feat(filter): 增强WordsLenFilter支持中英文混合文本

改进WordsLenFilter函数，使其能够正确处理中英文混合的提交信息：
1. 对于中文文本统计字符数
2. 对于英文文本统计单词数
3. 对于混合文本同时统计中文字符和英文单词

Author: inhere

chlog/filter.go

@@ -2,6 +2,7 @@ package chlog
 
 import (
 	"strings"
+	"unicode"
 
 	"github.com/gookit/goutil/strutil"
 )
@@ -12,8 +13,7 @@ type ItemFilter interface {
 	Handle(li *LogItem) bool
 }
 
-// ItemFilterFunc define. return false to filter item.
-// type LineFilterFunc func(line string) bool
+// ItemFilterFunc define. return False to filter(discard) item.
 type ItemFilterFunc func(li *LogItem) bool
 
 // Handle filtering
@@ -37,9 +37,36 @@ func MsgLenFilter(minLen int) ItemFilterFunc {
 }
 
 // WordsLenFilter handler
+//  - For English text: counts words separated by whitespace
+//  - For Chinese text: counts characters (runes) since Chinese doesn't use spaces
+//  - For mixed text: counts both English words and Chinese characters
 func WordsLenFilter(minLen int) ItemFilterFunc {
 	return func(li *LogItem) bool {
-		return len(strutil.Split(li.Msg, " ")) > minLen
+		msg := li.Msg
+		wordCount := 0
+		inWord := false
+		hasChinese := false
+
+		for _, r := range msg {
+			if unicode.Is(unicode.Han, r) {
+				hasChinese = true
+				wordCount++
+				inWord = false
+			} else if unicode.IsSpace(r) {
+				inWord = false
+			} else {
+				if !inWord {
+					wordCount++
+					inWord = true
+				}
+			}
+		}
+
+		if !hasChinese {
+			return len(strutil.Split(msg, " ")) > minLen
+		}
+
+		return wordCount > minLen
 	}
 }
 

chlog/filter_test.go

@@ -16,3 +16,27 @@ func TestKeywordsFilter(t *testing.T) {
 	li = &chlog.LogItem{Msg: "chore: fix gh action script error"}
 	assert.True(t, fl(li))
 }
+
+func TestWordsLenFilter(t *testing.T) {
+	fl := chlog.WordsLenFilter(3)
+
+	// 英文测试：4个单词，应该通过
+	li := &chlog.LogItem{Msg: "fix: update config file"}
+	assert.True(t, fl(li))
+
+	// 英文测试：2个单词，应该被过滤
+	li = &chlog.LogItem{Msg: "fix bug"}
+	assert.False(t, fl(li))
+
+	// 中文测试：超过3个字符，应该通过
+	li = &chlog.LogItem{Msg: "修复了一个重要的配置问题"}
+	assert.True(t, fl(li))
+
+	// 中文测试：少于3个字符，应该被过滤
+	li = &chlog.LogItem{Msg: "修bug"}
+	assert.False(t, fl(li))
+
+	// 中英混合测试
+	li = &chlog.LogItem{Msg: "fix 修复了问题"}
+	assert.True(t, fl(li))
+}