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
eb021e53
Commit
eb021e53
authored
Dec 06, 2024
by
dt-yy
Browse files
update yml
parent
494859c5
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
65 additions
and
21 deletions
+65
-21
.github/workflows/cli.yml
.github/workflows/cli.yml
+3
-18
.github/workflows/huigui.yml
.github/workflows/huigui.yml
+3
-3
download_models.py
download_models.py
+59
-0
No files found.
.github/workflows/cli.yml
View file @
eb021e53
...
@@ -30,7 +30,7 @@ jobs:
...
@@ -30,7 +30,7 @@ jobs:
source activate mineru
source activate mineru
conda env list
conda env list
pip show coverage
pip show coverage
#
cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
cd $GITHUB_WORKSPACE && python tests/clean_coverage.py
cd $GITHUB_WORKSPACE && python tests/clean_coverage.py
cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/ --cov-report html --cov-report term-missing
cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/ --cov-report html --cov-report term-missing
cd $GITHUB_WORKSPACE && python tests/get_coverage.py
cd $GITHUB_WORKSPACE && python tests/get_coverage.py
...
@@ -41,22 +41,7 @@ jobs:
...
@@ -41,22 +41,7 @@ jobs:
needs
:
cli-test
needs
:
cli-test
runs-on
:
pdf
runs-on
:
pdf
steps
:
steps
:
-
name
:
get_actor
run
:
|
metion_list="dt-yy"
echo $GITHUB_ACTOR
if [[ $GITHUB_ACTOR == "drunkpig" ]]; then
metion_list="xuchao"
elif [[ $GITHUB_ACTOR == "myhloli" ]]; then
metion_list="zhaoxiaomeng"
elif [[ $GITHUB_ACTOR == "icecraft" ]]; then
metion_list="xurui1"
fi
echo $metion_list
echo "METIONS=$metion_list" >> "$GITHUB_ENV"
echo ${{ env.METIONS }}
-
name
:
notify
-
name
:
notify
run
:
|
run
:
|
echo ${{ secrets.
USER_ID
}}
#
echo ${{ secrets.
WEBHOOK_URL
}}
curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}' $
{{ secrets.
WEBHOOK_URL
}}
curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}' $WEBHOOK_URL
.github/workflows/huigui.yml
View file @
eb021e53
...
@@ -29,7 +29,7 @@ jobs:
...
@@ -29,7 +29,7 @@ jobs:
source activate mineru
source activate mineru
conda env list
conda env list
pip show coverage
pip show coverage
#
cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
cd $GITHUB_WORKSPACE && sh tests/retry_env.sh
cd $GITHUB_WORKSPACE && python tests/clean_coverage.py
cd $GITHUB_WORKSPACE && python tests/clean_coverage.py
cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/ --cov-report html --cov-report term-missing
cd $GITHUB_WORKSPACE && coverage run -m pytest tests/unittest/ --cov=magic_pdf/ --cov-report html --cov-report term-missing
cd $GITHUB_WORKSPACE && python tests/get_coverage.py
cd $GITHUB_WORKSPACE && python tests/get_coverage.py
...
@@ -57,5 +57,5 @@ jobs:
...
@@ -57,5 +57,5 @@ jobs:
-
name
:
notify
-
name
:
notify
run
:
|
run
:
|
echo ${{ secrets.USER_ID }}
#
echo ${{ secrets.USER_ID }}
curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}' $
{{ secrets.
WEBHOOK_URL
}}
curl -X POST -H "Content-Type: application/json" -d '{"msg_type":"post","content":{"post":{"zh_cn":{"title":"'${{ github.repository }}' GitHubAction Failed","content":[[{"tag":"text","text":""},{"tag":"a","text":"Please click here for details ","href":"https://github.com/'${{ github.repository }}'/actions/runs/'${GITHUB_RUN_ID}'"},{"tag":"at","user_id":"'${{ secrets.USER_ID }}'"}]]}}}}' $WEBHOOK_URL
download_models.py
0 → 100644
View file @
eb021e53
import
json
import
os
import
requests
from
modelscope
import
snapshot_download
def
download_json
(
url
):
# 下载JSON文件
response
=
requests
.
get
(
url
)
response
.
raise_for_status
()
# 检查请求是否成功
return
response
.
json
()
def
download_and_modify_json
(
url
,
local_filename
,
modifications
):
if
os
.
path
.
exists
(
local_filename
):
data
=
json
.
load
(
open
(
local_filename
))
config_version
=
data
.
get
(
'config_version'
,
'0.0.0'
)
if
config_version
<
'1.0.0'
:
data
=
download_json
(
url
)
else
:
data
=
download_json
(
url
)
# 修改内容
for
key
,
value
in
modifications
.
items
():
data
[
key
]
=
value
# 保存修改后的内容
with
open
(
local_filename
,
'w'
,
encoding
=
'utf-8'
)
as
f
:
json
.
dump
(
data
,
f
,
ensure_ascii
=
False
,
indent
=
4
)
if
__name__
==
'__main__'
:
mineru_patterns
=
[
"models/Layout/LayoutLMv3/*"
,
"models/Layout/YOLO/*"
,
"models/MFD/YOLO/*"
,
"models/MFR/unimernet_small/*"
,
"models/TabRec/TableMaster/*"
,
"models/TabRec/StructEqTable/*"
,
]
model_dir
=
snapshot_download
(
'opendatalab/PDF-Extract-Kit-1.0'
,
allow_patterns
=
mineru_patterns
)
layoutreader_model_dir
=
snapshot_download
(
'ppaanngggg/layoutreader'
)
model_dir
=
model_dir
+
'/models'
print
(
f
'model_dir is:
{
model_dir
}
'
)
print
(
f
'layoutreader_model_dir is:
{
layoutreader_model_dir
}
'
)
json_url
=
'https://gitee.com/myhloli/MinerU/raw/master/magic-pdf.template.json'
config_file_name
=
'magic-pdf.json'
home_dir
=
os
.
path
.
expanduser
(
'~'
)
config_file
=
os
.
path
.
join
(
home_dir
,
config_file_name
)
json_mods
=
{
'models-dir'
:
model_dir
,
'layoutreader-model-dir'
:
layoutreader_model_dir
,
}
download_and_modify_json
(
json_url
,
config_file
,
json_mods
)
print
(
f
'The configuration file has been configured successfully, the path is:
{
config_file
}
'
)
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