name: Models as Data - Diff

on:
  workflow_dispatch:
    inputs:
      projects:
        description: "The projects to generate models for"
        required: true
        default: '["netty/netty"]'
  pull_request:
    branches:
      - main
    paths:
      - "java/ql/src/utils/modelgenerator/**/*.*"
      - ".github/workflows/mad_modelDiff.yml"

permissions:
  contents: read

jobs:
  model-diff:
    name: Model Difference
    runs-on: ubuntu-latest
    if: github.repository == 'github/codeql'
    strategy:
      matrix:
        slug: ${{fromJson(github.event.inputs.projects || '["apache/commons-codec", "apache/commons-io", "apache/commons-beanutils", "apache/commons-logging", "apache/commons-fileupload", "apache/commons-lang", "apache/commons-validator", "apache/commons-csv", "apache/dubbo"]' )}}
    steps:
      - name: Clone github/codeql from PR
        uses: actions/checkout@v4
        if: github.event.pull_request
        with:
          path: codeql-pr
      - name: Clone github/codeql from main
        uses: actions/checkout@v4
        with:
          path: codeql-main
          ref: main
      - uses: ./codeql-main/.github/actions/fetch-codeql
      - name: Download database
        env:
          SLUG: ${{ matrix.slug }}
          GH_TOKEN: ${{ github.token }}
        run: |
          set -x
          mkdir lib-dbs
          SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
          gh api -H "Accept: application/zip" "/repos/${SLUG}/code-scanning/codeql/databases/java" > "$SHORTNAME.zip"
          unzip -q -d "${SHORTNAME}-db" "${SHORTNAME}.zip"
          mkdir "lib-dbs/$SHORTNAME/"
          mv "${SHORTNAME}-db/"$(ls -1 "${SHORTNAME}"-db)/* "lib-dbs/${SHORTNAME}/"
      - name: Generate Models (PR and main)
        run: |
          set -x
          mkdir tmp-models
          MODELS=`pwd`/tmp-models
          DATABASES=`pwd`/lib-dbs

          analyzeDatabaseWithCheckout() {
            QL_VARIANT=$1
            DATABASE=$2
            cd codeql-$QL_VARIANT
            SHORTNAME=`basename $DATABASE`
            python java/ql/src/utils/modelgenerator/GenerateFlowModel.py --with-summaries --with-sinks $DATABASE ${SHORTNAME}.temp.model.yml
            mv java/ql/lib/ext/generated/${SHORTNAME}.temp.model.yml $MODELS/${SHORTNAME}Generated_${QL_VARIANT}.model.yml
            cd ..
          }

          for d in $DATABASES/*/ ; do
            ls -1 "$d"

            analyzeDatabaseWithCheckout "main" $d
            if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]
            then
              analyzeDatabaseWithCheckout "pr" $d
            fi
          done
      - name: Install diff2html
        if: github.event.pull_request
        run: |
          npm install -g diff2html-cli
      - name: Generate Model Diff
        if: github.event.pull_request
        run: |
          set -x
          MODELS=`pwd`/tmp-models
          ls -1 tmp-models/
          for m in $MODELS/*_main.model.yml ; do
            t="${m/main/"pr"}"
            basename=`basename $m`
            name="diff_${basename/_main.model.yml/""}"
            (diff -w -u $m $t | diff2html -i stdin -F $MODELS/$name.html) || true
          done
      - uses: actions/upload-artifact@v3
        with:
          name: models
          path: tmp-models/*.model.yml
          retention-days: 20
      - uses: actions/upload-artifact@v3
        with:
          name: diffs
          path: tmp-models/*.html
          # An html file is only produced if the generated models differ.
          if-no-files-found: ignore
          retention-days: 20