mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

use regex for supporting multiple sep

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi 2024-11-19 15:40:14 +01:00
parent e625f5d87b
commit 2a02ee83de
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
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
@ -129,10 +130,10 @@ def export_documents(
) )
def _comma_split(raw: Optional[str]) -> Optional[List[str]]: def _split_list(raw: Optional[str]) -> Optional[List[str]]:
if raw is None: if raw is None:
return None return None
return raw.split(",") return re.split(r"[;,]", raw)
@app.command(no_args_is_help=True) @app.command(no_args_is_help=True)
@ -261,7 +262,7 @@ 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 = _comma_split(ocr_lang) ocr_lang_list = _split_list(ocr_lang)
if ocr_lang_list is not None: if ocr_lang_list is not None:
ocr_options.lang = ocr_lang_list ocr_options.lang = ocr_lang_list