定期更新数据并生成 gfw.pac

.github/workflows/auto-generate-pac.yml

@@ -20,13 +20,25 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v4
 
+      - name: Check if gfw.pac is in the commit
+        id: check-file
+        run: |
+          if git diff --name-only HEAD^ HEAD | grep -q 'gfw\.pac'; then
+            echo "file-exists=true" >> $GITHUB_ENV
+          else
+            echo "file-exists=false" >> $GITHUB_ENV
+          fi
+
       - name: Download the latest cn.txt
+        if: env.file-exists == 'false'
         run: curl -L https://raw.githubusercontent.com/Loyalsoldier/geoip/release/text/cn.txt -o cidrs-cn.txt
 
       - name: Run gfw-pac.py script
+        if: env.file-exists == 'false'
         run: ./gfw-pac.py -f gfw.pac -p "PROXY 127.0.0.1:3128" --proxy-domains=proxy-domains.txt --direct-domains=direct-domains.txt --localtld-domains=local-tlds.txt --ip-file=cidrs-cn.txt
 
       - name: Commit and push changes
+        if: env.file-exists == 'false'
         run: |
           last_commit_message=$(git log -1 --pretty=%B)
           commit_message=$([[ "${{ github.event_name }}" == "schedule" ]] && echo "定期更新数据并生成 gfw.pac" || echo "自动生成 gfw.pac: $last_commit_message")
@@ -37,6 +49,7 @@ jobs:
           git push
 
       - name: Trigger Auto-Release
+        if: env.file-exists == 'false'
         uses: benc-uk/workflow-dispatch@v1
         with:
           workflow: Auto Generate Release

.gitignore

@@ -43,3 +43,5 @@ $RECYCLE.BIN/
 
 # Windows shortcuts
 *.lnk
+
+test.js

direct-domains.txt

@@ -132,6 +132,7 @@ ocsp.digicert.cn
 ocsp.dcocsp.cn
 api.onedrive.com
 storage.live.com
+gr.global.aa-rt.sharepoint.com
 skyapi.live.net
 roaming.officeapps.live.com
 blob.core.windows.net

gfw-pac.py

@@ -27,16 +27,18 @@ def parse_args():
 def convert_cidr(cidr):
     if '/' in cidr:
         network = ipaddress.ip_network(cidr.strip(), strict=False)
-        network_address = network.network_address
+        network_address = int(network.network_address) >> (network.max_prefixlen - network.prefixlen)
-        prefixlen = network.prefixlen
     else:
         network = ipaddress.ip_address(cidr.strip())
         network_address = network
-        prefixlen = network.max_prefixlen
+    return hex(int(network_address))[2:]
-    if network.version == 4:
+
-        return hex(int(network_address))[2:] + '/' + str(prefixlen)
+def longest_common_prefix(str1, str2):
-    else:
+    min_length = min(len(str1), len(str2))
-        return network.compressed
+    for i in range(min_length):
+        if str1[i] != str2[i]:
+            return str1[:i]
+    return str1[:min_length]
 
 def generate_cnip_cidrs():
     """ 从文件中读取CIDR地址 """
@@ -47,6 +49,22 @@ def generate_cnip_cidrs():
         for cidr in cidrs:
             converted_cidrs.append(convert_cidr(cidr))
 
+    converted_cidrs.sort(key=lambda x: (len(x), x), reverse=False)
+    converted_cidrs_clone = converted_cidrs[:]
+    
+    lastFullCidr = ''
+    for i in range(len(converted_cidrs)):
+        prevCidr = converted_cidrs_clone[i-1] if i > 0 else ''
+        currentCidr = converted_cidrs[i]
+        if len(prevCidr) != len(currentCidr):
+            lastFullCidr = currentCidr
+            continue
+        prefix = longest_common_prefix(lastFullCidr, currentCidr)
+        if len(prefix) < len(lastFullCidr)//1.2:
+            lastFullCidr = currentCidr
+            continue
+        converted_cidrs[i] = '~' + currentCidr[len(prefix):]
+    
     cidr_list = ','.join(converted_cidrs)
     return f"'{cidr_list}'.split(',')"
 

pac-template

@@ -10,35 +10,45 @@ var localTlds = __LOCAL_TLDS__;
 
 var cidrs = __CIDRS__;
 
-var hasOwnProperty = Object.hasOwnProperty;
-
 function isIpAddress(ip) {
     return /^\d{1,3}(\.\d{1,3}){3}$/.test(ip) || /^([0-9a-fA-F]{0,4}:){1,7}[0-9a-fA-F]{0,4}$/.test(ip);
 }
 
 function RadixTree() {
-    this.root = {};
+    this.root = new Map();
 }
 
 RadixTree.prototype.insert = function(string) {
     var node = this.root;
     for (var i = 0; i < string.length; i++) {
         var char = string[i];
-        if (!node[char]) {
+        if (!node.has(char)) {
-            node[char] = {};
+            node.set(char, new Map());
         }
-        node = node[char];
+        node = node.get(char);
     }
 };
 
-RadixTree.prototype.to_list = function() {
+RadixTree.prototype.search = function(string) {
-    return this.root;
+    var currentNode = this.root;
-};
+    var isLastNode = false;
+    for (var i=0; i < string.length; i++) {
+        var char = string[i];
+        if (currentNode.has(char)) {
+            currentNode = currentNode.get(char);
+            isLastNode = currentNode.size === 0;
+        } else {
+            break;
+        }
+    }
+    return isLastNode;
+}
 
 function ipToBinary(ip) {
+    var bin = ''
     // Check if it's IPv4
     if (/^\d{1,3}(\.\d{1,3}){3}$/.test(ip)) {
-        return ip.split('.').map(function(num) {
+        bin = ip.split('.').map(function(num) {
             return ("00000000" + parseInt(num, 10).toString(2)).slice(-8);
         }).join('');
     } else if (/^([0-9a-fA-F]{0,4}:){1,7}[0-9a-fA-F]{0,4}$/.test(ip)) {
@@ -54,25 +64,11 @@ function ipToBinary(ip) {
         var fullAddress = left.concat(Array(zeroGroups + 1).join('0').split('')).concat(right);
         
         // Convert each group to binary and pad to 16 bits
-        return fullAddress.map(function(group) {
+        bin = fullAddress.map(function(group) {
             return ("0000000000000000" + parseInt(group || '0', 16).toString(2)).slice(-16);
         }).join('');
     }
-}
+    return bin.replace(/^0+/, '');
-
-function searchRadixTree(bits) {
-    var currentNode = radixTree;
-    var isLastNode = false;
-    for (var i=0; i<bits.length; i++) {
-        var char = bits[i];
-        if (currentNode[char]) {
-            currentNode = currentNode[char];
-            isLastNode = Object.keys(currentNode).length === 0;
-        } else {
-            break;
-        }
-    }
-    return isLastNode;
 }
   
 function isInDirectDomain(host) {
@@ -142,7 +138,7 @@ function FindProxyForURL(url, host) {
     } else if (isPrivateIp(ip)) {
         debug('域名解析后命中私有 IP 地址', host, ip);
         return direct;
-    } else if (searchRadixTree(ipToBinary(ip))) {
+    } else if (radixTree.search(ipToBinary(ip))) {
         debug('匹配到直连IP', host, ip);
         return direct;
     }
@@ -152,7 +148,7 @@ function FindProxyForURL(url, host) {
 }
 
 var allowAlert = true
-function debug(msg, host, ip) {
+function debug(msg, host='', ip='') {
     if (!allowAlert) {
         return
     }
@@ -166,19 +162,17 @@ function debug(msg, host, ip) {
 var radixTree = new RadixTree();
 
 (function () {
-    var startTime = new Date().getMilliseconds();
+    debug('开始生成 Radix Tree', 'PAC文件载入开始');
-    debug('开始生成 Radix Tree', 'PAC文件载入开始', startTime.toString());
+    lastFullPrefix = ''
     for (let i=0; i<cidrs.length; i++) {
-        var cidr = cidrs[i];
+        var prefix = cidrs[i];
-        var [ip, prefixLen] = cidr.split('/');
+        if (prefix.substring(0, 1) !== '~') {
-        if (!cidr.includes(':')) {
+            lastFullPrefix = prefix
-            var ip = ip.match(/.{1,2}/g).map(function(byte) {
+        } else {
-                return parseInt(byte, 16);
+            prefix = lastFullPrefix.substring(0, lastFullPrefix.length-prefix.length+1) + prefix.substring(1)
-            }).join('.');
         }
-        var bits = ipToBinary(ip).slice(0, prefixLen);
+        var bits = (parseInt(prefix, 16)).toString(2);
         radixTree.insert(bits);
     }
-    radixTree = radixTree.to_list();
     debug('Radix Tree 已生成', 'PAC文件载入完毕', cidrs.length.toString()+'个CIDR条目');
 })();