Build Giant item enricher

enrich_giant.py

@@ -0,0 +1,426 @@
+import csv
+import json
+import re
+from decimal import Decimal, InvalidOperation, ROUND_HALF_UP
+from pathlib import Path
+
+import click
+
+
+PARSER_VERSION = "giant-enrich-v1"
+RETAILER = "giant"
+DEFAULT_INPUT_DIR = Path("giant_output/raw")
+DEFAULT_OUTPUT_CSV = Path("giant_output/items_enriched.csv")
+
+OUTPUT_FIELDS = [
+    "retailer",
+    "order_id",
+    "line_no",
+    "observed_item_key",
+    "order_date",
+    "pod_id",
+    "item_name",
+    "upc",
+    "category_id",
+    "category",
+    "qty",
+    "unit",
+    "unit_price",
+    "line_total",
+    "picked_weight",
+    "mvp_savings",
+    "reward_savings",
+    "coupon_savings",
+    "coupon_price",
+    "image_url",
+    "raw_order_path",
+    "item_name_norm",
+    "brand_guess",
+    "variant",
+    "size_value",
+    "size_unit",
+    "pack_qty",
+    "measure_type",
+    "is_store_brand",
+    "is_fee",
+    "price_per_each",
+    "price_per_lb",
+    "price_per_oz",
+    "parse_version",
+    "parse_notes",
+]
+
+STORE_BRAND_PREFIXES = {
+    "SB": "SB",
+    "NP": "NP",
+}
+
+ABBREVIATIONS = {
+    "APPLE": "APPLE",
+    "APPLES": "APPLES",
+    "APLE": "APPLE",
+    "BASIL": "BASIL",
+    "BLK": "BLACK",
+    "BNLS": "BONELESS",
+    "BRWN": "BROWN",
+    "CARROTS": "CARROTS",
+    "CHDR": "CHEDDAR",
+    "CHICKEN": "CHICKEN",
+    "CHOC": "CHOCOLATE",
+    "CHS": "CHEESE",
+    "CHSE": "CHEESE",
+    "CHZ": "CHEESE",
+    "CILANTRO": "CILANTRO",
+    "CKI": "COOKIE",
+    "CRSHD": "CRUSHED",
+    "FLR": "FLOUR",
+    "FRSH": "FRESH",
+    "GALA": "GALA",
+    "GRAHM": "GRAHAM",
+    "HOT": "HOT",
+    "HRSRDSH": "HORSERADISH",
+    "IMP": "IMPORTED",
+    "IQF": "IQF",
+    "LENTILS": "LENTILS",
+    "LG": "LARGE",
+    "MLK": "MILK",
+    "MSTRD": "MUSTARD",
+    "ONION": "ONION",
+    "ORG": "ORGANIC",
+    "PEPPER": "PEPPER",
+    "PEPPERS": "PEPPERS",
+    "POT": "POTATO",
+    "POTATO": "POTATO",
+    "PPR": "PEPPER",
+    "RICOTTA": "RICOTTA",
+    "ROASTER": "ROASTER",
+    "ROTINI": "ROTINI",
+    "SCE": "SAUCE",
+    "SLC": "SLICED",
+    "SPINCH": "SPINACH",
+    "SPNC": "SPINACH",
+    "SPINACH": "SPINACH",
+    "SQZ": "SQUEEZE",
+    "SWT": "SWEET",
+    "THYME": "THYME",
+    "TOM": "TOMATO",
+    "TOMS": "TOMATOES",
+    "TRTL": "TORTILLA",
+    "VEG": "VEGETABLE",
+    "VINEGAR": "VINEGAR",
+    "WHT": "WHITE",
+    "WHOLE": "WHOLE",
+    "YLW": "YELLOW",
+    "YLWGLD": "YELLOW_GOLD",
+}
+
+FEE_PATTERNS = [
+    re.compile(r"\bBAG CHARGE\b"),
+    re.compile(r"\bDISC AT TOTAL\b"),
+]
+
+SIZE_RE = re.compile(r"(?<![A-Z0-9])(\d+(?:\.\d+)?)(?:\s*)(OZ|Z|LB|LBS|ML|L|FZ|FL OZ|QT|PT|GAL|GA)\b")
+PACK_RE = re.compile(r"(?<![A-Z0-9])(\d+(?:\.\d+)?)(?:\s*)(CT|PK|PKG|PACK)\b")
+
+
+def to_decimal(value):
+    if value in ("", None):
+        return None
+
+    try:
+        return Decimal(str(value))
+    except (InvalidOperation, ValueError):
+        return None
+
+
+def format_decimal(value, places=4):
+    if value is None:
+        return ""
+
+    quant = Decimal("1").scaleb(-places)
+    normalized = value.quantize(quant, rounding=ROUND_HALF_UP).normalize()
+    return format(normalized, "f")
+
+
+def normalize_whitespace(value):
+    return " ".join(str(value or "").strip().split())
+
+
+def clean_item_name(name):
+    cleaned = normalize_whitespace(name).upper()
+    cleaned = re.sub(r"^\+", "", cleaned)
+    cleaned = re.sub(r"^PLU#\d+\s*", "", cleaned)
+    cleaned = cleaned.replace("#", " ")
+    return normalize_whitespace(cleaned)
+
+
+def extract_store_brand_prefix(cleaned_name):
+    for prefix, brand in STORE_BRAND_PREFIXES.items():
+        if cleaned_name == prefix or cleaned_name.startswith(f"{prefix} "):
+            return prefix, brand
+    return "", ""
+
+
+def extract_image_url(item):
+    image = item.get("image")
+    if isinstance(image, dict):
+        for key in ["xlarge", "large", "medium", "small"]:
+            value = image.get(key)
+            if value:
+                return value
+    if isinstance(image, str):
+        return image
+    return ""
+
+
+def parse_size_and_pack(cleaned_name):
+    size_value = ""
+    size_unit = ""
+    pack_qty = ""
+
+    size_matches = list(SIZE_RE.finditer(cleaned_name))
+    if size_matches:
+        match = size_matches[-1]
+        size_value = normalize_number(match.group(1))
+        size_unit = normalize_unit(match.group(2))
+
+    pack_matches = list(PACK_RE.finditer(cleaned_name))
+    if pack_matches:
+        match = pack_matches[-1]
+        pack_qty = normalize_number(match.group(1))
+
+    return size_value, size_unit, pack_qty
+
+
+def normalize_number(value):
+    decimal = to_decimal(value)
+    if decimal is None:
+        return ""
+    return format(decimal.normalize(), "f")
+
+
+def normalize_unit(unit):
+    collapsed = normalize_whitespace(unit).upper()
+    return {
+        "Z": "oz",
+        "OZ": "oz",
+        "FZ": "fl_oz",
+        "FL OZ": "fl_oz",
+        "LB": "lb",
+        "LBS": "lb",
+        "ML": "ml",
+        "L": "l",
+        "QT": "qt",
+        "PT": "pt",
+        "GAL": "gal",
+        "GA": "gal",
+    }.get(collapsed, collapsed.lower())
+
+
+def strip_measure_tokens(cleaned_name):
+    without_sizes = SIZE_RE.sub(" ", cleaned_name)
+    without_measures = PACK_RE.sub(" ", without_sizes)
+    return normalize_whitespace(without_measures)
+
+
+def expand_token(token):
+    return ABBREVIATIONS.get(token, token)
+
+
+def normalize_item_name(cleaned_name):
+    prefix, _brand = extract_store_brand_prefix(cleaned_name)
+    base = cleaned_name
+    if prefix:
+        base = normalize_whitespace(base[len(prefix):])
+
+    base = strip_measure_tokens(base)
+    expanded_tokens = [expand_token(token) for token in base.split()]
+    expanded = " ".join(token for token in expanded_tokens if token)
+    return normalize_whitespace(expanded)
+
+
+def guess_measure_type(item, size_unit, pack_qty):
+    unit = normalize_whitespace(item.get("lbEachCd")).upper()
+    picked_weight = to_decimal(item.get("totalPickedWeight"))
+    qty = to_decimal(item.get("shipQy"))
+
+    if unit == "LB" or (picked_weight is not None and picked_weight > 0 and unit != "EA"):
+        return "weight"
+    if size_unit in {"lb", "oz"}:
+        return "weight"
+    if size_unit in {"ml", "l", "qt", "pt", "gal", "fl_oz"}:
+        return "volume"
+    if pack_qty:
+        return "count"
+    if unit == "EA" or (qty is not None and qty > 0):
+        return "each"
+    return ""
+
+
+def is_fee_item(cleaned_name):
+    return any(pattern.search(cleaned_name) for pattern in FEE_PATTERNS)
+
+
+def derive_prices(item, measure_type, size_value="", size_unit="", pack_qty=""):
+    qty = to_decimal(item.get("shipQy"))
+    line_total = to_decimal(item.get("groceryAmount"))
+    picked_weight = to_decimal(item.get("totalPickedWeight"))
+    parsed_size = to_decimal(size_value)
+    parsed_pack = to_decimal(pack_qty) or Decimal("1")
+
+    price_per_each = ""
+    price_per_lb = ""
+    price_per_oz = ""
+
+    if line_total is None:
+        return price_per_each, price_per_lb, price_per_oz
+
+    if measure_type == "each" and qty not in (None, Decimal("0")):
+        price_per_each = format_decimal(line_total / qty)
+
+    if measure_type == "count" and qty not in (None, Decimal("0")):
+        price_per_each = format_decimal(line_total / qty)
+
+    if measure_type == "weight" and picked_weight not in (None, Decimal("0")):
+        per_lb = line_total / picked_weight
+        price_per_lb = format_decimal(per_lb)
+        price_per_oz = format_decimal(per_lb / Decimal("16"))
+        return price_per_each, price_per_lb, price_per_oz
+
+    if measure_type == "weight" and parsed_size not in (None, Decimal("0")) and qty not in (None, Decimal("0")):
+        total_units = qty * parsed_pack * parsed_size
+        if size_unit == "lb":
+            per_lb = line_total / total_units
+            price_per_lb = format_decimal(per_lb)
+            price_per_oz = format_decimal(per_lb / Decimal("16"))
+        elif size_unit == "oz":
+            per_oz = line_total / total_units
+            price_per_oz = format_decimal(per_oz)
+            price_per_lb = format_decimal(per_oz * Decimal("16"))
+
+    return price_per_each, price_per_lb, price_per_oz
+
+
+def parse_item(order_id, order_date, raw_path, line_no, item):
+    cleaned_name = clean_item_name(item.get("itemName", ""))
+    size_value, size_unit, pack_qty = parse_size_and_pack(cleaned_name)
+    prefix, brand_guess = extract_store_brand_prefix(cleaned_name)
+    normalized_name = normalize_item_name(cleaned_name)
+    measure_type = guess_measure_type(item, size_unit, pack_qty)
+    price_per_each, price_per_lb, price_per_oz = derive_prices(
+        item,
+        measure_type,
+        size_value=size_value,
+        size_unit=size_unit,
+        pack_qty=pack_qty,
+    )
+    is_fee = is_fee_item(cleaned_name)
+    parse_notes = []
+
+    if prefix:
+        parse_notes.append(f"store_brand_prefix={prefix}")
+    if is_fee:
+        parse_notes.append("fee_item")
+    if size_value and not size_unit:
+        parse_notes.append("size_without_unit")
+
+    return {
+        "retailer": RETAILER,
+        "order_id": str(order_id),
+        "line_no": str(line_no),
+        "observed_item_key": f"{RETAILER}:{order_id}:{line_no}",
+        "order_date": normalize_whitespace(order_date),
+        "pod_id": stringify(item.get("podId")),
+        "item_name": stringify(item.get("itemName")),
+        "upc": stringify(item.get("primUpcCd")),
+        "category_id": stringify(item.get("categoryId")),
+        "category": stringify(item.get("categoryDesc")),
+        "qty": stringify(item.get("shipQy")),
+        "unit": stringify(item.get("lbEachCd")),
+        "unit_price": stringify(item.get("unitPrice")),
+        "line_total": stringify(item.get("groceryAmount")),
+        "picked_weight": stringify(item.get("totalPickedWeight")),
+        "mvp_savings": stringify(item.get("mvpSavings")),
+        "reward_savings": stringify(item.get("rewardSavings")),
+        "coupon_savings": stringify(item.get("couponSavings")),
+        "coupon_price": stringify(item.get("couponPrice")),
+        "image_url": extract_image_url(item),
+        "raw_order_path": raw_path.as_posix(),
+        "item_name_norm": normalized_name,
+        "brand_guess": brand_guess,
+        "variant": "",
+        "size_value": size_value,
+        "size_unit": size_unit,
+        "pack_qty": pack_qty,
+        "measure_type": measure_type,
+        "is_store_brand": "true" if bool(prefix) else "false",
+        "is_fee": "true" if is_fee else "false",
+        "price_per_each": price_per_each,
+        "price_per_lb": price_per_lb,
+        "price_per_oz": price_per_oz,
+        "parse_version": PARSER_VERSION,
+        "parse_notes": ";".join(parse_notes),
+    }
+
+
+def stringify(value):
+    if value is None:
+        return ""
+    return str(value)
+
+
+def iter_order_rows(raw_dir):
+    for path in sorted(raw_dir.glob("*.json")):
+        if path.name == "history.json":
+            continue
+
+        payload = json.loads(path.read_text(encoding="utf-8"))
+        order_id = payload.get("orderId", path.stem)
+        order_date = payload.get("orderDate", "")
+
+        for line_no, item in enumerate(payload.get("items", []), start=1):
+            yield parse_item(order_id, order_date, path, line_no, item)
+
+
+def build_items_enriched(raw_dir):
+    rows = list(iter_order_rows(raw_dir))
+    rows.sort(key=lambda row: (row["order_date"], row["order_id"], int(row["line_no"])))
+    return rows
+
+
+def write_csv(path, rows):
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", newline="", encoding="utf-8") as handle:
+        writer = csv.DictWriter(handle, fieldnames=OUTPUT_FIELDS)
+        writer.writeheader()
+        writer.writerows(rows)
+
+
+@click.command()
+@click.option(
+    "--input-dir",
+    default=str(DEFAULT_INPUT_DIR),
+    show_default=True,
+    help="Directory containing Giant raw order json files.",
+)
+@click.option(
+    "--output-csv",
+    default=str(DEFAULT_OUTPUT_CSV),
+    show_default=True,
+    help="CSV path for enriched Giant item rows.",
+)
+def main(input_dir, output_csv):
+    raw_dir = Path(input_dir)
+    output_path = Path(output_csv)
+
+    if not raw_dir.exists():
+        raise click.ClickException(f"input dir does not exist: {raw_dir}")
+
+    rows = build_items_enriched(raw_dir)
+    write_csv(output_path, rows)
+
+    click.echo(f"wrote {len(rows)} rows to {output_path}")
+
+
+if __name__ == "__main__":
+    main()

pm/tasks.org

@@ -32,11 +32,11 @@
 - keep schema minimal but extensible
 
 ** evidence
-- commit:
+- commit: `42dbae1` on branch `cx`
 - tests: reviewed `giant_output/raw/history.json`, one sample raw order json, `giant_output/orders.csv`, `giant_output/items.csv`; documented schemas in `pm/data-model.org`
 - date: 2026-03-15
 
-* [ ] t1.3: build giant parser/enricher from raw json (2-4 commits)
+* [X] t1.3: build giant parser/enricher from raw json (2-4 commits)
 ** acceptance criteria
 - parser reads giant raw order json files
 - outputs `items_enriched.csv`
@@ -55,8 +55,8 @@
 
 ** evidence
 - commit:
-- tests:
+- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python enrich_giant.py`; verified `giant_output/items_enriched.csv` on real raw data
-- date:
+- date: 2026-03-16
 
 * [ ] t1.4: generate observed-product layer from enriched items (2-3 commits)
 

tests/test_enrich_giant.py

@@ -0,0 +1,190 @@
+import csv
+import json
+import tempfile
+import unittest
+from pathlib import Path
+
+import enrich_giant
+
+
+class EnrichGiantTests(unittest.TestCase):
+    def test_parse_size_and_pack_handles_pack_and_weight_tokens(self):
+        size_value, size_unit, pack_qty = enrich_giant.parse_size_and_pack(
+            "COKE CHERRY 6PK 7.5Z"
+        )
+
+        self.assertEqual("7.5", size_value)
+        self.assertEqual("oz", size_unit)
+        self.assertEqual("6", pack_qty)
+
+    def test_parse_item_marks_store_brand_fee_and_weight_prices(self):
+        row = enrich_giant.parse_item(
+            order_id="abc123",
+            order_date="2026-03-01",
+            raw_path=Path("raw/abc123.json"),
+            line_no=1,
+            item={
+                "podId": 1,
+                "shipQy": 1,
+                "totalPickedWeight": 2,
+                "unitPrice": 3.98,
+                "itemName": "+SB GALA APPLE 5 LB",
+                "lbEachCd": "LB",
+                "groceryAmount": 3.98,
+                "primUpcCd": "111",
+                "mvpSavings": 0,
+                "rewardSavings": 0,
+                "couponSavings": 0,
+                "couponPrice": 0,
+                "categoryId": "1",
+                "categoryDesc": "Grocery",
+                "image": {"large": "https://example.test/apple.jpg"},
+            },
+        )
+
+        self.assertEqual("SB", row["brand_guess"])
+        self.assertEqual("GALA APPLE", row["item_name_norm"])
+        self.assertEqual("5", row["size_value"])
+        self.assertEqual("lb", row["size_unit"])
+        self.assertEqual("weight", row["measure_type"])
+        self.assertEqual("true", row["is_store_brand"])
+        self.assertEqual("1.99", row["price_per_lb"])
+        self.assertEqual("0.1244", row["price_per_oz"])
+        self.assertEqual("https://example.test/apple.jpg", row["image_url"])
+
+        fee_row = enrich_giant.parse_item(
+            order_id="abc123",
+            order_date="2026-03-01",
+            raw_path=Path("raw/abc123.json"),
+            line_no=2,
+            item={
+                "podId": 2,
+                "shipQy": 1,
+                "totalPickedWeight": 0,
+                "unitPrice": 0.05,
+                "itemName": "GL BAG CHARGE",
+                "lbEachCd": "EA",
+                "groceryAmount": 0.05,
+                "primUpcCd": "",
+                "mvpSavings": 0,
+                "rewardSavings": 0,
+                "couponSavings": 0,
+                "couponPrice": 0,
+                "categoryId": "1",
+                "categoryDesc": "Grocery",
+            },
+        )
+
+        self.assertEqual("true", fee_row["is_fee"])
+        self.assertEqual("GL BAG CHARGE", fee_row["item_name_norm"])
+
+    def test_parse_item_derives_packaged_weight_prices_from_size_tokens(self):
+        row = enrich_giant.parse_item(
+            order_id="abc123",
+            order_date="2026-03-01",
+            raw_path=Path("raw/abc123.json"),
+            line_no=1,
+            item={
+                "podId": 1,
+                "shipQy": 2,
+                "totalPickedWeight": 0,
+                "unitPrice": 3.0,
+                "itemName": "PEPSI 6PK 7.5Z",
+                "lbEachCd": "EA",
+                "groceryAmount": 6.0,
+                "primUpcCd": "111",
+                "mvpSavings": 0,
+                "rewardSavings": 0,
+                "couponSavings": 0,
+                "couponPrice": 0,
+                "categoryId": "1",
+                "categoryDesc": "Grocery",
+            },
+        )
+
+        self.assertEqual("weight", row["measure_type"])
+        self.assertEqual("6", row["pack_qty"])
+        self.assertEqual("7.5", row["size_value"])
+        self.assertEqual("0.0667", row["price_per_oz"])
+        self.assertEqual("1.0667", row["price_per_lb"])
+
+    def test_build_items_enriched_reads_raw_order_files_and_writes_csv(self):
+        with tempfile.TemporaryDirectory() as tmpdir:
+            raw_dir = Path(tmpdir) / "raw"
+            raw_dir.mkdir()
+            (raw_dir / "history.json").write_text("{}", encoding="utf-8")
+            (raw_dir / "order-2.json").write_text(
+                json.dumps(
+                    {
+                        "orderId": "order-2",
+                        "orderDate": "2026-03-02",
+                        "items": [
+                            {
+                                "podId": 20,
+                                "shipQy": 1,
+                                "totalPickedWeight": 0,
+                                "unitPrice": 2.99,
+                                "itemName": "SB ROTINI 16Z",
+                                "lbEachCd": "EA",
+                                "groceryAmount": 2.99,
+                                "primUpcCd": "222",
+                                "mvpSavings": 0,
+                                "rewardSavings": 0,
+                                "couponSavings": 0,
+                                "couponPrice": 0,
+                                "categoryId": "1",
+                                "categoryDesc": "Grocery",
+                                "image": {"small": "https://example.test/rotini.jpg"},
+                            }
+                        ],
+                    }
+                ),
+                encoding="utf-8",
+            )
+            (raw_dir / "order-1.json").write_text(
+                json.dumps(
+                    {
+                        "orderId": "order-1",
+                        "orderDate": "2026-03-01",
+                        "items": [
+                            {
+                                "podId": 10,
+                                "shipQy": 2,
+                                "totalPickedWeight": 0,
+                                "unitPrice": 1.5,
+                                "itemName": "PEPSI 6PK 7.5Z",
+                                "lbEachCd": "EA",
+                                "groceryAmount": 3.0,
+                                "primUpcCd": "111",
+                                "mvpSavings": 0,
+                                "rewardSavings": 0,
+                                "couponSavings": 0,
+                                "couponPrice": 0,
+                                "categoryId": "1",
+                                "categoryDesc": "Grocery",
+                            }
+                        ],
+                    }
+                ),
+                encoding="utf-8",
+            )
+
+            rows = enrich_giant.build_items_enriched(raw_dir)
+            output_csv = Path(tmpdir) / "items_enriched.csv"
+            enrich_giant.write_csv(output_csv, rows)
+
+            self.assertEqual(["order-1", "order-2"], [row["order_id"] for row in rows])
+            self.assertEqual("PEPSI", rows[0]["item_name_norm"])
+            self.assertEqual("6", rows[0]["pack_qty"])
+            self.assertEqual("7.5", rows[0]["size_value"])
+            self.assertEqual("true", rows[1]["is_store_brand"])
+
+            with output_csv.open(newline="", encoding="utf-8") as handle:
+                written_rows = list(csv.DictReader(handle))
+
+            self.assertEqual(2, len(written_rows))
+            self.assertEqual(enrich_giant.OUTPUT_FIELDS, list(written_rows[0].keys()))
+
+
+if __name__ == "__main__":
+    unittest.main()