mirror of
https://github.com/Stirling-Tools/Stirling-PDF.git
synced 2025-07-23 13:45:21 +00:00
exception handling error to warn etc (#3866)
# 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/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/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/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/DeveloperGuide.md#6-testing) for more details. --------- Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
This commit is contained in:
Anthony Stirling
GitHub
parent
a95743286e
commit
7617e5176b
@ -411,7 +411,7 @@ public class CustomPDFDocumentFactory {
|
||||
try {
|
||||
document.setAllSecurityToBeRemoved(true);
|
||||
} catch (Exception e) {
|
||||
log.error("Decryption failed", e);
|
||||
ExceptionUtils.logException("PDF decryption", e);
|
||||
throw new IOException("PDF decryption failed", e);
|
||||
}
|
||||
}
|
||||
|
||||
@ -72,12 +72,12 @@ public class TempFileCleanupService {
|
||||
fileName ->
|
||||
fileName.contains("jetty")
|
||||
|| fileName.startsWith("jetty-")
|
||||
|| fileName.equals("proc")
|
||||
|| fileName.equals("sys")
|
||||
|| fileName.equals("dev")
|
||||
|| fileName.equals("hsperfdata_stirlingpdfuser")
|
||||
|| "proc".equals(fileName)
|
||||
|| "sys".equals(fileName)
|
||||
|| "dev".equals(fileName)
|
||||
|| "hsperfdata_stirlingpdfuser".equals(fileName)
|
||||
|| fileName.startsWith("hsperfdata_")
|
||||
|| fileName.equals(".pdfbox.cache");
|
||||
|| ".pdfbox.cache".equals(fileName);
|
||||
|
||||
@PostConstruct
|
||||
public void init() {
|
||||
@ -153,12 +153,14 @@ public class TempFileCleanupService {
|
||||
// Clean up unregistered temp files based on our cleanup strategy
|
||||
boolean containerMode = isContainerMode();
|
||||
int unregisteredDeletedCount = cleanupUnregisteredFiles(containerMode, true, maxAgeMillis);
|
||||
|
||||
|
||||
if(registeredDeletedCount >0 || unregisteredDeletedCount >0 || directoriesDeletedCount >0) {
|
||||
log.info(
|
||||
"Scheduled cleanup complete. Deleted {} registered files, {} unregistered files, {} directories",
|
||||
registeredDeletedCount,
|
||||
unregisteredDeletedCount,
|
||||
directoriesDeletedCount);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@ -166,7 +168,6 @@ public class TempFileCleanupService {
|
||||
* important in Docker environments where temp files persist between container restarts.
|
||||
*/
|
||||
private void runStartupCleanup() {
|
||||
log.info("Running startup temporary file cleanup");
|
||||
boolean containerMode = isContainerMode();
|
||||
|
||||
log.info(
|
||||
@ -178,7 +179,6 @@ public class TempFileCleanupService {
|
||||
long maxAgeMillis = containerMode ? 0 : 24 * 60 * 60 * 1000; // 0 or 24 hours
|
||||
|
||||
int totalDeletedCount = cleanupUnregisteredFiles(containerMode, false, maxAgeMillis);
|
||||
|
||||
log.info(
|
||||
"Startup cleanup complete. Deleted {} temporary files/directories",
|
||||
totalDeletedCount);
|
||||
@ -225,7 +225,7 @@ public class TempFileCleanupService {
|
||||
tempDir -> {
|
||||
try {
|
||||
String phase = isScheduled ? "scheduled" : "startup";
|
||||
log.info(
|
||||
log.debug(
|
||||
"Scanning directory for {} cleanup: {}",
|
||||
phase,
|
||||
tempDir);
|
||||
|
||||
@ -298,9 +298,9 @@ public class ExceptionUtils {
|
||||
* @param e the exception that occurred
|
||||
*/
|
||||
public static void logException(String operation, Exception e) {
|
||||
if (e instanceof IOException && PdfErrorUtils.isCorruptedPdfError((IOException) e)) {
|
||||
if (PdfErrorUtils.isCorruptedPdfError(e)) {
|
||||
log.warn("PDF corruption detected during {}: {}", operation, e.getMessage());
|
||||
} else if (isEncryptionError((IOException) e) || isPasswordError((IOException) e)) {
|
||||
} else if (e instanceof IOException && (isEncryptionError((IOException) e) || isPasswordError((IOException) e))) {
|
||||
log.info("PDF security issue during {}: {}", operation, e.getMessage());
|
||||
} else {
|
||||
log.error("Unexpected error during {}", operation, e);
|
||||
|
||||
@ -12,7 +12,26 @@ public class PdfErrorUtils {
|
||||
* @return true if the error indicates PDF corruption, false otherwise
|
||||
*/
|
||||
public static boolean isCorruptedPdfError(IOException e) {
|
||||
String message = e.getMessage();
|
||||
return isCorruptedPdfError(e.getMessage());
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if any Exception indicates a corrupted PDF file.
|
||||
*
|
||||
* @param e the Exception to check
|
||||
* @return true if the error indicates PDF corruption, false otherwise
|
||||
*/
|
||||
public static boolean isCorruptedPdfError(Exception e) {
|
||||
return isCorruptedPdfError(e.getMessage());
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if an error message indicates a corrupted PDF file.
|
||||
*
|
||||
* @param message the error message to check
|
||||
* @return true if the message indicates PDF corruption, false otherwise
|
||||
*/
|
||||
private static boolean isCorruptedPdfError(String message) {
|
||||
if (message == null) return false;
|
||||
|
||||
// Check for common corruption indicators
|
||||
@ -24,6 +43,10 @@ public class PdfErrorUtils {
|
||||
|| message.contains("damaged")
|
||||
|| message.contains("Unknown dir object")
|
||||
|| message.contains("Can't dereference COSObject")
|
||||
|| message.contains("parseCOSString string should start with")
|
||||
|| message.contains("ICCBased colorspace array must have a stream")
|
||||
|| message.contains("1-based index not found")
|
||||
|| message.contains("Invalid dictionary, found:")
|
||||
|| message.contains("AES initialization vector not fully read")
|
||||
|| message.contains("BadPaddingException")
|
||||
|| message.contains("Given final block not properly padded");
|
||||
|
||||
@ -148,7 +148,7 @@ public class MergeController {
|
||||
try (PDDocument doc = pdfDocumentFactory.load(file)) {
|
||||
pageIndex += doc.getNumberOfPages();
|
||||
} catch (IOException e) {
|
||||
log.error("Error loading document for TOC generation", e);
|
||||
ExceptionUtils.logException("document loading for TOC generation", e);
|
||||
pageIndex++; // Increment by at least one if we can't determine page count
|
||||
}
|
||||
}
|
||||
@ -240,7 +240,11 @@ public class MergeController {
|
||||
baos, mergedFileName); // Return the modified PDF
|
||||
|
||||
} catch (Exception ex) {
|
||||
log.error("Error in merge pdf process", ex);
|
||||
if (ex instanceof IOException && PdfErrorUtils.isCorruptedPdfError((IOException) ex)) {
|
||||
log.warn("Corrupted PDF detected in merge pdf process: {}", ex.getMessage());
|
||||
} else {
|
||||
log.error("Error in merge pdf process", ex);
|
||||
}
|
||||
throw ex;
|
||||
} finally {
|
||||
if (mergedDocument != null) {
|
||||
|
||||
@ -25,6 +25,7 @@ import stirling.software.SPDF.model.SortTypes;
|
||||
import stirling.software.SPDF.model.api.PDFWithPageNums;
|
||||
import stirling.software.SPDF.model.api.general.RearrangePagesRequest;
|
||||
import stirling.software.common.service.CustomPDFDocumentFactory;
|
||||
import stirling.software.common.util.ExceptionUtils;
|
||||
import stirling.software.common.util.GeneralUtils;
|
||||
import stirling.software.common.util.WebResponseUtils;
|
||||
|
||||
@ -288,7 +289,7 @@ public class RearrangePagesPDFController {
|
||||
.replaceFirst("[.][^.]+$", "")
|
||||
+ "_rearranged.pdf");
|
||||
} catch (IOException e) {
|
||||
log.error("Failed rearranging documents", e);
|
||||
ExceptionUtils.logException("document rearrangement", e);
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
@ -29,6 +29,7 @@ import lombok.extern.slf4j.Slf4j;
|
||||
|
||||
import stirling.software.SPDF.model.api.PDFWithPageNums;
|
||||
import stirling.software.common.service.CustomPDFDocumentFactory;
|
||||
import stirling.software.common.util.ExceptionUtils;
|
||||
import stirling.software.common.util.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@ -96,7 +97,7 @@ public class SplitPDFController {
|
||||
|
||||
splitDocumentsBoas.add(baos);
|
||||
} catch (Exception e) {
|
||||
log.error("Failed splitting documents and saving them", e);
|
||||
ExceptionUtils.logException("document splitting and saving", e);
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
@ -159,7 +159,7 @@ public class SplitPdfByChaptersController {
|
||||
Bookmark lastBookmark = bookmarks.get(bookmarks.size() - 1);
|
||||
|
||||
} catch (Exception e) {
|
||||
log.error("Unable to extract outline items", e);
|
||||
ExceptionUtils.logException("outline extraction", e);
|
||||
return ResponseEntity.internalServerError()
|
||||
.body("Unable to extract outline items".getBytes());
|
||||
}
|
||||
@ -294,7 +294,7 @@ public class SplitPdfByChaptersController {
|
||||
|
||||
splitDocumentsBoas.add(baos);
|
||||
} catch (Exception e) {
|
||||
log.error("Failed splitting documents and saving them", e);
|
||||
ExceptionUtils.logException("document splitting and saving", e);
|
||||
throw e;
|
||||
}
|
||||
}
|
||||
|
||||
@ -105,7 +105,7 @@ public class SplitPdfBySizeController {
|
||||
|
||||
log.debug("PDF splitting completed successfully");
|
||||
} catch (Exception e) {
|
||||
log.error("Error loading or processing PDF document", e);
|
||||
ExceptionUtils.logException("PDF document loading or processing", e);
|
||||
throw e;
|
||||
}
|
||||
} catch (IOException e) {
|
||||
@ -114,7 +114,7 @@ public class SplitPdfBySizeController {
|
||||
}
|
||||
|
||||
} catch (Exception e) {
|
||||
log.error("Exception during PDF splitting process", e);
|
||||
ExceptionUtils.logException("PDF splitting process", e);
|
||||
throw e; // Re-throw to ensure proper error response
|
||||
} finally {
|
||||
try {
|
||||
@ -278,7 +278,7 @@ public class SplitPdfBySizeController {
|
||||
currentDoc = pdfDocumentFactory.createNewDocumentBasedOnOldDocument(sourceDocument);
|
||||
log.debug("Successfully created initial output document");
|
||||
} catch (Exception e) {
|
||||
log.error("Error creating initial output document", e);
|
||||
ExceptionUtils.logException("initial output document creation", e);
|
||||
throw ExceptionUtils.createFileProcessingException("split", e);
|
||||
}
|
||||
|
||||
|
||||
@ -606,7 +606,7 @@ public class CompressController {
|
||||
return "empty-stream";
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.error("Error generating image hash", e);
|
||||
ExceptionUtils.logException("image hash generation", e);
|
||||
return "fallback-" + System.identityHashCode(image);
|
||||
}
|
||||
}
|
||||
|
||||
@ -26,6 +26,7 @@ import lombok.extern.slf4j.Slf4j;
|
||||
|
||||
import stirling.software.common.model.api.PDFFile;
|
||||
import stirling.software.common.service.CustomPDFDocumentFactory;
|
||||
import stirling.software.common.util.ExceptionUtils;
|
||||
import stirling.software.common.util.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@ -134,7 +135,7 @@ public class DecompressPdfController {
|
||||
stream.setInt(COSName.LENGTH, decompressedBytes.length);
|
||||
}
|
||||
} catch (IOException e) {
|
||||
log.error("Error decompressing stream", e);
|
||||
ExceptionUtils.logException("stream decompression", e);
|
||||
// Continue processing other streams even if this one fails
|
||||
}
|
||||
}
|
||||
|
||||
@ -91,39 +91,54 @@ public class ExtractImagesController {
|
||||
Executors.newFixedThreadPool(Runtime.getRuntime().availableProcessors());
|
||||
Set<Future<Void>> futures = new HashSet<>();
|
||||
|
||||
// Iterate over each page
|
||||
for (int pgNum = 0; pgNum < document.getPages().getCount(); pgNum++) {
|
||||
PDPage page = document.getPage(pgNum);
|
||||
Future<Void> future =
|
||||
executor.submit(
|
||||
() -> {
|
||||
// Use the page number directly from the iterator, so no need to
|
||||
// calculate manually
|
||||
int pageNum = document.getPages().indexOf(page) + 1;
|
||||
// Safely iterate over each page, handling corrupt PDFs where page count might be wrong
|
||||
try {
|
||||
int pageCount = document.getPages().getCount();
|
||||
log.debug("Document reports {} pages", pageCount);
|
||||
|
||||
int consecutiveFailures = 0;
|
||||
|
||||
for (int pgNum = 0; pgNum < pageCount; pgNum++) {
|
||||
try {
|
||||
PDPage page = document.getPage(pgNum);
|
||||
consecutiveFailures = 0; // Reset on success
|
||||
final int currentPageNum = pgNum + 1; // Convert to 1-based page numbering
|
||||
Future<Void> future =
|
||||
executor.submit(
|
||||
() -> {
|
||||
try {
|
||||
// Call the image extraction method for each page
|
||||
extractImagesFromPage(
|
||||
page,
|
||||
format,
|
||||
filename,
|
||||
currentPageNum,
|
||||
processedImages,
|
||||
zos,
|
||||
allowDuplicates);
|
||||
} catch (Exception e) {
|
||||
// Log the error and continue processing other pages
|
||||
ExceptionUtils.logException("image extraction from page " + currentPageNum, e);
|
||||
}
|
||||
|
||||
try {
|
||||
// Call the image extraction method for each page
|
||||
extractImagesFromPage(
|
||||
page,
|
||||
format,
|
||||
filename,
|
||||
pageNum,
|
||||
processedImages,
|
||||
zos,
|
||||
allowDuplicates);
|
||||
} catch (IOException e) {
|
||||
// Log the error and continue processing other pages
|
||||
log.error(
|
||||
"Error extracting images from page {}: {}",
|
||||
pageNum,
|
||||
e.getMessage());
|
||||
}
|
||||
return null; // Callable requires a return type
|
||||
});
|
||||
|
||||
return null; // Callable requires a return type
|
||||
});
|
||||
|
||||
// Add the Future object to the list to track completion
|
||||
futures.add(future);
|
||||
// Add the Future object to the list to track completion
|
||||
futures.add(future);
|
||||
} catch (Exception e) {
|
||||
consecutiveFailures++;
|
||||
ExceptionUtils.logException("page access for page " + (pgNum + 1), e);
|
||||
|
||||
if (consecutiveFailures >= 3) {
|
||||
log.warn("Stopping page iteration after 3 consecutive failures");
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
} catch (Exception e) {
|
||||
ExceptionUtils.logException("page count determination", e);
|
||||
throw e;
|
||||
}
|
||||
|
||||
// Wait for all tasks to complete
|
||||
|
||||
@ -150,11 +150,18 @@ public class PipelineProcessor {
|
||||
}
|
||||
}
|
||||
if (!hasInputFileType) {
|
||||
String filename = file.getFilename();
|
||||
String providedExtension = "no extension";
|
||||
if (filename != null && filename.contains(".")) {
|
||||
providedExtension = filename.substring(filename.lastIndexOf(".")).toLowerCase();
|
||||
}
|
||||
|
||||
logPrintStream.println(
|
||||
"No files with extension "
|
||||
+ String.join(", ", inputFileTypes)
|
||||
+ " found for operation "
|
||||
+ operation);
|
||||
+ operation
|
||||
+ ". Provided file '" + filename + "' has extension: " + providedExtension);
|
||||
hasErrors = true;
|
||||
}
|
||||
}
|
||||
@ -203,11 +210,26 @@ public class PipelineProcessor {
|
||||
hasErrors = true;
|
||||
}
|
||||
} else {
|
||||
// Get details about what files were actually provided
|
||||
List<String> providedExtensions = outputFiles.stream()
|
||||
.map(file -> {
|
||||
String filename = file.getFilename();
|
||||
if (filename != null && filename.contains(".")) {
|
||||
return filename.substring(filename.lastIndexOf(".")).toLowerCase();
|
||||
}
|
||||
return "no extension";
|
||||
})
|
||||
.distinct()
|
||||
.toList();
|
||||
|
||||
logPrintStream.println(
|
||||
"No files with extension "
|
||||
+ String.join(", ", inputFileTypes)
|
||||
+ " found for multi-input operation "
|
||||
+ operation);
|
||||
+ operation
|
||||
+ ". Provided files have extensions: "
|
||||
+ String.join(", ", providedExtensions)
|
||||
+ " (total files: " + outputFiles.size() + ")");
|
||||
hasErrors = true;
|
||||
}
|
||||
}
|
||||
|
||||
@ -133,7 +133,7 @@ public class CertSignController {
|
||||
}
|
||||
doc.saveIncremental(output);
|
||||
} catch (Exception e) {
|
||||
log.error("exception", e);
|
||||
ExceptionUtils.logException("PDF signing", e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -63,6 +63,7 @@ import lombok.extern.slf4j.Slf4j;
|
||||
|
||||
import stirling.software.common.model.api.PDFFile;
|
||||
import stirling.software.common.service.CustomPDFDocumentFactory;
|
||||
import stirling.software.common.util.ExceptionUtils;
|
||||
import stirling.software.common.util.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@ -181,7 +182,7 @@ public class GetInfoOnPDF {
|
||||
}
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.error("exception", e);
|
||||
ExceptionUtils.logException("PDF standard checking", e);
|
||||
}
|
||||
|
||||
return false;
|
||||
|
||||
@ -77,7 +77,7 @@ public class MetricsAggregatorService {
|
||||
double lastCount = lastSentMetrics.getOrDefault(key, 0.0);
|
||||
double difference = currentCount - lastCount;
|
||||
if (difference > 0) {
|
||||
logger.info("{}, {}", key, difference);
|
||||
logger.debug("{}, {}", key, difference);
|
||||
metrics.put(key, difference);
|
||||
lastSentMetrics.put(key, currentCount);
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user