#!/usr/bin/env bash
# Audit one Arcodange invoice end-to-end.
#
# Usage:
#   audit-invoice.sh <invoice-id>
#
# JSON side: pulls /invoices/{id} + /thirdparties/{socid}, prints facts
# (ref, dates, HT, TVA, TTC, paye flag, mode_reglement, cond_reglement).
#
# PDF side: pulls /documents/download, base64-decodes, runs pdftotext,
# then checks STRUCTURAL PRESENCE of mandatory French invoice mentions.
# We do NOT match against static/config/company.json — that file holds
# placeholder values today; Dolibarr renders the real legal data from
# its own setup. So we check shape, not exact strings.
#
# Mandatory-mention checklist (codified for SARL / SAS / EURL Arcodange):
#   - Forme juridique (any of SARL / SAS / EURL / SA / SCI / SASU)
#   - SIRET (14-digit number, optionally space-separated)
#   - TVA intracom (FR + 2 chars + 9 digits)
#   - RCS Évry / RCS Evry / R.C.S. Évry
#   - NAF-APE code (NNNNL pattern)
#   - Capital social ("capital" anywhere)
#   - TVA 259-1° CGI (autoliquidation for non-EU prestations de services)
#   - L.441-10 — late-payment penalties (BCE+10 or 12,15 %)
#   - 40 € indemnité forfaitaire (Décret 2012-1115)
#   - L.123-22 / R.123-237 identification mentions
#
# Exits 0 if every check passes, 1 otherwise.
#
# Requires: curl, python3, jq, pdftotext (brew install poppler).

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
DOL_CURL="${SCRIPT_DIR}/../../dolibarr/scripts/dol-curl.sh"

if [[ $# -lt 1 ]]; then
  echo "audit-invoice.sh: missing invoice id. Usage: audit-invoice.sh <id>" >&2
  exit 2
fi
INVOICE_ID="$1"

command -v pdftotext >/dev/null || { echo "audit-invoice.sh: pdftotext not found (brew install poppler)" >&2; exit 2; }
command -v jq        >/dev/null || { echo "audit-invoice.sh: jq not found" >&2; exit 2; }

# --- JSON side -------------------------------------------------------------
INV_JSON="$("${DOL_CURL}" "/invoices/${INVOICE_ID}")"
SOCID=$(  echo "${INV_JSON}" | jq -r .socid)
REF=$(    echo "${INV_JSON}" | jq -r .ref)
DATE_TS=$(echo "${INV_JSON}" | jq -r '.date // 0 | tonumber')
DUE_TS=$( echo "${INV_JSON}" | jq -r '.date_lim_reglement // 0 | tonumber')
HT=$(     echo "${INV_JSON}" | jq -r .total_ht)
TVA=$(    echo "${INV_JSON}" | jq -r .total_tva)
TTC=$(    echo "${INV_JSON}" | jq -r .total_ttc)
PAYE=$(   echo "${INV_JSON}" | jq -r .paye)
COND=$(   echo "${INV_JSON}" | jq -r '.cond_reglement_code // "-"')
PDF_PATH=$(echo "${INV_JSON}" | jq -r .last_main_doc)

DATE_HUMAN=$(python3 -c "import datetime,sys; ts=int(sys.argv[1]); print(datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d') if ts else '-')" "${DATE_TS}")
DUE_HUMAN=$( python3 -c "import datetime,sys; ts=int(sys.argv[1]); print(datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d') if ts else '-')" "${DUE_TS}")

TP_JSON="$("${DOL_CURL}" "/thirdparties/${SOCID}")"
TP_NAME=$(echo "${TP_JSON}" | jq -r '.name // .ref')

PAYE_HUMAN=$( [[ "${PAYE}" == "1" ]] && echo "PAID" || echo "UNPAID" )

# Heuristic: TVA == 0 -> likely reverse-charge (KM is in the US, 259-1° CGI).
TVA_NOTE=""
if [[ "${TVA}" == "0" || "${TVA}" == "0.00000000" || "${TVA}" == "0.00" ]]; then
  TVA_NOTE="(TVA=0 → reverse-charge expected; the 259-1° CGI mention MUST be on the PDF)"
fi

cat <<EOF
================================================================================
 Invoice ${INVOICE_ID} — ${REF}
================================================================================
  Thirdparty     : ${TP_NAME} (socid=${SOCID})
  Invoice date   : ${DATE_HUMAN}
  Due date       : ${DUE_HUMAN}  (cond_reglement_code=${COND})
  Total HT       : ${HT}
  Total TVA      : ${TVA}    ${TVA_NOTE}
  Total TTC      : ${TTC}
  Payment state  : ${PAYE_HUMAN}
  PDF            : ${PDF_PATH}
EOF

if [[ -z "${PDF_PATH}" || "${PDF_PATH}" == "null" ]]; then
  echo
  echo "  /!\\ No PDF attached (last_main_doc is null). Skipping mandatory-mention audit."
  echo
  exit 1
fi

# --- PDF side --------------------------------------------------------------
# original_file must be URL-encoded (the slash between dir and filename too).
ENCODED_PDF=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1], safe=''))" "${PDF_PATH#facture/}")
PDF_DOC_JSON="$("${DOL_CURL}" "/documents/download?modulepart=facture&original_file=${ENCODED_PDF}")"
PDF_B64="$(echo "${PDF_DOC_JSON}" | jq -r .content)"
if [[ -z "${PDF_B64}" || "${PDF_B64}" == "null" ]]; then
  echo "audit-invoice.sh: no base64 content returned for ${PDF_PATH}" >&2
  exit 1
fi

PDF_TMP="$(mktemp -t dolaudit.XXXXXX.pdf)"
TXT_TMP="$(mktemp -t dolaudit.XXXXXX.txt)"
trap 'rm -f "${PDF_TMP}" "${TXT_TMP}"' EXIT
echo "${PDF_B64}" | base64 -d > "${PDF_TMP}"
pdftotext -layout "${PDF_TMP}" "${TXT_TMP}"

pass_count=0
fail_count=0
check() {
  # check "label" "extended-regex-pattern"
  local label="$1" pat="$2"
  if grep -E -q -- "${pat}" "${TXT_TMP}"; then
    printf '  [OK] %s\n' "${label}"
    pass_count=$((pass_count+1))
  else
    printf '  [XX] %s   (looked for: %s)\n' "${label}" "${pat}"
    fail_count=$((fail_count+1))
  fi
}

echo
echo "  Mandatory-mention audit — structural presence on the PDF:"
check "Forme juridique (SARL/SAS/EURL/SA/SCI/SASU)"   "(SARL|SAS|EURL|SCI|SASU|SA[^[:alpha:]])"
check "SIRET (14 digits)"                              "SIRET[[:space:]:]*[0-9]{14}"
check "Numéro TVA intracom (FR + 11 chars)"            "(TVA|TVA intra)[[:space:]:]*FR[0-9A-Z]{11}"
check "RCS / R.C.S. Évry"                              "(R\\.?C\\.?S\\.?|RCS).*[EÉ]vry"
check "NAF-APE code"                                   "(NAF|APE)[[:space:]:-]*[0-9]{4}[A-Z]"
check "Capital social"                                 "[Cc]apital"
check "TVA 259-1° CGI / autoliquidation"               "(259-?1|autoliquidation|reverse[- ]charge)"
check "L.441-10 — BCE+10 or 12,15 %"                   "(L\\.?441-10|BCE[[:space:]]*\\+[[:space:]]*10|12[.,]15[[:space:]]*%)"
check "40 € indemnité forfaitaire"                     "(40[[:space:]]*€|indemnit[eé] forfaitaire|D[eé]cret 2012-1115)"
check "L.123-22 / R.123-237"                           "(L\\.?123-22|R\\.?123-237)"

# Surface the real legal identifiers extracted from the PDF — useful for
# cross-checking against the cohort review without re-running pdftotext.
echo
echo "  Real identifiers extracted from the PDF (informational):"
SIRET_FOUND=$( grep -E -o "SIRET[[:space:]:]*[0-9]{14}"      "${TXT_TMP}" | head -1 || true)
TVA_FOUND=$(   grep -E -o "(TVA|TVA intra)[[:space:]:]*FR[0-9A-Z]{11}" "${TXT_TMP}" | head -1 || true)
APE_FOUND=$(   grep -E -o "(NAF|APE)[[:space:]:-]*[0-9]{4}[A-Z]" "${TXT_TMP}" | head -1 || true)
FORM_FOUND=$(  grep -E -o "(SARL|SAS|EURL|SCI|SASU|Soci[eé]t[eé] [^[:cntrl:]]{0,40})" "${TXT_TMP}" | head -1 || true)
echo "      ${FORM_FOUND:-(forme juridique not found)}"
echo "      ${SIRET_FOUND:-(SIRET not found)}"
echo "      ${TVA_FOUND:-(TVA intracom not found)}"
echo "      ${APE_FOUND:-(NAF-APE not found)}"

echo
echo "  ${pass_count} pass / ${fail_count} fail"
[[ ${fail_count} -eq 0 ]]