video-shuoshan/backend/utils/tos_client.py

"""Volcano Engine TOS file upload utility using official TOS SDK."""

import hashlib
import uuid
import logging
from django.conf import settings

logger = logging.getLogger(__name__)


CONTENT_TYPE_MAP = {
    'jpg': 'image/jpeg', 'jpeg': 'image/jpeg', 'png': 'image/png',
    'webp': 'image/webp', 'gif': 'image/gif', 'bmp': 'image/bmp',
    'tiff': 'image/tiff',
    'mp4': 'video/mp4', 'mov': 'video/quicktime',
    'mp3': 'audio/mpeg', 'wav': 'audio/wav',
}

_client = None


def get_tos_client():
    import tos
    global _client
    if _client is None:
        endpoint = settings.TOS_ENDPOINT.replace('https://', '').replace('http://', '')
        _client = tos.TosClientV2(
            ak=settings.TOS_ACCESS_KEY,
            sk=settings.TOS_SECRET_KEY,
            endpoint=endpoint,
            region=settings.TOS_REGION,
        )
    return _client


def upload_file(file_obj, folder='uploads'):
    """Upload a file to TOS bucket with content-hash dedup, return its public URL.

    Uses MD5 hash of file content as the object key. If the same file
    has already been uploaded, the existing URL is returned without
    re-uploading, saving storage and bandwidth.
    """
    ext = file_obj.name.rsplit('.', 1)[-1].lower()
    content_type = CONTENT_TYPE_MAP.get(ext, 'application/octet-stream')

    client = get_tos_client()
    content = file_obj.read()

    # Use content hash as key for dedup
    content_hash = hashlib.sha256(content).hexdigest()
    key = f'{folder}/{content_hash}.{ext}'
    url = f'{settings.TOS_CDN_DOMAIN}/{key}'

    # Check if object already exists — skip upload if so
    try:
        client.head_object(bucket=settings.TOS_BUCKET, key=key)
        logger.info('TOS dedup hit: %s', key)
        return url
    except Exception as e:
        err_str = str(e).lower()
        if '404' not in err_str and 'not found' not in err_str and 'nosuchkey' not in err_str:
            logger.warning('TOS head_object unexpected error (proceeding with upload): %s', e)

    client.put_object(
        bucket=settings.TOS_BUCKET,
        key=key,
        content=content,
        content_type=content_type,
    )

    return url


def upload_from_file_path(file_path, folder='uploads', content_type=None):
    """Upload a local file to TOS by path (streaming, no full memory load).
    Returns the permanent CDN URL.
    """
    ext = file_path.rsplit('.', 1)[-1].lower() if '.' in file_path else 'bin'
    if not content_type:
        content_type = CONTENT_TYPE_MAP.get(ext, 'application/octet-stream')

    # Use content hash for dedup
    h = hashlib.sha256()
    with open(file_path, 'rb') as f:
        for chunk in iter(lambda: f.read(8192), b''):
            h.update(chunk)
    content_hash = h.hexdigest()
    key = f'{folder}/{content_hash}.{ext}'
    url = f'{settings.TOS_CDN_DOMAIN}/{key}'

    client = get_tos_client()
    try:
        client.head_object(bucket=settings.TOS_BUCKET, key=key)
        logger.info('TOS dedup hit: %s', key)
        return url
    except Exception as e:
        # Only proceed if object not found (404). Re-raise on auth/config errors.
        err_str = str(e).lower()
        if '404' not in err_str and 'not found' not in err_str and 'nosuchkey' not in err_str:
            logger.warning('TOS head_object unexpected error (proceeding with upload): %s', e)

    with open(file_path, 'rb') as f:
        client.put_object(
            bucket=settings.TOS_BUCKET,
            key=key,
            content=f,
            content_type=content_type,
        )
    return url


def upload_from_url(source_url, folder='results'):
    """Download a file from a URL and upload to TOS, return permanent CDN URL."""
    import requests as req

    resp = req.get(source_url, timeout=120, stream=True)
    resp.raise_for_status()
    content = resp.content

    content_type = resp.headers.get('Content-Type', 'video/mp4')
    ext = 'mp4'  # Seedance always returns mp4

    key = f'{folder}/{uuid.uuid4().hex}.{ext}'
    client = get_tos_client()
    client.put_object(
        bucket=settings.TOS_BUCKET,
        key=key,
        content=content,
        content_type=content_type,
    )

    return f'{settings.TOS_CDN_DOMAIN}/{key}'