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);
}
}
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 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()
{
// 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");
// ExStart: SearchInsideText
// Accept the absorber for a particular page
pdfDocument.Pages[2].Accept(textFragmentAbsorber);
// ExEnd: SearchInsideText
// 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 void LoadPdf()
{
//ExStart
//ExFor:Document.#ctor(String)
//ExSummary:Shows how to load a PDF.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
builder.Write("Hello world!");
doc.Save(ArtifactsDir + "PDF2Word.LoadPdf.pdf");
// Below are two ways of loading PDF documents using Aspose products.
// 1 - Load as an Aspose.Words document:
Aspose.Words.Document asposeWordsDoc = new Aspose.Words.Document(ArtifactsDir + "PDF2Word.LoadPdf.pdf");
Assert.AreEqual("Hello world!", asposeWordsDoc.GetText().Trim());
// 2 - Load as an Aspose.Pdf document:
Aspose.Pdf.Document asposePdfDoc = new Aspose.Pdf.Document(ArtifactsDir + "PDF2Word.LoadPdf.pdf");
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber();
asposePdfDoc.Pages.Accept(textFragmentAbsorber);
Assert.AreEqual("Hello world!", textFragmentAbsorber.Text.Trim());
//ExEnd
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
//open document
Document pdfDocument = new Document(dataDir + "SearchAndGetTextAll.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);
}
}
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
}
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);
}
}
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);
}
}
public void WithoutUpdateFields()
{
//ExStart
//ExFor:SaveOptions.UpdateFields
//ExSummary:Shows how to update fields before saving into a PDF document.
Document doc = DocumentHelper.CreateDocumentFillWithDummyText();
PdfSaveOptions pdfSaveOptions = new PdfSaveOptions
{
UpdateFields = false
};
doc.Save(MyDir + @"\Artifacts\UpdateFields_False.pdf", pdfSaveOptions);
//ExEnd
Aspose.Pdf.Document pdfDocument = new Aspose.Pdf.Document(MyDir + @"\Artifacts\UpdateFields_False.pdf");
// Get text fragment by search String
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Page of");
pdfDocument.Pages.Accept(textFragmentAbsorber);
// Assert that fields are not updated
Assert.AreEqual("Page of", textFragmentAbsorber.TextFragments[1].Text);
}
private void btnExtractTitles_Click(object sender, EventArgs e)
{
try
{
if (!String.IsNullOrEmpty(txtLicense.Text) && !String.IsNullOrEmpty(txtPDF.Text))
{
Document doc = new Document(txtPDF.Text);
foreach (Page page in doc.Pages)
{
TextFragmentAbsorber absorber = new TextFragmentAbsorber();
page.Accept(absorber);
if (lstTitles.Items.Contains(absorber.TextFragments[1].Text))
{
continue;
}
lstTitles.Items.Add(absorber.TextFragments[1].Text);
page.Dispose();
}
}
else
{
MessageBox.Show("Please select License and PDF file first.", "No File Selected");
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error");
}
}
public static void Run()
{
try
{
// ExStart:RemoveUnusedFonts
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Load source PDF file
Document doc = new Document(dataDir + "ReplaceTextPage.pdf");
TextFragmentAbsorber absorber = new TextFragmentAbsorber(new TextEditOptions(TextEditOptions.FontReplace.RemoveUnusedFonts));
doc.Pages.Accept(absorber);
// Iterate through all the TextFragments
foreach (TextFragment textFragment in absorber.TextFragments)
{
textFragment.TextState.Font = FontRepository.FindFont("Arial, Bold");
}
dataDir = dataDir + "RemoveUnusedFonts_out_.pdf";
// Save updated document
doc.Save(dataDir);
// ExEnd:RemoveUnusedFonts
Console.WriteLine("\nUnused fonts removed successfully from 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.");
}
}
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:SearchTextAndDrawRectangle
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document document = new Document(dataDir + "SearchAndGetTextFromAll.pdf");
// Create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber textAbsorber = new TextFragmentAbsorber(@"[\S]+");
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textAbsorber.TextSearchOptions = textSearchOptions;
document.Pages.Accept(textAbsorber);
var editor = new PdfContentEditor(document);
foreach (TextFragment textFragment in textAbsorber.TextFragments)
{
foreach (TextSegment textSegment in textFragment.Segments)
{
DrawBox(editor, textFragment.Page.Number, textSegment, System.Drawing.Color.Red);
}
}
dataDir = dataDir + "SearchTextAndDrawRectangle_out.pdf";
document.Save(dataDir);
// ExEnd:SearchTextAndDrawRectangle
Console.WriteLine("\nRectangle drawn successfully on searched text.\nFile saved at " + dataDir);
}
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 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 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 static void Run()
{
//ExStart: AddAndSearchHiddenText
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
//Create document with hidden text
Aspose.Pdf.Document doc = new Aspose.Pdf.Document();
Page page = doc.Pages.Add();
TextFragment frag1 = new TextFragment("This is common text.");
TextFragment frag2 = new TextFragment("This is invisible text.");
//Set text property - invisible
frag2.TextState.Invisible = true;
page.Paragraphs.Add(frag1);
page.Paragraphs.Add(frag2);
doc.Save(dataDir + "39400_out.pdf");
doc.Dispose();
//Search text in the document
doc = new Aspose.Pdf.Document(dataDir + "39400_out.pdf");
TextFragmentAbsorber absorber = new TextFragmentAbsorber();
absorber.Visit(doc.Pages[1]);
foreach (TextFragment fragment in absorber.TextFragments)
{
//Do something with fragments
Console.WriteLine("Text '{0}' on pos {1} invisibility: {2} ",
fragment.Text, fragment.Position.ToString(), fragment.TextState.Invisible);
}
doc.Dispose();
//ExEnd: AddAndSearchHiddenText
}
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 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 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 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 + "output.pdf");
}
public static void Run()
{
// ExStart:1
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_DocumentConversion();
Document doc = new Document(dataDir + "SampleHtmlFile.html", new HtmlLoadOptions());
doc.Save(new MemoryStream());
foreach (Annotation a in doc.Pages[1].Annotations)
{
if (a.AnnotationType == AnnotationType.Link)
{
LinkAnnotation la = (LinkAnnotation)a;
if (la.Action is GoToURIAction)
{
GoToURIAction gta = (GoToURIAction)la.Action;
gta.URI = "";
TextFragmentAbsorber tfa = new TextFragmentAbsorber();
tfa.TextSearchOptions = new TextSearchOptions(a.Rect);
doc.Pages[a.PageIndex].Accept(tfa);
foreach (TextFragment tf in tfa.TextFragments)
{
tf.TextState.Underline = false;
tf.TextState.ForegroundColor = Color.Black;
}
}
doc.Pages[a.PageIndex].Annotations.Delete(a);
}
}
doc.Save(dataDir + "RemoveHyperlinksFromText_out.pdf");
// ExEnd:1
}
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);
}
}
}
/// <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()
{
try
{
// ExStart:RearrangeContentsUsingTextReplacement
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Load source PDF file
Document doc = new Document(dataDir + "ExtractTextPage.pdf");
// Create TextFragment Absorber object with regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("[TextFragmentAbsorber,companyname,Textbox,50]");
doc.Pages.Accept(textFragmentAbsorber);
// Replace each TextFragment
foreach (TextFragment textFragment in textFragmentAbsorber.TextFragments)
{
// Set font of text fragment being replaced
textFragment.TextState.Font = FontRepository.FindFont("Arial");
// Set font size
textFragment.TextState.FontSize = 12;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.Navy;
// Replace the text with larger string than placeholder
textFragment.Text = "This is a Larger String for the Testing of this issue";
}
dataDir = dataDir + "RearrangeContentsUsingTextReplacement_out_.pdf";
// Save resultant PDF
doc.Save(dataDir);
// ExEnd:RearrangeContentsUsingTextReplacement
Console.WriteLine("\nContents rearranged successfully using text replacement.\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.");
}
}
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 Run()
{
try
{
// ExStart:RearrangeContentsUsingTextReplacement
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Load source PDF file
Document doc = new Document(dataDir + "ExtractTextPage.pdf");
// Create TextFragment Absorber object with regular expression
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("[TextFragmentAbsorber,companyname,Textbox,50]");
doc.Pages.Accept(textFragmentAbsorber);
// Replace each TextFragment
foreach (TextFragment textFragment in textFragmentAbsorber.TextFragments)
{
// Set font of text fragment being replaced
textFragment.TextState.Font = FontRepository.FindFont("Arial");
// Set font size
textFragment.TextState.FontSize = 12;
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.Navy;
// Replace the text with larger string than placeholder
textFragment.Text = "This is a Larger String for the Testing of this issue";
}
dataDir = dataDir + "RearrangeContentsUsingTextReplacement_out.pdf";
// Save resultant PDF
doc.Save(dataDir);
// ExEnd:RearrangeContentsUsingTextReplacement
Console.WriteLine("\nContents rearranged successfully using text replacement.\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.");
}
}
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 static void Run()
{
// ExStart:TextSegments
TextFragmentAbsorber textFragmentAbsorber;
// In order to search exact match of a word, you may consider using regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"\bWord\b", new TextSearchOptions(true));
// In order to search a string in either upper case or lowercase, you may consider using regular expression.
textFragmentAbsorber = new TextFragmentAbsorber("(?i)Line", new TextSearchOptions(true));
// In order to search all the strings (parse all strings) inside PDF document, please try using following regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"[\S]+");
// Find match of search string and get anything after the string till line break.
textFragmentAbsorber = new TextFragmentAbsorber(@"(?i)the ((.)*)");
// Please use following regular expression to find text following to the regex match.
textFragmentAbsorber = new TextFragmentAbsorber(@"(?<=word).*");
// In order to search Hyperlink/URL's inside PDF document, please try using following regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"(http|ftp|https):\/\/([\w\-_]+(?:(?:\.[\w\-_]+)+))([\w\-\.,@?^=%&:/~\+#]*[\w\-\@?^=%&/~\+#])?");
// ExEnd: TextSegments
}
public static void Run()
{
try
{
// ExStart:RemoveUnusedFonts
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Load source PDF file
Document doc = new Document(dataDir + "ReplaceTextPage.pdf");
TextFragmentAbsorber absorber = new TextFragmentAbsorber(new TextEditOptions(TextEditOptions.FontReplace.RemoveUnusedFonts));
doc.Pages.Accept(absorber);
// Iterate through all the TextFragments
foreach (TextFragment textFragment in absorber.TextFragments)
{
textFragment.TextState.Font = FontRepository.FindFont("Arial, Bold");
}
dataDir = dataDir + "RemoveUnusedFonts_out.pdf";
// Save updated document
doc.Save(dataDir);
// ExEnd:RemoveUnusedFonts
Console.WriteLine("\nUnused fonts removed successfully from 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.");
}
}
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);
}
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 async Task <MemoryStream> SubsituteValuesForPdf(string fileName, Dictionary <string, string> valuesToSubsitute)
{
var pdfStream = await GetBlobDataFromAzure(ConfigurationName, fileName);
await SetPdfLicense();
var pdfDocument = new Document(pdfStream);
foreach (var key in valuesToSubsitute)
{
var textFragmentAbsorber = new TextFragmentAbsorber($"__{key.Key}__")
{
TextSearchOptions = new TextSearchOptions(true)
};
pdfDocument.Pages[1].Accept(textFragmentAbsorber);
// Get the extracted text fragments
var textFragmentCollection = textFragmentAbsorber.TextFragments;
// Loop through the fragments
foreach (TextFragment textFragment in textFragmentCollection)
{
// Update text and other properties
textFragment.Text = key.Value;
textFragment.TextState.FontStyle = FontStyles.Bold;
}
}
var streamOutput = new MemoryStream();
pdfDocument.Save(streamOutput);
return(streamOutput);
}
public static void Run()
{
// ExStart:TextSegments
TextFragmentAbsorber textFragmentAbsorber;
// In order to search exact match of a word, you may consider using regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"\bWord\b", new TextSearchOptions(true));
// In order to search a string in either upper case or lowercase, you may consider using regular expression.
textFragmentAbsorber = new TextFragmentAbsorber("(?i)Line", new TextSearchOptions(true));
// In order to search all the strings (parse all strings) inside PDF document, please try using following regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"[\S]+");
// Find match of search string and get anything after the string till line break.
textFragmentAbsorber = new TextFragmentAbsorber(@"(?i)the ((.)*)");
// Please use following regular expression to find text following to the regex match.
textFragmentAbsorber = new TextFragmentAbsorber(@"(?<=word).*");
// In order to search Hyperlink/URL's inside PDF document, please try using following regular expression.
textFragmentAbsorber = new TextFragmentAbsorber(@"(http|ftp|https):\/\/([\w\-_]+(?:(?:\.[\w\-_]+)+))([\w\-\.,@?^=%&:/~\+#]*[\w\-\@?^=%&/~\+#])?");
// ExEnd: TextSegments
}
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
}
private static void AssertPage1HasText(this Document pdf, string fileName, string text)
{
var contractReferenceAbsorber = new TextFragmentAbsorber(text);
pdf.Pages[1].Accept(contractReferenceAbsorber);
Assert.AreEqual(1, contractReferenceAbsorber.TextFragments.Count, $"Could not find {text} for {fileName}");
}
private static TextFragmentAbsorber FindPageForText(Document document, string text)
{
var textFragmentAbsorber = new TextFragmentAbsorber("(?i)" + text, new TextSearchOptions(true));
textFragmentAbsorber.Visit(document);
return(textFragmentAbsorber);
}
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));
}
}
private void btnCreateTOC_Click(object sender, EventArgs e)
{
try
{
if (lstTitles.Items.Count > 0)
{
Document doc = new Document(txtPDF.Text);
Page tocPage = doc.Pages.Insert(1);
// Create object to represent TOC information
TocInfo tocInfo = new TocInfo();
TextFragment title = new TextFragment("Table Of Contents");
title.TextState.FontSize = 20;
title.TextState.FontStyle = FontStyles.Bold;
// Set the title for TOC
tocInfo.Title = title;
tocPage.TocInfo = tocInfo;
foreach (var item in lstTitles.Items)
{
TextFragmentAbsorber absorber = new TextFragmentAbsorber(item.ToString());
doc.Pages.Accept(absorber);
Page targetPage = doc.Pages[absorber.TextFragments[1].Page.Number];
// Create Heading object
Aspose.Pdf.Heading heading2 = new Aspose.Pdf.Heading(1);
TextSegment segment2 = new TextSegment();
heading2.TocPage = tocPage;
heading2.Segments.Add(segment2);
// Specify the destination page for heading object
heading2.DestinationPage = targetPage;
// Destination page
heading2.Top = targetPage.Rect.Height;
// Destination coordinate
segment2.Text = item.ToString();
// Add heading to page containing TOC
tocPage.Paragraphs.Add(heading2);
}
doc.Save("Toc_out.pdf");
MessageBox.Show("PDF with TOC has been created.", "Success");
}
else
{
MessageBox.Show("Please extract titles from PDF document first.", "Titles are not extracted");
}
}
catch (Exception ex)
{
MessageBox.Show(ex.Message, "Error");
}
}
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);
}
}
private static HeaderElement ExtractToHeaderElement(ITaggedContent taggedContent, Page page, int textIndex, int headerLevel = 1)
{
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber();
page.Accept(textFragmentAbsorber);
TextFragment originalHeaderText = textFragmentAbsorber.TextFragments[textIndex];
HeaderElement h1 = taggedContent.CreateHeaderElement(headerLevel);
h1.StructureTextState.ForegroundColor = originalHeaderText.TextState.ForegroundColor;
Font headerFont = FontRepository.FindFont(originalHeaderText.TextState.Font.FontName);
headerFont.IsEmbedded = true;
h1.StructureTextState.Font = headerFont;
h1.SetText(originalHeaderText.Text);
return(h1);
}
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 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[2].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()
{
try
{
// ExStart:UpdateLinkTextColor
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_LinksActions();
// Load the PDF file
Document doc = new Document(dataDir + "UpdateLinks.pdf");
foreach (Annotation annotation in doc.Pages[1].Annotations)
{
if (annotation is LinkAnnotation)
{
// Search the text under the annotation
TextFragmentAbsorber ta = new TextFragmentAbsorber();
Rectangle rect = annotation.Rect;
rect.LLX -= 10;
rect.LLY -= 10;
rect.URX += 10;
rect.URY += 10;
ta.TextSearchOptions = new TextSearchOptions(rect);
ta.Visit(doc.Pages[1]);
// Change color of the text.
foreach (TextFragment tf in ta.TextFragments)
{
tf.TextState.ForegroundColor = Color.Red;
}
}
}
dataDir = dataDir + "UpdateLinkTextColor_out.pdf";
// Save the document with updated link
doc.Save(dataDir);
// ExEnd:UpdateLinkTextColor
Console.WriteLine("\nLinkAnnotation text color updated successfully.\nFile saved at " + dataDir);
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
}
public static void Run()
{
// ExStart:SearchTextAndDrawRectangle
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Open document
Document document = new Document(dataDir + "SearchAndGetTextFromAll.pdf");
// Create TextAbsorber object to find all the phrases matching the regular expression
TextFragmentAbsorber textAbsorber = new TextFragmentAbsorber(@"[\S]+");
TextSearchOptions textSearchOptions = new TextSearchOptions(true);
textAbsorber.TextSearchOptions = textSearchOptions;
document.Pages.Accept(textAbsorber);
var editor = new PdfContentEditor(document);
foreach (TextFragment textFragment in textAbsorber.TextFragments)
{
foreach (TextSegment textSegment in textFragment.Segments)
{
DrawBox(editor, textFragment.Page.Number, textSegment, System.Drawing.Color.Red);
}
}
dataDir = dataDir + "SearchTextAndDrawRectangle_out.pdf";
document.Save(dataDir);
// ExEnd:SearchTextAndDrawRectangle
Console.WriteLine("\nRectangle drawn successfully on searched text.\nFile saved at " + dataDir);
}
public static void Run()
{
// ExStart:SearchTextAndAddHyperlink
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
// Create absorber object to find all instances of the input search phrase
TextFragmentAbsorber absorber = new TextFragmentAbsorber("\\d{4}-\\d{4}");
// Enable regular expression search
absorber.TextSearchOptions = new TextSearchOptions(true);
// Open document
PdfContentEditor editor = new PdfContentEditor();
// Bind source PDF file
editor.BindPdf(dataDir + "SearchRegularExpressionPage.pdf");
// Accept the absorber for the page
editor.Document.Pages[1].Accept(absorber);
int[] dashArray = { };
String[] LEArray = { };
System.Drawing.Color blue = System.Drawing.Color.Blue;
// Loop through the fragments
foreach (TextFragment textFragment in absorber.TextFragments)
{
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.Blue;
System.Drawing.Rectangle rect = new System.Drawing.Rectangle((int)textFragment.Rectangle.LLX,
(int)Math.Round(textFragment.Rectangle.LLY), (int)Math.Round(textFragment.Rectangle.Width + 2),
(int)Math.Round(textFragment.Rectangle.Height + 1));
Enum[] actionName = new Enum[2] { Aspose.Pdf.Annotations.PredefinedAction.Document_AttachFile, Aspose.Pdf.Annotations.PredefinedAction.Document_ExtractPages };
editor.CreateWebLink(rect, "http:// Www.aspose.com", 1, blue, actionName);
editor.CreateLine(rect, "", (float)textFragment.Rectangle.LLX + 1, (float)textFragment.Rectangle.LLY - 1,
(float)textFragment.Rectangle.URX, (float)textFragment.Rectangle.LLY - 1, 1, 1, blue, "S", dashArray, LEArray);
}
dataDir = dataDir + "SearchTextAndAddHyperlink_out.pdf";
editor.Save(dataDir);
editor.Close();
// ExEnd:SearchTextAndAddHyperlink
Console.WriteLine("\nText replaced and hyperlink added successfully based on a regular expression.\nFile saved at " + dataDir);
}
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()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_AsposePdf_Text();
//create absorber object to find all instances of the input search phrase
TextFragmentAbsorber absorber = new TextFragmentAbsorber("D[a-z]{7}:");
//Enable regular expression search
absorber.TextSearchOptions = new TextSearchOptions(true);
//open document
PdfContentEditor editor = new PdfContentEditor();
// bind source PDF file
editor.BindPdf(dataDir+ "Input_new.pdf");
//accept the absorber for the page
editor.Document.Pages[1].Accept(absorber);
int[] dashArray = { };
String[] LEArray = { };
System.Drawing.Color blue = System.Drawing.Color.Blue;
//loop through the fragments
foreach (TextFragment textFragment in absorber.TextFragments)
{
textFragment.TextState.ForegroundColor = Aspose.Pdf.Color.Blue;
System.Drawing.Rectangle rect = new System.Drawing.Rectangle((int)textFragment.Rectangle.LLX,
(int)Math.Round(textFragment.Rectangle.LLY), (int)Math.Round(textFragment.Rectangle.Width + 2),
(int)Math.Round(textFragment.Rectangle.Height + 1));
Enum[] actionName = new Enum[2] { Aspose.Pdf.InteractiveFeatures.PredefinedAction.Document_AttachFile, Aspose.Pdf.InteractiveFeatures.PredefinedAction.Document_ExtractPages };
editor.CreateWebLink(rect, "http://www.aspose.com", 1, blue, actionName);
editor.CreateLine(rect, "", (float)textFragment.Rectangle.LLX + 1, (float)textFragment.Rectangle.LLY - 1,
(float)textFragment.Rectangle.URX, (float)textFragment.Rectangle.LLY - 1, 1, 1, blue, "S", dashArray, LEArray);
}
//Save & Close the document
editor.Save(dataDir+ "TextReplaced_with_Links.pdf");
editor.Close();
}
public void WithUpdateFields()
{
Document doc = DocumentHelper.CreateDocumentFillWithDummyText();
PdfSaveOptions pdfSaveOptions = new PdfSaveOptions();
pdfSaveOptions.UpdateFields = true;
doc.Save(MyDir + @"\Artifacts\UpdateFields_False.pdf", pdfSaveOptions);
Aspose.Pdf.Document pdfDocument = new Aspose.Pdf.Document(MyDir + @"\Artifacts\UpdateFields_False.pdf");
//Get text fragment by search string
TextFragmentAbsorber textFragmentAbsorber = new TextFragmentAbsorber("Page 1 of 2");
pdfDocument.Pages.Accept(textFragmentAbsorber);
//Assert that fields are updated
Assert.AreEqual("Page 1 of 2", textFragmentAbsorber.TextFragments[1].Text);
}
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 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 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.");
}
}
