2023-08-01 01:03:13 +02:00
|
|
|
package stirling.software.SPDF.utils;
|
|
|
|
|
|
2024-02-01 23:41:49 +01:00
|
|
|
import io.github.pixee.security.ZipSecurity;
|
2023-08-01 01:03:13 +02:00
|
|
|
import java.io.ByteArrayInputStream;
|
|
|
|
|
import java.io.IOException;
|
2024-01-28 18:36:17 +01:00
|
|
|
import java.nio.charset.StandardCharsets;
|
2023-08-01 01:03:13 +02:00
|
|
|
import java.nio.file.Files;
|
|
|
|
|
import java.nio.file.Path;
|
|
|
|
|
import java.util.ArrayList;
|
|
|
|
|
import java.util.List;
|
|
|
|
|
import java.util.stream.Collectors;
|
|
|
|
|
import java.util.stream.Stream;
|
|
|
|
|
import java.util.zip.ZipEntry;
|
|
|
|
|
import java.util.zip.ZipInputStream;
|
|
|
|
|
|
2024-01-28 18:36:17 +01:00
|
|
|
import stirling.software.SPDF.model.api.converters.HTMLToPdfRequest;
|
2023-08-01 01:03:13 +02:00
|
|
|
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
|
|
|
|
|
|
|
|
|
public class FileToPdf {
|
2024-01-09 23:39:21 +01:00
|
|
|
|
|
|
|
|
public static byte[] convertHtmlToPdf(
|
2024-01-28 18:36:17 +01:00
|
|
|
HTMLToPdfRequest request,
|
|
|
|
|
byte[] fileBytes,
|
|
|
|
|
String fileName,
|
|
|
|
|
boolean htmlFormatsInstalled)
|
2023-08-01 01:03:13 +02:00
|
|
|
throws IOException, InterruptedException {
|
|
|
|
|
|
|
|
|
|
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
|
|
|
|
|
Path tempInputFile = null;
|
|
|
|
|
byte[] pdfBytes;
|
|
|
|
|
try {
|
|
|
|
|
if (fileName.endsWith(".html")) {
|
|
|
|
|
tempInputFile = Files.createTempFile("input_", ".html");
|
|
|
|
|
Files.write(tempInputFile, fileBytes);
|
|
|
|
|
} else {
|
|
|
|
|
tempInputFile = unzipAndGetMainHtml(fileBytes);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
List<String> command = new ArrayList<>();
|
2024-01-09 23:39:21 +01:00
|
|
|
if (!htmlFormatsInstalled) {
|
|
|
|
|
command.add("weasyprint");
|
|
|
|
|
} else {
|
|
|
|
|
command.add("wkhtmltopdf");
|
2024-01-10 01:33:07 +01:00
|
|
|
command.add("--enable-local-file-access");
|
2024-01-18 22:57:41 +01:00
|
|
|
command.add("--load-error-handling");
|
|
|
|
|
command.add("ignore");
|
|
|
|
|
command.add("--load-media-error-handling");
|
|
|
|
|
command.add("ignore");
|
2024-01-28 18:36:17 +01:00
|
|
|
command.add("--zoom");
|
|
|
|
|
command.add(String.valueOf(request.getZoom()));
|
|
|
|
|
|
|
|
|
|
// if custom zoom add zoom style direct to html
|
|
|
|
|
// https://github.com/wkhtmltopdf/wkhtmltopdf/issues/4900
|
|
|
|
|
if (request.getZoom() != 1.0) {
|
|
|
|
|
String htmlContent = new String(Files.readAllBytes(tempInputFile));
|
|
|
|
|
|
|
|
|
|
String zoomStyle = "<style>body { zoom: " + request.getZoom() + "; }</style>";
|
|
|
|
|
// Check for <head> tag, add style tag to associated tag
|
|
|
|
|
if (htmlContent.contains("<head>")) {
|
|
|
|
|
htmlContent = htmlContent.replace("<head>", "<head>" + zoomStyle);
|
|
|
|
|
} else if (htmlContent.contains("<html>")) {
|
|
|
|
|
// If no <head> tag, but <html> tag exists
|
|
|
|
|
htmlContent = htmlContent.replace("<html>", "<html>" + zoomStyle);
|
|
|
|
|
} else {
|
|
|
|
|
// If neither <head> nor <html> tags exist
|
|
|
|
|
htmlContent = zoomStyle + htmlContent;
|
|
|
|
|
}
|
|
|
|
|
// rewrite new html to file
|
|
|
|
|
Files.write(tempInputFile, htmlContent.getBytes(StandardCharsets.UTF_8));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (request.getPageWidth() != null) {
|
|
|
|
|
command.add("--page-width");
|
|
|
|
|
command.add(request.getPageWidth() + "cm");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (request.getPageHeight() != null) {
|
|
|
|
|
command.add("--page-height");
|
|
|
|
|
command.add(request.getPageHeight() + "cm");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (request.getMarginTop() != null) {
|
|
|
|
|
command.add("--margin-top");
|
|
|
|
|
command.add(request.getMarginTop() + "mm");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
// Repeat similar pattern for marginBottom, marginLeft, marginRight
|
|
|
|
|
|
|
|
|
|
if ("Yes".equalsIgnoreCase(request.getPrintBackground())) {
|
|
|
|
|
command.add("--background");
|
|
|
|
|
} else {
|
|
|
|
|
command.add("--no-background");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if ("Yes".equalsIgnoreCase(request.getDefaultHeader())) {
|
|
|
|
|
command.add("--default-header");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if ("print".equalsIgnoreCase(request.getCssMediaType())) {
|
|
|
|
|
command.add("--print-media-type");
|
|
|
|
|
} else if ("screen".equalsIgnoreCase(request.getCssMediaType())) {
|
|
|
|
|
command.add("--no-print-media-type");
|
|
|
|
|
}
|
2024-01-09 23:39:21 +01:00
|
|
|
}
|
2024-01-10 01:33:07 +01:00
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
command.add(tempInputFile.toString());
|
|
|
|
|
command.add(tempOutputFile.toString());
|
|
|
|
|
ProcessExecutorResult returnCode;
|
|
|
|
|
if (fileName.endsWith(".zip")) {
|
2024-01-09 23:39:21 +01:00
|
|
|
|
|
|
|
|
if (htmlFormatsInstalled) {
|
2024-01-10 01:33:07 +01:00
|
|
|
// command.add(1, "--allow");
|
|
|
|
|
// command.add(2, tempInputFile.getParent().toString());
|
2024-01-09 23:39:21 +01:00
|
|
|
}
|
2023-08-01 01:03:13 +02:00
|
|
|
returnCode =
|
|
|
|
|
ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
|
|
|
|
|
.runCommandWithOutputHandling(
|
|
|
|
|
command, tempInputFile.getParent().toFile());
|
2023-12-30 20:11:27 +01:00
|
|
|
} else {
|
2023-08-01 01:03:13 +02:00
|
|
|
|
|
|
|
|
returnCode =
|
|
|
|
|
ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
|
|
|
|
|
.runCommandWithOutputHandling(command);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
pdfBytes = Files.readAllBytes(tempOutputFile);
|
2024-01-19 00:28:39 +01:00
|
|
|
} catch (IOException e) {
|
|
|
|
|
pdfBytes = Files.readAllBytes(tempOutputFile);
|
|
|
|
|
if (pdfBytes.length < 1) {
|
|
|
|
|
throw e;
|
|
|
|
|
}
|
2023-08-01 01:03:13 +02:00
|
|
|
} finally {
|
2024-01-19 00:28:39 +01:00
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
// Clean up temporary files
|
|
|
|
|
Files.delete(tempOutputFile);
|
|
|
|
|
Files.delete(tempInputFile);
|
|
|
|
|
|
|
|
|
|
if (fileName.endsWith(".zip")) {
|
|
|
|
|
GeneralUtils.deleteDirectory(tempInputFile.getParent());
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
return pdfBytes;
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
|
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
private static Path unzipAndGetMainHtml(byte[] fileBytes) throws IOException {
|
|
|
|
|
Path tempDirectory = Files.createTempDirectory("unzipped_");
|
2024-02-01 23:41:49 +01:00
|
|
|
try (ZipInputStream zipIn = ZipSecurity.createHardenedInputStream(new ByteArrayInputStream(fileBytes))) {
|
2023-08-01 01:03:13 +02:00
|
|
|
ZipEntry entry = zipIn.getNextEntry();
|
|
|
|
|
while (entry != null) {
|
|
|
|
|
Path filePath = tempDirectory.resolve(entry.getName());
|
|
|
|
|
if (entry.isDirectory()) {
|
|
|
|
|
Files.createDirectories(filePath); // Explicitly create the directory structure
|
2023-12-30 20:11:27 +01:00
|
|
|
} else {
|
2023-08-01 01:03:13 +02:00
|
|
|
Files.createDirectories(
|
|
|
|
|
filePath.getParent()); // Create parent directories if they don't exist
|
|
|
|
|
Files.copy(zipIn, filePath);
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
2023-08-01 01:03:13 +02:00
|
|
|
zipIn.closeEntry();
|
|
|
|
|
entry = zipIn.getNextEntry();
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
// search for the main HTML file.
|
|
|
|
|
try (Stream<Path> walk = Files.walk(tempDirectory)) {
|
|
|
|
|
List<Path> htmlFiles =
|
|
|
|
|
walk.filter(file -> file.toString().endsWith(".html"))
|
|
|
|
|
.collect(Collectors.toList());
|
2023-12-30 20:11:27 +01:00
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
if (htmlFiles.isEmpty()) {
|
|
|
|
|
throw new IOException("No HTML files found in the unzipped directory.");
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
|
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
// Prioritize 'index.html' if it exists, otherwise use the first .html file
|
|
|
|
|
for (Path htmlFile : htmlFiles) {
|
2024-02-02 01:29:18 +01:00
|
|
|
if ("index.html".equals(htmlFile.getFileName().toString())) {
|
2023-08-01 01:03:13 +02:00
|
|
|
return htmlFile;
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2023-08-01 01:03:13 +02:00
|
|
|
return htmlFiles.get(0);
|
|
|
|
|
}
|
2023-12-30 20:11:27 +01:00
|
|
|
}
|
2024-01-09 23:39:21 +01:00
|
|
|
|
|
|
|
|
public static byte[] convertBookTypeToPdf(byte[] bytes, String originalFilename)
|
|
|
|
|
throws IOException, InterruptedException {
|
|
|
|
|
if (originalFilename == null || originalFilename.lastIndexOf('.') == -1) {
|
|
|
|
|
throw new IllegalArgumentException("Invalid original filename.");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
String fileExtension = originalFilename.substring(originalFilename.lastIndexOf('.'));
|
|
|
|
|
List<String> command = new ArrayList<>();
|
|
|
|
|
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
|
|
|
|
|
Path tempInputFile = null;
|
|
|
|
|
|
|
|
|
|
try {
|
|
|
|
|
// Create temp file with appropriate extension
|
|
|
|
|
tempInputFile = Files.createTempFile("input_", fileExtension);
|
|
|
|
|
Files.write(tempInputFile, bytes);
|
|
|
|
|
|
|
|
|
|
command.add("ebook-convert");
|
|
|
|
|
command.add(tempInputFile.toString());
|
|
|
|
|
command.add(tempOutputFile.toString());
|
|
|
|
|
ProcessExecutorResult returnCode =
|
|
|
|
|
ProcessExecutor.getInstance(ProcessExecutor.Processes.CALIBRE)
|
|
|
|
|
.runCommandWithOutputHandling(command);
|
|
|
|
|
|
|
|
|
|
return Files.readAllBytes(tempOutputFile);
|
|
|
|
|
} finally {
|
|
|
|
|
// Clean up temporary files
|
|
|
|
|
if (tempInputFile != null) {
|
|
|
|
|
Files.deleteIfExists(tempInputFile);
|
|
|
|
|
}
|
|
|
|
|
Files.deleteIfExists(tempOutputFile);
|
|
|
|
|
}
|
|
|
|
|
}
|
2023-08-01 01:03:13 +02:00
|
|
|
}
|
