Duplicate content for small text to have better encoding detection

go-gitea · Sep 29, 2018 · fab01bb · fab01bb
1 parent 5c4dac7
commit fab01bb
Showing 1 changed file with 11 additions and 1 deletion.
diff --git a/modules/base/tool.go b/modules/base/tool.go
@@ -59,7 +59,17 @@ func DetectEncoding(content []byte) (string, error) {
 		return "UTF-8", nil
 	}
 
-	result, err := chardet.NewTextDetector().DetectBest(content)
+	var detectContent []byte
+	if len(content) < 1024 {
+		times := 1024 / len(content)
+		detectContent = make([]byte, 0, times*len(content))
+		for i := 0; i < times; i++ {
+			detectContent = append(detectContent, content...)
+		}
+	} else {
+		detectContent = content
+	}
+	result, err := chardet.NewTextDetector().DetectBest(detectContent)
 	if err != nil {
 		return "", err
 	}