opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-24 23:10:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: recovert the lang option in tools/cli.py

Browse Source
This commit is contained in:
icecraft
2024-09-12 17:14:17 +08:00
parent eda8fc119e
commit 78bdf53ee4
1 changed files with 0 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/tools/common.py
-13
View File
@@ -44,10 +44,7 @@ def do_parse(
f_draw_model_bbox=False,
start_page_id=0,
end_page_id=None,
<<<<<<< HEAD
lang=None,
=======
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
):
if debug_able:
logger.warning('debug mode is on')
@@ -65,7 +62,6 @@ def do_parse(
if parse_method == 'auto':
jso_useful_key = {'_pdf_type': '', 'model_list': model_list}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True,
<<<<<<< HEAD
start_page_id=start_page_id, end_page_id=end_page_id, lang=lang)
elif parse_method == 'txt':
pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True,
@@ -73,15 +69,6 @@ def do_parse(
elif parse_method == 'ocr':
pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id, lang=lang)
=======
start_page_id=start_page_id, end_page_id=end_page_id)
elif parse_method == 'txt':
pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id)
elif parse_method == 'ocr':
pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id)
>>>>>>> 0140d7d271ac3b1561ca2272030e9e038b469999
else:
logger.error('unknown parse method')
exit(1)