private void FrmSettings_Load(object sender, EventArgs e)
{
txtRegExp.Text = Utils.StgGetString("TxtRegExp").Replace(@"\\", @"\");
if (Utils.StgGetInt("TxtCodepage") == 0)
{
comboBox1.Text = "Автоопределение";
}
else
{
// Saved encoding
Encoding enc = Encoding.GetEncoding(Utils.StgGetInt("TxtCodepage"));
comboBox1.Text = enc.WebName;
}
}
public FrmMain()
{
/* ANNOTATION
* The software should be able to read pdf,doc,txt and odf
* The software should take all files in the input folder and read them one at a time
* The software should prepare lists of words with their frequencie
* The software should be awesome
*
* TODO:
* 1.v Import doc, docx reader library
* 2.v Import pdf reader library
* 3.v Import odf reader library
* 4.v Create functions for each supporting format
* 5.v Create open file dialog to show the location of files
* 6.v List the files filtering the extension
* 7.v Take a file, read all of its contents
* 8.v Scan through file and create a list of frequencies for each file
* 9.v Sum-up the frequency files
* 10.v Percentage
* 11.v Percentage in export and in selection
* 12.v Общая частотность
* 13.v Add date from and date to, to SELECT for all history requests
* 14.v Окно со статистикой сразу после Начать
* 15.v Excel выгружать числа как числа а не текст!
* 16.v Статистика по слову
* 17. Import DB
* 18. Read line by line
* 19. Embed a log
*/
InitializeComponent();
// Load settings
if (Utils.StgGetString("WorkingDir") == "")
{
Utils.WorkDirPath = Environment.CurrentDirectory;
}
else
{
Utils.WorkDirPath = Utils.StgGetString("WorkingDir");
}
Utils.StgSet("TxtCodepage", Convert.ToInt32(Properties.Settings.Default["TxtCodepage"]));
chkSubdirectories.Checked = Utils.StgGetBool("ChkSubdirectories");
}
private void bgwCounter_DoWork(object sender, DoWorkEventArgs e)
{
foreach (xTextFile xFile in Utils.fList)
{
if (bgwCounter.CancellationPending)
{
bgwCounter.ReportProgress(-1, xFile);
return;
}
bgwCounter.ReportProgress(-2, xFile);
string contents = xFile.Processor.GetAllText(xFile.filePath);
xFile.charactersCount = contents.Length;
xFile.frequencies = new List <xWordFrequencies>();
var words = new Dictionary <string, int>(StringComparer.CurrentCultureIgnoreCase);
string stRegExp = Utils.StgGetString("TxtRegExp");
var wordPattern = new Regex(stRegExp.Replace(@"\\", @"\").Trim());
xFile.wordsCount = wordPattern.Matches(contents).Count;
if (xFile.wordsCount == 0)
{
continue;
}
// Check if exists
if (DbHelper.ifExists(xFile.charactersCount, xFile.wordsCount))
{
continue;
}
int progress = 0;
foreach (Match match in wordPattern.Matches(contents))
{
if (bgwCounter.CancellationPending)
{
bgwCounter.ReportProgress(-1, xFile);
return;
}
progress++;
int currentCount = 0;
words.TryGetValue(match.Value, out currentCount);
bgwCounter.ReportProgress(progress, xFile);
currentCount++;
words[match.Value] = currentCount;
}
// Add words to object's list of words with frequencies
int rank = 0;
foreach (var row in words.OrderByDescending(pair => pair.Value))
{
xWordFrequencies xwf = new xWordFrequencies();
xwf.word = row.Key.ToLower();
xwf.word = xwf.word.Substring(0, 1).ToUpper() + xwf.word.Substring(1);
xwf.frequency = row.Value;
if (rank != 0)
{
// It's not the first iteration
if (xFile.frequencies[xFile.frequencies.Count - 1].frequency > xwf.frequency)
{
rank++;
}
}
else
{
rank++;
}
xwf.rank = rank;
float freq = xwf.frequency;
// Why it doesn't work with xwf.frequency?
xwf.percentage = (freq / xFile.wordsCount) * 100;
xFile.frequencies.Add(xwf);
}
xFile.uniqueWordsCount = xFile.frequencies.Count();
xFile.SaveFileInfo();
}
bgwCounter.ReportProgress(-3, null);
}
