Skip to content

On Pull Request

On Pull Request #113

Workflow file for this run

name: On Pull Request
on:
workflow_dispatch:
inputs:
manual-pr-number:
description: 'PR Number'
required: true
default: '10'
#pull_request:
#paths:
# - '**/*.gpml'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
cancel-in-progress: false # to allow multiple runs to queue up rather than clobber
jobs:
get-pr:
# This job determines the PR number and stores it as a GITHUB_OUTPUT environment variable
# that can accessed by subsequent jobs.
runs-on: ubuntu-latest
outputs:
pr-number: ${{ steps.get-pr.outputs.pr-number }}
steps:
- name: Get PR
id: get-pr
# Get PR from triggering event, unless provided via manual workflow run
run: |
if [ -z "${{ inputs.manual-pr-number }}" ]; then
echo "pr-number=${{ github.event.pull_request.number }}" >> $GITHUB_OUTPUT
else
echo "pr-number=${{ inputs.manual-pr-number }}" >> $GITHUB_OUTPUT
fi
get-gpml:
# This job gets the GPML file and uploads it as an artifact
# that can accessed by subsequent jobs. It also extracts key information from
# the GPML file and starts a new PR description.
#
# A markdown text report is stored as pr-desc to be compiled and written to the PR description.
#
# The branch name from the submitter's fork is also extracted and stored (if needed).
needs: [get-pr]
#if: ${{ needs.get-pr.outputs.pr-number }}
runs-on: ubuntu-latest
outputs:
gpml-filepath: ${{ steps.get-gpml.outputs.gpml-filepath }}
gpml-file: ${{ steps.get-gpml.outputs.gpml-file }}
pr-desc: ${{ steps.get-gpml.outputs.pr-desc }}
branch-name: ${{ steps.get-branch.outputs.branch-name }}
env:
PR_NUMBER: ${{ needs.get-pr.outputs.pr-number }}
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: refs/pull/${{ needs.get-pr.outputs.pr-number }}/head
- name: Install XML processing tools
# Used to parse XML values from GPML
run: sudo apt-get install -y libxml2-utils
- name: Get GPML
id: get-gpml
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
GPML_FILEPATH=$(gh pr view $PR_NUMBER --json files --jq '.files.[].path' | grep '.gpml$')
echo "Found GPML file at: $GPML_FILEPATH"
echo "gpml-filepath=$GPML_FILEPATH" >> $GITHUB_OUTPUT #for subsequent jobs
# Extract information from GPML
GPML_FILE="$(basename ""$GPML_FILEPATH"")"
echo "gpml-file=$GPML_FILE" >> $GITHUB_OUTPUT
wpid="$($GPML_FILE | sed 's/.gpml//')"
org="$(xmllint --xpath 'string(//*[local-name()="Pathway"]/@Organism)' "$GPML_FILEPATH")"
name="$(xmllint --xpath 'string(//*[local-name()="Pathway"]/@Name)' "$GPML_FILEPATH")"
desc="$(xmllint --xpath 'string(//*[local-name()="Comment" and @Source="WikiPathways-description"])' "$GPML_FILEPATH")"
# Start PR description (newlines are important in NEW_DESCRIPTION string)
NEW_DESCRIPTION="
## Pathway Information
**WPID**: $wpid
**TITLE**: $name
**ORGANISM**: $org
**DESCRIPTION**: $desc
---
"
# Store PR description for compilation in final job
# EOF base64 needed for storing multi-line strings as output variables
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
# Temporarily append PR description
NEW_DESCRIPTION="$NEW_DESCRIPTION
Processing...
"
# Edit PR description
gh pr edit $PR_NUMBER --body "$NEW_DESCRIPTION"
- name: Upload GPML file as artifact
uses: actions/upload-artifact@v3
with:
name: gpml-file
path: ${{ steps.get-gpml.outputs.gpml-filepath }}
retention-days: 1
if-no-files-found: error # 'warn' or 'ignore' are also available, defaults to `warn`
- name: Get branch name
id: get-branch
# Determine PR branch from submitter's fork, if needed #TODO: prune if not needed
run: |
BRANCH_NAME=$(curl -s -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
https://api.github.com/repos/${{ github.repository }}/pulls/${{needs.get-pr.outputs.pr-number}} \
| jq -r .head.ref)
echo "branch-name=$BRANCH_NAME"
echo "branch-name=$BRANCH_NAME" >> $GITHUB_OUTPUT
if ! git ls-remote --heads origin $BRANCH_NAME; then
git push origin HEAD:refs/heads/$BRANCH_NAME
fi
metadata:
# This job generates files dervied from the GPML, including info.json, datanodes.tsv and refs.tsv.
# The meta-data-action Java application performs the bulk of the work:
# https://github.com/wikipathways/meta-data-action
#
# The generated files are uploaded as artifacts to be downloaded and pushed together with other files
# to another repo in a final sync job. This strategy allows for parallel job processing!
#
# A markdown text report is stored as pr-desc to be compiled and written to the PR description.
needs: [get-pr,get-gpml]
runs-on: ubuntu-latest
outputs:
pr-desc: ${{ steps.report.outputs.pr-desc }}
env:
GPML_FILE: ${{ needs.get-gpml.outputs.gpml-file }}
steps:
- name: Checkout repository for scripts
uses: actions/checkout@v4
- name: Download GPML artifact
# Downloads gpml-file artifact to working dir
# Note: Automatically unzips to provide GPML with original filename
uses: actions/download-artifact@v3
with:
name: gpml-file
- name: Setup Java
uses: actions/setup-java@v3
with:
distribution: 'temurin'
java-version: '11'
- name: Cache meta-data-action with dependencies
uses: actions/cache@v3
id: cacheMetaJar
with:
path: ./meta-data-action-1.1.2-jar-with-dependencies.jar
key: cached-meta-data-action-${{ hashFiles('meta-data-action-1.1.2-jar-with-dependencies.jar') }}
restore-keys: |
cached-meta-data-action-${{ hashFiles('meta-data-action-1.1.2-jar-with-dependencies.jar') }}
cached-meta-data-action-
- name: Install deps
run: |
echo "Refreshing cached-meta-data-action"
if [ ! -e ./meta-data-action-1.1.2-jar-with-dependencies.jar ]; then
wget -O meta-data-action-1.1.2-jar-with-dependencies.jar https://github.com/wikipathways/meta-data-action/releases/download/v1.1.2/meta-data-action-1.1.2-jar-with-dependencies.jar
fi
- name: Cache and install dependencies
uses: actions/cache@v3
id: cache
with:
path: ${{ github.workspace }}/Hs_Derby_Ensembl_108.bridge
key: ${{ runner.os }}-java-Hs_Derby_Ensembl_108
restore-keys: |
${{ runner.os }}-java-Hs_Derby_Ensembl_108
${{ runner.os }}-java-Hs_Derby_Ensembl_
- if: steps.cache.outputs.cache-hit != 'true'
name: Install deps
run: |
cd "${{ github.workspace }}"
if [ ! -e ./Hs_Derby_Ensembl_108.bridge ]; then
wget -O Hs_Derby_Ensembl_108.bridge https://zenodo.org/record/7781913/files/Hs_Derby_Ensembl_108.bridge?download=1
fi
- name: Generate gdb.config, fileNames.config, and fileDownloads.config
run: scripts/meta-data-action/configGenerator.sh ./$GPML_FILE
- name: Cache all bridge files
uses: actions/cache@v3
id: cacheAllBridge
with:
path: |
./metabolites*.bridge
./Ag*.bridge
./An*.bridge
./At*.bridge
./Bs*.bridge
./Bt*.bridge
./Ce*.bridge
./Cf*.bridge
./Ci*.bridge
./Dr*.bridge
./Da*.bridge
./Dp*.bridge
./Dm*.bridge
./Ec*.bridge
./Gg*.bridge
./Fg*.bridge
./Gm*.bridge
./Hs*.bridge
./Hv*.bridge
./Ml*.bridge
./Mm*.bridge
./Mx*.bridge
./Oa*.bridge
./Ova*.bridge
./Oi*.bridge
./Oj*.bridge
./Pi*.bridge
./Pt*.bridge
./Qc*.bridge
./Rn*.bridge
./Sc*.bridge
./Sl*.bridge
./Ss*.bridge
./Vv*.bridge
./Xt*.bridge
./Zm*.bridge
key: cached-bridge-files
restore-keys: |
cached-bridge-files
- if: steps.cacheAllBridge.outputs.cache-hit != 'true'
name: Install all bridge files
run: |
echo "Cache not found: cached-bridge-files"
declare -a OrganismNames=("Metabolites" "Anopheles gambiae" "Aspergillus niger" "Arabidopsis thaliana" "Bacillus subtilis" "Bos taurus" "Caenorhabditis elegans" "Canis familiaris" "Ciona intestinalis" "Danio rerio" "Daphnia magna" "Daphnia pulex" "Drosophila melanogaster" "Escherichia coli" "Gallus gallus" "Fusarium graminearum" "Glycine max" "Homo sapiens" "Hordeum vulgare" "Macaca mulatta" "Mus musculus" "Mycobacterium tuberculosis" "Ornithorhynchus anatinus" "Ovis aries" "Oryza indica" "Oryza japonica" "Populus trichocarpa" "Pan troglodytes" "Equus caballus" "Rattus norvegicus" "Saccharomyces cerevisiae" "Solanum lycopersicum" "Sus scrofa" "Vitis vinifera" "Xenopus tropicalis" "Zea mays")
for org in "${OrganismNames[@]}"; do
echo "generating configuration files for "$org""
scripts/meta-data-action/configGenerator.sh "$org"
echo "installing bridgedb files for "$org""
scripts/meta-data-action/installDependencies.sh "$org"
done
- name: Generate configs, install bridgeDb, generate info and tsv files
run: |
chmod 777 meta-data-action-1.1.2-jar-with-dependencies.jar
f=./$GPML_FILE
org="$(sed -n '/<Pathway /s/.*Organism=\(.*\)[^\n]*/\1/p' $f | tr -d '"' | tr -d '>' | tr -d '\r')"
echo "generating configuration files for "$org""
scripts/meta-data-action/configGenerator.sh "$org"
wpid="$(basename ""$f"" | sed 's/.gpml//')"
cat gdb.config
echo "generating info and datanode files for $wpid, organism "$org""
java -jar meta-data-action-1.1.2-jar-with-dependencies.jar local "$f" $(date --utc +%F) gdb.config "$org"
# generated files are placed in "pathways" dir
ls -R
mkdir ./metadata
mv pathways/"$wpid"-info.json metadata/.
mv pathways/"$wpid"*.tsv metadata/.
- name: Upload metadata files as artifacts
uses: actions/upload-artifact@v3
with:
name: metadata
path: metadata/
retention-days: 1
if-no-files-found: error # 'warn' or 'ignore' are also available, defaults to `warn`
- name: Report on meta-data-action
id: report
run: |
# Verify generated files
infojson=$(find . -path "./metadata/WP*info.json" -print -quit)
dntsv=$(find . -path "./metadata/WP*datanodes.tsv" -print -quit)
refstsv=$(find . -path "./metadata/WP*refs.tsv" -print -quit)
# Update PR description
NEW_DESCRIPTION="
## Generate Metadata Files
"
if [[ -n $infojson ]]; then
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [x] info.json generated"
else
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [] info.json generated"
fi
if [[ -n $dntsv ]]; then
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [x] datanodes.tsv generated"
else
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [] datanodes.tsv generated"
fi
if [[ -n $refstsv ]]; then
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [x] refs.tsv generated"
else
NEW_DESCRIPTION="$NEW_DESCRIPTION
- [] refs.tsv generated"
fi
# Store PR description for compilation in final job
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
pubmed:
if: true
needs: [get-pr,get-gpml, metadata]
runs-on: ubuntu-latest
outputs:
pr-desc: ${{ steps.report.outputs.pr-desc }}
env:
GPML_FILE: ${{ needs.get-gpml.outputs.gpml-file }}
steps:
- name: Checkout repository for scripts
uses: actions/checkout@v4
- name: Download GPML artifact
# Downloads gpml-file and metadata artifacts to working dir
# Note: Automatically unzips to provide files with original filenames
uses: actions/download-artifact@v3
- name: Run generate-references
run: |
echo "TODO: Run generate-references and attach output TSV to PR"
- name: Report on pubmed
id: report
run: |
# Update PR description
NEW_DESCRIPTION="- [x] references.tsv generated"
# Store PR description for compilation in final job
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
frontmatter:
if: true
needs: [get-pr,get-gpml,metadata]
runs-on: ubuntu-latest
outputs:
pr-desc: ${{ steps.report.outputs.pr-desc }}
env:
GPML_FILE: ${{ needs.get-gpml.outputs.gpml-file }}
steps:
- name: Checkout repository for scripts
uses: actions/checkout@v4
- name: Download GPML artifact
# Downloads gpml-file and metadata artifacts to working dir
# Note: Automatically unzips to provide files with original filenames
uses: actions/download-artifact@v3
- name: Run create_pathway_frontmatter.py
run: |
echo "TODO: Run create_pathway_frontmatter.py and attach output MD to PR"
- name: Report on pubmed
id: report
run: |
# Update PR description
NEW_DESCRIPTION="- [x] .md generated"
# Store PR description for compilation in final job
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
json-svg:
if: true
needs: [get-pr,get-gpml,metadata]
runs-on: ubuntu-latest
outputs:
pr-desc: ${{ steps.report.outputs.pr-desc }}
env:
GPML_FILE: ${{ needs.get-gpml.outputs.gpml-file }}
steps:
- name: Checkout repository for scripts
uses: actions/checkout@v4
- name: Download GPML artifact
# Downloads gpml-file and metadata artifacts to working dir
# Note: Automatically unzips to provide files with original filenames
uses: actions/download-artifact@v3
- name: Run generate-svgs
run: |
echo "TODO: Run generate-svgs and attach output JSON, SVG and PNG to PR"
- name: Report on pubmed
id: report
run: |
# Update PR description
NEW_DESCRIPTION="- [x] .json generated
- [x] .svg generated
- [x] .png generated
*TODO: insert PNG here*
"
# Store PR description for compilation in final job
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
testing:
if: true
needs: [get-pr,get-gpml,metadata]
runs-on: ubuntu-latest
outputs:
pr-desc: ${{ steps.report.outputs.pr-desc }}
env:
GPML_FILE: ${{ needs.get-gpml.outputs.gpml-file }}
steps:
- name: Checkout repository for scripts
uses: actions/checkout@v4
- name: Download GPML artifact
# Downloads gpml-file and metadata artifacts to working dir
# Note: Automatically unzips to provide files with original filenames
uses: actions/download-artifact@v3
- name: Perform automatic test
run: |
# TODO: perform testing
- name: Report on pubmed
id: report
run: |
# Update PR description
NEW_DESCRIPTION='
---
## Automated Testing
*As table*
| # | Test name | Link | Notes | Result |
|---|---|---|---|---|
| 1 | Test one | | | \$\${\color{green}PASS}\$\$ |
| 2 | Test two | | | \$\${\color{red}FAIL}\$\$ |
| 3 | Test three | | | \$\${\color{green}PASS}\$\$ |
*As checklist*
- [ ] Interactions are connected
- [ ] Datanodes are annotated with database references
- [ ] Decription, consisting of 2-3 sentence overview of processes described in the pathway
- [ ] At least one literature reference
- [ ] At least one pathway ontology term
- [ ] Pathway title conforms to the [guidelines](https://github.com/wikipathways/wikipathways-faq/discussions/24)
---
'
# Store PR description for compilation in final job
EOF=$(dd if=/dev/urandom bs=15 count=1 status=none | base64)
echo "pr-desc<<$EOF" >> $GITHUB_OUTPUT
echo "$NEW_DESCRIPTION" >> $GITHUB_OUTPUT
echo "$EOF" >> $GITHUB_OUTPUT
update-pr-desc:
needs: [get-pr,get-gpml,metadata,pubmed,frontmatter,json-svg,testing]
runs-on: ubuntu-latest
steps:
- name: Check out code
uses: actions/checkout@v4
with:
ref: refs/pull/${{ needs.get-pr.outputs.pr-number }}/head
- name: Compile and update PR description
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
PR_NUMBER: ${{ needs.get-pr.outputs.pr-number }}
run: |
NEW_DESCRIPTION="${{ needs.get-gpml.outputs.pr-desc }}
${{ needs.metadata.outputs.pr-desc }}
${{ needs.pubmed.outputs.pr-desc }}
${{ needs.frontmatter.outputs.pr-desc }}
${{ needs.json-svg.outputs.pr-desc }}
${{ needs.testing.outputs.pr-desc }}
"
# Edit PR description
gh pr edit $PR_NUMBER --body "$NEW_DESCRIPTION"