Files
HomeAgent/internal/agent/core/agent_functions_test.go
root 1cb3e87dde feat: 完整实现 NLP 三元组提取系统 + token budget 上下文分配
- 重写 extractor.go: 分句、17条 POS 模板、依存模板 + COO 链、ATT合并
- parser.go: 分句循环 + TransE 向量验证(h+r≈t)
- fallback.go: jieba POS 降级解析器
- bridge.go: nlp.Triple ↔ memory.Triple 转换
- pipeline.go: extractKeyTriples 改用 NLP 提取器, 删除5条旧前缀规则
- distill.go: docToTriples 改用 NLP 提取器
- reorgGraph: 语义相似度增强检测, 保持纯 LLM 决断
- Provider 接口加 MaxContextTokens() + 模型窗口映射表
- tokenbudget.go: 中文 token 估算器 + budget 分配(80%利用率)
- process.go/buildSystemPrompt: 按 token 预算截断 memory+timeline
2026-07-27 15:26:23 +08:00

100 lines
2.3 KiB
Go

package core
import (
"testing"
"gitcode.com/JianFeeeee/HomeAgent/internal/memory/document"
)
func TestEntitySimilarity(t *testing.T) {
tests := []struct {
a, b string
want float64
}{
{"", "", 0}, // empty → 0
{"a", "b", 0}, // single char → 0
{"张三", "张三", 1.0}, // identical → 1.0
{"张三", "李四", 0}, // no common bigrams
{"iPhone", "iPhone 15", 0.625}, // partial overlap
}
for _, tt := range tests {
got := entitySimilarity(tt.a, tt.b)
if got != tt.want {
t.Errorf("entitySimilarity(%q, %q) = %.3f, want %.3f", tt.a, tt.b, got, tt.want)
}
}
}
func TestDocToTriples(t *testing.T) {
doc := &document.Doc{
Summary: "用户喜欢编程",
Content: "用户提到喜欢Go和Python",
Source: "context",
}
triples := docToTriples(doc)
foundSummary := false
foundSource := false
for _, tr := range triples {
switch {
case tr.Subject == "文档" && tr.Relation == "主题":
foundSummary = true
case tr.Subject == "文档" && tr.Relation == "来源":
foundSource = true
}
}
if !foundSummary {
t.Error("missing '主题' triple")
}
if !foundSource {
t.Error("missing '来源' triple")
}
}
func TestDocToTriplesNil(t *testing.T) {
triples := docToTriples(nil)
if len(triples) != 0 {
t.Errorf("expected empty for nil doc, got %d", len(triples))
}
}
func TestDocToTriplesNoSource(t *testing.T) {
doc := &document.Doc{
Summary: "无来源文档",
Content: "content",
}
triples := docToTriples(doc)
for _, tr := range triples {
if tr.Relation == "来源" {
t.Error("should not have source triple when Source is empty")
}
}
}
func TestDocToTriplesTypes(t *testing.T) {
doc := &document.Doc{
Summary: "测试三元组类型",
Content: "用于验证 SubjectType 和 ObjectType",
Source: "test",
}
triples := docToTriples(doc)
for _, tr := range triples {
if tr.Subject == "文档" {
if tr.SubjectType != "Concept" {
t.Errorf("文档 subject_type should be Concept, got %q", tr.SubjectType)
}
if tr.Confidence != 1.0 {
t.Errorf("文档 triple confidence should be 1.0, got %f", tr.Confidence)
}
}
// all should have SubjectType/ObjectType set
if tr.SubjectType == "" || tr.ObjectType == "" {
t.Errorf("triple %+v missing SubjectType or ObjectType", tr)
}
}
}