arsvendg/Stirling-PDF
1
0
Fork 0
mirror of https://github.com/arsvendg/Stirling-PDF.git synced 2026-07-16 19:33:11 +02:00
Code Issues Actions 4 Packages Projects Releases 1 Wiki Activity

Minor: Office doc changes (#6571)

Browse Source
This commit is contained in:
Anthony Stirling
2026-06-09 18:00:34 +01:00
committed by GitHub
parent 6478c400db
commit 71361f0d33
3 changed files with 687 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/core/src/main/java/stirling/software/SPDF/controller/api/converters/ConvertOfficeController.java
+7 -3
View File
@@ -35,6 +35,7 @@ import stirling.software.common.service.CustomPDFDocumentFactory;
import stirling.software.common.util.CustomHtmlSanitizer;
import stirling.software.common.util.ExceptionUtils;
import stirling.software.common.util.GeneralUtils;
import stirling.software.common.util.OfficeDocumentSanitizer;
import stirling.software.common.util.ProcessExecutor;
import stirling.software.common.util.ProcessExecutor.ProcessExecutorResult;
import stirling.software.common.util.RegexPatternUtils;
@@ -50,6 +51,7 @@ public class ConvertOfficeController {
private final CustomPDFDocumentFactory pdfDocumentFactory;
private final RuntimePathConfig runtimePathConfig;
private final CustomHtmlSanitizer customHtmlSanitizer;
private final OfficeDocumentSanitizer officeDocumentSanitizer;
private final EndpointConfiguration endpointConfiguration;
private final TempFileManager tempFileManager;
@@ -83,14 +85,16 @@ public class ConvertOfficeController {
Path inputPath = workDir.resolve(baseName + "." + extensionLower);
Path outputPath = workDir.resolve(baseName + ".pdf");
// Check if the file is HTML and apply sanitization if needed
// Sanitize input before LibreOffice sees it so embedded URLs can't trigger SSRF.
if ("html".equals(extensionLower) || "htm".equals(extensionLower)) {
// Read and sanitize HTML content
String htmlContent = new String(inputFile.getBytes(), StandardCharsets.UTF_8);
String sanitizedHtml = customHtmlSanitizer.sanitize(htmlContent);
Files.writeString(inputPath, sanitizedHtml, StandardCharsets.UTF_8);
} else if (officeDocumentSanitizer.isSanitizableExtension(extensionLower)) {
byte[] sanitized =
officeDocumentSanitizer.sanitize(inputFile.getBytes(), extensionLower);
Files.write(inputPath, sanitized);
} else {
// copy file content
Files.copy(inputFile.getInputStream(), inputPath, StandardCopyOption.REPLACE_EXISTING);
}