Created
July 30, 2025 10:24
-
-
Save fuyi/f8e1801a1fd3d77adbd59c1408e96157 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import boto3 | |
| import struct | |
| def validate_wav_header_from_s3(bucket_name, object_key): | |
| """ | |
| Validate WAV file by reading only the header (first 44 bytes) | |
| """ | |
| session = boto3.Session(profile_name='product-admin') # use the underlying aws credential | |
| s3 = session.client('s3') | |
| try: | |
| # Download only the first 44 bytes (standard WAV header) | |
| response = s3.get_object( | |
| Bucket=bucket_name, | |
| Key=object_key, | |
| Range='bytes=0-43' # First 44 bytes | |
| ) | |
| header_data = response['Body'].read() | |
| # Validate WAV signature | |
| if len(header_data) < 44: | |
| return False, "File too small to be WAV" | |
| # Check RIFF signature | |
| riff_header = header_data[:4] | |
| if riff_header != b'RIFF': | |
| return False, "Not a RIFF file" | |
| # Check WAVE signature | |
| wave_header = header_data[8:12] | |
| if wave_header != b'WAVE': | |
| return False, "Not a WAVE file" | |
| # Check fmt chunk | |
| fmt_header = header_data[12:16] | |
| if fmt_header != b'fmt ': | |
| return False, "Invalid format chunk" | |
| # Extract audio parameters | |
| audio_format = struct.unpack('<H', header_data[20:22])[0] | |
| channels = struct.unpack('<H', header_data[22:24])[0] | |
| sample_rate = struct.unpack('<L', header_data[24:28])[0] | |
| return True, { | |
| 'format': audio_format, | |
| 'channels': channels, | |
| 'sample_rate': sample_rate, | |
| 'validated': 'header_only' | |
| } | |
| except Exception as e: | |
| return False, f"Validation error: {str(e)}" | |
| # Usage | |
| bucket_name = "astrid01-prod-astrid-speech-sessions-raw" | |
| object_key = "by-tenant-name/guldbrev/dstny-downloads/2e5e3f79-9027-4d35-add1-b7806392dd2c/80073065.wav" | |
| is_valid, details = validate_wav_header_from_s3(bucket_name, object_key) | |
| print(f"Valid WAV: {is_valid}, Details: {details}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment