Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
P
pdf-miner
Project
Project
Details
Activity
Releases
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Qin Kaijie
pdf-miner
Commits
1936703b
Commit
1936703b
authored
Apr 25, 2024
by
赵小蒙
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fix remove error
parent
fcf94b2d
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
9 additions
and
6 deletions
+9
-6
ocr_detect_all_bboxes.py
magic_pdf/pre_proc/ocr_detect_all_bboxes.py
+4
-3
ocr_span_list_modify.py
magic_pdf/pre_proc/ocr_span_list_modify.py
+5
-3
No files found.
magic_pdf/pre_proc/ocr_detect_all_bboxes.py
View file @
1936703b
...
@@ -73,9 +73,9 @@ def remove_need_drop_blocks(all_bboxes, discarded_blocks):
...
@@ -73,9 +73,9 @@ def remove_need_drop_blocks(all_bboxes, discarded_blocks):
if
calculate_overlap_area_in_bbox1_area_ratio
(
block_bbox
,
discarded_block
[
'bbox'
])
>
0.6
:
if
calculate_overlap_area_in_bbox1_area_ratio
(
block_bbox
,
discarded_block
[
'bbox'
])
>
0.6
:
need_remove
.
append
(
block
)
need_remove
.
append
(
block
)
for
block
in
need_remove
:
if
len
(
need_remove
)
>
0
:
all_bboxes
.
remove
(
block
)
for
block
in
need_remove
:
all_bboxes
.
remove
(
block
)
return
all_bboxes
return
all_bboxes
...
@@ -92,6 +92,7 @@ def remove_overlaps_min_blocks(all_bboxes):
...
@@ -92,6 +92,7 @@ def remove_overlaps_min_blocks(all_bboxes):
bbox_to_remove
=
next
((
block
for
block
in
all_bboxes
if
block
[:
4
]
==
overlap_box
),
None
)
bbox_to_remove
=
next
((
block
for
block
in
all_bboxes
if
block
[:
4
]
==
overlap_box
),
None
)
if
bbox_to_remove
is
not
None
:
if
bbox_to_remove
is
not
None
:
need_remove
.
append
(
bbox_to_remove
)
need_remove
.
append
(
bbox_to_remove
)
if
len
(
need_remove
)
>
0
:
if
len
(
need_remove
)
>
0
:
for
block
in
need_remove
:
for
block
in
need_remove
:
all_bboxes
.
remove
(
block
)
all_bboxes
.
remove
(
block
)
...
...
magic_pdf/pre_proc/ocr_span_list_modify.py
View file @
1936703b
...
@@ -18,10 +18,11 @@ def remove_overlaps_min_spans(spans):
...
@@ -18,10 +18,11 @@ def remove_overlaps_min_spans(spans):
if
bbox_to_remove
is
not
None
:
if
bbox_to_remove
is
not
None
:
dropped_spans
.
append
(
bbox_to_remove
)
dropped_spans
.
append
(
bbox_to_remove
)
if
len
(
dropped_spans
>
0
)
:
if
len
(
dropped_spans
)
>
0
:
for
dropped_span
in
dropped_spans
:
for
dropped_span
in
dropped_spans
:
spans
.
remove
(
dropped_span
)
spans
.
remove
(
dropped_span
)
dropped_span
[
'tag'
]
=
DropTag
.
SPAN_OVERLAP
dropped_span
[
'tag'
]
=
DropTag
.
SPAN_OVERLAP
return
spans
,
dropped_spans
return
spans
,
dropped_spans
...
@@ -35,8 +36,9 @@ def remove_spans_by_bboxes(spans, need_remove_spans_bboxes):
...
@@ -35,8 +36,9 @@ def remove_spans_by_bboxes(spans, need_remove_spans_bboxes):
need_remove_spans
.
append
(
span
)
need_remove_spans
.
append
(
span
)
break
break
for
span
in
need_remove_spans
:
if
len
(
need_remove_spans
)
>
0
:
spans
.
remove
(
span
)
for
span
in
need_remove_spans
:
spans
.
remove
(
span
)
return
spans
return
spans
...
...
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