高ビットレート音声対応

.github/workflows/ci.yaml

@@ -22,6 +22,9 @@ jobs:
 
       - run: go fmt .
 
+      - name: Patch
+        run: make patch
+
       - uses: dominikh/[email protected]
         with:
           version: "2023.1.6"

CHANGES.md

@@ -11,6 +11,9 @@
 
 ## develop
 
+- [FIX] 高ビットレートの音声データの場合に、解析結果が送られてこない不具合を修正する
+  - @Hexa
+
 ### misc
 
 ## 2024.4.0

Makefile

@@ -4,7 +4,8 @@ all: patch
 	go build -o bin/suzu cmd/suzu/main.go
 
 patch:
-	patch -o oggwriter.go ./pion/oggwriter.go ./patch/oggwriter.go.patch
+	patch -o oggwriter.go ./_third_party/pion/oggwriter.go ./patch/oggwriter.go.patch
+	patch -o util.go ./_third_party/pion/util.go ./patch/util.go.patch
 
 
 test:

pion/oggwriter.go → _third_party/pion/oggwriter.go

@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: 2023 The Pion community <https://pion.ly>
+// SPDX-License-Identifier: MIT
+
 // Package oggwriter implements OGG media container writer
 package oggwriter
 
@@ -7,9 +10,9 @@ import (
 	"io"
 	"os"
 
-	"github.com/pion/randutil"
 	"github.com/pion/rtp"
 	"github.com/pion/rtp/codecs"
+	"github.com/pion/webrtc/v4/internal/util"
 )
 
 const (
@@ -65,7 +68,7 @@ func NewWith(out io.Writer, sampleRate uint32, channelCount uint16) (*OggWriter,
 		stream:        out,
 		sampleRate:    sampleRate,
 		channelCount:  channelCount,
-		serial:        randutil.NewMathRandomGenerator().Uint32(),
+		serial:        util.RandUint32(),
 		checksumTable: generateChecksumTable(),
 
 		// Timestamp and Granule MUST start from 1
@@ -146,22 +149,33 @@ const (
 
 func (i *OggWriter) createPage(payload []uint8, headerType uint8, granulePos uint64, pageIndex uint32) []byte {
 	i.lastPayloadSize = len(payload)
-	page := make([]byte, pageHeaderSize+1+i.lastPayloadSize)
+	nSegments := (len(payload) / 255) + 1 // A segment can be at most 255 bytes long.
+
+	page := make([]byte, pageHeaderSize+i.lastPayloadSize+nSegments)
 
 	copy(page[0:], pageHeaderSignature)                 // page headers starts with 'OggS'
 	page[4] = 0                                         // Version
 	page[5] = headerType                                // 1 = continuation, 2 = beginning of stream, 4 = end of stream
 	binary.LittleEndian.PutUint64(page[6:], granulePos) // granule position
 	binary.LittleEndian.PutUint32(page[14:], i.serial)  // Bitstream serial number
 	binary.LittleEndian.PutUint32(page[18:], pageIndex) // Page sequence number
-	page[26] = 1                                        // Number of segments in page, giving always 1 segment
-	page[27] = uint8(i.lastPayloadSize)                 // Segment Table inserting at 27th position since page header length is 27
-	copy(page[28:], payload)                            // inserting at 28th since Segment Table(1) + header length(27)
+	page[26] = uint8(nSegments)                         // Number of segments in page.
+
+	// Filling segment table with the lacing values.
+	// First (nSegments - 1) values will always be 255.
+	for i := 0; i < nSegments-1; i++ {
+		page[pageHeaderSize+i] = 255
+	}
+	// The last value will be the remainder.
+	page[pageHeaderSize+nSegments-1] = uint8(len(payload) % 255)
+
+	copy(page[pageHeaderSize+nSegments:], payload) // Payload goes after the segment table, so at pageHeaderSize+nSegments.
 
 	var checksum uint32
 	for index := range page {
 		checksum = (checksum << 8) ^ i.checksumTable[byte(checksum>>24)^page[index]]
 	}
+
 	binary.LittleEndian.PutUint32(page[22:], checksum) // Checksum - generating for page data and inserting at 22th position into 32 bits
 
 	return page

_third_party/pion/util.go

@@ -0,0 +1,75 @@
+// SPDX-FileCopyrightText: 2023 The Pion community <https://pion.ly>
+// SPDX-License-Identifier: MIT
+
+// Package util provides auxiliary functions internally used in webrtc package
+package util
+
+import (
+	"errors"
+	"strings"
+
+	"github.com/pion/randutil"
+)
+
+const (
+	runesAlpha = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+)
+
+// Use global random generator to properly seed by crypto grade random.
+var globalMathRandomGenerator = randutil.NewMathRandomGenerator() // nolint:gochecknoglobals
+
+// MathRandAlpha generates a mathematical random alphabet sequence of the requested length.
+func MathRandAlpha(n int) string {
+	return globalMathRandomGenerator.GenerateString(n, runesAlpha)
+}
+
+// RandUint32 generates a mathematical random uint32.
+func RandUint32() uint32 {
+	return globalMathRandomGenerator.Uint32()
+}
+
+// FlattenErrs flattens multiple errors into one
+func FlattenErrs(errs []error) error {
+	errs2 := []error{}
+	for _, e := range errs {
+		if e != nil {
+			errs2 = append(errs2, e)
+		}
+	}
+	if len(errs2) == 0 {
+		return nil
+	}
+	return multiError(errs2)
+}
+
+type multiError []error //nolint:errname
+
+func (me multiError) Error() string {
+	var errstrings []string
+
+	for _, err := range me {
+		if err != nil {
+			errstrings = append(errstrings, err.Error())
+		}
+	}
+
+	if len(errstrings) == 0 {
+		return "multiError must contain multiple error but is empty"
+	}
+
+	return strings.Join(errstrings, "\n")
+}
+
+func (me multiError) Is(err error) bool {
+	for _, e := range me {
+		if errors.Is(e, err) {
+			return true
+		}
+		if me2, ok := e.(multiError); ok { //nolint:errorlint
+			if me2.Is(err) {
+				return true
+			}
+		}
+	}
+	return false
+}

go.mod

@@ -8,12 +8,12 @@ require (
 	github.com/labstack/echo-contrib v0.17.1
 	github.com/labstack/echo/v4 v4.12.0
 	github.com/pion/randutil v0.1.0
-	github.com/pion/rtp v1.8.6
+	github.com/pion/rtp v1.8.9
 	github.com/rs/zerolog v1.32.0
 	github.com/stretchr/testify v1.9.0
 	golang.org/x/exp v0.0.0-20240416160154-fe59bbe5cc7f
-	golang.org/x/net v0.24.0
-	golang.org/x/sync v0.7.0
+	golang.org/x/net v0.29.0
+	golang.org/x/sync v0.8.0
 	google.golang.org/api v0.176.1
 	google.golang.org/grpc v1.63.2
 	google.golang.org/protobuf v1.33.0
@@ -46,6 +46,7 @@ require (
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
+	github.com/pion/webrtc/v4 v4.0.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/prometheus/client_golang v1.19.0 // indirect
 	github.com/prometheus/client_model v0.6.1 // indirect
@@ -59,10 +60,10 @@ require (
 	go.opentelemetry.io/otel v1.24.0 // indirect
 	go.opentelemetry.io/otel/metric v1.24.0 // indirect
 	go.opentelemetry.io/otel/trace v1.24.0 // indirect
-	golang.org/x/crypto v0.22.0 // indirect
+	golang.org/x/crypto v0.28.0 // indirect
 	golang.org/x/oauth2 v0.19.0 // indirect
-	golang.org/x/sys v0.19.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
+	golang.org/x/sys v0.26.0 // indirect
+	golang.org/x/text v0.19.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
 	google.golang.org/appengine v1.6.8 // indirect
 	google.golang.org/genproto v0.0.0-20240227224415-6ceb2ff114de // indirect

go.sum

@@ -203,6 +203,10 @@ github.com/pion/rtp v1.8.5 h1:uYzINfaK+9yWs7r537z/Rc1SvT8ILjBcmDOpJcTB+OU=
 github.com/pion/rtp v1.8.5/go.mod h1:pBGHaFt/yW7bf1jjWAoUjpSNoDnw98KTMg+jWWvziqU=
 github.com/pion/rtp v1.8.6 h1:MTmn/b0aWWsAzux2AmP8WGllusBVw4NPYPVFFd7jUPw=
 github.com/pion/rtp v1.8.6/go.mod h1:pBGHaFt/yW7bf1jjWAoUjpSNoDnw98KTMg+jWWvziqU=
+github.com/pion/rtp v1.8.9 h1:E2HX740TZKaqdcPmf4pw6ZZuG8u5RlMMt+l3dxeu6Wk=
+github.com/pion/rtp v1.8.9/go.mod h1:pBGHaFt/yW7bf1jjWAoUjpSNoDnw98KTMg+jWWvziqU=
+github.com/pion/webrtc/v4 v4.0.1 h1:6Unwc6JzoTsjxetcAIoWH81RUM4K5dBc1BbJGcF9WVE=
+github.com/pion/webrtc/v4 v4.0.1/go.mod h1:SfNn8CcFxR6OUVjLXVslAQ3a3994JhyE3Hw1jAuqEto=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@@ -308,6 +312,8 @@ golang.org/x/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
 golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
 golang.org/x/crypto v0.22.0 h1:g1v0xeRhjcugydODzvb3mEM9SQ0HGp9s/nh3COQ/C30=
 golang.org/x/crypto v0.22.0/go.mod h1:vr6Su+7cTlO45qkww3VDJlzDn0ctJvRgYbC2NvXHt+M=
+golang.org/x/crypto v0.28.0 h1:GBDwsMXVQi34v5CCYUm2jkJvu4cbtru2U4TN2PSyQnw=
+golang.org/x/crypto v0.28.0/go.mod h1:rmgy+3RHxRZMyY0jjAJShp2zgEdOqj2AO7U0pYmeQ7U=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20231214170342-aacd6d4b4611 h1:qCEDpW1G+vcj3Y7Fy52pEM1AWm3abj8WimGYejI3SC4=
 golang.org/x/exp v0.0.0-20231214170342-aacd6d4b4611/go.mod h1:iRJReGqOEeBhDZGkGbynYwcHlctCvnjTYIamk7uXpHI=
@@ -362,6 +368,8 @@ golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
 golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
 golang.org/x/net v0.24.0 h1:1PcaxkF854Fu3+lvBIx5SYn9wRlBzzcnHZSiaFFAb0w=
 golang.org/x/net v0.24.0/go.mod h1:2Q7sJY5mzlzWjKtYUEXSlBWCdyaioyXzRB2RtU8KVE8=
+golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo=
+golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.15.0 h1:s8pnnxNVzjWyrvYdFUQq5llS1PX2zhPXmccZv99h7uQ=
 golang.org/x/oauth2 v0.15.0/go.mod h1:q48ptWNTY5XWf+JNten23lcvHpLJ0ZSxF5ttTHKVCAM=
@@ -384,6 +392,8 @@ golang.org/x/sync v0.6.0 h1:5BMeUDZ7vkXGfEr1x9B4bRcTH4lpkTkpdh0T/J+qjbQ=
 golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
 golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ=
+golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -408,6 +418,8 @@ golang.org/x/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
 golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.19.0 h1:q5f1RH2jigJ1MoAWp2KTp3gm5zAGFUTarQZ5U386+4o=
 golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.26.0 h1:KHjCJyddX0LoSTb3J+vWpupP9p0oznkqVk/IfjymZbo=
+golang.org/x/sys v0.26.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -416,6 +428,8 @@ golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.3.8/go.mod h1:E6s5w1FMmriuDzIBO73fBruAKo1PCIq6d2Q6DHfQ8WQ=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.19.0 h1:kTxAhCbGbxhK0IwgSKiMO5awPoDQ0RpfiVYBfK860YM=
+golang.org/x/text v0.19.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
 golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

handler.go

@@ -326,13 +326,6 @@ func opus2ogg(ctx context.Context, opusReader io.Reader, oggWriter io.Writer, sa
 	}
 	defer o.Close()
 
-	if err := o.writeHeaders(); err != nil {
-		if w, ok := oggWriter.(*io.PipeWriter); ok {
-			w.CloseWithError(err)
-		}
-		return err
-	}
-
 	var r io.Reader
 	if c.AudioStreamingHeader {
 		r, err = readPacketWithHeader(opusReader)

oggwriter.go

@@ -1,3 +1,7 @@
+// SPDX-FileCopyrightText: 2023 The Pion community <https://pion.ly>
+// SPDX-License-Identifier: MIT
+
+// Package oggwriter implements OGG media container writer
 package suzu
 
 import (
@@ -6,7 +10,6 @@ import (
 	"io"
 	"os"
 
-	"github.com/pion/randutil"
 	"github.com/pion/rtp"
 	"github.com/pion/rtp/codecs"
 )
@@ -19,7 +22,6 @@ const (
 	idPageSignature                    = "OpusHead"
 	commentPageSignature               = "OpusTags"
 	pageHeaderSignature                = "OggS"
-	vendorName                         = "pion"
 )
 
 var (
@@ -65,21 +67,25 @@ func NewWith(out io.Writer, sampleRate uint32, channelCount uint16) (*OggWriter,
 		stream:        out,
 		sampleRate:    sampleRate,
 		channelCount:  channelCount,
-		serial:        randutil.NewMathRandomGenerator().Uint32(),
+		serial:        RandUint32(),
 		checksumTable: generateChecksumTable(),
 
 		// Timestamp and Granule MUST start from 1
 		// Only headers can have 0 values
 		previousTimestamp:       1,
 		previousGranulePosition: 1,
 	}
+	if err := writer.writeHeaders(); err != nil {
+		return nil, err
+	}
 
 	return writer, nil
 }
 
 /*
     ref: https://tools.ietf.org/html/rfc7845.html
     https://git.xiph.org/?p=opus-tools.git;a=blob;f=src/opus_header.c#l219
+
        Page 0         Pages 1 ... n        Pages (n+1) ...
     +------------+ +---+ +---+ ... +---+ +-----------+ +---------+ +--
     |            | |   | |   |     |   | |           | |         | |
@@ -95,6 +101,7 @@ func NewWith(out io.Writer, sampleRate uint32, channelCount uint16) (*OggWriter,
     |      ID header is contained on a single page
     |
     'Beginning Of Stream'
+
    Figure 1: Example Packet Organization for a Logical Ogg Opus Stream
 */
 
@@ -119,11 +126,11 @@ func (i *OggWriter) writeHeaders() error {
 	i.pageIndex++
 
 	// Comment Header
-	oggCommentHeader := make([]byte, (8 + len(vendorName) + 4 + 4))
-	copy(oggCommentHeader[0:], commentPageSignature)                             // Magic Signature 'OpusTags'
-	binary.LittleEndian.PutUint32(oggCommentHeader[8:], uint32(len(vendorName))) // Vendor Length
-	copy(oggCommentHeader[12:], vendorName)                                      // Vendor name 'pion'
-	binary.LittleEndian.PutUint32(oggCommentHeader[16:], 0)                      // User Comment List Length
+	oggCommentHeader := make([]byte, 21)
+	copy(oggCommentHeader[0:], commentPageSignature)        // Magic Signature 'OpusTags'
+	binary.LittleEndian.PutUint32(oggCommentHeader[8:], 5)  // Vendor Length
+	copy(oggCommentHeader[12:], "pion")                     // Vendor name 'pion'
+	binary.LittleEndian.PutUint32(oggCommentHeader[17:], 0) // User Comment List Length
 
 	// RFC specifies that the page where the CommentHeader completes should have a granule position of 0
 	data = i.createPage(oggCommentHeader, pageHeaderTypeContinuationOfStream, 0, i.pageIndex)
@@ -141,22 +148,33 @@ const (
 
 func (i *OggWriter) createPage(payload []uint8, headerType uint8, granulePos uint64, pageIndex uint32) []byte {
 	i.lastPayloadSize = len(payload)
-	page := make([]byte, pageHeaderSize+1+i.lastPayloadSize)
+	nSegments := (len(payload) / 255) + 1 // A segment can be at most 255 bytes long.
+
+	page := make([]byte, pageHeaderSize+i.lastPayloadSize+nSegments)
 
 	copy(page[0:], pageHeaderSignature)                 // page headers starts with 'OggS'
 	page[4] = 0                                         // Version
 	page[5] = headerType                                // 1 = continuation, 2 = beginning of stream, 4 = end of stream
 	binary.LittleEndian.PutUint64(page[6:], granulePos) // granule position
 	binary.LittleEndian.PutUint32(page[14:], i.serial)  // Bitstream serial number
 	binary.LittleEndian.PutUint32(page[18:], pageIndex) // Page sequence number
-	page[26] = 1                                        // Number of segments in page, giving always 1 segment
-	page[27] = uint8(i.lastPayloadSize)                 // Segment Table inserting at 27th position since page header length is 27
-	copy(page[28:], payload)                            // inserting at 28th since Segment Table(1) + header length(27)
+	page[26] = uint8(nSegments)                         // Number of segments in page.
+
+	// Filling segment table with the lacing values.
+	// First (nSegments - 1) values will always be 255.
+	for i := 0; i < nSegments-1; i++ {
+		page[pageHeaderSize+i] = 255
+	}
+	// The last value will be the remainder.
+	page[pageHeaderSize+nSegments-1] = uint8(len(payload) % 255)
+
+	copy(page[pageHeaderSize+nSegments:], payload) // Payload goes after the segment table, so at pageHeaderSize+nSegments.
 
 	var checksum uint32
 	for index := range page {
 		checksum = (checksum << 8) ^ i.checksumTable[byte(checksum>>24)^page[index]]
 	}
+
 	binary.LittleEndian.PutUint32(page[22:], checksum) // Checksum - generating for page data and inserting at 22th position into 32 bits
 
 	return page