/// <summary>
/// Merge all paragraphs into a single in an existing PDF document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/merge-paragraphs-in-pdf-document-net-csharp-vb.php
/// </remarks>
static void MergeParagraphs()
{
string inpFile = @"..\..\example.pdf";
string outFile = @"Result.pdf";
DocumentCore dc = DocumentCore.Load(inpFile);
Paragraph firstPar = dc.GetChildElements(true, ElementType.Paragraph).First() as Paragraph;
int lastIndex = firstPar.Inlines.Count;
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph).Reverse().Where(p => p != firstPar))
{
int last = lastIndex;
foreach (Inline inline in par.Inlines)
{
firstPar.Inlines.Insert(last++, inline.Clone(true));
}
par.Content.Delete();
}
dc.Save(outFile);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(inpFile)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// How to get a content from a document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/get-content-net-csharp-vb.php
/// </remarks>
public static void GetContent()
{
// Path to an input document.
string documentPath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(documentPath);
StringBuilder sb = new StringBuilder();
// Get content of each paragraph in the document.
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph))
{
// The property 'Content' returns the content as ContentRange.
// Get content and append it into StringBuilder.
sb.AppendFormat("Paragraph: {0}", par.Content.ToString());
sb.AppendLine();
}
// Get content of each Run where the text color is Red.
foreach (Run run in dc.GetChildElements(true, ElementType.Run))
{
if (run.CharacterFormat.FontColor == Color.Red)
{
// The property 'Content' returns the content as ContentRange.
// Get content and append it into StringBuilder.
sb.AppendFormat("Red color: {0}", run.Content.ToString());
sb.AppendLine();
}
}
Console.WriteLine(sb.ToString());
Console.ReadKey();
}
public void LoadPages(int pagesCount)
{
for (int i = 0; i < pagesCount; i++)
{
List <SautinSoft.Document.Tables.TableRow> rowContent = new List <SautinSoft.Document.Tables.TableRow>();
DocumentCore dc = DocumentCore.Load(folderPath + @"\Page - " + (i + 1).ToString() + ".pdf");
foreach (SautinSoft.Document.Tables.TableRow run in dc.GetChildElements(true, ElementType.TableRow))
{
rowContent.Add(run);
}
;
foreach (SautinSoft.Document.Section run in dc.GetChildElements(true, ElementType.Section))
{
date = run.Blocks[run.Blocks.Count - 2].Content.ToString().Replace("\r\n", "").Substring(4, 10);
break;
}
;
foreach (SautinSoft.Document.Paragraph run in dc.GetChildElements(true, ElementType.Paragraph))
{
if (run.Content.ToString().Contains("Дата принятия уполномоченным банком"))
{
adoptionDate = run.Inlines[7].Content.ToString();
break;
}
}
;
ParseAndGetInfo(rowContent, i + 1);
}
}
// How to modify an existing table in a document.
public static void ModifyTable()
{
string sourcePath = @"..\..\..\..\..\..\Testing Files\table.docx";
string destPath = Path.ChangeExtension(sourcePath, ".modified.pdf");
// Load a document with a table.
DocumentCore dc = DocumentCore.Load(sourcePath);
// Find a first table in the document.
Table table = (Table)dc.GetChildElements(true, ElementType.Table).First();
// Set dashed borders and yellow background for all cells.
for (int r = 0; r < table.Rows.Count; r++)
{
for (int c = 0; c < table.Rows[r].Cells.Count; c++)
{
TableCell cell = table.Rows[r].Cells[c];
cell.CellFormat.Borders.SetBorders(MultipleBorderTypes.Outside, BorderStyle.Dashed, Color.Black, 1);
cell.CellFormat.BackgroundColor = new Color("#FFCC00");
}
}
// Save the document as PDF.
dc.Save(destPath, new PdfSaveOptions());
// Show the source and the dest documents.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(sourcePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(destPath)
{
UseShellExecute = true
});
}
/// <summary>
/// Creates a document containing FormDropDown element.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/advanced.php
/// </remarks>
static void FormDropDown()
{
string filePath = @"Advanced.pdf";
// Let's create document.
DocumentCore dc = new DocumentCore();
dc.Content.End.Insert(new Paragraph(dc, "The paragraph with FormDropDown element: ").Content);
Paragraph par = dc.GetChildElements(true, ElementType.Paragraph).FirstOrDefault() as Paragraph;
FormDropDownData field = new Field(dc, FieldType.FormDropDown).FormData as FormDropDownData;
field.Items.Add("First Item");
field.Items.Add("Second Item");
field.Items.Add("Third Item");
field.SelectedItemIndex = 2;
par.Inlines.Add(field.Field);
// Save our document.
dc.Save(filePath);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
}
private void buttonGetDocument_Click(object sender, EventArgs e)
{
SetDefaultDataTable();
List <string> lS1 = new List <string>(); // Лист всех элементов из .docx
OpenFileDialog opf = new OpenFileDialog();
opf.Filter = "Word 2007 Documents (*.docx)|*.docx";
if (opf.ShowDialog() == DialogResult.OK)
{
string filename = opf.FileName; // Path to Docx file.
DocumentCore dc = DocumentCore.Load(filename);
StringBuilder sb = new StringBuilder();
// Get content of each Run where the text color is Red.
foreach (Paragraph run in dc.GetChildElements(true, ElementType.Paragraph))
{
string str = run.Content.ToString();
string[] strpath = str.Split('\r'); // Не удавалось расплитить по '\r\n'. Расплититл по '\r'.
str = strpath[0]; // Хвост отбросил.
if (str != "") // Проверка на какой-либо элемент. В том числе и филды.
{
lS1.Add(str); // Список всех элементов документа, где каждый первый - Id, а каждый второй - дата.
}
}
ToTable TTable = new ToTable();
string FieldId = lS1[0];
string FieldData = lS1[1];
lS1.Remove(FieldId);
lS1.Remove(FieldData);
DataTable DT = TTable.ConvertToTable(lS1, FieldId, FieldData, GetPathAndName(opf.FileName)[1]);
dataGridView1.DataSource = DT;
}
}
/// <summary>
/// Replace all Run elements with Bold formatting to Italic and mark them by yellow.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/manipulation.php
/// </remarks>
static void Manipulation()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
string filePathResult = @"Result-file.pdf";
foreach (Run run in dc.GetChildElements(true, ElementType.Run))
{
if (run.CharacterFormat.Bold == true)
{
run.CharacterFormat.Bold = false;
run.CharacterFormat.Italic = true;
run.CharacterFormat.BackgroundColor = Color.Yellow;
}
}
dc.Save(filePathResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePath)
{
UseShellExecute = true
});
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePathResult)
{
UseShellExecute = true
});
}
public static void ExtractPictures()
{
// Path to a document where to extract pictures.
string filePath = @"..\..\..\..\..\..\Testing Files\example.pdf";
// Directory to store extracted pictures:
DirectoryInfo imageDirectory = new DirectoryInfo(Path.GetDirectoryName(filePath));
string imageTemplate = "Picture";
// Here we store extracted images.
List <ImageData> imageInventory = new List <ImageData>();
// Load the document.
DocumentCore dc = DocumentCore.Load(filePath);
// Extract all images from document, skip duplicates.
foreach (Picture pict in dc.GetChildElements(true, ElementType.Picture))
{
// Let's avoid the adding of duplicates.
if (imageInventory.Exists((img => (img.GetStream().Length == pict.ImageData.GetStream().Length))) == false)
{
imageInventory.Add(pict.ImageData);
}
}
// Save and show all images.
for (int i = 0; i < imageInventory.Count; i++)
{
string imagePath = Path.Combine(imageDirectory.FullName, String.Format("{0}{1}.{2}", imageTemplate, i + 1, imageInventory[i].Format.ToString().ToLower()));
File.WriteAllBytes(imagePath, imageInventory[i].GetStream().ToArray());
System.Diagnostics.Process.Start(imagePath);
}
}
/// <summary>
/// How to delete all hyperlink objects.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-delete-url-csharp-vb-net.php
/// </remarks>
public static void DeleteHyperlinksObjects()
{
// Let us say, we've a DOCX document.
// And we've to remove the hyperlink objects.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - Delete Hyperlinks completely.pdf";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Loop by all hyperlinks and replace the URL (address).
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink).Reverse())
{
hpl.ParentCollection.Remove(hpl);
}
// Save our document back, but in PDF format.
dc.Save(outFile, new PdfSaveOptions()
{
Compliance = PdfCompliance.PDF_14
});
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// How to replace a hyperlink URL by a new address.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-replace-url-csharp-vb-net.php
/// </remarks>
public static void ReplaceHyperlinksURL()
{
// Let us say, we've a DOCX document.
// And we've to replace the all URLs by the custom.
// Furthermore, let's save the result as PDF.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - URL.pdf";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Specify the custom URL.
string customURL = "https://www.sautinsoft.com";
// Loop by all hyperlinks and replace the URL (address).
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink))
{
hpl.Address = customURL;
}
// Save our document back, but in PDF format.
dc.Save(outFile, new PdfSaveOptions()
{
Compliance = PdfCompliance.PDF_14
});
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
public static void TOC_Update()
{
// Let's create a simple document.
DocumentCore dc = new DocumentCore();
// DocumentCore.Serial = "put your serial here";
//It's easy to load any document.
dc = DocumentCore.Load(@"..\..\..\..\..\..\Testing Files\toc.docx");
// Update TOC (TOC can be updated only after all document content is added).
var toc = (TableOfEntries)dc.GetChildElements(true, ElementType.TableOfEntries).FirstOrDefault();
toc.Update();
// Update TOC's page numbers.
// Page numbers are automatically updated in that case.
dc.GetPaginator(new PaginatorOptions()
{
UpdateFields = true
});
// Save DOCX to a file
dc.Save(@"..\..\..\..\..\..\Testing Files\TOC_Updated.docx");
ShowResult(@"..\..\..\..\..\..\Testing Files\TOC_Updated.docx");
}
public List <Paragraph> GetParagraphs(DocumentCore dc)
{
ParagraphList = new List <Paragraph>();
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph))
{
ParagraphList.Add(par);
}
return(ParagraphList);
}
/// <summary>
/// Calculate sections, paragraphs, inlines, runs and fields in DOCX document.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/iteration-in-element-collection-net-csharp-vb.php
/// </remarks>
static void IterationElement()
{
DocumentCore dc = DocumentCore.Load(@"..\..\Parsing.docx", LoadOptions.DocxDefault);
int numberOfSections = dc.Sections.Count;
int numberOfParagraphs = dc.GetChildElements(true, ElementType.Paragraph).Count();
int numberOfRunsAndFields = dc.GetChildElements(true, ElementType.Run, ElementType.Field).Count();
int numberOfInlines = dc.GetChildElements(true).OfType <Inline>().Count();
int elements = dc.Sections[0].GetChildElements(true).Count();
StringBuilder sb = new StringBuilder();
sb.AppendLine("File has:");
sb.AppendLine(numberOfSections + " section");
sb.AppendLine(numberOfParagraphs + " paragraphs");
sb.AppendLine(numberOfRunsAndFields + " runs and fields");
sb.AppendLine(numberOfInlines + " inlines");
sb.AppendLine("First section contains " + elements + " elements");
Console.WriteLine(sb.ToString());
Console.ReadKey();
}
/// <summary>
/// Find all paragraphs in a document marked as list (ordered or unordered).
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/elementcollection-linq.php
/// </remarks>
static void ShowLists()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
foreach (Paragraph p in dc.GetChildElements(true, ElementType.Paragraph).Where(p => (p as Paragraph).ListFormat.IsList))
{
Console.WriteLine(p.Content.ToString());
}
Console.ReadKey();
}
/// <summary>
/// Loads an existing DOCX document and renders all paragraphs to Console.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/get-paragraphs-from-docx-document-net-csharp-vb.php
/// </remarks>
static void GetParagraphs()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph))
{
Console.WriteLine(par.Content.ToString());
}
Console.ReadKey();
}
public static void SingleDigitalSignature()
{
// Path to a loadable document.
string loadPath = @"C:\workspace\PDFDigitalSign\Resource\digitalsignature.docx";
string savePath = @"C:\workspace\PDFDigitalSign\Resource\Result1.pdf";
DocumentCore dc = DocumentCore.Load(loadPath);
// Create a new invisible Shape for the digital signature.
// Place the Shape into top-left corner (0 mm, 0 mm) of page.
Shape signatureShape = new Shape(dc, Layout.Floating(new HorizontalPosition(0f, LengthUnit.Millimeter, HorizontalPositionAnchor.LeftMargin),
new VerticalPosition(0f, LengthUnit.Millimeter, VerticalPositionAnchor.TopMargin), new Size(1, 1)));
((FloatingLayout)signatureShape.Layout).WrappingStyle = WrappingStyle.InFrontOfText;
signatureShape.Outline.Fill.SetEmpty();
// Find a first paragraph and insert our Shape inside it.
Paragraph firstPar = dc.GetChildElements(true).OfType <Paragraph>().FirstOrDefault();
firstPar.Inlines.Add(signatureShape);
Picture signaturePict = new Picture(dc, @"C:\workspace\PDFDigitalSign\Resource\sign1.png");
// Signature picture will be positioned:
// 14.5 cm from Top of the Shape.
// 4.5 cm from Left of the Shape.
signaturePict.Layout = Layout.Floating(
new HorizontalPosition(4.5, LengthUnit.Centimeter, HorizontalPositionAnchor.Page),
new VerticalPosition(14.5, LengthUnit.Centimeter, VerticalPositionAnchor.Page),
new Size(20, 10, LengthUnit.Millimeter));
PdfSaveOptions options = new PdfSaveOptions();
// Path to the certificate (*.pfx).
options.DigitalSignature.CertificatePath = @"C:\workspace\PDFDigitalSign\Resource\sautinsoft.pfx";
options.DigitalSignature.CertificatePassword = "******";
options.DigitalSignature.Location = "World Wide Web";
options.DigitalSignature.Reason = "Test Signature 1";
options.DigitalSignature.ContactInfo = "*****@*****.**";
options.DigitalSignature.SignatureLine = signatureShape;
options.DigitalSignature.Signature = signaturePict;
dc.Save(savePath, options);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(savePath)
{
UseShellExecute = true
});
}
/// <summary>
/// How to replace a hyperlink content and formatting.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-replace-url-csharp-vb-net.php
/// </remarks>
public static void ReplaceHyperlinksByText()
{
// Let us say, we've a DOCX document.
// And we need to replace all hyperlinks by their text, color this text by red.
// Also we have to preserve the rest formatting: font family, size and so on.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - Replace By Text.docx";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Loop by all hyperlinks in a reverse, to remove the "Hyperlink" objects
// and replace them by "Inline" objects.
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink).Reverse())
{
// Check that the Hyperlink is specified for a text element.
if (hpl.DisplayInlines != null && hpl.DisplayInlines.Count > 0 && hpl.DisplayInlines[0] is Run)
{
// Get the "Hyperlink" index in the parent collection.
InlineCollection parentCollection = hpl.ParentCollection;
int index = parentCollection.IndexOf(hpl);
// Get the "Hyperlink" text as the Inline collection.
InlineCollection textInlines = hpl.DisplayInlines;
// Remove the "Hyperlink" object from the parent collection by index.
parentCollection.RemoveAt(index);
// Insert the text (collection of Inlines) instead of the removed "Hyperlink" object
// into the parent collection.
for (int i = 0; i < textInlines.Count; i++)
{
// Set the red font color, remove underline.
if (textInlines[i] is Run)
{
(textInlines[i] as Run).CharacterFormat.FontColor = Color.Red;
(textInlines[i] as Run).CharacterFormat.UnderlineStyle = UnderlineType.None;
}
parentCollection.Insert(index + i, textInlines[i].Clone(true));
}
}
}
// Save our document back.
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// How to delete all hyperlinks but preserve only their text.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/hyperlinks-delete-url-csharp-vb-net.php
/// </remarks>
public static void DeleteHyperlinksURL()
{
// Let us say, we've a DOCX document.
// And we've to remove all hyperlinks, preserve only their text.
// Note, we can't make the property 'Hyperlink.Address' empty, this is not allowed.
// Therefore we have to remove the all 'Hyperlinks' object and
// insert the text objects 'Inline' instead of them.
string inpFile = @"..\..\Hyperlinks example.docx";
string outFile = @"Result - delete links and preserve text.docx";
// Let's open our document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Loop by all hyperlinks in a reverse, to remove the "Hyperlink" objects
// and replace them by their text ("Inline" objects).
foreach (Hyperlink hpl in dc.GetChildElements(true, ElementType.Hyperlink).Reverse())
{
// Get the "Hyperlink" index in the parent collection.
InlineCollection parentCollection = hpl.ParentCollection;
int index = parentCollection.IndexOf(hpl);
// Get the "Hyperlink" text as the Inline collection.
InlineCollection textInlines = hpl.DisplayInlines;
// Remove the "Hyperlink" object from the parent collection by index.
parentCollection.RemoveAt(index);
// Insert the text (collection of Inlines) instead of the removed "Hyperlink" object
// into the parent collection.
for (int i = 0; i < textInlines.Count; i++)
{
// Set the Auto font color (Black for the most cases) and remove the underline.
// Hide these lines if you want to preserve the formatting the same as the hyperlink had.
if (textInlines[i] is Run)
{
(textInlines[i] as Run).CharacterFormat.FontColor = Color.Auto;
(textInlines[i] as Run).CharacterFormat.UnderlineStyle = UnderlineType.None;
}
parentCollection.Insert(index + i, textInlines[i].Clone(true));
}
}
// Save the document back.
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Get all Text (Run objects) from DOCX document and show it on Console.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/get-text-from-docx-document-net-csharp-vb.php
/// </remarks>
static void GetText()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
// Get all Run elements from document.
foreach (Run run in dc.GetChildElements(true, ElementType.Run))
{
Console.WriteLine(run.Text);
}
Console.ReadKey();
}
/// <summary>
/// How to remove the rows with the specified text from a table.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/from-customers-find-text-from-table-net-csharp-vb.php
/// </remarks>
public static void FindTextFromTable()
{
int longLiverMinYears = 90;
string inpFile = @"..\..\example.docx";
string outFile = Path.ChangeExtension(inpFile, ".pdf");
// Load a document with a table containing various persons with different age.
DocumentCore dc = DocumentCore.Load(inpFile);
// Find a first table in the document.
Table table = (Table)dc.GetChildElements(true, ElementType.Table).First();
// Loop by the all rows from the end.
// Find long-livers.
bool isLongLiver = false;
for (int r = table.Rows.Count - 1; r > 0; r--)
{
isLongLiver = false;
// Take the 3rd cell with the birth date.
TableCell tc = table.Rows[r].Cells[2];
// Get the birth date.
DateTime birthDate = DateTime.Now;
if (DateTime.TryParse(tc.Content.ToString(), CultureInfo.CreateSpecificCulture("en-US"), DateTimeStyles.None, out birthDate))
{
// Get the person age.
// Remove the row if the person isn't long-liver.
if (CalculateAge(birthDate) >= longLiverMinYears)
{
isLongLiver = true;
}
}
// Remove the row if it doesn't contain a long-liver.
if (!isLongLiver)
{
table.Rows.RemoveAt(r);
}
}
// Save the document as PDF.
dc.Save(outFile, new PdfSaveOptions());
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// <summary>
/// Load a scanned PDF document with help of Tesseract OCR (free OCR library) and save the result as DOCX document.
/// </summary>
/// <remarks>
/// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/ocr-load-scanned-pdf-using-tesseract-and-save-as-docx-net-csharp-vb.php
/// </remarks>
static void LoadScannedPdf()
{
DocumentCore.Serial = "12345";
// Here we'll load a scanned PDF document (perform OCR) containing a text on English, Russian and Vietnamese.
// Next save the OCR result as a new DOCX document.
// First steps:
// 1. Download data files for English, Russian and Vietnamese languages.
// Please download the files: eng.traineddata, rus.traineddata and vie.traineddata.
// From here (good and fast): https://github.com/tesseract-ocr/tessdata_fast
// or (best and slow): https://github.com/tesseract-ocr/tessdata_best
// 2. Copy the files: eng.traineddata, rus.traineddata and vie.traineddata to
// the folder "tessdata" in the Project root.
// 3. Be sure that the folder "tessdata" also contains "pdf.ttf" file.
// Let's start:
string inpFile = @"..\..\scan.pdf";
string outFile = "Result.docx";
PdfLoadOptions lo = new PdfLoadOptions();
lo.OCROptions.OCRMode = OCRMode.Enabled;
lo.PreserveEmbeddedFonts = true;
// You can specify all Tesseract parameters inside the method PerformOCR.
lo.OCROptions.Method = PerformOCRTesseract;
DocumentCore dc = DocumentCore.Load(inpFile, lo);
// Make all text visible after Tesseract OCR (change font color to Black).
// The matter is that Tesseract returns OCR result PDF document with invisible text.
// But with help of Document .Net, we can change the text color,
// char scaling and spacing to desired.
foreach (Run r in dc.GetChildElements(true, ElementType.Run))
{
r.CharacterFormat.FontColor = SautinSoft.Document.Color.Black;
r.CharacterFormat.Scaling = 100;
r.CharacterFormat.Spacing = 0;
}
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
/// Load an existing document (*.docx, *.rtf, *.pdf, *.html, *.txt, *.pdf) and save it in a PDF document with the digital signature.
public static void DigitalSignature()
{
// Path to a loadable document.
string loadPath = @"C:\Users\admin\Desktop\Test\Test\Test.pdf";
DocumentCore dc = DocumentCore.Load(loadPath);
// Signature line added with MS Word -> Insert tab -> Signature Line button by default has description 'Microsoft Office Signature Line...'.
ShapeBase signatureLine = dc.GetChildElements(true).OfType <ShapeBase>().FirstOrDefault();
// This picture symbolizes a handwritten signature
Picture signature = new Picture(dc, "C:\\Users\\admin\\Desktop\\Test\\Test\\signature.png");
// Signature in this document will be 4.5 cm right of TopLeft position of signature line
// and 4.5 cm below of TopLeft position of signature line.
signature.Layout = Layout.Floating(
new HorizontalPosition(4.5, LengthUnit.Centimeter, HorizontalPositionAnchor.Page),
new VerticalPosition(-4.5, LengthUnit.Centimeter, VerticalPositionAnchor.Page),
signature.Layout.Size);
dc.Sections.Last().Blocks.Add(
new Paragraph(dc, signature));
//signature.Layout = Layout.Inline(signature.Layout.Size);
PdfSaveOptions options = new PdfSaveOptions();
// Path to the certificate (*.pfx).
options.DigitalSignature.CertificatePath = "C:\\Users\\admin\\Desktop\\Test\\Test\\xyz.pfx";
// Password of the certificate.
options.DigitalSignature.CertificatePassword = "******";
// Additional information about the certificate.
options.DigitalSignature.Location = "World Wide Web";
options.DigitalSignature.Reason = "Document.Net by SautiSoft";
options.DigitalSignature.ContactInfo = "*****@*****.**";
// Placeholder where signature should be visualized.
options.DigitalSignature.SignatureLine = signatureLine;
// Visual representation of digital signature.
options.DigitalSignature.Signature = signature;
string savePath = Path.ChangeExtension(loadPath, ".pdf");
dc.Save(savePath, options);
ShowResult(savePath);
}
private string[] ReadWords(DocumentCore dc)
{
var allWords = new List <string>();
foreach (Run element in dc.GetChildElements(true, ElementType.Run))
{
var matches = Regex.Matches(element.Text, @"\b[\w']+\b");
var words = from m in matches.Cast <Match>()
select m.Value;
allWords.AddRange(words);
}
return(allWords.ToArray());
}
/// <summary>
/// Find all paragraphs aligned by center in DOCX document and mark it by yellow.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/find-paragraphs-in-docx-document-net-csharp-vb.php
/// </remarks>
static void FindParagraph()
{
string filePath = @"..\..\example.docx";
string fileResult = @"Result.docx";
DocumentCore dc = DocumentCore.Load(filePath);
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph).
Where(p => (p as Paragraph).ParagraphFormat.Alignment == HorizontalAlignment.Center))
{
par.ParagraphFormat.BackgroundColor = Color.Yellow;
}
dc.Save(fileResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(fileResult)
{
UseShellExecute = true
});
}
/// <summary>
/// The method converts a PDF document with scanned images to Word. But it works only if the PDF document contains a hidden text atop of the images.
/// </summary>
/// <remarks>
/// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/from-customers-scanned-pdf-to-word-in-csharp-vb-net.php
/// </remarks>
static void ScannedPdfToWord()
{
// Actually there are a lot of PDF documents which looks like created using a scanner,
// but they also contain a hidden text atop of the contents.
// This hidden text duplicates the content of the scanned images.
// This is made specially to have the ability to perform the 'find' operation.
// Our steps:
// 1. Load the PDF with the these settings:
// - show hidden text;
// - skip all images during the loading.
// 2. Change the font color to the 'Black' for the all text.
// 3. Save the document as DOCX.
string inpFile = @"..\..\Scanned.pdf";
string outFile = @"Result.docx";
PdfLoadOptions pdfLO = new PdfLoadOptions()
{
PreserveEmbeddedFonts = true,
PreserveImages = false,
ShowInvisibleText = true,
};
DocumentCore dc = DocumentCore.Load(inpFile, pdfLO);
dc.DefaultCharacterFormat.FontColor = Color.Black;
foreach (Element element in dc.GetChildElements(true, ElementType.Paragraph))
{
foreach (Inline inline in (element as Paragraph).Inlines)
{
if (inline is Run)
{
(inline as Run).CharacterFormat.FontColor = Color.Black;
}
}
(element as Paragraph).CharacterFormatForParagraphMark.FontColor = Color.Black;
}
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
private void Button_Click_1(object sender, RoutedEventArgs e)
{
FileInfo pathToDocx = new FileInfo(@"C:\Users\Faizi\Desktop\zzzz.docx");
// Let's parse docx docuemnt and get all text from it.
DocumentCore docx = DocumentCore.Load(pathToDocx.FullName);
StringBuilder text = new StringBuilder();
foreach (var par in docx.GetChildElements(true, ElementType.TableRow))
{
// MessageBox.Show((par.Content.ToString()));
Console.WriteLine((par.Content.ToString()));
}
// Show extracted text.
//Console.ReadLine();
}
static void Main(string[] args)
{
Console.WriteLine("Processing...............");
DocumentCore dcObj = DocumentCore.Load(blankdoc);
Shape signatureShape = new Shape(dcObj, Layout.Floating(new HorizontalPosition(0f, LengthUnit.Millimeter, HorizontalPositionAnchor.LeftMargin),
new VerticalPosition(0f, LengthUnit.Millimeter, VerticalPositionAnchor.TopMargin), new Size(3, 3)));
((FloatingLayout)signatureShape.Layout).WrappingStyle = WrappingStyle.InFrontOfText;
signatureShape.Outline.Fill.SetEmpty();
Paragraph firstPar = dcObj.GetChildElements(true).OfType <Paragraph>().FirstOrDefault();
firstPar.Inlines.Add(signatureShape);
Picture signaturePict = new Picture(dcObj, sign);
signaturePict.Layout = Layout.Floating(
new HorizontalPosition(2.5, LengthUnit.Centimeter, HorizontalPositionAnchor.Page),
new VerticalPosition(4.5, LengthUnit.Centimeter, VerticalPositionAnchor.Page),
new Size(10, 5, LengthUnit.Centimeter));
PdfSaveOptions options = new PdfSaveOptions();
options.DigitalSignature.CertificatePath = @"..\..\sautinsoft.pfx";
options.DigitalSignature.CertificatePassword = "******";
options.DigitalSignature.SignatureLine = signatureShape;
options.DigitalSignature.Signature = signaturePict;
dcObj.Save(resultpdf, options);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(resultpdf)
{
UseShellExecute = true
});
}
/// <summary>
/// Get a Picture size, Change it and Save the document back.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/get-and-change-picture-size-in-docx-csharp-vb-net.php
/// </remarks>
public static void GetAndChangePictureSize()
{
// Path to a document where to extract pictures.
string inpFile = @"..\..\example.docx";
string outFile = "Result.docx";
// Load the document.
DocumentCore dc = DocumentCore.Load(inpFile);
// Get the physical size of the first picture from the document.
Picture pict = dc.GetChildElements(true, ElementType.Picture).FirstOrDefault() as Picture;
Size size = pict.Layout.Size;
Console.WriteLine("The 1st picture has this size:\r\n");
Console.WriteLine("W: {0}, H: {1} (In points)", size.Width, size.Height);
Console.WriteLine("W: {0}, H: {1} (In pixels)", LengthUnitConverter.Convert(size.Width, LengthUnit.Point, LengthUnit.Pixel),
LengthUnitConverter.Convert(size.Height, LengthUnit.Point, LengthUnit.Pixel));
Console.WriteLine("W: {0:F2}, H: {1:F2} (In mm)", LengthUnitConverter.Convert(size.Width, LengthUnit.Point, LengthUnit.Millimeter),
LengthUnitConverter.Convert(size.Height, LengthUnit.Point, LengthUnit.Millimeter));
Console.WriteLine("W: {0:F2}, H: {1:F2} (In cm)", LengthUnitConverter.Convert(size.Width, LengthUnit.Point, LengthUnit.Centimeter),
LengthUnitConverter.Convert(size.Height, LengthUnit.Point, LengthUnit.Centimeter));
Console.WriteLine("W: {0:F2}, H: {1:F2} (In inches)", LengthUnitConverter.Convert(size.Width, LengthUnit.Point, LengthUnit.Inch),
LengthUnitConverter.Convert(size.Height, LengthUnit.Point, LengthUnit.Inch));
Console.WriteLine("\r\nNow let\'s increase the picture size in x1.5 times. Press any key ...");
Console.ReadKey();
// Note, we don't change the physical picture size we only scale/stretch the it.
pict.Layout.Size = new Size(size.Width * 1.5, size.Height * 1.5);
// Save the document as a new docx file.
dc.Save(outFile);
// Open the result for demonstration purposes.
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile)
{
UseShellExecute = true
});
}
public string GetText(string fileName)
{
var filename = _hostingEnvironment.WebRootPath + fileName;
FileInfo pathToDocx = new FileInfo(filename);
// Let's parse docx docuemnt and get all text from it.
DocumentCore docx = DocumentCore.Load(pathToDocx.FullName);
StringBuilder text = new StringBuilder();
foreach (Paragr par in docx.GetChildElements(true, ElementType.Paragraph))
{
foreach (Run run in par.GetChildElements(true, ElementType.Run))
{
text.Append(run.Text);
}
text.AppendLine();
}
return(text.ToString());
}
/// <summary>
/// Loads an existing DOCX document and calculates all 'Run' objects.
/// </summary>
/// <remarks>
/// Details: https://sautinsoft.com/products/document/help/net/developer-guide/run-element-text-in-docx-document-net-csharp-vb.php
/// </remarks>
static void CalculateRuns()
{
string filePath = @"..\..\example.docx";
DocumentCore dc = DocumentCore.Load(filePath);
string filePathResult = @"Result-file.docx";
foreach (Paragraph par in dc.GetChildElements(true, ElementType.Paragraph))
{
int totalRuns = par.GetChildElements(true, ElementType.Run).Count();
Run r = new Run(dc, "<<This paragraph contains " + totalRuns.ToString() + " Run(s)>>", new CharacterFormat()
{
BackgroundColor = Color.Yellow, Size = 10, FontColor = Color.Black
});
par.Content.End.Insert(r.Content);
}
dc.Save(filePathResult);
System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(filePathResult)
{
UseShellExecute = true
});
}