-5.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:c809eef167bf4a57af4b03007004896f5c60bd38dc3852fcd97a26eae3d4c9e6"},
{file = "lxml-5.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:e69add9b6b7b08c60d7ff0152c7c9a6c45b4a71a919be5abde6f98f1ea16421c"},
{file = "lxml-5.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:4e52e1b148867b01c05e21837586ee307a01e793b94072d7c7b91d2c2da02ffe"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4b382e0e636ed54cd278791d93fe2c4f370772743f02bcbe431a160089025c9"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c2e49dc23a10a1296b04ca9db200c44d3eb32c8d8ec532e8c1fd24792276522a"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4399b4226c4785575fb20998dc571bc48125dc92c367ce2602d0d70e0c455eb0"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5412500e0dc5481b1ee9cf6b38bb3b473f6e411eb62b83dc9b62699c3b7b79f7"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c93ed3c998ea8472be98fb55aed65b5198740bfceaec07b2eba551e55b7b9ae"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:63d57fc94eb0bbb4735e45517afc21ef262991d8758a8f2f05dd6e4174944519"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:b450d7cabcd49aa7ab46a3c6aa3ac7e1593600a1a0605ba536ec0f1b99a04322"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:4df0ec814b50275ad6a99bc82a38b59f90e10e47714ac9871e1b223895825468"},
{file = "lxml-5.3.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:d184f85ad2bb1f261eac55cddfcf62a70dee89982c978e92b9a74a1bfef2e367"},
{file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:b725e70d15906d24615201e650d5b0388b08a5187a55f119f25874d0103f90dd"},
{file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:a31fa7536ec1fb7155a0cd3a4e3d956c835ad0a43e3610ca32384d01f079ea1c"},
{file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:3c3c8b55c7fc7b7e8877b9366568cc73d68b82da7fe33d8b98527b73857a225f"},
{file = "lxml-5.3.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:d61ec60945d694df806a9aec88e8f29a27293c6e424f8ff91c80416e3c617645"},
{file = "lxml-5.3.1-cp312-cp312-win32.whl", hash = "sha256:f4eac0584cdc3285ef2e74eee1513a6001681fd9753b259e8159421ed28a72e5"},
{file = "lxml-5.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:29bfc8d3d88e56ea0a27e7c4897b642706840247f59f4377d81be8f32aa0cfbf"},
{file = "lxml-5.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:c093c7088b40d8266f57ed71d93112bd64c6724d31f0794c1e52cc4857c28e0e"},
{file = "lxml-5.3.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:b0884e3f22d87c30694e625b1e62e6f30d39782c806287450d9dc2fdf07692fd"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1637fa31ec682cd5760092adfabe86d9b718a75d43e65e211d5931809bc111e7"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a364e8e944d92dcbf33b6b494d4e0fb3499dcc3bd9485beb701aa4b4201fa414"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:779e851fd0e19795ccc8a9bb4d705d6baa0ef475329fe44a13cf1e962f18ff1e"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c4393600915c308e546dc7003d74371744234e8444a28622d76fe19b98fa59d1"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:673b9d8e780f455091200bba8534d5f4f465944cbdd61f31dc832d70e29064a5"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:2e4a570f6a99e96c457f7bec5ad459c9c420ee80b99eb04cbfcfe3fc18ec6423"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_ppc64le.whl", hash = "sha256:71f31eda4e370f46af42fc9f264fafa1b09f46ba07bdbee98f25689a04b81c20"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_s390x.whl", hash = "sha256:42978a68d3825eaac55399eb37a4d52012a205c0c6262199b8b44fcc6fd686e8"},
{file = "lxml-5.3.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:8b1942b3e4ed9ed551ed3083a2e6e0772de1e5e3aca872d955e2e86385fb7ff9"},
{file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:85c4f11be9cf08917ac2a5a8b6e1ef63b2f8e3799cec194417e76826e5f1de9c"},
{file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:231cf4d140b22a923b1d0a0a4e0b4f972e5893efcdec188934cc65888fd0227b"},
{file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:5865b270b420eda7b68928d70bb517ccbe045e53b1a428129bb44372bf3d7dd5"},
{file = "lxml-5.3.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dbf7bebc2275016cddf3c997bf8a0f7044160714c64a9b83975670a04e6d2252"},
{file = "lxml-5.3.1-cp313-cp313-win32.whl", hash = "sha256:d0751528b97d2b19a388b302be2a0ee05817097bab46ff0ed76feeec24951f78"},
{file = "lxml-5.3.1-cp313-cp313-win_amd64.whl", hash = "sha256:91fb6a43d72b4f8863d21f347a9163eecbf36e76e2f51068d59cd004c506f332"},
{file = "lxml-5.3.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:016b96c58e9a4528219bb563acf1aaaa8bc5452e7651004894a973f03b84ba81"},
{file = "lxml-5.3.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82a4bb10b0beef1434fb23a09f001ab5ca87895596b4581fd53f1e5145a8934a"},
{file = "lxml-5.3.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d68eeef7b4d08a25e51897dac29bcb62aba830e9ac6c4e3297ee7c6a0cf6439"},
{file = "lxml-5.3.1-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:f12582b8d3b4c6be1d298c49cb7ae64a3a73efaf4c2ab4e37db182e3545815ac"},
{file = "lxml-5.3.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:2df7ed5edeb6bd5590914cd61df76eb6cce9d590ed04ec7c183cf5509f73530d"},
{file = "lxml-5.3.1-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:585c4dc429deebc4307187d2b71ebe914843185ae16a4d582ee030e6cfbb4d8a"},
{file = "lxml-5.3.1-cp36-cp36m-win32.whl", hash = "sha256:06a20d607a86fccab2fc15a77aa445f2bdef7b49ec0520a842c5c5afd8381576"},
{file = "lxml-5.3.1-cp36-cp36m-win_amd64.whl", hash = "sha256:057e30d0012439bc54ca427a83d458752ccda725c1c161cc283db07bcad43cf9"},
{file = "lxml-5.3.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4867361c049761a56bd21de507cab2c2a608c55102311d142ade7dab67b34f32"},
{file = "lxml-5.3.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3dddf0fb832486cc1ea71d189cb92eb887826e8deebe128884e15020bb6e3f61"},
{file = "lxml-5.3.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1bcc211542f7af6f2dfb705f5f8b74e865592778e6cafdfd19c792c244ccce19"},
{file = "lxml-5.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aaca5a812f050ab55426c32177091130b1e49329b3f002a32934cd0245571307"},
{file = "lxml-5.3.1-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:236610b77589faf462337b3305a1be91756c8abc5a45ff7ca8f245a71c5dab70"},
{file = "lxml-5.3.1-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:aed57b541b589fa05ac248f4cb1c46cbb432ab82cbd467d1c4f6a2bdc18aecf9"},
{file = "lxml-5.3.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:75fa3d6946d317ffc7016a6fcc44f42db6d514b7fdb8b4b28cbe058303cb6e53"},
{file = "lxml-5.3.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:96eef5b9f336f623ffc555ab47a775495e7e8846dde88de5f941e2906453a1ce"},
{file = "lxml-5.3.1-cp37-cp37m-win32.whl", hash = "sha256:ef45f31aec9be01379fc6c10f1d9c677f032f2bac9383c827d44f620e8a88407"},
{file = "lxml-5.3.1-cp37-cp37m-win_amd64.whl", hash = "sha256:a0611da6b07dd3720f492db1b463a4d1175b096b49438761cc9f35f0d9eaaef5"},
{file = "lxml-5.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b2aca14c235c7a08558fe0a4786a1a05873a01e86b474dfa8f6df49101853a4e"},
{file = "lxml-5.3.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ae82fce1d964f065c32c9517309f0c7be588772352d2f40b1574a214bd6e6098"},
{file = "lxml-5.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7aae7a3d63b935babfdc6864b31196afd5145878ddd22f5200729006366bc4d5"},
{file = "lxml-5.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8e0d177b1fe251c3b1b914ab64135475c5273c8cfd2857964b2e3bb0fe196a7"},
{file = "lxml-5.3.1-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:6c4dd3bfd0c82400060896717dd261137398edb7e524527438c54a8c34f736bf"},
{file = "lxml-5.3.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:f1208c1c67ec9e151d78aa3435aa9b08a488b53d9cfac9b699f15255a3461ef2"},
{file = "lxml-5.3.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:c6aacf00d05b38a5069826e50ae72751cb5bc27bdc4d5746203988e429b385bb"},
{file = "lxml-5.3.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:5881aaa4bf3a2d086c5f20371d3a5856199a0d8ac72dd8d0dbd7a2ecfc26ab73"},
{file = "lxml-5.3.1-cp38-cp38-win32.whl", hash = "sha256:45fbb70ccbc8683f2fb58bea89498a7274af1d9ec7995e9f4af5604e028233fc"},
{file = "lxml-5.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:7512b4d0fc5339d5abbb14d1843f70499cab90d0b864f790e73f780f041615d7"},
{file = "lxml-5.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5885bc586f1edb48e5d68e7a4b4757b5feb2a496b64f462b4d65950f5af3364f"},
{file = "lxml-5.3.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1b92fe86e04f680b848fff594a908edfa72b31bfc3499ef7433790c11d4c8cd8"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a091026c3bf7519ab1e64655a3f52a59ad4a4e019a6f830c24d6430695b1cf6a"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8ffb141361108e864ab5f1813f66e4e1164181227f9b1f105b042729b6c15125"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3715cdf0dd31b836433af9ee9197af10e3df41d273c19bb249230043667a5dfd"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:88b72eb7222d918c967202024812c2bfb4048deeb69ca328363fb8e15254c549"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa59974880ab5ad8ef3afaa26f9bda148c5f39e06b11a8ada4660ecc9fb2feb3"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3bb8149840daf2c3f97cebf00e4ed4a65a0baff888bf2605a8d0135ff5cf764e"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:0d6b2fa86becfa81f0a0271ccb9eb127ad45fb597733a77b92e8a35e53414914"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:136bf638d92848a939fd8f0e06fcf92d9f2e4b57969d94faae27c55f3d85c05b"},
{file = "lxml-5.3.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:89934f9f791566e54c1d92cdc8f8fd0009447a5ecdb1ec6b810d5f8c4955f6be"},
{file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:a8ade0363f776f87f982572c2860cc43c65ace208db49c76df0a21dde4ddd16e"},
{file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:bfbbab9316330cf81656fed435311386610f78b6c93cc5db4bebbce8dd146675"},
{file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:172d65f7c72a35a6879217bcdb4bb11bc88d55fb4879e7569f55616062d387c2"},
{file = "lxml-5.3.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:e3c623923967f3e5961d272718655946e5322b8d058e094764180cdee7bab1af"},
{file = "lxml-5.3.1-cp39-cp39-win32.whl", hash = "sha256:ce0930a963ff593e8bb6fda49a503911accc67dee7e5445eec972668e672a0f0"},
{file = "lxml-5.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:f7b64fcd670bca8800bc10ced36620c6bbb321e7bc1214b9c0c0df269c1dddc2"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:afa578b6524ff85fb365f454cf61683771d0170470c48ad9d170c48075f86725"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67f5e80adf0aafc7b5454f2c1cb0cde920c9b1f2cbd0485f07cc1d0497c35c5d"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd0b80ac2d8f13ffc906123a6f20b459cb50a99222d0da492360512f3e50f84"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:422c179022ecdedbe58b0e242607198580804253da220e9454ffe848daa1cfd2"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:524ccfded8989a6595dbdda80d779fb977dbc9a7bc458864fc9a0c2fc15dc877"},
{file = "lxml-5.3.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:48fd46bf7155def2e15287c6f2b133a2f78e2d22cdf55647269977b873c65499"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:05123fad495a429f123307ac6d8fd6f977b71e9a0b6d9aeeb8f80c017cb17131"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a243132767150a44e6a93cd1dde41010036e1cbc63cc3e9fe1712b277d926ce3"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c92ea6d9dd84a750b2bae72ff5e8cf5fdd13e58dda79c33e057862c29a8d5b50"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:2f1be45d4c15f237209bbf123a0e05b5d630c8717c42f59f31ea9eae2ad89394"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:a83d3adea1e0ee36dac34627f78ddd7f093bb9cfc0a8e97f1572a949b695cb98"},
{file = "lxml-5.3.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:3edbb9c9130bac05d8c3fe150c51c337a471cc7fdb6d2a0a7d3a88e88a829314"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:2f23cf50eccb3255b6e913188291af0150d89dab44137a69e14e4dcb7be981f1"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df7e5edac4778127f2bf452e0721a58a1cfa4d1d9eac63bdd650535eb8543615"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:094b28ed8a8a072b9e9e2113a81fda668d2053f2ca9f2d202c2c8c7c2d6516b1"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:514fe78fc4b87e7a7601c92492210b20a1b0c6ab20e71e81307d9c2e377c64de"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8fffc08de02071c37865a155e5ea5fce0282e1546fd5bde7f6149fcaa32558ac"},
{file = "lxml-5.3.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:4b0d5cdba1b655d5b18042ac9c9ff50bda33568eb80feaaca4fc237b9c4fbfde"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:3031e4c16b59424e8d78522c69b062d301d951dc55ad8685736c3335a97fc270"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb659702a45136c743bc130760c6f137870d4df3a9e14386478b8a0511abcfca"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5a11b16a33656ffc43c92a5343a28dc71eefe460bcc2a4923a96f292692709f6"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c5ae125276f254b01daa73e2c103363d3e99e3e10505686ac7d9d2442dd4627a"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c76722b5ed4a31ba103e0dc77ab869222ec36efe1a614e42e9bcea88a36186fe"},
{file = "lxml-5.3.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:33e06717c00c788ab4e79bc4726ecc50c54b9bfb55355eae21473c145d83c2d2"},
{file = "lxml-5.3.1.tar.gz", hash = "sha256:106b7b5d2977b339f1e97efe2778e2ab20e99994cbb0ec5e55771ed0795920c8"},
]
[package.extras]
cssselect = ["cssselect (>=0.7)"]
html-clean = ["lxml-html-clean"]
html-clean = ["lxml_html_clean"]
html5 = ["html5lib"]
htmlsoup = ["BeautifulSoup4"]
source = ["Cython (>=3.0.11)"]
source = ["Cython (>=3.0.11,<3.1.0)"]
[[package]]
name = "markdown"
@ -7062,13 +7062,13 @@ vision = ["Pillow (>=10.0.1,<=15.0)"]
[[package]]
name = "transformers"
version = "4.48.2"
version = "4.48.3"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false
python-versions = ">=3.9.0"
files = [
{file = "transformers-4.48.2-py3-none-any.whl", hash = "sha256:493bc5b0268b116eff305edf6656367fc89cf570e7a9d5891369e04751db698a"},
{file = "transformers-4.48.2.tar.gz", hash = "sha256:dcfb73473e61f22fb3366fe2471ed2e42779ecdd49527a1bdf1937574855d516"},
{file = "transformers-4.48.3-py3-none-any.whl", hash = "sha256:78697f990f5ef350c23b46bf86d5081ce96b49479ab180b2de7687267de8fd36"},
{file = "transformers-4.48.3.tar.gz", hash = "sha256:a5e8f1e9a6430aa78215836be70cecd3f872d99eeda300f41ad6cc841724afdb"},
]
[package.dependencies]
@ -7851,4 +7851,4 @@ vlm = ["transformers", "transformers"]
[metadata]
lock-version = "2.0"
python-versions = "^3.9"
content-hash = "86d266adc6272f3db65ab07f5cce35cbe9626368dc0e09ab374c861f0809f693"
content-hash = "dc683f71ec9f8c0f94cef7c60a616aa17f3c831e322d136b76cef794e1809fd7"

2
pyproject.toml
View File

@ -26,7 +26,7 @@ packages = [{include = "docling"}]
######################
python = "^3.9"
pydantic = "^2.0.0"
docling-core = {extras = ["chunking"], version = "^2.17.2"}
docling-core = {extras = ["chunking"], version = "^2.18.0"}
docling-ibm-models = "^3.3.0"
deepsearch-glm = "^1.0.0"
docling-parse = "^3.3.0"

2
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/amt_handbook_sample.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2203.01017v2.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2206.01062.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2305.03393v1.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/amt_handbook_sample.json
View File

File diff suppressed because one or more lines are too long

139
tests/data/groundtruth/docling_v2/elife-56337.xml.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "elife-56337",
"origin": {
"mimetype": "application/xml",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -59,6 +60,7 @@
"$ref": "#/texts/63"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -238,6 +240,7 @@
"$ref": "#/texts/120"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -277,6 +280,7 @@
"$ref": "#/texts/64"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "KRAB-zinc finger protein gene expansion in response to active retrotransposons in the murine lineage",
@ -288,6 +292,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Wolf Gernot; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; de Iaco Alberto; 2: School of Life Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL): Lausanne: Switzerland; Sun Ming-An; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Bruno Melania; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Tinkham Matthew; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Hoang Don; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Mitra Apratim; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Ralls Sherry; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States; Trono Didier; 2: School of Life Sciences, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL): Lausanne: Switzerland; Macfarlan Todd S; 1: The Eunice Kennedy Shriver National Institute of Child Health and Human Development, The National Institutes of Health: Bethesda: United States",
@ -303,6 +308,7 @@
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Abstract",
@ -315,6 +321,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The Kr\u00fcppel-associated box zinc finger protein (KRAB-ZFP) family diversified in mammals. The majority of human KRAB-ZFPs bind transposable elements (TEs), however, since most TEs are inactive in humans it is unclear whether KRAB-ZFPs emerged to suppress TEs. We demonstrate that many recently emerged murine KRAB-ZFPs also bind to TEs, including the active ETn, IAP, and L1 families. Using a CRISPR/Cas9-based engineering approach, we genetically deleted five large clusters of KRAB-ZFPs and demonstrate that target TEs are de-repressed, unleashing TE-encoded enhancers. Homozygous knockout mice lacking one of two KRAB-ZFP gene clusters on chromosome 2 and chromosome 4 were nonetheless viable. In pedigrees of chromosome 4 cluster KRAB-ZFP mutants, we identified numerous novel ETn insertions with a modest increase in mutants. Our data strongly support the current model that recent waves of retrotransposon activity drove the expansion of KRAB-ZFP genes in mice and that many KRAB-ZFPs play a redundant role restricting TE activity.",
@ -333,6 +340,7 @@
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Introduction",
@ -345,6 +353,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Nearly half of the human and mouse genomes consist of transposable elements (TEs). TEs shape the evolution of species, serving as a source for genetic innovation (Chuong et al., 2016; Frank and Feschotte, 2017). However, TEs also potentially harm their hosts by insertional mutagenesis, gene deregulation and activation of innate immunity (Maksakova et al., 2006; Kano et al., 2007; Brodziak et al., 2012; Hancks and Kazazian, 2016). To protect themselves from TE activity, host organisms have developed a wide range of defense mechanisms targeting virtually all steps of the TE life cycle (Dewannieux and Heidmann, 2013). In tetrapods, KRAB zinc finger protein (KRAB-ZFP) genes have amplified and diversified, likely in response to TE colonization (Thomas and Schneider, 2011; Najafabadi et al., 2015; Wolf et al., 2015a; Wolf et al., 2015b; Imbeault et al., 2017). Conventional ZFPs bind DNA using tandem arrays of C2H2 zinc finger domains, each capable of specifically interacting with three nucleotides, whereas some zinc fingers can bind two or four nucleotides and include DNA backbone interactions depending on target DNA structure (Patel et al., 2018). This allows KRAB-ZFPs to flexibly bind to large stretches of DNA with high affinity. The KRAB domain binds the corepressor KAP1, which in turn recruits histone modifying enzymes including the NuRD histone deacetylase complex and the H3K9-specific methylase SETDB1 (Schultz et al., 2002; Sripathy et al., 2006), which induces persistent and heritable gene silencing (Groner et al., 2010). Deletion of KAP1 (Rowe et al., 2010) or SETDB1 (Matsui et al., 2010) in mouse embryonic stem (ES) cells induces TE reactivation and cell death, but only minor phenotypes in differentiated cells, suggesting KRAB-ZFPs are most important during early embryogenesis where they mark TEs for stable epigenetic silencing that persists through development. However, SETDB1-containing complexes are also required to repress TEs in primordial germ cells (Liu et al., 2014) and adult tissues (Ecco et al., 2016), indicating KRAB-ZFPs are active beyond early development.",
@ -356,6 +365,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "TEs, especially long terminal repeat (LTR) retrotransposons, also known as endogenous retroviruses (ERVs), can affect expression of neighboring genes through their promoter and enhancer functions (Macfarlan et al., 2012; Wang et al., 2014; Thompson et al., 2016). KAP1 deletion in mouse ES cells causes rapid gene deregulation (Rowe et al., 2013), indicating that KRAB-ZFPs may regulate gene expression by recruiting KAP1 to TEs. Indeed, Zfp809 knock-out (KO) in mice resulted in transcriptional activation of a handful of genes in various tissues adjacent to ZFP809-targeted VL30-Pro elements (Wolf et al., 2015b). It has therefore been speculated that KRAB-ZFPs bind to TE sequences to domesticate them for gene regulatory innovation (Ecco et al., 2017). This idea is supported by the observation that many human KRAB-ZFPs target TE groups that have lost their coding potential millions of years ago and that KRAB-ZFP target sequences within TEs are in some cases under purifying selection (Imbeault et al., 2017). However, there are also clear signs of an evolutionary arms-race between human TEs and KRAB-ZFPs (Jacobs et al., 2014), indicating that some KRAB-ZFPs may limit TE mobility for stretches of evolutionary time, prior to their ultimate loss from the genome or adaptation for other regulatory functions. Here we use the laboratory mouse, which has undergone a recent expansion of the KRAB-ZFP family, to determine the in vivo requirement of the majority of evolutionarily young KRAB-ZFP genes.",
@ -380,6 +390,7 @@
"$ref": "#/texts/19"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Results",
@ -408,6 +419,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Mouse KRAB-ZFPs target retrotransposons",
@ -420,6 +432,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We analyzed the RNA expression profiles of mouse KRAB-ZFPs across a wide range of tissues to identify candidates active in early embryos/ES cells. While the majority of KRAB-ZFPs are expressed at low levels and uniformly across tissues, a group of KRAB-ZFPs are highly and almost exclusively expressed in ES cells (Figure 1\u2014figure supplement 1A). About two thirds of these KRAB-ZFPs are physically linked in two clusters on chromosome 2 (Chr2-cl) and 4 (Chr4-cl) (Figure 1\u2014figure supplement 1B). These two clusters encode 40 and 21 KRAB-ZFP annotated genes, respectively, which, with one exception on Chr4-cl, do not have orthologues in rat or any other sequenced mammals (Supplementary file 1). The KRAB-ZFPs within these two genomic clusters also group together phylogenetically (Figure 1\u2014figure supplement 1C), indicating these gene clusters arose by a series of recent segmental gene duplications (Kauzlaric et al., 2017).",
@ -431,6 +444,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "To determine the binding sites of the KRAB-ZFPs within these and other gene clusters, we expressed epitope-tagged KRAB-ZFPs using stably integrating vectors in mouse embryonic carcinoma (EC) or ES cells (Table 1, Supplementary file 1) and performed chromatin immunoprecipitation followed by deep sequencing (ChIP-seq). We then determined whether the identified binding sites are significantly enriched over annotated TEs and used the non-repetitive peak fraction to identify binding motifs. We discarded 7 of 68 ChIP-seq datasets because we could not obtain a binding motif or a target TE and manual inspection confirmed low signal to noise ratio. Of the remaining 61 KRAB-ZFPs, 51 significantly overlapped at least one TE subfamily (adjusted p-value<1e-5). Altogether, 81 LTR retrotransposon, 18 LINE, 10 SINE and one DNA transposon subfamilies were targeted by at least one of the 51 KRAB-ZFPs (Figure 1A and Supplementary file 1). Chr2-cl KRAB-ZFPs preferably bound IAPEz retrotransposons and L1-type LINEs, while Chr4-cl KRAB-ZFPs targeted various retrotransposons, including the closely related MMETn (hereafter referred to as ETn) and ETnERV (also known as MusD) elements (Figure 1A). ETn elements are non-autonomous LTR retrotransposons that require trans-complementation by the fully coding ETnERV elements that contain Gag, Pro and Pol genes (Ribet et al., 2004). These elements have accumulated to\u00a0~240 and~100 copies in the reference C57BL/6 genome, respectively, with\u00a0~550 solitary LTRs (Baust et al., 2003). Both ETn and ETnERVs are still active, generating polymorphisms and mutations in several mouse strains (Gagnier et al., 2019). The validity of our ChIP-seq screen was confirmed by the identification of binding motifs - which often resembled the computationally predicted motifs (Figure 1\u2014figure supplement 2A) - for the majority of screened KRAB-ZFPs (Supplementary file 1). Moreover, predicted and experimentally determined motifs were found in targeted TEs in most cases (Supplementary file 1), and reporter repression assays confirmed KRAB-ZFP induced silencing for all the tested sequences (Figure 1\u2014figure supplement 2B). Finally, we observed KAP1 and H3K9me3 enrichment at most of the targeted TEs in wild type ES cells, indicating that most of these KRAB-ZFPs are functionally active in the early embryo (Figure 1A).",
@ -442,6 +456,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We generally observed that KRAB-ZFPs present exclusively in mouse target TEs that are restricted to the mouse genome, indicating KRAB-ZFPs and their targets emerged together. For example, several mouse-specific KRAB-ZFPs in Chr2-cl and Chr4-cl target IAP and ETn elements which are only found in the mouse genome and are highly active. This is the strongest data to date supporting that recent KRAB-ZFP expansions in these young clusters is a response to recent TE activity. Likewise, ZFP599 and ZFP617, both conserved in Muroidea, bind to various ORR1-type LTRs which are present in the rat genome (Supplementary file 1). However, ZFP961, a KRAB-ZFP encoded on a small gene cluster on chromosome 8 that is conserved in Muroidea targets TEs that are only found in the mouse genome (e.g. ETn), a paradox we have previously observed with ZFP809, which also targets TEs that are evolutionarily younger than itself (Wolf et al., 2015b). The ZFP961 binding site is located at the 5\u2019 end of the internal region of ETn and ETnERV elements, a sequence that usually contains the primer binding site (PBS), which is required to prime retroviral reverse transcription. Indeed, the ZFP961 motif closely resembles the PBSLys1,2 (Figure 1\u2014figure supplement 3A), which had been previously identified as a KAP1-dependent target of retroviral repression (Yamauchi et al., 1995; Wolf et al., 2008). Repression of the PBSLys1,2 by ZFP961 was also confirmed in reporter assays (Figure 1\u2014figure supplement 2B), indicating that ZFP961 is likely responsible for this silencing effect.",
@ -453,6 +468,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "To further test the hypothesis that KRAB-ZFPs target sites necessary for retrotransposition, we utilized previously generated ETn and ETnERV retrotransposition reporters in which we mutated KRAB-ZFP binding sites (Ribet et al., 2004). Whereas the ETnERV reporters are sufficient for retrotransposition, the ETn reporter requires ETnERV genes supplied in trans. We tested and confirmed that the REX2/ZFP600 and GM13051 binding sites within these TEs are required for efficient retrotransposition (Figure 1\u2014figure supplement 3B). REX2 and ZFP600 both bind a target about 200 bp from the start of the internal region (Figure 1B), a region that often encodes the packaging signal. GM13051 binds a target coding for part of a highly structured mRNA export signal (Legiewicz et al., 2010) near the 3\u2019 end of the internal region of ETn (Figure 1\u2014figure supplement 3C). Both signals are characterized by stem-loop intramolecular base-pairing in which a single mutation can disrupt loop formation. This indicates that at least some KRAB-ZFPs evolved to bind functionally essential target sequences which cannot easily evade repression by mutation.",
@ -464,6 +480,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Our KRAB-ZFP ChIP-seq dataset also provided unique insights into the emergence of new KRAB-ZFPs and binding patterns. The Chr4-cl KRAB-ZFPs REX2 and ZFP600 bind to the same target within ETn but with varying affinity (Figure 1C). Comparison of the amino acids responsible for DNA contact revealed a high similarity between REX2 and ZFP600, with the main differences at the most C-terminal zinc fingers. Additionally, we found that GM30910, another KRAB-ZFP encoded in the Chr4-cl, also shows a strong similarity to both KRAB-ZFPs yet targets entirely different groups of TEs (Figure 1C and Supplementary file 1). Together with previously shown data (Ecco et al., 2016), this example highlights how addition of a few new zinc fingers to an existing array can entirely shift the mode of DNA binding.",
@ -479,6 +496,7 @@
"$ref": "#/texts/15"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Genetic deletion of KRAB-ZFP gene clusters leads to retrotransposon reactivation",
@ -491,6 +509,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The majority of KRAB-ZFP genes are harbored in large, highly repetitive clusters that have formed by successive complex segmental duplications (Kauzlaric et al., 2017), rendering them inaccessible to conventional gene targeting. We therefore developed a strategy to delete entire KRAB-ZFP gene clusters in ES cells (including the Chr2-cl and Chr4-cl as well as two clusters on chromosome 13 and a cluster on chromosome 10) using two CRISPR/Cas9 gRNAs targeting unique regions flanking each cluster, and short single-stranded repair oligos with homologies to both sides of the projected cut sites. Using this approach, we generated five cluster KO ES cell lines in at least two biological replicates and performed RNA sequencing (RNA-seq) to determine TE expression levels. Strikingly, four of the five cluster KO ES cells exhibited distinct TE reactivation phenotypes (Figure 2A). Chr2-cl KO resulted in reactivation of several L1 subfamilies as well as RLTR10 (up to more than 100-fold as compared to WT) and IAPEz ERVs. In contrast, the most strongly upregulated TEs in Chr4-cl KO cells were ETn/ETnERV (up to 10-fold as compared to WT), with several other ERV groups modestly reactivated. ETn/ETnERV elements were also upregulated in Chr13.2-cl KO ES cells while the only upregulated ERVs in Chr13.1-cl KO ES cells were MMERVK10C elements (Figure 2A). Most reactivated retrotransposons were targeted by at least one KRAB-ZFP that was encoded in the deleted cluster (Figure 2A and Supplementary file 1), indicating a direct effect of these KRAB-ZFPs on TE expression levels. Furthermore, we observed a loss of KAP1 binding and H3K9me3 at several TE subfamilies that are targeted by at least one KRAB-ZFP within the deleted Chr2-cl and Chr4-cl (Figure 2B, Figure 2\u2014figure supplement 1A), including L1, ETn and IAPEz elements. Using reduced representation bisulfite sequencing (RRBS-seq), we found that a subset of KRAB-ZFP bound TEs were partially hypomethylated in Chr4-cl KO ES cells, but only when grown in genome-wide hypomethylation-inducing conditions (Blaschke et al., 2013; Figure 2C and Supplementary file 2). These data are consistent with the hypothesis that KRAB-ZFPs/KAP1 are not required to establish DNA methylation, but under certain conditions they protect specific TEs and imprint control regions from genome-wide demethylation (Leung et al., 2014; Deniz et al., 2018).",
@ -509,6 +528,7 @@
"$ref": "#/texts/18"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "KRAB-ZFP cluster deletions license TE-borne enhancers",
@ -521,6 +541,7 @@
"$ref": "#/texts/16"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We next used our RNA-seq datasets to determine the effect of KRAB-ZFP cluster deletions on gene expression. We identified 195 significantly upregulated and 130 downregulated genes in Chr4-cl KO ES cells, and 108 upregulated and 59 downregulated genes in Chr2-cl KO ES cells (excluding genes on the deleted cluster) (Figure 3A). To address whether gene deregulation in Chr2-cl and Chr4-cl KO ES cells is caused by nearby TE reactivation, we determined whether genes near certain TE subfamilies are more frequently deregulated than random genes. We found a strong correlation of gene upregulation and TE proximity for several TE subfamilies, of which many became transcriptionally activated themselves (Figure 3B). For example, nearly 10% of genes that are located within 100 kb (up- or downstream of the TSS) of an ETn element are upregulated in Chr4-cl KO ES cells, as compared to 0.8% of all genes. In Chr2-cl KO ES cells, upregulated genes were significantly enriched near various LINE groups but also IAPEz-int and RLTR10-int elements, indicating that TE-binding KRAB-ZFPs in these clusters limit the potential activating effects of TEs on nearby genes.",
@ -532,6 +553,7 @@
"$ref": "#/texts/16"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "While we generally observed that TE-associated gene reactivation is not caused by elongated or spliced transcription starting at the retrotransposons, we did observe that the strength of the effect of ETn elements on gene expression is stronger on genes in closer proximity. About 25% of genes located within 20 kb of an ETn element, but only 5% of genes located at a distance between 50 and 100 kb from the nearest ETn insertion, become upregulated in Chr4-cl KO ES cells. Importantly however, the correlation is still significant for genes that are located at distances between 50 and 100 kb from the nearest ETn insertion, indicating that ETn elements can act as long-range enhancers of gene expression in the absence of KRAB-ZFPs that target them. To confirm that Chr4-cl KRAB-ZFPs such as GM13051 block ETn-borne enhancers, we tested the ability of a putative ETn enhancer to activate transcription in a reporter assay. For this purpose, we cloned a 5 kb fragment spanning from the GM13051 binding site within the internal region of a truncated ETn insertion to the first exon of the Cd59a gene, which is strongly activated in Chr4-cl KO ES cells (Figure 2\u2014figure supplement 1B). We observed strong transcriptional activity of this fragment which was significantly higher in Chr4-cl KO ES cells. Surprisingly, this activity was reduced to background when the internal segment of the ETn element was not included in the fragment, suggesting the internal segment of the ETn element, but not its LTR, contains a Chr4-cl KRAB-ZFP sensitive enhancer. To further corroborate these findings, we genetically deleted an ETn element that is located about 60 kb from the TSS of Chst1, one of the top-upregulated genes in Chr4-cl KO ES cells (Figure 3C). RT-qPCR analysis revealed that the Chst1 upregulation phenotype in Chr4-cl KO ES cells diminishes when the ETn insertion is absent, providing direct evidence that a KRAB-ZFP controlled ETn-borne enhancer regulates Chst1 expression (Figure 3D). Furthermore, ChIP-seq confirmed a general increase of H3K4me3, H3K4me1 and H3K27ac marks at ETn elements in Chr4-cl KO ES cells (Figure 3E). Notably, enhancer marks were most pronounced around the GM13051 binding site near the 3\u2019 end of the internal region, confirming that the enhancer activity of ETn is located on the internal region and not on the LTR.",
@ -562,6 +584,7 @@
"$ref": "#/texts/25"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ETn retrotransposition in Chr4-cl KO and WT mice",
@ -574,6 +597,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "IAP, ETn/ETnERV and MuLV/RLTR4 retrotransposons are highly polymorphic in inbred mouse strains (Nell\u00e5ker et al., 2012), indicating that these elements are able to mobilize in the germ line. Since these retrotransposons are upregulated in Chr2-cl and Chr4-cl KO ES cells, we speculated that these KRAB-ZFP clusters evolved to minimize the risks of insertional mutagenesis by retrotransposition. To test this, we generated Chr2-cl and Chr4-cl KO mice via ES cell injection into blastocysts, and after germ line transmission we genotyped the offspring of heterozygous breeding pairs. While the offspring of Chr4-cl KO/WT parents were born close to Mendelian ratios in pure C57BL/6 and mixed C57BL/6 129Sv matings, one Chr4-cl KO/WT breeding pair gave birth to significantly fewer KO mice than expected (p-value=0.022) (Figure 4\u2014figure supplement 1A). Likewise, two out of four Chr2-cl KO breeding pairs on mixed C57BL/6 129Sv matings failed to give birth to a single KO offspring (p-value<0.01) while the two other mating pairs produced KO offspring at near Mendelian ratios (Figure 4\u2014figure supplement 1A). Altogether, these data indicate that KRAB-ZFP clusters are not absolutely essential in mice, but that genetic and/or epigenetic factors may contribute to reduced viability.",
@ -585,6 +609,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We reasoned that retrotransposon activation could account for the reduced viability of Chr2-cl and Chr4-cl KO mice in some matings. However, since only rare matings produced non-viable KO embryos, we instead turned to the viable KO mice to assay for increased transposon activity. RNA-seq in blood, brain and testis revealed that, with a few exceptions, retrotransposons upregulated in Chr2 and Chr4 KRAB-ZFP cluster KO ES cells are not expressed at higher levels in adult tissues (Figure 4\u2014figure supplement 1B). Likewise, no strong transcriptional TE reactivation phenotype was observed in liver and kidney of Chr4-cl KO mice (data not shown) and ChIP-seq with antibodies against H3K4me1, H3K4me3 and H3K27ac in testis of Chr4-cl WT and KO mice revealed no increase of active histone marks at ETn elements or other TEs (data not shown). This indicates that Chr2-cl and Chr4-cl KRAB-ZFPs are primarily required for TE repression during early development. This is consistent with the high expression of these KRAB-ZFPs uniquely in ES cells (Figure 1\u2014figure supplement 1A). To determine whether retrotransposition occurs at a higher frequency in Chr4-cl KO mice during development, we screened for novel ETn (ETn/ETnERV) and MuLV (MuLV/RLTR4_MM) insertions in viable Chr4-cl KO mice. For this purpose, we developed a capture-sequencing approach to enrich for ETn/MuLV DNA and flanking sequences from genomic DNA using probes that hybridize with the 5\u2019 and 3\u2019 ends of ETn and MuLV LTRs prior to deep sequencing. We screened genomic DNA samples from a total of 76 mice, including 54 mice from ancestry-controlled Chr4-cl KO matings in various strain backgrounds, the two ES cell lines the Chr4-cl KO mice were generated from, and eight mice from a Chr2-cl KO mating which served as a control (since ETn and MuLVs are not activated in Chr2-cl KO ES cells) (Supplementary file 4). Using this approach, we were able to enrich reads mapping to ETn/MuLV LTRs about 2,000-fold compared to genome sequencing without capture. ETn/MuLV insertions were determined by counting uniquely mapped reads that were paired with reads mapping to ETn/MuLV elements (see materials and methods for details). To assess the efficiency of the capture approach, we determined what proportion of a set of 309 largely intact (two LTRs flanking an internal sequence) reference ETn elements could be identified using our sequencing data. 95% of these insertions were called with high confidence in the majority of our samples (data not shown), indicating that we are able to identify ETn insertions at a high recovery rate.",
@ -596,6 +621,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Using this dataset, we first confirmed the polymorphic nature of both ETn and MuLV retrotransposons in laboratory mouse strains (Figure 4\u2014figure supplement 2A), highlighting the potential of these elements to retrotranspose. To identify novel insertions, we filtered out insertions that were supported by ETn/MuLV-paired reads in more than one animal. While none of the 54 ancestry-controlled mice showed a single novel MuLV insertion, we observed greatly varying numbers of up to 80 novel ETn insertions in our pedigree (Figure 4A).",
@ -607,6 +633,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "To validate some of the novel ETn insertions, we designed specific PCR primers for five of the insertions and screened genomic DNA of the mice in which they were identified as well as their parents. For all tested insertions, we were able to amplify their flanking sequence and show that these insertions are absent in their parents (Figure 4\u2014figure supplement 3A). To confirm their identity, we amplified and sequenced three of the novel full-length ETn insertions. Two of these elements (Genbank accession: MH449667-68) resembled typical ETnII elements with identical 5\u2019 and 3\u2019 LTRs and target site duplications (TSD) of 4 or 6 bp, respectively. The third sequenced element (MH449669) represented a hybrid element that contains both ETnI and MusD (ETnERV) sequences. Similar insertions can be found in the B6 reference genome; however, the identified novel insertion has a 2.5 kb deletion of the 5\u2019 end of the internal region. Additionally, the 5\u2019 and 3\u2019 LTR of this element differ in one nucleotide near the start site and contain an unusually large 248 bp TSD (containing a SINE repeat) indicating that an improper integration process might have truncated this element.",
@ -618,6 +645,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Besides novel ETn insertions that were only identified in one specific animal, we also observed three ETn insertions that could be detected in several siblings but not in their parents or any of the other screened mice. This strongly indicates that these retrotransposition events occurred in the germ line of the parents from which they were passed on to some of their offspring. One of these germ line insertions was evidently passed on from the offspring to the next generation (Figure 4A). As expected, the read numbers supporting these novel germ line insertions were comparable to the read numbers that were found in the flanking regions of annotated B6 ETn insertions (Figure 4\u2014figure supplement 3B). In contrast, virtually all novel insertions that were only found in one animal were supported by significantly fewer reads (Figure 4\u2014figure supplement 3B). This indicates that these elements resulted from retrotransposition events in the developing embryo and not in the zygote or parental germ cells. Indeed, we detected different sets of insertions in various tissues from the same animal (Figure 4\u2014figure supplement 3C). Even between tail samples that were collected from the same animal at different ages, only a fraction of the new insertions were present in both samples, while technical replicates from the same genomic DNA samples showed a nearly complete overlap in insertions (Figure 4\u2014figure supplement 3D).",
@ -629,6 +657,7 @@
"$ref": "#/texts/19"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Finally, we asked whether there were more novel ETn insertions in mice lacking the Chr4-cl relative to their wild type and heterozygous littermates in our pedigree. Interestingly, only one out of the eight Chr4-cl KO mice in a pure C57BL/6 strain background and none of the eight offspring from a Chr2-cl mating carried a single novel ETn insertion (Figure 4A). When crossing into a 129Sv background for a single generation before intercrossing heterozygous mice (F1), we observed 4 out of 8 Chr4-cl KO mice that contained at least one new ETn insertion, whereas none of 3 heterozygous mice contained any insertions. After crossing to the 129Sv background for a second generation (F2), we determined the number of novel ETn insertions in the offspring of one KO/WT x KO and two KO/WT x KO/WT matings, excluding all samples that were not derived from juvenile tail tissue. Only in the offspring of the KO/WT x KO mating, we observed a statistically significant higher average number of ETn insertions in KO vs. KO/WT animals (7.3 vs. 29.6, p=0.045, Figure 4B). Other than that, only a non-significant trend towards greater average numbers of ETn insertions in KO (11 vs. 27.8, p=0.192, Figure 4B) was apparent in one of the WT/KO x KO/WT matings whereas no difference in ETn insertion numbers between WT and KO mice could be observed in the second mating WT/KO x KO/WT (26 vs. 31, p=0.668, Figure 4B). When comparing all KO with all WT and WT/KO mice from these three matings, a trend towards more ETn insertions in KO remained but was not supported by strong significance (26 vs. 13, p=0.057, Figure 4B). Altogether, we observed a high variability in the number of new ETn insertions in both KO and WT but our data suggest that the Chr4-cl KRAB-ZFPs may have a modest effect on ETn retrotransposition rates in some mouse strains but other genetic and epigenetic effects clearly also play an important role.",
@ -647,6 +676,7 @@
"$ref": "#/texts/28"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Discussion",
@ -659,6 +689,7 @@
"$ref": "#/texts/26"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "C2H2 zinc finger proteins, about half of which contain a KRAB repressor domain, represent the largest DNA-binding protein family in mammals. Nevertheless, most of these factors have not been investigated using loss-of-function studies. The most comprehensive characterization of human KRAB-ZFPs revealed a strong preference to bind TEs (Imbeault et al., 2017;\u00a0Najafabadi et al., 2015) yet their function remains unknown. In humans, very few TEs are capable of retrotransposition yet many of them, often tens of million years old, are bound by KRAB-ZFPs. While this suggests that human KRAB-ZFPs mainly serve to control TE-borne enhancers and may have potentially transcription-independent functions, we were interested in the biological significance of KRAB-ZFPs in restricting potentially active TEs. The mouse is an ideal model for such studies since the mouse genome contains several active TE families, including IAP, ETn and L1 elements. We found that many of the young KRAB-ZFPs present in the genomic clusters of KRAB-ZFPs on chromosomes 2 and 4, which are highly expressed in a restricted pattern in ES cells, bound redundantly to these three active TE families. In several cases, KRAB-ZFPs bound to functionally constrained sequence elements we and others have demonstrated to be necessary for retrotransposition, including PBS and viral packaging signals. Targeting such sequences may help the host defense system keep pace with rapidly evolving mouse transposons. This provides strong evidence that many young KRAB-ZFPs are indeed expanding in response to TE activity. But do these young KRAB-ZFP genes limit the mobilization of TEs? Despite the large number of polymorphic ETn elements in mouse strains (Nell\u00e5ker et al., 2012) and several reports of phenotype-causing novel ETn germ line insertions, no new ETn insertions were reported in recent screens of C57BL/6 mouse genomes (Richardson et al., 2017; Gagnier et al., 2019), indicating that the overall rate of ETn germ line mobilization in inbred mice is rather low. We have demonstrated that Chr4-cl KRAB-ZFPs control ETn/ETnERV expression in ES cells, but this does not lead to widespread ETn mobility in viable C57BL/6 mice. In contrast, we found numerous novel, including several germ line, ETn insertions in both WT and Chr4-cl KO mice in a C57BL/6 129Sv mixed genetic background, with generally more insertions in KO mice and in mice with more 129Sv DNA. This is consistent with a report detecting ETn insertions in FVB.129 mice (Schauer et al., 2018). Notably, there was a large variation in the number of new insertions in these mice, possibly caused by hyperactive polymorphic ETn insertions that varied from individual to individual, epigenetic variation at ETn insertions between individuals and/or the general stochastic nature of ETn mobilization. Furthermore, recent reports have suggested that KRAB-ZFP gene content is distinct in different strains of laboratory mice (Lilue et al., 2018; Treger et al., 2019), and reduced KRAB-ZFP gene content could contribute to increased activity in individual mice. Although we have yet to find obvious phenotypes in the mice carrying new insertions, novel ETn germ line insertions have been shown to cause phenotypes from short tails (Lugani et al., 2013; Semba et al., 2013; Vlangos et al., 2013) to limb malformation (Kano et al., 2007) and severe morphogenetic defects including polypodia (Lehoczky et al., 2013) depending upon their insertion site.",
@ -670,6 +701,7 @@
"$ref": "#/texts/26"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Despite a lack of widespread ETn activation in Chr4-cl KO mice, it still remains to be determined whether other TEs, like L1, IAP or other LTR retrotransposons are activated in any of the KRAB-ZFP cluster KO mice, which will require the development of additional capture-seq based assays. Notably, two of the heterozygous matings from Chr2-cl KO mice failed to produce viable knockout offspring, which could indicate a TE-reactivation phenotype. It may also be necessary to generate compound homozygous mutants of distinct KRAB-ZFP clusters to eliminate redundancy before TEs become unleashed. The KRAB-ZFP cluster knockouts produced here will be useful reagents to test such hypotheses. In sum, our data supports that a major driver of KRAB-ZFP gene expansion in mice is recent retrotransposon insertions, and that redundancy within the KRAB-ZFP gene family and with other TE restriction pathways provides protection against widespread TE mobility, explaining the non-essential function of the majority of KRAB-ZFP genes.",
@ -709,6 +741,7 @@
"$ref": "#/texts/47"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Materials and methods",
@ -725,6 +758,7 @@
"$ref": "#/texts/31"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Cell lines and transgenic mice",
@ -737,6 +771,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Mouse ES cells and F9 EC cells were cultivated as described previously (Wolf et al., 2015b) unless stated otherwise. Chr4-cl KO ES cells originate from B6;129\u2010 Gt(ROSA)26Sortm1(cre/ERT)Nat/J mice (Jackson lab), all other KRAB-ZFP cluster KO ES cell lines originate from JM8A3.N1 C57BL/6N-Atm1Brd ES cells (KOMP Repository). Chr2-cl KO and WT ES cells were initially grown in serum-containing media (Wolf et al., 2015b) but changed to 2i media (De Iaco et al., 2017) for several weeks before analysis. To generate Chr4-cl and Chr2-cl KO mice, the cluster deletions were repeated in B6 ES (KOMP repository) or R1 (Nagy lab) ES cells, respectively, and heterozygous clones were injected into B6 albino blastocysts. Chr2-cl KO mice were therefore kept on a mixed B6/Svx129/Sv-CP strain background while Chr4-cl KO mice were initially derived on a pure C57BL/6 background. For capture-seq screens, Chr4-cl KO mice were crossed with 129 \u00d7 1/SvJ mice (Jackson lab) to produce the founder mice for Chr4-cl KO and WT (B6/129 F1) offspring. Chr4-cl KO/WT (B6/129 F1) were also crossed with 129 \u00d7 1/SvJ mice to get Chr4-cl KO/WT (B6/129 F1) mice, which were intercrossed to give rise to the parents of Chr4-cl KO/KO and KO/WT (B6/129 F2) offspring.",
@ -752,6 +787,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Generation of KRAB-ZFP expressing cell lines",
@ -764,6 +800,7 @@
"$ref": "#/texts/32"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "KRAB-ZFP ORFs were PCR-amplified from cDNA or synthesized with codon-optimization (Supplementary file 1), and stably expressed with 3XFLAG or 3XHA tags in F9 EC or ES cells using Sleeping beauty transposon-based (Wolf et al., 2015b) or lentiviral expression vectors (Imbeault et al., 2017; Supplementary file 1). Cells were selected with puromycin (1 \u00b5g/ml) and resistant clones were pooled and further expanded for ChIP-seq.",
@ -779,6 +816,7 @@
"$ref": "#/texts/35"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CRISPR/Cas9 mediated deletion of KRAB-ZFP clusters and an MMETn insertion",
@ -791,6 +829,7 @@
"$ref": "#/texts/34"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "All gRNAs were expressed from the pX330-U6-Chimeric_BB-CBh-hSpCas9 vector (RRID:Addgene_42230) and nucleofected into 106 ES cells using Amaxa nucleofection in the following amounts: 5 \u00b5g of each pX330-gRNA plasmid, 1 \u00b5g pPGK-puro and 500 pmoles single-stranded repair oligos (Supplementary file 3). One day after nucleofection, cells were kept under puromycin selection (1 \u00b5g/ml) for 24 hr. Individual KO and WT clones were picked 7\u20138 days after nucleofection and expanded for PCR genotyping (Supplementary file 3).",
@ -809,6 +848,7 @@
"$ref": "#/texts/38"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ChIP-seq analysis",
@ -821,6 +861,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "For ChIP-seq analysis of KRAB-ZFP expressing cells, 5\u201310 \u00d7 107 cells were crosslinked and immunoprecipitated with anti-FLAG (Sigma-Aldrich Cat# F1804, RRID:AB_262044) or anti-HA (Abcam Cat# ab9110, RRID:AB_307019 or Covance Cat# MMS-101P-200, RRID:AB_10064068) antibody using one of two previously described protocols (O'Geen et al., 2010; Imbeault et al., 2017) as indicated in Supplementary file 1. H3K9me3 distribution in Chr4-cl, Chr10-cl, Chr13.1-cl and Chr13.2-cl KO ES cells was determined by native ChIP-seq with anti-H3K9me3 serum (Active Motif Cat# 39161, RRID:AB_2532132) as described previously (Karimi et al., 2011). In Chr2-cl KO ES cells, H3K9me3 and KAP1 ChIP-seq was performed as previously described (Ecco et al., 2016). In Chr4-cl KO and WT ES cells KAP1 binding was determined by endogenous tagging of KAP1 with C-terminal GFP (Supplementary file 3), followed by FACS to enrich for GFP-positive cells and ChIP with anti-GFP (Thermo Fisher Scientific Cat# A-11122, RRID:AB_221569) using a previously described protocol (O'Geen et al., 2010). For ChIP-seq analysis of active histone marks, cross-linked chromatin from ES cells or testis (from two-week old mice) was immunoprecipitated with antibodies against H3K4me3 (Abcam Cat# ab8580, RRID:AB_306649), H3K4me1 (Abcam Cat# ab8895, RRID:AB_306847) and H3K27ac (Abcam Cat# ab4729, RRID:AB_2118291) following the protocol developed by O'Geen et al., 2010 or Khil et al., 2012 respectively.",
@ -832,6 +873,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "ChIP-seq libraries were constructed and sequenced as indicated in Supplementary file 4. Reads were mapped to the mm9 genome using Bowtie (RRID:SCR_005476; settings: --best) or Bowtie2 (Langmead and Salzberg, 2012) as indicated in Supplementary file 4. Under these settings, reads that map to multiple genomic regions are assigned to the top-scored match and, if a set of equally good choices is encountered, a pseudo-random number is used to choose one location. Peaks were called using MACS14 (RRID:SCR_013291) under high stringency settings (p<1e-10, peak enrichment\u00a0>20) (Zhang et al., 2008). Peaks were called both over the Input control and a FLAG or HA control ChIP (unless otherwise stated in Supplementary file 4) and only peaks that were called in both settings were kept for further analysis. In cases when the stringency settings did not result in at least 50 peaks, the settings were changed to medium (p<1e-10, peak enrichment\u00a0>10) or low (p<1e-5, peak enrichment\u00a0>10) stringency (Supplementary file 4). For further analysis, all peaks were scaled to 200 bp regions centered around the peak summits. The overlap of the scaled peaks to each repeat element in UCSC Genome Browser (RRID:SCR_005780) were calculated by using the bedfisher function (settings: -f 0.25) from BEDTools (RRID:SCR_006646). The right-tailed p-values between pair-wise comparison of each ChIP-seq peak and repeat element were extracted, and then adjusted using the Benjamini-Hochberg approach implemented in the R function p.adjust(). Binding motifs were determined using only nonrepetitive (<10% repeat content) peaks with MEME (Bailey et al., 2009). MEME motifs were compared with in silico predicted motifs (Najafabadi et al., 2015) using Tomtom (Bailey et al., 2009) and considered as significantly overlapping with a False Discovery Rate (FDR) below 0.1. To find MEME and predicted motifs in repetitive peaks, we used FIMO (Bailey et al., 2009). Differential H3K9me3 and KAP1 distribution in WT and Chr2-cl or Chr4-cl KO ES cells at TEs was determined by counting ChIP-seq reads overlapping annotated insertions of each TE group using BEDTools (MultiCovBed). Additionally, ChIP-seq reads were counted at the TE fraction that was bound by Chr2-cl or Chr4-cl KRAB-ZFPs (overlapping with 200 bp peaks). Count tables were concatenated and analyzed using DESeq2 (Love et al., 2014). The previously published ChIP-seq datasets for KAP1 (Castro-Diaz et al., 2014) and H3K9me3 (Dan et al., 2014) were re-mapped using Bowtie (--best).",
@ -847,6 +889,7 @@
"$ref": "#/texts/40"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Luciferase reporter assays",
@ -859,6 +902,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "For KRAB-ZFP repression assays, double-stranded DNA oligos containing KRAB-ZFP target sequences (Supplementary file 3) were cloned upstream of the SV40 promoter of the pGL3-Promoter vector (Promega) between the restriction sites for NheI and XhoI. 33 ng of reporter vectors were co-transfected (Lipofectamine 2000, Thermofisher) with 33 ng pRL-SV40 (Promega) for normalization and 33 ng of transient KRAB-ZFP expression vectors (in pcDNA3.1) or empty pcDNA3.1 into 293 T cells seeded one day earlier in 96-well plates. Cells were lysed 48 hr after transfection and luciferase/Renilla luciferase activity was measured using the Dual-Luciferase Reporter Assay System (Promega). To measure the transcriptional activity of the MMETn element upstream of the Cd59a gene, fragments of varying sizes (Supplementary file 3) were cloned into the promoter-less pGL3-basic vector (Promega) using NheI and NcoI sites. 70 ng of reporter vectors were cotransfected with 30 ng pRL-SV40 into feeder-depleted Chr4-cl WT and KO ES cells, seeded into a gelatinized 96-well plate 2 hr before transfection. Luciferase activity was measured 48 hr after transfection as described above.",
@ -874,6 +918,7 @@
"$ref": "#/texts/42"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "RNA-seq analysis",
@ -886,6 +931,7 @@
"$ref": "#/texts/41"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Whole RNA was purified using RNeasy columns (Qiagen) with on column DNase treatment or the High Pure RNA Isolation Kit (Roche) (Supplementary file 4). Tissues were first lysed in TRIzol reagent (ThermoFisher) and RNA was purified after the isopropanol precipitation step using RNeasy columns (Qiagen) with on column DNase treatment. Libraries were generated using the SureSelect Strand-Specific RNA Library Prep kit (Agilent) or Illumina\u2019s TruSeq RNA Library Prep Kit (with polyA selection) and sequenced as 50 or 100 bp paired-end reads on an Illumina HiSeq2500 (RRID:SCR_016383) or HiSeq3000 (RRID:SCR_016386) machine (Supplementary file 4). RNA-seq reads were mapped to the mouse genome (mm9) using Tophat (RRID:SCR_013035; settings: --I 200000 g 1) unless otherwise stated. These settings allow each mappable read to be reported once, in case the read maps to multiple locations equally well, one match is randomly chosen. For differential transposon expression, mapped reads that overlap with TEs annotated in Repeatmasker (RRID:SCR_012954) were counted using BEDTools MultiCovBed (setting: -split). Reads mapping to multiple fragments that belong to the same TE insertion (as indicated by the repeat ID) were summed up. Only transposons with a total of at least 20 (for two biological replicates) or 30 (for three biological replicates) mapped reads across WT and KO samples were considered for differential expression analysis. Transposons within the deleted KRAB-ZFP cluster were excluded from the analysis. Read count tables were used for differential expression analysis with DESeq2 (RRID:SCR_015687). For differential gene expression analysis, reads overlapping with gene exons were counted using HTSeq-count and analyzed using DESeq2. To test if KRAB-ZFP peaks are significantly enriched near up- or down-regulated genes, a binomial test was performed. Briefly, the proportion of the peaks that are located within a certain distance up- or downstream to the TSS of genes was determined using the windowBed function of BED tools. The probability p in the binomial distribution was estimated as the fraction of all genes overlapped with KRAB-ZFP peaks. Then, given n which is the number of specific groups of genes, and x which is the number of this group of genes overlapped with peaks, the R function binom.test() was used to estimate the p-value based on right-tailed Binomial test. Finally, the adjusted p-values were determined separately for LTR and LINE retrotransposon groups using the Benjamini-Hochberg approach implemented in the R function p.adjust().",
@ -901,6 +947,7 @@
"$ref": "#/texts/44"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Reduced representation bisulfite sequencing (RRBS-seq)",
@ -913,6 +960,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "For RRBS-seq analysis, Chr4-cl WT and KO ES cells were grown in either standard ES cell media containing FCS or for one week in 2i media containing vitamin C as described previously (Blaschke et al., 2013). Genomic DNA was purified from WT and Chr4-cl KO ES cells using the Quick-gDNA purification kit (Zymo Research) and bisulfite-converted with the NEXTflex Bisulfite-Seq Kit (Bio Scientific) using Msp1 digestion to fragment DNA. Libraries were sequenced as 50 bp paired-end reads on an Illumina HiSeq. The reads were processed using Trim Galore (--illumina --paired \u2013rrbs) to trim poor quality bases and adaptors. Additionally, the first 5 nt of R2 and the last 3 nt of R1 and R2 were trimmed. Reads were then mapped to the reference genome (mm9) using Bismark (Krueger and Andrews, 2011) to extract methylation calling results. The CpG methylation pattern for each covered CpG dyads (two complementary CG dinucleotides) was calculated using a custom script (Source code 1: get_CpG_ML.pl). For comparison of CpG methylation between WT and Chr4-cl KO ES cells (in serum or 2i + Vitamin C conditions) only CpG sites with at least 10-fold coverage in each sample were considered for analysis.",
@ -928,6 +976,7 @@
"$ref": "#/texts/46"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Retrotransposition assay",
@ -940,6 +989,7 @@
"$ref": "#/texts/45"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The retrotransposition vectors pCMV-MusD2, pCMV-MusD2-neoTNF and pCMV-ETnI1-neoTNF (Ribet et al., 2004) were a kind gift from Dixie Mager. To partially delete the Gm13051 binding site within pCMV-MusD2-neoTNF, the vector was cut with KpnI and re-ligated using a repair oligo, leaving a 24 bp deletion within the Gm13051 binding site. The Rex2 binding site in pCMV-ETnI1-neoTNF was deleted by cutting the vector with EcoRI and XbaI followed by re-ligation using two overlapping PCR products, leaving a 45 bp deletion while maintaining the rest of the vector unchanged (see Supplementary file 3 for primer sequences). For MusD retrotransposition assays, 5 \u00d7 104 HeLa cells (ATCC CCL-2) were transfected in a 24-well dish with 100 ng pCMV-MusD2-neoTNF or pCMV-MusD2-neoTNF (\u0394Gm13051-m) using Lipofectamine 2000. For ETn retrotransposition assays, 50 ng of pCMV-ETnI1-neoTNF or pCMV-ETnI1-neoTNF (\u0394Rex2) vectors were cotransfected with 50 ng pCMV-MusD2 to provide gag and pol proteins in trans. G418 (0.6 mg/ml) was added five days after transfection and cells were grown under selection until colonies were readily visible by eye. G418-resistant colonies were stained with Amido Black (Sigma).",
@ -955,6 +1005,7 @@
"$ref": "#/texts/48"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Capture-seq screen",
@ -967,6 +1018,7 @@
"$ref": "#/texts/47"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "To identify novel retrotransposon insertions, genomic DNA from various tissues (Supplementary file 4) was purified and used for library construction with target enrichment using the SureSelectQXT Target Enrichment kit (Agilent). Custom RNA capture probes were designed to hybridize with the 120 bp 5\u2019 ends of the 5\u2019 LTRs and the 120 bp 3\u2019 ends of the 3\u2019 LTR of about 600 intact (internal region flanked by two LTRs) MMETn/RLTRETN retrotransposons or of 140 RLTR4_MM/RLTR4 retrotransposons that were upregulated in Chr4-cl KO ES cells (Figure 4\u2014source data 2). Enriched libraries were sequenced on an Illumina HiSeq as paired-end 50 bp reads. R1 and R2 reads were mapped to the mm9 genome separately, using settings that only allow non-duplicated, uniquely mappable reads (Bowtie -m 1 --best --strata; samtools rmdup -s) and under settings that allow multimapping and duplicated reads (Bowtie --best). Of the latter, only reads that overlap (min. 50% of read) with RLTRETN, MMETn-int, ETnERV-int, ETnERV2-int or ETnERV3-int repeats (ETn) or RLTR4, RLTR4_MM-int or MuLV-int repeats (RLTR4) were kept. Only uniquely mappable reads whose paired reads were overlapping with the repeats mentioned above were used for further analysis. All ETn- and RLTR4-paired reads were then clustered (as bed files) using BEDTools (bedtools merge -i -n -d 1000) to receive a list of all potential annotated and non-annotated new ETn or RLTR4 insertion sites and all overlapping ETn- or RLTR4-paired reads were counted for each sample at each locus. Finally, all regions that were located within 1 kb of an annotated RLTRETN, MMETn-int, ETnERV-int, ETnERV2-int or ETnERV3-int repeat as well as regions overlapping with previously identified polymorphic ETn elements (Nell\u00e5ker et al., 2012) were removed. Genomic loci with at least 10 reads per million unique ETn- or RLTR4-paired reads were considered as insertion sites. To qualify for a de-novo insertion, we allowed no called insertions in any of the other screened mice at the locus and not a single read at the locus in the ancestors of the mouse. Insertions at the same locus in at least two siblings from the same offspring were considered as germ line insertions, if the insertion was absent in the parents and mice who were not direct descendants from these siblings. Full-length sequencing of new ETn insertions was done by Sanger sequencing of short PCR products in combination with Illumina sequencing of a large PCR product (Supplementary file 3), followed by de-novo assembly using the Unicycler software.",
@ -985,6 +1037,7 @@
"$ref": "#/tables/1"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Tables",
@ -997,6 +1050,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Table 1.: * Number of protein-coding KRAB-ZFP genes identified in a previously published screen (Imbeault et al., 2017) and the ChIP-seq data column indicates the number of KRAB-ZFPs for which ChIP-seq was performed in this study.",
@ -1008,6 +1062,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Key resources table: ",
@ -1053,6 +1108,7 @@
"$ref": "#/pictures/10"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Figures",
@ -1065,6 +1121,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 1.: Genome-wide binding patterns of mouse KRAB-ZFPs.\n(A) Probability heatmap of KRAB-ZFP binding to TEs. Blue color intensity (main field) corresponds to -log10 (adjusted p-value) enrichment of ChIP-seq peak overlap with TE groups (Fisher\u2019s exact test). The green/red color intensity (top panel) represents mean KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) enrichment (respectively) at peaks overlapping significantly targeted TEs (adjusted p-value<1e-5) in WT ES cells. (B) Summarized ChIP-seq signal for indicated KRAB-ZFPs and previously published KAP1 and H3K9me3 in WT ES cells across 127 intact ETn elements. (C) Heatmaps of KRAB-ZFP ChIP-seq signal at ChIP-seq peaks. For better comparison, peaks for all three KRAB-ZFPs were called with the same parameters (p<1e-10, peak enrichment\u00a0>20). The top panel shows a schematic of the arrangement of the contact amino acid composition of each zinc finger. Zinc fingers are grouped and colored according to similarity, with amino acid differences relative to the five consensus fingers highlighted in white.\nFigure 1\u2014source data 1.KRAB-ZFP expression in 40 mouse tissues and cell lines (ENCODE).Mean values of replicates are shown as log2 transcripts per million.\nFigure 1\u2014source data 2.Probability heatmap of KRAB-ZFP binding to TEs.Values corresponds to -log10 (adjusted p-value) enrichment of ChIP-seq peak overlap with TE groups (Fisher\u2019s exact test).",
@ -1076,6 +1133,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 1\u2014figure supplement 1.: ES cell-specific expression of KRAB-ZFP gene clusters.\n(A) Heatmap showing expression patterns of mouse KRAB-ZFPs in 40 mouse tissues and cell lines (ENCODE). Heatmap colors indicate gene expression levels in log2 transcripts per million (TPM). The asterisk indicates a group of 30 KRAB-ZFPs that are exclusively expressed in ES cells. (B) Physical location of the genes encoding for the 30 KRAB-ZFPs that are exclusively expressed in ES cells. (C) Phylogenetic (Maximum likelihood) tree of the KRAB domains of mouse KRAB-ZFPs. KRAB-ZFPs encoded on the gene clusters on chromosome 2 and 4 are highlighted. The scale bar at the bottom indicates amino acid substitutions per site.",
@ -1087,6 +1145,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 1\u2014figure supplement 2.: KRAB-ZFP binding motifs and their repression activity.\n(A) Comparison of computationally predicted (bottom) and experimentally determined (top) KRAB-ZFP binding motifs. Only significant pairs are shown (FDR\u00a0<\u00a00.1). (B) Luciferase reporter assays to confirm KRAB-ZFP repression of the identified target sites. Bars show the luciferase activity (normalized to Renilla luciferase) of reporter plasmids containing the indicated target sites cloned upstream of the SV40 promoter. Reporter plasmids were co-transfected into 293 T cells with a Renilla luciferase plasmid for normalization and plasmids expressing the targeting KRAB-ZFP. Normalized mean luciferase activity (from three replicates) is shown relative to luciferase activity of the reporter plasmid co-transfected with an empty pcDNA3.1 vector.",
@ -1098,6 +1157,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 1\u2014figure supplement 3.: KRAB-ZFP binding to ETn retrotransposons.\n(A) Comparison of the PBSLys1,2 sequence with Zfp961 binding motifs in nonrepetitive peaks (Nonrep) and peaks at ETn elements. (B) Retrotransposition assays of original (ETnI1-neoTNF and MusD2-neoTNF Ribet et al., 2004) and modified reporter vectors where the Rex2 or Gm13051 binding motifs where removed. Schematic of reporter vectors are displayed at the top. HeLa cells were transfected as described in the Materials and Methods section and neo-resistant colonies, indicating retrotransposition events, were selected and stained. (C) Stem-loop structure of the ETn RNA export signal, the Gm13051 motif on the corresponding DNA is marked with red circles, the part of the motif that was deleted is indicated with grey crosses (adapted from Legiewicz et al., 2010).",
@ -1109,6 +1169,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 2.: Retrotransposon reactivation in KRAB-ZFP cluster KO ES cells.\n(A) RNA-seq analysis of TE expression in five KRAB-ZFP cluster KO ES cells. Green and grey squares on top of the panel represent KRAB-ZFPs with or without ChIP-seq data, respectively, within each deleted gene cluster. Reactivated TEs that are bound by one or several KRAB-ZFPs are indicated by green squares in the panel. Significantly up- and downregulated elements (adjusted p-value<0.05) are highlighted in red and green, respectively. (B) Differential KAP1 binding and H3K9me3 enrichment at TE groups (summarized across all insertions) in Chr2-cl and Chr4-cl KO ES cells. TE groups targeted by one or several KRAB-ZFPs encoded within the deleted clusters are highlighted in blue (differential enrichment over the entire TE sequences) and red (differential enrichment at TE regions that overlap with KRAB-ZFP ChIP-seq peaks). (C) DNA methylation status of CpG sites at indicated TE groups in WT and Chr4-cl KO ES cells grown in serum containing media or in hypomethylation-inducing media (2i + Vitamin C). P-values were calculated using paired t-test.\nFigure 2\u2014source data 1.Differential H3K9me3 and KAP1 distribution in WT and KRAB-ZFP cluster KO ES cells at TE families and KRAB-ZFP bound TE insertions.Differential read counts and statistical testing were determined by DESeq2.",
@ -1120,6 +1181,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 2\u2014figure supplement 1.: Epigenetic changes at TEs and TE-borne enhancers in KRAB-ZFP cluster KO ES cells.\n(A) Differential analysis of summative (all individual insertions combined) H3K9me3 enrichment at TE groups in Chr10-cl, Chr13.1-cl and Chr13.2-cl KO ES cells.\u00a0TE groups targeted by one or several KRAB-ZFPs encoded within the deleted clusters are highlighted in orange (differential enrichment over the entire TE sequences) and red (differential enrichment at TE regions that overlap with KRAB-ZFP ChIP-seq peaks). (B) Top: Schematic view of the Cd59a/Cd59b locus with a 5\u2019 truncated ETn insertion. ChIP-seq (Input subtracted from ChIP) data for overexpressed epitope-tagged Gm13051 (a Chr4-cl KRAB-ZFP) in F9 EC cells, and re-mapped KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) in WT ES cells are shown together with RNA-seq data from Chr4-cl WT and KO ES cells (mapped using Bowtie (-a -m 1 --strata -v 2) to exclude reads that cannot be uniquely mapped). Bottom: Transcriptional activity of a 5 kb fragment with or without fragments of the ETn insertion was tested by luciferase reporter assay in Chr4-cl WT and KO ES cells.",
@ -1131,6 +1193,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 3.: TE-dependent gene activation in KRAB-ZFP cluster KO ES cells.\n(A) Differential gene expression in Chr2-cl and Chr4-cl KO ES cells. Significantly up- and downregulated genes (adjusted p-value<0.05) are highlighted in red and green, respectively, KRAB-ZFP genes within the deleted clusters are shown in blue. (B) Correlation of TEs and gene deregulation. Plots show enrichment of TE groups within 100 kb of up- and downregulated genes relative to all genes. Significantly overrepresented LTR and LINE groups (adjusted p-value<0.1) are highlighted in blue and red, respectively. (C) Schematic view of the downstream region of Chst1 where a 5\u2019 truncated ETn insertion is located. ChIP-seq (Input subtracted from ChIP) data for overexpressed epitope-tagged Gm13051 (a Chr4-cl KRAB-ZFP) in F9 EC cells, and re-mapped KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) in WT ES cells are shown together with RNA-seq data from Chr4-cl WT and KO ES cells (mapped using Bowtie (-a -m 1 --strata -v 2) to exclude reads that cannot be uniquely mapped). (D) RT-qPCR analysis of Chst1 mRNA expression in Chr4-cl WT and KO ES cells with or without the CRISPR/Cas9 deleted ETn insertion near Chst1. Values represent mean expression (normalized to Gapdh) from three biological replicates per sample (each performed in three technical replicates) in arbitrary units. Error bars represent standard deviation and asterisks indicate significance (p<0.01, Student\u2019s t-test). n.s.: not significant. (E) Mean coverage of ChIP-seq data (Input subtracted from ChIP) in Chr4-cl WT and KO ES cells over 127 full-length ETn insertions. The binding sites of the Chr4-cl KRAB-ZFPs Rex2 and Gm13051 are indicated by dashed lines.",
@ -1142,6 +1205,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 4.: ETn retrotransposition in Chr4-cl KO mice.\n(A) Pedigree of mice used for transposon insertion screening by capture-seq in mice of different strain backgrounds. The number of novel ETn insertions (only present in one animal) are indicated. For animals whose direct ancestors have not been screened, the ETn insertions are shown in parentheses since parental inheritance cannot be excluded in that case. Germ line insertions are indicated by asterisks. All DNA samples were prepared from tail tissues unless noted (-S: spleen, -E: ear, -B:Blood) (B) Statistical analysis of ETn insertion frequency in tail tissue from 30 Chr4-cl KO, KO/WT and WT mice that were derived from one Chr4-c KO x KO/WT and two Chr4-cl KO/WT x KO/WT matings. Only DNA samples that were collected from juvenile tails were considered for this analysis. P-values were calculated using one-sided Wilcoxon Rank Sum Test. In the last panel, KO, WT and KO/WT mice derived from all matings were combined for the statistical analysis.\nFigure 4\u2014source data 1.Coordinates of identified novel ETn insertions and supporting capture-seq read counts.Genomic regions indicate cluster of supporting reads.\nFigure 4\u2014source data 2.Sequences of capture-seq probes used to enrich genomic DNA for ETn and MuLV (RLTR4) insertions.",
@ -1153,6 +1217,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 4\u2014figure supplement 1.: Birth statistics of KRAB-ZFP cluster KO mice and TE reactivation in adult tissues.\n(A) Birth statistics of Chr4- and Chr2-cl mice derived from KO/WT x KO/WT matings in different strain backgrounds.\u00a0(B) RNA-seq analysis of TE expression in Chr2- (left) and Chr4-cl (right) KO tissues. TE groups with the highest reactivation phenotype in ES cells are shown separately. Significantly up- and downregulated elements (adjusted p-value<0.05) are highlighted in red and green, respectively. Experiments were performed in at least two biological replicates.",
@ -1164,6 +1229,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 4\u2014figure supplement 2.: Identification of polymorphic ETn and MuLV retrotransposon insertions in Chr4-cl KO and WT mice.\nHeatmaps show normalized capture-seq read counts in RPM (Read Per Million) for identified polymorphic ETn (A) and MuLV (B) loci in different mouse strains. Only loci with strong support for germ line ETn or MuLV insertions (at least 100 or 3000 ETn or MuLV RPM, respectively) in at least two animals are shown. Non-polymorphic insertion loci with high read counts in all screened mice were excluded for better visibility. The sample information (sample name and cell type/tissue) is annotated at the bottom, with the strain information indicated by color at the top. The color gradient indicates log10(RPM+1).",
@ -1175,6 +1241,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Figure 4\u2014figure supplement 3.: Confirmation of novel ETn insertions identified by capture-seq.\n(A) PCR validation of novel ETn insertions in genomic DNA of three littermates (IDs: T09673, T09674 and T00436) and their parents (T3913 and T3921). Primer sequences are shown in Supplementary file 3. (B) ETn capture-seq read counts (RPM) at putative novel somatic (loci identified exclusively in one single animal), novel germ line (loci identified in several littermates) insertions, and at B6 reference ETn elements. (C) Heatmap shows capture-seq read counts (RPM) of a Chr4-cl KO mouse (ID: C6733) as determined in different tissues. Each row represents a novel ETn locus that was identified in at least one tissue. The color gradient indicates log10(RPM+1). (D) Heatmap shows the capture-seq RPM in technical replicates using the same Chr4-cl KO DNA sample (rep1/rep2) or replicates with DNA samples prepared from different sections of the tail from the same mouse at different ages (tail1/tail2). Each row represents a novel ETn locus that was identified in at least one of the displayed samples. The color gradient indicates log10(RPM+1).",
@ -1190,6 +1257,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "References",
@ -1202,6 +1270,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "TL Bailey; M Boden; FA Buske; M Frith; CE Grant; L Clementi; J Ren; WW Li; WS Noble. MEME SUITE: tools for motif discovery and searching. Nucleic Acids Research (2009)",
@ -1215,6 +1284,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "C Baust; L Gagnier; GJ Baillie; MJ Harris; DM Juriloff; DL Mager. Structure and expression of mobile ETnII retroelements and their coding-competent MusD relatives in the mouse. Journal of Virology (2003)",
@ -1228,6 +1298,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "K Blaschke; KT Ebata; MM Karimi; JA Zepeda-Mart\u00ednez; P Goyal; S Mahapatra; A Tam; DJ Laird; M Hirst; A Rao; MC Lorincz; M Ramalho-Santos. Vitamin C induces Tet-dependent DNA demethylation and a blastocyst-like state in ES cells. Nature (2013)",
@ -1241,6 +1312,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "A Brodziak; E Zi\u00f3\u0142ko; M Muc-Wierzgo\u0144; E Nowakowska-Zajdel; T Kokot; K Klakla. The role of human endogenous retroviruses in the pathogenesis of autoimmune diseases. Medical Science Monitor : International Medical Journal of Experimental and Clinical Research (2012)",
@ -1254,6 +1326,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "N Castro-Diaz; G Ecco; A Coluccio; A Kapopoulou; B Yazdanpanah; M Friedli; J Duc; SM Jang; P Turelli; D Trono. Evolutionally dynamic L1 regulation in embryonic stem cells. Genes & Development (2014)",
@ -1267,6 +1340,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "EB Chuong; NC Elde; C Feschotte. Regulatory evolution of innate immunity through co-option of endogenous retroviruses. Science (2016)",
@ -1280,6 +1354,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "J Dan; Y Liu; N Liu; M Chiourea; M Okuka; T Wu; X Ye; C Mou; L Wang; L Wang; Y Yin; J Yuan; B Zuo; F Wang; Z Li; X Pan; Z Yin; L Chen; DL Keefe; S Gagos; A Xiao; L Liu. Rif1 maintains telomere length homeostasis of ESCs by mediating heterochromatin silencing. Developmental Cell (2014)",
@ -1293,6 +1368,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "A De Iaco; E Planet; A Coluccio; S Verp; J Duc; D Trono. DUX-family transcription factors regulate zygotic genome activation in placental mammals. Nature Genetics (2017)",
@ -1306,6 +1382,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "\u00d6 Deniz; L de la Rica; KCL Cheng; D Spensberger; MR Branco. SETDB1 prevents TET2-dependent activation of IAP retroelements in na\u00efve embryonic stem cells. Genome Biology (2018)",
@ -1319,6 +1396,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "M Dewannieux; T Heidmann. Endogenous retroviruses: acquisition, amplification and taming of genome invaders. Current Opinion in Virology (2013)",
@ -1332,6 +1410,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "G Ecco; M Cassano; A Kauzlaric; J Duc; A Coluccio; S Offner; M Imbeault; HM Rowe; P Turelli; D Trono. Transposable elements and their KRAB-ZFP controllers regulate gene expression in adult tissues. Developmental Cell (2016)",
@ -1345,6 +1424,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "G Ecco; M Imbeault; D Trono. KRAB zinc finger proteins. Development (2017)",
@ -1358,6 +1438,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "JA Frank; C Feschotte. Co-option of endogenous viral sequences for host cell function. Current Opinion in Virology (2017)",
@ -1371,6 +1452,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "L Gagnier; VP Belancio; DL Mager. Mouse germ line mutations due to retrotransposon insertions. Mobile DNA (2019)",
@ -1384,6 +1466,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "AC Groner; S Meylan; A Ciuffi; N Zangger; G Ambrosini; N D\u00e9nervaud; P Bucher; D Trono. KRAB-zinc finger proteins and KAP1 can mediate long-range transcriptional repression through heterochromatin spreading. PLOS Genetics (2010)",
@ -1397,6 +1480,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "DC Hancks; HH Kazazian. Roles for retrotransposon insertions in human disease. Mobile DNA (2016)",
@ -1410,6 +1494,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "M Imbeault; PY Helleboid; D Trono. KRAB zinc-finger proteins contribute to the evolution of gene regulatory networks. Nature (2017)",
@ -1423,6 +1508,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "FM Jacobs; D Greenberg; N Nguyen; M Haeussler; AD Ewing; S Katzman; B Paten; SR Salama; D Haussler. An evolutionary arms race between KRAB zinc-finger genes ZNF91/93 and SVA/L1 retrotransposons. Nature (2014)",
@ -1436,6 +1522,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "H Kano; H Kurahashi; T Toda. Genetically regulated epigenetic transcriptional activation of retrotransposon insertion confers mouse dactylaplasia phenotype. PNAS (2007)",
@ -1449,6 +1536,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "MM Karimi; P Goyal; IA Maksakova; M Bilenky; D Leung; JX Tang; Y Shinkai; DL Mager; S Jones; M Hirst; MC Lorincz. DNA methylation and SETDB1/H3K9me3 regulate predominantly distinct sets of genes, retroelements, and chimeric transcripts in mESCs. Cell Stem Cell (2011)",
@ -1462,6 +1550,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "A Kauzlaric; G Ecco; M Cassano; J Duc; M Imbeault; D Trono. The mouse genome displays highly dynamic populations of KRAB-zinc finger protein genes and related genetic units. PLOS ONE (2017)",
@ -1475,6 +1564,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "PP Khil; F Smagulova; KM Brick; RD Camerini-Otero; GV Petukhova. Sensitive mapping of recombination hotspots using sequencing-based detection of ssDNA. Genome Research (2012)",
@ -1488,6 +1578,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "F Krueger; SR Andrews. Bismark: a flexible aligner and methylation caller for Bisulfite-Seq applications. Bioinformatics (2011)",
@ -1501,6 +1592,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "B Langmead; SL Salzberg. Fast gapped-read alignment with bowtie 2. Nature Methods (2012)",
@ -1514,6 +1606,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "M Legiewicz; AS Zolotukhin; GR Pilkington; KJ Purzycka; M Mitchell; H Uranishi; J Bear; GN Pavlakis; SF Le Grice; BK Felber. The RNA transport element of the murine musD retrotransposon requires long-range intramolecular interactions for function. Journal of Biological Chemistry (2010)",
@ -1527,6 +1620,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "JA Lehoczky; PE Thomas; KM Patrie; KM Owens; LM Villarreal; K Galbraith; J Washburn; CN Johnson; B Gavino; AD Borowsky; KJ Millen; P Wakenight; W Law; ML Van Keuren; G Gavrilina; ED Hughes; TL Saunders; L Brihn; JH Nadeau; JW Innis. A novel intergenic ETnII-\u03b2 insertion mutation causes multiple malformations in Polypodia mice. PLOS Genetics (2013)",
@ -1540,6 +1634,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "D Leung; T Du; U Wagner; W Xie; AY Lee; P Goyal; Y Li; KE Szulwach; P Jin; MC Lorincz; B Ren. Regulation of DNA methylation turnover at LTR retrotransposons and imprinted loci by the histone methyltransferase Setdb1. PNAS (2014)",
@ -1553,6 +1648,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "J Lilue; AG Doran; IT Fiddes; M Abrudan; J Armstrong; R Bennett; W Chow; J Collins; S Collins; A Czechanski; P Danecek; M Diekhans; DD Dolle; M Dunn; R Durbin; D Earl; A Ferguson-Smith; P Flicek; J Flint; A Frankish; B Fu; M Gerstein; J Gilbert; L Goodstadt; J Harrow; K Howe; X Ibarra-Soria; M Kolmogorov; CJ Lelliott; DW Logan; J Loveland; CE Mathews; R Mott; P Muir; S Nachtweide; FCP Navarro; DT Odom; N Park; S Pelan; SK Pham; M Quail; L Reinholdt; L Romoth; L Shirley; C Sisu; M Sjoberg-Herrera; M Stanke; C Steward; M Thomas; G Threadgold; D Thybert; J Torrance; K Wong; J Wood; B Yalcin; F Yang; DJ Adams; B Paten; TM Keane. Sixteen diverse laboratory mouse reference genomes define strain-specific haplotypes and novel functional loci. Nature Genetics (2018)",
@ -1566,6 +1662,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "S Liu; J Brind'Amour; MM Karimi; K Shirane; A Bogutz; L Lefebvre; H Sasaki; Y Shinkai; MC Lorincz. Setdb1 is required for germline development and silencing of H3K9me3-marked endogenous retroviruses in primordial germ cells. Genes & Development (2014)",
@ -1579,6 +1676,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "MI Love; W Huber; S Anders. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biology (2014)",
@ -1592,6 +1690,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "F Lugani; R Arora; N Papeta; A Patel; Z Zheng; R Sterken; RA Singer; G Caridi; C Mendelsohn; L Sussel; VE Papaioannou; AG Gharavi. A retrotransposon insertion in the 5' regulatory domain of Ptf1a results in ectopic gene expression and multiple congenital defects in Danforth's short tail mouse. PLOS Genetics (2013)",
@ -1605,6 +1704,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "TS Macfarlan; WD Gifford; S Driscoll; K Lettieri; HM Rowe; D Bonanomi; A Firth; O Singer; D Trono; SL Pfaff. Embryonic stem cell potency fluctuates with endogenous retrovirus activity. Nature (2012)",
@ -1618,6 +1718,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "IA Maksakova; MT Romanish; L Gagnier; CA Dunn; LN van de Lagemaat; DL Mager. Retroviral elements and their hosts: insertional mutagenesis in the mouse germ line. PLOS Genetics (2006)",
@ -1631,6 +1732,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "T Matsui; D Leung; H Miyashita; IA Maksakova; H Miyachi; H Kimura; M Tachibana; MC Lorincz; Y Shinkai. Proviral silencing in embryonic stem cells requires the histone methyltransferase ESET. Nature (2010)",
@ -1644,6 +1746,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "HS Najafabadi; S Mnaimneh; FW Schmitges; M Garton; KN Lam; A Yang; M Albu; MT Weirauch; E Radovani; PM Kim; J Greenblatt; BJ Frey; TR Hughes. C2H2 zinc finger proteins greatly expand the human regulatory lexicon. Nature Biotechnology (2015)",
@ -1657,6 +1760,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "C Nell\u00e5ker; TM Keane; B Yalcin; K Wong; A Agam; TG Belgard; J Flint; DJ Adams; WN Frankel; CP Ponting. The genomic landscape shaped by selection on transposable elements across 18 mouse strains. Genome Biology (2012)",
@ -1670,6 +1774,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "H O'Geen; S Frietze; PJ Farnham. Using ChIP-seq technology to identify targets of zinc finger transcription factors. Methods in Molecular Biology (2010)",
@ -1683,6 +1788,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "A Patel; P Yang; M Tinkham; M Pradhan; M-A Sun; Y Wang; D Hoang; G Wolf; JR Horton; X Zhang; T Macfarlan; X Cheng. DNA conformation induces adaptable binding by tandem zinc finger proteins. Cell (2018)",
@ -1696,6 +1802,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "D Ribet; M Dewannieux; T Heidmann. An active murine transposon family pair: retrotransposition of \"master\" MusD copies and ETn trans-mobilization. Genome Research (2004)",
@ -1709,6 +1816,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "SR Richardson; P Gerdes; DJ Gerhardt; FJ Sanchez-Luque; GO Bodea; M Mu\u00f1oz-Lopez; JS Jesuadian; MHC Kempen; PE Carreira; JA Jeddeloh; JL Garcia-Perez; HH Kazazian; AD Ewing; GJ Faulkner. Heritable L1 retrotransposition in the mouse primordial germline and early embryo. Genome Research (2017)",
@ -1722,6 +1830,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "HM Rowe; J Jakobsson; D Mesnard; J Rougemont; S Reynard; T Aktas; PV Maillard; H Layard-Liesching; S Verp; J Marquis; F Spitz; DB Constam; D Trono. KAP1 controls endogenous retroviruses in embryonic stem cells. Nature (2010)",
@ -1735,6 +1844,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "HM Rowe; A Kapopoulou; A Corsinotti; L Fasching; TS Macfarlan; Y Tarabay; S Viville; J Jakobsson; SL Pfaff; D Trono. TRIM28 repression of retrotransposon-based enhancers is necessary to preserve transcriptional dynamics in embryonic stem cells. Genome Research (2013)",
@ -1748,6 +1858,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "SN Schauer; PE Carreira; R Shukla; DJ Gerhardt; P Gerdes; FJ Sanchez-Luque; P Nicoli; M Kindlova; S Ghisletti; AD Santos; D Rapoud; D Samuel; J Faivre; AD Ewing; SR Richardson; GJ Faulkner. L1 retrotransposition is a common feature of mammalian hepatocarcinogenesis. Genome Research (2018)",
@ -1761,6 +1872,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "DC Schultz; K Ayyanathan; D Negorev; GG Maul; FJ Rauscher. SETDB1: a novel KAP-1-associated histone H3, lysine 9-specific methyltransferase that contributes to HP1-mediated silencing of euchromatic genes by KRAB zinc-finger proteins. Genes & Development (2002)",
@ -1774,6 +1886,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "K Semba; K Araki; K Matsumoto; H Suda; T Ando; A Sei; H Mizuta; K Takagi; M Nakahara; M Muta; G Yamada; N Nakagata; A Iida; S Ikegawa; Y Nakamura; M Araki; K Abe; K Yamamura. Ectopic expression of Ptf1a induces spinal defects, urogenital defects, and anorectal malformations in Danforth's short tail mice. PLOS Genetics (2013)",
@ -1787,6 +1900,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "SP Sripathy; J Stevens; DC Schultz. The KAP1 corepressor functions to coordinate the assembly of de novo HP1-demarcated microenvironments of heterochromatin required for KRAB zinc finger protein-mediated transcriptional repression. Molecular and Cellular Biology (2006)",
@ -1800,6 +1914,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "JH Thomas; S Schneider. Coevolution of retroelements and tandem zinc finger genes. Genome Research (2011)",
@ -1813,6 +1928,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "PJ Thompson; TS Macfarlan; MC Lorincz. Long terminal repeats: from parasitic elements to building blocks of the transcriptional regulatory repertoire. Molecular Cell (2016)",
@ -1826,6 +1942,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "RS Treger; SD Pope; Y Kong; M Tokuyama; M Taura; A Iwasaki. The lupus susceptibility locus Sgp3 encodes the suppressor of endogenous retrovirus expression SNERV. Immunity (2019)",
@ -1839,6 +1956,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "CN Vlangos; AN Siuniak; D Robinson; AM Chinnaiyan; RH Lyons; JD Cavalcoli; CE Keegan. Next-generation sequencing identifies the Danforth's short tail mouse mutation as a retrotransposon insertion affecting Ptf1a expression. PLOS Genetics (2013)",
@ -1852,6 +1970,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "J Wang; G Xie; M Singh; AT Ghanbarian; T Rask\u00f3; A Szvetnik; H Cai; D Besser; A Prigione; NV Fuchs; GG Schumann; W Chen; MC Lorincz; Z Ivics; LD Hurst; Z Izsv\u00e1k. Primate-specific endogenous retrovirus-driven transcription defines naive-like stem cells. Nature (2014)",
@ -1865,6 +1984,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "D Wolf; K Hug; SP Goff. TRIM28 mediates primer binding site-targeted silencing of Lys1,2 tRNA-utilizing retroviruses in embryonic cells. PNAS (2008)",
@ -1878,6 +1998,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "G Wolf; D Greenberg; TS Macfarlan. Spotting the enemy within: targeted silencing of foreign DNA in mammalian genomes by the Kr\u00fcppel-associated box zinc finger protein family. Mobile DNA (2015a)",
@ -1891,6 +2012,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "G Wolf; P Yang; AC F\u00fcchtbauer; EM F\u00fcchtbauer; AM Silva; C Park; W Wu; AL Nielsen; FS Pedersen; TS Macfarlan. The KRAB zinc finger protein ZFP809 is required to initiate epigenetic silencing of endogenous retroviruses. Genes & Development (2015b)",
@ -1904,6 +2026,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "M Yamauchi; B Freitag; C Khan; B Berwin; E Barklis. Stem cell factor binding to retrovirus primer binding site silencers. Journal of Virology (1995)",
@ -1917,6 +2040,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Y Zhang; T Liu; CA Meyer; J Eeckhoute; DS Johnson; BE Bernstein; C Nusbaum; RM Myers; M Brown; W Li; XS Liu. Model-based analysis of ChIP-Seq (MACS). Genome Biology (2008)",
@ -1932,6 +2056,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1949,6 +2074,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1966,6 +2092,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1983,6 +2110,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2000,6 +2128,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2017,6 +2146,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2034,6 +2164,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2051,6 +2182,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2068,6 +2200,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2085,6 +2218,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2102,6 +2236,7 @@
"$ref": "#/texts/52"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -2121,6 +2256,7 @@
"$ref": "#/texts/49"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [
@ -3243,6 +3379,7 @@
"$ref": "#/texts/49"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [

15
tests/data/groundtruth/docling_v2/example_01.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_01",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -37,6 +39,7 @@
"$ref": "#/texts/5"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -53,6 +56,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
}
@ -71,6 +75,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Introduction",
@ -82,6 +87,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is the first paragraph of the introduction.",
@ -106,6 +112,7 @@
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Background",
@ -118,6 +125,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some background information here.",
@ -129,6 +137,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in unordered list",
@ -142,6 +151,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in unordered list",
@ -155,6 +165,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list",
@ -168,6 +179,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list",
@ -183,6 +195,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],

14
tests/data/groundtruth/docling_v2/example_02.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_02",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -37,6 +39,7 @@
"$ref": "#/texts/5"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -53,6 +56,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
}
@ -71,6 +75,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Introduction",
@ -82,6 +87,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is the first paragraph of the introduction.",
@ -103,6 +109,7 @@
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Background",
@ -115,6 +122,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some background information here.",
@ -126,6 +134,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in unordered list",
@ -139,6 +148,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in unordered list",
@ -152,6 +162,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list",
@ -165,6 +176,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list",

23
tests/data/groundtruth/docling_v2/example_03.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_03",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -37,6 +39,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -53,6 +56,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -69,6 +73,7 @@
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
},
@ -85,6 +90,7 @@
"$ref": "#/texts/11"
}
],
"content_layer": "body",
"name": "ordered list",
"label": "ordered_list"
}
@ -106,6 +112,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Example Document",
@ -121,6 +128,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Introduction",
@ -133,6 +141,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This is the first paragraph of the introduction.",
@ -154,6 +163,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Background",
@ -166,6 +176,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some background information here.",
@ -181,6 +192,7 @@
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in unordered list",
@ -194,6 +206,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested item 1",
@ -207,6 +220,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested item 2",
@ -220,6 +234,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in unordered list",
@ -237,6 +252,7 @@
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "First item in ordered list",
@ -250,6 +266,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested ordered item 1",
@ -263,6 +280,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Nested ordered item 2",
@ -276,6 +294,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Second item in ordered list",
@ -293,6 +312,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Data Table",
@ -308,6 +328,7 @@
"$ref": "#/texts/13"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

6
tests/data/groundtruth/docling_v2/example_04.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_04",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -35,6 +37,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Data Table with Rowspan and Colspan",
@ -49,6 +52,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

6
tests/data/groundtruth/docling_v2/example_05.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "example_05",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -35,6 +37,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Omitted html and body tags",
@ -49,6 +52,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

188
tests/data/groundtruth/docling_v2/ipa20180000016.json
View File

File diff suppressed because it is too large Load Diff

82
tests/data/groundtruth/docling_v2/ipa20200022300.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "ipa20200022300.xml",
"origin": {
"mimetype": "application/xml",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -53,6 +55,7 @@
"$ref": "#/texts/58"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "SYSTEM FOR CONTROLLING THE OPERATION OF AN ACTUATOR MOUNTED ON A SEED PLANTING IMPLEMENT",
@ -68,6 +71,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ABSTRACT",
@ -80,6 +84,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In one aspect, a system for controlling an operation of an actuator mounted on a seed planting implement may include an actuator configured to adjust a position of a row unit of the seed planting implement relative to a toolbar of the seed planting implement. The system may also include a flow restrictor fluidly coupled to a fluid chamber of the actuator, with the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the fluid chamber in a manner that provides damping to the row unit. Furthermore, the system may include a valve fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the fluid chamber to flow through the flow restrictor and the fluid entering the fluid chamber to bypass the flow restrictor.",
@ -95,6 +100,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "FIELD",
@ -107,6 +113,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present disclosure generally relates to seed planting implements and, more particularly, to systems for controlling the operation of an actuator mounted on a seed planting implement in a manner that provides damping to one or more components of the seed planting implement.",
@ -128,6 +135,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BACKGROUND",
@ -140,6 +148,7 @@
"$ref": "#/texts/5"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Modern farming practices strive to increase yields of agricultural fields. In this respect, seed planting implements are towed behind a tractor or other work vehicle to deposit seeds in a field. For example, seed planting implements typically include one or more ground engaging tools or openers that form a furrow or trench in the soil. One or more dispensing devices of the seed planting implement may, in turn, deposit seeds into the furrow(s). After deposition of the seeds, a packer wheel may pack the soil on top of the deposited seeds.",
@ -151,6 +160,7 @@
"$ref": "#/texts/5"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In certain instances, the packer wheel may also control the penetration depth of the furrow. In this regard, the position of the packer wheel may be moved vertically relative to the associated opener(s) to adjust the depth of the furrow. Additionally, the seed planting implement includes an actuator configured to exert a downward force on the opener(s) to ensure that the opener(s) is able to penetrate the soil to the depth set by the packer wheel. However, the seed planting implement may bounce or chatter when traveling at high speeds and/or when the opener(s) encounters hard or compacted soil. As such, operators generally operate the seed planting implement with the actuator exerting more downward force on the opener(s) than is necessary in order to prevent such bouncing or chatter. Operation of the seed planting implement with excessive down pressure applied to the opener(s), however, reduces the overall stability of the seed planting implement.",
@ -162,6 +172,7 @@
"$ref": "#/texts/5"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Accordingly, an improved system for controlling the operation of an actuator mounted on s seed planting implement to enhance the overall operation of the implement would be welcomed in the technology.",
@ -189,6 +200,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BRIEF DESCRIPTION",
@ -201,6 +213,7 @@
"$ref": "#/texts/9"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Aspects and advantages of the technology will be set forth in part in the following description, or may be obvious from the description, or may be learned through practice of the technology.",
@ -212,6 +225,7 @@
"$ref": "#/texts/9"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In one aspect, the present subject matter is directed to a system for controlling an operation of an actuator mounted on a seed planting implement. The system may include a toolbar and a row unit adjustably mounted on the toolbar. The system may also include a fluid-driven actuator configured to adjust a position of the row unit relative to the toolbar, with the fluid-driven actuator defining first and second fluid chambers. Furthermore, the system may include a flow restrictor fluidly coupled to the first fluid chamber, with the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the first fluid chamber in a manner that provides viscous damping to the row unit. Additionally, the system may include a valve fluidly coupled to the first fluid chamber. The valve may further be fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the first fluid chamber to flow through the flow restrictor and the fluid entering the first fluid chamber to bypass the flow restrictor.",
@ -223,6 +237,7 @@
"$ref": "#/texts/9"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In another aspect, the present subject matter is directed to a seed planting implement including a toolbar and a plurality of row units adjustably coupled to the toolbar. Each row unit may include a ground engaging tool configured to form a furrow in the soil. The seed planting implement may also include plurality of fluid-driven actuators, with each fluid-driven actuator being coupled between the toolbar and a corresponding row unit of the plurality of row units. As such, each fluid-driven actuator may be configured to adjust a position of the corresponding row unit relative to the toolbar. Moreover, each fluid-driven actuator may define first and second fluid chambers. Furthermore, the seed planting implement may include a flow restrictor fluidly coupled to the first fluid chamber of a first fluid-driven actuator of the plurality of fluid-driven actuators. The flow restrictor may be configured to reduce a rate at which fluid is permitted to exit the first fluid chamber of the first fluid-driven actuator in a manner that provides viscous damping to the corresponding row unit. Additionally, the seed planting implement may include a valve fluidly coupled to the first fluid chamber of the first fluid-driven actuator. The valve further may be fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the first fluid chamber to flow through the flow restrictor and the fluid entering the first fluid chamber to bypass the flow restrictor.",
@ -234,6 +249,7 @@
"$ref": "#/texts/9"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In a further aspect, the present subject matter is directed to a system for providing damping to a row unit of a seed planting implement. The system may include a toolbar, a row unit adjustably mounted on the toolbar, and a fluid-driven actuator configured to adjust a position of the row unit relative to the toolbar. As such, the fluid-driven actuator may define a fluid chamber. The system may also include a flow restrictor fluidly coupled to the fluid chamber. The flow restrictor may define an adjustable throat configured to reduce a rate at which fluid is permitted to exit the fluid chamber. In this regard, the throat may be adjustable between a first size configured to provide a first damping rate to the row unit and a second size configured to provide a second damping rate to the row unit, with the first and second damping rates being different.",
@ -245,6 +261,7 @@
"$ref": "#/texts/9"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "These and other features, aspects and advantages of the present technology will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the technology and, together with the description, serve to explain the principles of the technology.",
@ -290,6 +307,7 @@
"$ref": "#/texts/26"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BRIEF DESCRIPTION OF THE DRAWINGS",
@ -302,6 +320,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A full and enabling disclosure of the present technology, including the best mode thereof, directed to one of ordinary skill in the art, is set forth in the specification, which makes reference to the appended figures, in which:",
@ -313,6 +332,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 illustrates a perspective view of one embodiment of a seed planting implement in accordance with aspects of the present subject matter;",
@ -324,6 +344,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 2 illustrates a side view of one embodiment of a row unit suitable for use with a seed planting implement in accordance with aspects of the present subject matter;",
@ -335,6 +356,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 3 illustrates a schematic view of one embodiment of a system for controlling the operation of an actuator mounted on a seed planting implement in accordance with aspects of the present subject matter;",
@ -346,6 +368,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 4 illustrates a cross-sectional view of one embodiment of a flow restrictor suitable for use in the system shown in FIG. 3, particularly illustrating the flow restrictor defining a throat having a fixed size in accordance with aspects of the present subject matter;",
@ -357,6 +380,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 5 illustrates a cross-sectional view of another embodiment of a flow restrictor suitable for use in the system shown in FIG. 3, particularly illustrating the flow restrictor defining a throat having an adjustable size in accordance with aspects of the present subject matter;",
@ -368,6 +392,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 6 illustrates a simplified cross-sectional view of the flow restrictor shown in FIG. 5, particularly illustrating the throat having a first size configured to provide a first damping rate in accordance with aspects of the present subject matter;",
@ -379,6 +404,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 7 illustrates a simplified cross-sectional view of the flow restrictor shown in FIG. 5, particularly illustrating the throat having a second size configured to provide a second damping rate in accordance with aspects of the present subject matter;",
@ -390,6 +416,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 8 illustrates a cross-sectional view of another embodiment of a system for controlling the operation of an actuator mounted on a seed planting implement in accordance with aspects of the present subject matter, particularly illustrating the system including a fluidly actuated check valve; and",
@ -401,6 +428,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 9 illustrates a cross-sectional view of a further embodiment of a system for controlling the operation of an actuator mounted on a seed planting implement in accordance with aspects of the present subject matter, particularly illustrating the system including an electrically actuated check valve.",
@ -412,6 +440,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Repeat use of reference characters in the present specification and drawings is intended to represent the same or analogous features or elements of the present technology.",
@ -514,6 +543,7 @@
"$ref": "#/texts/57"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "DETAILED DESCRIPTION",
@ -526,6 +556,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Reference now will be made in detail to embodiments of the invention, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the invention, not limitation of the invention. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the scope or spirit of the invention. For instance, features illustrated or described as part of one embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the present invention covers such modifications and variations as come within the scope of the appended claims and their equivalents.",
@ -537,6 +568,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In general, the present subject matter is directed to systems for controlling the operation of an actuator mounted on a seed planting implement. Specifically, the disclosed systems may be configured to control the operation of the actuator in a manner that provides damping to one or more components of the seed planting implement. For example, in several embodiments, the seed planting implement may include a toolbar and one or more row units adjustably coupled to the toolbar. One or more fluid-driven actuators of the seed planting implement may be configured to control and/or adjust the position of the row unit(s) relative to the toolbar. Furthermore, a flow restrictor may be fluidly coupled to a fluid chamber of the actuator and configured to reduce the rate at which fluid is permitted to exit the fluid chamber so as to provide viscous damping to the row unit(s). In this regard, when the row unit(s) moves relative to the toolbar (e.g., when the row unit contacts a rock or other impediment in the soil), the flow restrictor may be configured to reduce the relative speed and/or displacement of such movement, thereby damping the movement of the row unit(s) relative to the toolbar.",
@ -548,6 +580,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In one embodiment, the flow restrictor may be configured to provide a variable damping rate to the component(s) of the seed planting implement. Specifically, in such embodiment, the flow restrictor may be configured as an adjustable valve having one or more components that may be adjusted to change the size of a fluid passage or throat defined by the valve. In this regard, changing the throat size of the valve varies the rate at which the fluid may exit the fluid chamber of the actuator, thereby adjusting the damping rate provided by the disclosed system. For example, adjusting the valve so as to increase the size of the throat may allow the fluid to exit the fluid chamber more quickly, thereby reducing the damping rate of the system. Conversely, adjusting the valve so as to decrease the size of the throat may allow the fluid to exit the fluid chamber more slowly, thereby increasing the damping rate of the system.",
@ -559,6 +592,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In accordance with aspects of the present subject matter, the system may further include a check valve fluidly coupled to the fluid chamber of the actuator. Specifically, in several embodiments, the check valve may also be fluidly coupled to the flow restrictor in a parallel relationship. As such, the check valve may be configured to direct the fluid exiting the fluid chamber of the actuator (e.g., when one of the row units hits a rock) to flow through the flow restrictor, thereby reducing the relative speed and/or displacement between the row unit(s) in the toolbar. Furthermore, the check valve may be configured to permit the fluid entering the fluid chamber to bypass the flow restrictor. For example, the fluid may return to the fluid chamber as the row unit(s) returns to its initial position following contact with the rock. In this regard, allowing the returning fluid to bypass the flow restrictor may increase the rate at which the fluid flows back into the fluid chamber, thereby further increasing the damping provided by the disclosed system.",
@ -570,6 +604,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 1, a perspective view of one embodiment of a seed planting implement 10 is illustrated in accordance with aspects of the present subject matter. As shown in FIG. 1, the implement 10 may include a laterally extending toolbar or frame assembly 12 connected at its middle to a forwardly extending tow bar 14 to allow the implement 10 to be towed by a work vehicle (not shown), such as an agricultural tractor, in a direction of travel (e.g., as indicated by arrow 16). The toolbar 12 may generally be configured to support a plurality of tool frames 18. Each tool frame 18 may, in turn, be configured to support a plurality of row units 20. As will be described below, each row unit 20 may include one or more ground engaging tools configured to excavate a furrow or trench in the soil.",
@ -581,6 +616,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It should be appreciated that, for purposes of illustration, only a portion of the row units 20 of the implement 10 have been shown in FIG. 1. In general, the implement 10 may include any number of row units 20, such as six, eight, twelve, sixteen, twenty-four, thirty-two, or thirty-six row units. In addition, it should be appreciated that the lateral spacing between row units 20 may be selected based on the type of crop being planted. For example, the row units 20 may be spaced approximately thirty inches from one another for planting corn, and approximately fifteen inches from one another for planting soybeans.",
@ -592,6 +628,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It should also be appreciated that the configuration of the implement 10 described above and shown in FIG. 1 is provided only to place the present subject matter in an exemplary field of use. Thus, it should be appreciated that the present subject matter may be readily adaptable to any manner of implement configuration.",
@ -603,6 +640,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 2, a side view of one embodiment of a row unit 20 is illustrated in accordance with aspects of the present subject matter. As shown, the row unit 20 is configured as a hoe opener row unit. However, it should be appreciated that, in alternative embodiments, the row unit 20 may be configured as a disc opener row unit or any other suitable type of seed planting unit. Furthermore, it should be appreciated that, although the row unit 20 will generally be described in the context of the implement 10 shown in FIG. 1, the row unit 20 may generally be configured to be installed on any suitable seed planting implement having any suitable implement configuration.",
@ -614,6 +652,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "As shown, the row unit 20 may be adjustably coupled to one of the tool frames 18 of the implement 10 by a suitable linkage assembly 22. For example, in one embodiment, the linkage assembly 22 may include a mounting bracket 24 coupled to the tool frame 18. Furthermore, the linkage assembly 22 may include first and second linkage members 26, 28. One end of each linkage member 26, 28 may be pivotably coupled to the mounting bracket 24, while an opposed end of each linkage member 26, 28 may be pivotally coupled to a support member 30 of the row unit 20. In this regard, the linkage assembly 22 may form a four bar linkage with the support member 30 that permits relative pivotable movement between the row unit 20 and the associated tool frame 18. However, it should be appreciated that, in alternative embodiments, the row unit 20 may be adjustably coupled to the tool frame 18 or the toolbar 12 via any other suitable linkage assembly. Furthermore, it should be appreciated that, in further embodiments the linkage assembly 22 may couple the row unit 20 directly to the toolbar 12.",
@ -625,6 +664,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Furthermore, the support member 30 may be configured to support one or more components of the row unit 20. For example, in several embodiments, a ground engaging shank 32 may be mounted or otherwise supported on support member 22. As shown, the shank 32 may include an opener 34 configured to excavate a furrow or trench in the soil as the implement 10 moves in the direction of travel 12 to facilitate deposition of a flowable granular or particulate-type agricultural product, such as seed, fertilizer, and/or the like. Moreover, the row unit 20 may include a packer wheel 36 configured to roll along the soil and close the furrow after deposition of the agricultural product. In one embodiment, the packer wheel 36 may be coupled to the support member 30 by an arm 38. It should be appreciated that, in alternative embodiments, any other suitable component(s) may be supported on or otherwise coupled to the support member 30. For example, the row unit 20 may include a ground engaging disc opener (not shown) in lieu of the ground engaging shank 32.",
@ -636,6 +676,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Additionally, in several embodiments, a fluid-driven actuator 102 of the implement 10 may be configured to adjust the position of one or more components of the row unit 20 relative to the tool frame 18. For example, in one embodiment, a rod 104 of the actuator 102 may be coupled to the shank 32 (e.g., the end of the shank 32 opposed from the opener 34), while a cylinder 106 of the actuator 102 may be coupled to the mounting bracket 24. As such, the rod 104 may be configured to extend and/or retract relative to the cylinder 106 to adjust the position of the shank 32 relative to the tool frame 18, which, in turn, adjusts the force being applied to the shank 32. However, it should be appreciated that, in alternative embodiments, the rod 104 may be coupled to the mounting bracket 24, while the cylinder 106 may be coupled to the shank 32. Furthermore, it should be appreciated that, in further embodiments, the actuator 102 may be coupled to any other suitable component of the row unit 20 and/or directly to the toolbar 12.",
@ -647,6 +688,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Moreover, it should be appreciated that the configuration of the row unit 20 described above and shown in FIG. 2 is provided only to place the present subject matter in an exemplary field of use. Thus, it should be appreciated that the present subject matter may be readily adaptable to any manner of seed planting unit configuration.",
@ -658,6 +700,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 3, a schematic view of one embodiment of a system 100 for controlling the operation of an actuator mounted on a seed planting implement is illustrated in accordance with aspects of the present subject matter. In general, the system 100 will be described herein with reference to the seed planting implement 10 and the row unit 20 described above with reference to FIGS. 1 and 2. However, it should be appreciated by those of ordinary skill in the art that the disclosed system 100 may generally be utilized with seed planting implements having any other suitable implement configuration and/or seed planting units having any other suitable unit configuration.",
@ -669,6 +712,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "As shown in FIG. 3, the system 100 may include a fluid-driven actuator, such as the actuator 102 of the row unit 20 described above with reference to FIG. 2. As shown, the actuator 102 may correspond to a hydraulic actuator. Thus, in several embodiments, the actuator 102 may include a piston 108 housed within the cylinder 106. One end of the rod 104 may be coupled to the piston 108, while an opposed end of the rod 104 may extend outwardly from the cylinder 106. Additionally, the actuator 102 may include a cap-side chamber 110 and a rod-side chamber 112 defined within the cylinder 106. As is generally understood, by regulating the pressure of the fluid supplied to one or both of the cylinder chambers 110, 112, the actuation of the rod 104 may be controlled. However, it should be appreciated that, in alternative embodiments, the actuator 102 may be configured as any other suitable type of actuator, such as a pneumatic actuator. Furthermore, it should be appreciated that, in further embodiments, the system 100 may include any other suitable number of fluid-driven actuators, such as additional actuators 102 mounted on the implement 10.",
@ -680,6 +724,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Furthermore, the system 100 may include various components configured to provide fluid (e.g., hydraulic oil) to the cylinder chambers 110, 112 of the actuator 102. For example, in several embodiments, the system 100 may include a fluid reservoir 114 and first and second fluid conduits 116, 118. As shown, a first fluid conduit 116 may extend between and fluidly couple the reservoir 114 and the rod-side chamber 112 of the actuator 102. Similarly, a second fluid conduit 118 may extend between and fluidly couple the reservoir 114 and the cap-side chamber 110 of the actuator 102. Additionally, a pump 115 and a remote switch 117 or other valve(s) may be configured to control the flow of the fluid between the reservoir 114 and the cylinder chambers 110, 112 of the actuator 102. In one embodiment, the reservoir 114, the pump 115, and the remote switch 117 may be mounted on the work vehicle (not shown) configured to tow the implement 10. However, it should be appreciated that, in alternative embodiments, the reservoir 114, the pump 115, and/or the remote switch 117 may be mounted on the implement 10. Furthermore, it should be appreciated that the system 100 may include any other suit component(s) configured to control the flow of fluid between the reservoir and the actuator 102.",
@ -691,6 +736,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In several embodiments, the system 100 may also include a flow restrictor 120 that is fluidly coupled to the cap-side chamber 110. As such, the flow restrictor 120 may be provided in series with the second fluid conduit 118. As will be described below, the flow restrictor 120 may be configured to reduce the flow rate of the fluid exiting the cap-side chamber 110 in a manner that provides damping to one or more components of the implement 10. However, it should be appreciated that, in alternative embodiments, the flow restrictor 120 may be fluidly coupled to the rod-side chamber 120 such that the flow restrictor 120 is provided in series with the first fluid conduit 116.",
@ -702,6 +748,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Additionally, in several embodiments, the system 100 may include a check valve 122 that is fluidly coupled to the cap-side chamber 110 and provided in series with the second fluid conduit 118. As shown, the check valve 122 may be fluidly coupled to the flow restrictor 120 in parallel. In this regard, the check valve 122 may be provided in series with a first branch 124 of the second fluid conduit 118, while the flow restrictor 120 may be provided in series with a second branch 126 of the second fluid conduit 118. As such, the check valve 122 may be configured to allow the fluid to flow through the first branch 124 of the second fluid conduit 118 from the reservoir 114 to the cap-side chamber 110. However, the check valve 122 may be configured to occlude or prevent the fluid from flowing through the first branch 124 of the second fluid conduit 118 from the cap-side chamber 110 to the reservoir 114. In this regard, the check valve 122 directs all of the fluid exiting the cap-side chamber 110 into the flow restrictor 120. Conversely, the check valve 122 permits the fluid flowing to the cap-side chamber 110 to bypass the flow restrictor 120. As will be described below, such configuration facilitates damping of one or more components of the implement 10. However, it should be appreciated that, in alternative embodiments, the check valve 122 may be fluidly coupled to the rod-side chamber 112 in combination with the flow restrictor 120 such that the check valve 122 is provided in series with the first fluid conduit 116.",
@ -713,6 +760,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "As indicated above, the system 100 may generally be configured to provide viscous damping to one or more components of the implement 10. For example, when a ground engaging tool of the implement 10, such as the shank 32, contacts a rock or other impediment in the soil, the corresponding row unit 20 may pivot relative to the corresponding tool frame 18 and/or the toolbar 12 against the down pressure load applied to the row unit 20 by the corresponding actuator 102. In several embodiments, such movement may cause the rod 104 of the actuator 102 to retract into the cylinder 106, thereby moving the piston 108 in a manner that decreases the volume of the cap-side chamber 110. In such instances, some of the fluid present within the cap-side chamber 110 may exit and flow into the second fluid conduit 118 toward the reservoir 114. The check valve 122 may prevent the fluid exiting the cap-side chamber 110 from flowing through the first branch 124 of the second fluid conduit 118. As such, all fluid exiting the cap-side chamber 110 may be directed into the second branch 126 and through the flow restrictor 120. As indicated above, the flow restrictor 120 reduces or limits the rate at which the fluid may flow through the second fluid conduit 118 so as to reduce the rate at which the fluid may exit the cap-side chamber 110. In this regard, the speed at which and/or the amount that the rod 104 retracts into the cylinder 106 when the shank 32 contacts a soil impediment may be reduced (e.g., because of the reduced rate at which the fluid is discharged from the cap-side chamber 110), thereby damping the movement of the row unit 20 relative to the corresponding tool frame 18 and/or the toolbar 12. Furthermore, after the initial retraction of the rod 104 into the cylinder 106, the piston 108 may then move in a manner that increases the volume of the cap-side chamber 110, thereby extending the rod 104 from the cylinder 106. In such instances, fluid present within the reservoir 114 and the second fluid conduit 118 may be drawn back into the cap-side chamber 110. As indicated above, the check valve 122 may permit the fluid within the second fluid conduit 118 to bypass the flow restrictor 120 and flow unobstructed through the first branch 124, thereby maximizing the rate at which the fluid returns to the cap-side chamber 110. Increasing the rate at which the fluid returns to the cap-side chamber 110 may decrease the time that the row unit 20 is displaced relative to the tool frame 18, thereby further damping of the row unit 20 relative to the corresponding tool frame 18 and/or the toolbar 12.",
@ -724,6 +772,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 4, a cross-sectional view of one embodiment of the flow restrictor 120 is illustrated in accordance with aspects of the present subject matter. For example, in the illustrated embodiment, the flow restrictor 120 may include a restrictor body 128 coupled to the second branch 126 of the second fluid conduit 118, with the restrictor body 128, in turn, defining a fluid passage 130 extending therethrough. Furthermore, the flow restrictor 120 may include an orifice plate 132 extending inward from the restrictor body 128 into the fluid passage 130. As shown, the orifice plate 132 may define a central aperture or throat 134 extending therethrough. In general, the size (e.g., the area, diameter, etc.) of the throat 134 may be smaller than the size of the fluid passage 130 so as to reduce the flow rate of the fluid through the flow restrictor 120. It should be appreciated that, in the illustrated embodiment, the throat 134 has a fixed size such that the throat 134 provides a fixed or constant backpressure for a given fluid flow rate. In this regard, in such embodiment, a fixed or constant damping rate is provided by the system 100. However, it should be appreciated that, in alternative embodiments, the flow restrictor 120 may have any other suitable configuration that reduces the flow rate of the fluid flowing therethrough.",
@ -735,6 +784,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 5, a cross-sectional view of another embodiment of the flow restrictor 120 is illustrated in accordance with aspects of the present subject matter. As shown, the flow restrictor 120 may generally be configured the same as or similar to that described above with reference to FIG. 4. For instance, the flow restrictor 120 may define the throat 134, which is configured to reduce the flow rate of the fluid through the flow restrictor 120. However, as shown in FIG. 5, unlike the above-describe embodiment, the size (e.g., the area, diameter, etc.) of the throat 134 is adjustable. For example, in such embodiment, the flow restrictor 120 may be configured as an adjustable valve 136. As shown, the valve 136 may include a valve body 138 coupled to the second branch 126 of the second fluid conduit 118, a shaft 140 rotatably coupled to the valve body 138, a disc 142 coupled to the shaft 140, and an actuator 144 (e.g., a suitable electric motor) coupled to the shaft 140. As such, the actuator 144 may be configured to rotate the shaft 140 and the disc 142 relative to the valve body 138 (e.g., as indicated by arrow 146 in FIG. 5) to change the size of the throat 134 defined between the disc 142 and the valve body 138. Although the valve 136 is configured as a butterfly valve in FIG. 5, it should be appreciated that, in alternative embodiments, the valve 136 may be configured as any other suitable type of valve or adjustable flow restrictor. For example, in one embodiment, the valve 136 may be configured as a suitable ball valve.",
@ -746,6 +796,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In accordance with aspects of the present disclosure, by adjusting the size of the throat 134, the system 100 may be able to provide variable damping rates. In general, the size of the throat 134 may be indicative of the amount of damping provided by the system 100. For example, in several embodiments, the disc 142 may be adjustable between a first position shown in FIG. 6 and a second position shown in FIG. 7. More specifically, when the disc 142 is at the first position, the throat 134 defines a first size (e.g., as indicated by arrow 148 in FIG. 6), thereby providing a first damping rate. Conversely, when the disc 142 is at the second position, the throat 134 defines a second size (e.g., as indicated by arrow 150 in FIG. 7), thereby providing a second damping rate. As shown in FIGS. 6 and 7, the first distance 148 is larger than the second distance 150. In such instance, the system 100 provides greater damping when the throat 134 is adjusted to the first size than when the throat 134 is adjusted to the second size. It should be appreciated that, in alternative embodiments, the disc 142 may be adjustable between any other suitable positions that provide any other suitable damping rates. For example, the disc 142 may be adjustable to a plurality of different positions defined between the fully opened and fully closed positions of the valve, thereby providing for a corresponding number of different damping rates. Furthermore, it should be appreciated that the disc 142 may be continuously adjustable or adjustable between various discrete positions.",
@ -757,6 +808,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring back to FIG. 5, a controller 152 of the system 100 may be configured to electronically control the operation of one or more components of the valve 138, such as the actuator 144. In general, the controller 152 may comprise any suitable processor-based device known in the art, such as a computing device or any suitable combination of computing devices. Thus, in several embodiments, the controller 152 may include one or more processor(s) 154 and associated memory device(s) 156 configured to perform a variety of computer-implemented functions. As used herein, the term \u201cprocessor\u201d refers not only to integrated circuits referred to in the art as being included in a computer, but also refers to a controller, a microcontroller, a microcomputer, a programmable logic controller (PLC), an application specific integrated circuit, and other programmable circuits. Additionally, the memory device(s) 156 of the controller 152 may generally comprise memory element(s) including, but not limited to, a computer readable medium (e.g., random access memory (RAM)), a computer readable non-volatile medium (e.g., a flash memory), a floppy disk, a compact disc-read only memory (CD-ROM), a magneto-optical disk (MOD), a digital versatile disc (DVD) and/or other suitable memory elements. Such memory device(s) 156 may generally be configured to store suitable computer-readable instructions that, when implemented by the processor(s) 154, configure the controller 152 to perform various computer-implemented functions. In addition, the controller 152 may also include various other suitable components, such as a communications circuit or module, one or more input/output channels, a data/control bus and/or the like.",
@ -768,6 +820,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It should be appreciated that the controller 152 may correspond to an existing controller of the implement 10 or associated work vehicle (not shown) or the controller 152 may correspond to a separate processing device. For instance, in one embodiment, the controller 152 may form all or part of a separate plug-in module that may be installed within the implement 10 or associated work vehicle to allow for the disclosed system and method to be implemented without requiring additional software to be uploaded onto existing control devices of the implement 10 or associated work vehicle.",
@ -779,6 +832,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Furthermore, in one embodiment, a user interface 158 of the system 100 may be communicatively coupled to the controller 152 via a wired or wireless connection to allow feedback signals (e.g., as indicated by dashed line 160 in FIG. 5) to be transmitted from the controller 152 to the user interface 158. More specifically, the user interface 158 may be configured to receive an input from an operator of the implement 10 or the associated work vehicle, such as an input associated with a desired damping characteristic(s) to be provided by the system 100. As such, the user interface 158 may include one or more input devices (not shown), such as touchscreens, keypads, touchpads, knobs, buttons, sliders, switches, mice, microphones, and/or the like. In addition, some embodiments of the user interface 158 may include one or more one or more feedback devices (not shown), such as display screens, speakers, warning lights, and/or the like, which are configured to communicate such feedback from the controller 152 to the operator of the implement 10. However, in alternative embodiments, the user interface 158 may have any suitable configuration.",
@ -790,6 +844,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Moreover, in one embodiment, one or more sensors 162 of the system 100 may be communicatively coupled to the controller 152 via a wired or wireless connection to allow sensor data (e.g., as indicated by dashed line 164 in FIG. 5) to be transmitted from the sensor(s) 162 to the controller 152. For example, in one embodiment, the sensor(s) 162 may include a location sensor, such as a GNSS-based sensor, that is configured to detect a parameter associated with the location of the implement 10 or associated work vehicle within the field. In another embodiment, the sensor(s) 162 may include a speed sensor, such as a Hall Effect sensor, that is configured to detect a parameter associated with the speed at which the implement 10 is moved across the field. However, it should be appreciated that, in alternative embodiments, the sensor(s) 162 may include any suitable sensing device(s) configured to detect any suitable operating parameter of the implement 10 and/or the associated work vehicle.",
@ -801,6 +856,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In several embodiments, the controller 152 may be configured to control the operation of the valve 136 based on the feedback signals 160 received from the user interface 158 and/or the sensor data 164 received from the sensor(s) 162. Specifically, as shown in FIG. 5, the controller 152 may be communicatively coupled to the actuator 144 of the valve 136 via a wired or wireless connection to allow control signals (e.g., indicated by dashed lines 166 in FIG. 5) to be transmitted from the controller 152 to the actuator 144. Such control signals 166 may be configured to regulate the operation of the actuator 144 to adjust the position of the disc 142 relative to the valve body 138, such as by moving the disc 142 along the direction 146 between the first position (FIG. 6) and the second position (FIG. 7). For example, the feedback signals 116 received by the controller 152 may be indicative that the operator desires to adjust the damping provided by the system 100. Furthermore, upon receipt of the sensor data 164 (e.g., data indicative of the location and/or speed of the implement 10), the controller 152 may be configured to determine that the damping rate of the system 100 should be adjusted. In either instance, the controller 152 may be configured to transmit the control signals 166 to the actuator 144, with such control signals 166 being configured to control the operation of the actuator 144 to adjust the position of the disc 142 to provide the desired damping rate. However, it should be appreciated that, in alternative embodiments, the controller 152 may be configured to control the operation of the valve 136 based on any other suitable input(s) and/or parameter(s).",
@ -812,6 +868,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 8, a schematic view of another embodiment of the system 100 is illustrated in accordance with aspects of the present subject matter. As shown, the system 100 may generally be configured the same as or similar to that described above with reference to FIG. 3. For instance, the system 100 may include the flow restrictor 120 and the check valve 122 fluidly coupled to the cap-side chamber 110 of the actuator 102 via the second fluid conduit 118. Furthermore, the flow restrictor 120 and the check valve 122 may be fluidly coupled together in parallel. However, as shown in FIG. 8, unlike the above-describe embodiment, the check valve 122 may be configured as a pilot-operated or fluid actuated three-way valve that is fluidly coupled to the first fluid conduit 116 by a pilot conduit 168.",
@ -823,6 +880,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In general, when the row unit 20 is lifted from an operational position relative to the ground to a raised position relative to the ground, it may be desirable for fluid to exit the cap-side chamber 110 without its flow rate being limited by the flow restrictor 120. For example, permitting such fluid to bypass the flow restrictor 120 may reduce the time required to lift the row unit 20 from the operational position to the raised position. More specifically, when lifting the row unit 20 from the operational position to the raised position, a pump (not shown) may pump fluid through the first fluid conduit 116 from the reservoir 114 to the rod-side chamber 112 of the actuator 102, thereby retracting the rod 104 into the cylinder 106. This may, in turn, discharge fluid from the cap-side chamber 110 into the second fluid conduit 118. As described above, the check valve 122 may generally be configured to direct all fluid exiting the cap-side chamber 110 into the flow restrictor 120. However, in the configuration of the system 100 shown in FIG. 8, when lifting the row unit 20 to the raised position, the pilot conduit 168 supplies fluid flowing through the first fluid conduit 116 to the check valve 122. The fluid received from the pilot conduit 168 may, in turn, actuate suitable component(s) of the check valve 122 (e.g., a diaphragm(s), a spring(s), and/or the like) in a manner that causes the check valve 122 to open, thereby permitting the fluid exiting the cap-side chamber 110 to bypass the flow restrictor 120 and flow unobstructed through the check valve 122 toward the reservoir 114. Conversely, when the row unit 20 is at the operational position, the check valve 122 may be closed, thereby directing all fluid exiting the cap-side chamber 110 into the flow restrictor 120.",
@ -834,6 +892,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Referring now to FIG. 9, a schematic view of a further embodiment of the system 100 is illustrated in accordance with aspects of the present subject matter. As shown, the system 100 may generally be configured the same as or similar to that described above with reference to FIGS. 3 and 8. For instance, the system 100 may include the flow restrictor 120 and the check valve 122 fluidly coupled to the cap-side chamber 110 of the actuator 102 via the second fluid conduit 118. Furthermore, the flow restrictor 120 and the check valve 122 may be fluidly coupled together in parallel. However, as shown in FIG. 9, unlike the above-describe embodiments, the check valve 122 may be configured as an electrically actuated valve. Specifically, as shown, the controller 152 may be communicatively coupled to the check valve 122 via a wired or wireless connection to allow control signals (e.g., indicated by dashed lines 170 in FIG. 9) to be transmitted from the controller 152 to the check valve 122. In this regard, when the row unit 20 is lifted from the operational position to the raised position, the control signals 170 may be configured to instruct the check valve 122 to open in a manner that permits the fluid exiting the cap-side chamber 110 to bypass the flow restrictor 120 and flow unobstructed through the check valve 122 toward the reservoir 114. Conversely, when the row unit 20 is at the operational position, the control signals 170 may be configured to instruct the check valve 122 to close, thereby directing all fluid exiting the cap-side chamber 110 into the flow restrictor 120.",
@ -845,6 +904,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This written description uses examples to disclose the technology, including the best mode, and also to enable any person skilled in the art to practice the technology, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the technology is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they include structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal language of the claims.",
@ -914,6 +974,7 @@
"$ref": "#/texts/77"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CLAIMS",
@ -926,6 +987,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. A system for controlling an operation of an actuator mounted on a seed planting implement, the system comprising: a toolbar; a row unit adjustably mounted on the toolbar; a fluid-driven actuator configured to adjust a position of the row unit relative to the toolbar, the fluid-driven actuator defining first and second fluid chambers; a flow restrictor fluidly coupled to the first fluid chamber, the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the first fluid chamber in a manner that provides damping to the row unit; and a valve fluidly coupled to the first fluid chamber, the valve further being fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the first fluid chamber to flow through the flow restrictor and the fluid entering the first fluid chamber to bypass the flow restrictor.",
@ -937,6 +999,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. The system of claim 1, wherein, when fluid is supplied to the second fluid chamber, the valve is configured to permit fluid exiting the first fluid chamber to bypass the flow restrictor.",
@ -948,6 +1011,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. The system of claim 1, wherein the valve is fluidly actuated.",
@ -959,6 +1023,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. The system of claim 3, further comprising: a fluid line configured to supply the fluid to the second fluid chamber, the fluid line being fluidly coupled to the valve such that, when the fluid flows through the fluid line to the second fluid chamber, the valve opens in a manner that permits the fluid exiting first fluid chamber to bypass the flow restrictor.",
@ -970,6 +1035,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. The system of claim 1, wherein the valve is electrically actuated.",
@ -981,6 +1047,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "6. The system of claim 1, wherein the flow restrictor defines a throat having a fixed size.",
@ -992,6 +1059,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "7. The system of claim 1, wherein the flow restrictor defines a throat having an adjustable size.",
@ -1003,6 +1071,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "8. A seed planting implement, comprising: a toolbar; a plurality of row units adjustably coupled to the toolbar, each row unit including a ground engaging tool configured to form a furrow in the soil; a plurality of fluid-driven actuators, each fluid-driven actuator being coupled between the toolbar and a corresponding row unit of the plurality of row units, each fluid-driven actuator being configured to adjust a position of the corresponding row unit relative to the toolbar, each fluid-driven actuator defining first and second fluid chambers; a flow restrictor fluidly coupled to the first fluid chamber of a first fluid-driven actuator of the plurality of fluid-driven actuators, the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the first fluid chamber of the first fluid-driven actuator in a manner that provides damping to the corresponding row unit; and a valve fluidly coupled to the first fluid chamber of the first fluid-driven actuator, the valve further being fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the first fluid chamber to flow through the flow restrictor and the fluid entering the first fluid chamber to bypass the flow restrictor.",
@ -1014,6 +1083,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "9. The seed planting implement of claim 8, wherein, when fluid is supplied to the second fluid chamber of the first fluid-driven actuator, the valve is configured to permit fluid exiting the first fluid chamber of the first fluid-driven actuator to bypass the flow restrictor.",
@ -1025,6 +1095,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "10. The seed planting implement of claim 8, wherein the valve is fluidly actuated.",
@ -1036,6 +1107,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "11. The seed planting implement of claim 10, further comprising: a fluid line configured to supply fluid to the second fluid chamber of the first fluid-driven actuator, the fluid line being fluidly coupled to the valve such that, when fluid flows through the fluid line to the second fluid chamber of the first fluid-driven actuator, the valve opens in a manner that permits the fluid exiting first fluid chamber of the first fluid-driven actuator to bypass the flow restrictor.",
@ -1047,6 +1119,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "12. The seed planting implement of claim 8, wherein the valve is electrically actuated.",
@ -1058,6 +1131,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "13. The seed planting implement of claim 8, wherein the flow restrictor defines a throat having a fixed size.",
@ -1069,6 +1143,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "14. The seed planting implement of claim 8, wherein the flow restrictor defines a throat having an adjustable size.",
@ -1080,6 +1155,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "15. A system for providing damping to a row unit of a seed planting implement, the system comprising: a toolbar; a row unit adjustably mounted on the toolbar; a fluid-driven actuator configured to adjust a position of the row unit relative to the toolbar, the fluid-driven actuator defining a fluid chamber; and a flow restrictor fluidly coupled to the fluid chamber, the flow restrictor defining an adjustable throat configured to reduce a rate at which fluid is permitted to exit the fluid chamber, the throat being adjustable between a first size configured to provide a first damping rate to the row unit and a second size configured to provide a second damping rate to the row unit, the first and second damping rates being different.",
@ -1091,6 +1167,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "16. The system of claim 15, wherein the throat is adjustable between the first and second damping rates based on an operator input.",
@ -1102,6 +1179,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "17. The system of claim 15, wherein the throat is adjustable between the first and second damping rates based on data received from one or more sensors on the seed planting implement.",
@ -1113,6 +1191,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "18. The system of claim 15, further comprising: a valve fluidly coupled to the fluid chamber, the valve being configured to selectively occlude the flow of fluid such that fluid exiting the fluid chamber flows through the flow restrictor and fluid entering the fluid chamber bypasses the flow restrictor.",
@ -1124,6 +1203,7 @@
"$ref": "#/texts/58"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "19. The system of claim 18, wherein the flow restrictor and the valve are fluidly coupled in a parallel relationship.",

13
tests/data/groundtruth/docling_v2/lorem_ipsum.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "lorem_ipsum",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -44,6 +45,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -55,6 +57,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Proin elit mi, fermentum vitae dolor facilisis, porttitor mollis quam. Cras quam massa, venenatis faucibus libero vel, euismod sollicitudin ipsum. Aliquam semper sapien leo, ac ultrices nibh mollis congue. Cras luctus ultrices est, ut scelerisque eros euismod ut. Curabitur ac tincidunt felis, non scelerisque lectus. Praesent sollicitudin vulputate est id consequat. Vestibulum pharetra ligula sit amet varius porttitor. Sed eros diam, gravida non varius at, scelerisque in libero. Ut auctor finibus mauris sit amet ornare. Sed facilisis leo at urna rhoncus, in facilisis arcu eleifend. Sed tincidunt lacinia fermentum. Cras non purus fringilla, semper quam non, sodales sem. Nulla facilisi.",
@ -66,6 +69,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -77,6 +81,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Duis condimentum dui eget ullamcorper maximus. Nulla tortor lectus, hendrerit at diam fermentum, euismod ornare orci. Integer ac mauris sed augue ultricies pellentesque. Etiam condimentum turpis a risus dictum, sed tempor arcu vestibulum. Quisque at venenatis tellus. Morbi id lobortis elit. In gravida metus at ornare suscipit. Donec euismod nibh sit amet commodo porttitor. Integer commodo sit amet nisi vel accumsan. Donec lacinia posuere porta. Pellentesque vulputate porta risus, vel consectetur nisl gravida sit amet. Nam scelerisque enim sodales lacus tempor, et tristique ante aliquet.",
@ -88,6 +93,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -99,6 +105,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Maecenas id neque pharetra, eleifend lectus a, vehicula sapien. Aliquam erat volutpat. Ut arcu erat, blandit id elementum at, aliquet pretium mauris. Nulla at semper orci. Nunc sed maximus metus. Duis eget tristique arcu. Phasellus fringilla augue est, ut bibendum est bibendum vitae. Nam et urna interdum, egestas velit a, consectetur metus. Pellentesque facilisis vehicula orci, eu posuere justo imperdiet non. Vestibulum tincidunt orci ac lorem consequat semper. Fusce semper sollicitudin orci, id lacinia nulla faucibus eu. Donec ut nisl metus.",
@ -110,6 +117,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -121,6 +129,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Duis ac tellus sed turpis feugiat aliquam sed vel justo. Fusce sit amet volutpat massa. Duis tristique finibus metus quis tincidunt. Etiam dapibus fringilla diam at pharetra. Vivamus dolor est, hendrerit ac ligula nec, pharetra lacinia sapien. Phasellus at malesuada orci. Maecenas est justo, mollis non ultrices ut, sagittis commodo odio. Integer viverra mauris pellentesque bibendum vestibulum. Sed eu felis mattis, efficitur justo non, finibus lorem. Phasellus viverra diam et sapien imperdiet interdum. Cras a convallis libero. Integer maximus dui vel lorem hendrerit, sit amet convallis ligula lobortis. Duis eu lacus elementum, scelerisque nunc eget, dignissim libero. Suspendisse mi quam, vehicula sit amet pellentesque rhoncus, blandit eu nisl.",
@ -132,6 +141,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -143,6 +153,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Nunc vehicula mattis erat ac consectetur. Etiam pharetra mauris ut tempor pellentesque. Sed vel libero vitae ante tempus sagittis vel sit amet dolor. Etiam faucibus viverra sodales. Pellentesque ullamcorper magna libero, non malesuada dui bibendum quis. Donec sed dolor non sem luctus volutpat. Morbi vel diam ut urna euismod gravida a id lectus. Vestibulum vel mauris eu tellus hendrerit dapibus. Etiam scelerisque lacus vel ante ultricies vulputate. In ullamcorper malesuada justo, vel scelerisque nisl lacinia at. Donec sodales interdum ipsum, ac bibendum ipsum pharetra interdum. Vivamus condimentum ac ante vel aliquam. Ut consectetur eu nibh nec gravida. Vestibulum accumsan, purus at mollis rutrum, sapien tortor accumsan purus, vitae fermentum urna mauris ut lacus. Fusce vitae leo sollicitudin, vehicula turpis eu, tempus nibh.",

108
tests/data/groundtruth/docling_v2/pa20010031492.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "pa20010031492.xml",
"origin": {
"mimetype": "application/xml",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -23,6 +24,7 @@
"$ref": "#/texts/102"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -167,6 +169,7 @@
"$ref": "#/texts/84"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Assay reagent",
@ -182,6 +185,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ABSTRACT",
@ -194,6 +198,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A cell-derived assay reagent prepared from cells which have been killed by treatment with an antibiotic selected from the bleomycin-phleomycin family of antibiotics but which retain a signal-generating metabolic activity such as bioluminescence. ",
@ -205,6 +210,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This application is a continuation of PCT/GB99/01730, filed Jun. 1, 1999 designating the United States (the disclosure of which is incorporated herein by reference) and claiming priority from British application serial no. 9811845.8, filed Jun. 2, 1998.",
@ -216,6 +222,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The invention relates to a cell-derived assay reagent, in particular to an assay reagent prepared from cells which have been killed but which retain a signal-generating metabolic activity such as bioluminescence and also to assay methods using the cell-derived reagent such as, for example, toxicity testing methods.",
@ -227,6 +234,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The use of bacteria with a signal-generating metabolic activity as indicators of toxicity is well established. UK patent number GB 2005018 describes a method of assaying a liquid sample for toxic substances which involves contacting a suspension of bioluminescent microorganisms with a sample suspected of containing a toxic substance and observing the change in the light output of the bioluminescent organisms as a result of contact with the suspected toxic substance. Furthermore, a toxicity monitoring system embodying the same assay principle, which is manufactured and sold under the Trade Mark Microtox\u00ae, is in routine use in both environmental laboratories and for a variety of industrial applications. An improved toxicity assay method using bioluminescent bacteria, which can be used in a wider range of test conditions than the method of GB 2005018, is described in International patent application number WO 95/10767.",
@ -238,6 +246,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The assay methods known in the prior art may utilize naturally occurring bioluminescent organisms, including Photobacterium phosphoreum and Vibrio fischeri. However, recent interest has focused on the use of genetically modified microorganisms which have been engineered to express bioluminescence. These genetically modified bioluminescent microorganisms usually express lux genes, encoding the enzyme luciferase, which have been cloned from a naturally occurring bioluminescent microorganism (E. A. Meighen (1994) Genetics of Bacterial Bioluminescence. Ann. Rev. Genet. 28: 117-139; Stewart, G. S. A. B. Jassin, S. A. A. and Denyer, S. P. (1993), Engineering Microbial bioluminescence and biosensor applications. In Molecular Diagnosis. Eds R. Rapley and M. R. Walker Blackwell Scientific Pubs/Oxford). A process for producing genetically modified bioluminescent microorganisms expressing lux genes cloned from Vibrio harveyi is described in U.S. Pat. No. 4,581,335.",
@ -249,6 +258,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The use of genetically modified bioluminescent microorganisms in toxicity testing applications has several advantages over the use of naturally occurring microorganisms. For example, it is possible to engineer microorganisms with different sensitivities to a range of different toxic substances or to a single toxic substance. However, genetically modified microorganisms are subject to marketing restrictions as a result of government legislation and there is major concern relating to the deliberate release of genetically modified microorganisms into the environment as components of commercial products. This is particularly relevant with regard to toxicity testing which is often performed in the field rather than within the laboratory. The potential risk from release of potentially pathogenic genetically modified microorganisms into the environment where they may continue to grow in an uncontrollable manner has led to the introduction of legal restrictions on the use of genetically modified organisms in the field in many countries.",
@ -260,6 +270,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It has been suggested, to avoid the problems discussed above, to use genetically modified bioluminescent microorganisms which have been treated so that they retain the metabolic function of bioluminescence but an no longer reproduce. The use of radiation (gamma-radiation), X-rays or an electron beam) to kill bioluminescent cells whilst retaining the metabolic function of bioluminescence is demonstrated in International patent application number WO 95/07346. It is an object of the present invention to provide an alternative method of killing bioluminescent cells whilst retaining the metabolic function of bioluminescence which does not require the use of radiation and, as such, can be easily carried out without the need for specialized radiation equipment and containment facilities and without the risk to laboratory personnel associated with the use of radiation.",
@ -271,6 +282,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Accordingly, in a first aspect the invention provides a method of making a non-viable preparation of prokaryotic or eukaryotic cells, which preparation has a signal-generating metabolic activity, which method comprises contacting a viable culture of cells with signal-generating metabolic activity with a member of the bleomycin/phleomycin family of antibiotics.",
@ -282,6 +294,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Bleomycin and phleomycin are closely related glycopeptide antibiotics that are isolated in the form of copper chelates from cultures of Streptomyces verticillus. They represent a group of proteins with molecular weights ranging from 1000 to 1000 kda that are potent antibiotics and anti-tumour agents. So far more than 200 members of the bleomycin/phleomycin family have been isolated and characterised as complex basic glycopeptides. Family members resemble each other with respect to their physicochemical properties and their structure, indicating that functionally they all behave in the same manner. Furthermore, the chemical structure of the active moiety is conserved between family members and consists of 5 amino acids, L-glucose, 3-O-carbamoyl-D-mannose and a terminal cation. The various different bleomycin/phleomycin family members differ from each other in the nature of the terminal cation moiety, which is usually an amine. A preferred bleomycin/phleomycin antibiotic for use in the method of the invention is phleomycin D1, sold under the trade name Zeocin\u2122.",
@ -293,6 +306,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Bleomycin and phleomycin are strong, selective inhibitors of DNA synthesis in intact bacteria and in mammalian cells. Bleomycin can be observed to attack purified DNA in vitro when incubated under appropriate conditions and analysis of the bleomycin damaged DNA shows that both single-stranded and double-stranded cleavages occur, the latter being the result of staggered single strand breaks formed approximately two base pairs apart in the complementary strands.",
@ -304,6 +318,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In in vivo systems, after being taken up by the cell, bleomycin enters the cell nucleus, binds to DNA (by virtue of the interaction between its positively charged terminal amine moiety and a negatively charged phosphate group of the DNA backbone) and causes strand scission. Bleomycin causes strand scission of DNA in viruses, bacteria and eukaryotic cell systems.",
@ -315,6 +330,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present inventors have surprisingly found that treatment of a culture of cells with signal-generating metabolic activity with a bleomycin/phleomycin antibiotic renders the culture non-viable whilst retaining a level of signal-generating metabolic activity suitable for use in toxicity testing applications. In the context of this application the term non-viable is taken to mean that the cells are unable to reproduce. The process of rendering cells non-viable whilst retaining signal-generating metabolic activity may hereinafter be referred to as \u2018inactivation\u2019 and cells which have been rendered non-viable according to the method of the invention may be referred to as \u2018inactivated\u2019.",
@ -326,6 +342,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Because of the broad spectrum of action of the bleomycin/phleomycin family of antibiotics the method of the invention is equally applicable to bacterial cells and to eukaryotic cells with signal generating metabolic activity. Preferably the signal-generating metabolic activity is bioluminescence but other signal-generating metabolic activities which are reporters of toxic damage could be used with equivalent effect.",
@ -337,6 +354,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The method of the invention is preferred for use with bacteria or eukaryotic cells that have been genetically modified to express a signal-generating metabolic activity. The examples given below relate to E. coil which have been engineered to express bioluminescence by transformation with a plasmid carrying lux genes. The eukaryotic equivalent would be cells transfected with a vector containing nucleic acid encoding a eukaryotic luciferase enzyme (abbreviated luc) such as, for example, luciferase from the firefly Photinus pyralis. A suitable plasmid vector containing cDNA encoding firefly luciferase under the control of an SV40 viral promoter is available from Promega Corporation, Madison Wis., USA. However, in connection with the present invention it is advantageous to use recombinant cells containing the entire eukaryotic luc operon so as to avoid the need to add an exogenous substrate ( e.g. luciferin) in order to generate light output.",
@ -348,6 +366,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The optimum concentration of bleomycin/phleomycin antibiotic and contact time required to render a culture of cells non-viable whilst retaining a useful level of signal-generating metabolic activity may vary according to the cell type but can be readily determined by routine experiment. In general, the lower the concentration of antibiotic used the longer the contact time required for cell inactivation. In connection with the production of assay reagents for use in toxicity testing applications, it is generally advantageous to keep the concentration of antibiotic low (e.g. around 1-1.5 mg/ml) and increase the contact time for inactivation. As will be shown in Example 1, treatment with Zeocin\u2122 at a concentration of 1.5 mg/ml for 3 to 5 hours is sufficient to completely inactivate a culture of recombinant E. coli.",
@ -359,6 +378,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In the case of bacteria, the contact time required to inactivate a culture of bacterial cells is found to vary according to the stage of growth of the bacterial culture at the time the antibiotic is administered. Although the method of the invention can be used on bacteria at all stages of growth it is generally preferable to perform the method on bacterial cells in an exponential growth phase because the optimum antibiotic contact time has been observed to be shortest when the antibiotic is administered to bacterial cells in an exponential growth phase.",
@ -370,6 +390,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Following treatment with bleomycin/phleomycin antibiotic the non-viable preparation of cells is preferably stabilised for ease of storage or shipment. The cells can be stabilised using known techniques such as, for example, freeze drying (lyophilization) or other cell preservation techniques known in the art. Stabilization by freeze drying has the added advantage that the freeze drying procedure itself can render cells non-viable. Thus, any cells in the preparation which remain viable after treatment of the culture with bleomycin/phleomycin antibiotic will be rendered non-viable by freeze drying. It is thought that freeze drying inactivates any remaining viable cells by enhancing the effect of antibiotic, such that sub-lethally injured cells in the culture are more sensitive to the stresses applied during freeze drying.",
@ -381,6 +402,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Prior to use the stabilised cell preparation is reconstituted using a reconstitution buffer to form an assay reagent. This reconstituted assay reagent may then be used directly in assays for analytes, for example in toxicity testing applications. It is preferable that the stabilised (i.e. freeze dried) assay reagent be reconstituted immediately prior to use, but after reconstitution it is generally necessary to allow sufficient time prior to use for the reconstituted reagent to reach a stable, high level of signal-generating activity. Suitable reconstitution buffers preferably contain an osmotically potent non-salt compound such as sucrose, dextran or polyethylene glycol, although salt based stabilisers may also be used.",
@ -392,6 +414,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Whilst the assay reagent of the invention is particularly suitable for use in toxicity testing applications it is to be understood that the invention is not limited to assay reagents for use in toxicity testing. The cell inactivation method of the invention can be used to inactivate any recombinant cells (prokaryotic or eukaryotic) with a signal generating metabolic activity that is not dependent upon cell viability.",
@ -403,6 +426,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In a further aspect the invention provides a method of assaying a potentially toxic analyte comprising the steps of,",
@ -414,6 +438,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "(a) contacting a sample to be assayed for the analyte with a sample of assay reagent comprising a non-viable preparation of cells with a signal-generating metabolic activity;",
@ -425,6 +450,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "(b) measuring the level of signal generated; and",
@ -436,6 +462,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "(c) using the measurement obtained as an indicator of the toxicity of the analyte.",
@ -447,6 +474,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In a still further aspect, the invention provides a kit for performing the above-stated assay comprising an assay reagent with signal generating metabolic activity and means for contacting the assay reagent with a sample to be assayed for an analyte.",
@ -458,6 +486,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The analytes tested using the assay of the invention are usually toxic substances, but it is to be understood that the precise nature of the analyte to be tested is not material to the invention.",
@ -469,6 +498,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Toxicity is a general term used to describe an adverse effect on biological system and the term \u2018toxic substances\u2019 includes both toxicants (synthetic chemicals that are toxic) and toxins (natural poisons). Toxicity is usually expressed as an effective concentration (EC) or inhibitory concentration (IC) value. The EC/IC value is usually denoted as a percentage response e.g. EC\u2085\u2080, EC\u2081\u2080 which denotes the concentration (dose) of a particular substance which affects the designated criteria for assessing toxicity (i.e. a behavioural trait or death) in the indicated proportion of the population tested. For example, an EC\u2085\u2080 of 10 ppm indicates that 50% of the population will be affected by a concentration of 10 ppm. In the case of a toxicity assay based on the use of a bioluminescent assay reagent, the EC\u2085\u2080 value is usually the concentration of sample substance causing a 50% change in light output.",
@ -480,6 +510,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present invention will be further understood by way of the following Examples with reference to the accompanying Figures in which:",
@ -491,6 +522,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 is a graph to show the effect of Zeocin\u2122 treatment on viable count and light output of recombinant bioluminescent E. coil cells.",
@ -502,6 +534,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 2 is a graph to show the light output from five separate vials of reconstituted assay reagent. The assay reagent was prepared from recombinant bioluminescent E. coil exposed to 1.5 mg/ml Zeocin\u2122 for 300 minutes. Five vials were used to reduce discrepancies resulting from vial to vial variation.",
@ -513,6 +546,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIGS. 3 to 8 are graphs to show the effect of Zeocin\u2122 treatment on the sensitivity of bioluminescent assay reagent to toxicant (ZnSO\u2084):",
@ -524,6 +558,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 3: Control cells, lag phase.",
@ -535,6 +570,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 4: Zeocin\u2122 treated cells, lag phase.",
@ -546,6 +582,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 5: Control cells, mid-exponential growth.",
@ -557,6 +594,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 6: Zeocin\u2122 treated cells, mid-exponential growth.",
@ -568,6 +606,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 7: Control cells, stationary phase.",
@ -579,6 +618,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 8: Zeocin\u2122 treated cells, stationary phase.",
@ -590,6 +630,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "EXAMPLE 1",
@ -621,6 +662,7 @@
"$ref": "#/texts/45"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "(A) Inactivation of Bioluminescent E. coil Method",
@ -633,6 +675,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. Bioluminescent genetically modified E. coil strain HB101 (E. coli HB101 made bioluminescent by transformation with a plasmid carrying the lux operon of Vibrio fischeri constructed by the method of Shaw and Kado, as described in Biotechnology 4: 560-564) were grown from a frozen stock in 5 ml of low salt medium (LB (5 g/ml NaCl)+glycerol+MgSO\u2084) for 24 hours.",
@ -644,6 +687,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. 1 ml of the 5 ml culture was then used to inoculate 200 ml of low salt medium in a shaker flask and the resultant culture grown to an OD\u2086\u2083\u2080 of 0.407 (exponential growth phase).",
@ -655,6 +699,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. 50 ml of this culture was removed to a fresh sterile shaker flask (control cells).",
@ -666,6 +711,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. Zeocin\u2122 was added to the 150 ml of culture in the original shaker flash, to a final concentration of 1.5 mg/ml. At the same time, an equivalent volume of water was added to the 50 ml culture removed from the original flask (control cells).",
@ -677,6 +723,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. The time course of cell inactivation was monitored by removing samples from the culture at 5, 60, 120, 180, 240 and 300 minutes after the addition of Zeocin\u2122 and taking measurements of both light output (measured using a Deltatox luminometer) and viable count (per ml, determined using the method given in Example 3 below) for each of the samples. Samples of the control cells were removed at 5 and 300 minutes after the addition of water and measurements of light output and viable count taken as for the Zeocin\u2122 treated cells.",
@ -688,6 +735,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 shows the effect of Zeocin\u2122 treatment on the light output and viable count (per ml) of recombinant bioluminescent E. coil. Zeocin\u2122 was added to a final concentration of 1.5 mg/ml at time zero. The number of viable cells in the culture was observed to decrease with increasing contact cells with Zeocin\u2122, the culture being completely inactivated after 3 hours. The light output from the culture was observed to decrease gradually with increasing Zeocin\u2122 contact time.",
@ -709,6 +757,7 @@
"$ref": "#/texts/49"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "(B) Production of Assay Reagent",
@ -721,6 +770,7 @@
"$ref": "#/texts/46"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Five hours after the addition of Zeocin\u2122 or water the remaining bacterial cells in the Zeocin\u2122 treated and control cultures were harvested by the centrifugation, washed (to remove traces of Zeocin\u2122 from the Zeocin\u2122 treated culture), re-centrifuged and resuspended in cryoprotectant to an OD\u2086\u2083\u2080 of 0.25. 200 \u03bcl aliquots of the cells in cryoprotectant were dispensed into single shot vials, and freeze dried. Freeze dried samples of the Zeocin\u2122 treated cells and control cells were reconstituted in 0.2M sucrose to form assay reagents and the light output of the assay reagents measured at various times after reconstitution.",
@ -732,6 +782,7 @@
"$ref": "#/texts/46"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The light output from assay reagent prepared from cells exposed to 1.5 mg/ml Zeocin\u2122 for 5 hours was not significantly different to the light output from assay reagent prepared from control (Zeocin\u2122 untreated) cells, indicating that Zeocin\u2122 treatment does not affect the light output of the reconstituted freeze dried assay reagent. Both Zeocin\u2122 treated and Zeocin\u2122 untreated assay reagents produced stable light output 15 minutes after reconstitution.",
@ -743,6 +794,7 @@
"$ref": "#/texts/46"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 2 shows the light output from five separate vials of reconstituted Zeocin\u2122 treated assay reagent inactivated according to the method of Example 1(A) and processed into assay reagent as described in Example 1(B). Reconstitution solution was added at time zero and thereafter light output was observed to increase steadily before stabilising out at around 15 minutes after reconstitution. All five vials were observed to give similar light profiles after reconstitution.",
@ -754,6 +806,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "EXAMPLE 2",
@ -845,6 +898,7 @@
"$ref": "#/texts/76"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Sensitivity of Zeocin\u2122 Treated Assay Reagent to Toxicant Method",
@ -857,6 +911,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. Bioluminescent genetically modified E. coil strain HB101 (E. coli HB101 made bioluminescent by transformation with a plasmid carrying the lux operon of vibrio fischeri constructed by the method of Shaw and Kado, as described in Biotechnology 4: 560-564) was grown in fermenter as a batch culture in low salt medium (LB(5 g/ml NaCl)+glycerol+MgSO\u2084).",
@ -868,6 +923,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. Two aliquots of the culture were removed from the fermenter into separate sterile shaker flasks at each of three different stages of growth i.e. at OD\u2086\u2083\u2080 values of 0.038 (lag phase growth), 1.31 (mid-exponential phase growth) and 2.468 (stationary phase growth).",
@ -879,6 +935,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. One aliquot of culture for each of the three growth stages was inactivated by contact with Zeocin\u2122 (1 mg Zeocin\u2122 added per 2.5\u00d710\u2076 cells, i.e. the concentration of Zeocin\u2122 per cell is kept constant) for 300 minutes and then processed into assay reagent by freeze drying and reconstitution, as described in part (B) of Example 1.",
@ -890,6 +947,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. An equal volume of water was added to the second aliquot of culture for each of the three growth stages and the cultures processed into assay reagent as described above.",
@ -901,6 +959,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. Samples of each of the three Zeocin\u2122 treated and three control assay reagents were then evaluated for sensitivity to toxicant (ZnSO\u2084) according to the following assay protocol:",
@ -912,6 +971,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "ZnSO\u2084 Sensitivity Assay",
@ -923,6 +983,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. ZnSO\u2084 solutions were prepared in pure water at 30, 10, 3, 1, 0.3 and 0.1 ppm. Pure water was also used as a control.",
@ -934,6 +995,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. Seven vials of each of the three Zeocin\u2122 treated and each of the three control assay reagents (i.e. one for each of the six ZnSO\u2084 solutions and one for the pure water control) were reconstituted using 0.5 ml of reconstitution solution (eg 0.2M sucrose) and then left to stand at room temperature for 15 minutes to allow the light output to stabilize. Base line (time zero) readings of light output were then measured for each of the reconstituted reagents.",
@ -945,6 +1007,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. 0.5 ml aliquots of each of the six ZnSO\u2084 solutions and the pure water control were added to separate vials of reconstituted assay reagent. This was repeated for each of the different Zeocin\u2122 treated and control assay reagents.",
@ -956,6 +1019,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. The vials were incubated at room temperature and light output readings were taken 5, 10, 15, 20, 25 and 30 minutes after addition of ZnSO\u2084 solution.",
@ -967,6 +1031,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. The % toxic effect for each sample was calculated as follows:",
@ -978,6 +1043,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "where: C\u2092=light in control at time zero",
@ -989,6 +1055,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Ct=light in control at reading time",
@ -1000,6 +1067,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "S\u2092=light in sample at time zero",
@ -1011,6 +1079,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "St=light in sample at reading time",
@ -1022,6 +1091,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The results of toxicity assays for sensitivity to ZnSO\u2084 for all the Zeocin\u2122 treated and control assay reagents are shown in FIGS. 3 to 8:",
@ -1033,6 +1103,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 3: Control cells, lag phase.",
@ -1044,6 +1115,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 4: Zeocin\u2122 treated cells, lag phase.",
@ -1055,6 +1127,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 5: Control cells, mid-exponential growth.",
@ -1066,6 +1139,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 6: Zeocin\u2122 treated cells, mid-exponential growth.",
@ -1077,6 +1151,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 7: Control cells, stationary phase.",
@ -1088,6 +1163,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 8: Zeocin\u2122 treated cells, stationary phase.",
@ -1099,6 +1175,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In each case, separate graphs of % toxic effect against log\u2081\u2080 concentration of ZnSO\u2084 were plotted on the same axes for each value of time (minutes) after addition of Zeocin\u2122 or water. The sensitivities of the various reagents, expressed as an EC\u2085\u2080 value for 15 minutes exposed to ZnSO\u2084, are summarised in Table 1 below.",
@ -1110,6 +1187,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Table 1: Sensitivity of the different assay reagents to ZnSo\u2084 expressed as EC\u2085\u2080 values for 15 minutes exposure to ZNSO\u2084.",
@ -1121,6 +1199,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The results of the toxicity assays indicate that Zeocin\u2122 treatment does not significantly affect the sensitivity of a recombinant bioluminescent E. coli derived assay reagent to ZnSO\u2084. Similar results could be expected with other toxic substances which have an effect on signal-generating metabolic activities.",
@ -1132,6 +1211,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "EXAMPLE 3",
@ -1160,6 +1240,7 @@
"$ref": "#/texts/83"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Method to Determine Viable Count",
@ -1172,6 +1253,7 @@
"$ref": "#/texts/78"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. Samples of bacterial culture to be assayed for viable count were centrifuged at 10,000 rpm for 5 minutes to pellet the bacterial cells.",
@ -1183,6 +1265,7 @@
"$ref": "#/texts/78"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. Bacterial cells were washed by resuspending in 1 ml of M9 medium, re-centrifuged at 10,000 rpm for 5 minutes and finally re-suspended in 1 ml of M9 medium.",
@ -1194,6 +1277,7 @@
"$ref": "#/texts/78"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. Serial dilutions of the bacterial cell suspension from 10\u207b\u00b9 to 10\u207b\u2077 were prepared in M9 medium.",
@ -1205,6 +1289,7 @@
"$ref": "#/texts/78"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. Three separate 10 \u03bcl aliquots of each of the serial dilutions were plated out on standard agar plates and the plates incubated at 37\u00b0 C.",
@ -1216,6 +1301,7 @@
"$ref": "#/texts/78"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. The number of bacterial colonies present for each of the three aliquots at each of the serial dilutions were counted and the values averaged. Viable count was calculated per ml of bacterial culture.",
@ -1279,6 +1365,7 @@
"$ref": "#/texts/101"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CLAIMS",
@ -1291,6 +1378,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. A method of making a non-viable preparation of prokaryotic or eukaryotic cells, which preparation has a signal-generating metabolic activity, which method comprises contacting a viable culture of said cells having signal-generating metabolic activity with an antibiotic selected from the bleomycin/phleomycin family of antibiotics.",
@ -1302,6 +1390,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. The method as claimed in claim 1 wherein following contact with antibiotic, said cells are subjected to a stabilization step.",
@ -1313,6 +1402,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. The method as claimed in claim 2 wherein said stabilization step comprises freeze drying.",
@ -1324,6 +1414,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. The method as claimed in claim 1 wherein said antibiotic is phleomycin D1.",
@ -1335,6 +1426,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. The method as claimed in claim 5 wherein said signal-generating metabolic activity is bioluminescence.",
@ -1346,6 +1438,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "6. The method as claimed in claim 5 wherein said cells are bacteria.",
@ -1357,6 +1450,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "7. The method as claimed in claim 6 wherein said bacteria are in an exponential growth phase when contacted with said antibiotic.",
@ -1368,6 +1462,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "8. The method as claimed in claim 6 wherein said bacteria are genetically modified.",
@ -1379,6 +1474,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "9. The method as claimed in claim 8 wherein said genetically modified bacteria contain nucleic acid encoding luciferase.",
@ -1390,6 +1486,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "10. The method as claimed in claim 9 wherein said bacteria are E. coli.",
@ -1401,6 +1498,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "11. The method as claimed in claim 5 wherein said cells are eukaryotic cells.",
@ -1412,6 +1510,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "12. The method as claimed in claim 11 wherein said eukaryotic cells are genetically modified.",
@ -1423,6 +1522,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "13. The method as claimed in claim 12 wherein said genetically modified eukaryotic cells contain nucleic acid encoding luciferase.",
@ -1434,6 +1534,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "14. A method of making a non-viable preparation of prokaryotic cells, which preparation has a signal-generating metabolic activity, which method comprises contacting a viable culture of a genetically modified E. coli strain made bioluminescent by transformation with a plasmid carrying the lux operon of Vibrio fischeri with an antibiotic selected from the bleomycin/phleomycin family of antibiotics.",
@ -1445,6 +1546,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "15. The method as claimed in claim 14 wherein said cells are contacted with phleomycin D1 at a concentration of at least about 1.5 mg/ml.",
@ -1456,6 +1558,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "16. The method as claimed in claim 15 wherein said contact is maintained for at least about 3 hours.",
@ -1467,6 +1570,7 @@
"$ref": "#/texts/84"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "17. The method as claimed in claim 16 wherein said antibiotic-treated cells are harvested, washed and freeze-dried.",
@ -1478,6 +1582,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Drawings",
@ -1493,6 +1598,7 @@
"$ref": "#/texts/51"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

79
tests/data/groundtruth/docling_v2/pftaps057006474.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "pftaps057006474.txt",
"origin": {
"mimetype": "text/plain",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -50,6 +52,7 @@
"$ref": "#/texts/54"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Carbocation containing cyanine-type dye",
@ -65,6 +68,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ABSTRACT",
@ -77,6 +81,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "To provide a reagent with excellent stability under storage, which can detect a subject compound to be measured with higher specificity and sensitibity.",
@ -119,6 +124,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BACKGROUND OF THE INVENTION",
@ -131,6 +137,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. Field of the Invention",
@ -142,6 +149,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present invention relates to a labeled complex for microassay using near-infrared radiation. More specifically, the present invention relates to a labeled complex capable of specifically detecting a certain particular component in a complex mixture with a higher sensitivity.",
@ -153,6 +161,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. Related Background Art",
@ -164,6 +173,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "On irradiating a laser beam on a trace substance labeled with dyes and the like, information due to the substance is generated such as scattered light, absorption light, fluorescent light and furthermore light acoustics. It is widely known in the field of analysis using lasers, to detect such information so as to practice microassays rapidly with a higher precision.",
@ -175,6 +185,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A gas laser represented by an argon laser and a helium laser has conventionally been used exclusively as a laser source. In recent years, however, a semi-conductor laser has been developed, and based on the characteristic features thereof such as inexpensive cost, small scale and easy output control, it is now desired to use the semiconductor laser as a light source.",
@ -186,6 +197,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "If diagnostically useful substances from living organisms are assayed by means of the wave-length in ultraviolet and visible regions as has conventionally been used, the background (blank) via the intrinsic fluorescence of naturally occurring products, such as flavin, pyridine coenzyme and serum proteins, which are generally contained in samples, is likely to increase. Only if a light source in a near-infrared region can be used, such background from naturally occurring products can be eliminated so that the sensitivity to substances to be measured might be enhanced, consequently.",
@ -197,6 +209,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "However, the oscillation wavelength of a semiconductor laser is generally in red and near-infrared regions (670 to 830 nm), where not too many dyes generate fluorescence via absorption or excitation. A representative example of such dyes is polymethine-type dye having a longer conjugated chain. Examples of labeling substances from living organisms with a polymethine-type dye and using the labeled substances for microanalysis are reported by K. Sauda, T. Imasaka, et al. in the report in Anal. Chem., 58, 2649-2653 (1986), such that plasma protein is labeled with a cyanine dye having a sulfonate group (for example, Indocyanine Green) for the analysis by high-performance liquid chromatography.",
@ -208,6 +221,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Japanese Patent Application Laid-open No. 2-191674 discloses that various cyanine dyes having sulfonic acid groups or sulfonate groups are used for labeling substances from living organisms and for detecting the fluorescence.",
@ -219,6 +233,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "However, these known cyanine dyes emitting fluorescence via absorption or excitation in the near-infrared region are generally not particularly stable under light or heat.",
@ -230,6 +245,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "If the dyes are used as labeling agents and bonded to substances from living organisms such as antibodies for preparing complexes, the complexes are likely to be oxidized easily by environmental factors such as light, heat, moisture, atmospheric oxygen and the like or to be subjected to modification such as generating cross-links. Particularly in water, a modification such as hydrolysis is further accelerated, disadvantageously. Therefore, the practical use of these complexes as detecting reagents in carrying out the microassay of the components of living organisms has encountered difficulties because of their poor stability under storage.",
@ -257,6 +273,7 @@
"$ref": "#/texts/19"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "SUMMARY OF THE INVENTION",
@ -269,6 +286,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present inventors have made various investigations so as to solve the above problems, and have found that a dye of a particular structure, more specifically a particular polymethine dye, and among others, a dye having an azulene skelton, are extremely stable even after the immobilization thereof as a labeling agent onto substances from living organisms. Thus, the inventors have achieved the present invention. It is an object of the present invention to provide a labeled complex with excellent storage stability which can overcome the above problems.",
@ -280,6 +298,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "According to an aspect of the present invention, there is provided a labeled complex for detecting a subject compound to be analyzed by means of optical means using near-infrared radiation which complex comprises a substance from a living organism and a labeling agent fixed onto the substance and is bonded to the subject compound to be analyzed, wherein the labeling agent comprises a compound represented by the general formula (I), (II) or (III): wherein R.sub.1 through R.sub.7 are independently selected from the group consisting of hydrogen atom, halogen atom, alkyl group, aryl group, aralkyl group, sulfonate group, amino group, styryl group, nitro group, hydroxyl group, carboxyl group, cyano group, or arylazo group; R.sub.1 through R.sub.7 may be bonded to each other to form a substituted or an unsubstituted condensed ring; R.sub.1 represents a divalent organic residue; and X.sub.1.sup..crclbar. represents an anion; wherein R.sub.8 through R14 are independently selected from the group consisting of hydrogen atom, halogen atom, alkyl group, aryl group, aralkyl group, sulfonate group, amino group, styryl group, nitro group, hydroxyl group, carboxyl group, cyano group, or arylazo group; R.sub.8 through R14 may be bonded to each other to form a substituted or an unsubstituted condensed ring; and R.sub.A represents a divalent organic residue; wherein R.sub.15 through R.sub.21 are independently selected from the group consisting of hydrogen atom, halogen atom, alkyl group, aryl group, a substituted or an unsubstituted aralkyl group, a substituted or an unsubstituted amino group, a substituted or an unsubstituted styryl group, nitro group, sulfonate group, hydroxyl group, carboxyl group, cyano group, or arylazo group; R.sub.15 through R.sub.21 may or may not be bonded to each other to form a substituted or an unsubstituted condensed ring; R.sub.B represents a divalent organic residue; and X.sub.1.sup..crclbar. represents an anion.",
@ -291,6 +310,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "According to another aspect of the present invention, there is provided a labeled complex for detecting a subject compound to be analyzed by means of optical means using near-infrared radiation which complex comprises a substance from a living organism and a labeling agent fixed onto the substance and is bonded to the subject compound to be analyzed, wherein the labeling agent comprises a compound represented by the general formula (IV): wherein A, B, D and E are independently selected from the group consisting of hydrogen atom, a substituted or an unsubstituted alkyl group having two or more carbon atoms, alkenyl group, aralkyl group, aryl group, styryl group and heterocyclic group; r.sub.1 ' and r.sub.2 ' are individually selected from the group consisting of hydrogen atom, a substituted or an unsubstituted alkyl group, cyclic alkyl group, alkenyl group, aralkyl group and aryl group; k is 0 or 1; 1 is 0, 1 or 2; and X.sub.2.sup..crclbar. represents an anion.",
@ -302,6 +322,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "According to another aspect of the present invention, there is provided a method of detecting a subject compound to be analyzed by means of optical means which method comprises using a labeled complex comprised of a substance from a living organism and a labeling agent fixed onto the substance and bonding the complex to the subject compound to be analyzed, wherein the labeling agent comprises a compound represented by the general formula (I), (II) or (III).",
@ -313,6 +334,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "According to still another aspect of the present invention, there is provided a method of detecting a subject compound to be analyzed by means of optical means which method comprises using a labeled complex comprised of a substance from a living organism and a labeling agent fixed onto the substance and bonding the complex to the subject compound to be analyzed, wherein the labeling agent comprises a compound represented by the general formula (iv).",
@ -328,6 +350,7 @@
"$ref": "#/texts/21"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BRIEF DESCRIPTION OF THE DRAWINGS",
@ -340,6 +363,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 depicts one example of fluorescence emitting wave form of a labeling agent.",
@ -445,6 +469,7 @@
"$ref": "#/texts/53"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS",
@ -457,6 +482,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The present invention will now be explained in detail hereinbelow.",
@ -468,6 +494,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In accordance with the present invention, the compound of the general formula (I), (II) or (III) is employed as a labeling agent, wherein R.sub.1 to R.sub.21 individually represent hydrogen atom, halogen atom (chlorine atom, bromine atom, and iodine atom) or a monovalent organic residue, and other such functional groups described above. The monovalent organic residue can be selected from a wide variety of such residues.",
@ -479,6 +506,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The alkyl group is preferably in straight chain or branched chain, having a carbon number of 1 to 12, such as for example methyl group, ethyl group, n-propyl group, iso-propyl group, n-butyl group, sec-butyl group, iso-butyl group, t-butyl group, n-amyl group, t-amyl group, n-hexyl group, n-octyl group, t-octyl group and the like.",
@ -490,6 +518,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The aryl group preferably has a carbon number of 6 to 20, such as for example phenyl group, naphthyl group, methoxyphenyl group, diethylaminophenyl group, dimethylaminophenyl group and the like.",
@ -501,6 +530,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The substituted aralkyl group preferably has a carbon number of 7 to 19, such as for example carboxybenzyl group, sulfobenzyl group, hydroxybenzyl group and the like.",
@ -512,6 +542,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The unsubstituted aralkyl group preferably has a carbon number of 7 to 19, such as for example benzyl group, phenethyl group, .alpha.-naphthylmethyl group, .beta.-naphthylmethyl group and the like.",
@ -523,6 +554,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The substituted or unsubstituted amino group preferably has a carbon number of 10 or less, such as for example amino group, dimethylamino group, diethylamino group, dipropylamino group, acetylamino group, benzoylamino group and the like.",
@ -534,6 +566,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The substituted or unsubstituted styryl group preferably has a carbon number of 8 to 14, such as for example styryl group, dimethylaminostyryl group, diethylaminostyryl group, dipropylaminostyryl group, methoxystyryl group, ethoxystyryl group, methylstyryl group and the like.",
@ -545,6 +578,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The aryl azo group preferably has a carbon number of 6 to 14, such as for example phenylazo group, .alpha.-naphthylazo group, .beta.-naphthylazo group, dimethylaminophenylazo group, chlorophenylazo group, nitrophenylazo group, methoxyphenylazo group and the like.",
@ -556,6 +590,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Of the combinations of R.sub.1 and R.sub.2, R.sub.2 and R.sub.3, R.sub.3 and R.sub.4, R.sub.4 and R.sub.5, R.sub.5 and R.sub.6, and R.sub.6 and R.sub.7 of the general formula (I), at least one combination may form a substituted or an unsubstituted condensed ring. The condensed ring may be five, six or seven membered, including aromatic ring (benzene, naphthalene, chlorobenzene, bromobenzene, methyl benzene, ethyl benzene, methoxybenzene, ethoxybenzene and the like); heterocyclic ring (furan ring, benzofuran ring, pyrrole ring, thiophene ring, pyridine ring, quinoline ring, thiazole ring and the like); and aliphatic ring (dimethylene, trimethylene, tetramethylene and the like). This is the case with the general formulas (II) and (III).",
@ -567,6 +602,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "For the general formula (II), at least one combination among the combinations of R.sub.8 and R.sub.9, R.sub.9 and R.sub.10, R.sub.10 and R.sub.11, R.sub.11 and R.sub.12, R.sub.12 and R.sub.13, and R.sub.13 and R.sub.14, may form a substituted or an unsubstituted condensed ring.",
@ -578,6 +614,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Also for the general formula (III), at least one combination of the combinations of R.sub.15 and R.sub.16, R.sub.16 and R.sub.17, R.sub.17 and R.sub.18, R.sub.18 and R.sub.19, R.sub.19 and R.sub.20, and R.sub.20 and R.sub.21, may form a substituted or an unsubstituted condensed ring.",
@ -589,6 +626,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In the general formulas (I) to (IV) described above, the general formula (I) is specifically preferable; preference is also given individually to hydrogen atom, alkyl group and sulfonate group in the case of R.sub.1 to R.sub.7 ; hydrogen atom, alkyl group and sulfonate group in the case of R.sub.8 to R.sub.14 ; hydrogen atom, alkyl group and sulfonate group in the case of R.sub.15 to R.sub.21 ; alkyl group and aryl group in the case of A, B, D and E; hydrogen atom and alkyl group in the case Of r.sub.1 ' to r.sub.2 '.",
@ -600,6 +638,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In the general formula (I), R represents a divalent organic residue bonded via a double bond. Specific examples of a compound containing such R to be used in the present invention, include those represented by the following general formulas (1) to (12), wherein Q.sup..sym. represents the following azulenium salt nucleus and the right side excluding Q.sup..sym. represents R. wherein the relation between the azulenium salt nucleus represented by Q.sup..crclbar. and the azulene salt nucleus on the right side in the formula (3) may be symmetric or asymmetric. In the above formulas (1) to (12) as in the case of R.sub.1 to R.sub.7, R.sub.1 ' to R.sub.7 ' and R.sub.1 \" to R.sub.7 \" independently represent hydrogen atom, halogen atom, alkyl group, aryl group, aralkyl group, amino group, styryl group, nitro group, hydroxyl group, carboxyl group, cyano group or aryl azo group, while R.sub.1 ' to R.sub.7 ' and R.sub.1 \" to R.sub.7 \" independently may form a substituted or an unsubstituted condensed ring; n is 0, 1 or 2; r is an integer of 1 to 8; S represents 0 or 1; and t represents 1 or 2.",
@ -611,6 +650,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "M.sub.2 represents a non-metallic atom group required for the completion of a nitrogen-containing heterocyclic ring.",
@ -622,6 +662,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Specific examples of M.sub.2 are atom groups required for the completion of a nitrogen-containing heterocyclic ring, including pyridine, thiazole, benzothiazole, naphthothiazole, oxazole, benzoxazole, naphthoxazole, imidazole, benzimidazole, naphthoimidazole, 2-quinoline, 4-quinoline, isoquinoline or indole, and may be substituted by halogen atom (chlorine atom, bromine atom, iodine atom and the like), alkyl group (methyl, ethyl, propyl, butyl and the like), aryl group (phenyl, tolyl, xylyl and the like), and aralkyl (benzene, p-trimethyl, and the like).",
@ -633,6 +674,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.22 represents hydrogen atom, nitro group, sulfonate group, cyano group, alkyl group (methyl, ethyl, propyl, butyl and the like), or aryl group (phenyl, tolyl, xylyl and the like). R.sub.23 represents alkyl group (methyl, ethyl, propyl, butyl and the like), a substituted alkyl group (2-hydroxyethyl, 2-methoxyethyl, 2-ethoxyethyl, 3-hydroxypropyl, 3-methoxypropyl, 3-ethoxypropyl, 3-chloropropyl, 3-bromopropyl, 3-carboxylpropyl and the like ), a cyclic alkyl group (cyclohexyl, cyclopropyl), aryl aralkyl group (benzene, 2-phenylethyl, 3-phenylpropyl, 3-phenylbutyl, 4-phenylbutyl, .alpha.-naphthylmethyl, .beta.-naphthylmethyl), a substituted aralkyl group (methylbenzyl, ethylbenzyl, dimethylbenzyl, trimethylbenzyl, chlorobenzyl, bromobenzyl and the like), aryl group (phenyl, tolyl, xylyl, .alpha.-naphtyl, .beta.-naphthyl) or a substituted aryl group (chlorophenyl, dichlorophenyl, trichlorophenyl, ethylphenyl, methoxydiphenyl, dimethoxyphenyl, aminophenyl, sulfonate phenyl, nitrophenyl, hydroxyphenyl and the like).",
@ -644,6 +686,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.24 represents a substituted or an unsubstituted aryl group or the cation group thereof, specifically including a substituted or an unsubstituted aryl group (phenyl, tolyl, xylyl, biphenyl, aminophenyl, .alpha.-naphthyl, .beta.-napthyl, anthranyl, pyrenyl, methoxyphenyl, dimethoxyphenyl, trimethoxyphenyl, ethoxyphenyl, diethoxyphenyl, chlorophenyl, dichlorophenyl, trichlorophenyl, bromophenyl, dibromophenyl, tribromophenyl, ethylphenyl, diethylphenyl, nitrophenyl, aminophenyl, dimethylaminophenyl, diethylaminophenyl, dibenzylaminophenyl, dipropylaminophenyl, morpholinophenyl, piperidinylphenyl, piperidinophenyl, diphenylaminophenyl, acetylaminophenyl, benzoylaminophenyl, acetylphenyl, benzoylphenyl, cyanophenyl, sulfonate phenyl, carboxylate phenyl and the like).",
@ -655,6 +698,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.25 represents a heterocyclic ring or the cation group thereof, specifically including a monovalent heterocyclic ring derived from cyclic rings, such as furan, thiophene, benzofuran, thionaphthene, dibenzofuran, carbazole, phenothiazine phenoxazine, pyridine and the like.",
@ -666,6 +710,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.26 represents hydrogen atom, alkyl group (methyl, ethyl, propyl, butyl and the like), or a substituted or an unsubstituted aryl group (phenyl, tolyl, xylyl, biphenyl, ethylphenyl, chlorophenyl, methoxyphenyl, ethoxyphenyl, nitrophenyl, aminophenyl, dimethylaminophenyl, diethylaminophenyl, acetylaminophenyl, .alpha.-naphthyl, .beta.-naphthyl, anthraryl, pyrenyl, sulfonate phenyl, carboxylate phenyl and the like. In the formula, Z.sub.7 represents an atom group required for the completion of pyran, thiapyran, selenapyran, telluropyran, benzopyran, benzothiapyran, benzoselenapyran, benzotelluropyran, naphthopyran, naphthothiapyran, or naphthoselenapyran, or naphthotelluropyran.",
@ -677,6 +722,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "L.sub.7 represents sulfur atom, oxygen atom or selenium atom or tellurium atom.",
@ -688,6 +734,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.27 and R.sub.28 individually represent hydrogen atom, alkoxy group, a substituted or an unsubstituted aryl group, alkenyl group and a heterocyclic group,",
@ -699,6 +746,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "More specifically, R.sub.27 and R.sub.28 individually represent hydrogen atom, alkyl group (methyl, ethyl, propyl, butyl and the like), alkyl sulfonate group, alkoxyl group (methoxy, ethoxy, propoxy, ethoxyethyl, methoxyethyl and the like), aryl group (phenyl, tolyl, xylyl, sulfonate phenyl, chlorophenyl, biphenyl, methoxyphenyl and the like), a substituted or an unsubstituted styryl group (styryl, p-methylstyryl, o-chlorostyryl, p-methoxystyryl and the like), a substituted or an unsubstituted 4-phenyl, 1,3-butadienyl group (r-phenyl, 1,3-butadienyl, 4-(p-methylphenyl), 1,3-butadienyl and the like), or a substituted or an unsubstituted heterocyclic group (quinolyl, pyridyl, carbazoyl, furyl and the like).",
@ -710,6 +758,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "As in the case of R, the same is true with R.sub.A and R.sub.B of the general formulas (II) and (III), respectively.",
@ -721,6 +770,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Then, in R, the symbols R.sub.8 ' to R.sub.14 ' individually correspond to R.sub.1 ' to R.sub.7 '; R.sub.8 \" to R.sub.14 \" individually correspond to R.sub.1 \" to R.sub.7 \"; in R.sub.B, R.sub.14 ' to R.sub.21 \" individually correspond to R.sub.1 ' to R.sub.7 '; R.sub.14 \" to R.sub.21 \" individually correspond to R.sub.1 \" to R.sub.7 \".",
@ -732,6 +782,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In the azulenium nucleus of the (1) to (12), described above, those represented by the formulas (3), (9) and (10) are more preferably used; and particularly, the formula (3) is preferable.",
@ -743,6 +794,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "R.sub.1 to R.sub.28, R.sub.1 ' to R.sub.21 ' and R.sub.1 \" to R.sub.21 \" preferably contain one or more well-known polar groups in order to impart water solubility to a compound (labeling agent) represented by the general formula (I), (II) or (III). The polar groups include, for example, hydroxyl group, alkylhydroxyl group, sulfonate group, alkylsulfonate group, carboxylate group, alkylcarboxylate group, tetra-ammonium base and the like. R.sub.1 to R.sub.28, R.sub.1 ' to R.sub.21 ', and R.sub.1 \" to R.sub.21 \" preferably contain one or more well-known reactive groups in order that the compound of the general formula (I) can form a covalent bond with a substance from a living organism.",
@ -754,6 +806,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The reactive groups include the reactive sites of isocyanate, isothiocyanate, succinimide ester, sulfosuccinimide ester, imide ester, hydrazine, nitroaryl halide, piperidine disulfide, maleimide, thiophthalimide, acid halide, sulfonyl halide, aziridine, azide nitrophenyl, azide amino, 3-(2-pyridyldithio) propionamide and the like. In these reactive sites, the following spacer groups (n=0, 1 to 6) may be interposed in order to prevent steric hindrance during on the bonding of a labeling agent and a substance from a living organism.",
@ -765,6 +818,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Preferable such reactive groups include isothiocyanate, sulfosuccinimide ester, succinimide ester maleimide and the like X.sub.1.sup..sym. represents an anion, including chloride ion, bromide ion, iodide ion, perchlorate ion, benzenesulfonate ion, p-toluene sulfonate ion, methylsulfate ion, ethylsulfate ion, propylsulfate ion, tetrafluoroborate ion, tetraphenylborate ion, hexafluorophosphate ion, benzenesulfinic acid salt ion, acetate ion, trifluoroacetate ion, propionate ion, benzoate ion, oxalate ion, succinate ion, malonate ion, oleate ion, stearate ion, citrate ion, monohydrogen diphosphate ion, dihydrogen monophosphate ion, pentachlorostannate ion, chlorosulfonate ion, fluorosulfonate ion, trifluoromethane sulfonate ion, hexafluoroantimonate ion, molybdate ion, tungstate ion, titanate ion, zirconate ion and the like.",
@ -776,6 +830,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Specific examples of these labeling agents are illustrated in Tables 1, 2 and 3, but are not limited thereto.",
@ -787,6 +842,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The synthetic method of these azulene dyes is described in U.S. Pat. No. 4,738,908.",
@ -859,6 +915,7 @@
"$ref": "#/texts/74"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CLAIMS",
@ -871,6 +928,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -882,6 +940,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -893,6 +952,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -904,6 +964,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -915,6 +976,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -926,6 +988,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -937,6 +1000,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -948,6 +1012,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -959,6 +1024,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -970,6 +1036,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -981,6 +1048,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -992,6 +1060,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1003,6 +1072,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1014,6 +1084,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1025,6 +1096,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1036,6 +1108,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1047,6 +1120,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1058,6 +1132,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1069,6 +1144,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -1080,6 +1156,7 @@
"$ref": "#/texts/54"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",

112
tests/data/groundtruth/docling_v2/pg06442728.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "pg06442728.xml",
"origin": {
"mimetype": "application/xml",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -56,6 +58,7 @@
"$ref": "#/texts/72"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Methods and apparatus for turbo code",
@ -71,6 +74,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "ABSTRACT",
@ -83,6 +87,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "An interleaver receives incoming data frames of size N. The interleaver indexes the elements of the frame with an N\u2081\u00d7N\u2082 index array. The interleaver then effectively rearranges (permutes) the data by permuting the rows of the index array. The interleaver employs the equation I(j,k)=I(j,\u03b1jk+\u03b2j)modP) to permute the columns (indexed by k) of each row (indexed by j). P is at least equal to N\u2082, \u03b2j is a constant which may be different for each row, and each \u03b1j is a relative prime number relative to P. After permuting, the interleaver outputs the data in a different order than received (e.g., receives sequentially row by row, outputs sequentially each column by column).",
@ -98,6 +103,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CROSS-REFERENCE TO RELATED APPLICATIONS",
@ -110,6 +116,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This application claims the benefit of U.S. Provisional Application No. 60/115,394 filed Jan. 11, 1999.",
@ -125,6 +132,7 @@
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "FIELD OF THE INVENTION",
@ -137,6 +145,7 @@
"$ref": "#/texts/5"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "This invention relates generally to communication systems and, more particularly, to interleavers for performing code modulation.",
@ -179,6 +188,7 @@
"$ref": "#/texts/17"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BACKGROUND OF THE INVENTION",
@ -191,6 +201,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Techniques for encoding communication channels, known as coded modulation, have been found to improve the bit error rate (BER) of electronic communication systems such as modem and wireless communication systems. Turbo coded modulation has proven to be a practical, power-efficient, and bandwidth-efficient modulation method for \u201crandom-error\u201d channels characterized by additive white Gaussian noise (AWGN) or fading. These random-error channels can be found, for example, in the code division multiple access (CDMA) environment. Since the capacity of a CDMA environment is dependent upon the operating signal to noise ratio, improved performance translates into higher capacity.",
@ -202,6 +213,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "An aspect of turbo coders which makes them so effective is an interleaver which permutes the original received or transmitted data frame before it is input to a second encoder. The permuting is accomplished by randomizing portions of the signal based upon one or more randomizing algorithms. Combining the permuted data frames with the original data frames has been shown to achieve low BERs in AWGN and fading channels. The interleaving process increases the diversity in the data such that if the modulated symbol is distorted in transmission the error may be recoverable with the use of error correcting algorithms in the decoder.",
@ -213,6 +225,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A conventional interleaver collects, or frames, the signal points to be transmitted into an array, where the array is sequentially filled up row by row. After a predefined number of signal points have been framed, the interleaver is emptied by sequentially reading out the columns of the array for transmission. As a result, signal points in the same row of the array that were near each other in the original signal point flow are separated by a number of signal points equal to the number of rows in the array. Ideally, the number of columns and rows would be picked such that interdependent signal points, after transmission, would be separated by more than the expected length of an error burst for the channel.",
@ -224,6 +237,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Non-uniform interleaving achieves \u201cmaximum scattering\u201d of data and \u201cmaximum disorder\u201d of the output sequence. Thus the redundancy introduced by the two convolutional encoders is more equally spread in the output sequence of the turbo encoder. The minimum distance is increased to much higher values than for uniform interleaving. A persistent problem for non-uniform interleaving is how to practically implement the interleaving while achieving sufficient \u201cnon-uniformity,\u201d and minimizing delay compensations which limit the use for applications with real-time requirements.",
@ -235,6 +249,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Finding an effective interleaver is a current topic in the third generation CDMA standard activities. It has been determined and generally agreed that, as the frame size approaches infinity, the most effective interleaver is the random interleaver. However, for finite frame sizes, the decision as to the most effective interleaver is still open for discussion.",
@ -246,6 +261,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Accordingly there exists a need for systems and methods of interleaving codes that improve non-uniformity for finite frame sizes.",
@ -257,6 +273,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "There also exists a need for such systems and methods of interleaving codes which are relatively simple to implement.",
@ -268,6 +285,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It is thus an object of the present invention to provide systems and methods of interleaving codes that improve non-uniformity for finite frame sizes.",
@ -279,6 +297,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It is also an object of the present invention to provide systems and methods of interleaving codes which are relatively simple to implement.",
@ -290,6 +309,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "These and other objects of the invention will become apparent to those skilled in the art from the following description thereof.",
@ -314,6 +334,7 @@
"$ref": "#/texts/22"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "SUMMARY OF THE INVENTION",
@ -326,6 +347,7 @@
"$ref": "#/texts/18"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The foregoing objects, and others, may be accomplished by the present invention, which interleaves a data frame, where the data frame has a predetermined size and is made up of portions. An embodiment of the invention includes an interleaver for interleaving these data frames. The interleaver includes an input memory configured to store a received data frame as an array organized into rows and columns, a processor connected to the input memory and configured to permute the received data frame in accordance with the equation D(j,k)=D (j, (\u03b1jk+\u03b2j)modP), and a working memory in electrical communication with the processor and configured to store a permuted version of the data frame. The elements of the equation are as follows: D is the data frame, j and k are indexes to the rows and columns, respectively, in the data frame, \u03b1 and \u03b2 are sets of constants selected according to the current row, and P and each \u03b1j are relative prime numbers. (\u201cRelative prime numbers\u201d connotes a set of numbers that have no common divisor other than 1. Members of a set of relative prime numbers, considered by themselves, need not be prime numbers.)",
@ -337,6 +359,7 @@
"$ref": "#/texts/18"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Another embodiment of the invention includes a method of storing a data frame and indexing it by an N\u2081\u00d7N\u2082 index array I, where the product of N\u2081 and N\u2082 is at least equal to N. The elements of the index array indicate positions of the elements of the data frame. The data frame elements may be stored in any convenient manner and need not be organized as an array. The method further includes permuting the index array according to I(j,k)=I(j,(\u03b1jk+\u03b2j)modP), wherein I is the index array, and as above j and k are indexes to the rows and columns, respectively, in the index array, \u03b1 and \u03b2 are sets of constants selected according to the current row, and P and each \u03b1j are relative prime numbers. The data frame, as indexed by the permuted index array I, is effectively permuted.",
@ -348,6 +371,7 @@
"$ref": "#/texts/18"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Still another embodiment of the invention includes an interleaver which includes a storage device for storing a data frame and for storing an N\u2081\u00d7N\u2082 index array I, where the product of N\u2081 and N\u2082 is at least equal to N. The elements of the index array indicate positions of the elements of the data frame. The data frame elements may be stored in any convenient manner and need not be organized as an array. The interleaver further includes a permuting device for permuting the index array according to I(j,k)=I(j,(\u03b1jk+\u03b2j)modP), wherein I is the index array, and as above j and k are indexes to the rows and columns, respectively, in the index array, \u03b1 and \u03b2 are sets of constants selected according to the current row, and P and each \u03b1j are relative prime numbers. The data frame, as indexed by the permuted index array I, is effectively permuted.",
@ -359,6 +383,7 @@
"$ref": "#/texts/18"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The invention will next be described in connection with certain illustrated embodiments and practices. However, it will be clear to those skilled in the art that various modifications, additions and subtractions can be made without departing from the spirit or scope of the claims.",
@ -389,6 +414,7 @@
"$ref": "#/texts/29"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "BRIEF DESCRIPTION OF THE DRAWINGS",
@ -401,6 +427,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The invention will be more clearly understood by reference to the following detailed description of an exemplary embodiment in conjunction with the accompanying drawings, in which:",
@ -412,6 +439,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 depicts a diagram of a conventional turbo encoder.",
@ -423,6 +451,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 2 depicts a block diagram of the interleaver illustrated in FIG. 1;",
@ -434,6 +463,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 3 depicts an array containing a data frame, and permutation of that array;",
@ -445,6 +475,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 4 depicts a data frame stored in consecutive storage locations;",
@ -456,6 +487,7 @@
"$ref": "#/texts/23"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 5 depicts an index array for indexing the data frame shown in FIG. 4, and permutation of the index array.",
@ -591,6 +623,7 @@
"$ref": "#/texts/71"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "DETAILED DESCRIPTION OF THE INVENTION",
@ -603,6 +636,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 1 illustrates a conventional turbo encoder. As illustrated, conventional turbo encoders include two encoders 20 and an interleaver 100. An interleaver 100 in accordance with the present invention receives incoming data frames 110 of size N, where N is the number of bits, number of bytes, or the number of some other portion the frame may be separated into, which are regarded as frame elements. The interleaver 100 separates the N frame elements into sets of data, such as rows. The interleaver then rearranges (permutes) the data in each set (row) in a pseudo-random fashion. The interleaver 100 may employ different methods for rearranging the data of the different sets. However, those skilled in the art will recognize that one or more of the methods could be reused on one or more of the sets without departing from the scope of the invention. After permuting the data in each of the sets, the interleaver outputs the data in a different order than received.",
@ -614,6 +648,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The interleaver 100 may store the data frame 110 in an array of size N\u2081\u00d7N\u2082 such that N\u2081*N\u2082=N. An example depicted in FIG. 3 shows an array 350 having 3 rows (N\u2081=3) of 6 columns (N\u2082=6)for storing a data frame 110 having 18 elements, denoted Frame Element 00 (FE00) through FE17 (N=18). While this is the preferred method, the array may also be designed such that N\u2081*N\u2082 is a fraction of N such that one or more of the smaller arrays is/are operated on in accordance with the present invention and the results from each of the smaller arrays are later combined.",
@ -625,6 +660,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "To permute array 350 according to the present invention, each row j of array 350 is individually operated on, to permute the columns k of each row according to the equation:",
@ -636,6 +672,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "D\u2081(j,k)=D(j,(\u03b1k+\u03b2)modP)",
@ -647,6 +684,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "where:",
@ -658,6 +696,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "j and k are row and column indices, respectively, in array 350;",
@ -669,6 +708,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "P is a number greater than or equal to N\u2082;",
@ -680,6 +720,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "\u03b1j and P arc relative prime numbers (one or both can be non-prime numbers, but the only divisor that they have in common is 1);",
@ -691,6 +732,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "\u03b2j is a constant, one value associated with each row.",
@ -702,6 +744,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Once the data for all of the rows are permuted, the new array is read out column by column. Also, once the rows have been permuted, it is possible (but not required) to permute the data grouped by column before outputting the data. In the event that both the rows and columns are permuted, the rows, the columns or both may be permuted in accordance with the present invention. It is also possible to transpose rows of array, for example by transposing bits in the binary representation of the row index j. (In a four-row array, for example, the second and third rows would be transposed under this scheme.) It is also possible that either the rows or the columns, but not both may be permuted in accordance with a different method of permuting. Those skilled in the art will recognize that the system could be rearranged to store the data column by column, permute each set of data in a column and read out the results row by row without departing from the scope of the invention.",
@ -713,6 +756,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "These methods of interleaving are based on number theory and may be implemented in software and/or hardware (i.e. application specific integrated circuits (ASIC), programmable logic arrays (PLA), or any other suitable logic devices). Further, a single pseudo random sequence generator (i.e. m-sequence, M-sequence, Gold sequence, Kasami sequence . . . ) can be employed as the interleaver.",
@ -724,6 +768,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In the example depicted in FIG. 3, the value selected for P is 6, the values of \u03b1 are 5 for all three rows, and the values of \u03b2 are 1, 2, and 3 respectively for the three rows. (These are merely exemplary. Other numbers may be chosen to achieve different permutation results.) The values of \u03b1 (5) are each relative prime numbers relative to the value of P (6), as stipulated above.",
@ -735,6 +780,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Calculating the specified equation with the specified values for permuting row 0 of array D 350 into row 0 of array D\u2081 360 proceeds as:",
@ -746,6 +792,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "and the permuted data frame is contained in array D\u2081 360 shown in FIG. 3. Outputting the array column by column outputs the frame elements in the order:",
@ -757,6 +804,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1,8,15,0,7,14,5,6,13,4,11,12,3,10,17,2,9,16.",
@ -768,6 +816,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In an alternative practice of the invention, data frame 110 is stored in consecutive storage locations, not as an array or matrix, and a separate index array is stored to index the elements of the data frame, the index array is permuted according to the equations of the present invention, and the data frame is output as indexed by the permuted index array.",
@ -779,6 +828,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 4 depicts a block 400 of storage 32 elements in length (thus having offsets of 0 through 31 from a starting storage location). A data frame 110, taken in this example to be 22 elements long and thus to consist of elements FE00 through FE21, occupies offset locations 00 through 21 within block 400. Offset locations 22 through 31 of block 400 contain unknown contents. A frame length of 22 elements is merely exemplary, and other lengths could be chosen. Also, storage of the frame elements in consecutive locations is exemplary, and non-consecutive locations could be employed.",
@ -790,6 +840,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "FIG. 5 depicts index array I 550 for indexing storage block 400. It is organized as 4 rows of 8 columns each (N\u2081=4, N\u2082=8, N=N\u2081*N\u2082=32). Initial contents are filled in to array I 550 as shown in FIG. 5 sequentially. This sequential initialization yields the same effect as a row-by-row read-in of data frame 110.",
@ -801,6 +852,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The index array is permuted according to",
@ -812,6 +864,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "I\u2081(j,k)=I(j,(\u03b1j*k+\u03b2j)modP)",
@ -823,6 +876,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "where",
@ -834,6 +888,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "\u03b1=1, 3, 5, 7",
@ -845,6 +900,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "\u03b2=0, 0, 0, 0",
@ -856,6 +912,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "P=8",
@ -867,6 +924,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "These numbers are exemplary and other numbers could be chosen, as long as the stipulations are observed that P is at least equal to N\u2082 and that each value of \u03b1 is a relative prime number relative to the chosen value of P.",
@ -878,6 +936,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "If the equation is applied to the columns of row 2, for example, it yields:",
@ -889,6 +948,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Applying the equation comparably to rows 0, 1, and 3 produces the permuted index array I\u2081 560 shown in FIG. 5.",
@ -900,6 +960,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The data frame 110 is read out of storage block 400 and output in the order specified in the permuted index array I\u2081 560 taken column by column. This would output storage locations in offset order:",
@ -911,6 +972,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "0,8,16,24,1,11,21,31,2,14,18,30,3,9,23,29,4,12,20,28,5,15,17,27,6,10,22,26,7,13,19,25.",
@ -922,6 +984,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "However, the example assumed a frame length of 22 elements, with offset locations 22-31 in block 400 not being part of the data frame. Accordingly, when outputting the data frame it would be punctured or pruned to a length of 22; i.e., offset locations greater than 21 are ignored. The data frame is thus output with an element order of 0,8,16,1,11,21,2,14,18,3,9,4,12,20,5,15,17,6,10,7,13,19.",
@ -933,6 +996,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In one aspect of the invention, rows of the array may be transposed prior to outputting, for example by reversing the bits in the binary representations of row index j.",
@ -944,6 +1008,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "There are a number of different ways to implement the interleavers 100 of the present invention. FIG. 2 illustrates an embodiment of the invention wherein the interleaver 100 includes an input memory 300 for receiving and storing the data frame 110. This memory 300 may include shift registers, RAM or the like. The interleaver 100 may also include a working memory 310 which may also include RAM, shift registers or the like. The interleaver includes a processor 320 (e.g., a microprocessor, ASIC, etc.) which may be configured to process I(j,k) in real time according to the above-identified equation or to access a table which includes the results of I(j,k) already stored therein. Those skilled in the art will recognize that memory 300 and memory 310 may be the same memory or they may be separate memories.",
@ -955,6 +1020,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "For real-time determinations of I(j,k), the first row of the index array is permuted and the bytes corresponding to the permuted index are stored in the working memory. Then the next row is permuted and stored, etc. until all rows have been permuted and stored. The permutation of rows may be done sequentially or in parallel.",
@ -966,6 +1032,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Whether the permuted I(j,k) is determined in real time or by lookup, the data may be stored in the working memory in a number of different ways. It can be stored by selecting the data from the input memory in the same order as the I(j,k)s in the permuted index array (i.e., indexing the input memory with the permuting function) and placing them in the working memory in sequential available memory locations. It may also be stored by selecting the bytes in the sequence they were stored in the input memory (i.e., FIFO) and storing them in the working memory directly into the location determined by the permuted I(j,k)s (i.e., indexing the working memory with the permuting function). Once this is done, the data may be read out of the working memory column by column based upon the permuted index array. As stated above, the data could be subjected to another round of permuting after it is stored in the working memory based upon columns rather than on rows to achieve different results.",
@ -977,6 +1044,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "If the system is sufficiently fast, one of the memories could be eliminated and as a data element is received it could be placed into the working memory, in real time or by table lookup, in the order corresponding to the permuted index array.",
@ -988,6 +1056,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "The disclosed interleavers are compatible with existing turbo code structures. These interleavers offer superior performance without increasing system complexity.",
@ -999,6 +1068,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "In addition, those skilled in the art will realize that de-interleavers can be used to decode the interleaved data frames. The construction of de-interleavers used in decoding turbo codes is well known in the art. As such they are not further discussed herein. However, a de-interleaver corresponding to the embodiments can be constructed using the permuted sequences discussed above.",
@ -1010,6 +1080,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Although the embodiment described above is a turbo encoder such as is found in a CDMA system, those skilled in the art realize that the practice of the invention is not limited thereto and that the invention may be practiced for any type of interleaving and de-interleaving in any communication system.",
@ -1021,6 +1092,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It will thus be seen that the invention efficiently attains the objects set forth above, among those made apparent from the preceding description. In particular, the invention provides improved apparatus and methods of interleaving codes of finite length while minimizing the complexity of the implementation.",
@ -1032,6 +1104,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It will be understood that changes may be made in the above construction and in the foregoing sequences of operation without departing from the scope of the invention. It is accordingly intended that all matter contained in the above description or shown in the accompanying drawings be interpreted as illustrative rather than in a limiting sense.",
@ -1043,6 +1116,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "It is also to be understood that the following claims are intended to cover all of the generic and specific features of the invention as described herein, and all statements of the scope of the invention which, as a matter of language, might be said to fall therebetween.",
@ -1160,6 +1234,7 @@
"$ref": "#/texts/107"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "CLAIMS",
@ -1172,6 +1247,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "1. A method of interleaving elements of frames of signal data communication channel, the method comprising; storing a frame of signal data comprising a plurality of elements as an array D having N\u2081 rows enumerated as 0, 1, . . . N\u2081\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1; and permuting array D into array D\u2081 according to D\u2081(\ud835\udc57,\ud835\udc58)=D(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays D and D\u2081; k is an index through the columns of arrays D and D\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P.",
@ -1183,6 +1259,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "2. The method according to claim 1 wherein said elements of array D are stored in accordance with a first order and wherein said elements of array D\u2081 are output in accordance with a second order.",
@ -1194,6 +1271,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "3. The method according to claim 2 wherein elements of array D are stored row by row and elements of array D\u2081 are output column by column.",
@ -1205,6 +1283,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "4. The method according to claim 1 further including outputting of array D\u2081 and wherein the product of N\u2081 and N\u2082 is greater than the number of elements in the frame and the frame is punctured during outputting to the number of elements in the frame.",
@ -1216,6 +1295,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "5. A method of interleaving elements of frames of signal data communication channel, the method comprising; creating and storing an index array I having N\u2081 rows enumerated as 0, 1, . . . N\u2081\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1, storing elements of a frame of signal data in each of a plurality of storage locations; storing in row-by-row sequential positions in array I values indicative of corresponding locations of frame elements; and permuting array I into array I\u2081 according to I\u2081(\ud835\udc57,\ud835\udc58)=I(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays I and I\u2081; k is an index through the columns of arrays I and I\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P, whereby the frame of signal data as indexed by array I\u2081 is effectively permuted.",
@ -1227,6 +1307,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "6. The method according to claim 5 further including permuting said stored elements according to said permuted index array I\u2081.",
@ -1238,6 +1319,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "7. The method according to claim 5 wherein said elements of the frame of data are output as indexed by entries of array I\u2081 taken other than row by row.",
@ -1249,6 +1331,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "8. The method according to claim 7 wherein elements of the frame of data are output as indexed by entries of array I\u2081 taken column by column.",
@ -1260,6 +1343,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "9. The method according to claim 5 including the step of transposing rows of array I prior to the step of permuting array I.",
@ -1271,6 +1355,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "10. The method according to claim 5 wherein N\u2081 is equal to 4, N\u2082 is equal to 8, P is equal to 8, and the values of \u03b1j are different for each row and are chosen from a group consisting of 1, 3, 5, and 7.",
@ -1282,6 +1367,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "11. The method according to claim 10 wherein the values of \u03b1j are 1, 3, 5, and 7 for j=0, 1, 2, and 3 respectively.",
@ -1293,6 +1379,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "12. The method according to claim 11 wherein all values of \u03b2 are zero.",
@ -1304,6 +1391,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "13. The method according to claim 10 wherein the values of \u03b1j are 1, 5, 3, and 7 for j=0, 1, 2, and 3 respectively.",
@ -1315,6 +1403,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "14. The method according to claim 13 wherein all values of \u03b2 are zero.",
@ -1326,6 +1415,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "15. The method according to claim 5 wherein all values of \u03b2 are zero.",
@ -1337,6 +1427,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "16. The method according to claim 5 wherein at least two values of \u03b2 are the same.",
@ -1348,6 +1439,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "17. The method according to claim 5 further including outputting of the frame of data and wherein the product of N\u2081 and N\u2082 is greater than the number of elements in the frame of data and the frame of data is punctured during outputting to the number of elements in the frame of data.",
@ -1359,6 +1451,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "18. An interleaver for interleaving elements of frames of data, the interleaver comprising; storage means for storing a frame of data comprising a plurality of elements as an array D having N\u2081 rows enumerated as 0, 1, . . . N\u2082\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1, and permuting means for permuting array D into array D\u2081 according to D\u2081(\ud835\udc57,\ud835\udc58)=D(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays D and D\u2081; k is an index through the columns of arrays D and D\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P.",
@ -1370,6 +1463,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "19. The interleaver according to claim 18 including means for storing said elements of array D in accordance with a first order and means for outputting said elements of array D\u2081 in accordance with a second order.",
@ -1381,6 +1475,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "20. The interleaver according to claim 19 wherein said means for storing said elements of array D stores row by row and said means for outputting elements of array D\u2081 outputs column by column.",
@ -1392,6 +1487,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "21. The interleaver according to claim 18 including means for outputting said array D\u2081 and for puncturing said array D\u2081 to the number of elements in the frame when the product of N\u2081 and N\u2082 is greater than the number of elements in the frame.",
@ -1403,6 +1499,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "22. An interleaver for interleaving elements of frames of data, the interleaver comprising; means for storing an index array I having N\u2081 rows enumerated as 0, 1, . . . N\u2081\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1, and means for receiving a frame of data and storing elements of the frame of data in each of a plurality of storage locations; means for storing in row-by-row sequential positions in array I values indicative of corresponding locations of frame elements; and means for permuting array I into array I\u2081 according to: I\u2081(\ud835\udc57,\ud835\udc58)=I(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays I and I\u2081; k is an index through the columns of arrays I and I\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P, whereby the frame of data as indexed by array I\u2081 is effectively permuted.",
@ -1414,6 +1511,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "23. The interleaver according to claim 22 further including means for permuting said stored elements according to said permuted index array I\u2081.",
@ -1425,6 +1523,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "24. The interleaver according to claim 22 including means for outputting frame elements as indexed by entries of array I\u2081 taken other than row by row.",
@ -1436,6 +1535,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "25. The interleaver according to claim 24 including means for outputting frame elements as indexed by entries of array I\u2081 taken column by column.",
@ -1447,6 +1547,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "26. The interleaver according to claim 22 wherein the product of N\u2081 and N\u2082 is greater than the number of elements in the frame and the frame is punctured by the means for outputting to the number of elements in the frame.",
@ -1458,6 +1559,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "27. An interleaver for interleaving elements of frames of data, the interleaver comprising; an input memory for storing a received frame of data comprising a plurality of elements as an array D having N\u2081 rows enumerated as 0, 1, . . . N\u2081\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1; a processor coupled to said input memory for permuting array D into array D\u2081 according to D\u2081(\ud835\udc57,\ud835\udc58)=D(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays D and D\u2081; k is an index through the columns of arrays D and D\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P, and a working memory coupled to said processor and configured to store the permuted array D\u2081.",
@ -1469,6 +1571,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "28. The interlcavcr according to claim 27 wherein said input memory stores said elements of array D in accordance with a first order and said working memory outputs said elements of array D\u2081 in accordance with a second order.",
@ -1480,6 +1583,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "29. The interleaver according to claim 28 wherein said input memory stores elements of array D row by row and said working memory outputs elements of array D\u2081 column by column.",
@ -1491,6 +1595,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "30. The interleaver according to claim 27 said working memory punctures said array D\u2081 to the number of elements in the frame when the product of N\u2081 and N\u2082 is greater than the number of elements in the frame.",
@ -1502,6 +1607,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "31. An interleaver for interleaving elements of frames of data, the interleaver comprising; a memory for storing an index array I having N\u2081 rows enumerated as 0, 1, . . . N\u2081\u22121; and N\u2082 columns enumerated as 0, 1, . . . N\u2082\u22121, wherein N\u2081 and N\u2082 are positive integers greater than 1, and said memory also for storing elements of a received frame of data in each of a plurality of storage locations; a processor coupled to said memory for storing in row-by-row sequential positions in array I values indicative of corresponding locations of frame elements; and said processor also for permuting array I into array I\u2081 stored in said memory according to: I\u2081(\ud835\udc57,\ud835\udc58)=I(\ud835\udc57,(\u03b1j\ud835\udc58+\u03b2j)\ud835\udc5a\ud835\udc5c\ud835\udc51\ud835\udc43) wherein j is an index through the rows of arrays I and I\u2081; k is an index through the columns of arrays I and I\u2081; \u03b1j and \u03b2j are integers predetermined for each row j; P is an integer at least equal to N\u2082; and each \u03b1j is a relative prime number relative to P, and whereby the frame of data as indexed by array I\u2081 is effectively permuted.",
@ -1513,6 +1619,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "32. The interleaver according to claim 31 wherein said processor permutes said stored elements according to said permuted index array I\u2081.",
@ -1524,6 +1631,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "33. The interleaver according to claim 31 wherein said memory outputs frame elements as indexed by entries of array I\u2081 taken other than row by row.",
@ -1535,6 +1643,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "34. The interleaver according to claim 33 wherein said memory outputs frame elements as indexed by entries of array I\u2081 taken column by column.",
@ -1546,6 +1655,7 @@
"$ref": "#/texts/72"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "35. The interleaver according to claim 31 wherein said memory punctures the frame of data to the number of elements in the frame of data when the product of N\u2081 and N\u2082 is greater than the number of elements in the frame of data.",

2
tests/data/groundtruth/docling_v2/picture_classification.json
View File

File diff suppressed because one or more lines are too long

128
tests/data/groundtruth/docling_v2/pntd.0008301.xml.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "pntd.0008301",
"origin": {
"mimetype": "application/xml",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -41,6 +42,7 @@
"$ref": "#/texts/61"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -211,6 +213,7 @@
"$ref": "#/texts/115"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -250,6 +253,7 @@
"$ref": "#/texts/62"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Risk factors associated with failing pre-transmission assessment surveys (pre-TAS) in lymphatic filariasis elimination programs: Results of a multi-country analysis",
@ -261,6 +265,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Burgert-Brucker Clara R.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Zoerhoff Kathryn L.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Headland Maureen; 1: Global Health Division, RTI International, Washington, DC, United States of America, 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Shoemaker Erica A.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Stelmach Rachel; 1: Global Health Division, RTI International, Washington, DC, United States of America; Karim Mohammad Jahirul; 3: Department of Disease Control, Ministry of Health and Family Welfare, Dhaka, Bangladesh; Batcho Wilfrid; 4: National Control Program of Communicable Diseases, Ministry of Health, Cotonou, Benin; Bougouma Clarisse; 5: Lymphatic Filariasis Elimination Program, Minist\u00e8re de la Sant\u00e9, Ouagadougou, Burkina Faso; Bougma Roland; 5: Lymphatic Filariasis Elimination Program, Minist\u00e8re de la Sant\u00e9, Ouagadougou, Burkina Faso; Benjamin Didier Biholong; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Georges Nko'Ayissi; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Marfo Benjamin; 7: Neglected Tropical Diseases Programme, Ghana Health Service, Accra, Ghana; Lemoine Jean Frantz; 8: Ministry of Health, Port-au-Prince, Haiti; Pangaribuan Helena Ullyartha; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Wijayanti Eksi; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Coulibaly Yaya Ibrahim; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Doumbia Salif Seriba; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Rimal Pradip; 11: Epidemiology and Disease Control Division, Department of Health Service, Kathmandu, Nepal; Salissou Adamou Bacthiri; 12: Programme Onchocercose et Filariose Lymphatique, Minist\u00e8re de la Sant\u00e9, Niamey, Niger; Bah Yukaba; 13: National Neglected Tropical Disease Program, Ministry of Health and Sanitation, Freetown, Sierra Leone; Mwingira Upendo; 14: Neglected Tropical Disease Control Programme, National Institute for Medical Research, Dar es Salaam, Tanzania; Nshala Andreas; 15: IMA World Health/Tanzania NTD Control Programme, Uppsala University, & TIBA Fellow, Dar es Salaam, Tanzania; Muheki Edridah; 16: Programme to Eliminate Lymphatic Filariasis, Ministry of Health, Kampala, Uganda; Shott Joseph; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Yevstigneyeva Violetta; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Ndayishimye Egide; 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Baker Margaret; 1: Global Health Division, RTI International, Washington, DC, United States of America; Kraemer John; 1: Global Health Division, RTI International, Washington, DC, United States of America, 18: Georgetown University, Washington, DC, United States of America; Brady Molly; 1: Global Health Division, RTI International, Washington, DC, United States of America",
@ -276,6 +281,7 @@
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Abstract",
@ -288,6 +294,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Achieving elimination of lymphatic filariasis (LF) as a public health problem requires a minimum of five effective rounds of mass drug administration (MDA) and demonstrating low prevalence in subsequent assessments. The first assessments recommended by the World Health Organization (WHO) are sentinel and spot-check sites\u2014referred to as pre-transmission assessment surveys (pre-TAS)\u2014in each implementation unit after MDA. If pre-TAS shows that prevalence in each site has been lowered to less than 1% microfilaremia or less than 2% antigenemia, the implementation unit conducts a TAS to determine whether MDA can be stopped. Failure to pass pre-TAS means that further rounds of MDA are required. This study aims to understand factors influencing pre-TAS results using existing programmatic data from 554 implementation units, of which 74 (13%) failed, in 13 countries. Secondary data analysis was completed using existing data from Bangladesh, Benin, Burkina Faso, Cameroon, Ghana, Haiti, Indonesia, Mali, Nepal, Niger, Sierra Leone, Tanzania, and Uganda. Additional covariate data were obtained from spatial raster data sets. Bivariate analysis and multilinear regression were performed to establish potential relationships between variables and the pre-TAS result. Higher baseline prevalence and lower elevation were significant in the regression model. Variables statistically significantly associated with failure (p-value \u22640.05) in the bivariate analyses included baseline prevalence at or above 5% or 10%, use of Filariasis Test Strips (FTS), primary vector of Culex, treatment with diethylcarbamazine-albendazole, higher elevation, higher population density, higher enhanced vegetation index (EVI), higher annual rainfall, and 6 or more rounds of MDA. This paper reports for the first time factors associated with pre-TAS results from a multi-country analysis. This information can help countries more effectively forecast program activities, such as the potential need for more rounds of MDA, and prioritize resources to ensure adequate coverage of all persons in areas at highest risk of failing pre-TAS.Author summaryAchieving elimination of lymphatic filariasis (LF) as a public health problem requires a minimum of five rounds of mass drug administration (MDA) and being able to demonstrate low prevalence in several subsequent assessments. LF elimination programs implement sentinel and spot-check site assessments, called pre-TAS, to determine whether districts are eligible to implement more rigorous population-based surveys to determine whether MDA can be stopped or if further rounds are required. Reasons for failing pre-TAS are not well understood and have not previously been examined with data compiled from multiple countries. For this analysis, we analyzed data from routine USAID and WHO reports from Bangladesh, Benin, Burkina Faso, Cameroon, Ghana, Haiti, Indonesia, Mali, Nepal, Niger, Sierra Leone, Tanzania, and Uganda. In a model that included multiple variables, high baseline prevalence and lower elevation were significant. In models comparing only one variable to the outcome, the following were statistically significantly associated with failure: higher baseline prevalence at or above 5% or 10%, use of the FTS, primary vector of Culex, treatment with diethylcarbamazine-albendazole, lower elevation, higher population density, higher Enhanced Vegetation Index, higher annual rainfall, and six or more rounds of mass drug administration. These results can help national programs plan MDA more effectively, e.g., by focusing resources on areas with higher baseline prevalence and/or lower elevation.",
@ -315,6 +322,7 @@
"$ref": "#/texts/9"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Introduction",
@ -327,6 +335,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Lymphatic filariasis (LF), a disease caused by parasitic worms transmitted to humans by mosquito bite, manifests in disabling and stigmatizing chronic conditions including lymphedema and hydrocele. To eliminate LF as a public health problem, the World Health Organization (WHO) recommends two strategies: reducing transmission through annual mass drug administration (MDA) and reducing suffering through ensuring the availability of morbidity management and disability prevention services to all patients [1]. For the first strategy, eliminating LF as a public health problem is defined as a \u2018reduction in measurable prevalence in infection in endemic areas below a target threshold at which further transmission is considered unlikely even in the absence of MDA\u2019 [2]. As of 2018, 14 countries have eliminated LF as a public health problem while 58 countries remain endemic for LF [3].",
@ -338,6 +347,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The road to elimination as a public health problem has several milestones. First, where LF prevalence at baseline has exceeded 1% as measured either through microfilaremia (Mf) or antigenemia (Ag), MDA is implemented and treatment coverage is measured in all implementation units, which usually correspond to districts. Implementation units must complete at least five rounds of \u2018effective\u2019 treatment, i.e. treatment with a minimum coverage of 65% of the total population. Then, WHO recommends sentinel and spot-check site assessments\u2014referred to as pre-transmission assessment surveys (pre-TAS)\u2014in each implementation unit to determine whether prevalence in each site is less than 1% Mf or less than 2% Ag [4]. Next, if these thresholds are met, national programs can progress to the first transmission assessment survey (TAS). The TAS is a population-based cluster or systematic survey of six- and seven-year-old children to assess whether transmission has fallen below the threshold at which infection is believed to persist. TAS is conducted at least three times, with two years between each survey. TAS 1 results determine if it is appropriate to stop MDA or whether further rounds are required. Finally, when TAS 2 and 3 also fall below the set threshold in every endemic implementation unit nationwide and morbidity criteria have been fulfilled, the national program submits a dossier to WHO requesting that elimination be officially validated.",
@ -349,6 +359,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Pre-TAS include at least one sentinel and one spot-check site per one million population. Sentinel sites are established at the start of the program in villages where LF prevalence was believed to be relatively high. Spot-check sites are villages not previously tested but purposively selected as potentially high-risk areas due to original high prevalence, low coverage during MDA, high vector density, or other factors [4]. At least six months after MDA implementation, data are collected from a convenience sample of at least 300 people over five years old in each site. Originally, Mf was recommended as the indicator of choice for pre-TAS, assessed by blood smears taken at the time of peak parasite periodicity [4]. WHO later recommended the use of circulating filarial antigen rapid diagnostic tests, BinaxNow immunochromatographic card tests (ICTs), and after 2016, Alere Filariasis Test Strips (FTS), because they are more sensitive, easier to implement, and more flexible about time of day that blood can be taken [5].",
@ -360,6 +371,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "When a country fails to meet the established thresholds in a pre-TAS, they must implement at least two more rounds of MDA. National programs need to forecast areas that might fail pre-TAS and need repeated MDA, so that they can inform the community and district decision-makers of the implications of pre-TAS failure, including the need for continued MDA to lower prevalence effectively. In addition, financial and human resources must be made available for ordering drugs, distributing drugs, supervision and monitoring to implement the further MDA rounds. Ordering drugs and providing MDA budgets often need to be completed before the pre-TAS are implemented, so contingency planning and funding are important to ensure rounds of MDA are not missed.",
@ -371,6 +383,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This study aims to understand which factors are associated with the need for additional rounds of MDA as identified by pre-TAS results using programmatic data from 13 countries. The factors associated with failing pre-TAS are not well understood and have not previously been examined at a multi-country scale in the literature. We examine the association between pre-TAS failure and baseline prevalence, parasites, environmental factors, MDA implementation, and pre-TAS implementation. Understanding determinants of pre-TAS failure will help countries identify where elimination may be most difficult and prioritize the use of limited LF elimination resources.",
@ -401,6 +414,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Methods",
@ -413,6 +427,7 @@
"$ref": "#/texts/10"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This is a secondary data analysis using existing data, collected for programmatic purposes. Data for this analysis come from 568 districts in 13 countries whose LF elimination programs were supported by the United States Agency for International Development (USAID) through the ENVISION project, led by RTI International, and the END in Africa and END in Asia projects, led by FHI 360. These countries are Bangladesh, Benin, Burkina Faso, Cameroon, Ghana, Haiti, Indonesia, Mali, Nepal, Niger, Sierra Leone, Tanzania, and Uganda. The data represent all pre-TAS funded by USAID from 2012 to 2017 and, in some cases, surveys funded by host government or other non-United States government funders. Because pre-TAS data were collected as part of routine program activities in most countries, in general, ethical clearance was not sought for these surveys. Our secondary analysis only included the aggregated survey results and therefore did not constitute human subjects research; no ethical approval was required.",
@ -424,6 +439,7 @@
"$ref": "#/texts/10"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Building on previous work, we delineated five domains of variables that could influence pre-TAS outcomes: prevalence, agent, environment, MDA, and pre-TAS implementation (Table 1) [6\u20138]. We prioritized key concepts that could be measured through our data or captured through publicly available global geospatial data sets.",
@ -439,6 +455,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Data sources",
@ -451,6 +468,7 @@
"$ref": "#/texts/13"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Information on baseline prevalence, MDA coverage, the number of MDA rounds, and pre-TAS information (month and year of survey, district, site name, and outcome) was gathered through regular reporting for the USAID-funded NTD programs (ENVISION, END in Africa, and END in Asia). These data were augmented by other reporting data such as the country\u2019s dossier data annexes, the WHO Preventive Chemotherapy and Transmission Control Databank, and WHO reporting forms. Data were then reviewed by country experts, including the Ministry of Health program staff and implementing program staff, and updated as necessary. Data on vectors were also obtained from country experts. The district geographic boundaries were matched to geospatial shapefiles from the ENVISION project geospatial data repository, while other geospatial data were obtained through publicly available sources (Table 1).",
@ -484,6 +502,7 @@
"$ref": "#/texts/29"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Outcome and covariate variables",
@ -496,6 +515,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The outcome of interest for this analysis was whether a district passed or failed the pre-TAS. Failure was defined as any district that had at least one sentinel or spot-check site with a prevalence higher than or equal to 1% Mf or 2% Ag [4].",
@ -507,6 +527,7 @@
"$ref": "#/texts/15"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Potential covariates were derived from the available data for each factor in the domain groups listed in Table 1. New dichotomous variables were created for all variables that had multiple categories or were continuous for ease of interpretation in models and use in program decision-making. Cut-points for continuous variables were derived from either a priori knowledge or through exploratory analysis considering the mean or median value of the dataset, looking to create two groups of similar size with logical cut-points (e.g. rounding numbers to whole numbers). All the variables derived from publicly available global spatial raster datasets were summarized to the district level in ArcGIS Pro using the \u201czonal statistics\u201d tool. The final output used the continuous value measuring the mean pixel value for the district for all variables except geographic area. Categories for each variable were determined by selecting the mean or median dataset value or cut-off used in other relevant literature [7]. The following section describes the variables that were included in the final analysis and the final categorizations used.",
@ -522,6 +543,7 @@
"$ref": "#/texts/19"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Baseline prevalence",
@ -534,6 +556,7 @@
"$ref": "#/texts/18"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Baseline prevalence can be assumed as a proxy for local transmission conditions [14] and correlates with prevalence after MDA [14\u201320]. Baseline prevalence for each district was measured by either blood smears to measure Mf or rapid diagnostic tests to measure Ag. Other studies have modeled Mf and Ag prevalence separately, due to lack of a standardized correlation between the two, especially at pre-MDA levels [21,22]. However, because WHO mapping guidance states that MDA is required if either Mf or Ag is \u22651% and there were not enough data to model each separately, we combined baseline prevalence values regardless of diagnostic test used. We created two variables for use in the analysis (1) using the cut-off of <5% or \u22655% (dataset median value of 5%) and (2) using the cut-off of <10% or \u226510%.",
@ -549,6 +572,7 @@
"$ref": "#/texts/21"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Agent",
@ -561,6 +585,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "In terms of differences in transmission dynamics by agent, research has shown that Brugia spp. are more susceptible to the anti-filarial drug regimens than Wuchereria bancrofti parasites [23]. Thus, we combined districts reporting B. malayi and B. timori and compared them to areas with W. bancrofti or mixed parasites. Two variables from other domains were identified in exploratory analyses to be highly colinear with the parasite, and thus we considered them in the same group of variables for the final regression models. These were variables delineating vectors (Anopheles or Mansonia compared to Culex) from the environmental domain and drug package [ivermectin-albendazole (IVM-ALB) compared to diethylcarbamazine-albendazole (DEC-ALB)] from the MDA domain.",
@ -582,6 +607,7 @@
"$ref": "#/texts/25"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Environment",
@ -594,6 +620,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "LF transmission intensity is influenced by differing vector transmission dynamics, including vector biting rates and competence, and the number of individuals with microfilaria [21,24,25]. Since vector data are not always available, previous studies have explored whether environmental variables associated with vector density, such as elevation, rainfall, and temperature, can be used to predict LF prevalence [8,21,26\u201331]. We included the district area and elevation in meters as geographic variables potentially associated with transmission intensity. In addition, within the climate factor, we included Enhanced Vegetation Index (EVI) and rainfall variables. EVI measures vegetation levels, or \u201cgreenness,\u201d where a higher index value indicates a higher level of \u201cgreenness.\u201d",
@ -605,6 +632,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We included the socio-economic variable of population density, as it has been positively associated with LF prevalence in some studies [8,27,29], but no significant association has been found in others [30]. Population density could be correlated with vector, as in eastern African countries LF is mostly transmitted by Culex in urban areas and by Anopheles in rural areas [32]. Additionally, inclusion of the satellite imagery of nighttime lights data is another a proxy for socio-economic status [33].",
@ -616,6 +644,7 @@
"$ref": "#/texts/22"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Finally, all or parts of districts that are co-endemic with onchocerciasis may have received multiple rounds of MDA with ivermectin before LF MDA started, which may have lowered LF prevalence in an area [34\u201336]. Thus, we included a categorical variable to distinguish if districts were co-endemic with onchocerciasis.",
@ -634,6 +663,7 @@
"$ref": "#/texts/28"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "MDA",
@ -646,6 +676,7 @@
"$ref": "#/texts/26"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Treatment effectiveness depends upon both drug efficacy (ability to kill adult worms, ability to kill Mf, drug resistance, drug quality) and implementation of MDA (coverage, compliance, number of rounds) [14,16]. Ivermectin is less effective against adult worms than DEC, and therefore it is likely that Ag reduction is slower in areas using ivermectin instead of DEC in MDA [37]. Models also have shown that MDA coverage affects prevalence, although coverage has been defined in various ways, such as median coverage, number of rounds, or individual compliance [14\u201316,20,38\u201340]. Furthermore, systematic non-compliance, or population sub-groups which consistently refuse to take medicines, has been shown to represent a threat to elimination [41,42].",
@ -657,6 +688,7 @@
"$ref": "#/texts/26"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "We considered three approaches when analyzing the MDA data: median MDA coverage in the most recent 5 rounds, number of rounds with sufficient coverage in the most recent 5 rounds, and count of the total number of rounds. MDA coverage is considered sufficient at or above 65% of the total population who were reported to have ingested the drugs; this was used as the cut point for MDA median coverage for the most recent 5 rounds. The \u2018rounds of sufficient coverage\u2019 variable was categorized as having 2 or fewer rounds compared to 3 or more sufficient rounds. The \u2018total number of MDA rounds\u2019 variable was categorized at 5 or fewer rounds compared to 6 or more rounds ever documented in that district.",
@ -672,6 +704,7 @@
"$ref": "#/texts/30"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Pre-TAS implementation",
@ -684,6 +717,7 @@
"$ref": "#/texts/29"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Pre-TAS results can be influenced by the implementation of the survey itself, including the use of a particular diagnostic test, the selection of sites, the timing of survey, and the appropriate application of methods for population recruitment and diagnostic test adminstration. We included two variables in the pre-TAS implementation domain: `type of diagnostic method used\u2019 and `diagnostic test used.\u2019 The \u2018type of diagnostic method used\u2019 variable categorized districts by either using Mf or Ag. The \u2018diagnostic test used\u2019 variable examined Mf (reference category) compared to ICT and compared to FTS (categorical variable with 3 values). This approach was used to compare each test to each other. Countries switched from ICT to FTS during 2016, while Mf testing continued to be used throughout the time period of study.",
@ -699,6 +733,7 @@
"$ref": "#/texts/32"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Data inclusion criteria",
@ -711,6 +746,7 @@
"$ref": "#/texts/31"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The dataset, summarized at the district level, included information from 568 districts where a pre-TAS was being implemented for the first time. A total of 14 districts were removed from the final analysis due to missing data related to the following points: geospatial boundaries (4), baseline prevalence (4), and MDA coverage (6). The final analysis dataset had 554 districts.",
@ -729,6 +765,7 @@
"$ref": "#/texts/35"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Statistical analysis and modeling",
@ -741,6 +778,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Statistical analysis and modeling were done with Stata MP 15.1 (College Station, TX). Descriptive statistics comparing various variables to the principle outcome were performed. Significant differences were identified using a chi-square test. A generalized linear model (GLM) with a log link and binomial error distribution\u2014which estimates relative risks\u2014was developed using forward stepwise modeling methods (called log-binomial model). Models with higher pseudo-r-squared and lower Akaike information criterion (AIC) were retained at each step. Pseudo-r-squared is a value between 0 and 1 with the higher the value, the better the model is at predicting the outcome of interest. AIC values are used to compare the relative quality of models compared to each other; in general, a lower value indicates a better model. Variables were tested by factor group. Once a variable was selected from the group, no other variable in that same group was eligible to be included in the final model due to issues of collinearity and small sample sizes. Interaction between terms in the model was tested after model selection, and interaction terms that modified the original terms\u2019 significance were included in the final model. Overall, the number of potential variables able to be included in the model remained low due to the relatively small number of failure results (13%) in the dataset. Furthermore, the models with more than 3 variables and one interaction term either were unstable (indicated by very large confidence interval widths) or did not improve the model by being significant predictors or by modifying other parameters already in the model. These models were at heightened risk of non-convergence; we limited the number of variables accordingly.",
@ -752,6 +790,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Sensitivity analysis was performed for the final log-binomial model to test for the validity of results under different parameters by excluding some sub-sets of districts from the dataset and rerunning the model. This analysis was done to understand the robustness of the model when (1) excluding all districts in Cameroon, (2) including only districts in Africa, (3) including only districts with W. bancrofti parasite, and (4) including only districts with Anopheles as the primary vector. The sensitivity analysis excluding Cameroon was done for two reasons. First, Cameroon had the most pre-TAS results included, but no failures. Second, 70% of the Cameroon districts included in the analysis are co-endemic for loiasis. Given that diagnostic tests used in LF mapping have since been shown to cross-react with loiasis, there is some concern that these districts might not have been truly LF-endemic [43,44].",
@ -782,6 +821,7 @@
"$ref": "#/texts/42"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Results",
@ -794,6 +834,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The overall pre-TAS pass rate for the districts included in this analysis was 87% (74 failures in 554 districts). Nearly 40% of the 554 districts were from Cameroon (134) and Tanzania (87) (Fig 1). No districts in Bangladesh, Cameroon, Mali, or Uganda failed a pre-TAS in this data set; over 25% of districts in Burkina Faso, Ghana, Haiti, Nepal, and Sierra Leone failed pre-TAS in this data set. Baseline prevalence varied widely within and between the 13 countries. Fig 2 shows the highest, lowest, and median baseline prevalence in the study districts by country. Burkina Faso had the highest median baseline prevalence at 52% and Burkina Faso, Tanzania, and Ghana all had at least one district with a very high baseline of over 70%. In Mali, Indonesia, Benin, and Bangladesh, all districts had baseline prevalences below 20%.",
@ -805,6 +846,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Fig 3 shows the unadjusted analysis for key variables by pre-TAS result. Variables statistically significantly associated with failure (p-value \u22640.05) included higher baseline prevalence at or above 5% or 10%, FTS diagnostic test, primary vector of Culex, treatment with DEC-ALB, higher elevation, higher population density, higher EVI, higher annual rainfall, and six or more rounds of MDA. Variables that were not significantly associated with pre-TAS failure included diagnostic method used (Ag or Mf), parasite, co-endemicity for onchocerciasis, median MDA coverage, and sufficient rounds of MDA.",
@ -816,6 +858,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The final log-binomial model included the variables of baseline prevalence \u226510%, the diagnostic test used (FTS and ICT), and elevation. The final model also included a significant interaction term between high baseline and diagnostic test used.",
@ -827,6 +870,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Fig 4 shows the risk ratio results with their corresponding confidence intervals. In a model with interaction between baseline and diagnostic test the baseline parameter was significant while diagnostic test and the interaction term were not. Districts with high baseline had a statistically significant (p-value \u22640.05) 2.52 times higher risk of failure (95% CI 1.37\u20134.64) compared to those with low baseline prevalence. The FTS diagnostic test or ICT diagnostic test alone were not significant nor was the interaction term. Additionally, districts with an elevation below 350 meters had a statistically significant (p-value \u22640.05) 3.07 times higher risk of failing pre-TAS (95% CI 1.95\u20134.83).",
@ -838,6 +882,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Sensitivity analyses were conducted using the same model with different subsets of the dataset including (1) all districts except for districts in Cameroon (134 total with no failures), (2) only districts in Africa, (3) only districts with W. bancrofti, and (4) only districts with Anopheles as primary vector. The results of the sensitivity models (Table 2) indicate an overall robust model. High baseline and lower elevation remained significant across all the models. The ICT diagnostic test used remains insignificant across all models. The FTS diagnostic test was positively significant in model 1 and negatively significant in model 4. The interaction term of baseline prevalence and FTS diagnostic test was significant in three models though the estimate was unstable in the W. bancrofti-only and Anopheles-only models (models 3 and 4 respectively), as signified by large confidence intervals.",
@ -849,6 +894,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Overall 74 districts in the dataset failed pre-TAS. Fig 5 summarizes the likelihood of failure by variable combinations identified in the log-binomial model. For those districts with a baseline prevalence \u226510% that used a FTS diagnostic test and have an average elevation below 350 meters (Combination C01), 87% of the 23 districts failed. Of districts with high baseline that used an ICT diagnostic test and have a low average elevation (C02) 45% failed. Overall, combinations with high baseline and low elevation C01, C02, and C04 accounted for 51% of all the failures (38 of 74).",
@ -888,6 +934,7 @@
"$ref": "#/texts/52"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Discussion",
@ -900,6 +947,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This paper reports for the first time factors associated with pre-TAS results from a multi-country analysis. Variables significantly associated with failure were higher baseline prevalence and lower elevation. Districts with a baseline prevalence of 10% or more were at 2.52 times higher risk to fail pre-TAS in the final log-binomial model. In the bivariate analysis, baseline prevalence above 5% was also significantly more likely to fail compared to lower baselines, which indicates that the threshold for higher baseline prevalence may be as little as 5%, similar to what was found in Goldberg et al., which explored ecological and socioeconomic factors associated with TAS failure [7].",
@ -911,6 +959,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Though diagnostic test used was selected for the final log-binomial model, neither category (FTS or ICT) were significant after interaction with high baseline. FTS alone is significant in the bivariate analysis compared to ICT or Mf. This result is not surprising given previous research which found that FTS was more sensitive than ICT [45].",
@ -922,6 +971,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Elevation was the only environmental domain variable selected for the final log-binomial model during the model selection process, with areas of lower elevation (<350m) found to be at 3.07 times higher risk to fail pre-TAS compared to districts with a higher elevation. Similar results related to elevation were found in previous studies [8,31], including Goldberg et al. [7], who used a cutoff of 200 meters. Elevation likely also encompasses some related environmental concepts, such as vector habitat, greenness (EVI), or rainfall, which impact vector chances of survival.",
@ -933,6 +983,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "The small number of failures overall prevented the inclusion of a large number of variables in the final log-binomial model. However, other variables that are associated with failure as identified in the bivariate analyses, such as Culex vector, higher population density, higher EVI, higher rainfall and more rounds of MDA, should not be discounted when making programmatic decisions. Other models have shown that Culex as the predominant vector in a district, compared to Anopheles, results in more intense interventions needed to reach elimination [24,41]. Higher population density, which was also found to predict TAS failure [7], could be related to different vector species\u2019 transmission dynamics in urban areas, as well as the fact that MDAs are harder to conduct and to accurately measure in urban areas [46,47]. Both higher enhanced vegetation index (>0.3) and higher rainfall (>700 mm per year) contribute to expansion of vector habitats and population. Additionally, having more than five rounds of MDA before pre-TAS was also statistically significantly associated with higher failure in the bivariate analysis. It is unclear why higher number of rounds is associated with first pre-TAS failure given that other research has shown the opposite [15,16].",
@ -944,6 +995,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "All other variables included in this analysis were not significantly associated with pre-TAS failure in our analysis. Goldberg et al. found Brugia spp. to be significantly associated with failure, but our results did not. This is likely due in part to the small number of districts with Brugia spp. in our dataset (6%) compared to 46% in the Goldberg et al. article [7]. MDA coverage levels were not significantly associated with pre-TAS failure, likely due to the lack of variance in the coverage data since WHO guidance dictates a minimum of five rounds of MDA with \u226565% epidemiological coverage to be eligible to implement pre-TAS. It should not be interpreted as evidence that high MDA coverage levels are not necessary to lower prevalence.",
@ -955,6 +1007,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Limitations to this study include data sources, excluded data, unreported data, misassigned data, and aggregation of results at the district level. The main data sources for this analysis were programmatic data, which may be less accurate than data collected specifically for research purposes. This is particularly true of the MDA coverage data, where some countries report data quality challenges in areas of instability or frequent population migration. Even though risk factors such as age, sex, compliance with MDA, and use of bednets have been shown to influence infection in individuals [40,48\u201350], we could not include factors from the human host domain in our analysis, as data sets were aggregated at site level and did not include individual information. In addition, vector control data were not universally available across the 13 countries and thus were not included in the analysis, despite studies showing that vector control has an impact on reducing LF prevalence [41,48,51\u201353].",
@ -966,6 +1019,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Fourteen districts were excluded from the analysis because we were not able to obtain complete data for baseline prevalence, MDA coverage, or geographic boundaries. One of these districts had failed pre-TAS. It is likely these exclusions had minimal impact on the conclusions, as they represented a small number of districts and were similar to other included districts in terms of key variables. Unreported data could have occurred if a country conducted a pre-TAS that failed and then chose not to report it or reported it as a mid-term survey instead. Anecdotally, we know this has occurred occasionally, but we do not believe the practice to be widespread. Another limitation in the analysis is a potential misassignment of key variable values to a district due to changes in the district over time. Redistricting, changes in district size or composition, was pervasive in many countries during the study period; however, we expect the impact on the study outcome to be minimal, as the historical prevalence and MDA data from the \u201cmother\u201d districts are usually flowed down to these new \u201cdaughter\u201d districts. However, it is possible that the split created an area of higher prevalence or lower MDA coverage than would have been found on average in the overall larger original \u201cmother\u201d district. Finally, the aggregation or averaging of results to the district level may mask heterogeneity within districts. Though this impact could be substantial in districts with considerable heterogeneity, the use of median values and binomial variables mitigated the likelihood of skewing the data to extreme outliners in a district.",
@ -977,6 +1031,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "As this analysis used data across a variety of countries and epidemiological situations, the results are likely relevant for other districts in the countries examined and in countries with similar epidemiological backgrounds. In general, as more data become available at site level through the increased use of electronic data collection tools, further analysis of geospatial variables and associations will be possible. For example, with the availability of GPS coordinates, it may become possible to analyze outcomes by site and to link the geospatial environmental domain variables at a smaller scale. Future analyses also might seek to include information from coverage surveys or qualitative research studies on vector control interventions such as bed net usage, MDA compliance, population movement, and sub-populations that might be missed during MDA. Future pre-TAS using electronic data collection could include sex and age of individuals included in the survey.",
@ -988,6 +1043,7 @@
"$ref": "#/texts/43"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "This paper provides evidence from analysis of 554 districts and 13 countries on the factors associated with pre-TAS results. Baseline prevalence, elevation, vector, population density, EVI, rainfall, and number of MDA rounds were all significant in either bivariate or multivariate analyses. This information along with knowledge of local context can help countries more effectively plan pre-TAS and forecast program activities, such as the potential need for more than five rounds of MDA in areas with high baseline and/or low elevation.",
@ -1006,6 +1062,7 @@
"$ref": "#/tables/1"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Tables",
@ -1018,6 +1075,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Table 1: Categorization of potential factors influencing pre-TAS results.",
@ -1029,6 +1087,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Table 2: Adjusted risk ratios for pre-TAS failure from log-binomial model sensitivity analysis.",
@ -1056,6 +1115,7 @@
"$ref": "#/pictures/4"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Figures",
@ -1068,6 +1128,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Fig 1: Number of pre-TAS by country.",
@ -1079,6 +1140,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Fig 2: District-level baseline prevalence by country.",
@ -1090,6 +1152,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Fig 3: Percent pre-TAS failure by each characteristic (unadjusted).",
@ -1101,6 +1164,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Fig 4: Adjusted risk ratios for pre-TAS failure with 95% Confidence Interval from log-binomial model.",
@ -1112,6 +1176,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "caption",
"prov": [],
"orig": "Fig 5: Analysis of failures by model combinations.",
@ -1127,6 +1192,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "References",
@ -1139,6 +1205,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "World Health Organization. Lymphatic filariasis: progress report 2000\u20132009 and strategic plan 2010\u20132020. Geneva; 2010. ",
@ -1152,6 +1219,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "World Health Organization. Validation of elimination of lymphatic filariasis as a public health problem. Geneva; 2017. ",
@ -1165,6 +1233,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Global programme to eliminate lymphatic filariasis: progress report, 2018. Wkly Epidemiol Rec (2019)",
@ -1178,6 +1247,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "World Health Organization. Global programme to eliminate lymphatic filariasis: monitoring and epidemiological assessment of mass drug administration. Geneva; 2011. ",
@ -1191,6 +1261,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "World Health Organization. Strengthening the assessment of lymphatic filariasis transmission and documenting the achievement of elimination\u2014Meeting of the Neglected Tropical Diseases Strategic and Technical Advisory Group\u2019s Monitoring and Evaluation Subgroup on Disease-specific Indicators. 2016; 42. ",
@ -1204,6 +1275,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Kyelem D; Biswas G; Bockarie MJ; Bradley MH; El-Setouhy M; Fischer PU. Determinants of success in national programs to eliminate lymphatic filariasis: a perspective identifying essential elements and research needs. Am J Trop Med Hyg (2008)",
@ -1217,6 +1289,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Goldberg EM; King JD; Mupfasoni D; Kwong K; Hay SI; Pigott DM. Ecological and socioeconomic predictors of transmission assessment survey failure for lymphatic filariasis. Am J Trop Med Hyg (2019)",
@ -1230,6 +1303,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Cano J; Rebollo MP; Golding N; Pullan RL; Crellen T; Soler A. The global distribution and transmission limits of lymphatic filariasis: past and present. Parasites and Vectors (2014)",
@ -1243,6 +1317,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "CGIAR-CSI. CGIAR-CSI SRTM 90m DEM Digital Elevation Database. In: . ",
@ -1256,6 +1331,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "USGS NASA. Vegetation indices 16-DAy L3 global 500 MOD13A1 dataset [Internet]. [cited 1 May 2018]. Available: . ",
@ -1269,6 +1345,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Funk C; Peterson P; Landsfeld M; Pedreros D; Verdin J; Shukla S. The climate hazards infrared precipitation with stations\u2014A new environmental record for monitoring extremes. Sci Data (2015)",
@ -1282,6 +1359,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Lloyd CT; Sorichetta A; Tatem AJ. High resolution global gridded data for use in population studies. Sci Data (2017)",
@ -1295,6 +1373,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Elvidge CD; Baugh KE; Zhizhin M; Hsu F-C. Why VIIRS data are superior to DMSP for mapping nighttime lights. Proc Asia-Pacific Adv Netw (2013)",
@ -1308,6 +1387,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Jambulingam P; Subramanian S; De Vlas SJ; Vinubala C; Stolk WA. Mathematical modelling of lymphatic filariasis elimination programmes in India: required duration of mass drug administration and post-treatment level of infection indicators. Parasites and Vectors (2016)",
@ -1321,6 +1401,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Michael E; Malecela-Lazaro MN; Simonsen PE; Pedersen EM; Barker G; Kumar A. Mathematical modelling and the control of lymphatic filariasis. Lancet Infect Dis (2004)",
@ -1334,6 +1415,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Stolk WA; Swaminathan S; van Oortmarssen GJ; Das PK; Habbema JDF. Prospects for elimination of bancroftian filariasis by mass drug treatment in Pondicherry, India: a simulation study. J Infect Dis (2003)",
@ -1347,6 +1429,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Grady CA; De Rochars MB; Direny AN; Orelus JN; Wendt J; Radday J. Endpoints for lymphatic filariasis programs. Emerg Infect Dis (2007)",
@ -1360,6 +1443,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Evans D; McFarland D; Adamani W; Eigege A; Miri E; Schulz J. Cost-effectiveness of triple drug administration (TDA) with praziquantel, ivermectin and albendazole for the prevention of neglected tropical diseases in Nigeria. Ann Trop Med Parasitol (2011)",
@ -1373,6 +1457,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Richards FO; Eigege A; Miri ES; Kal A; Umaru J; Pam D. Epidemiological and entomological evaluations after six years or more of mass drug administration for lymphatic filariasis elimination in Nigeria. PLoS Negl Trop Dis (2011)",
@ -1386,6 +1471,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Biritwum NK; Yikpotey P; Marfo BK; Odoom S; Mensah EO; Asiedu O. Persistent \u201chotspots\u201d of lymphatic filariasis microfilaraemia despite 14 years of mass drug administration in Ghana. Trans R Soc Trop Med Hyg (2016)",
@ -1399,6 +1485,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Moraga P; Cano J; Baggaley RF; Gyapong JO; Njenga SM; Nikolay B. Modelling the distribution and transmission intensity of lymphatic filariasis in sub-Saharan Africa prior to scaling up interventions: integrated use of geostatistical and mathematical modelling. Parasites and Vectors (2015)",
@ -1412,6 +1499,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Irvine MA; Njenga SM; Gunawardena S; Wamae CN; Cano J; Brooker SJ. Understanding the relationship between prevalence of microfilariae and antigenaemia using a model of lymphatic filariasis infection. Trans R Soc Trop Med Hyg (2016)",
@ -1425,6 +1513,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Ottesen EA. Efficacy of diethylcarbamazine in eradicating infection with lymphatic-dwelling filariae in humans. Rev Infect Dis (1985)",
@ -1438,6 +1527,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Gambhir M; Bockarie M; Tisch D; Kazura J; Remais J; Spear R. Geographic and ecologic heterogeneity in elimination thresholds for the major vector-borne helminthic disease, lymphatic filariasis. BMC Biol (2010)",
@ -1451,6 +1541,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "World Health Organization. Global programme to eliminate lymphatic filariasis: practical entomology handbook. Geneva; 2013. ",
@ -1464,6 +1555,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Slater H; Michael E. Predicting the current and future potential distributions of lymphatic filariasis in Africa using maximum entropy ecological niche modelling. PLoS One (2012)",
@ -1477,6 +1569,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Slater H; Michael E. Mapping, Bayesian geostatistical analysis and spatial prediction of lymphatic filariasis prevalence in Africa. PLoS One (2013)",
@ -1490,6 +1583,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Sabesan S; Raju KHK; Subramanian S; Srivastava PK; Jambulingam P. Lymphatic filariasis transmission risk map of India, based on a geo-environmental risk model. Vector-Borne Zoonotic Dis (2013)",
@ -1503,6 +1597,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Stanton MC; Molyneux DH; Kyelem D; Bougma RW; Koudou BG; Kelly-Hope LA. Baseline drivers of lymphatic filariasis in Burkina Faso. Geospat Health (2013)",
@ -1516,6 +1611,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Manhenje I; Teresa Gal\u00e1n-Puchades M; Fuentes M V. Socio-environmental variables and transmission risk of lymphatic filariasis in central and northern Mozambique. Geospat Health (2013)",
@ -1529,6 +1625,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Ngwira BM; Tambala P; Perez a M; Bowie C; Molyneux DH. The geographical distribution of lymphatic filariasis infection in Malawi. Filaria J (2007)",
@ -1542,6 +1639,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Simonsen PE; Mwakitalu ME. Urban lymphatic filariasis. Parasitol Res (2013)",
@ -1555,6 +1653,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Proville J; Zavala-Araiza D; Wagner G. Night-time lights: a global, long term look at links to socio-economic trends. PLoS One (2017)",
@ -1568,6 +1667,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Endeshaw T; Taye A; Tadesse Z; Katabarwa MN; Shafi O; Seid T. Presence of Wuchereria bancrofti microfilaremia despite seven years of annual ivermectin monotherapy mass drug administration for onchocerciasis control: a study in north-west Ethiopia. Pathog Glob Health (2015)",
@ -1581,6 +1681,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Richards FO; Eigege A; Pam D; Kal A; Lenhart A; Oneyka JOA. Mass ivermectin treatment for onchocerciasis: lack of evidence for collateral impact on transmission of Wuchereria bancrofti in areas of co-endemicity. Filaria J (2005)",
@ -1594,6 +1695,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Kyelem D; Sanou S; Boatin B a; Medlock J; Couibaly S; Molyneux DH. Impact of long-term ivermectin (Mectizan) on Wuchereria bancrofti and Mansonella perstans infections in Burkina Faso: strategic and policy implications. Ann Trop Med Parasitol (2003)",
@ -1607,6 +1709,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Weil GJ; Lammie PJ; Richards FO; Eberhard ML. Changes in circulating parasite antigen levels after treatment of bancroftian filariasis with diethylcarbamazine and ivermectin. J Infect Dis (1991)",
@ -1620,6 +1723,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Kumar A; Sachan P. Measuring impact on filarial infection status in a community study: role of coverage of mass drug administration. Trop Biomed (2014)",
@ -1633,6 +1737,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Njenga SM; Mwandawiro CS; Wamae CN; Mukoko DA; Omar AA; Shimada M. Sustained reduction in prevalence of lymphatic filariasis infection in spite of missed rounds of mass drug administration in an area under mosquito nets for malaria control. Parasites and Vectors (2011)",
@ -1646,6 +1751,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Boyd A; Won KY; McClintock SK; Donovan C V; Laney SJ; Williams SA. A community-based study of factors associated with continuing transmission of lymphatic filariasis in Leogane, Haiti. PLoS Negl Trop Dis (2010)",
@ -1659,6 +1765,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Irvine MA; Reimer LJ; Njenga SM; Gunawardena S; Kelly-Hope L; Bockarie M. Modelling strategies to break transmission of lymphatic filariasis\u2014aggregation, adherence and vector competence greatly alter elimination. Parasites and Vectors (2015)",
@ -1672,6 +1779,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Irvine MA; Stolk WA; Smith ME; Subramanian S; Singh BK; Weil GJ. Effectiveness of a triple-drug regimen for global elimination of lymphatic filariasis: a modelling study. Lancet Infect Dis (2017)",
@ -1685,6 +1793,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Pion SD; Montavon C; Chesnais CB; Kamgno J; Wanji S; Klion AD. Positivity of antigen tests used for diagnosis of lymphatic filariasis in individuals without Wuchereria bancrofti infection but with high loa loa microfilaremia. Am J Trop Med Hyg (2016)",
@ -1698,6 +1807,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Wanji S; Esum ME; Njouendou AJ; Mbeng AA; Chounna Ndongmo PW; Abong RA. Mapping of lymphatic filariasis in loiasis areas: a new strategy shows no evidence for Wuchereria bancrofti endemicity in Cameroon. PLoS Negl Trop Dis (2018)",
@ -1711,6 +1821,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Chesnais CB; Awaca-Uvon NP; Bolay FK; Boussinesq M; Fischer PU; Gankpala L. A multi-center field study of two point-of-care tests for circulating Wuchereria bancrofti antigenemia in Africa. PLoS Negl Trop Dis (2017)",
@ -1724,6 +1835,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Silumbwe A; Zulu JM; Halwindi H; Jacobs C; Zgambo J; Dambe R. A systematic review of factors that shape implementation of mass drug administration for lymphatic filariasis in sub-Saharan Africa. BMC Public Health (2017)",
@ -1737,6 +1849,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Adams AM; Vuckovic M; Birch E; Brant TA; Bialek S; Yoon D. Eliminating neglected tropical diseases in urban areas: a review of challenges, strategies and research directions for successful mass drug administration. Trop Med Infect Dis (2018)",
@ -1750,6 +1863,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Rao RU; Samarasekera SD; Nagodavithana KC; Dassanayaka TDM; Punchihewa MW; Ranasinghe USB. Reassessment of areas with persistent lymphatic filariasis nine years after cessation of mass drug administration in Sri Lanka. PLoS Negl Trop Dis (2017)",
@ -1763,6 +1877,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Xu Z; Graves PM; Lau CL; Clements A; Geard N; Glass K. GEOFIL: a spatially-explicit agent-based modelling framework for predicting the long-term transmission dynamics of lymphatic filariasis in American Samoa. Epidemics (2018)",
@ -1776,6 +1891,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Id CM; Tettevi EJ; Mechan F; Idun B; Biritwum N; Osei-atweneboana MY. Elimination within reach: a cross-sectional study highlighting the factors that contribute to persistent lymphatic filariasis in eight communities in rural Ghana. PLoS Negl Trop Dis (2019)",
@ -1789,6 +1905,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Eigege A; Kal A; Miri E; Sallau A; Umaru J; Mafuyai H. Long-lasting insecticidal nets are synergistic with mass drug administration for interruption of lymphatic filariasis transmission in Nigeria. PLoS Negl Trop Dis (2013)",
@ -1802,6 +1919,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Van den Berg H; Kelly-Hope LA; Lindsay SW. Malaria and lymphatic filariasis: The case for integrated vector management. Lancet Infect Dis (2013)",
@ -1815,6 +1933,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Webber R.. Eradication of Wuchereria bancrofti infection through vector control. Trans R Soc Trop Med Hyg (1979)",
@ -1830,6 +1949,7 @@
"$ref": "#/texts/56"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1847,6 +1967,7 @@
"$ref": "#/texts/56"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1864,6 +1985,7 @@
"$ref": "#/texts/56"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1881,6 +2003,7 @@
"$ref": "#/texts/56"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1898,6 +2021,7 @@
"$ref": "#/texts/56"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [
@ -1917,6 +2041,7 @@
"$ref": "#/texts/53"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [
@ -5433,6 +5558,7 @@
"$ref": "#/texts/53"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [

168
tests/data/groundtruth/docling_v2/pone.0234687.xml.json
View File

File diff suppressed because it is too large Load Diff

38
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "powerpoint_sample",
"origin": {
"mimetype": "application/vnd.ms-powerpoint",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -26,6 +27,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -46,6 +48,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"name": "slide-0",
"label": "chapter"
},
@ -74,6 +77,7 @@
"$ref": "#/texts/7"
}
],
"content_layer": "body",
"name": "slide-1",
"label": "chapter"
},
@ -105,6 +109,7 @@
"$ref": "#/groups/7"
}
],
"content_layer": "body",
"name": "slide-2",
"label": "chapter"
},
@ -124,6 +129,7 @@
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
},
@ -146,6 +152,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -162,6 +169,7 @@
"$ref": "#/texts/17"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -181,6 +189,7 @@
"$ref": "#/texts/21"
}
],
"content_layer": "body",
"name": "list",
"label": "ordered_list"
},
@ -200,6 +209,7 @@
"$ref": "#/texts/24"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -211,6 +221,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "title",
"prov": [
{
@ -237,6 +248,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -263,6 +275,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "title",
"prov": [
{
@ -289,6 +302,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -315,6 +329,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -341,6 +356,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -367,6 +383,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -393,6 +410,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -419,6 +437,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -447,6 +466,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -475,6 +495,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -503,6 +524,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -531,6 +553,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -559,6 +582,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -587,6 +611,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -615,6 +640,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -641,6 +667,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -669,6 +696,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -697,6 +725,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -723,6 +752,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -751,6 +781,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -779,6 +810,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -807,6 +839,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -835,6 +868,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -863,6 +897,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [
{
@ -894,6 +929,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [
{

8
tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "powerpoint_with_image",
"origin": {
"mimetype": "application/vnd.ms-powerpoint",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -40,6 +42,7 @@
"$ref": "#/pictures/0"
}
],
"content_layer": "body",
"name": "slide-0",
"label": "chapter"
}
@ -51,6 +54,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "title",
"prov": [
{
@ -77,6 +81,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [
{
@ -105,6 +110,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [
{

2
tests/data/groundtruth/docling_v2/redp5110_sampled.json
View File

File diff suppressed because one or more lines are too long

13
tests/data/groundtruth/docling_v2/tablecell.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "tablecell",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -38,6 +39,7 @@
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -55,6 +57,7 @@
"$ref": "#/texts/1"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -66,6 +69,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Hello world1",
@ -79,6 +83,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Hello2",
@ -92,6 +97,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -103,6 +109,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some text before",
@ -114,6 +121,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -125,6 +133,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -136,6 +145,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Some text after",
@ -150,6 +160,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

14
tests/data/groundtruth/docling_v2/test-01.xlsx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "test-01",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -26,6 +27,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -40,6 +42,7 @@
"$ref": "#/tables/0"
}
],
"content_layer": "body",
"name": "sheet: Sheet1",
"label": "section"
},
@ -59,6 +62,7 @@
"$ref": "#/tables/3"
}
],
"content_layer": "body",
"name": "sheet: Sheet2",
"label": "section"
},
@ -78,6 +82,7 @@
"$ref": "#/pictures/0"
}
],
"content_layer": "body",
"name": "sheet: Sheet3",
"label": "section"
}
@ -90,6 +95,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@ -114,6 +120,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -652,6 +659,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -1554,6 +1562,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -1944,6 +1953,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -2334,6 +2344,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -2800,6 +2811,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

11
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "test_emf_docx",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -38,6 +39,7 @@
"$ref": "#/pictures/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -49,6 +51,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Test with three images in unusual formats",
@ -60,6 +63,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Raster in emf:",
@ -71,6 +75,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Vector in emf:",
@ -82,6 +87,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Raster in webp:",
@ -95,6 +101,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@ -108,6 +115,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@ -121,6 +129,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],

12
tests/data/groundtruth/docling_v2/unit_test_01.html.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_01",
"origin": {
"mimetype": "text/html",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -34,6 +36,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"name": "header-3",
"label": "section"
}
@ -52,6 +55,7 @@
"$ref": "#/texts/3"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Title",
@ -67,6 +71,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1",
@ -79,6 +84,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-1.1",
@ -101,6 +107,7 @@
"$ref": "#/texts/6"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2",
@ -113,6 +120,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.0.1",
@ -125,6 +133,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.2",
@ -137,6 +146,7 @@
"$ref": "#/texts/3"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "section-2.3",

51
tests/data/groundtruth/docling_v2/unit_test_headers.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_headers",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -34,6 +36,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"name": "header-2",
"label": "section"
}
@ -55,6 +58,7 @@
"$ref": "#/texts/27"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Test Document",
@ -66,6 +70,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -99,6 +104,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1",
@ -111,6 +117,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -122,6 +129,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1",
@ -133,6 +141,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -144,6 +153,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2",
@ -155,6 +165,7 @@
"$ref": "#/texts/2"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -182,6 +193,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.1",
@ -194,6 +206,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -205,6 +218,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@ -216,6 +230,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -227,6 +242,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@ -238,6 +254,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -268,6 +285,7 @@
"$ref": "#/texts/20"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2",
@ -280,6 +298,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -291,6 +310,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@ -302,6 +322,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -313,6 +334,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@ -324,6 +346,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -354,6 +377,7 @@
"$ref": "#/texts/26"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2.3",
@ -366,6 +390,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -377,6 +402,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@ -388,6 +414,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -399,6 +426,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@ -410,6 +438,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -421,6 +450,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -454,6 +484,7 @@
"$ref": "#/texts/39"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2",
@ -466,6 +497,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -477,6 +509,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1",
@ -488,6 +521,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -499,6 +533,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.2",
@ -510,6 +545,7 @@
"$ref": "#/texts/27"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -537,6 +573,7 @@
"$ref": "#/texts/38"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1.1",
@ -549,6 +586,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -560,6 +598,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@ -571,6 +610,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -582,6 +622,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@ -593,6 +634,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -623,6 +665,7 @@
"$ref": "#/texts/45"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1",
@ -635,6 +678,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -646,6 +690,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1",
@ -657,6 +702,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -668,6 +714,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.2",
@ -679,6 +726,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -690,6 +738,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",

55
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_headers_numbered",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -56,6 +57,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -73,6 +75,7 @@
"$ref": "#/texts/27"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
},
@ -89,6 +92,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"name": "header-1",
"label": "section"
},
@ -102,6 +106,7 @@
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
},
@ -118,6 +123,7 @@
"$ref": "#/texts/39"
}
],
"content_layer": "body",
"name": "header-1",
"label": "section"
},
@ -131,6 +137,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"name": "header-2",
"label": "section"
}
@ -149,6 +156,7 @@
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Test Document",
@ -160,6 +168,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -171,6 +180,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1",
@ -183,6 +193,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -194,6 +205,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1",
@ -205,6 +217,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -216,6 +229,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2",
@ -227,6 +241,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -254,6 +269,7 @@
"$ref": "#/texts/13"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.1",
@ -266,6 +282,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -277,6 +294,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@ -288,6 +306,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -299,6 +318,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@ -310,6 +330,7 @@
"$ref": "#/texts/8"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -340,6 +361,7 @@
"$ref": "#/texts/20"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2",
@ -352,6 +374,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -363,6 +386,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.1",
@ -374,6 +398,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -385,6 +410,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.1.2",
@ -396,6 +422,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -426,6 +453,7 @@
"$ref": "#/texts/26"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2.3",
@ -438,6 +466,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -449,6 +478,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@ -460,6 +490,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -471,6 +502,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 1.2.3.1",
@ -482,6 +514,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -493,6 +526,7 @@
"$ref": "#/texts/20"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -504,6 +538,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2",
@ -516,6 +551,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -527,6 +563,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1",
@ -538,6 +575,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -549,6 +587,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.2",
@ -560,6 +599,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -587,6 +627,7 @@
"$ref": "#/texts/38"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1.1",
@ -599,6 +640,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -610,6 +652,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@ -621,6 +664,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -632,6 +676,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1.1",
@ -643,6 +688,7 @@
"$ref": "#/texts/33"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -673,6 +719,7 @@
"$ref": "#/texts/45"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1",
@ -685,6 +732,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -696,6 +744,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1",
@ -707,6 +756,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -718,6 +768,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.2",
@ -729,6 +780,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -740,6 +792,7 @@
"$ref": "#/texts/39"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",

64
tests/data/groundtruth/docling_v2/unit_test_lists.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "unit_test_lists",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -34,6 +36,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
},
@ -62,6 +65,7 @@
"$ref": "#/texts/36"
}
],
"content_layer": "body",
"name": "header-2",
"label": "section"
},
@ -81,6 +85,7 @@
"$ref": "#/texts/10"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -100,6 +105,7 @@
"$ref": "#/texts/15"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -122,6 +128,7 @@
"$ref": "#/texts/23"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -141,6 +148,7 @@
"$ref": "#/texts/22"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -160,6 +168,7 @@
"$ref": "#/texts/28"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -173,6 +182,7 @@
"$ref": "#/texts/27"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -192,6 +202,7 @@
"$ref": "#/texts/34"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -208,6 +219,7 @@
"$ref": "#/groups/10"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -221,6 +233,7 @@
"$ref": "#/texts/33"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -243,6 +256,7 @@
"$ref": "#/texts/42"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -262,6 +276,7 @@
"$ref": "#/groups/13"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -275,6 +290,7 @@
"$ref": "#/texts/41"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -308,6 +324,7 @@
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test Document",
@ -320,6 +337,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -331,6 +349,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -342,6 +361,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.1",
@ -353,6 +373,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -364,6 +385,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Paragraph 2.1.2",
@ -375,6 +397,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -393,6 +416,7 @@
"$ref": "#/texts/11"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 1:",
@ -405,6 +429,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1",
@ -418,6 +443,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 2",
@ -431,6 +457,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 3",
@ -444,6 +471,7 @@
"$ref": "#/texts/7"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -462,6 +490,7 @@
"$ref": "#/texts/16"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 2:",
@ -474,6 +503,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item a",
@ -487,6 +517,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item b",
@ -500,6 +531,7 @@
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item c",
@ -513,6 +545,7 @@
"$ref": "#/texts/12"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -531,6 +564,7 @@
"$ref": "#/texts/24"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 3:",
@ -543,6 +577,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1",
@ -556,6 +591,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 2",
@ -569,6 +605,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.1",
@ -582,6 +619,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.2",
@ -595,6 +633,7 @@
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.3",
@ -608,6 +647,7 @@
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 3",
@ -621,6 +661,7 @@
"$ref": "#/texts/17"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -639,6 +680,7 @@
"$ref": "#/texts/29"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 4:",
@ -651,6 +693,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1",
@ -664,6 +707,7 @@
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.1",
@ -677,6 +721,7 @@
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 2",
@ -690,6 +735,7 @@
"$ref": "#/texts/25"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -708,6 +754,7 @@
"$ref": "#/texts/35"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 5:",
@ -720,6 +767,7 @@
"$ref": "#/groups/8"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1",
@ -733,6 +781,7 @@
"$ref": "#/groups/9"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.1",
@ -746,6 +795,7 @@
"$ref": "#/groups/10"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.1.1",
@ -759,6 +809,7 @@
"$ref": "#/groups/8"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 3",
@ -772,6 +823,7 @@
"$ref": "#/texts/30"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -796,6 +848,7 @@
"$ref": "#/texts/45"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test 6:",
@ -808,6 +861,7 @@
"$ref": "#/groups/11"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1",
@ -821,6 +875,7 @@
"$ref": "#/groups/11"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 2",
@ -834,6 +889,7 @@
"$ref": "#/groups/12"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.1",
@ -847,6 +903,7 @@
"$ref": "#/groups/12"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.2",
@ -860,6 +917,7 @@
"$ref": "#/groups/13"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 1.2.1",
@ -873,6 +931,7 @@
"$ref": "#/groups/11"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "List item 3",
@ -886,6 +945,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -897,6 +957,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -908,6 +969,7 @@
"$ref": "#/texts/36"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",

467
tests/data/groundtruth/docling_v2/wiki_duck.html.json
View File

File diff suppressed because it is too large Load Diff

32
tests/data/groundtruth/docling_v2/word_sample.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "word_sample",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -23,6 +24,7 @@
"$ref": "#/texts/1"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -43,6 +45,7 @@
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -62,6 +65,7 @@
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
},
@ -81,6 +85,7 @@
"$ref": "#/texts/22"
}
],
"content_layer": "body",
"name": "list",
"label": "list"
}
@ -92,6 +97,7 @@
"$ref": "#/body"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Summer activities",
@ -116,6 +122,7 @@
"$ref": "#/texts/4"
}
],
"content_layer": "body",
"label": "title",
"prov": [],
"orig": "Swimming in the lake",
@ -127,6 +134,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Duck",
@ -138,6 +146,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Figure 1: This is a cute duckling",
@ -168,6 +177,7 @@
"$ref": "#/texts/14"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Let\u2019s swim!",
@ -180,6 +190,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "To get started with swimming, first lay down in a water and try not to drown:",
@ -191,6 +202,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "You can relax and look around",
@ -204,6 +216,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Paddle about",
@ -217,6 +230,7 @@
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Enjoy summer warmth",
@ -230,6 +244,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Also, don\u2019t forget:",
@ -241,6 +256,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Wear sunglasses",
@ -254,6 +270,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Don\u2019t forget to drink water",
@ -267,6 +284,7 @@
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Use sun cream",
@ -280,6 +298,7 @@
"$ref": "#/texts/4"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Hmm, what else\u2026",
@ -313,6 +332,7 @@
"$ref": "#/groups/2"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Let\u2019s eat",
@ -325,6 +345,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "After we had a good day of swimming in the lake, it\u2019s important to eat something nice",
@ -336,6 +357,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "I like to eat leaves",
@ -347,6 +369,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "Here are some interesting things a respectful duck could eat:",
@ -358,6 +381,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -369,6 +393,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "And let\u2019s add another list in the end:",
@ -380,6 +405,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Leaves",
@ -393,6 +419,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Berries",
@ -406,6 +433,7 @@
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "Grain",
@ -421,6 +449,7 @@
"$ref": "#/texts/1"
},
"children": [],
"content_layer": "body",
"label": "picture",
"prov": [],
"captions": [],
@ -445,6 +474,7 @@
"$ref": "#/texts/14"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

22
tests/data/groundtruth/docling_v2/word_tables.docx.json
View File

@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.0.0",
"version": "1.1.0",
"name": "word_tables",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -10,6 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
@ -20,6 +21,7 @@
"$ref": "#/groups/0"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
@ -34,6 +36,7 @@
"$ref": "#/texts/0"
}
],
"content_layer": "body",
"name": "header-0",
"label": "section"
}
@ -94,6 +97,7 @@
"$ref": "#/texts/11"
}
],
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Test with tables",
@ -106,6 +110,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A uniform table",
@ -117,6 +122,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -128,6 +134,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with horizontal spans",
@ -139,6 +146,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -150,6 +158,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with horizontal spans in inner columns",
@ -161,6 +170,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -172,6 +182,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with vertical spans",
@ -183,6 +194,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -194,6 +206,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "A non-uniform table with all kinds of spans and empty cells",
@ -205,6 +218,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -216,6 +230,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "paragraph",
"prov": [],
"orig": "",
@ -230,6 +245,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -472,6 +488,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -690,6 +707,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -980,6 +998,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],
@ -1346,6 +1365,7 @@
"$ref": "#/texts/0"
},
"children": [],
"content_layer": "body",
"label": "table",
"prov": [],
"captions": [],

2
tests/data_scanned/groundtruth/docling_v1/ocr_test.pages.json
View File

@ -1 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.json
View File

@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
{"schema_name": "DoclingDocument", "version": "1.1.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json
View File

@ -1 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

2
tests/test_backend_patent_uspto.py
View File

@ -14,7 +14,7 @@ from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend, XmlTab
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import InputDocument
GENERATE: bool = True
GENERATE: bool = False
DATA_PATH: Path = Path("./tests/data/uspto/")
GT_PATH: Path = Path("./tests/data/groundtruth/docling_v2/")