public string PdfToText()
{
string pdfText = String.Empty;
PDFParser parser = new PDFParser(new BufferedInputStream(new FileInputStream(PdfFile)));
parser.parse();
PDDocument originialPdfDoc = parser.getPDDocument();
bool isOriginalDocEncrypted = originialPdfDoc.isEncrypted();
if (isOriginalDocEncrypted)
{
originialPdfDoc.openProtection(new StandardDecryptionMaterial(PdfPassword));
}
PDFTextStripper stripper = new PDFTextStripper();
try
{
pdfText = stripper.getText(originialPdfDoc);
}
catch (java.io.IOException ex)
{
throw ex;
}
return(pdfText);
}
/**
* 提取部分页面文本
* @param file pdf文档路径
* @param startPage 开始页数
* @param endPage 结束页数
*/
public static string ExtractTXT(String file, int startPage, int endPage)
{
String content = string.Empty;
try
{
PDDocument document = PDDocument.load(file);
//获取一个PDFTextStripper文本剥离对象
PDFTextStripper stripper = new PDFTextStripper();
// 设置按顺序输出
stripper.setSortByPosition(true);
// 设置起始页
stripper.setStartPage(startPage);
// 设置结束页
stripper.setEndPage(endPage);
//获取文本内容
content = stripper.getText(document);
document.close();
}
catch (java.io.FileNotFoundException ex)
{
}
catch (java.io.IOException ex)
{
}
return(content);
}
public static PDFInfo GetPDFDoucmentInformation(PDDocument document)
{
PDFInfo i = new PDFInfo();
PDDocumentInformation info = document.getDocumentInformation();
i.Author = info.getAuthor();
if (info.getCreationDate() != null)
{
DateTime dt = Utilities.Utils.GetDateFromJava(info.getCreationDate());
i.CreationDate = dt.ToLongDateString() + " " + dt.ToLongTimeString();
}
i.Creator = info.getCreator();
i.Keywords = info.getKeywords();
if (info.getModificationDate() != null)
{
DateTime dt = Utilities.Utils.GetDateFromJava(info.getModificationDate());
i.ModificationDate = dt.ToLongDateString() + " " + dt.ToLongTimeString();
}
i.Producer = info.getProducer();
i.Subject = info.getSubject();
i.Title = info.getTitle();
i.Trapped = info.getTrapped();
i.NumberOfPages = document.getNumberOfPages();
return i;
}
public string PdfFields()
{
string pdfText = String.Empty;
PDFParser parser = new PDFParser(new BufferedInputStream(new FileInputStream(PdfFile)));
parser.parse();
PDDocument originialPdfDoc = parser.getPDDocument();
bool isOriginalDocEncrypted = originialPdfDoc.isEncrypted();
if (isOriginalDocEncrypted)
{
originialPdfDoc.openProtection(new StandardDecryptionMaterial(PdfPassword));
}
try
{
PDDocumentCatalog docCatalog = originialPdfDoc.getDocumentCatalog();
PDAcroForm acroForm = docCatalog.getAcroForm();
PDField field = acroForm.getField("Name");
if (field != null)
{
field.setValue("name");
}
}
catch (java.io.IOException ex)
{
throw ex;
}
return(pdfText);
}
/// <summary>
/// The below method is an example from https://svn.apache.org/viewvc/pdfbox/trunk/examples/src/main/java/org/apache/pdfbox/examples/util/AddWatermarkText.java?revision=1873147&view=markup
/// </summary>
/// <param name="doc"></param>
/// <param name="page"></param>
/// <param name="font"></param>
/// <param name="text"></param>
static void addWatermarkText(PDDocument doc, PDPage page, PDFont font, string text)
{
using (PDPageContentStream cs
= new PDPageContentStream(doc, page, PDPageContentStream.AppendMode.APPEND, true, true))
{
float fontHeight = 100; // arbitrary for short text
float width = page.getMediaBox().getWidth();
float height = page.getMediaBox().getHeight();
float stringWidth = font.getStringWidth(text) / 1000 * fontHeight;
float diagonalLength = (float)System.Math.Sqrt(width * width + height * height);
float angle = (float)System.Math.Atan2(height, width);
float x = (diagonalLength - stringWidth) / 2; // "horizontal" position in rotated world
float y = -fontHeight / 4; // 4 is a trial-and-error thing, this lowers the text a bit
cs.transform(Matrix.getRotateInstance(angle, 0, 0));
cs.setFont(font, fontHeight);
// cs.setRenderingMode(RenderingMode.STROKE) // for "hollow" effect
PDExtendedGraphicsState gs = new PDExtendedGraphicsState();
gs.setNonStrokingAlphaConstant(new Float(0.2f));
gs.setStrokingAlphaConstant(new Float(0.2f));
gs.setBlendMode(BlendMode.MULTIPLY);
gs.setLineWidth(new Float(3f));
cs.setGraphicsStateParameters(gs);
cs.setNonStrokingColor(Color.red);
cs.setStrokingColor(Color.red);
cs.beginText();
cs.newLineAtOffset(x, y);
cs.showText(text);
cs.endText();
}
}
public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
static void Main(string[] args)
{
if (args == null || args.Length < 2)
{
System.Console.WriteLine("Usage: " + AppDomain.CurrentDomain.FriendlyName + " <original PDF filename> <watermark text> [new PDF filename]" + Environment.NewLine +
" For example: " + AppDomain.CurrentDomain.FriendlyName + " myDoc.pdf \"This is a Draft\"");
}
else
{
string origName = args[0];
string watermarkTxt = args[1];
if (!System.IO.File.Exists(origName))
{
System.Console.WriteLine("Error: cannot find the original PDF file(" + origName + "). Please correct the filename or the path and try again.");
}
else
{
PDDocument origDoc = PDDocument.load(new java.io.File(origName)); // NOTE: PDDocument.load() only takes java.io.File, not System.IO.File from C#.Net
PDPageTree allPages = origDoc.getPages();
PDFont font = PDType1Font.HELVETICA_BOLD;
for (int i = 0, len = allPages.getCount(); i < len; ++i)
{
PDPage pg = (PDPage)allPages.get(i);
addWatermarkText(origDoc, pg, font, "This is a draft!!!");
}
origDoc.save("watermarked_" + origName);
origDoc.close();
}
}
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
//ExtractText(pdfStripper, pdfDocument,
// string.Format(@"c:\Users\tri.hoang\Desktop\temp\epub-belastingblad\2014-08\pdf\page_{0}.txt", i.ToString().PadLeft(5, '0')));
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
public PDFValidator(string fileName, string password)
{
try
{
this.IsValid = true;
if (!System.IO.File.Exists(fileName))
{
Console.WriteLine("The PDF file does not Exist.");
}
else
{
PDDocument pDDocument = null;
pDDocument = (!string.IsNullOrEmpty(password) ? PDDocument.load(new java.io.File(fileName), password) : PDDocument.load(new java.io.File(fileName)));
if (pDDocument.isEncrypted())
{
this.IsPasswordProtected = true;
}
this.CheckAllPages(pDDocument);
if (pDDocument != null)
{
pDDocument.close();
}
}
}
catch (InvalidPasswordException invalidPasswordException)
{
this.IsPasswordProtected = true;
this.IsValid = false;
}
catch (Exception exception)
{
this.ErrorMessage = string.Format("PDF analysis failed With exception {0}", exception.Message);
this.IsValid = false;
}
}
/// <summary>
/// 读取
/// </summary>
/// <param name="file"></param>
/// <returns></returns>
public string Read(IFormFile file)
{
/*var ss = Directory.GetCurrentDirectory();//获取项目路径
* var st = _hostingEnvironment.ContentRootPath;//获取项目路径
* var fileDir = ss+"\\pdf";
* if (Directory.Exists(fileDir))
* {
* Directory.Delete(fileDir,true);
* }
* Directory.CreateDirectory(fileDir);
* //string fileName = file.FileName;
* //string filePath= fileDir + $@"\{fileName}";
* var fileName = DateTime.Now.ToString("yyyyMMddHHmmss") +
* Path.GetExtension(file.FileName);
* var filePath = Path.Combine(fileDir, fileName);
* using (FileStream fs = System.IO.File.Create(filePath))
* {
* file.CopyTo(fs);
* fs.Flush();
* }
* var files = new FileInfo(filePath);*/
// string currentDirectory = Path.GetDirectoryName((new PdfController()).GetType().Assembly.Location);
PDDocument doc = PDDocument.load(@"G:/Read.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
string text = pdfStripper.getText(doc);
return(text);
}
public static Info ReadDocInfo(string fileName)
{
Info result = new Info();
try
{
PDDocument pDoc = PDDocument.load(fileName);
PDDocumentInformation docInfo = pDoc.getDocumentInformation();
if (docInfo != null)
{
var author = docInfo.getAuthor();
var title = docInfo.getTitle();
var summary = docInfo.getSubject();
var keywords = docInfo.getKeywords();
result.Author = author;
result.Title = title;
result.Summary = summary;
result.Keywords = keywords;
}
}
catch (Exception ex)
{
}
return(result);
}
public Exception ShowZUGFeRD(string filepath, out string message)
{
try
{
PDDocument doc = PDDocument.load(filepath);
// now check the contents (like MustangReaderTest)
NE4ZUGFeRDImporter zi = new NE4ZUGFeRDImporter();
zi.extract(filepath);
// ZUGFeRD lesen
if (zi.canParse())
{
zi.parse();
// ZUGFeRD Daten als string zurück
message = string.Format("Menge: {0}\nRechnungsempfänger: {1}\nReferenz: {2}",
zi.getAmount(), zi.getHolder(), zi.getForeignReference());
}
else
{
message = "Keine ZUGFeRD Daten gefunden!";
}
//return ok
return(null);
}
catch (Exception ex)
{
message = ex.InnerException.ToString();
return(ex);
}
}
public string parseUsingPDFBox(string input)
{
PDDocument doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
private string GetTextFromPdfFile(string fileName)
{
PDDocument doc = PDDocument.load(fileName);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(doc));
}
/// <summary>
/// 通过文件流方式解析PDF
/// </summary>
/// <param name="pdfStream">PDF流</param>
/// <param name="tableContainType">表格包含样式</param>
/// <returns></returns>
public static PDFModel Parser(byte[] pdfStream, TableContainType tableContainType)
{
PDFModel fileContent = null;
//打开文件
PDDocument reader = null;
try
{
InputStream sbs = new ByteArrayInputStream(pdfStream);
reader = PDDocument.load(sbs);
fileContent = Parser(reader, tableContainType);
}
catch (Exception ex)
{
if (reader != null)
{
reader.close();
reader = null;
}
return(null);
}
finally
{
reader.close();
reader = null;
}
return(fileContent);
}
public static String PDFText(String PDFFilePath)
{
PDDocument doc = PDDocument.load(PDFFilePath);
PDFTextStripper stripper = new PDFTextStripper();
var text = " ";
try
{
text = stripper.getText(doc);
return(text);
}
catch (UnauthorizedAccessException e)
{
MessageBox.Show("Невозможно скопировать текст из Пдф " + PDFFilePath + ". " + e.Message, "Сообщение об ошибке");
return("");
}
catch (FileLoadException FLe)
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". " + FLe.Message, "Сообщение об ошибке");
return("");
}
catch when(text == "")
{
MessageBox.Show("Невозможно загрузить Пдф " + PDFFilePath + ". ", "Сообщение об ошибке");
return("");
}
finally
{
doc.close();
}
}
private void Split(int start, int end, int repeatEvery)
{
if (this.CheckOutput())
{
PDFHelper.DisplayTrialPopupIfNecessary();
try
{
Splitter splitter = new Splitter();
splitter.setStartPage(start);
splitter.setEndPage(end);
splitter.setSplitAtPage(repeatEvery);
List list = splitter.split(this.pdfDocument.PDFBoxDocument);
for (int i = 0; i < list.size(); i++)
{
PDDocument pDDocument = PDFHelper.AddTrialStampIfNecessary((PDDocument)list.@get(i));
string str = string.Format("{0} [{1}].pdf", this.OutputFileName, i);
pDDocument.save(Path.Combine(this.OutputFilePath, str));
}
}
catch (Exception exception1)
{
Exception exception = exception1;
throw new PDFToolkitException(exception.Message, exception.InnerException);
}
}
}
/// <summary>
/// Validates the PDF File Downloaded and the text present in the file
/// </summary>
/// <param name="pdfFileName">The folder or filepath.</param>
/// <param name="textToCheck">The text to be validated.</param>
/// <returns>if the text is present or not</returns>
public static bool ExtractAndValidateTextFromPDF(string pdfFileName, string textToCheck)
{
try
{
string result = string.Empty;
bool validateText = false;
PDDocument doc = PDDocument.load(pdfFileName);
PDFTextStripper stripper = new PDFTextStripper();
result = stripper.getText(doc);
doc.close();
if (result.Length != 0)
{
byte[] bytes = Encoding.Default.GetBytes(result.ToString());
string decodedresult = Encoding.UTF8.GetString(bytes);
string outputPDF = decodedresult.Replace(" ", null).Replace("\r", null).Replace("\n", null);
string validationString = textToCheck.Replace(" ", null);
validateText = outputPDF.Contains(validationString);
}
return(validateText);
}
catch (Exception)
{
throw;
}
}
private void btnShowPDF_Click(object sender, EventArgs e)
{
PDDocument PDF = PDDocument.load(textBox1.Text);
PDFTextStripper stripper = new PDFTextStripper();
richTextBox1.Text = (stripper.getText(PDF));
}
internal static bool EmbedPDFAttachment(PDFAttachmentItem attachment, PDDocument doc)
{
bool flag;
try
{
PDEmbeddedFilesNameTreeNode pDEmbeddedFilesNameTreeNode = new PDEmbeddedFilesNameTreeNode();
List arrayList = new ArrayList();
PDComplexFileSpecification pDComplexFileSpecification = new PDComplexFileSpecification();
pDComplexFileSpecification.setFile(System.IO.Path.GetFileName(attachment.filePath));
java.io.File file = new java.io.File(attachment.filePath);
byte[] numArray = Files.readAllBytes(file.toPath());
PDEmbeddedFile pDEmbeddedFile = new PDEmbeddedFile(doc, new ByteArrayInputStream(numArray));
pDEmbeddedFile.setSize((int)numArray.Length);
pDEmbeddedFile.setCreationDate(new GregorianCalendar());
pDComplexFileSpecification.setEmbeddedFile(pDEmbeddedFile);
PDEmbeddedFilesNameTreeNode pDEmbeddedFilesNameTreeNode1 = new PDEmbeddedFilesNameTreeNode();
pDEmbeddedFilesNameTreeNode1.setNames(Collections.singletonMap("My first attachment", pDComplexFileSpecification));
arrayList.@add(pDEmbeddedFilesNameTreeNode1);
pDEmbeddedFilesNameTreeNode.setKids(arrayList);
PDDocumentNameDictionary pDDocumentNameDictionary = new PDDocumentNameDictionary(doc.getDocumentCatalog());
pDDocumentNameDictionary.setEmbeddedFiles(pDEmbeddedFilesNameTreeNode);
doc.getDocumentCatalog().setNames(pDDocumentNameDictionary);
flag = true;
}
catch (Exception exception1)
{
Exception exception = exception1;
throw new PDFToolkitException(exception.Message, exception);
}
return(flag);
}
public override string[] ExtractKeyWordCandidatesFromFile()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract creation date from empty bytes for file " + Name);
return(null);
}
try
{
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
// TODO Internationalize this conversion
text = doc.getDocumentInformation().getKeywords();
}
catch (Exception e)
{
log.Warn("Failed to get the keywords from the PDF file " + Name, e);
}
string[] returnText = null;
if (!string.IsNullOrEmpty(text))
{
returnText = text.Split(new char[] { ',', ';' });
}
return(returnText);
}
public static Dictionary <int, string> Extract(string pdfFileName)
{
if (!File.Exists(pdfFileName))
{
throw new FileNotFoundException("pdfFileName");
}
var result = new Dictionary <int, string>();
PDDocument pdfDocument = PDDocument.load(pdfFileName);
var pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
result.Add(i, GetText(pdfStripper, pdfDocument));
}
pdfDocument.close();
return(result);
}
/// <summary>
/// Get a thumbnail of the document, if possible
/// </summary>
/// <param name="sizeX">The maximum X size of the thumbnail</param>
/// <param name="sizeY">The maximum y size of the thumbnail</param>
/// <param name="forceFullSize">True if the thumbnail should be exatly XxY pixels and False if the thumbnail
/// should fit inside a XxY box but should maintain its aspect ratio</param>
/// <returns>A JPEG byte thumbnail or null if the thumbnail can´t be generated</returns>
public override byte[] GetThumbnail(int sizeX, int sizeY, bool forceFullSize)
{
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
return(null);
}
try
{
org.pdfbox.pdfviewer.PageDrawer pagedrawer = new
org.pdfbox.pdfviewer.PageDrawer();
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
int count = doc.getNumberOfPages();
java.util.List pages = doc.getDocumentCatalog().getAllPages();
if (pages.size() > 0)
{
PDPage page = pagedrawer.getPage();
java.awt.image.BufferedImage image = page.convertToImage();
java.io.ByteArrayOutputStream os = new java.io.ByteArrayOutputStream();
ImageIO.write(image, "jpg", os);
byte[] data = os.toByteArray();
return(data);
}
}
catch (Exception e)
{
log.Error("Failed to get the thumbnail from the PDF file " + Name, e);
}
return(null);
}
/// <summary>
/// Get text from the binary using PDFBox
/// </summary>
/// <returns>The text of the binary or null if we could not process the text</returns>
public override string GetTextFromDocumentBinary()
{
string text = null;
// If we have no bytes then we can't do anything.
if (Bytes == null || Bytes.Length == 0)
{
// Log the problem.
log.Error("Tried to extract text from empty bytes for file " + Name);
return(null);
}
try
{
java.io.ByteArrayInputStream byteStream = new java.io.ByteArrayInputStream(Bytes);
PDDocument doc = PDDocument.load(byteStream);
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(doc);
}
catch (Exception e)
{
log.Error("Failed to get the text from the PDF file " + Name, e);
}
return(text);
}
public string parsePDF(string filepath)
{
PDDocument document = PDDocument.load(filepath);
PDFTextStripper stripper = new PDFTextStripper();
return(stripper.getText(document));
}
static void Main(string[] args)
{
PDDocument doc = PDDocument.load("lopreacamasa.pdf");
PDFTextStripper pdfStripper = new PDFTextStripper();
Console.Write(pdfStripper.getText(doc));
}
private void CheckAllPages(PDDocument doc)
{
int num = 0;
try
{
this.NumberOfPagesDict = doc.getNumberOfPages();
foreach (PDPage page in doc.getPages())
{
if (page.getMediaBox() == null)
{
this.ErrorMessage = string.Format("Page number {0} has no media box", num);
this.IsValid = false;
}
if (page.getResources() == null)
{
this.ErrorMessage = string.Format("Page number {0}, has no page resources", num);
this.IsValid = false;
}
num++;
}
if (this.NumberOfPagesDict != num)
{
this.ErrorMessage = string.Format("Page Number Mismatch between dictionary and actual document", new object[0]);
this.IsValid = false;
}
}
catch (Exception exception1)
{
Exception exception = exception1;
this.ErrorMessage = string.Format("PDF analysis failed on page number {0},\nWith exception {1}", num, exception.Message);
this.IsValid = false;
}
}
public void ExtractText(string inpufFileName, string outputFileName)
{
#if false
IFilterTextReader.FilterReader reader = new FilterReader(inpufFileName);
var data = reader.ReadToEnd();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(data);
}
#else
PDDocument doc = null;
try
{
doc = PDDocument.load(inpufFileName);
PDFTextStripper stripper = new PDFTextStripper();
using (var writer = new StreamWriter(outputFileName, false, System.Text.Encoding.UTF8))
{
writer.Write(stripper.getText(doc));
}
}
finally
{
if (doc != null)
{
doc.close();
}
}
#endif
}
public PdfOcrResult Execute(byte[] bytes)
{
PDDocument document = null;
try
{
LoadPdf(bytes, ref document);
List allPages = document.getDocumentCatalog().getAllPages();
if (allPages.size() == 0)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
//only first page
PDPage page = (PDPage)allPages.get(0);
PDStream contents = page.getContents();
if (contents == null)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
var items = new PdfToCharacters().GetItems(page, page.findResources(), page.getContents().getStream());
if (items.Count == 0)
{
throw new PdfNotReadableException("Pdf contains no readable content");
}
var mediaBox = page.findMediaBox();
var height = mediaBox?.getHeight() ?? 0;
var width = mediaBox?.getWidth() ?? 0;
var itemsArray = items.ToArray();
var keywords = "";
try
{
keywords = document.getDocumentInformation()?.getKeywords();
}
catch (Exception) { } // we do not know if PDF box can fail on this, if there is no keywords or something else. We dont really care we just want the keywords if possible.
return(new PdfOcrResult()
{
Items = itemsArray, Height = height, Width = width, Keywords = keywords
});
}
catch (PdfReadException)
{
throw;
}
catch (Exception e)
{
throw new PdfReadException("Pdf could not be loaded. It is not a redable pdf.", e);
}
finally
{
document?.close();
}
}
private static void KamilPdfTest(string input)
{
PDDocument doc = null;
try
{
doc = PDDocument.load(input);
PDFTextStripper stripper = new PDFTextStripper();
// stripper.getText(doc);
Matrix line = stripper.getTextLineMatrix();
// int page_nr = stripper.getCurrentPageNo();
PDPage page = stripper.getCurrentPage();
Matrix line2 = stripper.getTextMatrix();
int char_cnt = stripper.getTotalCharCnt();
string article_start = stripper.getArticleStart();
string article_end = stripper.getArticleEnd();
string pdf = stripper.getText(doc); // wrzuca caly tekst do sringa - dziala
char_cnt = pdf.Length;
}
finally
{
if (doc != null)
{
doc.close();
}
}
}
protected internal String ConvertPDFToDoc(string PDFpath)
{
try
{
PDDocument PDFdoc = null;
PDFTextStripper textstrip = new PDFTextStripper();
String StringDocx = String.Empty;
String DocxPath = String.Empty;
PDFdoc = PDDocument.load(PDFpath);
StringDocx = textstrip.getText(PDFdoc);
PDFdoc.close(); //cierra el pdf
///DocxPath = fn.CreateFolderToSaveDocs(fn.GenerateName()); ///genera la ruta para guardar el archivo.
DocxPath = fn.CreateFolderToSaveDocs(fileName); ///genera la ruta para guardar el archivo.
var wordDoc = DocX.Create(DocxPath);
wordDoc.InsertParagraph(StringDocx);
wordDoc.Save();
////Process.Start("winword.exe", DocxPath);
return(DocxPath);
}
catch (Exception)
{
return("");
}
}
/// <summary>
/// Tries to decrypt a document with the given passwords.
/// </summary>
/// <param name="doc">Document of type PDDocument.</param>
/// <param name="passwords">Passwords of type string array.</param>
/// <returns>Decrypted document (PDDocument) or null if decryption fails.</returns>
private static PDDocument Decrypt(PDDocument doc, ICollection<string> passwords)
{
if (!passwords.Any())
{
throw new ApplicationException("PDfUtil :: Decrypt :: supplied empty password collection");
}
foreach (var password in passwords)
{
Log.Debug("PdfUtil :: trying to decrypt with Password: [" + password + "]", typeof(PdfUtil));
var tmpdoc = Decrypt(doc, password);
if (tmpdoc != null)
{
return tmpdoc;
}
}
return null;
}
public string Parse(string fileName)
{
//Load in file. Using java.io because pdfbox is ported from java.
var pdfFile = new FileInputStream(fileName);
//Load file into the pdf parser
var pdfParser = new PDFParser(pdfFile);
//Parse the document, so that we can get it for the COSDocument
pdfParser.parse();
/*
COSDocument is the in-memory representation of the PDF.
see https://pdfbox.apache.org/docs/1.8.4/javadocs/org/apache/pdfbox/cos/COSDocument.html
*/
var cosDocument = pdfParser.getDocument();
var pdDocument = new PDDocument(cosDocument);
//Instantiate text stripper.
var pdfTextStripper = new PDFTextStripper();
/* Needed for only stripping specific pages
pdfTextStripper.setStartPage(0);
pdfTextStripper.setEndPage(pdDocument.getNumberOfPages());
*/
//Needed so that we can close the pdDocument before returning from this method
var strippedText = pdfTextStripper.getText(pdDocument);
//This closes all storage and delete the tmp files.
pdDocument.close();
cosDocument.close();
return strippedText;
}
public void Initialize()
{
_pdfDocument = PDDocument.load(_pdfDocumentName);
}
private PdfTextReader(PDDocument document)
{
this.document = document;
}
/// <summary>
/// Tries to decrypt a document with the given password
/// </summary>
/// <param name="doc">Document of type PDDocument</param>
/// <param name="password">Password of type string</param>
/// <returns>decrypted document (PDDocument) or null if decryption fails</returns>
private static PDDocument Decrypt(PDDocument doc, string password)
{
var standardDecryptionMaterial = new StandardDecryptionMaterial(password);
try
{
doc.openProtection(standardDecryptionMaterial);
return doc;
}
catch (Exception ex)
{
Log.Debug("PdfUtil :: Decryption failed", ex);
return null;
}
}
public Dictionary<string, PDFField> DiscoverPDFFormFields(PDDocument document)
{
return GetPDFFormFields(document, false);
}
public Dictionary<string, PDFField> GetPDFFormFields(PDDocument document, bool includeValues)
{
Dictionary<string, PDFField> pdfFormFields = new Dictionary<string, PDFField>();
PDDocumentCatalog docCat = document.getDocumentCatalog();
PDAcroForm form = docCat.getAcroForm();
string aa = string.Empty;
var a = form.getFields();
var iterator = a.iterator();
while (iterator.hasNext())
{
try
{
PDFField pdffield = new PDFField();
PDField f = (PDField)iterator.next();
pdffield.Type = f.getFieldType();
pdffield.IsRequired = f.isRequired();
pdffield.IsReadOnly = f.isReadonly();
pdffield.FullName = f.getFullyQualifiedName();
pdffield.AlternativeName = f.getAlternateFieldName();
pdffield.PartialName = f.getPartialName();
string fieldvalue = string.Empty;
// sig field throws not implemented in ver 1.2.1
if (includeValues)
{
try
{
fieldvalue = f.getValue();
}
catch (Exception e) { }
}
if (pdffield.Type == "Sig")
{
PDSignatureField sig = (PDSignatureField)f;
var x = sig.getSignature();
if (x != null)
{
fieldvalue = x.getName();
}
}
pdffield.FieldValue = fieldvalue;
pdfFormFields.Add(pdffield.FullName, pdffield);
}
catch (Exception e) { }
}
return pdfFormFields;
}
