From a5c01a3f115399b55f43d639c8278b8d68c6211c Mon Sep 17 00:00:00 2001
From: ax_rd <ax_rd@aisim.cn>
Date: Thu, 03 Sep 2026 11:26:53 +0800
Subject: [PATCH] feat: wikilink 边可信度标注(exact/fuzzy)+ 悬空链接入 unresolved_links 表
---
internal/index/fts.go | 116 ++++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 77 insertions(+), 39 deletions(-)
diff --git a/internal/index/fts.go b/internal/index/fts.go
index 5e67985..4323985 100644
--- a/internal/index/fts.go
+++ b/internal/index/fts.go
@@ -3,9 +3,8 @@
import (
"database/sql"
"encoding/json"
- "strings"
+ "sort"
)
-
// FTSResult 全文搜索结果
type FTSResult struct {
ID int64
@@ -15,27 +14,46 @@
Rank float64
}
-// CreateFTS 创建 FTS5 虚拟表
+// CreateFTS 创建 FTS5 虚拟表(external-content 模式,由触发器增量维护)
+// 注意:external-content 模式下 FTS 列名必须与 content 表列名一致,
+// 故 content 列对应 nodes 表的 content_fts 列
func (s *Store) CreateFTS() error {
_, err := s.db.Exec(`
CREATE VIRTUAL TABLE IF NOT EXISTS nodes_fts USING fts5(
- title,
- content,
- tags,
- entities,
- content='nodes',
- content_rowid='id'
- )
- `)
- return err
+ title, content_fts, tags, aliases,
+ content='nodes', content_rowid='id'
+ )`)
+ if err != nil {
+ return err
+ }
+ // 触发器:nodes 的增删改同步维护 FTS
+ triggers := []string{
+ `CREATE TRIGGER IF NOT EXISTS nodes_fts_ai AFTER INSERT ON nodes BEGIN
+ INSERT INTO nodes_fts(rowid, title, content_fts, tags, aliases)
+ VALUES (new.id, new.title, new.content_fts, new.tags, new.aliases);
+ END`,
+ `CREATE TRIGGER IF NOT EXISTS nodes_fts_ad AFTER DELETE ON nodes BEGIN
+ INSERT INTO nodes_fts(nodes_fts, rowid, title, content_fts, tags, aliases)
+ VALUES ('delete', old.id, old.title, old.content_fts, old.tags, old.aliases);
+ END`,
+ `CREATE TRIGGER IF NOT EXISTS nodes_fts_au AFTER UPDATE ON nodes BEGIN
+ INSERT INTO nodes_fts(nodes_fts, rowid, title, content_fts, tags, aliases)
+ VALUES ('delete', old.id, old.title, old.content_fts, old.tags, old.aliases);
+ INSERT INTO nodes_fts(rowid, title, content_fts, tags, aliases)
+ VALUES (new.id, new.title, new.content_fts, new.tags, new.aliases);
+ END`,
+ }
+ for _, t := range triggers {
+ if _, err := s.db.Exec(t); err != nil {
+ return err
+ }
+ }
+ return nil
}
-// PopulateFTS 填充 FTS 索引
+// PopulateFTS 全量重灌 FTS(external-content 模式专用语法)
func (s *Store) PopulateFTS() error {
- _, err := s.db.Exec(`
- INSERT INTO nodes_fts(rowid, title, content, tags, entities)
- SELECT id, title, content_fts, tags, entities FROM nodes
- `)
+ _, err := s.db.Exec(`INSERT INTO nodes_fts(nodes_fts) VALUES('rebuild')`)
return err
}
@@ -45,31 +63,51 @@
return nil, nil
}
- // 构建 FTS5 查询
- query := strings.Join(keywords, " OR ")
+ // 对每个关键词单独搜索,然后合并结果(去重)
+ // 这样即使某个关键词匹配不到,其他关键词也能找到结果
+ seen := make(map[int64]bool)
+ var allResults []FTSResult
- rows, err := s.db.Query(`
- SELECT n.id, n.path, n.title, n.section, fts.rank
- FROM nodes_fts fts
- JOIN nodes n ON n.id = fts.rowid
- WHERE nodes_fts MATCH ?
- ORDER BY fts.rank
- LIMIT ?
- `, query, limit)
- if err != nil {
- return nil, err
- }
- defer rows.Close()
-
- var results []FTSResult
- for rows.Next() {
- var r FTSResult
- if err := rows.Scan(&r.ID, &r.Path, &r.Title, &r.Section, &r.Rank); err != nil {
- return nil, err
+ for _, kw := range keywords {
+ rows, err := s.db.Query(`
+ SELECT n.id, n.path, n.title, n.section, fts.rank
+ FROM nodes_fts fts
+ JOIN nodes n ON n.id = fts.rowid
+ WHERE nodes_fts MATCH ?
+ ORDER BY fts.rank
+ LIMIT ?
+ `, kw, limit)
+ if err != nil {
+ // 单个关键词搜索失败,跳过继续
+ continue
}
- results = append(results, r)
+
+ for rows.Next() {
+ var r FTSResult
+ if err := rows.Scan(&r.ID, &r.Path, &r.Title, &r.Section, &r.Rank); err != nil {
+ rows.Close()
+ continue
+ }
+ // 去重
+ if !seen[r.ID] {
+ seen[r.ID] = true
+ allResults = append(allResults, r)
+ }
+ }
+ rows.Close()
}
- return results, nil
+
+ // 按 rank 排序(FTS5 的 rank 越小越好)
+ sort.Slice(allResults, func(i, j int) bool {
+ return allResults[i].Rank < allResults[j].Rank
+ })
+
+ // 限制返回数量
+ if limit > 0 && len(allResults) > limit {
+ allResults = allResults[:limit]
+ }
+
+ return allResults, nil
}
// GetNodeContent 获取节点内容
--
Gitblit v1.10.0