fix: 第22轮搜索审计修复 — De Morgan语义/部分日期/has_not/custom URL等8项

Bug-R22-1 (MEDIUM): OR模式特殊字段NOT产生错误De Morgan语义 — 17处修正
Bug-R22-2 (MEDIUM): has_not不反映日期范围NOT — 添加_date_range_markers检查
Bug-R22-3 (MEDIUM): YYYY-MM[DP]未引号部分日期无法解析 — 预处理器标准化
Bug-R22-4 (MEDIUM): date_preset=custom URL恢复丢失年份范围 — 读取URL参数
Bug-R22-5 (MEDIUM): 错误状态下分页总数残留 — 搜索开始时重置total
Bug-R22-6 (LOW): 搜索错误状态未在开始时清除 — 搜索开始时重置searchError
Bug-R22-7 (LOW): DATE token不在未消耗标记恢复处理器中 — 添加DATE类型
Bug-R22-8 (LOW): 外部NOT组内is_not被忽略 — 保留t.is_not

backend/app/services/pubmed_query_parser.py

@@ -445,7 +445,7 @@ class PubmedQueryParser:
         # P12: has_not 同时检查分组内 NOT（如 NOT (a OR b)）
         result.has_not = any(t.is_not for t in _ungrouped) or any(
             t.is_not for g in result.groups for t in g
-        )
+        ) or any(t.is_not for t in result._date_range_markers)
         result.not_terms = [t for t in _ungrouped if t.is_not]
         for t in _ungrouped:
             self._dispatch_term(result, t)
@@ -453,7 +453,7 @@ class PubmedQueryParser:
         # P2-1: Handle unconsumed tokens (e.g., orphan text after RPAREN)
         if self.pos < len(self.tokens) - 1:
             for t in self.tokens[self.pos:-1]:  # exclude EOF token
-                if t.type in (TokenType.WORD, TokenType.QUOTED, TokenType.NUMBER):
+                if t.type in (TokenType.WORD, TokenType.QUOTED, TokenType.NUMBER, TokenType.DATE):
                     text = t.value.strip('"') if t.type == TokenType.QUOTED else t.value
                     result.plain_terms.append(Term(text=text, exact=(t.type == TokenType.QUOTED)))
 
@@ -1008,6 +1008,12 @@ def parse_pubmed_query(query: str) -> ParsedPubmedQuery:
             lambda m: f'{m.group(1)}{m.group(2)}-{int(m.group(3)):02d}-{int(m.group(4)):02d}',
             query,
         )
+        # P5: Normalize YYYY-MM (partial month) to YYYY-MM-01 when followed by date field tag
+        query = re.sub(
+            r'(\b\d{4}-\d{2})(?!-\d)(?=\s*\[(?:DP|EDAT|DEP|CRDT|MHDA|LR|DCOM)\])',
+            r'\1-01',
+            query,
+        )
         tokens = tokenise(query)
         parser = PubmedQueryParser(tokens)
         return parser.parse()

backend/app/services/search_engine.py

@@ -941,7 +941,7 @@ class AdvancedSearchEngine:
                 term_conditions.append(or_(*pos_conds))
             if neg:
                 neg_conds = [GlobalLiterature.pub_types.cast(JSONB).contains([t.text]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # 5b. [GR] [SH] [RN] [NM] [SI] [PA] → JSONB contains，支持 is_not
         if pp.grant_terms:
@@ -954,7 +954,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.grants.cast(JSONB).contains([{"grant_id": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.subheading_terms:
             pos = [t for t in pp.subheading_terms if not t.is_not]
             neg = [t for t in pp.subheading_terms if t.is_not]
@@ -965,7 +965,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.mesh_headings.cast(JSONB).contains([{"qualifiers": [t.text]}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.registry_terms:
             pos = [t for t in pp.registry_terms if not t.is_not]
             neg = [t for t in pp.registry_terms if t.is_not]
@@ -976,7 +976,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.chemical_list.cast(JSONB).contains([{"registry_number": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.substance_terms:
             pos = [t for t in pp.substance_terms if not t.is_not]
             neg = [t for t in pp.substance_terms if t.is_not]
@@ -987,7 +987,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.chemical_list.cast(JSONB).contains([{"name": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.databank_terms:
             pos = [t for t in pp.databank_terms if not t.is_not]
             neg = [t for t in pp.databank_terms if t.is_not]
@@ -998,7 +998,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.databank_list.cast(JSONB).contains([{"accession_numbers": [t.text]}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # 5c. [PA] → pharmacological_actions JSONB contains (by name or ui)，支持 is_not
         if pp.pharmaco_terms:
@@ -1020,7 +1020,7 @@ class AdvancedSearchEngine:
                     )
                     for t in neg
                 ]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # P4: [OT] → keywords JSONB contains（不再映射到 all）
         if pp.ot_terms:
@@ -1033,7 +1033,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.keywords.cast(JSONB).contains([t.text]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # P4: [GEN] → gene_symbols JSONB contains
         if pp.gene_terms:
@@ -1046,7 +1046,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.gene_symbols.cast(JSONB).contains([t.text]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # 5d. [ED] [IR] [PS] [PUBN] [AUID] [COIS] [TT] → 新增字段搜索，支持 is_not
         if pp.ed_terms:
@@ -1059,7 +1059,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.authors.cast(JSONB).contains([{"type": "editor", "family": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.investigator_terms:
             pos = [t for t in pp.investigator_terms if not t.is_not]
             neg = [t for t in pp.investigator_terms if t.is_not]
@@ -1070,7 +1070,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.investigators.cast(JSONB).contains([{"family": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.personal_name_terms:
             pos = [t for t in pp.personal_name_terms if not t.is_not]
             neg = [t for t in pp.personal_name_terms if t.is_not]
@@ -1081,7 +1081,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.personal_name_subjects.cast(JSONB).contains([{"family": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.pubnote_terms:
             pos = [t for t in pp.pubnote_terms if not t.is_not]
             neg = [t for t in pp.pubnote_terms if t.is_not]
@@ -1092,7 +1092,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [cast(GlobalLiterature.publication_notes, String).ilike(f"%{_escape_ilike(t.text)}%") for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.auid_terms:
             pos = [t for t in pp.auid_terms if not t.is_not]
             neg = [t for t in pp.auid_terms if t.is_not]
@@ -1103,7 +1103,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.auid_data.cast(JSONB).contains([{"value": t.text}]) for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.cois_terms:
             pos = [t for t in pp.cois_terms if not t.is_not]
             neg = [t for t in pp.cois_terms if t.is_not]
@@ -1114,7 +1114,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.cois_statement.ilike(f"%{_escape_ilike(t.text)}%") for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
         if pp.tt_terms:
             pos = [t for t in pp.tt_terms if not t.is_not]
             neg = [t for t in pp.tt_terms if t.is_not]
@@ -1125,7 +1125,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.vernacular_title.ilike(f"%{_escape_ilike(t.text)}%") for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # P1-2: [SB] Subset
         #   medline[SB] → citation_status='medline'（记录级）
@@ -1164,7 +1164,7 @@ class AdvancedSearchEngine:
                 ]))
             if neg:
                 neg_conds = [GlobalLiterature.citation_status == t.text.lower() for t in neg]
-                term_conditions.append(not_(or_(*neg_conds)))
+                term_conditions.extend(not_(c) for c in neg_conds)
 
         # P1-2: [UID] → PMID 优先，兜底 DOI
         if pp.uid_terms:
@@ -1201,7 +1201,8 @@ class AdvancedSearchEngine:
                     cond = await AdvancedSearchEngine._single_term_condition(db, t)
                     if cond is not None:
                         if _negated:
-                            g_neg.append(cond)
+                            # R22: preserve inner is_not when group is externally negated
+                            g_neg.append(not_(cond) if t.is_not else cond)
                         elif t.is_not:
                             g_neg.append(not_(cond))
                         else:

docs/13-搜索修复全记录.md

@@ -2,7 +2,7 @@
 
 > 本文档按修复轮次详细记录所有搜索功能合规性修复的背景、根因分析和修改内容。
 >
-> **累计**：21 轮，235 项修复，80+ 字段标签注册，1007+ 项测试覆盖，7 项已知限制
+> **累计**：22 轮，248 项修复，80+ 字段标签注册，1007+ 项测试覆盖，7 项已知限制
 > **时间跨度**：2026-07-24 ~ 2026-07-29
 > **核心文件**：`pubmed_query_parser.py`（~850 行）→ `search_engine.py`（~1360 行）
 
@@ -1588,6 +1588,74 @@
 
 ---
 
+## 第二十二轮：第 22 轮审计修复（8 项）
+
+**日期**：2026-07-29
+**提交**：`c68aa06..`（第 21 轮后追加）
+**数量**：8 项（5 MEDIUM + 3 LOW）
+**触发**：用户第 17 次要求全面检查（第 22 轮，4 并行审计 agent）
+**测试**：1007+ 全部通过 + 前端 build 通过
+
+### Bug-R22-1 (MEDIUM): OR 模式下特殊字段 NOT 产生错误 De Morgan 语义
+
+- **文件**：`search_engine.py:944-1167`
+- **根因**：`term_conditions.append(not_(or_(*neg_conds)))` 在 OR 模式下产生 `NOT(A OR B)` = `NOT A AND NOT B`。正确应为 `or_(not_(A), not_(B))` = `NOT A OR NOT B`。
+- **影响**：`NOT "Review"[PT] OR NOT "Clinical Trial"[PT]` 搜索结果过窄。
+- **修复**：将全部 17 处 `term_conditions.append(not_(or_(*neg_conds)))` 改为 `term_conditions.extend(not_(c) for c in neg_conds)`。AND 模式下语义等价，OR/mixed 模式语义修正。
+
+### Bug-R22-2 (MEDIUM): `has_not` 不反映日期范围 NOT
+
+- **文件**：`pubmed_query_parser.py:446`
+- **根因**：`_ungrouped` 过滤掉 `_is_range_end=True` 的标记，`has_not` 不检查 `_date_range_markers`。
+- **修复**：`has_not` 额外检查 `result._date_range_markers`。
+
+### Bug-R22-3 (MEDIUM): `YYYY-MM[DP]` 未引号部分日期无法解析
+
+- **文件**：`pubmed_query_parser.py:1010-1015`
+- **根因**：`2024-01[DP]` 分词为 `NUMBER(2024) WORD(-01) FIELD([DP])`。`-01` 不匹配 `_PARTIAL_DATE_RE`。
+- **修复**：预处理器将 `YYYY-MM[date_field]` 标准化为 `YYYY-MM-01[date_field]`。
+
+### Bug-R22-4 (MEDIUM): `date_preset=custom` URL 恢复丢失年份范围
+
+- **文件**：`SearchView.vue:393-396`
+- **根因**：`restoreFromQuery` 在 custom 分支无条件清空 yearFromStr/yearToStr。
+- **修复**：custom 分支读取 URL 中的 `year_from/year_to`。
+
+### Bug-R22-5 (MEDIUM): 错误状态下分页总数残留
+
+- **文件**：`SearchView.vue:274-276`
+- **根因**：catch 块清空 results 但不清除 total。
+- **修复**：搜索开始时重置 `total.value = 0`。
+
+### Bug-R22-6 (LOW): 搜索错误状态未在开始时清除
+
+- **文件**：`SearchView.vue:274-276`
+- **根因**：searchError 仅成功后清空。
+- **修复**：搜索开始时设置 `searchError.value = ''`。
+
+### Bug-R22-7 (LOW): DATE token 不在未消耗标记恢复处理器中
+
+- **文件**：`pubmed_query_parser.py:456`
+- **根因**：未消耗标记处理器仅捕获 WORD/QUOTED/NUMBER。
+- **修复**：添加 `TokenType.DATE`。
+
+### Bug-R22-8 (LOW): 外部 NOT 组内 `is_not` 被忽略
+
+- **文件**：`search_engine.py:1203`
+- **根因**：`NOT (A OR NOT B)` → `not_(or_(A, B))`，内部 NOT B 被吞掉。
+- **修复**：组内保留 `t.is_not`。
+
+### 审计结果汇总
+
+| 审计维度 | 结果 |
+|---------|------|
+| R21 回归 | ✅ 无回归 |
+| 搜索引擎代码 | ✅ De Morgan 语义 17 处修正、negated 组内 is_not |
+| 解析器/分词器 | ✅ YYYY-MM 预处理器、has_not 日期范围、DATE 恢复 |
+| 前端集成 | ✅ custom URL 恢复、total/error 清理 |
+
+---
+
 ## 附录：测试覆盖统计
 
 | 测试文件 | 用例数 | 范围 |

frontend/src/views/app/SearchView.vue

@@ -274,6 +274,8 @@ const { page, total, goToPage } = usePagination({
     const gen = ++searchGeneration.value
     loading.value = true
     searched.value = true
+    searchError.value = ''
+    total.value = 0
     try {
       if (p === 1 && query.value.trim()) {
         trackAction('search', 'search', query.value.trim(), { sort: sort.value })
@@ -392,8 +394,13 @@ function restoreFromQuery() {
   if (route.query.sort && VALID_SORTS.has(String(route.query.sort))) sort.value = String(route.query.sort)
   if (route.query.date_preset && ['1y','5y','10y','custom'].includes(String(route.query.date_preset))) {
     datePreset.value = String(route.query.date_preset)
+    if (datePreset.value === 'custom') {
+      if (route.query.year_from) yearFromStr.value = String(route.query.year_from)
+      if (route.query.year_to) yearToStr.value = String(route.query.year_to)
+    } else {
       yearFromStr.value = ''
       yearToStr.value = ''
+    }
   } else if (route.query.date_from || route.query.date_to) {
     datePreset.value = null
     if (route.query.date_from) {