pfm-ocr/backend/pfm-web-app/src/utils/product-scan.ts

import { query } from "../db";

// Bounds the classifier call so a wedged GPU container fails fast instead of
// hanging indefinitely. Raised from 90s (2026-07-14): hard images now
// legitimately take up to ~3 min - a 4-orientation OCR search plus a VL
// pipeline fallback when no expiry date is found (see
// config/classify_ocr_server.py) - and the old bound was killing exactly
// the images those fallbacks exist to save.
const PIPELINE_TIMEOUT_MS = 240_000;

// Thrown when the Python classifier service itself returns a non-2xx response,
// so callers can forward its actual status instead of collapsing everything to 500.
export class ClassifierError extends Error {
  status: number;
  constructor(status: number, message: string) {
    super(message);
    this.status = status;
  }
}

export interface SkuMatch {
  no_sku: string;
  nama_item: string;
  score: number;
  yoloSimilarity: number;
  isBestMatch: boolean;
}

export interface ProductScanResult {
  classification: any;
  ocr: any;
  possibleMatches: SkuMatch[];
}

function levenshteinDistance(s1: string, s2: string): number {
  const len1 = s1.length;
  const len2 = s2.length;
  const matrix = Array.from({ length: len1 + 1 }, () => new Array(len2 + 1).fill(0));

  for (let i = 0; i <= len1; i++) matrix[i][0] = i;
  for (let j = 0; j <= len2; j++) matrix[0][j] = j;

  for (let i = 1; i <= len1; i++) {
    for (let j = 1; j <= len2; j++) {
      const cost = s1[i - 1] === s2[j - 1] ? 0 : 1;
      matrix[i][j] = Math.min(
        matrix[i - 1][j] + 1,      // deletion
        matrix[i][j - 1] + 1,      // insertion
        matrix[i - 1][j - 1] + cost // substitution
      );
    }
  }
  return matrix[len1][len2];
}

function getStringSimilarity(s1: string, s2: string): number {
  const clean1 = s1.toLowerCase().replace(/[^a-z0-9]/g, '');
  const clean2 = s2.toLowerCase().replace(/[^a-z0-9]/g, '');
  if (!clean1 || !clean2) return 0;
  const distance = levenshteinDistance(clean1, clean2);
  const maxLength = Math.max(clean1.length, clean2.length);
  return (maxLength - distance) / maxLength;
}

// --- OCR-evidence re-ranking of the classifier's top-K candidates ---
//
// DINOv2's misses are near-twin confusions (same brand line, different
// flavor/size) - exactly the cases where the printed variant words differ,
// and PaddleOCR usually reads some of them. Within a narrow similarity band
// of the top-1 candidate, prefer the one whose distinctive name tokens
// actually appear in the OCR'd text. Coverage-normalized so generic
// packaging words (e.g. "French Fries", "Ayam") that happen to be unique to
// one candidate's *name* can't hijack the ranking. Parameters tuned offline
// against the 79-image validation set (scripts/experiment-rerank.mjs,
// 2026-07-14: fixes 8 of 18 top-1 misses, breaks 0 of 61 correct).
const RERANK_TOP_K = 12;
const RERANK_SIM_BAND = 0.12;
const RERANK_COVERAGE_MARGIN = 0.25;

function classNameSku(className: string): string {
  // foto-kemasan-v2 class names are "<SKU> <NAME...>"
  return (className || "").trim().split(/\s+/)[0] || "";
}

function tokenizeName(name: string): string[] {
  return name.toUpperCase().split(/[^A-Z0-9]+/).filter(t => t.length >= 2);
}

function withinEditDistance1(a: string, b: string): boolean {
  if (a === b) return true;
  const la = a.length, lb = b.length;
  if (Math.abs(la - lb) > 1) return false;
  if (la === lb) {
    let diff = 0;
    for (let i = 0; i < la; i++) if (a[i] !== b[i]) diff++;
    return diff <= 1;
  }
  const [s, l] = la < lb ? [a, b] : [b, a];
  let i = 0, j = 0, skipped = false;
  while (i < s.length && j < l.length) {
    if (s[i] === l[j]) { i++; j++; }
    else if (!skipped) { skipped = true; j++; }
    else return false;
  }
  return true;
}

interface OcrTextIndex { squashed: string; tokens: Set<string>; }

function buildOcrTextIndex(textLines: string[]): OcrTextIndex {
  const joined = textLines.join(" ").toUpperCase();
  return {
    squashed: joined.replace(/[^A-Z0-9]/g, ""),
    tokens: new Set(tokenizeName(joined))
  };
}

function tokenFoundInOcr(token: string, ocr: OcrTextIndex): boolean {
  if (token.length >= 4 && ocr.squashed.includes(token)) return true;
  if (ocr.tokens.has(token)) return true;
  if (token.length >= 5) {
    for (const t of ocr.tokens) {
      if (Math.abs(t.length - token.length) <= 1 && withinEditDistance1(token, t)) return true;
    }
  }
  return false;
}

// Returns the class name of the best candidate after OCR-evidence
// re-ranking (the classifier's top-1 unless a close band-mate has clearly
// stronger printed-text evidence).
function rerankClassCandidates(
  allProbabilities: Array<{ name: string; confidence: number }>,
  textLines: string[]
): string {
  if (!allProbabilities.length) return "";
  const top1Sim = allProbabilities[0].confidence;
  const band = allProbabilities
    .slice(0, RERANK_TOP_K)
    .filter(p => p.confidence >= top1Sim - RERANK_SIM_BAND);
  if (band.length <= 1 || !textLines.length) return allProbabilities[0].name;

  const ocrIdx = buildOcrTextIndex(textLines);
  const cands = band.map(p => {
    const sku = classNameSku(p.name);
    return { name: p.name, tokens: new Set(tokenizeName(p.name.replace(sku, ""))), coverage: 0 };
  });
  const tokenCounts = new Map<string, number>();
  for (const c of cands) {
    for (const tok of c.tokens) tokenCounts.set(tok, (tokenCounts.get(tok) || 0) + 1);
  }
  for (const c of cands) {
    let matched = 0, total = 0;
    for (const tok of c.tokens) {
      const nWith = tokenCounts.get(tok) || 1;
      if (nWith >= cands.length) continue; // shared by all band-mates -> no signal
      const w = 1 / nWith;
      total += w;
      if (tokenFoundInOcr(tok, ocrIdx)) matched += w;
    }
    c.coverage = total > 0 ? matched / total : 0;
  }

  let chosen = cands[0];
  for (const c of cands.slice(1)) {
    if (c.coverage >= chosen.coverage + RERANK_COVERAGE_MARGIN) chosen = c;
  }
  if (chosen !== cands[0]) {
    console.log(`[Rerank] OCR evidence overrode classifier top-1 "${cands[0].name}" -> "${chosen.name}" (coverage ${cands[0].coverage.toFixed(2)} vs ${chosen.coverage.toFixed(2)})`);
  }
  return chosen.name;
}

// Shared by the classic /api/scan-pfm dev route and the authenticated
// /api/v1/scan-product route: calls the Python classifier, then matches the
// result against sku_master, returning the top-5 candidates.
export async function classifyAndMatchProduct(imageBase64: string): Promise<ProductScanResult> {
  const pyServerUrl = process.env.CLASSIFIER_SERVER_URL || "http://paddleocr-pipeline-api:8120/classify-ocr";

  const response = await fetch(pyServerUrl, {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ image_base64: imageBase64 }),
    signal: AbortSignal.timeout(PIPELINE_TIMEOUT_MS)
  });

  if (!response.ok) {
    const errText = await response.text();
    throw new ClassifierError(response.status, `Classifier service error: ${errText}`);
  }

  const data = await response.json();

  const dbRes = await query("SELECT no_sku, nama_item FROM sku_master");
  const skuMasterList = dbRes.rows.map(row => ({
    no_sku: row.no_sku,
    nama_item: row.nama_item
  }));

  const extractedSku = data.ocr?.extracted_sku || "";

  // Re-rank the classifier's close candidates using OCR'd package text, then
  // map the winner straight to its sku_master row by the SKU prefix embedded
  // in the class name. The old approach (Levenshtein between top-1 class name
  // and every master nama_item) lost classifier-correct results whenever a
  // *different* SKU's master name happened to be textually closer.
  const rerankedName = rerankClassCandidates(
    data.classification?.all_probabilities || [],
    data.ocr?.text_lines || []
  ) || data.classification?.top1_name || "";
  const rerankedSku = classNameSku(rerankedName);

  const matchedList: SkuMatch[] = skuMasterList.map(sku => {
    const yoloSim = rerankedName ? getStringSimilarity(sku.nama_item, rerankedName) : 0;

    const cleanMasterSku = sku.no_sku.trim();
    const cleanExtractedSku = extractedSku.trim();
    const isSkuMatch = cleanExtractedSku && cleanMasterSku === cleanExtractedSku;
    const isClassifierPick = rerankedSku && cleanMasterSku === rerankedSku;

    const score = isSkuMatch ? 1.0 : isClassifierPick ? 0.995 : yoloSim;

    return {
      no_sku: sku.no_sku,
      nama_item: sku.nama_item,
      score,
      yoloSimilarity: yoloSim,
      isBestMatch: false
    };
  });

  matchedList.sort((a, b) => b.score - a.score);

  const possibleMatches = matchedList.slice(0, 5).filter(m => m.score > 0.1);
  if (possibleMatches.length > 0) {
    possibleMatches[0].isBestMatch = true;
  }

  return {
    classification: data.classification,
    ocr: data.ocr,
    possibleMatches
  };
}