private static void RunTest()
{
var parser = new ManualParser();
string csv = Properties.Resources.Csv;
var result = new StringBuilder();
var s = new Stopwatch();
for (int test = 0; test < 3; test++)
{
int lineCount = 0;
s.Start();
for (int i = 0; i < 1000000 / 50; i++)
{
foreach (var line in csv.Split(new[] { Environment.NewLine }, StringSplitOptions.None))
{
string cur = line + s.ElapsedTicks.ToString();
result.AppendLine(parser.Parse(cur).ToString());
lineCount++;
}
}
s.Stop();
Console.WriteLine("Completed {0} lines in {1}ms", lineCount, s.ElapsedMilliseconds);
s.Reset();
result = new StringBuilder();
}
}
public void Test_ManualParser_OnSomeInputString()
{
var parser = new ManualParser();
parser.ParseBlock($"<a>Hello world</a>");
var texts = parser.ResultTexts.ToList();
Assert.AreEqual(1, texts.Count);
Assert.AreEqual("Hello world", texts[0]);
}
public void Parse_GivenStringWithNoQuotesAndNoCommas_ShouldReturnThatString()
{
// Arrange
var parser = new ManualParser();
// Act
string[] result = parser.Parse("This is my data").ToArray();
// Assert
Assert.AreEqual(1, result.Length, "Should only be one column returned");
Assert.AreEqual("This is my data", result[0], "Incorrect value is returned");
}
public void Parse_GivenStringWithQuotesAndNoCommas_ShouldReturnColumnWithoutQuotes()
{
// Arrange
var parser = new ManualParser();
// Act
string[] result = parser.Parse("\"This is my data\"").ToArray();
// Assert
Assert.AreEqual(1, result.Length, "Should be 1 column returned");
Assert.AreEqual("This is my data", result[0], "Value is incorrect");
}
private async Task ParseByBlocks(StreamReader streamReader, ManualParser parser)
{
var buffer = new char[Configuration.BufferSize];
while (!streamReader.EndOfStream)
{
var count = await streamReader.ReadBlockAsync(buffer, 0, Configuration.BufferSize);
var textBlock = count == Configuration.BufferSize
? new string(buffer)
: new string(buffer[..count]);
public void Parse_GivenStringWithQuotesContainingCommasAndCommas_ShouldReturnColumnsWithoutQuotes()
{
// Arrange
var parser = new ManualParser();
// Act
string[] result = parser.Parse("\"This, is\", my data").ToArray();
// Assert
Assert.AreEqual(2, result.Length, "Should be 2 columns returned");
Assert.AreEqual("This, is", result[0], "First value is incorrect");
Assert.AreEqual("my data", result[1], "Second value is incorrect");
}
public void Parse_GivenStringWithNoQuotesAndOneComma_ShouldReturnTwoColumns()
{
// Arrange
var parser = new ManualParser();
// Act
string[] result = parser.Parse("This is, my data").ToArray();
// Assert
Assert.AreEqual(2, result.Length, "Should be 2 columns returned");
Assert.AreEqual("This is", result[0], "First value is incorrect");
Assert.AreEqual("my data", result[1], "Second value is incorrect");
}
/// <summary>
/// Основной метод запуска парсинга
/// </summary>
/// <param name="streamReader">Входной поток</param>
public override async Task Parse(StreamReader streamReader)
{
var parser = new ManualParser(Configuration.ExcludeTags);
await ParseByBlocks(streamReader, parser);
var texts = parser.ResultTexts;
var wordsDict = ExtractUniqueWords(texts);
PrintReport(wordsDict);
}
public void Test_ManualParser_OnFullReadFile_And_Count_ResultTexts()
{
var fileName = Path.Combine(TestContext.CurrentContext.GetTestProjectPath(),
@"SampleFiles\Создаем программное обеспечение для бизнеса - SimbirSoft.html");
var fileContent = File.ReadAllText(fileName);
var configuration = ParseConfiguration.Default();
var parser = new ManualParser(configuration.ExcludeTags);
parser.ParseBlock(fileContent);
Assert.AreEqual(250, parser.ResultTexts.Count());
}
static void Main(string[] args)
{
var parser = new ManualParser();
string csv = Properties.Resources.Csv;
var result = new StringBuilder();
var s = new Stopwatch();
int lineCount = 0;
s.Start();
for (int i = 0; i < 3000; i++)
{
foreach (var line in csv.Split(new[] { Environment.NewLine }, StringSplitOptions.None))
{
result.AppendLine(parser.Parse(line).ToString());
lineCount++;
}
}
s.Stop();
Console.WriteLine("Completed {0} lines in {1}ms", lineCount, s.ElapsedMilliseconds);
}
internal static int ERParser(ManualParser.Parser.Code e)
{
return ((int) e) + 2100;
}
internal static int ERLexer(ManualParser.Lexer.ErrorCode e)
{
return ((int) e) + 2000;
}
internal ErrorException(ManualParser.Parser.Code e, FileRange location, string stMessage)
: this(ERParser(e), location, stMessage) { }
public void Test_ManualParser_OnWrongInputString()
{
var parser = new ManualParser();
Assert.Throws <ParseException>(() => { parser.ParseBlock($"<a>Hello world</span>"); });
}