-
Notifications
You must be signed in to change notification settings - Fork 0
175 lines (140 loc) · 5.99 KB
/
build_packages_info.yml
File metadata and controls
175 lines (140 loc) · 5.99 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
# Start with a list of packages in packages.csv, and get external data about them (e.g. last commit date) to generate an HTML page with the package information. This workflow is triggered manually from the Actions tab.
# Olly Butters
# 1/5/26
name: Package list
# Controls when the workflow will run
on:
schedule:
- cron: '30 5 * * 0'
timezone: "Europe/London"
push:
branches: [ "main" ]
workflow_dispatch:
jobs:
build:
runs-on: ubuntu-slim
steps:
- name: Checkout repository
uses: actions/checkout@v4
# Parse the package list, get the external data, and write to a new CSV file
- name: Build package data
run: |
echo $GITHUB_WORKSPACE
ls $GITHUB_WORKSPACE
# Create new output file
echo "Name,Description,CRAN link,CRAN version, CRAN license,Last commit,GitHub version,GitHub license,Github owner,Status" > output.csv
while IFS="," read -r name description gh_link cran_link status
do
echo "-----------------------------------"
echo "name: $name"
echo "desc: $description"
echo "github_link: $gh_link"
echo "cran_link: $cran_link"
echo "status: $status"
echo ""
##### GitHub info
echo -e "\nGitHub repo information"
# Extract the repo name from the GitHub link
gh_repo_name=$(echo $gh_link | awk -F/ '{print $NF}')
echo $gh_repo_name
# clone the repo
git clone $gh_link
cd $gh_repo_name
# Last commit date of repo
gh_last_commit=$(git log -1 --format=%cs)
echo "last commit: $gh_last_commit"
# Last release
if [ $(git rev-list --tags --max-count=1) ]; then
gh_last_release=$(git describe --tags $(git rev-list --tags --max-count=1))
else
gh_last_release=""
fi
echo "last GitHub release: $gh_last_release"
# Use the GitHub API to pull in info about the repoisitory
echo "\nGitHub API information"
gh repo view --json codeOfConduct,description,homepageUrl,licenseInfo,owner,parent,updatedAt > gh_repo_info.json
echo "API response:"
cat gh_repo_info.json
# Get the license as it appears in GitHub
gh_license=$(cat gh_repo_info.json | jq '.licenseInfo.nickname')
if [ -z "${gh_license}" ] || [ "${gh_license}" = '""' ]; then
gh_license=$(cat gh_repo_info.json | jq '.licenseInfo.name')
fi
# If the license is "Other", check for a LICENSE.md file and see if it contains actual license
if [ "${gh_license}" = '"Other"' ]; then
if [ -f "LICENSE.md" ]; then
echo "License file found: LICENSE.md"
if $(grep -q "MIT License" LICENSE.md); then
gh_license="MIT License"
fi
fi
fi
echo "GitHub license: $gh_license"
gh_owner=$(cat gh_repo_info.json | jq '.owner.login')
echo "GitHub owner: $gh_owner"
gh_code_of_conduct=$(cat gh_repo_info.json | jq '.codeOfConduct.name')
echo "GitHub code of conduct: $gh_code_of_conduct"
# Tidy up
cd ..
rm -rf $gh_repo_name
##### CRAN info
echo "CRAN information"
if [ -z "${cran_link}" ]; then
cran_version=""
cran_license=""
else
# Get CRAN package name from cran_link
CRAN_package_name=$(echo $cran_link | awk -F= '{print $NF}')
echo "CRAN package name: $CRAN_package_name"
# Get the version number from CRAN
# This is overkill really, it takes ages to install all the R dependencies. Could just parse the CRAN DESCRIPTION file.
#version=$(Rscript --vanilla -e 'print(subset(tools::CRAN_package_db(), Package == "dsBase")[["Version"]], row.names=FALSE)')
#echo "version: $version"
cran_description_file_link="https://cran.r-project.org/web/packages/${CRAN_package_name}/DESCRIPTION"
wget --content-on-error $cran_description_file_link
# might not be on the CRAN
if [ -f DESCRIPTION ]; then
cran_version=$(grep -oP '^Version:\s*\K([a-zA-Z0-9\. _-]+)\s*$' DESCRIPTION)
cran_license=$(grep -oP '^License:\s*\K([a-zA-Z0-9\. _\-\(\)><=\+]+)\s*$' DESCRIPTION)
# tidy up
rm DESCRIPTION
else
cran_version=""
cran_license=""
fi
fi
echo "CRAN version: $cran_version"
echo "CRAN license: $cran_license"
# write to file
echo "$name,$description,$cran_link,$cran_version,$cran_license,$gh_link,$gh_last_commit,$gh_last_release,$gh_license,$gh_owner,$status" >> output.csv
echo "-----------------------------------"
done < <(tail -n +2 package_list.csv)
mkdir gh-pages
cp output.csv gh-pages/
cat output.csv
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Parse the output CSV file and generate an HTML page
- name: build html page
run: |
python3 web_pages/build_packages_page.py
mv output/* gh-pages/
- name: Upload static files as artifact
id: deployment
uses: actions/upload-pages-artifact@v3
with:
path: gh-pages
# Deployment job
deploy:
environment:
name: github-pages
url: ${{ steps.deployment.outputs.page_url }}
runs-on: ubuntu-slim
permissions:
pages: write
id-token: write
needs: build
steps:
- name: Deploy to GitHub Pages
id: deployment
uses: actions/deploy-pages@v4