1 /*
2 * Copyright (c) 1999, 2016, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package javax.sound.sampled;
27
28 import java.util.Collections;
29 import java.util.HashMap;
30 import java.util.Map;
31 import java.util.Objects;
32
33 /**
34 * {@code AudioFormat} is the class that specifies a particular arrangement of
35 * data in a sound stream. By examining the information stored in the audio
36 * format, you can discover how to interpret the bits in the binary sound data.
37 * <p>
38 * Every data line has an audio format associated with its data stream. The
39 * audio format of a source (playback) data line indicates what kind of data the
40 * data line expects to receive for output. For a target (capture) data line,
41 * the audio format specifies the kind of the data that can be read from the
42 * line.
43 * Sound files also have audio formats, of course. The {@link AudioFileFormat}
44 * class encapsulates an {@code AudioFormat} in addition to other, file-specific
45 * information. Similarly, an {@link AudioInputStream} has an
46 * {@code AudioFormat}.
47 * <p>
48 * The {@code AudioFormat} class accommodates a number of common sound-file
49 * encoding techniques, including pulse-code modulation (PCM), mu-law encoding,
50 * and a-law encoding. These encoding techniques are predefined, but service
51 * providers can create new encoding types. The encoding that a specific format
52 * uses is named by its {@code encoding} field.
53 * <p>
54 * In addition to the encoding, the audio format includes other properties that
55 * further specify the exact arrangement of the data. These include the number
56 * of channels, sample rate, sample size, byte order, frame rate, and frame
57 * size. Sounds may have different numbers of audio channels: one for mono, two
58 * for stereo. The sample rate measures how many "snapshots" (samples) of the
59 * sound pressure are taken per second, per channel. (If the sound is stereo
60 * rather than mono, two samples are actually measured at each instant of time:
61 * one for the left channel, and another for the right channel; however, the
62 * sample rate still measures the number per channel, so the rate is the same
63 * regardless of the number of channels. This is the standard use of the term.)
64 * The sample size indicates how many bits are used to store each snapshot; 8
65 * and 16 are typical values. For 16-bit samples (or any other sample size
66 * larger than a byte), byte order is important; the bytes in each sample are
67 * arranged in either the "little-endian" or "big-endian" style. For encodings
68 * like PCM, a frame consists of the set of samples for all channels at a given
69 * point in time, and so the size of a frame (in bytes) is always equal to the
70 * size of a sample (in bytes) times the number of channels. However, with some
71 * other sorts of encodings a frame can contain a bundle of compressed data for
72 * a whole series of samples, as well as additional, non-sample data. For such
73 * encodings, the sample rate and sample size refer to the data after it is
74 * decoded into PCM, and so they are completely different from the frame rate
75 * and frame size.
76 * <p>
77 * An {@code AudioFormat} object can include a set of properties. A property is
78 * a pair of key and value: the key is of type {@code String}, the associated
79 * property value is an arbitrary object. Properties specify additional format
80 * specifications, like the bit rate for compressed formats. Properties are
81 * mainly used as a means to transport additional information of the audio
82 * format to and from the service providers. Therefore, properties are ignored
83 * in the {@link #matches(AudioFormat)} method. However, methods which rely on
84 * the installed service providers, like
85 * {@link AudioSystem#isConversionSupported (AudioFormat, AudioFormat)
86 * isConversionSupported} may consider properties, depending on the respective
87 * service provider implementation.
88 * <p>
89 * The following table lists some common properties which service providers
90 * should use, if applicable:
91 *
92 * <table border=0>
93 * <caption>Audio Format Properties</caption>
94 * <tr>
95 * <th>Property key</th>
96 * <th>Value type</th>
97 * <th>Description</th>
98 * </tr>
99 * <tr>
100 * <td>"bitrate"</td>
101 * <td>{@link java.lang.Integer Integer}</td>
102 * <td>average bit rate in bits per second</td>
103 * </tr>
104 * <tr>
105 * <td>"vbr"</td>
106 * <td>{@link java.lang.Boolean Boolean}</td>
107 * <td>{@code true}, if the file is encoded in variable bit
108 * rate (VBR)</td>
109 * </tr>
110 * <tr>
111 * <td>"quality"</td>
112 * <td>{@link java.lang.Integer Integer}</td>
113 * <td>encoding/conversion quality, 1..100</td>
114 * </tr>
115 * </table>
116 * <p>
117 * Vendors of service providers (plugins) are encouraged to seek information
118 * about other already established properties in third party plugins, and follow
119 * the same conventions.
120 *
121 * @author Kara Kytle
122 * @author Florian Bomers
123 * @see DataLine#getFormat
124 * @see AudioInputStream#getFormat
125 * @see AudioFileFormat
126 * @see javax.sound.sampled.spi.FormatConversionProvider
127 * @since 1.3
128 */
129 public class AudioFormat {
130
131 /**
132 * The audio encoding technique used by this format.
133 */
134 protected Encoding encoding;
135
136 /**
137 * The number of samples played or recorded per second, for sounds that have
138 * this format.
139 */
140 protected float sampleRate;
141
142 /**
143 * The number of bits in each sample of a sound that has this format.
144 */
145 protected int sampleSizeInBits;
146
147 /**
148 * The number of audio channels in this format (1 for mono, 2 for stereo).
149 */
150 protected int channels;
151
152 /**
153 * The number of bytes in each frame of a sound that has this format.
154 */
155 protected int frameSize;
156
157 /**
158 * The number of frames played or recorded per second, for sounds that have
159 * this format.
160 */
161 protected float frameRate;
162
163 /**
164 * Indicates whether the audio data is stored in big-endian or little-endian
165 * order.
166 */
167 protected boolean bigEndian;
168
169 /**
170 * The set of properties.
171 */
172 private HashMap<String, Object> properties;
173
174 /**
175 * Constructs an {@code AudioFormat} with the given parameters. The encoding
176 * specifies the convention used to represent the data. The other parameters
177 * are further explained in the {@link AudioFormat class description}.
178 *
179 * @param encoding the audio encoding technique
180 * @param sampleRate the number of samples per second
181 * @param sampleSizeInBits the number of bits in each sample
182 * @param channels the number of channels (1 for mono, 2 for stereo,
183 * and so on)
184 * @param frameSize the number of bytes in each frame
185 * @param frameRate the number of frames per second
186 * @param bigEndian indicates whether the data for a single sample is
187 * stored in big-endian byte order ({@code false} means
188 * little-endian)
189 */
190 public AudioFormat(Encoding encoding, float sampleRate, int sampleSizeInBits,
191 int channels, int frameSize, float frameRate, boolean bigEndian) {
192
193 this.encoding = encoding;
194 this.sampleRate = sampleRate;
195 this.sampleSizeInBits = sampleSizeInBits;
196 this.channels = channels;
197 this.frameSize = frameSize;
198 this.frameRate = frameRate;
199 this.bigEndian = bigEndian;
200 this.properties = null;
201 }
202
203 /**
204 * Constructs an {@code AudioFormat} with the given parameters. The encoding
205 * specifies the convention used to represent the data. The other parameters
206 * are further explained in the {@link AudioFormat class description}.
207 *
208 * @param encoding the audio encoding technique
209 * @param sampleRate the number of samples per second
210 * @param sampleSizeInBits the number of bits in each sample
211 * @param channels the number of channels (1 for mono, 2 for stereo, and so
212 * on)
213 * @param frameSize the number of bytes in each frame
214 * @param frameRate the number of frames per second
215 * @param bigEndian indicates whether the data for a single sample is
216 * stored in big-endian byte order ({@code false} means little-endian)
217 * @param properties a {@code Map<String, Object>} object containing format
218 * properties
219 * @since 1.5
220 */
221 public AudioFormat(Encoding encoding, float sampleRate,
222 int sampleSizeInBits, int channels,
223 int frameSize, float frameRate,
224 boolean bigEndian, Map<String, Object> properties) {
225 this(encoding, sampleRate, sampleSizeInBits, channels,
226 frameSize, frameRate, bigEndian);
227 this.properties = new HashMap<>(properties);
228 }
229
230 /**
231 * Constructs an {@code AudioFormat} with a linear PCM encoding and the
232 * given parameters. The frame size is set to the number of bytes required
233 * to contain one sample from each channel, and the frame rate is set to the
234 * sample rate.
235 *
236 * @param sampleRate the number of samples per second
237 * @param sampleSizeInBits the number of bits in each sample
238 * @param channels the number of channels (1 for mono, 2 for stereo, and so
239 * on)
240 * @param signed indicates whether the data is signed or unsigned
241 * @param bigEndian indicates whether the data for a single sample is
242 * stored in big-endian byte order ({@code false} means
243 * little-endian)
244 */
245 public AudioFormat(float sampleRate, int sampleSizeInBits,
246 int channels, boolean signed, boolean bigEndian) {
247
248 this((signed == true ? Encoding.PCM_SIGNED : Encoding.PCM_UNSIGNED),
249 sampleRate,
250 sampleSizeInBits,
251 channels,
252 (channels == AudioSystem.NOT_SPECIFIED || sampleSizeInBits == AudioSystem.NOT_SPECIFIED)?
253 AudioSystem.NOT_SPECIFIED:
254 ((sampleSizeInBits + 7) / 8) * channels,
255 sampleRate,
256 bigEndian);
257 }
258
259 /**
260 * Obtains the type of encoding for sounds in this format.
261 *
262 * @return the encoding type
263 * @see Encoding#PCM_SIGNED
264 * @see Encoding#PCM_UNSIGNED
265 * @see Encoding#ULAW
266 * @see Encoding#ALAW
267 */
268 public Encoding getEncoding() {
269
270 return encoding;
271 }
272
273 /**
274 * Obtains the sample rate. For compressed formats, the return value is the
275 * sample rate of the uncompressed audio data. When this AudioFormat is used
276 * for queries (e.g. {@link AudioSystem#isConversionSupported(AudioFormat,
277 * AudioFormat) AudioSystem.isConversionSupported}) or capabilities (e.g.
278 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a sample rate
279 * of {@code AudioSystem.NOT_SPECIFIED} means that any sample rate is
280 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
281 * sample rate is not defined for this audio format.
282 *
283 * @return the number of samples per second, or
284 * {@code AudioSystem.NOT_SPECIFIED}
285 * @see #getFrameRate()
286 * @see AudioSystem#NOT_SPECIFIED
287 */
288 public float getSampleRate() {
289
290 return sampleRate;
291 }
292
293 /**
294 * Obtains the size of a sample. For compressed formats, the return value is
295 * the sample size of the uncompressed audio data. When this AudioFormat is
296 * used for queries (e.g. {@link AudioSystem#isConversionSupported(
297 * AudioFormat,AudioFormat) AudioSystem.isConversionSupported}) or
298 * capabilities (e.g.
299 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a sample size
300 * of {@code AudioSystem.NOT_SPECIFIED} means that any sample size is
301 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
302 * sample size is not defined for this audio format.
303 *
304 * @return the number of bits in each sample, or
305 * {@code AudioSystem.NOT_SPECIFIED}
306 * @see #getFrameSize()
307 * @see AudioSystem#NOT_SPECIFIED
308 */
309 public int getSampleSizeInBits() {
310
311 return sampleSizeInBits;
312 }
313
314 /**
315 * Obtains the number of channels. When this AudioFormat is used for queries
316 * (e.g. {@link AudioSystem#isConversionSupported(AudioFormat, AudioFormat)
317 * AudioSystem.isConversionSupported}) or capabilities (e.g.
318 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a return
319 * value of {@code AudioSystem.NOT_SPECIFIED} means that any (positive)
320 * number of channels is acceptable.
321 *
322 * @return The number of channels (1 for mono, 2 for stereo, etc.), or
323 * {@code AudioSystem.NOT_SPECIFIED}
324 * @see AudioSystem#NOT_SPECIFIED
325 */
326 public int getChannels() {
327
328 return channels;
329 }
330
331 /**
332 * Obtains the frame size in bytes. When this AudioFormat is used for
333 * queries (e.g. {@link AudioSystem#isConversionSupported(AudioFormat,
334 * AudioFormat) AudioSystem.isConversionSupported}) or capabilities (e.g.
335 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a frame size
336 * of {@code AudioSystem.NOT_SPECIFIED} means that any frame size is
337 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
338 * frame size is not defined for this audio format.
339 *
340 * @return the number of bytes per frame, or
341 * {@code AudioSystem.NOT_SPECIFIED}
342 * @see #getSampleSizeInBits()
343 * @see AudioSystem#NOT_SPECIFIED
344 */
345 public int getFrameSize() {
346
347 return frameSize;
348 }
349
350 /**
351 * Obtains the frame rate in frames per second. When this AudioFormat is
352 * used for queries (e.g. {@link AudioSystem#isConversionSupported(
353 * AudioFormat,AudioFormat) AudioSystem.isConversionSupported}) or
354 * capabilities (e.g.
355 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a frame rate
356 * of {@code AudioSystem.NOT_SPECIFIED} means that any frame rate is
357 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
358 * frame rate is not defined for this audio format.
359 *
360 * @return the number of frames per second, or
361 * {@code AudioSystem.NOT_SPECIFIED}
362 * @see #getSampleRate()
363 * @see AudioSystem#NOT_SPECIFIED
364 */
365 public float getFrameRate() {
366
367 return frameRate;
368 }
369
370 /**
371 * Indicates whether the audio data is stored in big-endian or little-endian
372 * byte order. If the sample size is not more than one byte, the return
373 * value is irrelevant.
374 *
375 * @return {@code true} if the data is stored in big-endian byte order,
376 * {@code false} if little-endian
377 */
378 public boolean isBigEndian() {
379
380 return bigEndian;
381 }
382
383 /**
384 * Obtain an unmodifiable map of properties. The concept of properties is
385 * further explained in the {@link AudioFileFormat class description}.
386 *
387 * @return a {@code Map<String, Object>} object containing all properties.
388 * If no properties are recognized, an empty map is returned.
389 * @see #getProperty(String)
390 * @since 1.5
391 */
392 @SuppressWarnings("unchecked") // Cast of result of clone.
393 public Map<String,Object> properties() {
394 Map<String,Object> ret;
395 if (properties == null) {
396 ret = new HashMap<>(0);
397 } else {
398 ret = (Map<String,Object>) (properties.clone());
399 }
400 return Collections.unmodifiableMap(ret);
401 }
402
403 /**
404 * Obtain the property value specified by the key. The concept of properties
405 * is further explained in the {@link AudioFileFormat class description}.
406 * <p>
407 * If the specified property is not defined for a particular file format,
408 * this method returns {@code null}.
409 *
410 * @param key the key of the desired property
411 * @return the value of the property with the specified key, or {@code null}
412 * if the property does not exist
413 * @see #properties()
414 * @since 1.5
415 */
416 public Object getProperty(String key) {
417 if (properties == null) {
418 return null;
419 }
420 return properties.get(key);
421 }
422
423 /**
424 * Indicates whether this format matches the one specified. To match, two
425 * formats must have the same encoding, and consistent values of the number
426 * of channels, sample rate, sample size, frame rate, and frame size. The
427 * values of the property are consistent if they are equal or the specified
428 * format has the property value {@code AudioSystem.NOT_SPECIFIED}. The byte
429 * order (big-endian or little-endian) must be the same if the sample size
430 * is greater than one byte.
431 *
432 * @param format format to test for match
433 * @return {@code true} if this format matches the one specified,
434 * {@code false} otherwise
435 */
436 public boolean matches(AudioFormat format) {
437 if (format.getEncoding().equals(getEncoding())
438 && (format.getChannels() == AudioSystem.NOT_SPECIFIED
439 || format.getChannels() == getChannels())
440 && (format.getSampleRate() == (float)AudioSystem.NOT_SPECIFIED
441 || format.getSampleRate() == getSampleRate())
442 && (format.getSampleSizeInBits() == AudioSystem.NOT_SPECIFIED
443 || format.getSampleSizeInBits() == getSampleSizeInBits())
444 && (format.getFrameRate() == (float)AudioSystem.NOT_SPECIFIED
445 || format.getFrameRate() == getFrameRate())
446 && (format.getFrameSize() == AudioSystem.NOT_SPECIFIED
447 || format.getFrameSize() == getFrameSize())
448 && (getSampleSizeInBits() <= 8
449 || format.isBigEndian() == isBigEndian())) {
450 return true;
451 }
452 return false;
453 }
454
455 /**
456 * Returns a string that describes the format, such as: "PCM SIGNED 22050 Hz
457 * 16 bit mono big-endian". The contents of the string may vary between
458 * implementations of Java Sound.
459 *
460 * @return a string that describes the format parameters
461 */
462 @Override
463 public String toString() {
464 String sEncoding = "";
465 if (getEncoding() != null) {
466 sEncoding = getEncoding().toString() + " ";
467 }
468
469 String sSampleRate;
470 if (getSampleRate() == (float) AudioSystem.NOT_SPECIFIED) {
471 sSampleRate = "unknown sample rate, ";
472 } else {
473 sSampleRate = "" + getSampleRate() + " Hz, ";
474 }
475
476 String sSampleSizeInBits;
477 if (getSampleSizeInBits() == (float) AudioSystem.NOT_SPECIFIED) {
478 sSampleSizeInBits = "unknown bits per sample, ";
479 } else {
480 sSampleSizeInBits = "" + getSampleSizeInBits() + " bit, ";
481 }
482
483 String sChannels;
484 if (getChannels() == 1) {
485 sChannels = "mono, ";
486 } else
487 if (getChannels() == 2) {
488 sChannels = "stereo, ";
489 } else {
490 if (getChannels() == AudioSystem.NOT_SPECIFIED) {
491 sChannels = " unknown number of channels, ";
492 } else {
493 sChannels = ""+getChannels()+" channels, ";
494 }
495 }
496
497 String sFrameSize;
498 if (getFrameSize() == (float) AudioSystem.NOT_SPECIFIED) {
499 sFrameSize = "unknown frame size, ";
500 } else {
501 sFrameSize = "" + getFrameSize()+ " bytes/frame, ";
502 }
503
504 String sFrameRate = "";
505 if (Math.abs(getSampleRate() - getFrameRate()) > 0.00001) {
506 if (getFrameRate() == (float) AudioSystem.NOT_SPECIFIED) {
507 sFrameRate = "unknown frame rate, ";
508 } else {
509 sFrameRate = getFrameRate() + " frames/second, ";
510 }
511 }
512
513 String sEndian = "";
514 if ((getEncoding().equals(Encoding.PCM_SIGNED)
515 || getEncoding().equals(Encoding.PCM_UNSIGNED))
516 && ((getSampleSizeInBits() > 8)
517 || (getSampleSizeInBits() == AudioSystem.NOT_SPECIFIED))) {
518 if (isBigEndian()) {
519 sEndian = "big-endian";
520 } else {
521 sEndian = "little-endian";
522 }
523 }
524
525 return sEncoding
526 + sSampleRate
527 + sSampleSizeInBits
528 + sChannels
529 + sFrameSize
530 + sFrameRate
531 + sEndian;
532
533 }
534
535 /**
536 * The {@code Encoding} class names the specific type of data representation
537 * used for an audio stream. The encoding includes aspects of the sound
538 * format other than the number of channels, sample rate, sample size, frame
539 * rate, frame size, and byte order.
540 * <p>
541 * One ubiquitous type of audio encoding is pulse-code modulation (PCM),
542 * which is simply a linear (proportional) representation of the sound
543 * waveform. With PCM, the number stored in each sample is proportional to
544 * the instantaneous amplitude of the sound pressure at that point in time.
545 * The numbers may be signed or unsigned integers or floats. Besides PCM,
546 * other encodings include mu-law and a-law, which are nonlinear mappings of
547 * the sound amplitude that are often used for recording speech.
548 * <p>
549 * You can use a predefined encoding by referring to one of the static
550 * objects created by this class, such as PCM_SIGNED or PCM_UNSIGNED.
551 * Service providers can create new encodings, such as compressed audio
552 * formats, and make these available through the {@link AudioSystem} class.
553 * <p>
554 * The {@code Encoding} class is static, so that all {@code AudioFormat}
555 * objects that have the same encoding will refer to the same object (rather
556 * than different instances of the same class). This allows matches to be
557 * made by checking that two format's encodings are equal.
558 *
559 * @author Kara Kytle
560 * @see AudioFormat
561 * @see javax.sound.sampled.spi.FormatConversionProvider
562 * @since 1.3
563 */
564 public static class Encoding {
565
566 /**
567 * Specifies signed, linear PCM data.
568 */
569 public static final Encoding PCM_SIGNED = new Encoding("PCM_SIGNED");
570
571 /**
572 * Specifies unsigned, linear PCM data.
573 */
574 public static final Encoding PCM_UNSIGNED = new Encoding("PCM_UNSIGNED");
575
576 /**
577 * Specifies floating-point PCM data.
578 *
579 * @since 1.7
580 */
581 public static final Encoding PCM_FLOAT = new Encoding("PCM_FLOAT");
582
583 /**
584 * Specifies u-law encoded data.
585 */
586 public static final Encoding ULAW = new Encoding("ULAW");
587
588 /**
589 * Specifies a-law encoded data.
590 */
591 public static final Encoding ALAW = new Encoding("ALAW");
592
593 /**
594 * Encoding name.
595 */
596 private final String name;
597
598 /**
599 * Constructs a new encoding.
600 *
601 * @param name the name of the new type of encoding
602 */
603 public Encoding(final String name) {
604 this.name = name;
605 }
606
607 /**
608 * Finalizes the equals method.
609 */
610 @Override
611 public final boolean equals(final Object obj) {
612 if (this == obj) {
613 return true;
614 }
615 if (!(obj instanceof Encoding)) {
616 return false;
617 }
618 return Objects.equals(name, ((Encoding) obj).name);
619 }
620
621 /**
622 * Finalizes the hashCode method.
623 */
624 @Override
625 public final int hashCode() {
626 return name != null ? name.hashCode() : 0;
627 }
628
629 /**
630 * Provides the {@code String} representation of the encoding. This
631 * {@code String} is the same name that was passed to the constructor.
632 * For the predefined encodings, the name is similar to the encoding's
633 * variable (field) name. For example, {@code PCM_SIGNED.toString()}
634 * returns the name "PCM_SIGNED".
635 *
636 * @return the encoding name
637 */
638 @Override
639 public final String toString() {
640 return name;
641 }
642 }
643 }