python - 在 Python 中高效匹配多个正则表达式

Question

当你有正则表达式时，词法分析器很容易编写。今天想用Python写一个简单的通用分析器，想出了:

import re
import sys

class Token(object):
    """ A simple Token structure.
        Contains the token type, value and position. 
    """
    def __init__(self, type, val, pos):
        self.type = type
        self.val = val
        self.pos = pos

    def __str__(self):
        return '%s(%s) at %s' % (self.type, self.val, self.pos)


class LexerError(Exception):
    """ Lexer error exception.

        pos:
            Position in the input line where the error occurred.
    """
    def __init__(self, pos):
        self.pos = pos


class Lexer(object):
    """ A simple regex-based lexer/tokenizer.

        See below for an example of usage.
    """
    def __init__(self, rules, skip_whitespace=True):
        """ Create a lexer.

            rules:
                A list of rules. Each rule is a `regex, type`
                pair, where `regex` is the regular expression used
                to recognize the token and `type` is the type
                of the token to return when it's recognized.

            skip_whitespace:
                If True, whitespace (\s+) will be skipped and not
                reported by the lexer. Otherwise, you have to 
                specify your rules for whitespace, or it will be
                flagged as an error.
        """
        self.rules = []

        for regex, type in rules:
            self.rules.append((re.compile(regex), type))

        self.skip_whitespace = skip_whitespace
        self.re_ws_skip = re.compile('\S')

    def input(self, buf):
        """ Initialize the lexer with a buffer as input.
        """
        self.buf = buf
        self.pos = 0

    def token(self):
        """ Return the next token (a Token object) found in the 
            input buffer. None is returned if the end of the 
            buffer was reached. 
            In case of a lexing error (the current chunk of the
            buffer matches no rule), a LexerError is raised with
            the position of the error.
        """
        if self.pos >= len(self.buf):
            return None
        else:
            if self.skip_whitespace:
                m = self.re_ws_skip.search(self.buf[self.pos:])

                if m:
                    self.pos += m.start()
                else:
                    return None

            for token_regex, token_type in self.rules:
                m = token_regex.match(self.buf[self.pos:])

                if m:
                    value = self.buf[self.pos + m.start():self.pos + m.end()]
                    tok = Token(token_type, value, self.pos)
                    self.pos += m.end()
                    return tok

            # if we're here, no rule matched
            raise LexerError(self.pos)

    def tokens(self):
        """ Returns an iterator to the tokens found in the buffer.
        """
        while 1:
            tok = self.token()
            if tok is None: break
            yield tok


if __name__ == '__main__':
    rules = [
        ('\d+',             'NUMBER'),
        ('[a-zA-Z_]\w+',    'IDENTIFIER'),
        ('\+',              'PLUS'),
        ('\-',              'MINUS'),
        ('\*',              'MULTIPLY'),
        ('\/',              'DIVIDE'),
        ('\(',              'LP'),
        ('\)',              'RP'),
        ('=',               'EQUALS'),
    ]

    lx = Lexer(rules, skip_whitespace=True)
    lx.input('erw = _abc + 12*(R4-623902)  ')

    try:
        for tok in lx.tokens():
            print tok
    except LexerError, err:
        print 'LexerError at position', err.pos

它工作得很好，但我有点担心它效率太低。是否有任何正则表达式技巧可以让我以更高效/优雅的方式编写它？

具体来说，有没有一种方法可以避免线性循环遍历所有正则表达式规则以找到适合的规则？

Answer 1

我建议使用 re.Scanner 类，它没有记录在标准库中，但非常值得使用。这是一个例子:

import re

scanner = re.Scanner([
    (r"-?[0-9]+\.[0-9]+([eE]-?[0-9]+)?", lambda scanner, token: float(token)),
    (r"-?[0-9]+", lambda scanner, token: int(token)),
    (r" +", lambda scanner, token: None),
])

>>> scanner.scan("0 -1 4.5 7.8e3")[0]
[0, -1, 4.5, 7800.0]