Android/frameworks_base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support for CharSequences in the V1 API.

Browse Source 
Two newly deprecated methods:
  - TextToSpeech.speak (over TextToSpeech.speak with mandatory utteranceId)
  - SynthesisRequest.getText (over SynthesisRequest.getCharSequenceText)

Change-Id: I8a75ed335c91074c72d6ef374ff8b9c79a7c208d
This commit is contained in:
Niels Egberts
2014-06-25 15:30:44 +01:00
parent 7028946402
commit df7deefe8e
5 changed files with 270 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
core/java/android/speech/tts/ITextToSpeechService.aidl
View File

@@ -36,8 +36,10 @@ interface ITextToSpeechService {
* @param text The text to synthesize.
* @param queueMode Determines what to do to requests already in the queue.
* @param param Request parameters.
* @param utteranceId Unique identifier of synthesized utterance.
*/
int speak(in IBinder callingInstance, in String text, in int queueMode, in Bundle params);
int speak(in IBinder callingInstance, in CharSequence text, in int queueMode, in Bundle params,
String utteranceId);
/**
* Tells the engine to synthesize some speech and write it to a file.
@@ -47,10 +49,11 @@ interface ITextToSpeechService {
* @param text The text to synthesize.
* @param fileDescriptor The file descriptor to write the synthesized audio to. Has to be
writable.
* @param utteranceId Unique identifier of synthesized utterance.
* @param param Request parameters.
*/
int synthesizeToFileDescriptor(in IBinder callingInstance, in String text,
in ParcelFileDescriptor fileDescriptor, in Bundle params);
int synthesizeToFileDescriptor(in IBinder callingInstance, in CharSequence text,
in ParcelFileDescriptor fileDescriptor, in Bundle params, String utteranceId);
/**
* Plays an existing audio resource.
@@ -59,9 +62,11 @@ interface ITextToSpeechService {
* TextToSpeech object.
* @param audioUri URI for the audio resource (a file or android.resource URI)
* @param queueMode Determines what to do to requests already in the queue.
* @param utteranceId Unique identifier of synthesized utterance.
* @param param Request parameters.
*/
int playAudio(in IBinder callingInstance, in Uri audioUri, in int queueMode, in Bundle params);
int playAudio(in IBinder callingInstance, in Uri audioUri, in int queueMode, in Bundle params,
String utteranceId);
/**
* Plays silence.

19
core/java/android/speech/tts/SynthesisRequest.java
View File

@@ -34,7 +34,7 @@ import android.os.Bundle;
* and {@link TextToSpeech#synthesizeToFile}.
*/
public final class SynthesisRequest {
private final String mText;
private final CharSequence mText;
private final Bundle mParams;
private String mLanguage;
private String mCountry;
@@ -49,10 +49,25 @@ public final class SynthesisRequest {
mParams = new Bundle(params);
}
public SynthesisRequest(CharSequence text, Bundle params) {
mText = text;
// Makes a copy of params.
mParams = new Bundle(params);
}
/**
* Gets the text which should be synthesized.
* @deprecated As of API level 20, replaced by {@link #getCharSequenceText}.
*/
@Deprecated
public String getText() {
return mText.toString();
}
/**
* Gets the text which should be synthesized.
*/
public String getText() {
public CharSequence getCharSequenceText() {
return mText;
}

241
core/java/android/speech/tts/TextToSpeech.java
View File

@@ -593,7 +593,7 @@ public class TextToSpeech {
// too.
private final boolean mUseFallback;
private final Map<String, Uri> mEarcons;
private final Map<String, Uri> mUtterances;
private final Map<CharSequence, Uri> mUtterances;
private final Bundle mParams = new Bundle();
private final TtsEngines mEnginesHelper;
private final String mPackageName;
@@ -644,7 +644,7 @@ public class TextToSpeech {
mUseFallback = useFallback;
mEarcons = new HashMap<String, Uri>();
mUtterances = new HashMap<String, Uri>();
mUtterances = new HashMap<CharSequence, Uri>();
mUtteranceProgressListener = null;
mEnginesHelper = new TtsEngines(mContext);
@@ -824,6 +824,40 @@ public class TextToSpeech {
}
}
/**
* Adds a mapping between a CharSequence (may be spanned with TtsSpans) of text
* and a sound resource in a package. After a call to this method, subsequent calls to
* {@link #speak(String, int, HashMap)} will play the specified sound resource
* if it is available, or synthesize the text it is missing.
*
* @param text
* The string of text. Example: <code>"south_south_east"</code>
*
* @param packagename
* Pass the packagename of the application that contains the
* resource. If the resource is in your own application (this is
* the most common case), then put the packagename of your
* application here.<br/>
* Example: <b>"com.google.marvin.compass"</b><br/>
* The packagename can be found in the AndroidManifest.xml of
* your application.
* <p>
* <code>&lt;manifest xmlns:android=&quot;...&quot;
* package=&quot;<b>com.google.marvin.compass</b>&quot;&gt;</code>
* </p>
*
* @param resourceId
* Example: <code>R.raw.south_south_east</code>
*
* @return Code indicating success or failure. See {@link #ERROR} and {@link #SUCCESS}.
*/
public int addSpeech(CharSequence text, String packagename, int resourceId) {
synchronized (mStartLock) {
mUtterances.put(text, makeResourceUri(packagename, resourceId));
return SUCCESS;
}
}
/**
* Adds a mapping between a string of text and a sound file. Using this, it
* is possible to add custom pronounciations for a string of text.
@@ -846,6 +880,28 @@ public class TextToSpeech {
}
}
/**
* Adds a mapping between a CharSequence (may be spanned with TtsSpans and a sound file.
* Using this, it is possible to add custom pronounciations for a string of text.
* After a call to this method, subsequent calls to {@link #speak(String, int, HashMap)}
* will play the specified sound resource if it is available, or synthesize the text it is
* missing.
*
* @param text
* The string of text. Example: <code>"south_south_east"</code>
* @param filename
* The full path to the sound file (for example:
* "/sdcard/mysounds/hello.wav")
*
* @return Code indicating success or failure. See {@link #ERROR} and {@link #SUCCESS}.
*/
public int addSpeech(CharSequence text, String filename) {
synchronized (mStartLock) {
mUtterances.put(text, Uri.parse(filename));
return SUCCESS;
}
}
/**
* Adds a mapping between a string of text and a sound resource in a
@@ -909,6 +965,51 @@ public class TextToSpeech {
.build();
}
/**
* Speaks the text using the specified queuing strategy and speech parameters, the text may
* be spanned with TtsSpans.
* This method is asynchronous, i.e. the method just adds the request to the queue of TTS
* requests and then returns. The synthesis might not have finished (or even started!) at the
* time when this method returns. In order to reliably detect errors during synthesis,
* we recommend setting an utterance progress listener (see
* {@link #setOnUtteranceProgressListener}) and using the
* {@link Engine#KEY_PARAM_UTTERANCE_ID} parameter.
*
* @param text The string of text to be spoken. No longer than
* {@link #getMaxSpeechInputLength()} characters.
* @param queueMode The queuing strategy to use, {@link #QUEUE_ADD} or {@link #QUEUE_FLUSH}.
* @param params Parameters for the request. Can be null.
* Supported parameter names:
* {@link Engine#KEY_PARAM_STREAM},
* {@link Engine#KEY_PARAM_VOLUME},
* {@link Engine#KEY_PARAM_PAN}.
* Engine specific parameters may be passed in but the parameter keys
* must be prefixed by the name of the engine they are intended for. For example
* the keys "com.svox.pico_foo" and "com.svox.pico:bar" will be passed to the
* engine named "com.svox.pico" if it is being used.
* @param utteranceId An unique identifier for this request.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the speak operation.
*/
public int speak(final CharSequence text,
final int queueMode,
final HashMap<String, String> params,
final String utteranceId) {
return runAction(new Action<Integer>() {
@Override
public Integer run(ITextToSpeechService service) throws RemoteException {
Uri utteranceUri = mUtterances.get(text);
if (utteranceUri != null) {
return service.playAudio(getCallerIdentity(), utteranceUri, queueMode,
getParams(params), utteranceId);
} else {
return service.speak(getCallerIdentity(), text, queueMode, getParams(params),
utteranceId);
}
}
}, ERROR, "speak");
}
/**
* Speaks the string using the specified queuing strategy and speech parameters.
* This method is asynchronous, i.e. the method just adds the request to the queue of TTS
@@ -933,20 +1034,50 @@ public class TextToSpeech {
* engine named "com.svox.pico" if it is being used.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the speak operation.
* @deprecated As of API level 20, replaced by
* {@link #speak(CharSequence, int, HashMap, String)}.
*/
@Deprecated
public int speak(final String text, final int queueMode, final HashMap<String, String> params) {
return speak(text, queueMode, params, params == null ? null : params.get(Engine.KEY_PARAM_UTTERANCE_ID));
}
/**
* Plays the earcon using the specified queueing mode and parameters.
* The earcon must already have been added with {@link #addEarcon(String, String)} or
* {@link #addEarcon(String, String, int)}.
* This method is asynchronous, i.e. the method just adds the request to the queue of TTS
* requests and then returns. The synthesis might not have finished (or even started!) at the
* time when this method returns. In order to reliably detect errors during synthesis,
* we recommend setting an utterance progress listener (see
* {@link #setOnUtteranceProgressListener}) and using the
* {@link Engine#KEY_PARAM_UTTERANCE_ID} parameter.
*
* @param earcon The earcon that should be played
* @param queueMode {@link #QUEUE_ADD} or {@link #QUEUE_FLUSH}.
* @param params Parameters for the request. Can be null.
* Supported parameter names:
* {@link Engine#KEY_PARAM_STREAM},
* Engine specific parameters may be passed in but the parameter keys
* must be prefixed by the name of the engine they are intended for. For example
* the keys "com.svox.pico_foo" and "com.svox.pico:bar" will be passed to the
* engine named "com.svox.pico" if it is being used.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the playEarcon operation.
*/
public int playEarcon(final String earcon, final int queueMode,
final HashMap<String, String> params, final String utteranceId) {
return runAction(new Action<Integer>() {
@Override
public Integer run(ITextToSpeechService service) throws RemoteException {
Uri utteranceUri = mUtterances.get(text);
if (utteranceUri != null) {
return service.playAudio(getCallerIdentity(), utteranceUri, queueMode,
getParams(params));
} else {
return service.speak(getCallerIdentity(), text, queueMode, getParams(params));
Uri earconUri = mEarcons.get(earcon);
if (earconUri == null) {
return ERROR;
}
return service.playAudio(getCallerIdentity(), earconUri, queueMode,
getParams(params), utteranceId);
}
}, ERROR, "speak");
}, ERROR, "playEarcon");
}
/**
@@ -972,20 +1103,44 @@ public class TextToSpeech {
* engine named "com.svox.pico" if it is being used.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the playEarcon operation.
* @deprecated As of API level 20, replaced by
* {@link #playEarcon(String, int, HashMap, String)}.
*/
@Deprecated
public int playEarcon(final String earcon, final int queueMode,
final HashMap<String, String> params) {
return playEarcon(earcon, queueMode, params, params == null ? null : params.get(Engine.KEY_PARAM_UTTERANCE_ID));
}
/**
* Plays silence for the specified amount of time using the specified
* queue mode.
* This method is asynchronous, i.e. the method just adds the request to the queue of TTS
* requests and then returns. The synthesis might not have finished (or even started!) at the
* time when this method returns. In order to reliably detect errors during synthesis,
* we recommend setting an utterance progress listener (see
* {@link #setOnUtteranceProgressListener}) and using the
* {@link Engine#KEY_PARAM_UTTERANCE_ID} parameter.
*
* @param durationInMs The duration of the silence.
* @param queueMode {@link #QUEUE_ADD} or {@link #QUEUE_FLUSH}.
* @param params Parameters for the request. Can be null.
* Engine specific parameters may be passed in but the parameter keys
* must be prefixed by the name of the engine they are intended for. For example
* the keys "com.svox.pico_foo" and "com.svox.pico:bar" will be passed to the
* engine named "com.svox.pico" if it is being used.
* @param utteranceId An unique identifier for this request.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the playSilence operation.
*/
public int playSilence(final long durationInMs, final int queueMode,
final HashMap<String, String> params, final String utteranceId) {
return runAction(new Action<Integer>() {
@Override
public Integer run(ITextToSpeechService service) throws RemoteException {
Uri earconUri = mEarcons.get(earcon);
if (earconUri == null) {
return ERROR;
}
return service.playAudio(getCallerIdentity(), earconUri, queueMode,
getParams(params));
return service.playSilence(getCallerIdentity(), durationInMs, queueMode, utteranceId);
}
}, ERROR, "playEarcon");
}, ERROR, "playSilence");
}
/**
@@ -1009,16 +1164,13 @@ public class TextToSpeech {
* engine named "com.svox.pico" if it is being used.
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the playSilence operation.
* @deprecated As of API level 20, replaced by
* {@link #playEarcon(String, int, HashMap, String)}.
*/
@Deprecated
public int playSilence(final long durationInMs, final int queueMode,
final HashMap<String, String> params) {
return runAction(new Action<Integer>() {
@Override
public Integer run(ITextToSpeechService service) throws RemoteException {
return service.playSilence(getCallerIdentity(), durationInMs, queueMode,
params == null ? null : params.get(Engine.KEY_PARAM_UTTERANCE_ID));
}
}, ERROR, "playSilence");
return playSilence(durationInMs, queueMode, params, params == null ? null : params.get(Engine.KEY_PARAM_UTTERANCE_ID));
}
/**
@@ -1294,25 +1446,22 @@ public class TextToSpeech {
* requests and then returns. The synthesis might not have finished (or even started!) at the
* time when this method returns. In order to reliably detect errors during synthesis,
* we recommend setting an utterance progress listener (see
* {@link #setOnUtteranceProgressListener}) and using the
* {@link Engine#KEY_PARAM_UTTERANCE_ID} parameter.
* {@link #setOnUtteranceProgressListener}).
*
* @param text The text that should be synthesized. No longer than
* {@link #getMaxSpeechInputLength()} characters.
* @param params Parameters for the request. Can be null.
* Supported parameter names:
* {@link Engine#KEY_PARAM_UTTERANCE_ID}.
* Engine specific parameters may be passed in but the parameter keys
* must be prefixed by the name of the engine they are intended for. For example
* the keys "com.svox.pico_foo" and "com.svox.pico:bar" will be passed to the
* engine named "com.svox.pico" if it is being used.
* @param filename Absolute file filename to write the generated audio data to.It should be
* something like "/sdcard/myappsounds/mysound.wav".
*
* @param utteranceId An unique identifier for this request.
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the synthesizeToFile operation.
*/
public int synthesizeToFile(final String text, final HashMap<String, String> params,
final String filename) {
public int synthesizeToFile(final CharSequence text, final HashMap<String, String> params,
final String filename, final String utteranceId) {
return runAction(new Action<Integer>() {
@Override
public Integer run(ITextToSpeechService service) throws RemoteException {
@@ -1329,7 +1478,7 @@ public class TextToSpeech {
ParcelFileDescriptor.MODE_CREATE |
ParcelFileDescriptor.MODE_TRUNCATE);
returnValue = service.synthesizeToFileDescriptor(getCallerIdentity(), text,
fileDescriptor, getParams(params));
fileDescriptor, getParams(params), utteranceId);
fileDescriptor.close();
return returnValue;
} catch (FileNotFoundException e) {
@@ -1343,6 +1492,36 @@ public class TextToSpeech {
}, ERROR, "synthesizeToFile");
}
/**
* Synthesizes the given text to a file using the specified parameters.
* This method is asynchronous, i.e. the method just adds the request to the queue of TTS
* requests and then returns. The synthesis might not have finished (or even started!) at the
* time when this method returns. In order to reliably detect errors during synthesis,
* we recommend setting an utterance progress listener (see
* {@link #setOnUtteranceProgressListener}) and using the
* {@link Engine#KEY_PARAM_UTTERANCE_ID} parameter.
*
* @param text The text that should be synthesized. No longer than
* {@link #getMaxSpeechInputLength()} characters.
* @param params Parameters for the request. Can be null.
* Supported parameter names:
* {@link Engine#KEY_PARAM_UTTERANCE_ID}.
* Engine specific parameters may be passed in but the parameter keys
* must be prefixed by the name of the engine they are intended for. For example
* the keys "com.svox.pico_foo" and "com.svox.pico:bar" will be passed to the
* engine named "com.svox.pico" if it is being used.
* @param filename Absolute file filename to write the generated audio data to.It should be
* something like "/sdcard/myappsounds/mysound.wav".
*
* @return {@link #ERROR} or {@link #SUCCESS} of <b>queuing</b> the synthesizeToFile operation.
* @deprecated As of API level 20, replaced by
* {@link #synthesizeToFile(CharSequence, HashMap, String, String)}.
*/
public int synthesizeToFile(final String text, final HashMap<String, String> params,
final String filename) {
return synthesizeToFile(text, params, filename, params.get(Engine.KEY_PARAM_UTTERANCE_ID));
}
private Bundle getParams(HashMap<String, String> params) {
if (params != null && !params.isEmpty()) {
Bundle bundle = new Bundle(mParams);

39
core/java/android/speech/tts/TextToSpeechService.java
View File

@@ -637,11 +637,13 @@ public abstract class TextToSpeechService extends Service {
*/
private abstract class SpeechItemV1 extends UtteranceSpeechItem {
protected final Bundle mParams;
protected final String mUtteranceId;
SpeechItemV1(Object callerIdentity, int callerUid, int callerPid,
Bundle params) {
Bundle params, String utteranceId) {
super(callerIdentity, callerUid, callerPid);
mParams = params;
mUtteranceId = utteranceId;
}
boolean hasLanguage() {
@@ -658,7 +660,7 @@ public abstract class TextToSpeechService extends Service {
@Override
public String getUtteranceId() {
return getStringParam(mParams, Engine.KEY_PARAM_UTTERANCE_ID, null);
return mUtteranceId;
}
AudioOutputParams getAudioParams() {
@@ -668,7 +670,7 @@ public abstract class TextToSpeechService extends Service {
class SynthesisSpeechItemV1 extends SpeechItemV1 {
// Never null.
private final String mText;
private final CharSequence mText;
private final SynthesisRequest mSynthesisRequest;
private final String[] mDefaultLocale;
// Non null after synthesis has started, and all accesses
@@ -678,8 +680,8 @@ public abstract class TextToSpeechService extends Service {
private final int mCallerUid;
public SynthesisSpeechItemV1(Object callerIdentity, int callerUid, int callerPid,
Bundle params, String text) {
super(callerIdentity, callerUid, callerPid, params);
Bundle params, String utteranceId, CharSequence text) {
super(callerIdentity, callerUid, callerPid, params, utteranceId);
mText = text;
mCallerUid = callerUid;
mSynthesisRequest = new SynthesisRequest(mText, mParams);
@@ -689,7 +691,7 @@ public abstract class TextToSpeechService extends Service {
mPackageName);
}
public String getText() {
public CharSequence getText() {
return mText;
}
@@ -774,8 +776,9 @@ public abstract class TextToSpeechService extends Service {
private final FileOutputStream mFileOutputStream;
public SynthesisToFileOutputStreamSpeechItemV1(Object callerIdentity, int callerUid,
int callerPid, Bundle params, String text, FileOutputStream fileOutputStream) {
super(callerIdentity, callerUid, callerPid, params, text);
int callerPid, Bundle params, String utteranceId, CharSequence text,
FileOutputStream fileOutputStream) {
super(callerIdentity, callerUid, callerPid, params, utteranceId, text);
mFileOutputStream = fileOutputStream;
}
@@ -801,8 +804,8 @@ public abstract class TextToSpeechService extends Service {
private final AudioPlaybackQueueItem mItem;
public AudioSpeechItemV1(Object callerIdentity, int callerUid, int callerPid,
Bundle params, Uri uri) {
super(callerIdentity, callerUid, callerPid, params);
Bundle params, String utteranceId, Uri uri) {
super(callerIdentity, callerUid, callerPid, params, utteranceId);
mItem = new AudioPlaybackQueueItem(this, getCallerIdentity(),
TextToSpeechService.this, uri, getAudioParams());
}
@@ -909,19 +912,20 @@ public abstract class TextToSpeechService extends Service {
// they can be used as message objects (which are tested for equality using ==).
private final ITextToSpeechService.Stub mBinder = new ITextToSpeechService.Stub() {
@Override
public int speak(IBinder caller, String text, int queueMode, Bundle params) {
public int speak(IBinder caller, CharSequence text, int queueMode, Bundle params,
String utteranceId) {
if (!checkNonNull(caller, text, params)) {
return TextToSpeech.ERROR;
}
SpeechItem item = new SynthesisSpeechItemV1(caller,
Binder.getCallingUid(), Binder.getCallingPid(), params, text);
Binder.getCallingUid(), Binder.getCallingPid(), params, utteranceId, text);
return mSynthHandler.enqueueSpeechItem(queueMode, item);
}
@Override
public int synthesizeToFileDescriptor(IBinder caller, String text, ParcelFileDescriptor
fileDescriptor, Bundle params) {
public int synthesizeToFileDescriptor(IBinder caller, CharSequence text, ParcelFileDescriptor
fileDescriptor, Bundle params, String utteranceId) {
if (!checkNonNull(caller, text, fileDescriptor, params)) {
return TextToSpeech.ERROR;
}
@@ -933,19 +937,20 @@ public abstract class TextToSpeechService extends Service {
fileDescriptor.detachFd());
SpeechItem item = new SynthesisToFileOutputStreamSpeechItemV1(caller,
Binder.getCallingUid(), Binder.getCallingPid(), params, text,
Binder.getCallingUid(), Binder.getCallingPid(), params, utteranceId, text,
new ParcelFileDescriptor.AutoCloseOutputStream(sameFileDescriptor));
return mSynthHandler.enqueueSpeechItem(TextToSpeech.QUEUE_ADD, item);
}
@Override
public int playAudio(IBinder caller, Uri audioUri, int queueMode, Bundle params) {
public int playAudio(IBinder caller, Uri audioUri, int queueMode, Bundle params,
String utteranceId) {
if (!checkNonNull(caller, audioUri, params)) {
return TextToSpeech.ERROR;
}
SpeechItem item = new AudioSpeechItemV1(caller,
Binder.getCallingUid(), Binder.getCallingPid(), params, audioUri);
Binder.getCallingUid(), Binder.getCallingPid(), params, utteranceId, audioUri);
return mSynthHandler.enqueueSpeechItem(queueMode, item);
}