From d4ed8d0a9e633c3e6df27f5bc42f163040410e41 Mon Sep 17 00:00:00 2001
From: Yanhu007 <huangfuyang900204@gmail.com>
Date: Wed, 15 Apr 2026 11:09:59 +0800
Subject: [PATCH] fix: handle multi-byte UTF-8 characters in DeleteWhiteSpace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DeleteWhiteSpace iterated over string bytes (str[i]) and cast each
byte to rune, which corrupts multi-byte UTF-8 characters like
Chinese, Japanese, Korean, emoji, etc.

  DeleteWhiteSpace(" 测试 测试 ") → "æµ\x8dè¯\x95æµ\x8dè¯\x95"

Fix: use range-based iteration which correctly yields Unicode runes.

  DeleteWhiteSpace(" 测试 测试 ") → "测试测试"

Fixes #29
---
 stringutils.go | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/stringutils.go b/stringutils.go
index 741bb53..8d36c11 100644
--- a/stringutils.go
+++ b/stringutils.go
@@ -110,17 +110,13 @@ func DeleteWhiteSpace(str string) string {
 	if str == "" {
 		return str
 	}
-	sz := len(str)
 	var chs bytes.Buffer
-	count := 0
-	for i := 0; i < sz; i++ {
-		ch := rune(str[i])
+	for _, ch := range str {
 		if !unicode.IsSpace(ch) {
 			chs.WriteRune(ch)
-			count++
 		}
 	}
-	if count == sz {
+	if chs.Len() == len(str) {
 		return str
 	}
 	return chs.String()