Agent-System-Backend/internal/ingest/ooxml_python_test.go

package ingest

// 真实生成器轮测：openpyxl / python-pptx 现场生成 xlsx/pptx 再解析，防止
// 手工夹具只验证"自己写的 XML"。生成器缺失时 t.Skip（诚实出口）；CI 已装
// 这两个包（.gitea/workflows/ci.yaml 安装 python-docx python-pptx openpyxl）。

import (
	"os"
	"os/exec"
	"path/filepath"
	"strings"
	"testing"

	core "agent-system-core"
)

func pythonModuleAvailable(t *testing.T, module string) bool {
	t.Helper()
	if _, err := exec.LookPath("python3"); err != nil {
		return false
	}
	return exec.Command("python3", "-c", "import "+module).Run() == nil
}

// runPythonScript 把脚本写到临时目录执行；失败即 t.Fatal（脚本属测试自身）。
func runPythonScript(t *testing.T, script string) {
	t.Helper()
	dir := t.TempDir()
	path := filepath.Join(dir, "gen.py")
	if err := os.WriteFile(path, []byte(script), 0o644); err != nil {
		t.Fatal(err)
	}
	out, err := exec.Command("python3", path).CombinedOutput()
	if err != nil {
		t.Fatalf("python generator failed: %v\n%s", err, out)
	}
}

func TestParseXlsxFromOpenpyxl(t *testing.T) {
	if !pythonModuleAvailable(t, "openpyxl") {
		t.Skip("python3 openpyxl not available")
	}
	dir := t.TempDir()
	file := filepath.Join(dir, "报价单.xlsx")
	runPythonScript(t, `
import openpyxl
from datetime import datetime
wb = openpyxl.Workbook()
ws = wb.active
ws.title = "报价"
ws.append(["物料", "单价", "日期"])
ws.append(["支架", 12.5, datetime(2024, 1, 1)])
ws["C2"].number_format = "yyyy-mm-dd"
ws["D2"] = "=A2&\"-x\""
ws["D3"] = True
wb.create_sheet("说明").append(["备注行"])
wb.save(r"`+file+`")
`)

	data, err := os.ReadFile(file)
	if err != nil {
		t.Fatal(err)
	}
	doc := Parse(file, "", data)
	if doc.Meta.Parser != "builtin:xlsx" || len(doc.Warnings) != 0 {
		t.Fatalf("meta: %+v warnings: %v", doc.Meta, doc.Warnings)
	}
	var heads []string
	for _, b := range doc.Blocks {
		if b.Type == core.BlockHeading {
			heads = append(heads, b.Text)
		}
	}
	if len(heads) != 2 || heads[0] != "报价" || heads[1] != "说明" {
		t.Fatalf("headings: %v", heads)
	}
	plain := doc.PlainText()
	for _, want := range []string{"物料", "支架", "12.5", "2024-01-01"} {
		if !strings.Contains(plain, want) {
			t.Errorf("missing %q in: %s", want, plain)
		}
	}
	// openpyxl 公式不带缓存值：回显公式本身（可检索、不冒充结果）。
	if !strings.Contains(plain, "=A2") {
		t.Errorf("formula without cache should echo: %s", plain)
	}
	if !strings.Contains(plain, "TRUE") {
		t.Errorf("boolean cell should render TRUE: %s", plain)
	}
}

func TestParsePptxFromPythonPptx(t *testing.T) {
	if !pythonModuleAvailable(t, "pptx") {
		t.Skip("python3 pptx not available")
	}
	dir := t.TempDir()
	file := filepath.Join(dir, "方案评审.pptx")
	runPythonScript(t, `
from pptx import Presentation
from pptx.util import Inches
prs = Presentation()
s1 = prs.slides.add_slide(prs.slide_layouts[0])
s1.shapes.title.text = "评审结论"
s1.placeholders[1].text = "通过"
s2 = prs.slides.add_slide(prs.slide_layouts[5])
s2.shapes.title.text = "报价明细"
tbl = s2.shapes.add_table(2, 2, Inches(1), Inches(2), Inches(6), Inches(1)).table
tbl.cell(0, 0).text = "物料"
tbl.cell(0, 1).text = "单价"
tbl.cell(1, 0).text = "支架"
tbl.cell(1, 1).text = "12.5"
notes = s1.notes_slide.notes_text_frame
notes.text = "需要补充法规依据"
prs.save(r"`+file+`")
`)

	data, err := os.ReadFile(file)
	if err != nil {
		t.Fatal(err)
	}
	doc := Parse(file, "", data)
	if doc.Meta.Parser != "builtin:pptx" || len(doc.Warnings) != 0 {
		t.Fatalf("meta: %+v warnings: %v", doc.Meta, doc.Warnings)
	}
	var heads []string
	for _, b := range doc.Blocks {
		if b.Type == core.BlockHeading {
			heads = append(heads, b.Text)
		}
	}
	if len(heads) != 2 || !strings.HasPrefix(heads[0], "幻灯片 1：评审结论") || !strings.HasPrefix(heads[1], "幻灯片 2：报价明细") {
		t.Fatalf("headings: %v", heads)
	}
	plain := doc.PlainText()
	for _, want := range []string{"通过", "物料", "支架", "12.5", "备注：需要补充法规依据"} {
		if !strings.Contains(plain, want) {
			t.Errorf("missing %q in: %s", want, plain)
		}
	}
}