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
4510a964
"src/graph/transform/to_block.h" did not exist on "8f0df39ee106efb665af90c61dddfdfbf4899991"
Unverified
Commit
4510a964
authored
Apr 23, 2024
by
myhloli
Committed by
GitHub
Apr 23, 2024
Browse files
Merge pull request #59 from myhloli/master
output dir by method
parents
21159040
d82d5d30
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
4 additions
and
4 deletions
+4
-4
magic_pdf/cli/magicpdf.py
magic_pdf/cli/magicpdf.py
+4
-4
No files found.
magic_pdf/cli/magicpdf.py
View file @
4510a964
...
@@ -45,9 +45,9 @@ from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
...
@@ -45,9 +45,9 @@ from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
parse_pdf_methods
=
click
.
Choice
([
"ocr"
,
"txt"
,
"auto"
])
parse_pdf_methods
=
click
.
Choice
([
"ocr"
,
"txt"
,
"auto"
])
def
prepare_env
(
pdf_file_name
):
def
prepare_env
(
pdf_file_name
,
method
):
local_parent_dir
=
os
.
path
.
join
(
local_parent_dir
=
os
.
path
.
join
(
get_local_dir
(),
"magic-pdf"
,
pdf_file_name
get_local_dir
(),
"magic-pdf"
,
pdf_file_name
,
method
)
)
local_image_dir
=
os
.
path
.
join
(
local_parent_dir
,
"images"
)
local_image_dir
=
os
.
path
.
join
(
local_parent_dir
,
"images"
)
...
@@ -131,7 +131,7 @@ def json_command(json, method):
...
@@ -131,7 +131,7 @@ def json_command(json, method):
s3_file_path
=
jso
[
"file_location"
]
s3_file_path
=
jso
[
"file_location"
]
pdf_file_name
=
Path
(
s3_file_path
).
stem
pdf_file_name
=
Path
(
s3_file_path
).
stem
pdf_data
=
read_s3_path
(
s3_file_path
)
pdf_data
=
read_s3_path
(
s3_file_path
)
local_image_dir
,
local_md_dir
=
prepare_env
(
pdf_file_name
)
local_image_dir
,
local_md_dir
=
prepare_env
(
pdf_file_name
,
method
)
local_image_rw
,
local_md_rw
=
DiskReaderWriter
(
local_image_dir
),
DiskReaderWriter
(
local_image_rw
,
local_md_rw
=
DiskReaderWriter
(
local_image_dir
),
DiskReaderWriter
(
local_md_dir
local_md_dir
...
@@ -174,7 +174,7 @@ def pdf_command(pdf, model, method):
...
@@ -174,7 +174,7 @@ def pdf_command(pdf, model, method):
pdf_data
=
read_fn
(
pdf
)
pdf_data
=
read_fn
(
pdf
)
jso
=
json_parse
.
loads
(
read_fn
(
model
).
decode
(
"utf-8"
))
jso
=
json_parse
.
loads
(
read_fn
(
model
).
decode
(
"utf-8"
))
pdf_file_name
=
Path
(
pdf
).
stem
pdf_file_name
=
Path
(
pdf
).
stem
local_image_dir
,
local_md_dir
=
prepare_env
(
pdf_file_name
)
local_image_dir
,
local_md_dir
=
prepare_env
(
pdf_file_name
,
method
)
local_image_rw
,
local_md_rw
=
DiskReaderWriter
(
local_image_dir
),
DiskReaderWriter
(
local_image_rw
,
local_md_rw
=
DiskReaderWriter
(
local_image_dir
),
DiskReaderWriter
(
local_md_dir
local_md_dir
)
)
...
...
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