How to read an .RTF file using .NET 4.0

问题:

I have seen samples using Word 9.0 object library. But I have Office 2010 Beta and .NET 4.0 in VS2010. Any tips on how to go with the new Word Dlls?

So I just wanted to get the functionality of RTF to TEXT with .NET3.5 or later.

回答1:

I got a better solution with WPF , using TextRange.

FlowDocument document = new FlowDocument();

//Read the file stream to a Byte array 'data'
TextRange txtRange = null;

using (MemoryStream stream = new MemoryStream(data))
{
    // create a TextRange around the entire document
    txtRange = new TextRange(document.ContentStart, document.ContentEnd);
    txtRange.Load(stream, DataFormats.Rtf);
}

Now you can see the extracted text inside documentTextRange.Text

回答2:

Do you really new to load .RTF into Word? .net has RichTextBox control that can handle .RTF files. See here: http://msdn.microsoft.com/en-us/library/1z7hy77a.aspx (How to: Load Files into the Windows Forms RichTextBox Control)

回答3:

public enum eFileType
{
    Invalid = -1,
    TextDocument = 0,
    RichTextDocument,
    WordDocument
}

public interface IRead
{
    string Read(string file);
}

public static class FileManager
{
    public static eFileType GetFileType(string extension)
    {
        var type = eFileType.Invalid;
        switch (extension)
        {
            case ".txt": type = eFileType.TextDocument;
                break;
            case ".rtf": type = eFileType.RichTextDocument;
                break;
            case ".docx": type = eFileType.WordDocument;
                break;
        }
        return type;
    }
}


public class TextDocument : IRead
{
    public string Read(string file)
    {
        try
        {
            var reader = new StreamReader(file);
            var content = reader.ReadToEnd();
            reader.Close();
            return content;
        }
        catch
        {
            return null;
        }
    }
}

public class RichTextDocument : IRead
{
    public string Read(string file)
    {
        try
        {
            var wordApp = new Application();
            object path = file;
            object nullobj = System.Reflection.Missing.Value;
            var doc = wordApp.Documents.Open(ref path,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj);
            var result = wordApp.ActiveDocument.Content.Text;
            var doc_close = (_Document)doc;
            doc_close.Close();
            return result;
        }
        catch
        {
            return null;
        }
    }
}

public class WordDocument : IRead
{
    public string Read(string file)
    {
        try
        {
            var wordApp = new Application();
            object path = file;
            object nullobj = System.Reflection.Missing.Value;
            var doc = wordApp.Documents.Open(ref path,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj,
                                                  ref nullobj);
            var result = wordApp.ActiveDocument.Content.Text;
            var doc_close = (_Document)doc;
            doc_close.Close();
            return result;
        }
        catch
        {
            return null;
        }
    }
}

public class Factory
{
    public IRead Get(eFileType type)
    {
        IRead read = null;
        switch (type)
        {
            case eFileType.RichTextDocument: read = new RichTextDocument();
                break;
            case eFileType.WordDocument: read = new WordDocument();
                break;
            case eFileType.TextDocument: read = new TextDocument();
                break;
        }
        return read;
    }
}

public class ResumeReader
{
    IRead _read;
    public ResumeReader(IRead read)
    {
        if (read == null) throw new InvalidDataException("read cannot be null");

        _read = read;
    }
    public string Read(string file)
    {
        return _read.Read(file);
    }
}    

edited to correct syntax highlighting