mirror of
https://github.com/navidrome/navidrome.git
synced 2026-10-18 07:30:29 +00:00
The FLAC muxer writes STREAMINFO before it knows the stream length, then rewinds at the end to fill total_samples in. Navidrome pipes ffmpeg's stdout (-f flac -), which is not seekable, so ffmpeg logs "unable to rewrite FLAC header" and the field stays 0. A decoder needs total_samples to turn a timestamp into a byte offset, so it reports an unknown duration and refuses to seek. Online playback hides this because the client re-requests with a new offset each time, but an offline copy is permanently unseekable, the symptom reported against Symfonium where seeking a downloaded track jumps back to the start. Transcode now wraps its own output and rewrites total_samples as the first bytes flow past. This lives in core/ffmpeg because the unseekable pipe is that package's doing: buildDynamicArgs is what appends the trailing '-'. core/stream only learns a target format and hands back an io.ReadCloser, so compensating there leaked a transcoder implementation detail one layer up. TranscodeOptions grows a Duration field alongside the existing Offset, which also puts the duration-minus-offset arithmetic in the same function that emits -ss. The wrapper runs on every transcode rather than only FLAC targets: the format on a transcoding row is a declared target that nothing validates against the command's actual -f, so a custom command can emit FLAC under any target_format. The magic-byte check inside the wrapper is the authoritative test and costs a 26-byte peek. The output sample rate is read back out of the header ffmpeg just wrote rather than taken from the transcode options, so a resampled (-ar) output still gets the right count. Anything that is not a FLAC stream with an unset total_samples passes through byte for byte. Measured on a 177s source: before, total_samples=0 and ffprobe reported duration N/A; after, total_samples=7807023 and duration 177.03s, with the audio payload byte-identical. This affects every piped FLAC regardless of the source format; only FLAC stores an authoritative "unknown", which is why mp3, opus and aac survive the same pipe. No SEEKTABLE is synthesised and the MD5 is left zero: both are optional, and decoders binary-search using total_samples alone.
143 lines
3.9 KiB
Go
143 lines
3.9 KiB
Go
package ffmpeg
|
|
|
|
import (
|
|
"bytes"
|
|
"errors"
|
|
"io"
|
|
"os"
|
|
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
)
|
|
|
|
// Decoded independently so the specs do not mirror the production bit-twiddling.
|
|
func readSampleRate(b []byte) int {
|
|
return int(b[18])<<12 | int(b[19])<<4 | int(b[20])>>4
|
|
}
|
|
|
|
func readTotalSamples(b []byte) uint64 {
|
|
return uint64(b[21]&0x0F)<<32 | uint64(b[22])<<24 | uint64(b[23])<<16 | uint64(b[24])<<8 | uint64(b[25])
|
|
}
|
|
|
|
var _ = Describe("patchFLACDuration", func() {
|
|
var fileFLAC []byte
|
|
|
|
// Zeroing total_samples reproduces what a piped transcode emits.
|
|
pipedFLAC := func() []byte {
|
|
b := bytes.Clone(fileFLAC)
|
|
b[21] &= 0xF0
|
|
clear(b[22:26])
|
|
return b
|
|
}
|
|
|
|
readAll := func(in []byte, duration float32) []byte {
|
|
out, err := io.ReadAll(patchFLACDuration(io.NopCloser(bytes.NewReader(in)), duration))
|
|
Expect(err).ToNot(HaveOccurred())
|
|
return out
|
|
}
|
|
|
|
BeforeEach(func() {
|
|
var err error
|
|
fileFLAC, err = os.ReadFile("tests/fixtures/test.flac")
|
|
Expect(err).ToNot(HaveOccurred())
|
|
Expect(readSampleRate(fileFLAC)).To(Equal(44100)) // specs below hard-code this rate
|
|
})
|
|
|
|
It("fills in total_samples from the duration", func() {
|
|
out := readAll(pipedFLAC(), 1.0)
|
|
Expect(readTotalSamples(out)).To(Equal(uint64(44100)))
|
|
})
|
|
|
|
It("takes the sample rate from the header, not from the source file", func() {
|
|
in := pipedFLAC()
|
|
// Rewrite the header's rate to 48000, as -ar would.
|
|
in[18], in[19] = 0x0B, 0xB8
|
|
in[20] &= 0x0F
|
|
|
|
out := readAll(in, 2.0)
|
|
|
|
Expect(readSampleRate(out)).To(Equal(48000))
|
|
Expect(readTotalSamples(out)).To(Equal(uint64(96000)))
|
|
})
|
|
|
|
It("rounds to the nearest sample rather than truncating", func() {
|
|
// float32(0.7)*44100 is 30869.9995, so truncation would lose a sample.
|
|
out := readAll(pipedFLAC(), 0.7)
|
|
Expect(readTotalSamples(out)).To(Equal(uint64(30870)))
|
|
})
|
|
|
|
It("passes through when the duration overflows the 36-bit field", func() {
|
|
in := pipedFLAC()
|
|
Expect(readAll(in, 2e6)).To(Equal(in))
|
|
})
|
|
|
|
It("leaves everything after the header untouched", func() {
|
|
in := pipedFLAC()
|
|
out := readAll(in, 1.0)
|
|
Expect(out).To(HaveLen(len(in)))
|
|
Expect(out[26:]).To(Equal(in[26:]))
|
|
Expect(out[:18]).To(Equal(in[:18]))
|
|
})
|
|
|
|
It("leaves an already-populated total_samples alone", func() {
|
|
out := readAll(fileFLAC, 99.0)
|
|
Expect(out).To(Equal(fileFLAC))
|
|
})
|
|
|
|
It("passes through a stream that is not FLAC", func() {
|
|
in := []byte("ID3\x04\x00\x00\x00\x00\x00\x00 not a flac stream at all, just bytes")
|
|
Expect(readAll(in, 1.0)).To(Equal(in))
|
|
})
|
|
|
|
It("passes through when the first metadata block is not STREAMINFO", func() {
|
|
in := pipedFLAC()
|
|
in[4] = 0x04 // VORBIS_COMMENT
|
|
Expect(readAll(in, 1.0)).To(Equal(in))
|
|
})
|
|
|
|
It("passes through a stream shorter than the STREAMINFO fields it patches", func() {
|
|
in := pipedFLAC()[:20]
|
|
Expect(readAll(in, 1.0)).To(Equal(in))
|
|
})
|
|
|
|
It("passes through an empty stream", func() {
|
|
Expect(readAll(nil, 1.0)).To(BeEmpty())
|
|
})
|
|
|
|
It("passes through when the duration is zero or negative", func() {
|
|
in := pipedFLAC()
|
|
Expect(readAll(in, 0)).To(Equal(in))
|
|
Expect(readAll(in, -5)).To(Equal(in))
|
|
})
|
|
|
|
It("passes through when the header declares no sample rate", func() {
|
|
in := pipedFLAC()
|
|
in[18], in[19] = 0, 0
|
|
in[20] &= 0x0F
|
|
Expect(readAll(in, 1.0)).To(Equal(in))
|
|
})
|
|
|
|
It("propagates a read error from the underlying stream", func() {
|
|
_, err := io.ReadAll(patchFLACDuration(io.NopCloser(io.MultiReader(
|
|
bytes.NewReader(pipedFLAC()[:10]), &errReader{})), 1.0))
|
|
Expect(err).To(MatchError("boom"))
|
|
})
|
|
|
|
It("closes the underlying stream", func() {
|
|
c := &closeSpy{Reader: bytes.NewReader(pipedFLAC())}
|
|
Expect(patchFLACDuration(c, 1.0).Close()).To(Succeed())
|
|
Expect(c.closed).To(BeTrue())
|
|
})
|
|
})
|
|
|
|
type errReader struct{}
|
|
|
|
func (e *errReader) Read([]byte) (int, error) { return 0, errors.New("boom") }
|
|
|
|
type closeSpy struct {
|
|
io.Reader
|
|
closed bool
|
|
}
|
|
|
|
func (c *closeSpy) Close() error { c.closed = true; return nil }
|