mirror of
https://github.com/Frooodle/Stirling-PDF.git
synced 2026-04-22 23:08:53 +02:00
removal of all getByte loads (#3153)
# 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: a <a>
This commit is contained in:
Anthony Stirling
GitHub
@@ -10,9 +10,9 @@ import java.nio.file.StandardCopyOption;
|
||||
import java.util.concurrent.atomic.AtomicLong;
|
||||
|
||||
import org.apache.pdfbox.Loader;
|
||||
import org.apache.pdfbox.examples.util.DeletingRandomAccessFile;
|
||||
import org.apache.pdfbox.io.IOUtils;
|
||||
import org.apache.pdfbox.io.MemoryUsageSetting;
|
||||
import org.apache.pdfbox.io.RandomAccessReadBufferedFile;
|
||||
import org.apache.pdfbox.io.RandomAccessStreamCache.StreamCacheCreateFunction;
|
||||
import org.apache.pdfbox.io.ScratchFile;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
@@ -102,16 +102,29 @@ public class CustomPDDocumentFactory {
|
||||
|
||||
// Since we don't know the size upfront, buffer to a temp file
|
||||
Path tempFile = createTempFile("pdf-stream-");
|
||||
try {
|
||||
Files.copy(input, tempFile, StandardCopyOption.REPLACE_EXISTING);
|
||||
return loadAdaptively(tempFile.toFile(), Files.size(tempFile));
|
||||
} catch (IOException e) {
|
||||
cleanupFile(tempFile);
|
||||
throw e;
|
||||
}
|
||||
|
||||
Files.copy(input, tempFile, StandardCopyOption.REPLACE_EXISTING);
|
||||
return loadAdaptively(tempFile.toFile(), Files.size(tempFile));
|
||||
}
|
||||
|
||||
private PDDocument loadAdaptively(Object source, long contentSize) throws IOException {
|
||||
/** Load with password from InputStream */
|
||||
public PDDocument load(InputStream input, String password) throws IOException {
|
||||
if (input == null) {
|
||||
throw new IllegalArgumentException("InputStream cannot be null");
|
||||
}
|
||||
|
||||
// Since we don't know the size upfront, buffer to a temp file
|
||||
Path tempFile = createTempFile("pdf-stream-");
|
||||
|
||||
Files.copy(input, tempFile, StandardCopyOption.REPLACE_EXISTING);
|
||||
return loadAdaptivelyWithPassword(tempFile.toFile(), Files.size(tempFile), password);
|
||||
}
|
||||
|
||||
/**
|
||||
* Determine the appropriate caching strategy based on file size and available memory. This
|
||||
* common method is used by both password and non-password loading paths.
|
||||
*/
|
||||
private StreamCacheCreateFunction getStreamCacheFunction(long contentSize) {
|
||||
long maxMemory = Runtime.getRuntime().maxMemory();
|
||||
long freeMemory = Runtime.getRuntime().freeMemory();
|
||||
long totalMemory = Runtime.getRuntime().totalMemory();
|
||||
@@ -129,32 +142,38 @@ public class CustomPDDocumentFactory {
|
||||
usedMemory / (1024 * 1024),
|
||||
maxMemory / (1024 * 1024));
|
||||
|
||||
// Determine caching strategy based on both file size and available memory
|
||||
StreamCacheCreateFunction cacheFunction;
|
||||
|
||||
// If free memory is critically low, always use file-based caching
|
||||
// In loadAdaptively method, replace current caching strategy decision with:
|
||||
if (freeMemoryPercent < MIN_FREE_MEMORY_PERCENTAGE
|
||||
|| actualFreeMemory < MIN_FREE_MEMORY_BYTES) {
|
||||
log.info(
|
||||
"Low memory detected ({}%), forcing file-based cache",
|
||||
String.format("%.2f", freeMemoryPercent));
|
||||
cacheFunction = createScratchFileCacheFunction(MemoryUsageSetting.setupTempFileOnly());
|
||||
return createScratchFileCacheFunction(MemoryUsageSetting.setupTempFileOnly());
|
||||
} else if (contentSize < SMALL_FILE_THRESHOLD) {
|
||||
log.info("Using memory-only cache for small document ({}KB)", contentSize / 1024);
|
||||
cacheFunction = IOUtils.createMemoryOnlyStreamCache();
|
||||
return IOUtils.createMemoryOnlyStreamCache();
|
||||
} else if (contentSize < LARGE_FILE_THRESHOLD) {
|
||||
// For medium files (10-50MB), use a mixed approach
|
||||
log.info(
|
||||
"Using mixed memory/file cache for medium document ({}MB)",
|
||||
contentSize / (1024 * 1024));
|
||||
cacheFunction =
|
||||
createScratchFileCacheFunction(MemoryUsageSetting.setupMixed(LARGE_FILE_USAGE));
|
||||
return createScratchFileCacheFunction(MemoryUsageSetting.setupMixed(LARGE_FILE_USAGE));
|
||||
} else {
|
||||
log.info("Using file-based cache for large document");
|
||||
cacheFunction = createScratchFileCacheFunction(MemoryUsageSetting.setupTempFileOnly());
|
||||
return createScratchFileCacheFunction(MemoryUsageSetting.setupTempFileOnly());
|
||||
}
|
||||
}
|
||||
|
||||
/** Update the existing loadAdaptively method to use the common function */
|
||||
private PDDocument loadAdaptively(Object source, long contentSize) throws IOException {
|
||||
// Get the appropriate caching strategy
|
||||
StreamCacheCreateFunction cacheFunction = getStreamCacheFunction(contentSize);
|
||||
|
||||
//If small handle as bytes and remove original file
|
||||
if (contentSize <= SMALL_FILE_THRESHOLD && source instanceof File file) {
|
||||
source = Files.readAllBytes(file.toPath());
|
||||
file.delete();
|
||||
}
|
||||
PDDocument document;
|
||||
if (source instanceof File file) {
|
||||
document = loadFromFile(file, contentSize, cacheFunction);
|
||||
@@ -168,6 +187,50 @@ public class CustomPDDocumentFactory {
|
||||
return document;
|
||||
}
|
||||
|
||||
/** Load a PDF with password protection using adaptive loading strategies */
|
||||
private PDDocument loadAdaptivelyWithPassword(Object source, long contentSize, String password)
|
||||
throws IOException {
|
||||
// Get the appropriate caching strategy
|
||||
StreamCacheCreateFunction cacheFunction = getStreamCacheFunction(contentSize);
|
||||
//If small handle as bytes and remove original file
|
||||
if (contentSize <= SMALL_FILE_THRESHOLD && source instanceof File file) {
|
||||
source = Files.readAllBytes(file.toPath());
|
||||
file.delete();
|
||||
}
|
||||
PDDocument document;
|
||||
if (source instanceof File file) {
|
||||
document = loadFromFileWithPassword(file, contentSize, cacheFunction, password);
|
||||
} else if (source instanceof byte[] bytes) {
|
||||
document = loadFromBytesWithPassword(bytes, contentSize, cacheFunction, password);
|
||||
} else {
|
||||
throw new IllegalArgumentException("Unsupported source type: " + source.getClass());
|
||||
}
|
||||
|
||||
postProcessDocument(document);
|
||||
return document;
|
||||
}
|
||||
|
||||
/** Load a file with password */
|
||||
private PDDocument loadFromFileWithPassword(
|
||||
File file, long size, StreamCacheCreateFunction cache, String password)
|
||||
throws IOException {
|
||||
return Loader.loadPDF(new DeletingRandomAccessFile(file), password, null, null, cache);
|
||||
}
|
||||
|
||||
/** Load bytes with password */
|
||||
private PDDocument loadFromBytesWithPassword(
|
||||
byte[] bytes, long size, StreamCacheCreateFunction cache, String password)
|
||||
throws IOException {
|
||||
if (size >= SMALL_FILE_THRESHOLD) {
|
||||
log.info("Writing large byte array to temp file for password-protected PDF");
|
||||
Path tempFile = createTempFile("pdf-bytes-");
|
||||
|
||||
Files.write(tempFile, bytes);
|
||||
return Loader.loadPDF(tempFile.toFile(), password, null, null, cache);
|
||||
}
|
||||
return Loader.loadPDF(bytes, password, null, null, cache);
|
||||
}
|
||||
|
||||
private StreamCacheCreateFunction createScratchFileCacheFunction(MemoryUsageSetting settings) {
|
||||
return () -> {
|
||||
try {
|
||||
@@ -185,11 +248,7 @@ public class CustomPDDocumentFactory {
|
||||
|
||||
private PDDocument loadFromFile(File file, long size, StreamCacheCreateFunction cache)
|
||||
throws IOException {
|
||||
if (size >= EXTREMELY_LARGE_THRESHOLD) {
|
||||
log.info("Loading extremely large file via buffered access");
|
||||
return Loader.loadPDF(new RandomAccessReadBufferedFile(file), "", null, null, cache);
|
||||
}
|
||||
return Loader.loadPDF(file, "", null, null, cache);
|
||||
return Loader.loadPDF(new DeletingRandomAccessFile(file), "", null, null, cache);
|
||||
}
|
||||
|
||||
private PDDocument loadFromBytes(byte[] bytes, long size, StreamCacheCreateFunction cache)
|
||||
@@ -197,12 +256,9 @@ public class CustomPDDocumentFactory {
|
||||
if (size >= SMALL_FILE_THRESHOLD) {
|
||||
log.info("Writing large byte array to temp file");
|
||||
Path tempFile = createTempFile("pdf-bytes-");
|
||||
try {
|
||||
Files.write(tempFile, bytes);
|
||||
return Loader.loadPDF(tempFile.toFile(), "", null, null, cache);
|
||||
} finally {
|
||||
cleanupFile(tempFile);
|
||||
}
|
||||
|
||||
Files.write(tempFile, bytes);
|
||||
return loadFromFile(tempFile.toFile(), size, cache);
|
||||
}
|
||||
return Loader.loadPDF(bytes, "", null, null, cache);
|
||||
}
|
||||
@@ -225,12 +281,9 @@ public class CustomPDDocumentFactory {
|
||||
}
|
||||
} else {
|
||||
Path tempFile = createTempFile("pdf-save-");
|
||||
try {
|
||||
document.save(tempFile.toFile());
|
||||
return Files.readAllBytes(tempFile);
|
||||
} finally {
|
||||
cleanupFile(tempFile);
|
||||
}
|
||||
|
||||
document.save(tempFile.toFile());
|
||||
return Files.readAllBytes(tempFile);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -258,17 +311,6 @@ public class CustomPDDocumentFactory {
|
||||
return Files.createTempDirectory(prefix + tempCounter.incrementAndGet() + "-");
|
||||
}
|
||||
|
||||
/** Clean up a temporary file */
|
||||
private void cleanupFile(Path file) {
|
||||
try {
|
||||
if (Files.deleteIfExists(file)) {
|
||||
log.info("Deleted temp file: {}", file);
|
||||
}
|
||||
} catch (IOException e) {
|
||||
log.info("Error deleting temp file {}", file, e);
|
||||
}
|
||||
}
|
||||
|
||||
/** Create new document bytes based on an existing document */
|
||||
public byte[] createNewBytesBasedOnOldDocument(byte[] oldDocument) throws IOException {
|
||||
try (PDDocument document = load(oldDocument)) {
|
||||
@@ -339,20 +381,11 @@ public class CustomPDDocumentFactory {
|
||||
|
||||
/** Load from a MultipartFile */
|
||||
public PDDocument load(MultipartFile pdfFile) throws IOException {
|
||||
return load(pdfFile.getBytes());
|
||||
return load(pdfFile.getInputStream());
|
||||
}
|
||||
|
||||
/** Load with password from MultipartFile */
|
||||
public PDDocument load(MultipartFile fileInput, String password) throws IOException {
|
||||
return load(fileInput.getBytes(), password);
|
||||
}
|
||||
|
||||
/** Load with password from byte array */
|
||||
private PDDocument load(byte[] bytes, String password) throws IOException {
|
||||
// Since we don't have direct password support in the adaptive loader,
|
||||
// we'll need to use PDFBox's Loader directly
|
||||
PDDocument document = Loader.loadPDF(bytes, password);
|
||||
pdfMetadataService.setDefaultMetadata(document);
|
||||
return document;
|
||||
return load(fileInput.getInputStream(), password);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user