mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 20:14:47 +00:00
Upgrading docling core and adding groups
This commit is contained in:
Rafael Teixeira de Lima
parent
5630c6b8fd
commit
655e95dd72
0
docling/backend/docx/latex/__init__.py
Normal file
0
docling/backend/docx/latex/__init__.py
Normal file
@ -268,4 +268,4 @@ LIM_TO = ("\\rightarrow", "\\to")
|
|||||||
|
|
||||||
LIM_UPP = "\\overset{{{lim}}}{{{text}}}"
|
LIM_UPP = "\\overset{{{lim}}}{{{text}}}"
|
||||||
|
|
||||||
M = "\\begin{{matrix}}{text}\end{{matrix}}"
|
M = "\\begin{{matrix}}{text}\\end{{matrix}}"
|
||||||
@ -8,7 +8,7 @@ On 23/01/2025
|
|||||||
import lxml.etree as ET
|
import lxml.etree as ET
|
||||||
from pylatexenc.latexencode import UnicodeToLatexEncoder
|
from pylatexenc.latexencode import UnicodeToLatexEncoder
|
||||||
|
|
||||||
from docling.backend.docx_latex.latex_dict import (
|
from docling.backend.docx.latex.latex_dict import (
|
||||||
ALN,
|
ALN,
|
||||||
ARR,
|
ARR,
|
||||||
BACKSLASH,
|
BACKSLASH,
|
||||||
@ -26,7 +26,7 @@ from PIL import Image, UnidentifiedImageError
|
|||||||
from typing_extensions import override
|
from typing_extensions import override
|
||||||
|
|
||||||
from docling.backend.abstract_backend import DeclarativeDocumentBackend
|
from docling.backend.abstract_backend import DeclarativeDocumentBackend
|
||||||
from docling.backend.docx_latex.omml import oMath2Latex
|
from docling.backend.docx.latex.omml import oMath2Latex
|
||||||
from docling.datamodel.base_models import InputFormat
|
from docling.datamodel.base_models import InputFormat
|
||||||
from docling.datamodel.document import InputDocument
|
from docling.datamodel.document import InputDocument
|
||||||
|
|
||||||
@ -164,7 +164,6 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
) -> DoclingDocument:
|
) -> DoclingDocument:
|
||||||
for element in body:
|
for element in body:
|
||||||
tag_name = etree.QName(element).localname
|
tag_name = etree.QName(element).localname
|
||||||
|
|
||||||
# Check for Inline Images (blip elements)
|
# Check for Inline Images (blip elements)
|
||||||
namespaces = {
|
namespaces = {
|
||||||
"a": "http://schemas.openxmlformats.org/drawingml/2006/main",
|
"a": "http://schemas.openxmlformats.org/drawingml/2006/main",
|
||||||
@ -262,6 +261,24 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
else:
|
else:
|
||||||
return label, None
|
return label, None
|
||||||
|
|
||||||
|
def handle_equations_in_text(self, element, text):
|
||||||
|
only_texts = []
|
||||||
|
only_equations = []
|
||||||
|
texts_and_equations = []
|
||||||
|
for subt in element.iter():
|
||||||
|
tag_name = etree.QName(subt).localname
|
||||||
|
if tag_name == "t" and "math" not in subt.tag:
|
||||||
|
only_texts.append(subt.text)
|
||||||
|
texts_and_equations.append(subt.text)
|
||||||
|
elif "oMath" in subt.tag and "oMathPara" not in subt.tag:
|
||||||
|
latex_equation = str(oMath2Latex(subt))
|
||||||
|
only_equations.append(latex_equation)
|
||||||
|
texts_and_equations.append(latex_equation)
|
||||||
|
|
||||||
|
if "".join(only_texts) != text:
|
||||||
|
return text
|
||||||
|
|
||||||
|
return "".join(texts_and_equations), only_equations
|
||||||
|
|
||||||
def handle_text_elements(
|
def handle_text_elements(
|
||||||
self,
|
self,
|
||||||
@ -272,7 +289,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
paragraph = Paragraph(element, docx_obj)
|
paragraph = Paragraph(element, docx_obj)
|
||||||
|
|
||||||
raw_text = paragraph.text
|
raw_text = paragraph.text
|
||||||
text = self.handle_equations_in_text(element=element, text=raw_text)
|
text, equations = self.handle_equations_in_text(element=element, text=raw_text)
|
||||||
|
|
||||||
if text is None:
|
if text is None:
|
||||||
return
|
return
|
||||||
@ -326,36 +343,57 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
self.parents[0] = doc.add_text(
|
self.parents[0] = doc.add_text(
|
||||||
parent=None, label=DocItemLabel.TITLE, text=text
|
parent=None, label=DocItemLabel.TITLE, text=text
|
||||||
)
|
)
|
||||||
|
|
||||||
elif "Heading" in p_style_id:
|
elif "Heading" in p_style_id:
|
||||||
self.add_header(doc, p_level, text)
|
self.add_header(doc, p_level, text)
|
||||||
|
|
||||||
elif p_style_id in [
|
elif len(equations) > 0:
|
||||||
"Subtitle",
|
if (raw_text is None or len(raw_text) == 0) and len(text) > 0:
|
||||||
"Author",
|
|
||||||
"ListParagraph",
|
|
||||||
"ListBullet",
|
|
||||||
"Quote",
|
|
||||||
]:
|
|
||||||
level = self.get_level()
|
|
||||||
doc.add_text(
|
|
||||||
label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
|
|
||||||
)
|
|
||||||
|
|
||||||
elif (raw_text is None or len(raw_text) == 0) and len(text) > 0:
|
|
||||||
# Standalone equation
|
# Standalone equation
|
||||||
# Entities in which all text comes from equations
|
|
||||||
level = self.get_level()
|
level = self.get_level()
|
||||||
if text.strip().startswith("$") and text.strip().endswith("$"):
|
|
||||||
text = text.strip()[1:-1]
|
|
||||||
doc.add_text(
|
doc.add_text(
|
||||||
label=DocItemLabel.FORMULA, parent=self.parents[level - 1], text=text
|
label=DocItemLabel.FORMULA,
|
||||||
|
parent=self.parents[level - 1],
|
||||||
|
text=text,
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
# Inline equation
|
||||||
|
level = self.get_level()
|
||||||
|
inline_equation = doc.add_group(
|
||||||
|
label=GroupLabel.INLINE, parent=self.parents[level - 1]
|
||||||
|
)
|
||||||
|
text_tmp = text
|
||||||
|
for eq in equations:
|
||||||
|
if len(text_tmp) == 0:
|
||||||
|
break
|
||||||
|
pre_eq_text = text_tmp.split(eq, maxsplit=1)[0]
|
||||||
|
text_tmp = text_tmp.split(eq, maxsplit=1)[1]
|
||||||
|
if len(pre_eq_text) > 0:
|
||||||
|
doc.add_text(
|
||||||
|
label=DocItemLabel.PARAGRAPH,
|
||||||
|
parent=inline_equation,
|
||||||
|
text=pre_eq_text,
|
||||||
|
)
|
||||||
|
doc.add_text(
|
||||||
|
label=DocItemLabel.FORMULA,
|
||||||
|
parent=inline_equation,
|
||||||
|
text=eq,
|
||||||
|
)
|
||||||
|
if len(text_tmp) > 0:
|
||||||
|
doc.add_text(
|
||||||
|
label=DocItemLabel.PARAGRAPH,
|
||||||
|
parent=inline_equation,
|
||||||
|
text=text_tmp,
|
||||||
)
|
)
|
||||||
|
|
||||||
elif p_style_id in [
|
elif p_style_id in [
|
||||||
"Paragraph",
|
"Paragraph",
|
||||||
"Normal",
|
"Normal",
|
||||||
|
"Subtitle",
|
||||||
|
"Author",
|
||||||
"DefaultText",
|
"DefaultText",
|
||||||
|
"ListParagraph",
|
||||||
|
"ListBullet",
|
||||||
|
"Quote",
|
||||||
]:
|
]:
|
||||||
level = self.get_level()
|
level = self.get_level()
|
||||||
doc.add_text(
|
doc.add_text(
|
||||||
@ -367,8 +405,9 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
|
|||||||
# hence we treat all other labels as pure text
|
# hence we treat all other labels as pure text
|
||||||
level = self.get_level()
|
level = self.get_level()
|
||||||
doc.add_text(
|
doc.add_text(
|
||||||
label=DocItemLabel.TEXT, parent=self.parents[level - 1], text=text
|
label=DocItemLabel.PARAGRAPH, parent=self.parents[level - 1], text=text
|
||||||
)
|
)
|
||||||
|
|
||||||
self.update_history(p_style_id, p_level, numid, ilevel)
|
self.update_history(p_style_id, p_level, numid, ilevel)
|
||||||
return
|
return
|
||||||
|
|
||||||
|
|||||||
122
poetry.lock
generated
122
poetry.lock
generated
@ -1,4 +1,4 @@
|
|||||||
# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
|
# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "accelerate"
|
name = "accelerate"
|
||||||
@ -33,13 +33,13 @@ testing = ["bitsandbytes", "datasets", "diffusers", "evaluate", "parameterized",
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "aiohappyeyeballs"
|
name = "aiohappyeyeballs"
|
||||||
version = "2.4.6"
|
version = "2.4.8"
|
||||||
description = "Happy Eyeballs for asyncio"
|
description = "Happy Eyeballs for asyncio"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.9"
|
python-versions = ">=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "aiohappyeyeballs-2.4.6-py3-none-any.whl", hash = "sha256:147ec992cf873d74f5062644332c539fcd42956dc69453fe5204195e560517e1"},
|
{file = "aiohappyeyeballs-2.4.8-py3-none-any.whl", hash = "sha256:6cac4f5dd6e34a9644e69cf9021ef679e4394f54e58a183056d12009e42ea9e3"},
|
||||||
{file = "aiohappyeyeballs-2.4.6.tar.gz", hash = "sha256:9b05052f9042985d32ecbe4b59a77ae19c006a78f1344d7fdad69d28ded3d0b0"},
|
{file = "aiohappyeyeballs-2.4.8.tar.gz", hash = "sha256:19728772cb12263077982d2f55453babd8bec6a052a926cd5c0c42796da8bf62"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
@ -311,6 +311,24 @@ files = [
|
|||||||
docs = ["furo", "jaraco.packaging (>=9.3)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
|
docs = ["furo", "jaraco.packaging (>=9.3)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
|
||||||
testing = ["jaraco.test", "pytest (!=8.0.*)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)"]
|
testing = ["jaraco.test", "pytest (!=8.0.*)", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)"]
|
||||||
|
|
||||||
|
[[package]]
|
||||||
|
name = "backrefs"
|
||||||
|
version = "5.8"
|
||||||
|
description = "A wrapper around re and regex that adds additional back references."
|
||||||
|
optional = false
|
||||||
|
python-versions = ">=3.9"
|
||||||
|
files = [
|
||||||
|
{file = "backrefs-5.8-py310-none-any.whl", hash = "sha256:c67f6638a34a5b8730812f5101376f9d41dc38c43f1fdc35cb54700f6ed4465d"},
|
||||||
|
{file = "backrefs-5.8-py311-none-any.whl", hash = "sha256:2e1c15e4af0e12e45c8701bd5da0902d326b2e200cafcd25e49d9f06d44bb61b"},
|
||||||
|
{file = "backrefs-5.8-py312-none-any.whl", hash = "sha256:bbef7169a33811080d67cdf1538c8289f76f0942ff971222a16034da88a73486"},
|
||||||
|
{file = "backrefs-5.8-py313-none-any.whl", hash = "sha256:e3a63b073867dbefd0536425f43db618578528e3896fb77be7141328642a1585"},
|
||||||
|
{file = "backrefs-5.8-py39-none-any.whl", hash = "sha256:a66851e4533fb5b371aa0628e1fee1af05135616b86140c9d787a2ffdf4b8fdc"},
|
||||||
|
{file = "backrefs-5.8.tar.gz", hash = "sha256:2cab642a205ce966af3dd4b38ee36009b31fa9502a35fd61d59ccc116e40a6bd"},
|
||||||
|
]
|
||||||
|
|
||||||
|
[package.extras]
|
||||||
|
extras = ["regex"]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "beautifulsoup4"
|
name = "beautifulsoup4"
|
||||||
version = "4.13.3"
|
version = "4.13.3"
|
||||||
@ -852,13 +870,13 @@ files = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "docling-core"
|
name = "docling-core"
|
||||||
version = "2.20.0"
|
version = "2.21.1"
|
||||||
description = "A python library to define and validate data types in Docling."
|
description = "A python library to define and validate data types in Docling."
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = "<4.0,>=3.9"
|
python-versions = "<4.0,>=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "docling_core-2.20.0-py3-none-any.whl", hash = "sha256:72f50fce277b7bb51f4134f443240c041582184305c3bcaabdea13fc5550f160"},
|
{file = "docling_core-2.21.1-py3-none-any.whl", hash = "sha256:b8112915728cdc14f328f636f6c0ed36e6bbcc02ff940cc0bf85e303738671c3"},
|
||||||
{file = "docling_core-2.20.0.tar.gz", hash = "sha256:9733581c15f5a9b5e3a6cb74fa995cc4078ff16668007f86c5f75d1ea9180d7f"},
|
{file = "docling_core-2.21.1.tar.gz", hash = "sha256:3ccc50197d24a3156cfc6c22c8404c58757749646d876a1c1c69fd800f664a4f"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -880,13 +898,13 @@ chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"]
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "docling-ibm-models"
|
name = "docling-ibm-models"
|
||||||
version = "3.4.0"
|
version = "3.4.1"
|
||||||
description = "This package contains the AI models used by the Docling PDF conversion package"
|
description = "This package contains the AI models used by the Docling PDF conversion package"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = "<4.0,>=3.9"
|
python-versions = "<4.0,>=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "docling_ibm_models-3.4.0-py3-none-any.whl", hash = "sha256:186517ff1f76e76113600fa1e5a699927325081a8013fdd5d0551121c2e34190"},
|
{file = "docling_ibm_models-3.4.1-py3-none-any.whl", hash = "sha256:c3582c99dddfa3f0eafcf80cf1267fd8efa39c4a74cc7a88f9dd49684fac2986"},
|
||||||
{file = "docling_ibm_models-3.4.0.tar.gz", hash = "sha256:fb79beeb07d1bb9bc8acf9d0a44643cd7ce1910aa418cd685e2e477b13eeafee"},
|
{file = "docling_ibm_models-3.4.1.tar.gz", hash = "sha256:093b4dff2ea284a4953c3aa009e29945208b8d389b94fb14940a03a93f673e96"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -1331,13 +1349,13 @@ test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit",
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "griffe"
|
name = "griffe"
|
||||||
version = "1.5.7"
|
version = "1.6.0"
|
||||||
description = "Signatures for entire Python programs. Extract the structure, the frame, the skeleton of your project, to generate API documentation or find breaking changes in your API."
|
description = "Signatures for entire Python programs. Extract the structure, the frame, the skeleton of your project, to generate API documentation or find breaking changes in your API."
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.9"
|
python-versions = ">=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "griffe-1.5.7-py3-none-any.whl", hash = "sha256:4af8ec834b64de954d447c7b6672426bb145e71605c74a4e22d510cc79fe7d8b"},
|
{file = "griffe-1.6.0-py3-none-any.whl", hash = "sha256:9f1dfe035d4715a244ed2050dfbceb05b1f470809ed4f6bb10ece5a7302f8dd1"},
|
||||||
{file = "griffe-1.5.7.tar.gz", hash = "sha256:465238c86deaf1137761f700fb343edd8ffc846d72f6de43c3c345ccdfbebe92"},
|
{file = "griffe-1.6.0.tar.gz", hash = "sha256:eb5758088b9c73ad61c7ac014f3cdfb4c57b5c2fcbfca69996584b702aefa354"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -1818,18 +1836,18 @@ testing = ["Django", "attrs", "colorama", "docopt", "pytest (<9.0.0)"]
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "jeepney"
|
name = "jeepney"
|
||||||
version = "0.8.0"
|
version = "0.9.0"
|
||||||
description = "Low-level, pure Python DBus protocol wrapper."
|
description = "Low-level, pure Python DBus protocol wrapper."
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.7"
|
python-versions = ">=3.7"
|
||||||
files = [
|
files = [
|
||||||
{file = "jeepney-0.8.0-py3-none-any.whl", hash = "sha256:c0a454ad016ca575060802ee4d590dd912e35c122fa04e70306de3d076cce755"},
|
{file = "jeepney-0.9.0-py3-none-any.whl", hash = "sha256:97e5714520c16fc0a45695e5365a2e11b81ea79bba796e26f9f1d178cb182683"},
|
||||||
{file = "jeepney-0.8.0.tar.gz", hash = "sha256:5efe48d255973902f6badc3ce55e2aa6c5c3b3bc642059ef3a91247bcfcc5806"},
|
{file = "jeepney-0.9.0.tar.gz", hash = "sha256:cf0e9e845622b81e4a28df94c40345400256ec608d0e55bb8a3feaa9163f5732"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.extras]
|
[package.extras]
|
||||||
test = ["async-timeout", "pytest", "pytest-asyncio (>=0.17)", "pytest-trio", "testpath", "trio"]
|
test = ["async-timeout", "pytest", "pytest-asyncio (>=0.17)", "pytest-trio", "testpath", "trio"]
|
||||||
trio = ["async_generator", "trio"]
|
trio = ["trio"]
|
||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "jinja2"
|
name = "jinja2"
|
||||||
@ -2715,17 +2733,18 @@ pygments = ">2.12.0"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "mkdocs-material"
|
name = "mkdocs-material"
|
||||||
version = "9.6.5"
|
version = "9.6.7"
|
||||||
description = "Documentation that simply works"
|
description = "Documentation that simply works"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.8"
|
python-versions = ">=3.8"
|
||||||
files = [
|
files = [
|
||||||
{file = "mkdocs_material-9.6.5-py3-none-any.whl", hash = "sha256:aad3e6fb860c20870f75fb2a69ef901f1be727891e41adb60b753efcae19453b"},
|
{file = "mkdocs_material-9.6.7-py3-none-any.whl", hash = "sha256:8a159e45e80fcaadd9fbeef62cbf928569b93df954d4dc5ba76d46820caf7b47"},
|
||||||
{file = "mkdocs_material-9.6.5.tar.gz", hash = "sha256:b714679a8c91b0ffe2188e11ed58c44d2523e9c2ae26a29cc652fa7478faa21f"},
|
{file = "mkdocs_material-9.6.7.tar.gz", hash = "sha256:3e2c1fceb9410056c2d91f334a00cdea3215c28750e00c691c1e46b2a33309b4"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
babel = ">=2.10,<3.0"
|
babel = ">=2.10,<3.0"
|
||||||
|
backrefs = ">=5.7.post1,<6.0"
|
||||||
colorama = ">=0.4,<1.0"
|
colorama = ">=0.4,<1.0"
|
||||||
jinja2 = ">=3.0,<4.0"
|
jinja2 = ">=3.0,<4.0"
|
||||||
markdown = ">=3.2,<4.0"
|
markdown = ">=3.2,<4.0"
|
||||||
@ -2734,7 +2753,6 @@ mkdocs-material-extensions = ">=1.3,<2.0"
|
|||||||
paginate = ">=0.5,<1.0"
|
paginate = ">=0.5,<1.0"
|
||||||
pygments = ">=2.16,<3.0"
|
pygments = ">=2.16,<3.0"
|
||||||
pymdown-extensions = ">=10.2,<11.0"
|
pymdown-extensions = ">=10.2,<11.0"
|
||||||
regex = ">=2022.4"
|
|
||||||
requests = ">=2.26,<3.0"
|
requests = ">=2.26,<3.0"
|
||||||
|
|
||||||
[package.extras]
|
[package.extras]
|
||||||
@ -4755,13 +4773,13 @@ typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "pydantic-settings"
|
name = "pydantic-settings"
|
||||||
version = "2.8.0"
|
version = "2.8.1"
|
||||||
description = "Settings management using Pydantic"
|
description = "Settings management using Pydantic"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.8"
|
python-versions = ">=3.8"
|
||||||
files = [
|
files = [
|
||||||
{file = "pydantic_settings-2.8.0-py3-none-any.whl", hash = "sha256:c782c7dc3fb40e97b238e713c25d26f64314aece2e91abcff592fcac15f71820"},
|
{file = "pydantic_settings-2.8.1-py3-none-any.whl", hash = "sha256:81942d5ac3d905f7f3ee1a70df5dfb62d5569c12f51a5a647defc1c3d9ee2e9c"},
|
||||||
{file = "pydantic_settings-2.8.0.tar.gz", hash = "sha256:88e2ca28f6e68ea102c99c3c401d6c9078e68a5df600e97b43891c34e089500a"},
|
{file = "pydantic_settings-2.8.1.tar.gz", hash = "sha256:d5c663dfbe9db9d5e1c646b2e161da12f0d734d422ee56f567d0ea2cee4e8585"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -5907,26 +5925,26 @@ files = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "safetensors"
|
name = "safetensors"
|
||||||
version = "0.5.2"
|
version = "0.5.3"
|
||||||
description = ""
|
description = ""
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.7"
|
python-versions = ">=3.7"
|
||||||
files = [
|
files = [
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:45b6092997ceb8aa3801693781a71a99909ab9cc776fbc3fa9322d29b1d3bef2"},
|
{file = "safetensors-0.5.3-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:bd20eb133db8ed15b40110b7c00c6df51655a2998132193de2f75f72d99c7073"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:6d0d6a8ee2215a440e1296b843edf44fd377b055ba350eaba74655a2fe2c4bae"},
|
{file = "safetensors-0.5.3-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:21d01c14ff6c415c485616b8b0bf961c46b3b343ca59110d38d744e577f9cce7"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:86016d40bcaa3bcc9a56cd74d97e654b5f4f4abe42b038c71e4f00a089c4526c"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:11bce6164887cd491ca75c2326a113ba934be596e22b28b1742ce27b1d076467"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:990833f70a5f9c7d3fc82c94507f03179930ff7d00941c287f73b6fcbf67f19e"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4a243be3590bc3301c821da7a18d87224ef35cbd3e5f5727e4e0728b8172411e"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3dfa7c2f3fe55db34eba90c29df94bcdac4821043fc391cb5d082d9922013869"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8bd84b12b1670a6f8e50f01e28156422a2bc07fb16fc4e98bded13039d688a0d"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:46ff2116150ae70a4e9c490d2ab6b6e1b1b93f25e520e540abe1b81b48560c3a"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:391ac8cab7c829452175f871fcaf414aa1e292b5448bd02620f675a7f3e7abb9"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ab696dfdc060caffb61dbe4066b86419107a24c804a4e373ba59be699ebd8d5"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cead1fa41fc54b1e61089fa57452e8834f798cb1dc7a09ba3524f1eb08e0317a"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:03c937100f38c9ff4c1507abea9928a6a9b02c9c1c9c3609ed4fb2bf413d4975"},
|
{file = "safetensors-0.5.3-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1077f3e94182d72618357b04b5ced540ceb71c8a813d3319f1aba448e68a770d"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:a00e737948791b94dad83cf0eafc09a02c4d8c2171a239e8c8572fe04e25960e"},
|
{file = "safetensors-0.5.3-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:799021e78287bac619c7b3f3606730a22da4cda27759ddf55d37c8db7511c74b"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:d3a06fae62418ec8e5c635b61a8086032c9e281f16c63c3af46a6efbab33156f"},
|
{file = "safetensors-0.5.3-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:df26da01aaac504334644e1b7642fa000bfec820e7cef83aeac4e355e03195ff"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:1506e4c2eda1431099cebe9abf6c76853e95d0b7a95addceaa74c6019c65d8cf"},
|
{file = "safetensors-0.5.3-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:32c3ef2d7af8b9f52ff685ed0bc43913cdcde135089ae322ee576de93eae5135"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:5c5b5d9da594f638a259fca766046f44c97244cc7ab8bef161b3e80d04becc76"},
|
{file = "safetensors-0.5.3-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:37f1521be045e56fc2b54c606d4455573e717b2d887c579ee1dbba5f868ece04"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-win32.whl", hash = "sha256:fe55c039d97090d1f85277d402954dd6ad27f63034fa81985a9cc59655ac3ee2"},
|
{file = "safetensors-0.5.3-cp38-abi3-win32.whl", hash = "sha256:cfc0ec0846dcf6763b0ed3d1846ff36008c6e7290683b61616c4b040f6a54ace"},
|
||||||
{file = "safetensors-0.5.2-cp38-abi3-win_amd64.whl", hash = "sha256:78abdddd03a406646107f973c7843276e7b64e5e32623529dc17f3d94a20f589"},
|
{file = "safetensors-0.5.3-cp38-abi3-win_amd64.whl", hash = "sha256:836cbbc320b47e80acd40e44c8682db0e8ad7123209f69b093def21ec7cafd11"},
|
||||||
{file = "safetensors-0.5.2.tar.gz", hash = "sha256:cb4a8d98ba12fa016f4241932b1fc5e702e5143f5374bba0bbcf7ddc1c4cf2b8"},
|
{file = "safetensors-0.5.3.tar.gz", hash = "sha256:b6b0d6ecacec39a4fdd99cc19f4576f5219ce858e6fd8dbe7609df0b8dc56965"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -6223,13 +6241,13 @@ train = ["accelerate (>=0.20.3)", "datasets"]
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "setuptools"
|
name = "setuptools"
|
||||||
version = "75.8.1"
|
version = "75.8.2"
|
||||||
description = "Easily download, build, install, upgrade, and uninstall Python packages"
|
description = "Easily download, build, install, upgrade, and uninstall Python packages"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.9"
|
python-versions = ">=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "setuptools-75.8.1-py3-none-any.whl", hash = "sha256:3bc32c0b84c643299ca94e77f834730f126efd621de0cc1de64119e0e17dab1f"},
|
{file = "setuptools-75.8.2-py3-none-any.whl", hash = "sha256:558e47c15f1811c1fa7adbd0096669bf76c1d3f433f58324df69f3f5ecac4e8f"},
|
||||||
{file = "setuptools-75.8.1.tar.gz", hash = "sha256:65fb779a8f28895242923582eadca2337285f0891c2c9e160754df917c3d2530"},
|
{file = "setuptools-75.8.2.tar.gz", hash = "sha256:4880473a969e5f23f2a2be3646b2dfd84af9028716d398e46192f84bc36900d2"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.extras]
|
[package.extras]
|
||||||
@ -7227,13 +7245,13 @@ files = [
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "types-requests"
|
name = "types-requests"
|
||||||
version = "2.32.0.20241016"
|
version = "2.32.0.20250301"
|
||||||
description = "Typing stubs for requests"
|
description = "Typing stubs for requests"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.8"
|
python-versions = ">=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "types-requests-2.32.0.20241016.tar.gz", hash = "sha256:0d9cad2f27515d0e3e3da7134a1b6f28fb97129d86b867f24d9c726452634d95"},
|
{file = "types_requests-2.32.0.20250301-py3-none-any.whl", hash = "sha256:0003e0124e2cbefefb88222ff822b48616af40c74df83350f599a650c8de483b"},
|
||||||
{file = "types_requests-2.32.0.20241016-py3-none-any.whl", hash = "sha256:4195d62d6d3e043a4eaaf08ff8a62184584d2e8684e9d2aa178c7915a7da3747"},
|
{file = "types_requests-2.32.0.20250301.tar.gz", hash = "sha256:3d909dc4eaab159c0d964ebe8bfa326a7afb4578d8706408d417e17d61b0c500"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -7241,13 +7259,13 @@ urllib3 = ">=2"
|
|||||||
|
|
||||||
[[package]]
|
[[package]]
|
||||||
name = "types-tqdm"
|
name = "types-tqdm"
|
||||||
version = "4.67.0.20241221"
|
version = "4.67.0.20250301"
|
||||||
description = "Typing stubs for tqdm"
|
description = "Typing stubs for tqdm"
|
||||||
optional = false
|
optional = false
|
||||||
python-versions = ">=3.8"
|
python-versions = ">=3.9"
|
||||||
files = [
|
files = [
|
||||||
{file = "types_tqdm-4.67.0.20241221-py3-none-any.whl", hash = "sha256:a1f1c9cda5c2d8482d2c73957a5398bfdedda10f6bc7b3b4e812d5c910486d29"},
|
{file = "types_tqdm-4.67.0.20250301-py3-none-any.whl", hash = "sha256:8af97deb8e6874af833555dc1fe0fcd456b1a789470bf6cd8813d4e7ee4f6c5b"},
|
||||||
{file = "types_tqdm-4.67.0.20241221.tar.gz", hash = "sha256:e56046631056922385abe89aeb18af5611f471eadd7918a0ad7f34d84cd4c8cc"},
|
{file = "types_tqdm-4.67.0.20250301.tar.gz", hash = "sha256:5e89a38ad89b867823368eb97d9f90d2fc69806bb055dde62716a05da62b5e0d"},
|
||||||
]
|
]
|
||||||
|
|
||||||
[package.dependencies]
|
[package.dependencies]
|
||||||
@ -7843,4 +7861,4 @@ vlm = ["accelerate", "transformers", "transformers"]
|
|||||||
[metadata]
|
[metadata]
|
||||||
lock-version = "2.0"
|
lock-version = "2.0"
|
||||||
python-versions = "^3.9"
|
python-versions = "^3.9"
|
||||||
content-hash = "1d4718b694098b0676f1ad1606d769887e51fc29f604e5f4c83dd5e1c90557e7"
|
content-hash = "a340b1230bc83cdcff125a84eee457b1d8786abc112f2c0553391a4ab9f092ea"
|
||||||
|
|||||||
@ -2,12 +2,32 @@
|
|||||||
name = "docling"
|
name = "docling"
|
||||||
version = "2.25.1" # DO NOT EDIT, updated automatically
|
version = "2.25.1" # DO NOT EDIT, updated automatically
|
||||||
description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
|
description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
|
||||||
authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Panos Vagenas <pva@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
|
authors = [
|
||||||
|
"Christoph Auer <cau@zurich.ibm.com>",
|
||||||
|
"Michele Dolfi <dol@zurich.ibm.com>",
|
||||||
|
"Maxim Lysak <mly@zurich.ibm.com>",
|
||||||
|
"Nikos Livathinos <nli@zurich.ibm.com>",
|
||||||
|
"Ahmed Nassar <ahn@zurich.ibm.com>",
|
||||||
|
"Panos Vagenas <pva@zurich.ibm.com>",
|
||||||
|
"Peter Staar <taa@zurich.ibm.com>",
|
||||||
|
]
|
||||||
license = "MIT"
|
license = "MIT"
|
||||||
readme = "README.md"
|
readme = "README.md"
|
||||||
repository = "https://github.com/DS4SD/docling"
|
repository = "https://github.com/DS4SD/docling"
|
||||||
homepage = "https://github.com/DS4SD/docling"
|
homepage = "https://github.com/DS4SD/docling"
|
||||||
keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown", "layout model", "segmentation", "table structure", "table former"]
|
keywords = [
|
||||||
|
"docling",
|
||||||
|
"convert",
|
||||||
|
"document",
|
||||||
|
"pdf",
|
||||||
|
"docx",
|
||||||
|
"html",
|
||||||
|
"markdown",
|
||||||
|
"layout model",
|
||||||
|
"segmentation",
|
||||||
|
"table structure",
|
||||||
|
"table former",
|
||||||
|
]
|
||||||
classifiers = [
|
classifiers = [
|
||||||
"License :: OSI Approved :: MIT License",
|
"License :: OSI Approved :: MIT License",
|
||||||
"Operating System :: MacOS :: MacOS X",
|
"Operating System :: MacOS :: MacOS X",
|
||||||
@ -16,7 +36,7 @@ keywords= ["docling", "convert", "document", "pdf", "docx", "html", "markdown",
|
|||||||
"Intended Audience :: Developers",
|
"Intended Audience :: Developers",
|
||||||
"Intended Audience :: Science/Research",
|
"Intended Audience :: Science/Research",
|
||||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||||
"Programming Language :: Python :: 3"
|
"Programming Language :: Python :: 3",
|
||||||
]
|
]
|
||||||
packages = [{ include = "docling" }]
|
packages = [{ include = "docling" }]
|
||||||
|
|
||||||
@ -26,7 +46,7 @@ packages = [{include = "docling"}]
|
|||||||
######################
|
######################
|
||||||
python = "^3.9"
|
python = "^3.9"
|
||||||
pydantic = "^2.0.0"
|
pydantic = "^2.0.0"
|
||||||
docling-core = {extras = ["chunking"], version = "^2.19.0"}
|
docling-core = { extras = ["chunking"], version = "^2.21.1" }
|
||||||
docling-ibm-models = "^3.4.0"
|
docling-ibm-models = "^3.4.0"
|
||||||
docling-parse = "^3.3.0"
|
docling-parse = "^3.3.0"
|
||||||
filetype = "^1.2.0"
|
filetype = "^1.2.0"
|
||||||
@ -40,7 +60,7 @@ certifi = ">=2024.7.4"
|
|||||||
rtree = "^1.3.0"
|
rtree = "^1.3.0"
|
||||||
scipy = [
|
scipy = [
|
||||||
{ version = "^1.6.0", markers = "python_version >= '3.10'" },
|
{ version = "^1.6.0", markers = "python_version >= '3.10'" },
|
||||||
{ version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" }
|
{ version = ">=1.6.0,<1.14.0", markers = "python_version < '3.10'" },
|
||||||
]
|
]
|
||||||
typer = "^0.12.5"
|
typer = "^0.12.5"
|
||||||
python-docx = "^1.1.2"
|
python-docx = "^1.1.2"
|
||||||
@ -56,18 +76,19 @@ onnxruntime = [
|
|||||||
# 1.19.2 is the last version with python3.9 support,
|
# 1.19.2 is the last version with python3.9 support,
|
||||||
# see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0
|
# see https://github.com/microsoft/onnxruntime/releases/tag/v1.20.0
|
||||||
{ version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
|
{ version = ">=1.7.0,<1.20.0", optional = true, markers = "python_version < '3.10'" },
|
||||||
{ version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" }
|
{ version = "^1.7.0", optional = true, markers = "python_version >= '3.10'" },
|
||||||
]
|
]
|
||||||
|
|
||||||
transformers = [
|
transformers = [
|
||||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
|
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^4.46.0", optional = true },
|
||||||
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true }
|
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~4.42.0", optional = true },
|
||||||
]
|
]
|
||||||
accelerate = [
|
accelerate = [
|
||||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
|
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^1.2.1", optional = true },
|
||||||
]
|
]
|
||||||
pillow = ">=10.0.0,<12.0.0"
|
pillow = ">=10.0.0,<12.0.0"
|
||||||
tqdm = "^4.65.0"
|
tqdm = "^4.65.0"
|
||||||
|
pylatexenc = "^2.10"
|
||||||
|
|
||||||
[tool.poetry.group.dev.dependencies]
|
[tool.poetry.group.dev.dependencies]
|
||||||
black = { extras = ["jupyter"], version = "^24.4.2" }
|
black = { extras = ["jupyter"], version = "^24.4.2" }
|
||||||
@ -118,11 +139,11 @@ optional = true
|
|||||||
[tool.poetry.group.mac_intel.dependencies]
|
[tool.poetry.group.mac_intel.dependencies]
|
||||||
torch = [
|
torch = [
|
||||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2" },
|
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^2.2.2" },
|
||||||
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2"}
|
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~2.2.2" },
|
||||||
]
|
]
|
||||||
torchvision = [
|
torchvision = [
|
||||||
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0" },
|
{ markers = "sys_platform != 'darwin' or platform_machine != 'x86_64'", version = "^0" },
|
||||||
{markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2"}
|
{ markers = "sys_platform == 'darwin' and platform_machine == 'x86_64'", version = "~0.17.2" },
|
||||||
]
|
]
|
||||||
|
|
||||||
[tool.poetry.extras]
|
[tool.poetry.extras]
|
||||||
@ -170,6 +191,7 @@ module = [
|
|||||||
"lxml.*",
|
"lxml.*",
|
||||||
"huggingface_hub.*",
|
"huggingface_hub.*",
|
||||||
"transformers.*",
|
"transformers.*",
|
||||||
|
"pylatexenc.*",
|
||||||
]
|
]
|
||||||
ignore_missing_imports = true
|
ignore_missing_imports = true
|
||||||
|
|
||||||
|
|||||||
@ -1,31 +1,40 @@
|
|||||||
item-0 at level 0: unspecified: group _root_
|
item-0 at level 0: unspecified: group _root_
|
||||||
item-1 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
|
item-1 at level 1: inline: group group
|
||||||
item-2 at level 1: paragraph:
|
item-2 at level 2: paragraph: This is a word document and this is an inline equation:
|
||||||
item-3 at level 1: formula: a^{2}+b^{2}=c^{2} \text{ \texttimes } 23
|
item-3 at level 2: formula: A= \pi r^{2}
|
||||||
item-4 at level 1: paragraph: And that is an equation by itself. Cheers!
|
item-4 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
|
||||||
item-5 at level 1: paragraph:
|
item-5 at level 1: paragraph:
|
||||||
item-6 at level 1: paragraph: This is another equation:
|
item-6 at level 1: formula: a^{2}+b^{2}=c^{2} \text{ \texttimes } 23
|
||||||
item-7 at level 1: formula: f\left(x\right)=a_{0}+\sum_{n=1} ... })+b_{n}\sin(\frac{n \pi x}{L})\right)
|
item-7 at level 1: paragraph: And that is an equation by itself. Cheers!
|
||||||
item-8 at level 1: paragraph:
|
item-8 at level 1: paragraph:
|
||||||
item-9 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
|
item-9 at level 1: paragraph: This is another equation:
|
||||||
item-10 at level 1: paragraph:
|
item-10 at level 1: formula: f\left(x\right)=a_{0}+\sum_{n=1} ... })+b_{n}\sin(\frac{n \pi x}{L})\right)
|
||||||
item-11 at level 1: paragraph:
|
item-11 at level 1: paragraph:
|
||||||
item-12 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
|
item-12 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
|
||||||
item-13 at level 1: paragraph:
|
item-13 at level 1: paragraph:
|
||||||
item-14 at level 1: formula: \left(x+a\right)^{n}=\sum_{k=0}^ ... ac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}
|
item-14 at level 1: paragraph:
|
||||||
item-15 at level 1: paragraph:
|
item-15 at level 1: inline: group group
|
||||||
item-16 at level 1: paragraph: And that is an equation by itself. Cheers!
|
item-16 at level 2: paragraph: This is a word document and this is an inline equation:
|
||||||
item-17 at level 1: paragraph:
|
item-17 at level 2: formula: A= \pi r^{2}
|
||||||
item-18 at level 1: paragraph: This is another equation:
|
item-18 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
|
||||||
item-19 at level 1: paragraph:
|
item-19 at level 1: paragraph:
|
||||||
item-20 at level 1: formula: \left(1+x\right)^{n}=1+\frac{nx} ... ht)x^{2}}{2!}+ \text{ \textellipsis }
|
item-20 at level 1: formula: \left(x+a\right)^{n}=\sum_{k=0}^ ... ac{}{}{0pt}{}{n}{k}\right)x^{k}a^{n-k}
|
||||||
item-21 at level 1: paragraph:
|
item-21 at level 1: paragraph:
|
||||||
item-22 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
|
item-22 at level 1: paragraph: And that is an equation by itself. Cheers!
|
||||||
item-23 at level 1: paragraph:
|
item-23 at level 1: paragraph:
|
||||||
item-24 at level 1: paragraph:
|
item-24 at level 1: paragraph: This is another equation:
|
||||||
item-25 at level 1: paragraph: This is a word document and this ... nt an equation by line, I can do this:
|
item-25 at level 1: paragraph:
|
||||||
item-26 at level 1: paragraph:
|
item-26 at level 1: formula: \left(1+x\right)^{n}=1+\frac{nx} ... ght)x^{2}}{2!}+ \text{ \textellipsis }
|
||||||
item-27 at level 1: formula: e^{x}=1+\frac{x}{1!}+\frac{x^{2} ... tellipsis } , - \infty < x < \infty
|
item-27 at level 1: paragraph:
|
||||||
item-28 at level 1: paragraph:
|
item-28 at level 1: paragraph: This is text. This is text. This ... s is text. This is text. This is text.
|
||||||
item-29 at level 1: paragraph: And that is an equation by itself. Cheers!
|
item-29 at level 1: paragraph:
|
||||||
item-30 at level 1: paragraph:
|
item-30 at level 1: paragraph:
|
||||||
|
item-31 at level 1: inline: group group
|
||||||
|
item-32 at level 2: paragraph: This is a word document and this is an inline equation:
|
||||||
|
item-33 at level 2: formula: A= \pi r^{2}
|
||||||
|
item-34 at level 2: paragraph: . If instead, I want an equation by line, I can do this:
|
||||||
|
item-35 at level 1: paragraph:
|
||||||
|
item-36 at level 1: formula: e^{x}=1+\frac{x}{1!}+\frac{x^{2} ... xtellipsis } , - \infty < x < \infty
|
||||||
|
item-37 at level 1: paragraph:
|
||||||
|
item-38 at level 1: paragraph: And that is an equation by itself. Cheers!
|
||||||
|
item-39 at level 1: paragraph:
|
||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.0.0",
|
"version": "1.2.0",
|
||||||
"name": "equations",
|
"name": "equations",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -10,6 +10,7 @@
|
|||||||
"furniture": {
|
"furniture": {
|
||||||
"self_ref": "#/furniture",
|
"self_ref": "#/furniture",
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "furniture",
|
||||||
"name": "_root_",
|
"name": "_root_",
|
||||||
"label": "unspecified"
|
"label": "unspecified"
|
||||||
},
|
},
|
||||||
@ -17,13 +18,7 @@
|
|||||||
"self_ref": "#/body",
|
"self_ref": "#/body",
|
||||||
"children": [
|
"children": [
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/0"
|
"$ref": "#/groups/0"
|
||||||
},
|
|
||||||
{
|
|
||||||
"$ref": "#/texts/1"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"$ref": "#/texts/2"
|
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/3"
|
"$ref": "#/texts/3"
|
||||||
@ -56,13 +51,7 @@
|
|||||||
"$ref": "#/texts/12"
|
"$ref": "#/texts/12"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/13"
|
"$ref": "#/groups/1"
|
||||||
},
|
|
||||||
{
|
|
||||||
"$ref": "#/texts/14"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"$ref": "#/texts/15"
|
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/16"
|
"$ref": "#/texts/16"
|
||||||
@ -100,50 +89,127 @@
|
|||||||
{
|
{
|
||||||
"$ref": "#/texts/27"
|
"$ref": "#/texts/27"
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/groups/2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/31"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/32"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/33"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/34"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/35"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"content_layer": "body",
|
||||||
|
"name": "_root_",
|
||||||
|
"label": "unspecified"
|
||||||
|
},
|
||||||
|
"groups": [
|
||||||
|
{
|
||||||
|
"self_ref": "#/groups/0",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/0"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/1"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/2"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"content_layer": "body",
|
||||||
|
"name": "group",
|
||||||
|
"label": "inline"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/groups/1",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/13"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/14"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/15"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"content_layer": "body",
|
||||||
|
"name": "group",
|
||||||
|
"label": "inline"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/groups/2",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/28"
|
"$ref": "#/texts/28"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"$ref": "#/texts/29"
|
"$ref": "#/texts/29"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"$ref": "#/texts/30"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"content_layer": "body",
|
||||||
|
"name": "group",
|
||||||
|
"label": "inline"
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"name": "_root_",
|
|
||||||
"label": "unspecified"
|
|
||||||
},
|
|
||||||
"groups": [],
|
|
||||||
"texts": [
|
"texts": [
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/0",
|
"self_ref": "#/texts/0",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/0"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
|
"orig": "This is a word document and this is an inline equation: ",
|
||||||
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
|
"text": "This is a word document and this is an inline equation: "
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/1",
|
"self_ref": "#/texts/1",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/0"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "A= \\pi r^{2} ",
|
||||||
"text": ""
|
"text": "A= \\pi r^{2} "
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/2",
|
"self_ref": "#/texts/2",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/0"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "formula",
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
|
"orig": ". If instead, I want an equation by line, I can do this:",
|
||||||
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
|
"text": ". If instead, I want an equation by line, I can do this:"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/3",
|
"self_ref": "#/texts/3",
|
||||||
@ -151,10 +217,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "And that is an equation by itself. Cheers!",
|
"orig": "",
|
||||||
"text": "And that is an equation by itself. Cheers!"
|
"text": ""
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/4",
|
"self_ref": "#/texts/4",
|
||||||
@ -162,10 +229,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23",
|
||||||
"text": ""
|
"text": "a^{2}+b^{2}=c^{2} \\text{ \\texttimes } 23"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/5",
|
"self_ref": "#/texts/5",
|
||||||
@ -173,10 +241,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is another equation:",
|
"orig": "And that is an equation by itself. Cheers!",
|
||||||
"text": "This is another equation:"
|
"text": "And that is an equation by itself. Cheers!"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/6",
|
"self_ref": "#/texts/6",
|
||||||
@ -184,10 +253,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "formula",
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
|
"orig": "",
|
||||||
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
|
"text": ""
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/7",
|
"self_ref": "#/texts/7",
|
||||||
@ -195,10 +265,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "This is another equation:",
|
||||||
"text": ""
|
"text": "This is another equation:"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/8",
|
"self_ref": "#/texts/8",
|
||||||
@ -206,10 +277,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
|
"orig": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)",
|
||||||
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
|
"text": "f\\left(x\\right)=a_{0}+\\sum_{n=1}^{ \\infty }\\left(a_{n}\\cos(\\frac{n \\pi x}{L})+b_{n}\\sin(\\frac{n \\pi x}{L})\\right)"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/9",
|
"self_ref": "#/texts/9",
|
||||||
@ -217,6 +289,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -228,10 +301,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
|
||||||
"text": ""
|
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/11",
|
"self_ref": "#/texts/11",
|
||||||
@ -239,10 +313,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
|
"orig": "",
|
||||||
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
|
"text": ""
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/12",
|
"self_ref": "#/texts/12",
|
||||||
@ -250,6 +325,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -258,35 +334,38 @@
|
|||||||
{
|
{
|
||||||
"self_ref": "#/texts/13",
|
"self_ref": "#/texts/13",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/1"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "formula",
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}",
|
"orig": "This is a word document and this is an inline equation: ",
|
||||||
"text": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}"
|
"text": "This is a word document and this is an inline equation: "
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/14",
|
"self_ref": "#/texts/14",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/1"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "A= \\pi r^{2} ",
|
||||||
"text": ""
|
"text": "A= \\pi r^{2} "
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/15",
|
"self_ref": "#/texts/15",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/groups/1"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "And that is an equation by itself. Cheers!",
|
"orig": ". If instead, I want an equation by line, I can do this:",
|
||||||
"text": "And that is an equation by itself. Cheers!"
|
"text": ". If instead, I want an equation by line, I can do this:"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/16",
|
"self_ref": "#/texts/16",
|
||||||
@ -294,6 +373,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -305,10 +385,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is another equation:",
|
"orig": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}",
|
||||||
"text": "This is another equation:"
|
"text": "\\left(x+a\\right)^{n}=\\sum_{k=0}^{n}\\left(\\genfrac{}{}{0pt}{}{n}{k}\\right)x^{k}a^{n-k}"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/18",
|
"self_ref": "#/texts/18",
|
||||||
@ -316,6 +397,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -327,10 +409,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "formula",
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis } ",
|
"orig": "And that is an equation by itself. Cheers!",
|
||||||
"text": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis } "
|
"text": "And that is an equation by itself. Cheers!"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/20",
|
"self_ref": "#/texts/20",
|
||||||
@ -338,6 +421,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -349,10 +433,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
|
"orig": "This is another equation:",
|
||||||
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
|
"text": "This is another equation:"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/22",
|
"self_ref": "#/texts/22",
|
||||||
@ -360,6 +445,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -371,10 +457,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "paragraph",
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis }",
|
||||||
"text": ""
|
"text": "\\left(1+x\\right)^{n}=1+\\frac{nx}{1!}+\\frac{n\\left(n-1\\right)x^{2}}{2!}+ \\text{ \\textellipsis }"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/24",
|
"self_ref": "#/texts/24",
|
||||||
@ -382,10 +469,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:",
|
"orig": "",
|
||||||
"text": "This is a word document and this is an inline equation: $A= \\pi r^{2} $. If instead, I want an equation by line, I can do this:"
|
"text": ""
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/25",
|
"self_ref": "#/texts/25",
|
||||||
@ -393,10 +481,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text.",
|
||||||
"text": ""
|
"text": "This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text. This is text."
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/26",
|
"self_ref": "#/texts/26",
|
||||||
@ -404,10 +493,11 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
"label": "formula",
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty ",
|
"orig": "",
|
||||||
"text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty "
|
"text": ""
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/27",
|
"self_ref": "#/texts/27",
|
||||||
@ -415,6 +505,7 @@
|
|||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -422,21 +513,95 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/28",
|
"self_ref": "#/texts/28",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/groups/2"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
|
"prov": [],
|
||||||
|
"orig": "This is a word document and this is an inline equation: ",
|
||||||
|
"text": "This is a word document and this is an inline equation: "
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/29",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/groups/2"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
|
"prov": [],
|
||||||
|
"orig": "A= \\pi r^{2} ",
|
||||||
|
"text": "A= \\pi r^{2} "
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/30",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/groups/2"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
|
"prov": [],
|
||||||
|
"orig": ". If instead, I want an equation by line, I can do this:",
|
||||||
|
"text": ". If instead, I want an equation by line, I can do this:"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/31",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
|
"prov": [],
|
||||||
|
"orig": "",
|
||||||
|
"text": ""
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/32",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "formula",
|
||||||
|
"prov": [],
|
||||||
|
"orig": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty",
|
||||||
|
"text": "e^{x}=1+\\frac{x}{1!}+\\frac{x^{2}}{2!}+\\frac{x^{3}}{3!}+ \\text{ \\textellipsis } , - \\infty < x < \\infty"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/33",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
|
"label": "paragraph",
|
||||||
|
"prov": [],
|
||||||
|
"orig": "",
|
||||||
|
"text": ""
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"self_ref": "#/texts/34",
|
||||||
|
"parent": {
|
||||||
|
"$ref": "#/body"
|
||||||
|
},
|
||||||
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "And that is an equation by itself. Cheers!",
|
"orig": "And that is an equation by itself. Cheers!",
|
||||||
"text": "And that is an equation by itself. Cheers!"
|
"text": "And that is an equation by itself. Cheers!"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"self_ref": "#/texts/29",
|
"self_ref": "#/texts/35",
|
||||||
"parent": {
|
"parent": {
|
||||||
"$ref": "#/body"
|
"$ref": "#/body"
|
||||||
},
|
},
|
||||||
"children": [],
|
"children": [],
|
||||||
|
"content_layer": "body",
|
||||||
"label": "paragraph",
|
"label": "paragraph",
|
||||||
"prov": [],
|
"prov": [],
|
||||||
"orig": "",
|
"orig": "",
|
||||||
@ -446,5 +611,6 @@
|
|||||||
"pictures": [],
|
"pictures": [],
|
||||||
"tables": [],
|
"tables": [],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "lorem_ipsum",
|
"name": "lorem_ipsum",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -163,5 +163,6 @@
|
|||||||
"pictures": [],
|
"pictures": [],
|
||||||
"tables": [],
|
"tables": [],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "tablecell",
|
"name": "tablecell",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -399,5 +399,6 @@
|
|||||||
}
|
}
|
||||||
],
|
],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
File diff suppressed because one or more lines are too long
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "unit_test_headers",
|
"name": "unit_test_headers",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -748,5 +748,6 @@
|
|||||||
"pictures": [],
|
"pictures": [],
|
||||||
"tables": [],
|
"tables": [],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "unit_test_headers_numbered",
|
"name": "unit_test_headers_numbered",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -802,5 +802,6 @@
|
|||||||
"pictures": [],
|
"pictures": [],
|
||||||
"tables": [],
|
"tables": [],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "unit_test_lists",
|
"name": "unit_test_lists",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -979,5 +979,6 @@
|
|||||||
"pictures": [],
|
"pictures": [],
|
||||||
"tables": [],
|
"tables": [],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
@ -3,7 +3,7 @@ item-0 at level 0: unspecified: group _root_
|
|||||||
item-2 at level 1: title: Swimming in the lake
|
item-2 at level 1: title: Swimming in the lake
|
||||||
item-3 at level 2: paragraph: Duck
|
item-3 at level 2: paragraph: Duck
|
||||||
item-4 at level 2: picture
|
item-4 at level 2: picture
|
||||||
item-5 at level 2: text: Figure 1: This is a cute duckling
|
item-5 at level 2: paragraph: Figure 1: This is a cute duckling
|
||||||
item-6 at level 2: section_header: Let’s swim!
|
item-6 at level 2: section_header: Let’s swim!
|
||||||
item-7 at level 3: paragraph: To get started with swimming, fi ... down in a water and try not to drown:
|
item-7 at level 3: paragraph: To get started with swimming, fi ... down in a water and try not to drown:
|
||||||
item-8 at level 3: list: group list
|
item-8 at level 3: list: group list
|
||||||
|
|||||||
File diff suppressed because one or more lines are too long
@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"schema_name": "DoclingDocument",
|
"schema_name": "DoclingDocument",
|
||||||
"version": "1.1.0",
|
"version": "1.2.0",
|
||||||
"name": "word_tables",
|
"name": "word_tables",
|
||||||
"origin": {
|
"origin": {
|
||||||
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
||||||
@ -2372,5 +2372,6 @@
|
|||||||
}
|
}
|
||||||
],
|
],
|
||||||
"key_value_items": [],
|
"key_value_items": [],
|
||||||
|
"form_items": [],
|
||||||
"pages": {}
|
"pages": {}
|
||||||
}
|
}
|
||||||
Loading…
Reference in New Issue
Block a user