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

fix: Test cases for RTL programmatic PDFs and fixes for the formula model (#903)

Browse Source 
fix: Support for RTL programmatic documents
fix(parser): detect and handle rotated pages
fix(parser): fix bug causing duplicated text
fix(formula): improve stopping criteria
chore: update lock file
fix: temporary constrain beautifulsoup


* switch to code formula model v1.0.1 and new test pdf

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* switch to code formula model v1.0.1 and new test pdf

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* cleaned up the data folder in the tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* switch to code formula model v1.0.1 and new test pdf

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* added three test-files for right-to-left

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fix black

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* added new gt for test_e2e_conversion

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* added new gt for test_e2e_conversion

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* Add code to expose text direction of cell

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

* new test file

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>

* update lock

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* fix mypy reports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* fix example filepaths

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add test data results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* pin wheel of latest docling-parse release

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* use latest docling-core

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* remove debugging code

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* fix path to files in example

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Revert unwanted RTL additions

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

* Fix test data paths in examples

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

---------

Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com>
Co-authored-by: Peter Staar <taa@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2025-02-07 08:43:31 +01:00 committed by GitHub
parent ed74fe2ec0
commit 9114ada7bc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
91 changed files with 620 additions and 313 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docling/models/code_formula_model.py
View File

@ -2,6 +2,7 @@ import re
from pathlib import Path from pathlib import Path
from typing import Iterable, List, Literal, Optional, Tuple, Union from typing import Iterable, List, Literal, Optional, Tuple, Union
import numpy as np
from docling_core.types.doc import ( from docling_core.types.doc import (
CodeItem, CodeItem,
DocItemLabel, DocItemLabel,
@ -103,7 +104,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
artifacts_path = artifacts_path / self._model_repo_folder artifacts_path = artifacts_path / self._model_repo_folder
self.code_formula_model = CodeFormulaPredictor( self.code_formula_model = CodeFormulaPredictor(
artifacts_path=artifacts_path, artifacts_path=str(artifacts_path),
device=device, device=device,
num_threads=accelerator_options.num_threads, num_threads=accelerator_options.num_threads,
) )
@ -123,7 +124,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
repo_id="ds4sd/CodeFormula", repo_id="ds4sd/CodeFormula",
force_download=force, force_download=force,
local_dir=local_dir, local_dir=local_dir,
revision="v1.0.0", revision="v1.0.1",
) )
return Path(download_path) return Path(download_path)
@ -231,7 +232,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
return return
labels: List[str] = [] labels: List[str] = []
images: List[Image.Image] = [] images: List[Union[Image.Image, np.ndarray]] = []
elements: List[TextItem] = [] elements: List[TextItem] = []
for el in element_batch: for el in element_batch:
assert isinstance(el.item, TextItem) assert isinstance(el.item, TextItem)

5
docling/models/document_picture_classifier.py
View File

@ -1,6 +1,7 @@
from pathlib import Path from pathlib import Path
from typing import Iterable, List, Literal, Optional, Tuple, Union from typing import Iterable, List, Literal, Optional, Tuple, Union
import numpy as np
from docling_core.types.doc import ( from docling_core.types.doc import (
DoclingDocument, DoclingDocument,
NodeItem, NodeItem,
@ -94,7 +95,7 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
artifacts_path = artifacts_path / self._model_repo_folder artifacts_path = artifacts_path / self._model_repo_folder
self.document_picture_classifier = DocumentFigureClassifierPredictor( self.document_picture_classifier = DocumentFigureClassifierPredictor(
artifacts_path=artifacts_path, artifacts_path=str(artifacts_path),
device=device, device=device,
num_threads=accelerator_options.num_threads, num_threads=accelerator_options.num_threads,
) )
@ -161,7 +162,7 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
yield element yield element
return return
images: List[Image.Image] = [] images: List[Union[Image.Image, np.ndarray]] = []
elements: List[PictureItem] = [] elements: List[PictureItem] = []
for el in element_batch: for el in element_batch:
assert isinstance(el, PictureItem) assert isinstance(el, PictureItem)

4
docling/models/layout_model.py
View File

@ -150,10 +150,12 @@ class LayoutModel(BasePageModel):
else: else:
with TimeRecorder(conv_res, "layout"): with TimeRecorder(conv_res, "layout"):
assert page.size is not None assert page.size is not None
page_image = page.get_image(scale=1.0)
assert page_image is not None
clusters = [] clusters = []
for ix, pred_item in enumerate( for ix, pred_item in enumerate(
self.layout_predictor.predict(page.get_image(scale=1.0)) self.layout_predictor.predict(page_image)
): ):
label = DocItemLabel( label = DocItemLabel(
pred_item["label"] pred_item["label"]

8
docs/examples/batch_convert.py
View File

@ -103,10 +103,10 @@ def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_paths = [ input_doc_paths = [
Path("./tests/data/2206.01062.pdf"), Path("./tests/data/pdf/2206.01062.pdf"),
Path("./tests/data/2203.01017v2.pdf"), Path("./tests/data/pdf/2203.01017v2.pdf"),
Path("./tests/data/2305.03393v1.pdf"), Path("./tests/data/pdf/2305.03393v1.pdf"),
Path("./tests/data/redp5110_sampled.pdf"), Path("./tests/data/pdf/redp5110_sampled.pdf"),
] ]
# buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read()) # buf = BytesIO(Path("./test/data/2206.01062.pdf").open("rb").read())

2
docs/examples/custom_convert.py
View File

@ -21,7 +21,7 @@ _log = logging.getLogger(__name__)
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
########################################################################### ###########################################################################

2
docs/examples/develop_formula_understanding.py
View File

@ -68,7 +68,7 @@ class ExampleFormulaUnderstandingPipeline(StandardPdfPipeline):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2203.01017v2.pdf") input_doc_path = Path("./tests/data/pdf/2203.01017v2.pdf")
pipeline_options = ExampleFormulaUnderstandingPipelineOptions() pipeline_options = ExampleFormulaUnderstandingPipelineOptions()
pipeline_options.do_formula_understanding = True pipeline_options.do_formula_understanding = True

2
docs/examples/develop_picture_enrichment.py
View File

@ -71,7 +71,7 @@ class ExamplePictureClassifierPipeline(StandardPdfPipeline):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
pipeline_options = ExamplePictureClassifierPipelineOptions() pipeline_options = ExamplePictureClassifierPipelineOptions()
pipeline_options.images_scale = 2.0 pipeline_options.images_scale = 2.0

2
docs/examples/export_figures.py
View File

@ -16,7 +16,7 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

2
docs/examples/export_multimodal.py
View File

@ -19,7 +19,7 @@ IMAGE_RESOLUTION_SCALE = 2.0
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

2
docs/examples/export_tables.py
View File

@ -12,7 +12,7 @@ _log = logging.getLogger(__name__)
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch") output_dir = Path("scratch")
doc_converter = DocumentConverter() doc_converter = DocumentConverter()

2
docs/examples/full_page_ocr.py
View File

@ -14,7 +14,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): def main():
input_doc = Path("./tests/data/2206.01062.pdf") input_doc = Path("./tests/data/pdf/2206.01062.pdf")
pipeline_options = PdfPipelineOptions() pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True pipeline_options.do_ocr = True

2
docs/examples/inspect_picture_content.py
View File

@ -4,7 +4,7 @@ from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption from docling.document_converter import DocumentConverter, PdfFormatOption
source = "tests/data/amt_handbook_sample.pdf" source = "tests/data/pdf/amt_handbook_sample.pdf"
pipeline_options = PdfPipelineOptions() pipeline_options = PdfPipelineOptions()
pipeline_options.images_scale = 2 pipeline_options.images_scale = 2

2
docs/examples/run_with_accelerator.py
View File

@ -14,7 +14,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): def main():
input_doc = Path("./tests/data/2206.01062.pdf") input_doc = Path("./tests/data/pdf/2206.01062.pdf")
# Explicitly set the accelerator # Explicitly set the accelerator
# accelerator_options = AcceleratorOptions( # accelerator_options = AcceleratorOptions(

5
docs/examples/run_with_formats.py
View File

@ -25,9 +25,8 @@ def main():
Path("tests/data/docx/lorem_ipsum.docx"), Path("tests/data/docx/lorem_ipsum.docx"),
Path("tests/data/pptx/powerpoint_sample.pptx"), Path("tests/data/pptx/powerpoint_sample.pptx"),
Path("tests/data/2305.03393v1-pg9-img.png"), Path("tests/data/2305.03393v1-pg9-img.png"),
Path("tests/data/2206.01062.pdf"), Path("tests/data/pdf/2206.01062.pdf"),
Path("tests/data/test_01.asciidoc"), Path("tests/data/asciidoc/test_01.asciidoc"),
Path("tests/data/test_01.asciidoc"),
] ]
## for defaults use: ## for defaults use:

2
docs/examples/tesseract_lang_detection.py
View File

@ -10,7 +10,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
def main(): def main():
input_doc = Path("./tests/data/2206.01062.pdf") input_doc = Path("./tests/data/pdf/2206.01062.pdf")
# Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions # Set lang=["auto"] with a tesseract OCR engine: TesseractOcrOptions, TesseractCliOcrOptions
# ocr_options = TesseractOcrOptions(lang=["auto"]) # ocr_options = TesseractOcrOptions(lang=["auto"])

2
docs/examples/translate.py
View File

@ -32,7 +32,7 @@ def translate(text: str, src: str = "en", dest: str = "de"):
def main(): def main():
logging.basicConfig(level=logging.INFO) logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/2206.01062.pdf") input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch") output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter # Important: For operating with page images, we must keep them, otherwise the DocumentConverter

10
docs/v2.md
View File

@ -117,12 +117,12 @@ conv_result: ConversionResult = doc_converter.convert("https://arxiv.org/pdf/240
## Convert several files at once: ## Convert several files at once:
input_files = [ input_files = [
"tests/data/wiki_duck.html", "tests/data/html/wiki_duck.html",
"tests/data/word_sample.docx", "tests/data/docx/word_sample.docx",
"tests/data/lorem_ipsum.docx", "tests/data/docx/lorem_ipsum.docx",
"tests/data/powerpoint_sample.pptx", "tests/data/pptx/powerpoint_sample.pptx",
"tests/data/2305.03393v1-pg9-img.png", "tests/data/2305.03393v1-pg9-img.png",
"tests/data/2206.01062.pdf", "tests/data/pdf/2206.01062.pdf",
] ]
# Directly pass list of files or streams to `convert_all` # Directly pass list of files or streams to `convert_all`

449
poetry.lock generated
View File

@ -13,87 +13,92 @@ files = [
[[package]] [[package]]
name = "aiohttp" name = "aiohttp"
version = "3.11.11" version = "3.11.12"
description = "Async http client/server framework (asyncio)" description = "Async http client/server framework (asyncio)"
optional = false optional = false
python-versions = ">=3.9" python-versions = ">=3.9"
files = [ files = [
{file = "aiohttp-3.11.11-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a60804bff28662cbcf340a4d61598891f12eea3a66af48ecfdc975ceec21e3c8"}, {file = "aiohttp-3.11.12-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:aa8a8caca81c0a3e765f19c6953416c58e2f4cc1b84829af01dd1c771bb2f91f"},
{file = "aiohttp-3.11.11-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4b4fa1cb5f270fb3eab079536b764ad740bb749ce69a94d4ec30ceee1b5940d5"}, {file = "aiohttp-3.11.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:84ede78acde96ca57f6cf8ccb8a13fbaf569f6011b9a52f870c662d4dc8cd854"},
{file = "aiohttp-3.11.11-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:731468f555656767cda219ab42e033355fe48c85fbe3ba83a349631541715ba2"}, {file = "aiohttp-3.11.12-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:584096938a001378484aa4ee54e05dc79c7b9dd933e271c744a97b3b6f644957"},
{file = "aiohttp-3.11.11-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cb23d8bb86282b342481cad4370ea0853a39e4a32a0042bb52ca6bdde132df43"}, {file = "aiohttp-3.11.12-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:392432a2dde22b86f70dd4a0e9671a349446c93965f261dbaecfaf28813e5c42"},
{file = "aiohttp-3.11.11-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f047569d655f81cb70ea5be942ee5d4421b6219c3f05d131f64088c73bb0917f"}, {file = "aiohttp-3.11.12-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:88d385b8e7f3a870146bf5ea31786ef7463e99eb59e31db56e2315535d811f55"},
{file = "aiohttp-3.11.11-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dd7659baae9ccf94ae5fe8bfaa2c7bc2e94d24611528395ce88d009107e00c6d"}, {file = "aiohttp-3.11.12-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b10a47e5390c4b30a0d58ee12581003be52eedd506862ab7f97da7a66805befb"},
{file = "aiohttp-3.11.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af01e42ad87ae24932138f154105e88da13ce7d202a6de93fafdafb2883a00ef"}, {file = "aiohttp-3.11.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b5263dcede17b6b0c41ef0c3ccce847d82a7da98709e75cf7efde3e9e3b5cae"},
{file = "aiohttp-3.11.11-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5854be2f3e5a729800bac57a8d76af464e160f19676ab6aea74bde18ad19d438"}, {file = "aiohttp-3.11.12-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:50c5c7b8aa5443304c55c262c5693b108c35a3b61ef961f1e782dd52a2f559c7"},
{file = "aiohttp-3.11.11-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:6526e5fb4e14f4bbf30411216780c9967c20c5a55f2f51d3abd6de68320cc2f3"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:d1c031a7572f62f66f1257db37ddab4cb98bfaf9b9434a3b4840bf3560f5e788"},
{file = "aiohttp-3.11.11-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:85992ee30a31835fc482468637b3e5bd085fa8fe9392ba0bdcbdc1ef5e9e3c55"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_armv7l.whl", hash = "sha256:7e44eba534381dd2687be50cbd5f2daded21575242ecfdaf86bbeecbc38dae8e"},
{file = "aiohttp-3.11.11-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:88a12ad8ccf325a8a5ed80e6d7c3bdc247d66175afedbe104ee2aaca72960d8e"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:145a73850926018ec1681e734cedcf2716d6a8697d90da11284043b745c286d5"},
{file = "aiohttp-3.11.11-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:0a6d3fbf2232e3a08c41eca81ae4f1dff3d8f1a30bae415ebe0af2d2458b8a33"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:2c311e2f63e42c1bf86361d11e2c4a59f25d9e7aabdbdf53dc38b885c5435cdb"},
{file = "aiohttp-3.11.11-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:84a585799c58b795573c7fa9b84c455adf3e1d72f19a2bf498b54a95ae0d194c"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:ea756b5a7bac046d202a9a3889b9a92219f885481d78cd318db85b15cc0b7bcf"},
{file = "aiohttp-3.11.11-cp310-cp310-win32.whl", hash = "sha256:bfde76a8f430cf5c5584553adf9926534352251d379dcb266ad2b93c54a29745"}, {file = "aiohttp-3.11.12-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:526c900397f3bbc2db9cb360ce9c35134c908961cdd0ac25b1ae6ffcaa2507ff"},
{file = "aiohttp-3.11.11-cp310-cp310-win_amd64.whl", hash = "sha256:0fd82b8e9c383af11d2b26f27a478640b6b83d669440c0a71481f7c865a51da9"}, {file = "aiohttp-3.11.12-cp310-cp310-win32.whl", hash = "sha256:b8d3bb96c147b39c02d3db086899679f31958c5d81c494ef0fc9ef5bb1359b3d"},
{file = "aiohttp-3.11.11-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ba74ec819177af1ef7f59063c6d35a214a8fde6f987f7661f4f0eecc468a8f76"}, {file = "aiohttp-3.11.12-cp310-cp310-win_amd64.whl", hash = "sha256:7fe3d65279bfbee8de0fb4f8c17fc4e893eed2dba21b2f680e930cc2b09075c5"},
{file = "aiohttp-3.11.11-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4af57160800b7a815f3fe0eba9b46bf28aafc195555f1824555fa2cfab6c1538"}, {file = "aiohttp-3.11.12-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:87a2e00bf17da098d90d4145375f1d985a81605267e7f9377ff94e55c5d769eb"},
{file = "aiohttp-3.11.11-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ffa336210cf9cd8ed117011085817d00abe4c08f99968deef0013ea283547204"}, {file = "aiohttp-3.11.12-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b34508f1cd928ce915ed09682d11307ba4b37d0708d1f28e5774c07a7674cac9"},
{file = "aiohttp-3.11.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:81b8fe282183e4a3c7a1b72f5ade1094ed1c6345a8f153506d114af5bf8accd9"}, {file = "aiohttp-3.11.12-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:936d8a4f0f7081327014742cd51d320296b56aa6d324461a13724ab05f4b2933"},
{file = "aiohttp-3.11.11-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3af41686ccec6a0f2bdc66686dc0f403c41ac2089f80e2214a0f82d001052c03"}, {file = "aiohttp-3.11.12-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2de1378f72def7dfb5dbd73d86c19eda0ea7b0a6873910cc37d57e80f10d64e1"},
{file = "aiohttp-3.11.11-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:70d1f9dde0e5dd9e292a6d4d00058737052b01f3532f69c0c65818dac26dc287"}, {file = "aiohttp-3.11.12-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b9d45dbb3aaec05cf01525ee1a7ac72de46a8c425cb75c003acd29f76b1ffe94"},
{file = "aiohttp-3.11.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:249cc6912405917344192b9f9ea5cd5b139d49e0d2f5c7f70bdfaf6b4dbf3a2e"}, {file = "aiohttp-3.11.12-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:930ffa1925393381e1e0a9b82137fa7b34c92a019b521cf9f41263976666a0d6"},
{file = "aiohttp-3.11.11-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0eb98d90b6690827dcc84c246811feeb4e1eea683c0eac6caed7549be9c84665"}, {file = "aiohttp-3.11.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8340def6737118f5429a5df4e88f440746b791f8f1c4ce4ad8a595f42c980bd5"},
{file = "aiohttp-3.11.11-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:ec82bf1fda6cecce7f7b915f9196601a1bd1a3079796b76d16ae4cce6d0ef89b"}, {file = "aiohttp-3.11.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4016e383f91f2814e48ed61e6bda7d24c4d7f2402c75dd28f7e1027ae44ea204"},
{file = "aiohttp-3.11.11-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:9fd46ce0845cfe28f108888b3ab17abff84ff695e01e73657eec3f96d72eef34"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:3c0600bcc1adfaaac321422d615939ef300df81e165f6522ad096b73439c0f58"},
{file = "aiohttp-3.11.11-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:bd176afcf8f5d2aed50c3647d4925d0db0579d96f75a31e77cbaf67d8a87742d"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:0450ada317a65383b7cce9576096150fdb97396dcfe559109b403c7242faffef"},
{file = "aiohttp-3.11.11-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:ec2aa89305006fba9ffb98970db6c8221541be7bee4c1d027421d6f6df7d1ce2"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:850ff6155371fd802a280f8d369d4e15d69434651b844bde566ce97ee2277420"},
{file = "aiohttp-3.11.11-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:92cde43018a2e17d48bb09c79e4d4cb0e236de5063ce897a5e40ac7cb4878773"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:8fd12d0f989c6099e7b0f30dc6e0d1e05499f3337461f0b2b0dadea6c64b89df"},
{file = "aiohttp-3.11.11-cp311-cp311-win32.whl", hash = "sha256:aba807f9569455cba566882c8938f1a549f205ee43c27b126e5450dc9f83cc62"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:76719dd521c20a58a6c256d058547b3a9595d1d885b830013366e27011ffe804"},
{file = "aiohttp-3.11.11-cp311-cp311-win_amd64.whl", hash = "sha256:ae545f31489548c87b0cced5755cfe5a5308d00407000e72c4fa30b19c3220ac"}, {file = "aiohttp-3.11.12-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:97fe431f2ed646a3b56142fc81d238abcbaff08548d6912acb0b19a0cadc146b"},
{file = "aiohttp-3.11.11-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:e595c591a48bbc295ebf47cb91aebf9bd32f3ff76749ecf282ea7f9f6bb73886"}, {file = "aiohttp-3.11.12-cp311-cp311-win32.whl", hash = "sha256:e10c440d142fa8b32cfdb194caf60ceeceb3e49807072e0dc3a8887ea80e8c16"},
{file = "aiohttp-3.11.11-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:3ea1b59dc06396b0b424740a10a0a63974c725b1c64736ff788a3689d36c02d2"}, {file = "aiohttp-3.11.12-cp311-cp311-win_amd64.whl", hash = "sha256:246067ba0cf5560cf42e775069c5d80a8989d14a7ded21af529a4e10e3e0f0e6"},
{file = "aiohttp-3.11.11-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8811f3f098a78ffa16e0ea36dffd577eb031aea797cbdba81be039a4169e242c"}, {file = "aiohttp-3.11.12-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:e392804a38353900c3fd8b7cacbea5132888f7129f8e241915e90b85f00e3250"},
{file = "aiohttp-3.11.11-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bd7227b87a355ce1f4bf83bfae4399b1f5bb42e0259cb9405824bd03d2f4336a"}, {file = "aiohttp-3.11.12-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8fa1510b96c08aaad49303ab11f8803787c99222288f310a62f493faf883ede1"},
{file = "aiohttp-3.11.11-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d40f9da8cabbf295d3a9dae1295c69975b86d941bc20f0a087f0477fa0a66231"}, {file = "aiohttp-3.11.12-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:dc065a4285307607df3f3686363e7f8bdd0d8ab35f12226362a847731516e42c"},
{file = "aiohttp-3.11.11-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ffb3dc385f6bb1568aa974fe65da84723210e5d9707e360e9ecb51f59406cd2e"}, {file = "aiohttp-3.11.12-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cddb31f8474695cd61fc9455c644fc1606c164b93bff2490390d90464b4655df"},
{file = "aiohttp-3.11.11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a8f5f7515f3552d899c61202d99dcb17d6e3b0de777900405611cd747cecd1b8"}, {file = "aiohttp-3.11.12-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9dec0000d2d8621d8015c293e24589d46fa218637d820894cb7356c77eca3259"},
{file = "aiohttp-3.11.11-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3499c7ffbfd9c6a3d8d6a2b01c26639da7e43d47c7b4f788016226b1e711caa8"}, {file = "aiohttp-3.11.12-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e3552fe98e90fdf5918c04769f338a87fa4f00f3b28830ea9b78b1bdc6140e0d"},
{file = "aiohttp-3.11.11-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:8e2bf8029dbf0810c7bfbc3e594b51c4cc9101fbffb583a3923aea184724203c"}, {file = "aiohttp-3.11.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6dfe7f984f28a8ae94ff3a7953cd9678550dbd2a1f9bda5dd9c5ae627744c78e"},
{file = "aiohttp-3.11.11-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:b6212a60e5c482ef90f2d788835387070a88d52cf6241d3916733c9176d39eab"}, {file = "aiohttp-3.11.12-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a481a574af914b6e84624412666cbfbe531a05667ca197804ecc19c97b8ab1b0"},
{file = "aiohttp-3.11.11-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:d119fafe7b634dbfa25a8c597718e69a930e4847f0b88e172744be24515140da"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1987770fb4887560363b0e1a9b75aa303e447433c41284d3af2840a2f226d6e0"},
{file = "aiohttp-3.11.11-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:6fba278063559acc730abf49845d0e9a9e1ba74f85f0ee6efd5803f08b285853"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:a4ac6a0f0f6402854adca4e3259a623f5c82ec3f0c049374133bcb243132baf9"},
{file = "aiohttp-3.11.11-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:92fc484e34b733704ad77210c7957679c5c3877bd1e6b6d74b185e9320cc716e"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c96a43822f1f9f69cc5c3706af33239489a6294be486a0447fb71380070d4d5f"},
{file = "aiohttp-3.11.11-cp312-cp312-win32.whl", hash = "sha256:9f5b3c1ed63c8fa937a920b6c1bec78b74ee09593b3f5b979ab2ae5ef60d7600"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:a5e69046f83c0d3cb8f0d5bd9b8838271b1bc898e01562a04398e160953e8eb9"},
{file = "aiohttp-3.11.11-cp312-cp312-win_amd64.whl", hash = "sha256:1e69966ea6ef0c14ee53ef7a3d68b564cc408121ea56c0caa2dc918c1b2f553d"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:68d54234c8d76d8ef74744f9f9fc6324f1508129e23da8883771cdbb5818cbef"},
{file = "aiohttp-3.11.11-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:541d823548ab69d13d23730a06f97460f4238ad2e5ed966aaf850d7c369782d9"}, {file = "aiohttp-3.11.12-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:c9fd9dcf9c91affe71654ef77426f5cf8489305e1c66ed4816f5a21874b094b9"},
{file = "aiohttp-3.11.11-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:929f3ed33743a49ab127c58c3e0a827de0664bfcda566108989a14068f820194"}, {file = "aiohttp-3.11.12-cp312-cp312-win32.whl", hash = "sha256:0ed49efcd0dc1611378beadbd97beb5d9ca8fe48579fc04a6ed0844072261b6a"},
{file = "aiohttp-3.11.11-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0882c2820fd0132240edbb4a51eb8ceb6eef8181db9ad5291ab3332e0d71df5f"}, {file = "aiohttp-3.11.12-cp312-cp312-win_amd64.whl", hash = "sha256:54775858c7f2f214476773ce785a19ee81d1294a6bedc5cc17225355aab74802"},
{file = "aiohttp-3.11.11-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b63de12e44935d5aca7ed7ed98a255a11e5cb47f83a9fded7a5e41c40277d104"}, {file = "aiohttp-3.11.12-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:413ad794dccb19453e2b97c2375f2ca3cdf34dc50d18cc2693bd5aed7d16f4b9"},
{file = "aiohttp-3.11.11-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aa54f8ef31d23c506910c21163f22b124facb573bff73930735cf9fe38bf7dff"}, {file = "aiohttp-3.11.12-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:4a93d28ed4b4b39e6f46fd240896c29b686b75e39cc6992692e3922ff6982b4c"},
{file = "aiohttp-3.11.11-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a344d5dc18074e3872777b62f5f7d584ae4344cd6006c17ba12103759d407af3"}, {file = "aiohttp-3.11.12-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:d589264dbba3b16e8951b6f145d1e6b883094075283dafcab4cdd564a9e353a0"},
{file = "aiohttp-3.11.11-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b7fb429ab1aafa1f48578eb315ca45bd46e9c37de11fe45c7f5f4138091e2f1"}, {file = "aiohttp-3.11.12-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5148ca8955affdfeb864aca158ecae11030e952b25b3ae15d4e2b5ba299bad2"},
{file = "aiohttp-3.11.11-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c341c7d868750e31961d6d8e60ff040fb9d3d3a46d77fd85e1ab8e76c3e9a5c4"}, {file = "aiohttp-3.11.12-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:525410e0790aab036492eeea913858989c4cb070ff373ec3bc322d700bdf47c1"},
{file = "aiohttp-3.11.11-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ed9ee95614a71e87f1a70bc81603f6c6760128b140bc4030abe6abaa988f1c3d"}, {file = "aiohttp-3.11.12-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9bd8695be2c80b665ae3f05cb584093a1e59c35ecb7d794d1edd96e8cc9201d7"},
{file = "aiohttp-3.11.11-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:de8d38f1c2810fa2a4f1d995a2e9c70bb8737b18da04ac2afbf3971f65781d87"}, {file = "aiohttp-3.11.12-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0203433121484b32646a5f5ea93ae86f3d9559d7243f07e8c0eab5ff8e3f70e"},
{file = "aiohttp-3.11.11-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:a9b7371665d4f00deb8f32208c7c5e652059b0fda41cf6dbcac6114a041f1cc2"}, {file = "aiohttp-3.11.12-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:40cd36749a1035c34ba8d8aaf221b91ca3d111532e5ccb5fa8c3703ab1b967ed"},
{file = "aiohttp-3.11.11-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:620598717fce1b3bd14dd09947ea53e1ad510317c85dda2c9c65b622edc96b12"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:a7442662afebbf7b4c6d28cb7aab9e9ce3a5df055fc4116cc7228192ad6cb484"},
{file = "aiohttp-3.11.11-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:bf8d9bfee991d8acc72d060d53860f356e07a50f0e0d09a8dfedea1c554dd0d5"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:8a2fb742ef378284a50766e985804bd6adb5adb5aa781100b09befdbfa757b65"},
{file = "aiohttp-3.11.11-cp313-cp313-win32.whl", hash = "sha256:9d73ee3725b7a737ad86c2eac5c57a4a97793d9f442599bea5ec67ac9f4bdc3d"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2cee3b117a8d13ab98b38d5b6bdcd040cfb4181068d05ce0c474ec9db5f3c5bb"},
{file = "aiohttp-3.11.11-cp313-cp313-win_amd64.whl", hash = "sha256:c7a06301c2fb096bdb0bd25fe2011531c1453b9f2c163c8031600ec73af1cc99"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f6a19bcab7fbd8f8649d6595624856635159a6527861b9cdc3447af288a00c00"},
{file = "aiohttp-3.11.11-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:3e23419d832d969f659c208557de4a123e30a10d26e1e14b73431d3c13444c2e"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:e4cecdb52aaa9994fbed6b81d4568427b6002f0a91c322697a4bfcc2b2363f5a"},
{file = "aiohttp-3.11.11-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:21fef42317cf02e05d3b09c028712e1d73a9606f02467fd803f7c1f39cc59add"}, {file = "aiohttp-3.11.12-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:30f546358dfa0953db92ba620101fefc81574f87b2346556b90b5f3ef16e55ce"},
{file = "aiohttp-3.11.11-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1f21bb8d0235fc10c09ce1d11ffbd40fc50d3f08a89e4cf3a0c503dc2562247a"}, {file = "aiohttp-3.11.12-cp313-cp313-win32.whl", hash = "sha256:ce1bb21fc7d753b5f8a5d5a4bae99566386b15e716ebdb410154c16c91494d7f"},
{file = "aiohttp-3.11.11-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1642eceeaa5ab6c9b6dfeaaa626ae314d808188ab23ae196a34c9d97efb68350"}, {file = "aiohttp-3.11.12-cp313-cp313-win_amd64.whl", hash = "sha256:f7914ab70d2ee8ab91c13e5402122edbc77821c66d2758abb53aabe87f013287"},
{file = "aiohttp-3.11.11-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2170816e34e10f2fd120f603e951630f8a112e1be3b60963a1f159f5699059a6"}, {file = "aiohttp-3.11.12-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7c3623053b85b4296cd3925eeb725e386644fd5bc67250b3bb08b0f144803e7b"},
{file = "aiohttp-3.11.11-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8be8508d110d93061197fd2d6a74f7401f73b6d12f8822bbcd6d74f2b55d71b1"}, {file = "aiohttp-3.11.12-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:67453e603cea8e85ed566b2700efa1f6916aefbc0c9fcb2e86aaffc08ec38e78"},
{file = "aiohttp-3.11.11-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4eed954b161e6b9b65f6be446ed448ed3921763cc432053ceb606f89d793927e"}, {file = "aiohttp-3.11.12-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6130459189e61baac5a88c10019b21e1f0c6d00ebc770e9ce269475650ff7f73"},
{file = "aiohttp-3.11.11-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d6c9af134da4bc9b3bd3e6a70072509f295d10ee60c697826225b60b9959acdd"}, {file = "aiohttp-3.11.12-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9060addfa4ff753b09392efe41e6af06ea5dd257829199747b9f15bfad819460"},
{file = "aiohttp-3.11.11-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:44167fc6a763d534a6908bdb2592269b4bf30a03239bcb1654781adf5e49caf1"}, {file = "aiohttp-3.11.12-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:34245498eeb9ae54c687a07ad7f160053911b5745e186afe2d0c0f2898a1ab8a"},
{file = "aiohttp-3.11.11-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:479b8c6ebd12aedfe64563b85920525d05d394b85f166b7873c8bde6da612f9c"}, {file = "aiohttp-3.11.12-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8dc0fba9a74b471c45ca1a3cb6e6913ebfae416678d90529d188886278e7f3f6"},
{file = "aiohttp-3.11.11-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:10b4ff0ad793d98605958089fabfa350e8e62bd5d40aa65cdc69d6785859f94e"}, {file = "aiohttp-3.11.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a478aa11b328983c4444dacb947d4513cb371cd323f3845e53caeda6be5589d5"},
{file = "aiohttp-3.11.11-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:b540bd67cfb54e6f0865ceccd9979687210d7ed1a1cc8c01f8e67e2f1e883d28"}, {file = "aiohttp-3.11.12-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c160a04283c8c6f55b5bf6d4cad59bb9c5b9c9cd08903841b25f1f7109ef1259"},
{file = "aiohttp-3.11.11-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:1dac54e8ce2ed83b1f6b1a54005c87dfed139cf3f777fdc8afc76e7841101226"}, {file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:edb69b9589324bdc40961cdf0657815df674f1743a8d5ad9ab56a99e4833cfdd"},
{file = "aiohttp-3.11.11-cp39-cp39-win32.whl", hash = "sha256:568c1236b2fde93b7720f95a890741854c1200fba4a3471ff48b2934d2d93fd3"}, {file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_armv7l.whl", hash = "sha256:4ee84c2a22a809c4f868153b178fe59e71423e1f3d6a8cd416134bb231fbf6d3"},
{file = "aiohttp-3.11.11-cp39-cp39-win_amd64.whl", hash = "sha256:943a8b052e54dfd6439fd7989f67fc6a7f2138d0a2cf0a7de5f18aa4fe7eb3b1"}, {file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:bf4480a5438f80e0f1539e15a7eb8b5f97a26fe087e9828e2c0ec2be119a9f72"},
{file = "aiohttp-3.11.11.tar.gz", hash = "sha256:bb49c7f1e6ebf3821a42d81d494f538107610c3a705987f53068546b0e90303e"}, {file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:e6b2732ef3bafc759f653a98881b5b9cdef0716d98f013d376ee8dfd7285abf1"},
{file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:f752e80606b132140883bb262a457c475d219d7163d996dc9072434ffb0784c4"},
{file = "aiohttp-3.11.12-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:ab3247d58b393bda5b1c8f31c9edece7162fc13265334217785518dd770792b8"},
{file = "aiohttp-3.11.12-cp39-cp39-win32.whl", hash = "sha256:0d5176f310a7fe6f65608213cc74f4228e4f4ce9fd10bcb2bb6da8fc66991462"},
{file = "aiohttp-3.11.12-cp39-cp39-win_amd64.whl", hash = "sha256:74bd573dde27e58c760d9ca8615c41a57e719bff315c9adb6f2a4281a28e8798"},
{file = "aiohttp-3.11.12.tar.gz", hash = "sha256:7603ca26d75b1b86160ce1bbe2787a0b706e592af5b2504e12caa88a217767b0"},
] ]
[package.dependencies] [package.dependencies]
@ -248,17 +253,17 @@ tomli = {version = "*", markers = "python_version < \"3.11\""}
[[package]] [[package]]
name = "babel" name = "babel"
version = "2.16.0" version = "2.17.0"
description = "Internationalization utilities" description = "Internationalization utilities"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "babel-2.16.0-py3-none-any.whl", hash = "sha256:368b5b98b37c06b7daf6696391c3240c938b37767d4584413e8438c5c435fa8b"}, {file = "babel-2.17.0-py3-none-any.whl", hash = "sha256:4d0b53093fdfb4b21c92b5213dba5a1b23885afa8383709427046b21c366e5f2"},
{file = "babel-2.16.0.tar.gz", hash = "sha256:d1f3554ca26605fe173f3de0c65f750f5a42f924499bf134de6423582298e316"}, {file = "babel-2.17.0.tar.gz", hash = "sha256:0c54cffb19f690cdcc52a3b50bcbf71e07a808d1c80d549f2459b9d2cf0afb9d"},
] ]
[package.extras] [package.extras]
dev = ["freezegun (>=1.0,<2.0)", "pytest (>=6.0)", "pytest-cov"] dev = ["backports.zoneinfo", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata"]
[[package]] [[package]]
name = "backports-tarfile" name = "backports-tarfile"
@ -364,13 +369,13 @@ css = ["tinycss2 (>=1.1.0,<1.5)"]
[[package]] [[package]]
name = "certifi" name = "certifi"
version = "2024.12.14" version = "2025.1.31"
description = "Python package for providing Mozilla's CA Bundle." description = "Python package for providing Mozilla's CA Bundle."
optional = false optional = false
python-versions = ">=3.6" python-versions = ">=3.6"
files = [ files = [
{file = "certifi-2024.12.14-py3-none-any.whl", hash = "sha256:1275f7a45be9464efc1173084eaa30f866fe2e47d389406136d332ed4967ec56"}, {file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"},
{file = "certifi-2024.12.14.tar.gz", hash = "sha256:b650d30f370c2b724812bee08008be0c4163b163ddaec3f2546c1caf65f191db"}, {file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"},
] ]
[[package]] [[package]]
@ -861,13 +866,13 @@ files = [
[[package]] [[package]]
name = "docling-core" name = "docling-core"
version = "2.17.0" version = "2.17.2"
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-2.17.0-py3-none-any.whl", hash = "sha256:5c3015e0eed8e939069bdfd566761dc9f39239647893ae42c53d1333dd0a4749"}, {file = "docling_core-2.17.2-py3-none-any.whl", hash = "sha256:9d344ebe39ca3714b38aa7d9c62e361a4fdbbdad4cda9b5177dcd524045dc679"},
{file = "docling_core-2.17.0.tar.gz", hash = "sha256:cfcba8d173730baf244f279369f68e3cb5ddc7680769841afd254b61e432133e"}, {file = "docling_core-2.17.2.tar.gz", hash = "sha256:8d6e6213eb78b421c7e75fff00902d11a0e8dec0717321ca3ed1c5e529f95c91"},
] ]
[package.dependencies] [package.dependencies]
@ -889,13 +894,13 @@ 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 = "3.3.0" version = "3.3.1"
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-3.3.0-py3-none-any.whl", hash = "sha256:f1c99d345cb524239c7a2090969920e4311fd2fe22dad9bd609bc38039ec56eb"}, {file = "docling_ibm_models-3.3.1-py3-none-any.whl", hash = "sha256:be8f6684839c48d4b318e58a558cd7e2af3351b712f9604a69a415a0e238d5e2"},
{file = "docling_ibm_models-3.3.0.tar.gz", hash = "sha256:5a7497053871179d59870c830945aa8664a34aac48b7e68edf602720ee7f6c49"}, {file = "docling_ibm_models-3.3.1.tar.gz", hash = "sha256:f1d64216bbca6507da6f80de1acf450f33bdc7dc81cfd7f532a6cfc545cc092a"},
] ]
[package.dependencies] [package.dependencies]
@ -918,39 +923,39 @@ transformers = [
[[package]] [[package]]
name = "docling-parse" name = "docling-parse"
version = "3.1.2" version = "3.3.0"
description = "Simple package to extract text with coordinates from programmatic PDFs" description = "Simple package to extract text with coordinates from programmatic PDFs"
optional = false optional = false
python-versions = "<4.0,>=3.9" python-versions = "<4.0,>=3.9"
files = [ files = [
{file = "docling_parse-3.1.2-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:da15cf948bad8421c6269f99ab23a41728862ca47c864bc949acfc76194387e7"}, {file = "docling_parse-3.3.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:25ac1137787d01cc1d402cd7f3bca2c702d8ae6d38cedd042337d04b5444aedb"},
{file = "docling_parse-3.1.2-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:96f440bddb3aa31e2c485a66acf3f0f8425a291221058f27c57a2297add47864"}, {file = "docling_parse-3.3.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:7d8dc58751bd6a3dcd371363152d98df8deb33ab0752c2fce6a7b380d6804958"},
{file = "docling_parse-3.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fa2e167e808967946273765d56705cd5cf8ae0269e1b4f53840eafe6f791ebd6"}, {file = "docling_parse-3.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:780a12e6fa7729f76d12dd0f6431192ad38cd3621bfcad77d6dc37a7bca78ca3"},
{file = "docling_parse-3.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d1e62878150497a01b325f694f6c630699946e9ea150b8952fe28ab25482430"}, {file = "docling_parse-3.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:15db955169ddb57e5fd9e887d5467789d5748154bedbe3e861003318b8de0ca3"},
{file = "docling_parse-3.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:602af17a842fd53cb27493b49de92d378e9eec17b4a5e240fee5a8d9d70c79bd"}, {file = "docling_parse-3.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:1104451aef07fdacb45341e1ce15f31193e32e46905d0703d0a3d62aeaa8632a"},
{file = "docling_parse-3.1.2-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:fd934888c69eb380c4ef4df3e78fcdd7699c151005292eae69f3dacbe39b7c19"}, {file = "docling_parse-3.3.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:b1768fca5700384ea309af3a2714ad0b06a9be00da24d171e840b0d2098d5e52"},
{file = "docling_parse-3.1.2-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:628f9d296bd5db503c7d5cf5523dff620008d32eeba4fbd245af8b8758eaa7fa"}, {file = "docling_parse-3.3.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:b5647814c701c6199ed3da5577aac292f42e22d581df206a81f34fbb7e9f2fec"},
{file = "docling_parse-3.1.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a3a8f4199a99611a7239f078aa1590acf5695d90eb168e5b1be54c84fc45efd0"}, {file = "docling_parse-3.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ae4bea3441d8f358a9669a6d40c510c640ae45fa5c3464698de9c01fa773f14"},
{file = "docling_parse-3.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f634811c547e9cbcef1ac5f027ac855c75fbd89159e6c2b32ee4a83f22d79c73"}, {file = "docling_parse-3.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b2e1aae698a0a7fe81ab394cb8fa328a0f4eaa883962168e7dea5387ee30e76d"},
{file = "docling_parse-3.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:8d9bacc45d3ad9d25c49c768029277009948bb9e4a193e9bc4c5a319d9592427"}, {file = "docling_parse-3.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:43757a1848dffe2262c10347115e4be38dd9565261659c3d8c29ce02770bbcfd"},
{file = "docling_parse-3.1.2-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:8556b21a0e5f725a598b478e53f222032ca661d581dcfc0805617be44c022b41"}, {file = "docling_parse-3.3.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:1498748fb3270ab8074ef48dcdcef1107c6e312e3b3793c71b1341bf6d706966"},
{file = "docling_parse-3.1.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:2026c312982749ea09ee137715f95dbd3939a78792d32e66e91965dc6280db29"}, {file = "docling_parse-3.3.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:b9e4db7bf9736c46a6b5cae45242f2dd2cc478f661bade3d06200ba86ad2aa33"},
{file = "docling_parse-3.1.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:74780285314eb0847b1779ee2587347c19881d148ff41b90f49ae8bc0685828c"}, {file = "docling_parse-3.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8d73364e16383403b0828ad12c74dd8dbb2bd5d572f4b62c9a417f0cdea2138"},
{file = "docling_parse-3.1.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b47be7156775831036800bdea6c6db97c51685f8f7582924f7bff1b75a63e650"}, {file = "docling_parse-3.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6fe95708c21039216ff0620ff2c822de14dd70cd61ac9b7117fc30b3d7990f81"},
{file = "docling_parse-3.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:43077e58e73711198b2f58ea43e58847b93451335b345b587c785867d5ba6a67"}, {file = "docling_parse-3.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:b23bc96c593979567ba18727a31adb1a4524d203feea9b12dac4c8774971d709"},
{file = "docling_parse-3.1.2-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:1d4917459410d7275246c29396ef7055af990185e0cd95b8df3c1dcbacc3db5d"}, {file = "docling_parse-3.3.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:ab240ce8c923143ef125291ee15121f67a99034df110133cd7d481c5f0b4525a"},
{file = "docling_parse-3.1.2-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:f41d5c34b98774d8015eb84295388ccc3cc0ce05f052829e7e09c3ffd46541d2"}, {file = "docling_parse-3.3.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:916cdd6fd52c32e7026c1e70795c0a9d2d3299f200cc240c047dcc702fcf268f"},
{file = "docling_parse-3.1.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d12df0b24026b454c1741dd2c4ea6be607e96b9f821778bfeee13b1bb5915a95"}, {file = "docling_parse-3.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b34f0c5629db675dda7bd8992a80416a03b9b75e99f6d6db8869cdd935d63b7f"},
{file = "docling_parse-3.1.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd341164248d20ec71b4711c33052be653f5f0972c81feb7a1c66ecc075a3140"}, {file = "docling_parse-3.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d260306cbe52a3954cba9f9b9459547b7f66156a1e85821b2f7106a3f230586"},
{file = "docling_parse-3.1.2-cp313-cp313-win_amd64.whl", hash = "sha256:c4015a0bcfab6a294ae78e9b789b081d342216b6349a6832c9b6e515603f2481"}, {file = "docling_parse-3.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:c37be103a07f27fb2bd77350f324e55822d7126b534ebd52ec9de3d10feae72f"},
{file = "docling_parse-3.1.2-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:a66da9e89cbde676c0fe7041b97701890eb107624a1fe8be8e4d5fecb0bc89dc"}, {file = "docling_parse-3.3.0-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:cfb921c4901e342c42d1754f0fe67e73577d6506143b75dfde44720efe89aae4"},
{file = "docling_parse-3.1.2-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:cad2ab8169110f39dc4d4f92e0eec523e85a378df3f84466c6d651c353ac009a"}, {file = "docling_parse-3.3.0-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:acc7b4929296f6c9fdc91851c999a353f785039c3f2eb591923564b42fc3d0d1"},
{file = "docling_parse-3.1.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23bd70576497ef01add1498dd0c79686d4cf6b8044f91d6d201cb123ab742d3b"}, {file = "docling_parse-3.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51e7640aadc75d9a3efa2f591b583824999111cc1830868dd8409c7f6f8e19a6"},
{file = "docling_parse-3.1.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:38c605927a7798613f0fcfee2cbd37ad1fb13f7e4a261f5ac575784e022339c4"}, {file = "docling_parse-3.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:118c69c81539bcac2b3b635edbabac29301e778894382688fedaa86f6dba5c13"},
{file = "docling_parse-3.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:cb4bdbdbfead3411531ab5a416ea7a1bbe46ac49e48e9b59c3c3ba7f5bf05564"}, {file = "docling_parse-3.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:556653428da5f2b9863f630222f5369c66a4ca0cadb42ea1d8db826cb4e6c4c6"},
{file = "docling_parse-3.1.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:2b76c552e98f6d7df7eb00c4e123eb16fde80578dfadf577cedb98e772be263e"}, {file = "docling_parse-3.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:d6f56e7ed06dee6451d0552c9c2221491af7a7a0cb8c9b8b9c78c1b728b35d27"},
{file = "docling_parse-3.1.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:5c8c182af4a4374dfa7a06c60d7e4d3b329a93faee485f47a8844e2fb3185f57"}, {file = "docling_parse-3.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:b83347e82dbb5bb58807cc605fd521803fc6a0852f0063b9f6d26b3f7426b662"},
{file = "docling_parse-3.1.2.tar.gz", hash = "sha256:f024d4eb82b9ab48eeb19700e63d3ba7c07e5255b239a4a0f7fcd823427a106e"}, {file = "docling_parse-3.3.0.tar.gz", hash = "sha256:38ed09e63c735b5e010e5a75af92da5d8b2fcab9e93d2d17873e9115290fd7fa"},
] ]
[package.dependencies] [package.dependencies]
@ -1338,13 +1343,13 @@ test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit",
[[package]] [[package]]
name = "griffe" name = "griffe"
version = "1.5.5" version = "1.5.6"
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-1.5.5-py3-none-any.whl", hash = "sha256:2761b1e8876c6f1f9ab1af274df93ea6bbadd65090de5f38f4cb5cc84897c7dd"}, {file = "griffe-1.5.6-py3-none-any.whl", hash = "sha256:b2a3afe497c6c1f952e54a23095ecc09435016293e77af8478ed65df1022a394"},
{file = "griffe-1.5.5.tar.gz", hash = "sha256:35ee5b38b93d6a839098aad0f92207e6ad6b70c3e8866c08ca669275b8cba585"}, {file = "griffe-1.5.6.tar.gz", hash = "sha256:181f6666d5aceb6cd6e2da5a2b646cfb431e47a0da1fda283845734b67e10944"},
] ]
[package.dependencies] [package.dependencies]
@ -1489,13 +1494,13 @@ zstd = ["zstandard (>=0.18.0)"]
[[package]] [[package]]
name = "huggingface-hub" name = "huggingface-hub"
version = "0.28.0" version = "0.28.1"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "huggingface_hub-0.28.0-py3-none-any.whl", hash = "sha256:71cff4e500efe68061d94b7f6d3114e183715088be7a90bf4dd84af83b5f5cdb"}, {file = "huggingface_hub-0.28.1-py3-none-any.whl", hash = "sha256:aa6b9a3ffdae939b72c464dbb0d7f99f56e649b55c3d52406f49e0a5a620c0a7"},
{file = "huggingface_hub-0.28.0.tar.gz", hash = "sha256:c2b18c02a47d4384763caddb4d0ab2a8fc6c16e0800d6de4d55d0a896244aba3"}, {file = "huggingface_hub-0.28.1.tar.gz", hash = "sha256:893471090c98e3b6efbdfdacafe4052b20b84d59866fb6f54c33d9af18c303ae"},
] ]
[package.dependencies] [package.dependencies]
@ -2722,13 +2727,13 @@ pygments = ">2.12.0"
[[package]] [[package]]
name = "mkdocs-material" name = "mkdocs-material"
version = "9.5.50" version = "9.6.2"
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-9.5.50-py3-none-any.whl", hash = "sha256:f24100f234741f4d423a9d672a909d859668a4f404796be3cf035f10d6050385"}, {file = "mkdocs_material-9.6.2-py3-none-any.whl", hash = "sha256:71d90dbd63b393ad11a4d90151dfe3dcbfcd802c0f29ce80bebd9bbac6abc753"},
{file = "mkdocs_material-9.5.50.tar.gz", hash = "sha256:ae5fe16f3d7c9ccd05bb6916a7da7420cf99a9ce5e33debd9d40403a090d5825"}, {file = "mkdocs_material-9.6.2.tar.gz", hash = "sha256:a3de1c5d4c745f10afa78b1a02f917b9dce0808fb206adc0f5bb48b58c1ca21f"},
] ]
[package.dependencies] [package.dependencies]
@ -2989,49 +2994,43 @@ dill = ">=0.3.8"
[[package]] [[package]]
name = "mypy" name = "mypy"
version = "1.14.1" version = "1.15.0"
description = "Optional static typing for Python" description = "Optional static typing for Python"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.9"
files = [ files = [
{file = "mypy-1.14.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:52686e37cf13d559f668aa398dd7ddf1f92c5d613e4f8cb262be2fb4fedb0fcb"}, {file = "mypy-1.15.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:979e4e1a006511dacf628e36fadfecbcc0160a8af6ca7dad2f5025529e082c13"},
{file = "mypy-1.14.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:1fb545ca340537d4b45d3eecdb3def05e913299ca72c290326be19b3804b39c0"}, {file = "mypy-1.15.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c4bb0e1bd29f7d34efcccd71cf733580191e9a264a2202b0239da95984c5b559"},
{file = "mypy-1.14.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:90716d8b2d1f4cd503309788e51366f07c56635a3309b0f6a32547eaaa36a64d"}, {file = "mypy-1.15.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:be68172e9fd9ad8fb876c6389f16d1c1b5f100ffa779f77b1fb2176fcc9ab95b"},
{file = "mypy-1.14.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2ae753f5c9fef278bcf12e1a564351764f2a6da579d4a81347e1d5a15819997b"}, {file = "mypy-1.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c7be1e46525adfa0d97681432ee9fcd61a3964c2446795714699a998d193f1a3"},
{file = "mypy-1.14.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:e0fe0f5feaafcb04505bcf439e991c6d8f1bf8b15f12b05feeed96e9e7bf1427"}, {file = "mypy-1.15.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:2e2c2e6d3593f6451b18588848e66260ff62ccca522dd231cd4dd59b0160668b"},
{file = "mypy-1.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:7d54bd85b925e501c555a3227f3ec0cfc54ee8b6930bd6141ec872d1c572f81f"}, {file = "mypy-1.15.0-cp310-cp310-win_amd64.whl", hash = "sha256:6983aae8b2f653e098edb77f893f7b6aca69f6cffb19b2cc7443f23cce5f4828"},
{file = "mypy-1.14.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f995e511de847791c3b11ed90084a7a0aafdc074ab88c5a9711622fe4751138c"}, {file = "mypy-1.15.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2922d42e16d6de288022e5ca321cd0618b238cfc5570e0263e5ba0a77dbef56f"},
{file = "mypy-1.14.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d64169ec3b8461311f8ce2fd2eb5d33e2d0f2c7b49116259c51d0d96edee48d1"}, {file = "mypy-1.15.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2ee2d57e01a7c35de00f4634ba1bbf015185b219e4dc5909e281016df43f5ee5"},
{file = "mypy-1.14.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ba24549de7b89b6381b91fbc068d798192b1b5201987070319889e93038967a8"}, {file = "mypy-1.15.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:973500e0774b85d9689715feeffcc980193086551110fd678ebe1f4342fb7c5e"},
{file = "mypy-1.14.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:183cf0a45457d28ff9d758730cd0210419ac27d4d3f285beda038c9083363b1f"}, {file = "mypy-1.15.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5a95fb17c13e29d2d5195869262f8125dfdb5c134dc8d9a9d0aecf7525b10c2c"},
{file = "mypy-1.14.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f2a0ecc86378f45347f586e4163d1769dd81c5a223d577fe351f26b179e148b1"}, {file = "mypy-1.15.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1905f494bfd7d85a23a88c5d97840888a7bd516545fc5aaedff0267e0bb54e2f"},
{file = "mypy-1.14.1-cp311-cp311-win_amd64.whl", hash = "sha256:ad3301ebebec9e8ee7135d8e3109ca76c23752bac1e717bc84cd3836b4bf3eae"}, {file = "mypy-1.15.0-cp311-cp311-win_amd64.whl", hash = "sha256:c9817fa23833ff189db061e6d2eff49b2f3b6ed9856b4a0a73046e41932d744f"},
{file = "mypy-1.14.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:30ff5ef8519bbc2e18b3b54521ec319513a26f1bba19a7582e7b1f58a6e69f14"}, {file = "mypy-1.15.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:aea39e0583d05124836ea645f412e88a5c7d0fd77a6d694b60d9b6b2d9f184fd"},
{file = "mypy-1.14.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:cb9f255c18052343c70234907e2e532bc7e55a62565d64536dbc7706a20b78b9"}, {file = "mypy-1.15.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:2f2147ab812b75e5b5499b01ade1f4a81489a147c01585cda36019102538615f"},
{file = "mypy-1.14.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8b4e3413e0bddea671012b063e27591b953d653209e7a4fa5e48759cda77ca11"}, {file = "mypy-1.15.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ce436f4c6d218a070048ed6a44c0bbb10cd2cc5e272b29e7845f6a2f57ee4464"},
{file = "mypy-1.14.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:553c293b1fbdebb6c3c4030589dab9fafb6dfa768995a453d8a5d3b23784af2e"}, {file = "mypy-1.15.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8023ff13985661b50a5928fc7a5ca15f3d1affb41e5f0a9952cb68ef090b31ee"},
{file = "mypy-1.14.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:fad79bfe3b65fe6a1efaed97b445c3d37f7be9fdc348bdb2d7cac75579607c89"}, {file = "mypy-1.15.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:1124a18bc11a6a62887e3e137f37f53fbae476dc36c185d549d4f837a2a6a14e"},
{file = "mypy-1.14.1-cp312-cp312-win_amd64.whl", hash = "sha256:8fa2220e54d2946e94ab6dbb3ba0a992795bd68b16dc852db33028df2b00191b"}, {file = "mypy-1.15.0-cp312-cp312-win_amd64.whl", hash = "sha256:171a9ca9a40cd1843abeca0e405bc1940cd9b305eaeea2dda769ba096932bb22"},
{file = "mypy-1.14.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:92c3ed5afb06c3a8e188cb5da4984cab9ec9a77ba956ee419c68a388b4595255"}, {file = "mypy-1.15.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:93faf3fdb04768d44bf28693293f3904bbb555d076b781ad2530214ee53e3445"},
{file = "mypy-1.14.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:dbec574648b3e25f43d23577309b16534431db4ddc09fda50841f1e34e64ed34"}, {file = "mypy-1.15.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:811aeccadfb730024c5d3e326b2fbe9249bb7413553f15499a4050f7c30e801d"},
{file = "mypy-1.14.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8c6d94b16d62eb3e947281aa7347d78236688e21081f11de976376cf010eb31a"}, {file = "mypy-1.15.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:98b7b9b9aedb65fe628c62a6dc57f6d5088ef2dfca37903a7d9ee374d03acca5"},
{file = "mypy-1.14.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d4b19b03fdf54f3c5b2fa474c56b4c13c9dbfb9a2db4370ede7ec11a2c5927d9"}, {file = "mypy-1.15.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c43a7682e24b4f576d93072216bf56eeff70d9140241f9edec0c104d0c515036"},
{file = "mypy-1.14.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:0c911fde686394753fff899c409fd4e16e9b294c24bfd5e1ea4675deae1ac6fd"}, {file = "mypy-1.15.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:baefc32840a9f00babd83251560e0ae1573e2f9d1b067719479bfb0e987c6357"},
{file = "mypy-1.14.1-cp313-cp313-win_amd64.whl", hash = "sha256:8b21525cb51671219f5307be85f7e646a153e5acc656e5cebf64bfa076c50107"}, {file = "mypy-1.15.0-cp313-cp313-win_amd64.whl", hash = "sha256:b9378e2c00146c44793c98b8d5a61039a048e31f429fb0eb546d93f4b000bedf"},
{file = "mypy-1.14.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7084fb8f1128c76cd9cf68fe5971b37072598e7c31b2f9f95586b65c741a9d31"}, {file = "mypy-1.15.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e601a7fa172c2131bff456bb3ee08a88360760d0d2f8cbd7a75a65497e2df078"},
{file = "mypy-1.14.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8f845a00b4f420f693f870eaee5f3e2692fa84cc8514496114649cfa8fd5e2c6"}, {file = "mypy-1.15.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:712e962a6357634fef20412699a3655c610110e01cdaa6180acec7fc9f8513ba"},
{file = "mypy-1.14.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:44bf464499f0e3a2d14d58b54674dee25c031703b2ffc35064bd0df2e0fac319"}, {file = "mypy-1.15.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f95579473af29ab73a10bada2f9722856792a36ec5af5399b653aa28360290a5"},
{file = "mypy-1.14.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c99f27732c0b7dc847adb21c9d47ce57eb48fa33a17bc6d7d5c5e9f9e7ae5bac"}, {file = "mypy-1.15.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8f8722560a14cde92fdb1e31597760dc35f9f5524cce17836c0d22841830fd5b"},
{file = "mypy-1.14.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:bce23c7377b43602baa0bd22ea3265c49b9ff0b76eb315d6c34721af4cdf1d9b"}, {file = "mypy-1.15.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:1fbb8da62dc352133d7d7ca90ed2fb0e9d42bb1a32724c287d3c76c58cbaa9c2"},
{file = "mypy-1.14.1-cp38-cp38-win_amd64.whl", hash = "sha256:8edc07eeade7ebc771ff9cf6b211b9a7d93687ff892150cb5692e4f4272b0837"}, {file = "mypy-1.15.0-cp39-cp39-win_amd64.whl", hash = "sha256:d10d994b41fb3497719bbf866f227b3489048ea4bbbb5015357db306249f7980"},
{file = "mypy-1.14.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:3888a1816d69f7ab92092f785a462944b3ca16d7c470d564165fe703b0970c35"}, {file = "mypy-1.15.0-py3-none-any.whl", hash = "sha256:5469affef548bd1895d86d3bf10ce2b44e33d86923c29e4d675b3e323437ea3e"},
{file = "mypy-1.14.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:46c756a444117c43ee984bd055db99e498bc613a70bbbc120272bd13ca579fbc"}, {file = "mypy-1.15.0.tar.gz", hash = "sha256:404534629d51d3efea5c800ee7c42b72a6554d6c400e6a79eafe15d11341fd43"},
{file = "mypy-1.14.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:27fc248022907e72abfd8e22ab1f10e903915ff69961174784a3900a8cba9ad9"},
{file = "mypy-1.14.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:499d6a72fb7e5de92218db961f1a66d5f11783f9ae549d214617edab5d4dbdbb"},
{file = "mypy-1.14.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:57961db9795eb566dc1d1b4e9139ebc4c6b0cb6e7254ecde69d1552bf7613f60"},
{file = "mypy-1.14.1-cp39-cp39-win_amd64.whl", hash = "sha256:07ba89fdcc9451f2ebb02853deb6aaaa3d2239a236669a63ab3801bbf923ef5c"},
{file = "mypy-1.14.1-py3-none-any.whl", hash = "sha256:b66a60cc4073aeb8ae00057f9c1f64d49e90f918fbcef9a977eb121da8b8f1d1"},
{file = "mypy-1.14.1.tar.gz", hash = "sha256:7ec88144fe9b510e8475ec2f5f251992690fcf89ccb4500b214b4226abcd32d6"},
] ]
[package.dependencies] [package.dependencies]
@ -4842,13 +4841,13 @@ testutils = ["gitpython (>3)"]
[[package]] [[package]]
name = "pymdown-extensions" name = "pymdown-extensions"
version = "10.14.2" version = "10.14.3"
description = "Extension pack for Python Markdown." description = "Extension pack for Python Markdown."
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.8"
files = [ files = [
{file = "pymdown_extensions-10.14.2-py3-none-any.whl", hash = "sha256:f45bc5892410e54fd738ab8ccd736098b7ff0cb27fdb4bf24d0a0c6584bc90e1"}, {file = "pymdown_extensions-10.14.3-py3-none-any.whl", hash = "sha256:05e0bee73d64b9c71a4ae17c72abc2f700e8bc8403755a00580b49a4e9f189e9"},
{file = "pymdown_extensions-10.14.2.tar.gz", hash = "sha256:7a77b8116dc04193f2c01143760a43387bd9dc4aa05efacb7d838885a7791253"}, {file = "pymdown_extensions-10.14.3.tar.gz", hash = "sha256:41e576ce3f5d650be59e900e4ceff231e0aed2a88cf30acaee41e02f063a061b"},
] ]
[package.dependencies] [package.dependencies]
@ -5318,13 +5317,13 @@ test = ["coverage (>=5,<6)", "mock (==1.3.0)", "pytest (>=7,<8)", "pytest-mock (
[[package]] [[package]]
name = "pytz" name = "pytz"
version = "2024.2" version = "2025.1"
description = "World timezone definitions, modern and historical" description = "World timezone definitions, modern and historical"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "pytz-2024.2-py2.py3-none-any.whl", hash = "sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725"}, {file = "pytz-2025.1-py2.py3-none-any.whl", hash = "sha256:89dd22dca55b46eac6eda23b2d72721bf1bdfef212645d81513ef5d03038de57"},
{file = "pytz-2024.2.tar.gz", hash = "sha256:2aa355083c50a0f93fa581709deac0c9ad65cca8a9e9beac660adcbd493c798a"}, {file = "pytz-2025.1.tar.gz", hash = "sha256:c2db42be2a2518b28e65f9207c4d05e6ff547d1efa4086469ef855e4ab70178e"},
] ]
[[package]] [[package]]
@ -6252,53 +6251,53 @@ type = ["importlib_metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (==1.14
[[package]] [[package]]
name = "shapely" name = "shapely"
version = "2.0.6" version = "2.0.7"
description = "Manipulation and analysis of geometric objects" description = "Manipulation and analysis of geometric objects"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "shapely-2.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:29a34e068da2d321e926b5073539fd2a1d4429a2c656bd63f0bd4c8f5b236d0b"}, {file = "shapely-2.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:33fb10e50b16113714ae40adccf7670379e9ccf5b7a41d0002046ba2b8f0f691"},
{file = "shapely-2.0.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e1c84c3f53144febf6af909d6b581bc05e8785d57e27f35ebaa5c1ab9baba13b"}, {file = "shapely-2.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f44eda8bd7a4bccb0f281264b34bf3518d8c4c9a8ffe69a1a05dabf6e8461147"},
{file = "shapely-2.0.6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2ad2fae12dca8d2b727fa12b007e46fbc522148a584f5d6546c539f3464dccde"}, {file = "shapely-2.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf6c50cd879831955ac47af9c907ce0310245f9d162e298703f82e1785e38c98"},
{file = "shapely-2.0.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3304883bd82d44be1b27a9d17f1167fda8c7f5a02a897958d86c59ec69b705e"}, {file = "shapely-2.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04a65d882456e13c8b417562c36324c0cd1e5915f3c18ad516bb32ee3f5fc895"},
{file = "shapely-2.0.6-cp310-cp310-win32.whl", hash = "sha256:3ec3a0eab496b5e04633a39fa3d5eb5454628228201fb24903d38174ee34565e"}, {file = "shapely-2.0.7-cp310-cp310-win32.whl", hash = "sha256:7e97104d28e60b69f9b6a957c4d3a2a893b27525bc1fc96b47b3ccef46726bf2"},
{file = "shapely-2.0.6-cp310-cp310-win_amd64.whl", hash = "sha256:28f87cdf5308a514763a5c38de295544cb27429cfa655d50ed8431a4796090c4"}, {file = "shapely-2.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:35524cc8d40ee4752520819f9894b9f28ba339a42d4922e92c99b148bed3be39"},
{file = "shapely-2.0.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5aeb0f51a9db176da9a30cb2f4329b6fbd1e26d359012bb0ac3d3c7781667a9e"}, {file = "shapely-2.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5cf23400cb25deccf48c56a7cdda8197ae66c0e9097fcdd122ac2007e320bc34"},
{file = "shapely-2.0.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9a7a78b0d51257a367ee115f4d41ca4d46edbd0dd280f697a8092dd3989867b2"}, {file = "shapely-2.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d8f1da01c04527f7da59ee3755d8ee112cd8967c15fab9e43bba936b81e2a013"},
{file = "shapely-2.0.6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f32c23d2f43d54029f986479f7c1f6e09c6b3a19353a3833c2ffb226fb63a855"}, {file = "shapely-2.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f623b64bb219d62014781120f47499a7adc30cf7787e24b659e56651ceebcb0"},
{file = "shapely-2.0.6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3dc9fb0eb56498912025f5eb352b5126f04801ed0e8bdbd867d21bdbfd7cbd0"}, {file = "shapely-2.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e6d95703efaa64aaabf278ced641b888fc23d9c6dd71f8215091afd8a26a66e3"},
{file = "shapely-2.0.6-cp311-cp311-win32.whl", hash = "sha256:d93b7e0e71c9f095e09454bf18dad5ea716fb6ced5df3cb044564a00723f339d"}, {file = "shapely-2.0.7-cp311-cp311-win32.whl", hash = "sha256:2f6e4759cf680a0f00a54234902415f2fa5fe02f6b05546c662654001f0793a2"},
{file = "shapely-2.0.6-cp311-cp311-win_amd64.whl", hash = "sha256:c02eb6bf4cfb9fe6568502e85bb2647921ee49171bcd2d4116c7b3109724ef9b"}, {file = "shapely-2.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:b52f3ab845d32dfd20afba86675c91919a622f4627182daec64974db9b0b4608"},
{file = "shapely-2.0.6-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:cec9193519940e9d1b86a3b4f5af9eb6910197d24af02f247afbfb47bcb3fab0"}, {file = "shapely-2.0.7-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:4c2b9859424facbafa54f4a19b625a752ff958ab49e01bc695f254f7db1835fa"},
{file = "shapely-2.0.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:83b94a44ab04a90e88be69e7ddcc6f332da7c0a0ebb1156e1c4f568bbec983c3"}, {file = "shapely-2.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:5aed1c6764f51011d69a679fdf6b57e691371ae49ebe28c3edb5486537ffbd51"},
{file = "shapely-2.0.6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:537c4b2716d22c92036d00b34aac9d3775e3691f80c7aa517c2c290351f42cd8"}, {file = "shapely-2.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73c9ae8cf443187d784d57202199bf9fd2d4bb7d5521fe8926ba40db1bc33e8e"},
{file = "shapely-2.0.6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98fea108334be345c283ce74bf064fa00cfdd718048a8af7343c59eb40f59726"}, {file = "shapely-2.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9469f49ff873ef566864cb3516091881f217b5d231c8164f7883990eec88b73"},
{file = "shapely-2.0.6-cp312-cp312-win32.whl", hash = "sha256:42fd4cd4834747e4990227e4cbafb02242c0cffe9ce7ef9971f53ac52d80d55f"}, {file = "shapely-2.0.7-cp312-cp312-win32.whl", hash = "sha256:6bca5095e86be9d4ef3cb52d56bdd66df63ff111d580855cb8546f06c3c907cd"},
{file = "shapely-2.0.6-cp312-cp312-win_amd64.whl", hash = "sha256:665990c84aece05efb68a21b3523a6b2057e84a1afbef426ad287f0796ef8a48"}, {file = "shapely-2.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:f86e2c0259fe598c4532acfcf638c1f520fa77c1275912bbc958faecbf00b108"},
{file = "shapely-2.0.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:42805ef90783ce689a4dde2b6b2f261e2c52609226a0438d882e3ced40bb3013"}, {file = "shapely-2.0.7-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:a0c09e3e02f948631c7763b4fd3dd175bc45303a0ae04b000856dedebefe13cb"},
{file = "shapely-2.0.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:6d2cb146191a47bd0cee8ff5f90b47547b82b6345c0d02dd8b25b88b68af62d7"}, {file = "shapely-2.0.7-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:06ff6020949b44baa8fc2e5e57e0f3d09486cd5c33b47d669f847c54136e7027"},
{file = "shapely-2.0.6-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3fdef0a1794a8fe70dc1f514440aa34426cc0ae98d9a1027fb299d45741c381"}, {file = "shapely-2.0.7-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d6dbf096f961ca6bec5640e22e65ccdec11e676344e8157fe7d636e7904fd36"},
{file = "shapely-2.0.6-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c665a0301c645615a107ff7f52adafa2153beab51daf34587170d85e8ba6805"}, {file = "shapely-2.0.7-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:adeddfb1e22c20548e840403e5e0b3d9dc3daf66f05fa59f1fcf5b5f664f0e98"},
{file = "shapely-2.0.6-cp313-cp313-win32.whl", hash = "sha256:0334bd51828f68cd54b87d80b3e7cee93f249d82ae55a0faf3ea21c9be7b323a"}, {file = "shapely-2.0.7-cp313-cp313-win32.whl", hash = "sha256:a7f04691ce1c7ed974c2f8b34a1fe4c3c5dfe33128eae886aa32d730f1ec1913"},
{file = "shapely-2.0.6-cp313-cp313-win_amd64.whl", hash = "sha256:d37d070da9e0e0f0a530a621e17c0b8c3c9d04105655132a87cfff8bd77cc4c2"}, {file = "shapely-2.0.7-cp313-cp313-win_amd64.whl", hash = "sha256:aaaf5f7e6cc234c1793f2a2760da464b604584fb58c6b6d7d94144fd2692d67e"},
{file = "shapely-2.0.6-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:fa7468e4f5b92049c0f36d63c3e309f85f2775752e076378e36c6387245c5462"}, {file = "shapely-2.0.7-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:19cbc8808efe87a71150e785b71d8a0e614751464e21fb679d97e274eca7bd43"},
{file = "shapely-2.0.6-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ed5867e598a9e8ac3291da6cc9baa62ca25706eea186117034e8ec0ea4355653"}, {file = "shapely-2.0.7-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fc19b78cc966db195024d8011649b4e22812f805dd49264323980715ab80accc"},
{file = "shapely-2.0.6-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81d9dfe155f371f78c8d895a7b7f323bb241fb148d848a2bf2244f79213123fe"}, {file = "shapely-2.0.7-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd37d65519b3f8ed8976fa4302a2827cbb96e0a461a2e504db583b08a22f0b98"},
{file = "shapely-2.0.6-cp37-cp37m-win32.whl", hash = "sha256:fbb7bf02a7542dba55129062570211cfb0defa05386409b3e306c39612e7fbcc"}, {file = "shapely-2.0.7-cp37-cp37m-win32.whl", hash = "sha256:25085a30a2462cee4e850a6e3fb37431cbbe4ad51cbcc163af0cea1eaa9eb96d"},
{file = "shapely-2.0.6-cp37-cp37m-win_amd64.whl", hash = "sha256:837d395fac58aa01aa544495b97940995211e3e25f9aaf87bc3ba5b3a8cd1ac7"}, {file = "shapely-2.0.7-cp37-cp37m-win_amd64.whl", hash = "sha256:1a2e03277128e62f9a49a58eb7eb813fa9b343925fca5e7d631d50f4c0e8e0b8"},
{file = "shapely-2.0.6-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c6d88ade96bf02f6bfd667ddd3626913098e243e419a0325ebef2bbd481d1eb6"}, {file = "shapely-2.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e1c4f1071fe9c09af077a69b6c75f17feb473caeea0c3579b3e94834efcbdc36"},
{file = "shapely-2.0.6-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:8b3b818c4407eaa0b4cb376fd2305e20ff6df757bf1356651589eadc14aab41b"}, {file = "shapely-2.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:3697bd078b4459f5a1781015854ef5ea5d824dbf95282d0b60bfad6ff83ec8dc"},
{file = "shapely-2.0.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1bbc783529a21f2bd50c79cef90761f72d41c45622b3e57acf78d984c50a5d13"}, {file = "shapely-2.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1e9fed9a7d6451979d914cb6ebbb218b4b4e77c0d50da23e23d8327948662611"},
{file = "shapely-2.0.6-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2423f6c0903ebe5df6d32e0066b3d94029aab18425ad4b07bf98c3972a6e25a1"}, {file = "shapely-2.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2934834c7f417aeb7cba3b0d9b4441a76ebcecf9ea6e80b455c33c7c62d96a24"},
{file = "shapely-2.0.6-cp38-cp38-win32.whl", hash = "sha256:2de00c3bfa80d6750832bde1d9487e302a6dd21d90cb2f210515cefdb616e5f5"}, {file = "shapely-2.0.7-cp38-cp38-win32.whl", hash = "sha256:2e4a1749ad64bc6e7668c8f2f9479029f079991f4ae3cb9e6b25440e35a4b532"},
{file = "shapely-2.0.6-cp38-cp38-win_amd64.whl", hash = "sha256:3a82d58a1134d5e975f19268710e53bddd9c473743356c90d97ce04b73e101ee"}, {file = "shapely-2.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:8ae5cb6b645ac3fba34ad84b32fbdccb2ab321facb461954925bde807a0d3b74"},
{file = "shapely-2.0.6-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:392f66f458a0a2c706254f473290418236e52aa4c9b476a072539d63a2460595"}, {file = "shapely-2.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4abeb44b3b946236e4e1a1b3d2a0987fb4d8a63bfb3fdefb8a19d142b72001e5"},
{file = "shapely-2.0.6-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:eba5bae271d523c938274c61658ebc34de6c4b33fdf43ef7e938b5776388c1be"}, {file = "shapely-2.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cd0e75d9124b73e06a42bf1615ad3d7d805f66871aa94538c3a9b7871d620013"},
{file = "shapely-2.0.6-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7060566bc4888b0c8ed14b5d57df8a0ead5c28f9b69fb6bed4476df31c51b0af"}, {file = "shapely-2.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7977d8a39c4cf0e06247cd2dca695ad4e020b81981d4c82152c996346cf1094b"},
{file = "shapely-2.0.6-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b02154b3e9d076a29a8513dffcb80f047a5ea63c897c0cd3d3679f29363cf7e5"}, {file = "shapely-2.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0145387565fcf8f7c028b073c802956431308da933ef41d08b1693de49990d27"},
{file = "shapely-2.0.6-cp39-cp39-win32.whl", hash = "sha256:44246d30124a4f1a638a7d5419149959532b99dfa25b54393512e6acc9c211ac"}, {file = "shapely-2.0.7-cp39-cp39-win32.whl", hash = "sha256:98697c842d5c221408ba8aa573d4f49caef4831e9bc6b6e785ce38aca42d1999"},
{file = "shapely-2.0.6-cp39-cp39-win_amd64.whl", hash = "sha256:2b542d7f1dbb89192d3512c52b679c822ba916f93479fa5d4fc2fe4fa0b3c9e8"}, {file = "shapely-2.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:a3fb7fbae257e1b042f440289ee7235d03f433ea880e73e687f108d044b24db5"},
{file = "shapely-2.0.6.tar.gz", hash = "sha256:997f6159b1484059ec239cacaa53467fd8b5564dabe186cd84ac2944663b0bf6"}, {file = "shapely-2.0.7.tar.gz", hash = "sha256:28fe2997aab9a9dc026dc6a355d04e85841546b2a5d232ed953e3321ab958ee5"},
] ]
[package.dependencies] [package.dependencies]
@ -7063,13 +7062,13 @@ vision = ["Pillow (>=10.0.1,<=15.0)"]
[[package]] [[package]]
name = "transformers" name = "transformers"
version = "4.48.1" version = "4.48.2"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false optional = false
python-versions = ">=3.9.0" python-versions = ">=3.9.0"
files = [ files = [
{file = "transformers-4.48.1-py3-none-any.whl", hash = "sha256:24be0564b0a36d9e433d9a65de248f1545b6f6edce1737669605eb6a8141bbbb"}, {file = "transformers-4.48.2-py3-none-any.whl", hash = "sha256:493bc5b0268b116eff305edf6656367fc89cf570e7a9d5891369e04751db698a"},
{file = "transformers-4.48.1.tar.gz", hash = "sha256:7c1931facc3ee8adcbf86fc7a87461d54c1e40eca3bb57fef1ee9f3ecd32187e"}, {file = "transformers-4.48.2.tar.gz", hash = "sha256:dcfb73473e61f22fb3366fe2471ed2e42779ecdd49527a1bdf1937574855d516"},
] ]
[package.dependencies] [package.dependencies]
@ -7225,13 +7224,13 @@ files = [
[[package]] [[package]]
name = "types-pytz" name = "types-pytz"
version = "2024.2.0.20241221" version = "2025.1.0.20250204"
description = "Typing stubs for pytz" description = "Typing stubs for pytz"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.9"
files = [ files = [
{file = "types_pytz-2024.2.0.20241221-py3-none-any.whl", hash = "sha256:8fc03195329c43637ed4f593663df721fef919b60a969066e22606edf0b53ad5"}, {file = "types_pytz-2025.1.0.20250204-py3-none-any.whl", hash = "sha256:32ca4a35430e8b94f6603b35beb7f56c32260ddddd4f4bb305fdf8f92358b87e"},
{file = "types_pytz-2024.2.0.20241221.tar.gz", hash = "sha256:06d7cde9613e9f7504766a0554a270c369434b50e00975b3a4a0f6eed0f2c1a9"}, {file = "types_pytz-2025.1.0.20250204.tar.gz", hash = "sha256:00f750132769f1c65a4f7240bc84f13985b4da774bd17dfbe5d9cd442746bd49"},
] ]
[[package]] [[package]]
@ -7851,4 +7850,4 @@ tesserocr = ["tesserocr"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = "^3.9" python-versions = "^3.9"
content-hash = "7d8c8a4c2562f3e88673fb9a32d0a5f85aca0f7c7aeaa67a7a65a0f930a5c6c7" content-hash = "ca0464df452664834ae9bccc59f89240e2f5e8f3b179761de615548c799680e7"

6
pyproject.toml
View File

@ -26,10 +26,10 @@ packages = [{include = "docling"}]
###################### ######################
python = "^3.9" python = "^3.9"
pydantic = "^2.0.0" pydantic = "^2.0.0"
docling-core = {extras = ["chunking"], version = "^2.17.0"} docling-core = {extras = ["chunking"], version = "^2.17.2"}
docling-ibm-models = "^3.3.0" docling-ibm-models = "^3.3.0"
deepsearch-glm = "^1.0.0" deepsearch-glm = "^1.0.0"
docling-parse = "^3.1.0" docling-parse = "^3.3.0"
filetype = "^1.2.0" filetype = "^1.2.0"
pypdfium2 = "^4.30.0" pypdfium2 = "^4.30.0"
pydantic-settings = "^2.3.0" pydantic-settings = "^2.3.0"
@ -46,7 +46,7 @@ scipy = [
typer = "^0.12.5" typer = "^0.12.5"
python-docx = "^1.1.2" python-docx = "^1.1.2"
python-pptx = "^1.0.2" python-pptx = "^1.0.2"
beautifulsoup4 = "^4.12.3" beautifulsoup4 = ">=4.12.3,<4.13.0"
pandas = "^2.1.4" pandas = "^2.1.4"
marko = "^2.1.2" marko = "^2.1.2"
openpyxl = "^3.1.5" openpyxl = "^3.1.5"

0
tests/data/test_01.asciidoc → tests/data/asciidoc/test_01.asciidoc
View File

0
tests/data/test_02.asciidoc → tests/data/asciidoc/test_02.asciidoc
View File

BIN
tests/data/code_and_formula.pdf
View File

Binary file not shown.

2
tests/data/groundtruth/docling_v1/2203.01017v2.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2203.01017v2.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2206.01062.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2206.01062.pages.json
View File

File diff suppressed because one or more lines are too long

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

File diff suppressed because one or more lines are too long

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

File diff suppressed because one or more lines are too long

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

File diff suppressed because one or more lines are too long

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

File diff suppressed because one or more lines are too long

14
tests/data/groundtruth/docling_v1/code_and_formula.doctags.txt
View File

@ -1,13 +1,15 @@
<document> <document>
<subtitle-level-1><location><page_1><loc_22><loc_83><loc_45><loc_84></location>Java Code Example</subtitle-level-1> <subtitle-level-1><location><page_1><loc_22><loc_83><loc_52><loc_84></location>JavaScript Code Example</subtitle-level-1>
<paragraph><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph> <paragraph><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
<paragraph><location><page_1><loc_39><loc_61><loc_61><loc_62></location>Listing 1: Simple Java Program</paragraph> <paragraph><location><page_1><loc_22><loc_57><loc_78><loc_63></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,</paragraph>
<paragraph><location><page_1><loc_22><loc_56><loc_55><loc_60></location>public static void print() { System.out.println( "Java Code" ); }</paragraph> <paragraph><location><page_1><loc_36><loc_55><loc_63><loc_56></location>Listing 1: Simple JavaScript Program</paragraph>
<paragraph><location><page_1><loc_22><loc_37><loc_78><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph> <paragraph><location><page_1><loc_22><loc_49><loc_43><loc_54></location>function add(a, b) { return a + b; } console.log(add(3, 5));</paragraph>
<paragraph><location><page_1><loc_22><loc_29><loc_78><loc_47></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
<paragraph><location><page_1><loc_22><loc_23><loc_78><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,</paragraph>
<subtitle-level-1><location><page_2><loc_22><loc_84><loc_32><loc_85></location>Formula</subtitle-level-1> <subtitle-level-1><location><page_2><loc_22><loc_84><loc_32><loc_85></location>Formula</subtitle-level-1>
<paragraph><location><page_2><loc_22><loc_65><loc_80><loc_82></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph> <paragraph><location><page_2><loc_22><loc_66><loc_80><loc_82></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
<paragraph><location><page_2><loc_22><loc_58><loc_80><loc_65></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.</paragraph> <paragraph><location><page_2><loc_22><loc_58><loc_80><loc_65></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.</paragraph>
<paragraph><location><page_2><loc_22><loc_38><loc_80><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph> <paragraph><location><page_2><loc_22><loc_38><loc_80><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</paragraph>
<paragraph><location><page_2><loc_22><loc_29><loc_80><loc_38></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</paragraph> <paragraph><location><page_2><loc_22><loc_29><loc_80><loc_37></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</paragraph>
<paragraph><location><page_2><loc_22><loc_21><loc_80><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</paragraph> <paragraph><location><page_2><loc_22><loc_21><loc_80><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</paragraph>
</document> </document>

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

File diff suppressed because one or more lines are too long

10
tests/data/groundtruth/docling_v1/code_and_formula.md
View File

@ -1,13 +1,17 @@
## Java Code Example ## JavaScript Code Example
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
Listing 1: Simple Java Program Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,
public static void print() { System.out.println( "Java Code" ); } Listing 1: Simple JavaScript Program
function add(a, b) { return a + b; } console.log(add(3, 5));
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,
## Formula ## Formula
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.

2
tests/data/groundtruth/docling_v1/code_and_formula.pages.json
View File

File diff suppressed because one or more lines are too long

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

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/picture_classification.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/redp5110_sampled.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/redp5110_sampled.pages.json
View File

File diff suppressed because one or more lines are too long

9
tests/data/groundtruth/docling_v1/right_to_left_01.doctags.txt Normal file
View File

@ -0,0 +1,9 @@
<document>
<subtitle-level-1><location><page_1><loc_37><loc_89><loc_85><loc_91></location>Pythonو R ةغلب ةجمربلا للاخ نم تلاكشملا لحو ةيجاتنلإا نيسحت</subtitle-level-1>
<paragraph><location><page_1><loc_15><loc_80><loc_85><loc_87></location>Python و R ةغلب ةجمربلا ربتعت ةلاعف لولح داجيإ يف دعاستو ةيجاتنلإا ززعت نأ نكمي يتلا ةيوقلا تاودلأا نم ءاملعلاو نيللحملا ىلع لهسي امم ،تانايبلا ليلحتل ةيلاثم اهلعجت ةديرف تازيمPython و R نم لك كلتمي .تلاكشملل ناك اذإ .ةلاعفو ةعيرس ةقيرطب ةدقعم تلايلحت ءارجإ مهسي نأ نكمي تاغللا هذه مادختسا نإف ،ةيليلحت ةيلقع كيدل .لمعلا جئاتن نيسحت يف ريبك لكشب</paragraph>
<paragraph><location><page_1><loc_34><loc_73><loc_34><loc_75></location>ً</paragraph>
<paragraph><location><page_1><loc_16><loc_71><loc_85><loc_78></location>جارختساو تانايبلا نم ةلئاه تايمك ةجلاعم نكمملا نم حبصي ،ةجمربلا تاراهم عم يليلحتلا ريكفتلا عمتجي امدنع ذيفنتلPython و R مادختسا نيجمربملل نكمي .اهنم تاهجوتلاو طامنلأا ةجذمنلا لثم ،ةمدقتم ةيليلحت تايلمع ةقد رثكأ تارارق ذاختا ىلإ ا ضيأ يدؤي نأ نكمي لب ،تقولا رفوي طقف سيل اذه .ةريبكلا تانايبلا ليلحتو ةيئاصحلإا تانايبلا ىلع ةمئاق تاجاتنتسا ىلع ءانب .</paragraph>
<paragraph><location><page_1><loc_83><loc_71><loc_83><loc_73></location>ً</paragraph>
<paragraph><location><page_1><loc_15><loc_63><loc_85><loc_70></location>ليلحتلا نم ،تاقيبطتلا نم ةعساو ةعومجم معدت ةينغ تاودأو تابتكمPython و R نم لك رفوت ،كلذ ىلع ةولاع ىلع .ةفلتخملا تلاكشملل ةركتبم لولح ريوطتل تابتكملا هذه نم ةدافتسلاا نيمدختسملل نكمي .يللآا ملعتلا ىلإ ينايبلا R رفوت امنيب ،ةءافكب تانايبلا ةرادلإ Python يف pandas ةبتكم مادختسا نكمي ،لاثملا ليبس مسرلل ةيوق تاودأ .نيللحملاو نيثحابلل ةيلاثم اهلعجي امم ،يئاصحلإا ليلحتلاو ينايبلا</paragraph>
<paragraph><location><page_1><loc_16><loc_56><loc_85><loc_61></location>Python و R ةغلب ةجمربلا يدؤت نأ نكمي ،ةياهنلا يف ةركتبم لولح ريفوتو ةيجاتنلإا نيسحت ىلإ ةيليلحت ةيلقع عم اهل نوكت نأ نكمي ةبسانملا ةيجمربلا بيلاسلأا قيبطتو لاعف لكشب تانايبلا ليلحت ىلع ةردقلا نإ .ةدقعملا تلاكشملل .ينهملاو يصخشلا ءادلأا ىلع ىدملا ةديعب ةيباجيإ تاريثأت</paragraph>
</document>

1
tests/data/groundtruth/docling_v1/right_to_left_01.json Normal file
View File

File diff suppressed because one or more lines are too long

13
tests/data/groundtruth/docling_v1/right_to_left_01.md Normal file
View File

@ -0,0 +1,13 @@
## Pythonو R ةغلب ةجمربلا للاخ نم تلاكشملا لحو ةيجاتنلإا نيسحت
Python و R ةغلب ةجمربلا ربتعت ةلاعف لولح داجيإ يف دعاستو ةيجاتنلإا ززعت نأ نكمي يتلا ةيوقلا تاودلأا نم ءاملعلاو نيللحملا ىلع لهسي امم ،تانايبلا ليلحتل ةيلاثم اهلعجت ةديرف تازيمPython و R نم لك كلتمي .تلاكشملل ناك اذإ .ةلاعفو ةعيرس ةقيرطب ةدقعم تلايلحت ءارجإ مهسي نأ نكمي تاغللا هذه مادختسا نإف ،ةيليلحت ةيلقع كيدل .لمعلا جئاتن نيسحت يف ريبك لكشب
ً
جارختساو تانايبلا نم ةلئاه تايمك ةجلاعم نكمملا نم حبصي ،ةجمربلا تاراهم عم يليلحتلا ريكفتلا عمتجي امدنع ذيفنتلPython و R مادختسا نيجمربملل نكمي .اهنم تاهجوتلاو طامنلأا ةجذمنلا لثم ،ةمدقتم ةيليلحت تايلمع ةقد رثكأ تارارق ذاختا ىلإ ا ضيأ يدؤي نأ نكمي لب ،تقولا رفوي طقف سيل اذه .ةريبكلا تانايبلا ليلحتو ةيئاصحلإا تانايبلا ىلع ةمئاق تاجاتنتسا ىلع ءانب .
ً
ليلحتلا نم ،تاقيبطتلا نم ةعساو ةعومجم معدت ةينغ تاودأو تابتكمPython و R نم لك رفوت ،كلذ ىلع ةولاع ىلع .ةفلتخملا تلاكشملل ةركتبم لولح ريوطتل تابتكملا هذه نم ةدافتسلاا نيمدختسملل نكمي .يللآا ملعتلا ىلإ ينايبلا R رفوت امنيب ،ةءافكب تانايبلا ةرادلإ Python يف pandas ةبتكم مادختسا نكمي ،لاثملا ليبس مسرلل ةيوق تاودأ .نيللحملاو نيثحابلل ةيلاثم اهلعجي امم ،يئاصحلإا ليلحتلاو ينايبلا
Python و R ةغلب ةجمربلا يدؤت نأ نكمي ،ةياهنلا يف ةركتبم لولح ريفوتو ةيجاتنلإا نيسحت ىلإ ةيليلحت ةيلقع عم اهل نوكت نأ نكمي ةبسانملا ةيجمربلا بيلاسلأا قيبطتو لاعف لكشب تانايبلا ليلحت ىلع ةردقلا نإ .ةدقعملا تلاكشملل .ينهملاو يصخشلا ءادلأا ىلع ىدملا ةديعب ةيباجيإ تاريثأت

1
tests/data/groundtruth/docling_v1/right_to_left_01.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

10
tests/data/groundtruth/docling_v1/right_to_left_02.doctags.txt Normal file
View File

@ -0,0 +1,10 @@
<document>
<paragraph><location><page_1><loc_8><loc_3><loc_10><loc_4></location>11</paragraph>
<paragraph><location><page_1><loc_11><loc_50><loc_73><loc_75></location>،هيلعو ملا ةوا رملا لاول خواهييع ووص عضت ةيرص م لا ةموكح لا نإف ةو اب لأا نم ددي قي حت ىاي لمعلخب خال ةير وام جلا سي ئر د يسلا فياكت ا دو ه :خاسعر ىاي ويولولأا ةومئخق سعر ىا ي يرصملا نخسنلإا ءخهب فام عضو ، تخ ووومن تحدووعم قووي حت ىوو اي لو وم علا ،ليوواعللاو ةحووصلا تحخووجم اووف ةووصخل ىوووواي خوووو حلا ا وووو و ،تخوووو ي خل لا فوووواذع اووووف ةامخوووو و ةمادلووووسمو ةوووويوق وو يلودلاو ةوويمياقلإا تخيدوو حلل ا ءوووض اووف يرووصملا امووو لا نووملأا تاددووحم ،ة وو ام ةووعبخلم رارملووساو ،ةيووسخيسلا ة رخوواملا ر ي وو و لت د ووواو ةاووصاومو تخ ايوووو لاو ةوووفخ لا تخووو ام ريوووولت ، خوووهرلإا ةوووحفخ كمو ر ار لوووسحاو نوووملأا لي هخووو م وووسري ي ووولا وووو حهل ا ىووواي لدووولعملا اهيدووو لا خووولبلاو ،اه،وووولا .اعملجملا ماسلاو ةه،اوملا</paragraph>
<paragraph><location><page_1><loc_13><loc_45><loc_74><loc_48></location>رول لا لاول ةيرو ص م لا ةو موكحلا امخونرب دالوسي ،قبس خمل خً فوو 2024( -)2026 اتلآا وحهلا ىاي اهو ،ةسيئر ةيجيتارلسا اد هع ةعبرع قي حت :</paragraph>
<paragraph><location><page_1><loc_12><loc_37><loc_73><loc_40></location>نــــــــم ما ةــــــــيا م رـ صم لا يم وقل ا اــــسن ا ءاــــ نب رــــــــــــــــــــصم لا عاـــــصت ا ءاـــــ نب يــــــــــــــــــــــسبا نت قتسظا ق يقحت را ر يــــــــــــــــــــــــساي سلا</paragraph>
<paragraph><location><page_1><loc_12><loc_23><loc_73><loc_31></location>خهلوسحخب امخونرب لا ت خفدالوسم ديدحت لت دق هن ع ىلإ رخ لإا ردجت لكواب د روووصم ةو ووي ر تخ فدال ووو س م ىووو اي سيوووئر 2023 ر اوو وو حلا تخووو ساو تخيوووصوتو ، كيال ا تخ اووصيل اه،ووولا امخوونربلاو ،تارا ووو لا ت خ فدا لوو سمو ،اه،ووولا ،ةوو ي ا ةيه، ولا تخ ي جيتا رلسحا فالبمو .</paragraph>
<figure>
<location><page_1><loc_75><loc_23><loc_100><loc_76></location>
</figure>
</document>

1
tests/data/groundtruth/docling_v1/right_to_left_02.json Normal file
View File

File diff suppressed because one or more lines are too long

11
tests/data/groundtruth/docling_v1/right_to_left_02.md Normal file
View File

@ -0,0 +1,11 @@
11
،هيلعو ملا ةوا رملا لاول خواهييع ووص عضت ةيرص م لا ةموكح لا نإف ةو اب لأا نم ددي قي حت ىاي لمعلخب خال ةير وام جلا سي ئر د يسلا فياكت ا دو ه :خاسعر ىاي ويولولأا ةومئخق سعر ىا ي يرصملا نخسنلإا ءخهب فام عضو ، تخ ووومن تحدووعم قووي حت ىوو اي لو وم علا ،ليوواعللاو ةحووصلا تحخووجم اووف ةووصخل ىوووواي خوووو حلا ا وووو و ،تخوووو ي خل لا فوووواذع اووووف ةامخوووو و ةمادلووووسمو ةوووويوق وو يلودلاو ةوويمياقلإا تخيدوو حلل ا ءوووض اووف يرووصملا امووو لا نووملأا تاددووحم ،ة وو ام ةووعبخلم رارملووساو ،ةيووسخيسلا ة رخوواملا ر ي وو و لت د ووواو ةاووصاومو تخ ايوووو لاو ةوووفخ لا تخووو ام ريوووولت ، خوووهرلإا ةوووحفخ كمو ر ار لوووسحاو نوووملأا لي هخووو م وووسري ي ووولا وووو حهل ا ىووواي لدووولعملا اهيدووو لا خووولبلاو ،اه،وووولا .اعملجملا ماسلاو ةه،اوملا
رول لا لاول ةيرو ص م لا ةو موكحلا امخونرب دالوسي ،قبس خمل خً فوو 2024( -)2026 اتلآا وحهلا ىاي اهو ،ةسيئر ةيجيتارلسا اد هع ةعبرع قي حت :
نــــــــم ما ةــــــــيا م رـ صم لا يم وقل ا اــــسن ا ءاــــ نب رــــــــــــــــــــصم لا عاـــــصت ا ءاـــــ نب يــــــــــــــــــــــسبا نت قتسظا ق يقحت را ر يــــــــــــــــــــــــساي سلا
خهلوسحخب امخونرب لا ت خفدالوسم ديدحت لت دق هن ع ىلإ رخ لإا ردجت لكواب د روووصم ةو ووي ر تخ فدال ووو س م ىووو اي سيوووئر 2023 ر اوو وو حلا تخووو ساو تخيوووصوتو ، كيال ا تخ اووصيل اه،ووولا امخوونربلاو ،تارا ووو لا ت خ فدا لوو سمو ،اه،ووولا ،ةوو ي ا ةيه، ولا تخ ي جيتا رلسحا فالبمو .
<!-- image -->

1
tests/data/groundtruth/docling_v1/right_to_left_02.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

32
tests/data/groundtruth/docling_v1/right_to_left_03.doctags.txt Normal file
View File

@ -0,0 +1,32 @@
<document>
<subtitle-level-1><location><page_1><loc_12><loc_90><loc_45><loc_93></location>یلخاد یلااک - یلصا رازاب رد شريذپ همانديما</subtitle-level-1>
<figure>
<location><page_1><loc_65><loc_88><loc_81><loc_96></location>
</figure>
<subtitle-level-1><location><page_1><loc_63><loc_81><loc_81><loc_84></location>لااک درادناتسا -2-5</subtitle-level-1>
<paragraph><location><page_1><loc_77><loc_79><loc_87><loc_81></location>درادناتسا مان</paragraph>
<paragraph><location><page_1><loc_11><loc_75><loc_44><loc_81></location>یرگ هتخير شور هب هدش ديلوت لاشمش و هشمش فرصم دروم هتسويپ یا هزاس یاهدلاوف رد - قباطم تسويپ زيلانآ</paragraph>
<paragraph><location><page_1><loc_71><loc_72><loc_87><loc_74></location>یلم درادناتسا هرامش</paragraph>
<paragraph><location><page_1><loc_40><loc_73><loc_45><loc_74></location>20300</paragraph>
<paragraph><location><page_1><loc_68><loc_70><loc_87><loc_72></location>؟تسا یرابجا درادناتسا</paragraph>
<paragraph><location><page_1><loc_65><loc_67><loc_87><loc_69></location>درادناتسا هدننکرداص عجرم</paragraph>
<paragraph><location><page_1><loc_28><loc_67><loc_44><loc_69></location>ناريا درادناتسا یلم نامزاس</paragraph>
<paragraph><location><page_1><loc_49><loc_62><loc_87><loc_66></location>ذخا ار روکذم درادناتسا ،لوصحم هدننکديلوت ايآ ؟تسا هدومن</paragraph>
<subtitle-level-1><location><page_1><loc_69><loc_56><loc_85><loc_58></location>سروب رد شريذپ -3</subtitle-level-1>
<paragraph><location><page_1><loc_68><loc_54><loc_83><loc_56></location>کرادم هئارا خيرات</paragraph>
<paragraph><location><page_1><loc_23><loc_54><loc_32><loc_56></location>1403/09/19</paragraph>
<paragraph><location><page_1><loc_72><loc_51><loc_83><loc_53></location>شريذپ خيرات</paragraph>
<paragraph><location><page_1><loc_23><loc_51><loc_32><loc_53></location>1403/10/04</paragraph>
<paragraph><location><page_1><loc_62><loc_48><loc_83><loc_50></location>هضرع هتيمک هسلج هرامش</paragraph>
<paragraph><location><page_1><loc_26><loc_49><loc_29><loc_50></location>436</paragraph>
<paragraph><location><page_1><loc_67><loc_45><loc_83><loc_47></location>همانديما جرد خيرات</paragraph>
<paragraph><location><page_1><loc_23><loc_46><loc_32><loc_48></location>1403/10/05</paragraph>
<paragraph><location><page_1><loc_71><loc_43><loc_83><loc_45></location>شريذپ رواشم</paragraph>
<paragraph><location><page_1><loc_21><loc_43><loc_34><loc_45></location>سروب نومرآ یرازگراک</paragraph>
<paragraph><location><page_1><loc_47><loc_37><loc_83><loc_42></location>رد لااک شريذپ زا سپ هياپ تميق نييعت ةوحن سروب</paragraph>
<paragraph><location><page_1><loc_18><loc_40><loc_36><loc_42></location>یناهج یاه تميق ساسا رب</paragraph>
<paragraph><location><page_1><loc_45><loc_32><loc_83><loc_37></location>شورف /شورف لک /ديلوت زا هضرع دصرد لقادح یلخاد</paragraph>
<paragraph><location><page_1><loc_14><loc_35><loc_40><loc_37></location>نت 47.500 اي هنايلاس ديلوت زا %50 لقادح</paragraph>
<paragraph><location><page_1><loc_68><loc_29><loc_83><loc_31></location>ليوحت زاجم یاطخ</paragraph>
<paragraph><location><page_1><loc_18><loc_30><loc_37><loc_31></location>ليوحت لباق هلومحم نيرخآ 5%</paragraph>
</document>

1
tests/data/groundtruth/docling_v1/right_to_left_03.json Normal file
View File

File diff suppressed because one or more lines are too long

55
tests/data/groundtruth/docling_v1/right_to_left_03.md Normal file
View File

@ -0,0 +1,55 @@
## یلخاد یلااک - یلصا رازاب رد شريذپ همانديما
<!-- image -->
## لااک درادناتسا -2-5
درادناتسا مان
یرگ هتخير شور هب هدش ديلوت لاشمش و هشمش فرصم دروم هتسويپ یا هزاس یاهدلاوف رد - قباطم تسويپ زيلانآ
یلم درادناتسا هرامش
20300
؟تسا یرابجا درادناتسا
درادناتسا هدننکرداص عجرم
ناريا درادناتسا یلم نامزاس
ذخا ار روکذم درادناتسا ،لوصحم هدننکديلوت ايآ ؟تسا هدومن
## سروب رد شريذپ -3
کرادم هئارا خيرات
1403/09/19
شريذپ خيرات
1403/10/04
هضرع هتيمک هسلج هرامش
436
همانديما جرد خيرات
1403/10/05
شريذپ رواشم
سروب نومرآ یرازگراک
رد لااک شريذپ زا سپ هياپ تميق نييعت ةوحن سروب
یناهج یاه تميق ساسا رب
شورف /شورف لک /ديلوت زا هضرع دصرد لقادح یلخاد
نت 47.500 اي هنايلاس ديلوت زا %50 لقادح
ليوحت زاجم یاطخ
ليوحت لباق هلومحم نيرخآ 5%

1
tests/data/groundtruth/docling_v1/right_to_left_03.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

14
tests/data/groundtruth/docling_v2/code_and_formula.doctags.txt
View File

@ -1,14 +1,16 @@
<document> <document>
<section_header_level_1><location><page_1><loc_22><loc_83><loc_45><loc_84></location>Java Code Example</section_header_level_1> <section_header_level_1><location><page_1><loc_22><loc_83><loc_52><loc_84></location>JavaScript Code Example</section_header_level_1>
<text><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text> <text><location><page_1><loc_22><loc_63><loc_78><loc_81></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
<paragraph><location><page_1><loc_39><loc_61><loc_61><loc_62></location>Listing 1: Simple Java Program</paragraph> <text><location><page_1><loc_22><loc_57><loc_78><loc_63></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,</text>
<code><location><page_1><loc_22><loc_56><loc_55><loc_60></location>public static void print() { System.out.println( "Java Code" ); }</code> <paragraph><location><page_1><loc_36><loc_55><loc_63><loc_56></location>Listing 1: Simple JavaScript Program</paragraph>
<text><location><page_1><loc_22><loc_37><loc_78><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text> <code><location><page_1><loc_22><loc_49><loc_43><loc_54></location>function add(a, b) { return a + b; } console.log(add(3, 5));</code>
<text><location><page_1><loc_22><loc_29><loc_78><loc_47></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
<text><location><page_1><loc_22><loc_23><loc_78><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,</text>
<section_header_level_1><location><page_2><loc_22><loc_84><loc_32><loc_85></location>Formula</section_header_level_1> <section_header_level_1><location><page_2><loc_22><loc_84><loc_32><loc_85></location>Formula</section_header_level_1>
<text><location><page_2><loc_22><loc_65><loc_80><loc_82></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text> <text><location><page_2><loc_22><loc_66><loc_80><loc_82></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
<text><location><page_2><loc_22><loc_58><loc_80><loc_65></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.</text> <text><location><page_2><loc_22><loc_58><loc_80><loc_65></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.</text>
<formula><location><page_2><loc_47><loc_56><loc_56><loc_57></location></formula> <formula><location><page_2><loc_47><loc_56><loc_56><loc_57></location></formula>
<text><location><page_2><loc_22><loc_38><loc_80><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text> <text><location><page_2><loc_22><loc_38><loc_80><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
<text><location><page_2><loc_22><loc_29><loc_80><loc_38></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text> <text><location><page_2><loc_22><loc_29><loc_80><loc_37></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text>
<text><location><page_2><loc_22><loc_21><loc_80><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text> <text><location><page_2><loc_22><loc_21><loc_80><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text>
</document> </document>

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

File diff suppressed because one or more lines are too long

10
tests/data/groundtruth/docling_v2/code_and_formula.md
View File

@ -1,15 +1,19 @@
## Java Code Example ## JavaScript Code Example
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
Listing 1: Simple Java Program Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,
Listing 1: Simple JavaScript Program
``` ```
public static void print() { System.out.println( "Java Code" ); } function add(a, b) { return a + b; } console.log(add(3, 5));
``` ```
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet,
## Formula ## Formula
Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.

2
tests/data/groundtruth/docling_v2/code_and_formula.pages.json
View File

File diff suppressed because one or more lines are too long

9
tests/data/groundtruth/docling_v2/right_to_left_01.doctags.txt Normal file
View File

@ -0,0 +1,9 @@
<document>
<section_header_level_1><location><page_1><loc_37><loc_89><loc_85><loc_91></location>Pythonو R ةغلب ةجمربلا للاخ نم تلاكشملا لحو ةيجاتنلإا نيسحت</section_header_level_1>
<text><location><page_1><loc_15><loc_80><loc_85><loc_87></location>Python و R ةغلب ةجمربلا ربتعت ةلاعف لولح داجيإ يف دعاستو ةيجاتنلإا ززعت نأ نكمي يتلا ةيوقلا تاودلأا نم ءاملعلاو نيللحملا ىلع لهسي امم ،تانايبلا ليلحتل ةيلاثم اهلعجت ةديرف تازيمPython و R نم لك كلتمي .تلاكشملل ناك اذإ .ةلاعفو ةعيرس ةقيرطب ةدقعم تلايلحت ءارجإ مهسي نأ نكمي تاغللا هذه مادختسا نإف ،ةيليلحت ةيلقع كيدل .لمعلا جئاتن نيسحت يف ريبك لكشب</text>
<text><location><page_1><loc_34><loc_73><loc_34><loc_75></location>ً</text>
<text><location><page_1><loc_16><loc_71><loc_85><loc_78></location>جارختساو تانايبلا نم ةلئاه تايمك ةجلاعم نكمملا نم حبصي ،ةجمربلا تاراهم عم يليلحتلا ريكفتلا عمتجي امدنع ذيفنتلPython و R مادختسا نيجمربملل نكمي .اهنم تاهجوتلاو طامنلأا ةجذمنلا لثم ،ةمدقتم ةيليلحت تايلمع ةقد رثكأ تارارق ذاختا ىلإ ا ضيأ يدؤي نأ نكمي لب ،تقولا رفوي طقف سيل اذه .ةريبكلا تانايبلا ليلحتو ةيئاصحلإا تانايبلا ىلع ةمئاق تاجاتنتسا ىلع ءانب .</text>
<text><location><page_1><loc_83><loc_71><loc_83><loc_73></location>ً</text>
<text><location><page_1><loc_15><loc_63><loc_85><loc_70></location>ليلحتلا نم ،تاقيبطتلا نم ةعساو ةعومجم معدت ةينغ تاودأو تابتكمPython و R نم لك رفوت ،كلذ ىلع ةولاع ىلع .ةفلتخملا تلاكشملل ةركتبم لولح ريوطتل تابتكملا هذه نم ةدافتسلاا نيمدختسملل نكمي .يللآا ملعتلا ىلإ ينايبلا R رفوت امنيب ،ةءافكب تانايبلا ةرادلإ Python يف pandas ةبتكم مادختسا نكمي ،لاثملا ليبس مسرلل ةيوق تاودأ .نيللحملاو نيثحابلل ةيلاثم اهلعجي امم ،يئاصحلإا ليلحتلاو ينايبلا</text>
<text><location><page_1><loc_16><loc_56><loc_85><loc_61></location>Python و R ةغلب ةجمربلا يدؤت نأ نكمي ،ةياهنلا يف ةركتبم لولح ريفوتو ةيجاتنلإا نيسحت ىلإ ةيليلحت ةيلقع عم اهل نوكت نأ نكمي ةبسانملا ةيجمربلا بيلاسلأا قيبطتو لاعف لكشب تانايبلا ليلحت ىلع ةردقلا نإ .ةدقعملا تلاكشملل .ينهملاو يصخشلا ءادلأا ىلع ىدملا ةديعب ةيباجيإ تاريثأت</text>
</document>

1
tests/data/groundtruth/docling_v2/right_to_left_01.json Normal file
View File

File diff suppressed because one or more lines are too long

13
tests/data/groundtruth/docling_v2/right_to_left_01.md Normal file
View File

@ -0,0 +1,13 @@
## Pythonو R ةغلب ةجمربلا للاخ نم تلاكشملا لحو ةيجاتنلإا نيسحت
Python و R ةغلب ةجمربلا ربتعت ةلاعف لولح داجيإ يف دعاستو ةيجاتنلإا ززعت نأ نكمي يتلا ةيوقلا تاودلأا نم ءاملعلاو نيللحملا ىلع لهسي امم ،تانايبلا ليلحتل ةيلاثم اهلعجت ةديرف تازيمPython و R نم لك كلتمي .تلاكشملل ناك اذإ .ةلاعفو ةعيرس ةقيرطب ةدقعم تلايلحت ءارجإ مهسي نأ نكمي تاغللا هذه مادختسا نإف ،ةيليلحت ةيلقع كيدل .لمعلا جئاتن نيسحت يف ريبك لكشب
ً
جارختساو تانايبلا نم ةلئاه تايمك ةجلاعم نكمملا نم حبصي ،ةجمربلا تاراهم عم يليلحتلا ريكفتلا عمتجي امدنع ذيفنتلPython و R مادختسا نيجمربملل نكمي .اهنم تاهجوتلاو طامنلأا ةجذمنلا لثم ،ةمدقتم ةيليلحت تايلمع ةقد رثكأ تارارق ذاختا ىلإ ا ضيأ يدؤي نأ نكمي لب ،تقولا رفوي طقف سيل اذه .ةريبكلا تانايبلا ليلحتو ةيئاصحلإا تانايبلا ىلع ةمئاق تاجاتنتسا ىلع ءانب .
ً
ليلحتلا نم ،تاقيبطتلا نم ةعساو ةعومجم معدت ةينغ تاودأو تابتكمPython و R نم لك رفوت ،كلذ ىلع ةولاع ىلع .ةفلتخملا تلاكشملل ةركتبم لولح ريوطتل تابتكملا هذه نم ةدافتسلاا نيمدختسملل نكمي .يللآا ملعتلا ىلإ ينايبلا R رفوت امنيب ،ةءافكب تانايبلا ةرادلإ Python يف pandas ةبتكم مادختسا نكمي ،لاثملا ليبس مسرلل ةيوق تاودأ .نيللحملاو نيثحابلل ةيلاثم اهلعجي امم ،يئاصحلإا ليلحتلاو ينايبلا
Python و R ةغلب ةجمربلا يدؤت نأ نكمي ،ةياهنلا يف ةركتبم لولح ريفوتو ةيجاتنلإا نيسحت ىلإ ةيليلحت ةيلقع عم اهل نوكت نأ نكمي ةبسانملا ةيجمربلا بيلاسلأا قيبطتو لاعف لكشب تانايبلا ليلحت ىلع ةردقلا نإ .ةدقعملا تلاكشملل .ينهملاو يصخشلا ءادلأا ىلع ىدملا ةديعب ةيباجيإ تاريثأت

1
tests/data/groundtruth/docling_v2/right_to_left_01.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

10
tests/data/groundtruth/docling_v2/right_to_left_02.doctags.txt Normal file
View File

@ -0,0 +1,10 @@
<document>
<text><location><page_1><loc_8><loc_3><loc_10><loc_4></location>11</text>
<text><location><page_1><loc_11><loc_50><loc_73><loc_75></location>،هيلعو ملا ةوا رملا لاول خواهييع ووص عضت ةيرص م لا ةموكح لا نإف ةو اب لأا نم ددي قي حت ىاي لمعلخب خال ةير وام جلا سي ئر د يسلا فياكت ا دو ه :خاسعر ىاي ويولولأا ةومئخق سعر ىا ي يرصملا نخسنلإا ءخهب فام عضو ، تخ ووومن تحدووعم قووي حت ىوو اي لو وم علا ،ليوواعللاو ةحووصلا تحخووجم اووف ةووصخل ىوووواي خوووو حلا ا وووو و ،تخوووو ي خل لا فوووواذع اووووف ةامخوووو و ةمادلووووسمو ةوووويوق وو يلودلاو ةوويمياقلإا تخيدوو حلل ا ءوووض اووف يرووصملا امووو لا نووملأا تاددووحم ،ة وو ام ةووعبخلم رارملووساو ،ةيووسخيسلا ة رخوواملا ر ي وو و لت د ووواو ةاووصاومو تخ ايوووو لاو ةوووفخ لا تخووو ام ريوووولت ، خوووهرلإا ةوووحفخ كمو ر ار لوووسحاو نوووملأا لي هخووو م وووسري ي ووولا وووو حهل ا ىووواي لدووولعملا اهيدووو لا خووولبلاو ،اه،وووولا .اعملجملا ماسلاو ةه،اوملا</text>
<text><location><page_1><loc_13><loc_45><loc_74><loc_48></location>رول لا لاول ةيرو ص م لا ةو موكحلا امخونرب دالوسي ،قبس خمل خً فوو 2024( -)2026 اتلآا وحهلا ىاي اهو ،ةسيئر ةيجيتارلسا اد هع ةعبرع قي حت :</text>
<text><location><page_1><loc_12><loc_37><loc_73><loc_40></location>نــــــــم ما ةــــــــيا م رـ صم لا يم وقل ا اــــسن ا ءاــــ نب رــــــــــــــــــــصم لا عاـــــصت ا ءاـــــ نب يــــــــــــــــــــــسبا نت قتسظا ق يقحت را ر يــــــــــــــــــــــــساي سلا</text>
<text><location><page_1><loc_12><loc_23><loc_73><loc_31></location>خهلوسحخب امخونرب لا ت خفدالوسم ديدحت لت دق هن ع ىلإ رخ لإا ردجت لكواب د روووصم ةو ووي ر تخ فدال ووو س م ىووو اي سيوووئر 2023 ر اوو وو حلا تخووو ساو تخيوووصوتو ، كيال ا تخ اووصيل اه،ووولا امخوونربلاو ،تارا ووو لا ت خ فدا لوو سمو ،اه،ووولا ،ةوو ي ا ةيه، ولا تخ ي جيتا رلسحا فالبمو .</text>
<figure>
<location><page_1><loc_75><loc_23><loc_100><loc_76></location>
</figure>
</document>

1
tests/data/groundtruth/docling_v2/right_to_left_02.json Normal file
View File

File diff suppressed because one or more lines are too long

11
tests/data/groundtruth/docling_v2/right_to_left_02.md Normal file
View File

@ -0,0 +1,11 @@
11
،هيلعو ملا ةوا رملا لاول خواهييع ووص عضت ةيرص م لا ةموكح لا نإف ةو اب لأا نم ددي قي حت ىاي لمعلخب خال ةير وام جلا سي ئر د يسلا فياكت ا دو ه :خاسعر ىاي ويولولأا ةومئخق سعر ىا ي يرصملا نخسنلإا ءخهب فام عضو ، تخ ووومن تحدووعم قووي حت ىوو اي لو وم علا ،ليوواعللاو ةحووصلا تحخووجم اووف ةووصخل ىوووواي خوووو حلا ا وووو و ،تخوووو ي خل لا فوووواذع اووووف ةامخوووو و ةمادلووووسمو ةوووويوق وو يلودلاو ةوويمياقلإا تخيدوو حلل ا ءوووض اووف يرووصملا امووو لا نووملأا تاددووحم ،ة وو ام ةووعبخلم رارملووساو ،ةيووسخيسلا ة رخوواملا ر ي وو و لت د ووواو ةاووصاومو تخ ايوووو لاو ةوووفخ لا تخووو ام ريوووولت ، خوووهرلإا ةوووحفخ كمو ر ار لوووسحاو نوووملأا لي هخووو م وووسري ي ووولا وووو حهل ا ىووواي لدووولعملا اهيدووو لا خووولبلاو ،اه،وووولا .اعملجملا ماسلاو ةه،اوملا
رول لا لاول ةيرو ص م لا ةو موكحلا امخونرب دالوسي ،قبس خمل خً فوو 2024( -)2026 اتلآا وحهلا ىاي اهو ،ةسيئر ةيجيتارلسا اد هع ةعبرع قي حت :
نــــــــم ما ةــــــــيا م رـ صم لا يم وقل ا اــــسن ا ءاــــ نب رــــــــــــــــــــصم لا عاـــــصت ا ءاـــــ نب يــــــــــــــــــــــسبا نت قتسظا ق يقحت را ر يــــــــــــــــــــــــساي سلا
خهلوسحخب امخونرب لا ت خفدالوسم ديدحت لت دق هن ع ىلإ رخ لإا ردجت لكواب د روووصم ةو ووي ر تخ فدال ووو س م ىووو اي سيوووئر 2023 ر اوو وو حلا تخووو ساو تخيوووصوتو ، كيال ا تخ اووصيل اه،ووولا امخوونربلاو ،تارا ووو لا ت خ فدا لوو سمو ،اه،ووولا ،ةوو ي ا ةيه، ولا تخ ي جيتا رلسحا فالبمو .
<!-- image -->

1
tests/data/groundtruth/docling_v2/right_to_left_02.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

35
tests/data/groundtruth/docling_v2/right_to_left_03.doctags.txt Normal file
View File

@ -0,0 +1,35 @@
<document>
<section_header_level_1><location><page_1><loc_12><loc_90><loc_45><loc_93></location>یلخاد یلااک - یلصا رازاب رد شريذپ همانديما</section_header_level_1>
<figure>
<location><page_1><loc_65><loc_88><loc_81><loc_96></location>
</figure>
<section_header_level_1><location><page_1><loc_63><loc_81><loc_81><loc_84></location>لااک درادناتسا -2-5</section_header_level_1>
<text><location><page_1><loc_77><loc_79><loc_87><loc_81></location>درادناتسا مان</text>
<text><location><page_1><loc_11><loc_75><loc_44><loc_81></location>یرگ هتخير شور هب هدش ديلوت لاشمش و هشمش فرصم دروم هتسويپ یا هزاس یاهدلاوف رد - قباطم تسويپ زيلانآ</text>
<text><location><page_1><loc_71><loc_72><loc_87><loc_74></location>یلم درادناتسا هرامش</text>
<text><location><page_1><loc_40><loc_73><loc_45><loc_74></location>20300</text>
<text><location><page_1><loc_68><loc_70><loc_87><loc_72></location>؟تسا یرابجا درادناتسا</text>
<checkbox_unselected><location><page_1><loc_33><loc_70><loc_44><loc_72></location>ريخ یلب</checkbox_unselected>
<text><location><page_1><loc_65><loc_67><loc_87><loc_69></location>درادناتسا هدننکرداص عجرم</text>
<text><location><page_1><loc_28><loc_67><loc_44><loc_69></location>ناريا درادناتسا یلم نامزاس</text>
<text><location><page_1><loc_49><loc_62><loc_87><loc_66></location>ذخا ار روکذم درادناتسا ،لوصحم هدننکديلوت ايآ ؟تسا هدومن</text>
<checkbox_selected><location><page_1><loc_33><loc_65><loc_35><loc_66></location>ريخ</checkbox_selected>
<checkbox_unselected><location><page_1><loc_40><loc_65><loc_42><loc_66></location>یلب</checkbox_unselected>
<section_header_level_1><location><page_1><loc_69><loc_56><loc_85><loc_58></location>سروب رد شريذپ -3</section_header_level_1>
<text><location><page_1><loc_68><loc_54><loc_83><loc_56></location>کرادم هئارا خيرات</text>
<text><location><page_1><loc_23><loc_54><loc_32><loc_56></location>1403/09/19</text>
<text><location><page_1><loc_72><loc_51><loc_83><loc_53></location>شريذپ خيرات</text>
<text><location><page_1><loc_23><loc_51><loc_32><loc_53></location>1403/10/04</text>
<text><location><page_1><loc_62><loc_48><loc_83><loc_50></location>هضرع هتيمک هسلج هرامش</text>
<text><location><page_1><loc_26><loc_49><loc_29><loc_50></location>436</text>
<text><location><page_1><loc_67><loc_45><loc_83><loc_47></location>همانديما جرد خيرات</text>
<text><location><page_1><loc_23><loc_46><loc_32><loc_48></location>1403/10/05</text>
<text><location><page_1><loc_71><loc_43><loc_83><loc_45></location>شريذپ رواشم</text>
<text><location><page_1><loc_21><loc_43><loc_34><loc_45></location>سروب نومرآ یرازگراک</text>
<text><location><page_1><loc_47><loc_37><loc_83><loc_42></location>رد لااک شريذپ زا سپ هياپ تميق نييعت ةوحن سروب</text>
<text><location><page_1><loc_18><loc_40><loc_36><loc_42></location>یناهج یاه تميق ساسا رب</text>
<text><location><page_1><loc_45><loc_32><loc_83><loc_37></location>شورف /شورف لک /ديلوت زا هضرع دصرد لقادح یلخاد</text>
<text><location><page_1><loc_14><loc_35><loc_40><loc_37></location>نت 47.500 اي هنايلاس ديلوت زا %50 لقادح</text>
<text><location><page_1><loc_68><loc_29><loc_83><loc_31></location>ليوحت زاجم یاطخ</text>
<text><location><page_1><loc_18><loc_30><loc_37><loc_31></location>ليوحت لباق هلومحم نيرخآ 5%</text>
</document>

1
tests/data/groundtruth/docling_v2/right_to_left_03.json Normal file
View File

File diff suppressed because one or more lines are too long

61
tests/data/groundtruth/docling_v2/right_to_left_03.md Normal file
View File

@ -0,0 +1,61 @@
## یلخاد یلااک - یلصا رازاب رد شريذپ همانديما
<!-- image -->
## لااک درادناتسا -2-5
درادناتسا مان
یرگ هتخير شور هب هدش ديلوت لاشمش و هشمش فرصم دروم هتسويپ یا هزاس یاهدلاوف رد - قباطم تسويپ زيلانآ
یلم درادناتسا هرامش
20300
؟تسا یرابجا درادناتسا
ريخ یلب
درادناتسا هدننکرداص عجرم
ناريا درادناتسا یلم نامزاس
ذخا ار روکذم درادناتسا ،لوصحم هدننکديلوت ايآ ؟تسا هدومن
ريخ
یلب
## سروب رد شريذپ -3
کرادم هئارا خيرات
1403/09/19
شريذپ خيرات
1403/10/04
هضرع هتيمک هسلج هرامش
436
همانديما جرد خيرات
1403/10/05
شريذپ رواشم
سروب نومرآ یرازگراک
رد لااک شريذپ زا سپ هياپ تميق نييعت ةوحن سروب
یناهج یاه تميق ساسا رب
شورف /شورف لک /ديلوت زا هضرع دصرد لقادح یلخاد
نت 47.500 اي هنايلاس ديلوت زا %50 لقادح
ليوحت زاجم یاطخ
ليوحت لباق هلومحم نيرخآ 5%

1
tests/data/groundtruth/docling_v2/right_to_left_03.pages.json Normal file
View File

File diff suppressed because one or more lines are too long

0
tests/data/2203.01017v2.pdf → tests/data/pdf/2203.01017v2.pdf
View File

0
tests/data/2206.01062.pdf → tests/data/pdf/2206.01062.pdf
View File

0
tests/data/2305.03393v1-pg9.pdf → tests/data/pdf/2305.03393v1-pg9.pdf
View File

0
tests/data/2305.03393v1.pdf → tests/data/pdf/2305.03393v1.pdf
View File

0
tests/data/amt_handbook_sample.pdf → tests/data/pdf/amt_handbook_sample.pdf
View File

BIN
tests/data/pdf/code_and_formula.pdf Normal file
View File

Binary file not shown.

0
tests/data/picture_classification.pdf → tests/data/pdf/picture_classification.pdf
View File

0
tests/data/redp5110_sampled.pdf → tests/data/pdf/redp5110_sampled.pdf
View File

BIN
tests/data/pdf/right_to_left_01.pdf Normal file
View File

Binary file not shown.

BIN
tests/data/pdf/right_to_left_02.pdf Normal file
View File

Binary file not shown.

BIN
tests/data/pdf/right_to_left_03.pdf Normal file
View File

Binary file not shown.

2
tests/test_backend_asciidoc.py
View File

@ -20,7 +20,7 @@ def _get_backend(fname):
def test_asciidocs_examples(): def test_asciidocs_examples():
fnames = sorted(glob.glob("./tests/data/*.asciidoc")) fnames = sorted(glob.glob("./tests/data/asciidoc/*.asciidoc"))
for fname in fnames: for fname in fnames:
print(f"reading {fname}") print(f"reading {fname}")

4
tests/test_backend_docling_parse.py
View File

@ -13,7 +13,7 @@ from docling.datamodel.document import InputDocument
@pytest.fixture @pytest.fixture
def test_doc_path(): def test_doc_path():
return Path("./tests/data/2206.01062.pdf") return Path("./tests/data/pdf/2206.01062.pdf")
def _get_backend(pdf_doc): def _get_backend(pdf_doc):
@ -28,7 +28,7 @@ def _get_backend(pdf_doc):
def test_text_cell_counts(): def test_text_cell_counts():
pdf_doc = Path("./tests/data/redp5110_sampled.pdf") pdf_doc = Path("./tests/data/pdf/redp5110_sampled.pdf")
doc_backend = _get_backend(pdf_doc) doc_backend = _get_backend(pdf_doc)

4
tests/test_backend_docling_parse_v2.py
View File

@ -12,7 +12,7 @@ from docling.datamodel.document import InputDocument
@pytest.fixture @pytest.fixture
def test_doc_path(): def test_doc_path():
return Path("./tests/data/2206.01062.pdf") return Path("./tests/data/pdf/2206.01062.pdf")
def _get_backend(pdf_doc): def _get_backend(pdf_doc):
@ -27,7 +27,7 @@ def _get_backend(pdf_doc):
def test_text_cell_counts(): def test_text_cell_counts():
pdf_doc = Path("./tests/data/redp5110_sampled.pdf") pdf_doc = Path("./tests/data/pdf/redp5110_sampled.pdf")
doc_backend = _get_backend(pdf_doc) doc_backend = _get_backend(pdf_doc)

4
tests/test_backend_pdfium.py
View File

@ -13,7 +13,7 @@ from docling.datamodel.document import InputDocument
@pytest.fixture @pytest.fixture
def test_doc_path(): def test_doc_path():
return Path("./tests/data/2206.01062.pdf") return Path("./tests/data/pdf/2206.01062.pdf")
def _get_backend(pdf_doc): def _get_backend(pdf_doc):
@ -28,7 +28,7 @@ def _get_backend(pdf_doc):
def test_text_cell_counts(): def test_text_cell_counts():
pdf_doc = Path("./tests/data/redp5110_sampled.pdf") pdf_doc = Path("./tests/data/pdf/redp5110_sampled.pdf")
doc_backend = _get_backend(pdf_doc) doc_backend = _get_backend(pdf_doc)

2
tests/test_cli.py
View File

@ -18,7 +18,7 @@ def test_cli_version():
def test_cli_convert(tmp_path): def test_cli_convert(tmp_path):
source = "./tests/data/2305.03393v1-pg9.pdf" source = "./tests/data/pdf/2305.03393v1-pg9.pdf"
output = tmp_path / "out" output = tmp_path / "out"
output.mkdir() output.mkdir()
result = runner.invoke(app, [source, "--output", str(output)]) result = runner.invoke(app, [source, "--output", str(output)])

6
tests/test_code_formula.py
View File

@ -36,7 +36,7 @@ def get_converter():
def test_code_and_formula_conversion(): def test_code_and_formula_conversion():
pdf_path = Path("tests/data/code_and_formula.pdf") pdf_path = Path("tests/data/pdf/code_and_formula.pdf")
converter = get_converter() converter = get_converter()
print(f"converting {pdf_path}") print(f"converting {pdf_path}")
@ -48,11 +48,11 @@ def test_code_and_formula_conversion():
code_blocks = [el for el in results if isinstance(el, CodeItem)] code_blocks = [el for el in results if isinstance(el, CodeItem)]
assert len(code_blocks) == 1 assert len(code_blocks) == 1
gt = 'public static void print() {\n System.out.println("Java Code");\n}' gt = "function add(a, b) {\n return a + b;\n}\nconsole.log(add(3, 5));"
predicted = code_blocks[0].text.strip() predicted = code_blocks[0].text.strip()
assert predicted == gt, f"mismatch in text {predicted=}, {gt=}" assert predicted == gt, f"mismatch in text {predicted=}, {gt=}"
assert code_blocks[0].code_language == CodeLanguageLabel.JAVA assert code_blocks[0].code_language == CodeLanguageLabel.JAVASCRIPT
formula_blocks = [ formula_blocks = [
el el

2
tests/test_document_picture_classifier.py
View File

@ -37,7 +37,7 @@ def get_converter():
def test_picture_classifier(): def test_picture_classifier():
pdf_path = Path("tests/data/picture_classification.pdf") pdf_path = Path("tests/data/pdf/picture_classification.pdf")
converter = get_converter() converter = get_converter()
print(f"converting {pdf_path}") print(f"converting {pdf_path}")

2
tests/test_e2e_conversion.py
View File

@ -15,7 +15,7 @@ GENERATE_V2 = False
def get_pdf_paths(): def get_pdf_paths():
# Define the directory you want to search # Define the directory you want to search
directory = Path("./tests/data") directory = Path("./tests/data/pdf/")
# List all PDF files in the directory and its subdirectories # List all PDF files in the directory and its subdirectories
pdf_files = sorted(directory.rglob("*.pdf")) pdf_files = sorted(directory.rglob("*.pdf"))

10
tests/test_input_doc.py
View File

@ -9,7 +9,7 @@ from docling.datamodel.settings import DocumentLimits
def test_in_doc_from_valid_path(): def test_in_doc_from_valid_path():
test_doc_path = Path("./tests/data/2206.01062.pdf") test_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
doc = _make_input_doc(test_doc_path) doc = _make_input_doc(test_doc_path)
assert doc.valid == True assert doc.valid == True
@ -24,7 +24,7 @@ def test_in_doc_from_invalid_path():
def test_in_doc_from_valid_buf(): def test_in_doc_from_valid_buf():
buf = BytesIO(Path("./tests/data/2206.01062.pdf").open("rb").read()) buf = BytesIO(Path("./tests/data/pdf/2206.01062.pdf").open("rb").read())
stream = DocumentStream(name="my_doc.pdf", stream=buf) stream = DocumentStream(name="my_doc.pdf", stream=buf)
doc = _make_input_doc_from_stream(stream) doc = _make_input_doc_from_stream(stream)
@ -41,7 +41,7 @@ def test_in_doc_from_invalid_buf():
def test_in_doc_with_page_range(): def test_in_doc_with_page_range():
test_doc_path = Path("./tests/data/2206.01062.pdf") test_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
limits = DocumentLimits() limits = DocumentLimits()
limits.page_range = (1, 10) limits.page_range = (1, 10)
@ -81,10 +81,10 @@ def test_guess_format(tmp_path):
temp_dir.mkdir() temp_dir.mkdir()
# Valid PDF # Valid PDF
buf = BytesIO(Path("./tests/data/2206.01062.pdf").open("rb").read()) buf = BytesIO(Path("./tests/data/pdf/2206.01062.pdf").open("rb").read())
stream = DocumentStream(name="my_doc.pdf", stream=buf) stream = DocumentStream(name="my_doc.pdf", stream=buf)
assert dci._guess_format(stream) == InputFormat.PDF assert dci._guess_format(stream) == InputFormat.PDF
doc_path = Path("./tests/data/2206.01062.pdf") doc_path = Path("./tests/data/pdf/2206.01062.pdf")
assert dci._guess_format(doc_path) == InputFormat.PDF assert dci._guess_format(doc_path) == InputFormat.PDF
# Valid MS Office # Valid MS Office

2
tests/test_interfaces.py
View File

@ -15,7 +15,7 @@ GENERATE = False
def get_pdf_path(): def get_pdf_path():
pdf_path = Path("./tests/data/2305.03393v1-pg9.pdf") pdf_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf")
return pdf_path return pdf_path

2
tests/test_invalid_input.py
View File

@ -9,7 +9,7 @@ from docling.document_converter import ConversionError, DocumentConverter
def get_pdf_path(): def get_pdf_path():
pdf_path = Path("./tests/data/2305.03393v1-pg9.pdf") pdf_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf")
return pdf_path return pdf_path

2
tests/test_legacy_format_transform.py
View File

@ -16,7 +16,7 @@ def test_doc_paths():
Path("tests/data/docx/lorem_ipsum.docx"), Path("tests/data/docx/lorem_ipsum.docx"),
Path("tests/data/pptx/powerpoint_sample.pptx"), Path("tests/data/pptx/powerpoint_sample.pptx"),
Path("tests/data/2305.03393v1-pg9-img.png"), Path("tests/data/2305.03393v1-pg9-img.png"),
Path("tests/data/2206.01062.pdf"), Path("tests/data/pdf/2206.01062.pdf"),
] ]

2
tests/test_options.py
View File

@ -17,7 +17,7 @@ from docling.document_converter import DocumentConverter, PdfFormatOption
@pytest.fixture @pytest.fixture
def test_doc_path(): def test_doc_path():
return Path("./tests/data/2206.01062.pdf") return Path("./tests/data/pdf/2206.01062.pdf")
def get_converters_with_table_options(): def get_converters_with_table_options():

12
tests/verify_utils.py
View File

@ -249,7 +249,13 @@ def verify_conversion_result_v1(
doc_pred_dt = doc_result.legacy_document.export_to_document_tokens() doc_pred_dt = doc_result.legacy_document.export_to_document_tokens()
engine_suffix = "" if ocr_engine is None else f".{ocr_engine}" engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"
gt_subpath = input_path.parent / "groundtruth" / "docling_v1" / input_path.name gt_subpath = input_path.parent / "groundtruth" / "docling_v1" / input_path.name
if str(input_path.parent).endswith("pdf"):
gt_subpath = (
input_path.parent.parent / "groundtruth" / "docling_v1" / input_path.name
)
pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json") pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json")
json_path = gt_subpath.with_suffix(f"{engine_suffix}.json") json_path = gt_subpath.with_suffix(f"{engine_suffix}.json")
md_path = gt_subpath.with_suffix(f"{engine_suffix}.md") md_path = gt_subpath.with_suffix(f"{engine_suffix}.md")
@ -325,7 +331,13 @@ def verify_conversion_result_v2(
doc_pred_dt = doc_result.document.export_to_document_tokens() doc_pred_dt = doc_result.document.export_to_document_tokens()
engine_suffix = "" if ocr_engine is None else f".{ocr_engine}" engine_suffix = "" if ocr_engine is None else f".{ocr_engine}"
gt_subpath = input_path.parent / "groundtruth" / "docling_v2" / input_path.name gt_subpath = input_path.parent / "groundtruth" / "docling_v2" / input_path.name
if str(input_path.parent).endswith("pdf"):
gt_subpath = (
input_path.parent.parent / "groundtruth" / "docling_v2" / input_path.name
)
pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json") pages_path = gt_subpath.with_suffix(f"{engine_suffix}.pages.json")
json_path = gt_subpath.with_suffix(f"{engine_suffix}.json") json_path = gt_subpath.with_suffix(f"{engine_suffix}.json")
md_path = gt_subpath.with_suffix(f"{engine_suffix}.md") md_path = gt_subpath.with_suffix(f"{engine_suffix}.md")