paliad/internal/db/migrations/152_dedupe_identical_sequencing_rule_clones.up.sql

-- 152_dedupe_identical_sequencing_rule_clones — t-paliad-321 / m/paliad#144 follow-up
--
-- Purpose: mig 151 archived 5 of 6 duplicate procedural_events for
-- "Mängelbeseitigung / Zahlung" and reparented their sequencing_rules
-- onto the canonical PE. The 6 sequencing_rules themselves remained
-- active. Because every one of them is a byte-for-byte clone (same
-- proceeding_type_id=NULL, rule_code=NULL, duration 14d, primary_party=NULL,
-- everything else NULL, lifecycle_state='published') and only sequence_order
-- differs, the admin shows six indistinguishable rows for one legal
-- concept. This mig archives 5 of the 6 keeping the lexicographically
-- lowest UUID as canonical.
--
-- Scope verified live before write (Supabase MCP, 2026-05-26):
--   * Exactly 1 clone-group surfaces by the full-signature query
--     below: 6 "Mängelbeseitigung / Zahlung" sequencing_rules with
--     all-NULL discriminators and (duration_value=14, duration_unit='days').
--   * 0 paliad.deadlines reference the 5 to-be-archived rows
--     (verified via deadlines.sequencing_rule_id JOIN; the column
--     formerly named deadlines.rule_id was dropped in mig 140 / B.4).
--   * Other name-groups in the live corpus — "Antrag auf
--     Patentänderung"×4, "Beginn des Hauptsacheverfahrens"×2,
--     "Berufungsbegründung-R.220.1"×2, "Berufungsschrift-R.220.1"×2 —
--     do NOT collapse under this signature because their
--     proceeding_type_id / rule_code / duration / primary_party
--     differ. They are legitimately distinct rules per proceeding;
--     this mig leaves them alone.
--
-- Hard constraints honoured (mirrors mig 151):
--   * No deletions. Archived rows flip to is_active=false +
--     lifecycle_state='archived'. Rows stay in the table for audit.
--   * Reparent paliad.deadlines.sequencing_rule_id duplicate →
--     canonical BEFORE archiving, so no live deadline keeps pointing
--     at an archived sequencing_rule. (deadlines.rule_id column
--     dropped in mig 140; the back-link lives on sequencing_rule_id
--     now — same UUID semantics.)
--   * Snapshot the affected rows into paliad.sequencing_rules_pre_152
--     in the same TX, mirroring precedent (migs 091/093/095/098/140/151).
--   * set_config('paliad.audit_reason') is defensively called even
--     though no audit trigger fires on sequencing_rules today (mig 151
--     §comments documented this). Future audit trigger would inherit
--     the reason automatically.
--
-- Generic-shape rationale: the audit query below uses the FULL
-- signature paliadin specified — procedural_event_id, proceeding_type_id,
-- rule_code, duration_value, duration_unit, primary_party, condition_expr,
-- trigger_event_id, alt_*, anchor_alt, combine_op, parent_id, is_spawn,
-- spawn_*. A NOTICE surfaces every group BEFORE the archive step so an
-- operator running the deploy logs sees what's about to be touched.
-- If new groups appear after future seeds, this mig is safe to re-run
-- conceptually (it would archive any new clones) but only fires once
-- via the applied_migrations protocol.

-- ----------------------------------------------------------------
-- 1. Build the dedupe mapping (duplicate_id → canonical_id) into a
--    TEMP table used by every subsequent step.
-- ----------------------------------------------------------------

CREATE TEMP TABLE tmp_sr_dedupe ON COMMIT DROP AS
WITH ranked AS (
    SELECT
        id, procedural_event_id, proceeding_type_id, rule_code,
        duration_value, duration_unit, primary_party,
        condition_expr, trigger_event_id, alt_duration_value,
        alt_duration_unit, alt_rule_code, anchor_alt, combine_op,
        parent_id, is_spawn, spawn_label, spawn_proceeding_type_id,
        created_at,
        ROW_NUMBER() OVER (
            PARTITION BY
                procedural_event_id, proceeding_type_id, rule_code,
                duration_value, duration_unit, primary_party,
                condition_expr::text, trigger_event_id,
                alt_duration_value, alt_duration_unit, alt_rule_code,
                anchor_alt, combine_op, parent_id, is_spawn, spawn_label,
                spawn_proceeding_type_id
            ORDER BY created_at, id::text
        ) AS rn,
        COUNT(*) OVER (
            PARTITION BY
                procedural_event_id, proceeding_type_id, rule_code,
                duration_value, duration_unit, primary_party,
                condition_expr::text, trigger_event_id,
                alt_duration_value, alt_duration_unit, alt_rule_code,
                anchor_alt, combine_op, parent_id, is_spawn, spawn_label,
                spawn_proceeding_type_id
        ) AS grp_size
      FROM paliad.sequencing_rules
     WHERE is_active = true
       AND lifecycle_state = 'published'
)
SELECT
    r.id AS duplicate_id,
    canon.id AS canonical_id,
    r.procedural_event_id,
    (SELECT name FROM paliad.procedural_events WHERE id = r.procedural_event_id) AS pe_name
  FROM ranked r
  JOIN ranked canon
    ON canon.procedural_event_id        IS NOT DISTINCT FROM r.procedural_event_id
   AND canon.proceeding_type_id         IS NOT DISTINCT FROM r.proceeding_type_id
   AND canon.rule_code                  IS NOT DISTINCT FROM r.rule_code
   AND canon.duration_value             IS NOT DISTINCT FROM r.duration_value
   AND canon.duration_unit              IS NOT DISTINCT FROM r.duration_unit
   AND canon.primary_party              IS NOT DISTINCT FROM r.primary_party
   AND canon.condition_expr::text       IS NOT DISTINCT FROM r.condition_expr::text
   AND canon.trigger_event_id           IS NOT DISTINCT FROM r.trigger_event_id
   AND canon.alt_duration_value         IS NOT DISTINCT FROM r.alt_duration_value
   AND canon.alt_duration_unit          IS NOT DISTINCT FROM r.alt_duration_unit
   AND canon.alt_rule_code              IS NOT DISTINCT FROM r.alt_rule_code
   AND canon.anchor_alt                 IS NOT DISTINCT FROM r.anchor_alt
   AND canon.combine_op                 IS NOT DISTINCT FROM r.combine_op
   AND canon.parent_id                  IS NOT DISTINCT FROM r.parent_id
   AND canon.is_spawn                   IS NOT DISTINCT FROM r.is_spawn
   AND canon.spawn_label                IS NOT DISTINCT FROM r.spawn_label
   AND canon.spawn_proceeding_type_id   IS NOT DISTINCT FROM r.spawn_proceeding_type_id
   AND canon.rn = 1
 WHERE r.rn > 1 AND r.grp_size > 1;

-- ----------------------------------------------------------------
-- 2. Surface every clone-group as a NOTICE before archiving.
-- ----------------------------------------------------------------

DO $$
DECLARE
    rec record;
    total_to_archive int;
BEGIN
    SELECT COUNT(*) INTO total_to_archive FROM tmp_sr_dedupe;
    RAISE NOTICE '[mig 152] PRE: % sequencing_rules row(s) will be archived', total_to_archive;
    FOR rec IN
        SELECT pe_name, canonical_id, COUNT(*) AS dup_count, array_agg(duplicate_id::text ORDER BY duplicate_id::text) AS dup_ids
          FROM tmp_sr_dedupe
         GROUP BY pe_name, canonical_id
         ORDER BY pe_name
    LOOP
        RAISE NOTICE '[mig 152]   %  canonical=%  duplicates=%  ids=%',
            rec.pe_name, rec.canonical_id, rec.dup_count, rec.dup_ids;
    END LOOP;
END $$;

-- ----------------------------------------------------------------
-- 3. Snapshot the rows about to be archived (only the duplicates;
--    the canonicals stay in the live table). Matches precedent.
-- ----------------------------------------------------------------

CREATE TABLE paliad.sequencing_rules_pre_152 AS
SELECT sr.*
  FROM paliad.sequencing_rules sr
  JOIN tmp_sr_dedupe d ON d.duplicate_id = sr.id;

COMMENT ON TABLE paliad.sequencing_rules_pre_152 IS
    'Snapshot of paliad.sequencing_rules rows archived by mig 152 '
    '(identical clones — Mängelbeseitigung / Zahlung × 5). Mirrors '
    'precedent pre_091/093/095/098/140/151. Read-only revert source. '
    't-paliad-321 / m/paliad#144 follow-up.';

-- ----------------------------------------------------------------
-- 4. Reparent paliad.deadlines.sequencing_rule_id duplicate → canonical
--    BEFORE archiving. Today's live data has 0 deadlines pointing at
--    any duplicate, but the statement is safe + defensive against a
--    race between drift-check and apply.
-- ----------------------------------------------------------------

UPDATE paliad.deadlines d
   SET sequencing_rule_id = m.canonical_id,
       procedural_event_id = (SELECT procedural_event_id
                                FROM paliad.sequencing_rules
                               WHERE id = m.canonical_id),
       updated_at = now()
  FROM tmp_sr_dedupe m
 WHERE d.sequencing_rule_id = m.duplicate_id;

-- ----------------------------------------------------------------
-- 5. Defensive audit-reason. Sequencing_rules has no audit trigger
--    today (mig 151 §scope verified), but set_config is transactional
--    and a future audit trigger inherits the reason automatically.
-- ----------------------------------------------------------------

SELECT set_config('paliad.audit_reason',
    'mig 152: archive identical sequencing_rule clones (mig 151 follow-up; t-paliad-321)',
    true);

-- ----------------------------------------------------------------
-- 6. Archive the duplicates.
-- ----------------------------------------------------------------

UPDATE paliad.sequencing_rules
   SET is_active = false,
       lifecycle_state = 'archived',
       updated_at = now()
 WHERE id IN (SELECT duplicate_id FROM tmp_sr_dedupe);

-- ----------------------------------------------------------------
-- 7. POST assertions.
-- ----------------------------------------------------------------

DO $$
DECLARE
    v_archived int;
    v_remaining_dupes int;
    v_orphan_deadlines int;
BEGIN
    -- a. Did the expected number of rows get archived?
    SELECT COUNT(*) INTO v_archived
      FROM paliad.sequencing_rules
     WHERE id IN (SELECT duplicate_id FROM tmp_sr_dedupe)
       AND lifecycle_state = 'archived'
       AND is_active = false;
    IF v_archived <> (SELECT COUNT(*) FROM tmp_sr_dedupe) THEN
        RAISE EXCEPTION '[mig 152] FAILED POST: expected % rows archived, got %',
            (SELECT COUNT(*) FROM tmp_sr_dedupe), v_archived;
    END IF;

    -- b. No clone group of size > 1 should remain in active+published.
    SELECT COUNT(*) INTO v_remaining_dupes FROM (
        SELECT 1
          FROM paliad.sequencing_rules
         WHERE is_active = true AND lifecycle_state = 'published'
         GROUP BY procedural_event_id, proceeding_type_id, rule_code,
                  duration_value, duration_unit, primary_party,
                  condition_expr::text, trigger_event_id,
                  alt_duration_value, alt_duration_unit, alt_rule_code,
                  anchor_alt, combine_op, parent_id, is_spawn, spawn_label,
                  spawn_proceeding_type_id
        HAVING COUNT(*) > 1
    ) g;
    IF v_remaining_dupes > 0 THEN
        RAISE EXCEPTION '[mig 152] FAILED POST: % clone group(s) still active+published after archive', v_remaining_dupes;
    END IF;

    -- c. No deadline points at an archived sequencing_rule.
    SELECT COUNT(*) INTO v_orphan_deadlines
      FROM paliad.deadlines d
      JOIN paliad.sequencing_rules sr ON sr.id = d.sequencing_rule_id
     WHERE sr.lifecycle_state = 'archived';
    IF v_orphan_deadlines > 0 THEN
        RAISE EXCEPTION '[mig 152] FAILED POST: % live deadline(s) still point at an archived sequencing_rule', v_orphan_deadlines;
    END IF;

    RAISE NOTICE '[mig 152] OK — archived=%, remaining clone groups=0, orphan deadlines=0',
        v_archived;
END $$;