| """Rule-based PO parser — fallback when the 7B model is unavailable or returns bad JSON.""" |
|
|
| import re |
| from typing import Optional |
|
|
| from data import SAMPLE_CATALOG |
|
|
| |
| PRODUCT_ALIASES: dict[str, str] = { |
| "kucing hologram": "Holographic Cat Sticker", |
| "kucing holo": "Holographic Cat Sticker", |
| "holographic cat": "Holographic Cat Sticker", |
| "stiker kucing hologram": "Holographic Cat Sticker", |
| "sakura die-cut": "Sakura Die-Cut Sticker", |
| "stiker sakura": "Sakura Die-Cut Sticker", |
| "sakura": "Sakura Die-Cut Sticker", |
| "cherry blossom": "Cherry Blossom Sticker", |
| "rainbow unicorn": "Rainbow Unicorn Sticker", |
| "unicorn": "Rainbow Unicorn Sticker", |
| "boba tea": "Kawaii Boba Tea Sticker", |
| "boba": "Kawaii Boba Tea Sticker", |
| "sushi kawaii": "Kawaii Sushi Sticker", |
| "sushi": "Kawaii Sushi Sticker", |
| "ramen kawaii": "Kawaii Ramen Sticker", |
| "ramen": "Kawaii Ramen Sticker", |
| "floral wreath": "Floral Wreath Sticker", |
| "butterfly garden": "Butterfly Garden Sticker", |
| "vintage bicycle": "Vintage Bicycle Sticker", |
| "coffee cup": "Coffee Cup Sticker", |
| "galaxy star": "Galaxy Star Sticker", |
| "monstera leaf": "Monstera Leaf Sticker", |
| "monstera": "Monstera Leaf Sticker", |
| "batik pattern": "Batik Pattern Sticker", |
| "batik": "Batik Pattern Sticker", |
| "koi fish": "Koi Fish Sticker", |
| "koi": "Koi Fish Sticker", |
| "borobudur": "Borobudur Temple Sticker", |
| "wayang": "Wayang Shadow Sticker", |
| "gamelan": "Gamelan Sticker", |
| "penari jawa": "Javanese Dancer Sticker", |
| "javanese dancer": "Javanese Dancer Sticker", |
| "mushroom forest": "Mushroom Forest Sticker", |
| "space astronaut": "Space Astronaut Sticker", |
| "mountain landscape": "Mountain Landscape Sticker", |
| "ocean wave": "Ocean Wave Sticker", |
| "cactus succulent": "Cactus Succulent Sticker", |
| "cute dog": "Cute Dog Sticker", |
| "cute rabbit": "Cute Rabbit Sticker", |
| "panda bear": "Panda Bear Sticker", |
| "retro cassette": "Retro Cassette Sticker", |
| "tropical bird": "Tropical Bird Sticker", |
| "komodo dragon": "Komodo Dragon Sticker", |
| } |
|
|
| _CATALOG_LOWER = {p.lower(): p for p in SAMPLE_CATALOG} |
|
|
|
|
| def _normalize_product(raw: str) -> str: |
| cleaned = re.sub(r"^[\-\*\d\.\)\s]+", "", raw.strip()) |
| cleaned = re.sub(r"\s*(pcs|pc|lembar|sheet|sheets|buah|unit)\.?\s*$", "", cleaned, flags=re.I) |
| cleaned = cleaned.strip(" ,;:") |
| if not cleaned: |
| return "" |
|
|
| key = cleaned.lower() |
| if key in _CATALOG_LOWER: |
| return _CATALOG_LOWER[key] |
|
|
| for alias, canonical in sorted(PRODUCT_ALIASES.items(), key=lambda x: -len(x[0])): |
| if alias in key or key in alias: |
| return canonical |
|
|
| for cat_lower, canonical in _CATALOG_LOWER.items(): |
| if cat_lower in key or key in cat_lower: |
| return canonical |
|
|
| return cleaned.title() |
|
|
|
|
| def _extract_qty(text: str) -> int: |
| m = re.search(r"(\d+)\s*(?:pcs|pc|lembar|sheet|sheets|buah|unit)?\.?\s*$", text, re.I) |
| if m: |
| return int(m.group(1)) |
| m = re.search(r"x\s*(\d+)\s*$", text, re.I) |
| if m: |
| return int(m.group(1)) |
| m = re.search(r"\b(\d+)\b", text) |
| return int(m.group(1)) if m else 0 |
|
|
|
|
| def _parse_line(line: str) -> Optional[dict]: |
| line = line.strip() |
| if not line or len(line) < 3: |
| return None |
| if re.match(r"^(item|product|qty|quantity|no\.?|#)\b", line, re.I): |
| return None |
| if re.match(r"^(pesanan|po\s*#|monthly|tolong|please|note|hai|makasih|thanks)", line, re.I): |
| return None |
|
|
| |
| m = re.match(r"^(.+?)\s*[x×]\s*(\d+)\s*$", line, re.I) |
| if m: |
| product = _normalize_product(m.group(1)) |
| return {"product": product, "quantity": int(m.group(2)), "notes": ""} if product else None |
|
|
| m = re.match(r"^(.+?)\s*\|\s*(\d+)\s*$", line) |
| if m: |
| product = _normalize_product(m.group(1)) |
| return {"product": product, "quantity": int(m.group(2)), "notes": ""} if product else None |
|
|
| |
| m = re.match(r"^(.+?)[,\s]+(\d+)\s*(?:pcs|pc)?\.?\s*$", line, re.I) |
| if m: |
| product = _normalize_product(m.group(1)) |
| return {"product": product, "quantity": int(m.group(2)), "notes": ""} if product else None |
|
|
| |
| if "," not in line and re.search(r"\d", line): |
| qty = _extract_qty(line) |
| if qty > 0: |
| product_part = re.sub(r"\d+.*$", "", line).strip(" ,-") |
| product = _normalize_product(product_part) |
| if product: |
| return {"product": product, "quantity": qty, "notes": ""} |
|
|
| return None |
|
|
|
|
| def _parse_comma_list(text: str) -> list[dict]: |
| items: list[dict] = [] |
| for chunk in re.split(r"[,;\n]+", text): |
| chunk = chunk.strip() |
| if not chunk: |
| continue |
| m = re.match(r"^(.+?)\s+(\d+)\s*$", chunk) |
| if m: |
| product = _normalize_product(m.group(1)) |
| if product: |
| items.append({"product": product, "quantity": int(m.group(2)), "notes": ""}) |
| return items |
|
|
|
|
| def parse_po_fallback(po_text: str) -> dict: |
| """Extract items from messy PO text without an LLM.""" |
| items: list[dict] = [] |
| seen: set[tuple[str, int]] = set() |
| store_notes: list[str] = [] |
|
|
| for line in po_text.splitlines(): |
| parsed = _parse_line(line) |
| if parsed and parsed["quantity"] > 0: |
| key = (parsed["product"], parsed["quantity"]) |
| if key not in seen: |
| seen.add(key) |
| items.append(parsed) |
| elif line.strip() and re.match(r"^(note|catatan|tolong|please|ship|kirim)", line.strip(), re.I): |
| store_notes.append(line.strip()) |
|
|
| if len(items) < 2: |
| items.extend(_parse_comma_list(po_text)) |
|
|
| |
| merged: dict[str, dict] = {} |
| for it in items: |
| name = it["product"] |
| if name in merged: |
| merged[name]["quantity"] += it["quantity"] |
| else: |
| merged[name] = dict(it) |
|
|
| return { |
| "items": list(merged.values()), |
| "store_notes": " ".join(store_notes)[:200], |
| } |
|
|
