SLICE-5: products import spine — canonical CSV → preview → confirm (SD-0002 §7.2) #26

Merged
ben.stull merged 21 commits from worktree-slice-5-import-spine into main 2026-06-12 03:50:21 +00:00
3 changed files with 321 additions and 2 deletions
Showing only changes of commit 9bc6e4dbd2 - Show all commits
+207
View File
@@ -0,0 +1,207 @@
"""Diff engine — catalog × canonical products → preview records (SD-0002 §6.5.2).
Classifies each canonical product against the storefront's current catalog as
add / update / unchanged / error, producing JSON-ready preview records (stored
as draft JSONB, served verbatim to the SPA) plus a summary and a deterministic
fingerprint that detects catalog drift between preview and confirm (INV-11).
Deliberately DB-free: the catalog snapshot dataclasses are defined here and the
repo layer builds them. Only fields present in the file's canonical fields{}
participate in a comparison — an absent column is untouched, never a change
(§6.5.1); a present-but-empty cell resolves to the field's CLEAR_DEFAULTS entry.
Catalog variants/images absent from the file are likewise untouched (INV-10).
"""
from __future__ import annotations
import hashlib
import json
from dataclasses import dataclass
from decimal import Decimal
from .models import CLEAR_DEFAULTS, CanonicalProduct, CanonicalVariant
@dataclass
class CatalogVariant:
id: int
options: tuple[str | None, str | None, str | None]
position: int
# sku, barcode, price (Decimal|None), cost, weight, weight_unit, volume,
# volume_unit, tax_id_1, tax_id_2, inventory_tracker, inventory_qty,
# variant_image (linked image source_url or None)
fields: dict[str, object]
@dataclass
class CatalogImage:
id: int
source_url: str
position: int
alt_text: str | None
@dataclass
class CatalogProduct:
id: int
handle: str
title: str
option_names: tuple[str | None, str | None, str | None]
# title, description_html, vendor, product_type, google_product_category,
# tags (list[str]), status, published (bool)
fields: dict[str, object]
variants: list[CatalogVariant]
images: list[CatalogImage]
@dataclass(frozen=True)
class DiffResult:
records: list[dict]
summary: dict
fingerprint: str
# Option-name presence markers in fields{} (see validate.py); the values are
# compared via the option_names attribute, not through the generic field loop.
_OPTION_NAME_FIELDS = ("option1_name", "option2_name", "option3_name")
_SUMMARY_KEY = {"add": "adds", "update": "updates", "unchanged": "unchanged", "error": "errors"}
def compute_diff(catalog: dict[str, CatalogProduct], products: list[CanonicalProduct]) -> DiffResult:
records: list[dict] = []
summary = {"adds": 0, "updates": 0, "unchanged": 0, "errors": 0}
for product in products:
current = catalog.get(product.handle)
if product.errors:
kind, detail = "error", {"errors": [e.as_json() for e in product.errors]}
elif current is None:
kind, detail = "add", _add_detail(product)
else:
detail = _update_detail(product, current)
kind = "update" if detail else "unchanged"
records.append(
{
"handle": product.handle,
"title": product.title or (current.title if current else ""),
"kind": kind,
"variant_count": len(current.variants) if kind == "unchanged" else len(product.variants),
"detail": detail,
}
)
summary[_SUMMARY_KEY[kind]] += 1
fingerprint = hashlib.sha256(
json.dumps(records, sort_keys=True, separators=(",", ":"), default=str).encode()
).hexdigest()
return DiffResult(records=records, summary=summary, fingerprint=fingerprint)
def _add_detail(product: CanonicalProduct) -> dict:
# On add, absent fields fall back to their defaults for display where one
# exists — the detail shows what will actually be set.
set_fields = _resolved_product_fields(product)
for field_name, default in CLEAR_DEFAULTS.items():
set_fields.setdefault(field_name, default)
return {
"set": {f: _json_safe(v) for f, v in set_fields.items()},
"option_names": list(product.option_names),
"variants": [
{"options": list(v.options), "set": _resolved_variant_fields(v)}
for v in product.variants
],
"images": [
{"src": i.source_url, "position": i.position, "alt_text": i.alt_text}
for i in product.images
],
}
def _update_detail(product: CanonicalProduct, current: CatalogProduct) -> dict:
changes: list[dict] = []
# Title is always file-present (required header column); "" means the block
# already carries an error and never reaches here.
if product.title and product.title != current.title:
changes.append(_change("title", current.title, product.title))
for field_name, resolved in _resolved_product_fields(product).items():
before = current.fields.get(field_name)
if resolved != before:
changes.append(_change(field_name, before, resolved))
for slot in (1, 2, 3):
if f"option{slot}_name" not in product.fields:
continue
before, after = current.option_names[slot - 1], product.option_names[slot - 1]
if after != before:
changes.append(_change(f"option{slot}_name", before, after))
variant_entries: list[dict] = []
by_options = {v.options: v for v in current.variants}
for variant in product.variants:
match = by_options.get(variant.options)
if match is None:
variant_entries.append(
{"options": list(variant.options), "kind": "add", "set": _resolved_variant_fields(variant)}
)
continue
variant_changes = [
_change(f, match.fields.get(f), resolved)
for f, resolved in _resolved_fields(variant.fields).items()
if resolved != match.fields.get(f)
]
if variant_changes:
variant_entries.append(
{"options": list(variant.options), "kind": "update", "changes": variant_changes}
)
image_entries: list[dict] = []
by_src = {i.source_url: i for i in current.images}
for image in product.images:
match = by_src.get(image.source_url)
if match is None:
image_entries.append(
{"src": image.source_url, "kind": "add", "position": image.position, "alt_text": image.alt_text}
)
continue
image_changes = [
_change(f, before, after)
for f, before, after in (
("position", match.position, image.position),
("alt_text", match.alt_text, image.alt_text),
)
if after != before
]
if image_changes:
image_entries.append({"src": image.source_url, "kind": "update", "changes": image_changes})
detail: dict = {}
if changes:
detail["changes"] = changes
if variant_entries:
detail["variants"] = variant_entries
if image_entries:
detail["images"] = image_entries
return detail
def _resolved_fields(fields: dict[str, object]) -> dict[str, object]:
"""File-present fields with None (an explicit clear) resolved to the default."""
return {f: (v if v is not None else CLEAR_DEFAULTS.get(f)) for f, v in fields.items()}
def _resolved_product_fields(product: CanonicalProduct) -> dict[str, object]:
return {
f: v for f, v in _resolved_fields(product.fields).items() if f not in _OPTION_NAME_FIELDS
}
def _resolved_variant_fields(variant: CanonicalVariant) -> dict[str, object]:
return {f: _json_safe(v) for f, v in _resolved_fields(variant.fields).items()}
def _change(field_name: str, before: object, after: object) -> dict:
return {"field": field_name, "before": _json_safe(before), "after": _json_safe(after)}
def _json_safe(value: object) -> object:
if isinstance(value, Decimal):
return str(value)
if isinstance(value, (tuple, list)):
return [_json_safe(v) for v in value]
return value
+4 -2
View File
@@ -31,8 +31,10 @@ from .models import (
_HANDLE_RE = re.compile(r"^[a-z0-9-]+$")
_STATUSES = {"draft", "active", "archived"}
# Product columns handled as attributes (title, option_names), not via fields{}.
_ATTRIBUTE_COLUMNS = {"Title", "Option1 Name", "Option2 Name", "Option3 Name"}
# Title is handled as an attribute, not via fields{}. Option names live in BOTH
# .option_names (the values) and fields{} (the file-presence signal the diff
# needs: absent column == untouched, never a clear).
_ATTRIBUTE_COLUMNS = {"Title"}
# Sentinel: the cell failed normalization (the error is already recorded).
_INVALID = object()
+110
View File
@@ -0,0 +1,110 @@
"""Diff engine — classification, blank-vs-absent, option matching, fingerprint (§6.8)."""
from decimal import Decimal
from app.domains.products.codec import parse_csv
from app.domains.products.diff import (
CatalogImage, CatalogProduct, CatalogVariant, compute_diff,
)
from app.domains.products.validate import build_products
def _canon(*lines: str):
return build_products(parse_csv(("\n".join(lines) + "\n").encode()))
def _catalog_mug(**overrides):
fields = {
"title": "Moon Mug", "description_html": None, "vendor": "Acme",
"product_type": "standalone", "google_product_category": None,
"tags": ["kitchen"], "status": "active", "published": True,
} | overrides
return {
"moon-mug": CatalogProduct(
id=1, handle="moon-mug", title=fields["title"],
option_names=(None, None, None), fields=fields,
variants=[CatalogVariant(id=10, options=(None, None, None), position=1,
fields={"sku": "SKU-1", "barcode": None, "price": Decimal("18.00"),
"cost": None, "weight": None, "weight_unit": None,
"volume": None, "volume_unit": None, "tax_id_1": None,
"tax_id_2": None, "inventory_tracker": None,
"inventory_qty": 40, "variant_image": None})],
images=[CatalogImage(id=100, source_url="https://x/a.jpg", position=1, alt_text=None)],
)
}
HEADER = "Handle,Title,Vendor,Tags,Status,Variant SKU,Variant Price,Variant Inventory Qty,Image Src"
MUG_ROW = 'moon-mug,Moon Mug,Acme,kitchen,active,SKU-1,18.00,40,https://x/a.jpg'
def test_new_handle_classifies_add():
diff = compute_diff({}, _canon(HEADER, MUG_ROW))
[rec] = diff.records
assert rec["kind"] == "add" and rec["handle"] == "moon-mug" and rec["variant_count"] == 1
assert diff.summary == {"adds": 1, "updates": 0, "unchanged": 0, "errors": 0}
assert rec["detail"]["set"]["status"] == "active"
def test_identical_file_classifies_unchanged():
diff = compute_diff(_catalog_mug(), _canon(HEADER, MUG_ROW))
assert diff.records[0]["kind"] == "unchanged"
assert diff.summary["unchanged"] == 1
def test_changed_price_classifies_update_with_before_after():
row = MUG_ROW.replace("18.00", "21.00")
diff = compute_diff(_catalog_mug(), _canon(HEADER, row))
[rec] = diff.records
assert rec["kind"] == "update"
[vchange] = rec["detail"]["variants"]
assert {"field": "price", "before": "18.00", "after": "21.00"} in vchange["changes"]
def test_absent_column_untouched_empty_cell_clears():
# Vendor column absent: vendor stays Acme. Status present-but-empty: clears to default 'active' (already active -> no change).
diff = compute_diff(
_catalog_mug(),
_canon("Handle,Title,Status,Variant SKU,Variant Price,Variant Inventory Qty,Image Src",
"moon-mug,Moon Mug,,SKU-1,18.00,40,https://x/a.jpg"),
)
assert diff.records[0]["kind"] == "unchanged"
def test_empty_cell_clear_shows_in_diff():
# Vendor present-but-empty clears Acme -> None: an explicit, previewable change (§6.5.1).
diff = compute_diff(
_catalog_mug(),
_canon("Handle,Title,Vendor,Variant SKU,Variant Price,Variant Inventory Qty,Image Src",
"moon-mug,Moon Mug,,SKU-1,18.00,40,https://x/a.jpg"),
)
[rec] = diff.records
assert rec["kind"] == "update"
assert {"field": "vendor", "before": "Acme", "after": None} in rec["detail"]["changes"]
def test_new_option_combo_is_variant_add_existing_untouched():
catalog = _catalog_mug()
diff = compute_diff(
catalog,
_canon("Handle,Title,Option1 Name,Option1 Value,Variant Price",
"moon-mug,Moon Mug,Size,Large,25.00"),
)
[rec] = diff.records
assert rec["kind"] == "update"
kinds = [v.get("kind") for v in rec["detail"]["variants"]]
assert "add" in kinds
def test_error_product_classifies_error():
diff = compute_diff({}, _canon("Handle,Title,Variant Price", "mug,Mug,nope"))
[rec] = diff.records
assert rec["kind"] == "error"
assert rec["detail"]["errors"][0]["column"] == "Variant Price"
def test_fingerprint_stable_and_drift_sensitive():
d1 = compute_diff(_catalog_mug(), _canon(HEADER, MUG_ROW))
d2 = compute_diff(_catalog_mug(), _canon(HEADER, MUG_ROW))
d3 = compute_diff(_catalog_mug(title="Renamed"), _canon(HEADER, MUG_ROW))
assert d1.fingerprint == d2.fingerprint
assert d1.fingerprint != d3.fingerprint