BNF
$ expr\to term((PLUS/MINUS)term)* $
$ term\to factor((MUL/DIV)factor)* $
$ factor\to INTERGER $
BNF到代码实现
按照如下规则即可将BNF转换成代码:
- 每个非终结符对应一个函数
- 每个终结符对应读取token
- ‘*‘对应while循环
- ’|‘对应if…else
Token类实现
class Token(object):
def __init__(self, type, value):
# token type: INTEGER, MUL, DIV, or EOF
self.type = type
# token value: non-negative integer value, '*', '/', or None
self.value = value
def __str__(self):
"""String representation of the class instance.
Examples:
Token(INTEGER, 3)
Token(MUL, '*')
"""
return 'Token({type}, {value})'.format(
type=self.type,
value=repr(self.value)
)
def __repr__(self):
return self.__str__()
lexer类实现
class Lexer(object):
def __init__(self, text):
# client string input, e.g. "3 * 5", "12 / 3 * 4", etc
self.text = text
# self.pos is an index into self.text
self.pos = 0
self.current_char = self.text[self.pos]
def error(self):
raise Exception('Invalid character')
def advance(self):
"""Advance the `pos` pointer and set the `current_char` variable."""
self.pos += 1
if self.pos > len(self.text) - 1:
self.current_char = None # Indicates end of input
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 integer(self):
"""Return a (multidigit) integer consumed from the input."""
result = ''
while self.current_char is not None and self.current_char.isdigit():
result += self.current_char
self.advance()
return int(result)
def get_next_token(self):
"""Lexical analyzer (also known as scanner or tokenizer)
This method is responsible for breaking a sentence
apart into tokens. One token at a time.
"""
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.integer())
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(PLUS, '+')
if self.current_char == '-':
self.advance()
return Token(MINUS, '-')
self.error()
return Token(EOF, None)
interpreter类实现
class Interpreter(object):
def __init__(self, lexer):
self.lexer = lexer
# set current token to the first token taken from the input
self.current_token = self.lexer.get_next_token()
def error(self):
raise Exception('Invalid syntax')
def eat(self, token_type):
# compare the current token type with the passed token
# type and if they match then "eat" the current token
# and assign the next token to the self.current_token,
# otherwise raise an exception.
if self.current_token.type == token_type:
self.current_token = self.lexer.get_next_token()
else:
self.error()
def factor(self):
"""Return an INTEGER token value.
factor : INTEGER
"""
token = self.current_token
self.eat(INTEGER)
return token.value
def term(self):
result = self.factor()
while self.current_token.type in (MUL, DIV):
token = self.current_token
if token.type == MUL:
self.eat(MUL)
result = result * self.factor()
elif token.type == DIV:
self.eat(DIV)
result = result / self.factor()
return result
def expr(self):
"""Arithmetic expression parser / interpreter.
expr : factor ((MUL | DIV) factor)*
factor : INTEGER
"""
result = self.term()
while self.current_token.type in (PLUS, MINUS):
token = self.current_token
if token.type == PLUS:
self.eat(PLUS)
result = result + self.term()
elif token.type == MINUS:
self.eat(MINUS)
result = result - self.term()
return result