v2ray-rules-dat/.github/workflows/run.yml

name: Build V2Ray rules dat files
on:
  workflow_dispatch:
  schedule:
    - cron: "0 22 * * *"
  push:
    branches:
      - master
    paths-ignore:
      - "**/README.md"
jobs:
  build:
    runs-on: ubuntu-latest
    steps:
      - name: Setup Go 1.x.y
        uses: actions/setup-go@v2
        with:
          go-version: "^1.15"

      - name: Set variables
        run: |
          echo "RELEASE_NAME=Released on $(date +%Y%m%d%H%M)" >> $GITHUB_ENV
          echo "TAG_NAME=$(date +%Y%m%d%H%M)" >> $GITHUB_ENV
          echo "CHINA_DOMAINS_URL=https://raw.githubusercontent.com/felixonmars/dnsmasq-china-list/master/accelerated-domains.china.conf" >> $GITHUB_ENV
          echo "GOOGLE_DOMAINS_URL=https://raw.githubusercontent.com/felixonmars/dnsmasq-china-list/master/google.china.conf" >> $GITHUB_ENV
          echo "APPLE_DOMAINS_URL=https://raw.githubusercontent.com/felixonmars/dnsmasq-china-list/master/apple.china.conf" >> $GITHUB_ENV
          echo "GFWLIST_DOMAINS_URL=https://cokebar.github.io/gfwlist2dnsmasq/gfwlist_domain.txt" >> $GITHUB_ENV
          echo "GFWLIST_EXTRAS_DOMAINS_URL=https://raw.githubusercontent.com/pexcn/gfwlist-extras/master/gfwlist-extras.txt" >> $GITHUB_ENV
          echo "GREATFIRE_DOMAINS_URL=https://raw.githubusercontent.com/Loyalsoldier/cn-blocked-domain/release/domains.txt" >> $GITHUB_ENV
          echo "GEQ1AN_RULES_GLOBAL_MEDIA_URL=https://raw.githubusercontent.com/GeQ1an/Rules/master/QuantumultX/Filter/GMedia.list" >> $GITHUB_ENV
          echo "LHIE1_RULES_PROXY_URL=https://raw.githubusercontent.com/lhie1/Rules/master/Surge/Surge%203/Provider/Proxy.list" >> $GITHUB_ENV
          echo "EASYLISTCHINA_EASYLIST_REJECT_URL=https://easylist-downloads.adblockplus.org/easylistchina+easylist.txt" >> $GITHUB_ENV
          echo "PETERLOWE_REJECT_URL=https://pgl.yoyo.org/adservers/serverlist.php?hostformat=hosts&showintro=1&mimetype=plaintext" >> $GITHUB_ENV
          echo "ADGUARD_DNS_REJECT_URL=https://adguardteam.github.io/AdGuardSDNSFilter/Filters/filter.txt" >> $GITHUB_ENV
          echo "DANPOLLOCK_REJECT_URL=https://someonewhocares.org/hosts/hosts" >> $GITHUB_ENV
          echo "CUSTOM_DIRECT=https://raw.githubusercontent.com/Loyalsoldier/domain-list-custom/release/cn.txt" >> $GITHUB_ENV
          echo "CUSTOM_PROXY=https://raw.githubusercontent.com/Loyalsoldier/domain-list-custom/release/geolocation-!cn.txt" >> $GITHUB_ENV
          echo "WIN_SPY=https://raw.githubusercontent.com/crazy-max/WindowsSpyBlocker/master/data/hosts/spy.txt" >> $GITHUB_ENV
          echo "WIN_UPDATE=https://raw.githubusercontent.com/crazy-max/WindowsSpyBlocker/master/data/hosts/update.txt" >> $GITHUB_ENV
          echo "WIN_EXTRA=https://raw.githubusercontent.com/crazy-max/WindowsSpyBlocker/master/data/hosts/extra.txt" >> $GITHUB_ENV
        shell: bash

      - name: Checkout the "hidden" branch of this repo
        uses: actions/checkout@v2.3.4
        with:
          ref: hidden

      - name: Checkout Loyalsoldier/domain-list-custom
        uses: actions/checkout@v2.3.4
        with:
          repository: Loyalsoldier/domain-list-custom
          path: custom

      - name: Checkout v2fly/domain-list-community
        uses: actions/checkout@v2.3.4
        with:
          repository: v2fly/domain-list-community
          path: community

      - name: Get geoip.dat relative files
        run: |
          wget https://github.com/Loyalsoldier/geoip/raw/release/geoip.dat
          wget https://github.com/Loyalsoldier/geoip/raw/release/geoip.dat.sha256sum

      - name: Get and add direct domains into temp-direct.txt file
        run: |
          curl -sSL $CHINA_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > temp-direct.txt
          curl -sSL ${CUSTOM_DIRECT} | perl -ne '/^(domain):([^:]+)(\n$|:@.+)/ && print "$2\n"' >> temp-direct.txt

      - name: Get and add proxy domains into temp-proxy.txt file
        run: |
          curl -sSL $GFWLIST_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' > temp-proxy.txt
          curl -sSL $GFWLIST_EXTRAS_DOMAINS_URL | perl -ne 'print if not /^(#|\s)/' >> temp-proxy.txt
          curl -sSL $GREATFIRE_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' >> temp-proxy.txt
          curl -sSL $GOOGLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' >> temp-proxy.txt
          curl -sSL $APPLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' >> temp-proxy.txt
          curl -sSL $GEQ1AN_RULES_GLOBAL_MEDIA_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+GMedia/ {print $2}' >> temp-proxy.txt
          curl -sSL $LHIE1_RULES_PROXY_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+/ {print $2}' >> temp-proxy.txt
          curl -sSL ${CUSTOM_PROXY} | grep -Ev ":@cn" | perl -ne '/^(domain):([^:]+)(\n$|:@.+)/ && print "$2\n"' >> temp-proxy.txt

      - name: Get and add reject domains into temp-reject.txt file
        run: |
          curl -sSL $EASYLISTCHINA_EASYLIST_REJECT_URL | perl -ne '/^\|\|([-_0-9a-zA-Z]+(\.[-_0-9a-zA-Z]+){1,64})\^$/ && print "$1\n"' | perl -ne 'print if not /^[0-9]{1,3}(\.[0-9]{1,3}){3}$/' > temp-reject.txt
          curl -sSL $ADGUARD_DNS_REJECT_URL | perl -ne '/^\|\|([-_0-9a-zA-Z]+(\.[-_0-9a-zA-Z]+){1,64})\^$/ && print "$1\n"' | perl -ne 'print if not /^[0-9]{1,3}(\.[0-9]{1,3}){3}$/' >> temp-reject.txt
          curl -sSL $PETERLOWE_REJECT_URL | perl -ne '/^127\.0\.0\.1\s([-_0-9a-zA-Z]+(\.[-_0-9a-zA-Z]+){1,64})$/ && print "$1\n"' >> temp-reject.txt
          curl -sSL $DANPOLLOCK_REJECT_URL | perl -ne '/^127\.0\.0\.1\s([-_0-9a-zA-Z]+(\.[-_0-9a-zA-Z]+){1,64})/ && print "$1\n"' | sed '1d' >> temp-reject.txt

      - name: Reserve `full`, `regexp` and `keyword` type of rules from custom lists to "reserve" files
        run: |
          curl -sSL ${CUSTOM_DIRECT} | perl -ne '/^((full|regexp|keyword):[^:]+)(\n$|:@.+)/ && print "$1\n"' | sort --ignore-case -u > direct-reserve.txt
          curl -sSL ${CUSTOM_PROXY} | grep -Ev ":@cn" | perl -ne '/^((full|regexp|keyword):[^:]+)(\n$|:@.+)/ && print "$1\n"' | sort --ignore-case -u > proxy-reserve.txt

      - name: Add proxy, direct and reject domains from "hidden" branch to appropriate temp files
        run: |
          cat proxy.txt >> temp-proxy.txt
          cat direct.txt >> temp-direct.txt
          cat reject.txt >> temp-reject.txt

      - name: Sort and generate redundant lists
        run: |
          cat temp-proxy.txt | sort --ignore-case -u > proxy-list-with-redundant
          cat temp-direct.txt | sort --ignore-case -u > direct-list-with-redundant
          cat temp-reject.txt | sort --ignore-case -u > reject-list-with-redundant

      - name: Remove redundant domains
        run: |
          chmod +x findRedundantDomain.py
          ./findRedundantDomain.py ./direct-list-with-redundant ./direct-list-deleted-unsort
          ./findRedundantDomain.py ./proxy-list-with-redundant ./proxy-list-deleted-unsort
          ./findRedundantDomain.py ./reject-list-with-redundant ./reject-list-deleted-unsort
          [ ! -f "direct-list-deleted-unsort" ] && touch direct-list-deleted-unsort
          [ ! -f "proxy-list-deleted-unsort" ] && touch proxy-list-deleted-unsort
          [ ! -f "reject-list-deleted-unsort" ] && touch reject-list-deleted-unsort
          sort ./direct-list-deleted-unsort > ./direct-list-deleted-sort
          sort ./proxy-list-deleted-unsort > ./proxy-list-deleted-sort
          sort ./reject-list-deleted-unsort > ./reject-list-deleted-sort
          diff ./direct-list-deleted-sort ./direct-list-with-redundant | awk '/^>/{print $2}' > ./direct-list-without-redundant
          diff ./proxy-list-deleted-sort ./proxy-list-with-redundant | awk '/^>/{print $2}' > ./proxy-list-without-redundant
          diff ./reject-list-deleted-sort ./reject-list-with-redundant | awk '/^>/{print $2}' > ./reject-list-without-redundant

      - name: Remove domains from "need-to-remove" lists in "hidden" branch
        run: |
          diff ./direct-need-to-remove.txt ./direct-list-without-redundant | awk '/^>/{print $2}' > temp-cn.txt
          diff ./proxy-need-to-remove.txt ./proxy-list-without-redundant | awk '/^>/{print $2}' > temp-geolocation-\!cn.txt
          diff ./reject-need-to-remove.txt ./reject-list-without-redundant | awk '/^>/{print $2}' > temp-category-ads-all.txt

      - name: Remove domains end with ".cn" in "temp-geolocation-!cn.txt" and write lists to data directory
        run: |
          cat temp-cn.txt | sort --ignore-case -u | perl -ne '/^((?=^.{1,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})*)/ && print "$1\n"' > ./community/data/cn
          cat temp-cn.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > direct-tld-list.txt
          cat temp-geolocation-\!cn.txt | sort --ignore-case -u | perl -ne '/^((?=^.{1,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})*)/ && print "$1\n"' | perl -ne 'print if not /\.cn$/' > ./community/data/geolocation-\!cn
          cat temp-geolocation-\!cn.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > proxy-tld-list.txt
          cat temp-category-ads-all.txt | sort --ignore-case -u | perl -ne '/^((?=^.{1,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})*)/ && print "$1\n"' > ./community/data/category-ads-all
          cat temp-category-ads-all.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > reject-tld-list.txt

      - name: Add `full`, `regexp` and `keyword` type of rules back into "cn", "geolocation-!cn" and "category-ads-all" list
        run: |
          [ -f "direct-reserve.txt" ] && cat direct-reserve.txt >> ./community/data/cn
          [ -f "proxy-reserve.txt" ] && cat proxy-reserve.txt >> ./community/data/geolocation-\!cn
          [ -f "reject-reserve.txt" ] && cat reject-reserve.txt >> ./community/data/category-ads-all
          cp ./community/data/cn direct-list.txt
          cp ./community/data/geolocation-\!cn proxy-list.txt
          cp ./community/data/category-ads-all reject-list.txt

      - name: Create `google-cn`、`apple-cn`、`gfw`、`greatfire` lists
        run: |
          curl -sSL $GOOGLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > ./community/data/google-cn
          curl -sSL $GOOGLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > google-cn.txt
          curl -sSL $APPLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > ./community/data/apple-cn
          curl -sSL $APPLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > apple-cn.txt
          curl -sSL $GFWLIST_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' >> ./community/data/gfw
          curl -sSL $GFWLIST_EXTRAS_DOMAINS_URL | perl -ne 'print if not /^(#|\s)/' >> ./community/data/gfw
          cat ./community/data/gfw | sort --ignore-case -u > gfw.txt
          curl -sSL $GREATFIRE_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' >> ./community/data/greatfire
          cat ./community/data/greatfire | sort --ignore-case -u > greatfire.txt
          curl -sSL $WIN_SPY | grep "0.0.0.0" | awk '{print $2}' > ./community/data/win-spy
          curl -sSL $WIN_SPY | grep "0.0.0.0" | awk '{print $2}' > win-spy.txt
          curl -sSL $WIN_UPDATE | grep "0.0.0.0" | awk '{print $2}' > ./community/data/win-update
          curl -sSL $WIN_UPDATE | grep "0.0.0.0" | awk '{print $2}' > win-update.txt
          curl -sSL $WIN_EXTRA | grep "0.0.0.0" | awk '{print $2}' > ./community/data/win-extra
          curl -sSL $WIN_EXTRA | grep "0.0.0.0" | awk '{print $2}' > win-extra.txt

      - name: Build geosite.dat file
        run: |
          cd custom || exit 1
          go run ./ --datapath=../community/data

      - name: Move and zip files and generate sha256 hash
        run: |
          install -Dp ./geoip.dat ./publish/geoip.dat
          install -Dp ./geoip.dat.sha256sum ./publish/geoip.dat.sha256sum
          install -Dp ./custom/publish/dlc.dat ./publish/geosite.dat
          install -p {proxy,direct,reject}-tld-list.txt ./publish/
          install -p {proxy,direct,reject}-list.txt ./publish/
          install -p {apple-cn,google-cn,gfw,greatfire,win-spy,win-update,win-extra}.txt ./publish/
          cd ./publish || exit 1
          zip rules.zip {proxy,direct,reject}-list.txt geoip.dat geosite.dat
          sha256sum geosite.dat > geosite.dat.sha256sum
          sha256sum rules.zip > rules.zip.sha256sum

      - name: Release and upload assets
        uses: softprops/action-gh-release@v1
        with:
          name: ${{ env.RELEASE_NAME }}
          tag_name: ${{ env.TAG_NAME }}
          draft: false
          prerelease: false
          files: |
            ./publish/*
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      - name: Git push assets to "release" branch
        run: |
          cd publish || exit 1
          git init
          git config --local user.name "actions"
          git config --local user.email "action@github.com"
          git checkout -b release
          git add .
          git commit -m "${{ env.RELEASE_NAME }}"
          git remote add origin "https://${{ github.actor }}:${{ secrets.GITHUB_TOKEN }}@github.com/${{ github.repository }}"
          git push -f -u origin release