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
c36ce88e
Unverified
Commit
c36ce88e
authored
Sep 12, 2024
by
Xiaomeng Zhao
Committed by
GitHub
Sep 12, 2024
Browse files
Merge pull request #604 from icecraft/fix/cli_tools
fix: recovert the lang option in tools/cli.py
parents
9b30ea20
78bdf53e
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
0 additions
and
13 deletions
+0
-13
magic_pdf/tools/common.py
magic_pdf/tools/common.py
+0
-13
No files found.
magic_pdf/tools/common.py
View file @
c36ce88e
...
@@ -44,10 +44,7 @@ def do_parse(
...
@@ -44,10 +44,7 @@ def do_parse(
f_draw_model_bbox
=
False
,
f_draw_model_bbox
=
False
,
start_page_id
=
0
,
start_page_id
=
0
,
end_page_id
=
None
,
end_page_id
=
None
,
<<<<<<<
HEAD
lang
=
None
,
lang
=
None
,
=======
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
):
):
if
debug_able
:
if
debug_able
:
logger
.
warning
(
'debug mode is on'
)
logger
.
warning
(
'debug mode is on'
)
...
@@ -65,7 +62,6 @@ def do_parse(
...
@@ -65,7 +62,6 @@ def do_parse(
if
parse_method
==
'auto'
:
if
parse_method
==
'auto'
:
jso_useful_key
=
{
'_pdf_type'
:
''
,
'model_list'
:
model_list
}
jso_useful_key
=
{
'_pdf_type'
:
''
,
'model_list'
:
model_list
}
pipe
=
UNIPipe
(
pdf_bytes
,
jso_useful_key
,
image_writer
,
is_debug
=
True
,
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
)
start_page_id
=
start_page_id
,
end_page_id
=
end_page_id
,
lang
=
lang
)
elif
parse_method
==
'txt'
:
elif
parse_method
==
'txt'
:
pipe
=
TXTPipe
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
=
True
,
pipe
=
TXTPipe
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
=
True
,
...
@@ -73,15 +69,6 @@ def do_parse(
...
@@ -73,15 +69,6 @@ def do_parse(
elif
parse_method
==
'ocr'
:
elif
parse_method
==
'ocr'
:
pipe
=
OCRPipe
(
pdf_bytes
,
model_list
,
image_writer
,
is_debug
=
True
,
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
,
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
)
>>>>>>>
0140
d7d271ac3b1561ca2272030e9e038b469999
else
:
else
:
logger
.
error
(
'unknown parse method'
)
logger
.
error
(
'unknown parse method'
)
exit
(
1
)
exit
(
1
)
...
...
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