python的即时标记项目练习笔记

from util import *
from rules import *

class Parser:
    def __init__(self,handler):
        self.handler = handler
        self.rules = []
        self.filters = []

    def addRule(self, rule):
        self.rules.append(rule)

    def addFilter(self,pattern,name):
        def filter(block, handler):
            return re.sub(pattern, handler.sub(name),block)
        self.filters.append(filter)

    def parse(self, file):
        self.handler.start('document')
        for block in blocks(file):
            for filter in self.filters:
                block = filter(block, self.handler)
            for rule in self.rules:
                if rule.condition(block):
                    last = rule.action(block, self.handler)
                    if last:break
        self.handler.end('document')

class BasicTextParser(Parser):
    def __init__(self,handler):
        Parser.__init__(self,handler)
        self.addRule(ListRule())
        self.addRule(ListItemRule())
        self.addRule(TitleRule())
        self.addRule(HeadingRule())
        self.addRule(ParagraphRule())

        self.addFilter(r'*(.+?)*', 'emphasis')
        self.addFilter(r'(http://[.a-z0-9A-Z/]+)', 'url')
        self.addFilter(r'([.a-zA-Z]+@[.a-zA-Z]+[a-zA-Z]+)','mail')

handler = HTMLRenderer()
parser = BasicTextParser(handler)

parser.parse(sys.stdin)

这个模块里面的处理思路是，遍历客户端（也就是程序执行的入口）给插进去的所有的规则和过滤器，来处理读进来的文本。

有一个细节的地方也要说一下，其实是和前面写的呼应一下，就是在遍历规则的时候通过调用condition这个东西来判断是否符合当前规则。