Compare commits
15 Commits
48793c65bc
...
main
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
4a9397457d | ||
|
|
e6e833533e | ||
|
|
1822fc3628 | ||
|
|
d80764b943 | ||
|
|
bd07add64e | ||
|
|
7fec8e1101 | ||
|
|
5b20d4406c | ||
|
|
40f683a917 | ||
|
|
ff460fffa1 | ||
|
|
70102e991a | ||
|
|
39fb913f87 | ||
|
|
8df18a243f | ||
|
|
613b74ee55 | ||
|
|
edb8d7e830 | ||
|
|
537179af03 |
1
.gitignore
vendored
1
.gitignore
vendored
@@ -1,3 +1,4 @@
|
||||
*.pdf
|
||||
assets
|
||||
dst
|
||||
*.zip
|
||||
@@ -1,7 +1,10 @@
|
||||
package converter
|
||||
|
||||
import (
|
||||
"archive/zip"
|
||||
"bytes"
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
@@ -16,15 +19,23 @@ import (
|
||||
|
||||
// html to pdf converter structure for
|
||||
type Converter struct {
|
||||
chromePath string
|
||||
ctx context.Context
|
||||
cancel context.CancelFunc
|
||||
chromePath string
|
||||
allocCtx context.Context
|
||||
allocCancel context.CancelFunc // Cancels the whole Chrome process manager
|
||||
browserCtx context.Context // The specific browser instance
|
||||
browserCancel context.CancelFunc // Closes the browser
|
||||
progress func(progress int)
|
||||
}
|
||||
|
||||
// NewConverter starts a new converter instance with a chrome headless shell executable
|
||||
func NewConverter(chromePath string) *Converter {
|
||||
func NewConverter(chromePath string) (*Converter, error) {
|
||||
var err error
|
||||
|
||||
c := &Converter{chromePath: chromePath}
|
||||
chromePath = c.getChromePath()
|
||||
chromePath, err = c.getChromePath()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
opts := append(chromedp.DefaultExecAllocatorOptions[:],
|
||||
chromedp.ExecPath(chromePath),
|
||||
@@ -33,15 +44,33 @@ func NewConverter(chromePath string) *Converter {
|
||||
chromedp.DisableGPU,
|
||||
)
|
||||
|
||||
var allocCtx context.Context
|
||||
allocCtx, c.cancel = chromedp.NewExecAllocator(context.Background(), opts...)
|
||||
c.ctx, c.cancel = chromedp.NewContext(allocCtx)
|
||||
return c
|
||||
opts = append(opts, platformOptions())
|
||||
|
||||
c.allocCtx, c.allocCancel = chromedp.NewExecAllocator(context.Background(), opts...)
|
||||
c.browserCtx, c.browserCancel = chromedp.NewContext(c.allocCtx)
|
||||
|
||||
// 5. "Warm up" the browser to ensure the executable actually runs
|
||||
// This catches "file not found" or permission errors immediately
|
||||
err = chromedp.Run(c.browserCtx)
|
||||
if err != nil {
|
||||
c.Close() // Cleanup if start fails
|
||||
return nil, fmt.Errorf("failed to start chrome: %w", err)
|
||||
}
|
||||
|
||||
return c, nil
|
||||
}
|
||||
|
||||
func (c *Converter) SetProgressCallback(cb func(progress int)) {
|
||||
c.progress = cb
|
||||
}
|
||||
|
||||
// Convert converts all given input files
|
||||
func (c *Converter) Convert(files ...models.File) error {
|
||||
for _, f := range files {
|
||||
func (c *Converter) ConvertToPdf(files ...models.File) error {
|
||||
for i, f := range files {
|
||||
if c.progress != nil {
|
||||
c.progress(i + 1)
|
||||
}
|
||||
|
||||
if f.Input == "" || filepath.Ext(f.Input) != ".html" {
|
||||
return fmt.Errorf("no .html input file path provided: %s", f.Input)
|
||||
} else if f.Output == "" || filepath.Ext(f.Output) != ".pdf" {
|
||||
@@ -64,11 +93,11 @@ func (c *Converter) Convert(files ...models.File) error {
|
||||
|
||||
htmlURL.WriteString(filepath.ToSlash(absPath))
|
||||
|
||||
c.ctx, c.cancel = context.WithTimeout(c.ctx, 60*time.Second)
|
||||
defer c.cancel()
|
||||
taskCtx, taskCancel := chromedp.NewContext(c.browserCtx)
|
||||
timeoutCtx, timeoutCancel := context.WithTimeout(taskCtx, 60*time.Second)
|
||||
|
||||
var pdfData []byte
|
||||
err = chromedp.Run(c.ctx,
|
||||
err = chromedp.Run(timeoutCtx,
|
||||
chromedp.Navigate(htmlURL.String()),
|
||||
chromedp.WaitReady("body", chromedp.ByQuery),
|
||||
chromedp.ActionFunc(func(ctx context.Context) error {
|
||||
@@ -84,6 +113,9 @@ func (c *Converter) Convert(files ...models.File) error {
|
||||
return nil
|
||||
}),
|
||||
)
|
||||
|
||||
timeoutCancel()
|
||||
taskCancel()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
@@ -96,11 +128,210 @@ func (c *Converter) Convert(files ...models.File) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// Convert converts all given input files
|
||||
func (c *Converter) ConvertHtmlsToPdf(htmls ...models.Html) error {
|
||||
for i, h := range htmls {
|
||||
if c.progress != nil {
|
||||
c.progress(i + 1)
|
||||
}
|
||||
if len(h.Html) == 0 {
|
||||
return fmt.Errorf("no .html input provided")
|
||||
} else if h.Output == "" || filepath.Ext(h.Output) != ".pdf" {
|
||||
return 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 err
|
||||
}
|
||||
|
||||
// Save PDF to file
|
||||
if err := os.WriteFile(h.Output, pdfData, 0644); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
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 {
|
||||
c.browserCancel()
|
||||
}
|
||||
if c.allocCancel != nil {
|
||||
c.allocCancel()
|
||||
}
|
||||
}
|
||||
|
||||
// getChromePath checks for system Chrome, else falls back to bundled headless shell
|
||||
func (c *Converter) getChromePath() string {
|
||||
func (c *Converter) getChromePath() (string, error) {
|
||||
|
||||
chromeExec := "chrome-headless-shell"
|
||||
if runtime.GOOS == "windows" {
|
||||
chromeExec += ".exe"
|
||||
}
|
||||
|
||||
path := filepath.Join(c.chromePath, chromeExec)
|
||||
if _, err := os.Stat(path); err == nil {
|
||||
return path, nil
|
||||
}
|
||||
|
||||
// Candidate paths for system Chrome
|
||||
candidates := []string{}
|
||||
|
||||
// Fallback:
|
||||
switch runtime.GOOS {
|
||||
case "windows":
|
||||
candidates = []string{
|
||||
@@ -124,14 +355,9 @@ func (c *Converter) getChromePath() string {
|
||||
// Check system paths first
|
||||
for _, path := range candidates {
|
||||
if _, err := os.Stat(path); err == nil {
|
||||
return path
|
||||
return path, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback: use bundled headless shell
|
||||
chromeExec := "chrome-headless-shell"
|
||||
if runtime.GOOS == "windows" {
|
||||
chromeExec += ".exe"
|
||||
}
|
||||
return filepath.Join(c.chromePath, chromeExec)
|
||||
return "", errors.New("chrome path not found")
|
||||
}
|
||||
|
||||
10
converter/hideOthers.go
Normal file
10
converter/hideOthers.go
Normal file
@@ -0,0 +1,10 @@
|
||||
//go:build !windows
|
||||
|
||||
package converter
|
||||
|
||||
import "github.com/chromedp/chromedp"
|
||||
|
||||
func platformOptions() chromedp.ExecAllocatorOption {
|
||||
// Returns a no-op option for Mac/Linux
|
||||
return chromedp.NoSandbox
|
||||
}
|
||||
20
converter/hideWindows.go
Normal file
20
converter/hideWindows.go
Normal file
@@ -0,0 +1,20 @@
|
||||
//go:build windows
|
||||
|
||||
package converter
|
||||
|
||||
import (
|
||||
"os/exec"
|
||||
"syscall"
|
||||
|
||||
"github.com/chromedp/chromedp"
|
||||
)
|
||||
|
||||
func platformOptions() chromedp.ExecAllocatorOption {
|
||||
return chromedp.ModifyCmdFunc(func(cmd *exec.Cmd) {
|
||||
if cmd.SysProcAttr == nil {
|
||||
cmd.SysProcAttr = &syscall.SysProcAttr{}
|
||||
}
|
||||
cmd.SysProcAttr.HideWindow = true
|
||||
cmd.SysProcAttr.CreationFlags = 0x08000000 // CREATE_NO_WINDOW
|
||||
})
|
||||
}
|
||||
11
html2pdf.go
11
html2pdf.go
@@ -11,11 +11,16 @@ func Convert(chromePath, inputFile, outputFile string) error {
|
||||
Input: inputFile,
|
||||
Output: outputFile,
|
||||
}
|
||||
c := converter.NewConverter(chromePath)
|
||||
return c.Convert(input)
|
||||
c, err := converter.NewConverter(chromePath)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer c.Close()
|
||||
|
||||
return c.ConvertToPdf(input)
|
||||
}
|
||||
|
||||
// NewConverterInstance start new chrome headless shell instance
|
||||
func NewConverterInstance(chromePath string) *converter.Converter {
|
||||
func NewConverterInstance(chromePath string) (*converter.Converter, error) {
|
||||
return converter.NewConverter(chromePath)
|
||||
}
|
||||
|
||||
146
html2pdf_test.go
146
html2pdf_test.go
@@ -1,12 +1,15 @@
|
||||
package html2pdf
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.tecamino.com/paadi/html2pdf/converter"
|
||||
"gitea.tecamino.com/paadi/html2pdf/models"
|
||||
)
|
||||
|
||||
func TestConvert(t *testing.T) {
|
||||
@@ -27,23 +30,158 @@ func TestConvertFiles(t *testing.T) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
var input []converter.File
|
||||
var input []models.File
|
||||
for _, f := range files {
|
||||
ext := filepath.Ext(f.Name())
|
||||
if ext != ".html" {
|
||||
continue
|
||||
}
|
||||
|
||||
input = append(input, converter.File{
|
||||
input = append(input, models.File{
|
||||
Input: filepath.Join(rootPath, f.Name()),
|
||||
Output: strings.Replace(f.Name(), ext, ".pdf", 1),
|
||||
})
|
||||
}
|
||||
|
||||
c := converter.NewConverter("./assets")
|
||||
c, err := converter.NewConverter("assets/chrome-headless-shell/win64")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer c.Close()
|
||||
|
||||
if err := c.Convert(input...); err != nil {
|
||||
c.SetProgressCallback(func(progress int) {
|
||||
fmt.Println(progress)
|
||||
})
|
||||
|
||||
if err := c.ConvertToPdf(input...); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Log("test successfull")
|
||||
}
|
||||
|
||||
func TestConvertHtml(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>
|
||||
`)
|
||||
|
||||
tmpDir := t.TempDir()
|
||||
outputPath := filepath.Join(tmpDir, "test.pdf")
|
||||
|
||||
c, err := converter.NewConverter("assets/chrome-headless-shell/win64")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
defer c.Close()
|
||||
|
||||
err = c.ConvertHtmlsToPdf(models.Html{Html: html, Output: outputPath})
|
||||
if err != nil {
|
||||
t.Fatalf("ConvertHtml failed: %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")
|
||||
}
|
||||
|
||||
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")
|
||||
}
|
||||
|
||||
9
models/html.go
Normal file
9
models/html.go
Normal file
@@ -0,0 +1,9 @@
|
||||
package models
|
||||
|
||||
type Htmls []Html
|
||||
|
||||
// input model for converter
|
||||
type Html struct {
|
||||
Html []byte
|
||||
Output string
|
||||
}
|
||||
Reference in New Issue
Block a user