手把手教你写解释器
01 Dec 2016
|
|
是这个系列文章的翻译总结，假设你已经像我一样懂点知识，懂python，懂基本的编译器概念，就是没上手过
这套文章带你用python上手实现一套自定义语言
先从一个经典的计算器开始
实现一个cli的计算器，首先做数据结构抽象
数字符号 1 2 3 4 5 6 7 8 9 0 - + / * 这些是token，我们要做的是tokenizer或者说Interpreter分析处理这些token
符号也分两类，一类是运算符号，一类是数字，加上结尾EOF，一共三种
这里要注意，Interpreter是对一串字符做处理，要有结尾EOF
INTEGER, PLUS, EOF = 'INTEGER', 'PLUS', 'EOF'
class Token(object):
def __init__(self, type, value):
# token type: INTEGER, PLUS, or EOF
self.type = type
# token value: 0, 1, 2. 3, 4, 5, 6, 7, 8, 9, '+', or None
self.value = value
def __str__(self):
return 'Token({type}, {value})'.format(
type=self.type,
value=repr(self.value)
)
def __repr__(self):
return self.__str__()
回到Interpreter 要做的就是接受一组字符串，这组字符串是Token组成的，先分析再求表达式
interpreter = Interpreter(text)
result = interpreter.expr()
当然，计算器是等待输出的，也就是死循环等着，也要处理终端发送的ctrl-d 自动退出 ctrl-d也就是EOFError了 你用过python就知道python退出是ctrl-d
另外，也可以处理ctrl-c之类的信号。不处理也没关系。进程就自己退了
完整实现如下
class Interpreter(object):
def __init__(self, text):
# client string input, e.g. "3+5"
self.text = text
# self.pos is an index into self.text
self.pos = 0
# current token instance
self.current_token = None
def error(self):
raise Exception('Error parsing input')
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.
"""
text = self.text
# is self.pos index past the end of the self.text ?
# if so, then return EOF token because there is no more
# input left to convert into tokens
if self.pos > len(text) - 1:
return Token(EOF, None)
# get a character at the position self.pos and decide
# what token to create based on the single character
current_char = text[self.pos]
# if the character is a digit then convert it to
# integer, create an INTEGER token, increment self.pos
# index to point to the next character after the digit,
# and return the INTEGER token
if current_char.isdigit():
token = Token(INTEGER, int(current_char))
self.pos += 1
return token
if current_char == '+':
token = Token(PLUS, current_char)
self.pos += 1
return token
self.error()
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.get_next_token()
else:
self.error()
def expr(self):
"""expr -> INTEGER PLUS INTEGER"""
# set current token to the first token taken from the input
self.current_token = self.get_next_token()
# we expect the current token to be a single-digit integer
left = self.current_token
self.eat(INTEGER)
# we expect the current token to be a '+' token
op = self.current_token
self.eat(PLUS)
# we expect the current token to be a single-digit integer
right = self.current_token
self.eat(INTEGER)
# after the above call the self.current_token is set to
# EOF token
# at this point INTEGER PLUS INTEGER sequence of tokens
# has been successfully found and the method can just
# return the result of adding two integers, thus
# effectively interpreting client input
result = left.value + right.value
return result
def main():
while True:
try:
# To run under Python3 replace 'raw_input' call
# with 'input'
text = raw_input('calc> ')
except EOFError:
break
if not text:
continue
interpreter = Interpreter(text)
result = interpreter.expr()
print(result)
if __name__ == '__main__':
main()
在expr流程里，会根据字符串遍历token 左边右边都是数字，中间是操作符号，存下来，然后运算返回就可以了
主要是遍历token 和处理token的逻辑，要明白缘由
这第一版本有几个问题
- 空格没处理
- 只能个位数加减
- 扩展到其他操作符号
扩展：处理空格和数字
空格其实挺好处理，遇到了空格直接前进一完事儿
def advance(self):
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()
至于数字，要前进继续解析，直到遇到不同的token/空格为止
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)
用新的接口重写一下get_next_token
def get_next_token(self):
"""Lexical analyzer (also known as scanner or tokenizer)
This method is responsible for breaking a sentence
apart into tokens.
"""
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(PLUS, '+')
if self.current_char == '-':
self.advance()
return Token(MINUS, '-')
self.error()
return Token(EOF, None)
支持连续运算
首先要界定词法分析(token 处理，lexer)和语法分析 (语义处理，parser)的界限
然后，如何连续？上面的expr，只处理三个字符，连续，循环读就可以了。循环调用get_next_token而不是手动调用
那就有一个问题
最新的代码是这样的
# Token types
#
# EOF (end-of-file) token is used to indicate that
# there is no more input left for lexical analysis
INTEGER, PLUS, MINUS, EOF = 'INTEGER', 'PLUS', 'MINUS', 'EOF'
class Token(object):
def __init__(self, type, value):
# token type: INTEGER, PLUS, MINUS, 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(PLUS, '+')
"""
return 'Token({type}, {value})'.format(
type=self.type,
value=repr(self.value)
)
def __repr__(self):
return self.__str__()
class Interpreter(object):
def __init__(self, text):
# client string input, e.g. "3 + 5", "12 - 5 + 3", etc
self.text = text
# self.pos is an index into self.text
self.pos = 0
# current token instance
self.current_token = None
self.current_char = self.text[self.pos]
##########################################################
# Lexer code #
##########################################################
def error(self):
raise Exception('Invalid syntax')
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(PLUS, '+')
if self.current_char == '-':
self.advance()
return Token(MINUS, '-')
self.error()
return Token(EOF, None)
##########################################################
# Parser / Interpreter code #
##########################################################
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.get_next_token()
else:
self.error()
def term(self):
"""Return an INTEGER token value."""
token = self.current_token
self.eat(INTEGER)
return token.value
def expr(self):
"""Arithmetic expression parser / interpreter."""
# set current token to the first token taken from the input
self.current_token = self.get_next_token()
#第一次在循环外执行，方便循环内部写判断操作符
# 不然就得in (PLUS, MINUS, 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
def main():
while True:
try:
# To run under Python3 replace 'raw_input' call
# with 'input'
text = raw_input('calc> ')
except EOFError:
break
if not text:
continue
interpreter = Interpreter(text)
result = interpreter.expr()
print(result)
if __name__ == '__main__':
main()
加入乘除
上面聊到的抽象，先列出来
INTEGER, PLUS, MINUS, MUL, DIV, EOF = (
'INTEGER', 'PLUS', 'MINUS', 'MUL', 'DIV', 'EOF'
)
class Token(object):
def __init__(self, type, value):
# token type: INTEGER, PLUS, MINUS, 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(PLUS, '+')
Token(MUL, '*')
"""
return 'Token({type}, {value})'.format(
type=self.type,
value=repr(self.value)
)
def __repr__(self):
return self.__str__()
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(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, '/')
self.error()
return Token(EOF, None)
考虑优先级，同样一个字符串，要先计算乘除，再计算加减，所以乘除的逻辑放到term中，原来的term逻辑再抽象成factor
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):
"""factor : INTEGER"""
token = self.current_token
self.eat(INTEGER)
return token.value
def term(self):
"""term : factor ((MUL | DIV) factor)*"""
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.
calc> 14 + 2 * 3 - 6 / 2
17
expr : term ((PLUS | MINUS) term)*
term : 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
def main():
while True:
try:
# To run under Python3 replace 'raw_input' call
# with 'input'
text = raw_input('calc> ')
except EOFError:
break
if not text:
continue
lexer = Lexer(text)
interpreter = Interpreter(lexer)
result = interpreter.expr()
print(result)
if __name__ == '__main__':
main()
感觉有递归那味了
更高的优先级，处理括号
括号内的子串先计算，自动脱掉括号
ref
作者推荐书籍
Writing Compilers and Interpreters: A Software Engineering Approach
Modern Compiler Implementation in Java
Compilers: Principles, Techniques, and Tools (2nd Edition)
