// Extract searchable text from a file using IFilterTextReader.
// Extract text from document, then replace multiple white space sequences with a single space.
// If IFilterTextReader fails (for example, old Office document; or unknown document type), an exception is logged and null is returned.
// Prefix is optional text to prepend to the result - such as document filename, metadata properties, anything else to include in search text.
private static String ExtractTextFromFile(ILogger log, String inputFile, String prefix = null)
{
String line;
String cleanedString = prefix;
try
{
FilterReaderOptions options = new FilterReaderOptions()
{
};
using (var reader = new FilterReader(inputFile, string.Empty, options))
{
while ((line = reader.ReadLine()) != null)
{
line = line.Trim();
if (!String.IsNullOrEmpty(line))
{
line = System.Text.RegularExpressions.Regex.Replace(line, @"[,]\s+", " ");
line = System.Text.RegularExpressions.Regex.Replace(line, @"[,]", "");
line = System.Text.RegularExpressions.Regex.Replace(line, @"[^a-zA-Z'\d\s:]", " ");
line = System.Text.RegularExpressions.Regex.Replace(line, @"\s+", " ");
cleanedString += line + " ";
}
}
} // end reader
}
catch (Exception ex)
{
log.LogError("ExtractTextFromFile: " + ex.Message);
}
return(cleanedString);
}
private static void TryReadFile(FileInfo file)
{
var stream = file.OpenRead();
FilterReader reader = null;
try
{
FilterReaderOptions filterReaderOptions = new FilterReaderOptions();
reader = new FilterReader(stream, file.Extension, filterReaderOptions);
var result = reader.ReadToEnd();
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
finally
{
reader?.Close();
stream?.Close();
}
}
private void SelectButton_Click(object sender, EventArgs e)
{
// Create an instance of the open file dialog box.
var openFileDialog1 = new OpenFileDialog
{
// ReSharper disable once LocalizableElement
Filter = "Alle files (*.*)|*.*",
FilterIndex = 1,
Multiselect = false
};
// Process input if the user clicked OK.
if (openFileDialog1.ShowDialog() == DialogResult.OK)
{
FileLabel.Text = openFileDialog1.FileName;
FindTextButton.Enabled = true;
TextToFindTextBox.Enabled = true;
FindWithRegexButton.Enabled = true;
TextToFindWithRegexTextBox.Enabled = true;
try
{
DisableInput();
FilterTextBox.AppendText("*** Processing file '" + openFileDialog1.FileName + "' ***" + Environment.NewLine + Environment.NewLine);
Application.DoEvents();
var stopWatch = new Stopwatch();
var timeoutOption = FilterReaderTimeout.NoTimeout;
switch (TimeoutOptionsComboBox.SelectedIndex)
{
case 0:
timeoutOption = FilterReaderTimeout.NoTimeout;
break;
case 1:
timeoutOption = FilterReaderTimeout.TimeoutOnly;
break;
case 2:
timeoutOption = FilterReaderTimeout.TimeoutWithException;
break;
}
var options = new FilterReaderOptions()
{
DisableEmbeddedContent = DisableEmbeddedContentCheckBox.Checked,
IncludeProperties = IncludePropertiesCheckBox.Checked,
ReadIntoMemory = ReadIntoMemoryCheckBox.Checked,
ReaderTimeout = timeoutOption,
Timeout = int.Parse(TimeoutTextBox.Text)
};
using (var reader = new FilterReader(openFileDialog1.FileName, string.Empty, options))
{
stopWatch.Start();
string line;
string tempFileName = Path.GetTempFileName();
while ((line = reader.ReadLine()) != null)
{
FilterTextBox.AppendText(line + Environment.NewLine);
Application.DoEvents();
System.IO.File.AppendAllLines(tempFileName, new[] { line });
}
stopWatch.Stop();
FilterTextBox.AppendText(Environment.NewLine + "*** DONE IN " + stopWatch.Elapsed + " ***" + Environment.NewLine);
Application.DoEvents();
}
}
catch (Exception exception)
{
DisableInput();
FilterTextBox.Text = exception.StackTrace + Environment.NewLine + GetInnerException(exception);
}
finally
{
EnableInput();
}
}
}
