private void ScanIdentifierOrKeyword(ref TokenInfo tokenInfo)
{
var startOffset = _textData.Position;
var currentOffset = startOffset;
var chars = _textData.SourceCode;
while (chars.Length > currentOffset)
{
switch (chars[currentOffset])
{
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
case 'g':
case 'h':
case 'i':
case 'j':
case 'k':
case 'l':
case 'm':
case 'n':
case 'o':
case 'p':
case 'q':
case 'r':
case 's':
case 't':
case 'u':
case 'v':
case 'w':
case 'x':
case 'y':
case 'z':
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
case 'G':
case 'H':
case 'I':
case 'J':
case 'K':
case 'L':
case 'M':
case 'N':
case 'O':
case 'P':
case 'Q':
case 'R':
case 'S':
case 'T':
case 'U':
case 'V':
case 'W':
case 'X':
case 'Y':
case 'Z':
currentOffset++;
break;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
if (currentOffset == startOffset)
{
throw new FormatException("Первым символом идентификатора не может быть число");
}
currentOffset++;
break;
default:
goto EndOfLoop;
}
}
EndOfLoop:
var length = currentOffset - startOffset;
tokenInfo.Text = chars.Substring(startOffset, length);
if (TryGetKeyword(tokenInfo.Text, out var kind))
{
tokenInfo.kind = kind;
}
else
{
tokenInfo.kind = SyntaxKind.IdentifierToken;
}
_textData.AdvanceChar(length);
}
//private int counter;
internal static List <ISyntaxToken> GetTokens(TextData data)
{
TokenInfo tokenInfo = new TokenInfo
{
kind = SyntaxKind.None,
specialType = SpecialType.None,
};
var lexer = new Lexer(data);
var tempTokens = new List <ISyntaxToken>();
while (!data.IsEndOfData)
{
switch (data.PeekChar())
{
case ' ':
case '\n':
case '\r':
case '\0':
//Here we skip whitespace
data.AdvanceChar();
tokenInfo.kind = SyntaxKind.None;
break;
case '+':
tokenInfo.position = data.Position;
if (data.PeekChar(1) == '+')
{
tokenInfo.kind = SyntaxKind.PlusPlusToken;
data.AdvanceChar(2);
}
else if (data.PeekChar(1) == '=')
{
tokenInfo.kind = SyntaxKind.PlusEqualToken;
data.AdvanceChar(2);
}
else
{
tokenInfo.kind = SyntaxKind.PlusToken;
data.AdvanceChar();
}
break;
case '-':
tokenInfo.position = data.Position;
if (data.PeekChar(1) == '-')
{
tokenInfo.kind = SyntaxKind.MinusMinusToken;
data.AdvanceChar(2);
}
else if (data.PeekChar(1) == '=')
{
tokenInfo.kind = SyntaxKind.MinusEqualToken;
data.AdvanceChar(2);
}
else
{
tokenInfo.kind = SyntaxKind.MinusToken;
data.AdvanceChar();
}
break;
case '*':
tokenInfo.position = data.Position;
if (data.PeekChar(1) == '=')
{
tokenInfo.kind = SyntaxKind.MultEqualToken;
data.AdvanceChar(2);
}
else
{
tokenInfo.kind = SyntaxKind.MultToken;
data.AdvanceChar();
}
break;
case '/':
tokenInfo.position = data.Position;
if (data.PeekChar(1) == '=')
{
tokenInfo.kind = SyntaxKind.DivEqualToken;
data.AdvanceChar(2);
}
else
{
tokenInfo.kind = SyntaxKind.DivEqualToken;
data.AdvanceChar();
}
break;
case '=':
tokenInfo.position = data.Position;
if (data.PeekChar(1) == '=')
{
tokenInfo.kind = SyntaxKind.EqualEqualToken;
data.AdvanceChar(2);
}
else
{
tokenInfo.kind = SyntaxKind.EqualToken;
data.AdvanceChar();
}
break;
case '(':
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.OpeningBracket;
data.AdvanceChar();
break;
case '{':
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.OpeningBrace;
data.AdvanceChar();
break;
case ')':
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.ClosingBracket;
data.AdvanceChar();
break;
case '}':
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.ClosingBrace;
data.AdvanceChar();
break;
case '\'':
lexer.ScanCharacter(ref tokenInfo);
break;
case ';':
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.SemicolonToken;
data.AdvanceChar();
break;
case 'a':
case 'b':
case 'c':
case 'd':
case 'e':
case 'f':
case 'g':
case 'h':
case 'i':
case 'j':
case 'k':
case 'l':
case 'm':
case 'n':
case 'o':
case 'p':
case 'q':
case 'r':
case 's':
case 't':
case 'u':
case 'v':
case 'w':
case 'x':
case 'y':
case 'z':
case 'A':
case 'B':
case 'C':
case 'D':
case 'E':
case 'F':
case 'G':
case 'H':
case 'I':
case 'J':
case 'K':
case 'L':
case 'M':
case 'N':
case 'O':
case 'P':
case 'Q':
case 'R':
case 'S':
case 'T':
case 'U':
case 'V':
case 'W':
case 'X':
case 'Y':
case 'Z':
lexer.ScanIdentifierOrKeyword(ref tokenInfo);
break;
case '"':
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
lexer.ScanNumericOrLiteralValue(ref tokenInfo);
break;
default:
tokenInfo.position = data.Position;
tokenInfo.kind = SyntaxKind.Unknown;
tokenInfo.Text = data.PeekChar().ToString();
data.AdvanceChar();
break;
}
if (tokenInfo.kind != SyntaxKind.None)
{
tempTokens.Add(GetToken(ref tokenInfo));
}
}
return(tempTokens);
}
