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

disable s3 test

Browse Source
This commit is contained in:
myhloli
2024-07-12 13:43:15 +08:00
parent d458b705aa
commit 46bcddf4f2
1 changed files with 25 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_cli/test_cli.py
+25 -25
View File
@@ -19,32 +19,32 @@ class TestCli:
#common.count_folders_and_check_contents(pdf_res_path)
def test_pdf_specify_jsonl(self):
"""
输入jsonl, 默认方式解析
"""
cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972'" % (code_path)
logging.info(cmd)
common.check_shell(cmd)
#common.count_folders_and_check_contents(pdf_res_path)
# def test_pdf_specify_jsonl(self):
# """
# 输入jsonl, 默认方式解析
# """
# cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972'" % (code_path)
# logging.info(cmd)
# common.check_shell(cmd)
# #common.count_folders_and_check_contents(pdf_res_path)
def test_pdf_specify_jsonl_txt(self):
"""
输入jsonl, txt方式解析
"""
cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972' --method txt" % (code_path)
logging.info(cmd)
common.check_shell(cmd)
#common.count_folders_and_check_contents(pdf_res_path)
def test_pdf_specify_jsonl_ocr(self):
"""
输入jsonl, ocr方式解析
"""
cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972' --method ocr" % (code_path)
logging.info(cmd)
common.check_shell(cmd)
#common.count_folders_and_check_contents(pdf_res_path)
# def test_pdf_specify_jsonl_txt(self):
# """
# 输入jsonl, txt方式解析
# """
# cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972' --method txt" % (code_path)
# logging.info(cmd)
# common.check_shell(cmd)
# #common.count_folders_and_check_contents(pdf_res_path)
#
# def test_pdf_specify_jsonl_ocr(self):
# """
# 输入jsonl, ocr方式解析
# """
# cmd = "cd %s && export PYTHONPATH=. && python magic_pdf/cli/magicpdf.py json-command --json 's3://llm-process-pperf/ebook_index_textbook_40k/中高考&竞赛知识点/part-663f1ef5e7c1-009416.jsonl?bytes=0,1133972' --method ocr" % (code_path)
# logging.info(cmd)
# common.check_shell(cmd)
# #common.count_folders_and_check_contents(pdf_res_path)
if __name__ == "__main__":