package search

import (
	"testing"
)

// TestExploreParagraphExtraction 段落截取：只输出命中关键词的段落，整段不截半句
func TestExploreParagraphExtraction(t *testing.T) {
	content := "# 标题\n\n第一段讲称重。\n\n## 补气流程\n\n补气失败时先检查阀门。\n\n## 其他\n\n无关内容。\n"
	got := extractRelevantParagraphs(content, []string{"补气"}, 100)
	want := "## 补气流程\n\n补气失败时先检查阀门。\n"
	if got != want {
		t.Errorf("段落截取:\n got=%q\nwant=%q", got, want)
	}
}

// TestExploreWholeDocWhenSmall 文档短于预算时整篇输出
func TestExploreWholeDocWhenSmall(t *testing.T) {
	got := extractRelevantParagraphs("短文档\n", []string{"不存在"}, 10000)
	if got != "短文档\n" {
		t.Errorf("应整篇输出: %q", got)
	}
}

// TestExploreKeywordExpansion 长 CJK 词拆 bigram（原词保留，ASCII/短词不拆）
func TestExploreKeywordExpansion(t *testing.T) {
	got := expandKeywords([]string{"电子秤补气失败", "补气", "abc"})
	want := []string{"电子秤补气失败", "电子", "子秤", "秤补", "补气", "气失", "失败", "补气", "abc"}
	if len(got) != len(want) {
		t.Fatalf("展开数量: got=%d want=%d (%v)", len(got), len(want), got)
	}
	for i := range want {
		if got[i] != want[i] {
			t.Errorf("第 %d 项: got=%q want=%q", i, got[i], want[i])
		}
	}
}

func TestExploreBudget(t *testing.T) {
	// 用 extractRelevantParagraphs 的预算版验证：预算 20 字节，命中段落 30 字节 → 输出空（宁缺毋滥，不截半段）
	got := extractWithBudget("## 段落\n\n这是一段超过预算的内容啊\n", []string{"段落"}, 20)
	if got != "" {
		t.Errorf("超预算段落应跳过: %q", got)
	}
}