package docs
import (
"archive/zip"
"bytes"
"encoding/json"
"io"
"net/http"
"strings"
"testing"
)
// richDocJSON is a Tiptap document exercising headings, marks, and a list —
// including CJK text, which every format must carry through intact.
const richDocJSON = `{"type":"doc","content":[` +
`{"type":"heading","attrs":{"level":2},"content":[{"type":"text","text":"My Section"}]},` +
`{"type":"paragraph","content":[{"type":"text","text":"Hello "},{"type":"text","marks":[{"type":"bold"}],"text":"world"},{"type":"text","text":" 你好"}]},` +
`{"type":"bulletList","content":[` +
`{"type":"listItem","content":[{"type":"paragraph","content":[{"type":"text","text":"first"}]}]},` +
`{"type":"listItem","content":[{"type":"paragraph","content":[{"type":"text","text":"second"}]}]}` +
`]}` +
`]}`
func seedRichDoc(t *testing.T, srv http.Handler) string {
t.Helper()
id := newDoc(t, srv)
body := `{"title":"日记 Diary","content":` + jsonString(richDocJSON) + `,"content_text":"My Section\nHello world 你好\nfirst\nsecond","word_count":6}`
if rec := do(t, srv, http.MethodPut, "/"+id, body); rec.Code != http.StatusOK {
t.Fatalf("seed rich doc: code=%d body=%s", rec.Code, rec.Body)
}
return id
}
// jsonString quotes a string as a JSON string literal (so the Tiptap JSON can be
// embedded as the "content" field value).
func jsonString(s string) string {
b, _ := json.Marshal(s)
return string(b)
}
func TestExportMarkdown(t *testing.T) {
srv := newTestServer(t)
id := seedRichDoc(t, srv)
rec := do(t, srv, http.MethodGet, "/"+id+"/export?format=md", "")
if rec.Code != http.StatusOK {
t.Fatalf("export md: code=%d body=%s", rec.Code, rec.Body)
}
if ct := rec.Header().Get("Content-Type"); !strings.HasPrefix(ct, "text/markdown") {
t.Fatalf("unexpected content-type: %q", ct)
}
out := rec.Body.String()
for _, want := range []string{"## My Section", "**world**", "你好", "- first", "- second"} {
if !strings.Contains(out, want) {
t.Fatalf("markdown missing %q in:\n%s", want, out)
}
}
// CJK filename must survive in the RFC 5987 form.
if cd := rec.Header().Get("Content-Disposition"); !strings.Contains(cd, "filename*=UTF-8''") {
t.Fatalf("expected RFC 5987 filename, got %q", cd)
}
}
func TestExportAll(t *testing.T) {
srv := newTestServer(t)
// Two docs, one with a duplicate title to exercise filename de-duplication.
seedRichDoc(t, srv)
id2 := newDoc(t, srv)
if rec := do(t, srv, http.MethodPut, "/"+id2, `{"title":"日记 Diary","content":`+jsonString(richDocJSON)+`,"content_text":"x","word_count":1}`); rec.Code != http.StatusOK {
t.Fatalf("seed second doc: %d %s", rec.Code, rec.Body)
}
rec := do(t, srv, http.MethodGet, "/export-all?format=md", "")
if rec.Code != http.StatusOK {
t.Fatalf("export-all: code=%d body=%s", rec.Code, rec.Body)
}
if ct := rec.Header().Get("Content-Type"); ct != "application/zip" {
t.Fatalf("unexpected content-type: %q", ct)
}
zr, err := zip.NewReader(bytes.NewReader(rec.Body.Bytes()), int64(rec.Body.Len()))
if err != nil {
t.Fatalf("zip open: %v", err)
}
if len(zr.File) != 2 {
t.Fatalf("expected 2 files in backup, got %d", len(zr.File))
}
names := map[string]bool{}
for _, f := range zr.File {
names[f.Name] = true
rc, _ := f.Open()
b, _ := io.ReadAll(rc)
rc.Close()
if !strings.Contains(string(b), "你好") {
t.Fatalf("backup entry %q missing CJK body", f.Name)
}
}
// The duplicate title must have been disambiguated, not overwritten.
if !names["日记 Diary.md"] || !names["日记 Diary (1).md"] {
t.Fatalf("expected de-duplicated filenames, got %v", names)
}
}
func TestExportHTML(t *testing.T) {
srv := newTestServer(t)
id := seedRichDoc(t, srv)
rec := do(t, srv, http.MethodGet, "/"+id+"/export?format=html", "")
out := rec.Body.String()
for _, want := range []string{"", "My Section
", "world", "你好", "first"} {
if !strings.Contains(out, want) {
t.Fatalf("html missing %q", want)
}
}
}
func TestExportPlainText(t *testing.T) {
srv := newTestServer(t)
id := seedRichDoc(t, srv)
rec := do(t, srv, http.MethodGet, "/"+id+"/export?format=txt", "")
out := rec.Body.String()
for _, want := range []string{"My Section", "Hello world 你好", "• first"} {
if !strings.Contains(out, want) {
t.Fatalf("txt missing %q in:\n%s", want, out)
}
}
}
func TestExportDocx(t *testing.T) {
srv := newTestServer(t)
id := seedRichDoc(t, srv)
rec := do(t, srv, http.MethodGet, "/"+id+"/export?format=docx", "")
if rec.Code != http.StatusOK {
t.Fatalf("export docx: code=%d", rec.Code)
}
raw := rec.Body.Bytes()
zr, err := zip.NewReader(bytes.NewReader(raw), int64(len(raw)))
if err != nil {
t.Fatalf("docx is not a valid zip: %v", err)
}
want := map[string]bool{"[Content_Types].xml": false, "word/document.xml": false}
var docXML string
for _, f := range zr.File {
if _, ok := want[f.Name]; ok {
want[f.Name] = true
}
if f.Name == "word/document.xml" {
rc, _ := f.Open()
b, _ := io.ReadAll(rc)
rc.Close()
docXML = string(b)
}
}
for name, found := range want {
if !found {
t.Fatalf("docx missing part %q", name)
}
}
for _, w := range []string{"My Section", "你好", "", "Heading2"} {
if !strings.Contains(docXML, w) {
t.Fatalf("document.xml missing %q", w)
}
}
}
// richDocJSON2 exercises the newer node/mark types: links, highlight, an image,
// and a table (with a header row). Each export format should carry them through.
const richDocJSON2 = `{"type":"doc","content":[` +
`{"type":"paragraph","content":[` +
`{"type":"text","marks":[{"type":"link","attrs":{"href":"https://petal.test"}}],"text":"site"},` +
`{"type":"text","text":" and "},` +
`{"type":"text","marks":[{"type":"highlight","attrs":{"color":"#FFF1A8"}}],"text":"lit"}` +
`]},` +
`{"type":"image","attrs":{"src":"/api/images/abc123.png","alt":"a cat"}},` +
`{"type":"table","content":[` +
`{"type":"tableRow","content":[` +
`{"type":"tableHeader","content":[{"type":"paragraph","content":[{"type":"text","text":"Name"}]}]},` +
`{"type":"tableHeader","content":[{"type":"paragraph","content":[{"type":"text","text":"年龄"}]}]}` +
`]},` +
`{"type":"tableRow","content":[` +
`{"type":"tableCell","content":[{"type":"paragraph","content":[{"type":"text","text":"Mei"}]}]},` +
`{"type":"tableCell","content":[{"type":"paragraph","content":[{"type":"text","text":"30"}]}]}` +
`]}` +
`]}` +
`]}`
func seedRichDoc2(t *testing.T, srv http.Handler) string {
t.Helper()
id := newDoc(t, srv)
body := `{"title":"Rich2","content":` + jsonString(richDocJSON2) + `,"content_text":"site and lit\nName 年龄 Mei 30","word_count":6}`
if rec := do(t, srv, http.MethodPut, "/"+id, body); rec.Code != http.StatusOK {
t.Fatalf("seed rich doc 2: code=%d body=%s", rec.Code, rec.Body)
}
return id
}
func TestExportLinksImagesTables(t *testing.T) {
srv := newTestServer(t)
id := seedRichDoc2(t, srv)
md := do(t, srv, http.MethodGet, "/"+id+"/export?format=md", "").Body.String()
for _, want := range []string{"[site](https://petal.test)", "", "| Name | 年龄 |", "| --- | --- |", "| Mei | 30 |"} {
if !strings.Contains(md, want) {
t.Fatalf("markdown missing %q in:\n%s", want, md)
}
}
html := do(t, srv, http.MethodGet, "/"+id+"/export?format=html", "").Body.String()
for _, want := range []string{`site`, "lit", `
`, "Name | ", "Mei | "} {
if !strings.Contains(html, want) {
t.Fatalf("html missing %q in:\n%s", want, html)
}
}
docx := do(t, srv, http.MethodGet, "/"+id+"/export?format=docx", "")
raw := docx.Body.Bytes()
zr, err := zip.NewReader(bytes.NewReader(raw), int64(len(raw)))
if err != nil {
t.Fatalf("docx not a zip: %v", err)
}
var docXML string
for _, f := range zr.File {
if f.Name == "word/document.xml" {
rc, _ := f.Open()
b, _ := io.ReadAll(rc)
rc.Close()
docXML = string(b)
}
}
for _, want := range []string{"", "Name", "年龄", "[a cat]", "