change: mp4ff-wvttlister replacd by mp4ff-subslister

CHANGELOG.md

@@ -7,15 +7,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-
 ### Added
 
 - New TryDecodeMfro function
+- New mp4ff-subslister tool replacing mp4ff-wvttlister, but also supporting stpp
 
 ### Fixed
 
 - More robust check for mfro at the end of file
 
+### Removed
+
+- mp4ff-wvttlister tool removed and replaced by mp4ff-subslister
+
 ## [0.43.0] - 2024-04-04
 
 ### Added

README.md

@@ -21,7 +21,7 @@ Some useful command line tools are available in `cmd`.
 2. `mp4ff-pslister` extracts and displays SPS and PPS for AVC or HEVC in a mp4 or a bytestream (Annex B) file.
     Partial information is printed for HEVC.
 3. `mp4ff-nallister` lists NALUs and picture types for video in progressive or fragmented file
-4. `mp4ff-wvttlister` lists details of wvtt (WebVTT in ISOBMFF) samples
+4. `mp4ff-subslister` lists details of wvtt or stpp (WebVTT or TTML in ISOBMFF) subtitle samples
 5. `mp4ff-crop` shortens a progressive mp4 file to a specified duration
 6. `mp4ff-encrypt` encrypts a fragmented file using cenc or cbcs Common Encryption scheme
 7. `mp4ff-decrypt` decrypts a fragmented file encrypted using cenc or cbcs Common Encryption scheme

cmd/mp4ff-wvttlister/main.go → cmd/mp4ff-subslister/main.go

@@ -1,4 +1,4 @@
-// mp4ff-wvttlister - list wvtt (WebVTT in ISOBMFF) samples
+// mp4ff-subslister - list wvtt or stpp (WebVTT or TTML in ISOBMFF) samples
 package main
 
 import (
@@ -13,10 +13,11 @@ import (
 	"github.com/Eyevinn/mp4ff/mp4"
 )
 
-var usg = `Usage of mp4ff-wvttlister:
+var usg = `Usage of mp4ff-subslister:
 
-mp4ff-wvttlister lists and displays content of wvtt (WebVTT in ISOBMFF) samples.
-Uses track with given non-zero track ID or first wvtt track found in an asset.
+mp4ff-subslister lists and displays content of wvtt or stpp samples.
+These corresponds to WebVTT or TTML subtitles in ISOBMFF files.
+Uses track with given non-zero track ID or first subtitle track found in an asset.
 `
 
 var usage = func() {
@@ -35,7 +36,7 @@ func main() {
 	flag.Parse()
 
 	if *version {
-		fmt.Printf("mp4ff-wvttlister %s\n", mp4.GetVersion())
+		fmt.Printf("mp4ff-subslister %s\n", mp4.GetVersion())
 		os.Exit(0)
 	}
 
@@ -95,22 +96,20 @@ func findTrack(moov *mp4.MoovBox, hdlrType string, trackID uint32) (*mp4.TrakBox
 	return nil, fmt.Errorf("no matching track found")
 }
 
-func parseProgressiveMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples int) error {
-	wvttTrak, err := findTrack(f.Moov, "text", trackID)
-	if err != nil {
-		return err
-	}
-
-	stbl := wvttTrak.Mdia.Minf.Stbl
-	if stbl.Stsd.Wvtt == nil {
-		return fmt.Errorf("no wvtt track found")
-	}
+type subtitleTrack struct {
+	variant string
+	trak    *mp4.TrakBox
+}
 
-	fmt.Fprintf(w, "Track %d, timescale = %d\n", wvttTrak.Tkhd.TrackID, wvttTrak.Mdia.Mdhd.Timescale)
-	err = stbl.Stsd.Wvtt.VttC.Info(os.Stdout, "", "  ", "  ")
+func parseProgressiveMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples int) error {
+	subsTrak, err := findWvttTrack(f.Moov, w, trackID)
 	if err != nil {
-		return err
+		subsTrak, err = findStppTrack(f.Moov, w, trackID)
+		if err != nil {
+			return fmt.Errorf("no subtitle track found: %w", err)
+		}
 	}
+	stbl := subsTrak.trak.Mdia.Minf.Stbl
 	nrSamples := stbl.Stsz.SampleNumber
 	mdat := f.Mdat
 	mdatPayloadStart := mdat.PayloadAbsoluteOffset()
@@ -137,7 +136,12 @@ func parseProgressiveMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples
 		// Next find sample bytes as slice in mdat
 		offsetInMdatData := uint64(offset) - mdatPayloadStart
 		sample := mdat.Data[offsetInMdatData : offsetInMdatData+uint64(size)]
-		err = printWvttSample(w, sample, sampleNr, decTime+uint64(cto), dur)
+		switch subsTrak.variant {
+		case "wvtt":
+			err = printWvttSample(w, sample, sampleNr, decTime+uint64(cto), dur)
+		case "stpp":
+			err = printStppSample(w, sample, sampleNr, decTime+uint64(cto), dur)
+		}
 		if err != nil {
 			return err
 		}
@@ -148,27 +152,65 @@ func parseProgressiveMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples
 	return nil
 }
 
-func parseFragmentedMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples int) error {
-	var wvttTrex *mp4.TrexBox
-	if f.Init != nil { // Print vttC header and timescale if moov-box is present
-		wvttTrak, err := findTrack(f.Init.Moov, "text", trackID)
-		if err != nil {
-			return err
-		}
+func findWvttTrack(moov *mp4.MoovBox, w io.Writer, trackID uint32) (*subtitleTrack, error) {
+	subsTrak, err := findTrack(moov, "text", trackID)
+	if err != nil {
+		return nil, err
+	}
 
-		stbl := wvttTrak.Mdia.Minf.Stbl
-		if stbl.Stsd.Wvtt == nil {
-			return fmt.Errorf("no wvtt track found")
-		}
+	stbl := subsTrak.Mdia.Minf.Stbl
+	if stbl.Stsd.Wvtt == nil {
+		return nil, fmt.Errorf("no wvtt track found")
+	}
+
+	fmt.Fprintf(w, "Track %d, timescale = %d\n", subsTrak.Tkhd.TrackID, subsTrak.Mdia.Mdhd.Timescale)
+	err = stbl.Stsd.Wvtt.VttC.Info(os.Stdout, "", "  ", "  ")
+	if err != nil {
+		return nil, err
+	}
+	return &subtitleTrack{
+		variant: "wvtt",
+		trak:    subsTrak,
+	}, nil
+}
+
+func findStppTrack(moov *mp4.MoovBox, w io.Writer, trackID uint32) (*subtitleTrack, error) {
+	subsTrak, err := findTrack(moov, "subt", trackID)
+	if err != nil {
+		return nil, err
+	}
+
+	stbl := subsTrak.Mdia.Minf.Stbl
+	if stbl.Stsd.Stpp == nil {
+		return nil, fmt.Errorf("no stpp track found")
+	}
 
-		fmt.Fprintf(w, "Track %d, timescale = %d\n", wvttTrak.Tkhd.TrackID, wvttTrak.Mdia.Mdhd.Timescale)
-		err = stbl.Stsd.Wvtt.VttC.Info(w, "  ", "", "  ")
+	fmt.Fprintf(w, "Track %d, timescale = %d\n", subsTrak.Tkhd.TrackID, subsTrak.Mdia.Mdhd.Timescale)
+	err = stbl.Stsd.Stpp.Info(w, "", "  ", "  ")
+	if err != nil {
+		return nil, err
+	}
+	return &subtitleTrack{
+		variant: "stpp",
+		trak:    subsTrak,
+	}, nil
+}
+
+func parseFragmentedMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples int) error {
+	var subsTrex *mp4.TrexBox
+	var subsTrak *subtitleTrack
+	var err error
+	if f.Init != nil { // Print vttC header and timescale if moov-box is present
+		subsTrak, err = findWvttTrack(f.Moov, w, trackID)
 		if err != nil {
-			return err
+			subsTrak, err = findStppTrack(f.Moov, w, trackID)
+			if err != nil {
+				return fmt.Errorf("no subtitle track found: %w", err)
+			}
 		}
 		for _, trex := range f.Init.Moov.Mvex.Trexs {
-			if trex.TrackID == wvttTrak.Tkhd.TrackID {
-				wvttTrex = trex
+			if trex.TrackID == subsTrak.trak.Tkhd.TrackID {
+				subsTrex = trex
 			}
 		}
 	}
@@ -183,7 +225,7 @@ func parseFragmentedMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples i
 					tfraTime = entry.Time
 				}
 			}
-			fSamples, err := iFrag.GetFullSamples(wvttTrex)
+			fSamples, err := iFrag.GetFullSamples(subsTrex)
 			if err != nil {
 				return err
 			}
@@ -195,9 +237,28 @@ func parseFragmentedMp4(f *mp4.File, w io.Writer, trackID uint32, maxNrSamples i
 			iSamples = append(iSamples, fSamples...)
 		}
 	}
-	var err error
+	if subsTrak == nil {
+		if len(iSamples) == 0 {
+			return fmt.Errorf("no subtitle samples found")
+		}
+		variant := "stpp"
+		if iSamples[0].Data[0] == 0 { // Only wvtt start with a length field.
+			variant = "wvtt"
+		}
+
+		subsTrak = &subtitleTrack{
+			variant: variant,
+		}
+	}
 	for i, sample := range iSamples {
-		err = printWvttSample(w, sample.Data, i+1, sample.PresentationTime(), sample.Dur)
+		switch subsTrak.variant {
+		case "wvtt":
+			err = printWvttSample(w, sample.Data, i+1, sample.PresentationTime(), sample.Dur)
+		case "stpp":
+			err = printStppSample(w, sample.Data, i+1, sample.PresentationTime(), sample.Dur)
+		default:
+			return fmt.Errorf("unknown subtitle track type")
+		}
 
 		if err != nil {
 			return err
@@ -232,3 +293,9 @@ func printWvttSample(w io.Writer, sample []byte, nr int, pts uint64, dur uint32)
 	}
 	return nil
 }
+
+func printStppSample(w io.Writer, sample []byte, nr int, pts uint64, dur uint32) error {
+	fmt.Fprintf(w, "Sample %d, pts=%d, dur=%d\n", nr, pts, dur)
+	_, err := w.Write(sample)
+	return err
+}

cmd/mp4ff-wvttlister/main_test.go → cmd/mp4ff-subslister/main_test.go

@@ -7,9 +7,7 @@ import (
 	"testing"
 )
 
-var wantedSampleShort = `Track 1, timescale = 1000
-[vttC] size=14
- - config: "WEBVTT"
+var wantedWvttShort = `Track 1, timescale = 1000
 Sample 1, pts=0, dur=6640
 [vttc] size=52
   [sttg] size=18
@@ -67,20 +65,67 @@ var wantedMultiVttc = `Sample 1, pts=291054710760, dur=2560
    - cueText: "<c.white.bg_black>Ouais ! Belle gosse ! Voici 2 M !</c>"
 `
 
-func TestWvttLister(t *testing.T) {
+var wantedStppCombined = `Track 1, timescale = 90000
+  [stpp] size=43
+   - dataReferenceIndex: 1
+   - nameSpace: "http://www.w3.org/ns/ttml"
+   - schemaLocation: ""
+   - auxiliaryMimeTypes: ""
+Sample 1, pts=0, dur=540000
+<?xml version="1.0" encoding="UTF-8"?>
+<tt xmlns="http://www.w3.org/ns/ttml" xmlns:tts="http://www.w3.org/ns/ttml#styling" xml:lang="eng" ` +
+	`xmlns:ttp="http://www.w3.org/ns/ttml#parameter" xmlns:ttm="http://www.w3.org/ns/ttml#metadata" ` +
+	`xmlns:ebuttm="urn:ebu:tt:metadata" xmlns:ebutts="urn:ebu:tt:style" xml:space="default" ` +
+	`ttp:timeBase="media" ttp:cellResolution="32 15">
+  <head>
+    <metadata/>
+    <styling>
+      <style xml:id="default" tts:fontStyle="normal" tts:fontFamily="sansSerif" tts:fontSize="100%" ` +
+	`tts:lineHeight="normal" tts:textAlign="center" ebutts:linePadding="0.5c"/>
+      <style xml:id="white_black" tts:backgroundColor="black" tts:color="white"/>
+    </styling>
+    <layout>
+      <region xml:id="ttx_11" tts:origin="10% 84%" tts:extent="80% 15%" tts:overflow="visible"/>
+      <region xml:id="ttx_9" tts:origin="10% 70%" tts:extent="80% 15%" tts:overflow="visible"/>
+    </layout>
+  </head>
+  <body style="default">
+    <div>
+      <p begin="00:00:02.520" end="00:00:04.120" region="ttx_9" tts:textAlign="right">
+        <span style="white_black">-Pourquoi ?</span>
+      </p>
+      <p begin="00:00:02.520" end="00:00:04.120" region="ttx_11" tts:textAlign="center">
+        <span style="white_black">-J'ai...</span>
+      </p>
+      <p begin="00:00:04.520" end="00:00:06.600" region="ttx_9" tts:textAlign="center">
+        <span style="white_black">J'ai un tas de trucs à faire.</span>
+      </p>
+      <p begin="00:00:04.520" end="00:00:06.600" region="ttx_11" tts:textAlign="center">
+        <span style="white_black">-Non !</span>
+      </p>
+    </div>
+  </body>
+</tt>
+`
+
+func TestSubsLister(t *testing.T) {
 
 	testCases := []struct {
 		testFile string
 		wanted   string
 	}{
 		{
 			testFile: "testdata/sample_short.ismt",
-			wanted:   wantedSampleShort,
+			wanted:   wantedWvttShort,
 		},
 		{
 			testFile: "testdata/multi_vttc.mp4",
 			wanted:   wantedMultiVttc,
 		},
+		{
+			testFile: "testdata/stpp_combined.mp4",
+			wanted:   wantedStppCombined,
+		},
 	}
 
 	for _, tc := range testCases {
@@ -106,6 +151,9 @@ func TestWvttLister(t *testing.T) {
 					t.Errorf("line %d: got: %q\n wanted %q", i, gotLines[i], wantedLines[i])
 				}
 			}
+			if got != tc.wanted {
+				t.Errorf("got: %q\n wanted %q", got, tc.wanted)
+			}
 		})
 	}
 }