enriched_attributes 现在会按 name 聚合，同名项下的 value.zh / value.en

都会合并成数组，和 qanchors / enriched_tags 的处理方式保持一致，更符合你现在这套 ES mapping 的灌入方式。ES 的 text 字段本身支持数组，所以像 value.zh: ["舒适", "无鞋带设计"] 这种写法是可以正常入库的；nested 只是外层对象数组，不影响内部语言字段存数组。

enriched_attributes 现在会按 name 聚合，同名项下的 value.zh / value.en
都会合并成数组，和 qanchors / enriched_tags 的处理方式保持一致，更符合你现在这套 ES mapping 的灌入方式。ES 的 text 字段本身支持数组，所以像 value.zh: ["舒适", "无鞋带设计"] 这种写法是可以正常入库的；nested 只是外层对象数组，不影响内部语言字段存数组。
tangwang
1 parent 42024409
Showing 4 changed files with 34 additions and 24 deletions Show diff stats
indexer/product_enrich.py
tests/ci/test_service_api_contracts.py
tests/test_llm_enrichment_batch_fill.py
tests/test_product_enrich_partial_mode.py
@@ -203,21 +203,32 @@ def _append_lang_phrase_map(target: Dict[str, List[str]], lang: str, raw_value: 
         target[lang] = merged
-def _append_enriched_attribute(
+def _get_or_create_named_value_entry(
+    target: List[Dict[str, Any]],
+    name: str,
+    *,
+    default_value: Optional[Dict[str, Any]] = None,
+) -> Dict[str, Any]:
+    for item in target:
+        if item.get("name") == name:
+            value = item.get("value")
+            if isinstance(value, dict):
+                return item
+            break
+
+    entry = {"name": name, "value": default_value or {}}
+    target.append(entry)
+    return entry
+
+
+def _append_named_lang_phrase_map(
     target: List[Dict[str, Any]],
     name: str,
     lang: str,
     raw_value: Any,
 ) -> None:
-    for value in split_multi_value_field(raw_value):
-        if any(
-            item.get("name") == name
-            and isinstance(item.get("value"), dict)
-            and item["value"].get(lang) == value
-            for item in target
-        ):
-            continue
-        target.append({"name": name, "value": {lang: value}})
+    entry = _get_or_create_named_value_entry(target, name=name, default_value={})
+    _append_lang_phrase_map(entry["value"], lang=lang, raw_value=raw_value)
 def _get_product_id(product: Dict[str, Any]) -> str:
@@ -306,7 +317,7 @@ def _apply_index_content_row(result: Dict[str, Any], row: Dict[str, Any], lang: 
         raw = _get_analysis_field_value(row, source_name)
         if not raw:
             continue
-        _append_enriched_attribute(
+        _append_named_lang_phrase_map(
             result["enriched_attributes"],
             name=output_name,
             lang=lang,
@@ -356,8 +356,7 @@ def test_indexer_enrich_content_contract(indexer_client: TestClient, monkeypatch
                 },
                 "enriched_tags": {"zh": ["tag1", "tag2"], "en": ["tag1", "tag2"]},
                 "enriched_attributes": [
-                    {"name": "enriched_tags", "value": {"zh": "tag1"}},
-                    {"name": "enriched_tags", "value": {"en": "tag1"}},
+                    {"name": "enriched_tags", "value": {"zh": ["tag1"], "en": ["tag1"]}},
                 ],
             }
             for p in items
@@ -387,7 +386,7 @@ def test_indexer_enrich_content_contract(indexer_client: TestClient, monkeypatch
     assert data["results"][0]["enriched_tags"]["en"] == ["tag1", "tag2"]
     assert data["results"][0]["enriched_attributes"][0] == {
         "name": "enriched_tags",
-        "value": {"zh": "tag1"},
+        "value": {"zh": ["tag1"], "en": ["tag1"]},
     }
@@ -21,8 +21,7 @@ def test_fill_llm_attributes_batch_uses_product_enrich_helper(monkeypatch):
                 },
                 "tags": {"zh": ["t1", "t2"], "en": ["t1", "t2"]},
                 "enriched_attributes": [
-                    {"name": "tags", "value": {"zh": "t1"}},
-                    {"name": "tags", "value": {"en": "t1"}},
+                    {"name": "tags", "value": {"zh": ["t1"], "en": ["t1"]}},
                 ],
             }
             for item in items
@@ -57,5 +56,4 @@ def test_fill_llm_attributes_batch_uses_product_enrich_helper(monkeypatch):
     assert docs[0]["qanchors"]["en"] == ["en-anchor-0"]
     assert docs[0]["tags"]["zh"] == ["t1", "t2"]
     assert docs[0]["tags"]["en"] == ["t1", "t2"]
-    assert {"name": "tags", "value": {"zh": "t1"}} in docs[0]["enriched_attributes"]
-    assert {"name": "tags", "value": {"en": "t1"}} in docs[0]["enriched_attributes"]
+    assert {"name": "tags", "value": {"zh": ["t1"], "en": ["t1"]}} in docs[0]["enriched_attributes"]
@@ -414,12 +414,14 @@ def test_build_index_content_fields_maps_internal_tags_to_enriched_tags_output()
             "qanchors": {"zh": ["zh-anchor"], "en": ["en-anchor"]},
             "enriched_tags": {"zh": ["zh-tag1", "zh-tag2"], "en": ["en-tag1", "en-tag2"]},
             "enriched_attributes": [
-                {"name": "enriched_tags", "value": {"zh": "zh-tag1"}},
-                {"name": "enriched_tags", "value": {"zh": "zh-tag2"}},
-                {"name": "target_audience", "value": {"zh": "zh-audience"}},
-                {"name": "enriched_tags", "value": {"en": "en-tag1"}},
-                {"name": "enriched_tags", "value": {"en": "en-tag2"}},
-                {"name": "target_audience", "value": {"en": "en-audience"}},
+                {
+                    "name": "enriched_tags",
+                    "value": {
+                        "zh": ["zh-tag1", "zh-tag2"],
+                        "en": ["en-tag1", "en-tag2"],
+                    },
+                },
+                {"name": "target_audience", "value": {"zh": ["zh-audience"], "en": ["en-audience"]}},
             ],
         }
     ]