test(goauto): pin SYB filter behaviour against real variationSku samples #269

The samples are the ones the production database actually holds: 档口 codes like "新寮-雅伊阁大码女装#301" and "DD#004" must be filtered, while own codes like "PDD0582", "my238", "1" and "引流款" must not, and an empty variationSku is a product without a supplier code rather than a 档口 item. The test also asserts the two structural rules record different hit counts. That is the property the previous aggregate-per-kind write could not hold, and the disable-confirmation dialog depends on it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NTDbDcwbDw1TSAcE6wfh2F
2026-09-11 16:37:43 +08:00
parent 20f59b68bd
commit 78df997fc3
1 changed files with 84 additions and 0 deletions
@@ -0,0 +1,84 @@
+package sybproductfilter
+
+import (
+	"context"
+	"testing"
+	"time"
+)
+
+// 用线上真实取到的 variationSku 样本，验证过滤判定与每条规则各自计数。
+func TestRealWorldSamplesPerRuleCounting(t *testing.T) {
+	db := testDB(t)
+	ctx := context.Background()
+	set, err := LoadEnabled(ctx, db)
+	if err != nil {
+		t.Fatal(err)
+	}
+	samples := []struct {
+		v        string
+		wantKind string // "" = 不过滤
+	}{
+		{"新寮-雅伊阁大码女装#301", "char"},
+		{"广达-爆款大码女装#9018", "char"},
+		{"DD#004", "char"},
+		{"300斤牛奶絲圓領#A057", "char"},
+		{"上寮-琪琪尚雅网批#2604##(&15)", "char"},
+		{"PDD0582", ""},
+		{"my238", ""},
+		{"le171", ""},
+		{"1", ""},
+		{"引流款", ""},
+		{"", ""},
+	}
+	hits := HitCounter{}
+	var charN, kwN, keptN int
+	for _, s := range samples {
+		rule := set.Match(s.v)
+		if s.wantKind == "" {
+			if rule != nil {
+				t.Fatalf("%q 不应被过滤，却命中了 %q", s.v, rule.Keyword)
+			}
+			keptN++
+			continue
+		}
+		if rule == nil || rule.Kind != s.wantKind {
+			t.Fatalf("%q 应命中 %s 规则，实际 %v", s.v, s.wantKind, rule)
+		}
+		hits.Add(rule)
+		if rule.Kind == "char" {
+			charN++
+		} else {
+			kwN++
+		}
+	}
+	if charN != 5 || kwN != 0 || keptN != 6 {
+		t.Fatalf("统计不符：char=%d keyword=%d kept=%d", charN, kwN, keptN)
+	}
+	if err := UpdateHits(ctx, db, set, hits, time.Now().UTC()); err != nil {
+		t.Fatal(err)
+	}
+	after, err := LoadEnabled(ctx, db)
+	if err != nil {
+		t.Fatal(err)
+	}
+	got := map[string]int{}
+	for _, x := range after.Chars {
+		if x.LastHitCount == nil {
+			t.Fatalf("规则 %q 必须被写入命中数", x.Keyword)
+		}
+		got[x.Keyword] = *x.LastHitCount
+	}
+	// "#" 命中 4 条（301/9018/DD#004/A057 ... 其中带 - 的先被 "-" 规则接走）
+	if got["-"]+got["#"] != 5 {
+		t.Fatalf("两条结构规则命中数之和应为 5，实际 - =%d # =%d", got["-"], got["#"])
+	}
+	if got["-"] == got["#"] {
+		t.Fatalf("两条规则不应记成同一个数（这正是 #269 修的 bug）: - =%d # =%d", got["-"], got["#"])
+	}
+	for _, x := range after.Keywords {
+		if x.LastHitCount == nil || *x.LastHitCount != 0 {
+			t.Fatalf("未命中的关键词 %q 应记 0，实际 %v", x.Keyword, x.LastHitCount)
+		}
+	}
+	t.Logf("结构规则命中：- =%d  # =%d", got["-"], got["#"])
+}