FabledCurator/backend/app/services/gallery_service.py

"""Cursor-paginated gallery queries.

Cursor format: opaque base64-encoded "<iso8601_effective_date>:<image_id>".

Pagination key is (effective_date DESC, id DESC) where effective_date is
COALESCE(post.post_date, image_record.created_at) so the gallery surfaces
images by ORIGINAL publish date when known, falling back to FC's scan
date. Important for migrated content: ~57k IR images scanned in a single
week would otherwise all share the same created_at and pile up in one
month bucket. The effective_date spreads them across the years they
were originally published.

Decoding rejects malformed cursors with a ValueError; the API layer
translates that to HTTP 400.
"""

import base64
from dataclasses import dataclass
from datetime import datetime

from sqlalchemy import Select, and_, exists, func, or_, select
from sqlalchemy.ext.asyncio import AsyncSession

from ..models import Artist, ImageProvenance, ImageRecord, Post, Source, Tag
from ..models.tag import image_tag

CURSOR_SEPARATOR = "|"


def encode_cursor(effective_date: datetime, image_id: int) -> str:
    raw = f"{effective_date.isoformat()}{CURSOR_SEPARATOR}{image_id}"
    return base64.urlsafe_b64encode(raw.encode()).decode()


def decode_cursor(cursor: str) -> tuple[datetime, int]:
    try:
        raw = base64.urlsafe_b64decode(cursor.encode()).decode()
        ts_part, id_part = raw.split(CURSOR_SEPARATOR, 1)
        return datetime.fromisoformat(ts_part), int(id_part)
    except Exception as exc:
        raise ValueError(f"invalid cursor: {cursor!r}") from exc


def _effective_date_col():
    """SQL expression: COALESCE(post.post_date, image_record.created_at).

    Used as the canonical sort/group/filter key across the gallery so
    images backfilled with primary_post_id (e.g. via tag_apply phase 4)
    surface at their original publish date, not their FC import date.
    Images without a Post (or with Post.post_date NULL) fall back to
    image_record.created_at and still order coherently against
    post-attached ones.
    """
    return func.coalesce(Post.post_date, ImageRecord.created_at)


def _outer_join_primary_post(stmt: Select) -> Select:
    """LEFT JOIN Post on ImageRecord.primary_post_id so the COALESCE
    above sees Post.post_date when available. Images without a post
    survive the join as NULL on the Post side; COALESCE handles it."""
    return stmt.outerjoin(Post, Post.id == ImageRecord.primary_post_id)


@dataclass(frozen=True)
class GalleryImage:
    id: int
    path: str
    sha256: str
    mime: str
    width: int | None
    height: int | None
    created_at: datetime          # FC's row-insert time
    effective_date: datetime      # COALESCE(post.post_date, created_at)
    posted_at: datetime | None    # post.post_date if known, else None
    thumbnail_url: str
    artist: dict | None = None


@dataclass(frozen=True)
class GalleryPage:
    images: list[GalleryImage]
    next_cursor: str | None
    date_groups: list[tuple[int, int, list[int]]]  # (year, month, [image_id...])


@dataclass(frozen=True)
class TimelineBucket:
    year: int
    month: int
    count: int


def thumbnail_url(thumbnail_path: str | None, sha256_hex: str, mime: str) -> str:
    """Return the URL to fetch a thumbnail.

    Prefers the stored thumbnail_path verbatim — Quart serves /images/*
    1:1 from the volume (frontend.py:20-36), so the URL IS the disk
    path. Falls back to deriving from (sha256, mime) only when the
    record's thumbnail_path is NULL (thumbnailer hasn't run yet); that
    URL will 404 until backfill catches it, same as before the path
    was tracked.

    Pre-2026-05-30 this was derived only from (sha256, mime), which
    disagreed with the actual on-disk extension when the thumbnailer
    chose its format from transparency rather than MIME — every PNG
    source without alpha (extension was .jpg on disk) and every WebP
    source with alpha (extension was .png on disk) silently 404'd
    despite the thumbnail file existing.
    """
    if thumbnail_path:
        return thumbnail_path
    # Fallback for records with no thumbnail recorded yet — preserves
    # prior behavior (URL exists but 404s until backfill regenerates).
    ext = ".png" if mime in ("image/png", "image/gif") else ".jpg"
    bucket = sha256_hex[:3]
    return f"/images/thumbs/{bucket}/{sha256_hex}{ext}"


def _require_single_filter(tag_id, post_id, artist_id) -> None:
    if sum(x is not None for x in (tag_id, post_id, artist_id)) > 1:
        raise ValueError(
            "tag_id, post_id, artist_id are mutually exclusive"
        )


def _provenance_clause(post_id, artist_id):
    """Correlated EXISTS clause (NOT a join) so an image with multiple
    matching provenance rows is returned exactly once and the
    (effective_date DESC, id DESC) cursor ordering is unaffected."""
    if post_id is not None:
        return exists().where(
            ImageProvenance.image_record_id == ImageRecord.id,
            ImageProvenance.post_id == post_id,
        )
    if artist_id is not None:
        # Use Post.artist_id (alembic 0030 denormalized column) instead
        # of joining through ImageProvenance.source_id → Source.artist_id.
        # The denormalization is the always-present linkage; the source
        # path now drops NULL-source provenance rows (filesystem-imported
        # content) which would otherwise vanish from artist-filtered
        # gallery views.
        return exists().where(
            ImageProvenance.image_record_id == ImageRecord.id,
            ImageProvenance.post_id == Post.id,
            Post.artist_id == artist_id,
        )
    return None


async def _artists_for(session, image_ids: list[int]) -> dict[int, dict]:
    """Map image_id -> {"name","slug"} via the canonical
    image_record.artist_id (FC-2d-vii-c). Bounded by page size."""
    if not image_ids:
        return {}
    stmt = (
        select(ImageRecord.id, Artist.name, Artist.slug)
        .join(Artist, Artist.id == ImageRecord.artist_id)
        .where(ImageRecord.id.in_(image_ids))
    )
    return {
        img_id: {"name": name, "slug": slug}
        for img_id, name, slug in (await session.execute(stmt)).all()
    }


class GalleryService:
    def __init__(self, session: AsyncSession):
        self.session = session

    async def scroll(
        self,
        cursor: str | None,
        limit: int = 50,
        tag_id: int | None = None,
        post_id: int | None = None,
        artist_id: int | None = None,
    ) -> GalleryPage:
        if limit < 1 or limit > 200:
            raise ValueError("limit must be between 1 and 200")
        _require_single_filter(tag_id, post_id, artist_id)

        eff = _effective_date_col()
        stmt = select(ImageRecord, Post.post_date, eff.label("eff"))
        stmt = _outer_join_primary_post(stmt)
        if tag_id is not None:
            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
                image_tag.c.tag_id == tag_id
            )
        prov = _provenance_clause(post_id, artist_id)
        if prov is not None:
            stmt = stmt.where(prov)

        if cursor:
            cur_ts, cur_id = decode_cursor(cursor)
            stmt = stmt.where(
                or_(
                    eff < cur_ts,
                    and_(eff == cur_ts, ImageRecord.id < cur_id),
                )
            )

        stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc()).limit(limit + 1)
        rows = (await self.session.execute(stmt)).all()

        next_cursor = None
        if len(rows) > limit:
            last_record, _last_posted_at, last_eff = rows[limit - 1]
            next_cursor = encode_cursor(last_eff, last_record.id)
            rows = rows[:limit]

        artists = await _artists_for(
            self.session, [r[0].id for r in rows]
        )
        images = [
            GalleryImage(
                id=record.id,
                path=record.path,
                sha256=record.sha256,
                mime=record.mime,
                width=record.width,
                height=record.height,
                created_at=record.created_at,
                effective_date=eff_date,
                posted_at=posted_at,
                thumbnail_url=thumbnail_url(record.thumbnail_path, record.sha256, record.mime),
                artist=artists.get(record.id),
            )
            for record, posted_at, eff_date in rows
        ]
        return GalleryPage(
            images=images,
            next_cursor=next_cursor,
            date_groups=_group_by_year_month(images),
        )

    async def timeline(
        self,
        tag_id: int | None = None,
        post_id: int | None = None,
        artist_id: int | None = None,
    ) -> list[TimelineBucket]:
        eff = _effective_date_col()
        year_col = func.date_part("year", eff).label("yr")
        month_col = func.date_part("month", eff).label("mo")
        stmt = select(
            year_col, month_col, func.count(ImageRecord.id).label("cnt")
        )
        stmt = _outer_join_primary_post(stmt)
        _require_single_filter(tag_id, post_id, artist_id)
        if tag_id is not None:
            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
                image_tag.c.tag_id == tag_id
            )
        prov = _provenance_clause(post_id, artist_id)
        if prov is not None:
            stmt = stmt.where(prov)
        stmt = stmt.group_by(year_col, month_col).order_by(year_col.desc(), month_col.desc())
        rows = (await self.session.execute(stmt)).all()
        return [TimelineBucket(year=int(r.yr), month=int(r.mo), count=int(r.cnt)) for r in rows]

    async def jump_cursor(
        self, year: int, month: int, tag_id: int | None = None,
        post_id: int | None = None, artist_id: int | None = None,
    ) -> str | None:
        """Returns a cursor that, when passed to scroll(), positions at the
        first image of the given year-month (by effective_date, not
        created_at). None if the bucket is empty.
        """
        from sqlalchemy import extract

        eff = _effective_date_col()
        stmt = select(ImageRecord, eff.label("eff")).where(
            extract("year", eff) == year,
            extract("month", eff) == month,
        )
        stmt = _outer_join_primary_post(stmt)
        _require_single_filter(tag_id, post_id, artist_id)
        if tag_id is not None:
            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
                image_tag.c.tag_id == tag_id
            )
        prov = _provenance_clause(post_id, artist_id)
        if prov is not None:
            stmt = stmt.where(prov)
        stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc()).limit(1)
        first = (await self.session.execute(stmt)).first()
        if first is None:
            return None
        record, eff_date = first
        # Cursor is exclusive; we encode a cursor with id+1 so the row itself
        # is the first result in the next scroll().
        return encode_cursor(eff_date, record.id + 1)

    async def get_image_with_tags(self, image_id: int) -> dict | None:
        record = await self.session.get(ImageRecord, image_id)
        if record is None:
            return None
        tag_stmt = (
            select(Tag)
            .join(image_tag, image_tag.c.tag_id == Tag.id)
            .where(image_tag.c.image_record_id == image_id)
            .order_by(Tag.kind.asc(), Tag.name.asc())
        )
        tags = (await self.session.execute(tag_stmt)).scalars().all()
        # Fetch the canonical post.post_date for this image (if any) so
        # the modal can show "Posted on <date>" alongside import date.
        posted_at = None
        if record.primary_post_id is not None:
            posted_at = (await self.session.execute(
                select(Post.post_date).where(Post.id == record.primary_post_id)
            )).scalar_one_or_none()
        neighbors = await self._neighbors(record)
        # Direct artist FK — used by the modal's ProvenancePanel as a
        # fallback when ImageProvenance is empty (i.e., filesystem-
        # imported images without a post-track provenance row). The
        # source of truth for richer post-level data is still
        # ImageProvenance/Post; this is just the "we at least know who
        # made it" line.
        artist = None
        if record.artist_id is not None:
            artist = await self.session.get(Artist, record.artist_id)
        return {
            "id": record.id,
            "path": record.path,
            "sha256": record.sha256,
            "mime": record.mime,
            "width": record.width,
            "height": record.height,
            "size_bytes": record.size_bytes,
            "integrity_status": record.integrity_status,
            "created_at": record.created_at.isoformat(),
            "posted_at": posted_at.isoformat() if posted_at else None,
            "thumbnail_url": thumbnail_url(record.thumbnail_path, record.sha256, record.mime),
            "image_url": f"/images/{record.path.split('/images/', 1)[-1]}",
            "artist": (
                {"id": artist.id, "name": artist.name, "slug": artist.slug}
                if artist is not None else None
            ),
            "tags": [
                {
                    "id": t.id,
                    "name": t.name,
                    "kind": t.kind.value if hasattr(t.kind, "value") else t.kind,
                    "fandom_id": t.fandom_id,
                }
                for t in tags
            ],
            "neighbors": neighbors,
        }

    async def _neighbors(self, record: ImageRecord) -> dict:
        # Compute the boundary image's effective_date in Python (one query
        # below + the SELECT we already have on `record`) and use it for
        # the neighbor comparison. Cheaper than re-deriving in SQL via
        # correlated subquery.
        boundary_eff = record.created_at
        if record.primary_post_id is not None:
            post_date = (await self.session.execute(
                select(Post.post_date).where(Post.id == record.primary_post_id)
            )).scalar_one_or_none()
            if post_date is not None:
                boundary_eff = post_date

        eff = _effective_date_col()
        prev_stmt = _outer_join_primary_post(
            select(ImageRecord.id).where(
                or_(
                    eff > boundary_eff,
                    and_(
                        eff == boundary_eff,
                        ImageRecord.id > record.id,
                    ),
                )
            )
        ).order_by(eff.asc(), ImageRecord.id.asc()).limit(1)
        next_stmt = _outer_join_primary_post(
            select(ImageRecord.id).where(
                or_(
                    eff < boundary_eff,
                    and_(
                        eff == boundary_eff,
                        ImageRecord.id < record.id,
                    ),
                )
            )
        ).order_by(eff.desc(), ImageRecord.id.desc()).limit(1)
        prev_id = (await self.session.execute(prev_stmt)).scalar_one_or_none()
        next_id = (await self.session.execute(next_stmt)).scalar_one_or_none()
        return {"prev_id": prev_id, "next_id": next_id}


def _group_by_year_month(
    images: list[GalleryImage],
) -> list[tuple[int, int, list[int]]]:
    """Group by effective_date's year/month so migrated content surfaces
    in the publish-date buckets, not the FC-scan-date bucket."""
    groups: list[tuple[int, int, list[int]]] = []
    for img in images:
        y, m = img.effective_date.year, img.effective_date.month
        if groups and groups[-1][0] == y and groups[-1][1] == m:
            groups[-1][2].append(img.id)
        else:
            groups.append((y, m, [img.id]))
    return groups