1 Commits

Author SHA1 Message Date
Adrian Zürcher
4a9397457d add new functions for zip and byte slices 2026-01-07 17:04:26 +01:00
4 changed files with 197 additions and 6 deletions

3
.gitignore vendored
View File

@@ -1,3 +1,4 @@
*.pdf
assets
dst
dst
*.zip

View File

@@ -1,6 +1,8 @@
package converter
import (
"archive/zip"
"bytes"
"context"
"errors"
"fmt"
@@ -63,7 +65,7 @@ func (c *Converter) SetProgressCallback(cb func(progress int)) {
}
// Convert converts all given input files
func (c *Converter) Convert(files ...models.File) error {
func (c *Converter) ConvertToPdf(files ...models.File) error {
for i, f := range files {
if c.progress != nil {
c.progress(i + 1)
@@ -127,7 +129,7 @@ func (c *Converter) Convert(files ...models.File) error {
}
// Convert converts all given input files
func (c *Converter) ConvertHtmls(htmls ...models.Html) error {
func (c *Converter) ConvertHtmlsToPdf(htmls ...models.Html) error {
for i, h := range htmls {
if c.progress != nil {
c.progress(i + 1)
@@ -183,6 +185,126 @@ func (c *Converter) ConvertHtmls(htmls ...models.Html) error {
return nil
}
// Convert converts all given input files
func (c *Converter) ConvertHtmlsToBytes(htmls ...models.Html) ([][]byte, error) {
var output [][]byte
for i, h := range htmls {
if c.progress != nil {
c.progress(i + 1)
}
if len(h.Html) == 0 {
return nil, fmt.Errorf("no .html input provided")
} else if h.Output == "" || filepath.Ext(h.Output) != ".pdf" {
return nil, fmt.Errorf("no .pdf output file path provided: %s", h.Output)
}
taskCtx, taskCancel := chromedp.NewContext(c.browserCtx)
timeoutCtx, timeoutCancel := context.WithTimeout(taskCtx, 60*time.Second)
var pdfData []byte
err := chromedp.Run(timeoutCtx,
// Start with a blank page
chromedp.Navigate("about:blank"),
// Inject HTML directly
chromedp.ActionFunc(func(ctx context.Context) error {
frameTree, err := page.GetFrameTree().Do(ctx)
if err != nil {
return err
}
return page.SetDocumentContent(frameTree.Frame.ID, string(h.Html)).Do(ctx)
}),
chromedp.WaitReady("body", chromedp.ByQuery),
chromedp.ActionFunc(func(ctx context.Context) error {
buf, _, err := page.PrintToPDF().
WithPrintBackground(true).
WithPaperWidth(8.27).
WithPaperHeight(11.69).
Do(ctx)
if err != nil {
return err
}
pdfData = buf
return nil
}),
)
timeoutCancel()
taskCancel()
if err != nil {
return nil, err
}
// add to array of bytes
output = append(output, pdfData)
}
return output, nil
}
// Convert html to pdf and return zip as bytes
func (c *Converter) ConvertHtmlsToZip(htmls ...models.Html) ([]byte, error) {
zipBuf := new(bytes.Buffer)
zipWriter := zip.NewWriter(zipBuf)
for i, h := range htmls {
if c.progress != nil {
c.progress(i + 1)
}
if len(h.Html) == 0 {
return nil, fmt.Errorf("no .html input provided")
} else if h.Output == "" || filepath.Ext(h.Output) != ".pdf" {
return nil, fmt.Errorf("no .pdf output file path provided: %s", h.Output)
}
taskCtx, taskCancel := chromedp.NewContext(c.browserCtx)
timeoutCtx, timeoutCancel := context.WithTimeout(taskCtx, 60*time.Second)
var pdfData []byte
err := chromedp.Run(timeoutCtx,
// Start with a blank page
chromedp.Navigate("about:blank"),
// Inject HTML directly
chromedp.ActionFunc(func(ctx context.Context) error {
frameTree, err := page.GetFrameTree().Do(ctx)
if err != nil {
return err
}
return page.SetDocumentContent(frameTree.Frame.ID, string(h.Html)).Do(ctx)
}),
chromedp.WaitReady("body", chromedp.ByQuery),
chromedp.ActionFunc(func(ctx context.Context) error {
buf, _, err := page.PrintToPDF().
WithPrintBackground(true).
WithPaperWidth(8.27).
WithPaperHeight(11.69).
Do(ctx)
if err != nil {
return err
}
pdfData = buf
return nil
}),
)
timeoutCancel()
taskCancel()
if err != nil {
return nil, err
}
// add to zip
f, err := zipWriter.Create(h.Output)
if err != nil {
return nil, err
}
f.Write(pdfData)
}
zipWriter.Close()
return zipBuf.Bytes(), nil
}
func (c *Converter) Close() {
// Close browser first, then allocator
if c.browserCancel != nil {

View File

@@ -17,7 +17,7 @@ func Convert(chromePath, inputFile, outputFile string) error {
}
defer c.Close()
return c.Convert(input)
return c.ConvertToPdf(input)
}
// NewConverterInstance start new chrome headless shell instance

View File

@@ -53,7 +53,7 @@ func TestConvertFiles(t *testing.T) {
fmt.Println(progress)
})
if err := c.Convert(input...); err != nil {
if err := c.ConvertToPdf(input...); err != nil {
t.Fatal(err)
}
t.Log("test successfull")
@@ -94,7 +94,7 @@ func TestConvertHtml(t *testing.T) {
}
defer c.Close()
err = c.ConvertHtmls(models.Html{Html: html, Output: outputPath})
err = c.ConvertHtmlsToPdf(models.Html{Html: html, Output: outputPath})
if err != nil {
t.Fatalf("ConvertHtml failed: %v", err)
}
@@ -117,3 +117,71 @@ func TestConvertHtml(t *testing.T) {
t.Log("ConvertHtml test successful")
}
func TestConvertHtmlsToPDFZip(t *testing.T) {
t.Log("start test ConvertHtml")
// Skip in short mode (useful for CI)
if testing.Short() {
t.Skip("skipping ConvertHtml integration test in short mode")
}
html := []byte(`
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>Test PDF</title>
<style>
body { font-family: Arial, sans-serif; }
h1 { color: #333; }
</style>
</head>
<body>
<h1>Hello PDF</h1>
<p>This is a test.</p>
</body>
</html>
`)
outputPath := filepath.Join("test.pdf")
c, err := converter.NewConverter("assets/chrome-headless-shell/win64")
if err != nil {
t.Fatal(err)
}
defer c.Close()
b, err := c.ConvertHtmlsToZip(models.Html{Html: html, Output: outputPath})
if err != nil {
t.Fatalf("ConvertHtml failed: %v", err)
}
f, err := os.Create("test.zip")
if err != nil {
t.Fatalf("create file: %v", err)
}
defer f.Close()
_, err = f.Write(b)
if err != nil {
t.Fatalf("write to file: %v", err)
}
// // Assert PDF exists
// data, err := os.ReadFile(outputPath)
// if err != nil {
// t.Fatalf("PDF not created: %v", err)
// }
// // Assert non-empty
// if len(data) == 0 {
// t.Fatal("PDF file is empty")
// }
// // Assert valid PDF header
// if !bytes.HasPrefix(data, []byte("%PDF-")) {
// t.Fatalf("output is not a valid PDF (missing %%PDF- header)")
// }
t.Log("ConvertHtml test successful")
}