-- Read-only audit for posted entries that a defective booking template may have
-- mis-classified. Covers the two defects fixed in #1396 and #1397 whose bad
-- postings succeeded and therefore may remain in customers' ledgers.
--
-- Not covered, deliberately: vehicle_parking (5614) and it_cloud_hosting (5421)
-- named accounts that never existed in BAS, so account-backfill could not seed
-- them and every booking through those templates failed. Nothing was posted.
--
-- The query separates template-remediation evidence from broad account
-- signatures. Imported entries and earlier corrections cannot have been
-- generated by either live template in this database. The remaining signatures
-- can still have legitimate shapes: 5820 is correct for actual car hire, and
-- representation can lawfully carry 25% VAT when the supply itself is subject
-- to 25% and the invoice is correct. Review the underlag before acting.
--
-- The query performs no writes, creates no objects, and returns one row per
-- posted journal entry and defect. Companion procedure:
-- docs/TEMPLATE_MISBOOKING_REMEDIATION.md.

with debit_line_groups as (
  -- Aggregate before classification so entries with several 6072 or 2641
  -- lines are evaluated once. This avoids the previous many-to-many pairing.
  select
    jel.journal_entry_id,
    jel.account_number,
    array_agg(jel.id order by jel.sort_order, jel.id) as line_ids,
    sum(jel.debit_amount) as debit_amount
  from public.journal_entry_lines jel
  where jel.account_number in ('5820', '6072', '2641')
    and jel.debit_amount > 0
  group by jel.journal_entry_id, jel.account_number
),

candidate_entry_ids as (
  select distinct journal_entry_id
  from debit_line_groups
  where account_number in ('5820', '6072')
),

candidate_transactions as (
  select
    t.journal_entry_id,
    t.id as transaction_id,
    t.document_id,
    concat_ws(' ', nullif(t.merchant_name, ''), nullif(t.description, '')) as transaction_description
  from public.transactions t
  join candidate_entry_ids candidate on candidate.journal_entry_id = t.journal_entry_id
  where t.journal_entry_id is not null

  union all

  select
    tvl.journal_entry_id,
    t.id as transaction_id,
    t.document_id,
    concat_ws(' ', nullif(t.merchant_name, ''), nullif(t.description, '')) as transaction_description
  from public.transaction_voucher_links tvl
  join candidate_entry_ids candidate on candidate.journal_entry_id = tvl.journal_entry_id
  join public.transactions t on t.id = tvl.transaction_id
),

transaction_context as (
  select
    journal_entry_id,
    string_agg(
      distinct transaction_description,
      ' | ' order by transaction_description
    ) as transaction_description
  from candidate_transactions
  group by journal_entry_id
),

hotel_candidates as (
  -- The Hotell template debited 5820 (Hyrbilskostnader) instead of 5830
  -- (Kost och logi) until #1397.
  select
    'travel_hotel_5820'::text as defect,
    je.company_id,
    je.id as journal_entry_id,
    je.voucher_series,
    je.voucher_number,
    je.entry_date,
    je.committed_at,
    je.fiscal_period_id,
    je.source_type,
    cost.line_ids as cost_line_ids,
    coalesce(vat.line_ids, '{}'::uuid[]) as vat_line_ids,
    '5820'::text as observed_cost_account,
    '5830'::text as expected_cost_account,
    case when vat.line_ids is null then null else '2641'::text end as observed_vat_account,
    case when vat.line_ids is null then null else '2641'::text end as expected_vat_account,
    cost.debit_amount as cost_debit_amount,
    vat.debit_amount as vat_debit_amount,
    round(vat.debit_amount / nullif(cost.debit_amount, 0), 6) as observed_vat_rate,
    0.12::numeric as expected_vat_rate,
    tx.transaction_description,
    case
      when tx.transaction_description ~* '(hotel|hotell|scandic|elite|best western|nordic choice|clarion|quality inn|radisson|booking\.com|airbnb|logi|övernattning)'
        then 'high_hotel_counterparty_on_car_hire_account'
      when abs(vat.debit_amount - cost.debit_amount * 0.12) < 0.02
        then 'medium_12pct_vat_on_car_hire_account'
      else 'manual_review_5820_no_corroborating_signal'
    end::text as review_priority
  from public.journal_entries je
  join debit_line_groups cost
    on cost.journal_entry_id = je.id and cost.account_number = '5820'
  left join debit_line_groups vat
    on vat.journal_entry_id = je.id and vat.account_number = '2641'
  left join transaction_context tx on tx.journal_entry_id = je.id
  where je.status = 'posted'
),

representation_candidates as (
  -- The representation template deducted 25% input VAT on what was intended
  -- to be a 12% restaurant supply until #1396. Totals are evaluated per entry,
  -- never by pairing individual lines.
  select
    'representation_25pct_vat'::text as defect,
    je.company_id,
    je.id as journal_entry_id,
    je.voucher_series,
    je.voucher_number,
    je.entry_date,
    je.committed_at,
    je.fiscal_period_id,
    je.source_type,
    cost.line_ids as cost_line_ids,
    vat.line_ids as vat_line_ids,
    '6072'::text as observed_cost_account,
    '6072'::text as expected_cost_account,
    '2641'::text as observed_vat_account,
    '2641'::text as expected_vat_account,
    cost.debit_amount as cost_debit_amount,
    vat.debit_amount as vat_debit_amount,
    round(vat.debit_amount / nullif(cost.debit_amount, 0), 6) as observed_vat_rate,
    0.12::numeric as expected_vat_rate,
    tx.transaction_description,
    case
      when abs(vat.debit_amount - cost.debit_amount * 0.25) < 0.02
        then 'high_vat_is_25pct_of_6072_cost'
      else 'manual_review_6072_with_vat'
    end::text as review_priority
  from public.journal_entries je
  join debit_line_groups cost
    on cost.journal_entry_id = je.id and cost.account_number = '6072'
  join debit_line_groups vat
    on vat.journal_entry_id = je.id and vat.account_number = '2641'
  left join transaction_context tx on tx.journal_entry_id = je.id
  where je.status = 'posted'
),

all_candidates as (
  select
    defect,
    company_id,
    journal_entry_id,
    voucher_series,
    voucher_number,
    entry_date,
    committed_at,
    fiscal_period_id,
    source_type,
    cost_line_ids,
    vat_line_ids,
    observed_cost_account,
    expected_cost_account,
    observed_vat_account,
    expected_vat_account,
    cost_debit_amount,
    vat_debit_amount,
    observed_vat_rate,
    expected_vat_rate,
    transaction_description,
    review_priority
  from hotel_candidates

  union all

  select
    defect,
    company_id,
    journal_entry_id,
    voucher_series,
    voucher_number,
    entry_date,
    committed_at,
    fiscal_period_id,
    source_type,
    cost_line_ids,
    vat_line_ids,
    observed_cost_account,
    expected_cost_account,
    observed_vat_account,
    expected_vat_account,
    cost_debit_amount,
    vat_debit_amount,
    observed_vat_rate,
    expected_vat_rate,
    transaction_description,
    review_priority
  from representation_candidates
),

entry_line_snapshots as (
  -- Retain every field accepted by gnubok_correct_entry for candidate entries
  -- only, without scanning and serializing the entire journal-line table.
  select
    jel.journal_entry_id,
    jsonb_agg(
      jsonb_strip_nulls(jsonb_build_object(
        'account_number', jel.account_number,
        'debit_amount', jel.debit_amount,
        'credit_amount', jel.credit_amount,
        'line_description', jel.line_description,
        'currency', jel.currency,
        'amount_in_currency', jel.amount_in_currency,
        'exchange_rate', jel.exchange_rate,
        'tax_code', jel.tax_code,
        'dimensions', jel.dimensions
      ))
      order by jel.sort_order, jel.id
    ) as original_lines
  from public.journal_entry_lines jel
  join (
    select distinct journal_entry_id
    from all_candidates
  ) candidate on candidate.journal_entry_id = jel.journal_entry_id
  group by jel.journal_entry_id
),

candidate_documents as (
  -- Resolve every current underlag path that can legally support the entry:
  -- direct entry or line links, transaction links, and supplier-invoice
  -- references. Return document ids only, never storage paths or file names.
  select distinct
    c.journal_entry_id,
    d.id as document_id,
    d.extracted_data
  from all_candidates c
  join public.document_attachments d
    on d.is_current_version = true
   and (
     d.journal_entry_id = c.journal_entry_id
     or exists (
       select 1
       from public.journal_entry_lines jel
       where jel.journal_entry_id = c.journal_entry_id
         and jel.id = d.journal_entry_line_id
     )
   )

  union

  select distinct
    tx.journal_entry_id,
    d.id as document_id,
    d.extracted_data
  from candidate_transactions tx
  join public.document_attachments d
    on d.id = tx.document_id
   and d.is_current_version = true

  union

  select distinct
    c.journal_entry_id,
    d.id as document_id,
    d.extracted_data
  from all_candidates c
  join public.supplier_invoices si
    on si.registration_journal_entry_id = c.journal_entry_id
    or si.payment_journal_entry_id = c.journal_entry_id
    or exists (
      select 1
      from public.supplier_invoice_payments sip
      where sip.supplier_invoice_id = si.id
        and sip.journal_entry_id = c.journal_entry_id
    )
  join public.document_attachments d
    on d.id = si.document_id
   and d.is_current_version = true
),

candidate_document_vat_rates as (
  -- Extraction payloads are historical data and may have missing, malformed,
  -- or differently scaled rate values. Accept only numeric values, normalizing
  -- both 0.25 and 25 to percent before they reach the classifier.
  select
    cd.journal_entry_id,
    cd.document_id,
    case
      when rate.raw_rate::numeric <= 1 then rate.raw_rate::numeric * 100
      else rate.raw_rate::numeric
    end as normalized_rate
  from candidate_documents cd
  cross join lateral (
    select vat ->> 'rate' as raw_rate
    from jsonb_array_elements(
      case
        when jsonb_typeof(cd.extracted_data -> 'vatBreakdown') = 'array'
          then cd.extracted_data -> 'vatBreakdown'
        else '[]'::jsonb
      end
    ) vat

    union all

    select item ->> 'vatRate' as raw_rate
    from jsonb_array_elements(
      case
        when jsonb_typeof(cd.extracted_data -> 'lineItems') = 'array'
          then cd.extracted_data -> 'lineItems'
        else '[]'::jsonb
      end
    ) item
  ) rate
  where rate.raw_rate ~ '^\s*[0-9]+(?:\.[0-9]+)?\s*$'
),

document_signals as (
  select
    cd.journal_entry_id,
    array_agg(distinct cd.document_id order by cd.document_id) as document_ids,
    count(distinct cd.document_id)::integer as document_count,
    count(distinct cd.document_id) filter (
      where cd.extracted_data is not null
    )::integer as extracted_document_count,
    max(
      case
        when cd.extracted_data ->> 'confidence'
          ~ '^\s*[0-9]+(?:\.[0-9]+)?\s*$'
          then (cd.extracted_data ->> 'confidence')::numeric
      end
    ) as max_extraction_confidence,
    bool_or(rate.normalized_rate between 11.9 and 12.1)
      as document_has_12pct_vat,
    bool_or(rate.normalized_rate between 24.9 and 25.1)
      as document_has_25pct_vat
  from candidate_documents cd
  left join candidate_document_vat_rates rate
    on rate.journal_entry_id = cd.journal_entry_id
   and rate.document_id = cd.document_id
  group by cd.journal_entry_id
),

candidate_output as (
  select
    c.*,
    co.name as company_name,
    lines.original_lines,
    jsonb_array_length(lines.original_lines) as line_count,
    coalesce(doc.document_ids, '{}'::uuid[]) as document_ids,
    coalesce(doc.document_count, 0) as document_count,
    coalesce(doc.extracted_document_count, 0) as extracted_document_count,
    doc.max_extraction_confidence,
    coalesce(doc.document_has_12pct_vat, false) as document_has_12pct_vat,
    coalesce(doc.document_has_25pct_vat, false) as document_has_25pct_vat,
    case
      when c.defect = 'representation_25pct_vat'
        then 'participants_purpose_and_300_sek_vat_base_cap_required'
      else 'not_applicable'
    end as independent_representation_review,
    c.defect = 'representation_25pct_vat'
      and c.cost_debit_amount > 300
      as observed_6072_cost_exceeds_300_sek,
    reporting.vat_reporting_period,
    coalesce(filing.deadline_statuses, '{}'::text[]) as vat_deadline_statuses,
    case
      when c.defect <> 'representation_25pct_vat' then 'not_applicable'
      when reporting.vat_reporting_period is null
        then 'unknown_reporting_period'
      when coalesce(filing.has_confirmed_record, false)
        then 'confirmed_in_app'
      when coalesce(filing.has_submitted_record, false)
        then 'submitted_in_app'
      else 'not_proven_by_in_app_records'
    end as vat_filing_status,
    case
      when fp.id is null then 'missing_fiscal_period'
      when fp.is_closed then 'closed'
      when fp.locked_at is not null then 'locked'
      when cs.bookkeeping_locked_through is not null
        and c.entry_date <= cs.bookkeeping_locked_through then 'behind_company_lock_date'
      else 'open'
    end as effective_lock_status
  from all_candidates c
  join public.companies co on co.id = c.company_id
  join entry_line_snapshots lines on lines.journal_entry_id = c.journal_entry_id
  left join document_signals doc on doc.journal_entry_id = c.journal_entry_id
  left join public.company_settings cs on cs.company_id = c.company_id
  left join public.fiscal_periods fp on fp.id = c.fiscal_period_id
  left join lateral (
    select case
      when c.defect <> 'representation_25pct_vat' then null
      when cs.moms_period = 'monthly'
        then to_char(c.entry_date, 'YYYY-MM')
      when cs.moms_period = 'quarterly'
        then concat(
          extract(year from c.entry_date)::integer,
          '-Q',
          ceil(extract(month from c.entry_date) / 3.0)::integer
        )
      when cs.moms_period = 'yearly' and fp.period_end is not null
        then case
          when extract(month from fp.period_end) = 12
            then extract(year from fp.period_end)::integer::text
          else concat(
            extract(year from fp.period_end)::integer - 1,
            '/',
            extract(year from fp.period_end)::integer
          )
        end
      else null
    end as vat_reporting_period
  ) reporting on true
  left join lateral (
    select
      array_agg(distinct d.status order by d.status) as deadline_statuses,
      bool_or(d.status = 'submitted') as has_submitted_record,
      bool_or(d.status = 'confirmed') as has_confirmed_record
    from public.deadlines d
    where c.defect = 'representation_25pct_vat'
      and d.company_id = c.company_id
      and d.tax_deadline_type = case cs.moms_period
        when 'monthly' then 'moms_monthly'
        when 'quarterly' then 'moms_quarterly'
        when 'yearly' then 'moms_yearly'
      end
      and d.tax_period = reporting.vat_reporting_period
  ) filing on true
),

classified as (
  select
    candidate.*,
    case
      -- Imports and earlier corrections were not generated by either live
      -- template in this database. They can have independent accounting
      -- issues, but are false positives for this template-remediation audit.
      when candidate.source_type in ('import', 'correction')
        then 'false_positive'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.review_priority = 'high_vat_is_25pct_of_6072_cost'
        and candidate.document_has_25pct_vat
        and not candidate.document_has_12pct_vat
        then 'false_positive'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.review_priority = 'high_vat_is_25pct_of_6072_cost'
        then 'insufficient_evidence'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.observed_vat_rate between 0.119 and 0.121
        then 'false_positive'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.document_has_12pct_vat
        and not candidate.document_has_25pct_vat
        then 'false_positive'
      when candidate.defect = 'representation_25pct_vat'
        then 'insufficient_evidence'
      -- The defective hotel template deterministically emitted three lines:
      -- 5820 cost, 2641 at 12 percent, and one settlement credit. The hotel
      -- counterparty signal supplies the final discriminator from car hire.
      when candidate.defect = 'travel_hotel_5820'
        and candidate.line_count = 3
        and candidate.observed_vat_rate between 0.119 and 0.121
        and candidate.review_priority = 'high_hotel_counterparty_on_car_hire_account'
        then 'confirmed_correction'
      when candidate.defect = 'travel_hotel_5820'
        and candidate.line_count = 3
        and candidate.observed_vat_rate between 0.119 and 0.121
        then 'insufficient_evidence'
      else 'false_positive'
    end as evidence_classification,
    case
      when candidate.source_type in ('import', 'correction')
        then 'entry source cannot be either live template'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.review_priority = 'high_vat_is_25pct_of_6072_cost'
        and candidate.document_has_25pct_vat
        and not candidate.document_has_12pct_vat
        then 'extracted underlag confirms a 25 percent supply'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.review_priority = 'high_vat_is_25pct_of_6072_cost'
        then 'exact defective signature but no decisive underlag or provenance'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.observed_vat_rate between 0.119 and 0.121
        then 'voucher has the intended 12 percent aggregate VAT signature'
      when candidate.defect = 'representation_25pct_vat'
        and candidate.document_has_12pct_vat
        and not candidate.document_has_25pct_vat
        then 'extracted underlag confirms a 12 percent supply'
      when candidate.defect = 'representation_25pct_vat'
        then 'mixed representation voucher needs decisive underlag or provenance'
      when candidate.defect = 'travel_hotel_5820'
        and candidate.line_count = 3
        and candidate.observed_vat_rate between 0.119 and 0.121
        and candidate.review_priority = 'high_hotel_counterparty_on_car_hire_account'
        then 'exact defective hotel shape plus hotel counterparty'
      when candidate.defect = 'travel_hotel_5820'
        and candidate.line_count = 3
        and candidate.observed_vat_rate between 0.119 and 0.121
        then 'exact defective hotel shape without hotel evidence'
      else 'voucher does not have the defective hotel template shape'
    end as classification_reason
  from candidate_output candidate
)

select
  c.defect,
  c.evidence_classification,
  c.classification_reason,
  case
    when c.evidence_classification = 'confirmed_correction'
      then 'explicit_write_approval_required_after_underlag_review'
    when c.evidence_classification = 'insufficient_evidence'
      then 'underlag_required_before_approval_request'
    else 'no_template_remediation'
  end as approval_status,
  case
    when c.defect = 'representation_25pct_vat'
      and c.evidence_classification <> 'false_positive'
      then 'potential_if_confirmed'
    else 'none_from_this_defect'
  end as vat_return_impact,
  c.company_id,
  c.company_name,
  c.journal_entry_id,
  c.voucher_series,
  c.voucher_number,
  c.entry_date,
  c.committed_at,
  c.fiscal_period_id,
  c.source_type,
  c.cost_line_ids,
  c.vat_line_ids,
  c.observed_cost_account,
  c.expected_cost_account,
  c.observed_vat_account,
  c.expected_vat_account,
  c.cost_debit_amount,
  c.vat_debit_amount,
  c.observed_vat_rate,
  c.expected_vat_rate,
  c.transaction_description,
  c.review_priority,
  c.line_count,
  c.document_ids,
  c.document_count,
  c.extracted_document_count,
  c.max_extraction_confidence,
  c.document_has_12pct_vat,
  c.document_has_25pct_vat,
  c.independent_representation_review,
  c.observed_6072_cost_exceeds_300_sek,
  c.vat_reporting_period,
  c.vat_deadline_statuses,
  c.vat_filing_status,
  c.original_lines,
  c.effective_lock_status
from classified c
order by
  case c.evidence_classification
    when 'confirmed_correction' then 0
    when 'insufficient_evidence' then 1
    else 2
  end,
  c.defect,
  case
    when c.review_priority like 'high%' then 0
    when c.review_priority like 'medium%' then 1
    else 2
  end,
  c.entry_date desc;