From 3e6659d64a22fe664d72f9eb83310f697ff27a94 Mon Sep 17 00:00:00 2001
From: ax_rd <ax_rd@aisim.cn>
Date: Thu, 03 Sep 2026 11:40:07 +0800
Subject: [PATCH] feat: 悬空双链自动补全(RetryUnresolved,Reconcile 末尾自动调用)+ 3 个 Task3 审查 Minor 修复
---
internal/index/reconcile.go | 126 +++++++++++++++++++++++++++++--
internal/index/unresolved_test.go | 98 ++++++++++++++++++++++++
internal/graph/builder.go | 3
3 files changed, 218 insertions(+), 9 deletions(-)
diff --git a/internal/graph/builder.go b/internal/graph/builder.go
index d3fbd3e..9c89e7a 100644
--- a/internal/graph/builder.go
+++ b/internal/graph/builder.go
@@ -108,7 +108,8 @@
if base == link {
return node, "exact"
}
- if fuzzy == nil && strings.Contains(node.Title, link) {
+ // 空 link 跳过 fuzzy(Contains 对空串恒真)
+ if fuzzy == nil && link != "" && strings.Contains(node.Title, link) {
fuzzy = node
}
}
diff --git a/internal/index/reconcile.go b/internal/index/reconcile.go
index 8024eb3..18c25c3 100644
--- a/internal/index/reconcile.go
+++ b/internal/index/reconcile.go
@@ -18,6 +18,7 @@
Modified int
Deleted int
Unchanged int
+ Resolved int // 悬空链接自动补全成功的条数
}
// Reconcile 增量对账:stat 比对 → 只对变更文件解析和写库
@@ -101,10 +102,12 @@
}
}
- // 5. 悬空链接重试(新增/修改节点可能让 failed 链接变可解析)
- if res.Added+res.Modified > 0 {
- store.RetryUnresolved() // 见 Task 4,此处先以空实现占位编译通过
+ // 5. 悬空链接重试:新节点入库后,历史悬空链接可能变可解析
+ resolved, err := store.RetryUnresolved()
+ if err != nil {
+ return nil, fmt.Errorf("悬空链接重试失败: %w", err)
}
+ res.Resolved = resolved
return res, nil
}
@@ -156,8 +159,12 @@
targetID, prov, ok := s.resolveWikilink(link)
if !ok {
tail := nameTail(link)
+ // 幂等守卫:同 from_node+link_text 不重复插(unresolved_links 无 UNIQUE 约束,用 WHERE NOT EXISTS)
s.db.Exec(`INSERT INTO unresolved_links (from_node, link_text, name_tail, status)
- VALUES (?, ?, ?, 'pending') ON CONFLICT DO NOTHING`, nodeID, link, tail)
+ SELECT ?, ?, ?, 'pending'
+ WHERE NOT EXISTS (
+ SELECT 1 FROM unresolved_links WHERE from_node = ? AND link_text = ?)`,
+ nodeID, link, tail, nodeID, link)
continue
}
if err := s.InsertEdge(&graph.Edge{
@@ -180,7 +187,7 @@
s.db.QueryRow(`SELECT COALESCE(MAX(to_node), 1000000) FROM edges WHERE to_node >= 1000000 AND relation=?`, relation).Scan(&maxID)
virtualID = maxID + 1
}
- return s.InsertEdge(&graph.Edge{FromNode: fromNode, ToNode: virtualID, Relation: relation, Label: label})
+ return s.InsertEdge(&graph.Edge{FromNode: fromNode, ToNode: virtualID, Relation: relation, Label: label, Provenance: relation})
}
// resolveWikilink 解析 wikilink 目标,返回 (nodeID, provenance, ok)
@@ -218,7 +225,8 @@
if base == link || nTitle == link {
return nid, "exact", true
}
- if fuzzyID == 0 && strings.Contains(nTitle, link) {
+ // 空 link 跳过 fuzzy(Contains 对空串恒真会误建边)
+ if fuzzyID == 0 && link != "" && strings.Contains(nTitle, link) {
fuzzyID = nid
}
}
@@ -236,8 +244,110 @@
return link
}
-// RetryUnresolved 重试解析悬空链接(Task 4 补全完整实现)
-func (s *Store) RetryUnresolved() {}
+// RetryUnresolved 重试解析悬空链接:用当前全部节点的标题/文件名去匹配 unresolved_links 的 name_tail。
+// 命中则建边(provenance 按匹配严格度)、删行。返回成功解析条数。
+func (s *Store) RetryUnresolved() (int, error) {
+ rows, err := s.db.Query(`SELECT id, from_node, link_text, name_tail FROM unresolved_links`)
+ if err != nil {
+ return 0, err
+ }
+ type pending struct {
+ id int64
+ fromNode int64
+ linkText string
+ tail string
+ }
+ var pendings []pending
+ for rows.Next() {
+ var p pending
+ if err := rows.Scan(&p.id, &p.fromNode, &p.linkText, &p.tail); err != nil {
+ rows.Close()
+ return 0, err
+ }
+ pendings = append(pendings, p)
+ }
+ rows.Close()
+ if len(pendings) == 0 {
+ return 0, nil
+ }
+
+ // 建匹配索引:标题/文件名(去编号) → nodeID,精确匹配优先
+ type matchInfo struct {
+ id int64
+ prov string
+ }
+ exactMap := make(map[string]matchInfo)
+ var fuzzyRows []struct {
+ id int64
+ title string
+ }
+ nrows, err := s.db.Query(`SELECT id, title, path FROM nodes`)
+ if err != nil {
+ return 0, err
+ }
+ for nrows.Next() {
+ var id int64
+ var title, path string
+ if err := nrows.Scan(&id, &title, &path); err != nil {
+ nrows.Close()
+ return 0, err
+ }
+ if _, ok := exactMap[title]; !ok {
+ exactMap[title] = matchInfo{id, "exact"}
+ }
+ base := filepath.Base(path)
+ base = strings.TrimSuffix(base, ".md")
+ if dash := strings.Index(base, "-"); dash >= 0 {
+ base = base[dash+1:]
+ }
+ if _, ok := exactMap[base]; !ok {
+ exactMap[base] = matchInfo{id, "exact"}
+ }
+ fuzzyRows = append(fuzzyRows, struct {
+ id int64
+ title string
+ }{id, title})
+ }
+ nrows.Close()
+
+ resolved := 0
+ for _, p := range pendings {
+ if info, ok := exactMap[p.tail]; ok {
+ // 精确命中:建边 + 删悬空行
+ if err := s.InsertEdge(&graph.Edge{
+ FromNode: p.fromNode, ToNode: info.id,
+ Relation: "wikilink", Label: p.linkText, Provenance: info.prov,
+ }); err != nil {
+ return resolved, err
+ }
+ if _, err := s.db.Exec(`DELETE FROM unresolved_links WHERE id=?`, p.id); err != nil {
+ return resolved, err
+ }
+ resolved++
+ continue
+ }
+ // fuzzy:标题包含(空 tail 跳过,避免 Contains 恒真)
+ if p.tail == "" {
+ continue
+ }
+ for _, fr := range fuzzyRows {
+ if strings.Contains(fr.title, p.tail) {
+ if err := s.InsertEdge(&graph.Edge{
+ FromNode: p.fromNode, ToNode: fr.id,
+ Relation: "wikilink", Label: p.linkText, Provenance: "fuzzy",
+ }); err != nil {
+ return resolved, err
+ }
+ if _, err := s.db.Exec(`DELETE FROM unresolved_links WHERE id=?`, p.id); err != nil {
+ return resolved, err
+ }
+ resolved++
+ break
+ }
+ }
+ }
+ return resolved, nil
+}
// QuickCheck 只 stat 比对(不读内容不哈希),返回是否有差异
func QuickCheck(store *Store, vaultPath string) (bool, error) {
diff --git a/internal/index/unresolved_test.go b/internal/index/unresolved_test.go
new file mode 100644
index 0000000..c598256
--- /dev/null
+++ b/internal/index/unresolved_test.go
@@ -0,0 +1,98 @@
+package index
+
+import (
+ "os"
+ "path/filepath"
+ "testing"
+)
+
+func TestRetryUnresolved(t *testing.T) {
+ dir := t.TempDir()
+ os.MkdirAll(filepath.Join(dir, "FAQ"), 0755)
+ os.WriteFile(filepath.Join(dir, "FAQ", "001-旧文档.md"),
+ []byte("---\ntitle: 旧文档\n---\n提到 [[补气失败]]\n"), 0644)
+
+ store, _ := Open(filepath.Join(t.TempDir(), "kb.db"))
+ defer store.Close()
+
+ Reconcile(store, dir)
+
+ // 验证悬空链接入表
+ var n int
+ store.db.QueryRow(`SELECT COUNT(*) FROM unresolved_links WHERE link_text='补气失败'`).Scan(&n)
+ if n != 1 {
+ t.Fatalf("悬空链接未入表: %d", n)
+ }
+
+ // 新文档入库:标题正好是 "补气失败"
+ os.WriteFile(filepath.Join(dir, "FAQ", "002-补气失败.md"),
+ []byte("---\ntitle: 补气失败\n---\n补气失败排查\n"), 0644)
+
+ res, err := Reconcile(store, dir)
+ if err != nil {
+ t.Fatal(err)
+ }
+ if res.Added != 1 {
+ t.Fatalf("新增: %+v", res)
+ }
+
+ // 悬空链接应被解析:行删除 + 边建立
+ store.db.QueryRow(`SELECT COUNT(*) FROM unresolved_links WHERE link_text='补气失败'`).Scan(&n)
+ if n != 0 {
+ t.Errorf("悬空行未清除: %d", n)
+ }
+ store.db.QueryRow(`SELECT COUNT(*) FROM edges WHERE relation='wikilink' AND label='补气失败'`).Scan(&n)
+ if n != 1 {
+ t.Errorf("wikilink 边未建立: %d", n)
+ }
+ var prov string
+ store.db.QueryRow(`SELECT provenance FROM edges WHERE relation='wikilink' AND label='补气失败'`).Scan(&prov)
+ if prov != "exact" {
+ t.Errorf("补全边应为 exact: %s", prov)
+ }
+}
+
+func TestResolveWikilinkEmptyLink(t *testing.T) {
+ dir := t.TempDir()
+ os.MkdirAll(filepath.Join(dir, "FAQ"), 0755)
+ os.WriteFile(filepath.Join(dir, "FAQ", "001-文档.md"),
+ []byte("---\ntitle: 文档\n---\n提到 [[|别名]]\n"), 0644)
+
+ store, _ := Open(filepath.Join(t.TempDir(), "kb.db"))
+ defer store.Close()
+ Reconcile(store, dir)
+
+ // 空 link 不应 fuzzy 误建边(Contains 空串恒真)
+ var n int
+ store.db.QueryRow(`SELECT COUNT(*) FROM edges WHERE relation='wikilink' AND label='|别名'`).Scan(&n)
+ if n != 0 {
+ t.Errorf("空 link 不应建 wikilink 边: %d", n)
+ }
+ // 悬空行应入表且只入一行
+ store.db.QueryRow(`SELECT COUNT(*) FROM unresolved_links WHERE link_text='|别名'`).Scan(&n)
+ if n != 1 {
+ t.Errorf("悬空行应为 1: %d", n)
+ }
+}
+
+func TestTagEntityEdgeProvenance(t *testing.T) {
+ dir := t.TempDir()
+ os.MkdirAll(filepath.Join(dir, "FAQ"), 0755)
+ os.WriteFile(filepath.Join(dir, "FAQ", "001-文档.md"),
+ []byte("---\ntitle: 文档\ntags: [t1]\nentities: [张三]\n---\n内容\n"), 0644)
+
+ store, _ := Open(filepath.Join(t.TempDir(), "kb.db"))
+ defer store.Close()
+ Reconcile(store, dir)
+
+ // tag/entity 边的 provenance 应为 relation 本身(Minor 1 修复)
+ var prov string
+ store.db.QueryRow(`SELECT provenance FROM edges WHERE relation='tag' AND label='t1'`).Scan(&prov)
+ if prov != "tag" {
+ t.Errorf("tag 边 provenance: %q", prov)
+ }
+ store.db.QueryRow(`SELECT provenance FROM edges WHERE relation='entity' AND label='张三'`).Scan(&prov)
+ if prov != "entity" {
+ t.Errorf("entity 边 provenance: %q", prov)
+ }
+}
--
Gitblit v1.10.0