编写如下 pascal 子集的词法分析程序

以下是一个简单的Pascal子集的词法分析程序示例：

# 定义保留字集合
reserved = {
    'program': 'PROGRAM',
    'var': 'VAR',
    'integer': 'INTEGER',
    'real': 'REAL',
    'begin': 'BEGIN',
    'end': 'END'
    # 其他保留字
}

# 定义Token类
class Token:
    def __init__(self, type, value):
        self.type = type
        self.value = value

    def __str__(self):
        return 'Token({type}, {value})'.format(
            type=self.type,
            value=repr(self.value)
        )

# 定义词法分析器类
class Lexer:
    def __init__(self, text):
        self.text = text
        self.pos = 0
        self.current_char = self.text[self.pos]

    def error(self):
        raise Exception('Invalid character')

    def advance(self):
        self.pos += 1
        if self.pos > len(self.text) - 1:
            self.current_char = None
        else:
            self.current_char = self.text[self.pos]

    def skip_whitespace(self):
        while self.current_char is not None and self.current_char.isspace():
            self.advance()

    def get_integer(self):
        result = ''
        while self.current_char is not None and self.current_char.isdigit():
            result += self.current_char
            self.advance()
        return int(result)

    def get_real(self):
        result = ''
        while self.current_char is not None and (self.current_char.isdigit() or self.current_char == '.'):
            result += self.current_char
            self.advance()
        return float(result)

    def get_id(self):
        result = ''
        while self.current_char is not None and (self.current_char.isalnum() or self.current_char == '_'):
            result += self.current_char
            self.advance()
        token_type = reserved.get(result, 'ID')
        return Token(token_type, result)

    def get_next_token(self):
        while self.current_char is not None:
            if self.current_char.isspace():
                self.skip_whitespace()
                continue

            if self.current_char.isdigit():
                return Token('INTEGER', self.get_integer())

            if self.current_char.isalpha() or self.current_char == '_':
                return self.get_id()

            if self.current_char == '.':
                self.advance()
                return Token('DOT', '.')

            if self.current_char == ':' and self.text[self.pos+1] == '=':
                self.advance()
                self.advance()
                return Token('ASSIGN', ':=')

            if self.current_char == ';':
                self.advance()
                return Token('SEMI', ';')

            if self.current_char == ',':
                self.advance()
                return Token('COMMA', ',')

            if self.current_char == '+':
                self.advance()
                return Token('PLUS', '+')

            if self.current_char == '-':
                self.advance()
                return Token('MINUS', '-')

            if self.current_char == '*':
                self.advance()
                return Token('MUL', '*')

            if self.current_char == '/':
                self.advance()
                return Token('DIV', '/')

            if self.current_char == '(':
                self.advance()
                return Token('LPAREN', '(')

            if self.current_char == ')':
                self.advance()
                return Token('RPAREN', ')')

            self.error()

        return Token('EOF', None)

这个词法分析器可以处理整数、实数、保留字、标识符、运算符和分隔符。你可以在这个基础上进行扩展，例如添加其他类型的字面量或运算符。