Detect ogg mime-type as audio or video (#26494)

"ogg" is just a "container" format for audio and video.

Golang's `DetectContentType` only reports "application/ogg" for
potential ogg files.

Actually it could do more "guess" to see whether it is a audio file or a
video file.

Author: wxiaoguang

modules/typesniffer/typesniffer.go

@@ -71,7 +71,7 @@ func (ct SniffedType) IsRepresentableAsText() bool {
 	return ct.IsText() || ct.IsSvgImage()
 }
 
-// IsBrowsableType returns whether a non-text type can be displayed in a browser
+// IsBrowsableBinaryType returns whether a non-text type can be displayed in a browser
 func (ct SniffedType) IsBrowsableBinaryType() bool {
 	return ct.IsImage() || ct.IsSvgImage() || ct.IsPDF() || ct.IsVideo() || ct.IsAudio()
 }
@@ -116,6 +116,17 @@ func DetectContentType(data []byte) SniffedType {
 		}
 	}
 
+	if ct == "application/ogg" {
+		dataHead := data
+		if len(dataHead) > 256 {
+			dataHead = dataHead[:256] // only need to do a quick check for the file header
+		}
+		if bytes.Contains(dataHead, []byte("theora")) || bytes.Contains(dataHead, []byte("dirac")) {
+			ct = "video/ogg" // ogg is only used for some video formats, and it's not popular
+		} else {
+			ct = "audio/ogg" // for most cases, it is used as an audio container
+		}
+	}
 	return SniffedType{ct}
 }
 

modules/typesniffer/typesniffer_test.go

@@ -6,6 +6,7 @@ package typesniffer
 import (
 	"bytes"
 	"encoding/base64"
+	"encoding/hex"
 	"strings"
 	"testing"
 
@@ -121,3 +122,15 @@ func TestDetectContentTypeFromReader(t *testing.T) {
 	assert.NoError(t, err)
 	assert.True(t, st.IsAudio())
 }
+
+func TestDetectContentTypeOgg(t *testing.T) {
+	oggAudio, _ := hex.DecodeString("4f67675300020000000000000000352f0000000000007dc39163011e01766f72626973000000000244ac0000000000000071020000000000b8014f6767530000")
+	st, err := DetectContentTypeFromReader(bytes.NewReader(oggAudio))
+	assert.NoError(t, err)
+	assert.True(t, st.IsAudio())
+
+	oggVideo, _ := hex.DecodeString("4f676753000200000000000000007d9747ef000000009b59daf3012a807468656f7261030201001e00110001e000010e00020000001e00000001000001000001")
+	st, err = DetectContentTypeFromReader(bytes.NewReader(oggVideo))
+	assert.NoError(t, err)
+	assert.True(t, st.IsVideo())
+}