static void Search()
{
//open document
Document pdfDocument = new Document(Config.TestPdf);
string keyword = "pattern";
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(keyword);
//accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
Console.WriteLine("Page Number : {0} ", textFragment.Page.Number);
//Console.WriteLine("Text : {0} ", textFragment.Text);
//Console.WriteLine("Position : {0} ", textFragment.Position);
//Console.WriteLine("XIndent : {0} ", textFragment.Position.XIndent);
//Console.WriteLine("YIndent : {0} ", textFragment.Position.YIndent);
//Console.WriteLine("Font - Name : {0}", textFragment.TextState.Font.FontName);
//Console.WriteLine("Font - IsAccessible : {0} ", textFragment.TextState.Font.IsAccessible);
//Console.WriteLine("Font - IsEmbedded : {0} ", textFragment.TextState.Font.IsEmbedded);
//Console.WriteLine("Font - IsSubset : {0} ", textFragment.TextState.Font.IsSubset);
//Console.WriteLine("Font Size : {0} ", textFragment.TextState.FontSize);
//Console.WriteLine("Foreground Color : {0} ", textFragment.TextState.ForegroundColor);
}
}
/// <summary>
/// Written by Fredio
/// </summary>
/// <param name="path"></param>
/// <param name="phrase"></param>
/// <returns></returns>
public System.IO.MemoryStream SearcText(string path, string phrase)
{
InjectAsposeLicemse();
Aspose.Pdf.Document document = new Aspose.Pdf.Document(path);
string searchTextValue = string.Format("(?i){0}", phrase);
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(searchTextValue, new TextSearchOptions(true));
//TextSearchOptions textSearchOptions = new TextSearchOptions(true);
//textFragmentAbsorber.TextSearchOptions = textSearchOptions;
document.Pages.Accept(textFragmentAbsorber);
TextFragmentCollection textFragmentCollection1 = textFragmentAbsorber.TextFragments;
if (textFragmentCollection1.Count > 0)
{
foreach (TextFragment textFragment in textFragmentCollection1)
{
Aspose.Pdf.Annotations.HighlightAnnotation freeText = new Aspose.Pdf.Annotations.HighlightAnnotation(textFragment.Page, new Aspose.Pdf.Rectangle(textFragment.Position.XIndent, textFragment.Position.YIndent, textFragment.Position.XIndent + textFragment.Rectangle.Width, textFragment.Position.YIndent + textFragment.Rectangle.Height));
freeText.Opacity = 0.5;
//freeText.Color = Aspose.Pdf.Color.FromRgb(0.6, 0.8, 0.98);
freeText.Color = Aspose.Pdf.Color.Yellow;
textFragment.Page.Annotations.Add(freeText);
}
}
System.IO.MemoryStream ms = new System.IO.MemoryStream();
document.Save(ms);
return(ms);
}
public static void Run()
{
// ExStart:ReplaceTextAll
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document pdfDocument = new Document(dataDir + "ReplaceTextAll.pdf");
// Create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
// Accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = "TEXT";
textFragment.TextState.Font = FontRepository.FindFont("Verdana");
textFragment.TextState.FontSize = 22;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Blue);
textFragment.TextState.BackgroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Green);
}
dataDir = dataDir + "ReplaceTextAll_out_.pdf";
// Save resulting PDF document.
pdfDocument.Save(dataDir);
// ExEnd:ReplaceTextAll
Console.WriteLine("\nText replaced successfully.\nFile saved at " + dataDir);
}
public static void Main(string[] args)
{
// The path to the documents directory.
string dataDir = Path.GetFullPath("../../../Data/");
//open document
Document pdfDocument = new Document(dataDir + "input.pdf");
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
//accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
//update text and other properties
textFragment.Text = "TEXT";
textFragment.TextState.Font = FontRepository.FindFont("Verdana");
textFragment.TextState.FontSize = 22;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Blue);
textFragment.TextState.BackgroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Green);
}
// Save resulting PDF document.
pdfDocument.Save(dataDir + "output.pdf");
// Let user know about the outcome of the processing.
System.Console.WriteLine("Text replaced successfully!");
}
public ActionResult DownloadCertificate()
{
string dataDir = Server.MapPath("~/Images/test.pdf");
// Open document
Document pdfDocument = new Document(dataDir);
// Create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Name");
// Accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = "HIYA HIYA HIYA";
}
dataDir = dataDir + "test3.pdf";
// Save resulting PDF document.
pdfDocument.Save(dataDir);
return(View());
}
public static void Main(string[] args)
{
// The path to the documents directory.
string dataDir = Path.GetFullPath("../../../Data/");
//open document
Document pdfDocument = new Document(dataDir + "input.pdf");
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
//accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
foreach (TextSegment textSegment in textFragment.Segments)
{
Console.WriteLine("Text : {0} ", textSegment.Text);
Console.WriteLine("Position : {0} ", textSegment.Position);
Console.WriteLine("XIndent : {0} ", textSegment.Position.XIndent);
Console.WriteLine("YIndent : {0} ", textSegment.Position.YIndent);
Console.WriteLine("Font - Name : {0}", textSegment.TextState.Font.FontName);
Console.WriteLine("Font - IsAccessible : {0} ", textSegment.TextState.Font.IsAccessible);
Console.WriteLine("Font - IsEmbedded : {0} ", textSegment.TextState.Font.IsEmbedded);
Console.WriteLine("Font - IsSubset : {0} ", textSegment.TextState.Font.IsSubset);
Console.WriteLine("Font Size : {0} ", textSegment.TextState.FontSize);
Console.WriteLine("Foreground Color : {0} ", textSegment.TextState.ForegroundColor);
}
}
}
public static void Run()
{
// ExStart:ReplaceFirstOccurrence
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document pdfDocument = new Document(dataDir + "ReplaceTextPage.pdf");
// Create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
// Accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
if (textFragmentCollection.Count > 0)
{
// Get first occurance of text and replace
TextFragment textFragment = textFragmentCollection[1];
// Update text and other properties
textFragment.Text = "New Phrase";
textFragment.TextState.Font = FontRepository.FindFont("Verdana");
textFragment.TextState.FontSize = 22;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Blue);
dataDir = dataDir + "ReplaceFirstOccurrence_out_.pdf";
pdfDocument.Save(dataDir);
Console.WriteLine("\nText replaced successfully.\nFile saved at " + dataDir);
}
// ExEnd:ReplaceFirstOccurrence
}
public IHttpActionResult DownloadCertificate(string idEvent, string nameParticipant)
{
string dataDir = "http://localhost:49661/Images/test.pdf";
//HttpWebRequest request = (HttpWebRequest)WebRequest.Create(dataDir);
//HttpWebResponse response = (HttpWebResponse)request.GetResponse();
//Stream receiveStream = response.GetResponseStream();
HttpWebRequest myReq = (HttpWebRequest)WebRequest.Create(dataDir);
WebResponse myResp = myReq.GetResponse();
StreamReader reader = new StreamReader(myResp.GetResponseStream());
Document pdfDocument = new Document(reader.BaseStream);
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Name");
pdfDocument.Pages.Accept(textFragmentAbsorber);
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = nameParticipant;
}
dataDir = dataDir + "/Images/" + idEvent + "_" + nameParticipant + ".pdf";
pdfDocument.Save(dataDir);
return(Ok(dataDir));
}
public static void Run()
{
// ExStart:SearchAndGetTextAll
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document pdfDocument = new Document(dataDir + "SearchAndGetTextFromAll.pdf");
// Create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
// Accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
Console.WriteLine("Text : {0} ", textFragment.Text);
Console.WriteLine("Position : {0} ", textFragment.Position);
Console.WriteLine("XIndent : {0} ", textFragment.Position.XIndent);
Console.WriteLine("YIndent : {0} ", textFragment.Position.YIndent);
Console.WriteLine("Font - Name : {0}", textFragment.TextState.Font.FontName);
Console.WriteLine("Font - IsAccessible : {0} ", textFragment.TextState.Font.IsAccessible);
Console.WriteLine("Font - IsEmbedded : {0} ", textFragment.TextState.Font.IsEmbedded);
Console.WriteLine("Font - IsSubset : {0} ", textFragment.TextState.Font.IsSubset);
Console.WriteLine("Font Size : {0} ", textFragment.TextState.FontSize);
Console.WriteLine("Foreground Color : {0} ", textFragment.TextState.ForegroundColor);
}
// ExEnd:SearchAndGetTextAll
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
//open document
Document pdfDocument = new Document(dataDir + "ReplaceTextPage.pdf");
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("text");
//accept the absorber for a particular page
pdfDocument.Pages[2].Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
//update text and other properties
textFragment.Text = "New Phrase";
textFragment.TextState.Font = FontRepository.FindFont("Verdana");
textFragment.TextState.FontSize = 22;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Blue);
textFragment.TextState.BackgroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Green);
}
pdfDocument.Save(dataDir + "ReplaceTextPage_out.pdf");
}
public static void Run()
{
//ExStart: SearchTextWithDotNetRegex
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Create Regex object to find all words
System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(@"[\S]+");
// Open document
Aspose.Pdf.Document document = new Aspose.Pdf.Document(dataDir + "SearchTextRegex.pdf");
// Get a particular page
Page page = document.Pages[1];
// Create TextAbsorber object to find all instances of the input regex
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(regex);
textFragmentAbsorber.TextSearchOptions.IsRegularExpressionUsed = true;
// Accept the absorber for the page
page.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
Console.WriteLine(textFragment.Text);
}
//ExEnd: SearchTextWithDotNetRegex
}
public static void Run()
{
// ExStart:1
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Annotations();
Document doc = new Document(dataDir + "ExtractHighlightedText.pdf");
// Loop through all the annotations
foreach (Annotation annotation in doc.Pages[1].Annotations)
{
// Filter TextMarkupAnnotation
if (annotation is TextMarkupAnnotation)
{
TextMarkupAnnotation highlightedAnnotation = annotation as TextMarkupAnnotation;
// Retrieve highlighted text fragments
TextFragmentCollection collection = highlightedAnnotation.GetMarkedTextFragments();
foreach (TextFragment tf in collection)
{
// Display highlighted text
Console.WriteLine(tf.Text);
}
}
}
// ExEnd:1
}
static void SearchWithRegularExpression()
{
//open document
Document pdfDocument = new Document(Config.TestPdf);
//create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("\\d{4}-\\d{4}"); //like 1999-2000
//###set text search option to specify regular expression usage
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textFragmentAbsorber.TextSearchOptions = textSearchOptions;
//accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
Console.WriteLine("Text : {0} ", textFragment.Text);
//Console.WriteLine("Position : {0} ", textFragment.Position);
//Console.WriteLine("XIndent : {0} ", textFragment.Position.XIndent);
//Console.WriteLine("YIndent : {0} ", textFragment.Position.YIndent);
//Console.WriteLine("Font - Name : {0}", textFragment.TextState.Font.FontName);
//Console.WriteLine("Font - IsAccessible : {0} ", textFragment.TextState.Font.IsAccessible);
//Console.WriteLine("Font - IsEmbedded : {0} ", textFragment.TextState.Font.IsEmbedded);
//Console.WriteLine("Font - IsSubset : {0} ", textFragment.TextState.Font.IsSubset);
//Console.WriteLine("Font Size : {0} ", textFragment.TextState.FontSize);
//Console.WriteLine("Foreground Color : {0} ", textFragment.TextState.ForegroundColor);
}
}
public static void Run()
{
// ExStart:1
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
string outputFile = dataDir + "Tooltip_out.pdf";
// Create sample document with text
Document doc = new Document();
doc.Pages.Add().Paragraphs.Add(new TextFragment("Move the mouse cursor here to display a tooltip"));
doc.Pages[1].Paragraphs.Add(new TextFragment("Move the mouse cursor here to display a very long tooltip"));
doc.Save(outputFile);
// Open document with text
Document document = new Document(outputFile);
// Create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber absorber = new TextFragmentAbsorber("Move the mouse cursor here to display a tooltip");
// Accept the absorber for the document pages
document.Pages.Accept(absorber);
// Get the extracted text fragments
TextFragmentCollection textFragments = absorber.TextFragments;
// Loop through the fragments
foreach (TextFragment fragment in textFragments)
{
// Create invisible button on text fragment position
ButtonField field = new ButtonField(fragment.Page, fragment.Rectangle);
// AlternateName value will be displayed as tooltip by a viewer application
field.AlternateName = "Tooltip for text.";
// Add button field to the document
document.Form.Add(field);
}
// Next will be sapmle of very long tooltip
absorber = new TextFragmentAbsorber("Move the mouse cursor here to display a very long tooltip");
document.Pages.Accept(absorber);
textFragments = absorber.TextFragments;
foreach (TextFragment fragment in textFragments)
{
ButtonField field = new ButtonField(fragment.Page, fragment.Rectangle);
// Set very long text
field.AlternateName = "Lorem ipsum dolor sit amet, consectetur adipiscing elit," +
" sed do eiusmod tempor incididunt ut labore et dolore magna" +
" aliqua. Ut enim ad minim veniam, quis nostrud exercitation" +
" ullamco laboris nisi ut aliquip ex ea commodo consequat." +
" Duis aute irure dolor in reprehenderit in voluptate velit" +
" esse cillum dolore eu fugiat nulla pariatur. Excepteur sint" +
" occaecat cupidatat non proident, sunt in culpa qui officia" +
" deserunt mollit anim id est laborum.";
document.Form.Add(field);
}
// Save document
document.Save(outputFile);
// ExEnd:1
}
public IHttpActionResult ReplaceText(ReplaceTextModel replaceTextModel)
{
var documentFileName = System.IO.Path.Combine(Config.Configuration.WorkingDirectory, "Editor", replaceTextModel.documentId, "document.pdf");
try
{
Document doc = new Document(documentFileName);
// TODO: Imporve alghorithm
//create TextAbsorber object to find all instances of the input search phrase
//TextFragmentAbsorber textFragmentAbsorber =
// new TextFragmentAbsorber("(?i)" + replaceTextModel.txtFind, new TextSearchOptions(true))
// {
// TextReplaceOptions =
// {
// ReplaceAdjustmentAction = TextReplaceOptions.ReplaceAdjustment.WholeWordsHyphenation
// }
// };
TextFragmentAbsorber textFragmentAbsorber =
new TextFragmentAbsorber(replaceTextModel.txtFind);
doc.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
//update text and other properties
textFragment.Text = replaceTextModel.txtReplace;
}
doc.Save(documentFileName);
//doc = new Document(HttpContext.Current.Server.MapPath("Convert/output.pdf"));
var downloadedMessageInfo = new DirectoryInfo(Path.GetDirectoryName(documentFileName));
foreach (FileInfo file in downloadedMessageInfo.GetFiles("*.png"))
{
file.Delete();
}
var model = new DocStatusModel
{
d = ImageConverter(documentFileName),
Path = replaceTextModel.documentId
};
return(Ok(replaceTextModel));
}
catch (Exception ex)
{
return(InternalServerError(ex));
}
}
public void HideHeader(string fileName, string newFileName, Document pdfDocument)
{
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Employment History");
pdfDocument.Pages[1].Accept(textFragmentAbsorber);
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
if (textFragmentCollection.Any())
{
foreach (TextFragment textFragment in textFragmentCollection)
{
textFragment.TextState.Invisible = true;
}
}
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
//open document
Document pdfDocument = new Document(dataDir + "SearchRegularExpressionPage.pdf");
//create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("\\d{4}-\\d{4}"); //like 1999-2000
//set text search option to specify regular expression usage
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textFragmentAbsorber.TextSearchOptions = textSearchOptions;
//accept the absorber for a single page
pdfDocument.Pages[1].Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
Console.WriteLine("Text : {0} ", textFragment.Text);
Console.WriteLine("Position : {0} ", textFragment.Position);
Console.WriteLine("XIndent : {0} ",
textFragment.Position.XIndent);
Console.WriteLine("YIndent : {0} ",
textFragment.Position.YIndent);
Console.WriteLine("Font - Name : {0}",
textFragment.TextState.Font.FontName);
Console.WriteLine("Font - IsAccessible : {0} ",
textFragment.TextState.Font.IsAccessible);
Console.WriteLine("Font - IsEmbedded : {0} ",
textFragment.TextState.Font.IsEmbedded);
Console.WriteLine("Font - IsSubset : {0} ",
textFragment.TextState.Font.IsSubset);
Console.WriteLine("Font Size : {0} ",
textFragment.TextState.FontSize);
Console.WriteLine("Foreground Color : {0} ",
textFragment.TextState.ForegroundColor);
}
}
public IHttpActionResult DownloadCertificate(string idEvent, string nameParticipant)
{
string dataDir = HttpContext.Current.Request.UserHostName;
Document pdfDocument = new Document(dataDir + "/Images/test.pdf");
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Name");
pdfDocument.Pages.Accept(textFragmentAbsorber);
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = nameParticipant;
}
dataDir = dataDir + "/Images/" + idEvent + "_" + nameParticipant + ".pdf";
pdfDocument.Save(dataDir);
return(Ok());
}
public int Highlight(Document pdfDocument, List <string> highlightPhrases)
{
int highlights = 0;
TextFragmentAbsorber textAbsorder;
foreach (string higlightPhrase in highlightPhrases)
{
textAbsorder = new TextFragmentAbsorber("(?i)" + higlightPhrase, new TextSearchOptions(true));
TextFragmentCollection txtFragmentCollection = textAbsorder.TextFragments;
pdfDocument.Pages.Accept(textAbsorder);
highlights += txtFragmentCollection.Count;
foreach (TextFragment tf in txtFragmentCollection)
{
tf.TextState.BackgroundColor = Color.Yellow;
}
}
return(highlights);
}
public static void Run()
{
// ExStart:ReplaceTextonRegularExpression
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document pdfDocument = new Document(dataDir + "SearchRegularExpressionPage.pdf");
// Create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("\\d{4}-\\d{4}"); //like 1999-2000
// Set text search option to specify regular expression usage
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textFragmentAbsorber.TextSearchOptions = textSearchOptions;
// Accept the absorber for a single page
pdfDocument.Pages[1].Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = "New Phrase";
// Set to an instance of an object.
textFragment.TextState.Font = FontRepository.FindFont("Verdana");
textFragment.TextState.FontSize = 22;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Blue);
textFragment.TextState.BackgroundColor = Aspose.Pdf.Color.FromRgb(System.Drawing.Color.Green);
}
dataDir = dataDir + "ReplaceTextonRegularExpression_out_.pdf";
pdfDocument.Save(dataDir);
// ExEnd:ReplaceTextonRegularExpression
Console.WriteLine("\nText replaced successfully based on a regular expression.\nFile saved at " + dataDir);
}
public static void Run()
{
// ExStart:ExtractColumnsText
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document pdfDocument = new Document(dataDir + "ExtractTextPage.pdf");
TextFragmentAbsorber tfa = new TextFragmentAbsorber();
pdfDocument.Pages.Accept(tfa);
TextFragmentCollection tfc = tfa.TextFragments;
foreach (TextFragment tf in tfc)
{
// Need to reduce font size at least for 70%
tf.TextState.FontSize = tf.TextState.FontSize * 0.7f;
}
Stream st = new MemoryStream();
pdfDocument.Save(st);
pdfDocument = new Document(st);
TextAbsorber textAbsorber = new TextAbsorber();
pdfDocument.Pages.Accept(textAbsorber);
String extractedText = textAbsorber.Text;
textAbsorber.Visit(pdfDocument);
dataDir = dataDir + "ExtractColumnsText_out.txt";
System.IO.File.WriteAllText(dataDir, extractedText);
// ExEnd:ExtractColumnsText
Console.WriteLine("\nColumns text extracted successfully from Pages of PDF Document.\nFile saved at " + dataDir);
}
public static string ReplaceText(string txtFind, string txtReplace, string[] pageList)
{
try
{
Document doc = new Document(HttpContext.Current.Server.MapPath("Convert/output.pdf"));
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("(?i)" + txtFind, new Aspose.Pdf.Text.TextOptions.TextSearchOptions(true));
textFragmentAbsorber.TextReplaceOptions.ReplaceAdjustmentAction = TextReplaceOptions.ReplaceAdjustment.WholeWordsHyphenation;
//accept the absorber for all the pages
doc.Pages.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
//update text and other properties
textFragment.Text = txtReplace;
}
doc.Save(HttpContext.Current.Server.MapPath("Convert/output.pdf"));
doc = new Document(HttpContext.Current.Server.MapPath("Convert/output.pdf"));
System.IO.DirectoryInfo downloadedMessageInfo = new DirectoryInfo(HttpContext.Current.Server.MapPath("Input/"));
foreach (FileInfo file in downloadedMessageInfo.GetFiles())
{
file.Delete();
}
for (int pageCount = 1; pageCount <= doc.Pages.Count; pageCount++)
{
string filename = "Input/" + pageList[pageCount - 1];
filename = filename.Replace("image", "image-1");
using (FileStream imageStream = new FileStream(HttpContext.Current.Server.MapPath(filename), FileMode.Create))
{
//Create Resolution object
Resolution resolution = new Resolution(300);
//create PNG device with specified attributes
PngDevice pngDevice = new PngDevice();
//Convert a particular page and save the image to stream
pngDevice.Process(doc.Pages[pageCount], imageStream);
//Close stream
imageStream.Close();
System.Drawing.Image image = System.Drawing.Image.FromFile(HttpContext.Current.Server.MapPath(filename));
string height = "";
string Aratio = "";
ScaleImage(image, 1138, 760, HttpContext.Current.Server.MapPath(filename.Replace("image-1", "image")), out height, out Aratio);
image.Dispose();
}
}
}
catch (Exception exp)
{
}
return("success");
}
public static string SearchData(string searchText, string[] pageList)
{
string name = DateTime.Now.Millisecond.ToString();
System.IO.DirectoryInfo downloadedMessageInfo = new DirectoryInfo(HttpContext.Current.Server.MapPath("search/"));
foreach (FileInfo file in downloadedMessageInfo.GetFiles())
{
file.Delete();
}
foreach (DirectoryInfo dir in downloadedMessageInfo.GetDirectories())
{
dir.Delete(true);
}
System.IO.Directory.CreateDirectory(HttpContext.Current.Server.MapPath("search/" + name));
Document doc = new Document(HttpContext.Current.Server.MapPath("Convert/output.pdf"));
for (int i = 1; i <= doc.Pages.Count; i++)
{
string filename = "Input/" + pageList[i - 1];
filename = filename.Replace("image", "image-1");
Bitmap bmp = (Bitmap)Bitmap.FromFile(HttpContext.Current.Server.MapPath(filename));
using (System.Drawing.Graphics gr = System.Drawing.Graphics.FromImage(bmp))
{
float scale = 150 / 72f;
gr.Transform = new System.Drawing.Drawing2D.Matrix(scale, 0, 0, -scale, 0, bmp.Height);
Aspose.Pdf.Page page = doc.Pages[i];
//create TextAbsorber object to find all words
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(searchText);
// textFragmentAbsorber.TextSearchOptions.IsRegularExpressionUsed = true;
page.Accept(textFragmentAbsorber);
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
Brush brush = new SolidBrush(System.Drawing.Color.FromArgb(50, 255, 255, 0));
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
// if (i == 0)
{
gr.FillRectangle(
// gr.DrawRectangle(
brush,
(float)(textFragment.Position.XIndent),
(float)(textFragment.Position.YIndent),
(float)(textFragment.Rectangle.Width),
(float)(textFragment.Rectangle.Height));
for (int segNum = 1; segNum <= textFragment.Segments.Count; segNum++)
{
TextSegment segment = textFragment.Segments[segNum];
gr.DrawRectangle(
Pens.Green,
(float)segment.Rectangle.LLX,
(float)segment.Rectangle.LLY,
(float)segment.Rectangle.Width,
(float)segment.Rectangle.Height);
}
}
}
gr.Dispose();
}
bmp.Save(HttpContext.Current.Server.MapPath(filename.Replace("image-1", "image_search")), System.Drawing.Imaging.ImageFormat.Png);
bmp.Dispose();
string height = "";
string Aratio = "";
System.Drawing.Image image = System.Drawing.Image.FromFile(HttpContext.Current.Server.MapPath(filename.Replace("image-1", "image_search")));
ScaleImage(image, 1138, 760, HttpContext.Current.Server.MapPath("search/" + name + "/" + pageList[i - 1]), out height, out Aratio);
image.Dispose();
// System.IO.File.Copy(HttpContext.Current.Server.MapPath("Input/image_search" + i + ".png"), HttpContext.Current.Server.MapPath("Input/image" + i + ".png"));
}
return(name);
}
public static void Run()
{
try
{
// ExStart:HighlightCharacterInPDF
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
int resolution = 150;
Aspose.Pdf.Document pdfDocument = new Aspose.Pdf.Document(dataDir + "input.pdf");
using (MemoryStream ms = new MemoryStream())
{
PdfConverter conv = new PdfConverter(pdfDocument);
conv.Resolution = new Resolution(resolution, resolution);
conv.GetNextImage(ms, System.Drawing.Imaging.ImageFormat.Png);
Bitmap bmp = (Bitmap)Bitmap.FromStream(ms);
using (System.Drawing.Graphics gr = System.Drawing.Graphics.FromImage(bmp))
{
float scale = resolution / 72f;
gr.Transform = new System.Drawing.Drawing2D.Matrix(scale, 0, 0, -scale, 0, bmp.Height);
for (int i = 0; i < pdfDocument.Pages.Count; i++)
{
Page page = pdfDocument.Pages[1];
// Create TextAbsorber object to find all words
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(@"[\S]+");
textFragmentAbsorber.TextSearchOptions.IsRegularExpressionUsed = true;
page.Accept(textFragmentAbsorber);
// Get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
if (i == 0)
{
gr.DrawRectangle(
Pens.Yellow,
(float)textFragment.Position.XIndent,
(float)textFragment.Position.YIndent,
(float)textFragment.Rectangle.Width,
(float)textFragment.Rectangle.Height);
for (int segNum = 1; segNum <= textFragment.Segments.Count; segNum++)
{
TextSegment segment = textFragment.Segments[segNum];
for (int charNum = 1; charNum <= segment.Characters.Count; charNum++)
{
CharInfo characterInfo = segment.Characters[charNum];
Aspose.Pdf.Rectangle rect = page.GetPageRect(true);
Console.WriteLine("TextFragment = " + textFragment.Text + " Page URY = " + rect.URY +
" TextFragment URY = " + textFragment.Rectangle.URY);
gr.DrawRectangle(
Pens.Black,
(float)characterInfo.Rectangle.LLX,
(float)characterInfo.Rectangle.LLY,
(float)characterInfo.Rectangle.Width,
(float)characterInfo.Rectangle.Height);
}
gr.DrawRectangle(
Pens.Green,
(float)segment.Rectangle.LLX,
(float)segment.Rectangle.LLY,
(float)segment.Rectangle.Width,
(float)segment.Rectangle.Height);
}
}
}
}
}
dataDir = dataDir + "HighlightCharacterInPDF_out.png";
bmp.Save(dataDir, System.Drawing.Imaging.ImageFormat.Png);
}
// ExEnd:HighlightCharacterInPDF
Console.WriteLine("\nCharacters highlighted successfully in pdf document.\nFile saved at " + dataDir);
}
catch (Exception ex)
{
Console.WriteLine(ex.Message + "\nThis example will only work if you apply a valid Aspose License. You can purchase full license or get 30 day temporary license from http:// Www.aspose.com/purchase/default.aspx.");
}
}
private void btnCreate_Click(object sender, EventArgs e)
{
if (txtFilePath.Text != String.Empty)
{
Document doc = new Document(txtFilePath.Text);
Document newDoc = new Document();
if (rdoRange.Checked)
{
for (decimal i = txtFrom.Value; i <= txtTo.Value; i++)
{
newDoc.Pages.Add(doc.Pages[Convert.ToInt32(i)]);
}
newDoc.Save("output_" + DateTime.Now.Millisecond + ".pdf");
MessageBox.Show("Document has been created.", "Success");
}
else if (rdoNumber.Checked)
{
try
{
string[] pages = txtPageNumbers.Text.Split(',');
foreach (string s in pages)
{
newDoc.Pages.Add(doc.Pages[Convert.ToInt32(s)]);
}
newDoc.Save("output_" + DateTime.Now.Millisecond + ".pdf");
MessageBox.Show("Document has been created.", "Success");
}
catch (Exception ex)
{
MessageBox.Show("Error in processing Page Numbers. Some values are not in correct format.\n" + ex.Message, "Error");
}
}
else
{
if (txtSearchText.Text != String.Empty)
{
TextFragmentAbsorber absorber = new TextFragmentAbsorber(txtSearchText.Text, new TextSearchOptions(true));
doc.Pages.Accept(absorber);
TextFragmentCollection collection = absorber.TextFragments;
List <int> pagenumbers = new List <int>();
if (collection.Count > 0)
{
foreach (TextFragment textFragment in collection)
{
if (pagenumbers.Contains(textFragment.Page.Number))
{
continue;
}
else
{
pagenumbers.Add(textFragment.Page.Number);
}
}
foreach (int s in pagenumbers)
{
newDoc.Pages.Add(doc.Pages[s]);
}
newDoc.Save("output_" + DateTime.Now.Millisecond + ".pdf");
MessageBox.Show("Document has been created.", "Success");
}
else
{
MessageBox.Show("No Results found against Search.", "No Results");
}
}
else
{
MessageBox.Show("Please Enter a Search Term.", "No Search Term");
}
}
}
else
{
MessageBox.Show("Please Select a PDF File First.", "File Not Found");
}
}
static void Main(string[] args)
{
//License license = new Aspose.Pdf.License();
//license.SetLicense("Aspose.Pdf.lic");
SqlConnection con = new SqlConnection(constr);
con.Open();
SqlCommand cmd = new SqlCommand("spconfiguration", con);
cmd.CommandType = CommandType.StoredProcedure;
SqlDataReader dr = cmd.ExecuteReader();
dr.Read();
source = dr["FTPURLSource"].ToString();
destination = dr["FTPURLDestination"].ToString();
dr.Close();
con.Close();
string mydir = source + @"\";
string[] myfiles = Directory.GetFiles(mydir + "").Select(Path.GetFileName).ToArray();
foreach (var i in myfiles)
{
if (i.Contains("HSBC"))
{
string sub = "HSBC SA " + i.Split(' ', '.')[2];
string sub1 = i.Split(' ', '.')[2];
//string sub = str.Substring(8, 6);
//string sub1 = rowString.Substring(0, 3);
//string sub = rowString.Replace('"', ' ').Trim();
if (sub.Contains("DPM"))
{
Document pdfDocument = new Document(mydir + i);
//create TextAbsorber object to find all instances of the input search phrase
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber(sub);
//accept the absorber for all the pages
pdfDocument.Pages.Accept(textFragmentAbsorber);
SqlCommand com1 = new SqlCommand("spGetMaster", con);
con.Open();
com1.CommandType = CommandType.StoredProcedure;
com1.Parameters.Add("@masked", SqlDbType.VarChar).Value = sub1;
com1.ExecuteNonQuery();
SqlDataReader reader = com1.ExecuteReader();
reader.Read();
if (reader.HasRows)
{
//update text and other properties
CustName = reader["de_masked"].ToString();
reader.Close();
//get the extracted text fragments
TextFragmentCollection textFragmentCollection = textFragmentAbsorber.TextFragments;
//loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
//string str = "select de_masked from master where Masked='" + sub.ToString() + "'";
SqlCommand com = new SqlCommand("spGetMaster", con);
com.CommandType = CommandType.StoredProcedure;
com.Parameters.Add("@masked", SqlDbType.VarChar).Value = sub1;
com.ExecuteNonQuery();
SqlDataReader reader1 = com.ExecuteReader();
reader1.Read();
//update text and other properties
string CustName1 = reader1["de_masked"].ToString();
textFragment.Text = CustName1;
reader1.Close();
}
//setting password to pdf
SqlCommand cmd1 = new SqlCommand("spGetMaster", con);
cmd1.CommandType = CommandType.StoredProcedure;
cmd1.Parameters.Add("masked", SqlDbType.VarChar).Value = sub1;
cmd1.ExecuteNonQuery();
SqlDataReader rd = cmd1.ExecuteReader();
rd.Read();
string pass = rd["pdfpassword"].ToString();
custEmail = rd["Email"].ToString();
ccemail = rd["ccemail"].ToString();
pdfDocument.Encrypt(pass, "", 0, CryptoAlgorithm.RC4x128);
rd.Close();
newfilename = i + ".pdf";
pdfDocument.Save(destination + @"\" + newfilename);
sendEmail();
insertdata();
//setpass();
string oldfile = mydir + i;
File.Delete(oldfile);
}
con.Close();
}
}
}
}
public static void Run()
{
// ExStart:1
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
string outputFile = dataDir + "TextBlock_HideShow_MouseOverOut_out.pdf";
// Create sample document with text
Document doc = new Document();
doc.Pages.Add().Paragraphs.Add(new TextFragment("Move the mouse cursor here to display floating text"));
doc.Save(outputFile);
// Open document with text
Document document = new Document(outputFile);
// Create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber absorber = new TextFragmentAbsorber("Move the mouse cursor here to display floating text");
// Accept the absorber for the document pages
document.Pages.Accept(absorber);
// Get the first extracted text fragment
TextFragmentCollection textFragments = absorber.TextFragments;
TextFragment fragment = textFragments[1];
// Create hidden text field for floating text in the specified rectangle of the page
TextBoxField floatingField = new TextBoxField(fragment.Page, new Rectangle(100, 700, 220, 740));
// Set text to be displayed as field value
floatingField.Value = "This is the \"floating text field\".";
// We recommend to make field 'readonly' for this scenario
floatingField.ReadOnly = true;
// Set 'hidden' flag to make field invisible on document opening
floatingField.Flags |= AnnotationFlags.Hidden;
// Setting a unique field name isn't necessary but allowed
floatingField.PartialName = "FloatingField_1";
// Setting characteristics of field appearance isn't necessary but makes it better
floatingField.DefaultAppearance = new DefaultAppearance("Helv", 10, System.Drawing.Color.Blue);
floatingField.Characteristics.Background = System.Drawing.Color.LightBlue;
floatingField.Characteristics.Border = System.Drawing.Color.DarkBlue;
floatingField.Border = new Border(floatingField);
floatingField.Border.Width = 1;
floatingField.Multiline = true;
// Add text field to the document
document.Form.Add(floatingField);
// Create invisible button on text fragment position
ButtonField buttonField = new ButtonField(fragment.Page, fragment.Rectangle);
// Create new hide action for specified field (annotation) and invisibility flag.
// (You also may reffer floating field by the name if you specified it above.)
// Add actions on mouse enter/exit at the invisible button field
buttonField.Actions.OnEnter = new HideAction(floatingField, false);
buttonField.Actions.OnExit = new HideAction(floatingField);
// Add button field to the document
document.Form.Add(buttonField);
// Save document
document.Save(outputFile);
// ExEnd:1
}
