rfc-app/backend/tests/test_migration_029_collections.py

"""Migration 029 — the collection grain beneath projects (§22 three-tier S1).

Proves: a `collections` table exists with one default collection per project
(id='default', subfolder=repo root); the per-corpus fields (type, initial_state)
moved off `projects`; the 13 entry-corpus tables re-key (project_id,slug) ->
(collection_id,slug) with the composite PK/FK enforced; and project_members
generalises into memberships(scope_type, …) with the role enum collapsed.
Template: test_migration_028_project_scoped_keys.py.
"""
from __future__ import annotations

import sqlite3
import tempfile
from pathlib import Path

import pytest

from app import db


class _Cfg:
    def __init__(self, path):
        self.database_path = path


def _fresh_db():
    d = tempfile.mkdtemp()
    path = Path(d) / "t.db"
    db.run_migrations(_Cfg(str(path)))
    return db.connect(str(path))


def test_collections_table_exists_with_default_per_project():
    conn = _fresh_db()
    cols = {r["name"] for r in conn.execute("PRAGMA table_info(collections)")}
    assert {"id", "project_id", "type", "subfolder",
            "initial_state", "visibility", "name", "registry_sha"} <= cols
    # one default collection seeded for the bootstrap 'default' project (026)
    row = conn.execute(
        "SELECT id, project_id, subfolder FROM collections WHERE project_id='default'"
    ).fetchone()
    assert row is not None
    assert row["id"] == "default"
    assert row["subfolder"] == ""  # repo root


def test_per_corpus_fields_moved_off_projects():
    conn = _fresh_db()
    proj_cols = {r["name"] for r in conn.execute("PRAGMA table_info(projects)")}
    assert "type" not in proj_cols
    assert "initial_state" not in proj_cols
    # projects keeps the grouping-tier fields
    assert {"id", "name", "content_repo", "visibility"} <= proj_cols


def test_entry_tables_rekeyed_to_collection_id():
    conn = _fresh_db()
    for t in ("cached_rfcs", "cached_branches", "stars", "watches",
              "rfc_collaborators", "contribution_requests", "proposed_use_cases",
              "branch_visibility", "branch_contribute_grants", "pr_seen",
              "branch_chat_seen", "funder_consents", "rfc_invitations"):
        cols = {r["name"] for r in conn.execute(f"PRAGMA table_info({t})")}
        assert "collection_id" in cols, f"{t} missing collection_id"
        assert "project_id" not in cols, f"{t} still has project_id"


def test_cached_rfcs_pk_is_collection_slug():
    conn = _fresh_db()
    # a second collection under the default project
    conn.execute(
        "INSERT INTO collections (id, project_id, type, subfolder, initial_state, visibility, name) "
        "VALUES ('c2','default','document','specs','active','public','Specs')"
    )
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','A','active','default')")
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','B','active','c2')")
    n = conn.execute("SELECT COUNT(*) c FROM cached_rfcs WHERE slug='intro'").fetchone()["c"]
    assert n == 2
    with pytest.raises(sqlite3.IntegrityError):
        conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','dup','active','default')")


def test_cached_rfcs_collection_fk_enforced():
    conn = _fresh_db()
    conn.execute("PRAGMA foreign_keys=ON")
    with pytest.raises(sqlite3.IntegrityError):
        conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('x','X','active','nope')")


def test_collaborator_fk_is_composite_on_collection():
    conn = _fresh_db()
    conn.execute(
        "INSERT INTO collections (id, project_id, type, subfolder, initial_state, visibility, name) "
        "VALUES ('c2','default','document','specs','active','public','Specs')"
    )
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','A','active','c2')")
    conn.execute("INSERT INTO users (id, gitea_login, display_name, role) VALUES (1,'a','A','contributor')")
    conn.execute("PRAGMA foreign_keys=ON")
    conn.execute(
        "INSERT INTO rfc_collaborators (rfc_slug, user_id, role_in_rfc, collection_id) "
        "VALUES ('intro',1,'contributor','c2')"
    )
    with pytest.raises(sqlite3.IntegrityError):
        # same slug, a collection with no such entry — composite FK rejects
        conn.execute(
            "INSERT INTO rfc_collaborators (rfc_slug, user_id, role_in_rfc, collection_id) "
            "VALUES ('intro',1,'contributor','default')"
        )


def test_stars_unique_now_scoped_by_collection():
    conn = _fresh_db()
    conn.execute(
        "INSERT INTO collections (id, project_id, type, subfolder, initial_state, visibility, name) "
        "VALUES ('c2','default','document','specs','active','public','Specs')"
    )
    conn.execute("INSERT INTO users (id, gitea_login, display_name, role) VALUES (1,'a','A','contributor')")
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','A','active','default')")
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, collection_id) VALUES ('intro','B','active','c2')")
    conn.execute("INSERT INTO stars (user_id, rfc_slug, collection_id) VALUES (1,'intro','default')")
    conn.execute("INSERT INTO stars (user_id, rfc_slug, collection_id) VALUES (1,'intro','c2')")
    with pytest.raises(sqlite3.IntegrityError):
        conn.execute("INSERT INTO stars (user_id, rfc_slug, collection_id) VALUES (1,'intro','default')")


def test_memberships_table_replaces_project_members():
    conn = _fresh_db()
    cols = {r["name"] for r in conn.execute("PRAGMA table_info(memberships)")}
    assert {"scope_type", "scope_id", "user_id", "role", "granted_by", "granted_at"} <= cols
    # project_members is gone
    assert conn.execute(
        "SELECT name FROM sqlite_master WHERE type='table' AND name='project_members'"
    ).fetchone() is None
    conn.execute("INSERT INTO users (id, gitea_login, display_name, role) VALUES (9,'x','X','contributor')")
    conn.execute("INSERT INTO memberships (scope_type, scope_id, user_id, role) VALUES ('project','default',9,'owner')")
    # scope_type and role are CHECK-constrained
    with pytest.raises(sqlite3.IntegrityError):
        conn.execute("INSERT INTO memberships (scope_type, scope_id, user_id, role) VALUES ('bogus','default',9,'owner')")
    with pytest.raises(sqlite3.IntegrityError):
        conn.execute("INSERT INTO memberships (scope_type, scope_id, user_id, role) VALUES ('project','default',9,'viewer')")


# ── regression: §22.13 satellite re-stamp repair (the OHM-data deploy fault) ──
# Reproduces the shape that crashed the v0.46.0 deploy: the default→ohm re-stamp
# updated cached_rfcs but left cached_branches at the stale project_id='default',
# with (a) a stale row duplicating a freshly-stamped one, (b) a stale row with no
# fresh counterpart, and (c) a stale row whose RFC no longer exists. 029 must
# repair all three rather than hit NOT NULL / UNIQUE on the rebuild.

def _apply_through(path, ceiling):
    conn = sqlite3.connect(path, isolation_level=None)
    conn.row_factory = sqlite3.Row
    conn.execute("CREATE TABLE IF NOT EXISTS schema_migrations (version TEXT PRIMARY KEY, applied_at TEXT NOT NULL DEFAULT (datetime('now')))")
    done = {r["version"] for r in conn.execute("SELECT version FROM schema_migrations")}
    for p in sorted(db.MIGRATIONS_DIR.glob("*.sql")):
        v = p.stem
        if v in done or v > ceiling:
            continue
        sql = p.read_text()
        if "-- migrate:no-foreign-keys" in sql:
            conn.execute("PRAGMA foreign_keys = OFF")
            conn.executescript("BEGIN; " + sql + "; COMMIT;")
            conn.execute("PRAGMA foreign_keys = ON")
        else:
            conn.executescript("BEGIN; " + sql + "; COMMIT;")
        conn.execute("INSERT INTO schema_migrations (version) VALUES (?)", (v,))
    return conn


def test_029_repairs_stale_duplicate_and_orphan_satellite_rows():
    d = tempfile.mkdtemp()
    path = str(Path(d) / "t.db")
    conn = _apply_through(path, "028_project_scoped_keys")
    # simulate the §22.13 re-stamp having renamed the default project + its RFCs
    # to 'ohm', but NOT the satellite tables (the actual prod fault).
    conn.execute("UPDATE projects SET id='ohm' WHERE id='default'")
    conn.execute("INSERT INTO cached_rfcs (slug, title, state, project_id) VALUES ('human','Human','active','ohm')")
    conn.execute("INSERT INTO cached_branches (rfc_slug, branch_name, project_id) VALUES ('human','main','ohm')")      # fresh/correct
    conn.execute("INSERT INTO cached_branches (rfc_slug, branch_name, project_id) VALUES ('human','main','default')")  # stale DUP of the fresh one
    conn.execute("INSERT INTO cached_branches (rfc_slug, branch_name, project_id) VALUES ('human','edit-1','default')")# stale, unique -> re-stamp+keep
    conn.execute("INSERT INTO cached_branches (rfc_slug, branch_name, project_id) VALUES ('ghost','main','default')")  # no live RFC -> drop
    conn.close()

    # apply 029+ (the patched migration). Must NOT raise.
    db.run_migrations(_Cfg(path))
    conn = db.connect(path)

    rows = conn.execute(
        "SELECT rfc_slug, branch_name, collection_id FROM cached_branches"
    ).fetchall()
    got = {(r["rfc_slug"], r["branch_name"]) for r in rows}
    # every surviving row mapped to a collection (the single-project 'default' one)
    assert all(r["collection_id"] is not None for r in rows)
    assert {r["collection_id"] for r in rows} == {"default"}
    # the duplicate collapsed to exactly one human/main
    assert len([r for r in rows if (r["rfc_slug"], r["branch_name"]) == ("human", "main")]) == 1
    # the unique stale row survived (re-stamped)
    assert ("human", "edit-1") in got
    # the no-RFC stale row was dropped
    assert ("ghost", "main") not in got