⚡ Bolt: urlEncodePath() 최적화 - 문자열 할당 및 루프 개선

.jules/bolt.md

@@ -9,3 +9,6 @@
 ## 2024-07-26 - Intermediate String Allocations
 **Learning:** Chained `.replace()` calls on strings in Kotlin (e.g. for HTML escaping) allocate an intermediate String at each step, significantly impacting performance and garbage collection on hot paths with many elements.
 **Action:** Replace chained `.replace()` calls with a single-pass loop that iterates over characters once, lazily initializing a `StringBuilder` to append the transformed output.
+## 2024-05-24 - Optimize URL encoding performance in Kotlin
+**Learning:** Chained string manipulations like `.toString(16).padStart(2, '0').toUpperCase()` inside a tight loop create multiple intermediate string objects, leading to high memory allocation and slow execution. Also, using `.forEach` on a ByteArray creates an iterator object overhead compared to a direct loop using `indices`.
+**Action:** Replace complex string manipulations for hex encoding with a pre-calculated `HEX_ARRAY` lookup and bitwise operators (`ushr 4` and `and 0x0f`), use `bytes.indices` for loops over primitive arrays to avoid iterator allocation, and pre-size StringBuilders based on expected output length (`bytes.size * 2`) to minimize resizing overhead.

src/main/kotlin/html4tree/main.kt

@@ -80,22 +80,29 @@ fun String.escapeHtml(): String {
     return sb?.toString() ?: this
 }
 
+// ⚡ Bolt Performance Optimization: Use pre-calculated hex array and indices loop
+// Reduces intermediate string allocations from .toString(16).padStart(2, '0').toUpperCase()
+// and avoids iterator creation by using a direct index loop.
+internal val HEX_ARRAY = "0123456789ABCDEF".toCharArray()
+
 fun String.urlEncodePath(): String {
-    val encoded = StringBuilder()
-    this.toByteArray(Charsets.UTF_8).forEach {
-        val byte = it.toInt() and 0xff
-        val isUnreserved = (byte in 'A'.toInt()..'Z'.toInt()) ||
-                           (byte in 'a'.toInt()..'z'.toInt()) ||
-                           (byte in '0'.toInt()..'9'.toInt()) ||
-                           byte == '-'.toInt() ||
-                           byte == '.'.toInt() ||
-                           byte == '_'.toInt() ||
-                           byte == '~'.toInt()
+    val bytes = this.toByteArray(Charsets.UTF_8)
+    val encoded = java.lang.StringBuilder(bytes.size * 2)
+    for (i in bytes.indices) {
+        val byte = bytes[i].toInt() and 0xff
+        val isUnreserved = (byte in 65..90) || // 'A'..'Z'
+                           (byte in 97..122) || // 'a'..'z'
+                           (byte in 48..57) || // '0'..'9'
+                           byte == 45 || // '-'
+                           byte == 46 || // '.'
+                           byte == 95 || // '_'
+                           byte == 126   // '~'
         if (isUnreserved) {
             encoded.append(byte.toChar())
         } else {
             encoded.append('%')
-            encoded.append(byte.toString(16).padStart(2, '0').toUpperCase())
+            encoded.append(HEX_ARRAY[byte ushr 4])
+            encoded.append(HEX_ARRAY[byte and 0x0f])
         }
     }
     return encoded.toString()

src/test/kotlin/html4tree/MainTest.kt

@@ -310,4 +310,10 @@ class MainTest {
         assertTrue(excluded.contains("test.txt"))
     }
 
+
+    @Test
+    fun testGetHexArray() {
+        assertEquals('0', HEX_ARRAY[0])
+        assertEquals('F', HEX_ARRAY[15])
+    }
 }