feat(products): Shopify dialect adapter — header detection + canonical mapping (SD-0002 §6.5.1, SLICE-8)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-12 02:19:15 -07:00
parent e16ec7cf94
commit daa237dd59
2 changed files with 114 additions and 0 deletions
@@ -0,0 +1,71 @@
+"""Shopify product-CSV adapter (INV-17): detect by header signature, map to canonical.
+
+The mapping is the §6.5.1 contract; the exhaustive table is pinned here and
+mirrored by tests/test_products_dialect_shopify.py + e2e/fixtures/shopify-export.csv.
+"""
+from __future__ import annotations
+
+from .models import KNOWN_COLUMNS
+
+# Shopify header -> canonical header (renames only; direct same-name columns pass
+# through via KNOWN_COLUMNS). Variant Grams carries a value transform (see codec).
+SHOPIFY_RENAME: dict[str, str] = {
+    "Body (HTML)": "Description",
+    "Product Category": "Google Product Category",
+    "Cost per item": "Variant Cost",
+    "Variant Grams": "Variant Weight",
+}
+
+# Canonical-named columns Shopify uses differently — must NOT pass through.
+# Type: Shopify's free-text type vs canonical's structural Type (§6.5.1, decision D).
+# Variant Weight Unit: superseded by the Variant Grams -> Variant Weight transform.
+SHOPIFY_DROP: frozenset[str] = frozenset({"Type", "Variant Weight Unit"})
+
+# Columns whose presence proves the file is a Shopify export (canonical never has them).
+_SIGNATURE: frozenset[str] = frozenset(
+    {
+        "Body (HTML)",
+        "Variant Grams",
+        "Cost per item",
+        "Variant Compare At Price",
+        "Variant Inventory Policy",
+        "Variant Fulfillment Service",
+        "Variant Requires Shipping",
+        "Variant Taxable",
+        "Gift Card",
+        "SEO Title",
+        "SEO Description",
+    }
+)
+
+
+def is_shopify_header(header: list[str]) -> bool:
+    """True iff the header carries a Shopify-only signature column. Otherwise the
+    file is treated as canonical — shared columns map identically, so an ambiguous
+    header never misparses (§7.4)."""
+    cols = {h.strip() for h in header}
+    if cols & _SIGNATURE:
+        return True
+    return any(c.startswith("Google Shopping / ") for c in cols)
+
+
+def map_shopify_header(header: list[str]) -> tuple[list[str | None], list[str]]:
+    """Return (mapped, not_imported): mapped[i] is the canonical name for header[i],
+    or None when that Shopify column has no canonical home; not_imported lists the
+    original Shopify names (in order) that were dropped — the preview warning."""
+    mapped: list[str | None] = []
+    not_imported: list[str] = []
+    for raw in header:
+        col = raw.strip()
+        if col in SHOPIFY_RENAME:
+            mapped.append(SHOPIFY_RENAME[col])
+        elif col in SHOPIFY_DROP:
+            mapped.append(None)
+            not_imported.append(col)
+        elif col in KNOWN_COLUMNS:
+            mapped.append(col)
+        else:
+            mapped.append(None)
+            if col:
+                not_imported.append(col)
+    return mapped, not_imported