mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-31 14:34:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: remove old code from custom_convert.py

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-11-04 09:39:28 +01:00
parent 244ca69cfd
commit e1865fb519
1 changed files with 41 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
docs/examples/custom_convert.py
View File

@ -3,9 +3,12 @@ import logging
import time import time
from pathlib import Path from pathlib import Path
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
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
from docling.document_converter import DocumentConverter, PdfFormatOption from docling.document_converter import DocumentConverter, PdfFormatOption
from docling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
from docling.models.tesseract_ocr_model import TesseractOcrOptions
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
@ -23,32 +26,51 @@ def main():
# PyPdfium without EasyOCR # PyPdfium without EasyOCR
# -------------------- # --------------------
# pipeline_options = PipelineOptions() # pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr=False # pipeline_options.do_ocr = False
# pipeline_options.do_table_structure=True # pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = False # pipeline_options.table_structure_options.do_cell_matching = False
# doc_converter = DocumentConverter( # doc_converter = DocumentConverter(
# pipeline_options=pipeline_options, # format_options={
# pdf_backend=PyPdfiumDocumentBackend, # InputFormat.PDF: PdfFormatOption(
# pipeline_options=pipeline_options, backend=PyPdfiumDocumentBackend
# )
# }
# ) # )
# PyPdfium with EasyOCR # PyPdfium with EasyOCR
# ----------------- # -----------------
# pipeline_options = PipelineOptions() # pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr=True # pipeline_options.do_ocr = True
# pipeline_options.do_table_structure=True # pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True # pipeline_options.table_structure_options.do_cell_matching = True
# doc_converter = DocumentConverter( # doc_converter = DocumentConverter(
# pipeline_options=pipeline_options, # format_options={
# pdf_backend=PyPdfiumDocumentBackend, # InputFormat.PDF: PdfFormatOption(
# pipeline_options=pipeline_options, backend=PyPdfiumDocumentBackend
# )
# }
# ) # )
# Docling Parse without EasyOCR # Docling Parse without EasyOCR
# ------------------------- # -------------------------
# pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr = False
# pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True
# doc_converter = DocumentConverter(
# format_options={
# InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
# }
# )
# Docling Parse with EasyOCR
# ----------------------
pipeline_options = PdfPipelineOptions() pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = False pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True pipeline_options.table_structure_options.do_cell_matching = True
@ -58,42 +80,32 @@ def main():
} }
) )
# Docling Parse with EasyOCR
# ----------------------
# 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,
# )
# Docling Parse with Tesseract # Docling Parse with Tesseract
# ---------------------- # ----------------------
# pipeline_options = PipelineOptions() # pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr = True # pipeline_options.do_ocr = True
# pipeline_options.do_table_structure = True # pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True # pipeline_options.table_structure_options.do_cell_matching = True
# pipeline_options.ocr_options = TesseractOcrOptions() # pipeline_options.ocr_options = TesseractOcrOptions()
# doc_converter = DocumentConverter( # doc_converter = DocumentConverter(
# pipeline_options=pipeline_options, # format_options={
# pdf_backend=DoclingParseDocumentBackend, # InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
# }
# ) # )
# Docling Parse with Tesseract CLI # Docling Parse with Tesseract CLI
# ---------------------- # ----------------------
# pipeline_options = PipelineOptions() # pipeline_options = PdfPipelineOptions()
# pipeline_options.do_ocr = True # pipeline_options.do_ocr = True
# pipeline_options.do_table_structure = True # pipeline_options.do_table_structure = True
# pipeline_options.table_structure_options.do_cell_matching = True # pipeline_options.table_structure_options.do_cell_matching = True
# pipeline_options.ocr_options = TesseractCliOcrOptions() # pipeline_options.ocr_options = TesseractCliOcrOptions()
# doc_converter = DocumentConverter( # doc_converter = DocumentConverter(
# pipeline_options=pipeline_options, # format_options={
# pdf_backend=DoclingParseDocumentBackend, # InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
# }
# ) # )
########################################################################### ###########################################################################