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

feat: expose ocr-lang in CLI (#375)

Browse Source 
* feat: expose ocr-lang in CLI

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

* use regex for supporting multiple sep

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

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-11-19 15:58:49 +01:00 committed by GitHub
parent 926dfd29d5
commit ed785ea122
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docling/cli/main.py
View File

@ -1,6 +1,7 @@
import importlib import importlib
import json import json
import logging import logging
import re
import time import time
import warnings import warnings
from enum import Enum from enum import Enum
@ -129,6 +130,12 @@ def export_documents(
) )
def _split_list(raw: Optional[str]) -> Optional[List[str]]:
if raw is None:
return None
return re.split(r"[;,]", raw)
@app.command(no_args_is_help=True) @app.command(no_args_is_help=True)
def convert( def convert(
input_sources: Annotated[ input_sources: Annotated[
@ -163,6 +170,13 @@ def convert(
ocr_engine: Annotated[ ocr_engine: Annotated[
OcrEngine, typer.Option(..., help="The OCR engine to use.") OcrEngine, typer.Option(..., help="The OCR engine to use.")
] = OcrEngine.EASYOCR, ] = OcrEngine.EASYOCR,
ocr_lang: Annotated[
Optional[str],
typer.Option(
...,
help="Provide a comma-separated list of languages used by the OCR engine. Note that each OCR engine has different values for the language names.",
),
] = None,
pdf_backend: Annotated[ pdf_backend: Annotated[
PdfBackend, typer.Option(..., help="The PDF backend to use.") PdfBackend, typer.Option(..., help="The PDF backend to use.")
] = PdfBackend.DLPARSE_V1, ] = PdfBackend.DLPARSE_V1,
@ -248,6 +262,10 @@ def convert(
case _: case _:
raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}") raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
ocr_lang_list = _split_list(ocr_lang)
if ocr_lang_list is not None:
ocr_options.lang = ocr_lang_list
pipeline_options = PdfPipelineOptions( pipeline_options = PdfPipelineOptions(
do_ocr=ocr, do_ocr=ocr,
ocr_options=ocr_options, ocr_options=ocr_options,

1
docling/datamodel/pipeline_options.py
View File

@ -22,6 +22,7 @@ class TableStructureOptions(BaseModel):
class OcrOptions(BaseModel): class OcrOptions(BaseModel):
kind: str kind: str
lang: List[str]
force_full_page_ocr: bool = False # If enabled a full page OCR is always applied force_full_page_ocr: bool = False # If enabled a full page OCR is always applied
bitmap_area_threshold: float = ( bitmap_area_threshold: float = (
0.05 # percentage of the area for a bitmap to processed with OCR 0.05 # percentage of the area for a bitmap to processed with OCR