# Description of Changes

<!--
Please provide a summary of the changes, including:

- What was changed
- Why the change was made
- Any challenges encountered

Closes #(issue_number)
-->

---

## Checklist

### General

- [ ] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have read the [Stirling-PDF Developer
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md)
(if applicable)
- [ ] I have read the [How to add new languages to
Stirling-PDF](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md)
(if applicable)
- [ ] I have performed a self-review of my own code
- [ ] My changes generate no new warnings

### Documentation

- [ ] I have updated relevant docs on [Stirling-PDF's doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
(if functionality has heavily changed)
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)

### UI Changes (if applicable)

- [ ] Screenshots or videos demonstrating the UI changes are attached
(e.g., as comments or direct attachments in the PR)

### Testing (if applicable)

- [ ] I have tested my changes locally. Refer to the [Testing
Guide](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/devGuide/DeveloperGuide.md#6-testing)
for more details.

---------

Signed-off-by: dependabot[bot] <[email protected]>
Signed-off-by: Balázs Szücs <[email protected]>
Signed-off-by: stirlingbot[bot] <stirlingbot[bot]@users.noreply.github.com>
Co-authored-by: ConnorYoh <[email protected]>
Co-authored-by: Connor Yoh <[email protected]>
Co-authored-by: OUNZAR Aymane <[email protected]>
Co-authored-by: YAOU Reda <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com>
Co-authored-by: Balázs Szücs <[email protected]>
Co-authored-by: Ludy <[email protected]>
Co-authored-by: tkymmm <[email protected]>
Co-authored-by: Peter Dave Hello <[email protected]>
Co-authored-by: albanobattistella <[email protected]>
Co-authored-by: PingLin8888 <[email protected]>
Co-authored-by: FdaSilvaYY <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: OteJlo <[email protected]>
Co-authored-by: Angel <[email protected]>
Co-authored-by: Ricardo Catarino <[email protected]>
Co-authored-by: Luis Antonio Argüelles González <[email protected]>
Co-authored-by: Dawid Urbański <[email protected]>
Co-authored-by: Stephan Paternotte <[email protected]>
Co-authored-by: Leonardo Santos Paulucio <[email protected]>
Co-authored-by: hamza khalem <[email protected]>
Co-authored-by: IT Creativity + Art Team <[email protected]>
Co-authored-by: Reece Browne <[email protected]>
Co-authored-by: James Brunton <[email protected]>
Co-authored-by: Victor Villarreal <[email protected]>
This commit is contained in:
Anthony Stirling
2025-12-21 10:40:32 +00:00
committed by GitHub
co-authored by ConnorYoh Connor Yoh OUNZAR Aymane YAOU Reda dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> stirlingbot[bot] <195170888+stirlingbot[bot]@users.noreply.github.com> Balázs Szücs Ludy tkymmm Peter Dave Hello albanobattistella PingLin8888 FdaSilvaYY Copilot OteJlo Angel Ricardo Catarino Luis Antonio Argüelles González Dawid Urbański Stephan Paternotte Leonardo Santos Paulucio hamza khalem IT Creativity + Art Team Reece Browne James Brunton Victor Villarreal
parent a5dcdd5bd9
commit 68ed54e398
343 changed files with 25208 additions and 6588 deletions
@@ -334,6 +334,9 @@ public class EndpointConfiguration {
addEndpointToGroup("Convert", "pdf-to-csv");
addEndpointToGroup("Convert", "pdf-to-markdown");
addEndpointToGroup("Convert", "eml-to-pdf");
addEndpointToGroup("Convert", "pdf-to-vector");
addEndpointToGroup("Convert", "vector-to-pdf");
addEndpointToGroup("Convert", "pdf-to-video");
addEndpointToGroup("Convert", "cbz-to-pdf");
addEndpointToGroup("Convert", "pdf-to-cbz");
addEndpointToGroup("Convert", "pdf-to-json");
@@ -490,6 +493,10 @@ public class EndpointConfiguration {
/* Ghostscript */
addEndpointToGroup("Ghostscript", "repair");
addEndpointToGroup("Ghostscript", "compress-pdf");
addEndpointToGroup("Ghostscript", "crop");
addEndpointToGroup("Ghostscript", "replace-invert-pdf");
addEndpointToGroup("Ghostscript", "pdf-to-vector");
addEndpointToGroup("Ghostscript", "vector-to-pdf");
/* ImageMagick */
addEndpointToGroup("ImageMagick", "compress-pdf");
@@ -554,7 +561,7 @@ public class EndpointConfiguration {
disableGroup("enterprise");
}
if (!applicationProperties.getSystem().getEnableUrlToPDF()) {
if (!applicationProperties.getSystem().isEnableUrlToPDF()) {
disableEndpoint("url-to-pdf");
}
}
@@ -37,7 +37,7 @@ public class AutoJobAspect {
@Around("@annotation(autoJobPostMapping)")
public Object wrapWithJobExecution(
ProceedingJoinPoint joinPoint, AutoJobPostMapping autoJobPostMapping) {
ProceedingJoinPoint joinPoint, AutoJobPostMapping autoJobPostMapping) throws Exception {
// This aspect will run before any audit aspects due to @Order(0)
// Extract parameters from the request and annotation
boolean async = Boolean.parseBoolean(request.getParameter("async"));
@@ -81,6 +81,12 @@ public class AutoJobAspect {
"AutoJobAspect caught exception during job execution: {}",
ex.getMessage(),
ex);
// Rethrow RuntimeException as-is to preserve exception type
if (ex instanceof RuntimeException) {
throw (RuntimeException) ex;
}
// Wrap checked exceptions - GlobalExceptionHandler will unwrap
// BaseAppException
throw new RuntimeException(ex);
}
},
@@ -109,7 +115,8 @@ public class AutoJobAspect {
int maxRetries,
boolean trackProgress,
boolean queueable,
int resourceWeight) {
int resourceWeight)
throws Exception {
// Keep jobId reference for progress tracking in TaskManager
AtomicReference<String> jobIdRef = new AtomicReference<>();
@@ -207,6 +214,12 @@ public class AutoJobAspect {
// If we get here, all retries failed
if (lastException != null) {
// Rethrow RuntimeException as-is to preserve exception type
if (lastException instanceof RuntimeException) {
throw (RuntimeException) lastException;
}
// Wrap checked exceptions - GlobalExceptionHandler will unwrap
// BaseAppException
throw new RuntimeException(
"Job failed after "
+ maxRetries
@@ -76,7 +76,7 @@ public class AppConfig {
@Bean(name = "loginEnabled")
public boolean loginEnabled() {
return applicationProperties.getSecurity().getEnableLogin();
return applicationProperties.getSecurity().isEnableLogin();
}
@Bean(name = "appName")
@@ -120,9 +120,7 @@ public class AppConfig {
@Bean(name = "enableAlphaFunctionality")
public boolean enableAlphaFunctionality() {
return applicationProperties.getSystem().getEnableAlphaFunctionality() != null
? applicationProperties.getSystem().getEnableAlphaFunctionality()
: false;
return applicationProperties.getSystem().isEnableAlphaFunctionality();
}
@Bean(name = "rateLimit")
@@ -265,9 +263,14 @@ public class AppConfig {
return "NORMAL";
}
@Bean(name = "disablePixel")
public boolean disablePixel() {
return Boolean.parseBoolean(env.getProperty("DISABLE_PIXEL", "false"));
@Bean(name = "scarfEnabled")
public boolean scarfEnabled() {
return applicationProperties.getSystem().isScarfEnabled();
}
@Bean(name = "posthogEnabled")
public boolean posthogEnabled() {
return applicationProperties.getSystem().isPosthogEnabled();
}
@Bean(name = "machineType")
@@ -2,6 +2,7 @@ package stirling.software.common.configuration;
import java.io.File;
import java.nio.file.Paths;
import java.util.Locale;
import lombok.extern.slf4j.Slf4j;
@@ -61,7 +62,7 @@ public class InstallationPathConfig {
private static String initializeBasePath() {
if (Boolean.parseBoolean(System.getProperty("STIRLING_PDF_DESKTOP_UI", "false"))) {
String os = System.getProperty("os.name").toLowerCase();
String os = System.getProperty("os.name").toLowerCase(Locale.ROOT);
if (os.contains("win")) {
return Paths.get(
System.getenv("APPDATA"), // parent path
@@ -10,8 +10,10 @@ import lombok.Getter;
import lombok.extern.slf4j.Slf4j;
import stirling.software.common.model.ApplicationProperties;
import stirling.software.common.model.ApplicationProperties.CustomPaths;
import stirling.software.common.model.ApplicationProperties.CustomPaths.Operations;
import stirling.software.common.model.ApplicationProperties.CustomPaths.Pipeline;
import stirling.software.common.model.ApplicationProperties.System;
@Slf4j
@Configuration
@@ -19,8 +21,16 @@ import stirling.software.common.model.ApplicationProperties.CustomPaths.Pipeline
public class RuntimePathConfig {
private final ApplicationProperties properties;
private final String basePath;
// Operation paths
private final String weasyPrintPath;
private final String unoConvertPath;
private final String calibrePath;
private final String ocrMyPdfPath;
private final String sOfficePath;
// Tesseract data path
private final String tessDataPath;
// Pipeline paths
private final String pipelineWatchedFoldersPath;
@@ -37,7 +47,10 @@ public class RuntimePathConfig {
String defaultFinishedFolders = Path.of(this.pipelinePath, "finishedFolders").toString();
String defaultWebUIConfigs = Path.of(this.pipelinePath, "defaultWebUIConfigs").toString();
Pipeline pipeline = properties.getSystem().getCustomPaths().getPipeline();
System system = properties.getSystem();
CustomPaths customPaths = system.getCustomPaths();
Pipeline pipeline = customPaths.getPipeline();
this.pipelineWatchedFoldersPath =
resolvePath(
@@ -57,8 +70,11 @@ public class RuntimePathConfig {
// Initialize Operation paths
String defaultWeasyPrintPath = isDocker ? "/opt/venv/bin/weasyprint" : "weasyprint";
String defaultUnoConvertPath = isDocker ? "/opt/venv/bin/unoconvert" : "unoconvert";
String defaultCalibrePath = isDocker ? "/opt/calibre/ebook-convert" : "ebook-convert";
String defaultOcrMyPdfPath = isDocker ? "/usr/bin/ocrmypdf" : "ocrmypdf";
String defaultSOfficePath = isDocker ? "/usr/bin/soffice" : "soffice";
Operations operations = properties.getSystem().getCustomPaths().getOperations();
Operations operations = customPaths.getOperations();
this.weasyPrintPath =
resolvePath(
defaultWeasyPrintPath,
@@ -67,6 +83,28 @@ public class RuntimePathConfig {
resolvePath(
defaultUnoConvertPath,
operations != null ? operations.getUnoconvert() : null);
this.calibrePath =
resolvePath(
defaultCalibrePath, operations != null ? operations.getCalibre() : null);
this.ocrMyPdfPath =
resolvePath(
defaultOcrMyPdfPath, operations != null ? operations.getOcrmypdf() : null);
this.sOfficePath =
resolvePath(
defaultSOfficePath, operations != null ? operations.getSoffice() : null);
// Initialize Tesseract data path
String defaultTessDataPath =
isDocker ? "/usr/share/tesseract-ocr/5/tessdata" : "/usr/share/tessdata";
String tessPath = system.getTessdataDir();
String tessdataDir = java.lang.System.getenv("TESSDATA_PREFIX");
this.tessDataPath =
resolvePath(
defaultTessDataPath,
(tessPath != null && !tessPath.isEmpty()) ? tessPath : tessdataDir);
log.info("Using Tesseract data path: {}", this.tessDataPath);
}
private String resolvePath(String defaultPath, String customPath) {
@@ -12,6 +12,7 @@ import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collection;
import java.util.List;
import java.util.Locale;
import org.springframework.boot.context.properties.ConfigurationProperties;
import org.springframework.context.annotation.Bean;
@@ -152,7 +153,7 @@ public class ApplicationProperties {
@Data
public static class Security {
private Boolean enableLogin;
private boolean enableLogin;
private InitialLogin initialLogin = new InitialLogin();
private OAUTH2 oauth2 = new OAUTH2();
private SAML2 saml2 = new SAML2();
@@ -327,7 +328,7 @@ public class ApplicationProperties {
private KeycloakProvider keycloak = new KeycloakProvider();
public Provider get(String registrationId) throws UnsupportedProviderException {
return switch (registrationId.toLowerCase()) {
return switch (registrationId.toLowerCase(Locale.ROOT)) {
case "google" -> getGoogle();
case "github" -> getGithub();
case "keycloak" -> getKeycloak();
@@ -335,8 +336,8 @@ public class ApplicationProperties {
throw new UnsupportedProviderException(
"Logout from the provider "
+ registrationId
+ " is not supported. "
+ "Report it at https://github.com/Stirling-Tools/Stirling-PDF/issues");
+ " is not supported. Report it at"
+ " https://github.com/Stirling-Tools/Stirling-PDF/issues");
};
}
}
@@ -389,20 +390,20 @@ public class ApplicationProperties {
@Data
public static class System {
private String defaultLocale;
private Boolean googlevisibility;
private boolean googlevisibility;
private boolean showUpdate;
private Boolean showUpdateOnlyAdmin;
private boolean showUpdateOnlyAdmin;
private boolean customHTMLFiles;
private String tessdataDir;
private Boolean enableAlphaFunctionality;
private boolean enableAlphaFunctionality;
private Boolean enableAnalytics;
private Boolean enablePosthog;
private Boolean enableScarf;
private Boolean enableDesktopInstallSlide;
private Datasource datasource;
private Boolean disableSanitize;
private boolean disableSanitize;
private int maxDPI;
private Boolean enableUrlToPDF;
private boolean enableUrlToPDF;
private Html html = new Html();
private CustomPaths customPaths = new CustomPaths();
private String fileUploadLimit;
@@ -454,6 +455,9 @@ public class ApplicationProperties {
public static class Operations {
private String weasyprint;
private String unoconvert;
private String calibre;
private String ocrmypdf;
private String soffice;
}
}
@@ -536,10 +540,10 @@ public class ApplicationProperties {
@Override
public String toString() {
return """
Driver {
driverName='%s'
}
"""
Driver {
driverName='%s'
}
"""
.formatted(driverName);
}
}
@@ -571,7 +575,7 @@ public class ApplicationProperties {
@Data
public static class Metrics {
private Boolean enabled;
private boolean enabled;
}
@Data
@@ -668,6 +672,25 @@ public class ApplicationProperties {
public static class EnterpriseFeatures {
private PersistentMetrics persistentMetrics = new PersistentMetrics();
private Audit audit = new Audit();
private DatabaseNotifications databaseNotifications = new DatabaseNotifications();
@Data
public static class DatabaseNotifications {
private Backup backups = new Backup();
private Imports imports = new Imports();
@Data
public static class Backup {
private boolean successful = false;
private boolean failed = false;
}
@Data
public static class Imports {
private boolean successful = false;
private boolean failed = false;
}
}
@Data
public static class Audit {
@@ -702,6 +725,7 @@ public class ApplicationProperties {
private int tesseractSessionLimit;
private int ghostscriptSessionLimit;
private int ocrMyPdfSessionLimit;
private int ffmpegSessionLimit;
public int getQpdfSessionLimit() {
return qpdfSessionLimit > 0 ? qpdfSessionLimit : 2;
@@ -746,6 +770,10 @@ public class ApplicationProperties {
public int getOcrMyPdfSessionLimit() {
return ocrMyPdfSessionLimit > 0 ? ocrMyPdfSessionLimit : 2;
}
public int getFfmpegSessionLimit() {
return ffmpegSessionLimit > 0 ? ffmpegSessionLimit : 2;
}
}
@Data
@@ -774,6 +802,7 @@ public class ApplicationProperties {
private long qpdfTimeoutMinutes;
private long ghostscriptTimeoutMinutes;
private long ocrMyPdfTimeoutMinutes;
private long ffmpegTimeoutMinutes;
public long getTesseractTimeoutMinutes() {
return tesseractTimeoutMinutes > 0 ? tesseractTimeoutMinutes : 30;
@@ -818,6 +847,10 @@ public class ApplicationProperties {
public long getOcrMyPdfTimeoutMinutes() {
return ocrMyPdfTimeoutMinutes > 0 ? ocrMyPdfTimeoutMinutes : 30;
}
public long getFfmpegTimeoutMinutes() {
return ffmpegTimeoutMinutes > 0 ? ffmpegTimeoutMinutes : 30;
}
}
}
}
@@ -30,11 +30,11 @@ public class FileInfo {
// Formats the file size into a human-readable string.
public String getFormattedFileSize() {
if (fileSize >= 1024 * 1024 * 1024) {
return String.format(Locale.US, "%.2f GB", fileSize / (1024.0 * 1024 * 1024));
return String.format(Locale.ROOT, "%.2f GB", fileSize / (1024.0 * 1024 * 1024));
} else if (fileSize >= 1024 * 1024) {
return String.format(Locale.US, "%.2f MB", fileSize / (1024.0 * 1024));
return String.format(Locale.ROOT, "%.2f MB", fileSize / (1024.0 * 1024));
} else if (fileSize >= 1024) {
return String.format(Locale.US, "%.2f KB", fileSize / 1024.0);
return String.format(Locale.ROOT, "%.2f KB", fileSize / 1024.0);
} else {
return String.format("%d Bytes", fileSize);
}
@@ -7,6 +7,7 @@ import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.StandardCopyOption;
import java.util.Locale;
import java.util.concurrent.atomic.AtomicLong;
import org.apache.pdfbox.Loader;
@@ -249,7 +250,7 @@ public class CustomPDFDocumentFactory {
log.debug(
"Memory status - Free: {}MB ({}%), Used: {}MB, Max: {}MB",
actualFreeMemory / (1024 * 1024),
String.format("%.2f", freeMemoryPercent),
String.format(Locale.ROOT, "%.2f", freeMemoryPercent),
usedMemory / (1024 * 1024),
maxMemory / (1024 * 1024));
@@ -258,7 +259,7 @@ public class CustomPDFDocumentFactory {
|| actualFreeMemory < MIN_FREE_MEMORY_BYTES) {
log.debug(
"Low memory detected ({}%), forcing file-based cache",
String.format("%.2f", freeMemoryPercent));
String.format(Locale.ROOT, "%.2f", freeMemoryPercent));
return createScratchFileCacheFunction(MemoryUsageSetting.setupTempFileOnly());
} else if (contentSize < SMALL_FILE_THRESHOLD) {
log.debug("Using memory-only cache for small document ({}KB)", contentSize / 1024);
@@ -477,11 +478,6 @@ public class CustomPDFDocumentFactory {
return file;
}
/** Create a uniquely named temporary directory */
private Path createTempDirectory(String prefix) throws IOException {
return Files.createTempDirectory(prefix + tempCounter.incrementAndGet() + "-");
}
/** Create new document bytes based on an existing document */
public byte[] createNewBytesBasedOnOldDocument(byte[] oldDocument) throws IOException {
try (PDDocument document = load(oldDocument)) {
@@ -253,6 +253,22 @@ public class JobExecutorService {
log.error("Synchronous job timed out after {} ms", timeoutToUse);
return ResponseEntity.internalServerError()
.body(Map.of("error", "Job timed out after " + timeoutToUse + " ms"));
} catch (RuntimeException e) {
// Check if this is a wrapped typed exception that should be handled by
// GlobalExceptionHandler
Throwable cause = e.getCause();
if (cause instanceof stirling.software.common.util.ExceptionUtils.BaseAppException
|| cause
instanceof
stirling.software.common.util.ExceptionUtils
.BaseValidationException) {
// Rethrow so GlobalExceptionHandler can handle with proper HTTP status codes
throw e;
}
// Handle other RuntimeExceptions as generic errors
log.error("Error executing synchronous job: {}", e.getMessage(), e);
return ResponseEntity.internalServerError()
.body(Map.of("error", "Job failed: " + e.getMessage()));
} catch (Exception e) {
log.error("Error executing synchronous job: {}", e.getMessage(), e);
// Construct a JSON error response
@@ -253,7 +253,7 @@ public class PostHogService {
addIfNotEmpty(
properties,
"security_enableLogin",
applicationProperties.getSecurity().getEnableLogin());
applicationProperties.getSecurity().isEnableLogin());
addIfNotEmpty(properties, "security_csrfDisabled", true);
addIfNotEmpty(
properties,
@@ -299,13 +299,13 @@ public class PostHogService {
addIfNotEmpty(
properties,
"system_googlevisibility",
applicationProperties.getSystem().getGooglevisibility());
applicationProperties.getSystem().isGooglevisibility());
addIfNotEmpty(
properties, "system_showUpdate", applicationProperties.getSystem().isShowUpdate());
addIfNotEmpty(
properties,
"system_showUpdateOnlyAdmin",
applicationProperties.getSystem().getShowUpdateOnlyAdmin());
applicationProperties.getSystem().isShowUpdateOnlyAdmin());
addIfNotEmpty(
properties,
"system_customHTMLFiles",
@@ -317,7 +317,7 @@ public class PostHogService {
addIfNotEmpty(
properties,
"system_enableAlphaFunctionality",
applicationProperties.getSystem().getEnableAlphaFunctionality());
applicationProperties.getSystem().isEnableAlphaFunctionality());
addIfNotEmpty(
properties,
"system_enableAnalytics",
@@ -337,7 +337,7 @@ public class PostHogService {
// Capture Metrics properties
addIfNotEmpty(
properties, "metrics_enabled", applicationProperties.getMetrics().getEnabled());
properties, "metrics_enabled", applicationProperties.getMetrics().isEnabled());
// Capture EnterpriseEdition properties
addIfNotEmpty(
@@ -5,6 +5,7 @@ import java.lang.management.MemoryMXBean;
import java.lang.management.OperatingSystemMXBean;
import java.time.Duration;
import java.time.Instant;
import java.util.Locale;
import java.util.concurrent.Executors;
import java.util.concurrent.ScheduledExecutorService;
import java.util.concurrent.TimeUnit;
@@ -173,8 +174,8 @@ public class ResourceMonitor {
log.info("System resource status changed from {} to {}", oldStatus, newStatus);
log.info(
"Current metrics - CPU: {}%, Memory: {}%, Free Memory: {} MB",
String.format("%.1f", cpuUsage * 100),
String.format("%.1f", memoryUsage * 100),
String.format(Locale.ROOT, "%.1f", cpuUsage * 100),
String.format(Locale.ROOT, "%.1f", memoryUsage * 100),
freeMemory / (1024 * 1024));
}
} catch (Exception e) {
@@ -5,6 +5,7 @@ import java.net.Inet6Address;
import java.net.InetAddress;
import java.net.URI;
import java.net.UnknownHostException;
import java.util.Locale;
import java.util.regex.Pattern;
import org.springframework.stereotype.Service;
@@ -83,7 +84,7 @@ public class SsrfProtectionService {
return false;
}
return config.getAllowedDomains().contains(host.toLowerCase());
return config.getAllowedDomains().contains(host.toLowerCase(Locale.ROOT));
} catch (Exception e) {
log.debug("Failed to parse URL for MAX security check: {}", url, e);
@@ -101,7 +102,7 @@ public class SsrfProtectionService {
return false;
}
String hostLower = host.toLowerCase();
String hostLower = host.toLowerCase(Locale.ROOT);
// Check explicit blocked domains
if (config.getBlockedDomains().contains(hostLower)) {
@@ -111,7 +112,7 @@ public class SsrfProtectionService {
// Check internal TLD patterns
for (String tld : config.getInternalTlds()) {
if (hostLower.endsWith(tld.toLowerCase())) {
if (hostLower.endsWith(tld.toLowerCase(Locale.ROOT))) {
log.debug("URL blocked by internal TLD pattern '{}': {}", tld, url);
return false;
}
@@ -123,9 +124,11 @@ public class SsrfProtectionService {
config.getAllowedDomains().stream()
.anyMatch(
domain ->
hostLower.equals(domain.toLowerCase())
hostLower.equals(domain.toLowerCase(Locale.ROOT))
|| hostLower.endsWith(
"." + domain.toLowerCase()));
"."
+ domain.toLowerCase(
Locale.ROOT)));
if (!isAllowed) {
log.debug("URL not in allowed domains list: {}", url);
@@ -7,6 +7,7 @@ import java.time.LocalDateTime;
import java.time.temporal.ChronoUnit;
import java.util.ArrayList;
import java.util.List;
import java.util.Locale;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.Executors;
@@ -101,14 +102,16 @@ public class TaskManager {
if (!extractedFiles.isEmpty()) {
jobResult.completeWithFiles(extractedFiles);
log.debug(
"Set multiple file results for job ID: {} with {} files extracted from ZIP",
"Set multiple file results for job ID: {} with {} files extracted from"
+ " ZIP",
jobId,
extractedFiles.size());
return;
}
} catch (Exception e) {
log.warn(
"Failed to extract ZIP file for job {}: {}. Falling back to single file result.",
"Failed to extract ZIP file for job {}: {}. Falling back to single file"
+ " result.",
jobId,
e.getMessage());
}
@@ -342,12 +345,12 @@ public class TaskManager {
/** Check if a file is a ZIP file based on content type and filename */
private boolean isZipFile(String contentType, String fileName) {
if (contentType != null
&& (contentType.equals("application/zip")
|| contentType.equals("application/x-zip-compressed"))) {
&& ("application/zip".equals(contentType)
|| "application/x-zip-compressed".equals(contentType))) {
return true;
}
if (fileName != null && fileName.toLowerCase().endsWith(".zip")) {
if (fileName != null && fileName.toLowerCase(Locale.ROOT).endsWith(".zip")) {
return true;
}
@@ -414,7 +417,7 @@ public class TaskManager {
return MediaType.APPLICATION_OCTET_STREAM_VALUE;
}
String lowerName = fileName.toLowerCase();
String lowerName = fileName.toLowerCase(Locale.ROOT);
if (lowerName.endsWith(".pdf")) {
return MediaType.APPLICATION_PDF_VALUE;
} else if (lowerName.endsWith(".txt")) {
@@ -6,6 +6,7 @@ import java.io.InputStream;
import java.util.ArrayList;
import java.util.Comparator;
import java.util.List;
import java.util.Locale;
import org.apache.commons.io.FilenameUtils;
import org.apache.pdfbox.pdmodel.PDDocument;
@@ -58,31 +59,24 @@ public class CbrUtils {
log.warn(
"Failed to open CBR/RAR archive due to corrupt header: {}",
e.getMessage());
throw ExceptionUtils.createIllegalArgumentException(
"error.invalidFormat",
"Invalid or corrupted CBR/RAR archive. "
+ "The file may be corrupted, use an unsupported RAR format (RAR5+), "
+ "or may not be a valid RAR archive. "
+ "Please ensure the file is a valid RAR archive.");
throw ExceptionUtils.createCbrInvalidFormatException(null);
} catch (RarException e) {
log.warn("Failed to open CBR/RAR archive: {}", e.getMessage());
String errorMessage;
String exMessage = e.getMessage() != null ? e.getMessage() : "";
if (exMessage.contains("encrypted")) {
errorMessage = "Encrypted CBR/RAR archives are not supported.";
throw ExceptionUtils.createCbrEncryptedException();
} else if (exMessage.isEmpty()) {
errorMessage =
"Invalid CBR/RAR archive. "
+ "The file may be encrypted, corrupted, or use an unsupported format.";
throw ExceptionUtils.createCbrInvalidFormatException(
"Invalid CBR/RAR archive. The file may be encrypted, corrupted, or"
+ " use an unsupported format.");
} else {
errorMessage =
throw ExceptionUtils.createCbrInvalidFormatException(
"Invalid CBR/RAR archive: "
+ exMessage
+ ". The file may be encrypted, corrupted, or use an unsupported format.";
+ ". The file may be encrypted, corrupted, or use an"
+ " unsupported format.");
}
throw ExceptionUtils.createIllegalArgumentException(
"error.invalidFormat", errorMessage);
} catch (IOException e) {
log.warn("IO error reading CBR/RAR archive: {}", e.getMessage());
throw ExceptionUtils.createFileProcessingException("CBR extraction", e);
@@ -121,7 +115,8 @@ public class CbrUtils {
if (imageEntries.isEmpty()) {
throw ExceptionUtils.createIllegalArgumentException(
"error.fileProcessing",
"No valid images found in the CBR file. The archive may be empty or contain no supported image formats.");
"No valid images found in the CBR file. The archive may be empty or"
+ " contain no supported image formats.");
}
for (ImageEntryData imageEntry : imageEntries) {
@@ -146,7 +141,8 @@ public class CbrUtils {
if (document.getNumberOfPages() == 0) {
throw ExceptionUtils.createIllegalArgumentException(
"error.fileProcessing",
"No images could be processed from the CBR file. All images may be corrupted or in unsupported formats.");
"No images could be processed from the CBR file. All images may be"
+ " corrupted or in unsupported formats.");
}
ByteArrayOutputStream baos = new ByteArrayOutputStream();
@@ -159,7 +155,6 @@ public class CbrUtils {
return GeneralUtils.optimizePdfWithGhostscript(pdfBytes);
} catch (IOException e) {
log.warn("Ghostscript optimization failed, returning unoptimized PDF", e);
return pdfBytes;
}
}
@@ -170,17 +165,17 @@ public class CbrUtils {
private void validateCbrFile(MultipartFile file) {
if (file == null || file.isEmpty()) {
throw new IllegalArgumentException("File cannot be null or empty");
throw ExceptionUtils.createFileNullOrEmptyException();
}
String filename = file.getOriginalFilename();
if (filename == null) {
throw new IllegalArgumentException("File must have a name");
throw ExceptionUtils.createFileNoNameException();
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
if (!"cbr".equals(extension) && !"rar".equals(extension)) {
throw new IllegalArgumentException("File must be a CBR or RAR archive");
throw ExceptionUtils.createNotCbrFileException();
}
}
@@ -190,7 +185,7 @@ public class CbrUtils {
return false;
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
return "cbr".equals(extension) || "rar".equals(extension);
}
@@ -8,6 +8,7 @@ import java.util.ArrayList;
import java.util.Comparator;
import java.util.Enumeration;
import java.util.List;
import java.util.Locale;
import java.util.zip.ZipEntry;
import java.util.zip.ZipFile;
import java.util.zip.ZipInputStream;
@@ -55,10 +56,10 @@ public class CbzUtils {
new java.io.FileInputStream(tempFile.getFile()));
ZipInputStream zis = new ZipInputStream(bis)) {
if (zis.getNextEntry() == null) {
throw new IllegalArgumentException("Archive is empty or invalid ZIP");
throw ExceptionUtils.createCbzEmptyException();
}
} catch (IOException e) {
throw new IllegalArgumentException("Invalid CBZ/ZIP archive", e);
throw ExceptionUtils.createCbzInvalidFormatException(e);
}
try (PDDocument document = pdfDocumentFactory.createNewDocument();
@@ -83,7 +84,7 @@ public class CbzUtils {
Comparator.comparing(ImageEntryData::name, new NaturalOrderComparator()));
if (imageEntries.isEmpty()) {
throw new IllegalArgumentException("No valid images found in the CBZ file");
throw ExceptionUtils.createCbzNoImagesException();
}
for (ImageEntryData imageEntry : imageEntries) {
@@ -106,8 +107,7 @@ public class CbzUtils {
}
if (document.getNumberOfPages() == 0) {
throw new IllegalArgumentException(
"No images could be processed from the CBZ file");
throw ExceptionUtils.createCbzCorruptedImagesException();
}
ByteArrayOutputStream baos = new ByteArrayOutputStream();
document.save(baos);
@@ -119,7 +119,6 @@ public class CbzUtils {
return GeneralUtils.optimizePdfWithGhostscript(pdfBytes);
} catch (IOException e) {
log.warn("Ghostscript optimization failed, returning unoptimized PDF", e);
return pdfBytes;
}
}
@@ -130,17 +129,17 @@ public class CbzUtils {
private void validateCbzFile(MultipartFile file) {
if (file == null || file.isEmpty()) {
throw new IllegalArgumentException("File cannot be null or empty");
throw ExceptionUtils.createFileNullOrEmptyException();
}
String filename = file.getOriginalFilename();
if (filename == null) {
throw new IllegalArgumentException("File must have a name");
throw ExceptionUtils.createFileNoNameException();
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
if (!"cbz".equals(extension) && !"zip".equals(extension)) {
throw new IllegalArgumentException("File must be a CBZ or ZIP archive");
throw ExceptionUtils.createNotCbzFileException();
}
}
@@ -150,7 +149,7 @@ public class CbzUtils {
return false;
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
return "cbz".equals(extension) || "zip".equals(extension);
}
@@ -160,7 +159,7 @@ public class CbzUtils {
return false;
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
return "cbz".equals(extension)
|| "zip".equals(extension)
|| "cbr".equals(extension)
@@ -11,6 +11,8 @@ public class CheckProgramInstall {
private static final List<String> PYTHON_COMMANDS = Arrays.asList("python3", "python");
private static boolean pythonAvailableChecked = false;
private static String availablePythonCommand = null;
private static boolean ffmpegAvailableChecked = false;
private static boolean ffmpegAvailable = false;
/**
* Checks which Python command is available and returns it.
@@ -56,4 +58,25 @@ public class CheckProgramInstall {
public static boolean isPythonAvailable() {
return getAvailablePythonCommand() != null;
}
/**
* Checks if FFmpeg is available on the system.
*
* @return true if FFmpeg is installed and accessible, false otherwise.
*/
public static boolean isFfmpegAvailable() {
if (!ffmpegAvailableChecked) {
try {
ProcessExecutorResult result =
ProcessExecutor.getInstance(ProcessExecutor.Processes.FFMPEG)
.runCommandWithOutputHandling(Arrays.asList("ffmpeg", "-version"));
ffmpegAvailable = true;
} catch (IOException | InterruptedException e) {
ffmpegAvailable = false;
} finally {
ffmpegAvailableChecked = true;
}
}
return ffmpegAvailable;
}
}
@@ -58,14 +58,11 @@ public class ChecksumUtils {
* @throws IOException if reading from the stream fails
*/
public static String checksum(InputStream is, String algorithm) throws IOException {
switch (algorithm.toUpperCase(Locale.ROOT)) {
case "CRC32":
return checksumChecksum(is, new CRC32());
case "ADLER32":
return checksumChecksum(is, new Adler32());
default:
return toHex(checksumBytes(is, algorithm));
}
return switch (algorithm.toUpperCase(Locale.ROOT)) {
case "CRC32" -> checksumChecksum(is, new CRC32());
case "ADLER32" -> checksumChecksum(is, new Adler32());
default -> toHex(checksumBytes(is, algorithm));
};
}
/**
@@ -98,14 +95,13 @@ public class ChecksumUtils {
* @throws IOException if reading from the stream fails
*/
public static String checksumBase64(InputStream is, String algorithm) throws IOException {
switch (algorithm.toUpperCase(Locale.ROOT)) {
case "CRC32":
return Base64.getEncoder().encodeToString(checksumChecksumBytes(is, new CRC32()));
case "ADLER32":
return Base64.getEncoder().encodeToString(checksumChecksumBytes(is, new Adler32()));
default:
return Base64.getEncoder().encodeToString(checksumBytes(is, algorithm));
}
return switch (algorithm.toUpperCase(Locale.ROOT)) {
case "CRC32" ->
Base64.getEncoder().encodeToString(checksumChecksumBytes(is, new CRC32()));
case "ADLER32" ->
Base64.getEncoder().encodeToString(checksumChecksumBytes(is, new Adler32()));
default -> Base64.getEncoder().encodeToString(checksumBytes(is, algorithm));
};
}
/**
@@ -179,7 +175,7 @@ public class ChecksumUtils {
for (Map.Entry<String, Checksum> entry : checksums.entrySet()) {
// Keep value as long and mask to ensure unsigned hex formatting.
long unsigned32 = entry.getValue().getValue() & UNSIGNED_32_BIT_MASK;
results.put(entry.getKey(), String.format("%08x", unsigned32));
results.put(entry.getKey(), String.format(Locale.ROOT, "%08x", unsigned32));
}
return results;
}
@@ -258,7 +254,7 @@ public class ChecksumUtils {
}
// Keep as long and mask to ensure correct unsigned representation.
long unsigned32 = checksum.getValue() & UNSIGNED_32_BIT_MASK;
return String.format("%08x", unsigned32);
return String.format(Locale.ROOT, "%08x", unsigned32);
}
/**
@@ -294,7 +290,7 @@ public class ChecksumUtils {
private static String toHex(byte[] hash) {
StringBuilder sb = new StringBuilder(hash.length * 2);
for (byte b : hash) {
sb.append(String.format("%02x", b));
sb.append(String.format(Locale.ROOT, "%02x", b));
}
return sb.toString();
}
@@ -62,8 +62,7 @@ public class CustomHtmlSanitizer {
.and(new HtmlPolicyBuilder().disallowElements("noscript").toFactory());
public String sanitize(String html) {
boolean disableSanitize =
Boolean.TRUE.equals(applicationProperties.getSystem().getDisableSanitize());
boolean disableSanitize = applicationProperties.getSystem().isDisableSanitize();
return disableSanitize ? html : POLICY.sanitize(html);
}
}
@@ -11,6 +11,7 @@ import java.time.ZonedDateTime;
import java.util.ArrayList;
import java.util.Date;
import java.util.List;
import java.util.Locale;
import java.util.Properties;
import java.util.regex.Pattern;
@@ -229,7 +230,8 @@ public class EmlParser {
Method getContentType = message.getClass().getMethod("getContentType");
String contentType = (String) getContentType.invoke(message);
if (contentType != null && contentType.toLowerCase().contains(TEXT_HTML)) {
if (contentType != null
&& contentType.toLowerCase(Locale.ROOT).contains(TEXT_HTML)) {
content.setHtmlBody(stringContent);
} else {
content.setTextBody(stringContent);
@@ -296,7 +298,7 @@ public class EmlParser {
String contentType = (String) getContentType.invoke(part);
String normalizedDisposition =
disposition != null ? ((String) disposition).toLowerCase() : null;
disposition != null ? ((String) disposition).toLowerCase(Locale.ROOT) : null;
if ((Boolean) isMimeType.invoke(part, TEXT_PLAIN) && normalizedDisposition == null) {
Object partContent = getContent.invoke(part);
@@ -422,7 +424,7 @@ public class EmlParser {
RegexPatternUtils.getInstance().getNewlineSplitPattern().split(emlContent);
for (int i = 0; i < lines.length; i++) {
String line = lines[i];
if (line.toLowerCase().startsWith(headerName.toLowerCase())) {
if (line.toLowerCase(Locale.ROOT).startsWith(headerName.toLowerCase(Locale.ROOT))) {
StringBuilder value =
new StringBuilder(line.substring(headerName.length()).trim());
for (int j = i + 1; j < lines.length; j++) {
@@ -444,7 +446,7 @@ public class EmlParser {
private static String extractHtmlBody(String emlContent) {
try {
String lowerContent = emlContent.toLowerCase();
String lowerContent = emlContent.toLowerCase(Locale.ROOT);
int htmlStart = lowerContent.indexOf(HEADER_CONTENT_TYPE + " " + TEXT_HTML);
if (htmlStart == -1) return null;
@@ -463,7 +465,7 @@ public class EmlParser {
private static String extractTextBody(String emlContent) {
try {
String lowerContent = emlContent.toLowerCase();
String lowerContent = emlContent.toLowerCase(Locale.ROOT);
int textStart = lowerContent.indexOf(HEADER_CONTENT_TYPE + " " + TEXT_PLAIN);
if (textStart == -1) {
int bodyStart = emlContent.indexOf("\r\n\r\n");
@@ -516,7 +518,7 @@ public class EmlParser {
String currentEncoding = "";
for (String line : lines) {
String lowerLine = line.toLowerCase().trim();
String lowerLine = line.toLowerCase(Locale.ROOT).trim();
if (line.trim().isEmpty()) {
inHeaders = false;
@@ -554,9 +556,12 @@ public class EmlParser {
}
private static boolean isAttachment(String disposition, String filename, String contentType) {
return (disposition.toLowerCase().contains(DISPOSITION_ATTACHMENT) && !filename.isEmpty())
|| (!filename.isEmpty() && !contentType.toLowerCase().startsWith("text/"))
|| (contentType.toLowerCase().contains("application/") && !filename.isEmpty());
return (disposition.toLowerCase(Locale.ROOT).contains(DISPOSITION_ATTACHMENT)
&& !filename.isEmpty())
|| (!filename.isEmpty()
&& !contentType.toLowerCase(Locale.ROOT).startsWith("text/"))
|| (contentType.toLowerCase(Locale.ROOT).contains("application/")
&& !filename.isEmpty());
}
private static String extractFilenameFromDisposition(String disposition) {
@@ -565,8 +570,8 @@ public class EmlParser {
}
// Handle filename*= (RFC 2231 encoded filename)
if (disposition.toLowerCase().contains("filename*=")) {
int filenameStarStart = disposition.toLowerCase().indexOf("filename*=") + 10;
if (disposition.toLowerCase(Locale.ROOT).contains("filename*=")) {
int filenameStarStart = disposition.toLowerCase(Locale.ROOT).indexOf("filename*=") + 10;
int filenameStarEnd = disposition.indexOf(";", filenameStarStart);
if (filenameStarEnd == -1) filenameStarEnd = disposition.length();
String extendedFilename =
@@ -586,7 +591,7 @@ public class EmlParser {
}
// Handle regular filename=
int filenameStart = disposition.toLowerCase().indexOf("filename=") + 9;
int filenameStart = disposition.toLowerCase(Locale.ROOT).indexOf("filename=") + 9;
int filenameEnd = disposition.indexOf(";", filenameStart);
if (filenameEnd == -1) filenameEnd = disposition.length();
String filename = disposition.substring(filenameStart, filenameEnd).trim();
@@ -48,11 +48,11 @@ public class EmlProcessingUtils {
public static void validateEmlInput(byte[] emlBytes) {
if (emlBytes == null || emlBytes.length == 0) {
throw new IllegalArgumentException("EML file is empty or null");
throw ExceptionUtils.createEmlEmptyException();
}
if (isInvalidEmlFormat(emlBytes)) {
throw new IllegalArgumentException("Invalid EML file format");
throw ExceptionUtils.createEmlInvalidFormatException();
}
}
@@ -109,12 +109,13 @@ public class EmlProcessingUtils {
html.append(
String.format(
Locale.ROOT,
"""
<!DOCTYPE html>
<html lang="en"><head><meta charset="UTF-8">
<title>%s</title>
<style>
""",
<!DOCTYPE html>
<html lang="en"><head><meta charset="UTF-8">
<title>%s</title>
<style>
""",
sanitizeText(content.getSubject(), customHtmlSanitizer)));
appendEnhancedStyles(html);
@@ -127,14 +128,15 @@ public class EmlProcessingUtils {
html.append(
String.format(
Locale.ROOT,
"""
<div class="email-container">
<div class="email-header">
<h1>%s</h1>
<div class="email-meta">
<div><strong>From:</strong> %s</div>
<div><strong>To:</strong> %s</div>
""",
<div class="email-container">
<div class="email-header">
<h1>%s</h1>
<div class="email-meta">
<div><strong>From:</strong> %s</div>
<div><strong>To:</strong> %s</div>
""",
sanitizeText(content.getSubject(), customHtmlSanitizer),
sanitizeText(content.getFrom(), customHtmlSanitizer),
sanitizeText(content.getTo(), customHtmlSanitizer)));
@@ -142,6 +144,7 @@ public class EmlProcessingUtils {
if (content.getCc() != null && !content.getCc().trim().isEmpty()) {
html.append(
String.format(
Locale.ROOT,
"<div><strong>CC:</strong> %s</div>\n",
sanitizeText(content.getCc(), customHtmlSanitizer)));
}
@@ -149,6 +152,7 @@ public class EmlProcessingUtils {
if (content.getBcc() != null && !content.getBcc().trim().isEmpty()) {
html.append(
String.format(
Locale.ROOT,
"<div><strong>BCC:</strong> %s</div>\n",
sanitizeText(content.getBcc(), customHtmlSanitizer)));
}
@@ -156,11 +160,13 @@ public class EmlProcessingUtils {
if (content.getDate() != null) {
html.append(
String.format(
Locale.ROOT,
"<div><strong>Date:</strong> %s</div>\n",
PdfAttachmentHandler.formatEmailDate(content.getDate())));
} else if (content.getDateString() != null && !content.getDateString().trim().isEmpty()) {
html.append(
String.format(
Locale.ROOT,
"<div><strong>Date:</strong> %s</div>\n",
sanitizeText(content.getDateString(), customHtmlSanitizer)));
}
@@ -175,6 +181,7 @@ public class EmlProcessingUtils {
} else if (content.getTextBody() != null && !content.getTextBody().trim().isEmpty()) {
html.append(
String.format(
Locale.ROOT,
"<div class=\"text-body\">%s</div>",
convertTextToHtml(content.getTextBody(), customHtmlSanitizer)));
} else {
@@ -234,14 +241,16 @@ public class EmlProcessingUtils {
.getUrlLinkPattern()
.matcher(html)
.replaceAll(
"<a href=\"$1\" style=\"color: #1a73e8; text-decoration: underline;\">$1</a>");
"<a href=\"$1\" style=\"color: #1a73e8; text-decoration:"
+ " underline;\">$1</a>");
html =
RegexPatternUtils.getInstance()
.getEmailLinkPattern()
.matcher(html)
.replaceAll(
"<a href=\"mailto:$1\" style=\"color: #1a73e8; text-decoration: underline;\">$1</a>");
"<a href=\"mailto:$1\" style=\"color: #1a73e8; text-decoration:"
+ " underline;\">$1</a>");
return html;
}
@@ -249,127 +258,128 @@ public class EmlProcessingUtils {
private static void appendEnhancedStyles(StringBuilder html) {
String css =
String.format(
Locale.ROOT,
"""
body {
font-family: %s;
font-size: %dpx;
line-height: %s;
color: %s;
margin: 0;
padding: 16px;
background-color: %s;
}
body {
font-family: %s;
font-size: %dpx;
line-height: %s;
color: %s;
margin: 0;
padding: 16px;
background-color: %s;
}
.email-container {
width: 100%%;
max-width: 100%%;
margin: 0 auto;
}
.email-container {
width: 100%%;
max-width: 100%%;
margin: 0 auto;
}
.email-header {
padding-bottom: 10px;
border-bottom: 1px solid %s;
margin-bottom: 10px;
}
.email-header {
padding-bottom: 10px;
border-bottom: 1px solid %s;
margin-bottom: 10px;
}
.email-header h1 {
margin: 0 0 10px 0;
font-size: %dpx;
font-weight: bold;
}
.email-header h1 {
margin: 0 0 10px 0;
font-size: %dpx;
font-weight: bold;
}
.email-meta div {
margin-bottom: 2px;
font-size: %dpx;
}
.email-meta div {
margin-bottom: 2px;
font-size: %dpx;
}
.email-body {
word-wrap: break-word;
}
.email-body {
word-wrap: break-word;
}
.attachment-section {
margin-top: 15px;
padding: 10px;
background-color: %s;
border: 1px solid %s;
border-radius: 3px;
}
.attachment-section {
margin-top: 15px;
padding: 10px;
background-color: %s;
border: 1px solid %s;
border-radius: 3px;
}
.attachment-section h3 {
margin: 0 0 8px 0;
font-size: %dpx;
}
.attachment-section h3 {
margin: 0 0 8px 0;
font-size: %dpx;
}
.attachment-item {
padding: 5px 0;
}
.attachment-item {
padding: 5px 0;
}
.attachment-icon {
margin-right: 5px;
}
.attachment-icon {
margin-right: 5px;
}
.attachment-details, .attachment-type {
font-size: %dpx;
color: #555555;
}
.attachment-details, .attachment-type {
font-size: %dpx;
color: #555555;
}
.attachment-inclusion-note, .attachment-info-note {
margin-top: 8px;
padding: 6px;
font-size: %dpx;
border-radius: 3px;
}
.attachment-inclusion-note, .attachment-info-note {
margin-top: 8px;
padding: 6px;
font-size: %dpx;
border-radius: 3px;
}
.attachment-inclusion-note {
background-color: #e6ffed;
border: 1px solid #d4f7dc;
color: #006420;
}
.attachment-inclusion-note {
background-color: #e6ffed;
border: 1px solid #d4f7dc;
color: #006420;
}
.attachment-info-note {
background-color: #fff9e6;
border: 1px solid #fff0c2;
color: #664d00;
}
.attachment-info-note {
background-color: #fff9e6;
border: 1px solid #fff0c2;
color: #664d00;
}
.attachment-link-container {
display: flex;
align-items: center;
padding: 8px;
background-color: #f8f9fa;
border: 1px solid #dee2e6;
border-radius: 4px;
margin: 4px 0;
}
.attachment-link-container {
display: flex;
align-items: center;
padding: 8px;
background-color: #f8f9fa;
border: 1px solid #dee2e6;
border-radius: 4px;
margin: 4px 0;
}
.attachment-link-container:hover {
background-color: #e9ecef;
}
.attachment-link-container:hover {
background-color: #e9ecef;
}
.attachment-note {
font-size: %dpx;
color: #6c757d;
font-style: italic;
margin-left: 8px;
}
.attachment-note {
font-size: %dpx;
color: #6c757d;
font-style: italic;
margin-left: 8px;
}
.no-content {
padding: 20px;
text-align: center;
color: #666;
font-style: italic;
}
.no-content {
padding: 20px;
text-align: center;
color: #666;
font-style: italic;
}
.text-body {
white-space: pre-wrap;
}
.text-body {
white-space: pre-wrap;
}
img {
max-width: 100%%;
height: auto;
display: block;
}
""",
img {
max-width: 100%%;
height: auto;
display: block;
}
""",
DEFAULT_FONT_FAMILY,
DEFAULT_FONT_SIZE,
DEFAULT_LINE_HEIGHT,
@@ -420,13 +430,14 @@ public class EmlProcessingUtils {
String attachmentId = "attachment_" + i;
html.append(
String.format(
Locale.ROOT,
"""
<div class="attachment-item" id="%s">
<span class="attachment-icon" data-filename="%s">@</span>
<span class="attachment-name">%s</span>
<span class="attachment-details">(%s%s)</span>
</div>
""",
<div class="attachment-item" id="%s">
<span class="attachment-icon" data-filename="%s">@</span>
<span class="attachment-name">%s</span>
<span class="attachment-details">(%s%s)</span>
</div>
""",
attachmentId,
escapeHtml(embeddedFilename),
escapeHtml(EmlParser.safeMimeDecode(attachment.getFilename())),
@@ -470,7 +481,7 @@ public class EmlProcessingUtils {
}
if (filename != null) {
String lowerFilename = filename.toLowerCase();
String lowerFilename = filename.toLowerCase(Locale.ROOT);
for (Map.Entry<String, String> entry : EXTENSION_TO_MIME_TYPE.entrySet()) {
if (lowerFilename.endsWith(entry.getKey())) {
return entry.getValue();
@@ -516,7 +527,7 @@ public class EmlProcessingUtils {
result.append(processedText, lastEnd, matcher.start());
String charset = matcher.group(1);
String encoding = matcher.group(2).toUpperCase();
String encoding = matcher.group(2).toUpperCase(Locale.ROOT);
String encodedValue = matcher.group(3);
try {
File diff suppressed because it is too large Load Diff
@@ -5,13 +5,11 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.UncheckedIOException;
import java.nio.charset.StandardCharsets;
import java.nio.file.FileVisitResult;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.SimpleFileVisitor;
import java.nio.file.attribute.BasicFileAttributes;
import java.util.ArrayList;
import java.util.List;
import java.util.Locale;
import java.util.stream.Stream;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
@@ -37,9 +35,11 @@ public class FileToPdf {
try (TempFile tempInputFile =
new TempFile(
tempFileManager,
fileName.toLowerCase().endsWith(".html") ? ".html" : ".zip")) {
fileName.toLowerCase(Locale.ROOT).endsWith(".html")
? ".html"
: ".zip")) {
if (fileName.toLowerCase().endsWith(".html")) {
if (fileName.toLowerCase(Locale.ROOT).endsWith(".html")) {
String sanitizedHtml =
sanitizeHtmlContent(
new String(fileBytes, StandardCharsets.UTF_8),
@@ -47,7 +47,7 @@ public class FileToPdf {
Files.write(
tempInputFile.getPath(),
sanitizedHtml.getBytes(StandardCharsets.UTF_8));
} else if (fileName.toLowerCase().endsWith(".zip")) {
} else if (fileName.toLowerCase(Locale.ROOT).endsWith(".zip")) {
Files.write(tempInputFile.getPath(), fileBytes);
sanitizeHtmlFilesInZip(
tempInputFile.getPath(), tempFileManager, customHtmlSanitizer);
@@ -102,8 +102,8 @@ public class FileToPdf {
tempUnzippedDir.getPath().resolve(sanitizeZipFilename(entry.getName()));
if (!entry.isDirectory()) {
Files.createDirectories(filePath.getParent());
if (entry.getName().toLowerCase().endsWith(".html")
|| entry.getName().toLowerCase().endsWith(".htm")) {
if (entry.getName().toLowerCase(Locale.ROOT).endsWith(".html")
|| entry.getName().toLowerCase(Locale.ROOT).endsWith(".htm")) {
String content =
new String(zipIn.readAllBytes(), StandardCharsets.UTF_8);
String sanitizedContent =
@@ -145,64 +145,6 @@ public class FileToPdf {
}
}
private static void deleteDirectory(Path dir) throws IOException {
Files.walkFileTree(
dir,
new SimpleFileVisitor<Path>() {
@Override
public FileVisitResult visitFile(Path file, BasicFileAttributes attrs)
throws IOException {
Files.delete(file);
return FileVisitResult.CONTINUE;
}
@Override
public FileVisitResult postVisitDirectory(Path dir, IOException exc)
throws IOException {
Files.delete(dir);
return FileVisitResult.CONTINUE;
}
});
}
private static Path unzipAndGetMainHtml(byte[] fileBytes) throws IOException {
Path tempDirectory = Files.createTempDirectory("unzipped_");
try (ZipInputStream zipIn =
ZipSecurity.createHardenedInputStream(new ByteArrayInputStream(fileBytes))) {
ZipEntry entry = zipIn.getNextEntry();
while (entry != null) {
Path filePath = tempDirectory.resolve(sanitizeZipFilename(entry.getName()));
if (entry.isDirectory()) {
Files.createDirectories(filePath); // Explicitly create the directory structure
} else {
Files.createDirectories(
filePath.getParent()); // Create parent directories if they don't exist
Files.copy(zipIn, filePath);
}
zipIn.closeEntry();
entry = zipIn.getNextEntry();
}
}
// Search for the main HTML file.
try (Stream<Path> walk = Files.walk(tempDirectory)) {
List<Path> htmlFiles = walk.filter(file -> file.toString().endsWith(".html")).toList();
if (htmlFiles.isEmpty()) {
throw new IOException("No HTML files found in the unzipped directory.");
}
// Prioritize 'index.html' if it exists, otherwise use the first .html file
for (Path htmlFile : htmlFiles) {
if ("index.html".equals(htmlFile.getFileName().toString())) {
return htmlFile;
}
}
return htmlFiles.get(0);
}
}
static String sanitizeZipFilename(String entryName) {
if (entryName == null || entryName.trim().isEmpty()) {
return "";
@@ -0,0 +1,350 @@
package stirling.software.common.util;
import java.io.IOException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Optional;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.common.PDRectangle;
import org.apache.pdfbox.pdmodel.font.PDType1Font;
import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationWidget;
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
import org.apache.pdfbox.pdmodel.interactive.form.PDTerminalField;
import lombok.experimental.UtilityClass;
import lombok.extern.slf4j.Slf4j;
/**
* Utility class for copying and transforming PDF form fields during page operations. Used by
* multi-page layout and other page manipulation operations that need to preserve form fields.
*/
@Slf4j
@UtilityClass
public class GeneralFormCopyUtils {
public boolean hasAnyRotatedPage(PDDocument document) {
try {
for (PDPage page : document.getPages()) {
int rot = page.getRotation();
int norm = ((rot % 360) + 360) % 360;
if (norm != 0) {
return true;
}
}
} catch (Exception e) {
log.warn("Failed to inspect page rotations: {}", e.getMessage(), e);
}
return false;
}
public void copyAndTransformFormFields(
PDDocument sourceDocument,
PDDocument newDocument,
int totalPages,
int pagesPerSheet,
int cols,
int rows,
float cellWidth,
float cellHeight)
throws IOException {
PDDocumentCatalog sourceCatalog = sourceDocument.getDocumentCatalog();
PDAcroForm sourceAcroForm = sourceCatalog.getAcroForm();
if (sourceAcroForm == null || sourceAcroForm.getFields().isEmpty()) {
return;
}
PDDocumentCatalog newCatalog = newDocument.getDocumentCatalog();
PDAcroForm newAcroForm = new PDAcroForm(newDocument);
newCatalog.setAcroForm(newAcroForm);
PDResources dr = new PDResources();
PDType1Font helvetica = new PDType1Font(Standard14Fonts.FontName.HELVETICA);
PDType1Font zapfDingbats = new PDType1Font(Standard14Fonts.FontName.ZAPF_DINGBATS);
dr.put(COSName.getPDFName("Helv"), helvetica);
dr.put(COSName.getPDFName("ZaDb"), zapfDingbats);
newAcroForm.setDefaultResources(dr);
newAcroForm.setDefaultAppearance("/Helv 12 Tf 0 g");
// Temporarily set NeedAppearances to true during field creation
newAcroForm.setNeedAppearances(true);
Map<String, Integer> fieldNameCounters = new HashMap<>();
// Build widget -> field map once for efficient lookups
Map<PDAnnotationWidget, PDField> widgetFieldMap = buildWidgetFieldMap(sourceAcroForm);
for (int pageIndex = 0; pageIndex < totalPages; pageIndex++) {
PDPage sourcePage = sourceDocument.getPage(pageIndex);
List<PDAnnotation> annotations = sourcePage.getAnnotations();
if (annotations.isEmpty()) {
continue;
}
int destinationPageIndex = pageIndex / pagesPerSheet;
int adjustedPageIndex = pageIndex % pagesPerSheet;
int rowIndex = adjustedPageIndex / cols;
int colIndex = adjustedPageIndex % cols;
if (rowIndex >= rows) {
continue;
}
if (destinationPageIndex >= newDocument.getNumberOfPages()) {
continue;
}
PDPage destinationPage = newDocument.getPage(destinationPageIndex);
PDRectangle sourceRect = sourcePage.getMediaBox();
float scaleWidth = cellWidth / sourceRect.getWidth();
float scaleHeight = cellHeight / sourceRect.getHeight();
float scale = Math.min(scaleWidth, scaleHeight);
float x = colIndex * cellWidth + (cellWidth - sourceRect.getWidth() * scale) / 2;
float y =
destinationPage.getMediaBox().getHeight()
- ((rowIndex + 1) * cellHeight
- (cellHeight - sourceRect.getHeight() * scale) / 2);
copyBasicFormFields(
sourceAcroForm,
newAcroForm,
sourcePage,
destinationPage,
x,
y,
scale,
pageIndex,
fieldNameCounters,
widgetFieldMap);
}
// Generate appearance streams and embed them authoritatively
boolean appearancesGenerated = false;
try {
newAcroForm.refreshAppearances();
appearancesGenerated = true;
} catch (NoSuchMethodError nsme) {
log.warn(
"AcroForm.refreshAppearances() not available in this PDFBox version; "
+ "leaving NeedAppearances=true for viewer-side rendering.");
} catch (Exception t) {
log.warn(
"Failed to refresh field appearances via AcroForm: {}. "
+ "Leaving NeedAppearances=true as fallback.",
t.getMessage(),
t);
}
// After successful appearance generation, set NeedAppearances to false
// to signal that appearance streams are now embedded authoritatively
if (appearancesGenerated) {
try {
newAcroForm.setNeedAppearances(false);
} catch (Exception e) {
log.debug(
"Failed to set NeedAppearances to false: {}. "
+ "Appearances were generated but flag could not be updated.",
e.getMessage());
}
}
}
private void copyBasicFormFields(
PDAcroForm sourceAcroForm,
PDAcroForm newAcroForm,
PDPage sourcePage,
PDPage destinationPage,
float offsetX,
float offsetY,
float scale,
int pageIndex,
Map<String, Integer> fieldNameCounters,
Map<PDAnnotationWidget, PDField> widgetFieldMap) {
try {
List<PDAnnotation> sourceAnnotations = sourcePage.getAnnotations();
List<PDAnnotation> destinationAnnotations = destinationPage.getAnnotations();
for (PDAnnotation annotation : sourceAnnotations) {
if (annotation instanceof PDAnnotationWidget widgetAnnotation) {
if (widgetAnnotation.getRectangle() == null) {
continue;
}
PDField sourceField =
widgetFieldMap != null ? widgetFieldMap.get(widgetAnnotation) : null;
if (sourceField == null) {
continue; // skip widgets without a matching field
}
if (!(sourceField instanceof PDTerminalField terminalField)) {
continue;
}
GeneralFormFieldTypeSupport handler =
GeneralFormFieldTypeSupport.forField(terminalField);
if (handler == null) {
log.debug(
"Skipping unsupported field type '{}' for widget '{}'",
sourceField.getClass().getSimpleName(),
Optional.ofNullable(sourceField.getFullyQualifiedName())
.orElseGet(sourceField::getPartialName));
continue;
}
copyFieldUsingHandler(
handler,
terminalField,
newAcroForm,
destinationPage,
destinationAnnotations,
widgetAnnotation,
offsetX,
offsetY,
scale,
pageIndex,
fieldNameCounters);
}
}
} catch (Exception e) {
log.warn(
"Failed to copy basic form fields for page {}: {}",
pageIndex,
e.getMessage(),
e);
}
}
private void copyFieldUsingHandler(
GeneralFormFieldTypeSupport handler,
PDTerminalField sourceField,
PDAcroForm newAcroForm,
PDPage destinationPage,
List<PDAnnotation> destinationAnnotations,
PDAnnotationWidget sourceWidget,
float offsetX,
float offsetY,
float scale,
int pageIndex,
Map<String, Integer> fieldNameCounters) {
try {
PDTerminalField newField = handler.createField(newAcroForm);
boolean initialized =
initializeFieldWithWidget(
newAcroForm,
destinationPage,
destinationAnnotations,
newField,
sourceField.getPartialName(),
handler.fallbackWidgetName(),
sourceWidget,
offsetX,
offsetY,
scale,
pageIndex,
fieldNameCounters);
if (!initialized) {
return;
}
handler.copyFromOriginal(sourceField, newField);
} catch (Exception e) {
log.warn(
"Failed to copy {} field '{}': {}",
handler.typeName(),
Optional.ofNullable(sourceField.getFullyQualifiedName())
.orElseGet(sourceField::getPartialName),
e.getMessage(),
e);
}
}
private <T extends PDTerminalField> boolean initializeFieldWithWidget(
PDAcroForm newAcroForm,
PDPage destinationPage,
List<PDAnnotation> destinationAnnotations,
T newField,
String originalName,
String fallbackName,
PDAnnotationWidget sourceWidget,
float offsetX,
float offsetY,
float scale,
int pageIndex,
Map<String, Integer> fieldNameCounters) {
String baseName = (originalName != null) ? originalName : fallbackName;
String newFieldName = generateUniqueFieldName(baseName, pageIndex, fieldNameCounters);
newField.setPartialName(newFieldName);
PDAnnotationWidget newWidget = new PDAnnotationWidget();
PDRectangle sourceRect = sourceWidget.getRectangle();
if (sourceRect == null) {
return false;
}
float newX = (sourceRect.getLowerLeftX() * scale) + offsetX;
float newY = (sourceRect.getLowerLeftY() * scale) + offsetY;
float newWidth = sourceRect.getWidth() * scale;
float newHeight = sourceRect.getHeight() * scale;
newWidget.setRectangle(new PDRectangle(newX, newY, newWidth, newHeight));
newWidget.setPage(destinationPage);
newField.getWidgets().add(newWidget);
newWidget.setParent(newField);
newAcroForm.getFields().add(newField);
destinationAnnotations.add(newWidget);
return true;
}
private String generateUniqueFieldName(
String originalName, int pageIndex, Map<String, Integer> fieldNameCounters) {
String baseName = "page" + pageIndex + "_" + originalName;
Integer counter = fieldNameCounters.get(baseName);
if (counter == null) {
counter = 0;
} else {
counter++;
}
fieldNameCounters.put(baseName, counter);
return counter == 0 ? baseName : baseName + "_" + counter;
}
private Map<PDAnnotationWidget, PDField> buildWidgetFieldMap(PDAcroForm acroForm) {
Map<PDAnnotationWidget, PDField> map = new HashMap<>();
if (acroForm == null) {
return map;
}
try {
for (PDField field : acroForm.getFieldTree()) {
List<PDAnnotationWidget> widgets = field.getWidgets();
if (widgets == null) {
continue;
}
for (PDAnnotationWidget widget : widgets) {
if (widget != null) {
map.put(widget, field);
}
}
}
} catch (Exception e) {
log.warn("Failed to build widget->field map: {}", e.getMessage(), e);
}
return map;
}
}
@@ -0,0 +1,165 @@
package stirling.software.common.util;
import java.io.IOException;
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
import org.apache.pdfbox.pdmodel.interactive.form.PDCheckBox;
import org.apache.pdfbox.pdmodel.interactive.form.PDComboBox;
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
import org.apache.pdfbox.pdmodel.interactive.form.PDListBox;
import org.apache.pdfbox.pdmodel.interactive.form.PDPushButton;
import org.apache.pdfbox.pdmodel.interactive.form.PDRadioButton;
import org.apache.pdfbox.pdmodel.interactive.form.PDSignatureField;
import org.apache.pdfbox.pdmodel.interactive.form.PDTerminalField;
import org.apache.pdfbox.pdmodel.interactive.form.PDTextField;
import lombok.extern.slf4j.Slf4j;
/**
* Simplified form field type support for general PDF operations. This is a subset of the full
* proprietary FormFieldTypeSupport, containing only what's needed for basic form field copying
* during page operations.
*/
@Slf4j
public enum GeneralFormFieldTypeSupport {
TEXT("text", "textField", PDTextField.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
PDTextField textField = new PDTextField(acroForm);
textField.setDefaultAppearance("/Helv 12 Tf 0 g");
return textField;
}
@Override
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
PDTextField src = (PDTextField) source;
PDTextField dst = (PDTextField) target;
String value = src.getValueAsString();
if (value != null) {
dst.setValue(value);
}
}
},
CHECKBOX("checkbox", "checkBox", PDCheckBox.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDCheckBox(acroForm);
}
@Override
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
PDCheckBox src = (PDCheckBox) source;
PDCheckBox dst = (PDCheckBox) target;
if (src.isChecked()) {
dst.check();
} else {
dst.unCheck();
}
}
},
RADIO("radio", "radioButton", PDRadioButton.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDRadioButton(acroForm);
}
@Override
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
PDRadioButton src = (PDRadioButton) source;
PDRadioButton dst = (PDRadioButton) target;
if (src.getExportValues() != null) {
dst.setExportValues(src.getExportValues());
}
if (src.getValue() != null) {
dst.setValue(src.getValue());
}
}
},
COMBOBOX("combobox", "comboBox", PDComboBox.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDComboBox(acroForm);
}
@Override
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
PDComboBox src = (PDComboBox) source;
PDComboBox dst = (PDComboBox) target;
if (src.getOptions() != null) {
dst.setOptions(src.getOptions());
}
if (src.getValue() != null && !src.getValue().isEmpty()) {
dst.setValue(src.getValue());
}
}
},
LISTBOX("listbox", "listBox", PDListBox.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDListBox(acroForm);
}
@Override
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
PDListBox src = (PDListBox) source;
PDListBox dst = (PDListBox) target;
if (src.getOptions() != null) {
dst.setOptions(src.getOptions());
}
if (src.getValue() != null && !src.getValue().isEmpty()) {
dst.setValue(src.getValue());
}
}
},
SIGNATURE("signature", "signature", PDSignatureField.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDSignatureField(acroForm);
}
},
BUTTON("button", "pushButton", PDPushButton.class) {
@Override
PDTerminalField createField(PDAcroForm acroForm) {
return new PDPushButton(acroForm);
}
};
private final String typeName;
private final String fallbackWidgetName;
private final Class<? extends PDTerminalField> fieldClass;
GeneralFormFieldTypeSupport(
String typeName,
String fallbackWidgetName,
Class<? extends PDTerminalField> fieldClass) {
this.typeName = typeName;
this.fallbackWidgetName = fallbackWidgetName;
this.fieldClass = fieldClass;
}
public static GeneralFormFieldTypeSupport forField(PDField field) {
if (field == null) {
return null;
}
for (GeneralFormFieldTypeSupport handler : values()) {
if (handler.fieldClass.isInstance(field)) {
return handler;
}
}
return null;
}
String typeName() {
return typeName;
}
String fallbackWidgetName() {
return fallbackWidgetName;
}
abstract PDTerminalField createField(PDAcroForm acroForm);
void copyFromOriginal(PDTerminalField source, PDTerminalField target) throws IOException {
// default no-op
}
}
@@ -33,6 +33,11 @@ import stirling.software.common.configuration.InstallationPathConfig;
@UtilityClass
public class GeneralUtils {
/**
* Maximum number of resolved DNS addresses allowed for a host before it is considered unsafe.
*/
private static final int MAX_DNS_ADDRESSES = 20;
private final Set<String> DEFAULT_VALID_SCRIPTS = Set.of("png_to_webp.py", "split_photos.py");
private final Set<String> DEFAULT_VALID_PIPELINE =
Set.of(
@@ -90,32 +95,6 @@ public class GeneralUtils {
return tempFile;
}
/*
* Gets the configured temporary directory, creating it if necessary.
*
* @return Path to the temporary directory
* @throws IOException if directory creation fails
*/
private Path getTempDirectory() throws IOException {
String customTempDir = System.getenv("STIRLING_TEMPFILES_DIRECTORY");
if (customTempDir == null || customTempDir.isEmpty()) {
customTempDir = System.getProperty("stirling.tempfiles.directory");
}
Path tempDir;
if (customTempDir != null && !customTempDir.isEmpty()) {
tempDir = Path.of(customTempDir);
} else {
tempDir = Path.of(System.getProperty("java.io.tmpdir"), "stirling-pdf");
}
if (!Files.exists(tempDir)) {
Files.createDirectories(tempDir);
}
return tempDir;
}
/*
* Remove file extension
*
@@ -154,7 +133,7 @@ public class GeneralUtils {
return matcher.find() ? matcher.replaceFirst("") : filename;
}
/*
/**
* Append suffix to base name with null safety.
*
* @param baseName the base filename, null becomes "default"
@@ -165,7 +144,7 @@ public class GeneralUtils {
return (baseName == null ? "default" : baseName) + (suffix != null ? suffix : "");
}
/*
/**
* Generate a PDF filename by removing extension from first file and adding suffix.
*
* <p>High-level utility method for common PDF naming scenarios. Handles null safety and uses
@@ -180,7 +159,7 @@ public class GeneralUtils {
return appendSuffix(baseName, suffix);
}
/*
/**
* Process a list of filenames by removing extensions and adding suffix.
*
* <p>Efficiently processes multiple filenames using streaming operations and bulk operations
@@ -201,7 +180,7 @@ public class GeneralUtils {
.forEach(processor);
}
/*
/**
* Extract title from filename by removing extension, with fallback handling.
*
* <p>Returns "Untitled" for null or empty filenames, otherwise removes the extension using the
@@ -269,6 +248,12 @@ public class GeneralUtils {
.getResources(pattern);
}
/**
* Validates URL syntax and disallows common-infrastructure targets to reduce SSRF risk.
*
* @param urlStr a URL string to validate
* @return {@code true} if the URL is syntactically valid and allowed; {@code false} otherwise
*/
public boolean isValidURL(String urlStr) {
try {
Urls.create(
@@ -279,7 +264,7 @@ public class GeneralUtils {
}
}
/*
/**
* Checks if a URL is reachable with proper timeout configuration and error handling.
*
* @param urlStr the URL string to check
@@ -289,15 +274,17 @@ public class GeneralUtils {
return isURLReachable(urlStr, 5000, 5000);
}
/*
* Checks if a URL is reachable with configurable timeouts.
/**
* Checks whether a URL is reachable using configurable timeouts. Only {@code http} and {@code
* https} protocols are permitted, and local/private/multicast ranges are blocked.
*
* @param urlStr the URL string to check
* @param urlStr the URL to probe
* @param connectTimeout connection timeout in milliseconds
* @param readTimeout read timeout in milliseconds
* @return true if URL is reachable, false otherwise
* @return {@code true} if a HEAD request returns a 2xx or 3xx status; {@code false} otherwise
*/
public boolean isURLReachable(String urlStr, int connectTimeout, int readTimeout) {
HttpURLConnection connection = null;
try {
// Parse the URL
URL url = URI.create(urlStr).toURL();
@@ -308,14 +295,17 @@ public class GeneralUtils {
return false; // Disallow other protocols
}
// Check if the host is a local address
String host = url.getHost();
if (isLocalAddress(host)) {
return false; // Exclude local addresses
if (host == null || host.isBlank()) {
return false;
}
if (isDisallowedNetworkLocation(host)) {
return false; // Exclude local, private or otherwise sensitive addresses
}
// Check if the URL is reachable
HttpURLConnection connection = (HttpURLConnection) url.openConnection();
connection = (HttpURLConnection) url.openConnection();
connection.setRequestMethod("HEAD");
connection.setConnectTimeout(connectTimeout);
connection.setReadTimeout(readTimeout);
@@ -326,29 +316,173 @@ public class GeneralUtils {
} catch (Exception e) {
log.debug("URL {} is not reachable: {}", urlStr, e.getMessage());
return false; // Return false in case of any exception
} finally {
if (connection != null) {
connection.disconnect();
}
}
}
private boolean isLocalAddress(String host) {
/**
* Determines whether the specified host resolves to a disallowed network location, such as
* local, private, multicast, or reserved ranges. Excessive DNS results are also blocked.
*
* @param host the hostname to resolve
* @return {@code true} if the host should be considered unsafe
*/
private boolean isDisallowedNetworkLocation(String host) {
// Resolution is delegated to the JVM/OS resolver which already applies system
// configured query limits and timeouts. We only need the resolved addresses here so
// that we can enforce the MAX_DNS_ADDRESSES limit and perform the sensitive range
// checks below.
try {
// Resolve DNS to IP address
InetAddress address = InetAddress.getByName(host);
// Check for local addresses
return address.isAnyLocalAddress()
|| // Matches 0.0.0.0 or similar
address.isLoopbackAddress()
|| // Matches 127.0.0.1 or ::1
address.isSiteLocalAddress()
|| // Matches private IPv4 ranges: 192.168.x.x, 10.x.x.x, 172.16.x.x to
// 172.31.x.x
address.getHostAddress()
.startsWith("fe80:"); // Matches link-local IPv6 addresses
InetAddress[] addresses = InetAddress.getAllByName(host);
if (addresses.length > MAX_DNS_ADDRESSES) {
log.debug(
"Blocking URL to host {} due to excessive DNS records (>{})",
host,
MAX_DNS_ADDRESSES);
return true;
}
for (InetAddress address : addresses) {
if (address == null || isSensitiveAddress(address)) {
log.debug("Blocking URL to host {} resolved to {}", host, address);
return true;
}
}
return false;
} catch (Exception e) {
return false; // Return false for invalid or unresolved addresses
log.debug("Unable to resolve host {}: {}", host, e.getMessage());
return true; // Treat resolution issues as unsafe to avoid SSRF
}
}
/**
* Returns whether the given IP address lies within ranges that should not be contacted by the
* server (loopback, link-local, private, multicast, etc.). IPv6 ULA and IPv4-mapped addresses
* are handled.
*
* @param address the resolved address
* @return {@code true} if the address is considered sensitive
*/
private boolean isSensitiveAddress(InetAddress address) {
if (address.isAnyLocalAddress()
|| address.isLoopbackAddress()
|| address.isLinkLocalAddress()
|| address.isSiteLocalAddress()
|| address.isMulticastAddress()) {
return true;
}
byte[] rawAddress = address.getAddress();
if (address instanceof Inet4Address) {
return isPrivateOrReservedIPv4(rawAddress);
}
if (address instanceof Inet6Address inet6Address) {
if (isUniqueLocalIPv6(rawAddress)) {
return true;
}
if (isIPv4MappedAddress(rawAddress) || inet6Address.isIPv4CompatibleAddress()) {
byte[] ipv4 =
Arrays.copyOfRange(rawAddress, rawAddress.length - 4, rawAddress.length);
return isPrivateOrReservedIPv4(ipv4);
}
}
return false;
}
/**
* Checks whether an IPv4 address is private or reserved. Any malformed input defaults to {@code
* true} (conservative) to avoid misuse.
*
* @param address 4-byte IPv4 address
* @return {@code true} if private/reserved
*/
private boolean isPrivateOrReservedIPv4(byte[] address) {
// IPv4 addresses must be exactly 4 bytes. Treat null or unexpected lengths as
// sensitive to avoid processing malformed input.
if (address == null || address.length != 4) {
return true;
}
int first = Byte.toUnsignedInt(address[0]);
int second = Byte.toUnsignedInt(address[1]);
if (first == 0 || first == 127) {
return true; // 0.0.0.0/8 and 127.0.0.0/8
}
if (first == 100 && second >= 64 && second <= 127) {
return true; // 100.64.0.0/10 Carrier-grade NAT
}
if (first == 169 && second == 254) {
return true; // 169.254.0.0/16 Link-local
}
if (first == 172 && second >= 16 && second <= 31) {
return true; // 172.16.0.0/12 Private
}
if (first == 192 && second == 0 && Byte.toUnsignedInt(address[2]) == 0) {
return true; // 192.0.0.0/24 IETF Protocol Assignments
}
if (first == 192 && second == 0 && Byte.toUnsignedInt(address[2]) == 2) {
return true; // 192.0.2.0/24 TEST-NET-1
}
if (first == 192 && second == 168) {
return true; // 192.168.0.0/16 Private
}
if (first == 198 && (second == 18 || second == 19)) {
return true; // 198.18.0.0/15 Benchmark tests
}
if (first == 198 && second == 51 && Byte.toUnsignedInt(address[2]) == 100) {
return true; // 198.51.100.0/24 TEST-NET-2
}
if (first == 203 && second == 0 && Byte.toUnsignedInt(address[2]) == 113) {
return true; // 203.0.113.0/24 TEST-NET-3
}
if (first == 10) {
return true; // 10.0.0.0/8 Private
}
if (first >= 224) {
return true; // 224.0.0.0/4 Multicast and 240.0.0.0/4 Reserved for future use
}
return false;
}
/**
* Checks whether an IPv6 address is a Unique Local Address (ULA, fc00::/7). Any malformed input
* defaults to {@code true} (conservative) to avoid misuse.
*
* @param address 16-byte IPv6 address
* @return {@code true} if ULA
*/
private boolean isUniqueLocalIPv6(byte[] address) {
if (address == null || address.length != 16) {
return true;
}
int first = Byte.toUnsignedInt(address[0]);
return (first & 0xFE) == 0xFC; // fc00::/7 Unique local addresses
}
/**
* Checks whether an IPv6 address is an IPv4-mapped address (::ffff:0:0/96). Any malformed input
* defaults to {@code false} (conservative) to avoid misuse.
*
* @param address 16-byte IPv6 address
* @return {@code true} if IPv4-mapped
*/
private boolean isIPv4MappedAddress(byte[] address) {
if (address == null || address.length != 16) {
return false;
}
for (int i = 0; i < 10; i++) {
if (address[i] != 0) {
return false;
}
}
return address[10] == (byte) 0xFF && address[11] == (byte) 0xFF;
}
/*
* Improved multipart file conversion using the shared helper method.
*
@@ -386,7 +520,7 @@ public class GeneralUtils {
throw new IllegalArgumentException("Invalid default unit: " + defaultUnit);
}
sizeStr = sizeStr.trim().toUpperCase();
sizeStr = sizeStr.trim().toUpperCase(Locale.ROOT);
sizeStr = sizeStr.replace(",", ".").replace(" ", "");
try {
@@ -415,7 +549,7 @@ public class GeneralUtils {
return Long.parseLong(sizeStr.substring(0, sizeStr.length() - 1));
} else {
// Use provided default unit or fall back to MB
String unit = defaultUnit != null ? defaultUnit.toUpperCase() : "MB";
String unit = defaultUnit != null ? defaultUnit.toUpperCase(Locale.ROOT) : "MB";
double value = Double.parseDouble(sizeStr);
return switch (unit) {
case "TB" -> (long) (value * 1024L * 1024L * 1024L * 1024L);
@@ -457,13 +591,14 @@ public class GeneralUtils {
if (bytes < 1024) {
return bytes + " B";
} else if (bytes < 1024L * 1024L) {
return String.format(Locale.US, "%.2f KB", bytes / 1024.0);
return String.format(Locale.ROOT, "%.2f KB", bytes / 1024.0);
} else if (bytes < 1024L * 1024L * 1024L) {
return String.format(Locale.US, "%.2f MB", bytes / (1024.0 * 1024.0));
return String.format(Locale.ROOT, "%.2f MB", bytes / (1024.0 * 1024.0));
} else if (bytes < 1024L * 1024L * 1024L * 1024L) {
return String.format(Locale.US, "%.2f GB", bytes / (1024.0 * 1024.0 * 1024.0));
return String.format(Locale.ROOT, "%.2f GB", bytes / (1024.0 * 1024.0 * 1024.0));
} else {
return String.format(Locale.US, "%.2f TB", bytes / (1024.0 * 1024.0 * 1024.0 * 1024.0));
return String.format(
Locale.ROOT, "%.2f TB", bytes / (1024.0 * 1024.0 * 1024.0 * 1024.0));
}
}
@@ -723,7 +858,7 @@ public class GeneralUtils {
byte[] mac = net.getHardwareAddress();
if (mac != null && mac.length > 0) {
for (byte b : mac) {
sb.append(String.format("%02X", b));
sb.append(String.format(Locale.ROOT, "%02X", b));
}
break; // Use the first valid network interface
}
@@ -733,7 +868,7 @@ public class GeneralUtils {
byte[] mac = network.getHardwareAddress();
if (mac != null) {
for (byte b : mac) {
sb.append(String.format("%02X", b));
sb.append(String.format(Locale.ROOT, "%02X", b));
}
}
}
@@ -940,17 +1075,29 @@ public class GeneralUtils {
ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT)
.runCommandWithOutputHandling(command);
ExceptionUtils.GhostscriptException detectedError =
ExceptionUtils.detectGhostscriptCriticalError(result.getMessages());
if (detectedError != null) {
log.warn(
"Ghostscript ebook optimization reported a critical error: {}",
detectedError.getMessage());
throw detectedError;
}
if (result.getRc() != 0) {
log.warn(
"Ghostscript ebook optimization failed with return code: {}",
result.getRc());
throw ExceptionUtils.createGhostscriptCompressionException();
throw ExceptionUtils.createGhostscriptCompressionException(result.getMessages());
}
return Files.readAllBytes(tempOutput);
} catch (Exception e) {
log.warn("Ghostscript ebook optimization failed", e);
if (e instanceof ExceptionUtils.GhostscriptException ghostscriptException) {
throw ghostscriptException;
}
throw ExceptionUtils.createGhostscriptCompressionException(e);
} finally {
if (tempInput != null) {
@@ -6,6 +6,7 @@ import java.io.IOException;
import java.io.InputStream;
import java.nio.ByteBuffer;
import java.util.Iterator;
import java.util.Locale;
import javax.imageio.ImageIO;
import javax.imageio.ImageReader;
@@ -118,7 +119,7 @@ public class ImageProcessingUtils {
BufferedImage image = null;
String filename = file.getOriginalFilename();
if (filename != null && filename.toLowerCase().endsWith(".psd")) {
if (filename != null && filename.toLowerCase(Locale.ROOT).endsWith(".psd")) {
// For PSD files, try explicit ImageReader
Iterator<ImageReader> readers = ImageIO.getImageReadersByFormatName("PSD");
if (readers.hasNext()) {
@@ -134,7 +135,8 @@ public class ImageProcessingUtils {
throw new IOException(
"Unable to read image from file: "
+ filename
+ ". Supported PSD formats: RGB/CMYK/Gray 8-32 bit, RLE/ZIP compression");
+ ". Supported PSD formats: RGB/CMYK/Gray 8-32 bit, RLE/ZIP"
+ " compression");
}
} else {
// For non-PSD files, use standard ImageIO
@@ -142,7 +144,7 @@ public class ImageProcessingUtils {
}
if (image == null) {
throw new IOException("Unable to read image from file: " + filename);
throw ExceptionUtils.createImageReadException(filename);
}
double orientation = extractImageOrientation(file.getInputStream());
@@ -27,15 +27,22 @@ import io.github.pixee.security.Filenames;
import lombok.extern.slf4j.Slf4j;
import stirling.software.common.configuration.RuntimePathConfig;
import stirling.software.common.util.ProcessExecutor.ProcessExecutorResult;
@Slf4j
public class PDFToFile {
private final TempFileManager tempFileManager;
private final RuntimePathConfig runtimePathConfig;
public PDFToFile(TempFileManager tempFileManager) {
this(tempFileManager, null);
}
public PDFToFile(TempFileManager tempFileManager, RuntimePathConfig runtimePathConfig) {
this.tempFileManager = tempFileManager;
this.runtimePathConfig = runtimePathConfig;
}
public ResponseEntity<byte[]> processPdfToMarkdown(MultipartFile inputFile)
@@ -241,31 +248,65 @@ public class PDFToFile {
byte[] fileBytes;
String fileName;
Path libreOfficeProfile = null;
try (TempFile inputFileTemp = new TempFile(tempFileManager, ".pdf");
TempDirectory outputDirTemp = new TempDirectory(tempFileManager)) {
Path tempInputFile = inputFileTemp.getPath();
Path tempOutputDir = outputDirTemp.getPath();
Path unoOutputFile =
tempOutputDir.resolve(
pdfBaseName + "." + resolvePrimaryExtension(outputFormat));
// Save the uploaded file to a temporary location
inputFile.transferTo(tempInputFile);
// Run the LibreOffice command
List<String> command =
new ArrayList<>(
Arrays.asList(
"soffice",
"--headless",
"--nologo",
"--infilter=" + libreOfficeFilter,
"--convert-to",
outputFormat,
"--outdir",
tempOutputDir.toString(),
tempInputFile.toString()));
ProcessExecutorResult returnCode =
ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE)
.runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = null;
IOException unoconvertException = null;
if (isUnoConvertEnabled()) {
try {
List<String> unoCommand =
buildUnoConvertCommand(
tempInputFile, unoOutputFile, outputFormat, libreOfficeFilter);
returnCode =
ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE)
.runCommandWithOutputHandling(unoCommand);
} catch (IOException e) {
unoconvertException = e;
log.warn(
"Unoconvert command failed ({}). Falling back to soffice command.",
e.getMessage());
}
}
if (returnCode == null) {
// Run the LibreOffice command as a fallback
libreOfficeProfile = Files.createTempDirectory("libreoffice_profile_");
List<String> command = new ArrayList<>();
command.add(runtimePathConfig.getSOfficePath());
command.add("-env:UserInstallation=" + libreOfficeProfile.toUri().toString());
command.add("--headless");
command.add("--nologo");
command.add("--infilter=" + libreOfficeFilter);
command.add("--convert-to");
command.add(outputFormat);
command.add("--outdir");
command.add(tempOutputDir.toString());
command.add(tempInputFile.toString());
try {
returnCode =
ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE)
.runCommandWithOutputHandling(command);
} catch (IOException e) {
if (unoconvertException != null) {
e.addSuppressed(unoconvertException);
}
throw e;
}
}
// Get output files
List<File> outputFiles = Arrays.asList(tempOutputDir.toFile().listFiles());
@@ -300,8 +341,42 @@ public class PDFToFile {
fileBytes = byteArrayOutputStream.toByteArray();
}
} finally {
if (libreOfficeProfile != null) {
FileUtils.deleteQuietly(libreOfficeProfile.toFile());
}
}
return WebResponseUtils.bytesToWebResponse(
fileBytes, fileName, MediaType.APPLICATION_OCTET_STREAM);
}
private boolean isUnoConvertEnabled() {
return runtimePathConfig != null
&& runtimePathConfig.getUnoConvertPath() != null
&& !runtimePathConfig.getUnoConvertPath().isBlank();
}
private List<String> buildUnoConvertCommand(
Path inputFile, Path outputFile, String outputFormat, String libreOfficeFilter) {
List<String> command = new ArrayList<>();
command.add(runtimePathConfig.getUnoConvertPath());
command.add("--port");
command.add("2003");
command.add("--convert-to");
command.add(outputFormat);
if (libreOfficeFilter != null && !libreOfficeFilter.isBlank()) {
command.add("--input-filter=" + libreOfficeFilter);
}
command.add(inputFile.toString());
command.add(outputFile.toString());
return command;
}
private String resolvePrimaryExtension(String outputFormat) {
if (outputFormat == null) {
return "";
}
int colonIndex = outputFormat.indexOf(':');
return colonIndex > 0 ? outputFormat.substring(0, colonIndex) : outputFormat;
}
}
@@ -318,7 +318,7 @@ public class PdfAttachmentHandler {
private static String normalizeFilename(String filename) {
if (filename == null) return "";
String normalized = filename.toLowerCase().trim();
String normalized = filename.toLowerCase(Locale.ROOT).trim();
normalized =
RegexPatternUtils.getInstance()
.getWhitespacePattern()
@@ -560,7 +560,7 @@ public class PdfAttachmentHandler {
@Override
protected void writeString(String string, List<TextPosition> textPositions)
throws IOException {
String lowerString = string.toLowerCase();
String lowerString = string.toLowerCase(Locale.ROOT);
if (ATTACHMENT_SECTION_PATTERN.matcher(lowerString).find()) {
isInAttachmentSection = true;
@@ -9,6 +9,7 @@ import java.nio.file.Path;
import java.util.ArrayList;
import java.util.Comparator;
import java.util.List;
import java.util.Locale;
import javax.imageio.ImageIO;
@@ -34,7 +35,7 @@ public class PdfToCbrUtils {
try (PDDocument document = pdfDocumentFactory.load(pdfFile)) {
if (document.getNumberOfPages() == 0) {
throw new IllegalArgumentException("PDF file contains no pages");
throw ExceptionUtils.createPdfNoPages();
}
return createCbrFromPdf(document, dpi);
@@ -43,17 +44,17 @@ public class PdfToCbrUtils {
private static void validatePdfFile(MultipartFile file) {
if (file == null || file.isEmpty()) {
throw new IllegalArgumentException("File cannot be null or empty");
throw ExceptionUtils.createFileNullOrEmptyException();
}
String filename = file.getOriginalFilename();
if (filename == null) {
throw new IllegalArgumentException("File must have a name");
throw ExceptionUtils.createFileNoNameException();
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
if (!"pdf".equals(extension)) {
throw new IllegalArgumentException("File must be a PDF");
throw ExceptionUtils.createPdfFileRequiredException();
}
}
@@ -66,27 +67,36 @@ public class PdfToCbrUtils {
int totalPages = document.getNumberOfPages();
for (int pageIndex = 0; pageIndex < totalPages; pageIndex++) {
final int currentPage = pageIndex;
try {
BufferedImage image =
pdfRenderer.renderImageWithDPI(pageIndex, dpi, ImageType.RGB);
ExceptionUtils.handleOomRendering(
currentPage + 1,
dpi,
() ->
pdfRenderer.renderImageWithDPI(
currentPage, dpi, ImageType.RGB));
String imageFilename = String.format("page_%03d.png", pageIndex + 1);
String imageFilename =
String.format(Locale.ROOT, "page_%03d.png", currentPage + 1);
Path imagePath = tempDir.resolve(imageFilename);
ImageIO.write(image, "PNG", imagePath.toFile());
generatedImages.add(imagePath);
} catch (ExceptionUtils.OutOfMemoryDpiException e) {
// Re-throw OOM exceptions without wrapping
throw e;
} catch (IOException e) {
log.warn("Error processing page {}: {}", pageIndex + 1, e.getMessage());
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(pageIndex + 1, dpi, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(pageIndex + 1, dpi, e);
// Wrap other IOExceptions with context
throw ExceptionUtils.createFileProcessingException(
"CBR creation for page " + (currentPage + 1), e);
}
}
if (generatedImages.isEmpty()) {
throw new IOException("Failed to render any pages to images for CBR conversion");
throw ExceptionUtils.createFileProcessingException(
"CBR conversion", new IOException("No pages were successfully rendered"));
}
return createRarArchive(tempDir, generatedImages);
@@ -115,15 +125,18 @@ public class PdfToCbrUtils {
ProcessExecutorResult result =
executor.runCommandWithOutputHandling(command, tempDir.toFile());
if (result.getRc() != 0) {
throw new IOException("RAR command failed: " + result.getMessages());
throw ExceptionUtils.createFileProcessingException(
"RAR archive creation",
new IOException("RAR command failed with code " + result.getRc()));
}
} catch (InterruptedException e) {
Thread.currentThread().interrupt();
throw new IOException("RAR command interrupted", e);
throw ExceptionUtils.createProcessingInterruptedException("RAR creation", e);
}
if (!Files.exists(rarFile)) {
throw new IOException("RAR file was not created");
throw ExceptionUtils.createFileProcessingException(
"RAR archive creation", new IOException("RAR file was not created"));
}
try (FileInputStream fis = new FileInputStream(rarFile.toFile());
@@ -167,7 +180,7 @@ public class PdfToCbrUtils {
return false;
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
return "pdf".equals(extension);
}
}
@@ -3,6 +3,7 @@ package stirling.software.common.util;
import java.awt.image.BufferedImage;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.util.Locale;
import java.util.zip.ZipEntry;
import java.util.zip.ZipOutputStream;
@@ -29,7 +30,7 @@ public class PdfToCbzUtils {
try (PDDocument document = pdfDocumentFactory.load(pdfFile)) {
if (document.getNumberOfPages() == 0) {
throw new IllegalArgumentException("PDF file contains no pages");
throw ExceptionUtils.createPdfNoPages();
}
return createCbzFromPdf(document, dpi);
@@ -38,17 +39,17 @@ public class PdfToCbzUtils {
private static void validatePdfFile(MultipartFile file) {
if (file == null || file.isEmpty()) {
throw new IllegalArgumentException("File cannot be null or empty");
throw ExceptionUtils.createFileNullOrEmptyException();
}
String filename = file.getOriginalFilename();
if (filename == null) {
throw new IllegalArgumentException("File must have a name");
throw ExceptionUtils.createFileNoNameException();
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
if (!"pdf".equals(extension)) {
throw new IllegalArgumentException("File must be a PDF");
throw ExceptionUtils.createPdfFileRequiredException();
}
}
@@ -61,24 +62,31 @@ public class PdfToCbzUtils {
int totalPages = document.getNumberOfPages();
for (int pageIndex = 0; pageIndex < totalPages; pageIndex++) {
final int currentPage = pageIndex;
try {
BufferedImage image =
pdfRenderer.renderImageWithDPI(pageIndex, dpi, ImageType.RGB);
String imageFilename = String.format("page_%03d.png", pageIndex + 1);
ExceptionUtils.handleOomRendering(
currentPage + 1,
dpi,
() ->
pdfRenderer.renderImageWithDPI(
currentPage, dpi, ImageType.RGB));
String imageFilename =
String.format(Locale.ROOT, "page_%03d.png", currentPage + 1);
ZipEntry zipEntry = new ZipEntry(imageFilename);
zipOut.putNextEntry(zipEntry);
ImageIO.write(image, "PNG", zipOut);
zipOut.closeEntry();
} catch (ExceptionUtils.OutOfMemoryDpiException e) {
// Re-throw OOM exceptions without wrapping
throw e;
} catch (IOException e) {
log.warn("Error processing page {}: {}", pageIndex + 1, e.getMessage());
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(pageIndex + 1, dpi, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(pageIndex + 1, dpi, e);
// Wrap other IOExceptions with context
throw ExceptionUtils.createFileProcessingException(
"CBZ creation for page " + (currentPage + 1), e);
}
}
@@ -93,7 +101,7 @@ public class PdfToCbzUtils {
return false;
}
String extension = FilenameUtils.getExtension(filename).toLowerCase();
String extension = FilenameUtils.getExtension(filename).toLowerCase(Locale.ROOT);
return "pdf".equals(extension);
}
}
@@ -8,6 +8,7 @@ import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Locale;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.zip.ZipEntry;
@@ -50,36 +51,18 @@ public class PdfUtils {
public PDRectangle textToPageSize(String size) {
switch (size.toUpperCase()) {
case "A0" -> {
return PDRectangle.A0;
}
case "A1" -> {
return PDRectangle.A1;
}
case "A2" -> {
return PDRectangle.A2;
}
case "A3" -> {
return PDRectangle.A3;
}
case "A4" -> {
return PDRectangle.A4;
}
case "A5" -> {
return PDRectangle.A5;
}
case "A6" -> {
return PDRectangle.A6;
}
case "LETTER" -> {
return PDRectangle.LETTER;
}
case "LEGAL" -> {
return PDRectangle.LEGAL;
}
return switch (size.toUpperCase(Locale.ROOT)) {
case "A0" -> PDRectangle.A0;
case "A1" -> PDRectangle.A1;
case "A2" -> PDRectangle.A2;
case "A3" -> PDRectangle.A3;
case "A4" -> PDRectangle.A4;
case "A5" -> PDRectangle.A5;
case "A6" -> PDRectangle.A6;
case "LETTER" -> PDRectangle.LETTER;
case "LEGAL" -> PDRectangle.LEGAL;
default -> throw ExceptionUtils.createInvalidPageSizeException(size);
}
};
}
public List<RenderedImage> getAllImages(PDResources resources) throws IOException {
@@ -182,8 +165,8 @@ public class PdfUtils {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
if (singleImage) {
if ("tiff".equals(imageType.toLowerCase())
|| "tif".equals(imageType.toLowerCase())) {
if ("tiff".equals(imageType.toLowerCase(Locale.ROOT))
|| "tif".equals(imageType.toLowerCase(Locale.ROOT))) {
// Write the images to the output stream as a TIFF with multiple frames
ImageWriter writer = ImageIO.getImageWritersByFormatName("tiff").next();
ImageWriteParam param = writer.getDefaultWriteParam();
@@ -196,9 +179,20 @@ public class PdfUtils {
writer.prepareWriteSequence(null);
for (int i = 0; i < pageCount; ++i) {
final int pageIndex = i;
BufferedImage image;
try {
image = pdfRenderer.renderImageWithDPI(i, DPI, colorType);
// Validate dimensions before rendering
ExceptionUtils.validateRenderingDimensions(
document.getPage(pageIndex), pageIndex + 1, DPI);
image =
ExceptionUtils.handleOomRendering(
pageIndex + 1,
DPI,
() ->
pdfRenderer.renderImageWithDPI(
pageIndex, DPI, colorType));
} catch (IllegalArgumentException e) {
if (e.getMessage() != null
&& e.getMessage()
@@ -212,10 +206,6 @@ public class PdfUtils {
DPI);
}
throw e;
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
}
writer.writeToSequence(new IIOImage(image, null, null), param);
}
@@ -239,6 +229,7 @@ public class PdfUtils {
HashMap<PdfRenderSettingsKey, PdfImageDimensionValue> pageSizes =
new HashMap<>();
for (int i = 0; i < pageCount; ++i) {
final int pageIndex = i;
PDPage page = document.getPage(i);
PDRectangle mediaBox = page.getMediaBox();
int rotation = page.getRotation();
@@ -249,7 +240,17 @@ public class PdfUtils {
if (dimension == null) {
// Render the image to get the dimensions
try {
pdfSizeImage = pdfRenderer.renderImageWithDPI(i, DPI, colorType);
// Validate dimensions before rendering
ExceptionUtils.validateRenderingDimensions(
page, pageIndex + 1, DPI);
pdfSizeImage =
ExceptionUtils.handleOomRendering(
pageIndex + 1,
DPI,
() ->
pdfRenderer.renderImageWithDPI(
pageIndex, DPI, colorType));
} catch (IllegalArgumentException e) {
if (e.getMessage() != null
&& e.getMessage()
@@ -264,10 +265,6 @@ public class PdfUtils {
DPI);
}
throw e;
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
}
pdfSizeImageIndex = i;
dimension =
@@ -293,11 +290,22 @@ public class PdfUtils {
boolean firstImageAlreadyRendered = pdfSizeImageIndex == 0;
for (int i = 0; i < pageCount; ++i) {
final int pageIndex = i;
if (firstImageAlreadyRendered && i == 0) {
pageImage = pdfSizeImage;
} else {
try {
pageImage = pdfRenderer.renderImageWithDPI(i, DPI, colorType);
// Validate dimensions before rendering
ExceptionUtils.validateRenderingDimensions(
document.getPage(pageIndex), pageIndex + 1, DPI);
pageImage =
ExceptionUtils.handleOomRendering(
pageIndex + 1,
DPI,
() ->
pdfRenderer.renderImageWithDPI(
pageIndex, DPI, colorType));
} catch (IllegalArgumentException e) {
if (e.getMessage() != null
&& e.getMessage()
@@ -311,10 +319,6 @@ public class PdfUtils {
DPI);
}
throw e;
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
}
}
@@ -335,9 +339,20 @@ public class PdfUtils {
// Zip the images and return as byte array
try (ZipOutputStream zos = new ZipOutputStream(baos)) {
for (int i = 0; i < pageCount; ++i) {
final int pageIndex = i;
BufferedImage image;
try {
image = pdfRenderer.renderImageWithDPI(i, DPI, colorType);
// Validate dimensions before rendering
ExceptionUtils.validateRenderingDimensions(
document.getPage(pageIndex), pageIndex + 1, DPI);
image =
ExceptionUtils.handleOomRendering(
pageIndex + 1,
DPI,
() ->
pdfRenderer.renderImageWithDPI(
pageIndex, DPI, colorType));
} catch (IllegalArgumentException e) {
if (e.getMessage() != null
&& e.getMessage().contains("Maximum size of image exceeded")) {
@@ -349,10 +364,6 @@ public class PdfUtils {
DPI);
}
throw e;
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(i + 1, DPI, e);
}
try (ByteArrayOutputStream baosImage = new ByteArrayOutputStream()) {
ImageIO.write(image, imageType, baosImage);
@@ -361,9 +372,10 @@ public class PdfUtils {
zos.putNextEntry(
new ZipEntry(
String.format(
Locale.ROOT,
filename + "_%d.%s",
i + 1,
imageType.toLowerCase())));
imageType.toLowerCase(Locale.ROOT))));
zos.write(baosImage.toByteArray());
}
}
@@ -391,6 +403,7 @@ public class PdfUtils {
PDFRenderer pdfRenderer = new PDFRenderer(document);
pdfRenderer.setSubsamplingAllowed(true);
for (int page = 0; page < document.getNumberOfPages(); ++page) {
final int pageIndex = page;
BufferedImage bim;
// Use global maximum DPI setting, fallback to 300 if not set
@@ -400,9 +413,16 @@ public class PdfUtils {
if (properties != null && properties.getSystem() != null) {
renderDpi = properties.getSystem().getMaxDPI();
}
final int dpi = renderDpi;
try {
bim = pdfRenderer.renderImageWithDPI(page, renderDpi, ImageType.RGB);
bim =
ExceptionUtils.handleOomRendering(
pageIndex + 1,
dpi,
() ->
pdfRenderer.renderImageWithDPI(
pageIndex, dpi, ImageType.RGB));
} catch (IllegalArgumentException e) {
if (e.getMessage() != null
&& e.getMessage().contains("Maximum size of image exceeded")) {
@@ -411,13 +431,9 @@ public class PdfUtils {
"PDF page {0} is too large to render at 300 DPI. The resulting image"
+ " would exceed Java's maximum array size. Please use a lower DPI"
+ " value for PDF-to-image conversion.",
page + 1);
pageIndex + 1);
}
throw e;
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(page + 1, 300, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(page + 1, 300, e);
}
PDPage originalPage = document.getPage(page);
@@ -463,8 +479,8 @@ public class PdfUtils {
String contentType = file.getContentType();
String originalFilename = Filenames.toSimpleFileName(file.getOriginalFilename());
if (originalFilename != null
&& (originalFilename.toLowerCase().endsWith(".tiff")
|| originalFilename.toLowerCase().endsWith(".tif"))) {
&& (originalFilename.toLowerCase(Locale.ROOT).endsWith(".tiff")
|| originalFilename.toLowerCase(Locale.ROOT).endsWith(".tif"))) {
ImageReader reader = ImageIO.getImageReadersByFormatName("tiff").next();
reader.setInput(ImageIO.createImageInputStream(file.getInputStream()));
int numPages = reader.getNumImages(true);
@@ -567,7 +583,7 @@ public class PdfUtils {
PDImageXObject image = PDImageXObject.createFromByteArray(document, imageBytes, "");
// Draw the image onto the page at the specified x and y coordinates
contentStream.drawImage(image, x, y);
log.info("Image successfully overlayed onto PDF");
log.info("Image successfully overlaid onto PDF");
if (!everyPage && i == 0) {
break;
}
@@ -631,7 +647,7 @@ public class PdfUtils {
int actualPageCount = pdfDocument.getNumberOfPages();
pdfDocument.close();
return switch (comparator.toLowerCase()) {
return switch (comparator.toLowerCase(Locale.ROOT)) {
case "greater" -> actualPageCount > pageCount;
case "equal" -> actualPageCount == pageCount;
case "less" -> actualPageCount < pageCount;
@@ -102,6 +102,11 @@ public class ProcessExecutor {
.getSessionLimit()
.getOcrMyPdfSessionLimit();
case CFF_CONVERTER -> 1;
case FFMPEG ->
applicationProperties
.getProcessExecutor()
.getSessionLimit()
.getFfmpegSessionLimit();
};
long timeoutMinutes =
@@ -162,6 +167,11 @@ public class ProcessExecutor {
.getTimeoutMinutes()
.getOcrMyPdfTimeoutMinutes();
case CFF_CONVERTER -> 5L;
case FFMPEG ->
applicationProperties
.getProcessExecutor()
.getTimeoutMinutes()
.getFfmpegTimeoutMinutes();
};
return new ProcessExecutor(semaphoreLimit, liveUpdates, timeoutMinutes);
});
@@ -316,7 +326,8 @@ public class ProcessExecutor {
QPDF,
GHOSTSCRIPT,
OCR_MY_PDF,
CFF_CONVERTER
CFF_CONVERTER,
FFMPEG
}
@Setter
@@ -325,6 +325,11 @@ public final class RegexPatternUtils {
return getPattern("\\+");
}
/** Pattern for splitting on pipe delimiter (used for hint lists in i18n messages) */
public Pattern getPipeDelimiterPattern() {
return getPattern("\\|");
}
/** Pattern for username validation */
public Pattern getUsernameValidationPattern() {
return getPattern("^[a-zA-Z0-9](?!.*[-@._+]{2,})[a-zA-Z0-9@._+-]{1,48}[a-zA-Z0-9]$");
@@ -567,6 +572,16 @@ public final class RegexPatternUtils {
return getPattern("^[a-zA-Z0-9]{2,4}$", Pattern.CASE_INSENSITIVE);
}
/** Pattern for splitting on line breaks (Unicode line separator) */
public Pattern getLineSeparatorPattern() {
return getPattern("\\R");
}
/** Pattern for removing leading asterisks and whitespace */
public Pattern getLeadingAsterisksWhitespacePattern() {
return getPattern("^[*\\s]+");
}
private record PatternKey(String regex, int flags) {
// Record automatically provides equals, hashCode, and toString
}
@@ -28,6 +28,17 @@ public class TempFileManager {
private final TempFileRegistry registry;
private final ApplicationProperties applicationProperties;
/**
* Create a managed temporary file that will be tracked by the TempFileManager.
*
* @param suffix The suffix for the temporary file
* @return The created temporary file wrapper
* @throws IOException If an I/O error occurs
*/
public TempFile createManagedTempFile(String suffix) throws IOException {
return new TempFile(this, suffix);
}
/**
* Create a temporary file with the Stirling-PDF prefix. The file is automatically registered
* with the registry.
@@ -130,7 +141,6 @@ public class TempFileManager {
return deleted;
} catch (IOException e) {
log.warn("Failed to delete temp file: {}", path.toString(), e);
return false;
}
}
return false;
@@ -1,14 +0,0 @@
package stirling.software.common.util;
import java.util.Collection;
public class ValidationUtil {
public static boolean isStringEmpty(String input) {
return input == null || input.isBlank();
}
public static boolean isCollectionEmpty(Collection<String> input) {
return input == null || input.isEmpty();
}
}
@@ -56,16 +56,14 @@ public class InvertFullColorStrategy extends ReplaceAndInvertColorStrategy {
if (properties != null && properties.getSystem() != null) {
renderDpi = properties.getSystem().getMaxDPI();
}
final int dpi = renderDpi;
final int pageNum = page;
try {
image =
pdfRenderer.renderImageWithDPI(
page, renderDpi); // Render page with global DPI setting
} catch (OutOfMemoryError e) {
throw ExceptionUtils.createOutOfMemoryDpiException(page + 1, renderDpi, e);
} catch (NegativeArraySizeException e) {
throw ExceptionUtils.createOutOfMemoryDpiException(page + 1, renderDpi, e);
}
image =
ExceptionUtils.handleOomRendering(
pageNum + 1,
dpi,
() -> pdfRenderer.renderImageWithDPI(pageNum, dpi));
// Invert the colors
invertImageColors(image);