Files
HomeAgent/internal/nlp/extractor_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
2.5 KiB
Go

package nlp
import (
"testing"
)
func TestFallbackParseDebug(t *testing.T) {
cases := []string{"我打球", "我在杭州读书", "小明喜欢吃苹果", "天气很好", "我住在杭州"}
p := newFallbackParser()
for _, c := range cases {
result, err := p.Parse(c)
if err != nil || result == nil || len(result.Tokens) == 0 {
t.Skip("jieba not available")
}
t.Logf("%q → tokens=%v pos=%v", c, result.Tokens, result.POS)
}
}
func TestExtractFromPOS(t *testing.T) {
p := newFallbackParser()
tests := []struct {
name string
input string
}{
{"pronoun_prep_ns_noun", "我在杭州读书"},
{"pronoun_verb_noun", "我打球"},
{"name_verb_noun", "小明喜欢吃苹果"},
{"adj_predicate", "天气很好"},
{"pronoun_verb_prep_ns", "我住在杭州"},
{"empty", ""},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
if tt.input == "" {
result, _ := p.Parse("")
triples := extractFromPOS(result)
if len(triples) != 0 {
t.Errorf("expected 0 triples for empty, got %d", len(triples))
}
return
}
result, err := p.Parse(tt.input)
if err != nil || result == nil || len(result.Tokens) == 0 {
t.Skip("jieba not available")
}
t.Logf("input=%q tokens=%v pos=%v", tt.input, result.Tokens, result.POS)
triples := extractFromPOS(result)
for _, tr := range triples {
if tr.Subject == "" || tr.Relation == "" || tr.Object == "" {
t.Errorf("triple has empty field: %+v", tr)
}
t.Logf("triple: Subject=%q Relation=%q Object=%q score=%.2f", tr.Subject, tr.Relation, tr.Object, tr.Score)
}
if len(triples) == 0 {
t.Logf("no triples extracted (may be expected depending on jieba POS tagging)")
}
})
}
}
func TestExtractorFallback(t *testing.T) {
e := NewExtractor(nil)
result := e.Extract("我住在杭州")
if result == nil {
t.Fatal("expected result")
}
if result.Src == "" {
t.Skip("jieba not available")
}
if len(result.Triples) > 0 {
tr := result.Triples[0]
t.Logf("extracted: Subject=%q Relation=%q Object=%q (score=%.2f, src=%s)",
tr.Subject, tr.Relation, tr.Object, tr.Score, tr.Src)
}
}
func TestExtractorWithDepStub(t *testing.T) {
dummy := &dummyParser{}
e := NewExtractor(dummy)
result := e.Extract("我今天去北京")
if result == nil {
t.Fatal("expected result")
}
if len(result.Triples) > 0 {
t.Logf("result: src=%s, triples=%+v", result.Src, result.Triples)
}
}
type dummyParser struct{}
func (d *dummyParser) Parse(text string) (*ParseResult, error) {
return &ParseResult{}, nil
}