private string[] mergeSourceFiles(string[] sourceFiles, int mergeOption, out string[] mergedFileNames)
{
string name = CharsetDetector.GuessCharsetOfFile(sourceFiles[0]);
List <string> list = new List <string>();
List <string> list2 = new List <string>();
StringBuilder stringBuilder = new StringBuilder();
StringBuilder stringBuilder2 = new StringBuilder();
bool @checked = changeFileNameCheckBox.Checked;
int num = sourceFiles.Length;
bool needMarkChapterHeaders = outputTypeComboBox.SelectedIndex == 2 || outputTypeComboBox.SelectedIndex == 4 || outputTypeComboBox.SelectedIndex == 6;
for (int i = 0; i < num; i += mergeOption)
{
stringBuilder.Length = 0;
stringBuilder2.Length = 0;
int num2 = 0;
while (num2 < mergeOption && sourceFiles.Length > i + num2)
{
stringBuilder.Append(Util.NormalizeTextAndRemoveIgnoredChinesePhrases(readFile(sourceFiles[i + num2], Encoding.GetEncoding(name), needMarkChapterHeaders))).Append("\n\n----------oOo----------\n\n");
if (num2 == 0)
{
stringBuilder2.Append(getOutputFileName(sourceFiles[i + num2], i + num2, num, @checked));
}
else if (mergeOption != 1 && (num2 == mergeOption - 1 || i + num2 == sourceFiles.Length - 1))
{
stringBuilder2.Append(" - ").Append(getOutputFileName(sourceFiles[i + num2], i + num2, num, @checked));
}
num2++;
}
list.Add(stringBuilder.ToString());
list2.Add(stringBuilder2.ToString());
}
mergedFileNames = list2.ToArray();
return(list.ToArray());
}
private string[] LoadFilterRules(string rulePath)
{
var charset = CharsetDetector.GuessCharsetOfFile(rulePath);
if (charset == "GB2312")
{
charset = "UTF-8";
}
return(File.ReadAllLines(rulePath, Encoding.GetEncoding(charset)));
}
private Dictionary <string, string> LoadDictionaryAndGetFirstMeaningOfEach(string dictPath)
{
var dict = new Dictionary <string, string>();
var charSet = CharsetDetector.GuessCharsetOfFile(dictPath);
using var textReader = new StreamReader(dictPath, Encoding.GetEncoding(charSet));
foreach (var line in textReader.Lines())
{
var tuple = line.Split('=');
if (tuple.Length == 2 && !dict.ContainsKey(tuple[0]))
{
dict.Add(tuple[0], tuple[1].Split('/', '|')[0]);
}
}
return(dict);
}
string ReadAllFiles(string[] files)
{
if (files.Length < 1)
{
return(string.Empty);
}
string name = CharsetDetector.GuessCharsetOfFile(files[0]);
Encoding encoding = Encoding.GetEncoding(name);
StringBuilder stringBuilder = new StringBuilder();
foreach (string filePath in files)
{
stringBuilder.AppendLine(ReadFile(filePath, encoding, false));
}
return(stringBuilder.ToString());
}
private Dictionary <string, string> LoadDictionary(string dictPath)
{
var dict = new Dictionary <string, string>();
var charset = CharsetDetector.GuessCharsetOfFile(dictPath);
using (var textReader = new StreamReader(dictPath, Encoding.GetEncoding(charset)))
{
string line;
while ((line = textReader.ReadLine()) != null)
{
var tuple = line.Split('=');
if (tuple.Length == 2 && !dict.ContainsKey(tuple[0]))
{
dict.Add(tuple[0], tuple[1]);
}
}
}
return(dict);
}
private Dictionary <string, string> LoadDictionary(string dictPath)
{
var dict = new Dictionary <string, string>();
var charset = CharsetDetector.GuessCharsetOfFile(dictPath);
// TODO: explain this
if (charset == "GB2312")
{
charset = "UTF-8";
}
using var textReader = new StreamReader(dictPath, Encoding.GetEncoding(charset));
foreach (var line in textReader.Lines())
{
var tuple = line.Split('=');
if (tuple.Length == 2 && !dict.ContainsKey(tuple[0]))
{
dict.Add(tuple[0], tuple[1]);
}
}
return(dict);
}
private void RunButton_Clicked(object sender, EventArgs e)
{
if (!File.Exists(txtInputFilePath.Text))
{
MessageBox.Show("Đường dẫn đến file nguồn không đúng!", "Error",
MessageBoxButtons.OK, MessageBoxIcon.Hand);
btnSelectInputFilePath.Focus();
return;
}
if (string.IsNullOrEmpty(txtOutputDirPath.Text))
{
MessageBox.Show("Nhập thư mục chứa kết quả!", "Error",
MessageBoxButtons.OK, MessageBoxIcon.Hand);
btnSelectOutputDirPath.Focus();
return;
}
Directory.CreateDirectory(txtOutputDirPath.Text);
if (radSplitIntoChunks.Checked)
{
var inputFile = new FileStream(txtInputFilePath.Text, FileMode.Open, FileAccess.Read);
var inputFileSize = inputFile.Length;
var nChunks = numChunks.Value;
int chunkSize = (int)Math.Ceiling(inputFileSize / nChunks);
int amountStrWidth = nChunks.ToString().Length;
for (int i = 0; i < nChunks; i++)
{
var chunk = new byte[chunkSize];
int nByteRead;
if ((nByteRead = inputFile.Read(chunk, 0, chunkSize)) > 0)
{
var outputFilePath = Path.Combine(
txtOutputDirPath.Text, i.ToString().PadLeft(amountStrWidth, '0') + ".txt");
var outputFile = new FileStream(outputFilePath, FileMode.OpenOrCreate, FileAccess.Write);
outputFile.Write(chunk, 0, nByteRead);
outputFile.Close();
}
}
inputFile.Close();
}
else
{
var charset = CharsetDetector.GuessCharsetOfFile(txtInputFilePath.Text);
var inputLines = File.ReadAllLines(txtInputFilePath.Text, Encoding.GetEncoding(charset));
int amountStrWidth = 4;
var stringBuilder = new StringBuilder();
var pattern =
radSplitIntoChapters.Checked ? DefaultPattern :
chkUseRegex.Checked ? txtSeparatorToken.Text : Regex.Escape(txtSeparatorToken.Text);
var regex = new Regex(pattern, RegexOptions.Compiled);
int i = 0;
foreach (var line in inputLines)
{
// normal line
if (stringBuilder.Length == 0 || !regex.IsMatch(line))
{
stringBuilder.AppendLine(line);
continue;
}
// separator line
if (radSplitBySeparatorToken.Checked)
{
stringBuilder.AppendLine(line);
}
var outputFilePath = Path.Combine(txtOutputDirPath.Text,
i.ToString().PadLeft(amountStrWidth, '0') + ".txt");
File.WriteAllText(outputFilePath, stringBuilder.ToString(), Encoding.GetEncoding(charset));
stringBuilder.Length = 0;
if (!radSplitBySeparatorToken.Checked)
{
stringBuilder.AppendLine(line);
}
i++;
}
if (stringBuilder.Length > 0)
{
var outputFilePath = Path.Combine(txtOutputDirPath.Text,
i.ToString().PadLeft(amountStrWidth, '0') + ".txt");
File.WriteAllText(outputFilePath, stringBuilder.ToString(), Encoding.GetEncoding(charset));
}
}
MessageBox.Show("Xong!!!", Text, MessageBoxButtons.OK, MessageBoxIcon.Asterisk);
}