Python项目练习之——即时标记

来源：互联网发布：前台数据传到后台编辑：程序博客网时间：2024/06/05 07:56

项目功能

遍历我所定义的规则，来处理实时读进来的文本，利用condition判断当前规则，可以用来作代码高亮处理

模块划分

处理程序模块
过滤器模块
处理规则模块
语法分析器模块
补充模块
处理程序模块
功能：
1.提供固定的HTML标记的输出（start & end）
2.对标记输出的start end提供友好的访问接口

class Handler:    def callback(self, prefix, name, *args):        method = getattr(self, prefix + name, None)        if callable(method):return method(*args)    def start(self, name):        self.callback('start_', name)    def end(self, name):        self.callback('end_', name)    def sub(self, name):        def substation(match):            result =  self.callback('sub_', name, match)            if result is 'None': match.group(0)            return  result        return substationclass HTMLRenderer(Handler):    def start_document(self):        print('<html><head><title>...</title></head><body')    def end_document(self):        print('</body></html>')    def start_paragraph(self):        print('<p>')    def end_paragraph(self):        print ('</p>')    def start_heading(self):        print ( '<h2>')    def end_heading(self):        print ('</h2>')    def start_list(self):        print ('<ul>')    def end_list(self):        print ('</ul>')    def start_listitem(self):        print ('<li>')    def end_listitem(self):        print ('</li>')    def start_title(self):        print ('<h1>')    def end_title(self):        print ( '</h1>')    def sub_emphasis(self, match):        return '<em>%s</em>' % match.group(1)    def sub_url(self, match):        return '<a href="%s">%s</a>' % (match.group(1), match.group(1))    def sub_mail(self, match):        return '<a href="mailto:%s">%s</a>' % (match.group(1), match.group(1))    def feed(self, data):        print(data)if __name__ == '__main__':    callable(callable)

过滤器模块

功能：

由正则表达式组成的过滤器
1.强调过滤器（用×号标出的）
2.url过滤器
3.email过滤器

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')

处理规则模块

功能：

主要有两个方法，condition & action
condition：用来判断读入的字符串是否符合我们的规则
action：用来执行，调用处理程序模块，输出前标签，内容，后标签

class Rule:    def action(self, block, handler):        handler.start(self.type)        handler.feed(block)        handler.end(self.type)        return Trueclass HeadingRule(Rule):    type = 'heading'    def condition(self, block):        return not '\n' in block and len(block) <= 70 and not  block[-1] == ':'class TitleRule(HeadingRule):    type = 'title'    first = True    def condition(self, block):        if not self.first: return  False        self.first = False        return HeadingRule.condition(self, block)class ListItemRule(Rule):    type = 'listitem'    def condition(self, block):        return block[0] == '-'    def action(self, block, handler):        handler.start(self.type)        handler.feed(block[1:].strip())        handler.end(self.type)        return Trueclass ListRule(ListItemRule):    type = 'list'    inside = False    def condition(self, block):        return True    def action(self,block, handler):        if not self.inside and ListItemRule.condition(self,block):            handler.start(self.type)            self.inside = True        elif self.inside and not ListItemRule.condition(self,block):            handler.end(self.type)            self.inside = False        return Falseclass ParagraphRule(Rule):    type = 'paragraph'    def condition(self, block):        return True

语法分析器模块

功能：

协调读入的文本和其他模块的关系，提供了两个存放规则和过滤器的列表，使得规则和过滤器可以动态改变。

import sys, refrom Handler import *from uilts 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)

补充模块

def line(file):    for line in file:yield line    yield '\n'def blocks(file):    block = []    for line in file:        if line.strip():            block.append(line)        elif block:            yield ''.join(block).strip()            block = []

阅读全文

0 0