词法分析器定义
- 关键字有if、else、while、continue、break、true、false、int、char、bool;
- if和while语句同c#;
- 四则运算、逻辑运算、关系运算同c#;
- 基本数据类型char、bool、int;
- 不支持注释。
Token & TokenType
词法分析器用来给语法分析器提供Token,每个Token都有一个属性TokenType用来指明其类别。
public enum TokenType
{
//if, while
IF,
ELSE,
WHILE,
BREAK,
CONTINUE,
//<=, >=, ==, !=, &&, ||, <, >
LE,
GE,
EQ,
NE,
AND,
OR,
LT,
GT,
//=, !, &, |
ASSIGN,
BITNOT,
BITAND,
BITOR,
//primitive type, identifier
PRIMITIVE,
ID,
//integer, char
INTEGER,
CHAR,
//true, false
TRUE,
FALSE,
//arithmetic, delimiter
ARITHMETIC,
DELIMITER,
}
public class Token
{
public TokenType Type { get; private set; }
public Token(TokenType type)
=> this.Type = type;
public override string ToString()
=> $"{Enum.GetName(typeof(TokenType), Type)}";
}
Integer & Char
Integer Token是代码输入的整数值,Char Token是代码输入的字符值。
public class Integer : Token
{
public int Value { get; private set; }
public Integer(int value) : base(TokenType.INTEGER)
=> this.Value = value;
public override string ToString()
=> $"INTEGER\t{Value}";;
}
public class Char : Token
{
public char Value { get; private set; }
public Char(char value) : base(TokenType.CHAR)
=> this.Value = value;
public override string ToString()
=> $"Char\t{Value}";
}
Word & Type
Word Token是运算符、关键字和变量名,Type Token是基本类型bool、int、char。
public class Type : Word
{
public static readonly Type INT = new Type(TokenType.PRIMITIVE, "int", 4);
public static readonly Type CHAR = new Type(TokenType.PRIMITIVE, "char", 1);
public static readonly Type BOOL = new Type(TokenType.PRIMITIVE, "bool", 1);
public int Width { get; private set; } // width is used for storage allocation
public Type(TokenType type, string lexeme, int width) : base(type, lex