private UnicodeCategory validateChar()
{
char c = code[index];
if (c >= 0xD800 && c <= 0xDBFF)
{
// Leading surrogate
char c2 = code[index + 1];
if (c2 >= 0xDC00 && c2 <= 0xDFFF)
{
// Trailing surrogate - ignore for now
}
else
{
reportError("L0007", "Illegal lone surrogate");
}
}
else if (c >= 0xDC00 && c <= 0xDFFF)
{
// Trailing surrogate
reportError("L0007", "Illegal lone surrogate");
}
UnicodeCategory cat = UnicodeLookup.GetUnicodeCategory(code, index);
if (c == '\t')
{
reportError("L0001", "Tab characters are not permitted.");
}
if (cat == UnicodeCategory.ParagraphSeparator ||
cat == UnicodeCategory.SpaceSeparator)
{
if (c != ' ' && c != '\u2028')
{
reportError("L0002", new Dictionary <string, string>()
{
{ "codepoint", formatCodepoint(Char.ConvertToUtf32(code, index)) },
{ "name", UnicodeLookup.GetCodepointName(Char.ConvertToUtf32(code, index)) }
},
"Illegal whitespace.");
}
}
else if ((cat == UnicodeCategory.Control ||
cat == UnicodeCategory.Format ||
cat == UnicodeCategory.Surrogate
) &&
c != '\n' && c != '\r')
{
reportError("L0003", new Dictionary <string, string>()
{
{ "codepoint", formatCodepoint(Char.ConvertToUtf32(code, index)) },
{ "name", UnicodeLookup.GetCodepointName(Char.ConvertToUtf32(code, index)) }
},
"Illegal control character. ");
}
return(cat);
}
private CodepointObject(int cp)
{
codepoint = cp;
parts = UnicodeLookup.GetCodepointParts(cp);
if (sharedMethods == null)
{
createSharedMethods();
}
AddMethods(sharedMethods);
}
/// <summary>
/// Check whether a given string is an identifier.
/// </summary>
/// <param name="s">String to check</param>
public static bool IsIdentifier(string s)
{
var first = StringInfo.GetNextTextElement(s);
var cat = UnicodeLookup.GetUnicodeCategory(s, 0);
if (!isIdentifierStartCharacter(first[0], cat))
{
return(false);
}
var en = StringInfo.GetTextElementEnumerator(s);
while (en.MoveNext())
{
var el = (string)en.Current;
cat = UnicodeLookup.GetUnicodeCategory(el, 0);
if (!isIdentifierCharacter(el[0], cat))
{
return(false);
}
}
return(true);
}
/// <summary>Get the next token from the stream and
/// advance the lexer</summary>
public Token NextToken()
{
previous = current;
if (index >= code.Length)
{
current = new EndToken(moduleName, line, column);
return(current);
}
char c = code[index];
column = index - lineStart;
Token ret = null;
UnicodeCategory cat = validateChar();
string cStr = StringInfo.GetNextTextElement(code, index);
if (isIdentifierStartCharacter(c, cat))
{
ret = lexIdentifier();
}
if (isOperatorCharacter(c, cat))
{
ret = lexOperator();
}
if (isNumberStartCharacter(c))
{
ret = lexNumber();
}
if (c == ' ')
{
skipSpaces();
return(NextToken());
}
if (c == '#' && allowShebang && column == 1)
{
// Eat the rest of the line, ignoring its
// contents entirely.
while (code[index] != '\n' && code[index] != '\u2028')
{
index++;
}
line++;
lineStart = index;
advanceIndex();
return(NextToken());
}
else if (column == 1)
{
allowShebang = false;
}
if (c == '"')
{
ret = lexString();
}
if (c == '(')
{
ret = lexLParen();
}
if (c == ')')
{
ret = lexRParen();
}
if (c == '{')
{
ret = lexLBrace();
}
if (c == '}')
{
ret = lexRBrace();
}
if (ret == null && UnicodeLookup.OpenBrackets.Contains(cStr))
{
ret = lexOpenBracket();
}
if (ret == null && UnicodeLookup.CloseBrackets.Contains(cStr))
{
ret = lexCloseBracket();
}
//if (UnicodeLookup.CloseBrackets.Contains(cStr))
// ret = lexCloseBracket();
if (c == ',')
{
ret = lexComma();
}
if (c == ';')
{
ret = lexSemicolon();
}
if (c == '\n' || c == '\u2028' || c == '\r')
{
ret = new NewLineToken(moduleName, line, column);
lineStart = index;
line++;
advanceIndex();
if (c == '\r' && index < code.Length && code[index] == '\n')
{
advanceIndex();
lineStart++;
}
}
if (ret == null)
{
reportError("L0000", new Dictionary <string, string>()
{
{ "codepoint", formatCodepoint(Char.ConvertToUtf32(code, index)) },
{ "name", UnicodeLookup.GetCodepointName(Char.ConvertToUtf32(code, index)) }
},
"Character '" + c + "' may not appear here");
ret = new UnknownToken(moduleName, line, index - 1);
}
current = ret;
return(ret);
}
