Faster ipv4 parsing (#3413)

* Update ipv4 benchmark * Update ipv4 regex
colinhacks · Apr 18, 2024 · 27daef7 · 27daef7
1 parent 0ca48b2
commit 27daef7
Show file tree

Hide file tree

Showing 6 changed files with 132 additions and 2 deletions.
diff --git a/deno/lib/benchmarks/index.ts b/deno/lib/benchmarks/index.ts
@@ -2,6 +2,7 @@ import Benchmark from "benchmark";
 
 import datetimeBenchmarks from "./datetime.ts";
 import discriminatedUnionBenchmarks from "./discriminatedUnion.ts";
+import ipv4Benchmarks from "./ipv4.ts";
 import objectBenchmarks from "./object.ts";
 import primitiveBenchmarks from "./primitives.ts";
 import realworld from "./realworld.ts";
@@ -42,6 +43,9 @@ if (!argv.length) {
   if (argv.includes("--datetime")) {
     suites.push(...datetimeBenchmarks.suites);
   }
+  if (argv.includes("--ipv4")) {
+    suites.push(...ipv4Benchmarks.suites);
+  }
 }
 
 for (const suite of suites) {

diff --git a/deno/lib/benchmarks/ipv4.ts b/deno/lib/benchmarks/ipv4.ts
@@ -0,0 +1,60 @@
+import Benchmark from "benchmark";
+
+const suite = new Benchmark.Suite("ipv4");
+
+const DATA = "127.0.0.1";
+const ipv4RegexA =
+  /^(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))$/;
+const ipv4RegexB =
+  /^(?:(?:(?=(25[0-5]))\1|(?=(2[0-4][0-9]))\2|(?=(1[0-9]{2}))\3|(?=([0-9]{1,2}))\4)\.){3}(?:(?=(25[0-5]))\5|(?=(2[0-4][0-9]))\6|(?=(1[0-9]{2}))\7|(?=([0-9]{1,2}))\8)$/;
+const ipv4RegexC =
+  /^(?:(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)\.){3}(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)$/;
+const ipv4RegexD =
+  /^(\b25[0-5]|\b2[0-4][0-9]|\b[01]?[0-9][0-9]?)(\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)){3}$/;
+const ipv4RegexE =
+  /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)\.){3}(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)$/;
+const ipv4RegexF = /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)\.?\b){4}$/;
+const ipv4RegexG = /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)(\.(?!$)|$)){4}$/;
+const ipv4RegexH = /^((25[0-5]|(2[0-4]|1[0-9]|[1-9]|)[0-9])(\.(?!$)|$)){4}$/;
+const ipv4RegexI =
+  /^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.){3}(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$/;
+
+suite
+  .add("A", () => {
+    return ipv4RegexA.test(DATA);
+  })
+  .add("B", () => {
+    return ipv4RegexB.test(DATA);
+  })
+  .add("C", () => {
+    return ipv4RegexC.test(DATA);
+  })
+  .add("D", () => {
+    return ipv4RegexD.test(DATA);
+  })
+  .add("E", () => {
+    return ipv4RegexE.test(DATA);
+  })
+  .add("F", () => {
+    return ipv4RegexF.test(DATA);
+  })
+  .add("G", () => {
+    return ipv4RegexG.test(DATA);
+  })
+  .add("H", () => {
+    return ipv4RegexH.test(DATA);
+  })
+  .add("I", () => {
+    return ipv4RegexI.test(DATA);
+  })
+  .on("cycle", (e: Benchmark.Event) => {
+    console.log(`${suite.name!}: ${e.target}`);
+  });
+
+export default {
+  suites: [suite],
+};
+
+if (require.main === module) {
+  suite.run();
+}
diff --git a/deno/lib/types.ts b/deno/lib/types.ts
@@ -605,8 +605,9 @@ const emailRegex =
 const _emojiRegex = `^(\\p{Extended_Pictographic}|\\p{Emoji_Component})+$`;
 let emojiRegex: RegExp;
 
+// faster, simpler, safer
 const ipv4Regex =
-  /^(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))$/;
+  /^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.){3}(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$/;
 
 const ipv6Regex =
   /^(([a-f0-9]{1,4}:){7}|::([a-f0-9]{1,4}:){0,6}|([a-f0-9]{1,4}:){1}:([a-f0-9]{1,4}:){0,5}|([a-f0-9]{1,4}:){2}:([a-f0-9]{1,4}:){0,4}|([a-f0-9]{1,4}:){3}:([a-f0-9]{1,4}:){0,3}|([a-f0-9]{1,4}:){4}:([a-f0-9]{1,4}:){0,2}|([a-f0-9]{1,4}:){5}:([a-f0-9]{1,4}:){0,1})([a-f0-9]{1,4}|(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2})))$/;

diff --git a/src/benchmarks/index.ts b/src/benchmarks/index.ts
@@ -2,6 +2,7 @@ import Benchmark from "benchmark";
 
 import datetimeBenchmarks from "./datetime";
 import discriminatedUnionBenchmarks from "./discriminatedUnion";
+import ipv4Benchmarks from "./ipv4";
 import objectBenchmarks from "./object";
 import primitiveBenchmarks from "./primitives";
 import realworld from "./realworld";
@@ -42,6 +43,9 @@ if (!argv.length) {
   if (argv.includes("--datetime")) {
     suites.push(...datetimeBenchmarks.suites);
   }
+  if (argv.includes("--ipv4")) {
+    suites.push(...ipv4Benchmarks.suites);
+  }
 }
 
 for (const suite of suites) {

diff --git a/src/benchmarks/ipv4.ts b/src/benchmarks/ipv4.ts
@@ -0,0 +1,60 @@
+import Benchmark from "benchmark";
+
+const suite = new Benchmark.Suite("ipv4");
+
+const DATA = "127.0.0.1";
+const ipv4RegexA =
+  /^(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))$/;
+const ipv4RegexB =
+  /^(?:(?:(?=(25[0-5]))\1|(?=(2[0-4][0-9]))\2|(?=(1[0-9]{2}))\3|(?=([0-9]{1,2}))\4)\.){3}(?:(?=(25[0-5]))\5|(?=(2[0-4][0-9]))\6|(?=(1[0-9]{2}))\7|(?=([0-9]{1,2}))\8)$/;
+const ipv4RegexC =
+  /^(?:(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)\.){3}(?:25[0-5]|2[0-4]\d|1\d\d|[1-9]?\d)$/;
+const ipv4RegexD =
+  /^(\b25[0-5]|\b2[0-4][0-9]|\b[01]?[0-9][0-9]?)(\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)){3}$/;
+const ipv4RegexE =
+  /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)\.){3}(25[0-5]|(2[0-4]|1\d|[1-9]|)\d)$/;
+const ipv4RegexF = /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)\.?\b){4}$/;
+const ipv4RegexG = /^((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)(\.(?!$)|$)){4}$/;
+const ipv4RegexH = /^((25[0-5]|(2[0-4]|1[0-9]|[1-9]|)[0-9])(\.(?!$)|$)){4}$/;
+const ipv4RegexI =
+  /^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.){3}(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$/;
+
+suite
+  .add("A", () => {
+    return ipv4RegexA.test(DATA);
+  })
+  .add("B", () => {
+    return ipv4RegexB.test(DATA);
+  })
+  .add("C", () => {
+    return ipv4RegexC.test(DATA);
+  })
+  .add("D", () => {
+    return ipv4RegexD.test(DATA);
+  })
+  .add("E", () => {
+    return ipv4RegexE.test(DATA);
+  })
+  .add("F", () => {
+    return ipv4RegexF.test(DATA);
+  })
+  .add("G", () => {
+    return ipv4RegexG.test(DATA);
+  })
+  .add("H", () => {
+    return ipv4RegexH.test(DATA);
+  })
+  .add("I", () => {
+    return ipv4RegexI.test(DATA);
+  })
+  .on("cycle", (e: Benchmark.Event) => {
+    console.log(`${suite.name!}: ${e.target}`);
+  });
+
+export default {
+  suites: [suite],
+};
+
+if (require.main === module) {
+  suite.run();
+}
diff --git a/src/types.ts b/src/types.ts
@@ -605,8 +605,9 @@ const emailRegex =
 const _emojiRegex = `^(\\p{Extended_Pictographic}|\\p{Emoji_Component})+$`;
 let emojiRegex: RegExp;
 
+// faster, simpler, safer
 const ipv4Regex =
-  /^(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))$/;
+  /^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])\.){3}(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|[1-9][0-9]|[0-9])$/;
 
 const ipv6Regex =
   /^(([a-f0-9]{1,4}:){7}|::([a-f0-9]{1,4}:){0,6}|([a-f0-9]{1,4}:){1}:([a-f0-9]{1,4}:){0,5}|([a-f0-9]{1,4}:){2}:([a-f0-9]{1,4}:){0,4}|([a-f0-9]{1,4}:){3}:([a-f0-9]{1,4}:){0,3}|([a-f0-9]{1,4}:){4}:([a-f0-9]{1,4}:){0,2}|([a-f0-9]{1,4}:){5}:([a-f0-9]{1,4}:){0,1})([a-f0-9]{1,4}|(((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2}))\.){3}((25[0-5])|(2[0-4][0-9])|(1[0-9]{2})|([0-9]{1,2})))$/;