Question

I’m trying to read a MS Office Excel document so I can test a group of regular expressions against it. I have something that works but it seems incredibly clumsy. Checking every single cell…. I just can’t imagine this is the best way. Any suggestions to make this better.

    static void ReadMSOfficeExcelFile(string file) {
        try {
            Microsoft.Office.Interop.Excel.Application xlsApp = new Microsoft.Office.Interop.Excel.Application();
            object nullobj = System.Reflection.Missing.Value;
            object ofalse = false;
            object ofile = file;

            Microsoft.Office.Interop.Excel.Workbook xlsWorkbook = xlsApp.Workbooks.Open(
                                                             file, nullobj, nullobj,
                                                             nullobj, nullobj, nullobj,
                                                             nullobj, nullobj, nullobj,
                                                             nullobj, nullobj, nullobj,
                                                             nullobj, nullobj, nullobj);

            Microsoft.Office.Interop.Excel.Sheets xlsSheets = xlsWorkbook.Worksheets;

            foreach (Microsoft.Office.Interop.Excel.Worksheet xlsWorkSheet in xlsWorkbook.Sheets) {
                Microsoft.Office.Interop.Excel.Range xlsRange = xlsWorkSheet.UsedRange;
                foreach (Microsoft.Office.Interop.Excel.Range xlsRow in xlsRange.Rows) {
                    foreach (Microsoft.Office.Interop.Excel.Range xlsCell in xlsRow.Columns) {
                        CheckLineMatch(file, xlsCell.Text.ToString());
                    }
                }
            }
            xlsWorkbook.Close(ofalse, nullobj, nullobj);
        }
        catch {
            PrintError("Unable to parse file because of MS Office error.", file);
        }
    }

Answer 1

I kept looking at that other post. I noticed the post that reads:

“””
How about Excel Data Reader?

http://exceldatareader.codeplex.com/

I’ve used in it anger, in a production environment, to pull large amounts of data from a variety of Excel files into SQL Server Compact. It works very well and it’s rather robust.
“””

It ended up working very well for what I need.

    static void ReadMSOffice2003ExcelFile(string file) {
        FileStream stream = File.Open(file, FileMode.Open, FileAccess.Read);
        ReadMSOfficeExcelFile(file, ExcelReaderFactory.CreateBinaryReader(stream));
    }


    static void ReadMSOffice2007ExcelFile(string file) {
        FileStream stream = File.Open(file, FileMode.Open, FileAccess.Read);
        ReadMSOfficeExcelFile(file, ExcelReaderFactory.CreateOpenXmlReader(stream));
    }


    static void ReadMSOfficeExcelFile(string file, IExcelDataReader xlsReader) {
        string xlsRow;
        while (xlsReader.Read()) {
            xlsRow = "";
            for (int i = 0; i < xlsReader.FieldCount; i++) {
                xlsRow += " " + xlsReader.GetString(i);
            }
            CheckLineMatch(file, xlsRow);
        }
    }