diff --git a/core/ffmpeg/ffmpeg.go b/core/ffmpeg/ffmpeg.go index bab3263a0..b88f5b1f8 100644 --- a/core/ffmpeg/ffmpeg.go +++ b/core/ffmpeg/ffmpeg.go @@ -2,6 +2,7 @@ package ffmpeg import ( "context" + "encoding/json" "errors" "fmt" "io" @@ -28,10 +29,21 @@ type TranscodeOptions struct { Offset int // seconds } +// AudioProbeResult contains authoritative audio stream properties from ffprobe. +type AudioProbeResult struct { + Codec string `json:"codec"` + Profile string `json:"profile,omitempty"` + BitRate int `json:"bitRate"` + SampleRate int `json:"sampleRate"` + BitDepth int `json:"bitDepth"` + Channels int `json:"channels"` +} + type FFmpeg interface { Transcode(ctx context.Context, opts TranscodeOptions) (io.ReadCloser, error) ExtractImage(ctx context.Context, path string) (io.ReadCloser, error) Probe(ctx context.Context, files []string) (string, error) + ProbeAudioStream(ctx context.Context, filePath string) (*AudioProbeResult, error) CmdPath() (string, error) IsAvailable() bool Version() string @@ -97,6 +109,82 @@ func (e *ffmpeg) Probe(ctx context.Context, files []string) (string, error) { return string(output), nil } +func (e *ffmpeg) ProbeAudioStream(ctx context.Context, filePath string) (*AudioProbeResult, error) { + cmdPath, err := ffmpegCmd() + if err != nil { + return nil, err + } + if err := fileExists(filePath); err != nil { + return nil, err + } + probePath := strings.Replace(cmdPath, "ffmpeg", "ffprobe", 1) + args := []string{probePath, "-v", "quiet", "-print_format", "json", "-show_streams", filePath} + log.Trace(ctx, "Executing ffprobe command", "args", args) + cmd := exec.CommandContext(ctx, args[0], args[1:]...) // #nosec + output, err := cmd.Output() + if err != nil { + return nil, fmt.Errorf("running ffprobe on %q: %w", filePath, err) + } + return parseProbeOutput(output) +} + +type probeOutput struct { + Streams []probeStream `json:"streams"` +} + +type probeStream struct { + CodecName string `json:"codec_name"` + CodecType string `json:"codec_type"` + Profile string `json:"profile"` + SampleRate string `json:"sample_rate"` + BitRate string `json:"bit_rate"` + Channels int `json:"channels"` + BitsPerSample int `json:"bits_per_sample"` + BitsPerRawSample string `json:"bits_per_raw_sample"` +} + +func parseProbeOutput(data []byte) (*AudioProbeResult, error) { + var output probeOutput + if err := json.Unmarshal(data, &output); err != nil { + return nil, fmt.Errorf("parsing ffprobe output: %w", err) + } + + for _, s := range output.Streams { + if s.CodecType != "audio" { + continue + } + bitDepth := s.BitsPerSample + if bitDepth == 0 && s.BitsPerRawSample != "" { + bitDepth, _ = strconv.Atoi(s.BitsPerRawSample) + } + result := &AudioProbeResult{ + Codec: s.CodecName, + Channels: s.Channels, + BitDepth: bitDepth, + } + + // Profile: "unknown" → empty + if s.Profile != "" && !strings.EqualFold(s.Profile, "unknown") { + result.Profile = s.Profile + } + + // Sample rate: string → int + if s.SampleRate != "" { + result.SampleRate, _ = strconv.Atoi(s.SampleRate) + } + + // Bit rate: bps string → kbps int + if s.BitRate != "" { + bps, _ := strconv.Atoi(s.BitRate) + result.BitRate = bps / 1000 + } + + return result, nil + } + + return nil, fmt.Errorf("no audio stream found in ffprobe output") +} + func (e *ffmpeg) CmdPath() (string, error) { return ffmpegCmd() } diff --git a/core/ffmpeg/ffmpeg_test.go b/core/ffmpeg/ffmpeg_test.go index 1649700d5..b272db274 100644 --- a/core/ffmpeg/ffmpeg_test.go +++ b/core/ffmpeg/ffmpeg_test.go @@ -358,6 +358,182 @@ var _ = Describe("ffmpeg", func() { }) }) + Describe("parseProbeOutput", func() { + It("parses MP3 with embedded artwork (real ffprobe output)", func() { + // Real: MP3 file with mjpeg artwork stream after audio + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"mp3","codec_long_name":"MP3 (MPEG audio layer 3)","codec_type":"audio",` + + `"sample_fmt":"fltp","sample_rate":"44100","channels":2,"channel_layout":"stereo",` + + `"bits_per_sample":0,"bit_rate":"198314","tags":{"encoder":"LAME3.99r"}},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline","width":400,"height":400}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("mp3")) + Expect(result.Profile).To(BeEmpty()) // MP3 has no profile field + Expect(result.SampleRate).To(Equal(44100)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(198)) // 198314 bps -> 198 kbps + Expect(result.BitDepth).To(Equal(0)) // lossy codec + }) + + It("parses AAC-LC in m4a container (real ffprobe output)", func() { + // Real: AAC LC file with profile and artwork + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"aac","codec_long_name":"AAC (Advanced Audio Coding)",` + + `"profile":"LC","codec_type":"audio","sample_fmt":"fltp","sample_rate":"44100",` + + `"channels":2,"channel_layout":"stereo","bits_per_sample":0,"bit_rate":"279958"},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("aac")) + Expect(result.Profile).To(Equal("LC")) + Expect(result.SampleRate).To(Equal(44100)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(279)) // 279958 bps -> 279 kbps + }) + + It("parses HE-AACv2 in mp4 container with video stream (real ffprobe output)", func() { + // Real: Fraunhofer HE-AACv2 sample (LFE-SBRstereo.mp4), video stream before audio + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"h264","codec_type":"video","profile":"Main"},` + + `{"index":1,"codec_name":"aac","codec_long_name":"AAC (Advanced Audio Coding)",` + + `"profile":"HE-AACv2","codec_type":"audio","sample_fmt":"fltp",` + + `"sample_rate":"48000","channels":2,"channel_layout":"stereo",` + + `"bits_per_sample":0,"bit_rate":"55999"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("aac")) + Expect(result.Profile).To(Equal("HE-AACv2")) + Expect(result.SampleRate).To(Equal(48000)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(55)) // 55999 bps -> 55 kbps + }) + + It("parses FLAC using bits_per_raw_sample (real ffprobe output)", func() { + // Real: FLAC reports bit depth in bits_per_raw_sample, not bits_per_sample + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"flac","codec_long_name":"FLAC (Free Lossless Audio Codec)",` + + `"codec_type":"audio","sample_fmt":"s16","sample_rate":"44100","channels":2,` + + `"channel_layout":"stereo","bits_per_sample":0,"bits_per_raw_sample":"16"},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("flac")) + Expect(result.SampleRate).To(Equal(44100)) + Expect(result.BitDepth).To(Equal(16)) // from bits_per_raw_sample + Expect(result.BitRate).To(Equal(0)) // FLAC has no bit_rate + Expect(result.Profile).To(BeEmpty()) // no profile field in real output + }) + + It("parses Opus without bit_rate (real ffprobe output)", func() { + // Real: Opus files often have no bit_rate field + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"opus","codec_long_name":"Opus (Opus Interactive Audio Codec)",` + + `"codec_type":"audio","sample_fmt":"fltp","sample_rate":"48000","channels":2,` + + `"channel_layout":"stereo","bits_per_sample":0}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("opus")) + Expect(result.SampleRate).To(Equal(48000)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(0)) + Expect(result.BitDepth).To(Equal(0)) + }) + + It("parses WAV/PCM with bits_per_sample (real ffprobe output)", func() { + // Real: WAV uses bits_per_sample directly + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"pcm_s16le","codec_long_name":"PCM signed 16-bit little-endian",` + + `"codec_type":"audio","sample_fmt":"s16","sample_rate":"44100","channels":2,` + + `"bits_per_sample":16,"bit_rate":"1411200"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("pcm_s16le")) + Expect(result.SampleRate).To(Equal(44100)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitDepth).To(Equal(16)) + Expect(result.BitRate).To(Equal(1411)) + }) + + It("parses ALAC in m4a container (real ffprobe output)", func() { + // Real: Beatles - You Can't Do That (2023 Mix), ALAC 16-bit + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"alac","codec_long_name":"ALAC (Apple Lossless Audio Codec)",` + + `"codec_type":"audio","sample_fmt":"s16p","sample_rate":"44100","channels":2,` + + `"channel_layout":"stereo","bits_per_sample":0,"bit_rate":"1011003",` + + `"bits_per_raw_sample":"16"},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("alac")) + Expect(result.BitDepth).To(Equal(16)) // from bits_per_raw_sample + Expect(result.SampleRate).To(Equal(44100)) + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(1011)) // 1011003 bps -> 1011 kbps + }) + + It("skips video-only streams", func() { + data := []byte(`{"streams":[{"index":0,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline"}]}`) + _, err := parseProbeOutput(data) + Expect(err).To(HaveOccurred()) + Expect(err.Error()).To(ContainSubstring("no audio stream")) + }) + + It("returns error for empty streams array", func() { + data := []byte(`{"streams":[]}`) + _, err := parseProbeOutput(data) + Expect(err).To(HaveOccurred()) + }) + + It("returns error for invalid JSON", func() { + data := []byte(`not json`) + _, err := parseProbeOutput(data) + Expect(err).To(HaveOccurred()) + }) + + It("parses HiRes multichannel FLAC (real ffprobe output)", func() { + // Real: Pink Floyd - 192kHz/24-bit/7.1 surround FLAC + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"flac","codec_long_name":"FLAC (Free Lossless Audio Codec)",` + + `"codec_type":"audio","sample_fmt":"s32","sample_rate":"192000","channels":8,` + + `"channel_layout":"7.1","bits_per_sample":0,"bits_per_raw_sample":"24"},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Progressive"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("flac")) + Expect(result.SampleRate).To(Equal(192000)) + Expect(result.BitDepth).To(Equal(24)) + Expect(result.Channels).To(Equal(8)) + Expect(result.BitRate).To(Equal(0)) + }) + + It("parses DSD/DSF file (real ffprobe output)", func() { + // Real: Yes - Owner of a Lonely Heart, DSD64 DSF + data := []byte(`{"streams":[` + + `{"index":0,"codec_name":"dsd_lsbf_planar",` + + `"codec_long_name":"DSD (Direct Stream Digital), least significant bit first, planar",` + + `"codec_type":"audio","sample_fmt":"fltp","sample_rate":"352800","channels":2,` + + `"channel_layout":"stereo","bits_per_sample":8,"bit_rate":"5644800"},` + + `{"index":1,"codec_name":"mjpeg","codec_type":"video","profile":"Baseline"}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Codec).To(Equal("dsd_lsbf_planar")) + Expect(result.BitDepth).To(Equal(8)) // DSD reports 8 bits_per_sample + Expect(result.SampleRate).To(Equal(352800)) // DSD64 sample rate + Expect(result.Channels).To(Equal(2)) + Expect(result.BitRate).To(Equal(5644)) // 5644800 bps -> 5644 kbps + }) + + It("clears 'unknown' profile to empty string", func() { + data := []byte(`{"streams":[{"index":0,"codec_name":"flac",` + + `"codec_type":"audio","profile":"unknown","sample_rate":"44100",` + + `"channels":2,"bits_per_sample":0}]}`) + result, err := parseProbeOutput(data) + Expect(err).ToNot(HaveOccurred()) + Expect(result.Profile).To(BeEmpty()) + }) + }) + Describe("FFmpeg", func() { Context("when FFmpeg is available", func() { var ff FFmpeg diff --git a/tests/mock_ffmpeg.go b/tests/mock_ffmpeg.go index 9b66134ec..a35defeae 100644 --- a/tests/mock_ffmpeg.go +++ b/tests/mock_ffmpeg.go @@ -16,9 +16,10 @@ func NewMockFFmpeg(data string) *MockFFmpeg { type MockFFmpeg struct { io.Reader - lock sync.Mutex - closed atomic.Bool - Error error + lock sync.Mutex + closed atomic.Bool + Error error + ProbeAudioResult *ffmpeg.AudioProbeResult } func (ff *MockFFmpeg) IsAvailable() bool { @@ -45,6 +46,13 @@ func (ff *MockFFmpeg) Probe(context.Context, []string) (string, error) { } return "", nil } +func (ff *MockFFmpeg) ProbeAudioStream(context.Context, string) (*ffmpeg.AudioProbeResult, error) { + if ff.Error != nil { + return nil, ff.Error + } + return ff.ProbeAudioResult, nil +} + func (ff *MockFFmpeg) CmdPath() (string, error) { if ff.Error != nil { return "", ff.Error