import boto3
import json
import time
from urllib.parse import urlparse, unquote_plus

transcribe = boto3.client('transcribe')
comprehend = boto3.client('comprehend')
bedrock = boto3.client('bedrock-runtime')
s3 = boto3.client('s3')

def lambda_handler(event, context):
    print("Event:", json.dumps(event))
    
    bucket = event['Records'][0]['s3']['bucket']['name']
    audio_key = unquote_plus(event['Records'][0]['s3']['object']['key'])
    job_name = f"transcription-{int(time.time())}"
    file_uri = f"s3://{bucket}/{audio_key}"

    # Bắt đầu phiên âm
    transcribe.start_transcription_job(
        TranscriptionJobName=job_name,
        Media={'MediaFileUri': file_uri},
        MediaFormat=audio_key.split('.')[-1],
        LanguageCode='en-US',
        OutputBucketName=bucket
    )

    # Đợi phiên âm hoàn tất
    while True:
        status = transcribe.get_transcription_job(TranscriptionJobName=job_name)
        if status['TranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']:
            break
        time.sleep(5)

    if status['TranscriptionJob']['TranscriptionJobStatus'] == 'FAILED':
        raise Exception("Transcription failed")

    transcript_uri = status['TranscriptionJob']['Transcript']['TranscriptFileUri']
    parsed = urlparse(transcript_uri)
    transcript_bucket = parsed.path.split('/')[1]
    transcript_key = '/'.join(parsed.path.split('/')[2:])
    
    # Lấy file phiên âm
    obj = s3.get_object(Bucket=transcript_bucket, Key=transcript_key)
    transcript_data = json.loads(obj['Body'].read())
    transcript_text = transcript_data['results']['transcripts'][0]['transcript']

    print("--> Transcribed Text:\n", transcript_text)

    # Phân tích cảm xúc với Comprehend
    sentiment = comprehend.detect_sentiment(Text=transcript_text[:5000], LanguageCode='en')

    # Tóm tắt bản ghi với Claude (Bedrock)
    summary = summarize_with_claude(transcript_text)

    return {
        "statusCode": 200,
        "body": {
            "summary": summary,
            "sentiment": sentiment,
            "transcription": transcript_text[:500],
        }
    }

BEDROCK_MODEL_ID = "eu.anthropic.claude-3-7-sonnet-20250219-v1:0"

def summarize_with_claude(text):
    body = {
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 200,
        "top_k": 250,
        "stop_sequences": [],
        "temperature": 1,
        "top_p": 0.999,
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": (
                            "Summarize this meeting or speech in clear bullet points, "
                            "highlight any action items or topics discussed:\n\n" + text[:4000]
                        )
                    }
                ]
            }
        ]
    }

    response = bedrock.invoke_model(
        modelId=BEDROCK_MODEL_ID,
        body=json.dumps(body),
        contentType="application/json",
        accept="application/json",
    )
    response_body = json.loads(response["body"].read())
    return response_body.get("content", "No summary generated.")

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObject",
        "s3:PutObject",
        "transcribe:StartTranscriptionJob",
        "transcribe:GetTranscriptionJob",
        "comprehend:DetectSentiment",
        "bedrock:InvokeModel"
      ],
      "Resource": "*"
    }
  ]
}