Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
MinerU
Commits
b7a2f547
"vscode:/vscode.git/clone" did not exist on "8eb9fb179f2730ed0d9cfc2f59410ade285d00b6"
Commit
b7a2f547
authored
May 22, 2024
by
quyuan
Browse files
skip case
parent
a6be18fb
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
tests/test_cli/test_cli.py
tests/test_cli/test_cli.py
+3
-3
No files found.
tests/test_cli/test_cli.py
View file @
b7a2f547
...
@@ -23,7 +23,7 @@ class TestCli:
...
@@ -23,7 +23,7 @@ class TestCli:
"""
"""
输入jsonl, 默认方式解析
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'"
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
)
logging
.
info
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
...
@@ -32,7 +32,7 @@ class TestCli:
...
@@ -32,7 +32,7 @@ class TestCli:
"""
"""
输入jsonl, txt方式解析
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"
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
)
logging
.
info
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
...
@@ -41,7 +41,7 @@ class TestCli:
...
@@ -41,7 +41,7 @@ class TestCli:
"""
"""
输入jsonl, ocr方式解析
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"
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
)
logging
.
info
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
check_shell
(
cmd
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
common
.
count_folders_and_check_contents
(
pdf_res_path
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment