ref: c561f2900068530633992798e667ef3131a2420c
parent: da9ecc9768c7ec97a7d29e4e8a2dcb3659685e92
author: cbagwell <cbagwell>
date: Thu Sep 30 20:54:45 EDT 2004
Adding support for floats to wav handler.
--- a/TODO
+++ b/TODO
@@ -13,8 +13,6 @@
of drain (ie. can't run the "reverse" effect twice
on the same command line and have a good output file).
- o Document how to play to audio device in man pages.
-
o Have sox.c auto remove an resample effects when rates are the same
(allows scripts to be dumper).
@@ -69,12 +67,12 @@
o Make a global version of clip() instead of sprinked in all files.
- o Add support to all file handlers to handle 32-bit and float
- data types since raw functions can handle them.
+ o Fix conversions to and from st_sample_t to floats. Currently,
+ its an approximation because it doesn't account from negative
+ side having 1 more value then positive side. That means instead
+ of -1:1 range, its more like -0.999:1 or -1:0.9999.
- o Comment strings. Some file formats have space for embedded comments.
- These are currently thrown away. Printing them out, carrying them
- forward, and an option to add new ones would be handy.
+ o Add command line option to override comment string.
o Add support for .TXT format as Cooledit supports. Not really fit for
graphing since it is only a stream of ascii sample values but some
@@ -85,10 +83,6 @@
a sound library called "ST" but libraries shouldn't exit a program,
they should return error codes for users to handle. Initial support
for this has been added. Needs to be completed.
-
- o Enhance general robustness... For instance, malloc is called in
- lots of places without checking its return value. See last option
- as well.
SOX includes skeleton format files to assist you in supporting new
formats, sound effect loops, and special-purpose programs.
--- a/sox.1
+++ b/sox.1
@@ -194,7 +194,7 @@
The option syntax is a little grotty, but in essence:
.P
.br
- sox File.au file.wav
+ sox file.au file.wav
.P
.br
translates a sound file in SUN Sparc .AU format
@@ -374,6 +374,20 @@
can have multiple audio and picture chunks.
You may need a separate archiver to work with them.
.TP 10
+.B .alsa
+ALSA /dev/snd/pcmCxDxp device driver
+.br
+This is a pseudo-file type and can be optionally compiled into SoX. Run
+.B sox -h
+to see if you have support for this file type. When this driver is used
+it allows you to open up the ALSA /dev/snd/pcmCxDxp file and configure it to
+use the same data format as passed in to \fBSoX\fR.
+It works for both playing and recording sound samples. When playing sound
+files it attempts to set up the ALSA driver to use the same format as the
+input file. It is suggested to always override the output values to use
+the highest quality samples your sound card can handle. Example:
+.I sox infile -t alsa -w -s /dev/snd/pcmC0D0p
+.TP 10
.B .au
SUN Microsystems AU files.
There are apparently many types of .au files;
@@ -502,7 +516,7 @@
files it attempts to set up the OSS driver to use the same format as the
input file. It is suggested to always override the output values to use
the highest quality samples your sound card can handle. Example:
-.I -t ossdsp -w -s /dev/dsp
+.I sox infile -t ossdsp -w -s /dev/dsp
.TP 10
.B .prc
Psion record.app
@@ -558,9 +572,9 @@
files it attempts to set up the audio driver to use the same format as the
input file. It is suggested to always override the output values to use
the highest quality samples your hardware can handle. Example:
-.I -t sunau -w -s /dev/audio
+.I sox infile -t sunau -w -s /dev/audio
or
-.I -t sunau -U -c 1 /dev/audio
+.I sox infile -t sunau -U -c 1 /dev/audio
for older sun equipment.
.TP 10
.B .txw
--- a/sox.txt
+++ b/sox.txt
@@ -126,7 +126,7 @@
OPTIONS
The option syntax is a little grotty, but in essence:
- sox File.au file.wav
+ sox file.au file.wav
translates a sound file in SUN Sparc .AU format into a Microsoft .WAV
file, while
@@ -286,6 +286,19 @@
can have multiple audio and picture chunks. You may need a
separate archiver to work with them.
+ .alsa ALSA /dev/snd/pcmCxDxp device driver
+ This is a pseudo-file type and can be optionally compiled
+ into SoX. Run sox -h to see if you have support for this
+ file type. When this driver is used it allows you to open up
+ the ALSA /dev/snd/pcmCxDxp file and configure it to use the
+ same data format as passed in to SoX. It works for both
+ playing and recording sound samples. When playing sound
+ files it attempts to set up the ALSA driver to use the same
+ format as the input file. It is suggested to always override
+ the output values to use the highest quality samples your
+ sound card can handle. Example: sox infile -t alsa -w -s
+ /dev/snd/pcmC0D0p
+
.au SUN Microsystems AU files. There are apparently many types
of .au files; DEC has invented its own with a different magic
number and word order. The .au handler can read these files
@@ -384,7 +397,7 @@
attempts to set up the OSS driver to use the same format as
the input file. It is suggested to always override the out-
put values to use the highest quality samples your sound card
- can handle. Example: -t ossdsp -w -s /dev/dsp
+ can handle. Example: sox infile -t ossdsp -w -s /dev/dsp
.prc Psion record.app
Used in some Psion devices for System alarms. This format is
@@ -430,109 +443,110 @@
attempts to set up the audio driver to use the same format as
the input file. It is suggested to always override the out-
put values to use the highest quality samples your hardware
- can handle. Example: -t sunau -w -s /dev/audio or -t sunau
- -U -c 1 /dev/audio for older sun equipment.
+ can handle. Example: sox infile -t sunau -w -s /dev/audio or
+ sox infile -t sunau -U -c 1 /dev/audio for older sun equip-
+ ment.
.txw Yamaha TX-16W sampler.
- A file format from a Yamaha sampling keyboard which wrote
- IBM-PC format 3.5" floppies. Handles reading of files which
- do not have the sample rate field set to one of the expected
- by looking at some other bytes in the attack/loop length
- fields, and defaulting to 33kHz if the sample rate is still
+ A file format from a Yamaha sampling keyboard which wrote
+ IBM-PC format 3.5" floppies. Handles reading of files which
+ do not have the sample rate field set to one of the expected
+ by looking at some other bytes in the attack/loop length
+ fields, and defaulting to 33kHz if the sample rate is still
unknown.
.vms More info to come.
- Used to compress speech audio for applications such as voice
+ Used to compress speech audio for applications such as voice
mail.
.voc Sound Blaster VOC files.
- VOC files are multi-part and contain silence parts, looping,
- and different sample rates for different chunks. On input,
- the silence parts are filled out, loops are rejected, and
+ VOC files are multi-part and contain silence parts, looping,
+ and different sample rates for different chunks. On input,
+ the silence parts are filled out, loops are rejected, and
sample data with a new sample rate is rejected. Silence with
- a different sample rate is generated appropriately. On out-
- put, silence is not detected, nor are impossible sample
- rates. Note, this version now supports playing VOC files
+ a different sample rate is generated appropriately. On out-
+ put, silence is not detected, nor are impossible sample
+ rates. Note, this version now supports playing VOC files
with multiple blocks and supports playing files containing u-
law and A-law samples.
vorbis See .ogg format.
- vox A headerless file of Dialogic/OKI ADPCM audio data commonly
- comes with the extension .vox. This ADPCM data has 12-bit
+ vox A headerless file of Dialogic/OKI ADPCM audio data commonly
+ comes with the extension .vox. This ADPCM data has 12-bit
precision packed into only 4-bits.
.wav Microsoft .WAV RIFF files.
- These appear to be very similar to IFF files, but not the
- same. They are the native sound file format of Windows.
- (Obviously, Windows was of such incredible importance to the
+ These appear to be very similar to IFF files, but not the
+ same. They are the native sound file format of Windows.
+ (Obviously, Windows was of such incredible importance to the
computer industry that it just had to have its own sound file
format.) Normally .wav files have all formatting information
in their headers, and so do not need any format options spec-
- ified for an input file. If any are, they will override the
- file header, and you will be warned to this effect. You had
- better know what you are doing! Output format options will
- cause a format conversion, and the .wav will written appro-
- priately. SoX currently can read PCM, ULAW, ALAW, MS ADPCM,
- and IMA (or DVI) ADPCM. It can write all of these formats
+ ified for an input file. If any are, they will override the
+ file header, and you will be warned to this effect. You had
+ better know what you are doing! Output format options will
+ cause a format conversion, and the .wav will written appro-
+ priately. SoX currently can read PCM, ULAW, ALAW, MS ADPCM,
+ and IMA (or DVI) ADPCM. It can write all of these formats
including (NEW!) the ADPCM encoding.
.wve Psion 8-bit A-law
- These are 8-bit A-law 8khz sound files used on the Psion
+ These are 8-bit A-law 8khz sound files used on the Psion
palmtop portable computer.
.raw Raw files (no header).
The sample rate, size (byte, word, etc), and encoding
- (signed, unsigned, etc.) of the sample file must be given.
+ (signed, unsigned, etc.) of the sample file must be given.
The number of channels defaults to 1.
.ub, .sb, .uw, .sw, .ul, .al, .lu, .la, .sl
These are several suffices which serve as a shorthand for raw
- files with a given size and encoding. Thus, ub, sb, uw, sw,
- ul, al, lu, la and sl correspond to "unsigned byte", "signed
- byte", "unsigned word", "signed word", "u-law" (byte), "A-
+ files with a given size and encoding. Thus, ub, sb, uw, sw,
+ ul, al, lu, la and sl correspond to "unsigned byte", "signed
+ byte", "unsigned word", "signed word", "u-law" (byte), "A-
law" (byte), inverse bit order "u-law", inverse bit order "A-
law", and "signed long". The sample rate defaults to 8000 hz
if not explicitly set, and the number of channels defaults to
- 1. There are lots of Sparc samples floating around in u-law
- format with no header and fixed at a sample rate of 8000 hz.
- (Certain sound management software cheerfully ignores the
- headers.) Similarly, most Mac sound files are in unsigned
+ 1. There are lots of Sparc samples floating around in u-law
+ format with no header and fixed at a sample rate of 8000 hz.
+ (Certain sound management software cheerfully ignores the
+ headers.) Similarly, most Mac sound files are in unsigned
byte format with a sample rate of 11025 or 22050 hz.
- .auto This is a ‘‘meta-type’’: specifying this type for an input
- file triggers some code that tries to guess the real type by
- looking for magic words in the header. If the type can’t be
- guessed, the program exits with an error message. The input
- must be a plain file, not a pipe. This type can’t be used
+ .auto This is a ‘‘meta-type’’: specifying this type for an input
+ file triggers some code that tries to guess the real type by
+ looking for magic words in the header. If the type can’t be
+ guessed, the program exits with an error message. The input
+ must be a plain file, not a pipe. This type can’t be used
for output files.
EFFECTS
- Multiple effects may be applied to the audio data by specifying them
+ Multiple effects may be applied to the audio data by specifying them
one after another at the end of the command line.
avg [ -l | -r | -f | -b | -1 | -2 | -3 | -4 | n,n,...,n ]
- Reduce the number of channels by averaging the samples, or
- duplicate channels to increase the number of channels. This
- effect is automatically used when the number of input chan-
- nels differ from the number of output channels. When reduc-
+ Reduce the number of channels by averaging the samples, or
+ duplicate channels to increase the number of channels. This
+ effect is automatically used when the number of input chan-
+ nels differ from the number of output channels. When reduc-
ing the number of channels it is possible to manually specify
- the avg effect and use the -l, -r, -f, -b, -1, -2, -3, -4,
- options to select only the left, right, front, back chan-
- nel(s) or specific channel for the output instead of averag-
- ing the channels. The -l, and -r options will do averaging
- in quad-channel files so select the exact channel to prevent
+ the avg effect and use the -l, -r, -f, -b, -1, -2, -3, -4,
+ options to select only the left, right, front, back chan-
+ nel(s) or specific channel for the output instead of averag-
+ ing the channels. The -l, and -r options will do averaging
+ in quad-channel files so select the exact channel to prevent
this.
- The avg effect can also be invoked with up to 16 double-pre-
- cision numbers, seperated by commas, which specify the pro-
- portion (0.0 = 0% and 1.0 = 100%) of each input channel that
- is to be mixed into each output channel. In two-channel
- mode, 4 numbers are given: l->l, l->r, r->l, and r->r,
+ The avg effect can also be invoked with up to 16 double-
+ precision numbers, seperated by commas, which specify the
+ proportion (0.0 = 0% and 1.0 = 100%) of each input channel
+ that is to be mixed into each output channel. In two-channel
+ mode, 4 numbers are given: l->l, l->r, r->l, and r->r,
respectively. In four-channel mode, the first 4 numbers give
- the proportions for the left-front output channel, as fol-
- lows: lf->lf, rf->lf, lb->lf, and rb->rf. The next 4 give
- the right-front output in the same order, then left-back and
+ the proportions for the left-front output channel, as fol-
+ lows: lf->lf, rf->lf, lb->lf, and rb->rf. The next 4 give
+ the right-front output in the same order, then left-back and
right-back.
It is also possible to use the 16 numbers to expand or reduce
@@ -555,15 +569,15 @@
band [ -n ] center [ width ]
Apply a band-pass filter. The frequency response drops loga-
rithmically around the center frequency. The width gives the
- slope of the drop. The frequencies at center + width and
- center - width will be half of their original amplitudes.
- Band defaults to a mode oriented to pitched signals, i.e.
- voice, singing, or instrumental music. The -n (for noise)
+ slope of the drop. The frequencies at center + width and
+ center - width will be half of their original amplitudes.
+ Band defaults to a mode oriented to pitched signals, i.e.
+ voice, singing, or instrumental music. The -n (for noise)
option uses the alternate mode for un-pitched signals. Warn-
- ing: -n introduces a power-gain of about 11dB in the filter,
- so beware of output clipping. Band introduces noise in the
+ ing: -n introduces a power-gain of about 11dB in the filter,
+ so beware of output clipping. Band introduces noise in the
shape of the filter, i.e. peaking at the center frequency and
- settling around it. See filter for a bandpass effect with
+ settling around it. See filter for a bandpass effect with
steeper shoulders.
bandpass frequency bandwidth
@@ -575,11 +589,11 @@
chorus gain-in gain-out delay decay speed depth
-s | -t [ delay decay speed depth -s | -t ... ]
- Add a chorus to a sound sample. Each quadtuple
- delay/decay/speed/depth gives the delay in milliseconds and
+ Add a chorus to a sound sample. Each quadtuple
+ delay/decay/speed/depth gives the delay in milliseconds and
the decay (relative to gain-in) with a modulation speed in Hz
- using depth in milliseconds. The modulation is either sinu-
- soidal (-s) or triangular (-t). Gain-out is the volume of
+ using depth in milliseconds. The modulation is either sinu-
+ soidal (-s) or triangular (-t). Gain-out is the volume of
the output.
compand attack1,decay1[,attack2,decay2...]
@@ -587,63 +601,63 @@
in-dB1,out-dB1[,in-dB2,out-dB2...]
[gain [initial-volume [delay ] ] ]
- Compand (compress or expand) the dynamic range of a sample.
- The attack and decay time specify the integration time over
+ Compand (compress or expand) the dynamic range of a sample.
+ The attack and decay time specify the integration time over
which the absolute value of the input signal is integrated to
- determine its volume; attacks refer to increases in volume
- and decays refer to decreases. Where more than one pair of
- attack/decay parameters are specified, each channel is
- treated separately and the number of pairs must agree with
+ determine its volume; attacks refer to increases in volume
+ and decays refer to decreases. Where more than one pair of
+ attack/decay parameters are specified, each channel is
+ treated separately and the number of pairs must agree with
the number of input channels. The second parameter is a list
- of points on the compander’s transfer function specified in
- dB relative to the maximum possible signal amplitude. The
- input values must be in a strictly increasing order but the
- transfer function does not have to be monotonically rising.
+ of points on the compander’s transfer function specified in
+ dB relative to the maximum possible signal amplitude. The
+ input values must be in a strictly increasing order but the
+ transfer function does not have to be monotonically rising.
The special value -inf may be used to indicate that the input
volume should be associated output volume. The points
- -inf,-inf and 0,0 are assumed; the latter may be overridden,
+ -inf,-inf and 0,0 are assumed; the latter may be overridden,
but the former may not.
- The third (optional) parameter is a post-processing gain in
- dB which is applied after the compression has taken place;
- the fourth (optional) parameter is an initial volume to be
- assumed for each channel when the effect starts. This per-
- mits the user to supply a nominal level initially, so that,
+ The third (optional) parameter is a post-processing gain in
+ dB which is applied after the compression has taken place;
+ the fourth (optional) parameter is an initial volume to be
+ assumed for each channel when the effect starts. This per-
+ mits the user to supply a nominal level initially, so that,
for example, a very large gain is not applied to initial sig-
nal levels before the companding action has begun to operate:
- it is quite probable that in such an event, the output would
+ it is quite probable that in such an event, the output would
be severely clipped while the compander gain properly adjusts
itself.
- The fifth (optional) parameter is a delay in seconds. The
- input signal is analyzed immediately to control the compan-
- der, but it is delayed before being fed to the volume
- adjuster. Specifying a delay approximately equal to the
- attack/decay times allows the compander to effectively oper-
+ The fifth (optional) parameter is a delay in seconds. The
+ input signal is analyzed immediately to control the compan-
+ der, but it is delayed before being fed to the volume
+ adjuster. Specifying a delay approximately equal to the
+ attack/decay times allows the compander to effectively oper-
ate in a "predictive" rather than a reactive mode.
- copy Copy the input file to the output file. This is the default
+ copy Copy the input file to the output file. This is the default
effect if both files have the same sampling rate.
dcshift shift [ limitergain ]
DC Shift the audio data, with basic linear amplitude formula.
- This is most useful if your audio data tends to not be cen-
- tered around a value of 0. Shifting it back will allow you
- to get the most volume adjustments without clipping audio
+ This is most useful if your audio data tends to not be cen-
+ tered around a value of 0. Shifting it back will allow you
+ to get the most volume adjustments without clipping audio
data.
- The first option is the dcshift value. It is a floating
+ The first option is the dcshift value. It is a floating
point number that indicates the amount to shift.
- An option limtergain value can be specified as well. It
- should have a value much less then 1.0 and is used only on
+ An option limtergain value can be specified as well. It
+ should have a value much less then 1.0 and is used only on
peaks to prevent clipping.
- deemph Apply a treble attenuation shelving filter to samples in
- audio cd format. The frequency response of pre-emphasized
- recordings is rectified. The filtering is defined in the
+ deemph Apply a treble attenuation shelving filter to samples in
+ audio cd format. The frequency response of pre-emphasized
+ recordings is rectified. The filtering is defined in the
standard document ISO 908.
- earwax Makes sound easier to listen to on headphones. Adds audio-
- cues to samples in audio cd format so that when listened to
+ earwax Makes sound easier to listen to on headphones. Adds audio-
+ cues to samples in audio cd format so that when listened to
on headphones the stereo image is moved from inside your head
(standard for headphones) to outside and in front of the lis-
tener (standard for speakers). See
@@ -650,13 +664,13 @@
www.geocities.com/beinges for a full explanation.
echo gain-in gain-out delay decay [ delay decay ... ]
- Add echoing to a sound sample. Each delay/decay part gives
+ Add echoing to a sound sample. Each delay/decay part gives
the delay in milliseconds and the decay (relative to gain-in)
of that echo. Gain-out is the volume of the output.
echos gain-in gain-out delay decay [ delay decay ... ]
- Add a sequence of echos to a sound sample. Each delay/decay
- part gives the delay in milliseconds and the decay (relative
+ Add a sequence of echos to a sound sample. Each delay/decay
+ part gives the delay in milliseconds and the decay (relative
to gain-in) of that echo. Gain-out is the volume of the out-
put.
@@ -670,52 +684,52 @@
volume of the audio from 0 to full volume over fade-in-length
seconds. Specify 0 seconds if no fade-in is wanted.
- For fade-outs, the audio data will be truncated at the stop-
+ For fade-outs, the audio data will be truncated at the stop-
time and the volume will be ramped from full volume down to 0
starting at fade-out-length seconds before the stop-time. If
- fade-out-length is not specified, it defaults to the same
- value as fade-in-length. No fade-out is performed if the
+ fade-out-length is not specified, it defaults to the same
+ value as fade-in-length. No fade-out is performed if the
stop-time is not specified.
- All times can be specified in either periods of time or sam-
- ple counts. To specify time periods use the format
- hh:mm:ss.frac format. To specify using sample counts, spec-
- ify the number of samples and append the letter ’s’ to the
+ All times can be specified in either periods of time or sam-
+ ple counts. To specify time periods use the format
+ hh:mm:ss.frac format. To specify using sample counts, spec-
+ ify the number of samples and append the letter ’s’ to the
sample count (for example 8000s).
An optional type can be specified to change the type of enve-
- lope. Choices are q for quarter of a sinewave, h for half a
- sinewave, t for linear slope, l for logarithmic, and p for
+ lope. Choices are q for quarter of a sinewave, h for half a
+ sinewave, t for linear slope, l for logarithmic, and p for
inverted parabola. The default is a linear slope.
filter [ low ]-[ high ] [ window-len [ beta ] ]
- Apply a Sinc-windowed lowpass, highpass, or bandpass filter
+ Apply a Sinc-windowed lowpass, highpass, or bandpass filter
of given window length to the signal. low refers to the fre-
quency of the lower 6dB corner of the filter. high refers to
the frequency of the upper 6dB corner of the filter.
- A lowpass filter is obtained by leaving low unspecified, or
- 0. A highpass filter is obtained by leaving high unspeci-
- fied, or 0, or greater than or equal to the Nyquist fre-
+ A lowpass filter is obtained by leaving low unspecified, or
+ 0. A highpass filter is obtained by leaving high unspeci-
+ fied, or 0, or greater than or equal to the Nyquist fre-
quency.
The window-len, if unspecified, defaults to 128. Longer win-
- dows give a sharper cutoff, smaller windows a more gradual
+ dows give a sharper cutoff, smaller windows a more gradual
cutoff.
- The beta, if unspecified, defaults to 16. This selects a
+ The beta, if unspecified, defaults to 16. This selects a
Kaiser window. You can select a Nuttall window by specifying
- anything <= 2.0 here. For more discussion of beta, look
+ anything <= 2.0 here. For more discussion of beta, look
under the resample effect.
flanger gain-in gain-out delay decay speed < -s | -t >
Add a flanger to a sound sample. Each triple
- delay/decay/speed gives the delay in milliseconds and the
- decay (relative to gain-in) with a modulation speed in Hz.
- The modulation is either sinodial (-s) or triangular (-t).
+ delay/decay/speed gives the delay in milliseconds and the
+ decay (relative to gain-in) with a modulation speed in Hz.
+ The modulation is either sinodial (-s) or triangular (-t).
Gain-out is the volume of the output.
highp frequency
- Apply a single pole recursive high-pass filter. The fre-
+ Apply a single pole recursive high-pass filter. The fre-
quency response drops logarithmically with I frequency in the
middle of the drop. The slope of the filter is quite gentle.
See filter for a highpass effect with sharper cutoff.
@@ -725,8 +739,8 @@
lowp frequency
Apply a single pole recursive low-pass filter. The frequency
- response drops logarithmically with frequency in the middle
- of the drop. The slope of the filter is quite gentle. See
+ response drops logarithmically with frequency in the middle
+ of the drop. The slope of the filter is quite gentle. See
filter for a lowpass effect with sharper cutoff.
lowpass frequency
@@ -734,8 +748,8 @@
mask Add "masking noise" to signal. This effect deliberately adds
white noise to a sound in order to mask quantization effects,
- created by the process of playing a sound digitally. It
- tends to mask buzzing voices, for example. It adds 1/2 bit
+ created by the process of playing a sound digitally. It
+ tends to mask buzzing voices, for example. It adds 1/2 bit
of noise to the sound file at the output bit depth.
mcompand "attack1,decay1[,attack2,decay2...]
@@ -744,48 +758,48 @@
[gain [initial-volume [delay ] ] ]" xover_freq
- Multi-band compander is similar to the single band compander
- but the audio file is first divided up into bands and then
- the compander is ran on each band. See the compand effect
+ Multi-band compander is similar to the single band compander
+ but the audio file is first divided up into bands and then
+ the compander is ran on each band. See the compand effect
for definition of its options. Compand options are specified
- between double quotes and the crossover frequency for that
- band is specefied seperately with xover_fre. This can be
+ between double quotes and the crossover frequency for that
+ band is specefied seperately with xover_fre. This can be
repeated multiple times to create multiple bands.
pan direction
- Pan the sound of an audio file from one channel to another.
- This is done by changing the volume of the input channels so
+ Pan the sound of an audio file from one channel to another.
+ This is done by changing the volume of the input channels so
that it fades out on one channel and fades-in on another. If
- the number of input channels is different then the number of
- output channels then this effect tries to intelligently han-
- dle this. For instance, if the input contains 1 channel and
+ the number of input channels is different then the number of
+ output channels then this effect tries to intelligently han-
+ dle this. For instance, if the input contains 1 channel and
the output contains 2 channels, then it will create the miss-
- ing channel itself. The direction is a value from -1.0 to
- 1.0. -1.0 represents far left and 1.0 represents far right.
- Numbers in between will start the pan effect without totally
+ ing channel itself. The direction is a value from -1.0 to
+ 1.0. -1.0 represents far left and 1.0 represents far right.
+ Numbers in between will start the pan effect without totally
muting the opposite channel.
phaser gain-in gain-out delay decay speed < -s | -t >
- Add a phaser to a sound sample. Each triple
- delay/decay/speed gives the delay in milliseconds and the
- decay (relative to gain-in) with a modulation speed in Hz.
- The modulation is either sinodial (-s) or triangular (-t).
- The decay should be less than 0.5 to avoid feedback. Gain-
+ Add a phaser to a sound sample. Each triple
+ delay/decay/speed gives the delay in milliseconds and the
+ decay (relative to gain-in) with a modulation speed in Hz.
+ The modulation is either sinodial (-s) or triangular (-t).
+ The decay should be less than 0.5 to avoid feedback. Gain-
out is the volume of the output.
pick [ -1 | -2 | -3 | -4 | -l | -r | -f | -b ]
- Pick a subset of channels to be copied into the output file.
- This effect is just an alias of the "avg" effect but is left
+ Pick a subset of channels to be copied into the output file.
+ This effect is just an alias of the "avg" effect but is left
here for historical reasons.
pitch shift [ width interpole fade ]
- Change the pitch of file without affecting its duration by
+ Change the pitch of file without affecting its duration by
cross-fading shifted samples. shift is given in cents. Use a
positive value to shift to treble, negative value to shift to
bass. Default shift is 0. width of window is in ms. Default
- width is 20ms. Try 30ms to lower pitch, and 10ms to raise
+ width is 20ms. Try 30ms to lower pitch, and 10ms to raise
pitch. interpole option, can be "cubic" or "linear". Default
- is "cubic". The fade option, can be "cos", "hamming", "lin-
+ is "cubic". The fade option, can be "cos", "hamming", "lin-
ear" or "trapezoid". Default is "cos".
polyphase [ -w < nut / ham > ]
@@ -793,68 +807,68 @@
[ -width < long / short / # > ]
[ -cutoff # ]
- Translate input sampling rate to output sampling rate via
- polyphase interpolation, a DSP algorithm. This method is
+ Translate input sampling rate to output sampling rate via
+ polyphase interpolation, a DSP algorithm. This method is
slow and uses lots of RAM, but gives much better results than
rate.
- -w < nut / ham > : select either a Nuttal (~90 dB stopband)
+ -w < nut / ham > : select either a Nuttal (~90 dB stopband)
or Hamming (~43 dB stopband) window. Default is nut.
- -width long / short / # : specify the (approximate) width of
- the filter. long is 1024 samples; short is 128 samples.
+ -width long / short / # : specify the (approximate) width of
+ the filter. long is 1024 samples; short is 128 samples.
Alternatively, an exact number can be used. Default is long.
- The short option is not recommended, as it produces poor
+ The short option is not recommended, as it produces poor
quality results.
- -cutoff # : specify the filter cutoff frequency in terms of
- fraction of frequency bandwidth, also know as the Nyquist
+ -cutoff # : specify the filter cutoff frequency in terms of
+ fraction of frequency bandwidth, also know as the Nyquist
frequency. Please see the resample effect for further infor-
mation on Nyquist frequency. If upsampling, then this is the
- fraction of the original signal that should go through. If
- downsampling, this is the fraction of the signal left after
- downsampling. Default is 0.95. Remember that this is a
+ fraction of the original signal that should go through. If
+ downsampling, this is the fraction of the signal left after
+ downsampling. Default is 0.95. Remember that this is a
float.
- rate Translate input sampling rate to output sampling rate via
- linear interpolation to the Least Common Multiple of the two
- sampling rates. This is the default effect if the two files
- have different sampling rates and the preview options was
+ rate Translate input sampling rate to output sampling rate via
+ linear interpolation to the Least Common Multiple of the two
+ sampling rates. This is the default effect if the two files
+ have different sampling rates and the preview options was
specified. This is fast but noisy: the spectrum of the orig-
- inal sound will be shifted upwards and duplicated faintly
+ inal sound will be shifted upwards and duplicated faintly
when up-translating by a multiple.
- Lerp-ing is acceptable for cheap 8-bit sound hardware, but
- for CD-quality sound you should instead use either resample
- or polyphase. If you are wondering which rate changing
- effects to use, you will want to read a detailed analysis of
- all of them at http://eakaw2.et.tu-dresden.de/~wilde/resam-
+ Lerp-ing is acceptable for cheap 8-bit sound hardware, but
+ for CD-quality sound you should instead use either resample
+ or polyphase. If you are wondering which rate changing
+ effects to use, you will want to read a detailed analysis of
+ all of them at http://eakaw2.et.tu-dresden.de/~wilde/resam-
ple/resample.html
repeat count
- Repeats the audio data count times. Requires disk space to
+ Repeats the audio data count times. Requires disk space to
store the data to be repeated.
resample [ -qs | -q | -ql ] [ rolloff [ beta ] ]
- Translate input sampling rate to output sampling rate via
- simulated analog filtration. This method is slower than
+ Translate input sampling rate to output sampling rate via
+ simulated analog filtration. This method is slower than
rate, but gives much better results.
By default, linear interpolation is used, with a window width
about 45 samples at the lower of the two rate. This gives an
- accuracy of about 16 bits, but insufficient stopband rejec-
- tion in the case that you want to have rolloff greater than
+ accuracy of about 16 bits, but insufficient stopband rejec-
+ tion in the case that you want to have rolloff greater than
about 0.80 of the Nyquist frequency.
- The -q* options will change the default values for rolloff
- and beta as well as use quadratic interpolation of filter
+ The -q* options will change the default values for rolloff
+ and beta as well as use quadratic interpolation of filter
coefficients, resulting in about 24 bits precision. The -qs,
- -q, or -ql options specify increased accuracy at the cost of
+ -q, or -ql options specify increased accuracy at the cost of
lower execution speed. It is optional to specify rolloff and
beta parameters when using the -q* options.
- Following is a table of the reasonable defaults which are
+ Following is a table of the reasonable defaults which are
built-in to SoX:
Option Window rolloff beta interpolation
@@ -866,67 +880,67 @@
------ ------ ------- ---- -------------
-qs, -q, or -ql use window lengths of 45, 75, or 149 samples,
- respectively, at the lower sample-rate of the two files.
+ respectively, at the lower sample-rate of the two files.
This means progressively sharper stop-band rejection, at pro-
portionally slower execution times.
- rolloff refers to the cut-off frequency of the low pass fil-
- ter and is given in terms of the Nyquist frequency for the
- lower sample rate. rolloff therefore should be something
- between 0.0 and 1.0, in practice 0.8-0.95. The defaults are
+ rolloff refers to the cut-off frequency of the low pass fil-
+ ter and is given in terms of the Nyquist frequency for the
+ lower sample rate. rolloff therefore should be something
+ between 0.0 and 1.0, in practice 0.8-0.95. The defaults are
indicated above.
- The Nyquist frequency is equal to (sample rate / 2). Logi-
- cally, this is because the A/D converter needs at least 2
+ The Nyquist frequency is equal to (sample rate / 2). Logi-
+ cally, this is because the A/D converter needs at least 2
samples to detect 1 cycle at the Nyquist frequency. Frequen-
- cies higher then the Nyquist will actually appear as lower
- frequencies to the A/D converter and is called aliasing.
+ cies higher then the Nyquist will actually appear as lower
+ frequencies to the A/D converter and is called aliasing.
Normally, A/D converts run the signal through a highpass fil-
ter first to avoid these problems.
- Similar problems will happen in software when reducing the
- sample rate of an audio file (frequencies above the new
- Nyquist frequency can be aliased to lower frequencies).
- Therefore, a good resample effect will remove all frequency
+ Similar problems will happen in software when reducing the
+ sample rate of an audio file (frequencies above the new
+ Nyquist frequency can be aliased to lower frequencies).
+ Therefore, a good resample effect will remove all frequency
information above the new Nyquist frequency.
The rolloff refers to how close to the Nyquist frequency this
- cutoff is, with closer being better. When increasing the
+ cutoff is, with closer being better. When increasing the
sample rate of an audio file you would not expect to have any
- frequencies exist that are past the original Nyquist fre-
- quency. Because of resampling properties, it is common to
+ frequencies exist that are past the original Nyquist fre-
+ quency. Because of resampling properties, it is common to
have aliasing data created that is above the old Nyquist fre-
- quency. In that case the rolloff refers to how close to the
+ quency. In that case the rolloff refers to how close to the
original Nyquist frequency to use a highpass filter to remove
this false data, with closer also being better.
The beta parameter determines the type of filter window used.
- Any value greater than 2.0 is the beta for a Kaiser window.
- Beta <= 2.0 selects a Nuttall window. If unspecified, the
+ Any value greater than 2.0 is the beta for a Kaiser window.
+ Beta <= 2.0 selects a Nuttall window. If unspecified, the
default is a Kaiser window with beta 16.
- In the case of Kaiser window (beta > 2.0), lower betas pro-
- duce a somewhat faster transition from passband to stopband,
- at the cost of noticeable artifacts. A beta of 16 is the
+ In the case of Kaiser window (beta > 2.0), lower betas pro-
+ duce a somewhat faster transition from passband to stopband,
+ at the cost of noticeable artifacts. A beta of 16 is the
default, beta less than 10 is not recommended. If you want a
- sharper cutoff, don’t use low beta’s, use a longer sample
- window. A Nuttall window is selected by specifying any
+ sharper cutoff, don’t use low beta’s, use a longer sample
+ window. A Nuttall window is selected by specifying any
’beta’ <= 2, and the Nuttall window has somewhat steeper cut-
- off than the default Kaiser window. You will probably not
- need to use the beta parameter at all, unless you are just
- curious about comparing the effects of Nuttall vs. Kaiser
+ off than the default Kaiser window. You will probably not
+ need to use the beta parameter at all, unless you are just
+ curious about comparing the effects of Nuttall vs. Kaiser
windows.
- This is the default effect if the two files have different
- sampling rates. Default parameters are, as indicated above,
- Kaiser window of length 45, rolloff 0.80, beta 16, linear
+ This is the default effect if the two files have different
+ sampling rates. Default parameters are, as indicated above,
+ Kaiser window of length 45, rolloff 0.80, beta 16, linear
interpolation.
- NOTE: -qs is only slightly slower, but more accurate for
+ NOTE: -qs is only slightly slower, but more accurate for
16-bit or higher precision.
- NOTE: In many cases of up-sampling, no interpolation is
- needed, as exact filter coefficients can be computed in a
+ NOTE: In many cases of up-sampling, no interpolation is
+ needed, as exact filter coefficients can be computed in a
reasonable amount of space. To be precise, this is done when
input_rate < output_rate
@@ -934,13 +948,13 @@
output_rate/gcd(input_rate,output_rate) <= 511
reverb gain-out reverbe-time delay [ delay ... ]
- Add reverberation to a sound sample. Each delay is given in
+ Add reverberation to a sound sample. Each delay is given in
milliseconds and its feedback is depending on the reverb-time
- in milliseconds. Each delay should be in the range of half
- to quarter of reverb-time to get a realistic reverberation.
+ in milliseconds. Each delay should be in the range of half
+ to quarter of reverb-time to get a realistic reverberation.
Gain-out is the volume of the output.
- reverse Reverse the sound sample completely. Included for finding
+ reverse Reverse the sound sample completely. Included for finding
Satanic subliminals.
silence above_periods [ duration threshold[ d | % ]
@@ -948,99 +962,99 @@
[ below_periods duration
threshold[ d | % ]]
- Removes silence from the beginning or end of a sound file.
+ Removes silence from the beginning or end of a sound file.
Silence is anything below a specified threshold.
When trimming silence from the beginning of a sound file, you
- specify a duration of audio that is above a given silence
+ specify a duration of audio that is above a given silence
threshold before audio data is processed. You can also spec-
- ify the count of periods of none-silence you want to detect
- before processing audio data. Specify a period of 0 if you
+ ify the count of periods of none-silence you want to detect
+ before processing audio data. Specify a period of 0 if you
do not want to trim data from the front of the sound file.
- When optionally trimming silence form the end of a sound
- file, you specify the duration of audio that must be below a
- given threshold before stopping to process audio data. A
- count of periods that occur below the threshold may also be
- specified. If this options are not specified then data is
+ When optionally trimming silence form the end of a sound
+ file, you specify the duration of audio that must be below a
+ given threshold before stopping to process audio data. A
+ count of periods that occur below the threshold may also be
+ specified. If this options are not specified then data is
not trimmed from the end of the audio file. If below_periods
- is negative, it is treated as a positive value and is also
- used to indicate the effect should restart processing as
+ is negative, it is treated as a positive value and is also
+ used to indicate the effect should restart processing as
specified by the above_periods, making it suitable for remov-
ing periods of silence in the middle of a sound file.
- Duration counts may be in the format of time, hh:mm:ss.frac,
+ Duration counts may be in the format of time, hh:mm:ss.frac,
or in the exact count of samples.
Threshold may be suffixed with d, or % to indicated the value
- is in decibels or a percentage of max value of the sample
+ is in decibels or a percentage of max value of the sample
value. A value of ’0%’ will look for total silence.
speed [ -c ] factor
- Speed up or down the sound, as a magnetic tape with a speed
- control. It affects both pitch and time. A factor of 1.0
+ Speed up or down the sound, as a magnetic tape with a speed
+ control. It affects both pitch and time. A factor of 1.0
means no change, and is the default. 2.0 doubles speed, thus
- time length is cut by a half and pitch is one octave higher.
- 0.5 halves speed thus time length doubles and pitch is one
- octave lower. If the optional -c parameter is used then the
+ time length is cut by a half and pitch is one octave higher.
+ 0.5 halves speed thus time length doubles and pitch is one
+ octave lower. If the optional -c parameter is used then the
factor is specified in "cents".
stat [ -s n ] [-rms ] [ -v ] [ -d ]
- Do a statistical check on the input file, and print results
- on the standard error file. Audio data is passed unmodified
- from input to output file unless used along with the -e
+ Do a statistical check on the input file, and print results
+ on the standard error file. Audio data is passed unmodified
+ from input to output file unless used along with the -e
option.
- The "Volume Adjustment:" field in the statistics gives you
- the argument to the -v number which will make the sample as
+ The "Volume Adjustment:" field in the statistics gives you
+ the argument to the -v number which will make the sample as
loud as possible without clipping.
The option -v will print out the "Volume Adjustment:" field’s
- value only and return. This could be of use in scripts to
+ value only and return. This could be of use in scripts to
auto convert the volume.
- The -s n option is used to scale the input data by a given
- factor. The default value of n is the max value of a signed
- long variable (0x7fffffff). Internal effects always work
- with signed long PCM data and so the value should relate to
+ The -s n option is used to scale the input data by a given
+ factor. The default value of n is the max value of a signed
+ long variable (0x7fffffff). Internal effects always work
+ with signed long PCM data and so the value should relate to
this fact.
- The -rms option will convert all output average values to
+ The -rms option will convert all output average values to
root mean square format.
- There is also an optional parameter -d that will print out a
- hex dump of the sound file from the internal buffer that is
- in 32-bit signed PCM data. This is mainly only of use in
- tracking down endian problems that creep in to SoX on cross-
+ There is also an optional parameter -d that will print out a
+ hex dump of the sound file from the internal buffer that is
+ in 32-bit signed PCM data. This is mainly only of use in
+ tracking down endian problems that creep in to SoX on cross-
platform versions.
stretch factor [window fade shift fading]
- Time stretch file by a given factor. Change duration without
- affecting the pitch. factor of stretching: >1.0 lengthen,
- <1.0 shorten duration. window size is in ms. Default is
- 20ms. The fade option, can be "lin". shift ratio, in [0.0
- 1.0]. Default depends on stretch factor. 1.0 to shorten, 0.8
+ Time stretch file by a given factor. Change duration without
+ affecting the pitch. factor of stretching: >1.0 lengthen,
+ <1.0 shorten duration. window size is in ms. Default is
+ 20ms. The fade option, can be "lin". shift ratio, in [0.0
+ 1.0]. Default depends on stretch factor. 1.0 to shorten, 0.8
to lengthen. The fading ratio, in [0.0 0.5]. The amount of a
fade’s default depends on factor and shift.
swap [ 1 2 | 1 2 3 4 ]
- Swap channels in multi-channel sound files. Optionally, you
- may specify the channel order you would like the output in.
- This defaults to output channel 2 and then 1 for stereo and
+ Swap channels in multi-channel sound files. Optionally, you
+ may specify the channel order you would like the output in.
+ This defaults to output channel 2 and then 1 for stereo and
2, 1, 4, 3 for quad-channels. An interesting feature is that
- you may duplicate a given channel by overwriting another.
- This is done by repeating an output channel on the command
- line. For example, swap 2 2 will overwrite channel 1 with
- channel 2’s data; creating a stereo file with both channels
+ you may duplicate a given channel by overwriting another.
+ This is done by repeating an output channel on the command
+ line. For example, swap 2 2 will overwrite channel 1 with
+ channel 2’s data; creating a stereo file with both channels
containing the same audio data.
synth [ length ] type mix [ freq [ -freq2 ]
[ off ] [ ph ] [ p1 ] [ p2 ] [ p3 ]
- The synth effect will generate various types of audio data.
+ The synth effect will generate various types of audio data.
Although this effect is used to generate audio data, an input
- file must be specified. The length of the input audio file
+ file must be specified. The length of the input audio file
determines the length of the output audio file.
<length> length in sec or hh:mm:ss.frac, 0=inputlength,
default=0
- <type> is sine, square, triangle, sawtooth, trapetz, exp,
+ <type> is sine, square, triangle, sawtooth, trapetz, exp,
whitenoise, pinknoise, brownnoise, default=sine
<mix> is create, mix, amod, default=create
<freq> frequency at beginning in Hz, not used for noise..
@@ -1048,66 +1062,66 @@
<freq/2> can be given as %%n, where ’n’ is the number of half
notes in respect to A (440Hz)
<off> Bias (DC-offset) of signal in percent, default=0
- <ph> phase shift 0..100 shift phase 0..2*Pi, not used for
+ <ph> phase shift 0..100 shift phase 0..2*Pi, not used for
noise..
- <p1> square: Ton/Toff, triangle+trapetz: rising slope time
+ <p1> square: Ton/Toff, triangle+trapetz: rising slope time
(0..100)
<p2> trapetz: ON time (0..100)
<p3> trapetz: falling slope position (0..100)
trim start [ length ]
- Trim can trim off unwanted audio data from the beginning and
- end of the audio file. Audio samples are not sent to the
+ Trim can trim off unwanted audio data from the beginning and
+ end of the audio file. Audio samples are not sent to the
output stream until the start location is reached.
- The optional length parameter tells the number of samples to
- output after the start sample and is used to trim off the
- back side of the audio data. Using a value of 0 for the
+ The optional length parameter tells the number of samples to
+ output after the start sample and is used to trim off the
+ back side of the audio data. Using a value of 0 for the
start parameter will allow trimming off the back side only.
- Both options can be specified using either an amount of time
- and an exact count of samples. The format for specifying
- lengths in time is hh:mm:ss.frac. A start value of 1:30.5
- will not start until 1 minute, thirty and 1/2 seconds into
- the audio data. The format for specifying sample counts is
- the number of samples with the letter ’s’ appended to it. A
- value of 8000s will wait until 8000 samples are read before
+ Both options can be specified using either an amount of time
+ and an exact count of samples. The format for specifying
+ lengths in time is hh:mm:ss.frac. A start value of 1:30.5
+ will not start until 1 minute, thirty and 1/2 seconds into
+ the audio data. The format for specifying sample counts is
+ the number of samples with the letter ’s’ appended to it. A
+ value of 8000s will wait until 8000 samples are read before
starting to process audio data.
vibro speed [ depth ]
- Add the world-famous Fender Vibro-Champ sound effect to a
- sound sample by using a sine wave as the volume knob. Speed
- gives the Hertz value of the wave. This must be under 30.
- Depth gives the amount the volume is cut into by the sine
+ Add the world-famous Fender Vibro-Champ sound effect to a
+ sound sample by using a sine wave as the volume knob. Speed
+ gives the Hertz value of the wave. This must be under 30.
+ Depth gives the amount the volume is cut into by the sine
wave, ranging 0.0 to 1.0 and defaulting to 0.5.
vol gain [ type [ limitergain ] ]
- The vol effect is much like the command line option -v. It
- allows you to adjust the volume of an input file and allows
- you to specify the adjustment in relation to amplitude,
- power, or dB. If type is not specified then it defaults to
+ The vol effect is much like the command line option -v. It
+ allows you to adjust the volume of an input file and allows
+ you to specify the adjustment in relation to amplitude,
+ power, or dB. If type is not specified then it defaults to
amplitude.
- When type is amplitude then a linear change of the amplitude
- is performed based on the gain. Therefore, a value of 1.0
- will keep the volume the same, 0.0 to < 1.0 will cause the
- volume to decrease and values of > 1.0 will cause the volume
- to increase. Beware of clipping audio data when the gain is
+ When type is amplitude then a linear change of the amplitude
+ is performed based on the gain. Therefore, a value of 1.0
+ will keep the volume the same, 0.0 to < 1.0 will cause the
+ volume to decrease and values of > 1.0 will cause the volume
+ to increase. Beware of clipping audio data when the gain is
greater then 1.0. A negative value performs the same adjust-
ment while also changing the phase.
- When type is power then a value of 1.0 also means no change
+ When type is power then a value of 1.0 also means no change
in volume.
- When type is dB the amplitude is changed logarithmically.
+ When type is dB the amplitude is changed logarithmically.
0.0 is constant while +6 doubles the amplitude.
- An optional limitergain value can be specified and should be
+ An optional limitergain value can be specified and should be
a value much less then 1.0 (ie 0.05 or 0.02) and is used only
- on peaks to prevent clipping. Not specifying this parameter
- will cause no limiter to be used. In verbose mode, this
- effect will display the percentage of audio data that needed
+ on peaks to prevent clipping. Not specifying this parameter
+ will cause no limiter to be used. In verbose mode, this
+ effect will display the percentage of audio data that needed
to be limited.
BUGS
- The syntax is horrific. Thats the breaks when trying to handle all
+ The syntax is horrific. Thats the breaks when trying to handle all
things from the command line.
- Please report any bugs found in this version of SoX to Chris Bagwell
+ Please report any bugs found in this version of SoX to Chris Bagwell
(cbagwell@users.sourceforge.net)
FILES
@@ -1115,9 +1129,9 @@
play(1), rec(1), soxexam(1)
NOTICES
- The version of SoX that accompanies this manual page is support by
+ The version of SoX that accompanies this manual page is support by
Chris Bagwell (cbagwell@users.sourceforge.net). Please refer any ques-
- tions regarding it to this address. You may obtain the latest version
+ tions regarding it to this address. You may obtain the latest version
at the the web site http://sox.sourceforge.net/
AUTHOR
--- a/src/raw.c
+++ b/src/raw.c
@@ -452,7 +452,7 @@
ft->file.pos = 0;
ft->file.count = st_read(ft, ft->file.buf+i, 1, ft->file.size-i);
- if (ft->file.count != ft->file.size-i)
+ if (ft->file.count != ft->file.size-i || ft->file.count == 0)
{ft->file.eof = 1;
}
--- a/src/wav.c
+++ b/src/wav.c
@@ -518,8 +518,17 @@
break;
case WAVE_FORMAT_IEEE_FLOAT:
- st_fail_errno(ft,ST_EHDR,"Sorry, this WAV file is in IEEE Float format.");
- return ST_EOF;
+ if (ft->info.encoding == -1 || ft->info.encoding == ST_ENCODING_FLOAT)
+ ft->info.encoding = ST_ENCODING_FLOAT;
+ else
+ st_report("User options overriding encoding read in .wav header");+
+ /* Needed by rawread() functions */
+ rc = st_rawstartread(ft);
+ if (rc)
+ return rc;
+
+ break;
case WAVE_FORMAT_ALAW:
if (ft->info.encoding == -1 || ft->info.encoding == ST_ENCODING_ALAW)
@@ -829,8 +838,8 @@
dwDataLength = len = findChunk(ft, "data");
/* findChunk() only returns if chunk was found */
- /* Data starts here */
- wav->dataStart = st_tell(ft);
+ /* Data starts here */
+ wav->dataStart = st_tell(ft);
switch (wav->formatTag)
{@@ -912,60 +921,85 @@
ft->comment = (char*)malloc(256);
/* Initialize comment to a NULL string */
ft->comment[0] = 0;
- while(!st_eof(ft)){- st_reads(ft,magic,4);
- if(strncmp(magic,"INFO",4) == 0){- /*Skip*/
- } else if(strncmp(magic,"ICRD",4) == 0){- st_readdw(ft,&len);
- len = (len + 1) & ~1;
+ while(!st_eof(ft))
+ {+ if (st_reads(ft,magic,4) == ST_EOF)
+ break;
+ if (strncmp(magic,"INFO",4) == 0)
+ {+ /*Skip*/
+ st_report("Chunk INFO");+ }
+ else
+ {+ if (st_readdw(ft,&len) == ST_EOF)
+ break;
+ if (strncmp(magic,"ICRD",4) == 0)
+ {+ int needs_return = 0;
+
+ st_report("Chunk ICRD");if (len > 254)
{- fprintf(stderr, "Possible buffer overflow hack attack (ICRD)!\n");
+ st_warn("Possible buffer overflow hack attack (ICRD)!\n");break;
}
st_reads(ft,text,len);
if (strlen(ft->comment) + strlen(text) < 254)
{+ if (strlen(ft->comment) != 0)
+ needs_return = 1;
+
strcat(ft->comment,text);
- strcat(ft->comment,"\n");
+
+ if (needs_return)
+ strcat(ft->comment,"\n");
}
- } else if(strncmp(magic,"ISFT",4) == 0){- st_readdw(ft,&len);
- len = (len + 1) & ~1;
+ if (strlen(text) < len)
+ st_seek(ft, len - strlen(text), SEEK_CUR);
+ }
+ else if (strncmp(magic,"ISFT",4) == 0)
+ {+ int needs_return = 0;
+
+ st_report("Chunk ISFT");if (len > 254)
{- fprintf(stderr, "Possible buffer overflow hack attack (ISFT)!\n");
+ st_warn("Possible buffer overflow hack attack (ISFT)!\n");break;
}
st_reads(ft,text,len);
if (strlen(ft->comment) + strlen(text) < 254)
{+ if (strlen(ft->comment) != 0)
+ needs_return = 1;
+
strcat(ft->comment,text);
- strcat(ft->comment,"\n");
+
+ if (needs_return)
+ strcat(ft->comment,"\n");
}
- } else if(strncmp(magic,"cue ",4) == 0){- st_readdw(ft,&len);
- len = (len + 1) & ~1;
+ if (strlen(text) < len)
+ st_seek(ft, len - strlen(text), SEEK_CUR);
+ }
+ else if (strncmp(magic,"cue ",4) == 0)
+ {+ st_report("Chunk cue ");st_seek(ft,len-4,SEEK_CUR);
st_readdw(ft,&dwLoopPos);
ft->loops[0].start = dwLoopPos;
- } else if(strncmp(magic,"note",4) == 0){- /*Skip*/
- st_readdw(ft,&len);
- len = (len + 1) & ~1;
- st_seek(ft,len-4,SEEK_CUR);
- } else if(strncmp(magic,"adtl",4) == 0){- /*Skip*/
- } else if(strncmp(magic,"ltxt",4) == 0){- st_seek(ft,4,SEEK_CUR);
+ }
+ else if (strncmp(magic,"ltxt",4) == 0)
+ {+ st_report("Chunk ltxt");st_readdw(ft,&dwLoopPos);
ft->loops[0].length = dwLoopPos - ft->loops[0].start;
- } else if(strncmp(magic,"labl",4) == 0){- /*Skip*/
- st_readdw(ft,&len);
- len = (len + 1) & ~1;
- st_seek(ft,len-4,SEEK_CUR);
+ }
+ else
+ {+ st_report("Attempting to seek beyond unsupported chunk '%c%c%c%c' of length %d bytes\n", magic[0], magic[1], magic[2], magic[3], len);+ st_seek(ft, len, SEEK_CUR);
+ }
}
}
}
@@ -1058,9 +1092,11 @@
st_warn("Premature EOF on .wav input file");break;
#endif
- default: /* assume PCM encoding */
+ default: /* assume PCM or float encoding */
+#if 0
if (len > wav->numSamples)
len = wav->numSamples;
+#endif
done = st_rawread(ft, buf, len);
/* If software thinks there are more samples but I/O */
@@ -1306,7 +1342,8 @@
break;
case ST_SIZE_DWORD:
wBitsPerSample = 32;
- if (ft->info.encoding != ST_ENCODING_SIGN2)
+ if (ft->info.encoding != ST_ENCODING_SIGN2 &&
+ ft->info.encoding != ST_ENCODING_FLOAT)
{ st_warn("Do not support %s with 32-bit data. Forcing to Signed.",st_encodings_str[(unsigned char)ft->info.encoding]);ft->info.encoding = ST_ENCODING_SIGN2;
@@ -1328,6 +1365,11 @@
case ST_ENCODING_UNSIGNED:
case ST_ENCODING_SIGN2:
wFormatTag = WAVE_FORMAT_PCM;
+ bytespersample = (wBitsPerSample + 7)/8;
+ wBlockAlign = wChannels * bytespersample;
+ break;
+ case ST_ENCODING_FLOAT:
+ wFormatTag = WAVE_FORMAT_IEEE_FLOAT;
bytespersample = (wBitsPerSample + 7)/8;
wBlockAlign = wChannels * bytespersample;
break;