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

filter

Browse Source
This commit is contained in:
Anthony Stirling
2023-07-16 00:36:58 +01:00
parent 9af1b0cfdc
commit 29aabdfba8
5 changed files with 302 additions and 249 deletions
Download Patch File Download Diff File Expand all files Collapse all files

220
src/main/java/stirling/software/SPDF/utils/GeneralUtils.java
View File

@@ -1,107 +1,113 @@
package stirling.software.SPDF.utils;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;
public class GeneralUtils {
public static Long convertSizeToBytes(String sizeStr) {
if (sizeStr == null) {
return null;
}
sizeStr = sizeStr.trim().toUpperCase();
try {
if (sizeStr.endsWith("KB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024);
} else if (sizeStr.endsWith("MB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024 * 1024);
} else if (sizeStr.endsWith("GB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024 * 1024 * 1024);
} else if (sizeStr.endsWith("B")) {
return Long.parseLong(sizeStr.substring(0, sizeStr.length() - 1));
} else {
// Input string does not have a valid format, handle this case
}
} catch (NumberFormatException e) {
// The numeric part of the input string cannot be parsed, handle this case
}
return null;
}
public static List<Integer> parsePageList(String[] pageOrderArr, int totalPages) {
List<Integer> newPageOrder = new ArrayList<>();
// loop through the page order array
for (String element : pageOrderArr) {
// check if the element contains a range of pages
if (element.matches("\\d*n\\+?-?\\d*|\\d*\\+?n")) {
// Handle page order as a function
int coefficient = 0;
int constant = 0;
boolean coefficientExists = false;
boolean constantExists = false;
if (element.contains("n")) {
String[] parts = element.split("n");
if (!parts[0].equals("") && parts[0] != null) {
coefficient = Integer.parseInt(parts[0]);
coefficientExists = true;
}
if (parts.length > 1 && !parts[1].equals("") && parts[1] != null) {
constant = Integer.parseInt(parts[1]);
constantExists = true;
}
} else if (element.contains("+")) {
constant = Integer.parseInt(element.replace("+", ""));
constantExists = true;
}
for (int i = 1; i <= totalPages; i++) {
int pageNum = coefficientExists ? coefficient * i : i;
pageNum += constantExists ? constant : 0;
if (pageNum <= totalPages && pageNum > 0) {
newPageOrder.add(pageNum - 1);
}
}
} else if (element.contains("-")) {
// split the range into start and end page
String[] range = element.split("-");
int start = Integer.parseInt(range[0]);
int end = Integer.parseInt(range[1]);
// check if the end page is greater than total pages
if (end > totalPages) {
end = totalPages;
}
// loop through the range of pages
for (int j = start; j <= end; j++) {
// print the current index
newPageOrder.add(j - 1);
}
} else {
// if the element is a single page
newPageOrder.add(Integer.parseInt(element) - 1);
}
}
return newPageOrder;
}
public static boolean createDir(String path) {
Path folder = Paths.get(path);
if (!Files.exists(folder)) {
try {
Files.createDirectories(folder);
} catch (IOException e) {
e.printStackTrace();
return false;
}
}
return true;
}
}
package stirling.software.SPDF.utils;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;
public class GeneralUtils {
public static Long convertSizeToBytes(String sizeStr) {
if (sizeStr == null) {
return null;
}
sizeStr = sizeStr.trim().toUpperCase();
try {
if (sizeStr.endsWith("KB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024);
} else if (sizeStr.endsWith("MB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024 * 1024);
} else if (sizeStr.endsWith("GB")) {
return (long) (Double.parseDouble(sizeStr.substring(0, sizeStr.length() - 2)) * 1024 * 1024 * 1024);
} else if (sizeStr.endsWith("B")) {
return Long.parseLong(sizeStr.substring(0, sizeStr.length() - 1));
} else {
// Input string does not have a valid format, handle this case
}
} catch (NumberFormatException e) {
// The numeric part of the input string cannot be parsed, handle this case
}
return null;
}
public static List<Integer> parsePageList(String[] pageOrderArr, int totalPages) {
List<Integer> newPageOrder = new ArrayList<>();
// loop through the page order array
for (String element : pageOrderArr) {
if (element.equalsIgnoreCase("all")) {
for (int i = 0; i < totalPages; i++) {
newPageOrder.add(i);
}
// As all pages are already added, no need to check further
break;
}
else if (element.matches("\\d*n\\+?-?\\d*|\\d*\\+?n")) {
// Handle page order as a function
int coefficient = 0;
int constant = 0;
boolean coefficientExists = false;
boolean constantExists = false;
if (element.contains("n")) {
String[] parts = element.split("n");
if (!parts[0].equals("") && parts[0] != null) {
coefficient = Integer.parseInt(parts[0]);
coefficientExists = true;
}
if (parts.length > 1 && !parts[1].equals("") && parts[1] != null) {
constant = Integer.parseInt(parts[1]);
constantExists = true;
}
} else if (element.contains("+")) {
constant = Integer.parseInt(element.replace("+", ""));
constantExists = true;
}
for (int i = 1; i <= totalPages; i++) {
int pageNum = coefficientExists ? coefficient * i : i;
pageNum += constantExists ? constant : 0;
if (pageNum <= totalPages && pageNum > 0) {
newPageOrder.add(pageNum - 1);
}
}
} else if (element.contains("-")) {
// split the range into start and end page
String[] range = element.split("-");
int start = Integer.parseInt(range[0]);
int end = Integer.parseInt(range[1]);
// check if the end page is greater than total pages
if (end > totalPages) {
end = totalPages;
}
// loop through the range of pages
for (int j = start; j <= end; j++) {
// print the current index
newPageOrder.add(j - 1);
}
} else {
// if the element is a single page
newPageOrder.add(Integer.parseInt(element) - 1);
}
}
return newPageOrder;
}
public static boolean createDir(String path) {
Path folder = Paths.get(path);
if (!Files.exists(folder)) {
try {
Files.createDirectories(folder);
} catch (IOException e) {
e.printStackTrace();
return false;
}
}
return true;
}
}

71
src/main/java/stirling/software/SPDF/utils/PdfUtils.java
View File

@@ -68,43 +68,37 @@ public class PdfUtils {
}
}
public boolean hasImageInFile(PDDocument pdfDocument, String text, String pagesToCheck) throws IOException {
PDFTextStripper textStripper = new PDFTextStripper();
String pdfText = "";
if(pagesToCheck == null || pagesToCheck.equals("all")) {
pdfText = textStripper.getText(pdfDocument);
} else {
// remove whitespaces
pagesToCheck = pagesToCheck.replaceAll("\\s+", "");
public static boolean hasImages(PDDocument document, String pagesToCheck) throws IOException {
String[] pageOrderArr = pagesToCheck.split(",");
List<Integer> pageList = GeneralUtils.parsePageList(pageOrderArr, document.getNumberOfPages());
String[] splitPoints = pagesToCheck.split(",");
for (String splitPoint : splitPoints) {
if (splitPoint.contains("-")) {
// Handle page ranges
String[] range = splitPoint.split("-");
int startPage = Integer.parseInt(range[0]);
int endPage = Integer.parseInt(range[1]);
for (int i = startPage; i <= endPage; i++) {
textStripper.setStartPage(i);
textStripper.setEndPage(i);
pdfText += textStripper.getText(pdfDocument);
}
} else {
// Handle individual page
int page = Integer.parseInt(splitPoint);
textStripper.setStartPage(page);
textStripper.setEndPage(page);
pdfText += textStripper.getText(pdfDocument);
}
for (int pageNumber : pageList) {
PDPage page = document.getPage(pageNumber);
if (hasImagesOnPage(page)) {
return true;
}
}
pdfDocument.close();
return pdfText.contains(text);
return false;
}
public static boolean hasText(PDDocument document, String pageNumbersToCheck, String phrase) throws IOException {
String[] pageOrderArr = pageNumbersToCheck.split(",");
List<Integer> pageList = GeneralUtils.parsePageList(pageOrderArr, document.getNumberOfPages());
for (int pageNumber : pageList) {
PDPage page = document.getPage(pageNumber);
if (hasTextOnPage(page, phrase)) {
return true;
}
}
return false;
}
public static boolean hasImagesOnPage(PDPage page) throws IOException {
ImageFinder imageFinder = new ImageFinder(page);
@@ -113,12 +107,17 @@ public class PdfUtils {
}
public static boolean hasText(PDDocument document, String phrase) throws IOException {
PDFTextStripper pdfStripper = new PDFTextStripper();
String text = pdfStripper.getText(document);
return text.contains(phrase);
}
public static boolean hasTextOnPage(PDPage page, String phrase) throws IOException {
PDFTextStripper textStripper = new PDFTextStripper();
PDDocument tempDoc = new PDDocument();
tempDoc.addPage(page);
String pageText = textStripper.getText(tempDoc);
tempDoc.close();
return pageText.contains(phrase);
}
public boolean containsTextInFile(PDDocument pdfDocument, String text, String pagesToCheck) throws IOException {
PDFTextStripper textStripper = new PDFTextStripper();

111
src/main/java/stirling/software/SPDF/utils/WebResponseUtils.java
View File

@@ -1,50 +1,61 @@
package stirling.software.SPDF.utils;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpStatus;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
public class WebResponseUtils {
public static ResponseEntity<byte[]> boasToWebResponse(ByteArrayOutputStream baos, String docName) throws IOException {
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(), docName);
}
public static ResponseEntity<byte[]> boasToWebResponse(ByteArrayOutputStream baos, String docName, MediaType mediaType) throws IOException {
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(), docName, mediaType);
}
public static ResponseEntity<byte[]> bytesToWebResponse(byte[] bytes, String docName, MediaType mediaType) throws IOException {
// Return the PDF as a response
HttpHeaders headers = new HttpHeaders();
headers.setContentType(mediaType);
headers.setContentLength(bytes.length);
String encodedDocName = URLEncoder.encode(docName, StandardCharsets.UTF_8.toString()).replaceAll("\\+", "%20");
headers.setContentDispositionFormData("attachment", encodedDocName);
return new ResponseEntity<>(bytes, headers, HttpStatus.OK);
}
public static ResponseEntity<byte[]> bytesToWebResponse(byte[] bytes, String docName) throws IOException {
return bytesToWebResponse(bytes, docName, MediaType.APPLICATION_PDF);
}
public static ResponseEntity<byte[]> pdfDocToWebResponse(PDDocument document, String docName) throws IOException {
// Open Byte Array and save document to it
ByteArrayOutputStream baos = new ByteArrayOutputStream();
document.save(baos);
// Close the document
document.close();
return boasToWebResponse(baos, docName);
}
}
package stirling.software.SPDF.utils;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.net.URLEncoder;
import java.nio.charset.StandardCharsets;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.springframework.http.HttpHeaders;
import org.springframework.http.HttpStatus;
import org.springframework.http.MediaType;
import org.springframework.http.ResponseEntity;
import org.springframework.web.multipart.MultipartFile;
public class WebResponseUtils {
public static ResponseEntity<byte[]> boasToWebResponse(ByteArrayOutputStream baos, String docName) throws IOException {
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(), docName);
}
public static ResponseEntity<byte[]> boasToWebResponse(ByteArrayOutputStream baos, String docName, MediaType mediaType) throws IOException {
return WebResponseUtils.bytesToWebResponse(baos.toByteArray(), docName, mediaType);
}
public static ResponseEntity<byte[]> multiPartFileToWebResponse(MultipartFile file) throws IOException {
String fileName = file.getOriginalFilename();
MediaType mediaType = MediaType.parseMediaType(file.getContentType());
byte[] bytes = file.getBytes();
return bytesToWebResponse(bytes, fileName, mediaType);
}
public static ResponseEntity<byte[]> bytesToWebResponse(byte[] bytes, String docName, MediaType mediaType) throws IOException {
// Return the PDF as a response
HttpHeaders headers = new HttpHeaders();
headers.setContentType(mediaType);
headers.setContentLength(bytes.length);
String encodedDocName = URLEncoder.encode(docName, StandardCharsets.UTF_8.toString()).replaceAll("\\+", "%20");
headers.setContentDispositionFormData("attachment", encodedDocName);
return new ResponseEntity<>(bytes, headers, HttpStatus.OK);
}
public static ResponseEntity<byte[]> bytesToWebResponse(byte[] bytes, String docName) throws IOException {
return bytesToWebResponse(bytes, docName, MediaType.APPLICATION_PDF);
}
public static ResponseEntity<byte[]> pdfDocToWebResponse(PDDocument document, String docName) throws IOException {
// Open Byte Array and save document to it
ByteArrayOutputStream baos = new ByteArrayOutputStream();
document.save(baos);
// Close the document
document.close();
return boasToWebResponse(baos, docName);
}
}