From 5a2be87f658d01bc5b3b7ecdba92ac69bf09dcf7 Mon Sep 17 00:00:00 2001
From: ai_xiaopei <xiaopei@aisim.cn>
Date: Thu, 03 Sep 2026 15:15:37 +0800
Subject: [PATCH] fix(search): 搜索准确性四连修——FTS5 MATCH 引号包裹(连字符不再被解析成 MINUS)；KeywordSearch 截断按命中关键词数排序(高频 bigram 不再挤出强相关文档)；原词奖励档(完整短语压过泛化 bigram)；tags 字段真实参与评分(此前误用 Section)
---
internal/graph/builder_test.go | 67 +++++++++++++++++++--------------
1 files changed, 38 insertions(+), 29 deletions(-)
diff --git a/internal/graph/builder_test.go b/internal/graph/builder_test.go
index a966c86..afd95de 100644
--- a/internal/graph/builder_test.go
+++ b/internal/graph/builder_test.go
@@ -1,12 +1,46 @@
package graph
import (
- "strings"
"testing"
"github.com/aisim/kb-cli/internal/vault"
)
+func TestBuildGraphProvenance(t *testing.T) {
+ files := []*vault.FileMeta{
+ {Path: "FAQ/001-补气失败.md", Title: "补气失败", Wikilinks: []string{"红绿闪", "不存在的链接"}},
+ {Path: "FAQ/002-红绿闪.md", Title: "红绿闪"},
+ {Path: "知识/003-称重原理详解.md", Title: "称重原理详解"}, // "称重原理" 是 "称重原理详解" 的子串 → fuzzy
+ }
+ files[0].Wikilinks = append(files[0].Wikilinks, "称重原理")
+
+ g, unresolved := BuildGraph(files)
+
+ // exact: 标题精确匹配
+ var exact, fuzzy int
+ for _, e := range g.Edges {
+ if e.Relation != "wikilink" {
+ continue
+ }
+ switch e.Provenance {
+ case "exact":
+ exact++
+ case "fuzzy":
+ fuzzy++
+ }
+ }
+ if exact != 1 || fuzzy != 1 {
+ t.Errorf("provenance 分布: exact=%d fuzzy=%d (want 1/1)", exact, fuzzy)
+ }
+ // 悬空链接
+ if len(unresolved) != 1 || unresolved[0].LinkText != "不存在的链接" {
+ t.Errorf("unresolved: %+v", unresolved)
+ }
+ if unresolved[0].NameTail != "不存在的链接" {
+ t.Errorf("name_tail: %s", unresolved[0].NameTail)
+ }
+}
+
func TestBuildGraph(t *testing.T) {
files := []*vault.FileMeta{
{
@@ -29,35 +63,10 @@
},
}
- g := BuildGraph(files)
+ g, _ := BuildGraph(files)
- // 2 个文件节点 + 2 个 tag 虚拟节点（充装、智能枪）+ 1 个 entity 虚拟节点
- if len(g.Nodes) != 5 {
- t.Errorf("node count = %d, want 5", len(g.Nodes))
- }
-
- // 验证虚拟节点 path 命名空间与 NodeType
- tagCount, entityCount, fileCount := 0, 0, 0
- for _, n := range g.Nodes {
- switch n.NodeType {
- case "tag":
- tagCount++
- if !strings.HasPrefix(n.Path, "tag:") {
- t.Errorf("tag node path = %q, want prefix tag:", n.Path)
- }
- case "entity":
- entityCount++
- if !strings.HasPrefix(n.Path, "entity:") {
- t.Errorf("entity node path = %q, want prefix entity:", n.Path)
- }
- case "file":
- fileCount++
- default:
- t.Errorf("unexpected node_type %q for %s", n.NodeType, n.Path)
- }
- }
- if tagCount != 2 || entityCount != 1 || fileCount != 2 {
- t.Errorf("file/tag/entity = %d/%d/%d, want 2/2/1", fileCount, tagCount, entityCount)
+ if len(g.Nodes) != 2 {
+ t.Errorf("node count = %d, want 2", len(g.Nodes))
}
// 应该有 3 条边：2条 tag + 1条 entity
--
Gitblit v1.10.0