apply pre-commit with new path

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-10-16 19:42:02 +02:00
parent 4cead1e38b
commit 4918e11cbe
7 changed files with 28 additions and 19 deletions

View File

@ -4,13 +4,13 @@ repos:
hooks: hooks:
- id: black - id: black
name: Black name: Black
entry: poetry run black docling examples tests entry: poetry run black docling docs/examples tests
pass_filenames: false pass_filenames: false
language: system language: system
files: '\.py$' files: '\.py$'
- id: isort - id: isort
name: isort name: isort
entry: poetry run isort docling examples tests entry: poetry run isort docling docs/examples tests
pass_filenames: false pass_filenames: false
language: system language: system
files: '\.py$' files: '\.py$'
@ -28,13 +28,13 @@ repos:
files: '\.py$' files: '\.py$'
- id: nbqa_black - id: nbqa_black
name: nbQA Black name: nbQA Black
entry: poetry run nbqa black examples entry: poetry run nbqa black docs/examples
pass_filenames: false pass_filenames: false
language: system language: system
files: '\.ipynb$' files: '\.ipynb$'
- id: nbqa_isort - id: nbqa_isort
name: nbQA isort name: nbQA isort
entry: poetry run nbqa isort examples entry: poetry run nbqa isort docs/examples
pass_filenames: false pass_filenames: false
language: system language: system
files: '\.ipynb$' files: '\.ipynb$'

View File

@ -1,9 +1,9 @@
import json import json
import logging import logging
import time
from pathlib import Path from pathlib import Path
from typing import Iterable from typing import Iterable
import time
import yaml import yaml
from docling.datamodel.base_models import ConversionStatus from docling.datamodel.base_models import ConversionStatus

View File

@ -1,13 +1,10 @@
import json import json
import logging import logging
import time
from pathlib import Path from pathlib import Path
import time
from docling.datamodel.base_models import InputFormat from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import ( from docling.datamodel.pipeline_options import PdfPipelineOptions
PdfPipelineOptions,
)
from docling.document_converter import DocumentConverter, PdfFormatOption from docling.document_converter import DocumentConverter, PdfFormatOption
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)

View File

@ -2,8 +2,13 @@ import logging
from pathlib import Path from pathlib import Path
from typing import Any, Iterable from typing import Any, Iterable
from docling_core.types.doc import DoclingDocument, NodeItem from docling_core.types.doc import (
from docling_core.types.doc import PictureClassificationData, PictureItem, PictureClassificationClass DoclingDocument,
NodeItem,
PictureClassificationClass,
PictureClassificationData,
PictureItem,
)
from docling.datamodel.base_models import InputFormat from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions from docling.datamodel.pipeline_options import PdfPipelineOptions
@ -36,10 +41,14 @@ class ExamplePictureClassifierEnrichmentModel(BaseEnrichmentModel):
# uncomment this to interactively visualize the image # uncomment this to interactively visualize the image
# element.image.pil_image.show() # element.image.pil_image.show()
element.annotations.append(PictureClassificationData( element.annotations.append(
PictureClassificationData(
provenance="example_classifier-0.0.1", provenance="example_classifier-0.0.1",
predicted_classes=[PictureClassificationClass(class_name="dummy", confidence=0.42)] predicted_classes=[
)) PictureClassificationClass(class_name="dummy", confidence=0.42)
],
)
)
yield element yield element

View File

@ -1,9 +1,9 @@
import datetime import datetime
import logging import logging
import time
from pathlib import Path from pathlib import Path
import pandas as pd import pandas as pd
import time
from docling.datamodel.base_models import InputFormat from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions from docling.datamodel.pipeline_options import PdfPipelineOptions

View File

@ -1,8 +1,8 @@
import logging import logging
import time
from pathlib import Path from pathlib import Path
import pandas as pd import pandas as pd
import time
from docling.document_converter import DocumentConverter from docling.document_converter import DocumentConverter

View File

@ -16,6 +16,7 @@ from docling.pipeline.standard_pdf_pipeline import StandardPdfPipeline
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
def main(): def main():
input_paths = [ input_paths = [
Path("tests/data/wiki_duck.html"), Path("tests/data/wiki_duck.html"),
@ -69,5 +70,7 @@ def main():
with (out_path / f"{res.input.file.name}.yaml").open("w") as fp: with (out_path / f"{res.input.file.name}.yaml").open("w") as fp:
fp.write(yaml.safe_dump(res.document.export_to_dict())) fp.write(yaml.safe_dump(res.document.export_to_dict()))
if __name__ == "__main__": if __name__ == "__main__":
main() main()