ShH|rdZddlmZmZddlZddlmZddlmZmZm Z m Z ddl m Z ddl Z ddlZdZn#e$r Zd ZYdZ[ndZ[wwxYw dd lmZeZn#e$rZe jd kreZYdZ[ndZ[wwxYwgd ZGd dZGddZGddeZGddZGddeZdS)aA Class summary ============= .. autosummary:: DataSource StringDataSource ADSFactory ADSFactory.AudioDataSource ADSFactory.ADSDecorator ADSFactory.OverlapADS ADSFactory.LimiterADS ADSFactory.RecorderADS DataValidator AudioEnergyValidator )ABCMetaabstractmethodN)array) Rewindable from_fileBufferAudioSource PyAudioSource)DuplicateArgumentTF)str)r) DataSource DataValidatorStringDataSource ADSFactoryAudioEnergyValidatorc,eZdZdZeZedZdS)rz Base class for objects passed to :func:`auditok.core.StreamTokenizer.tokenize`. Subclasses should implement a :func:`DataSource.read` method. cdS)zp Read a piece of data read from this source. If no more data is available, return None. Nselfs R/var/www/html/movieo_spanner_bot/venv/lib/python3.11/site-packages/auditok/util.pyreadzDataSource.read6N)__name__ __module__ __qualname____doc__r __metaclass__rrrrrrr/s>M  ^   rrc,eZdZdZeZedZdS)rz Base class for a validator object used by :class:`.core.StreamTokenizer` to check if read data is valid. Subclasses should implement :func:`is_valid` method. cdS)z/ Check whether `data` is valid Nrrdatas ris_validzDataValidator.is_validFrrN)rrrrrr rr%rrrrr>s> M  ^   rrc$eZdZdZdZdZdZdS)ra? A class that represent a :class:`DataSource` as a string buffer. Each call to :func:`DataSource.read` returns on character and moves one step forward. If the end of the buffer is reached, :func:`read` returns None. :Parameters: `data` : a basestring object. cLd|_d|_||dSNr)_data_currentset_datar#s r__init__zStringDataSource.__init__Ys(   drc|jt|jkrdS|xjdz c_|j|jdz S)z Read one character from buffer. :Returns: Current character or None if end of buffer is reached Nr)r*lenr)rs rrzStringDataSource.read`sB =C OO + +4  z$-!+,,rcjt|tstd||_d|_dS)z Set a new data buffer. :Parameters: `data` : a basestring object New data buffer. z#data must an instance of basestringrN) isinstance basestring ValueErrorr)r*r#s rr+zStringDataSource.set_datans8$ ++ DBCC C  rN)rrrrr,rr+rrrrrLsK   - - -     rrceZdZdZedZedZGddeZGddeZ Gdd e Z Gd d e Z Gd d e Z dS)ra Factory class that makes it easy to create an :class:`ADSFactory.AudioDataSource` object that implements :class:`DataSource` and can therefore be passed to :func:`auditok.core.StreamTokenizer.tokenize`. Whether you read audio data from a file, the microphone or a memory buffer, this factory instantiates and returns the right :class:`ADSFactory.AudioDataSource` object. There are many other features you want your :class:`ADSFactory.AudioDataSource` object to have, such as: memorize all read audio data so that you can rewind and reuse it (especially useful when reading data from the microphone), read a fixed amount of data (also useful when reading from the microphone), read overlapping audio frames (often needed when dosing a spectral analysis of data). :func:`ADSFactory.ads` automatically creates and return object with the desired behavior according to the supplied keyword arguments. c |D](}|dvr"td|)d|vrd|vrtdd|vrd|vrtdd |vrd |vrtd d |vrd |vrtdd|vrd|vrtdd|vrd|vrtdd|vrd|vrtdd|vrd|vrtdd|vrd|vrtdd|vrd|vrtd d!|vrd"|vrtd#d$|vrd%|vrtd&d'|vrd(|vrtd)|ddp|dd|d<|ddp|dd|d<|d dp|d d|d <|d dp|d d|d <|ddp|dd|d<|ddp|dd|d<|ddp|dd|d<|ddp|dd|d<|d'd*}|s:|d(d*}t |t st d+||d(<d|vsd,|vr/|ddp|d,d|d<d|vsd|vr/|ddp|dd|d<d!|vsd"|vr/|d!dp|d"d|d!<d$|vsd%|vr1|d$dp|d%d|d$<dSdS)-N) block_durhop_dur block_sizehop_sizemax_timerecord audio_sourcefilename data_bufferframes_per_buffer sampling_rate sample_widthchannelssrswchasrcfnfpbdbmtrecbdhdbshszInvalid argument: {0}r5rKz6Either 'block_dur' or 'bd' must be specified, not bothr6rLz4Either 'hop_dur' or 'hd' must be specified, not bothr7rMz7Either 'block_size' or 'bs' must be specified, not bothr8rNz5Either 'hop_size' or 'hs' must be specified, not bothr9rIz5Either 'max_time' or 'mt' must be specified, not bothr;rEz;Either 'audio_source' or 'asrc' must be specified, not bothr<rFz5Either 'filename' or 'fn' must be specified, not bothr=rHz5Either 'filename' or 'db' must be specified, not bothr>fbbz?Either 'frames_per_buffer' or 'fpb' must be specified, not bothr?rBz:Either 'sampling_rate' or 'sr' must be specified, not bothr@rCz9Either 'sample_width' or 'sw' must be specified, not bothrArDz5Either 'channels' or 'ch' must be specified, not bothr:rJz4Either 'record' or 'rec' must be specified, not bothFz'record' must be a booleanrG)r2formatr popr0bool TypeError)kwargskr:s r_check_normalize_argsz ADSFactory._check_normalize_argss D DA888!!8!?!?!B!BCCC 8 & TV^^#$\]] ]   46>>#$Z[[ [ 6 ! !dfnn#$]^^ ^   DFNN#$[\\ \   DFNN#$[\\ \ V # #&(8(8#$abb b   DFNN#$[\\ \ F " "tv~~#$[\\ \ & ( (Uf__#$eff f f $ $#$`aa a V # ##$_`` `   DFNN#$[\\ \ v  %6//#$Z[[ [zz+t44N 48N8Nt zz)T22Lfjjt6L6Lt zz,55OD$9O9Ot zz*d33Mvzz$7M7Mt zz*d33Mvzz$7M7Mt ND99UVZZPT=U=Uvzz*d33Mvzz$7M7Mt zz-66P&**T4:P:Pt He,, >ZZu--Ffd++ > <===u  & ( (EVOO*0**5H$*O*O*jSYS]S]^ceiSjSjF& ' f $ $&,jj$&G&G&a6::VZ\`KaKaF? # V # #tv~~%+ZZ%E%E%_TXZ^I_I_F> "   46>>!'J!=!=!WDRVAWAWF:   $2>rc |}t||d}|d}|d}|d}|d}|d}|d}|d}|d } |||fd krt d n@|!|t d t |}n|t dd|i|}n tdi|}|6|tdt| |z}n&|$t| dz }t ||} |t | |} | rt | } |5|tdt| |z}|=|dks||krtd||krt| |} | S)a Create an return an :class:`ADSFactory.AudioDataSource`. The type and behavior of the object is the result of the supplied parameters. :Parameters: *No parameters* : read audio data from the available built-in microphone with the default parameters. The returned :class:`ADSFactory.AudioDataSource` encapsulate an :class:`io.PyAudioSource` object and hence it accepts the next four parameters are passed to use instead of their default values. `sampling_rate`, `sr` : *(int)* number of samples per second. Default = 16000. `sample_width`, `sw` : *(int)* number of bytes per sample (must be in (1, 2, 4)). Default = 2 `channels`, `ch` : *(int)* number of audio channels. Default = 1 (only this value is currently accepted) `frames_per_buffer`, `fpb` : *(int)* number of samples of PyAudio buffer. Default = 1024. `audio_source`, `asrc` : an `AudioSource` object read data from this audio source `filename`, `fn` : *(string)* build an `io.AudioSource` object using this file (currently only wave format is supported) `data_buffer`, `db` : *(string)* build an `io.BufferAudioSource` using data in `data_buffer`. If this keyword is used, `sampling_rate`, `sample_width` and `channels` are passed to `io.BufferAudioSource` constructor and used instead of default values. `max_time`, `mt` : *(float)* maximum time (in seconds) to read. Default behavior: read until there is no more data available. `record`, `rec` : *(bool)* save all read data in cache. Provide a navigable object which boasts a `rewind` method. Default = False. `block_dur`, `bd` : *(float)* processing block duration in seconds. This represents the quantity of audio data to return each time the :func:`read` method is invoked. If `block_dur` is 0.025 (i.e. 25 ms) and the sampling rate is 8000 and the sample width is 2 bytes, :func:`read` returns a buffer of 0.025 * 8000 * 2 = 400 bytes at most. This parameter will be looked for (and used if available) before `block_size`. If neither parameter is given, `block_dur` will be set to 0.01 second (i.e. 10 ms) `hop_dur`, `hd` : *(float)* quantity of data to skip from current processing window. if `hop_dur` is supplied then there will be an overlap of `block_dur` - `hop_dur` between two adjacent blocks. This parameter will be looked for (and used if available) before `hop_size`. If neither parameter is given, `hop_dur` will be set to `block_dur` which means that there will be no overlap between two consecutively read blocks. `block_size`, `bs` : *(int)* number of samples to read each time the `read` method is called. Default: a block size that represents a window of 10ms, so for a sampling rate of 16000, the default `block_size` is 160 samples, for a rate of 44100, `block_size` = 441 samples, etc. `hop_size`, `hs` : *(int)* determines the number of overlapping samples between two adjacent read windows. For a `hop_size` of value *N*, the overlap is `block_size` - *N*. Default : `hop_size` = `block_size`, means that there is no overlap. :Returns: An AudioDataSource object that has the desired features. :Exampels: 1. **Create an AudioDataSource that reads data from the microphone (requires Pyaudio) with default audio parameters:** .. code:: python from auditok import ADSFactory ads = ADSFactory.ads() ads.get_sampling_rate() 16000 ads.get_sample_width() 2 ads.get_channels() 1 2. **Create an AudioDataSource that reads data from the microphone with a sampling rate of 48KHz:** .. code:: python from auditok import ADSFactory ads = ADSFactory.ads(sr=48000) ads.get_sampling_rate() 48000 3. **Create an AudioDataSource that reads data from a wave file:** .. code:: python import auditok from auditok import ADSFactory ads = ADSFactory.ads(fn=auditok.dataset.was_der_mensch_saet_mono_44100_lead_trail_silence) ads.get_sampling_rate() 44100 ads.get_sample_width() 2 ads.get_channels() 1 4. **Define size of read blocks as 20 ms** .. code:: python import auditok from auditok import ADSFactory ''' we know samling rate for previous file is 44100 samples/second so 10 ms are equivalent to 441 samples and 20 ms to 882 ''' block_size = 882 ads = ADSFactory.ads(bs = 882, fn=auditok.dataset.was_der_mensch_saet_mono_44100_lead_trail_silence) ads.open() # read one block data = ads.read() ads.close() len(data) 1764 assert len(data) == ads.get_sample_width() * block_size 5. **Define block size as a duration (use block_dur or bd):** .. code:: python import auditok from auditok import ADSFactory dur = 0.25 # second ads = ADSFactory.ads(bd = dur, fn=auditok.dataset.was_der_mensch_saet_mono_44100_lead_trail_silence) ''' we know samling rate for previous file is 44100 samples/second for a block duration of 250 ms, block size should be 0.25 * 44100 = 11025 ''' ads.get_block_size() 11025 assert ads.get_block_size() == int(0.25 * 44100) ads.open() # read one block data = ads.read() ads.close() len(data) 22050 assert len(data) == ads.get_sample_width() * ads.get_block_size() 6. **Read overlapping blocks (one of hope_size, hs, hop_dur or hd > 0):** For better readability we'd better use :class:`auditok.io.BufferAudioSource` with a string buffer: .. code:: python import auditok from auditok import ADSFactory ''' we supply a data beffer instead of a file (keyword 'bata_buffer' or 'db') sr : sampling rate = 16 samples/sec sw : sample width = 1 byte ch : channels = 1 ''' buffer = "abcdefghijklmnop" # 16 bytes = 1 second of data bd = 0.250 # block duration = 250 ms = 4 bytes hd = 0.125 # hop duration = 125 ms = 2 bytes ads = ADSFactory.ads(db = "abcdefghijklmnop", bd = bd, hd = hd, sr = 16, sw = 1, ch = 1) ads.open() ads.read() 'abcd' ads.read() 'cdef' ads.read() 'efgh' ads.read() 'ghij' data = ads.read() assert data == 'ijkl' 7. **Limit amount of read data (use max_time or mt):** .. code:: python ''' We know audio file is larger than 2.25 seconds We want to read up to 2.25 seconds of audio data ''' ads = ADSFactory.ads(mt = 2.25, fn=auditok.dataset.was_der_mensch_saet_mono_44100_lead_trail_silence) ads.open() data = [] while True: d = ads.read() if d is None: break data.append(d) ads.close() data = b''.join(data) assert len(data) == int(ads.get_sampling_rate() * 2.25 * ads.get_sample_width() * ads.get_channels()) rKrLrMrNrIrErFrHrJN)NNzYou should provide one of 'audio_source', 'filename' or 'data_buffer' keyword parameters. 'audio_source' will be usedzqYou should provide one of 'filename' or 'data_buffer' keyword parameters. 'filename' will be usedr=z=Either 'block_dur' or 'block_size' can be specified, not bothdr;r7)adsr9)rZz9Either 'hop_dur' or 'hop_size' can be specified, not bothrz&hop_size must be > 0 and <= block_size)rZr8r)copyrrVrQWarningrr r r intget_sampling_rateAudioDataSource LimiterADS RecorderADSr2 OverlapADS) rTr5r6r7r8r9r;r<r=r:rZs rrZzADSFactory.adssb ((000JJt$$ **T""ZZ%% ::d##::d##zz&)) ::d##jj&& E""  #+&,66BCCC7  !&>???$X..LL $,QQ;Q&QQLL)22622L  %'(ghhh !?!?!A!AI!MNN  \;;==CDDJ((lz(ZZ  ''C('CCC  2((S(11C  #'(cddd|==??'IJJ  1}}J!6!6 !IJJJ*$$ ++h+GG rcfeZdZdZdZdZdZdZdZdZ dZ d Z d Z d Z d Zd ZdZdZdS)ADSFactory.AudioDataSourcez Base class for AudioDataSource objects. It inherits from DataSource and encapsulates an AudioSource object. c"||_||_dSNrY)rr;r7s rr,z#ADSFactory.AudioDataSource.__init__s ,D (DOOOrc|jSrfr7rs rget_block_sizez)ADSFactory.AudioDataSource.get_block_size s ? "rc||_dSrfrh)rsizes rset_block_sizez)ADSFactory.AudioDataSource.set_block_sizes "DOOOrc|jSrfr;rs rget_audio_sourcez+ADSFactory.AudioDataSource.get_audio_sources $ $rc||_dSrfrnrr;s rset_audio_sourcez+ADSFactory.AudioDataSource.set_audio_sources ,D   rc8|jdSrf)r;openrs rrtzADSFactory.AudioDataSource.opens   " " $ $ $ $ $rc8|jdSrf)r;closers rrvz ADSFactory.AudioDataSource.closes   # # % % % % %rc4|jSrf)r;is_openrs rrxz"ADSFactory.AudioDataSource.is_opens$,,.. .rc4|jSrf)r;r^rs rr^z,ADSFactory.AudioDataSource.get_sampling_rate"s$6688 8rc4|jSrf)r;get_sample_widthrs rr{z+ADSFactory.AudioDataSource.get_sample_width%s$5577 7rc4|jSrf)r; get_channelsrs rr}z'ADSFactory.AudioDataSource.get_channels(s$1133 3rct|jtr|jdSt d)NzAudio source is not rewindable)r0r;rrewind Exceptionrs rrz!ADSFactory.AudioDataSource.rewind,sB$+Z88 B!((***** @AAArc6t|jtSrf)r0r;rrs r is_rewindablez(ADSFactory.AudioDataSource.is_rewindable4sd/<< ._get_block_sizets ..r)rrr,rir2r8rr)rrZr8rs` rr,zADSFactory.OverlapADS.__init__is  # , ,T3 7 7 71}}4+>+>+@+@ @ @ "<===$DM&*&9&9&;&;D # LLNNN / / / / / / /rc|j}|dSt||jkr||jd|_|j|j|j|_|Srf)rZrr._hop_size_bytes_cacherlr8_read_next_blocksrblocks r_read_first_blockz'ADSFactory.OverlapADS._read_first_blockxsoHMMOOE}t5zzD000#D$8$9$9:  H # #DM 2 2 2.DILrc|j}|dS|j|z}t||jkr||jd|_nd|_|Srf)rZrrr._block_size_bytesrrs rrz'ADSFactory.OverlapADS._read_next_blockssbHMMOOE}tK%'E5zzT333#D$8$9$9: " LrcdSrfrrs rrzADSFactory.OverlapADS.read Drc\d|_|j|j|j|z|z|_||z|z|_ |j |_ dSrf) rrZrlrr8r{r}rrirrrrs rrzADSFactory.OverlapADS._reinitsDK H # #D$; < < <#'=#4466$7#0022$3D &*%8%8%:%:#4466&7#0022&3D ".DIIIrN) rrrrr,rrrrrrrrbrdsi   / / /   "        / / / / /rrbc$eZdZdZdZdZdZdS)ADSFactory.LimiterADSz A class for AudioDataSource objects that can read a fixed amount of data. This can be useful when reading data from the microphone or from large audio files. c|tj||||_|dSrf)rrr,r9r)rrZr9s rr,zADSFactory.LimiterADS.__init__s3  # , ,T3 7 7 7$DM LLNNNNNrc|j|jkrdS|j}|dS|xjt |z c_|j|jkr||Srf)_total_read_bytes_max_read_bytesrZrr.rvrs rrzADSFactory.LimiterADS.readsn%$*>>>tHMMOOE}t  " "c%jj 0 " "%$*>>> Lrct|j|z|z|z|_d|_dSr()r]r9r^r{r}rrrs rrzADSFactory.LimiterADS._reinits]#&t}8N8N8P8P'P#Q#Q"&"7"7"9"9$:"&"3"3"5"5$6D &'D " " "rN)rrrrr,rrrrrr`rsK         ' ' ' ' 'rr`cBeZdZdZdZdZdZdZdZdZ dZ d Z d S) ADSFactory.RecorderADSz A class for AudioDataSource objects that can record all audio data they read, with a rewind facility. cntj|||dSrf)rrr,rrs rr,zADSFactory.RecorderADS.__init__s,  # , ,T3 7 7 7 LLNNNNNrcdSrfrrs rrzADSFactory.RecorderADS.readrrcp|j}||j||Srf)rZrrappendrs r _read_and_recz$ADSFactory.RecorderADS._read_and_recs2HMMOOE  ""5)))Lrc4|jSrf)rZrrs r _read_simplez#ADSFactory.RecorderADS._read_simples8==?? "rc|jr||j}t||||}|||g|_d|_|j |_ dS|j | s|dSdS)NF)_record _concatenaterr r^r{r}rrrtrrrZrrx)rdbufferasources rrzADSFactory.RecorderADS.rewinds| ++DK88+GT5K5K5M5M-1-B-B-D-D-1->->-@-@BB %%g...   $  - !!!||~~ IIKKKKK  rcdSNTrrs rrz$ADSFactory.RecorderADS.is_rewindables4rc:d|_g|_|j|_dSr)rrrrrs rrzADSFactory.RecorderADS._reinitsDLDK*DIIIrcx d|S#t$rd|cYSwxYw)Nr)joinrSr#s rrz#ADSFactory.RecorderADS._concatenatesJ %xx~~% % % %wwt}}$$$ %s 99N) rrrrr,rrrrrrrrrrrars             # # #   ,    + + +  % % % % %rraN) rrrr staticmethodrVrZrr_rrbr`rarrrrrsG$MXMX\MXjVV\Vr7;7;7;7;7;*7;7;7;t%%%%%%%%PA/A/A/A/A/\A/A/A/J'''''\'''DB%B%B%B%B%lB%B%B%B%B%rrceZdZdZer7ejejejdZ e dZ e dZ e dZ n'ddddZ e d Z e d Z e d Z dd ZdZdZdZdS)ra The most basic auditok audio frame validator. This validator computes the log energy of an input audio frame and return True if the result is >= a given threshold, False otherwise. :Parameters: `sample_width` : *(int)* Number of bytes of one audio sample. This is used to convert data from `basestring` or `Bytes` to an array of floats. `energy_threshold` : *(float)* A threshold used to check whether an input data buffer is valid. )rctjtj|tj|tjS)N)dtype)numpyr frombufferr_formatsfloat64signalr@s r_convertzAudioEnergyValidator._convert&sA;u/>R>[\h>ijjjrwrAAA Arcfttj||t|z Srf)floatrdotr.)rs r_signal_energyz#AudioEnergyValidator._signal_energy*s'662233c&kkA Arctt|}|dkrdSdtj|zSNri8g$@)rrrlog10renergys r_signal_log_energyz'AudioEnergyValidator._signal_log_energy.s8)88@@F{{tV,,, ,rbhic^tdttj||S)Nd)rrrrs rrzAudioEnergyValidator._convert:s&e$8$A,$OQWXXYY YrcDd}|D] }|||zz } |t|z S)Ng)r.)rras rrz#AudioEnergyValidator._signal_energy>s6F  !a%CKK' 'rctt|}|dkrdSdtj|zSr)rrmathrrs rrz'AudioEnergyValidator._signal_log_energyEs8)88@@F{{tF+++ +r-c"||_||_dSrf)r@_energy_threshold)rr@energy_thresholds rr,zAudioEnergyValidator.__init__Ms(!1rct||j}t||jkS)a Check if data is valid. Audio data will be converted into an array (of signed values) of which the log energy is computed. Log energy is computed as follows: .. code:: python arr = AudioEnergyValidator._convert(signal, sample_width) energy = float(numpy.dot(arr, arr)) / len(arr) log_energy = 10. * numpy.log10(energy) :Parameters: `data` : either a *string* or a *Bytes* buffer `data` is converted into a numerical array using the `sample_width` given in the constructor. :Retruns: True if `log_energy` >= `energy_threshold`, False otherwise. )rrr@rr)rr$rs rr%zAudioEnergyValidator.is_validRs80&..tT5FGG#66v>>$BXXXrc|jSrfrrs rget_energy_thresholdz)AudioEnergyValidator.get_energy_thresholdms %%rc||_dSrfr)r thresholds rset_energy_thresholdz)AudioEnergyValidator.set_energy_thresholdps!*rN)r)rrrr _WITH_NUMPYrint8int16int32rrrrrr,r%rrrrrrrs>"(,zu{u{CC  A A  A  B B  B  - -  - -,,  Z Z  Z  ( (  (  , ,  ,2222 YYY6&&&+++++rr)rabcrrrriorrr r exceptionsr sysrr ImportErrorebuiltinsr r1 version_info__all__rrrrrrrrrs((''''''' GGGGGGGGGGGG)))))) LLLKKKKKKKKJJ 6!!  d c c                  /////z///fN %N %N %N %N %N %N %N %ba+a+a+a+a+=a+a+a+a+a+s*3A?AAA- A((A-