feat(flyer-import): integrate AI-based flyer parsing with image support

- Add support for PNG, JPEG, and WebP image formats in flyer import - Replace external importer service with internal AI-based parsing pipeline - Add new services: TextExtractorService, AiFlyerParserService, FlyerNormalizerService - Integrate Mistral AI, pdf-parse, and tesseract.js dependencies - Add quality confidence indicators and warning panels in Flutter UI - Update package.json with new dependencies and transform ignore patterns - Add documentation for flyer importer system - Add Kilo AI planning file for Happy Island project BREAKING CHANGE: Flyer import now uses internal AI parsing instead of external importer service
2026-05-19 19:57:54 +02:00
parent 0ce1db5471
commit 187d0283a5
14 changed files with 1479 additions and 103 deletions
@@ -0,0 +1,158 @@
+import { Injectable, Logger } from '@nestjs/common';
+
+export interface NormalizedFlyerItem {
+  rawName: string;
+  normalizedName: string;
+  categoryHint: string | null;
+  price: number | null;
+  priceUnit: string | null;
+  comparisonPrice: number | null;
+  comparisonUnit: string | null;
+  offerText: string | null;
+  parseConfidence: number;
+  parseReasons: string[];
+}
+
+@Injectable()
+export class FlyerNormalizerService {
+  private readonly logger = new Logger(FlyerNormalizerService.name);
+
+  private readonly UNIT_MAPPING: Record<string, string> = {
+    // Längd
+    mm: 'mm',
+    cm: 'cm',
+    m: 'm',
+    // Vikt
+    mg: 'mg',
+    g: 'g',
+    hg: 'hg',
+    kg: 'kg',
+    ton: 'ton',
+    // Volym
+    ml: 'ml',
+    cl: 'cl',
+    dl: 'dl',
+    l: 'l',
+    // Övrigt
+    st: 'st',
+    styck: 'st',
+    stycke: 'st',
+    pkt: 'pkt',
+    paket: 'pkt',
+    fp: 'pkt',
+    förp: 'pkt',
+    förpackning: 'pkt',
+  };
+
+  /**
+   * Normaliserar en AI-parsad produktlista.
+   */
+  normalize(items: any[]): NormalizedFlyerItem[] {
+    if (!Array.isArray(items)) {
+      this.logger.warn('normalize() received non-array, returning empty list');
+      return [];
+    }
+
+    return items
+      .map((item, idx) => this.normalizeItem(item, idx))
+      .filter((item): item is NormalizedFlyerItem => item !== null);
+  }
+
+  private normalizeItem(item: any, index: number): NormalizedFlyerItem | null {
+    if (!item || typeof item !== 'object') {
+      this.logger.warn(`Item ${index} is not an object, skipping`);
+      return null;
+    }
+
+    const rawName = this.extractString(item.rawName) || this.extractString(item.name);
+    if (!rawName) {
+      this.logger.warn(`Item ${index} has no name, skipping`);
+      return null;
+    }
+
+    const normalizedName = this.extractString(item.normalizedName) || this.normalizeName(rawName);
+
+    return {
+      rawName,
+      normalizedName,
+      categoryHint: this.normalizeCategory(this.extractString(item.category)),
+      price: this.extractPrice(item.price),
+      priceUnit: this.normalizeUnit(this.extractString(item.unit)),
+      comparisonPrice: this.extractPrice(item.comparisonPrice),
+      comparisonUnit: this.normalizeUnit(this.extractString(item.comparisonUnit)),
+      offerText: this.normalizeOfferText(item.offer),
+      parseConfidence: item.confidence ?? 0.85,
+      parseReasons: Array.isArray(item.reasonCodes)
+        ? item.reasonCodes.map(String)
+        : ['normalized'],
+    };
+  }
+
+  private extractString(val: any): string | null {
+    if (typeof val === 'string') return val.trim() || null;
+    return null;
+  }
+
+  private extractPrice(val: any): number | null {
+    if (typeof val === 'number') return val;
+    if (typeof val === 'string') {
+      const num = parseFloat(val.replace(/,/g, '.'));
+      return isFinite(num) ? num : null;
+    }
+    return null;
+  }
+
+  private normalizeName(name: string): string {
+    return name
+      .toLowerCase()
+      .replace(/[^a-zåäö0-9\s]/g, '')
+      .replace(/\s+/g, ' ')
+      .trim();
+  }
+
+  private normalizeUnit(unit: string | null): string | null {
+    if (!unit) return null;
+
+    const cleaned = unit.trim().toLowerCase().replace(/\./g, '');
+    return this.UNIT_MAPPING[cleaned] ?? null;
+  }
+
+  private normalizeCategory(category: string | null): string | null {
+    if (!category) return null;
+
+    const normalized = category.trim().toLowerCase();
+
+    // Mappning av tänkta kategorivärdena från AI
+    const categoryMap: Record<string, string> = {
+      fisk: 'Fisk',
+      kött: 'Kött',
+      mejeri: 'Mejeri',
+      grönsaker: 'Grönsaker',
+      frukt: 'Frukt',
+      dryck: 'Dryck',
+      frukt_grönsaker: 'Frukt & Grönsaker',
+      fastfood: 'Fastfood',
+      bröd: 'Bröd',
+      fryst: 'Fryst',
+      godis: 'Godis',
+      pasta: 'Pasta',
+    };
+
+    return categoryMap[normalized] ?? null;
+  }
+
+  private normalizeOfferText(offer: any): string | null {
+    if (!offer) return null;
+
+    if (typeof offer === 'string') {
+      return offer.trim() || null;
+    }
+
+    if (Array.isArray(offer)) {
+      const joined = offer.map(String).filter(s => s.trim()).join(' ');
+      return joined || null;
+    }
+
+    return null;
+  }
+}