Read content from Microsoft word files in C#

Question

I tried to read .docx and .txt in C# The content from ABC.docx is :

Test1

Test2

My code actually read the ABC.docx but one problem is when the data stored in the sql server the output is like this:

Below is my code:

 void WalkDirectoryTree(System.IO.DirectoryInfo root)
    {
        //System.IO.FileInfo[] files = null;

        System.IO.DirectoryInfo[] subDirs = null;

        //need to add-in more extension file such as .doc,  .ppt, .xlsx
        //files = root.GetFiles("*.txt");


        var files = root.GetFiles().Where(a => a.Extension.Contains(".docx") || a.Extension.Contains(".txt"));

        //  files = new string[] { "*.txt", "*.docx" }
        //.SelectMany(i => root.GetFiles(i, SearchOption.AllDirectories))
        //.ToArray();

        //if file is not null, read filename & file extension
        if (files != null)
        {
            foreach (System.IO.FileInfo fi in files)
            {
                StringBuilder text = new StringBuilder();
                Microsoft.Office.Interop.Word.Application word = new Microsoft.Office.Interop.Word.Application();
                object miss = System.Reflection.Missing.Value;
                //object path = @"I:\def.docx";
                object path = fi.FullName;
                object readOnly = true;
                Microsoft.Office.Interop.Word.Document docs = word.Documents.Open(ref path, ref miss, ref readOnly, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss, ref miss);

                for (int i = 0; i < docs.Paragraphs.Count; i++)
                {
                    text.Append(" \r\n " + docs.Paragraphs[i + 1].Range.Text.ToString());
                }


                //Get the full patch of the file extension
                string[] lines = System.IO.File.ReadAllLines(fi.FullName);
                //TextReader reader = new FilterReader(fi.FullName);
                //StreamReader m = new StreamReader(fi.FullName);



                foreach (string line in lines)
                {

                    String[] substrings = fi.FullName.Split('\\');
                    string strFileName = string.Empty;
                    string strFileExtension = string.Empty;


                    if (substrings.Length > 0)
                    {
                        strFileName = substrings[ substrings.Length -1 ];
                        if( !string.IsNullOrEmpty(strFileName) )
                        {
                            string[] extensionSplit = strFileName.Split('.');
                            if (extensionSplit.Length > 0)
                            {
                                strFileExtension = extensionSplit[extensionSplit.Length - 1];
                            }
                        }
                    }
                    else
                    {
                        strFileName = fi.FullName;
                    }

                     InsertData(strFileName, line.Replace("'",""),  fi.FullName,strFileExtension);
                }
            }

            //After searched from root, continue search from subDirectories
            subDirs = root.GetDirectories();

            #region Exclude all the hidden files from drives
            foreach (System.IO.DirectoryInfo dirInfo in subDirs)
            {
                if ((dirInfo.Attributes & FileAttributes.Hidden) == 0)
                {
                    WalkDirectoryTree(dirInfo);
                }
            }
            #endregion
        }
    }

Please advice how to store inside the sql server. Thanks.

Answer 1

Save the Word document data as a Base64 string within the database.

Using that base64String of the document, not only can you save the document, but you can also then open it (by converting it back) at a later stage.

Saving this result to the database;

Public string GetDocumentBinary()
    {
        string docPath = "DocumentPath";
        byte[] binarydata = File.ReadAllBytes(docPath);
        base64 = System.Convert.ToBase64String(binarydata, 0, binarydata.Length);
        return base64;
    }

Then when you needing to display the document, convert it back save it to disk (optional);

Public void SaveBinaryAsDocument(string filePath, string base64String)
    {
        Byte[] bytes = Convert.FromBase64String(base64String);
        File.WriteAllBytes(filePath, bytes);
    }