1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
|
/*
* Copyright (C) 2020 Apple Inc. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY APPLE INC. AND ITS CONTRIBUTORS ``AS IS''
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
* THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR ITS CONTRIBUTORS
* BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
* THE POSSIBILITY OF SUCH DAMAGE.
*/
#include "config.h"
#include "SpeechRecognitionCaptureSourceImpl.h"
#if ENABLE(MEDIA_STREAM)
#include "SpeechRecognitionUpdate.h"
#if PLATFORM(COCOA)
#include "CAAudioStreamDescription.h"
#include "WebAudioBufferList.h"
#endif
namespace WebCore {
#if !RELEASE_LOG_DISABLED
static const void* nextLogIdentifier()
{
static uint64_t logIdentifier = cryptographicallyRandomNumber();
return reinterpret_cast<const void*>(++logIdentifier);
}
static RefPtr<Logger>& nullLogger()
{
static NeverDestroyed<RefPtr<Logger>> logger;
return logger;
}
#endif
SpeechRecognitionCaptureSourceImpl::SpeechRecognitionCaptureSourceImpl(SpeechRecognitionConnectionClientIdentifier identifier, DataCallback&& dataCallback, StateUpdateCallback&& stateUpdateCallback, Ref<RealtimeMediaSource>&& source)
: m_clientIdentifier(identifier)
, m_dataCallback(WTFMove(dataCallback))
, m_stateUpdateCallback(WTFMove(stateUpdateCallback))
, m_source(WTFMove(source))
{
m_source->addAudioSampleObserver(*this);
m_source->addObserver(*this);
m_source->start();
#if !RELEASE_LOG_DISABLED
if (!nullLogger().get()) {
nullLogger() = Logger::create(this);
nullLogger()->setEnabled(this, false);
}
m_source->setLogger(*nullLogger(), nextLogIdentifier());
#endif
initializeWeakPtrFactory();
}
SpeechRecognitionCaptureSourceImpl::~SpeechRecognitionCaptureSourceImpl()
{
m_source->removeAudioSampleObserver(*this);
m_source->removeObserver(*this);
m_source->stop();
}
#if PLATFORM(COCOA)
bool SpeechRecognitionCaptureSourceImpl::updateDataSource(const CAAudioStreamDescription& audioDescription)
{
if (!m_dataSourceLock.tryLock())
return false;
Locker locker { AdoptLock, m_dataSourceLock };
auto dataSource = AudioSampleDataSource::create(audioDescription.sampleRate() * 1, m_source.get());
if (dataSource->setInputFormat(audioDescription)) {
callOnMainThread([this, weakThis = WeakPtr { *this }] {
if (weakThis)
m_stateUpdateCallback(SpeechRecognitionUpdate::createError(m_clientIdentifier, SpeechRecognitionError { SpeechRecognitionErrorType::AudioCapture, "Unable to set input format" }));
});
return false;
}
if (dataSource->setOutputFormat(audioDescription)) {
callOnMainThread([this, weakThis = WeakPtr { *this }] {
if (weakThis)
m_stateUpdateCallback(SpeechRecognitionUpdate::createError(m_clientIdentifier, SpeechRecognitionError { SpeechRecognitionErrorType::AudioCapture, "Unable to set output format" }));
});
return false;
}
m_dataSource = WTFMove(dataSource);
return true;
}
void SpeechRecognitionCaptureSourceImpl::pullSamplesAndCallDataCallback(const MediaTime& time, const CAAudioStreamDescription& audioDescription, size_t sampleCount)
{
ASSERT(isMainThread());
auto data = WebAudioBufferList { audioDescription, static_cast<uint32_t>(sampleCount) };
{
Locker locker { m_dataSourceLock };
m_dataSource->pullSamples(*data.list(), sampleCount, time.timeValue(), 0, AudioSampleDataSource::Copy);
}
m_dataCallback(time, data, audioDescription, sampleCount);
}
#endif
// FIXME: It is unclear why it is safe to use m_dataSource without locking in this function.
void SpeechRecognitionCaptureSourceImpl::audioSamplesAvailable(const MediaTime& time, const PlatformAudioData& data, const AudioStreamDescription& description, size_t sampleCount) WTF_IGNORES_THREAD_SAFETY_ANALYSIS
{
#if PLATFORM(COCOA)
DisableMallocRestrictionsForCurrentThreadScope scope;
ASSERT(description.platformDescription().type == PlatformDescription::CAAudioStreamBasicType);
auto audioDescription = toCAAudioStreamDescription(description);
if (!m_dataSource || !m_dataSource->inputDescription() || *m_dataSource->inputDescription() != description) {
if (!updateDataSource(audioDescription))
return;
}
m_dataSource->pushSamples(time, data, sampleCount);
callOnMainThread([weakThis = WeakPtr { *this }, time, audioDescription, sampleCount] {
if (weakThis)
weakThis->pullSamplesAndCallDataCallback(time, audioDescription, sampleCount);
});
#else
m_dataCallback(time, data, description, sampleCount);
#endif
}
void SpeechRecognitionCaptureSourceImpl::sourceStarted()
{
ASSERT(isMainThread());
m_stateUpdateCallback(SpeechRecognitionUpdate::create(m_clientIdentifier, SpeechRecognitionUpdateType::AudioStart));
}
void SpeechRecognitionCaptureSourceImpl::sourceStopped()
{
ASSERT(isMainThread());
ASSERT(m_source->captureDidFail());
m_stateUpdateCallback(SpeechRecognitionUpdate::createError(m_clientIdentifier, SpeechRecognitionError { SpeechRecognitionErrorType::AudioCapture, "Source is stopped" }));
}
void SpeechRecognitionCaptureSourceImpl::sourceMutedChanged()
{
ASSERT(isMainThread());
m_stateUpdateCallback(SpeechRecognitionUpdate::createError(m_clientIdentifier, SpeechRecognitionError { SpeechRecognitionErrorType::AudioCapture, "Source is muted" }));
}
void SpeechRecognitionCaptureSourceImpl::mute()
{
m_source->setMuted(true);
}
} // namespace WebCore
#endif
|
