javier/Stirling-PDF
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

More fixes for RequestPart mixing

Browse Source
This commit is contained in:
Anthony Stirling
2023-07-30 11:39:29 +01:00
parent 6b618f3abe 0732ffa76e
commit f98f089d63
55 changed files with 3789 additions and 653 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java
View File

@@ -83,7 +83,9 @@ public class EndpointConfiguration {
addEndpointToGroup("Convert", "pdf-to-text");
addEndpointToGroup("Convert", "pdf-to-html");
addEndpointToGroup("Convert", "pdf-to-xml");
addEndpointToGroup("Convert", "html-to-pdf");
addEndpointToGroup("Convert", "url-to-pdf");
// Adding endpoints to "Security" group
addEndpointToGroup("Security", "add-password");
addEndpointToGroup("Security", "remove-password");
@@ -125,12 +127,15 @@ public class EndpointConfiguration {
addEndpointToGroup("CLI", "pdf-to-html");
addEndpointToGroup("CLI", "pdf-to-xml");
addEndpointToGroup("CLI", "ocr-pdf");
addEndpointToGroup("CLI", "html-to-pdf");
addEndpointToGroup("CLI", "url-to-pdf");
//python
addEndpointToGroup("Python", "extract-image-scans");
addEndpointToGroup("Python", "remove-blanks");
addEndpointToGroup("Python", "html-to-pdf");
addEndpointToGroup("Python", "url-to-pdf");
//openCV
addEndpointToGroup("OpenCV", "extract-image-scans");

125
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertHtmlToPDF.java
View File

@@ -4,9 +4,13 @@ import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import java.util.zip.ZipEntry;
import java.util.zip.ZipInputStream;
import java.util.*;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestPart;
@@ -17,6 +21,7 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.GeneralUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -24,7 +29,7 @@ import stirling.software.SPDF.utils.WebResponseUtils;
public class ConvertHtmlToPDF {
@PostMapping(consumes = "multipart/form-data", value = "/convert-to-pdf")
@PostMapping(consumes = "multipart/form-data", value = "/html-to-pdf")
@Operation(
summary = "Convert an HTML or ZIP (containing HTML and CSS) to PDF",
description = "This endpoint takes an HTML or ZIP file input and converts it to a PDF format."
@@ -40,61 +45,83 @@ public class ConvertHtmlToPDF {
if (originalFilename == null || (!originalFilename.endsWith(".html") && !originalFilename.endsWith(".zip"))) {
throw new IllegalArgumentException("File must be either .html or .zip format.");
}
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
Path tempInputFile;
if (originalFilename.endsWith(".html")) {
tempInputFile = Files.createTempFile("input_", ".html");
Files.write(tempInputFile, fileInput.getBytes());
} else {
tempInputFile = unzipAndGetMainHtml(fileInput);
Path tempInputFile = null;
byte[] pdfBytes;
try {
if (originalFilename.endsWith(".html")) {
tempInputFile = Files.createTempFile("input_", ".html");
Files.write(tempInputFile, fileInput.getBytes());
} else {
tempInputFile = unzipAndGetMainHtml(fileInput);
}
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
ProcessExecutorResult returnCode;
if (originalFilename.endsWith(".zip")) {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command, tempInputFile.getParent().toFile());
} else {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command);
}
pdfBytes = Files.readAllBytes(tempOutputFile);
} finally {
// Clean up temporary files
Files.delete(tempOutputFile);
Files.delete(tempInputFile);
if (originalFilename.endsWith(".zip")) {
GeneralUtils.deleteDirectory(tempInputFile.getParent());
}
}
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
int returnCode = 0;
if (originalFilename.endsWith(".zip")) {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command, tempInputFile.getParent().toFile());
} else {
returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT)
.runCommandWithOutputHandling(command);
}
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
// Clean up temporary files
Files.delete(tempOutputFile);
Files.delete(tempInputFile);
if (originalFilename.endsWith(".zip")) {
GeneralUtils.deleteDirectory(tempInputFile.getParent());
}
String outputFilename = originalFilename.replaceFirst("[.][^.]+$", "") + ".pdf"; // Remove file extension and append .pdf
return WebResponseUtils.bytesToWebResponse(pdfBytes, outputFilename);
}
private Path unzipAndGetMainHtml(MultipartFile zipFile) throws IOException {
Path tempDirectory = Files.createTempDirectory("unzipped_");
try (ZipInputStream zipIn = new ZipInputStream(new ByteArrayInputStream(zipFile.getBytes()))) {
ZipEntry entry = zipIn.getNextEntry();
while (entry != null) {
Path filePath = tempDirectory.resolve(entry.getName());
if (!entry.isDirectory()) {
Files.copy(zipIn, filePath);
}
zipIn.closeEntry();
entry = zipIn.getNextEntry();
}
}
return tempDirectory.resolve("index.html");
}
private Path unzipAndGetMainHtml(MultipartFile zipFile) throws IOException {
Path tempDirectory = Files.createTempDirectory("unzipped_");
try (ZipInputStream zipIn = new ZipInputStream(new ByteArrayInputStream(zipFile.getBytes()))) {
ZipEntry entry = zipIn.getNextEntry();
while (entry != null) {
Path filePath = tempDirectory.resolve(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"))
.collect(Collectors.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 (htmlFile.getFileName().toString().equals("index.html")) {
return htmlFile;
}
}
return htmlFiles.get(0);
}
}

4
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertImgPDFController.java
View File

@@ -43,7 +43,7 @@ public class ConvertImgPDFController {
@Parameter(description = "Choose between a single image containing all pages or separate images for each page", schema = @Schema(allowableValues = {"single", "multiple"}))
String singleOrMultiple,
@RequestParam("colorType")
@Parameter(description = "The color type of the output image(s)", schema = @Schema(allowableValues = {"rgb", "greyscale", "blackwhite"}))
@Parameter(description = "The color type of the output image(s)", schema = @Schema(allowableValues = {"color", "greyscale", "blackwhite"}))
String colorType,
@RequestParam("dpi")
@Parameter(description = "The DPI (dots per inch) for the output image(s)")
@@ -94,7 +94,7 @@ public class ConvertImgPDFController {
@Parameter(description = "Whether to stretch the images to fit the PDF page or maintain the aspect ratio", example = "false")
boolean stretchToFit,
@RequestParam("colorType")
@Parameter(description = "The color type of the output image(s)", schema = @Schema(allowableValues = {"rgb", "greyscale", "blackwhite"}))
@Parameter(description = "The color type of the output image(s)", schema = @Schema(allowableValues = {"color", "greyscale", "blackwhite"}))
String colorType,
@RequestParam(defaultValue = "false", name = "autoRotate")
@Parameter(description = "Whether to automatically rotate the images to better fit the PDF page", example = "true")

7
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertOfficeController.java
View File

@@ -19,6 +19,7 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -41,7 +42,7 @@ public class ConvertOfficeController {
// Run the LibreOffice command
List<String> command = new ArrayList<>(Arrays.asList("unoconv", "-vvv", "-f", "pdf", "-o", tempOutputFile.toString(), tempInputFile.toString()));
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE).runCommandWithOutputHandling(command);
// Read the converted PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
@@ -62,10 +63,10 @@ public class ConvertOfficeController {
summary = "Convert a file to a PDF using LibreOffice",
description = "This endpoint converts a given file to a PDF using LibreOffice API Input:Any Output:PDF Type:SISO"
)
public ResponseEntity<byte[]> processPdfWithOCR(
public ResponseEntity<byte[]> processFileToPDF(
@RequestPart(required = true, value = "fileInput")
@Parameter(
description = "The input file to be converted to a PDF file using OCR",
description = "The input file to be converted to a PDF file using LibreOffice",
required = true
)
MultipartFile inputFile

3
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertPDFToPDFA.java
View File

@@ -16,6 +16,7 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -49,7 +50,7 @@ public class ConvertPDFToPDFA {
command.add(tempInputFile.toString());
command.add(tempOutputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
// Read the optimized PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);

45
src/main/java/stirling/software/SPDF/controller/api/converters/ConvertWebsiteToPDF.java
View File

@@ -8,6 +8,7 @@ import java.util.List;
import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RequestPart;
import org.springframework.web.bind.annotation.RestController;
import org.springframework.web.multipart.MultipartFile;
@@ -17,6 +18,7 @@ import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.GeneralUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -29,32 +31,35 @@ public class ConvertWebsiteToPDF {
description = "This endpoint fetches content from a URL and converts it to a PDF format."
)
public ResponseEntity<byte[]> urlToPdf(
@RequestPart(required = true, value = "urlInput")
@RequestParam(required = true, value = "urlInput")
@Parameter(description = "The input URL to be converted to a PDF file", required = true)
String URL) throws IOException, InterruptedException {
// Validate the URL format
if(!URL.matches("^https?://.*") && GeneralUtils.isValidURL(URL)) {
if(!URL.matches("^https?://.*") || !GeneralUtils.isValidURL(URL)) {
throw new IllegalArgumentException("Invalid URL format provided.");
}
// Prepare the output file path
Path tempOutputFile = Files.createTempFile("output_", ".pdf");
// Prepare the OCRmyPDF command
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(URL);
command.add(tempOutputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT).runCommandWithOutputHandling(command);
// Read the optimized PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);
// Clean up the temporary files
Files.delete(tempOutputFile);
Path tempOutputFile = null;
byte[] pdfBytes;
try {
// Prepare the output file path
tempOutputFile = Files.createTempFile("output_", ".pdf");
// Prepare the OCRmyPDF command
List<String> command = new ArrayList<>();
command.add("weasyprint");
command.add(URL);
command.add(tempOutputFile.toString());
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.WEASYPRINT).runCommandWithOutputHandling(command);
// Read the optimized PDF file
pdfBytes = Files.readAllBytes(tempOutputFile);
}
finally {
// Clean up the temporary files
Files.delete(tempOutputFile);
}
// Convert URL to a safe filename
String outputFilename = convertURLToFileName(URL);

28
src/main/java/stirling/software/SPDF/controller/api/other/AutoSplitPdfController.java
View File

@@ -41,20 +41,22 @@ public class AutoSplitPdfController {
@PostMapping(value = "/auto-split-pdf", consumes = "multipart/form-data")
@Operation(summary = "Auto split PDF pages into separate documents", description = "This endpoint accepts a PDF file, scans each page for a specific QR code, and splits the document at the QR code boundaries. The output is a zip file containing each separate PDF document. Input:PDF Output:ZIP Type:SISO")
public ResponseEntity<byte[]> autoSplitPdf(
@RequestParam("fileInput") @Parameter(description = "The input PDF file which needs to be split into separate documents based on QR code boundaries.", required = true) MultipartFile file)
@RequestParam("fileInput") @Parameter(description = "The input PDF file which needs to be split into separate documents based on QR code boundaries.", required = true) MultipartFile file,
@RequestParam(value ="duplexMode",defaultValue = "false") @Parameter(description = "Flag indicating if the duplex mode is active, where the page after the divider also gets removed.", required = false) boolean duplexMode)
throws IOException {
InputStream inputStream = file.getInputStream();
PDDocument document = PDDocument.load(inputStream);
PDFRenderer pdfRenderer = new PDFRenderer(document);
List<PDDocument> splitDocuments = new ArrayList<>();
List<ByteArrayOutputStream> splitDocumentsBoas = new ArrayList<>(); // create this list to store ByteArrayOutputStreams for zipping
List<ByteArrayOutputStream> splitDocumentsBoas = new ArrayList<>();
for (int page = 0; page < document.getNumberOfPages(); ++page) {
BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 150);
String result = decodeQRCode(bim);
if(QR_CONTENT.equals(result) && page != 0) {
if (QR_CONTENT.equals(result) && page != 0) {
splitDocuments.add(new PDDocument());
}
@@ -65,9 +67,16 @@ public class AutoSplitPdfController {
firstDocument.addPage(document.getPage(page));
splitDocuments.add(firstDocument);
}
// If duplexMode is true and current page is a divider, then skip next page
if (duplexMode && QR_CONTENT.equals(result)) {
page++;
}
}
// After all pages are added to splitDocuments, convert each to ByteArrayOutputStream and add to splitDocumentsBoas
// Remove split documents that have no pages
splitDocuments.removeIf(pdDocument -> pdDocument.getNumberOfPages() == 0);
for (PDDocument splitDocument : splitDocuments) {
ByteArrayOutputStream baos = new ByteArrayOutputStream();
splitDocument.save(baos);
@@ -77,18 +86,16 @@ public class AutoSplitPdfController {
document.close();
// After this line, you can find your zip logic integrated
Path zipFile = Files.createTempFile("split_documents", ".zip");
String filename = file.getOriginalFilename().replaceFirst("[.][^.]+$", "");
byte[] data;
try (ZipOutputStream zipOut = new ZipOutputStream(Files.newOutputStream(zipFile))) {
// loop through the split documents and write them to the zip file
for (int i = 0; i < splitDocumentsBoas.size(); i++) {
String fileName = filename + "_" + (i + 1) + ".pdf"; // You should replace "originalFileName" with the real file name
String fileName = filename + "_" + (i + 1) + ".pdf";
ByteArrayOutputStream baos = splitDocumentsBoas.get(i);
byte[] pdf = baos.toByteArray();
// Add PDF file to the zip
ZipEntry pdfEntry = new ZipEntry(fileName);
zipOut.putNextEntry(pdfEntry);
zipOut.write(pdf);
@@ -101,9 +108,6 @@ public class AutoSplitPdfController {
Files.delete(zipFile);
}
// return the Resource in the response
return WebResponseUtils.bytesToWebResponse(data, filename + ".zip", MediaType.APPLICATION_OCTET_STREAM);
}

5
src/main/java/stirling/software/SPDF/controller/api/other/BlankPageController.java
View File

@@ -31,6 +31,7 @@ import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.PdfUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -86,10 +87,10 @@ public class BlankPageController {
List<String> command = new ArrayList<>(Arrays.asList("python3", System.getProperty("user.dir") + "/scripts/detect-blank-pages.py", tempFile.toString() ,"--threshold", String.valueOf(threshold), "--white_percent", String.valueOf(whitePercent)));
// Run CLI command
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.PYTHON_OPENCV).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.PYTHON_OPENCV).runCommandWithOutputHandling(command);
// does contain data
if (returnCode == 0) {
if (returnCode.getRc() == 0) {
System.out.println("page " + pageIndex + " has image which is not blank");
pagesToKeepIndex.add(pageIndex);
} else {

3
src/main/java/stirling/software/SPDF/controller/api/other/CompressController.java
View File

@@ -34,6 +34,7 @@ import io.swagger.v3.oas.annotations.media.Schema;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.GeneralUtils;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -116,7 +117,7 @@ public class CompressController {
command.add("-sOutputFile=" + tempOutputFile.toString());
command.add(tempInputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(command);
// Check if file size is within expected size or not auto mode so instantly finish
long outputFileSize = Files.size(tempOutputFile);

3
src/main/java/stirling/software/SPDF/controller/api/other/ExtractImageScansController.java
View File

@@ -33,6 +33,7 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -117,7 +118,7 @@ public class ExtractImageScansController {
// Run CLI command
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.PYTHON_OPENCV).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.PYTHON_OPENCV).runCommandWithOutputHandling(command);
// Read the output photos in temp directory
List<Path> tempOutputFiles = Files.list(tempDir).sorted().collect(Collectors.toList());

11
src/main/java/stirling/software/SPDF/controller/api/other/OCRController.java
View File

@@ -29,6 +29,7 @@ import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.media.Schema;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -141,8 +142,12 @@ public class OCRController {
command.addAll(Arrays.asList("--language", languageOption, tempInputFile.toString(), tempOutputFile.toString()));
// Run CLI command
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
ProcessExecutorResult result = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
if(result.getRc() != 0 && result.getMessages().contains("multiprocessing/synchronize.py") && result.getMessages().contains("OSError: [Errno 38] Function not implemented")) {
command.add("--jobs");
command.add("1");
result = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
}
@@ -153,7 +158,7 @@ public class OCRController {
List<String> gsCommand = Arrays.asList("gs", "-sDEVICE=pdfwrite", "-dFILTERIMAGE", "-o", tempPdfWithoutImages.toString(), tempOutputFile.toString());
int gsReturnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(gsCommand);
ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(gsCommand);
tempOutputFile = tempPdfWithoutImages;
}
// Read the OCR processed PDF file

6
src/main/java/stirling/software/SPDF/controller/api/other/PageNumbersController.java
View File

@@ -165,10 +165,8 @@ public class PageNumbersController {
pdfDoc.close();
byte[] resultBytes = baos.toByteArray();
return ResponseEntity.ok()
.header("Content-Type", "application/pdf; charset=UTF-8")
.header("Content-Disposition", "inline; filename=" + URLEncoder.encode(file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_numbersAdded.pdf", "UTF-8"))
.body(resultBytes);
return WebResponseUtils.bytesToWebResponse(resultBytes, URLEncoder.encode(file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_numbersAdded.pdf", "UTF-8"), MediaType.APPLICATION_PDF);
}

3
src/main/java/stirling/software/SPDF/controller/api/other/RepairController.java
View File

@@ -18,6 +18,7 @@ import io.swagger.v3.oas.annotations.Operation;
import io.swagger.v3.oas.annotations.Parameter;
import io.swagger.v3.oas.annotations.tags.Tag;
import stirling.software.SPDF.utils.ProcessExecutor;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
import stirling.software.SPDF.utils.WebResponseUtils;
@RestController
@@ -51,7 +52,7 @@ public class RepairController {
command.add(tempInputFile.toString());
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(command);
// Read the optimized PDF file
byte[] pdfBytes = Files.readAllBytes(tempOutputFile);

22
src/main/java/stirling/software/SPDF/controller/api/security/PasswordController.java
View File

@@ -52,37 +52,37 @@ public class PasswordController {
@RequestPart(required = true, value = "fileInput")
@Parameter(description = "The input PDF file to which the password should be added", required = true)
MultipartFile fileInput,
@RequestParam(defaultValue = "", name = "ownerPassword")
@RequestParam(value = "", name = "ownerPassword")
@Parameter(description = "The owner password to be added to the PDF file (Restricts what can be done with the document once it is opened)")
String ownerPassword,
@RequestParam(defaultValue = "", name = "password")
@RequestParam( name = "password", required = false)
@Parameter(description = "The password to be added to the PDF file (Restricts the opening of the document itself.)")
String password,
@RequestParam(defaultValue = "128", name = "keyLength")
@RequestParam( name = "keyLength", required = false)
@Parameter(description = "The length of the encryption key", schema = @Schema(allowableValues = {"40", "128", "256"}))
int keyLength,
@RequestParam(defaultValue = "false", name = "canAssembleDocument")
@RequestParam( name = "canAssembleDocument", required = false)
@Parameter(description = "Whether the document assembly is allowed", example = "false")
boolean canAssembleDocument,
@RequestParam(defaultValue = "false", name = "canExtractContent")
@RequestParam( name = "canExtractContent", required = false)
@Parameter(description = "Whether content extraction for accessibility is allowed", example = "false")
boolean canExtractContent,
@RequestParam(defaultValue = "false", name = "canExtractForAccessibility")
@RequestParam( name = "canExtractForAccessibility", required = false)
@Parameter(description = "Whether content extraction for accessibility is allowed", example = "false")
boolean canExtractForAccessibility,
@RequestParam(defaultValue = "false", name = "canFillInForm")
@RequestParam( name = "canFillInForm", required = false)
@Parameter(description = "Whether form filling is allowed", example = "false")
boolean canFillInForm,
@RequestParam(defaultValue = "false", name = "canModify")
@RequestParam( name = "canModify", required = false)
@Parameter(description = "Whether the document modification is allowed", example = "false")
boolean canModify,
@RequestParam(defaultValue = "false", name = "canModifyAnnotations")
@RequestParam( name = "canModifyAnnotations", required = false)
@Parameter(description = "Whether modification of annotations is allowed", example = "false")
boolean canModifyAnnotations,
@RequestParam(defaultValue = "false", name = "canPrint")
@RequestParam(name = "canPrint", required = false)
@Parameter(description = "Whether printing of the document is allowed", example = "false")
boolean canPrint,
@RequestParam(defaultValue = "false", name = "canPrintFaithful")
@RequestParam( name = "canPrintFaithful", required = false)
@Parameter(description = "Whether faithful printing is allowed", example = "false")
boolean canPrintFaithful
) throws IOException {

190
src/main/java/stirling/software/SPDF/controller/web/ConverterWebController.java
View File

@@ -1,88 +1,102 @@
package stirling.software.SPDF.controller.web;
import org.springframework.stereotype.Controller;
import org.springframework.ui.Model;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.servlet.ModelAndView;
import io.swagger.v3.oas.annotations.Hidden;
import io.swagger.v3.oas.annotations.tags.Tag;
@Controller
@Tag(name = "Convert", description = "Convert APIs")
public class ConverterWebController {
@GetMapping("/img-to-pdf")
@Hidden
public String convertImgToPdfForm(Model model) {
model.addAttribute("currentPage", "img-to-pdf");
return "convert/img-to-pdf";
}
@GetMapping("/pdf-to-img")
@Hidden
public String pdfToimgForm(Model model) {
model.addAttribute("currentPage", "pdf-to-img");
return "convert/pdf-to-img";
}
@GetMapping("/file-to-pdf")
@Hidden
public String convertToPdfForm(Model model) {
model.addAttribute("currentPage", "file-to-pdf");
return "convert/file-to-pdf";
}
//PDF TO......
@GetMapping("/pdf-to-html")
@Hidden
public ModelAndView pdfToHTML() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-html");
modelAndView.addObject("currentPage", "pdf-to-html");
return modelAndView;
}
@GetMapping("/pdf-to-presentation")
@Hidden
public ModelAndView pdfToPresentation() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-presentation");
modelAndView.addObject("currentPage", "pdf-to-presentation");
return modelAndView;
}
@GetMapping("/pdf-to-text")
@Hidden
public ModelAndView pdfToText() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-text");
modelAndView.addObject("currentPage", "pdf-to-text");
return modelAndView;
}
@GetMapping("/pdf-to-word")
@Hidden
public ModelAndView pdfToWord() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-word");
modelAndView.addObject("currentPage", "pdf-to-word");
return modelAndView;
}
@GetMapping("/pdf-to-xml")
@Hidden
public ModelAndView pdfToXML() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-xml");
modelAndView.addObject("currentPage", "pdf-to-xml");
return modelAndView;
}
@GetMapping("/pdf-to-pdfa")
@Hidden
public String pdfToPdfAForm(Model model) {
model.addAttribute("currentPage", "pdf-to-pdfa");
return "convert/pdf-to-pdfa";
}
}
package stirling.software.SPDF.controller.web;
import org.springframework.stereotype.Controller;
import org.springframework.ui.Model;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.servlet.ModelAndView;
import io.swagger.v3.oas.annotations.Hidden;
import io.swagger.v3.oas.annotations.tags.Tag;
@Controller
@Tag(name = "Convert", description = "Convert APIs")
public class ConverterWebController {
@GetMapping("/img-to-pdf")
@Hidden
public String convertImgToPdfForm(Model model) {
model.addAttribute("currentPage", "img-to-pdf");
return "convert/img-to-pdf";
}
@GetMapping("/html-to-pdf")
@Hidden
public String convertHTMLToPdfForm(Model model) {
model.addAttribute("currentPage", "html-to-pdf");
return "convert/html-to-pdf";
}
@GetMapping("/url-to-pdf")
@Hidden
public String convertURLToPdfForm(Model model) {
model.addAttribute("currentPage", "url-to-pdf");
return "convert/url-to-pdf";
}
@GetMapping("/pdf-to-img")
@Hidden
public String pdfToimgForm(Model model) {
model.addAttribute("currentPage", "pdf-to-img");
return "convert/pdf-to-img";
}
@GetMapping("/file-to-pdf")
@Hidden
public String convertToPdfForm(Model model) {
model.addAttribute("currentPage", "file-to-pdf");
return "convert/file-to-pdf";
}
//PDF TO......
@GetMapping("/pdf-to-html")
@Hidden
public ModelAndView pdfToHTML() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-html");
modelAndView.addObject("currentPage", "pdf-to-html");
return modelAndView;
}
@GetMapping("/pdf-to-presentation")
@Hidden
public ModelAndView pdfToPresentation() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-presentation");
modelAndView.addObject("currentPage", "pdf-to-presentation");
return modelAndView;
}
@GetMapping("/pdf-to-text")
@Hidden
public ModelAndView pdfToText() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-text");
modelAndView.addObject("currentPage", "pdf-to-text");
return modelAndView;
}
@GetMapping("/pdf-to-word")
@Hidden
public ModelAndView pdfToWord() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-word");
modelAndView.addObject("currentPage", "pdf-to-word");
return modelAndView;
}
@GetMapping("/pdf-to-xml")
@Hidden
public ModelAndView pdfToXML() {
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-xml");
modelAndView.addObject("currentPage", "pdf-to-xml");
return modelAndView;
}
@GetMapping("/pdf-to-pdfa")
@Hidden
public String pdfToPdfAForm(Model model) {
model.addAttribute("currentPage", "pdf-to-pdfa");
return "convert/pdf-to-pdfa";
}
}

45
src/main/java/stirling/software/SPDF/controller/web/GeneralWebController.java
View File

@@ -1,30 +1,25 @@
package stirling.software.SPDF.controller.web;
import java.io.File;
import java.io.IOException;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.core.io.Resource;
import org.springframework.core.io.ResourceLoader;
import org.springframework.core.io.support.ResourcePatternUtils;
import org.springframework.stereotype.Controller;
import org.springframework.ui.Model;
import org.springframework.web.bind.annotation.GetMapping;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;
import java.util.HashMap;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.ModelAttribute;
import com.fasterxml.jackson.databind.ObjectMapper;
import io.swagger.v3.oas.annotations.Hidden;
@@ -123,18 +118,30 @@ public class GeneralWebController {
model.addAttribute("fonts", getFontNames());
return "sign";
}
@Autowired
private ResourceLoader resourceLoader;
private List<String> getFontNames() {
try {
return Files.list(Paths.get("src/main/resources/static/fonts"))
.map(Path::getFileName)
.map(Path::toString)
.filter(name -> name.endsWith(".woff2"))
.map(name -> name.substring(0, name.length() - 6)) // Remove .woff2 extension
Resource[] resources = ResourcePatternUtils.getResourcePatternResolver(resourceLoader)
.getResources("classpath:static/fonts/*.woff2");
return Arrays.stream(resources)
.map(resource -> {
try {
String filename = resource.getFilename();
return filename.substring(0, filename.length() - 6); // Remove .woff2 extension
} catch (Exception e) {
throw new RuntimeException("Error processing filename", e);
}
})
.collect(Collectors.toList());
} catch (IOException e) {
} catch (Exception e) {
throw new RuntimeException("Failed to read font directory", e);
}
}
@GetMapping("/crop")

2
src/main/java/stirling/software/SPDF/controller/web/SecurityWebController.java
View File

@@ -10,6 +10,8 @@ import io.swagger.v3.oas.annotations.tags.Tag;
@Controller
@Tag(name = "Security", description = "Security APIs")
public class SecurityWebController {
@GetMapping("/add-password")
@Hidden
public String addPasswordForm(Model model) {

4
src/main/java/stirling/software/SPDF/utils/PDFToFile.java
View File

@@ -20,6 +20,8 @@ import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.multipart.MultipartFile;
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
public class PDFToFile {
public ResponseEntity<byte[]> processPdfToOfficeFormat(MultipartFile inputFile, String outputFormat, String libreOfficeFilter) throws IOException, InterruptedException {
@@ -53,7 +55,7 @@ public class PDFToFile {
// Run the LibreOffice command
List<String> command = new ArrayList<>(
Arrays.asList("soffice", "--infilter=" + libreOfficeFilter, "--convert-to", outputFormat, "--outdir", tempOutputDir.toString(), tempInputFile.toString()));
int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE).runCommandWithOutputHandling(command);
ProcessExecutorResult returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.LIBRE_OFFICE).runCommandWithOutputHandling(command);
// Get output files
List<File> outputFiles = Arrays.asList(tempOutputDir.toFile().listFiles());

34
src/main/java/stirling/software/SPDF/utils/ProcessExecutor.java
View File

@@ -37,11 +37,12 @@ public class ProcessExecutor {
private ProcessExecutor(int semaphoreLimit) {
this.semaphore = new Semaphore(semaphoreLimit);
}
public int runCommandWithOutputHandling(List<String> command) throws IOException, InterruptedException {
public ProcessExecutorResult runCommandWithOutputHandling(List<String> command) throws IOException, InterruptedException {
return runCommandWithOutputHandling(command, null);
}
public int runCommandWithOutputHandling(List<String> command, File workingDirectory) throws IOException, InterruptedException {
public ProcessExecutorResult runCommandWithOutputHandling(List<String> command, File workingDirectory) throws IOException, InterruptedException {
int exitCode = 1;
String messages = "";
semaphore.acquire();
try {
@@ -89,14 +90,16 @@ public class ProcessExecutor {
// Wait for the reader threads to finish
errorReaderThread.join();
outputReaderThread.join();
if (outputLines.size() > 0) {
String outputMessage = String.join("\n", outputLines);
messages += outputMessage;
System.out.println("Command output:\n" + outputMessage);
}
if (errorLines.size() > 0) {
String errorMessage = String.join("\n", errorLines);
messages += errorMessage;
System.out.println("Command error output:\n" + errorMessage);
if (exitCode != 0) {
throw new IOException("Command process failed with exit code " + exitCode + ". Error message: " + errorMessage);
@@ -105,7 +108,28 @@ public class ProcessExecutor {
} finally {
semaphore.release();
}
return exitCode;
return new ProcessExecutorResult(exitCode, messages);
}
public class ProcessExecutorResult{
int rc;
String messages;
public ProcessExecutorResult(int rc, String messages) {
this.rc = rc;
this.messages = messages;
}
public int getRc() {
return rc;
}
public void setRc(int rc) {
this.rc = rc;
}
public String getMessages() {
return messages;
}
public void setMessages(String messages) {
this.messages = messages;
}
}
}