feat: decode percent-encoded path in getPath

honojs · May 16, 2024 · f79832d · f79832d
1 parent d87d996
commit f79832d
Show file tree

Hide file tree

Showing 2 changed files with 65 additions and 7 deletions.
diff --git a/benchmarks/utils/src/get-path.ts b/benchmarks/utils/src/get-path.ts
@@ -5,15 +5,60 @@ bench('noop', () => {})
 const request = new Request('http://localhost/about/me')
 
 group('getPath', () => {
-  bench('slice + indexOf', () => {
+  bench('slice + indexOf : w/o decodeURI', () => {
     const url = request.url
     const queryIndex = url.indexOf('?', 8)
-    url.slice(url.indexOf('/', 8), queryIndex === -1 ? undefined : queryIndex)
+    return url.slice(url.indexOf('/', 8), queryIndex === -1 ? undefined : queryIndex)
   })
 
-  bench('regexp', () => {
+  bench('regexp : w/o decodeURI', () => {
     const match = request.url.match(/^https?:\/\/[^/]+(\/[^?]*)/)
-    match ? match[1] : ''
+    return match ? match[1] : ''
+  })
+
+  bench('slice + indexOf', () => {
+    const url = request.url
+    const queryIndex = url.indexOf('?', 8)
+    const path = url.slice(url.indexOf('/', 8), queryIndex === -1 ? undefined : queryIndex)
+    return path.includes('%') ? decodeURIComponent(path) : path
+  })
+
+  bench('slice + for-loop + flag', () => {
+    const url = request.url
+    let start = url.indexOf('/', 8)
+    let i = start
+    let hasPercentEncoding = false
+    for (; i < url.length; i++) {
+      const charCode = url.charCodeAt(i)
+      if (charCode === 37) {
+        // '%'
+        hasPercentEncoding = true
+      } else if (charCode === 63) {
+        // '?'
+        break
+      }
+    }
+    return hasPercentEncoding ? decodeURIComponent(url.slice(start, i)) : url.slice(start, i)
+  })
+
+  bench('slice + for-loop + immediate return', () => {
+    const url = request.url
+    const start = url.indexOf('/', 8)
+    let i = start
+    for (; i < url.length; i++) {
+      const charCode = url.charCodeAt(i)
+      if (charCode === 37) {
+        // '%'
+        // If the path contains percent encoding, use `indexOf()` to find '?' and return the result immediately.
+        // Although this is a performance disadvantage, it is acceptable since we prefer cases that do not include percent encoding.
+        const queryIndex = url.indexOf('?', i)
+        return decodeURIComponent(url.slice(start, queryIndex === -1 ? undefined : queryIndex))
+      } else if (charCode === 63) {
+        // '?'
+        break
+      }
+    }
+    return url.slice(start, i)
   })
 })
 

diff --git a/src/utils/url.ts b/src/utils/url.ts
@@ -70,10 +70,23 @@ export const getPattern = (label: string): Pattern | null => {
 }
 
 export const getPath = (request: Request): string => {
-  // Optimized: indexOf() + slice() is faster than RegExp
   const url = request.url
-  const queryIndex = url.indexOf('?', 8)
-  return url.slice(url.indexOf('/', 8), queryIndex === -1 ? undefined : queryIndex)
+  const start = url.indexOf('/', 8)
+  let i = start
+  for (; i < url.length; i++) {
+    const charCode = url.charCodeAt(i)
+    if (charCode === 37) {
+      // '%'
+      // If the path contains percent encoding, use `indexOf()` to find '?' and return the result immediately.
+      // Although this is a performance disadvantage, it is acceptable since we prefer cases that do not include percent encoding.
+      const queryIndex = url.indexOf('?', i)
+      return decodeURIComponent(url.slice(start, queryIndex === -1 ? undefined : queryIndex))
+    } else if (charCode === 63) {
+      // '?'
+      break
+    }
+  }
+  return url.slice(start, i)
 }
 
 export const getQueryStrings = (url: string): string => {