-- One account, one identity — without destroying how the number reads.
--
-- `account_number` carries the same fragmentation `bank_name` had, from the
-- same cause: Gemini copies whatever the PDF prints, and the formatting varies
-- per document.
--
--   ANZ  '4085-56264'  4 statements   ANZ ACCESS ADVANTAGE
--   ANZ  '408556264'   1 statement    ACCESS ADVANTAGE      <- same account
--
-- That matters because `uq_statement_identity` is
-- (bank_name, account_number, billing_end_date). Re-importing one period under
-- the other spelling evades the duplicate check entirely.
--
-- (It is NOT what caused the documented 31-row / $42,040.68 ANZ duplication.
-- Statements 107/142/143 overlap on *different* end dates, which that index
-- cannot catch at any spelling. Different problem, same table.)
--
-- WHY A GENERATED COLUMN RATHER THAN REWRITING THE VALUE: the raw number is the
-- readable one and some of it is structure, not noise. Up stores
-- '633-123 / 176540052' — a BSB and an account number — and flattening that to
-- '633123176540052' would lose a distinction a human reads at a glance, to fix
-- a machine problem. So the raw text stays exactly as extracted and the
-- comparison key is derived beside it. Same reason the app derives trip
-- participation instead of storing it: two records of one fact drift.
--
-- Separators only. Case and the Amex mask ('XXXX-XXXXXX-01000') are preserved,
-- because 'X' is real information about which digits were redacted, and
-- case-folding an alphanumeric account id could merge two genuinely different
-- ones.
--
-- Verified collision-free before rebuilding the index: no two statements share
-- (bank_name, stripped account_number, billing_end_date).
--
-- Idempotent: safe to re-run.

ALTER TABLE statements
  ADD COLUMN IF NOT EXISTS account_number_key TEXT
  GENERATED ALWAYS AS (
    NULLIF(regexp_replace(coalesce(account_number, ''), '[^0-9A-Za-z]', '', 'g'), '')
  ) STORED;

COMMENT ON COLUMN statements.account_number_key IS
  'Derived from account_number, separators stripped. The identity used by '
  'uq_statement_identity so one account under two formats is one account. '
  'Never write to it — it is GENERATED. Display account_number instead.';

-- Rebuild the identity index on the derived key. Dropped and recreated rather
-- than added alongside: leaving the old one in place would keep admitting the
-- duplicate it exists to stop.
DROP INDEX IF EXISTS uq_statement_identity;
CREATE UNIQUE INDEX uq_statement_identity
  ON statements (bank_name, account_number_key, billing_end_date)
  WHERE bank_name IS NOT NULL AND billing_end_date IS NOT NULL;

-- The fragmentation detector, now able to see both halves: one account under
-- two bank names, or one bank under two spellings of one number.
CREATE OR REPLACE VIEW statement_identity_drift AS
  SELECT account_number_key,
         array_agg(DISTINCT bank_name)      AS bank_names,
         array_agg(DISTINCT account_number) AS account_numbers,
         count(*)                           AS statements
  FROM statements
  WHERE account_number_key IS NOT NULL
  GROUP BY account_number_key
  HAVING count(DISTINCT bank_name) > 1
      OR count(DISTINCT account_number) > 1;

COMMENT ON VIEW statement_identity_drift IS
  'Non-empty means an account is fragmented: normalize_bank_name() cannot know '
  'that two names for a bank it has never seen are one institution, and this is '
  'how that always shows up. Check it after loading a new bank.';