package ingest

import (
	"archive/zip"
	"bytes"
	"encoding/xml"
	"strings"
	"testing"

	core "agent-system-core"
)

func TestParseMarkdown(t *testing.T) {
	doc := Parse("笔记.md", "text/markdown", []byte("# 标题一\n\n段落甲。\n\n- 要点 1\n- 要点 2\n\n## 标题二\n\n段落乙。\n"))
	if doc.Meta.Parser != "builtin:md" || doc.Meta.Confidence != 1.0 {
		t.Fatalf("meta: %+v", doc.Meta)
	}
	var heads, paras, lists int
	for _, b := range doc.Blocks {
		switch b.Type {
		case core.BlockHeading:
			heads++
		case core.BlockPara:
			paras++
		case core.BlockList:
			lists++
			if len(b.Items) != 2 {
				t.Errorf("list items: %v", b.Items)
			}
		}
	}
	if heads != 2 || paras != 2 || lists != 1 {
		t.Errorf("blocks: heads=%d paras=%d lists=%d", heads, paras, lists)
	}
	if !strings.Contains(doc.PlainText(), "# 标题一") {
		t.Error("PlainText missing heading")
	}
}

func TestParseUnknownBinary(t *testing.T) {
	doc := Parse("blob.bin", "application/octet-stream", []byte{0x00, 0x01, 0x02, 0xFF})
	if len(doc.Blocks) != 0 {
		t.Error("binary should not produce blocks")
	}
	if len(doc.Warnings) == 0 {
		t.Error("binary should carry explicit warning (fail visible, not silent)")
	}
}

// 构造最小 docx（zip + word/document.xml）验证 OOXML 解析。
func TestParseDocx(t *testing.T) {
	var buf bytes.Buffer
	zw := zip.NewWriter(&buf)
	docXML := `<?xml version="1.0"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
 <w:body>
  <w:p><w:pPr><w:pStyle w:val="Heading1"/></w:pPr><w:r><w:t>总则</w:t></w:r></w:p>
  <w:p><w:r><w:t>本文件说明医疗器械文档要求。</w:t></w:r></w:p>
  <w:tbl>
   <w:tr><w:tc><w:p><w:r><w:t>项</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>值</w:t></w:r></w:p></w:tc></w:tr>
   <w:tr><w:tc><w:p><w:r><w:t>版本</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>1.0</w:t></w:r></w:p></w:tc></w:tr>
  </w:tbl>
 </w:body>
</w:document>`
	if f, err := zw.Create("word/document.xml"); err == nil {
		f.Write([]byte(docXML))
	} else {
		t.Fatal(err)
	}
	zw.Close()

	doc := Parse("报告.docx", "application/vnd.openxmlformats-officedocument.wordprocessingml.document", buf.Bytes())
	if doc.Meta.Parser != "builtin:docx" || len(doc.Warnings) != 0 {
		t.Fatalf("meta: %+v warnings: %v", doc.Meta, doc.Warnings)
	}
	var heading, para, table bool
	for _, b := range doc.Blocks {
		switch b.Type {
		case core.BlockHeading:
			heading = b.Level == 1 && b.Text == "总则"
		case core.BlockPara:
			para = strings.Contains(b.Text, "医疗器械")
		case core.BlockTable:
			table = len(b.Rows) == 2 && b.Rows[1][1] == "1.0"
		}
	}
	if !heading || !para || !table {
		t.Errorf("docx blocks wrong: heading=%v para=%v table=%v blocks=%+v", heading, para, table, doc.Blocks)
	}
	if !strings.Contains(doc.PlainText(), "医疗器械") {
		t.Error("PlainText missing docx text")
	}
}

func TestParsePDFInvalid(t *testing.T) {
	doc := Parse("scan.pdf", "application/pdf", []byte("not a pdf"))
	if len(doc.Warnings) == 0 || doc.Meta.Confidence > 0.5 {
		t.Errorf("invalid pdf should warn with low confidence: %+v", doc.Meta)
	}
}

var _ = xml.Marshal