o iO6@sdZddlZddlZddlZddlZddlZddlZddlZddl m Z m Z dddddddd d d d e d e e e e fd e de de de dede de e de e dedede fddZGdddZde de defddZd edefd!d"Zd#d$ZdS)%zAWS Transcribe utility functions and classes for WebSocket streaming. This module provides utilities for creating presigned URLs, building event messages, and handling AWS event stream protocol for real-time transcription services. N)DictOptionalpcmi>ThighF) media_encoding sample_ratenumber_of_channels$enable_partial_results_stabilizationpartial_results_stabilityvocabulary_namevocabulary_filter_nameshow_speaker_labelenable_channel_identificationregion credentials language_coderrr r r r r rrreturnc  Cs\|d} |d} |d}| r| stdt| | ||d}|j||||| | | |||d S)aXCreate a presigned URL for AWS Transcribe streaming. Args: region: AWS region for the service. credentials: Dictionary containing AWS credentials. Must include 'access_key' and 'secret_key', with optional 'session_token'. language_code: Language code for transcription (e.g., "en-US"). media_encoding: Audio encoding format. Defaults to "pcm". sample_rate: Audio sample rate in Hz. Defaults to 16000. number_of_channels: Number of audio channels. Defaults to 1. enable_partial_results_stabilization: Whether to enable partial result stabilization. partial_results_stability: Stability level for partial results. vocabulary_name: Custom vocabulary name to use. vocabulary_filter_name: Vocabulary filter name to apply. show_speaker_label: Whether to include speaker labels. enable_channel_identification: Whether to enable channel identification. Returns: Presigned WebSocket URL for AWS Transcribe streaming. Raises: ValueError: If required AWS credentials are missing. access_key secret_key session_tokenzAWS credentials are required)rrrr) rrrr r rrr r r )get ValueErrorAWSTranscribePresignedURLget_request_url)rrrrrr r r r r rrrrr url_generatorrN/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/aws/utils.pyget_presigned_urls( &  rc@sxeZdZdZ ddedededefddZ dd ededededededededededefddZdS)rzGenerator for AWS Transcribe presigned WebSocket URLs. Handles AWS Signature Version 4 signing process to create authenticated WebSocket URLs for streaming transcription requests. us-east-1rrrrcCs||_||_||_d|_d|_||_d|_d|_d|_d|_ d|_ d|_ d|_ d|_ d|_d|_d|_d|_d|_d|_d|_dS)a*Initialize the presigned URL generator. Args: access_key: AWS access key ID. secret_key: AWS secret access key. session_token: AWS session token for temporary credentials. region: AWS region for the service. Defaults to "us-east-1". GET transcribez/stream-transcription-websockethostzAWS4-HMAC-SHA256N)rrrmethodservicerendpointr#amz_date datestamp canonical_uricanonical_headerssigned_headers algorithmcredential_scopecanonical_querystring payload_hashcanonical_requeststring_to_sign signature request_url)selfrrrrrrr__init___s*  z"AWSTranscribePresignedURL.__init__r"rFrrrrr r rrr r r rc  Cs,d|jd|_d|jd|_tj} | d|_| d|_d|jd|_|jd|jd|j d |_ d |j |_ |j d |j d|j 7_ |j d |j7_ |j d 7_ |jrq|j dtjj|jdd7_ |j d|j7_ |r|j d7_ | r|j d7_ |r|j d|7_ |r|j d|7_ |dkr|j dt|7_ | r|j d| 7_ |r|j dt|7_ |r|j d7_ |r|j d|7_ |r|j d|7_ tdd|_|jd|jd|j d|jd|jd|j |_|jd|jd|j d} |j d|jd| dt|jd} td |jd|jdtj}t||jdtj}t||j dtj}t|d!tj}t|| dtj|_ |j d"|j 7_ |j|jd#|j |_!|j!S)$a6Generate a presigned WebSocket URL for AWS Transcribe. Args: sample_rate: Audio sample rate in Hz. language_code: Language code for transcription. media_encoding: Audio encoding format. vocabulary_name: Custom vocabulary name. vocabulary_filter_name: Vocabulary filter name. show_speaker_label: Whether to include speaker labels. enable_channel_identification: Whether to enable channel identification. number_of_channels: Number of audio channels. enable_partial_results_stabilization: Whether to enable partial result stabilization. partial_results_stability: Stability level for partial results. Returns: Presigned WebSocket URL with authentication parameters. zwss://transcribestreaming.z.amazonaws.com:8443ztranscribestreaming.z%Y%m%dT%H%M%SZz%Y%m%dzhost: z%2Fz%2Faws4_requestzX-Amz-Algorithm=z&X-Amz-Credential=z &X-Amz-Date=z&X-Amz-Expires=300z&X-Amz-Security-Token=r")safez&X-Amz-SignedHeaders=z#&enable-channel-identification=truez*&enable-partial-results-stabilization=truez&language-code=z&media-encoding=rz&number-of-channels=z&partial-results-stability=z &sample-rate=z&show-speaker-label=truez&vocabulary-filter-name=z&vocabulary-name=utf-8/z /aws4_requestAWS4s aws4_requestz&X-Amz-Signature=?)"rr&r#datetimeutcnowstrftimer'r(r*r%r-r,r.rrurllibparsequoter+strhashlibsha256encode hexdigestr/r$r)r0hmacnewrdigestr2r3)r4rrrr r rrr r r nowr-r1k_datek_region k_service k_signingrrrrsz     4z)AWSTranscribePresignedURL.get_request_urlN)r) r"rr"r"FFrFr") __name__ __module__ __qualname____doc__rBr5intboolrrrrrrXsX $    r header_name header_valuecCsx|d}tt|g}tdg}|d}tdt|}t}|||||||||||S)zBuild a header following AWS event stream format. Args: header_name: Name of the header. header_value: Value of the header. Returns: Encoded header as a bytearray following AWS event stream protocol. r8>H)rEbyteslenstructpack bytearrayextend)rUrVnamename_byte_length value_typevaluevalue_byte_length header_listrrr get_headerss        repayloadc Cstdd}tdd}tdd}t}||||||tdt|t|d}tdt|}td gd }||d d <||d d <tdt|d @}t} | || || || |t| } tdt| d @} | | t| S)aMBuild an event message for AWS Transcribe streaming. Creates a properly formatted AWS event stream message containing audio data for real-time transcription. Follows the AWS event stream protocol with prelude, headers, payload, and CRC checksums. Args: payload: Raw audio bytes to include in the event message. Returns: Complete event message as bytes, ready to send via WebSocket. Note: Implementation matches AWS sample: https://github.com/aws-samples/amazon-transcribe-streaming-python-websockets/blob/main/eventstream.py z :content-typezapplication/octet-streamz :event-type AudioEventz :message-typeevent>IrN) rer]r^r[r\rZbinasciicrc32rY) rfcontent_type_headerevent_type_headermessage_type_headerheaderstotal_byte_lengthheaders_byte_lengthprelude prelude_crcmessage_as_listmessage message_crcrrrbuild_event_messages,             r{cCsF|dd}td|\}}td|ddd}|dd|}|d|d}td|ddd}|t|d@ksCJd |t|ddd@ksTJd i}|r|d} |d d | d } |d | } td |d| d| d} |d| d| | d } | || <|d| | d}|sX|t|fS)aDecode an AWS event stream message. Parses an AWS event stream message to extract headers and payload, verifying CRC checksums for data integrity. Args: message: Raw event stream message bytes received from AWS. Returns: A tuple of (headers, payload) where: - headers: Dictionary of parsed headers - payload: Dictionary of parsed JSON payload Raises: AssertionError: If CRC checksum verification fails. Nrkz>IIri rrmzPrelude CRC check failedzMessage CRC check failedrr8rXrl)r[unpackrnrodecodejsonloads)ryrv total_lengthheaders_lengthrwrsrfrz headers_dictname_lenr_ra value_lenrbrrr decode_event<s& "   r)rRrnr<rCrGrr[ urllib.parser?typingrrrBrSrTrrr]rerYr{rrrrrsd      A 9