1 /*
2 * Copyright (c) 1999, 2014, 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
32 /**
33 * {@code AudioFormat} is the class that specifies a particular arrangement of
34 * data in a sound stream. By examining the information stored in the audio
35 * format, you can discover how to interpret the bits in the binary sound data.
36 * <p>
37 * Every data line has an audio format associated with its data stream. The
38 * audio format of a source (playback) data line indicates what kind of data the
39 * data line expects to receive for output. For a target (capture) data line,
40 * the audio format specifies the kind of the data that can be read from the
41 * line.
42 * Sound files also have audio formats, of course. The {@link AudioFileFormat}
43 * class encapsulates an {@code AudioFormat} in addition to other, file-specific
44 * information. Similarly, an {@link AudioInputStream} has an
45 * {@code AudioFormat}.
46 * <p>
47 * The {@code AudioFormat} class accommodates a number of common sound-file
48 * encoding techniques, including pulse-code modulation (PCM), mu-law encoding,
49 * and a-law encoding. These encoding techniques are predefined, but service
50 * providers can create new encoding types. The encoding that a specific format
51 * uses is named by its {@code encoding} field.
52 * <p>
53 * In addition to the encoding, the audio format includes other properties that
54 * further specify the exact arrangement of the data. These include the number
55 * of channels, sample rate, sample size, byte order, frame rate, and frame
56 * size. Sounds may have different numbers of audio channels: one for mono, two
57 * for stereo. The sample rate measures how many "snapshots" (samples) of the
58 * sound pressure are taken per second, per channel. (If the sound is stereo
59 * rather than mono, two samples are actually measured at each instant of time:
60 * one for the left channel, and another for the right channel; however, the
61 * sample rate still measures the number per channel, so the rate is the same
62 * regardless of the number of channels. This is the standard use of the term.)
63 * The sample size indicates how many bits are used to store each snapshot; 8
64 * and 16 are typical values. For 16-bit samples (or any other sample size
65 * larger than a byte), byte order is important; the bytes in each sample are
66 * arranged in either the "little-endian" or "big-endian" style. For encodings
67 * like PCM, a frame consists of the set of samples for all channels at a given
68 * point in time, and so the size of a frame (in bytes) is always equal to the
69 * size of a sample (in bytes) times the number of channels. However, with some
70 * other sorts of encodings a frame can contain a bundle of compressed data for
71 * a whole series of samples, as well as additional, non-sample data. For such
72 * encodings, the sample rate and sample size refer to the data after it is
73 * decoded into PCM, and so they are completely different from the frame rate
74 * and frame size.
75 * <p>
76 * An {@code AudioFormat} object can include a set of properties. A property is
77 * a pair of key and value: the key is of type {@code String}, the associated
78 * property value is an arbitrary object. Properties specify additional format
79 * specifications, like the bit rate for compressed formats. Properties are
80 * mainly used as a means to transport additional information of the audio
81 * format to and from the service providers. Therefore, properties are ignored
82 * in the {@link #matches(AudioFormat)} method. However, methods which rely on
83 * the installed service providers, like
84 * {@link AudioSystem#isConversionSupported (AudioFormat, AudioFormat)
85 * isConversionSupported} may consider properties, depending on the respective
86 * service provider implementation.
87 * <p>
88 * The following table lists some common properties which service providers
89 * should use, if applicable:
90 *
91 * <table border=0>
92 * <caption>Audio Format Properties</caption>
93 * <tr>
94 * <th>Property key</th>
95 * <th>Value type</th>
96 * <th>Description</th>
97 * </tr>
98 * <tr>
99 * <td>"bitrate"</td>
100 * <td>{@link java.lang.Integer Integer}</td>
101 * <td>average bit rate in bits per second</td>
102 * </tr>
103 * <tr>
104 * <td>"vbr"</td>
105 * <td>{@link java.lang.Boolean Boolean}</td>
106 * <td>{@code true}, if the file is encoded in variable bit
107 * rate (VBR)</td>
108 * </tr>
109 * <tr>
110 * <td>"quality"</td>
111 * <td>{@link java.lang.Integer Integer}</td>
112 * <td>encoding/conversion quality, 1..100</td>
113 * </tr>
114 * </table>
115 * <p>
116 * Vendors of service providers (plugins) are encouraged to seek information
117 * about other already established properties in third party plugins, and follow
118 * the same conventions.
119 *
120 * @author Kara Kytle
121 * @author Florian Bomers
122 * @see DataLine#getFormat
123 * @see AudioInputStream#getFormat
124 * @see AudioFileFormat
125 * @see javax.sound.sampled.spi.FormatConversionProvider
126 * @since 1.3
127 */
128 public class AudioFormat {
129
130 /**
131 * The audio encoding technique used by this format.
132 */
133 protected Encoding encoding;
134
135 /**
136 * The number of samples played or recorded per second, for sounds that have
137 * this format.
138 */
139 protected float sampleRate;
140
141 /**
142 * The number of bits in each sample of a sound that has this format.
143 */
144 protected int sampleSizeInBits;
145
146 /**
147 * The number of audio channels in this format (1 for mono, 2 for stereo).
148 */
149 protected int channels;
150
151 /**
152 * The number of bytes in each frame of a sound that has this format.
153 */
154 protected int frameSize;
155
156 /**
157 * The number of frames played or recorded per second, for sounds that have
158 * this format.
159 */
160 protected float frameRate;
161
162 /**
163 * Indicates whether the audio data is stored in big-endian or little-endian
164 * order.
165 */
166 protected boolean bigEndian;
167
168 /**
169 * The set of properties.
170 */
171 private HashMap<String, Object> properties;
172
173 /**
174 * Constructs an {@code AudioFormat} with the given parameters. The encoding
175 * specifies the convention used to represent the data. The other parameters
176 * are further explained in the {@link AudioFormat class description}.
177 *
178 * @param encoding the audio encoding technique
179 * @param sampleRate the number of samples per second
180 * @param sampleSizeInBits the number of bits in each sample
181 * @param channels the number of channels (1 for mono, 2 for stereo,
182 * and so on)
183 * @param frameSize the number of bytes in each frame
184 * @param frameRate the number of frames per second
185 * @param bigEndian indicates whether the data for a single sample is
186 * stored in big-endian byte order ({@code false} means
187 * little-endian)
188 */
189 public AudioFormat(Encoding encoding, float sampleRate, int sampleSizeInBits,
190 int channels, int frameSize, float frameRate, boolean bigEndian) {
191
192 this.encoding = encoding;
193 this.sampleRate = sampleRate;
194 this.sampleSizeInBits = sampleSizeInBits;
195 this.channels = channels;
196 this.frameSize = frameSize;
197 this.frameRate = frameRate;
198 this.bigEndian = bigEndian;
199 this.properties = null;
200 }
201
202 /**
203 * Constructs an {@code AudioFormat} with the given parameters. The encoding
204 * specifies the convention used to represent the data. The other parameters
205 * are further explained in the {@link AudioFormat class description}.
206 *
207 * @param encoding the audio encoding technique
208 * @param sampleRate the number of samples per second
209 * @param sampleSizeInBits the number of bits in each sample
210 * @param channels the number of channels (1 for mono, 2 for stereo, and so
211 * on)
212 * @param frameSize the number of bytes in each frame
213 * @param frameRate the number of frames per second
214 * @param bigEndian indicates whether the data for a single sample is
215 * stored in big-endian byte order ({@code false} means little-endian)
216 * @param properties a {@code Map<String, Object>} object containing format
217 * properties
218 * @since 1.5
219 */
220 public AudioFormat(Encoding encoding, float sampleRate,
221 int sampleSizeInBits, int channels,
222 int frameSize, float frameRate,
223 boolean bigEndian, Map<String, Object> properties) {
224 this(encoding, sampleRate, sampleSizeInBits, channels,
225 frameSize, frameRate, bigEndian);
226 this.properties = new HashMap<String, Object>(properties);
227 }
228
229 /**
230 * Constructs an {@code AudioFormat} with a linear PCM encoding and the
231 * given parameters. The frame size is set to the number of bytes required
232 * to contain one sample from each channel, and the frame rate is set to the
233 * sample rate.
234 *
235 * @param sampleRate the number of samples per second
236 * @param sampleSizeInBits the number of bits in each sample
237 * @param channels the number of channels (1 for mono, 2 for stereo, and so
238 * on)
239 * @param signed indicates whether the data is signed or unsigned
240 * @param bigEndian indicates whether the data for a single sample is
241 * stored in big-endian byte order ({@code false} means
242 * little-endian)
243 */
244 public AudioFormat(float sampleRate, int sampleSizeInBits,
245 int channels, boolean signed, boolean bigEndian) {
246
247 this((signed == true ? Encoding.PCM_SIGNED : Encoding.PCM_UNSIGNED),
248 sampleRate,
249 sampleSizeInBits,
250 channels,
251 (channels == AudioSystem.NOT_SPECIFIED || sampleSizeInBits == AudioSystem.NOT_SPECIFIED)?
252 AudioSystem.NOT_SPECIFIED:
253 ((sampleSizeInBits + 7) / 8) * channels,
254 sampleRate,
255 bigEndian);
256 }
257
258 /**
259 * Obtains the type of encoding for sounds in this format.
260 *
261 * @return the encoding type
262 * @see Encoding#PCM_SIGNED
263 * @see Encoding#PCM_UNSIGNED
264 * @see Encoding#ULAW
265 * @see Encoding#ALAW
266 */
267 public Encoding getEncoding() {
268
269 return encoding;
270 }
271
272 /**
273 * Obtains the sample rate. For compressed formats, the return value is the
274 * sample rate of the uncompressed audio data. When this AudioFormat is used
275 * for queries (e.g. {@link AudioSystem#isConversionSupported(AudioFormat,
276 * AudioFormat) AudioSystem.isConversionSupported}) or capabilities (e.g.
277 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a sample rate
278 * of {@code AudioSystem.NOT_SPECIFIED} means that any sample rate is
279 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
280 * sample rate is not defined for this audio format.
281 *
282 * @return the number of samples per second, or
283 * {@code AudioSystem.NOT_SPECIFIED}
284 * @see #getFrameRate()
285 * @see AudioSystem#NOT_SPECIFIED
286 */
287 public float getSampleRate() {
288
289 return sampleRate;
290 }
291
292 /**
293 * Obtains the size of a sample. For compressed formats, the return value is
294 * the sample size of the uncompressed audio data. When this AudioFormat is
295 * used for queries (e.g. {@link AudioSystem#isConversionSupported(
296 * AudioFormat,AudioFormat) AudioSystem.isConversionSupported}) or
297 * capabilities (e.g.
298 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a sample size
299 * of {@code AudioSystem.NOT_SPECIFIED} means that any sample size is
300 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
301 * sample size is not defined for this audio format.
302 *
303 * @return the number of bits in each sample, or
304 * {@code AudioSystem.NOT_SPECIFIED}
305 * @see #getFrameSize()
306 * @see AudioSystem#NOT_SPECIFIED
307 */
308 public int getSampleSizeInBits() {
309
310 return sampleSizeInBits;
311 }
312
313 /**
314 * Obtains the number of channels. When this AudioFormat is used for queries
315 * (e.g. {@link AudioSystem#isConversionSupported(AudioFormat, AudioFormat)
316 * AudioSystem.isConversionSupported}) or capabilities (e.g.
317 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a return
318 * value of {@code AudioSystem.NOT_SPECIFIED} means that any (positive)
319 * number of channels is acceptable.
320 *
321 * @return The number of channels (1 for mono, 2 for stereo, etc.), or
322 * {@code AudioSystem.NOT_SPECIFIED}
323 * @see AudioSystem#NOT_SPECIFIED
324 */
325 public int getChannels() {
326
327 return channels;
328 }
329
330 /**
331 * Obtains the frame size in bytes. When this AudioFormat is used for
332 * queries (e.g. {@link AudioSystem#isConversionSupported(AudioFormat,
333 * AudioFormat) AudioSystem.isConversionSupported}) or capabilities (e.g.
334 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a frame size
335 * of {@code AudioSystem.NOT_SPECIFIED} means that any frame size is
336 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
337 * frame size is not defined for this audio format.
338 *
339 * @return the number of bytes per frame, or
340 * {@code AudioSystem.NOT_SPECIFIED}
341 * @see #getSampleSizeInBits()
342 * @see AudioSystem#NOT_SPECIFIED
343 */
344 public int getFrameSize() {
345
346 return frameSize;
347 }
348
349 /**
350 * Obtains the frame rate in frames per second. When this AudioFormat is
351 * used for queries (e.g. {@link AudioSystem#isConversionSupported(
352 * AudioFormat,AudioFormat) AudioSystem.isConversionSupported}) or
353 * capabilities (e.g.
354 * {@link DataLine.Info#getFormats DataLine.Info.getFormats}), a frame rate
355 * of {@code AudioSystem.NOT_SPECIFIED} means that any frame rate is
356 * acceptable. {@code AudioSystem.NOT_SPECIFIED} is also returned when the
357 * frame rate is not defined for this audio format.
358 *
359 * @return the number of frames per second, or
360 * {@code AudioSystem.NOT_SPECIFIED}
361 * @see #getSampleRate()
362 * @see AudioSystem#NOT_SPECIFIED
363 */
364 public float getFrameRate() {
365
366 return frameRate;
367 }
368
369 /**
370 * Indicates whether the audio data is stored in big-endian or little-endian
371 * byte order. If the sample size is not more than one byte, the return
372 * value is irrelevant.
373 *
374 * @return {@code true} if the data is stored in big-endian byte order,
375 * {@code false} if little-endian
376 */
377 public boolean isBigEndian() {
378
379 return bigEndian;
380 }
381
382 /**
383 * Obtain an unmodifiable map of properties. The concept of properties is
384 * further explained in the {@link AudioFileFormat class description}.
385 *
386 * @return a {@code Map<String, Object>} object containing all properties.
387 * If no properties are recognized, an empty map is returned.
388 * @see #getProperty(String)
389 * @since 1.5
390 */
391 @SuppressWarnings("unchecked") // Cast of result of clone.
392 public Map<String,Object> properties() {
393 Map<String,Object> ret;
394 if (properties == null) {
395 ret = new HashMap<>(0);
396 } else {
397 ret = (Map<String,Object>) (properties.clone());
398 }
399 return Collections.unmodifiableMap(ret);
400 }
401
402 /**
403 * Obtain the property value specified by the key. The concept of properties
404 * is further explained in the {@link AudioFileFormat class description}.
405 * <p>
406 * If the specified property is not defined for a particular file format,
407 * this method returns {@code null}.
408 *
409 * @param key the key of the desired property
410 * @return the value of the property with the specified key, or {@code null}
411 * if the property does not exist
412 * @see #properties()
413 * @since 1.5
414 */
415 public Object getProperty(String key) {
416 if (properties == null) {
417 return null;
418 }
419 return properties.get(key);
420 }
421
422 /**
423 * Indicates whether this format matches the one specified. To match, two
424 * formats must have the same encoding, and consistent values of the number
425 * of channels, sample rate, sample size, frame rate, and frame size. The
426 * values of the property are consistent if they are equal or the specified
427 * format has the property value {@code AudioSystem.NOT_SPECIFIED}. The byte
428 * order (big-endian or little-endian) must be the same if the sample size
429 * is greater than one byte.
430 *
431 * @param format format to test for match
432 * @return {@code true} if this format matches the one specified,
433 * {@code false} otherwise
434 */
435 public boolean matches(AudioFormat format) {
436 if (format.getEncoding().equals(getEncoding())
437 && (format.getChannels() == AudioSystem.NOT_SPECIFIED
438 || format.getChannels() == getChannels())
439 && (format.getSampleRate() == (float)AudioSystem.NOT_SPECIFIED
440 || format.getSampleRate() == getSampleRate())
441 && (format.getSampleSizeInBits() == AudioSystem.NOT_SPECIFIED
442 || format.getSampleSizeInBits() == getSampleSizeInBits())
443 && (format.getFrameRate() == (float)AudioSystem.NOT_SPECIFIED
444 || format.getFrameRate() == getFrameRate())
445 && (format.getFrameSize() == AudioSystem.NOT_SPECIFIED
446 || format.getFrameSize() == getFrameSize())
447 && (getSampleSizeInBits() <= 8
448 || format.isBigEndian() == isBigEndian())) {
449 return true;
450 }
451 return false;
452 }
453
454 /**
455 * Returns a string that describes the format, such as: "PCM SIGNED 22050 Hz
456 * 16 bit mono big-endian". The contents of the string may vary between
457 * implementations of Java Sound.
458 *
459 * @return a string that describes the format parameters
460 */
461 @Override
462 public String toString() {
463 String sEncoding = "";
464 if (getEncoding() != null) {
465 sEncoding = getEncoding().toString() + " ";
466 }
467
468 String sSampleRate;
469 if (getSampleRate() == (float) AudioSystem.NOT_SPECIFIED) {
470 sSampleRate = "unknown sample rate, ";
471 } else {
472 sSampleRate = "" + getSampleRate() + " Hz, ";
473 }
474
475 String sSampleSizeInBits;
476 if (getSampleSizeInBits() == (float) AudioSystem.NOT_SPECIFIED) {
477 sSampleSizeInBits = "unknown bits per sample, ";
478 } else {
479 sSampleSizeInBits = "" + getSampleSizeInBits() + " bit, ";
480 }
481
482 String sChannels;
483 if (getChannels() == 1) {
484 sChannels = "mono, ";
485 } else
486 if (getChannels() == 2) {
487 sChannels = "stereo, ";
488 } else {
489 if (getChannels() == AudioSystem.NOT_SPECIFIED) {
490 sChannels = " unknown number of channels, ";
491 } else {
492 sChannels = ""+getChannels()+" channels, ";
493 }
494 }
495
496 String sFrameSize;
497 if (getFrameSize() == (float) AudioSystem.NOT_SPECIFIED) {
498 sFrameSize = "unknown frame size, ";
499 } else {
500 sFrameSize = "" + getFrameSize()+ " bytes/frame, ";
501 }
502
503 String sFrameRate = "";
504 if (Math.abs(getSampleRate() - getFrameRate()) > 0.00001) {
505 if (getFrameRate() == (float) AudioSystem.NOT_SPECIFIED) {
506 sFrameRate = "unknown frame rate, ";
507 } else {
508 sFrameRate = getFrameRate() + " frames/second, ";
509 }
510 }
511
512 String sEndian = "";
513 if ((getEncoding().equals(Encoding.PCM_SIGNED)
514 || getEncoding().equals(Encoding.PCM_UNSIGNED))
515 && ((getSampleSizeInBits() > 8)
516 || (getSampleSizeInBits() == AudioSystem.NOT_SPECIFIED))) {
517 if (isBigEndian()) {
518 sEndian = "big-endian";
519 } else {
520 sEndian = "little-endian";
521 }
522 }
523
524 return sEncoding
525 + sSampleRate
526 + sSampleSizeInBits
527 + sChannels
528 + sFrameSize
529 + sFrameRate
530 + sEndian;
531
532 }
533
534 /**
535 * The {@code Encoding} class names the specific type of data representation
536 * used for an audio stream. The encoding includes aspects of the sound
537 * format other than the number of channels, sample rate, sample size, frame
538 * rate, frame size, and byte order.
539 * <p>
540 * One ubiquitous type of audio encoding is pulse-code modulation (PCM),
541 * which is simply a linear (proportional) representation of the sound
542 * waveform. With PCM, the number stored in each sample is proportional to
543 * the instantaneous amplitude of the sound pressure at that point in time.
544 * The numbers may be signed or unsigned integers or floats. Besides PCM,
545 * other encodings include mu-law and a-law, which are nonlinear mappings of
546 * the sound amplitude that are often used for recording speech.
547 * <p>
548 * You can use a predefined encoding by referring to one of the static
549 * objects created by this class, such as PCM_SIGNED or PCM_UNSIGNED.
550 * Service providers can create new encodings, such as compressed audio
551 * formats, and make these available through the {@link AudioSystem} class.
552 * <p>
553 * The {@code Encoding} class is static, so that all {@code AudioFormat}
554 * objects that have the same encoding will refer to the same object (rather
555 * than different instances of the same class). This allows matches to be
556 * made by checking that two format's encodings are equal.
557 *
558 * @author Kara Kytle
559 * @see AudioFormat
560 * @see javax.sound.sampled.spi.FormatConversionProvider
561 * @since 1.3
562 */
563 public static class Encoding {
564
565 /**
566 * Specifies signed, linear PCM data.
567 */
568 public static final Encoding PCM_SIGNED = new Encoding("PCM_SIGNED");
569
570 /**
571 * Specifies unsigned, linear PCM data.
572 */
573 public static final Encoding PCM_UNSIGNED = new Encoding("PCM_UNSIGNED");
574
575 /**
576 * Specifies floating-point PCM data.
577 *
578 * @since 1.7
579 */
580 public static final Encoding PCM_FLOAT = new Encoding("PCM_FLOAT");
581
582 /**
583 * Specifies u-law encoded data.
584 */
585 public static final Encoding ULAW = new Encoding("ULAW");
586
587 /**
588 * Specifies a-law encoded data.
589 */
590 public static final Encoding ALAW = new Encoding("ALAW");
591
592 /**
593 * Encoding name.
594 */
595 private String name;
596
597 /**
598 * Constructs a new encoding.
599 *
600 * @param name the name of the new type of encoding
601 */
602 public Encoding(String name) {
603 this.name = name;
604 }
605
606 /**
607 * Finalizes the equals method.
608 */
609 @Override
610 public final boolean equals(Object obj) {
611 if (toString() == null) {
612 return (obj != null) && (obj.toString() == null);
613 }
614 if (obj instanceof Encoding) {
615 return toString().equals(obj.toString());
616 }
617 return false;
618 }
619
620 /**
621 * Finalizes the hashCode method.
622 */
623 @Override
624 public final int hashCode() {
625 if (toString() == null) {
626 return 0;
627 }
628 return toString().hashCode();
629 }
630
631 /**
632 * Provides the {@code String} representation of the encoding. This
633 * {@code String} is the same name that was passed to the constructor.
634 * For the predefined encodings, the name is similar to the encoding's
635 * variable (field) name. For example, {@code PCM_SIGNED.toString()}
636 * returns the name "PCM_SIGNED".
637 *
638 * @return the encoding name
639 */
640 @Override
641 public final String toString() {
642 return name;
643 }
644 }
645 }