wordtable2sqlite/main_test.go

package main

import (
	"archive/zip"
	"context"
	"database/sql"
	"encoding/csv"
	"os"
	"path/filepath"
	"testing"

	_ "modernc.org/sqlite"
)

func TestParseDocumentXMLExtractsTableCells(t *testing.T) {
	xml := `<?xml version="1.0" encoding="UTF-8"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
  <w:body>
    <w:tbl>
      <w:tr>
        <w:tc><w:tcPr><w:gridSpan w:val="2"/></w:tcPr><w:p><w:r><w:t>报备表</w:t></w:r></w:p></w:tc>
      </w:tr>
      <w:tr>
        <w:tc><w:p><w:r><w:t>序号</w:t></w:r></w:p></w:tc>
        <w:tc><w:p><w:r><w:t>事件过程</w:t></w:r></w:p></w:tc>
      </w:tr>
      <w:tr>
        <w:tc><w:p><w:r><w:t>1</w:t></w:r></w:p></w:tc>
        <w:tc><w:p><w:r><w:t>起因</w:t><w:br/><w:t>处理经过</w:t></w:r></w:p></w:tc>
      </w:tr>
    </w:tbl>
  </w:body>
</w:document>`

	tables, err := parseDocumentXML([]byte(xml))
	if err != nil {
		t.Fatalf("parseDocumentXML returned error: %v", err)
	}
	if len(tables) != 1 {
		t.Fatalf("got %d tables, want 1", len(tables))
	}
	if got := tables[0].Rows[0].Cells[0].Text; got != "报备表" {
		t.Fatalf("title cell text = %q, want 报备表", got)
	}
	if got := tables[0].Rows[0].Cells[0].ColSpan; got != 2 {
		t.Fatalf("title cell colspan = %d, want 2", got)
	}
	if got := tables[0].Rows[2].Cells[1].Text; got != "起因\n处理经过" {
		t.Fatalf("multiline text = %q, want 起因\\n处理经过", got)
	}
}

func TestInferHeaderFieldsSkipsTitleRow(t *testing.T) {
	table := Table{
		Rows: []Row{
			{Cells: []Cell{{Text: "报备表", ColSpan: 2}}},
			{Cells: []Cell{{Text: "序号", ColSpan: 1}, {Text: "事件过程", ColSpan: 1}}},
			{Cells: []Cell{{Text: "1", ColSpan: 1}, {Text: "客户反映设备位置不合理", ColSpan: 1}}},
		},
	}

	fields := inferFields(table)
	if len(fields) != 2 {
		t.Fatalf("got %d fields, want 2", len(fields))
	}
	if fields[0].Key != "序号" || fields[0].Value != "1" || fields[0].SourceKind != "header_row" {
		t.Fatalf("unexpected first field: %#v", fields[0])
	}
	if fields[1].Key != "事件过程" || fields[1].Value != "客户反映设备位置不合理" {
		t.Fatalf("unexpected second field: %#v", fields[1])
	}
}

func TestInferHeaderFieldsAlignsByLogicalColumnWithColSpan(t *testing.T) {
	table := Table{
		Rows: []Row{
			{Cells: []Cell{{Text: "序号", ColIndex: 0, ColSpan: 1}, {Text: "客户信息", ColIndex: 1, ColSpan: 2}, {Text: "工单编号", ColIndex: 3, ColSpan: 1}}},
			{Cells: []Cell{{Text: "1", ColIndex: 0, ColSpan: 1}, {Text: "高先生", ColIndex: 1, ColSpan: 1}, {Text: "靖远县乌兰镇", ColIndex: 2, ColSpan: 1}, {Text: "9726060110063361", ColIndex: 3, ColSpan: 1}}},
		},
	}

	fields := inferFields(table)
	got := fieldMap(fields)
	if got["序号"] != "1" {
		t.Fatalf("序号 = %q, want 1", got["序号"])
	}
	if got["客户信息"] != "高先生\n靖远县乌兰镇" {
		t.Fatalf("客户信息 = %q, want combined logical-column value", got["客户信息"])
	}
	if got["工单编号"] != "9726060110063361" {
		t.Fatalf("工单编号 = %q, want 9726060110063361", got["工单编号"])
	}
}

func TestImportDocumentWritesSQLiteTables(t *testing.T) {
	dbPath := filepath.Join(t.TempDir(), "import.sqlite")
	db, err := sql.Open("sqlite", dbPath)
	if err != nil {
		t.Fatalf("open sqlite: %v", err)
	}
	defer db.Close()

	xml := `<?xml version="1.0" encoding="UTF-8"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
  <w:body>
    <w:tbl>
      <w:tr><w:tc><w:tcPr><w:gridSpan w:val="2"/></w:tcPr><w:p><w:r><w:t>报备表</w:t></w:r></w:p></w:tc></w:tr>
      <w:tr><w:tc><w:p><w:r><w:t>序号</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>事件过程</w:t></w:r></w:p></w:tc></w:tr>
      <w:tr><w:tc><w:p><w:r><w:t>1</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>客户反映设备位置不合理</w:t></w:r></w:p></w:tc></w:tr>
    </w:tbl>
  </w:body>
</w:document>`

	docxPath := filepath.Join(t.TempDir(), "sample.docx")
	if err := writeTestDocx(docxPath, []byte(xml)); err != nil {
		t.Fatalf("write test docx: %v", err)
	}

	if err := importDocument(context.Background(), db, docxPath); err != nil {
		t.Fatalf("importDocument: %v", err)
	}

	var cells int
	if err := db.QueryRow(`SELECT COUNT(*) FROM cells`).Scan(&cells); err != nil {
		t.Fatalf("count cells: %v", err)
	}
	if cells != 5 {
		t.Fatalf("got %d cells, want 5", cells)
	}

	var value string
	if err := db.QueryRow(`SELECT value FROM fields WHERE key = '事件过程'`).Scan(&value); err != nil {
		t.Fatalf("query field: %v", err)
	}
	if value != "客户反映设备位置不合理" {
		t.Fatalf("field value = %q", value)
	}
}

func TestRunExportsFieldsCSV(t *testing.T) {
	dir := t.TempDir()
	dbPath := filepath.Join(dir, "import.sqlite")
	outPath := filepath.Join(dir, "fields.csv")
	xml := `<?xml version="1.0" encoding="UTF-8"?>
<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
  <w:body>
    <w:tbl>
      <w:tr><w:tc><w:p><w:r><w:t>字段</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>内容</w:t></w:r></w:p></w:tc></w:tr>
      <w:tr><w:tc><w:p><w:r><w:t>工单编号</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>9726060110063361</w:t></w:r></w:p></w:tc></w:tr>
    </w:tbl>
  </w:body>
</w:document>`
	docxPath := filepath.Join(dir, "sample.docx")
	if err := writeTestDocx(docxPath, []byte(xml)); err != nil {
		t.Fatalf("write test docx: %v", err)
	}

	if err := run([]string{"-reset", "-quiet", "-db", dbPath, docxPath}); err != nil {
		t.Fatalf("import run: %v", err)
	}
	if err := run([]string{"export-fields", "-db", dbPath, "-out", outPath}); err != nil {
		t.Fatalf("export run: %v", err)
	}

	f, err := os.Open(outPath)
	if err != nil {
		t.Fatalf("open csv: %v", err)
	}
	defer f.Close()
	records, err := csv.NewReader(f).ReadAll()
	if err != nil {
		t.Fatalf("read csv: %v", err)
	}
	if len(records) != 3 {
		t.Fatalf("got %d csv records, want header + 2 fields: %#v", len(records), records)
	}
	if records[0][0] != "filename" || records[0][1] != "key" || records[0][2] != "value" {
		t.Fatalf("unexpected header: %#v", records[0])
	}
	if records[2][1] != "内容" || records[2][2] != "9726060110063361" {
		t.Fatalf("unexpected exported field: %#v", records[2])
	}
}

func fieldMap(fields []Field) map[string]string {
	out := map[string]string{}
	for _, field := range fields {
		out[field.Key] = field.Value
	}
	return out
}

func writeTestDocx(path string, documentXML []byte) error {
	f, err := os.Create(path)
	if err != nil {
		return err
	}
	defer f.Close()

	zw := zip.NewWriter(f)
	defer zw.Close()

	w, err := zw.Create("word/document.xml")
	if err != nil {
		return err
	}
	_, err = w.Write(documentXML)
	return err
}