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
16699a9a
Commit
16699a9a
authored
Sep 18, 2024
by
myhloli
Browse files
fix(ocr_mkcontent): streamline drop reason handling
parent
196de029
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
7 additions
and
4 deletions
+7
-4
magic_pdf/dict2md/ocr_mkcontent.py
magic_pdf/dict2md/ocr_mkcontent.py
+7
-4
No files found.
magic_pdf/dict2md/ocr_mkcontent.py
View file @
16699a9a
...
@@ -400,11 +400,14 @@ def union_make(pdf_info_dict: list,
...
@@ -400,11 +400,14 @@ def union_make(pdf_info_dict: list,
img_buket_path
:
str
=
''
):
img_buket_path
:
str
=
''
):
output_content
=
[]
output_content
=
[]
for
page_info
in
pdf_info_dict
:
for
page_info
in
pdf_info_dict
:
drop_reason
=
page_info
.
get
(
'drop_reason'
,
None
)
drop_reason_flag
=
False
drop_reason
=
None
if
page_info
.
get
(
'need_drop'
,
False
):
if
page_info
.
get
(
'need_drop'
,
False
):
#
drop_reason = page_info.get('drop_reason')
drop_reason
=
page_info
.
get
(
'drop_reason'
)
if
drop_mode
==
DropMode
.
NONE
or
drop_mode
==
DropMode
.
NONE_WITH_REASON
:
if
drop_mode
==
DropMode
.
NONE
:
pass
pass
elif
drop_mode
==
DropMode
.
NONE_WITH_REASON
:
drop_reason_flag
=
True
elif
drop_mode
==
DropMode
.
WHOLE_PDF
:
elif
drop_mode
==
DropMode
.
WHOLE_PDF
:
raise
Exception
((
f
'drop_mode is
{
DropMode
.
WHOLE_PDF
}
,'
raise
Exception
((
f
'drop_mode is
{
DropMode
.
WHOLE_PDF
}
,'
f
'drop_reason is
{
drop_reason
}
'
))
f
'drop_reason is
{
drop_reason
}
'
))
...
@@ -429,7 +432,7 @@ def union_make(pdf_info_dict: list,
...
@@ -429,7 +432,7 @@ def union_make(pdf_info_dict: list,
output_content
.
extend
(
page_markdown
)
output_content
.
extend
(
page_markdown
)
elif
make_mode
==
MakeMode
.
STANDARD_FORMAT
:
elif
make_mode
==
MakeMode
.
STANDARD_FORMAT
:
for
para_block
in
paras_of_layout
:
for
para_block
in
paras_of_layout
:
if
drop_
mode
==
DropMode
.
NONE_WITH_REASON
:
if
drop_
reason_flag
:
para_content
=
para_to_standard_format_v2
(
para_content
=
para_to_standard_format_v2
(
para_block
,
img_buket_path
,
page_idx
,
drop_reason
)
para_block
,
img_buket_path
,
page_idx
,
drop_reason
)
else
:
else
:
...
...
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