"""Fold the undated shell posts a misfiled attachment created into the real post.

#4435. A non-image file (an archive, a pdf) downloaded for one of an artist's
Discord channels was filed under the artist's FIRST Discord source: the
attachment path looked the source up by (artist, platform), which takes the
lowest id. That created an undated, url-less post there holding only the
attachment, and the message's real post record then created the dated post
under the right source. The importer now uses the source it was downloading
for; this repairs the pairs it left.

A shell is folded only when all of this holds:

* it has no date and no url, and nothing synthesized it;
* another post of the same artist, platform and external id HAS a date;
* no image is linked to the shell (it held an attachment and nothing else).

Its attachments move to the dated post, dropping any the dated post already
has (same sha256, which the per-post unique forbids twice), and the shell is
deleted. A shell with no dated twin is left alone: which channel it belongs to
is not recorded anywhere but the file name. The downgrade does nothing.

Revision ID: 0114
Revises: 0113
Create Date: 2026-09-25

"""
import sqlalchemy as sa
from alembic import op

revision = "0114"
down_revision = "0113"
branch_labels = None
depends_on = None

_PAIRS = """
    SELECT DISTINCT ON (shell.id) shell.id AS shell_id, real.id AS real_id
    FROM post shell
    JOIN source ss ON ss.id = shell.source_id
    JOIN post real
      ON real.artist_id = shell.artist_id
     AND real.external_post_id = shell.external_post_id
     AND real.id <> shell.id
     AND real.post_date IS NOT NULL
    JOIN source rs ON rs.id = real.source_id AND rs.platform = ss.platform
    WHERE shell.post_date IS NULL
      AND shell.post_url IS NULL
      AND shell.synthesized_by IS NULL
      AND NOT EXISTS (SELECT 1 FROM image_provenance ip WHERE ip.post_id = shell.id)
    ORDER BY shell.id, real.id
"""


def fold_misfiled_attachment_posts(conn) -> int:
    """The data step, on a plain connection, so a test can run it directly.
    Returns how many shells were folded."""
    pairs = conn.execute(sa.text(_PAIRS)).all()
    for shell_id, real_id in pairs:
        conn.execute(sa.text("""
            DELETE FROM post_attachment pa
            WHERE pa.post_id = :shell
              AND EXISTS (
                SELECT 1 FROM post_attachment keep
                WHERE keep.post_id = :real AND keep.sha256 = pa.sha256
              )
        """), {"shell": shell_id, "real": real_id})
        conn.execute(
            sa.text("UPDATE post_attachment SET post_id = :real WHERE post_id = :shell"),
            {"shell": shell_id, "real": real_id},
        )
        conn.execute(sa.text("DELETE FROM post WHERE id = :shell"), {"shell": shell_id})
    return len(pairs)


def upgrade() -> None:
    fold_misfiled_attachment_posts(op.get_bind())


def downgrade() -> None:
    pass