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

fix: fix OCR setting for pypdfium, minor refactor (#102)

Browse Source 
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Panos Vagenas 2024-09-24 14:36:00 +02:00 committed by GitHub
parent f8f2303348
commit d96b96c848
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
docling/cli/main.py
View File

@ -9,7 +9,6 @@ from typing import Annotated, Iterable, List, Optional
import typer import typer
from docling_core.utils.file import resolve_file_source from docling_core.utils.file import resolve_file_source
from pydantic import AnyUrl
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
@ -181,58 +180,25 @@ def convert(
else: else:
input_doc_paths.append(source) input_doc_paths.append(source)
########################################################################### match backend:
case Backend.PYPDFIUM2:
do_cell_matching = ocr # only do cell matching when OCR enabled
pdf_backend = PyPdfiumDocumentBackend
case Backend.DOCLING:
do_cell_matching = True
pdf_backend = DoclingParseDocumentBackend
case _:
raise RuntimeError(f"Unexpected backend type {backend}")
# The following sections contain a combination of PipelineOptions pipeline_options = PipelineOptions(
# and PDF Backends for various configurations. do_ocr=ocr,
# Uncomment one section at the time to see the differences in the output. do_table_structure=True,
)
doc_converter = None pipeline_options.table_structure_options.do_cell_matching = do_cell_matching
if backend == Backend.PYPDFIUM2 and not ocr: # PyPdfium without OCR doc_converter = DocumentConverter(
pipeline_options = PipelineOptions() pipeline_options=pipeline_options,
pipeline_options.do_ocr = False pdf_backend=pdf_backend,
pipeline_options.do_table_structure = True )
pipeline_options.table_structure_options.do_cell_matching = False
doc_converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=PyPdfiumDocumentBackend,
)
elif backend == Backend.PYPDFIUM2.value and ocr: # PyPdfium with OCR
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
doc_converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=PyPdfiumDocumentBackend,
)
elif backend == Backend.DOCLING.value and not ocr: # Docling Parse without OCR
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
doc_converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
)
elif backend == Backend.DOCLING.value and ocr: # Docling Parse with OCR
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
doc_converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
)
###########################################################################
# Define input files # Define input files
input = DocumentConversionInput.from_paths(input_doc_paths) input = DocumentConversionInput.from_paths(input_doc_paths)