From db7c0359f438a5724d09bf3502d09d75431e5cd7 Mon Sep 17 00:00:00 2001
From: ZhouYongyou <128128010+zhouyongyou@users.noreply.github.com>
Date: Wed, 5 Nov 2025 01:02:49 +0800
Subject: [PATCH] fix(decision+news): correct Unicode regex escaping &
 precompile telegram patterns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

## Critical Fix: Unicode Regex Escaping

### decision/engine.go
- ❌ WRONG: `regexp.MustCompile(`[\u200B...]`)` (raw string, no escaping)
- ✅ FIXED: `regexp.MustCompile("[\u200B...]")` (double quotes, proper Unicode)

**Impact**: Backticks don't parse \uXXXX escape sequences in Go!
- Raw string: matches literal text "\u200B" (useless)
- Double quotes: matches Unicode characters U+200B, U+200C, U+200D, U+FEFF (correct)

### news/provider/telegram/telegram.go
- Move regex patterns to global precompiled variables
- Eliminates repeated compilation in stripHTML()

## Performance
- Regex compilation: O(n) → O(1)
- stripHTML() now uses precompiled patterns

## Testing
✅ Compilation successful
✅ Unicode characters properly matched
---
 decision/engine.go                 |  2 +-
 news/provider/telegram/telegram.go | 33 +++++++++++++++---------------
 2 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/decision/engine.go b/decision/engine.go
index a8dbdd5e..7f28738f 100644
--- a/decision/engine.go
+++ b/decision/engine.go
@@ -22,7 +22,7 @@ var (
 	reJSONArray      = regexp.MustCompile(`(?is)\[\s*\{.*?\}\s*\]`)
 	reArrayHead      = regexp.MustCompile(`^\[\s*\{`)
 	reArrayOpenSpace = regexp.MustCompile(`^\[\s+\{`)
-	reInvisibleRunes = regexp.MustCompile(`[\u200B\u200C\u200D\uFEFF]`)
+	reInvisibleRunes = regexp.MustCompile("[\u200B\u200C\u200D\uFEFF]")
 )
 
 // PositionInfo 持仓信息
diff --git a/news/provider/telegram/telegram.go b/news/provider/telegram/telegram.go
index 821cefa5..9d4ed252 100644
--- a/news/provider/telegram/telegram.go
+++ b/news/provider/telegram/telegram.go
@@ -14,6 +14,13 @@ import (
 	"github.com/samber/lo"
 )
 
+var (
+	reHTMLTag     = regexp.MustCompile(`\<[\S\s]+?\>`)
+	reStyleBlock  = regexp.MustCompile(`\<style[\S\s]+?\</style\>`)
+	reScriptBlock = regexp.MustCompile(`\<script[\S\s]+?\</script\>`)
+	reMultiSpace  = regexp.MustCompile(`\s{2,}`)
+)
+
 // Message 表示 Telegram 消息结构
 type Message struct {
 	MessageID string   `json:"messageId"`
@@ -268,27 +275,19 @@ func splitLast(s, sep string) []string {
 
 // stripHTML 移除字符串中的所有 HTML 标签，只保留纯文本
 func stripHTML(s string) string {
-	// 将HTML标签全转换成小写（确保匹配大小写不敏感的标签）
-	re := regexp.MustCompile(`\<[\S\s]+?\>`)
-	s = re.ReplaceAllStringFunc(s, strings.ToLower)
+	// 先將 HTML 標籤統一成小寫字母，方便後續匹配
+	s = reHTMLTag.ReplaceAllStringFunc(s, strings.ToLower)
 
-	// 去除 <style> 标签及其内容
-	re = regexp.MustCompile(`\<style[\S\s]+?\</style\>`)
-	s = re.ReplaceAllString(s, "")
+	// 移除樣式與腳本區塊
+	s = reStyleBlock.ReplaceAllString(s, "")
+	s = reScriptBlock.ReplaceAllString(s, "")
 
-	// 去除 <script> 标签及其内容
-	re = regexp.MustCompile(`\<script[\S\s]+?\</script\>`)
-	s = re.ReplaceAllString(s, "")
+	// 將剩餘標籤替換為換行，保留文本結構
+	s = reHTMLTag.ReplaceAllString(s, "\n")
 
-	// 去除所有尖括号内的 HTML 代码，并换成换行符
-	re = regexp.MustCompile(`\<[\S\s]+?\>`)
-	s = re.ReplaceAllString(s, "\n")
+	// 收斂連續空白為單一換行
+	s = reMultiSpace.ReplaceAllString(s, "\n")
 
-	// 去除连续的换行符和空白字符
-	re = regexp.MustCompile(`\s{2,}`)
-	s = re.ReplaceAllString(s, "\n")
-
-	// 去除首尾的空白字符
 	return strings.TrimSpace(s)
 }