go-onlyoffice/docx_comment_test.go

package onlyoffice

import (
	"archive/zip"
	"bytes"
	"io"
	"regexp"
	"strings"
	"testing"
)

// buildTestDocx returns a minimal valid .docx with two paragraphs.
func buildTestDocx(t *testing.T) []byte {
	t.Helper()
	const (
		contentTypes = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="xml" ContentType="application/xml"/><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>`
		document     = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body><w:p><w:pPr><w:jc w:val="both"/></w:pPr><w:r><w:t>The term is two years, ending 8 October 2028.</w:t></w:r></w:p><w:p><w:r><w:t>Nothing relevant here.</w:t></w:r></w:p></w:body></w:document>`
		rels         = `<?xml version="1.0" encoding="UTF-8" standalone="yes"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"></Relationships>`
	)
	var buf bytes.Buffer
	zw := zip.NewWriter(&buf)
	for name, body := range map[string]string{
		"[Content_Types].xml":          contentTypes,
		"word/document.xml":            document,
		"word/_rels/document.xml.rels": rels,
	} {
		w, err := zw.Create(name)
		if err != nil {
			t.Fatalf("zip create: %v", err)
		}
		if _, err := w.Write([]byte(body)); err != nil {
			t.Fatalf("zip write: %v", err)
		}
	}
	if err := zw.Close(); err != nil {
		t.Fatalf("zip close: %v", err)
	}
	return buf.Bytes()
}

func unzipPart(t *testing.T, data []byte, name string) string {
	t.Helper()
	zr, err := zip.NewReader(bytes.NewReader(data), int64(len(data)))
	if err != nil {
		t.Fatalf("zip reader: %v", err)
	}
	for _, f := range zr.File {
		if f.Name != name {
			continue
		}
		rc, err := f.Open()
		if err != nil {
			t.Fatalf("open part: %v", err)
		}
		defer rc.Close()
		b, err := io.ReadAll(rc)
		if err != nil {
			t.Fatalf("read part: %v", err)
		}
		return string(b)
	}
	t.Fatalf("part %s not found", name)
	return ""
}

func TestInjectDocxComments(t *testing.T) {
	src := buildTestDocx(t)
	comments := []DocxComment{
		{Anchor: "8 October 2028", Text: "Change to two years."},
		{Anchor: "two years", Text: "second anchor, same paragraph"},
		{Anchor: "no such text anywhere", Text: "skipped"},
	}
	// First anchor matches the first paragraph; the second also matches that
	// paragraph but must be skipped (one comment per paragraph).
	out, applied, err := InjectDocxComments(src, "Andriy Oblivantsev", comments)
	if err != nil {
		t.Fatalf("inject: %v", err)
	}
	if applied != 1 {
		t.Fatalf("applied = %d, want 1", applied)
	}

	doc := unzipPart(t, out, "word/document.xml")
	for _, want := range []string{"commentRangeStart", "commentRangeEnd", "commentReference"} {
		if !strings.Contains(doc, want) {
			t.Errorf("document.xml missing %s", want)
		}
	}
	if strings.Contains(doc, `<w:pPr><w:commentRangeStart`) {
		t.Error("commentRangeStart inserted inside pPr")
	}

	cmts := unzipPart(t, out, "word/comments.xml")
	if strings.Count(cmts, "<w:comment ") != 1 {
		t.Fatalf("comments count = %d, want 1", strings.Count(cmts, "<w:comment "))
	}
	if !strings.Contains(cmts, `w:author="Andriy Oblivantsev"`) {
		t.Error("author missing in comments.xml")
	}
	if !strings.Contains(cmts, "Change to two years.") {
		t.Error("comment text missing")
	}

	ct := unzipPart(t, out, "[Content_Types].xml")
	if !strings.Contains(ct, "/word/comments.xml") {
		t.Error("content types missing comments override")
	}
	rels := unzipPart(t, out, "word/_rels/document.xml.rels")
	if !strings.Contains(rels, "relationships/comments") {
		t.Error("document rels missing comments relationship")
	}
}

func TestInjectDocxCommentsNoMatch(t *testing.T) {
	src := buildTestDocx(t)
	out, applied, err := InjectDocxComments(src, "X", []DocxComment{{Anchor: "absent", Text: "t"}})
	if err != nil {
		t.Fatalf("inject: %v", err)
	}
	if applied != 0 {
		t.Fatalf("applied = %d, want 0", applied)
	}
	if out == nil {
		t.Fatal("output nil")
	}
}

// TestInjectDocxCommentsOrder guards the marker-id ↔ comments.xml pairing when
// the spec order differs from the document order.
func TestInjectDocxCommentsOrder(t *testing.T) {
	src := buildTestDocx(t)
	spec := []DocxComment{
		{Anchor: "Nothing relevant", Text: "comment B"},
		{Anchor: "The term is two years", Text: "comment A"},
	}
	out, applied, err := InjectDocxComments(src, "A", spec)
	if err != nil || applied != 2 {
		t.Fatalf("inject: applied=%d err=%v", applied, err)
	}
	doc := unzipPart(t, out, "word/document.xml")
	cmts := unzipPart(t, out, "word/comments.xml")

	// id -> text from comments.xml
	byID := map[string]string{}
	for _, m := range regexp.MustCompile(`(?s)<w:comment w:id="(\d+)"[^>]*>(.*?)</w:comment>`).FindAllStringSubmatch(cmts, -1) {
		txt := strings.TrimSpace(stripTags(m[2]))
		byID[m[1]] = txt
	}
	// paragraph that starts with the term text must point at "comment A"
	for _, p := range regexp.MustCompile(`(?s)<w:p\b[^>]*>.*?</w:p>`).FindAllString(doc, -1) {
		if !strings.Contains(stripTags(p), "The term is two years") {
			continue
		}
		m := regexp.MustCompile(`<w:commentRangeStart w:id="(\d+)"/>`).FindStringSubmatch(p)
		if m == nil {
			t.Fatal("no commentRangeStart in the term paragraph")
		}
		if got := byID[m[1]]; got != "comment A" {
			t.Fatalf("term paragraph points at id %s = %q, want \"comment A\"", m[1], got)
		}
		return
	}
	t.Fatal("term paragraph not found")
}

func stripTags(s string) string {
	return regexp.MustCompile(`<[^>]*>`).ReplaceAllString(s, "")
}

func TestParseDocxComments(t *testing.T) {
	got, err := ParseDocxComments([]byte(`[{"anchor":"a","text":"b"}]`))
	if err != nil {
		t.Fatalf("parse: %v", err)
	}
	if len(got) != 1 || got[0].Anchor != "a" || got[0].Text != "b" {
		t.Fatalf("unexpected: %+v", got)
	}
	if _, err := ParseDocxComments([]byte(`{"anchor":"a"}`)); err == nil {
		t.Fatal("expected error for object input")
	}
}