hyungi_document_server/app/api/audio.py

"""오디오 전사(STT) 조회 API — /api/audio

AudioPlayer 가 줄 단위로 렌더하고 클릭 시 audio.currentTime 으로 점프한다.
"""

from typing import Annotated

from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession

from core.auth import get_current_user
from core.database import get_session
from models.audio_segment import AudioSegment
from models.document import Document
from models.user import User

router = APIRouter()


class AudioSegmentResponse(BaseModel):
    start: float
    end: float
    text: str

    model_config = {"from_attributes": True}


class AudioSegmentsResponse(BaseModel):
    document_id: int
    language: str | None
    duration: float | None
    segments: list[AudioSegmentResponse]


@router.get("/{doc_id}/segments", response_model=AudioSegmentsResponse)
async def get_audio_segments(
    doc_id: int,
    user: Annotated[User, Depends(get_current_user)],
    session: Annotated[AsyncSession, Depends(get_session)],
):
    """audio 문서의 전사 세그먼트 조회.

    category='audio' 가 아닌 문서는 404. 세그먼트가 아직 없는 경우 빈 배열 반환.
    language / duration 은 현재 ORM 에 별도 컬럼이 없어 None (필요 시 후속 확장).
    """
    doc = await session.get(Document, doc_id)
    if not doc or doc.deleted_at is not None:
        raise HTTPException(status_code=404, detail="문서를 찾을 수 없습니다")

    if getattr(doc, "category", None) != "audio":
        raise HTTPException(status_code=404, detail="오디오 문서가 아닙니다")

    result = await session.execute(
        select(AudioSegment)
        .where(AudioSegment.document_id == doc_id)
        .order_by(AudioSegment.start_s.asc())
    )
    rows = result.scalars().all()

    segments = [
        AudioSegmentResponse(start=r.start_s, end=r.end_s, text=r.text)
        for r in rows
    ]

    return AudioSegmentsResponse(
        document_id=doc_id,
        language=None,
        duration=None,
        segments=segments,
    )