tessera-ctl/apps/api/src/dkv/dkv-parser.validate.ts

/**
 * Wave 0 validation script for the DKV PDF parser.
 *
 * Usage (from project root):
 *   node --experimental-strip-types apps/api/src/dkv/dkv-parser.validate.ts
 *
 * Reads user-files/invoice.pdf, extracts text via pdf-parse v2,
 * runs the vehicle-block regex and transaction parsers, prints results.
 * Exits 1 if zero vehicle blocks are found (assertion failure).
 */

import { readFileSync } from 'node:fs';
import { join } from 'node:path';
import { PDFParse } from 'pdf-parse';
import type { DkvVehicleBlock, DkvTransaction } from './dkv.types.js';

// ─── German number parser ─────────────────────────────────────────────────────
function parseDE(raw: string): number {
  return parseFloat(raw.replace(/\./g, '').replace(',', '.'));
}

// ─── Single-transaction line parser ──────────────────────────────────────────
// Format: DD.MM.YYYY \t Name \t Ort \t StNr \t TxNr \t "KM PRODUKT" \t "CODE UNIT" \t Menge \t PriceBrutto \t PriceNetto \t TotalBrutto \t TotalNetto \t ...
function parseSingleTxLine(line: string): DkvTransaction | null {
  const fields = line.split('\t').map(f => f.trim());
  if (fields.length < 8) return null;

  const datePattern = /^\d{2}\.\d{2}\.\d{4}$/;
  if (!datePattern.test(fields[0])) return null;

  // fields[5] = "KM_VALUE PRODUKT" (km and produkt merged — no tab between them in PDF)
  const kmAndProdukt = fields[5].split(/\s+/);
  const km = kmAndProdukt[0] ?? '0';
  const produkt = kmAndProdukt.slice(1).join(' ');

  // fields[6] = "UNITCODE UNIT" (e.g., "0009 LTR" or "0036 LTR")
  const unitParts = fields[6].split(/\s+/);
  const einheit = unitParts.slice(1).join(' ') || unitParts[0];

  return {
    lieferdatum: fields[0],
    ort: fields[2] ?? '',
    kilometerstand: parseDE(km),
    produkt,
    menge: parseDE(fields[7] ?? '0'),
    einheit,
    netto: parseDE(fields[11] ?? '0'),
    brutto: parseDE(fields[10] ?? '0'),
  };
}

// ─── Multi-transaction columnar parser ───────────────────────────────────────
// Format (3 transactions with n=3):
//   [0..2]    dates         n values
//   [3..5]    names         n values
//   [6..8]    orts          n values
//   [9..11]   station_nrs   n values
//   [12..14]  tx_nrs        n values
//   [15..17]  km_values     n values
//   [18..20]  products      n values
//   [21..23]  unit_codes    n values
//   [24..26]  units         n values
//   [27..29]  quantities    n values
//   [30..32]  unit_brutto   n values
//   [33..35]  unit_netto    n values
//   [36..38]  total_brutto  n values
//   [39..41]  total_netto   n values
//   ... (discounts, taxes, final totals)
function parseMultiTxColumnar(lines: string[]): DkvTransaction[] {
  // Count leading date lines to determine n (number of transactions)
  const datePattern = /^\d{2}\.\d{2}\.\d{4}$/;
  let n = 0;
  for (const line of lines) {
    if (datePattern.test(line)) n++;
    else break;
  }
  if (n === 0) return [];

  const g = (groupIdx: number): string[] =>
    lines.slice(groupIdx * n, (groupIdx + 1) * n);

  const dates = g(0);
  const orts = g(2);
  const kms = g(5);
  const products = g(6);
  const units = g(8);
  const quantities = g(9);
  const totals_brutto = g(12);
  const totals_netto = g(13);

  return dates.map((date, i) => ({
    lieferdatum: date,
    ort: orts[i] ?? '',
    kilometerstand: parseDE(kms[i] ?? '0'),
    produkt: products[i] ?? '',
    menge: parseDE(quantities[i] ?? '0'),
    einheit: units[i] ?? '',
    netto: parseDE(totals_netto[i] ?? '0'),
    brutto: parseDE(totals_brutto[i] ?? '0'),
  }));
}

// ─── Transaction rows dispatcher ─────────────────────────────────────────────
function parseTransactionRows(blockText: string): DkvTransaction[] {
  const lines = blockText
    .split('\n')
    .map(l => l.trim())
    .filter(l => l && !l.startsWith('»'));

  if (lines.length === 0) return [];

  const datePattern = /^\d{2}\.\d{2}\.\d{4}/;

  // Detect format: if any date-starting line also contains a tab → single-tx format
  const hasTabbedDateLine = lines.some(l => datePattern.test(l) && l.includes('\t'));

  if (hasTabbedDateLine) {
    // Single-transaction format
    return lines
      .filter(l => datePattern.test(l) && l.includes('\t'))
      .map(parseSingleTxLine)
      .filter((tx): tx is DkvTransaction => tx !== null);
  }

  // Multi-transaction columnar format
  return parseMultiTxColumnar(lines);
}

// ─── Vehicle block parser ─────────────────────────────────────────────────────
function parseDkvText(text: string): DkvVehicleBlock[] {
  const vehicles: DkvVehicleBlock[] = [];

  // Anchor on VEHICLE: marker — each block extends until next VEHICLE: or end of text
  // Kennzeichen can contain letters, digits, hyphens, spaces, dots (e.g. "GP-JL 728E")
  const vehicleBlockPattern =
    /VEHICLE:\s+([A-Z0-9 ._\-]+?)\s+CARD NO\.:\s+(\S+)([\s\S]*?)(?=VEHICLE:|$)/g;

  let match: RegExpExecArray | null;
  while ((match = vehicleBlockPattern.exec(text)) !== null) {
    const kennzeichen = match[1].trim();
    const cardNumber = match[2].trim();
    const blockText = match[3];

    const transactions = parseTransactionRows(blockText);
    vehicles.push({ kennzeichen, cardNumber, transactions });
  }
  return vehicles;
}

// ─── PDF extraction ───────────────────────────────────────────────────────────
async function extractPdfText(buffer: Buffer): Promise<string> {
  const parser = new PDFParse({ data: buffer });
  const result = await parser.getText();
  await parser.destroy(); // free memory per pdf-parse guidance (T-07-01)
  return result.text;
}

// ─── Main ─────────────────────────────────────────────────────────────────────
async function main(): Promise<void> {
  const invoicePath = join(process.cwd(), 'user-files', 'invoice.pdf');
  let buffer: Buffer;
  try {
    buffer = readFileSync(invoicePath);
  } catch {
    console.error(`ERROR: Cannot read invoice file at ${invoicePath}`);
    process.exit(1);
  }

  console.log(`[DKV Validate] Reading ${invoicePath} (${buffer.length} bytes)`);

  let text: string;
  try {
    text = await extractPdfText(buffer);
  } catch (err) {
    console.error('[DKV Validate] pdf-parse extraction failed:', err);
    process.exit(1);
  }

  console.log(`[DKV Validate] Extracted ${text.length} characters of text`);

  const vehicles = parseDkvText(text);

  if (vehicles.length === 0) {
    console.error('[DKV Validate] ASSERTION FAILED: Zero vehicle blocks parsed!');
    console.error('[DKV Validate] Full extracted text for regex debugging:');
    console.error(text);
    process.exit(1);
  }

  const totalTx = vehicles.reduce((s, v) => s + v.transactions.length, 0);
  console.log(`[DKV Validate] PASSED: ${vehicles.length} vehicle block(s), ${totalTx} transaction(s) total\n`);

  // Print first 3 blocks
  for (const [i, v] of vehicles.slice(0, 3).entries()) {
    console.log(`Block ${i + 1}: ${v.kennzeichen} (card: ${v.cardNumber}) — ${v.transactions.length} tx`);
    for (const tx of v.transactions.slice(0, 2)) {
      console.log(`  ${tx.lieferdatum} @ ${tx.ort} | ${tx.kilometerstand} km | ${tx.menge} ${tx.einheit} ${tx.produkt}`);
    }
  }

  console.log(`\nAll vehicles: ${vehicles.map(v => `${v.kennzeichen}(${v.transactions.length}tx)`).join(', ')}`);
}

main().catch(err => {
  console.error('[DKV Validate] Unhandled error:', err);
  process.exit(1);
});