backend/app/domains/products/codec.py

@@ -6,6 +6,7 @@ from __future__ import annotations
 import csv
 import io
 
+from .dialect_shopify import is_shopify_header, map_shopify_header
 from .errors import FileRejected
 from .models import KNOWN_COLUMNS, MAX_DATA_ROWS, MAX_FILE_BYTES, ParsedFile, Row
 
@@ -13,8 +14,8 @@ _REQUIRED_HEADER_COLUMNS = ("Handle", "Title")
 
 
 def detect_dialect(header: list[str]) -> str:
-    """The INV-17 seam: SLICE-8 recognizes Shopify's exact header set here."""
+    """The INV-17 seam: recognize Shopify's header set, else canonical (§6.5.1)."""
-    return "canonical"
+    return "shopify" if is_shopify_header(header) else "canonical"
 
 
 def parse_csv(data: bytes) -> ParsedFile:
@@ -31,19 +32,34 @@ def parse_csv(data: bytes) -> ParsedFile:
         except StopIteration:
             raise FileRejected("not_csv", "This file isn't readable as CSV.") from None
         header = [h.strip() for h in raw_header]
+        dialect = detect_dialect(header)
+
+        # INV-17: normalize the header to canonical names at the boundary. mapped[i]
+        # is the canonical name for header[i] (or None when that column has no
+        # canonical home); unknown is the not-imported warning list. Canonical files
+        # map to themselves; unknown columns are warned exactly as before.
+        if dialect == "shopify":
+            mapped, unknown = map_shopify_header(header)
+        else:
+            mapped = [c if c in KNOWN_COLUMNS else None for c in header]
+            unknown = [c for c in header if c and c not in KNOWN_COLUMNS]
+
         for col in _REQUIRED_HEADER_COLUMNS:
-            if col not in header:
+            if col not in mapped:
                 raise FileRejected(
                     "missing_required_column",
                     f"This file is missing the required column '{col}'.",
                 )
-        # First occurrence of a duplicated column wins.
+
+        # First occurrence of a duplicated canonical column wins.
         col_index: dict[str, int] = {}
-        for i, name in enumerate(header):
+        for i, name in enumerate(mapped):
             if name and name not in col_index:
                 col_index[name] = i
-        known_present = [c for c in col_index if c in KNOWN_COLUMNS]
+        # De-dup the warning list, order-preserving.
-        unknown = [c for c in col_index if c not in KNOWN_COLUMNS]
+        seen: set[str] = set()
+        unknown = [c for c in unknown if not (c in seen or seen.add(c))]
+
         rows: list[Row] = []
         for raw in reader:
             if not any(cell.strip() for cell in raw):
@@ -55,11 +71,12 @@ def parse_csv(data: bytes) -> ParsedFile:
                 )
             cells = {
                 c: (raw[col_index[c]].strip() if col_index[c] < len(raw) else "")
-                for c in known_present
+                for c in col_index
             }
+            # Shopify grams carry an implicit unit; canonical needs it explicit (§6.5.1).
+            if dialect == "shopify" and cells.get("Variant Weight"):
+                cells["Variant Weight Unit"] = "g"
             rows.append(Row(line_number=reader.line_num, cells=cells))
     except csv.Error:
         raise FileRejected("not_csv", "This file isn't readable as CSV.") from None
-    return ParsedFile(
+    return ParsedFile(dialect=dialect, header=header, unknown_columns=unknown, rows=rows)
-        dialect=detect_dialect(header), header=header, unknown_columns=unknown, rows=rows
-    )

backend/tests/test_products_codec.py

@@ -67,3 +67,29 @@ def test_missing_column_message_names_the_column():
     with pytest.raises(FileRejected) as exc:
         parse_csv(_csv("Handle,Vendor", "mug,Acme"))
     assert "'Title'" in exc.value.message
+
+
+def test_parse_detects_and_maps_shopify():
+    data = (
+        "Handle,Title,Body (HTML),Cost per item,Variant Price,Variant Grams,Type,Gift Card\n"
+        "mug,Moon Mug,<p>Grey</p>,9.50,18.00,300,Drinkware,false\n"
+    ).encode("utf-8")
+    parsed = parse_csv(data)
+    assert parsed.dialect == "shopify"
+    cells = parsed.rows[0].cells
+    assert cells["Description"] == "<p>Grey</p>"
+    assert cells["Variant Cost"] == "9.50"
+    assert cells["Variant Weight"] == "300"
+    assert cells["Variant Weight Unit"] == "g"  # synthesized
+    # Type (free-text) and Gift Card warned, never mapped:
+    assert "Type" in parsed.unknown_columns
+    assert "Gift Card" in parsed.unknown_columns
+    assert "product_type" not in str(cells)  # Type never reached canonical
+
+
+def test_parse_canonical_unchanged():
+    data = b"Handle,Title,Description,Variant Price\nmug,Moon Mug,Grey,18.00\n"
+    parsed = parse_csv(data)
+    assert parsed.dialect == "canonical"
+    assert parsed.rows[0].cells["Description"] == "Grey"
+    assert parsed.unknown_columns == []