Sort and unique lists from domain-list-community

.github/workflows/build.yml

@@ -7,7 +7,6 @@ on:
       - master
       - hidden
     paths-ignore:
-      - ".github/**"
       - "**/README.md"
 jobs:
   build:
@@ -39,6 +38,10 @@ jobs:
           echo "::set-env name=LHIE1_RULES_PROXY_URL::https://raw.githubusercontent.com/lhie1/Rules/master/Surge/Surge%203/Provider/Proxy.list"
           echo "::set-env name=LHIE1_RULES_REJECT_URL::https://raw.githubusercontent.com/lhie1/Rules/master/Surge/Surge%203/Provider/Reject.list"
           echo "::set-env name=ADAWAY_REJECT_URL::https://raw.githubusercontent.com/AdAway/adaway.github.io/master/hosts.txt"
+          echo "::set-env name=EASYLISTCHINA_EASYLIST_REJECT_URL::https://easylist-downloads.adblockplus.org/easylistchina+easylist.txt"
+          echo "::set-env name=v2fly_direct::https://raw.githubusercontent.com/v2fly/domain-list-community/release/cn.txt"
+          echo "::set-env name=v2fly_proxy::https://raw.githubusercontent.com/v2fly/domain-list-community/release/geolocation-!cn.txt"
+          echo "::set-env name=v2fly_reject::https://raw.githubusercontent.com/v2fly/domain-list-community/release/category-ads-all.txt"
           echo "::set-env name=GOPATH::$(dirname $GITHUB_WORKSPACE)"
           echo "::add-path::$(dirname $GITHUB_WORKSPACE)/bin"
         shell: bash
@@ -57,16 +60,17 @@ jobs:
 
       - name: Generate geoip.dat file
         run: |
-          go get -u -v -insecure $GEOIP_REPO
+          go get -v -insecure $GEOIP_REPO
           geoip --country=./geoip/GeoLite2-Country-Locations-en.csv --ipv4=./geoip/GeoLite2-Country-Blocks-IPv4.csv --ipv6=./geoip/GeoLite2-Country-Blocks-IPv6.csv --ipv4CN=https://raw.githubusercontent.com/pexcn/daily/gh-pages/chnroute/chnroute.txt
 
       - name: Download geosite project
         run: |
-          go get -u -v -insecure $GEOSITE_REPO
+          go get -v -insecure $GEOSITE_REPO
 
       - 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 ${v2fly_direct} | perl -ne '/^(domain|full):([^:]+)(\n$|:@.+)/ && print "$2\n"' >> temp-direct.txt
 
       - name: Get and add proxy domains into temp-proxy.txt file
         run: |
@@ -80,12 +84,21 @@ jobs:
           curl -sSL $GEQ1AN_RULES_GLOBAL_MEDIA_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+GMedia/ {print $2}' >> temp-proxy.txt
           curl -sSL $GEQ1AN_RULES_OUTSIDE_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+Outside/ {print $2}' >> temp-proxy.txt
           curl -sSL $LHIE1_RULES_PROXY_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+/ {print $2}' >> temp-proxy.txt
+          curl -sSL ${v2fly_proxy} | perl -ne '/^(domain|full):([^:]+)(\n$|:@.+)/ && print "$2\n"' >> temp-proxy.txt
 
       - name: Get and add reject domains into temp-reject.txt file
         run: |
           curl -sSL $GEQ1AN_RULES_REJECT_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+AdBlock/ {print $2}' > temp-reject.txt
           curl -sSL $LHIE1_RULES_REJECT_URL | awk -F ',' '/^DOMAIN(,|\-SUFFIX,).+/ {print $2}' >> temp-reject.txt
           curl -sSL $ADAWAY_REJECT_URL | grep "127.0.0.1" | sed '1d' | awk '{print $2}' >> temp-reject.txt
+          curl -sSL $EASYLISTCHINA_EASYLIST_REJECT_URL | perl -ne '/^\|\|([-_0-9a-zA-Z]+(\.[-_0-9a-zA-Z]+){1,64})\^($|\$third-party$)/ && print "$1\n"' | perl -ne 'print if not /^[0-9]{1,3}(\.[0-9]{1,3}){3}$/' >> temp-reject.txt
+          curl -sSL ${v2fly_reject} | perl -ne '/^(domain|full):([^:]+)(\n$|:@.+)/ && print "$2\n"' >> temp-reject.txt
+
+      - name: Reserve `regex` and `keyword` type of rules from v2fly lists to "reserve" files
+        run: |
+          curl -sSL ${v2fly_direct} | perl -ne '/^((regex|keyword):[^:]+)(\n$|:@.+)/ && print "$1\n"' > direct-reserve.txt
+          curl -sSL ${v2fly_proxy} | perl -ne '/^((regex|keyword):[^:]+)(\n$|:@.+)/ && print "$1\n"' > proxy-reserve.txt
+          curl -sSL ${v2fly_reject} | perl -ne '/^((regex|keyword):[^:]+)(\n$|:@.+)/ && print "$1\n"' > reject-reserve.txt
 
       - name: Add proxy, direct and reject domains from "hidden" branch to appropriate temp files
         run: |
@@ -95,12 +108,9 @@ jobs:
 
       - name: Sort and generate redundant lists
         run: |
-          cat temp-proxy.txt | sort --ignore-case -u | 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"' > proxy-list-with-redundant
-          cat temp-proxy.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-excluse-list.txt
-          cat temp-direct.txt | sort --ignore-case -u | 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"' > direct-list-with-redundant
-          cat temp-direct.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-excluse-list.txt
-          cat temp-reject.txt | sort --ignore-case -u | 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"' > reject-list-with-redundant
-          cat temp-reject.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-excluse-list.txt
+          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: |
@@ -118,18 +128,31 @@ jobs:
           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 and remove domains end with ".cn" in proxy-list
+      - 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}' > $GOPATH/src/$GEOSITE_REPO/data/direct-list.txt
-          diff ./proxy-need-to-remove.txt ./proxy-list-without-redundant | awk '/^>/{print $2}' | perl -ne 'print if not /\.cn$/' > $GOPATH/src/$GEOSITE_REPO/data/proxy-list.txt
-          diff ./reject-need-to-remove.txt ./reject-list-without-redundant | awk '/^>/{print $2}' > $GOPATH/src/$GEOSITE_REPO/data/reject-list.txt
+          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: Add list into appropriate category file
+      - name: Remove domains end with ".cn" in "temp-geolocation-!cn.txt" and write lists to data directory
         run: |
-          cd $GOPATH/src/$GEOSITE_REPO/data
-          echo "include:proxy-list.txt" >> geolocation-\!cn
-          echo "include:direct-list.txt" >> cn
-          echo "include:reject-list.txt" >> category-ads-all
+          cat temp-cn.txt | sort --ignore-case -u | 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"' > $GOPATH/src/$GEOSITE_REPO/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-excluse-list.txt
+          cat temp-geolocation-\!cn.txt | sort --ignore-case -u | 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 "$1\n"' | perl -ne 'print if not /\.cn$/' > $GOPATH/src/$GEOSITE_REPO/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-excluse-list.txt
+          cat temp-category-ads-all.txt | sort --ignore-case -u | 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"' > $GOPATH/src/$GEOSITE_REPO/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-excluse-list.txt
+
+      - name: Add TLDs, `regex` and `keyword` type of rules back into "cn", "geolocation-!cn" and "category-ads-all" lists
+        run: |
+          cat $GOPATH/src/$GEOSITE_REPO/data/tld-cn | perl -ne '/^([-_.0-9a-zA-Z]+)/ && print "$1\n"' >> $GOPATH/src/$GEOSITE_REPO/data/cn
+          [ -f "direct-reserve.txt" ] && cat direct-reserve.txt >> $GOPATH/src/$GEOSITE_REPO/data/cn
+          cat $GOPATH/src/$GEOSITE_REPO/data/tld-\!cn | perl -ne '/^([-_.0-9a-zA-Z]+)/ && print "$1\n"' >> $GOPATH/src/$GEOSITE_REPO/data/geolocation-\!cn
+          [ -f "proxy-reserve.txt" ] && cat proxy-reserve.txt >> $GOPATH/src/$GEOSITE_REPO/data/geolocation-\!cn
+          [ -f "reject-reserve.txt" ] && cat reject-reserve.txt >> $GOPATH/src/$GEOSITE_REPO/data/category-ads-all
+          cp $GOPATH/src/$GEOSITE_REPO/data/cn direct-list.txt
+          cp $GOPATH/src/$GEOSITE_REPO/data/geolocation-\!cn proxy-list.txt
+          cp $GOPATH/src/$GEOSITE_REPO/data/category-ads-all reject-list.txt
 
       - name: Add `google-cn` and `apple-cn` sub-lists for custom routing settings for third-party users due to accessibility in China mainland
         run: |
@@ -145,7 +168,7 @@ jobs:
           install -Dp geoip.dat ./publish/geoip.dat
           install -Dp dlc.dat ./publish/geosite.dat
           install -p {proxy,direct,reject}-excluse-list.txt ./publish/
-          install -p $GOPATH/src/$GEOSITE_REPO/data/{proxy,direct,reject}-list.txt ./publish/
+          install -p {proxy,direct,reject}-list.txt ./publish/
           cd ./publish
           zip rules.zip {proxy,direct,reject}-list.txt geoip.dat geosite.dat
           sha256sum geoip.dat > geoip.dat.sha256sum

README.md

@@ -167,10 +167,10 @@ scoop install v2ray-rules-dat
 下面为自用 V2Ray 客户端完整配置，注意事项：
 
 - 由于下面客户端配置使用了 DoH DNS 功能，所以必须使用 v4.22.0 或更新版本的 [V2Ray](https://github.com/v2fly/v2ray-core/releases)
-- 下面客户端配置使 V2Ray 在本机开启 SOCKS 代理（监听 1080 端口）和 HTTP 代理（监听 2080 端口）
+- 下面客户端配置使 V2Ray 在本机开启 SOCKS 代理（监听 1080 端口）和 HTTP 代理（监听 2080 端口），允许局域网内其他设备连接并使用代理
 - BT 流量统统直连（实测依然会有部分 BT 流量走代理，尚不清楚是不是 V2Ray 的 bug。如果服务商禁止 BT 下载的话，请不要为下载软件设置代理）
 - 最后，不命中任何路由规则的请求和流量，统统走代理
-- `outbounds` 里的第一个大括号内的配置，即为 V2Ray 代理服务的配置。请根据自身需求进行修改，并参照 V2Ray 官网配置说明中的 [配置文件 > 文件格式 > OutboundObject](https://www.v2fly.org/chapter_02/01_overview.html#outboundobject) 部分进行补全
+- `outbounds` 里的第一个大括号内的配置，即为 V2Ray 代理服务的配置。请根据自身需求进行修改，并参照 V2Ray 官网配置说明中的 [配置 > Outbounds > OutboundObject](https://www.v2fly.org/chapter_02/outbounds.html#outboundobject) 部分进行补全
 
 ```json
 {
@@ -179,25 +179,29 @@ scoop install v2ray-rules-dat
   },
   "dns": {
     "hosts": {
-      "dns.google": "8.8.8.8"
+      "dns.google": "8.8.8.8",
+      "doh.pub": "119.29.29.29"
     },
     "servers": [
+      {
+        "address": "https+local://doh.pub/dns-query",
+        "domains": [
+          "geosite:cn"
+        ],
+        "expectIPs": [
+          "geoip:cn"
+        ]
+      },
       {
         "address": "https://1.1.1.1/dns-query",
         "domains": [
           "geosite:geolocation-!cn"
         ]
       },
-      "https://1.1.1.1/dns-query",
-      "https://dns.google/dns-query",
       {
-        "address": "114.114.114.114",
-        "port": 53,
+        "address": "https+local://223.5.5.5/dns-query",
         "domains": [
-          "geosite:cn"
-        ],
-        "expectIPs": [
-          "geoip:cn"
+          "geosite:tld-cn"
         ]
       }
     ]
@@ -205,7 +209,7 @@ scoop install v2ray-rules-dat
   "inbounds": [
     {
       "protocol": "socks",
-      "listen": "127.0.0.1",
+      "listen": "0.0.0.0",
       "port": 1080,
       "tag": "Socks-In",
       "settings": {
@@ -220,7 +224,7 @@ scoop install v2ray-rules-dat
     },
     {
       "protocol": "http",
-      "listen": "127.0.0.1",
+      "listen": "0.0.0.0",
       "port": 2080,
       "tag": "Http-In",
       "sniffing": {
@@ -261,7 +265,7 @@ scoop install v2ray-rules-dat
     }
   ],
   "routing": {
-    "domainStrategy": "AsIs",
+    "domainStrategy": "IPIfNonMatch",
     "rules": [
       {
         "type": "field",
@@ -285,11 +289,20 @@ scoop install v2ray-rules-dat
           "geosite:category-ads-all"
         ]
       },
+      {
+        "type": "field",
+        "outboundTag": "Proxy",
+        "domain": [
+          "full:www.icloud.com",
+          "domain:icloud-content.com"
+        ]
+      },
       {
         "type": "field",
         "outboundTag": "Direct",
         "domain": [
-          "geosite:tld-cn"
+          "geosite:tld-cn",
+          "geosite:icloud"
         ]
       },
       {
@@ -306,26 +319,6 @@ scoop install v2ray-rules-dat
           "geosite:cn"
         ]
       },
-      {
-        "type": "field",
-        "outboundTag": "Direct",
-        "ip": [
-          "223.5.5.5/32",
-          "119.29.29.29/32",
-          "180.76.76.76/32",
-          "114.114.114.114/32"
-        ]
-      },
-      {
-        "type": "field",
-        "outboundTag": "Proxy",
-        "ip": [
-          "1.1.1.1/32",
-          "1.0.0.1/32",
-          "8.8.8.8/32",
-          "8.8.4.4/32"
-        ]
-      },
       {
         "type": "field",
         "outboundTag": "Direct",