siftlode/backend/app/routes/feed.py

from datetime import datetime, timezone

from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy import and_, func, or_, select
from sqlalchemy.orm import Session, aliased

from app.auth import current_user
from app.db import get_db
from app.models import Channel, ChannelTag, Tag, User, Video, VideoState

router = APIRouter(prefix="/api", tags=["feed"])

VALID_STATES = {"new", "watched", "saved", "hidden"}
HIDDEN_LIVE = ("live", "upcoming")


def _channel_url(channel_id: str, handle: str | None) -> str:
    if handle and handle.startswith("@"):
        return f"https://www.youtube.com/{handle}"
    return f"https://www.youtube.com/channel/{channel_id}"


def _serialize(row) -> dict:
    return {
        "id": row.id,
        "title": row.title,
        "channel_id": row.channel_id,
        "channel_title": row.channel_title,
        "channel_thumbnail": row.channel_thumbnail,
        "channel_url": _channel_url(row.channel_id, row.channel_handle),
        "published_at": row.published_at.isoformat() if row.published_at else None,
        "thumbnail_url": row.thumbnail_url,
        "duration_seconds": row.duration_seconds,
        "view_count": row.view_count,
        "is_short": row.is_short,
        "live_status": row.live_status,
        "status": row.status or "new",
        "watch_url": f"https://www.youtube.com/watch?v={row.id}",
    }


@router.get("/feed")
def get_feed(
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
    tags: list[int] = Query(default=[]),
    tag_mode: str = "or",
    channel_id: str | None = None,
    q: str | None = None,
    min_duration: int | None = None,
    max_duration: int | None = None,
    max_age_days: int | None = None,
    include_shorts: bool = False,
    include_live: bool = False,
    show: str = "unwatched",  # all | unwatched | watched | saved | hidden
    sort: str = "newest",
    seed: int = 0,
    limit: int = Query(default=60, le=200),
    offset: int = 0,
) -> dict:
    state = aliased(VideoState)
    status_expr = func.coalesce(state.status, "new").label("status")

    query = (
        select(
            Video.id,
            Video.title,
            Video.channel_id,
            Channel.title.label("channel_title"),
            Channel.thumbnail_url.label("channel_thumbnail"),
            Channel.handle.label("channel_handle"),
            Video.published_at,
            Video.thumbnail_url,
            Video.duration_seconds,
            Video.view_count,
            Video.is_short,
            Video.live_status,
            status_expr,
        )
        .join(Channel, Channel.id == Video.channel_id)
        .outerjoin(
            state, and_(state.video_id == Video.id, state.user_id == user.id)
        )
    )

    if not include_shorts:
        query = query.where(Video.is_short.is_(False))
    if not include_live:
        query = query.where(Video.live_status.notin_(HIDDEN_LIVE))
    if channel_id:
        query = query.where(Video.channel_id == channel_id)
    if min_duration is not None:
        query = query.where(Video.duration_seconds >= min_duration)
    if max_duration is not None:
        query = query.where(Video.duration_seconds <= max_duration)
    if max_age_days is not None:
        cutoff = datetime.now(timezone.utc).timestamp() - max_age_days * 86400
        query = query.where(
            Video.published_at >= datetime.fromtimestamp(cutoff, tz=timezone.utc)
        )
    if q:
        # Title (and channel name) only — searching descriptions produced noisy matches.
        like = f"%{q}%"
        query = query.where(or_(Video.title.ilike(like), Channel.title.ilike(like)))

    if tags:
        # Group selected tags by category: AND across categories (e.g. language AND
        # topic narrows results), OR within a category. The any/all toggle controls
        # whether multiple topic tags are OR'd (any) or AND'd (all).
        cat_rows = db.execute(
            select(Tag.id, Tag.category).where(Tag.id.in_(tags))
        ).all()
        by_category: dict[str, list[int]] = {}
        for tag_id, category in cat_rows:
            by_category.setdefault(category, []).append(tag_id)

        visible = or_(ChannelTag.user_id.is_(None), ChannelTag.user_id == user.id)
        for category, ids in by_category.items():
            if category == "topic" and tag_mode == "and" and len(ids) > 1:
                sub = (
                    select(ChannelTag.channel_id)
                    .where(ChannelTag.tag_id.in_(ids), visible)
                    .group_by(ChannelTag.channel_id)
                    .having(func.count(func.distinct(ChannelTag.tag_id)) == len(set(ids)))
                )
            else:
                sub = select(ChannelTag.channel_id).where(
                    ChannelTag.tag_id.in_(ids), visible
                )
            query = query.where(Video.channel_id.in_(sub))

    # Watch-state visibility.
    if show == "unwatched":
        query = query.where(status_expr.notin_(("watched", "hidden")))
    elif show == "watched":
        query = query.where(status_expr == "watched")
    elif show == "saved":
        query = query.where(status_expr == "saved")
    elif show == "hidden":
        query = query.where(status_expr == "hidden")
    else:  # all
        query = query.where(status_expr != "hidden")

    sorts = {
        "newest": Video.published_at.desc().nulls_last(),
        "oldest": Video.published_at.asc().nulls_last(),
        "views": Video.view_count.desc().nulls_last(),
        "duration_desc": Video.duration_seconds.desc().nulls_last(),
        "duration_asc": Video.duration_seconds.asc().nulls_last(),
        "shuffle": func.md5(func.concat(Video.id, str(seed))),
    }
    query = query.order_by(sorts.get(sort, sorts["newest"]))

    rows = db.execute(query.offset(offset).limit(limit + 1)).all()
    has_more = len(rows) > limit
    items = [_serialize(r) for r in rows[:limit]]
    return {"items": items, "has_more": has_more, "offset": offset, "limit": limit}


@router.post("/videos/{video_id}/state")
def set_video_state(
    video_id: str,
    payload: dict,
    user: User = Depends(current_user),
    db: Session = Depends(get_db),
) -> dict:
    status = payload.get("status")
    if status not in VALID_STATES:
        raise HTTPException(status_code=400, detail=f"status must be one of {VALID_STATES}")
    if db.get(Video, video_id) is None:
        raise HTTPException(status_code=404, detail="Unknown video")

    row = db.execute(
        select(VideoState).where(
            VideoState.user_id == user.id, VideoState.video_id == video_id
        )
    ).scalar_one_or_none()

    if status == "new":
        if row is not None:
            db.delete(row)
            db.commit()
        return {"video_id": video_id, "status": "new"}

    if row is None:
        row = VideoState(user_id=user.id, video_id=video_id)
        db.add(row)
    row.status = status
    row.watched_at = datetime.now(timezone.utc) if status == "watched" else row.watched_at
    db.commit()
    return {"video_id": video_id, "status": status}