Merge remote-tracking branch 'origin/main' into add-elements
This commit is contained in:
Anthony Stirling
@@ -4,75 +4,83 @@ import java.io.ByteArrayInputStream;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.pdfbox.multipdf.LayerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.kernel.geom.PageSize;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfPage;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfWriter;
|
||||
import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
|
||||
import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.general.CropPdfForm;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class CropController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(CropController.class);
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(CropController.class);
|
||||
|
||||
@PostMapping(value = "/crop", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Crops a PDF document", description = "This operation takes an input PDF file and crops it according to the given coordinates. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> cropPdf(
|
||||
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
|
||||
@Parameter(description = "The x-coordinate of the top-left corner of the crop area", required = true, schema = @Schema(type = "number")) @RequestParam("x") float x,
|
||||
@Parameter(description = "The y-coordinate of the top-left corner of the crop area", required = true, schema = @Schema(type = "number")) @RequestParam("y") float y,
|
||||
@Parameter(description = "The width of the crop area", required = true, schema = @Schema(type = "number")) @RequestParam("width") float width,
|
||||
@Parameter(description = "The height of the crop area", required = true, schema = @Schema(type = "number")) @RequestParam("height") float height) throws IOException {
|
||||
byte[] bytes = file.getBytes();
|
||||
System.out.println("x=" + x + ", " + "y=" + y + ", " + "width=" + width + ", " +"height=" + height );
|
||||
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
|
||||
PdfDocument pdfDoc = new PdfDocument(reader);
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
PdfDocument outputPdf = new PdfDocument(writer);
|
||||
|
||||
int totalPages = pdfDoc.getNumberOfPages();
|
||||
|
||||
for (int i = 1; i <= totalPages; i++) {
|
||||
PdfPage page = outputPdf.addNewPage(new PageSize(width, height));
|
||||
PdfCanvas pdfCanvas = new PdfCanvas(page);
|
||||
public ResponseEntity<byte[]> cropPdf(@ModelAttribute CropPdfForm form)
|
||||
throws IOException {
|
||||
|
||||
PdfFormXObject formXObject = pdfDoc.getPage(i).copyAsFormXObject(outputPdf);
|
||||
|
||||
// Save the graphics state, apply the transformations, add the object, and then
|
||||
// restore the graphics state
|
||||
pdfCanvas.saveState();
|
||||
pdfCanvas.rectangle(x, y, width, height);
|
||||
pdfCanvas.clip();
|
||||
pdfCanvas.addXObject(formXObject, -x, -y);
|
||||
pdfCanvas.restoreState();
|
||||
}
|
||||
|
||||
|
||||
|
||||
outputPdf.close();
|
||||
byte[] pdfContent = baos.toByteArray();
|
||||
pdfDoc.close();
|
||||
return WebResponseUtils.bytesToWebResponse(pdfContent,
|
||||
file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_cropped.pdf");
|
||||
PDDocument sourceDocument = PDDocument.load(new ByteArrayInputStream(form.getFileInput().getBytes()));
|
||||
|
||||
PDDocument newDocument = new PDDocument();
|
||||
|
||||
int totalPages = sourceDocument.getNumberOfPages();
|
||||
|
||||
LayerUtility layerUtility = new LayerUtility(newDocument);
|
||||
|
||||
for (int i = 0; i < totalPages; i++) {
|
||||
PDPage sourcePage = sourceDocument.getPage(i);
|
||||
|
||||
// Create a new page with the size of the source page
|
||||
PDPage newPage = new PDPage(sourcePage.getMediaBox());
|
||||
newDocument.addPage(newPage);
|
||||
PDPageContentStream contentStream = new PDPageContentStream(newDocument, newPage);
|
||||
|
||||
// Import the source page as a form XObject
|
||||
PDFormXObject formXObject = layerUtility.importPageAsForm(sourceDocument, i);
|
||||
|
||||
contentStream.saveGraphicsState();
|
||||
|
||||
// Define the crop area
|
||||
contentStream.addRect(form.getX(), form.getY(), form.getWidth(), form.getHeight());
|
||||
contentStream.clip();
|
||||
|
||||
// Draw the entire formXObject
|
||||
contentStream.drawForm(formXObject);
|
||||
|
||||
contentStream.restoreGraphicsState();
|
||||
|
||||
contentStream.close();
|
||||
|
||||
// Now, set the new page's media box to the cropped size
|
||||
newPage.setMediaBox(new PDRectangle(form.getX(), form.getY(), form.getWidth(), form.getHeight()));
|
||||
}
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
newDocument.save(baos);
|
||||
newDocument.close();
|
||||
sourceDocument.close();
|
||||
|
||||
byte[] pdfContent = baos.toByteArray();
|
||||
return WebResponseUtils.bytesToWebResponse(pdfContent, form.getFileInput().getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_cropped.pdf");
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -1,125 +1,114 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Paths;
|
||||
import java.nio.file.attribute.BasicFileAttributes;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Arrays;
|
||||
import java.util.Comparator;
|
||||
import java.util.List;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import org.apache.pdfbox.io.MemoryUsageSetting;
|
||||
import org.apache.pdfbox.multipdf.PDFMergerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.general.MergePdfsRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Paths;
|
||||
import java.nio.file.attribute.BasicFileAttributes;
|
||||
import java.util.Arrays;
|
||||
import java.util.Comparator;
|
||||
import java.util.List;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class MergeController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(MergeController.class);
|
||||
|
||||
|
||||
private PDDocument mergeDocuments(List<PDDocument> documents) throws IOException {
|
||||
PDDocument mergedDoc = new PDDocument();
|
||||
for (PDDocument doc : documents) {
|
||||
for (PDPage page : doc.getPages()) {
|
||||
mergedDoc.addPage(page);
|
||||
}
|
||||
}
|
||||
return mergedDoc;
|
||||
}
|
||||
|
||||
private Comparator<MultipartFile> getSortComparator(String sortType) {
|
||||
switch (sortType) {
|
||||
case "byFileName":
|
||||
return Comparator.comparing(MultipartFile::getOriginalFilename);
|
||||
case "byDateModified":
|
||||
return (file1, file2) -> {
|
||||
try {
|
||||
BasicFileAttributes attr1 = Files.readAttributes(Paths.get(file1.getOriginalFilename()), BasicFileAttributes.class);
|
||||
BasicFileAttributes attr2 = Files.readAttributes(Paths.get(file2.getOriginalFilename()), BasicFileAttributes.class);
|
||||
return attr1.lastModifiedTime().compareTo(attr2.lastModifiedTime());
|
||||
} catch (IOException e) {
|
||||
return 0; // If there's an error, treat them as equal
|
||||
}
|
||||
};
|
||||
case "byDateCreated":
|
||||
return (file1, file2) -> {
|
||||
try {
|
||||
BasicFileAttributes attr1 = Files.readAttributes(Paths.get(file1.getOriginalFilename()), BasicFileAttributes.class);
|
||||
BasicFileAttributes attr2 = Files.readAttributes(Paths.get(file2.getOriginalFilename()), BasicFileAttributes.class);
|
||||
return attr1.creationTime().compareTo(attr2.creationTime());
|
||||
} catch (IOException e) {
|
||||
return 0; // If there's an error, treat them as equal
|
||||
}
|
||||
};
|
||||
case "byPDFTitle":
|
||||
return (file1, file2) -> {
|
||||
try (PDDocument doc1 = PDDocument.load(file1.getInputStream());
|
||||
PDDocument doc2 = PDDocument.load(file2.getInputStream())) {
|
||||
String title1 = doc1.getDocumentInformation().getTitle();
|
||||
String title2 = doc2.getDocumentInformation().getTitle();
|
||||
return title1.compareTo(title2);
|
||||
} catch (IOException e) {
|
||||
return 0;
|
||||
}
|
||||
};
|
||||
case "orderProvided":
|
||||
default:
|
||||
return (file1, file2) -> 0; // Default is the order provided
|
||||
}
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/merge-pdfs")
|
||||
@Operation(summary = "Merge multiple PDF files into one",
|
||||
description = "This endpoint merges multiple PDF files into a single PDF file. The merged file will contain all pages from the input files in the order they were provided. Input:PDF Output:PDF Type:MISO")
|
||||
public ResponseEntity<byte[]> mergePdfs(
|
||||
@RequestPart(required = true, value = "fileInput") MultipartFile[] files,
|
||||
@RequestParam(value = "sortType", defaultValue = "orderProvided")
|
||||
@Parameter(schema = @Schema(description = "The type of sorting to be applied on the input files before merging.",
|
||||
allowableValues = {
|
||||
"orderProvided",
|
||||
"byFileName",
|
||||
"byDateModified",
|
||||
"byDateCreated",
|
||||
"byPDFTitle"
|
||||
}))
|
||||
String sortType) throws IOException {
|
||||
|
||||
Arrays.sort(files, getSortComparator(sortType));
|
||||
|
||||
List<PDDocument> documents = new ArrayList<>();
|
||||
for (MultipartFile file : files) {
|
||||
try (InputStream is = file.getInputStream()) {
|
||||
documents.add(PDDocument.load(is));
|
||||
}
|
||||
}
|
||||
|
||||
try (PDDocument mergedDoc = mergeDocuments(documents)) {
|
||||
ResponseEntity<byte[]> response = WebResponseUtils.pdfDocToWebResponse(mergedDoc, files[0].getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_merged.pdf");
|
||||
return response;
|
||||
} finally {
|
||||
private PDDocument mergeDocuments(List<PDDocument> documents) throws IOException {
|
||||
PDDocument mergedDoc = new PDDocument();
|
||||
for (PDDocument doc : documents) {
|
||||
if (doc != null) {
|
||||
doc.close();
|
||||
for (PDPage page : doc.getPages()) {
|
||||
mergedDoc.addPage(page);
|
||||
}
|
||||
}
|
||||
return mergedDoc;
|
||||
}
|
||||
|
||||
private Comparator<MultipartFile> getSortComparator(String sortType) {
|
||||
switch (sortType) {
|
||||
case "byFileName":
|
||||
return Comparator.comparing(MultipartFile::getOriginalFilename);
|
||||
case "byDateModified":
|
||||
return (file1, file2) -> {
|
||||
try {
|
||||
BasicFileAttributes attr1 = Files.readAttributes(Paths.get(file1.getOriginalFilename()), BasicFileAttributes.class);
|
||||
BasicFileAttributes attr2 = Files.readAttributes(Paths.get(file2.getOriginalFilename()), BasicFileAttributes.class);
|
||||
return attr1.lastModifiedTime().compareTo(attr2.lastModifiedTime());
|
||||
} catch (IOException e) {
|
||||
return 0; // If there's an error, treat them as equal
|
||||
}
|
||||
};
|
||||
case "byDateCreated":
|
||||
return (file1, file2) -> {
|
||||
try {
|
||||
BasicFileAttributes attr1 = Files.readAttributes(Paths.get(file1.getOriginalFilename()), BasicFileAttributes.class);
|
||||
BasicFileAttributes attr2 = Files.readAttributes(Paths.get(file2.getOriginalFilename()), BasicFileAttributes.class);
|
||||
return attr1.creationTime().compareTo(attr2.creationTime());
|
||||
} catch (IOException e) {
|
||||
return 0; // If there's an error, treat them as equal
|
||||
}
|
||||
};
|
||||
case "byPDFTitle":
|
||||
return (file1, file2) -> {
|
||||
try (PDDocument doc1 = PDDocument.load(file1.getInputStream());
|
||||
PDDocument doc2 = PDDocument.load(file2.getInputStream())) {
|
||||
String title1 = doc1.getDocumentInformation().getTitle();
|
||||
String title2 = doc2.getDocumentInformation().getTitle();
|
||||
return title1.compareTo(title2);
|
||||
} catch (IOException e) {
|
||||
return 0;
|
||||
}
|
||||
};
|
||||
case "orderProvided":
|
||||
default:
|
||||
return (file1, file2) -> 0; // Default is the order provided
|
||||
}
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/merge-pdfs")
|
||||
@Operation(summary = "Merge multiple PDF files into one",
|
||||
description = "This endpoint merges multiple PDF files into a single PDF file. The merged file will contain all pages from the input files in the order they were provided. Input:PDF Output:PDF Type:MISO")
|
||||
public ResponseEntity<byte[]> mergePdfs(@ModelAttribute MergePdfsRequest form) throws IOException {
|
||||
try {
|
||||
MultipartFile[] files = form.getFileInput();
|
||||
Arrays.sort(files, getSortComparator(form.getSortType()));
|
||||
|
||||
PDFMergerUtility mergedDoc = new PDFMergerUtility();
|
||||
ByteArrayOutputStream docOutputstream = new ByteArrayOutputStream();
|
||||
|
||||
for (MultipartFile file : files) {
|
||||
mergedDoc.addSource(new ByteArrayInputStream(file.getBytes()));
|
||||
}
|
||||
|
||||
mergedDoc.setDestinationFileName(files[0].getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_merged.pdf");
|
||||
mergedDoc.setDestinationStream(docOutputstream);
|
||||
mergedDoc.mergeDocuments(MemoryUsageSetting.setupMainMemoryOnly());
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(docOutputstream.toByteArray(), mergedDoc.getDestinationFileName());
|
||||
} catch (Exception ex) {
|
||||
logger.error("Error in merge pdf process", ex);
|
||||
throw ex;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@@ -1,101 +1,124 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
|
||||
import java.awt.Color;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.pdfbox.multipdf.LayerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.apache.pdfbox.util.Matrix;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.kernel.geom.PageSize;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfPage;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfWriter;
|
||||
import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
|
||||
import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.general.MergeMultiplePagesRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class MultiPageLayoutController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(MultiPageLayoutController.class);
|
||||
|
||||
@PostMapping(value = "/multi-page-layout", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Merge multiple pages of a PDF document into a single page", description = "This operation takes an input PDF file and the number of pages to merge into a single sheet in the output PDF file. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> mergeMultiplePagesIntoOne(
|
||||
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
|
||||
@Parameter(description = "The number of pages to fit onto a single sheet in the output PDF. Acceptable values are 2, 3, 4, 9, 16.", required = true, schema = @Schema(type = "integer", allowableValues = {
|
||||
"2", "3", "4", "9", "16" })) @RequestParam("pagesPerSheet") int pagesPerSheet)
|
||||
throws IOException {
|
||||
@Operation(
|
||||
summary = "Merge multiple pages of a PDF document into a single page",
|
||||
description = "This operation takes an input PDF file and the number of pages to merge into a single sheet in the output PDF file. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> mergeMultiplePagesIntoOne(@ModelAttribute MergeMultiplePagesRequest request)
|
||||
throws IOException {
|
||||
|
||||
if (pagesPerSheet != 2 && pagesPerSheet != 3
|
||||
&& pagesPerSheet != (int) Math.sqrt(pagesPerSheet) * Math.sqrt(pagesPerSheet)) {
|
||||
throw new IllegalArgumentException("pagesPerSheet must be 2, 3 or a perfect square");
|
||||
}
|
||||
int pagesPerSheet = request.getPagesPerSheet();
|
||||
MultipartFile file = request.getFileInput();
|
||||
boolean addBorder = request.isAddBorder();
|
||||
|
||||
if (pagesPerSheet != 2 && pagesPerSheet != 3 && pagesPerSheet != (int) Math.sqrt(pagesPerSheet) * Math.sqrt(pagesPerSheet)) {
|
||||
throw new IllegalArgumentException("pagesPerSheet must be 2, 3 or a perfect square");
|
||||
}
|
||||
|
||||
int cols = pagesPerSheet == 2 || pagesPerSheet == 3 ? pagesPerSheet : (int) Math.sqrt(pagesPerSheet);
|
||||
int rows = pagesPerSheet == 2 || pagesPerSheet == 3 ? 1 : (int) Math.sqrt(pagesPerSheet);
|
||||
int cols = pagesPerSheet == 2 || pagesPerSheet == 3 ? pagesPerSheet : (int) Math.sqrt(pagesPerSheet);
|
||||
int rows = pagesPerSheet == 2 || pagesPerSheet == 3 ? 1 : (int) Math.sqrt(pagesPerSheet);
|
||||
|
||||
byte[] bytes = file.getBytes();
|
||||
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
|
||||
PdfDocument pdfDoc = new PdfDocument(reader);
|
||||
PDDocument sourceDocument = PDDocument.load(file.getInputStream());
|
||||
PDDocument newDocument = new PDDocument();
|
||||
PDPage newPage = new PDPage(PDRectangle.A4);
|
||||
newDocument.addPage(newPage);
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
PdfDocument outputPdf = new PdfDocument(writer);
|
||||
PageSize pageSize = new PageSize(PageSize.A4.rotate());
|
||||
int totalPages = sourceDocument.getNumberOfPages();
|
||||
float cellWidth = newPage.getMediaBox().getWidth() / cols;
|
||||
float cellHeight = newPage.getMediaBox().getHeight() / rows;
|
||||
|
||||
int totalPages = pdfDoc.getNumberOfPages();
|
||||
float cellWidth = pageSize.getWidth() / cols;
|
||||
float cellHeight = pageSize.getHeight() / rows;
|
||||
PDPageContentStream contentStream = new PDPageContentStream(newDocument, newPage, PDPageContentStream.AppendMode.APPEND, true, true);
|
||||
LayerUtility layerUtility = new LayerUtility(newDocument);
|
||||
|
||||
for (int i = 1; i <= totalPages; i += pagesPerSheet) {
|
||||
PdfPage page = outputPdf.addNewPage(pageSize);
|
||||
PdfCanvas pdfCanvas = new PdfCanvas(page);
|
||||
float borderThickness = 1.5f; // Specify border thickness as required
|
||||
contentStream.setLineWidth(borderThickness);
|
||||
contentStream.setStrokingColor(Color.BLACK);
|
||||
|
||||
for (int i = 0; i < totalPages; i++) {
|
||||
if (i != 0 && i % pagesPerSheet == 0) {
|
||||
// Close the current content stream and create a new page and content stream
|
||||
contentStream.close();
|
||||
newPage = new PDPage(PDRectangle.A4);
|
||||
newDocument.addPage(newPage);
|
||||
contentStream = new PDPageContentStream(newDocument, newPage, PDPageContentStream.AppendMode.APPEND, true, true);
|
||||
}
|
||||
|
||||
for (int row = 0; row < rows; row++) {
|
||||
for (int col = 0; col < cols; col++) {
|
||||
int index = i + row * cols + col;
|
||||
if (index <= totalPages) {
|
||||
// Get the page and calculate scaling factors
|
||||
Rectangle rect = pdfDoc.getPage(index).getPageSize();
|
||||
float scaleWidth = cellWidth / rect.getWidth();
|
||||
float scaleHeight = cellHeight / rect.getHeight();
|
||||
float scale = Math.min(scaleWidth, scaleHeight);
|
||||
PDPage sourcePage = sourceDocument.getPage(i);
|
||||
PDRectangle rect = sourcePage.getMediaBox();
|
||||
float scaleWidth = cellWidth / rect.getWidth();
|
||||
float scaleHeight = cellHeight / rect.getHeight();
|
||||
float scale = Math.min(scaleWidth, scaleHeight);
|
||||
|
||||
PdfFormXObject formXObject = pdfDoc.getPage(index).copyAsFormXObject(outputPdf);
|
||||
float x = col * cellWidth + (cellWidth - rect.getWidth() * scale) / 2;
|
||||
float y = (rows - 1 - row) * cellHeight + (cellHeight - rect.getHeight() * scale) / 2;
|
||||
int adjustedPageIndex = i % pagesPerSheet; // This will reset the index for every new page
|
||||
int rowIndex = adjustedPageIndex / cols;
|
||||
int colIndex = adjustedPageIndex % cols;
|
||||
|
||||
// Save the graphics state, apply the transformations, add the object, and then
|
||||
// restore the graphics state
|
||||
pdfCanvas.saveState();
|
||||
pdfCanvas.concatMatrix(scale, 0, 0, scale, x, y);
|
||||
pdfCanvas.addXObject(formXObject, 0, 0);
|
||||
pdfCanvas.restoreState();
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
float x = colIndex * cellWidth + (cellWidth - rect.getWidth() * scale) / 2;
|
||||
float y = newPage.getMediaBox().getHeight() - ((rowIndex + 1) * cellHeight - (cellHeight - rect.getHeight() * scale) / 2);
|
||||
|
||||
outputPdf.close();
|
||||
byte[] pdfContent = baos.toByteArray();
|
||||
pdfDoc.close();
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(pdfContent, file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_layoutChanged.pdf");
|
||||
contentStream.saveGraphicsState();
|
||||
contentStream.transform(Matrix.getTranslateInstance(x, y));
|
||||
contentStream.transform(Matrix.getScaleInstance(scale, scale));
|
||||
|
||||
PDFormXObject formXObject = layerUtility.importPageAsForm(sourceDocument, i);
|
||||
contentStream.drawForm(formXObject);
|
||||
|
||||
contentStream.restoreGraphicsState();
|
||||
|
||||
if(addBorder) {
|
||||
// Draw border around each page
|
||||
float borderX = colIndex * cellWidth;
|
||||
float borderY = newPage.getMediaBox().getHeight() - (rowIndex + 1) * cellHeight;
|
||||
contentStream.addRect(borderX, borderY, cellWidth, cellHeight);
|
||||
contentStream.stroke();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
contentStream.close(); // Close the final content stream
|
||||
sourceDocument.close();
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
newDocument.save(baos);
|
||||
newDocument.close();
|
||||
|
||||
byte[] result = baos.toByteArray();
|
||||
return WebResponseUtils.bytesToWebResponse(result, file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_layoutChanged.pdf");
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
@@ -0,0 +1,125 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.util.HashMap;
|
||||
import java.util.Map;
|
||||
|
||||
import org.apache.pdfbox.multipdf.Overlay;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.general.OverlayPdfsRequest;
|
||||
import stirling.software.SPDF.utils.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class PdfOverlayController {
|
||||
|
||||
@PostMapping(value = "/overlay-pdfs", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Overlay PDF files in various modes", description = "Overlay PDF files onto a base PDF with different modes: Sequential, Interleaved, or Fixed Repeat. Input:PDF Output:PDF Type:MIMO")
|
||||
public ResponseEntity<byte[]> overlayPdfs(@ModelAttribute OverlayPdfsRequest request) throws IOException {
|
||||
MultipartFile baseFile = request.getFileInput();
|
||||
int overlayPos = request.getOverlayPosition();
|
||||
|
||||
MultipartFile[] overlayFiles = request.getOverlayFiles();
|
||||
File[] overlayPdfFiles = new File[overlayFiles.length];
|
||||
try{
|
||||
for (int i = 0; i < overlayFiles.length; i++) {
|
||||
overlayPdfFiles[i] = GeneralUtils.multipartToFile(overlayFiles[i]);
|
||||
}
|
||||
|
||||
String mode = request.getOverlayMode(); // "SequentialOverlay", "InterleavedOverlay", "FixedRepeatOverlay"
|
||||
int[] counts = request.getCounts(); // Used for FixedRepeatOverlay mode
|
||||
|
||||
try (PDDocument basePdf = PDDocument.load(baseFile.getInputStream());
|
||||
Overlay overlay = new Overlay()) {
|
||||
Map<Integer, String> overlayGuide = prepareOverlayGuide(basePdf.getNumberOfPages(), overlayPdfFiles, mode, counts);
|
||||
|
||||
overlay.setInputPDF(basePdf);
|
||||
if(overlayPos == 0) {
|
||||
overlay.setOverlayPosition(Overlay.Position.FOREGROUND);
|
||||
} else {
|
||||
overlay.setOverlayPosition(Overlay.Position.BACKGROUND);
|
||||
}
|
||||
|
||||
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
|
||||
overlay.overlay(overlayGuide).save(outputStream);
|
||||
byte[] data = outputStream.toByteArray();
|
||||
String outputFilename = baseFile.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_overlayed.pdf"; // Remove file extension and append .pdf
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(data, outputFilename, MediaType.APPLICATION_PDF);
|
||||
}
|
||||
} finally {
|
||||
for (File overlayPdfFile : overlayPdfFiles) {
|
||||
if (overlayPdfFile != null) overlayPdfFile.delete();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private Map<Integer, String> prepareOverlayGuide(int basePageCount, File[] overlayFiles, String mode, int[] counts) throws IOException {
|
||||
Map<Integer, String> overlayGuide = new HashMap<>();
|
||||
switch (mode) {
|
||||
case "SequentialOverlay":
|
||||
sequentialOverlay(overlayGuide, overlayFiles, basePageCount);
|
||||
break;
|
||||
case "InterleavedOverlay":
|
||||
interleavedOverlay(overlayGuide, overlayFiles, basePageCount);
|
||||
break;
|
||||
case "FixedRepeatOverlay":
|
||||
fixedRepeatOverlay(overlayGuide, overlayFiles, counts, basePageCount);
|
||||
break;
|
||||
default:
|
||||
throw new IllegalArgumentException("Invalid overlay mode");
|
||||
}
|
||||
return overlayGuide;
|
||||
}
|
||||
|
||||
private void sequentialOverlay(Map<Integer, String> overlayGuide, File[] overlayFiles, int basePageCount) throws IOException {
|
||||
if (overlayFiles.length != 1 || basePageCount != PDDocument.load(overlayFiles[0]).getNumberOfPages()) {
|
||||
throw new IllegalArgumentException("Overlay file count and base page count must match for sequential overlay.");
|
||||
}
|
||||
|
||||
File overlayFile = overlayFiles[0];
|
||||
try (PDDocument overlayPdf = PDDocument.load(overlayFile)) {
|
||||
for (int i = 1; i <= overlayPdf.getNumberOfPages(); i++) {
|
||||
if (i > basePageCount) break;
|
||||
overlayGuide.put(i, overlayFile.getAbsolutePath());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private void interleavedOverlay(Map<Integer, String> overlayGuide, File[] overlayFiles, int basePageCount) throws IOException {
|
||||
for (int i = 0; i < basePageCount; i++) {
|
||||
File overlayFile = overlayFiles[i % overlayFiles.length];
|
||||
overlayGuide.put(i + 1, overlayFile.getAbsolutePath());
|
||||
}
|
||||
}
|
||||
|
||||
private void fixedRepeatOverlay(Map<Integer, String> overlayGuide, File[] overlayFiles, int[] counts, int basePageCount) throws IOException {
|
||||
if (overlayFiles.length != counts.length) {
|
||||
throw new IllegalArgumentException("Counts array length must match the number of overlay files");
|
||||
}
|
||||
int currentPage = 1;
|
||||
for (int i = 0; i < overlayFiles.length; i++) {
|
||||
File overlayFile = overlayFiles[i];
|
||||
int repeatCount = counts[i];
|
||||
for (int j = 0; j < repeatCount; j++) {
|
||||
if (currentPage > basePageCount) break;
|
||||
overlayGuide.put(currentPage++, overlayFile.getAbsolutePath());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Additional classes like OverlayPdfsRequest, WebResponseUtils, etc. are assumed to be defined elsewhere.
|
||||
@@ -9,20 +9,21 @@ import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.SortTypes;
|
||||
import stirling.software.SPDF.model.api.PDFWithPageNums;
|
||||
import stirling.software.SPDF.model.api.general.RearrangePagesRequest;
|
||||
import stirling.software.SPDF.utils.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class RearrangePagesPDFController {
|
||||
|
||||
@@ -30,11 +31,12 @@ public class RearrangePagesPDFController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/remove-pages")
|
||||
@Operation(summary = "Remove pages from a PDF file", description = "This endpoint removes specified pages from a given PDF file. Users can provide a comma-separated list of page numbers or ranges to delete. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> deletePages(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file from which pages will be removed") MultipartFile pdfFile,
|
||||
@RequestParam("pagesToDelete") @Parameter(description = "Comma-separated list of pages or page ranges to delete, e.g., '1,3,5-8'") String pagesToDelete)
|
||||
public ResponseEntity<byte[]> deletePages(@ModelAttribute PDFWithPageNums request )
|
||||
throws IOException {
|
||||
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
String pagesToDelete = request.getPageNumbers();
|
||||
|
||||
PDDocument document = PDDocument.load(pdfFile.getBytes());
|
||||
|
||||
// Split the page order string into an array of page numbers or range of numbers
|
||||
@@ -51,9 +53,7 @@ public class RearrangePagesPDFController {
|
||||
|
||||
}
|
||||
|
||||
private enum CustomMode {
|
||||
REVERSE_ORDER, DUPLEX_SORT, BOOKLET_SORT, ODD_EVEN_SPLIT, REMOVE_FIRST, REMOVE_LAST, REMOVE_FIRST_AND_LAST,
|
||||
}
|
||||
|
||||
|
||||
private List<Integer> removeFirst(int totalPages) {
|
||||
if (totalPages <= 1)
|
||||
@@ -114,6 +114,18 @@ public class RearrangePagesPDFController {
|
||||
return newPageOrder;
|
||||
}
|
||||
|
||||
private List<Integer> sideStitchBooklet(int totalPages) {
|
||||
List<Integer> newPageOrder = new ArrayList<>();
|
||||
for (int i = 0; i < (totalPages + 3) / 4; i++) {
|
||||
int begin = i * 4;
|
||||
newPageOrder.add(Math.min(begin + 3, totalPages - 1));
|
||||
newPageOrder.add(Math.min(begin, totalPages - 1));
|
||||
newPageOrder.add(Math.min(begin + 1, totalPages - 1));
|
||||
newPageOrder.add(Math.min(begin + 2, totalPages - 1));
|
||||
}
|
||||
return newPageOrder;
|
||||
}
|
||||
|
||||
private List<Integer> oddEvenSplit(int totalPages) {
|
||||
List<Integer> newPageOrder = new ArrayList<>();
|
||||
for (int i = 1; i <= totalPages; i += 2) {
|
||||
@@ -125,9 +137,9 @@ public class RearrangePagesPDFController {
|
||||
return newPageOrder;
|
||||
}
|
||||
|
||||
private List<Integer> processCustomMode(String customMode, int totalPages) {
|
||||
private List<Integer> processSortTypes(String sortTypes, int totalPages) {
|
||||
try {
|
||||
CustomMode mode = CustomMode.valueOf(customMode.toUpperCase());
|
||||
SortTypes mode = SortTypes.valueOf(sortTypes.toUpperCase());
|
||||
switch (mode) {
|
||||
case REVERSE_ORDER:
|
||||
return reverseOrder(totalPages);
|
||||
@@ -135,6 +147,8 @@ public class RearrangePagesPDFController {
|
||||
return duplexSort(totalPages);
|
||||
case BOOKLET_SORT:
|
||||
return bookletSort(totalPages);
|
||||
case SIDE_STITCH_BOOKLET_SORT:
|
||||
return sideStitchBooklet(totalPages);
|
||||
case ODD_EVEN_SPLIT:
|
||||
return oddEvenSplit(totalPages);
|
||||
case REMOVE_FIRST:
|
||||
@@ -154,16 +168,10 @@ public class RearrangePagesPDFController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/rearrange-pages")
|
||||
@Operation(summary = "Rearrange pages in a PDF file", description = "This endpoint rearranges pages in a given PDF file based on the specified page order or custom mode. Users can provide a page order as a comma-separated list of page numbers or page ranges, or a custom mode. Input:PDF Output:PDF")
|
||||
public ResponseEntity<byte[]> rearrangePages(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to rearrange pages") MultipartFile pdfFile,
|
||||
@RequestParam(required = false, value = "pageOrder") @Parameter(description = "The new page order as a comma-separated list of page numbers, page ranges (e.g., '1,3,5-7'), or functions in the format 'an+b' where 'a' is the multiplier of the page number 'n', and 'b' is a constant (e.g., '2n+1', '3n', '6n-5')") String pageOrder,
|
||||
@RequestParam(required = false, value = "customMode") @Parameter(schema = @Schema(implementation = CustomMode.class, description = "The custom mode for page rearrangement. "
|
||||
+ "Valid values are:\n" + "REVERSE_ORDER: Reverses the order of all pages.\n"
|
||||
+ "DUPLEX_SORT: Sorts pages as if all fronts were scanned then all backs in reverse (1, n, 2, n-1, ...). "
|
||||
+ "BOOKLET_SORT: Arranges pages for booklet printing (last, first, second, second last, ...).\n"
|
||||
+ "ODD_EVEN_SPLIT: Splits and arranges pages into odd and even numbered pages.\n"
|
||||
+ "REMOVE_FIRST: Removes the first page.\n" + "REMOVE_LAST: Removes the last page.\n"
|
||||
+ "REMOVE_FIRST_AND_LAST: Removes both the first and the last pages.\n")) String customMode) {
|
||||
public ResponseEntity<byte[]> rearrangePages(@ModelAttribute RearrangePagesRequest request) throws IOException {
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
String pageOrder = request.getPageNumbers();
|
||||
String sortType = request.getCustomMode();
|
||||
try {
|
||||
// Load the input PDF
|
||||
PDDocument document = PDDocument.load(pdfFile.getInputStream());
|
||||
@@ -171,15 +179,14 @@ public class RearrangePagesPDFController {
|
||||
// Split the page order string into an array of page numbers or range of numbers
|
||||
String[] pageOrderArr = pageOrder != null ? pageOrder.split(",") : new String[0];
|
||||
int totalPages = document.getNumberOfPages();
|
||||
System.out.println("pageOrder=" + pageOrder);
|
||||
System.out.println("customMode length =" + customMode.length());
|
||||
List<Integer> newPageOrder;
|
||||
if (customMode != null && customMode.length() > 0) {
|
||||
newPageOrder = processCustomMode(customMode, totalPages);
|
||||
if (sortType != null && sortType.length() > 0) {
|
||||
newPageOrder = processSortTypes(sortType, totalPages);
|
||||
} else {
|
||||
newPageOrder = GeneralUtils.parsePageList(pageOrderArr, totalPages);
|
||||
}
|
||||
|
||||
logger.info("newPageOrder = " +newPageOrder);
|
||||
logger.info("totalPages = " +totalPages);
|
||||
// Create a new list to hold the pages in the new order
|
||||
List<PDPage> newPages = new ArrayList<>();
|
||||
for (int i = 0; i < newPageOrder.size(); i++) {
|
||||
|
||||
@@ -8,18 +8,19 @@ import org.apache.pdfbox.pdmodel.PDPageTree;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.general.RotatePDFRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class RotationController {
|
||||
|
||||
@@ -31,13 +32,9 @@ public class RotationController {
|
||||
description = "This endpoint rotates a given PDF file by a specified angle. The angle must be a multiple of 90. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> rotatePDF(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The PDF file to be rotated", required = true)
|
||||
MultipartFile pdfFile,
|
||||
@RequestParam("angle")
|
||||
@Parameter(description = "The angle by which to rotate the PDF file. This should be a multiple of 90.", example = "90", required = true)
|
||||
Integer angle) throws IOException {
|
||||
|
||||
@ModelAttribute RotatePDFRequest request) throws IOException {
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
Integer angle = request.getAngle();
|
||||
// Load the PDF document
|
||||
PDDocument document = PDDocument.load(pdfFile.getBytes());
|
||||
|
||||
|
||||
@@ -1,48 +1,32 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.Collections;
|
||||
import java.util.Comparator;
|
||||
import java.util.HashMap;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.Set;
|
||||
|
||||
import org.apache.pdfbox.multipdf.LayerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.apache.pdfbox.util.Matrix;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.HttpHeaders;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.kernel.geom.PageSize;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfPage;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfWriter;
|
||||
import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
|
||||
import com.itextpdf.kernel.pdf.canvas.parser.EventType;
|
||||
import com.itextpdf.kernel.pdf.canvas.parser.PdfCanvasProcessor;
|
||||
import com.itextpdf.kernel.pdf.canvas.parser.data.IEventData;
|
||||
import com.itextpdf.kernel.pdf.canvas.parser.data.TextRenderInfo;
|
||||
import com.itextpdf.kernel.pdf.canvas.parser.listener.IEventListener;
|
||||
import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Hidden;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.general.ScalePagesRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class ScalePagesController {
|
||||
|
||||
@@ -50,194 +34,77 @@ public class ScalePagesController {
|
||||
|
||||
@PostMapping(value = "/scale-pages", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Change the size of a PDF page/document", description = "This operation takes an input PDF file and the size to scale the pages to in the output PDF file. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> scalePages(
|
||||
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
|
||||
@Parameter(description = "The scale of pages in the output PDF. Acceptable values are A0-A10, B0-B9, LETTER, TABLOID, LEDGER, LEGAL, EXECUTIVE.", required = true, schema = @Schema(type = "string", allowableValues = {
|
||||
"A0", "A1", "A2", "A3", "A4", "A5", "A6", "A7", "A8", "A9", "A10", "B0", "B1", "B2", "B3", "B4",
|
||||
"B5", "B6", "B7", "B8", "B9", "LETTER", "TABLOID", "LEDGER", "LEGAL",
|
||||
"EXECUTIVE" })) @RequestParam("pageSize") String targetPageSize,
|
||||
@Parameter(description = "The scale of the content on the pages of the output PDF. Acceptable values are floats.", required = true, schema = @Schema(type = "integer")) @RequestParam("scaleFactor") float scaleFactor)
|
||||
throws IOException {
|
||||
public ResponseEntity<byte[]> scalePages(@ModelAttribute ScalePagesRequest request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String targetPDRectangle = request.getPageSize();
|
||||
float scaleFactor = request.getScaleFactor();
|
||||
|
||||
Map<String, PageSize> sizeMap = new HashMap<>();
|
||||
Map<String, PDRectangle> sizeMap = new HashMap<>();
|
||||
// Add A0 - A10
|
||||
sizeMap.put("A0", PageSize.A0);
|
||||
sizeMap.put("A1", PageSize.A1);
|
||||
sizeMap.put("A2", PageSize.A2);
|
||||
sizeMap.put("A3", PageSize.A3);
|
||||
sizeMap.put("A4", PageSize.A4);
|
||||
sizeMap.put("A5", PageSize.A5);
|
||||
sizeMap.put("A6", PageSize.A6);
|
||||
sizeMap.put("A7", PageSize.A7);
|
||||
sizeMap.put("A8", PageSize.A8);
|
||||
sizeMap.put("A9", PageSize.A9);
|
||||
sizeMap.put("A10", PageSize.A10);
|
||||
// Add B0 - B9
|
||||
sizeMap.put("B0", PageSize.B0);
|
||||
sizeMap.put("B1", PageSize.B1);
|
||||
sizeMap.put("B2", PageSize.B2);
|
||||
sizeMap.put("B3", PageSize.B3);
|
||||
sizeMap.put("B4", PageSize.B4);
|
||||
sizeMap.put("B5", PageSize.B5);
|
||||
sizeMap.put("B6", PageSize.B6);
|
||||
sizeMap.put("B7", PageSize.B7);
|
||||
sizeMap.put("B8", PageSize.B8);
|
||||
sizeMap.put("B9", PageSize.B9);
|
||||
sizeMap.put("A0", PDRectangle.A0);
|
||||
sizeMap.put("A1", PDRectangle.A1);
|
||||
sizeMap.put("A2", PDRectangle.A2);
|
||||
sizeMap.put("A3", PDRectangle.A3);
|
||||
sizeMap.put("A4", PDRectangle.A4);
|
||||
sizeMap.put("A5", PDRectangle.A5);
|
||||
sizeMap.put("A6", PDRectangle.A6);
|
||||
|
||||
// Add other sizes
|
||||
sizeMap.put("LETTER", PageSize.LETTER);
|
||||
sizeMap.put("TABLOID", PageSize.TABLOID);
|
||||
sizeMap.put("LEDGER", PageSize.LEDGER);
|
||||
sizeMap.put("LEGAL", PageSize.LEGAL);
|
||||
sizeMap.put("EXECUTIVE", PageSize.EXECUTIVE);
|
||||
sizeMap.put("LETTER", PDRectangle.LETTER);
|
||||
sizeMap.put("LEGAL", PDRectangle.LEGAL);
|
||||
|
||||
if (!sizeMap.containsKey(targetPageSize)) {
|
||||
if (!sizeMap.containsKey(targetPDRectangle)) {
|
||||
throw new IllegalArgumentException(
|
||||
"Invalid pageSize. It must be one of the following: A0, A1, A2, A3, A4, A5, A6, A7, A8, A9, A10");
|
||||
"Invalid PDRectangle. It must be one of the following: A0, A1, A2, A3, A4, A5, A6, A7, A8, A9, A10");
|
||||
}
|
||||
|
||||
PageSize pageSize = sizeMap.get(targetPageSize);
|
||||
PDRectangle targetSize = sizeMap.get(targetPDRectangle);
|
||||
|
||||
byte[] bytes = file.getBytes();
|
||||
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
|
||||
PdfDocument pdfDoc = new PdfDocument(reader);
|
||||
PDDocument sourceDocument = PDDocument.load(file.getBytes());
|
||||
PDDocument outputDocument = new PDDocument();
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
PdfDocument outputPdf = new PdfDocument(writer);
|
||||
int totalPages = sourceDocument.getNumberOfPages();
|
||||
for (int i = 0; i < totalPages; i++) {
|
||||
PDPage sourcePage = sourceDocument.getPage(i);
|
||||
PDRectangle sourceSize = sourcePage.getMediaBox();
|
||||
|
||||
float scaleWidth = targetSize.getWidth() / sourceSize.getWidth();
|
||||
float scaleHeight = targetSize.getHeight() / sourceSize.getHeight();
|
||||
float scale = Math.min(scaleWidth, scaleHeight) * scaleFactor;
|
||||
|
||||
PDPage newPage = new PDPage(targetSize);
|
||||
outputDocument.addPage(newPage);
|
||||
|
||||
PDPageContentStream contentStream = new PDPageContentStream(outputDocument, newPage, PDPageContentStream.AppendMode.APPEND, true);
|
||||
|
||||
float x = (targetSize.getWidth() - sourceSize.getWidth() * scale) / 2;
|
||||
float y = (targetSize.getHeight() - sourceSize.getHeight() * scale) / 2;
|
||||
|
||||
contentStream.saveGraphicsState();
|
||||
contentStream.transform(Matrix.getTranslateInstance(x, y));
|
||||
contentStream.transform(Matrix.getScaleInstance(scale, scale));
|
||||
|
||||
LayerUtility layerUtility = new LayerUtility(outputDocument);
|
||||
PDFormXObject form = layerUtility.importPageAsForm(sourceDocument, i);
|
||||
contentStream.drawForm(form);
|
||||
|
||||
int totalPages = pdfDoc.getNumberOfPages();
|
||||
contentStream.restoreGraphicsState();
|
||||
contentStream.close();
|
||||
}
|
||||
|
||||
for (int i = 1; i <= totalPages; i++) {
|
||||
PdfPage page = outputPdf.addNewPage(pageSize);
|
||||
PdfCanvas pdfCanvas = new PdfCanvas(page);
|
||||
|
||||
// Get the page and calculate scaling factors
|
||||
Rectangle rect = pdfDoc.getPage(i).getPageSize();
|
||||
float scaleWidth = pageSize.getWidth() / rect.getWidth();
|
||||
float scaleHeight = pageSize.getHeight() / rect.getHeight();
|
||||
float scale = Math.min(scaleWidth, scaleHeight) * scaleFactor;
|
||||
System.out.println("Scale: " + scale);
|
||||
|
||||
PdfFormXObject formXObject = pdfDoc.getPage(i).copyAsFormXObject(outputPdf);
|
||||
float x = (pageSize.getWidth() - rect.getWidth() * scale) / 2; // Center Page
|
||||
float y = (pageSize.getHeight() - rect.getHeight() * scale) / 2;
|
||||
|
||||
// Save the graphics state, apply the transformations, add the object, and then
|
||||
// restore the graphics state
|
||||
pdfCanvas.saveState();
|
||||
pdfCanvas.concatMatrix(scale, 0, 0, scale, x, y);
|
||||
pdfCanvas.addXObject(formXObject, 0, 0);
|
||||
pdfCanvas.restoreState();
|
||||
}
|
||||
|
||||
outputPdf.close();
|
||||
byte[] pdfContent = baos.toByteArray();
|
||||
pdfDoc.close();
|
||||
return WebResponseUtils.bytesToWebResponse(pdfContent,
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
outputDocument.save(baos);
|
||||
outputDocument.close();
|
||||
sourceDocument.close();
|
||||
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(),
|
||||
file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_scaled.pdf");
|
||||
}
|
||||
|
||||
//TODO
|
||||
@Hidden
|
||||
@PostMapping(value = "/auto-crop", consumes = "multipart/form-data")
|
||||
public ResponseEntity<byte[]> cropPdf(@RequestParam("fileInput") MultipartFile file) throws IOException {
|
||||
byte[] bytes = file.getBytes();
|
||||
PdfReader reader = new PdfReader(new ByteArrayInputStream(bytes));
|
||||
PdfDocument pdfDoc = new PdfDocument(reader);
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
PdfDocument outputPdf = new PdfDocument(writer);
|
||||
|
||||
int totalPages = pdfDoc.getNumberOfPages();
|
||||
for (int i = 1; i <= totalPages; i++) {
|
||||
PdfPage page = pdfDoc.getPage(i);
|
||||
Rectangle originalMediaBox = page.getMediaBox();
|
||||
|
||||
Rectangle contentBox = determineContentBox(page);
|
||||
|
||||
// Make sure we don't go outside the original media box.
|
||||
Rectangle intersection = originalMediaBox.getIntersection(contentBox);
|
||||
page.setCropBox(intersection);
|
||||
|
||||
// Copy page to the new document
|
||||
outputPdf.addPage(page.copyTo(outputPdf));
|
||||
}
|
||||
|
||||
outputPdf.close();
|
||||
byte[] pdfContent = baos.toByteArray();
|
||||
pdfDoc.close();
|
||||
return ResponseEntity.ok()
|
||||
.header(HttpHeaders.CONTENT_DISPOSITION, "attachment; filename=\""
|
||||
+ file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_cropped.pdf\"")
|
||||
.contentType(MediaType.APPLICATION_PDF).body(pdfContent);
|
||||
}
|
||||
|
||||
private Rectangle determineContentBox(PdfPage page) {
|
||||
// Extract the text from the page and find the bounding box.
|
||||
TextBoundingRectangleFinder finder = new TextBoundingRectangleFinder();
|
||||
PdfCanvasProcessor processor = new PdfCanvasProcessor(finder);
|
||||
processor.processPageContent(page);
|
||||
return finder.getBoundingBox();
|
||||
}
|
||||
|
||||
private static class TextBoundingRectangleFinder implements IEventListener {
|
||||
private List<Rectangle> allTextBoxes = new ArrayList<>();
|
||||
|
||||
public Rectangle getBoundingBox() {
|
||||
// Sort the text boxes based on their vertical position
|
||||
allTextBoxes.sort(Comparator.comparingDouble(Rectangle::getTop));
|
||||
|
||||
// Consider a box an outlier if its top is more than 1.5 times the IQR above the
|
||||
// third quartile.
|
||||
int q1Index = allTextBoxes.size() / 4;
|
||||
int q3Index = 3 * allTextBoxes.size() / 4;
|
||||
double iqr = allTextBoxes.get(q3Index).getTop() - allTextBoxes.get(q1Index).getTop();
|
||||
double threshold = allTextBoxes.get(q3Index).getTop() + 1.5 * iqr;
|
||||
|
||||
// Initialize boundingBox to the first non-outlier box
|
||||
int i = 0;
|
||||
while (i < allTextBoxes.size() && allTextBoxes.get(i).getTop() > threshold) {
|
||||
i++;
|
||||
}
|
||||
if (i == allTextBoxes.size()) {
|
||||
// If all boxes are outliers, just return the first one
|
||||
return allTextBoxes.get(0);
|
||||
}
|
||||
Rectangle boundingBox = allTextBoxes.get(i);
|
||||
|
||||
// Extend the bounding box to include all non-outlier boxes
|
||||
for (; i < allTextBoxes.size(); i++) {
|
||||
Rectangle textBoundingBox = allTextBoxes.get(i);
|
||||
if (textBoundingBox.getTop() > threshold) {
|
||||
// This box is an outlier, skip it
|
||||
continue;
|
||||
}
|
||||
float left = Math.min(boundingBox.getLeft(), textBoundingBox.getLeft());
|
||||
float bottom = Math.min(boundingBox.getBottom(), textBoundingBox.getBottom());
|
||||
float right = Math.max(boundingBox.getRight(), textBoundingBox.getRight());
|
||||
float top = Math.max(boundingBox.getTop(), textBoundingBox.getTop());
|
||||
|
||||
// Add a small padding around the bounding box
|
||||
float padding = 10;
|
||||
boundingBox = new Rectangle(left - padding, bottom - padding, right - left + 2 * padding,
|
||||
top - bottom + 2 * padding);
|
||||
}
|
||||
return boundingBox;
|
||||
}
|
||||
|
||||
@Override
|
||||
public void eventOccurred(IEventData data, EventType type) {
|
||||
if (type == EventType.RENDER_TEXT) {
|
||||
TextRenderInfo renderInfo = (TextRenderInfo) data;
|
||||
allTextBoxes.add(renderInfo.getBaseline().getBoundingRectangle());
|
||||
}
|
||||
}
|
||||
|
||||
@Override
|
||||
public Set<EventType> getSupportedEvents() {
|
||||
return Collections.singleton(EventType.RENDER_TEXT);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -17,19 +17,19 @@ import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.GeneralUtils;
|
||||
import stirling.software.SPDF.model.api.PDFWithPageNums;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class SplitPDFController {
|
||||
|
||||
@@ -38,35 +38,16 @@ public class SplitPDFController {
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/split-pages")
|
||||
@Operation(summary = "Split a PDF file into separate documents",
|
||||
description = "This endpoint splits a given PDF file into separate documents based on the specified page numbers or ranges. Users can specify pages using individual numbers, ranges, or 'all' for every page. Input:PDF Output:PDF Type:SIMO")
|
||||
public ResponseEntity<byte[]> splitPdf(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be split")
|
||||
MultipartFile file,
|
||||
@RequestParam("pages")
|
||||
@Parameter(description = "The pages to be included in separate documents. Specify individual page numbers (e.g., '1,3,5'), ranges (e.g., '1-3,5-7'), or 'all' for every page.")
|
||||
String pages) throws IOException {
|
||||
// parse user input
|
||||
|
||||
public ResponseEntity<byte[]> splitPdf(@ModelAttribute PDFWithPageNums request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String pages = request.getPageNumbers();
|
||||
// open the pdf document
|
||||
InputStream inputStream = file.getInputStream();
|
||||
PDDocument document = PDDocument.load(inputStream);
|
||||
|
||||
List<Integer> pageNumbers = new ArrayList<>();
|
||||
pages = pages.replaceAll("\\s+", ""); // remove whitespaces
|
||||
if (pages.toLowerCase().equals("all")) {
|
||||
for (int i = 0; i < document.getNumberOfPages(); i++) {
|
||||
pageNumbers.add(i);
|
||||
}
|
||||
} else {
|
||||
String[] splitPoints = pages.split(",");
|
||||
for (String splitPoint : splitPoints) {
|
||||
List<Integer> orderedPages = GeneralUtils.parsePageList(new String[] {splitPoint}, document.getNumberOfPages());
|
||||
pageNumbers.addAll(orderedPages);
|
||||
}
|
||||
// Add the last page as a split point
|
||||
pageNumbers.add(document.getNumberOfPages() - 1);
|
||||
}
|
||||
|
||||
List<Integer> pageNumbers = request.getPageNumbersList(document);
|
||||
if(!pageNumbers.contains(document.getNumberOfPages() - 1))
|
||||
pageNumbers.add(document.getNumberOfPages()- 1);
|
||||
logger.info("Splitting PDF into pages: {}", pageNumbers.stream().map(String::valueOf).collect(Collectors.joining(",")));
|
||||
|
||||
// split the document
|
||||
@@ -127,4 +108,4 @@ public class SplitPDFController {
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,135 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
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.zip.ZipEntry;
|
||||
import java.util.zip.ZipOutputStream;
|
||||
|
||||
import org.apache.pdfbox.multipdf.LayerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.apache.pdfbox.util.Matrix;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.SplitPdfBySectionsRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class SplitPdfBySectionsController {
|
||||
|
||||
|
||||
@PostMapping(value = "/split-pdf-by-sections", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Split PDF pages into smaller sections", description = "Split each page of a PDF into smaller sections based on the user's choice (halves, thirds, quarters, etc.), both vertically and horizontally. Input: PDF, Split Parameters. Output: ZIP containing split documents.")
|
||||
public ResponseEntity<byte[]> splitPdf(@ModelAttribute SplitPdfBySectionsRequest request) throws Exception {
|
||||
List<ByteArrayOutputStream> splitDocumentsBoas = new ArrayList<>();
|
||||
|
||||
MultipartFile file = request.getFileInput();
|
||||
PDDocument sourceDocument = PDDocument.load(file.getInputStream());
|
||||
|
||||
// Process the PDF based on split parameters
|
||||
int horiz = request.getHorizontalDivisions() + 1;
|
||||
int verti = request.getVerticalDivisions() + 1;
|
||||
|
||||
List<PDDocument> splitDocuments = splitPdfPages(sourceDocument, verti, horiz);
|
||||
for (PDDocument doc : splitDocuments) {
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
doc.save(baos);
|
||||
doc.close();
|
||||
splitDocumentsBoas.add(baos);
|
||||
}
|
||||
|
||||
sourceDocument.close();
|
||||
|
||||
Path zipFile = Files.createTempFile("split_documents", ".zip");
|
||||
String filename = file.getOriginalFilename().replaceFirst("[.][^.]+$", "");
|
||||
byte[] data;
|
||||
|
||||
|
||||
|
||||
try (ZipOutputStream zipOut = new ZipOutputStream(Files.newOutputStream(zipFile))) {
|
||||
int pageNum = 1;
|
||||
for (int i = 0; i < splitDocumentsBoas.size(); i++) {
|
||||
ByteArrayOutputStream baos = splitDocumentsBoas.get(i);
|
||||
int sectionNum = (i % (horiz * verti)) + 1;
|
||||
String fileName = filename + "_" + pageNum + "_" + sectionNum + ".pdf";
|
||||
byte[] pdf = baos.toByteArray();
|
||||
ZipEntry pdfEntry = new ZipEntry(fileName);
|
||||
zipOut.putNextEntry(pdfEntry);
|
||||
zipOut.write(pdf);
|
||||
zipOut.closeEntry();
|
||||
|
||||
if (sectionNum == horiz * verti) pageNum++;
|
||||
}
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
} finally {
|
||||
data = Files.readAllBytes(zipFile);
|
||||
Files.delete(zipFile);
|
||||
}
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(data, filename + "_split.zip", MediaType.APPLICATION_OCTET_STREAM);
|
||||
}
|
||||
|
||||
public List<PDDocument> splitPdfPages(PDDocument document, int horizontalDivisions, int verticalDivisions) throws IOException {
|
||||
List<PDDocument> splitDocuments = new ArrayList<>();
|
||||
|
||||
for (PDPage originalPage : document.getPages()) {
|
||||
PDRectangle originalMediaBox = originalPage.getMediaBox();
|
||||
float width = originalMediaBox.getWidth();
|
||||
float height = originalMediaBox.getHeight();
|
||||
float subPageWidth = width / horizontalDivisions;
|
||||
float subPageHeight = height / verticalDivisions;
|
||||
|
||||
LayerUtility layerUtility = new LayerUtility(document);
|
||||
|
||||
for (int i = 0; i < horizontalDivisions; i++) {
|
||||
for (int j = 0; j < verticalDivisions; j++) {
|
||||
PDDocument subDoc = new PDDocument();
|
||||
PDPage subPage = new PDPage(new PDRectangle(subPageWidth, subPageHeight));
|
||||
subDoc.addPage(subPage);
|
||||
|
||||
PDFormXObject form = layerUtility.importPageAsForm(document, document.getPages().indexOf(originalPage));
|
||||
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(subDoc, subPage)) {
|
||||
// Set clipping area and position
|
||||
float translateX = -subPageWidth * i;
|
||||
float translateY = height - subPageHeight * (verticalDivisions - j);
|
||||
|
||||
contentStream.saveGraphicsState();
|
||||
contentStream.addRect(0, 0, subPageWidth, subPageHeight);
|
||||
contentStream.clip();
|
||||
contentStream.transform(new Matrix(1, 0, 0, 1, translateX, translateY));
|
||||
|
||||
// Draw the form
|
||||
contentStream.drawForm(form);
|
||||
contentStream.restoreGraphicsState();
|
||||
}
|
||||
|
||||
splitDocuments.add(subDoc);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return splitDocuments;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
@@ -0,0 +1,153 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
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.zip.ZipEntry;
|
||||
import java.util.zip.ZipOutputStream;
|
||||
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.general.SplitPdfBySizeOrCountRequest;
|
||||
import stirling.software.SPDF.utils.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class SplitPdfBySizeController {
|
||||
|
||||
|
||||
@PostMapping(value = "/split-by-size-or-count", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Auto split PDF pages into separate documents based on size or count", description = "split PDF into multiple paged documents based on size/count, ie if 20 pages and split into 5, it does 5 documents each 4 pages\r\n"
|
||||
+ " if 10MB and each page is 1MB and you enter 2MB then 5 docs each 2MB (rounded so that it accepts 1.9MB but not 2.1MB) Input:PDF Output:ZIP Type:SIMO")
|
||||
public ResponseEntity<byte[]> autoSplitPdf(@ModelAttribute SplitPdfBySizeOrCountRequest request) throws Exception {
|
||||
List<ByteArrayOutputStream> splitDocumentsBoas = new ArrayList<ByteArrayOutputStream>();
|
||||
|
||||
|
||||
|
||||
MultipartFile file = request.getFileInput();
|
||||
PDDocument sourceDocument = PDDocument.load(file.getInputStream());
|
||||
|
||||
//0 = size, 1 = page count, 2 = doc count
|
||||
int type = request.getSplitType();
|
||||
String value = request.getSplitValue();
|
||||
|
||||
if (type == 0) { // Split by size
|
||||
long maxBytes = GeneralUtils.convertSizeToBytes(value);
|
||||
long currentSize = 0;
|
||||
PDDocument currentDoc = new PDDocument();
|
||||
|
||||
for (PDPage page : sourceDocument.getPages()) {
|
||||
ByteArrayOutputStream pageOutputStream = new ByteArrayOutputStream();
|
||||
PDDocument tempDoc = new PDDocument();
|
||||
tempDoc.addPage(page);
|
||||
tempDoc.save(pageOutputStream);
|
||||
tempDoc.close();
|
||||
|
||||
long pageSize = pageOutputStream.size();
|
||||
if (currentSize + pageSize > maxBytes) {
|
||||
// Save and reset current document
|
||||
splitDocumentsBoas.add(currentDocToByteArray(currentDoc));
|
||||
currentDoc = new PDDocument();
|
||||
currentSize = 0;
|
||||
}
|
||||
|
||||
currentDoc.addPage(page);
|
||||
currentSize += pageSize;
|
||||
}
|
||||
// Add the last document if it contains any pages
|
||||
if (currentDoc.getPages().getCount() != 0) {
|
||||
splitDocumentsBoas.add(currentDocToByteArray(currentDoc));
|
||||
}
|
||||
} else if (type == 1) { // Split by page count
|
||||
int pageCount = Integer.parseInt(value);
|
||||
int currentPageCount = 0;
|
||||
PDDocument currentDoc = new PDDocument();
|
||||
|
||||
for (PDPage page : sourceDocument.getPages()) {
|
||||
currentDoc.addPage(page);
|
||||
currentPageCount++;
|
||||
|
||||
if (currentPageCount == pageCount) {
|
||||
// Save and reset current document
|
||||
splitDocumentsBoas.add(currentDocToByteArray(currentDoc));
|
||||
currentDoc = new PDDocument();
|
||||
currentPageCount = 0;
|
||||
}
|
||||
}
|
||||
// Add the last document if it contains any pages
|
||||
if (currentDoc.getPages().getCount() != 0) {
|
||||
splitDocumentsBoas.add(currentDocToByteArray(currentDoc));
|
||||
}
|
||||
} else if (type == 2) { // Split by doc count
|
||||
int documentCount = Integer.parseInt(value);
|
||||
int totalPageCount = sourceDocument.getNumberOfPages();
|
||||
int pagesPerDocument = totalPageCount / documentCount;
|
||||
int extraPages = totalPageCount % documentCount;
|
||||
int currentPageIndex = 0;
|
||||
|
||||
for (int i = 0; i < documentCount; i++) {
|
||||
PDDocument currentDoc = new PDDocument();
|
||||
int pagesToAdd = pagesPerDocument + (i < extraPages ? 1 : 0);
|
||||
|
||||
for (int j = 0; j < pagesToAdd; j++) {
|
||||
currentDoc.addPage(sourceDocument.getPage(currentPageIndex++));
|
||||
}
|
||||
|
||||
splitDocumentsBoas.add(currentDocToByteArray(currentDoc));
|
||||
}
|
||||
} else {
|
||||
throw new IllegalArgumentException("Invalid argument for split type");
|
||||
}
|
||||
|
||||
sourceDocument.close();
|
||||
|
||||
|
||||
|
||||
Path zipFile = Files.createTempFile("split_documents", ".zip");
|
||||
String filename = file.getOriginalFilename().replaceFirst("[.][^.]+$", "");
|
||||
byte[] data;
|
||||
|
||||
try (ZipOutputStream zipOut = new ZipOutputStream(Files.newOutputStream(zipFile))) {
|
||||
for (int i = 0; i < splitDocumentsBoas.size(); i++) {
|
||||
String fileName = filename + "_" + (i + 1) + ".pdf";
|
||||
ByteArrayOutputStream baos = splitDocumentsBoas.get(i);
|
||||
byte[] pdf = baos.toByteArray();
|
||||
|
||||
ZipEntry pdfEntry = new ZipEntry(fileName);
|
||||
zipOut.putNextEntry(pdfEntry);
|
||||
zipOut.write(pdf);
|
||||
zipOut.closeEntry();
|
||||
}
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
} finally {
|
||||
data = Files.readAllBytes(zipFile);
|
||||
Files.delete(zipFile);
|
||||
}
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(data, filename + ".zip", MediaType.APPLICATION_OCTET_STREAM);
|
||||
}
|
||||
|
||||
private ByteArrayOutputStream currentDocToByteArray(PDDocument document) throws IOException {
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
document.save(baos);
|
||||
document.close();
|
||||
return baos;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
@@ -1,30 +1,29 @@
|
||||
package stirling.software.SPDF.controller.api;
|
||||
|
||||
import java.awt.geom.AffineTransform;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.pdfbox.multipdf.LayerUtility;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.kernel.geom.PageSize;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfWriter;
|
||||
import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
|
||||
import com.itextpdf.layout.Document;
|
||||
import com.itextpdf.layout.element.Image;
|
||||
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/general")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class ToSinglePageController {
|
||||
|
||||
@@ -36,45 +35,52 @@ public class ToSinglePageController {
|
||||
summary = "Convert a multi-page PDF into a single long page PDF",
|
||||
description = "This endpoint converts a multi-page PDF document into a single paged PDF document. The width of the single page will be same as the input's width, but the height will be the sum of all the pages' heights. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> pdfToSinglePage(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input multi-page PDF file to be converted into a single page", required = true)
|
||||
MultipartFile file) throws IOException {
|
||||
public ResponseEntity<byte[]> pdfToSinglePage(@ModelAttribute PDFFile request) throws IOException {
|
||||
|
||||
PdfReader reader = new PdfReader(file.getInputStream());
|
||||
PdfDocument sourceDocument = new PdfDocument(reader);
|
||||
|
||||
float totalHeight = 0;
|
||||
float width = 0;
|
||||
// Load the source document
|
||||
PDDocument sourceDocument = PDDocument.load(request.getFileInput().getInputStream());
|
||||
|
||||
for (int i = 1; i <= sourceDocument.getNumberOfPages(); i++) {
|
||||
Rectangle pageSize = sourceDocument.getPage(i).getPageSize();
|
||||
totalHeight += pageSize.getHeight();
|
||||
if(width < pageSize.getWidth())
|
||||
width = pageSize.getWidth();
|
||||
}
|
||||
// Calculate total height and max width
|
||||
float totalHeight = 0;
|
||||
float maxWidth = 0;
|
||||
for (PDPage page : sourceDocument.getPages()) {
|
||||
PDRectangle pageSize = page.getMediaBox();
|
||||
totalHeight += pageSize.getHeight();
|
||||
maxWidth = Math.max(maxWidth, pageSize.getWidth());
|
||||
}
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
PdfDocument newDocument = new PdfDocument(writer);
|
||||
PageSize newPageSize = new PageSize(width, totalHeight);
|
||||
newDocument.addNewPage(newPageSize);
|
||||
// Create new document and page with calculated dimensions
|
||||
PDDocument newDocument = new PDDocument();
|
||||
PDPage newPage = new PDPage(new PDRectangle(maxWidth, totalHeight));
|
||||
newDocument.addPage(newPage);
|
||||
|
||||
Document layoutDoc = new Document(newDocument);
|
||||
float yOffset = totalHeight;
|
||||
// Initialize the content stream of the new page
|
||||
PDPageContentStream contentStream = new PDPageContentStream(newDocument, newPage);
|
||||
contentStream.close();
|
||||
|
||||
LayerUtility layerUtility = new LayerUtility(newDocument);
|
||||
float yOffset = totalHeight;
|
||||
|
||||
for (int i = 1; i <= sourceDocument.getNumberOfPages(); i++) {
|
||||
PdfFormXObject pageCopy = sourceDocument.getPage(i).copyAsFormXObject(newDocument);
|
||||
Image copiedPage = new Image(pageCopy);
|
||||
copiedPage.setFixedPosition(0, yOffset - sourceDocument.getPage(i).getPageSize().getHeight());
|
||||
yOffset -= sourceDocument.getPage(i).getPageSize().getHeight();
|
||||
layoutDoc.add(copiedPage);
|
||||
}
|
||||
// For each page, copy its content to the new page at the correct offset
|
||||
for (PDPage page : sourceDocument.getPages()) {
|
||||
PDFormXObject form = layerUtility.importPageAsForm(sourceDocument, sourceDocument.getPages().indexOf(page));
|
||||
AffineTransform af = AffineTransform.getTranslateInstance(0, yOffset - page.getMediaBox().getHeight());
|
||||
layerUtility.wrapInSaveRestore(newPage);
|
||||
String defaultLayerName = "Layer" + sourceDocument.getPages().indexOf(page);
|
||||
layerUtility.appendFormAsLayer(newPage, form, af, defaultLayerName);
|
||||
yOffset -= page.getMediaBox().getHeight();
|
||||
}
|
||||
|
||||
layoutDoc.close();
|
||||
sourceDocument.close();
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
newDocument.save(baos);
|
||||
newDocument.close();
|
||||
sourceDocument.close();
|
||||
|
||||
byte[] result = baos.toByteArray();
|
||||
return WebResponseUtils.bytesToWebResponse(result, file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_singlePage.pdf");
|
||||
byte[] result = baos.toByteArray();
|
||||
return WebResponseUtils.bytesToWebResponse(result, request.getFileInput().getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_singlePage.pdf");
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
}
|
||||
@@ -13,10 +13,12 @@ import org.springframework.security.core.Authentication;
|
||||
import org.springframework.security.web.authentication.logout.SecurityContextLogoutHandler;
|
||||
import org.springframework.stereotype.Controller;
|
||||
import org.springframework.ui.Model;
|
||||
import org.springframework.web.bind.annotation.GetMapping;
|
||||
import org.springframework.web.bind.annotation.PathVariable;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.servlet.mvc.support.RedirectAttributes;
|
||||
import org.springframework.web.servlet.view.RedirectView;
|
||||
|
||||
import jakarta.servlet.http.HttpServletRequest;
|
||||
import jakarta.servlet.http.HttpServletResponse;
|
||||
@@ -24,6 +26,7 @@ import stirling.software.SPDF.config.security.UserService;
|
||||
import stirling.software.SPDF.model.User;
|
||||
|
||||
@Controller
|
||||
@RequestMapping("/api/v1/user")
|
||||
public class UserController {
|
||||
|
||||
@Autowired
|
||||
@@ -40,59 +43,117 @@ public class UserController {
|
||||
return "redirect:/login?registered=true";
|
||||
}
|
||||
|
||||
@PostMapping("/change-username")
|
||||
public ResponseEntity<String> changeUsername(Principal principal, @RequestParam String currentPassword, @RequestParam String newUsername, HttpServletRequest request, HttpServletResponse response) {
|
||||
if (principal == null) {
|
||||
return ResponseEntity.status(HttpStatus.FORBIDDEN).body("User not authenticated.");
|
||||
}
|
||||
|
||||
Optional<User> userOpt = userService.findByUsername(principal.getName());
|
||||
|
||||
if(userOpt == null || userOpt.isEmpty()) {
|
||||
return ResponseEntity.status(HttpStatus.NOT_FOUND).body("User not found.");
|
||||
}
|
||||
User user = userOpt.get();
|
||||
|
||||
if(!userService.isPasswordCorrect(user, currentPassword)) {
|
||||
return ResponseEntity.status(HttpStatus.FORBIDDEN).body("Current password is incorrect.");
|
||||
}
|
||||
|
||||
if(userService.usernameExists(newUsername)) {
|
||||
return ResponseEntity.status(HttpStatus.CONFLICT).body("New username already exists.");
|
||||
}
|
||||
@PostMapping("/change-username-and-password")
|
||||
public RedirectView changeUsernameAndPassword(Principal principal,
|
||||
@RequestParam String currentPassword,
|
||||
@RequestParam String newUsername,
|
||||
@RequestParam String newPassword,
|
||||
HttpServletRequest request,
|
||||
HttpServletResponse response,
|
||||
RedirectAttributes redirectAttributes) {
|
||||
if (principal == null) {
|
||||
return new RedirectView("/change-creds?messageType=notAuthenticated");
|
||||
}
|
||||
|
||||
userService.changeUsername(user, newUsername);
|
||||
Optional<User> userOpt = userService.findByUsername(principal.getName());
|
||||
|
||||
if (userOpt == null || userOpt.isEmpty()) {
|
||||
return new RedirectView("/change-creds?messageType=userNotFound");
|
||||
}
|
||||
|
||||
User user = userOpt.get();
|
||||
|
||||
if (!userService.isPasswordCorrect(user, currentPassword)) {
|
||||
return new RedirectView("/change-creds?messageType=incorrectPassword");
|
||||
}
|
||||
|
||||
if (!user.getUsername().equals(newUsername) && userService.usernameExists(newUsername)) {
|
||||
return new RedirectView("/change-creds?messageType=usernameExists");
|
||||
}
|
||||
|
||||
|
||||
userService.changePassword(user, newPassword);
|
||||
if(newUsername != null && newUsername.length() > 0 && !user.getUsername().equals(newUsername)) {
|
||||
userService.changeUsername(user, newUsername);
|
||||
}
|
||||
userService.changeFirstUse(user, false);
|
||||
|
||||
// Logout using Spring's utility
|
||||
new SecurityContextLogoutHandler().logout(request, response, null);
|
||||
|
||||
|
||||
return ResponseEntity.ok("Username updated successfully.");
|
||||
return new RedirectView("/login?messageType=credsUpdated");
|
||||
}
|
||||
|
||||
|
||||
|
||||
@PostMapping("/change-username")
|
||||
public RedirectView changeUsername(Principal principal,
|
||||
@RequestParam String currentPassword,
|
||||
@RequestParam String newUsername,
|
||||
HttpServletRequest request,
|
||||
HttpServletResponse response,
|
||||
RedirectAttributes redirectAttributes) {
|
||||
if (principal == null) {
|
||||
return new RedirectView("/account?messageType=notAuthenticated");
|
||||
}
|
||||
|
||||
Optional<User> userOpt = userService.findByUsername(principal.getName());
|
||||
|
||||
if (userOpt == null || userOpt.isEmpty()) {
|
||||
return new RedirectView("/account?messageType=userNotFound");
|
||||
}
|
||||
|
||||
User user = userOpt.get();
|
||||
|
||||
if (!userService.isPasswordCorrect(user, currentPassword)) {
|
||||
return new RedirectView("/account?messageType=incorrectPassword");
|
||||
}
|
||||
|
||||
if (!user.getUsername().equals(newUsername) && userService.usernameExists(newUsername)) {
|
||||
return new RedirectView("/account?messageType=usernameExists");
|
||||
}
|
||||
|
||||
if(newUsername != null && newUsername.length() > 0) {
|
||||
userService.changeUsername(user, newUsername);
|
||||
}
|
||||
|
||||
// Logout using Spring's utility
|
||||
new SecurityContextLogoutHandler().logout(request, response, null);
|
||||
|
||||
return new RedirectView("/login?messageType=credsUpdated");
|
||||
}
|
||||
|
||||
@PostMapping("/change-password")
|
||||
public ResponseEntity<String> changePassword(Principal principal, @RequestParam String currentPassword, @RequestParam String newPassword, HttpServletRequest request, HttpServletResponse response) {
|
||||
if (principal == null) {
|
||||
return ResponseEntity.status(HttpStatus.FORBIDDEN).body("User not authenticated.");
|
||||
}
|
||||
public RedirectView changePassword(Principal principal,
|
||||
@RequestParam String currentPassword,
|
||||
@RequestParam String newPassword,
|
||||
HttpServletRequest request,
|
||||
HttpServletResponse response,
|
||||
RedirectAttributes redirectAttributes) {
|
||||
if (principal == null) {
|
||||
return new RedirectView("/account?messageType=notAuthenticated");
|
||||
}
|
||||
|
||||
Optional<User> userOpt = userService.findByUsername(principal.getName());
|
||||
|
||||
if(userOpt == null || userOpt.isEmpty()) {
|
||||
return ResponseEntity.status(HttpStatus.NOT_FOUND).body("User not found.");
|
||||
}
|
||||
User user = userOpt.get();
|
||||
if(!userService.isPasswordCorrect(user, currentPassword)) {
|
||||
return ResponseEntity.status(HttpStatus.FORBIDDEN).body("Current password is incorrect.");
|
||||
}
|
||||
Optional<User> userOpt = userService.findByUsername(principal.getName());
|
||||
|
||||
if (userOpt == null || userOpt.isEmpty()) {
|
||||
return new RedirectView("/account?messageType=userNotFound");
|
||||
}
|
||||
|
||||
User user = userOpt.get();
|
||||
|
||||
if (!userService.isPasswordCorrect(user, currentPassword)) {
|
||||
return new RedirectView("/account?messageType=incorrectPassword");
|
||||
}
|
||||
|
||||
userService.changePassword(user, newPassword);
|
||||
|
||||
// Logout using Spring's utility
|
||||
new SecurityContextLogoutHandler().logout(request, response, null);
|
||||
|
||||
return ResponseEntity.ok("Password updated successfully.");
|
||||
|
||||
return new RedirectView("/login?messageType=credsUpdated");
|
||||
}
|
||||
|
||||
|
||||
@PostMapping("/updateUserSettings")
|
||||
public String updateUserSettings(HttpServletRequest request, Principal principal) {
|
||||
@@ -115,9 +176,14 @@ public class UserController {
|
||||
|
||||
@PreAuthorize("hasRole('ROLE_ADMIN')")
|
||||
@PostMapping("/admin/saveUser")
|
||||
public String saveUser(@RequestParam String username, @RequestParam String password, @RequestParam String role) {
|
||||
userService.saveUser(username, password, role);
|
||||
return "redirect:/addUsers"; // Redirect to account page after adding the user
|
||||
public RedirectView saveUser(@RequestParam String username, @RequestParam String password, @RequestParam String role,
|
||||
@RequestParam(name = "forceChange", required = false, defaultValue = "false") boolean forceChange) {
|
||||
|
||||
if(userService.usernameExists(username)) {
|
||||
return new RedirectView("/addUsers?messageType=usernameExists");
|
||||
}
|
||||
userService.saveUser(username, password, role, forceChange);
|
||||
return new RedirectView("/addUsers"); // Redirect to account page after adding the user
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -14,8 +14,9 @@ import javax.xml.parsers.DocumentBuilder;
|
||||
import javax.xml.parsers.DocumentBuilderFactory;
|
||||
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
import org.w3c.dom.Document;
|
||||
@@ -26,10 +27,12 @@ import org.xml.sax.InputSource;
|
||||
import io.swagger.v3.oas.annotations.Hidden;
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.GeneralFile;
|
||||
import stirling.software.SPDF.utils.FileToPdf;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
public class ConvertEpubToPdf {
|
||||
//TODO
|
||||
@@ -40,9 +43,9 @@ public class ConvertEpubToPdf {
|
||||
description = "This endpoint takes an EPUB file input and converts it to a single PDF."
|
||||
)
|
||||
public ResponseEntity<byte[]> epubToSinglePdf(
|
||||
@RequestPart(required = true, value = "fileInput") MultipartFile fileInput)
|
||||
@ModelAttribute GeneralFile request)
|
||||
throws Exception {
|
||||
|
||||
MultipartFile fileInput = request.getFileInput();
|
||||
if (fileInput == null) {
|
||||
throw new IllegalArgumentException("Please provide an EPUB file for conversion.");
|
||||
}
|
||||
@@ -71,7 +74,7 @@ public class ConvertEpubToPdf {
|
||||
|
||||
// Assuming a pseudo-code function that merges multiple PDFs into one.
|
||||
private byte[] mergeMultiplePdfsIntoOne(List<byte[]> individualPdfs) {
|
||||
// You can use a library such as iText or PDFBox to perform the merging here.
|
||||
// You can use a library such as PDFBox to perform the merging here.
|
||||
// Return the byte[] of the merged PDF.
|
||||
return null;
|
||||
}
|
||||
|
||||
@@ -1,30 +1,33 @@
|
||||
package stirling.software.SPDF.controller.api.converters;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.GeneralFile;
|
||||
import stirling.software.SPDF.utils.FileToPdf;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
public class ConvertHtmlToPDF {
|
||||
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/html-to-pdf")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/html/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."
|
||||
)
|
||||
public ResponseEntity<byte[]> HtmlToPdf(
|
||||
@RequestPart(required = true, value = "fileInput") MultipartFile fileInput) throws IOException, InterruptedException {
|
||||
@ModelAttribute GeneralFile request)
|
||||
throws Exception {
|
||||
MultipartFile fileInput = request.getFileInput();
|
||||
|
||||
if (fileInput == null) {
|
||||
throw new IllegalArgumentException("Please provide an HTML or ZIP file for conversion.");
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
package stirling.software.SPDF.controller.api.converters;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.URLConnection;
|
||||
|
||||
import org.apache.pdfbox.rendering.ImageType;
|
||||
import org.slf4j.Logger;
|
||||
@@ -11,44 +12,36 @@ import org.springframework.http.HttpHeaders;
|
||||
import org.springframework.http.HttpStatus;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.converters.ConvertToImageRequest;
|
||||
import stirling.software.SPDF.model.api.converters.ConvertToPdfRequest;
|
||||
import stirling.software.SPDF.utils.PdfUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
public class ConvertImgPDFController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(ConvertImgPDFController.class);
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-img")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/img")
|
||||
@Operation(summary = "Convert PDF to image(s)",
|
||||
description = "This endpoint converts a PDF file to image(s) with the specified image format, color type, and DPI. Users can choose to get a single image or multiple images. Input:PDF Output:Image Type:SI-Conditional")
|
||||
public ResponseEntity<Resource> convertToImage(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be converted")
|
||||
MultipartFile file,
|
||||
@RequestParam("imageFormat")
|
||||
@Parameter(description = "The output image format", schema = @Schema(allowableValues = {"png", "jpeg", "jpg", "gif"}))
|
||||
String imageFormat,
|
||||
@RequestParam("singleOrMultiple")
|
||||
@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 = {"color", "greyscale", "blackwhite"}))
|
||||
String colorType,
|
||||
@RequestParam("dpi")
|
||||
@Parameter(description = "The DPI (dots per inch) for the output image(s)")
|
||||
String dpi) throws IOException {
|
||||
|
||||
public ResponseEntity<Resource> convertToImage(@ModelAttribute ConvertToImageRequest request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String imageFormat = request.getImageFormat();
|
||||
String singleOrMultiple = request.getSingleOrMultiple();
|
||||
String colorType = request.getColorType();
|
||||
String dpi = request.getDpi();
|
||||
|
||||
byte[] pdfBytes = file.getBytes();
|
||||
ImageType colorTypeResult = ImageType.RGB;
|
||||
if ("greyscale".equals(colorType)) {
|
||||
@@ -83,37 +76,22 @@ public class ConvertImgPDFController {
|
||||
}
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/img-to-pdf")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/img/pdf")
|
||||
@Operation(summary = "Convert images to a PDF file",
|
||||
description = "This endpoint converts one or more images to a PDF file. Users can specify whether to stretch the images to fit the PDF page, and whether to automatically rotate the images. Input:Image Output:PDF Type:SISO?")
|
||||
public ResponseEntity<byte[]> convertToPdf(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input images to be converted to a PDF file")
|
||||
MultipartFile[] file,
|
||||
@RequestParam(defaultValue = "false", name = "stretchToFit")
|
||||
@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 = {"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")
|
||||
boolean autoRotate) throws IOException {
|
||||
public ResponseEntity<byte[]> convertToPdf(@ModelAttribute ConvertToPdfRequest request) throws IOException {
|
||||
MultipartFile[] file = request.getFileInput();
|
||||
String fitOption = request.getFitOption();
|
||||
String colorType = request.getColorType();
|
||||
boolean autoRotate = request.isAutoRotate();
|
||||
|
||||
// Convert the file to PDF and get the resulting bytes
|
||||
byte[] bytes = PdfUtils.imageToPdf(file, stretchToFit, autoRotate, colorType);
|
||||
byte[] bytes = PdfUtils.imageToPdf(file, fitOption, autoRotate, colorType);
|
||||
return WebResponseUtils.bytesToWebResponse(bytes, file[0].getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_converted.pdf");
|
||||
}
|
||||
|
||||
private String getMediaType(String imageFormat) {
|
||||
if (imageFormat.equalsIgnoreCase("PNG"))
|
||||
return "image/png";
|
||||
else if (imageFormat.equalsIgnoreCase("JPEG") || imageFormat.equalsIgnoreCase("JPG"))
|
||||
return "image/jpeg";
|
||||
else if (imageFormat.equalsIgnoreCase("GIF"))
|
||||
return "image/gif";
|
||||
else
|
||||
return "application/octet-stream";
|
||||
String mimeType = URLConnection.guessContentTypeFromName("." + imageFormat);
|
||||
return mimeType.equals("null") ? "application/octet-stream" : mimeType;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
@@ -1,33 +1,35 @@
|
||||
package stirling.software.SPDF.controller.api.converters;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
import org.commonmark.node.Node;
|
||||
import org.commonmark.parser.Parser;
|
||||
import org.commonmark.renderer.html.HtmlRenderer;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.GeneralFile;
|
||||
import stirling.software.SPDF.utils.FileToPdf;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
public class ConvertMarkdownToPdf {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/markdown-to-pdf")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/markdown/pdf")
|
||||
@Operation(
|
||||
summary = "Convert a Markdown file to PDF",
|
||||
description = "This endpoint takes a Markdown file input, converts it to HTML, and then to PDF format."
|
||||
)
|
||||
public ResponseEntity<byte[]> markdownToPdf(
|
||||
@RequestPart(required = true, value = "fileInput") MultipartFile fileInput)
|
||||
throws IOException, InterruptedException {
|
||||
@ModelAttribute GeneralFile request)
|
||||
throws Exception {
|
||||
MultipartFile fileInput = request.getFileInput();
|
||||
|
||||
if (fileInput == null) {
|
||||
throw new IllegalArgumentException("Please provide a Markdown file for conversion.");
|
||||
|
||||
@@ -10,20 +10,22 @@ import java.util.List;
|
||||
|
||||
import org.apache.commons.io.FilenameUtils;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.GeneralFile;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
public class ConvertOfficeController {
|
||||
|
||||
public byte[] convertToPdf(MultipartFile inputFile) throws IOException, InterruptedException {
|
||||
@@ -58,19 +60,14 @@ public class ConvertOfficeController {
|
||||
return fileExtension.matches(extensionPattern);
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/file-to-pdf")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/file/pdf")
|
||||
@Operation(
|
||||
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[]> processFileToPDF(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(
|
||||
description = "The input file to be converted to a PDF file using LibreOffice",
|
||||
required = true
|
||||
)
|
||||
MultipartFile inputFile
|
||||
) throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processFileToPDF(@ModelAttribute GeneralFile request)
|
||||
throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
// unused but can start server instance if startup time is to long
|
||||
// LibreOfficeListener.getInstance().start();
|
||||
|
||||
|
||||
@@ -3,69 +3,67 @@ package stirling.software.SPDF.controller.api.converters;
|
||||
import java.io.IOException;
|
||||
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.model.api.converters.PdfToPresentationRequest;
|
||||
import stirling.software.SPDF.model.api.converters.PdfToTextOrRTFRequest;
|
||||
import stirling.software.SPDF.model.api.converters.PdfToWordRequest;
|
||||
import stirling.software.SPDF.utils.PDFToFile;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
public class ConvertPDFToOffice {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-html")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/html")
|
||||
@Operation(summary = "Convert PDF to HTML", description = "This endpoint converts a PDF file to HTML format. Input:PDF Output:HTML Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToHTML(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to be converted to HTML format", required = true) MultipartFile inputFile)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processPdfToHTML(@ModelAttribute PDFFile request)
|
||||
throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, "html", "writer_pdf_import");
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-presentation")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/presentation")
|
||||
@Operation(summary = "Convert PDF to Presentation format", description = "This endpoint converts a given PDF file to a Presentation format. Input:PDF Output:PPT Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToPresentation(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file") MultipartFile inputFile,
|
||||
@RequestParam("outputFormat") @Parameter(description = "The output Presentation format", schema = @Schema(allowableValues = {
|
||||
"ppt", "pptx", "odp" })) String outputFormat)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processPdfToPresentation(@ModelAttribute PdfToPresentationRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String outputFormat = request.getOutputFormat();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "impress_pdf_import");
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-text")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/text")
|
||||
@Operation(summary = "Convert PDF to Text or RTF format", description = "This endpoint converts a given PDF file to Text or RTF format. Input:PDF Output:TXT Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToRTForTXT(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file") MultipartFile inputFile,
|
||||
@RequestParam("outputFormat") @Parameter(description = "The output Text or RTF format", schema = @Schema(allowableValues = {
|
||||
"rtf", "txt:Text" })) String outputFormat)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processPdfToRTForTXT(@ModelAttribute PdfToTextOrRTFRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String outputFormat = request.getOutputFormat();
|
||||
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "writer_pdf_import");
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-word")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/word")
|
||||
@Operation(summary = "Convert PDF to Word document", description = "This endpoint converts a given PDF file to a Word document format. Input:PDF Output:WORD Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToWord(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file") MultipartFile inputFile,
|
||||
@RequestParam("outputFormat") @Parameter(description = "The output Word document format", schema = @Schema(allowableValues = {
|
||||
"doc", "docx", "odt" })) String outputFormat)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processPdfToWord(@ModelAttribute PdfToWordRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String outputFormat = request.getOutputFormat();
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, outputFormat, "writer_pdf_import");
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-xml")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/xml")
|
||||
@Operation(summary = "Convert PDF to XML", description = "This endpoint converts a PDF file to an XML file. Input:PDF Output:XML Type:SISO")
|
||||
public ResponseEntity<byte[]> processPdfToXML(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to be converted to an XML file", required = true) MultipartFile inputFile)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> processPdfToXML(@ModelAttribute PDFFile request)
|
||||
throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
|
||||
PDFToFile pdfToFile = new PDFToFile();
|
||||
return pdfToFile.processPdfToOfficeFormat(inputFile, "xml", "writer_pdf_import");
|
||||
|
||||
@@ -1,37 +1,37 @@
|
||||
package stirling.software.SPDF.controller.api.converters;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
public class ConvertPDFToPDFA {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf-to-pdfa")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/pdf/pdfa")
|
||||
@Operation(
|
||||
summary = "Convert a PDF to a PDF/A",
|
||||
description = "This endpoint converts a PDF file to a PDF/A file. PDF/A is a format designed for long-term archiving of digital documents. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> pdfToPdfA(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be converted to a PDF/A file", required = true)
|
||||
MultipartFile inputFile) throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> pdfToPdfA(@ModelAttribute PDFFile request)
|
||||
throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
|
||||
// Save the uploaded file to a temporary location
|
||||
Path tempInputFile = Files.createTempFile("input_", ".pdf");
|
||||
|
||||
@@ -7,13 +7,14 @@ import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
|
||||
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.model.api.converters.UrlToPdfRequest;
|
||||
import stirling.software.SPDF.utils.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
@@ -21,17 +22,16 @@ import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Convert", description = "Convert APIs")
|
||||
@RequestMapping("/api/v1/convert")
|
||||
public class ConvertWebsiteToPDF {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/url-to-pdf")
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/url/pdf")
|
||||
@Operation(
|
||||
summary = "Convert a URL to a PDF",
|
||||
description = "This endpoint fetches content from a URL and converts it to a PDF format."
|
||||
)
|
||||
public ResponseEntity<byte[]> urlToPdf(
|
||||
@RequestParam(required = true, value = "urlInput")
|
||||
@Parameter(description = "The input URL to be converted to a PDF file", required = true)
|
||||
String URL) throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> urlToPdf(@ModelAttribute UrlToPdfRequest request) throws IOException, InterruptedException {
|
||||
String URL = request.getUrlInput();
|
||||
|
||||
// Validate the URL format
|
||||
if(!URL.matches("^https?://.*") || !GeneralUtils.isValidURL(URL)) {
|
||||
|
||||
@@ -0,0 +1,123 @@
|
||||
package stirling.software.SPDF.controller.api.converters;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.StringWriter;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ContentDisposition;
|
||||
import org.springframework.http.HttpHeaders;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
|
||||
import com.opencsv.CSVWriter;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.controller.api.CropController;
|
||||
import stirling.software.SPDF.controller.api.strippers.PDFTableStripper;
|
||||
import stirling.software.SPDF.model.api.extract.PDFFilePage;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/convert")
|
||||
@Tag(name = "General", description = "General APIs")
|
||||
public class ExtractController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(CropController.class);
|
||||
|
||||
@PostMapping(value = "/pdf-to-csv", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Extracts a PDF document to csv", description = "This operation takes an input PDF file and returns CSV file of whole page. Input:PDF Output:CSV Type:SISO")
|
||||
public ResponseEntity<String> PdfToCsv(@ModelAttribute PDFFilePage form)
|
||||
throws Exception {
|
||||
|
||||
ArrayList<String> tableData = new ArrayList<>();
|
||||
int columnsCount = 0;
|
||||
|
||||
try (PDDocument document = PDDocument.load(new ByteArrayInputStream(form.getFileInput().getBytes()))) {
|
||||
final double res = 72; // PDF units are at 72 DPI
|
||||
PDFTableStripper stripper = new PDFTableStripper();
|
||||
PDPage pdPage = document.getPage(form.getPageId() - 1);
|
||||
stripper.extractTable(pdPage);
|
||||
columnsCount = stripper.getColumns();
|
||||
for (int c = 0; c < columnsCount; ++c) {
|
||||
for(int r=0; r<stripper.getRows(); ++r) {
|
||||
tableData.add(stripper.getText(r, c));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
ArrayList<String> notEmptyColumns = new ArrayList<>();
|
||||
|
||||
for (String item: tableData) {
|
||||
if(!item.trim().isEmpty()){
|
||||
notEmptyColumns.add(item);
|
||||
}else{
|
||||
columnsCount--;
|
||||
}
|
||||
}
|
||||
|
||||
List<String> fullTable = notEmptyColumns.stream().map((entity)->
|
||||
entity.replace('\n',' ').replace('\r',' ').trim().replaceAll("\\s{2,}", "|")).toList();
|
||||
|
||||
int rowsCount = fullTable.get(0).split("\\|").length;
|
||||
|
||||
ArrayList<String> headersList = getTableHeaders(columnsCount,fullTable);
|
||||
ArrayList<String> recordList = getRecordsList(rowsCount,fullTable);
|
||||
|
||||
if(headersList.size() == 0 && recordList.size() == 0) {
|
||||
throw new Exception("No table detected, no headers or records found");
|
||||
}
|
||||
|
||||
StringWriter writer = new StringWriter();
|
||||
try (CSVWriter csvWriter = new CSVWriter(writer)) {
|
||||
csvWriter.writeNext(headersList.toArray(new String[0]));
|
||||
for (String record : recordList) {
|
||||
csvWriter.writeNext(record.split("\\|"));
|
||||
}
|
||||
}
|
||||
|
||||
HttpHeaders headers = new HttpHeaders();
|
||||
headers.setContentDisposition(ContentDisposition.builder("attachment").filename(form.getFileInput().getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_extracted.csv").build());
|
||||
headers.setContentType(MediaType.parseMediaType("text/csv"));
|
||||
|
||||
return ResponseEntity.ok()
|
||||
.headers(headers)
|
||||
.body(writer.toString());
|
||||
}
|
||||
|
||||
private ArrayList<String> getRecordsList( int rowsCounts ,List<String> items){
|
||||
ArrayList<String> recordsList = new ArrayList<>();
|
||||
|
||||
for (int b=1; b<rowsCounts;b++) {
|
||||
StringBuilder strbldr = new StringBuilder();
|
||||
|
||||
for (int i=0;i<items.size();i++){
|
||||
String[] parts = items.get(i).split("\\|");
|
||||
strbldr.append(parts[b]);
|
||||
if (i!= items.size()-1){
|
||||
strbldr.append("|");
|
||||
}
|
||||
}
|
||||
recordsList.add(strbldr.toString());
|
||||
}
|
||||
|
||||
return recordsList;
|
||||
}
|
||||
private ArrayList<String> getTableHeaders(int columnsCount, List<String> items){
|
||||
ArrayList<String> resultList = new ArrayList<>();
|
||||
for (int i=0;i<columnsCount;i++){
|
||||
String[] parts = items.get(i).split("\\|");
|
||||
resultList.add(parts[0]);
|
||||
}
|
||||
|
||||
return resultList;
|
||||
}
|
||||
}
|
||||
@@ -6,29 +6,35 @@ import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.PDFComparisonAndCount;
|
||||
import stirling.software.SPDF.model.api.PDFWithPageNums;
|
||||
import stirling.software.SPDF.model.api.filter.ContainsTextRequest;
|
||||
import stirling.software.SPDF.model.api.filter.FileSizeRequest;
|
||||
import stirling.software.SPDF.model.api.filter.PageRotationRequest;
|
||||
import stirling.software.SPDF.model.api.filter.PageSizeRequest;
|
||||
import stirling.software.SPDF.utils.PdfUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/filter")
|
||||
@Tag(name = "Filter", description = "Filter APIs")
|
||||
public class FilterController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-contains-text")
|
||||
@Operation(summary = "Checks if a PDF contains set text, returns true if does", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> containsText(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to be converted to a PDF/A file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "The text to check for", required = true) String text,
|
||||
@Parameter(description = "The page number to check for text on accepts 'All', ranges like '1-4'", required = false) String pageNumber)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> containsText(@ModelAttribute ContainsTextRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String text = request.getText();
|
||||
String pageNumber = request.getPageNumbers();
|
||||
|
||||
PDDocument pdfDocument = PDDocument.load(inputFile.getInputStream());
|
||||
if (PdfUtils.hasText(pdfDocument, pageNumber, text))
|
||||
return WebResponseUtils.pdfDocToWebResponse(pdfDocument, inputFile.getOriginalFilename());
|
||||
@@ -38,10 +44,11 @@ public class FilterController {
|
||||
// TODO
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-contains-image")
|
||||
@Operation(summary = "Checks if a PDF contains an image", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> containsImage(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to be converted to a PDF/A file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "The page number to check for image on accepts 'All', ranges like '1-4'", required = false) String pageNumber)
|
||||
public ResponseEntity<byte[]> containsImage(@ModelAttribute PDFWithPageNums request)
|
||||
throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String pageNumber = request.getPageNumbers();
|
||||
|
||||
PDDocument pdfDocument = PDDocument.load(inputFile.getInputStream());
|
||||
if (PdfUtils.hasImages(pdfDocument, pageNumber))
|
||||
return WebResponseUtils.pdfDocToWebResponse(pdfDocument, inputFile.getOriginalFilename());
|
||||
@@ -50,12 +57,10 @@ public class FilterController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-page-count")
|
||||
@Operation(summary = "Checks if a PDF is greater, less or equal to a setPageCount", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> pageCount(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "Page Count", required = true) String pageCount,
|
||||
@Parameter(description = "Comparison type", schema = @Schema(description = "The comparison type, accepts Greater, Equal, Less than", allowableValues = {
|
||||
"Greater", "Equal", "Less" })) String comparator)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> pageCount(@ModelAttribute PDFComparisonAndCount request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String pageCount = request.getPageCount();
|
||||
String comparator = request.getComparator();
|
||||
// Load the PDF
|
||||
PDDocument document = PDDocument.load(inputFile.getInputStream());
|
||||
int actualPageCount = document.getNumberOfPages();
|
||||
@@ -83,12 +88,10 @@ public class FilterController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-page-size")
|
||||
@Operation(summary = "Checks if a PDF is of a certain size", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> pageSize(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "Standard Page Size", required = true) String standardPageSize,
|
||||
@Parameter(description = "Comparison type", schema = @Schema(description = "The comparison type, accepts Greater, Equal, Less than", allowableValues = {
|
||||
"Greater", "Equal", "Less" })) String comparator)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> pageSize(@ModelAttribute PageSizeRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String standardPageSize = request.getStandardPageSize();
|
||||
String comparator = request.getComparator();
|
||||
|
||||
// Load the PDF
|
||||
PDDocument document = PDDocument.load(inputFile.getInputStream());
|
||||
@@ -126,12 +129,10 @@ public class FilterController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-file-size")
|
||||
@Operation(summary = "Checks if a PDF is a set file size", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> fileSize(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "File Size", required = true) String fileSize,
|
||||
@Parameter(description = "Comparison type", schema = @Schema(description = "The comparison type, accepts Greater, Equal, Less than", allowableValues = {
|
||||
"Greater", "Equal", "Less" })) String comparator)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> fileSize(@ModelAttribute FileSizeRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String fileSize = request.getFileSize();
|
||||
String comparator = request.getComparator();
|
||||
|
||||
// Get the file size
|
||||
long actualFileSize = inputFile.getSize();
|
||||
@@ -159,12 +160,10 @@ public class FilterController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/filter-page-rotation")
|
||||
@Operation(summary = "Checks if a PDF is of a certain rotation", description = "Input:PDF Output:Boolean Type:SISO")
|
||||
public ResponseEntity<byte[]> pageRotation(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file", required = true) MultipartFile inputFile,
|
||||
@Parameter(description = "Rotation in degrees", required = true) int rotation,
|
||||
@Parameter(description = "Comparison type", schema = @Schema(description = "The comparison type, accepts Greater, Equal, Less than", allowableValues = {
|
||||
"Greater", "Equal", "Less" })) String comparator)
|
||||
throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> pageRotation(@ModelAttribute PageRotationRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
int rotation = request.getRotation();
|
||||
String comparator = request.getComparator();
|
||||
|
||||
// Load the PDF
|
||||
PDDocument document = PDDocument.load(inputFile.getInputStream());
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
@@ -11,18 +11,19 @@ import org.apache.pdfbox.text.TextPosition;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.misc.ExtractHeaderRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class AutoRenameController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(AutoRenameController.class);
|
||||
@@ -32,10 +33,9 @@ public class AutoRenameController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/auto-rename")
|
||||
@Operation(summary = "Extract header from PDF file", description = "This endpoint accepts a PDF file and attempts to extract its title or header based on heuristics. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> extractHeader(
|
||||
@RequestPart(value = "fileInput") @Parameter(description = "The input PDF file from which the header is to be extracted.", required = true) MultipartFile file,
|
||||
@RequestParam(required = false, defaultValue = "false") @Parameter(description = "Flag indicating whether to use the first text as a fallback if no suitable title is found. Defaults to false.", required = false) Boolean useFirstTextAsFallback)
|
||||
throws Exception {
|
||||
public ResponseEntity<byte[]> extractHeader(@ModelAttribute ExtractHeaderRequest request) throws Exception {
|
||||
MultipartFile file = request.getFileInput();
|
||||
Boolean useFirstTextAsFallback = request.isUseFirstTextAsFallback();
|
||||
|
||||
PDDocument document = PDDocument.load(file.getInputStream());
|
||||
PDFTextStripper reader = new PDFTextStripper() {
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
import java.awt.image.BufferedImage;
|
||||
import java.awt.image.DataBufferByte;
|
||||
import java.awt.image.DataBufferInt;
|
||||
@@ -16,8 +16,9 @@ import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.rendering.PDFRenderer;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
@@ -30,20 +31,22 @@ import com.google.zxing.Result;
|
||||
import com.google.zxing.common.HybridBinarizer;
|
||||
|
||||
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.model.api.misc.AutoSplitPdfRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class AutoSplitPdfController {
|
||||
|
||||
private static final String QR_CONTENT = "https://github.com/Frooodle/Stirling-PDF";
|
||||
|
||||
@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(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 {
|
||||
public ResponseEntity<byte[]> autoSplitPdf(@ModelAttribute AutoSplitPdfRequest request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
boolean duplexMode = request.isDuplexMode();
|
||||
|
||||
InputStream inputStream = file.getInputStream();
|
||||
PDDocument document = PDDocument.load(inputStream);
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.awt.image.BufferedImage;
|
||||
import java.io.IOException;
|
||||
@@ -20,22 +20,23 @@ import org.apache.pdfbox.rendering.PDFRenderer;
|
||||
import org.apache.pdfbox.text.PDFTextStripper;
|
||||
import org.springframework.http.HttpStatus;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.misc.RemoveBlankPagesRequest;
|
||||
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
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class BlankPageController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/remove-blanks")
|
||||
@@ -43,16 +44,10 @@ public class BlankPageController {
|
||||
summary = "Remove blank pages from a PDF file",
|
||||
description = "This endpoint removes blank pages from a given PDF file. Users can specify the threshold and white percentage to tune the detection of blank pages. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> removeBlankPages(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file from which blank pages will be removed", required = true)
|
||||
MultipartFile inputFile,
|
||||
@RequestParam(defaultValue = "10", name = "threshold")
|
||||
@Parameter(description = "The threshold value to determine blank pages", example = "10")
|
||||
int threshold,
|
||||
@RequestParam(defaultValue = "99.9", name = "whitePercent")
|
||||
@Parameter(description = "The percentage of white color on a page to consider it as blank", example = "99.9")
|
||||
float whitePercent) throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> removeBlankPages(@ModelAttribute RemoveBlankPagesRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
int threshold = request.getThreshold();
|
||||
float whitePercent = request.getWhitePercent();
|
||||
|
||||
PDDocument document = null;
|
||||
try {
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.awt.Image;
|
||||
import java.awt.image.BufferedImage;
|
||||
@@ -22,35 +22,34 @@ import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.misc.OptimizePdfRequest;
|
||||
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
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class CompressController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(CompressController.class);
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/compress-pdf")
|
||||
@Operation(summary = "Optimize PDF file", description = "This endpoint accepts a PDF file and optimizes it based on the provided parameters. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> optimizePdf(
|
||||
@RequestPart(value = "fileInput") @Parameter(description = "The input PDF file to be optimized.", required = true) MultipartFile inputFile,
|
||||
@RequestParam(required = false, value = "optimizeLevel") @Parameter(description = "The level of optimization to apply to the PDF file. Higher values indicate greater compression but may reduce quality.", schema = @Schema(allowableValues = {
|
||||
"1", "2", "3", "4", "5" })) Integer optimizeLevel,
|
||||
@RequestParam(value = "expectedOutputSize", required = false) @Parameter(description = "The expected output size, e.g. '100MB', '25KB', etc.", required = false) String expectedOutputSizeString)
|
||||
throws Exception {
|
||||
public ResponseEntity<byte[]> optimizePdf(@ModelAttribute OptimizePdfRequest request) throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
Integer optimizeLevel = request.getOptimizeLevel();
|
||||
String expectedOutputSizeString = request.getExpectedOutputSize();
|
||||
|
||||
|
||||
if(expectedOutputSizeString == null && optimizeLevel == null) {
|
||||
throw new Exception("Both expected output size and optimize level are not specified");
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.awt.image.BufferedImage;
|
||||
import java.io.ByteArrayInputStream;
|
||||
@@ -24,20 +24,21 @@ import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.Parameter;
|
||||
import io.swagger.v3.oas.annotations.media.Content;
|
||||
import io.swagger.v3.oas.annotations.media.Schema;
|
||||
import io.swagger.v3.oas.annotations.parameters.RequestBody;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.misc.ExtractImageScansRequest;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class ExtractImageScansController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(ExtractImageScansController.class);
|
||||
@@ -46,26 +47,16 @@ public class ExtractImageScansController {
|
||||
@Operation(summary = "Extract image scans from an input file",
|
||||
description = "This endpoint extracts image scans from a given file based on certain parameters. Users can specify angle threshold, tolerance, minimum area, minimum contour area, and border size. Input:PDF Output:IMAGE/ZIP Type:SIMO")
|
||||
public ResponseEntity<byte[]> extractImageScans(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input file containing image scans")
|
||||
MultipartFile inputFile,
|
||||
@RequestParam(name = "angle_threshold", defaultValue = "5")
|
||||
@Parameter(description = "The angle threshold for the image scan extraction", example = "5")
|
||||
int angleThreshold,
|
||||
@RequestParam(name = "tolerance", defaultValue = "20")
|
||||
@Parameter(description = "The tolerance for the image scan extraction", example = "20")
|
||||
int tolerance,
|
||||
@RequestParam(name = "min_area", defaultValue = "8000")
|
||||
@Parameter(description = "The minimum area for the image scan extraction", example = "8000")
|
||||
int minArea,
|
||||
@RequestParam(name = "min_contour_area", defaultValue = "500")
|
||||
@Parameter(description = "The minimum contour area for the image scan extraction", example = "500")
|
||||
int minContourArea,
|
||||
@RequestParam(name = "border_size", defaultValue = "1")
|
||||
@Parameter(description = "The border size for the image scan extraction", example = "1")
|
||||
int borderSize) throws IOException, InterruptedException {
|
||||
|
||||
String fileName = inputFile.getOriginalFilename();
|
||||
@RequestBody(
|
||||
description = "Form data containing file and extraction parameters",
|
||||
required = true,
|
||||
content = @Content(
|
||||
mediaType = "multipart/form-data",
|
||||
schema = @Schema(implementation = ExtractImageScansRequest.class) // This should represent your form's structure
|
||||
)
|
||||
)
|
||||
ExtractImageScansRequest form) throws IOException, InterruptedException {
|
||||
String fileName = form.getFileInput().getOriginalFilename();
|
||||
String extension = fileName.substring(fileName.lastIndexOf(".") + 1);
|
||||
|
||||
List<String> images = new ArrayList<>();
|
||||
@@ -73,7 +64,7 @@ public class ExtractImageScansController {
|
||||
// Check if input file is a PDF
|
||||
if (extension.equalsIgnoreCase("pdf")) {
|
||||
// Load PDF document
|
||||
try (PDDocument document = PDDocument.load(new ByteArrayInputStream(inputFile.getBytes()))) {
|
||||
try (PDDocument document = PDDocument.load(new ByteArrayInputStream(form.getFileInput().getBytes()))) {
|
||||
PDFRenderer pdfRenderer = new PDFRenderer(document);
|
||||
int pageCount = document.getNumberOfPages();
|
||||
images = new ArrayList<>();
|
||||
@@ -93,7 +84,7 @@ public class ExtractImageScansController {
|
||||
}
|
||||
} else {
|
||||
Path tempInputFile = Files.createTempFile("input_", "." + extension);
|
||||
Files.copy(inputFile.getInputStream(), tempInputFile, StandardCopyOption.REPLACE_EXISTING);
|
||||
Files.copy(form.getFileInput().getInputStream(), tempInputFile, StandardCopyOption.REPLACE_EXISTING);
|
||||
// Add input file path to images list
|
||||
images.add(tempInputFile.toString());
|
||||
}
|
||||
@@ -109,11 +100,11 @@ public class ExtractImageScansController {
|
||||
"./scripts/split_photos.py",
|
||||
images.get(i),
|
||||
tempDir.toString(),
|
||||
"--angle_threshold", String.valueOf(angleThreshold),
|
||||
"--tolerance", String.valueOf(tolerance),
|
||||
"--min_area", String.valueOf(minArea),
|
||||
"--min_contour_area", String.valueOf(minContourArea),
|
||||
"--border_size", String.valueOf(borderSize)
|
||||
"--angle_threshold", String.valueOf(form.getAngleThreshold()),
|
||||
"--tolerance", String.valueOf(form.getTolerance()),
|
||||
"--min_area", String.valueOf(form.getMinArea()),
|
||||
"--min_contour_area", String.valueOf(form.getMinContourArea()),
|
||||
"--border_size", String.valueOf(form.getBorderSize())
|
||||
));
|
||||
|
||||
|
||||
@@ -1,11 +1,12 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
import java.awt.Graphics2D;
|
||||
import java.awt.Image;
|
||||
import java.awt.image.BufferedImage;
|
||||
import java.awt.image.RenderedImage;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.util.HashSet;
|
||||
import java.util.Set;
|
||||
import java.util.zip.Deflater;
|
||||
import java.util.zip.ZipEntry;
|
||||
import java.util.zip.ZipOutputStream;
|
||||
@@ -20,19 +21,19 @@ import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.PDFWithImageFormatRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class ExtractImagesController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(ExtractImagesController.class);
|
||||
@@ -40,13 +41,9 @@ public class ExtractImagesController {
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/extract-images")
|
||||
@Operation(summary = "Extract images from a PDF file",
|
||||
description = "This endpoint extracts images from a given PDF file and returns them in a zip file. Users can specify the output image format. Input:PDF Output:IMAGE/ZIP Type:SIMO")
|
||||
public ResponseEntity<byte[]> extractImages(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file containing images")
|
||||
MultipartFile file,
|
||||
@RequestParam("format")
|
||||
@Parameter(description = "The output image format e.g., 'png', 'jpeg', or 'gif'", schema = @Schema(allowableValues = {"png", "jpeg", "gif"}))
|
||||
String format) throws IOException {
|
||||
public ResponseEntity<byte[]> extractImages(@ModelAttribute PDFWithImageFormatRequest request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String format = request.getFormat();
|
||||
|
||||
System.out.println(System.currentTimeMillis() + "file=" + file.getName() + ", format=" + format);
|
||||
PDDocument document = PDDocument.load(file.getBytes());
|
||||
@@ -62,7 +59,8 @@ public class ExtractImagesController {
|
||||
|
||||
int imageIndex = 1;
|
||||
String filename = file.getOriginalFilename().replaceFirst("[.][^.]+$", "");
|
||||
int pageNum = 1;
|
||||
int pageNum = 0;
|
||||
Set<Integer> processedImages = new HashSet<>();
|
||||
// Iterate over each page
|
||||
for (PDPage page : document.getPages()) {
|
||||
++pageNum;
|
||||
@@ -70,7 +68,12 @@ public class ExtractImagesController {
|
||||
for (COSName name : page.getResources().getXObjectNames()) {
|
||||
if (page.getResources().isImageXObject(name)) {
|
||||
PDImageXObject image = (PDImageXObject) page.getResources().getXObject(name);
|
||||
|
||||
int imageHash = image.hashCode();
|
||||
if(processedImages.contains(imageHash)) {
|
||||
continue; // Skip already processed images
|
||||
}
|
||||
processedImages.add(imageHash);
|
||||
|
||||
// Convert image to desired format
|
||||
RenderedImage renderedImage = image.getImage();
|
||||
BufferedImage bufferedImage = null;
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.awt.Color;
|
||||
import java.awt.geom.AffineTransform;
|
||||
@@ -9,9 +9,11 @@ import java.awt.image.BufferedImageOp;
|
||||
import java.awt.image.ConvolveOp;
|
||||
import java.awt.image.Kernel;
|
||||
import java.awt.image.RescaleOp;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
//Required for file input/output
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.security.SecureRandom;
|
||||
//Other required classes
|
||||
import java.util.Random;
|
||||
|
||||
@@ -29,21 +31,21 @@ import org.apache.pdfbox.rendering.PDFRenderer;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.io.source.ByteArrayOutputStream;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Hidden;
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class FakeScanControllerWIP {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(FakeScanControllerWIP.class);
|
||||
@@ -55,10 +57,8 @@ public class FakeScanControllerWIP {
|
||||
summary = "Repair a PDF file",
|
||||
description = "This endpoint repairs a given PDF file by running Ghostscript command. The PDF is first saved to a temporary location, repaired, read back, and then returned as a response."
|
||||
)
|
||||
public ResponseEntity<byte[]> repairPdf(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be repaired", required = true)
|
||||
MultipartFile inputFile) throws IOException, InterruptedException {
|
||||
public ResponseEntity<byte[]> repairPdf(@ModelAttribute PDFFile request) throws IOException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
|
||||
PDDocument document = PDDocument.load(inputFile.getBytes());
|
||||
PDFRenderer pdfRenderer = new PDFRenderer(document);
|
||||
@@ -86,7 +86,7 @@ public class FakeScanControllerWIP {
|
||||
op.filter(sourceImage, destinationImage);
|
||||
|
||||
// Apply a rotation effect
|
||||
double rotationRequired = Math.toRadians((new Random().nextInt(3 - 1) + 1)); // Random angle between 1 and 3 degrees
|
||||
double rotationRequired = Math.toRadians((new SecureRandom().nextInt(3 - 1) + 1)); // Random angle between 1 and 3 degrees
|
||||
double locationX = destinationImage.getWidth() / 2;
|
||||
double locationY = destinationImage.getHeight() / 2;
|
||||
AffineTransform tx = AffineTransform.getRotateInstance(rotationRequired, locationX, locationY);
|
||||
@@ -104,7 +104,7 @@ public class FakeScanControllerWIP {
|
||||
destinationImage = blurOp.filter(destinationImage, null);
|
||||
|
||||
// Add noise to the image based on the "dirtiness"
|
||||
Random random = new Random();
|
||||
Random random = new SecureRandom();
|
||||
for (int y = 0; y < destinationImage.getHeight(); y++) {
|
||||
for (int x = 0; x < destinationImage.getWidth(); x++) {
|
||||
if (random.nextInt(100) < dirtiness) {
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.text.ParseException;
|
||||
@@ -11,19 +11,20 @@ import org.apache.pdfbox.cos.COSName;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.misc.MetadataRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class MetadataController {
|
||||
|
||||
|
||||
@@ -41,44 +42,28 @@ public class MetadataController {
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/update-metadata")
|
||||
@Operation(summary = "Update metadata of a PDF file",
|
||||
description = "This endpoint allows you to update the metadata of a given PDF file. You can add, modify, or delete standard and custom metadata fields. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> metadata(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to update metadata")
|
||||
MultipartFile pdfFile,
|
||||
@RequestParam(value = "deleteAll", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Delete all metadata if set to true")
|
||||
Boolean deleteAll,
|
||||
@RequestParam(value = "author", required = false)
|
||||
@Parameter(description = "The author of the document")
|
||||
String author,
|
||||
@RequestParam(value = "creationDate", required = false)
|
||||
@Parameter(description = "The creation date of the document (format: yyyy/MM/dd HH:mm:ss)")
|
||||
String creationDate,
|
||||
@RequestParam(value = "creator", required = false)
|
||||
@Parameter(description = "The creator of the document")
|
||||
String creator,
|
||||
@RequestParam(value = "keywords", required = false)
|
||||
@Parameter(description = "The keywords for the document")
|
||||
String keywords,
|
||||
@RequestParam(value = "modificationDate", required = false)
|
||||
@Parameter(description = "The modification date of the document (format: yyyy/MM/dd HH:mm:ss)")
|
||||
String modificationDate,
|
||||
@RequestParam(value = "producer", required = false)
|
||||
@Parameter(description = "The producer of the document")
|
||||
String producer,
|
||||
@RequestParam(value = "subject", required = false)
|
||||
@Parameter(description = "The subject of the document")
|
||||
String subject,
|
||||
@RequestParam(value = "title", required = false)
|
||||
@Parameter(description = "The title of the document")
|
||||
String title,
|
||||
@RequestParam(value = "trapped", required = false)
|
||||
@Parameter(description = "The trapped status of the document")
|
||||
String trapped,
|
||||
@Parameter(description = "Map list of key and value of custom parameters, note these must start with customKey and customValue if they are non standard")
|
||||
@RequestParam Map<String, String> allRequestParams)
|
||||
throws IOException {
|
||||
public ResponseEntity<byte[]> metadata(@ModelAttribute MetadataRequest request) throws IOException {
|
||||
|
||||
// Extract PDF file from the request object
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
|
||||
// Extract metadata information
|
||||
Boolean deleteAll = request.isDeleteAll();
|
||||
String author = request.getAuthor();
|
||||
String creationDate = request.getCreationDate();
|
||||
String creator = request.getCreator();
|
||||
String keywords = request.getKeywords();
|
||||
String modificationDate = request.getModificationDate();
|
||||
String producer = request.getProducer();
|
||||
String subject = request.getSubject();
|
||||
String title = request.getTitle();
|
||||
String trapped = request.getTrapped();
|
||||
|
||||
// Extract additional custom parameters
|
||||
Map<String, String> allRequestParams = request.getAllRequestParams();
|
||||
if(allRequestParams == null) {
|
||||
allRequestParams = new java.util.HashMap<String, String>();
|
||||
}
|
||||
// Load the PDF file into a PDDocument
|
||||
PDDocument document = PDDocument.load(pdfFile.getBytes());
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.File;
|
||||
import java.io.FileOutputStream;
|
||||
@@ -18,28 +18,28 @@ import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.misc.ProcessPdfWithOcrRequest;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class OCRController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(OCRController.class);
|
||||
|
||||
public List<String> getAvailableTesseractLanguages() {
|
||||
String tessdataDir = "/usr/share/tesseract-ocr/4.00/tessdata";
|
||||
String tessdataDir = "/usr/share/tesseract-ocr/5/tessdata";
|
||||
File[] files = new File(tessdataDir).listFiles();
|
||||
if (files == null) {
|
||||
return Collections.emptyList();
|
||||
@@ -51,35 +51,16 @@ public class OCRController {
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/ocr-pdf")
|
||||
@Operation(summary = "Process a PDF file with OCR",
|
||||
description = "This endpoint processes a PDF file using OCR (Optical Character Recognition). Users can specify languages, sidecar, deskew, clean, cleanFinal, ocrType, ocrRenderType, and removeImagesAfter options. Input:PDF Output:PDF Type:SI-Conditional")
|
||||
public ResponseEntity<byte[]> processPdfWithOCR(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be processed with OCR")
|
||||
MultipartFile inputFile,
|
||||
@RequestParam("languages")
|
||||
@Parameter(description = "List of languages to use in OCR processing")
|
||||
List<String> selectedLanguages,
|
||||
@RequestParam(name = "sidecar", required = false)
|
||||
@Parameter(description = "Include OCR text in a sidecar text file if set to true")
|
||||
Boolean sidecar,
|
||||
@RequestParam(name = "deskew", required = false)
|
||||
@Parameter(description = "Deskew the input file if set to true")
|
||||
Boolean deskew,
|
||||
@RequestParam(name = "clean", required = false)
|
||||
@Parameter(description = "Clean the input file if set to true")
|
||||
Boolean clean,
|
||||
@RequestParam(name = "clean-final", required = false)
|
||||
@Parameter(description = "Clean the final output if set to true")
|
||||
Boolean cleanFinal,
|
||||
@RequestParam(name = "ocrType", required = false)
|
||||
@Parameter(description = "Specify the OCR type, e.g., 'skip-text', 'force-ocr', or 'Normal'", schema = @Schema(allowableValues = {"skip-text", "force-ocr", "Normal"}))
|
||||
String ocrType,
|
||||
@RequestParam(name = "ocrRenderType", required = false, defaultValue = "hocr")
|
||||
@Parameter(description = "Specify the OCR render type, either 'hocr' or 'sandwich'", schema = @Schema(allowableValues = {"hocr", "sandwich"}))
|
||||
String ocrRenderType,
|
||||
@RequestParam(name = "removeImagesAfter", required = false)
|
||||
@Parameter(description = "Remove images from the output PDF if set to true")
|
||||
Boolean removeImagesAfter) throws IOException, InterruptedException {
|
||||
|
||||
public ResponseEntity<byte[]> processPdfWithOCR(@ModelAttribute ProcessPdfWithOcrRequest request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
List<String> selectedLanguages = request.getLanguages();
|
||||
Boolean sidecar = request.isSidecar();
|
||||
Boolean deskew = request.isDeskew();
|
||||
Boolean clean = request.isClean();
|
||||
Boolean cleanFinal = request.isCleanFinal();
|
||||
String ocrType = request.getOcrType();
|
||||
String ocrRenderType = request.getOcrRenderType();
|
||||
Boolean removeImagesAfter = request.isRemoveImagesAfter();
|
||||
// --output-type pdfa
|
||||
if (selectedLanguages == null || selectedLanguages.isEmpty()) {
|
||||
throw new IOException("Please select at least one language.");
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
@@ -6,20 +6,21 @@ import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.HttpStatus;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.misc.OverlayImageRequest;
|
||||
import stirling.software.SPDF.utils.PdfUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class OverlayImageController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(OverlayImageController.class);
|
||||
@@ -29,22 +30,12 @@ public class OverlayImageController {
|
||||
summary = "Overlay image onto a PDF file",
|
||||
description = "This endpoint overlays an image onto a PDF file at the specified coordinates. The image can be overlaid on every page of the PDF if specified. Input:PDF/IMAGE Output:PDF Type:MF-SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> overlayImage(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to overlay the image onto.", required = true)
|
||||
MultipartFile pdfFile,
|
||||
@RequestParam("fileInput2")
|
||||
@Parameter(description = "The image file to be overlaid onto the PDF.", required = true)
|
||||
MultipartFile imageFile,
|
||||
@RequestParam("x")
|
||||
@Parameter(description = "The x-coordinate at which to place the top-left corner of the image.", example = "0")
|
||||
float x,
|
||||
@RequestParam("y")
|
||||
@Parameter(description = "The y-coordinate at which to place the top-left corner of the image.", example = "0")
|
||||
float y,
|
||||
@RequestParam("everyPage")
|
||||
@Parameter(description = "Whether to overlay the image onto every page of the PDF.", example = "false")
|
||||
boolean everyPage) {
|
||||
public ResponseEntity<byte[]> overlayImage(@ModelAttribute OverlayImageRequest request) {
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
MultipartFile imageFile = request.getImageFile();
|
||||
float x = request.getX();
|
||||
float y = request.getY();
|
||||
boolean everyPage = request.isEveryPage();
|
||||
try {
|
||||
byte[] pdfBytes = pdfFile.getBytes();
|
||||
byte[] imageBytes = imageFile.getBytes();
|
||||
@@ -0,0 +1,135 @@
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.font.PDType1Font;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.misc.AddPageNumbersRequest;
|
||||
import stirling.software.SPDF.utils.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class PageNumbersController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(PageNumbersController.class);
|
||||
|
||||
@PostMapping(value = "/add-page-numbers", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Add page numbers to a PDF document", description = "This operation takes an input PDF file and adds page numbers to it. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> addPageNumbers(@ModelAttribute AddPageNumbersRequest request) throws IOException {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String customMargin = request.getCustomMargin();
|
||||
int position = request.getPosition();
|
||||
int startingNumber = request.getStartingNumber();
|
||||
String pagesToNumber = request.getPagesToNumber();
|
||||
String customText = request.getCustomText();
|
||||
int pageNumber = startingNumber;
|
||||
byte[] fileBytes = file.getBytes();
|
||||
PDDocument document = PDDocument.load(fileBytes);
|
||||
|
||||
float marginFactor;
|
||||
switch (customMargin.toLowerCase()) {
|
||||
case "small":
|
||||
marginFactor = 0.02f;
|
||||
break;
|
||||
case "medium":
|
||||
marginFactor = 0.035f;
|
||||
break;
|
||||
case "large":
|
||||
marginFactor = 0.05f;
|
||||
break;
|
||||
case "x-large":
|
||||
marginFactor = 0.075f;
|
||||
break;
|
||||
|
||||
|
||||
default:
|
||||
marginFactor = 0.035f;
|
||||
break;
|
||||
}
|
||||
|
||||
float fontSize = 12.0f;
|
||||
PDType1Font font = PDType1Font.HELVETICA;
|
||||
if(pagesToNumber == null || pagesToNumber.length() == 0) {
|
||||
pagesToNumber = "all";
|
||||
}
|
||||
if(customText == null || customText.length() == 0) {
|
||||
customText = "{n}";
|
||||
}
|
||||
List<Integer> pagesToNumberList = GeneralUtils.parsePageList(pagesToNumber.split(","), document.getNumberOfPages());
|
||||
|
||||
for (int i : pagesToNumberList) {
|
||||
PDPage page = document.getPage(i);
|
||||
PDRectangle pageSize = page.getMediaBox();
|
||||
|
||||
String text = customText != null ? customText.replace("{n}", String.valueOf(pageNumber)).replace("{total}", String.valueOf(document.getNumberOfPages())).replace("{filename}", file.getOriginalFilename().replaceFirst("[.][^.]+$", "")) : String.valueOf(pageNumber);
|
||||
|
||||
float x, y;
|
||||
|
||||
int xGroup = (position - 1) % 3;
|
||||
int yGroup = 2 - (position - 1) / 3;
|
||||
|
||||
switch (xGroup) {
|
||||
case 0: // left
|
||||
x = pageSize.getLowerLeftX() + marginFactor * pageSize.getWidth();
|
||||
break;
|
||||
case 1: // center
|
||||
x = pageSize.getLowerLeftX() + (pageSize.getWidth() / 2);
|
||||
break;
|
||||
default: // right
|
||||
x = pageSize.getUpperRightX() - marginFactor * pageSize.getWidth();
|
||||
break;
|
||||
}
|
||||
|
||||
switch (yGroup) {
|
||||
case 0: // bottom
|
||||
y = pageSize.getLowerLeftY() + marginFactor * pageSize.getHeight();
|
||||
break;
|
||||
case 1: // middle
|
||||
y = pageSize.getLowerLeftY() + (pageSize.getHeight() / 2);
|
||||
break;
|
||||
default: // top
|
||||
y = pageSize.getUpperRightY() - marginFactor * pageSize.getHeight();
|
||||
break;
|
||||
}
|
||||
|
||||
PDPageContentStream contentStream = new PDPageContentStream(document, page, PDPageContentStream.AppendMode.APPEND, true);
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(font, fontSize);
|
||||
contentStream.newLineAtOffset(x, y);
|
||||
contentStream.showText(text);
|
||||
contentStream.endText();
|
||||
contentStream.close();
|
||||
|
||||
pageNumber++;
|
||||
}
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
document.save(baos);
|
||||
document.close();
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(), file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_numbersAdded.pdf", MediaType.APPLICATION_PDF);
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
@@ -9,20 +9,22 @@ import java.util.List;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor;
|
||||
import stirling.software.SPDF.utils.ProcessExecutor.ProcessExecutorResult;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class RepairController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(RepairController.class);
|
||||
@@ -32,11 +34,8 @@ public class RepairController {
|
||||
summary = "Repair a PDF file",
|
||||
description = "This endpoint repairs a given PDF file by running Ghostscript command. The PDF is first saved to a temporary location, repaired, read back, and then returned as a response. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> repairPdf(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be repaired", required = true)
|
||||
MultipartFile inputFile) throws IOException, InterruptedException {
|
||||
|
||||
public ResponseEntity<byte[]> repairPdf(@ModelAttribute PDFFile request) throws IOException, InterruptedException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
// Save the uploaded file to a temporary location
|
||||
Path tempInputFile = Files.createTempFile("input_", ".pdf");
|
||||
inputFile.transferTo(tempInputFile.toFile());
|
||||
@@ -0,0 +1,61 @@
|
||||
package stirling.software.SPDF.controller.api.misc;
|
||||
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.Map;
|
||||
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.common.PDNameTreeNode;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionJavaScript;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/misc")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class ShowJavascript {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(ShowJavascript.class);
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/show-javascript")
|
||||
public ResponseEntity<byte[]> extractHeader(@ModelAttribute PDFFile request) throws Exception {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
String script = "";
|
||||
|
||||
try (PDDocument document = PDDocument.load(inputFile.getInputStream())) {
|
||||
|
||||
if(document.getDocumentCatalog() != null && document.getDocumentCatalog().getNames() != null) {
|
||||
PDNameTreeNode<PDActionJavaScript> jsTree = document.getDocumentCatalog().getNames().getJavaScript();
|
||||
|
||||
if (jsTree != null) {
|
||||
Map<String, PDActionJavaScript> jsEntries = jsTree.getNames();
|
||||
|
||||
for (Map.Entry<String, PDActionJavaScript> entry : jsEntries.entrySet()) {
|
||||
String name = entry.getKey();
|
||||
PDActionJavaScript jsAction = entry.getValue();
|
||||
String jsCodeStr = jsAction.getAction();
|
||||
|
||||
script += "// File: " + inputFile.getOriginalFilename() + ", Script: " + name + "\n" + jsCodeStr + "\n";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (script.isEmpty()) {
|
||||
script = "PDF '" + inputFile.getOriginalFilename() + "' does not contain Javascript";
|
||||
}
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(script.getBytes(StandardCharsets.UTF_8), inputFile.getOriginalFilename() + ".js");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
@@ -1,148 +0,0 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.net.URLEncoder;
|
||||
import java.util.List;
|
||||
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.MediaType;
|
||||
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.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.io.font.constants.StandardFonts;
|
||||
import com.itextpdf.kernel.font.PdfFont;
|
||||
import com.itextpdf.kernel.font.PdfFontFactory;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfPage;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfWriter;
|
||||
import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
|
||||
import com.itextpdf.layout.Canvas;
|
||||
import com.itextpdf.layout.element.Paragraph;
|
||||
import com.itextpdf.layout.properties.TextAlignment;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.GeneralUtils;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
public class PageNumbersController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(PageNumbersController.class);
|
||||
|
||||
@PostMapping(value = "/add-page-numbers", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Add page numbers to a PDF document", description = "This operation takes an input PDF file and adds page numbers to it. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> addPageNumbers(
|
||||
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
|
||||
@Parameter(description = "Custom margin: small/medium/large", required = true, schema = @Schema(type = "string", allowableValues = {"small", "medium", "large"})) @RequestParam("customMargin") String customMargin,
|
||||
@Parameter(description = "Position: 1 of 9 positions", required = true, schema = @Schema(type = "integer", minimum = "1", maximum = "9")) @RequestParam("position") int position,
|
||||
@Parameter(description = "Starting number", required = true, schema = @Schema(type = "integer", minimum = "1")) @RequestParam("startingNumber") int startingNumber,
|
||||
@Parameter(description = "Which pages to number, default all", required = false, schema = @Schema(type = "string")) @RequestParam(value = "pagesToNumber", required = false) String pagesToNumber,
|
||||
@Parameter(description = "Custom text: defaults to just number but can have things like \"Page {n} of {p}\"", required = false, schema = @Schema(type = "string")) @RequestParam(value = "customText", required = false) String customText)
|
||||
throws IOException {
|
||||
|
||||
byte[] fileBytes = file.getBytes();
|
||||
ByteArrayInputStream bais = new ByteArrayInputStream(fileBytes);
|
||||
|
||||
int pageNumber = startingNumber;
|
||||
float marginFactor;
|
||||
switch (customMargin.toLowerCase()) {
|
||||
case "small":
|
||||
marginFactor = 0.02f;
|
||||
break;
|
||||
case "medium":
|
||||
marginFactor = 0.035f;
|
||||
break;
|
||||
case "large":
|
||||
marginFactor = 0.05f;
|
||||
break;
|
||||
case "x-large":
|
||||
marginFactor = 0.1f;
|
||||
break;
|
||||
default:
|
||||
marginFactor = 0.035f;
|
||||
break;
|
||||
}
|
||||
|
||||
float fontSize = 12.0f;
|
||||
|
||||
PdfReader reader = new PdfReader(bais);
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
PdfWriter writer = new PdfWriter(baos);
|
||||
|
||||
PdfDocument pdfDoc = new PdfDocument(reader, writer);
|
||||
|
||||
List<Integer> pagesToNumberList = GeneralUtils.parsePageList(pagesToNumber.split(","), pdfDoc.getNumberOfPages());
|
||||
|
||||
for (int i : pagesToNumberList) {
|
||||
PdfPage page = pdfDoc.getPage(i+1);
|
||||
Rectangle pageSize = page.getPageSize();
|
||||
PdfCanvas pdfCanvas = new PdfCanvas(page.newContentStreamAfter(), page.getResources(), pdfDoc);
|
||||
|
||||
String text = customText != null ? customText.replace("{n}", String.valueOf(pageNumber)).replace("{total}", String.valueOf(pdfDoc.getNumberOfPages())).replace("{filename}", file.getOriginalFilename().replaceFirst("[.][^.]+$", "")) : String.valueOf(pageNumber);
|
||||
|
||||
PdfFont font = PdfFontFactory.createFont(StandardFonts.HELVETICA);
|
||||
float textWidth = font.getWidth(text, fontSize);
|
||||
float textHeight = font.getAscent(text, fontSize) - font.getDescent(text, fontSize);
|
||||
|
||||
float x, y;
|
||||
TextAlignment alignment;
|
||||
|
||||
int xGroup = (position - 1) % 3;
|
||||
int yGroup = 2 - (position - 1) / 3;
|
||||
|
||||
switch (xGroup) {
|
||||
case 0: // left
|
||||
x = pageSize.getLeft() + marginFactor * pageSize.getWidth();
|
||||
alignment = TextAlignment.LEFT;
|
||||
break;
|
||||
case 1: // center
|
||||
x = pageSize.getLeft() + (pageSize.getWidth()) / 2;
|
||||
alignment = TextAlignment.CENTER;
|
||||
break;
|
||||
default: // right
|
||||
x = pageSize.getRight() - marginFactor * pageSize.getWidth();
|
||||
alignment = TextAlignment.RIGHT;
|
||||
break;
|
||||
}
|
||||
|
||||
switch (yGroup) {
|
||||
case 0: // bottom
|
||||
y = pageSize.getBottom() + marginFactor * pageSize.getHeight();
|
||||
break;
|
||||
case 1: // middle
|
||||
y = pageSize.getBottom() + (pageSize.getHeight() ) / 2;
|
||||
break;
|
||||
default: // top
|
||||
y = pageSize.getTop() - marginFactor * pageSize.getHeight();
|
||||
break;
|
||||
}
|
||||
|
||||
new Canvas(pdfCanvas, page.getPageSize())
|
||||
.showTextAligned(new Paragraph(text).setFont(font).setFontSize(fontSize), x, y, alignment);
|
||||
|
||||
pageNumber++;
|
||||
}
|
||||
|
||||
|
||||
pdfDoc.close();
|
||||
byte[] resultBytes = baos.toByteArray();
|
||||
|
||||
return WebResponseUtils.bytesToWebResponse(resultBytes, URLEncoder.encode(file.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_numbersAdded.pdf", "UTF-8"), MediaType.APPLICATION_PDF);
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
@@ -1,85 +0,0 @@
|
||||
package stirling.software.SPDF.controller.api.other;
|
||||
|
||||
import java.nio.charset.StandardCharsets;
|
||||
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.kernel.pdf.PdfArray;
|
||||
import com.itextpdf.kernel.pdf.PdfDictionary;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfName;
|
||||
import com.itextpdf.kernel.pdf.PdfObject;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfStream;
|
||||
|
||||
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.WebResponseUtils;
|
||||
@RestController
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
public class ShowJavascript {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(ShowJavascript.class);
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/show-javascript")
|
||||
@Operation(summary = "Extract header from PDF file", description = "This endpoint accepts a PDF file and attempts to extract its title or header based on heuristics. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> extractHeader(
|
||||
@RequestPart(value = "fileInput") @Parameter(description = "The input PDF file from which the javascript is to be extracted.", required = true) MultipartFile inputFile)
|
||||
throws Exception {
|
||||
|
||||
try (
|
||||
PdfDocument itextDoc = new PdfDocument(new PdfReader(inputFile.getInputStream()))
|
||||
) {
|
||||
|
||||
String name = "";
|
||||
String script = "";
|
||||
String entryName = "File: "+inputFile.getOriginalFilename() + ", Script: ";
|
||||
//Javascript
|
||||
PdfDictionary namesDict = itextDoc.getCatalog().getPdfObject().getAsDictionary(PdfName.Names);
|
||||
if (namesDict != null) {
|
||||
PdfDictionary javascriptDict = namesDict.getAsDictionary(PdfName.JavaScript);
|
||||
if (javascriptDict != null) {
|
||||
|
||||
PdfArray namesArray = javascriptDict.getAsArray(PdfName.Names);
|
||||
for (int i = 0; i < namesArray.size(); i += 2) {
|
||||
if(namesArray.getAsString(i) != null)
|
||||
name = namesArray.getAsString(i).toString();
|
||||
|
||||
PdfObject jsCode = namesArray.get(i+1);
|
||||
if (jsCode instanceof PdfStream) {
|
||||
byte[] jsCodeBytes = ((PdfStream)jsCode).getBytes();
|
||||
String jsCodeStr = new String(jsCodeBytes, StandardCharsets.UTF_8);
|
||||
script = "//" + entryName + name + "\n" +jsCodeStr;
|
||||
|
||||
} else if (jsCode instanceof PdfDictionary) {
|
||||
// If the JS code is in a dictionary, you'll need to know the key to use.
|
||||
// Assuming the key is PdfName.JS:
|
||||
PdfStream jsCodeStream = ((PdfDictionary)jsCode).getAsStream(PdfName.JS);
|
||||
if (jsCodeStream != null) {
|
||||
byte[] jsCodeBytes = jsCodeStream.getBytes();
|
||||
String jsCodeStr = new String(jsCodeBytes, StandardCharsets.UTF_8);
|
||||
script = "//" + entryName + name + "\n" +jsCodeStr;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
if(script.equals("")) {
|
||||
script = "PDF '" +inputFile.getOriginalFilename() + "' does not contain Javascript";
|
||||
}
|
||||
return WebResponseUtils.bytesToWebResponse(script.getBytes(), name + ".js");
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
@@ -37,9 +37,9 @@ import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.scheduling.annotation.Scheduled;
|
||||
import org.springframework.util.LinkedMultiValueMap;
|
||||
import org.springframework.util.MultiValueMap;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.client.RestTemplate;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
@@ -51,9 +51,11 @@ import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import stirling.software.SPDF.model.ApplicationProperties;
|
||||
import stirling.software.SPDF.model.PipelineConfig;
|
||||
import stirling.software.SPDF.model.PipelineOperation;
|
||||
import stirling.software.SPDF.model.api.HandleDataRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/pipeline")
|
||||
@Tag(name = "Pipeline", description = "Pipeline APIs")
|
||||
public class PipelineController {
|
||||
|
||||
@@ -418,8 +420,9 @@ public class PipelineController {
|
||||
}
|
||||
|
||||
@PostMapping("/handleData")
|
||||
public ResponseEntity<byte[]> handleData(@RequestPart("fileInput") MultipartFile[] files,
|
||||
@RequestParam("json") String jsonString) {
|
||||
public ResponseEntity<byte[]> handleData(@ModelAttribute HandleDataRequest request) {
|
||||
MultipartFile[] files = request.getFileInputs();
|
||||
String jsonString = request.getJsonString();
|
||||
logger.info("Received POST request to /handleData with {} files", files.length);
|
||||
try {
|
||||
List<Resource> outputFiles = handleFiles(files, jsonString);
|
||||
|
||||
@@ -3,294 +3,256 @@ package stirling.software.SPDF.controller.api.security;
|
||||
import java.io.ByteArrayInputStream;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.io.InputStreamReader;
|
||||
import java.security.KeyFactory;
|
||||
import java.security.KeyStore;
|
||||
import java.security.Principal;
|
||||
import java.security.PrivateKey;
|
||||
import java.security.Security;
|
||||
import java.security.cert.Certificate;
|
||||
import java.security.cert.CertificateFactory;
|
||||
import java.security.cert.X509Certificate;
|
||||
import java.security.spec.PKCS8EncodedKeySpec;
|
||||
import java.text.SimpleDateFormat;
|
||||
import java.util.Arrays;
|
||||
import java.util.Calendar;
|
||||
import java.util.Collections;
|
||||
import java.util.Date;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDPageContentStream;
|
||||
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.interactive.annotation.PDAnnotationWidget;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAppearanceDictionary;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAppearanceStream;
|
||||
import org.apache.pdfbox.pdmodel.interactive.digitalsignature.ExternalSigningSupport;
|
||||
import org.apache.pdfbox.pdmodel.interactive.digitalsignature.PDSignature;
|
||||
import org.apache.pdfbox.pdmodel.interactive.digitalsignature.SignatureOptions;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDSignatureField;
|
||||
import org.bouncycastle.cert.jcajce.JcaCertStore;
|
||||
import org.bouncycastle.cms.CMSProcessableByteArray;
|
||||
import org.bouncycastle.cms.CMSSignedData;
|
||||
import org.bouncycastle.cms.CMSSignedDataGenerator;
|
||||
import org.bouncycastle.cms.CMSTypedData;
|
||||
import org.bouncycastle.cms.jcajce.JcaSignerInfoGeneratorBuilder;
|
||||
import org.bouncycastle.jce.provider.BouncyCastleProvider;
|
||||
import org.bouncycastle.operator.ContentSigner;
|
||||
import org.bouncycastle.operator.jcajce.JcaContentSignerBuilder;
|
||||
import org.bouncycastle.operator.jcajce.JcaDigestCalculatorProviderBuilder;
|
||||
import org.bouncycastle.util.io.pem.PemReader;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.itextpdf.io.font.constants.StandardFonts;
|
||||
import com.itextpdf.kernel.font.PdfFont;
|
||||
import com.itextpdf.kernel.font.PdfFontFactory;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfPage;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.StampingProperties;
|
||||
import com.itextpdf.signatures.BouncyCastleDigest;
|
||||
import com.itextpdf.signatures.DigestAlgorithms;
|
||||
import com.itextpdf.signatures.IExternalDigest;
|
||||
import com.itextpdf.signatures.IExternalSignature;
|
||||
import com.itextpdf.signatures.PdfPKCS7;
|
||||
import com.itextpdf.signatures.PdfSignatureAppearance;
|
||||
import com.itextpdf.signatures.PdfSigner;
|
||||
import com.itextpdf.signatures.PrivateKeySignature;
|
||||
import com.itextpdf.signatures.SignatureUtil;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.security.SignPDFWithCertRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class CertSignController {
|
||||
|
||||
private static final Logger logger = LoggerFactory.getLogger(CertSignController.class);
|
||||
private static final Logger logger = LoggerFactory.getLogger(CertSignController.class);
|
||||
|
||||
static {
|
||||
Security.addProvider(new BouncyCastleProvider());
|
||||
}
|
||||
static {
|
||||
Security.addProvider(new BouncyCastleProvider());
|
||||
}
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/cert-sign")
|
||||
@Operation(summary = "Sign PDF with a Digital Certificate",
|
||||
description = "This endpoint accepts a PDF file, a digital certificate and related information to sign the PDF. It then returns the digitally signed PDF file. Input:PDF Output:PDF Type:MF-SISO")
|
||||
public ResponseEntity<byte[]> signPDF(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be signed")
|
||||
MultipartFile pdf,
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/cert-sign")
|
||||
@Operation(summary = "Sign PDF with a Digital Certificate", description = "This endpoint accepts a PDF file, a digital certificate and related information to sign the PDF. It then returns the digitally signed PDF file. Input:PDF Output:PDF Type:MF-SISO")
|
||||
public ResponseEntity<byte[]> signPDFWithCert(@ModelAttribute SignPDFWithCertRequest request) throws Exception {
|
||||
MultipartFile pdf = request.getFileInput();
|
||||
String certType = request.getCertType();
|
||||
MultipartFile privateKeyFile = request.getPrivateKeyFile();
|
||||
MultipartFile certFile = request.getCertFile();
|
||||
MultipartFile p12File = request.getP12File();
|
||||
String password = request.getPassword();
|
||||
Boolean showSignature = request.isShowSignature();
|
||||
String reason = request.getReason();
|
||||
String location = request.getLocation();
|
||||
String name = request.getName();
|
||||
Integer pageNumber = request.getPageNumber();
|
||||
|
||||
@RequestParam(value = "certType", required = false)
|
||||
@Parameter(description = "The type of the digital certificate", schema = @Schema(allowableValues = {"PKCS12", "PEM"}))
|
||||
String certType,
|
||||
PrivateKey privateKey = null;
|
||||
X509Certificate cert = null;
|
||||
|
||||
@RequestParam(value = "key", required = false)
|
||||
@Parameter(description = "The private key for the digital certificate (required for PEM type certificates)")
|
||||
MultipartFile privateKeyFile,
|
||||
if (certType != null) {
|
||||
logger.info("Cert type provided: {}", certType);
|
||||
switch (certType) {
|
||||
case "PKCS12":
|
||||
if (p12File != null) {
|
||||
KeyStore ks = KeyStore.getInstance("PKCS12");
|
||||
ks.load(new ByteArrayInputStream(p12File.getBytes()), password.toCharArray());
|
||||
String alias = ks.aliases().nextElement();
|
||||
if (!ks.isKeyEntry(alias)) {
|
||||
throw new IllegalArgumentException("The provided PKCS12 file does not contain a private key.");
|
||||
}
|
||||
privateKey = (PrivateKey) ks.getKey(alias, password.toCharArray());
|
||||
cert = (X509Certificate) ks.getCertificate(alias);
|
||||
}
|
||||
break;
|
||||
case "PEM":
|
||||
if (privateKeyFile != null && certFile != null) {
|
||||
// Load private key
|
||||
KeyFactory keyFactory = KeyFactory.getInstance("RSA", BouncyCastleProvider.PROVIDER_NAME);
|
||||
if (isPEM(privateKeyFile.getBytes())) {
|
||||
privateKey = keyFactory
|
||||
.generatePrivate(new PKCS8EncodedKeySpec(parsePEM(privateKeyFile.getBytes())));
|
||||
} else {
|
||||
privateKey = keyFactory.generatePrivate(new PKCS8EncodedKeySpec(privateKeyFile.getBytes()));
|
||||
}
|
||||
|
||||
@RequestParam(value = "cert", required = false)
|
||||
@Parameter(description = "The digital certificate (required for PEM type certificates)")
|
||||
MultipartFile certFile,
|
||||
// Load certificate
|
||||
CertificateFactory certFactory = CertificateFactory.getInstance("X.509",
|
||||
BouncyCastleProvider.PROVIDER_NAME);
|
||||
if (isPEM(certFile.getBytes())) {
|
||||
cert = (X509Certificate) certFactory
|
||||
.generateCertificate(new ByteArrayInputStream(parsePEM(certFile.getBytes())));
|
||||
} else {
|
||||
cert = (X509Certificate) certFactory
|
||||
.generateCertificate(new ByteArrayInputStream(certFile.getBytes()));
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
PDSignature signature = new PDSignature();
|
||||
signature.setFilter(PDSignature.FILTER_ADOBE_PPKLITE); // default filter
|
||||
signature.setSubFilter(PDSignature.SUBFILTER_ADBE_PKCS7_SHA1);
|
||||
signature.setName(name);
|
||||
signature.setLocation(location);
|
||||
signature.setReason(reason);
|
||||
signature.setSignDate(Calendar.getInstance());
|
||||
|
||||
// Load the PDF
|
||||
try (PDDocument document = PDDocument.load(pdf.getBytes())) {
|
||||
logger.info("Successfully loaded the provided PDF");
|
||||
SignatureOptions signatureOptions = new SignatureOptions();
|
||||
|
||||
@RequestParam(value = "p12", required = false)
|
||||
@Parameter(description = "The PKCS12 keystore file (required for PKCS12 type certificates)")
|
||||
MultipartFile p12File,
|
||||
// If you want to show the signature
|
||||
|
||||
@RequestParam(value = "password", required = false)
|
||||
@Parameter(description = "The password for the keystore or the private key")
|
||||
String password,
|
||||
// ATTEMPT 2
|
||||
if (showSignature != null && showSignature) {
|
||||
PDPage page = document.getPage(pageNumber - 1);
|
||||
|
||||
@RequestParam(value = "showSignature", required = false)
|
||||
@Parameter(description = "Whether to visually show the signature in the PDF file")
|
||||
Boolean showSignature,
|
||||
PDAcroForm acroForm = document.getDocumentCatalog().getAcroForm();
|
||||
if (acroForm == null) {
|
||||
acroForm = new PDAcroForm(document);
|
||||
document.getDocumentCatalog().setAcroForm(acroForm);
|
||||
}
|
||||
|
||||
@RequestParam(value = "reason", required = false)
|
||||
@Parameter(description = "The reason for signing the PDF")
|
||||
String reason,
|
||||
// Create a new signature field and widget
|
||||
|
||||
@RequestParam(value = "location", required = false)
|
||||
@Parameter(description = "The location where the PDF is signed")
|
||||
String location,
|
||||
PDSignatureField signatureField = new PDSignatureField(acroForm);
|
||||
PDAnnotationWidget widget = signatureField.getWidgets().get(0);
|
||||
PDRectangle rect = new PDRectangle(100, 100, 200, 50); // Define the rectangle size here
|
||||
widget.setRectangle(rect);
|
||||
page.getAnnotations().add(widget);
|
||||
|
||||
@RequestParam(value = "name", required = false)
|
||||
@Parameter(description = "The name of the signer")
|
||||
String name,
|
||||
// Set the appearance for the signature field
|
||||
PDAppearanceDictionary appearanceDict = new PDAppearanceDictionary();
|
||||
PDAppearanceStream appearanceStream = new PDAppearanceStream(document);
|
||||
appearanceStream.setResources(new PDResources());
|
||||
appearanceStream.setBBox(rect);
|
||||
appearanceDict.setNormalAppearance(appearanceStream);
|
||||
widget.setAppearance(appearanceDict);
|
||||
|
||||
@RequestParam(value = "pageNumber", required = false)
|
||||
@Parameter(description = "The page number where the signature should be visible. This is required if showSignature is set to true")
|
||||
Integer pageNumber) throws Exception {
|
||||
|
||||
BouncyCastleProvider provider = new BouncyCastleProvider();
|
||||
Security.addProvider(provider);
|
||||
try (PDPageContentStream contentStream = new PDPageContentStream(document, appearanceStream)) {
|
||||
contentStream.beginText();
|
||||
contentStream.setFont(PDType1Font.HELVETICA_BOLD, 12);
|
||||
contentStream.newLineAtOffset(110, 130);
|
||||
contentStream.showText("Digitally signed by: " + (name != null ? name : "Unknown"));
|
||||
contentStream.newLineAtOffset(0, -15);
|
||||
contentStream.showText("Date: " + new SimpleDateFormat("yyyy.MM.dd HH:mm:ss z").format(new Date()));
|
||||
contentStream.newLineAtOffset(0, -15);
|
||||
if (reason != null && !reason.isEmpty()) {
|
||||
contentStream.showText("Reason: " + reason);
|
||||
contentStream.newLineAtOffset(0, -15);
|
||||
}
|
||||
if (location != null && !location.isEmpty()) {
|
||||
contentStream.showText("Location: " + location);
|
||||
contentStream.newLineAtOffset(0, -15);
|
||||
}
|
||||
contentStream.endText();
|
||||
}
|
||||
|
||||
PrivateKey privateKey = null;
|
||||
X509Certificate cert = null;
|
||||
|
||||
if (certType != null) {
|
||||
switch (certType) {
|
||||
case "PKCS12":
|
||||
if (p12File != null) {
|
||||
KeyStore ks = KeyStore.getInstance("PKCS12");
|
||||
ks.load(new ByteArrayInputStream(p12File.getBytes()), password.toCharArray());
|
||||
String alias = ks.aliases().nextElement();
|
||||
privateKey = (PrivateKey) ks.getKey(alias, password.toCharArray());
|
||||
cert = (X509Certificate) ks.getCertificate(alias);
|
||||
}
|
||||
break;
|
||||
case "PEM":
|
||||
if (privateKeyFile != null && certFile != null) {
|
||||
// Load private key
|
||||
KeyFactory keyFactory = KeyFactory.getInstance("RSA", provider);
|
||||
if (isPEM(privateKeyFile.getBytes())) {
|
||||
privateKey = keyFactory.generatePrivate(new PKCS8EncodedKeySpec(parsePEM(privateKeyFile.getBytes())));
|
||||
} else {
|
||||
privateKey = keyFactory.generatePrivate(new PKCS8EncodedKeySpec(privateKeyFile.getBytes()));
|
||||
}
|
||||
// Add the widget annotation to the page
|
||||
page.getAnnotations().add(widget);
|
||||
|
||||
// Load certificate
|
||||
CertificateFactory certFactory = CertificateFactory.getInstance("X.509", provider);
|
||||
if (isPEM(certFile.getBytes())) {
|
||||
cert = (X509Certificate) certFactory.generateCertificate(new ByteArrayInputStream(parsePEM(certFile.getBytes())));
|
||||
} else {
|
||||
cert = (X509Certificate) certFactory.generateCertificate(new ByteArrayInputStream(certFile.getBytes()));
|
||||
}
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
// Add the signature field to the acroform
|
||||
acroForm.getFields().add(signatureField);
|
||||
|
||||
Principal principal = cert.getSubjectDN();
|
||||
String dn = principal.getName();
|
||||
// Handle multiple signatures by ensuring a unique field name
|
||||
String baseFieldName = "Signature";
|
||||
String signatureFieldName = baseFieldName;
|
||||
int suffix = 1;
|
||||
while (acroForm.getField(signatureFieldName) != null) {
|
||||
suffix++;
|
||||
signatureFieldName = baseFieldName + suffix;
|
||||
}
|
||||
signatureField.setPartialName(signatureFieldName);
|
||||
}
|
||||
|
||||
document.addSignature(signature, signatureOptions);
|
||||
logger.info("Signature added to the PDF document");
|
||||
// External signing
|
||||
ExternalSigningSupport externalSigning = document
|
||||
.saveIncrementalForExternalSigning(new ByteArrayOutputStream());
|
||||
|
||||
// Extract the "CN" (Common Name) field from the distinguished name (if it's present)
|
||||
String cn = null;
|
||||
for (String part : dn.split(",")) {
|
||||
if (part.trim().startsWith("CN=")) {
|
||||
cn = part.trim().substring("CN=".length());
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Set up the PDF reader and stamper
|
||||
PdfReader reader = new PdfReader(new ByteArrayInputStream(pdf.getBytes()));
|
||||
ByteArrayOutputStream signedPdf = new ByteArrayOutputStream();
|
||||
PdfSigner signer = new PdfSigner(reader, signedPdf, new StampingProperties());
|
||||
byte[] content = IOUtils.toByteArray(externalSigning.getContent());
|
||||
|
||||
// Set up the signing appearance
|
||||
PdfSignatureAppearance appearance = signer.getSignatureAppearance()
|
||||
.setReason("Test")
|
||||
.setLocation("TestLocation");
|
||||
// Using BouncyCastle to sign
|
||||
CMSTypedData cmsData = new CMSProcessableByteArray(content);
|
||||
|
||||
if (showSignature != null && showSignature) {
|
||||
float fontSize = 4; // the font size of the signature
|
||||
float marginRight = 36; // Margin from the right
|
||||
float marginBottom = 36; // Margin from the bottom
|
||||
String signingDate = new SimpleDateFormat("yyyy.MM.dd HH:mm:ss z").format(new Date());
|
||||
CMSSignedDataGenerator gen = new CMSSignedDataGenerator();
|
||||
ContentSigner signer = new JcaContentSignerBuilder("SHA256withRSA")
|
||||
.setProvider(BouncyCastleProvider.PROVIDER_NAME).build(privateKey);
|
||||
|
||||
// Prepare the text for the digital signature
|
||||
StringBuilder layer2TextBuilder = new StringBuilder(String.format("Digitally signed by: %s\nDate: %s",
|
||||
name != null ? name : "Unknown", signingDate));
|
||||
gen.addSignerInfoGenerator(new JcaSignerInfoGeneratorBuilder(
|
||||
new JcaDigestCalculatorProviderBuilder().setProvider(BouncyCastleProvider.PROVIDER_NAME).build())
|
||||
.build(signer, cert));
|
||||
|
||||
if (reason != null && !reason.isEmpty()) {
|
||||
layer2TextBuilder.append("\nReason: ").append(reason);
|
||||
}
|
||||
gen.addCertificates(new JcaCertStore(Collections.singletonList(cert)));
|
||||
CMSSignedData signedData = gen.generate(cmsData, false);
|
||||
|
||||
if (location != null && !location.isEmpty()) {
|
||||
layer2TextBuilder.append("\nLocation: ").append(location);
|
||||
}
|
||||
String layer2Text = layer2TextBuilder.toString();
|
||||
// Get the PDF font and measure the width and height of the text block
|
||||
PdfFont font = PdfFontFactory.createFont(StandardFonts.HELVETICA_BOLD);
|
||||
float textWidth = Arrays.stream(layer2Text.split("\n"))
|
||||
.map(line -> font.getWidth(line, fontSize))
|
||||
.max(Float::compare)
|
||||
.orElse(0f);
|
||||
int numLines = layer2Text.split("\n").length;
|
||||
float textHeight = numLines * fontSize;
|
||||
byte[] cmsSignature = signedData.getEncoded();
|
||||
logger.info("About to sign content using BouncyCastle");
|
||||
externalSigning.setSignature(cmsSignature);
|
||||
logger.info("Signature set successfully");
|
||||
|
||||
// Calculate the signature rectangle size
|
||||
float sigWidth = textWidth + marginRight * 2;
|
||||
float sigHeight = textHeight + marginBottom * 2;
|
||||
// After setting the signature, return the resultant PDF
|
||||
try (ByteArrayOutputStream signedPdfOutput = new ByteArrayOutputStream()) {
|
||||
document.save(signedPdfOutput);
|
||||
return WebResponseUtils.boasToWebResponse(signedPdfOutput,
|
||||
pdf.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_signed.pdf");
|
||||
|
||||
// Get the page size
|
||||
PdfPage page = signer.getDocument().getPage(1);
|
||||
Rectangle pageSize = page.getPageSize();
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
} catch (Exception e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
|
||||
// Define the position and dimension of the signature field
|
||||
Rectangle rect = new Rectangle(
|
||||
pageSize.getRight() - sigWidth - marginRight,
|
||||
pageSize.getBottom() + marginBottom,
|
||||
sigWidth,
|
||||
sigHeight
|
||||
);
|
||||
return null;
|
||||
}
|
||||
|
||||
// Configure the appearance of the digital signature
|
||||
appearance.setPageRect(rect)
|
||||
.setContact(name != null ? name : "")
|
||||
.setPageNumber(pageNumber)
|
||||
.setReason(reason != null ? reason : "")
|
||||
.setLocation(location != null ? location : "")
|
||||
.setReuseAppearance(false)
|
||||
.setLayer2Text(layer2Text.toString());
|
||||
|
||||
signer.setFieldName("sig");
|
||||
} else {
|
||||
appearance.setRenderingMode(PdfSignatureAppearance.RenderingMode.DESCRIPTION);
|
||||
}
|
||||
|
||||
// Set up the signer
|
||||
PrivateKeySignature pks = new PrivateKeySignature(privateKey, DigestAlgorithms.SHA256, provider.getName());
|
||||
IExternalSignature pss = new PrivateKeySignature(privateKey, DigestAlgorithms.SHA256, provider.getName());
|
||||
IExternalDigest digest = new BouncyCastleDigest();
|
||||
|
||||
// Call iTex7 to sign the PDF
|
||||
signer.signDetached(digest, pks, new Certificate[] {cert}, null, null, null, 0, PdfSigner.CryptoStandard.CMS);
|
||||
|
||||
|
||||
System.out.println("Signed PDF size: " + signedPdf.size());
|
||||
|
||||
System.out.println("PDF signed = " + isPdfSigned(signedPdf.toByteArray()));
|
||||
return WebResponseUtils.bytesToWebResponse(signedPdf.toByteArray(), "example.pdf");
|
||||
}
|
||||
|
||||
public boolean isPdfSigned(byte[] pdfData) throws IOException {
|
||||
InputStream pdfStream = new ByteArrayInputStream(pdfData);
|
||||
PdfDocument pdfDoc = new PdfDocument(new PdfReader(pdfStream));
|
||||
SignatureUtil signatureUtil = new SignatureUtil(pdfDoc);
|
||||
List<String> names = signatureUtil.getSignatureNames();
|
||||
|
||||
boolean isSigned = false;
|
||||
|
||||
for (String name : names) {
|
||||
PdfPKCS7 pkcs7 = signatureUtil.readSignatureData(name);
|
||||
if (pkcs7 != null) {
|
||||
System.out.println("Signature found.");
|
||||
|
||||
// Log certificate details
|
||||
Certificate[] signChain = pkcs7.getSignCertificateChain();
|
||||
for (Certificate cert : signChain) {
|
||||
if (cert instanceof X509Certificate) {
|
||||
X509Certificate x509 = (X509Certificate) cert;
|
||||
System.out.println("Certificate Details:");
|
||||
System.out.println("Subject: " + x509.getSubjectDN());
|
||||
System.out.println("Issuer: " + x509.getIssuerDN());
|
||||
System.out.println("Serial: " + x509.getSerialNumber());
|
||||
System.out.println("Not Before: " + x509.getNotBefore());
|
||||
System.out.println("Not After: " + x509.getNotAfter());
|
||||
}
|
||||
}
|
||||
|
||||
isSigned = true;
|
||||
}
|
||||
}
|
||||
|
||||
pdfDoc.close();
|
||||
|
||||
return isSigned;
|
||||
}
|
||||
private byte[] parsePEM(byte[] content) throws IOException {
|
||||
PemReader pemReader = new PemReader(new InputStreamReader(new ByteArrayInputStream(content)));
|
||||
return pemReader.readPemObject().getContent();
|
||||
}
|
||||
|
||||
private boolean isPEM(byte[] content) {
|
||||
String contentStr = new String(content);
|
||||
return contentStr.contains("-----BEGIN") && contentStr.contains("-----END");
|
||||
}
|
||||
|
||||
|
||||
|
||||
private byte[] parsePEM(byte[] content) throws IOException {
|
||||
PemReader pemReader = new PemReader(new InputStreamReader(new ByteArrayInputStream(content)));
|
||||
return pemReader.readPemObject().getContent();
|
||||
}
|
||||
|
||||
private boolean isPEM(byte[] content) {
|
||||
String contentStr = new String(content);
|
||||
return contentStr.contains("-----BEGIN") && contentStr.contains("-----END");
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
package stirling.software.SPDF.controller.api.security;
|
||||
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.text.SimpleDateFormat;
|
||||
import java.util.Calendar;
|
||||
@@ -11,53 +11,71 @@ import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.Set;
|
||||
|
||||
import org.apache.pdfbox.cos.COSDocument;
|
||||
import org.apache.pdfbox.cos.COSInputStream;
|
||||
import org.apache.pdfbox.cos.COSName;
|
||||
import org.apache.pdfbox.cos.COSObject;
|
||||
import org.apache.pdfbox.cos.COSStream;
|
||||
import org.apache.pdfbox.cos.COSString;
|
||||
import org.apache.pdfbox.pdmodel.PDDocument;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentCatalog;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentInformation;
|
||||
import org.apache.pdfbox.pdmodel.PDDocumentNameDictionary;
|
||||
import org.apache.pdfbox.pdmodel.PDEmbeddedFilesNameTreeNode;
|
||||
import org.apache.pdfbox.pdmodel.PDJavascriptNameTreeNode;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.PDResources;
|
||||
import org.apache.pdfbox.pdmodel.common.PDMetadata;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.common.PDStream;
|
||||
import org.apache.pdfbox.pdmodel.common.filespecification.PDComplexFileSpecification;
|
||||
import org.apache.pdfbox.pdmodel.common.filespecification.PDEmbeddedFile;
|
||||
import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureElement;
|
||||
import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureNode;
|
||||
import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureTreeRoot;
|
||||
import org.apache.pdfbox.pdmodel.encryption.AccessPermission;
|
||||
import org.apache.pdfbox.pdmodel.encryption.PDEncryption;
|
||||
import org.apache.pdfbox.pdmodel.font.PDFont;
|
||||
import org.apache.pdfbox.pdmodel.font.PDFontDescriptor;
|
||||
import org.apache.pdfbox.pdmodel.graphics.PDXObject;
|
||||
import org.apache.pdfbox.pdmodel.graphics.color.PDColorSpace;
|
||||
import org.apache.pdfbox.pdmodel.graphics.color.PDICCBased;
|
||||
import org.apache.pdfbox.pdmodel.graphics.form.PDFormXObject;
|
||||
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
|
||||
import org.apache.pdfbox.pdmodel.graphics.optionalcontent.PDOptionalContentGroup;
|
||||
import org.apache.pdfbox.pdmodel.graphics.optionalcontent.PDOptionalContentProperties;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionJavaScript;
|
||||
import org.apache.pdfbox.pdmodel.interactive.action.PDActionURI;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationFileAttachment;
|
||||
import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationLink;
|
||||
import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem;
|
||||
import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineNode;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
|
||||
import org.apache.pdfbox.pdmodel.interactive.form.PDField;
|
||||
import org.apache.pdfbox.text.PDFTextStripper;
|
||||
import org.apache.xmpbox.XMPMetadata;
|
||||
import org.apache.xmpbox.xml.DomXmpParser;
|
||||
import org.apache.xmpbox.xml.XmpParsingException;
|
||||
import org.apache.xmpbox.xml.XmpSerializer;
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestPart;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import com.fasterxml.jackson.databind.node.ArrayNode;
|
||||
import com.fasterxml.jackson.databind.node.ObjectNode;
|
||||
import com.itextpdf.forms.PdfAcroForm;
|
||||
import com.itextpdf.forms.fields.PdfFormField;
|
||||
import com.itextpdf.kernel.geom.Rectangle;
|
||||
import com.itextpdf.kernel.pdf.PdfArray;
|
||||
import com.itextpdf.kernel.pdf.PdfCatalog;
|
||||
import com.itextpdf.kernel.pdf.PdfDictionary;
|
||||
import com.itextpdf.kernel.pdf.PdfDocument;
|
||||
import com.itextpdf.kernel.pdf.PdfName;
|
||||
import com.itextpdf.kernel.pdf.PdfObject;
|
||||
import com.itextpdf.kernel.pdf.PdfOutline;
|
||||
import com.itextpdf.kernel.pdf.PdfReader;
|
||||
import com.itextpdf.kernel.pdf.PdfResources;
|
||||
import com.itextpdf.kernel.pdf.PdfStream;
|
||||
import com.itextpdf.kernel.pdf.PdfString;
|
||||
import com.itextpdf.kernel.pdf.annot.PdfAnnotation;
|
||||
import com.itextpdf.kernel.pdf.annot.PdfFileAttachmentAnnotation;
|
||||
import com.itextpdf.kernel.pdf.annot.PdfLinkAnnotation;
|
||||
import com.itextpdf.kernel.pdf.layer.PdfLayer;
|
||||
import com.itextpdf.kernel.pdf.layer.PdfOCProperties;
|
||||
import com.itextpdf.kernel.xmp.XMPException;
|
||||
import com.itextpdf.kernel.xmp.XMPMeta;
|
||||
import com.itextpdf.kernel.xmp.XMPMetaFactory;
|
||||
import com.itextpdf.kernel.xmp.options.SerializeOptions;
|
||||
|
||||
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.model.api.PDFFile;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class GetInfoOnPDF {
|
||||
|
||||
@@ -65,14 +83,11 @@ public class GetInfoOnPDF {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/get-info-on-pdf")
|
||||
@Operation(summary = "Summary here", description = "desc. Input:PDF Output:JSON Type:SISO")
|
||||
public ResponseEntity<byte[]> getPdfInfo(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to get info on", required = true) MultipartFile inputFile)
|
||||
public ResponseEntity<byte[]> getPdfInfo(@ModelAttribute PDFFile request)
|
||||
throws IOException {
|
||||
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
try (
|
||||
PDDocument pdfBoxDoc = PDDocument.load(inputFile.getInputStream());
|
||||
PdfDocument itextDoc = new PdfDocument(new PdfReader(inputFile.getInputStream()))
|
||||
) {
|
||||
ObjectMapper objectMapper = new ObjectMapper();
|
||||
ObjectNode jsonOutput = objectMapper.createObjectNode();
|
||||
@@ -120,21 +135,17 @@ public class GetInfoOnPDF {
|
||||
boolean hasCompression = false;
|
||||
String compressionType = "None";
|
||||
|
||||
// Check for object streams
|
||||
for (int i = 1; i <= itextDoc.getNumberOfPdfObjects(); i++) {
|
||||
PdfObject obj = itextDoc.getPdfObject(i);
|
||||
if (obj != null && obj.isStream() && ((PdfStream) obj).get(PdfName.Type) == PdfName.ObjStm) {
|
||||
hasCompression = true;
|
||||
compressionType = "Object Streams";
|
||||
break;
|
||||
COSDocument cosDoc = pdfBoxDoc.getDocument();
|
||||
for (COSObject cosObject : cosDoc.getObjects()) {
|
||||
if (cosObject.getObject() instanceof COSStream) {
|
||||
COSStream cosStream = (COSStream) cosObject.getObject();
|
||||
if (COSName.OBJ_STM.equals(cosStream.getItem(COSName.TYPE))) {
|
||||
hasCompression = true;
|
||||
compressionType = "Object Streams";
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// If not compressed using object streams, check for compressed Xref tables
|
||||
if (!hasCompression && itextDoc.getReader().hasRebuiltXref()) {
|
||||
hasCompression = true;
|
||||
compressionType = "Compressed Xref or Rebuilt Xref";
|
||||
}
|
||||
basicInfo.put("Compression", hasCompression);
|
||||
if(hasCompression)
|
||||
basicInfo.put("CompressionType", compressionType);
|
||||
@@ -144,9 +155,8 @@ public class GetInfoOnPDF {
|
||||
basicInfo.put("Number of pages", pdfBoxDoc.getNumberOfPages());
|
||||
|
||||
|
||||
// Page Mode using iText7
|
||||
PdfCatalog catalog = itextDoc.getCatalog();
|
||||
PdfName pageMode = catalog.getPdfObject().getAsName(PdfName.PageMode);
|
||||
PDDocumentCatalog catalog = pdfBoxDoc.getDocumentCatalog();
|
||||
String pageMode = catalog.getPageMode().name();
|
||||
|
||||
// Document Information using PDFBox
|
||||
docInfoNode.put("PDF version", pdfBoxDoc.getVersion());
|
||||
@@ -157,49 +167,56 @@ public class GetInfoOnPDF {
|
||||
|
||||
|
||||
|
||||
PdfAcroForm acroForm = PdfAcroForm.getAcroForm(itextDoc, false);
|
||||
PDAcroForm acroForm = pdfBoxDoc.getDocumentCatalog().getAcroForm();
|
||||
|
||||
ObjectNode formFieldsNode = objectMapper.createObjectNode();
|
||||
if (acroForm != null) {
|
||||
for (Map.Entry<String, PdfFormField> entry : acroForm.getFormFields().entrySet()) {
|
||||
formFieldsNode.put(entry.getKey(), entry.getValue().getValueAsString());
|
||||
for (PDField field : acroForm.getFieldTree()) {
|
||||
formFieldsNode.put(field.getFullyQualifiedName(), field.getValueAsString());
|
||||
}
|
||||
}
|
||||
jsonOutput.set("FormFields", formFieldsNode);
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
//embeed files TODO size
|
||||
ArrayNode embeddedFilesArray = objectMapper.createArrayNode();
|
||||
if(itextDoc.getCatalog().getPdfObject().getAsDictionary(PdfName.Names) != null)
|
||||
{
|
||||
PdfDictionary embeddedFiles = itextDoc.getCatalog().getPdfObject().getAsDictionary(PdfName.Names)
|
||||
.getAsDictionary(PdfName.EmbeddedFiles);
|
||||
if (embeddedFiles != null) {
|
||||
|
||||
PdfArray namesArray = embeddedFiles.getAsArray(PdfName.Names);
|
||||
if(namesArray != null) {
|
||||
for (int i = 0; i < namesArray.size(); i += 2) {
|
||||
ObjectNode embeddedFileNode = objectMapper.createObjectNode();
|
||||
embeddedFileNode.put("Name", namesArray.getAsString(i).toString());
|
||||
// Add other details if required
|
||||
embeddedFilesArray.add(embeddedFileNode);
|
||||
if(catalog.getNames() != null) {
|
||||
PDEmbeddedFilesNameTreeNode efTree = catalog.getNames().getEmbeddedFiles();
|
||||
|
||||
ArrayNode embeddedFilesArray = objectMapper.createArrayNode();
|
||||
if (efTree != null) {
|
||||
Map<String, PDComplexFileSpecification> efMap = efTree.getNames();
|
||||
if (efMap != null) {
|
||||
for (Map.Entry<String, PDComplexFileSpecification> entry : efMap.entrySet()) {
|
||||
ObjectNode embeddedFileNode = objectMapper.createObjectNode();
|
||||
embeddedFileNode.put("Name", entry.getKey());
|
||||
PDEmbeddedFile embeddedFile = entry.getValue().getEmbeddedFile();
|
||||
if (embeddedFile != null) {
|
||||
embeddedFileNode.put("FileSize", embeddedFile.getLength()); // size in bytes
|
||||
}
|
||||
embeddedFilesArray.add(embeddedFileNode);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
other.set("EmbeddedFiles", embeddedFilesArray);
|
||||
}
|
||||
}
|
||||
other.set("EmbeddedFiles", embeddedFilesArray);
|
||||
|
||||
|
||||
|
||||
//attachments TODO size
|
||||
ArrayNode attachmentsArray = objectMapper.createArrayNode();
|
||||
for (int pageNum = 1; pageNum <= itextDoc.getNumberOfPages(); pageNum++) {
|
||||
for (PdfAnnotation annotation : itextDoc.getPage(pageNum).getAnnotations()) {
|
||||
if (annotation instanceof PdfFileAttachmentAnnotation) {
|
||||
for (PDPage page : pdfBoxDoc.getPages()) {
|
||||
for (PDAnnotation annotation : page.getAnnotations()) {
|
||||
if (annotation instanceof PDAnnotationFileAttachment) {
|
||||
PDAnnotationFileAttachment fileAttachmentAnnotation = (PDAnnotationFileAttachment) annotation;
|
||||
|
||||
ObjectNode attachmentNode = objectMapper.createObjectNode();
|
||||
attachmentNode.put("Name", ((PdfFileAttachmentAnnotation) annotation).getName().toString());
|
||||
attachmentNode.put("Description", annotation.getContents().getValue());
|
||||
attachmentNode.put("Name", fileAttachmentAnnotation.getAttachmentName());
|
||||
attachmentNode.put("Description", fileAttachmentAnnotation.getContents());
|
||||
|
||||
attachmentsArray.add(attachmentNode);
|
||||
}
|
||||
}
|
||||
@@ -207,65 +224,54 @@ public class GetInfoOnPDF {
|
||||
other.set("Attachments", attachmentsArray);
|
||||
|
||||
//Javascript
|
||||
PdfDictionary namesDict = itextDoc.getCatalog().getPdfObject().getAsDictionary(PdfName.Names);
|
||||
PDDocumentNameDictionary namesDict = catalog.getNames();
|
||||
ArrayNode javascriptArray = objectMapper.createArrayNode();
|
||||
|
||||
if (namesDict != null) {
|
||||
PdfDictionary javascriptDict = namesDict.getAsDictionary(PdfName.JavaScript);
|
||||
PDJavascriptNameTreeNode javascriptDict = namesDict.getJavaScript();
|
||||
if (javascriptDict != null) {
|
||||
try {
|
||||
Map<String, PDActionJavaScript> jsEntries = javascriptDict.getNames();
|
||||
|
||||
PdfArray namesArray = javascriptDict.getAsArray(PdfName.Names);
|
||||
for (int i = 0; i < namesArray.size(); i += 2) {
|
||||
ObjectNode jsNode = objectMapper.createObjectNode();
|
||||
if(namesArray.getAsString(i) != null)
|
||||
jsNode.put("JS Name", namesArray.getAsString(i).toString());
|
||||
for (Map.Entry<String, PDActionJavaScript> entry : jsEntries.entrySet()) {
|
||||
ObjectNode jsNode = objectMapper.createObjectNode();
|
||||
jsNode.put("JS Name", entry.getKey());
|
||||
|
||||
// Here we check for a PdfStream object and retrieve the JS code from it
|
||||
PdfObject jsCode = namesArray.get(i+1);
|
||||
if (jsCode instanceof PdfStream) {
|
||||
byte[] jsCodeBytes = ((PdfStream)jsCode).getBytes();
|
||||
String jsCodeStr = new String(jsCodeBytes, StandardCharsets.UTF_8);
|
||||
jsNode.put("JS Script Length", jsCodeStr.length());
|
||||
} else if (jsCode instanceof PdfDictionary) {
|
||||
// If the JS code is in a dictionary, you'll need to know the key to use.
|
||||
// Assuming the key is PdfName.JS:
|
||||
PdfStream jsCodeStream = ((PdfDictionary)jsCode).getAsStream(PdfName.JS);
|
||||
if (jsCodeStream != null) {
|
||||
byte[] jsCodeBytes = jsCodeStream.getBytes();
|
||||
String jsCodeStr = new String(jsCodeBytes, StandardCharsets.UTF_8);
|
||||
jsNode.put("JS Script Character Length", jsCodeStr.length());
|
||||
PDActionJavaScript jsAction = entry.getValue();
|
||||
if (jsAction != null) {
|
||||
String jsCodeStr = jsAction.getAction();
|
||||
if (jsCodeStr != null) {
|
||||
jsNode.put("JS Script Length", jsCodeStr.length());
|
||||
}
|
||||
}
|
||||
|
||||
javascriptArray.add(jsNode);
|
||||
}
|
||||
|
||||
javascriptArray.add(jsNode);
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
other.set("JavaScript", javascriptArray);
|
||||
|
||||
|
||||
//TODO size
|
||||
PdfOCProperties ocProperties = itextDoc.getCatalog().getOCProperties(false);
|
||||
PDOptionalContentProperties ocProperties = pdfBoxDoc.getDocumentCatalog().getOCProperties();
|
||||
ArrayNode layersArray = objectMapper.createArrayNode();
|
||||
|
||||
if (ocProperties != null) {
|
||||
|
||||
for (PdfLayer layer : ocProperties.getLayers()) {
|
||||
for (PDOptionalContentGroup ocg : ocProperties.getOptionalContentGroups()) {
|
||||
ObjectNode layerNode = objectMapper.createObjectNode();
|
||||
layerNode.put("Name", layer.getPdfObject().getAsString(PdfName.Name).toString());
|
||||
layerNode.put("Name", ocg.getName());
|
||||
layersArray.add(layerNode);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
other.set("Layers", layersArray);
|
||||
|
||||
//TODO Security
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
// Digital Signatures using iText7 TODO
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -282,13 +288,13 @@ public class GetInfoOnPDF {
|
||||
}
|
||||
|
||||
|
||||
boolean isPdfACompliant = checkOutputIntent(itextDoc, "PDF/A");
|
||||
boolean isPdfXCompliant = checkOutputIntent(itextDoc, "PDF/X");
|
||||
boolean isPdfECompliant = checkForStandard(itextDoc, "PDF/E");
|
||||
boolean isPdfVTCompliant = checkForStandard(itextDoc, "PDF/VT");
|
||||
boolean isPdfUACompliant = checkForStandard(itextDoc, "PDF/UA");
|
||||
boolean isPdfBCompliant = checkForStandard(itextDoc, "PDF/B"); // If you want to check for PDF/Broadcast, though this isn't an official ISO standard.
|
||||
boolean isPdfSECCompliant = checkForStandard(itextDoc, "PDF/SEC"); // This might not be effective since PDF/SEC was under development in 2021.
|
||||
boolean isPdfACompliant = checkForStandard(pdfBoxDoc, "PDF/A");
|
||||
boolean isPdfXCompliant = checkForStandard(pdfBoxDoc, "PDF/X");
|
||||
boolean isPdfECompliant = checkForStandard(pdfBoxDoc, "PDF/E");
|
||||
boolean isPdfVTCompliant = checkForStandard(pdfBoxDoc, "PDF/VT");
|
||||
boolean isPdfUACompliant = checkForStandard(pdfBoxDoc, "PDF/UA");
|
||||
boolean isPdfBCompliant = checkForStandard(pdfBoxDoc, "PDF/B"); // If you want to check for PDF/Broadcast, though this isn't an official ISO standard.
|
||||
boolean isPdfSECCompliant = checkForStandard(pdfBoxDoc, "PDF/SEC"); // This might not be effective since PDF/SEC was under development in 2021.
|
||||
|
||||
compliancy.put("IsPDF/ACompliant", isPdfACompliant);
|
||||
compliancy.put("IsPDF/XCompliant", isPdfXCompliant);
|
||||
@@ -302,27 +308,39 @@ public class GetInfoOnPDF {
|
||||
|
||||
|
||||
|
||||
PDOutlineNode root = pdfBoxDoc.getDocumentCatalog().getDocumentOutline();
|
||||
ArrayNode bookmarksArray = objectMapper.createArrayNode();
|
||||
PdfOutline root = itextDoc.getOutlines(false);
|
||||
|
||||
if (root != null) {
|
||||
for (PdfOutline child : root.getAllChildren()) {
|
||||
for (PDOutlineItem child : root.children()) {
|
||||
addOutlinesToArray(child, bookmarksArray);
|
||||
}
|
||||
}
|
||||
|
||||
other.set("Bookmarks/Outline/TOC", bookmarksArray);
|
||||
|
||||
byte[] xmpBytes = itextDoc.getXmpMetadata();
|
||||
String xmpString = null;
|
||||
if (xmpBytes != null) {
|
||||
try {
|
||||
XMPMeta xmpMeta = XMPMetaFactory.parseFromBuffer(xmpBytes);
|
||||
xmpString = new String(XMPMetaFactory.serializeToBuffer(xmpMeta, new SerializeOptions()));
|
||||
} catch (XMPException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
other.put("XMPMetadata", xmpString);
|
||||
|
||||
|
||||
|
||||
PDMetadata pdMetadata = pdfBoxDoc.getDocumentCatalog().getMetadata();
|
||||
|
||||
String xmpString = null;
|
||||
|
||||
if (pdMetadata != null) {
|
||||
try {
|
||||
COSInputStream is = pdMetadata.createInputStream();
|
||||
DomXmpParser domXmpParser = new DomXmpParser();
|
||||
XMPMetadata xmpMeta = domXmpParser.parse(is);
|
||||
|
||||
ByteArrayOutputStream os = new ByteArrayOutputStream();
|
||||
new XmpSerializer().serialize(xmpMeta, os, true);
|
||||
xmpString = new String(os.toByteArray(), StandardCharsets.UTF_8);
|
||||
} catch (XmpParsingException | IOException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
|
||||
other.put("XMPMetadata", xmpString);
|
||||
|
||||
|
||||
|
||||
if (pdfBoxDoc.isEncrypted()) {
|
||||
@@ -356,43 +374,65 @@ public class GetInfoOnPDF {
|
||||
|
||||
|
||||
ObjectNode pageInfoParent = objectMapper.createObjectNode();
|
||||
for (int pageNum = 1; pageNum <= itextDoc.getNumberOfPages(); pageNum++) {
|
||||
for (int pageNum = 0; pageNum < pdfBoxDoc.getNumberOfPages(); pageNum++) {
|
||||
ObjectNode pageInfo = objectMapper.createObjectNode();
|
||||
|
||||
// Retrieve the page
|
||||
PDPage page = pdfBoxDoc.getPage(pageNum);
|
||||
|
||||
// Page-level Information
|
||||
Rectangle pageSize = itextDoc.getPage(pageNum).getPageSize();
|
||||
pageInfo.put("Width", pageSize.getWidth());
|
||||
pageInfo.put("Height", pageSize.getHeight());
|
||||
pageInfo.put("Rotation", itextDoc.getPage(pageNum).getRotation());
|
||||
pageInfo.put("Page Orientation", getPageOrientation(pageSize.getWidth(),pageSize.getHeight()));
|
||||
pageInfo.put("Standard Size", getPageSize(pageSize.getWidth(),pageSize.getHeight()));
|
||||
PDRectangle mediaBox = page.getMediaBox();
|
||||
|
||||
float width = mediaBox.getWidth();
|
||||
float height = mediaBox.getHeight();
|
||||
|
||||
ObjectNode sizeInfo = objectMapper.createObjectNode();
|
||||
|
||||
getDimensionInfo(sizeInfo, width, height);
|
||||
|
||||
sizeInfo.put("Standard Page", getPageSize(width, height));
|
||||
pageInfo.set("Size", sizeInfo);
|
||||
|
||||
pageInfo.put("Rotation", page.getRotation());
|
||||
pageInfo.put("Page Orientation", getPageOrientation(width, height));
|
||||
|
||||
|
||||
// Boxes
|
||||
pageInfo.put("MediaBox", itextDoc.getPage(pageNum).getMediaBox().toString());
|
||||
pageInfo.put("CropBox", itextDoc.getPage(pageNum).getCropBox().toString());
|
||||
pageInfo.put("BleedBox", itextDoc.getPage(pageNum).getBleedBox().toString());
|
||||
pageInfo.put("TrimBox", itextDoc.getPage(pageNum).getTrimBox().toString());
|
||||
pageInfo.put("ArtBox", itextDoc.getPage(pageNum).getArtBox().toString());
|
||||
pageInfo.put("MediaBox", mediaBox.toString());
|
||||
|
||||
// Assuming the following boxes are defined for your document; if not, you may get null values.
|
||||
PDRectangle cropBox = page.getCropBox();
|
||||
pageInfo.put("CropBox", cropBox == null ? "Undefined" : cropBox.toString());
|
||||
|
||||
PDRectangle bleedBox = page.getBleedBox();
|
||||
pageInfo.put("BleedBox", bleedBox == null ? "Undefined" : bleedBox.toString());
|
||||
|
||||
PDRectangle trimBox = page.getTrimBox();
|
||||
pageInfo.put("TrimBox", trimBox == null ? "Undefined" : trimBox.toString());
|
||||
|
||||
PDRectangle artBox = page.getArtBox();
|
||||
pageInfo.put("ArtBox", artBox == null ? "Undefined" : artBox.toString());
|
||||
|
||||
// Content Extraction
|
||||
PDFTextStripper textStripper = new PDFTextStripper();
|
||||
textStripper.setStartPage(pageNum -1);
|
||||
textStripper.setEndPage(pageNum - 1);
|
||||
textStripper.setStartPage(pageNum + 1);
|
||||
textStripper.setEndPage(pageNum +1);
|
||||
String pageText = textStripper.getText(pdfBoxDoc);
|
||||
|
||||
pageInfo.put("Text Characters Count", pageText.length()); //
|
||||
|
||||
// Annotations
|
||||
List<PdfAnnotation> annotations = itextDoc.getPage(pageNum).getAnnotations();
|
||||
// Annotations
|
||||
|
||||
List<PDAnnotation> annotations = page.getAnnotations();
|
||||
|
||||
int subtypeCount = 0;
|
||||
int contentsCount = 0;
|
||||
|
||||
for (PdfAnnotation annotation : annotations) {
|
||||
if(annotation.getSubtype() != null) {
|
||||
for (PDAnnotation annotation : annotations) {
|
||||
if (annotation.getSubtype() != null) {
|
||||
subtypeCount++; // Increase subtype count
|
||||
}
|
||||
if(annotation.getContents() != null) {
|
||||
if (annotation.getContents() != null) {
|
||||
contentsCount++; // Increase contents count
|
||||
}
|
||||
}
|
||||
@@ -403,25 +443,31 @@ public class GetInfoOnPDF {
|
||||
annotationsObject.put("ContentsCount", contentsCount);
|
||||
pageInfo.set("Annotations", annotationsObject);
|
||||
|
||||
|
||||
|
||||
// Images (simplified)
|
||||
// This part is non-trivial as images can be embedded in multiple ways in a PDF.
|
||||
// Here is a basic structure to recognize image XObjects on a page.
|
||||
ArrayNode imagesArray = objectMapper.createArrayNode();
|
||||
PdfResources resources = itextDoc.getPage(pageNum).getResources();
|
||||
for (PdfName name : resources.getResourceNames()) {
|
||||
PdfObject obj = resources.getResource(name);
|
||||
if (obj instanceof PdfStream) {
|
||||
PdfStream stream = (PdfStream) obj;
|
||||
if (PdfName.Image.equals(stream.getAsName(PdfName.Subtype))) {
|
||||
ObjectNode imageNode = objectMapper.createObjectNode();
|
||||
imageNode.put("Width", stream.getAsNumber(PdfName.Width).intValue());
|
||||
imageNode.put("Height", stream.getAsNumber(PdfName.Height).intValue());
|
||||
PdfObject colorSpace = stream.get(PdfName.ColorSpace);
|
||||
if (colorSpace != null) {
|
||||
imageNode.put("ColorSpace", colorSpace.toString());
|
||||
}
|
||||
imagesArray.add(imageNode);
|
||||
PDResources resources = page.getResources();
|
||||
|
||||
|
||||
for (COSName name : resources.getXObjectNames()) {
|
||||
PDXObject xObject = resources.getXObject(name);
|
||||
if (xObject instanceof PDImageXObject) {
|
||||
PDImageXObject image = (PDImageXObject) xObject;
|
||||
|
||||
ObjectNode imageNode = objectMapper.createObjectNode();
|
||||
imageNode.put("Width", image.getWidth());
|
||||
imageNode.put("Height", image.getHeight());
|
||||
if(image.getMetadata() != null && image.getMetadata().getFile() != null && image.getMetadata().getFile().getFile() != null) {
|
||||
imageNode.put("Name", image.getMetadata().getFile().getFile());
|
||||
}
|
||||
if (image.getColorSpace() != null) {
|
||||
imageNode.put("ColorSpace", image.getColorSpace().getName());
|
||||
}
|
||||
|
||||
imagesArray.add(imageNode);
|
||||
}
|
||||
}
|
||||
pageInfo.set("Images", imagesArray);
|
||||
@@ -431,12 +477,13 @@ public class GetInfoOnPDF {
|
||||
ArrayNode linksArray = objectMapper.createArrayNode();
|
||||
Set<String> uniqueURIs = new HashSet<>(); // To store unique URIs
|
||||
|
||||
for (PdfAnnotation annotation : annotations) {
|
||||
if (annotation instanceof PdfLinkAnnotation) {
|
||||
PdfLinkAnnotation linkAnnotation = (PdfLinkAnnotation) annotation;
|
||||
if(linkAnnotation != null && linkAnnotation.getAction() != null) {
|
||||
String uri = linkAnnotation.getAction().toString();
|
||||
uniqueURIs.add(uri); // Add to set to ensure uniqueness
|
||||
for (PDAnnotation annotation : annotations) {
|
||||
if (annotation instanceof PDAnnotationLink) {
|
||||
PDAnnotationLink linkAnnotation = (PDAnnotationLink) annotation;
|
||||
if (linkAnnotation.getAction() instanceof PDActionURI) {
|
||||
PDActionURI uriAction = (PDActionURI) linkAnnotation.getAction();
|
||||
String uri = uriAction.getURI();
|
||||
uniqueURIs.add(uri); // Add to set to ensure uniqueness
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -449,96 +496,52 @@ public class GetInfoOnPDF {
|
||||
}
|
||||
pageInfo.set("Links", linksArray);
|
||||
|
||||
// Fonts
|
||||
|
||||
// Fonts
|
||||
ArrayNode fontsArray = objectMapper.createArrayNode();
|
||||
PdfDictionary fontDicts = resources.getResource(PdfName.Font);
|
||||
Set<String> uniqueSubtypes = new HashSet<>(); // To store unique subtypes
|
||||
|
||||
// Map to store unique fonts and their counts
|
||||
Map<String, ObjectNode> uniqueFontsMap = new HashMap<>();
|
||||
|
||||
if (fontDicts != null) {
|
||||
for (PdfName key : fontDicts.keySet()) {
|
||||
ObjectNode fontNode = objectMapper.createObjectNode(); // Create a new font node for each font
|
||||
PdfDictionary font = fontDicts.getAsDictionary(key);
|
||||
for (COSName fontName : resources.getFontNames()) {
|
||||
PDFont font = resources.getFont(fontName);
|
||||
ObjectNode fontNode = objectMapper.createObjectNode();
|
||||
|
||||
boolean isEmbedded = font.containsKey(PdfName.FontFile) ||
|
||||
font.containsKey(PdfName.FontFile2) ||
|
||||
font.containsKey(PdfName.FontFile3);
|
||||
fontNode.put("IsEmbedded", isEmbedded);
|
||||
fontNode.put("IsEmbedded", font.isEmbedded());
|
||||
|
||||
if (font.containsKey(PdfName.Encoding)) {
|
||||
String encoding = font.getAsName(PdfName.Encoding).toString();
|
||||
fontNode.put("Encoding", encoding);
|
||||
}
|
||||
// PDFBox provides Font's BaseFont (i.e., the font name) directly
|
||||
fontNode.put("Name", font.getName());
|
||||
|
||||
if (font.getAsString(PdfName.BaseFont) != null) {
|
||||
fontNode.put("Name", font.getAsString(PdfName.BaseFont).toString());
|
||||
}
|
||||
fontNode.put("Subtype", font.getType());
|
||||
|
||||
String subtype = null;
|
||||
if (font.containsKey(PdfName.Subtype)) {
|
||||
subtype = font.getAsName(PdfName.Subtype).toString();
|
||||
uniqueSubtypes.add(subtype); // Add to set to ensure uniqueness
|
||||
}
|
||||
fontNode.put("Subtype", subtype);
|
||||
PDFontDescriptor fontDescriptor = font.getFontDescriptor();
|
||||
|
||||
PdfDictionary fontDescriptor = font.getAsDictionary(PdfName.FontDescriptor);
|
||||
if (fontDescriptor != null) {
|
||||
if (fontDescriptor.containsKey(PdfName.ItalicAngle)) {
|
||||
fontNode.put("ItalicAngle", fontDescriptor.getAsNumber(PdfName.ItalicAngle).floatValue());
|
||||
}
|
||||
if (fontDescriptor != null) {
|
||||
fontNode.put("ItalicAngle", fontDescriptor.getItalicAngle());
|
||||
int flags = fontDescriptor.getFlags();
|
||||
fontNode.put("IsItalic", (flags & 1) != 0);
|
||||
fontNode.put("IsBold", (flags & 64) != 0);
|
||||
fontNode.put("IsFixedPitch", (flags & 2) != 0);
|
||||
fontNode.put("IsSerif", (flags & 4) != 0);
|
||||
fontNode.put("IsSymbolic", (flags & 8) != 0);
|
||||
fontNode.put("IsScript", (flags & 16) != 0);
|
||||
fontNode.put("IsNonsymbolic", (flags & 32) != 0);
|
||||
|
||||
if (fontDescriptor.containsKey(PdfName.Flags)) {
|
||||
int flags = fontDescriptor.getAsNumber(PdfName.Flags).intValue();
|
||||
fontNode.put("IsItalic", (flags & 64) != 0);
|
||||
fontNode.put("IsBold", (flags & 1 << 16) != 0);
|
||||
fontNode.put("IsFixedPitch", (flags & 1) != 0);
|
||||
fontNode.put("IsSerif", (flags & 2) != 0);
|
||||
fontNode.put("IsSymbolic", (flags & 4) != 0);
|
||||
fontNode.put("IsScript", (flags & 8) != 0);
|
||||
fontNode.put("IsNonsymbolic", (flags & 16) != 0);
|
||||
}
|
||||
fontNode.put("FontFamily", fontDescriptor.getFontFamily());
|
||||
// Font stretch and BBox are not directly available in PDFBox's API, so these are omitted for simplicity
|
||||
fontNode.put("FontWeight", fontDescriptor.getFontWeight());
|
||||
}
|
||||
|
||||
if (fontDescriptor.containsKey(PdfName.FontFamily)) {
|
||||
String fontFamily = fontDescriptor.getAsString(PdfName.FontFamily).toString();
|
||||
fontNode.put("FontFamily", fontFamily);
|
||||
}
|
||||
|
||||
if (fontDescriptor.containsKey(PdfName.FontStretch)) {
|
||||
String fontStretch = fontDescriptor.getAsName(PdfName.FontStretch).toString();
|
||||
fontNode.put("FontStretch", fontStretch);
|
||||
}
|
||||
// Create a unique key for this font node based on its attributes
|
||||
String uniqueKey = fontNode.toString();
|
||||
|
||||
if (fontDescriptor.containsKey(PdfName.FontBBox)) {
|
||||
PdfArray bbox = fontDescriptor.getAsArray(PdfName.FontBBox);
|
||||
fontNode.put("FontBoundingBox", bbox.toString());
|
||||
}
|
||||
|
||||
if (fontDescriptor.containsKey(PdfName.FontWeight)) {
|
||||
float fontWeight = fontDescriptor.getAsNumber(PdfName.FontWeight).floatValue();
|
||||
fontNode.put("FontWeight", fontWeight);
|
||||
}
|
||||
}
|
||||
|
||||
if (font.containsKey(PdfName.ToUnicode)) {
|
||||
fontNode.put("HasToUnicodeMap", true);
|
||||
}
|
||||
|
||||
if (fontNode.size() > 0) {
|
||||
// Create a unique key for this font node based on its attributes
|
||||
String uniqueKey = fontNode.toString();
|
||||
|
||||
// Increment count if this font exists, or initialize it if new
|
||||
if (uniqueFontsMap.containsKey(uniqueKey)) {
|
||||
ObjectNode existingFontNode = uniqueFontsMap.get(uniqueKey);
|
||||
int count = existingFontNode.get("Count").asInt() + 1;
|
||||
existingFontNode.put("Count", count);
|
||||
} else {
|
||||
fontNode.put("Count", 1);
|
||||
uniqueFontsMap.put(uniqueKey, fontNode);
|
||||
}
|
||||
}
|
||||
// Increment count if this font exists, or initialize it if new
|
||||
if (uniqueFontsMap.containsKey(uniqueKey)) {
|
||||
ObjectNode existingFontNode = uniqueFontsMap.get(uniqueKey);
|
||||
int count = existingFontNode.get("Count").asInt() + 1;
|
||||
existingFontNode.put("Count", count);
|
||||
} else {
|
||||
fontNode.put("Count", 1);
|
||||
uniqueFontsMap.put(uniqueKey, fontNode);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -552,41 +555,49 @@ public class GetInfoOnPDF {
|
||||
|
||||
|
||||
|
||||
// Access resources dictionary
|
||||
PdfDictionary resourcesDict = itextDoc.getPage(pageNum).getResources().getPdfObject();
|
||||
|
||||
// Color Spaces & ICC Profiles
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
// Access resources dictionary
|
||||
ArrayNode colorSpacesArray = objectMapper.createArrayNode();
|
||||
PdfDictionary colorSpaces = resourcesDict.getAsDictionary(PdfName.ColorSpace);
|
||||
if (colorSpaces != null) {
|
||||
for (PdfName name : colorSpaces.keySet()) {
|
||||
PdfObject colorSpaceObject = colorSpaces.get(name);
|
||||
if (colorSpaceObject instanceof PdfArray) {
|
||||
PdfArray colorSpaceArray = (PdfArray) colorSpaceObject;
|
||||
if (colorSpaceArray.size() > 1 && colorSpaceArray.get(0) instanceof PdfName && PdfName.ICCBased.equals(colorSpaceArray.get(0))) {
|
||||
ObjectNode iccProfileNode = objectMapper.createObjectNode();
|
||||
PdfStream iccStream = (PdfStream) colorSpaceArray.get(1);
|
||||
byte[] iccData = iccStream.getBytes();
|
||||
// TODO: Further decode and analyze the ICC data if needed
|
||||
iccProfileNode.put("ICC Profile Length", iccData.length);
|
||||
colorSpacesArray.add(iccProfileNode);
|
||||
}
|
||||
}
|
||||
|
||||
Iterable<COSName> colorSpaceNames = resources.getColorSpaceNames();
|
||||
for (COSName name : colorSpaceNames) {
|
||||
PDColorSpace colorSpace = resources.getColorSpace(name);
|
||||
if (colorSpace instanceof PDICCBased) {
|
||||
PDICCBased iccBased = (PDICCBased) colorSpace;
|
||||
PDStream iccData = iccBased.getPDStream();
|
||||
byte[] iccBytes = iccData.toByteArray();
|
||||
|
||||
// TODO: Further decode and analyze the ICC data if needed
|
||||
ObjectNode iccProfileNode = objectMapper.createObjectNode();
|
||||
iccProfileNode.put("ICC Profile Length", iccBytes.length);
|
||||
colorSpacesArray.add(iccProfileNode);
|
||||
}
|
||||
}
|
||||
pageInfo.set("Color Spaces & ICC Profiles", colorSpacesArray);
|
||||
|
||||
|
||||
// Other XObjects
|
||||
Map<String, Integer> xObjectCountMap = new HashMap<>(); // To store the count for each type
|
||||
PdfDictionary xObjects = resourcesDict.getAsDictionary(PdfName.XObject);
|
||||
if (xObjects != null) {
|
||||
for (PdfName name : xObjects.keySet()) {
|
||||
PdfStream xObjectStream = xObjects.getAsStream(name);
|
||||
String xObjectType = xObjectStream.getAsName(PdfName.Subtype).toString();
|
||||
|
||||
// Increment the count for this type in the map
|
||||
xObjectCountMap.put(xObjectType, xObjectCountMap.getOrDefault(xObjectType, 0) + 1);
|
||||
for (COSName name : resources.getXObjectNames()) {
|
||||
PDXObject xObject = resources.getXObject(name);
|
||||
String xObjectType;
|
||||
|
||||
if (xObject instanceof PDImageXObject) {
|
||||
xObjectType = "Image";
|
||||
} else if (xObject instanceof PDFormXObject) {
|
||||
xObjectType = "Form";
|
||||
} else {
|
||||
xObjectType = "Other";
|
||||
}
|
||||
|
||||
// Increment the count for this type in the map
|
||||
xObjectCountMap.put(xObjectType, xObjectCountMap.getOrDefault(xObjectType, 0) + 1);
|
||||
}
|
||||
|
||||
// Add the count map to pageInfo (or wherever you want to store it)
|
||||
@@ -598,19 +609,22 @@ public class GetInfoOnPDF {
|
||||
|
||||
|
||||
|
||||
|
||||
ArrayNode multimediaArray = objectMapper.createArrayNode();
|
||||
for (PdfAnnotation annotation : annotations) {
|
||||
if (PdfName.RichMedia.equals(annotation.getSubtype())) {
|
||||
|
||||
for (PDAnnotation annotation : annotations) {
|
||||
if ("RichMedia".equals(annotation.getSubtype())) {
|
||||
ObjectNode multimediaNode = objectMapper.createObjectNode();
|
||||
// Extract details from the dictionary as needed
|
||||
// Extract details from the annotation as needed
|
||||
multimediaArray.add(multimediaNode);
|
||||
}
|
||||
}
|
||||
|
||||
pageInfo.set("Multimedia", multimediaArray);
|
||||
|
||||
|
||||
|
||||
pageInfoParent.set("Page " + pageNum, pageInfo);
|
||||
pageInfoParent.set("Page " + (pageNum+1), pageInfo);
|
||||
}
|
||||
|
||||
|
||||
@@ -636,17 +650,21 @@ public class GetInfoOnPDF {
|
||||
return null;
|
||||
}
|
||||
|
||||
private static void addOutlinesToArray(PdfOutline outline, ArrayNode arrayNode) {
|
||||
private static void addOutlinesToArray(PDOutlineItem outline, ArrayNode arrayNode) {
|
||||
if (outline == null) return;
|
||||
|
||||
ObjectNode outlineNode = objectMapper.createObjectNode();
|
||||
outlineNode.put("Title", outline.getTitle());
|
||||
// You can add other properties if needed
|
||||
arrayNode.add(outlineNode);
|
||||
|
||||
for (PdfOutline child : outline.getAllChildren()) {
|
||||
|
||||
PDOutlineItem child = outline.getFirstChild();
|
||||
while (child != null) {
|
||||
addOutlinesToArray(child, arrayNode);
|
||||
child = child.getNextSibling();
|
||||
}
|
||||
}
|
||||
|
||||
public String getPageOrientation(double width, double height) {
|
||||
if (width > height) {
|
||||
return "Landscape";
|
||||
@@ -656,66 +674,78 @@ public class GetInfoOnPDF {
|
||||
return "Square";
|
||||
}
|
||||
}
|
||||
public String getPageSize(double width, double height) {
|
||||
// Common aspect ratios used for standard paper sizes
|
||||
double[] aspectRatios = {4.0 / 3.0, 3.0 / 2.0, Math.sqrt(2.0), 16.0 / 9.0};
|
||||
public String getPageSize(float width, float height) {
|
||||
// Define standard page sizes
|
||||
Map<String, PDRectangle> standardSizes = new HashMap<>();
|
||||
standardSizes.put("Letter", PDRectangle.LETTER);
|
||||
standardSizes.put("LEGAL", PDRectangle.LEGAL);
|
||||
standardSizes.put("A0", PDRectangle.A0);
|
||||
standardSizes.put("A1", PDRectangle.A1);
|
||||
standardSizes.put("A2", PDRectangle.A2);
|
||||
standardSizes.put("A3", PDRectangle.A3);
|
||||
standardSizes.put("A4", PDRectangle.A4);
|
||||
standardSizes.put("A5", PDRectangle.A5);
|
||||
standardSizes.put("A6", PDRectangle.A6);
|
||||
|
||||
// Check if the page matches any common aspect ratio
|
||||
for (double aspectRatio : aspectRatios) {
|
||||
if (isCloseToAspectRatio(width, height, aspectRatio)) {
|
||||
return "Standard";
|
||||
for (Map.Entry<String, PDRectangle> entry : standardSizes.entrySet()) {
|
||||
PDRectangle size = entry.getValue();
|
||||
if (isCloseToSize(width, height, size.getWidth(), size.getHeight())) {
|
||||
return entry.getKey();
|
||||
}
|
||||
}
|
||||
|
||||
// If not a standard aspect ratio, consider it as a custom size
|
||||
return "Custom";
|
||||
}
|
||||
private boolean isCloseToAspectRatio(double width, double height, double aspectRatio) {
|
||||
// Calculate the aspect ratio of the page
|
||||
double pageAspectRatio = width / height;
|
||||
|
||||
// Compare the page aspect ratio with the common aspect ratio within a threshold
|
||||
return Math.abs(pageAspectRatio - aspectRatio) <= 0.05;
|
||||
private boolean isCloseToSize(float width, float height, float standardWidth, float standardHeight) {
|
||||
float tolerance = 1.0f; // You can adjust the tolerance as needed
|
||||
return Math.abs(width - standardWidth) <= tolerance && Math.abs(height - standardHeight) <= tolerance;
|
||||
}
|
||||
|
||||
|
||||
public ObjectNode getDimensionInfo(ObjectNode dimensionInfo, float width, float height) {
|
||||
float ppi = 72; // Points Per Inch
|
||||
|
||||
float widthInInches = width / ppi;
|
||||
float heightInInches = height / ppi;
|
||||
|
||||
float widthInCm = widthInInches * 2.54f;
|
||||
float heightInCm = heightInInches * 2.54f;
|
||||
|
||||
dimensionInfo.put("Width (px)", String.format("%.2f", width));
|
||||
dimensionInfo.put("Height (px)", String.format("%.2f", height));
|
||||
dimensionInfo.put("Width (in)", String.format("%.2f", widthInInches));
|
||||
dimensionInfo.put("Height (in)", String.format("%.2f", heightInInches));
|
||||
dimensionInfo.put("Width (cm)", String.format("%.2f", widthInCm));
|
||||
dimensionInfo.put("Height (cm)", String.format("%.2f", heightInCm));
|
||||
return dimensionInfo;
|
||||
}
|
||||
|
||||
|
||||
|
||||
public static boolean checkForStandard(PDDocument document, String standardKeyword) {
|
||||
// Check XMP Metadata
|
||||
try {
|
||||
PDMetadata pdMetadata = document.getDocumentCatalog().getMetadata();
|
||||
if (pdMetadata != null) {
|
||||
COSInputStream metaStream = pdMetadata.createInputStream();
|
||||
DomXmpParser domXmpParser = new DomXmpParser();
|
||||
XMPMetadata xmpMeta = domXmpParser.parse(metaStream);
|
||||
|
||||
ByteArrayOutputStream baos = new ByteArrayOutputStream();
|
||||
new XmpSerializer().serialize(xmpMeta, baos, true);
|
||||
String xmpString = new String(baos.toByteArray(), StandardCharsets.UTF_8);
|
||||
|
||||
if (xmpString.contains(standardKeyword)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
} catch (Exception e) { // Catching general exception for brevity, ideally you'd catch specific exceptions.
|
||||
e.printStackTrace();
|
||||
}
|
||||
|
||||
public boolean checkForStandard(PdfDocument document, String standardKeyword) {
|
||||
// Check Output Intents
|
||||
boolean foundInOutputIntents = checkOutputIntent(document, standardKeyword);
|
||||
if (foundInOutputIntents) return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
// Check XMP Metadata (rudimentary)
|
||||
try {
|
||||
byte[] metadataBytes = document.getXmpMetadata();
|
||||
if (metadataBytes != null) {
|
||||
XMPMeta xmpMeta = XMPMetaFactory.parseFromBuffer(metadataBytes);
|
||||
String xmpString = xmpMeta.dumpObject();
|
||||
if (xmpString.contains(standardKeyword)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
} catch (XMPException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
public boolean checkOutputIntent(PdfDocument document, String standard) {
|
||||
PdfArray outputIntents = document.getCatalog().getPdfObject().getAsArray(PdfName.OutputIntents);
|
||||
if (outputIntents != null && !outputIntents.isEmpty()) {
|
||||
for (int i = 0; i < outputIntents.size(); i++) {
|
||||
PdfDictionary outputIntentDict = outputIntents.getAsDictionary(i);
|
||||
if (outputIntentDict != null) {
|
||||
PdfString s = outputIntentDict.getAsString(PdfName.S);
|
||||
if (s != null && s.toString().contains(standard)) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
public ArrayNode exploreStructureTree(List<Object> nodes) {
|
||||
ArrayNode elementsArray = objectMapper.createArrayNode();
|
||||
@@ -771,7 +801,7 @@ public class GetInfoOnPDF {
|
||||
}
|
||||
}
|
||||
|
||||
private String getPageModeDescription(PdfName pageMode) {
|
||||
private String getPageModeDescription(String pageMode) {
|
||||
return pageMode != null ? pageMode.toString().replaceFirst("/", "") : "Unknown";
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,18 +8,19 @@ import org.apache.pdfbox.pdmodel.encryption.StandardProtectionPolicy;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.security.AddPasswordRequest;
|
||||
import stirling.software.SPDF.model.api.security.PDFPasswordRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class PasswordController {
|
||||
|
||||
@@ -31,13 +32,12 @@ public class PasswordController {
|
||||
summary = "Remove password from a PDF file",
|
||||
description = "This endpoint removes the password from a protected PDF file. Users need to provide the existing password. Input:PDF Output:PDF Type:SISO"
|
||||
)
|
||||
public ResponseEntity<byte[]> removePassword(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file from which the password should be removed", required = true)
|
||||
MultipartFile fileInput,
|
||||
@RequestParam(name = "password")
|
||||
@Parameter(description = "The password of the PDF file", required = true)
|
||||
String password) throws IOException {
|
||||
public ResponseEntity<byte[]> removePassword(@ModelAttribute PDFPasswordRequest request) throws IOException {
|
||||
MultipartFile fileInput = request.getFileInput();
|
||||
String password = request.getPassword();
|
||||
|
||||
|
||||
|
||||
PDDocument document = PDDocument.load(fileInput.getBytes(), password);
|
||||
document.setAllSecurityToBeRemoved(true);
|
||||
return WebResponseUtils.pdfDocToWebResponse(document, fileInput.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_password_removed.pdf");
|
||||
@@ -48,44 +48,19 @@ public class PasswordController {
|
||||
summary = "Add password to a PDF file",
|
||||
description = "This endpoint adds password protection to a PDF file. Users can specify a set of permissions that should be applied to the file. Input:PDF Output:PDF"
|
||||
)
|
||||
public ResponseEntity<byte[]> addPassword(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to which the password should be added", required = true)
|
||||
MultipartFile fileInput,
|
||||
@RequestParam(value = "", name = "ownerPassword", required = false, defaultValue = "")
|
||||
@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( name = "password", required = false, defaultValue = "")
|
||||
@Parameter(description = "The password to be added to the PDF file (Restricts the opening of the document itself.)")
|
||||
String password,
|
||||
@RequestParam( name = "keyLength", required = false, defaultValue = "256")
|
||||
@Parameter(description = "The length of the encryption key", schema = @Schema(allowableValues = {"40", "128", "256"}))
|
||||
int keyLength,
|
||||
@RequestParam( name = "canAssembleDocument", required = false)
|
||||
@Parameter(description = "Whether the document assembly is allowed", example = "false")
|
||||
boolean canAssembleDocument,
|
||||
@RequestParam( name = "canExtractContent", required = false)
|
||||
@Parameter(description = "Whether content extraction for accessibility is allowed", example = "false")
|
||||
boolean canExtractContent,
|
||||
@RequestParam( name = "canExtractForAccessibility", required = false)
|
||||
@Parameter(description = "Whether content extraction for accessibility is allowed", example = "false")
|
||||
boolean canExtractForAccessibility,
|
||||
@RequestParam( name = "canFillInForm", required = false)
|
||||
@Parameter(description = "Whether form filling is allowed", example = "false")
|
||||
boolean canFillInForm,
|
||||
@RequestParam( name = "canModify", required = false)
|
||||
@Parameter(description = "Whether the document modification is allowed", example = "false")
|
||||
boolean canModify,
|
||||
@RequestParam( name = "canModifyAnnotations", required = false)
|
||||
@Parameter(description = "Whether modification of annotations is allowed", example = "false")
|
||||
boolean canModifyAnnotations,
|
||||
@RequestParam(name = "canPrint", required = false)
|
||||
@Parameter(description = "Whether printing of the document is allowed", example = "false")
|
||||
boolean canPrint,
|
||||
@RequestParam( name = "canPrintFaithful", required = false)
|
||||
@Parameter(description = "Whether faithful printing is allowed", example = "false")
|
||||
boolean canPrintFaithful
|
||||
) throws IOException {
|
||||
public ResponseEntity<byte[]> addPassword(@ModelAttribute AddPasswordRequest request) throws IOException {
|
||||
MultipartFile fileInput = request.getFileInput();
|
||||
String ownerPassword = request.getOwnerPassword();
|
||||
String password = request.getPassword();
|
||||
int keyLength = request.getKeyLength();
|
||||
boolean canAssembleDocument = request.isCanAssembleDocument();
|
||||
boolean canExtractContent = request.isCanExtractContent();
|
||||
boolean canExtractForAccessibility = request.isCanExtractForAccessibility();
|
||||
boolean canFillInForm = request.isCanFillInForm();
|
||||
boolean canModify = request.isCanModify();
|
||||
boolean canModifyAnnotations = request.isCanModifyAnnotations();
|
||||
boolean canPrint = request.isCanPrint();
|
||||
boolean canPrintFaithful = request.isCanPrintFaithful();
|
||||
|
||||
PDDocument document = PDDocument.load(fileInput.getBytes());
|
||||
AccessPermission ap = new AccessPermission();
|
||||
|
||||
@@ -18,19 +18,20 @@ import org.apache.pdfbox.rendering.PDFRenderer;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
import org.springframework.web.bind.annotation.PostMapping;
|
||||
import org.springframework.web.bind.annotation.RequestParam;
|
||||
import org.springframework.web.bind.annotation.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.PDFText;
|
||||
import stirling.software.SPDF.model.api.security.RedactPdfRequest;
|
||||
import stirling.software.SPDF.pdf.TextFinder;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class RedactController {
|
||||
|
||||
@@ -40,14 +41,14 @@ public class RedactController {
|
||||
@PostMapping(value = "/auto-redact", consumes = "multipart/form-data")
|
||||
@Operation(summary = "Redacts listOfText in a PDF document",
|
||||
description = "This operation takes an input PDF file and redacts the provided listOfText. Input:PDF, Output:PDF, Type:SISO")
|
||||
public ResponseEntity<byte[]> redactPdf(
|
||||
@Parameter(description = "The input PDF file", required = true) @RequestParam("fileInput") MultipartFile file,
|
||||
@Parameter(description = "List of listOfText to redact from the PDF", required = true, schema = @Schema(type = "string")) @RequestParam("listOfText") String listOfTextString,
|
||||
@RequestParam(value = "useRegex", required = false) boolean useRegex,
|
||||
@RequestParam(value = "wholeWordSearch", required = false) boolean wholeWordSearchBool,
|
||||
@RequestParam(value = "redactColor", required = false, defaultValue = "#000000") String colorString,
|
||||
@RequestParam(value = "customPadding", required = false) float customPadding,
|
||||
@RequestParam(value = "convertPDFToImage", required = false) boolean convertPDFToImage) throws Exception {
|
||||
public ResponseEntity<byte[]> redactPdf(@ModelAttribute RedactPdfRequest request) throws Exception {
|
||||
MultipartFile file = request.getFileInput();
|
||||
String listOfTextString = request.getListOfText();
|
||||
boolean useRegex = request.isUseRegex();
|
||||
boolean wholeWordSearchBool = request.isWholeWordSearch();
|
||||
String colorString = request.getRedactColor();
|
||||
float customPadding = request.getCustomPadding();
|
||||
boolean convertPDFToImage = request.isConvertPDFToImage();
|
||||
|
||||
System.out.println(listOfTextString);
|
||||
String[] listOfText = listOfTextString.split("\n");
|
||||
|
||||
@@ -20,41 +20,32 @@ 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.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
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.model.api.security.SanitizePdfRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class SanitizeController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/sanitize-pdf")
|
||||
@Operation(summary = "Sanitize a PDF file",
|
||||
description = "This endpoint processes a PDF file and removes specific elements based on the provided options. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> sanitizePDF(
|
||||
@RequestPart(required = true, value = "fileInput")
|
||||
@Parameter(description = "The input PDF file to be sanitized")
|
||||
MultipartFile inputFile,
|
||||
@RequestParam(name = "removeJavaScript", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Remove JavaScript actions from the PDF if set to true")
|
||||
Boolean removeJavaScript,
|
||||
@RequestParam(name = "removeEmbeddedFiles", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Remove embedded files from the PDF if set to true")
|
||||
Boolean removeEmbeddedFiles,
|
||||
@RequestParam(name = "removeMetadata", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Remove metadata from the PDF if set to true")
|
||||
Boolean removeMetadata,
|
||||
@RequestParam(name = "removeLinks", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Remove links from the PDF if set to true")
|
||||
Boolean removeLinks,
|
||||
@RequestParam(name = "removeFonts", required = false, defaultValue = "false")
|
||||
@Parameter(description = "Remove fonts from the PDF if set to true")
|
||||
Boolean removeFonts) throws IOException {
|
||||
public ResponseEntity<byte[]> sanitizePDF(@ModelAttribute SanitizePdfRequest request) throws IOException {
|
||||
MultipartFile inputFile = request.getFileInput();
|
||||
boolean removeJavaScript = request.isRemoveJavaScript();
|
||||
boolean removeEmbeddedFiles = request.isRemoveEmbeddedFiles();
|
||||
boolean removeMetadata = request.isRemoveMetadata();
|
||||
boolean removeLinks = request.isRemoveLinks();
|
||||
boolean removeFonts = request.isRemoveFonts();
|
||||
|
||||
try (PDDocument document = PDDocument.load(inputFile.getInputStream())) {
|
||||
if (removeJavaScript) {
|
||||
|
||||
@@ -22,40 +22,35 @@ import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;
|
||||
import org.apache.pdfbox.util.Matrix;
|
||||
import org.springframework.core.io.ClassPathResource;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.ModelAttribute;
|
||||
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.RequestMapping;
|
||||
import org.springframework.web.bind.annotation.RestController;
|
||||
import org.springframework.web.multipart.MultipartFile;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Operation;
|
||||
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.model.api.security.AddWatermarkRequest;
|
||||
import stirling.software.SPDF.utils.WebResponseUtils;
|
||||
|
||||
@RestController
|
||||
@RequestMapping("/api/v1/security")
|
||||
@Tag(name = "Security", description = "Security APIs")
|
||||
public class WatermarkController {
|
||||
|
||||
@PostMapping(consumes = "multipart/form-data", value = "/add-watermark")
|
||||
@Operation(summary = "Add watermark to a PDF file", description = "This endpoint adds a watermark to a given PDF file. Users can specify the watermark type (text or image), rotation, opacity, width spacer, and height spacer. Input:PDF Output:PDF Type:SISO")
|
||||
public ResponseEntity<byte[]> addWatermark(
|
||||
@RequestPart(required = true, value = "fileInput") @Parameter(description = "The input PDF file to add a watermark") MultipartFile pdfFile,
|
||||
@RequestParam(required = true) @Parameter(description = "The watermark type (text or image)") String watermarkType,
|
||||
@RequestParam(required = false) @Parameter(description = "The watermark text") String watermarkText,
|
||||
@RequestPart(required = false) @Parameter(description = "The watermark image") MultipartFile watermarkImage,
|
||||
|
||||
@RequestParam(defaultValue = "roman", name = "alphabet") @Parameter(description = "The selected alphabet",
|
||||
schema = @Schema(type = "string",
|
||||
allowableValues = {"roman","arabic","japanese","korean","chinese"},
|
||||
defaultValue = "roman")) String alphabet,
|
||||
@RequestParam(defaultValue = "30", name = "fontSize") @Parameter(description = "The font size of the watermark text", example = "30") float fontSize,
|
||||
@RequestParam(defaultValue = "0", name = "rotation") @Parameter(description = "The rotation of the watermark in degrees", example = "0") float rotation,
|
||||
@RequestParam(defaultValue = "0.5", name = "opacity") @Parameter(description = "The opacity of the watermark (0.0 - 1.0)", example = "0.5") float opacity,
|
||||
@RequestParam(defaultValue = "50", name = "widthSpacer") @Parameter(description = "The width spacer between watermark elements", example = "50") int widthSpacer,
|
||||
@RequestParam(defaultValue = "50", name = "heightSpacer") @Parameter(description = "The height spacer between watermark elements", example = "50") int heightSpacer)
|
||||
throws IOException, Exception {
|
||||
public ResponseEntity<byte[]> addWatermark(@ModelAttribute AddWatermarkRequest request) throws IOException, Exception {
|
||||
MultipartFile pdfFile = request.getFileInput();
|
||||
String watermarkType = request.getWatermarkType();
|
||||
String watermarkText = request.getWatermarkText();
|
||||
MultipartFile watermarkImage = request.getWatermarkImage();
|
||||
String alphabet = request.getAlphabet();
|
||||
float fontSize = request.getFontSize();
|
||||
float rotation = request.getRotation();
|
||||
float opacity = request.getOpacity();
|
||||
int widthSpacer = request.getWidthSpacer();
|
||||
int heightSpacer = request.getHeightSpacer();
|
||||
|
||||
// Load the input PDF
|
||||
PDDocument document = PDDocument.load(pdfFile.getInputStream());
|
||||
|
||||
@@ -0,0 +1,358 @@
|
||||
package stirling.software.SPDF.controller.api.strippers;
|
||||
|
||||
import java.awt.Shape;
|
||||
import java.awt.geom.AffineTransform;
|
||||
import java.awt.geom.Rectangle2D;
|
||||
import java.io.ByteArrayOutputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.OutputStreamWriter;
|
||||
import java.io.Writer;
|
||||
import java.util.ArrayList;
|
||||
import java.util.HashSet;
|
||||
import java.util.Iterator;
|
||||
import java.util.LinkedList;
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
|
||||
import org.apache.fontbox.util.BoundingBox;
|
||||
import org.apache.pdfbox.pdmodel.PDPage;
|
||||
import org.apache.pdfbox.pdmodel.common.PDRectangle;
|
||||
import org.apache.pdfbox.pdmodel.font.PDFont;
|
||||
import org.apache.pdfbox.pdmodel.font.PDType3Font;
|
||||
import org.apache.pdfbox.text.PDFTextStripper;
|
||||
import org.apache.pdfbox.text.PDFTextStripperByArea;
|
||||
import org.apache.pdfbox.text.TextPosition;
|
||||
|
||||
/**
|
||||
*
|
||||
* Class to extract tabular data from a PDF.
|
||||
* Works by making a first pass of the page to group all nearby text items
|
||||
* together, and then inferring a 2D grid from these regions. Each table cell
|
||||
* is then extracted using a PDFTextStripperByArea object.
|
||||
*
|
||||
* Works best when
|
||||
* headers are included in the detected region, to ensure representative text
|
||||
* in every column.
|
||||
*
|
||||
* Based upon DrawPrintTextLocations PDFBox example
|
||||
* (https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/util/DrawPrintTextLocations.java)
|
||||
*
|
||||
* @author Beldaz
|
||||
*/
|
||||
public class PDFTableStripper extends PDFTextStripper
|
||||
{
|
||||
|
||||
/**
|
||||
* This will print the documents data, for each table cell.
|
||||
*
|
||||
* @param args The command line arguments.
|
||||
*
|
||||
* @throws IOException If there is an error parsing the document.
|
||||
*/
|
||||
/*
|
||||
* Used in methods derived from DrawPrintTextLocations
|
||||
*/
|
||||
private AffineTransform flipAT;
|
||||
private AffineTransform rotateAT;
|
||||
|
||||
/**
|
||||
* Regions updated by calls to writeString
|
||||
*/
|
||||
private Set<Rectangle2D> boxes;
|
||||
|
||||
// Border to allow when finding intersections
|
||||
private double dx = 1.0; // This value works for me, feel free to tweak (or add setter)
|
||||
private double dy = 0.000; // Rows of text tend to overlap, so need to extend
|
||||
|
||||
/**
|
||||
* Region in which to find table (otherwise whole page)
|
||||
*/
|
||||
private Rectangle2D regionArea;
|
||||
|
||||
/**
|
||||
* Number of rows in inferred table
|
||||
*/
|
||||
private int nRows=0;
|
||||
|
||||
/**
|
||||
* Number of columns in inferred table
|
||||
*/
|
||||
private int nCols=0;
|
||||
|
||||
/**
|
||||
* This is the object that does the text extraction
|
||||
*/
|
||||
private PDFTextStripperByArea regionStripper;
|
||||
|
||||
/**
|
||||
* 1D intervals - used for calculateTableRegions()
|
||||
* @author Beldaz
|
||||
*
|
||||
*/
|
||||
public static class Interval {
|
||||
double start;
|
||||
double end;
|
||||
public Interval(double start, double end) {
|
||||
this.start=start; this.end = end;
|
||||
}
|
||||
public void add(Interval col) {
|
||||
if(col.start<start)
|
||||
start = col.start;
|
||||
if(col.end>end)
|
||||
end = col.end;
|
||||
}
|
||||
public static void addTo(Interval x, LinkedList<Interval> columns) {
|
||||
int p = 0;
|
||||
Iterator<Interval> it = columns.iterator();
|
||||
// Find where x should go
|
||||
while(it.hasNext()) {
|
||||
Interval col = it.next();
|
||||
if(x.end>=col.start) {
|
||||
if(x.start<=col.end) { // overlaps
|
||||
x.add(col);
|
||||
it.remove();
|
||||
}
|
||||
break;
|
||||
}
|
||||
++p;
|
||||
}
|
||||
while(it.hasNext()) {
|
||||
Interval col = it.next();
|
||||
if(x.start>col.end)
|
||||
break;
|
||||
x.add(col);
|
||||
it.remove();
|
||||
}
|
||||
columns.add(p, x);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Instantiate a new PDFTableStripper object.
|
||||
*
|
||||
* @param document
|
||||
* @throws IOException If there is an error loading the properties.
|
||||
*/
|
||||
public PDFTableStripper() throws IOException
|
||||
{
|
||||
super.setShouldSeparateByBeads(false);
|
||||
regionStripper = new PDFTextStripperByArea();
|
||||
regionStripper.setSortByPosition( true );
|
||||
}
|
||||
|
||||
/**
|
||||
* Define the region to group text by.
|
||||
*
|
||||
* @param rect The rectangle area to retrieve the text from.
|
||||
*/
|
||||
public void setRegion(Rectangle2D rect )
|
||||
{
|
||||
regionArea = rect;
|
||||
}
|
||||
|
||||
public int getRows()
|
||||
{
|
||||
return nRows;
|
||||
}
|
||||
|
||||
public int getColumns()
|
||||
{
|
||||
return nCols;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the text for the region, this should be called after extractTable().
|
||||
*
|
||||
* @return The text that was identified in that region.
|
||||
*/
|
||||
public String getText(int row, int col)
|
||||
{
|
||||
return regionStripper.getTextForRegion("el"+col+"x"+row);
|
||||
}
|
||||
|
||||
public void extractTable(PDPage pdPage) throws IOException
|
||||
{
|
||||
setStartPage(getCurrentPageNo());
|
||||
setEndPage(getCurrentPageNo());
|
||||
|
||||
boxes = new HashSet<Rectangle2D>();
|
||||
// flip y-axis
|
||||
flipAT = new AffineTransform();
|
||||
flipAT.translate(0, pdPage.getBBox().getHeight());
|
||||
flipAT.scale(1, -1);
|
||||
|
||||
// page may be rotated
|
||||
rotateAT = new AffineTransform();
|
||||
int rotation = pdPage.getRotation();
|
||||
if (rotation != 0)
|
||||
{
|
||||
PDRectangle mediaBox = pdPage.getMediaBox();
|
||||
switch (rotation)
|
||||
{
|
||||
case 90:
|
||||
rotateAT.translate(mediaBox.getHeight(), 0);
|
||||
break;
|
||||
case 270:
|
||||
rotateAT.translate(0, mediaBox.getWidth());
|
||||
break;
|
||||
case 180:
|
||||
rotateAT.translate(mediaBox.getWidth(), mediaBox.getHeight());
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
rotateAT.rotate(Math.toRadians(rotation));
|
||||
}
|
||||
// Trigger processing of the document so that writeString is called.
|
||||
try (Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream())) {
|
||||
super.output = dummy;
|
||||
super.processPage(pdPage);
|
||||
}
|
||||
|
||||
Rectangle2D[][] regions = calculateTableRegions();
|
||||
|
||||
// System.err.println("Drawing " + nCols + "x" + nRows + "="+ nRows*nCols + " regions");
|
||||
for(int i=0; i<nCols; ++i) {
|
||||
for(int j=0; j<nRows; ++j) {
|
||||
final Rectangle2D region = regions[i][j];
|
||||
regionStripper.addRegion("el"+i+"x"+j, region);
|
||||
}
|
||||
}
|
||||
|
||||
regionStripper.extractRegions(pdPage);
|
||||
}
|
||||
|
||||
/**
|
||||
* Infer a rectangular grid of regions from the boxes field.
|
||||
*
|
||||
* @return 2D array of table regions (as Rectangle2D objects). Note that
|
||||
* some of these regions may have no content.
|
||||
*/
|
||||
private Rectangle2D[][] calculateTableRegions() {
|
||||
|
||||
// Build up a list of all table regions, based upon the populated
|
||||
// regions of boxes field. Treats the horizontal and vertical extents
|
||||
// of each box as distinct
|
||||
LinkedList<Interval> columns = new LinkedList<Interval>();
|
||||
LinkedList<Interval> rows = new LinkedList<Interval>();
|
||||
|
||||
for(Rectangle2D box: boxes) {
|
||||
Interval x = new Interval(box.getMinX(), box.getMaxX());
|
||||
Interval y = new Interval(box.getMinY(), box.getMaxY());
|
||||
|
||||
Interval.addTo(x, columns);
|
||||
Interval.addTo(y, rows);
|
||||
}
|
||||
|
||||
nRows = rows.size();
|
||||
nCols = columns.size();
|
||||
Rectangle2D[][] regions = new Rectangle2D[nCols][nRows];
|
||||
int i=0;
|
||||
// Label regions from top left, rather than the transformed orientation
|
||||
for(Interval column: columns) {
|
||||
int j=0;
|
||||
for(Interval row: rows) {
|
||||
regions[nCols-i-1][nRows-j-1] = new Rectangle2D.Double(column.start, row.start, column.end - column.start, row.end - row.start);
|
||||
++j;
|
||||
}
|
||||
++i;
|
||||
}
|
||||
|
||||
return regions;
|
||||
}
|
||||
|
||||
/**
|
||||
* Register each character's bounding box, updating boxes field to maintain
|
||||
* a list of all distinct groups of characters.
|
||||
*
|
||||
* Overrides the default functionality of PDFTextStripper.
|
||||
* Most of this is taken from DrawPrintTextLocations.java, with extra steps
|
||||
* at end of main loop
|
||||
*/
|
||||
@Override
|
||||
protected void writeString(String string, List<TextPosition> textPositions) throws IOException
|
||||
{
|
||||
for (TextPosition text : textPositions)
|
||||
{
|
||||
// glyph space -> user space
|
||||
// note: text.getTextMatrix() is *not* the Text Matrix, it's the Text Rendering Matrix
|
||||
AffineTransform at = text.getTextMatrix().createAffineTransform();
|
||||
PDFont font = text.getFont();
|
||||
BoundingBox bbox = font.getBoundingBox();
|
||||
|
||||
// advance width, bbox height (glyph space)
|
||||
float xadvance = font.getWidth(text.getCharacterCodes()[0]); // todo: should iterate all chars
|
||||
Rectangle2D.Float rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), xadvance, bbox.getHeight());
|
||||
|
||||
if (font instanceof PDType3Font)
|
||||
{
|
||||
// bbox and font matrix are unscaled
|
||||
at.concatenate(font.getFontMatrix().createAffineTransform());
|
||||
}
|
||||
else
|
||||
{
|
||||
// bbox and font matrix are already scaled to 1000
|
||||
at.scale(1/1000f, 1/1000f);
|
||||
}
|
||||
Shape s = at.createTransformedShape(rect);
|
||||
s = flipAT.createTransformedShape(s);
|
||||
s = rotateAT.createTransformedShape(s);
|
||||
|
||||
|
||||
//
|
||||
// Merge character's bounding box with boxes field
|
||||
//
|
||||
Rectangle2D bounds = s.getBounds2D();
|
||||
// Pad sides to detect almost touching boxes
|
||||
Rectangle2D hitbox = bounds.getBounds2D();
|
||||
hitbox.add(bounds.getMinX() - dx , bounds.getMinY() - dy);
|
||||
hitbox.add(bounds.getMaxX() + dx , bounds.getMaxY() + dy);
|
||||
|
||||
// Find all overlapping boxes
|
||||
List<Rectangle2D> intersectList = new ArrayList<Rectangle2D>();
|
||||
for(Rectangle2D box: boxes) {
|
||||
if(box.intersects(hitbox)) {
|
||||
intersectList.add(box);
|
||||
}
|
||||
}
|
||||
|
||||
// Combine all touching boxes and update
|
||||
// (NOTE: Potentially this could leave some overlapping boxes un-merged,
|
||||
// but it's sufficient for now and get's fixed up in calculateTableRegions)
|
||||
for(Rectangle2D box: intersectList) {
|
||||
bounds.add(box);
|
||||
boxes.remove(box);
|
||||
}
|
||||
boxes.add(bounds);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* This method does nothing in this derived class, because beads and regions are incompatible. Beads are
|
||||
* ignored when stripping by area.
|
||||
*
|
||||
* @param aShouldSeparateByBeads The new grouping of beads.
|
||||
*/
|
||||
@Override
|
||||
public final void setShouldSeparateByBeads(boolean aShouldSeparateByBeads)
|
||||
{
|
||||
}
|
||||
|
||||
/**
|
||||
* Adapted from PDFTextStripperByArea
|
||||
* {@inheritDoc}
|
||||
*/
|
||||
@Override
|
||||
protected void processTextPosition( TextPosition text )
|
||||
{
|
||||
if(regionArea!=null && !regionArea.contains( text.getX(), text.getY() ) ) {
|
||||
// skip character
|
||||
} else {
|
||||
super.processTextPosition( text );
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,22 +1,8 @@
|
||||
package stirling.software.SPDF.controller.web;
|
||||
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.Optional;
|
||||
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.security.access.prepost.PreAuthorize;
|
||||
import org.springframework.security.core.Authentication;
|
||||
import org.springframework.security.core.userdetails.UserDetails;
|
||||
@@ -27,10 +13,8 @@ import org.springframework.web.bind.annotation.GetMapping;
|
||||
import com.fasterxml.jackson.core.JsonProcessingException;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Hidden;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
import jakarta.servlet.http.HttpServletRequest;
|
||||
import stirling.software.SPDF.config.security.UserService;
|
||||
import stirling.software.SPDF.model.User;
|
||||
import stirling.software.SPDF.repository.UserRepository;
|
||||
@Controller
|
||||
@@ -107,6 +91,7 @@ public class AccountWebController {
|
||||
model.addAttribute("username", username);
|
||||
model.addAttribute("role", user.get().getRolesAsString());
|
||||
model.addAttribute("settings", settingsJson);
|
||||
model.addAttribute("changeCredsFlag", user.get().isFirstLogin());
|
||||
}
|
||||
} else {
|
||||
return "redirect:/";
|
||||
@@ -116,5 +101,35 @@ public class AccountWebController {
|
||||
|
||||
|
||||
|
||||
@GetMapping("/change-creds")
|
||||
public String changeCreds(HttpServletRequest request, Model model, Authentication authentication) {
|
||||
if (authentication == null || !authentication.isAuthenticated()) {
|
||||
return "redirect:/";
|
||||
}
|
||||
if (authentication != null && authentication.isAuthenticated()) {
|
||||
Object principal = authentication.getPrincipal();
|
||||
|
||||
if (principal instanceof UserDetails) {
|
||||
// Cast the principal object to UserDetails
|
||||
UserDetails userDetails = (UserDetails) principal;
|
||||
|
||||
// Retrieve username and other attributes
|
||||
String username = userDetails.getUsername();
|
||||
|
||||
// Fetch user details from the database
|
||||
Optional<User> user = userRepository.findByUsername(username); // Assuming findByUsername method exists
|
||||
if (!user.isPresent()) {
|
||||
// Handle error appropriately
|
||||
return "redirect:/error"; // Example redirection in case of error
|
||||
}
|
||||
// Add attributes to the model
|
||||
model.addAttribute("username", username);
|
||||
}
|
||||
} else {
|
||||
return "redirect:/";
|
||||
}
|
||||
return "change-creds";
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
@@ -99,6 +99,14 @@ public class ConverterWebController {
|
||||
return modelAndView;
|
||||
}
|
||||
|
||||
@GetMapping("/pdf-to-csv")
|
||||
@Hidden
|
||||
public ModelAndView pdfToCSV() {
|
||||
ModelAndView modelAndView = new ModelAndView("convert/pdf-to-csv");
|
||||
modelAndView.addObject("currentPage", "pdf-to-csv");
|
||||
return modelAndView;
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/pdf-to-pdfa")
|
||||
@Hidden
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
package stirling.software.SPDF.controller.web;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.nio.file.Files;
|
||||
@@ -9,6 +10,7 @@ import java.util.Arrays;
|
||||
import java.util.HashMap;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
import java.util.Objects;
|
||||
import java.util.stream.Collectors;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
@@ -20,6 +22,7 @@ import org.springframework.stereotype.Controller;
|
||||
import org.springframework.ui.Model;
|
||||
import org.springframework.web.bind.annotation.GetMapping;
|
||||
|
||||
import com.fasterxml.jackson.core.type.TypeReference;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import io.swagger.v3.oas.annotations.Hidden;
|
||||
@@ -50,7 +53,8 @@ public class GeneralWebController {
|
||||
}
|
||||
List<Map<String, String>> pipelineConfigsWithNames = new ArrayList<>();
|
||||
for (String config : pipelineConfigs) {
|
||||
Map<String, Object> jsonContent = new ObjectMapper().readValue(config, Map.class);
|
||||
Map<String, Object> jsonContent = new ObjectMapper().readValue(config, new TypeReference<Map<String, Object>>(){});
|
||||
|
||||
String name = (String) jsonContent.get("name");
|
||||
Map<String, String> configWithName = new HashMap<>();
|
||||
configWithName.put("json", config);
|
||||
@@ -78,6 +82,19 @@ public class GeneralWebController {
|
||||
return "merge-pdfs";
|
||||
}
|
||||
|
||||
@GetMapping("/split-pdf-by-sections")
|
||||
@Hidden
|
||||
public String splitPdfBySections(Model model) {
|
||||
model.addAttribute("currentPage", "split-pdf-by-sections");
|
||||
return "split-pdf-by-sections";
|
||||
}
|
||||
|
||||
@GetMapping("/view-pdf")
|
||||
@Hidden
|
||||
public String ViewPdfForm2(Model model) {
|
||||
model.addAttribute("currentPage", "view-pdf");
|
||||
return "view-pdf";
|
||||
}
|
||||
|
||||
@GetMapping("/multi-tool")
|
||||
@Hidden
|
||||
@@ -145,30 +162,132 @@ public class GeneralWebController {
|
||||
return "add-elements";
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/multi-page-layout")
|
||||
@Hidden
|
||||
public String multiPageLayoutForm(Model model) {
|
||||
model.addAttribute("currentPage", "multi-page-layout");
|
||||
return "multi-page-layout";
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/scale-pages")
|
||||
@Hidden
|
||||
public String scalePagesFrom(Model model) {
|
||||
model.addAttribute("currentPage", "scale-pages");
|
||||
return "scale-pages";
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/split-by-size-or-count")
|
||||
@Hidden
|
||||
public String splitBySizeOrCount(Model model) {
|
||||
model.addAttribute("currentPage", "split-by-size-or-count");
|
||||
return "split-by-size-or-count";
|
||||
}
|
||||
|
||||
@GetMapping("/overlay-pdf")
|
||||
@Hidden
|
||||
public String overlayPdf(Model model) {
|
||||
model.addAttribute("currentPage", "overlay-pdf");
|
||||
return "overlay-pdf";
|
||||
}
|
||||
|
||||
|
||||
|
||||
@Autowired
|
||||
private ResourceLoader resourceLoader;
|
||||
|
||||
private List<String> getFontNames() {
|
||||
private List<FontResource> getFontNames() {
|
||||
List<FontResource> fontNames = new ArrayList<>();
|
||||
|
||||
// Extract font names from classpath
|
||||
fontNames.addAll(getFontNamesFromLocation("classpath:static/fonts/*.woff2"));
|
||||
|
||||
// Extract font names from external directory
|
||||
fontNames.addAll(getFontNamesFromLocation("file:customFiles/static/fonts/*"));
|
||||
|
||||
return fontNames;
|
||||
}
|
||||
|
||||
private List<FontResource> getFontNamesFromLocation(String locationPattern) {
|
||||
try {
|
||||
Resource[] resources = ResourcePatternUtils.getResourcePatternResolver(resourceLoader)
|
||||
.getResources("classpath:static/fonts/*.woff2");
|
||||
|
||||
.getResources(locationPattern);
|
||||
return Arrays.stream(resources)
|
||||
.map(resource -> {
|
||||
try {
|
||||
String filename = resource.getFilename();
|
||||
return filename.substring(0, filename.length() - 6); // Remove .woff2 extension
|
||||
if (filename != null) {
|
||||
int lastDotIndex = filename.lastIndexOf('.');
|
||||
if (lastDotIndex != -1) {
|
||||
String name = filename.substring(0, lastDotIndex);
|
||||
String extension = filename.substring(lastDotIndex + 1);
|
||||
return new FontResource(name, extension);
|
||||
}
|
||||
}
|
||||
return null;
|
||||
} catch (Exception e) {
|
||||
throw new RuntimeException("Error processing filename", e);
|
||||
}
|
||||
})
|
||||
.filter(Objects::nonNull)
|
||||
.collect(Collectors.toList());
|
||||
} catch (Exception e) {
|
||||
throw new RuntimeException("Failed to read font directory", e);
|
||||
throw new RuntimeException("Failed to read font directory from " + locationPattern, e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public String getFormatFromExtension(String extension) {
|
||||
switch (extension) {
|
||||
case "ttf": return "truetype";
|
||||
case "woff": return "woff";
|
||||
case "woff2": return "woff2";
|
||||
case "eot": return "embedded-opentype";
|
||||
case "svg": return "svg";
|
||||
default: return ""; // or throw an exception if an unexpected extension is encountered
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public class FontResource {
|
||||
private String name;
|
||||
private String extension;
|
||||
private String type;
|
||||
public FontResource(String name, String extension) {
|
||||
this.name = name;
|
||||
this.extension = extension;
|
||||
this.type = getFormatFromExtension(extension);
|
||||
}
|
||||
|
||||
public String getName() {
|
||||
return name;
|
||||
}
|
||||
|
||||
public void setName(String name) {
|
||||
this.name = name;
|
||||
}
|
||||
|
||||
public String getExtension() {
|
||||
return extension;
|
||||
}
|
||||
|
||||
public void setExtension(String extension) {
|
||||
this.extension = extension;
|
||||
}
|
||||
|
||||
public String getType() {
|
||||
return type;
|
||||
}
|
||||
|
||||
public void setType(String type) {
|
||||
this.type = type;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/crop")
|
||||
@Hidden
|
||||
|
||||
@@ -15,19 +15,19 @@ import io.swagger.v3.oas.annotations.Hidden;
|
||||
import io.swagger.v3.oas.annotations.tags.Tag;
|
||||
|
||||
@Controller
|
||||
@Tag(name = "Other", description = "Other APIs")
|
||||
@Tag(name = "Misc", description = "Miscellaneous APIs")
|
||||
public class OtherWebController {
|
||||
@GetMapping("/compress-pdf")
|
||||
@Hidden
|
||||
public String compressPdfForm(Model model) {
|
||||
model.addAttribute("currentPage", "compress-pdf");
|
||||
return "other/compress-pdf";
|
||||
return "misc/compress-pdf";
|
||||
}
|
||||
|
||||
@GetMapping("/extract-image-scans")
|
||||
@Hidden
|
||||
public ModelAndView extractImageScansForm() {
|
||||
ModelAndView modelAndView = new ModelAndView("other/extract-image-scans");
|
||||
ModelAndView modelAndView = new ModelAndView("misc/extract-image-scans");
|
||||
modelAndView.addObject("currentPage", "extract-image-scans");
|
||||
return modelAndView;
|
||||
}
|
||||
@@ -36,7 +36,7 @@ public class OtherWebController {
|
||||
@Hidden
|
||||
public String extractJavascriptForm(Model model) {
|
||||
model.addAttribute("currentPage", "show-javascript");
|
||||
return "other/show-javascript";
|
||||
return "misc/show-javascript";
|
||||
}
|
||||
|
||||
|
||||
@@ -44,21 +44,21 @@ public class OtherWebController {
|
||||
@Hidden
|
||||
public String addPageNumbersForm(Model model) {
|
||||
model.addAttribute("currentPage", "add-page-numbers");
|
||||
return "other/add-page-numbers";
|
||||
return "misc/add-page-numbers";
|
||||
}
|
||||
|
||||
@GetMapping("/extract-images")
|
||||
@Hidden
|
||||
public String extractImagesForm(Model model) {
|
||||
model.addAttribute("currentPage", "extract-images");
|
||||
return "other/extract-images";
|
||||
return "misc/extract-images";
|
||||
}
|
||||
|
||||
@GetMapping("/flatten")
|
||||
@Hidden
|
||||
public String flattenForm(Model model) {
|
||||
model.addAttribute("currentPage", "flatten");
|
||||
return "other/flatten";
|
||||
return "misc/flatten";
|
||||
}
|
||||
|
||||
|
||||
@@ -67,18 +67,18 @@ public class OtherWebController {
|
||||
@Hidden
|
||||
public String addWatermarkForm(Model model) {
|
||||
model.addAttribute("currentPage", "change-metadata");
|
||||
return "other/change-metadata";
|
||||
return "misc/change-metadata";
|
||||
}
|
||||
|
||||
@GetMapping("/compare")
|
||||
@Hidden
|
||||
public String compareForm(Model model) {
|
||||
model.addAttribute("currentPage", "compare");
|
||||
return "other/compare";
|
||||
return "misc/compare";
|
||||
}
|
||||
|
||||
public List<String> getAvailableTesseractLanguages() {
|
||||
String tessdataDir = "/usr/share/tesseract-ocr/4.00/tessdata";
|
||||
String tessdataDir = "/usr/share/tesseract-ocr/5/tessdata";
|
||||
File[] files = new File(tessdataDir).listFiles();
|
||||
if (files == null) {
|
||||
return Collections.emptyList();
|
||||
@@ -90,7 +90,7 @@ public class OtherWebController {
|
||||
@GetMapping("/ocr-pdf")
|
||||
@Hidden
|
||||
public ModelAndView ocrPdfPage() {
|
||||
ModelAndView modelAndView = new ModelAndView("other/ocr-pdf");
|
||||
ModelAndView modelAndView = new ModelAndView("misc/ocr-pdf");
|
||||
List<String> languages = getAvailableTesseractLanguages();
|
||||
Collections.sort(languages);
|
||||
modelAndView.addObject("languages", languages);
|
||||
@@ -98,61 +98,54 @@ public class OtherWebController {
|
||||
return modelAndView;
|
||||
}
|
||||
|
||||
|
||||
|
||||
@GetMapping("/add-image")
|
||||
@Hidden
|
||||
public String overlayImage(Model model) {
|
||||
model.addAttribute("currentPage", "add-image");
|
||||
return "other/add-image";
|
||||
return "misc/add-image";
|
||||
}
|
||||
|
||||
@GetMapping("/adjust-contrast")
|
||||
@Hidden
|
||||
public String contrast(Model model) {
|
||||
model.addAttribute("currentPage", "adjust-contrast");
|
||||
return "other/adjust-contrast";
|
||||
return "misc/adjust-contrast";
|
||||
}
|
||||
|
||||
@GetMapping("/repair")
|
||||
@Hidden
|
||||
public String repairForm(Model model) {
|
||||
model.addAttribute("currentPage", "repair");
|
||||
return "other/repair";
|
||||
return "misc/repair";
|
||||
}
|
||||
|
||||
@GetMapping("/remove-blanks")
|
||||
@Hidden
|
||||
public String removeBlanksForm(Model model) {
|
||||
model.addAttribute("currentPage", "remove-blanks");
|
||||
return "other/remove-blanks";
|
||||
return "misc/remove-blanks";
|
||||
}
|
||||
|
||||
@GetMapping("/multi-page-layout")
|
||||
|
||||
@GetMapping("/remove-annotations")
|
||||
@Hidden
|
||||
public String multiPageLayoutForm(Model model) {
|
||||
model.addAttribute("currentPage", "multi-page-layout");
|
||||
return "other/multi-page-layout";
|
||||
public String removeAnnotationsForm(Model model) {
|
||||
model.addAttribute("currentPage", "remove-annotations");
|
||||
return "misc/remove-annotations";
|
||||
}
|
||||
|
||||
@GetMapping("/scale-pages")
|
||||
@Hidden
|
||||
public String scalePagesFrom(Model model) {
|
||||
model.addAttribute("currentPage", "scale-pages");
|
||||
return "other/scale-pages";
|
||||
}
|
||||
|
||||
|
||||
@GetMapping("/auto-crop")
|
||||
@Hidden
|
||||
public String autoCropForm(Model model) {
|
||||
model.addAttribute("currentPage", "auto-crop");
|
||||
return "other/auto-crop";
|
||||
return "misc/auto-crop";
|
||||
}
|
||||
|
||||
@GetMapping("/auto-rename")
|
||||
@Hidden
|
||||
public String autoRenameForm(Model model) {
|
||||
model.addAttribute("currentPage", "auto-rename");
|
||||
return "other/auto-rename";
|
||||
return "misc/auto-rename";
|
||||
}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user