mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
OCR tests use DPv1 until rotation bugs are fixed
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
parent
8a9228a9a2
commit
460b247b66
@ -2,6 +2,10 @@ import sys
|
|||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from typing import List, Tuple
|
from typing import List, Tuple
|
||||||
|
|
||||||
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
||||||
|
from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
|
||||||
|
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
|
||||||
|
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
||||||
from docling.datamodel.accelerator_options import AcceleratorDevice
|
from docling.datamodel.accelerator_options import AcceleratorDevice
|
||||||
from docling.datamodel.base_models import InputFormat
|
from docling.datamodel.base_models import InputFormat
|
||||||
from docling.datamodel.document import ConversionResult
|
from docling.datamodel.document import ConversionResult
|
||||||
@ -43,7 +47,7 @@ def get_converter(ocr_options: OcrOptions):
|
|||||||
format_options={
|
format_options={
|
||||||
InputFormat.PDF: PdfFormatOption(
|
InputFormat.PDF: PdfFormatOption(
|
||||||
pipeline_options=pipeline_options,
|
pipeline_options=pipeline_options,
|
||||||
backend=PdfFormatOption().backend,
|
backend=DoclingParseDocumentBackend, # PdfFormatOption().backend,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
)
|
)
|
||||||
|
Loading…
Reference in New Issue
Block a user