lzhenf

  博客园  :: 首页  :: 新随笔  :: 联系 :: 订阅 订阅  :: 管理

主要包括4个文件,util.py文件主要负责截取每个块。

rules.py文件定义两个类,超类Rule和分别对应的子类,子类定义了不同的划分块的要求,子类包换action函数,调用handler处理

handlers.py定义了处理类,超类定义了方法,子类通过名字调用

markup.py定义了超类parser,定义了子类basicTextParser,超类主要负责创造过滤器,添加规则,对每个块执行处理。

#handler.py
#
-*- coding: cp936 -*-
class Handler:
"""
处理从parser调用的方法对象

这个解析器会在每个块的开始部分调用start()和end()方法,使用合适的块名作为参数。sub()会用于
正则表达式替换中,当使用了'emphasis'这样的名字调用时,它会返回核实的替换函数
"""
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 substitution(match):
result = self.callback('sub_', name,match)
if result is None:
result = match.group(1)
return result
return substitution
class HTMLRenderer(Handler):
"""
用于生成HTML的具体处理程序
类中所有的方法都可以通过超类处理程序的START()、end()、sub()方法来访问,他们实现了HTML的基本标签
"""
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
# -*- coding: cp936 -*-
#
rules.py
class Rule:
"""所有规则的基类"""
def action(self,block ,handler):
handler.start(self.type)
handler.feed(block)
handler.end(self.type)
return True

class HeadingRule(Rule):
"""
标题占一行,且标题的数目不大于70个字符,且最后不能以冒号结尾
"""
type = 'heading'
def condition(self,block):
return not '\n' in block and len(block)<=70 and not block[-1]==':'

class TitleRule(HeadingRule):
"""
题目是文档的第一个块,前提他是大标题
"""
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 True
class 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 False

class ParagraphRule(Rule):

type ='paragraph'
def condition(self,block):
return True


#util.py
def lines(file):
for line in file:yield line
yield '\n'

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

 

#markup.py
import sys , re
from handlers import *
from util import *
from rules import *

class Parser:
"""
the processer of this , read data ,then use rule , and control to process data block
"""
#initial
def __init__(self,handler):
self.handler = handler
self.rules =[]
self.filters =[]
#addrule to the Parser
def addRule(self,rule):
self.rules.append(rule)
#add filter to the Parser
def addFilters(self,patten,name):
def filter(block , handler):
return re.sub(patten,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,hanler):
Parser.__init__(self,handler)
self.addRule(ListRule())
self.addRule(ListItemRule())
self.addRule(TitleRule())
self.addRule(HeadingRule())
self.addRule(ParagraphRule())

self.addFilters(r'\*(.+?)\*', 'emphasis')
self.addFilters(r'(http://[\.a-zA-z/]+)', 'url')
self.addFilters(r'([\.a-zA-Z/]+@[\.a-zA-z]+[a-zA-Z]+)', 'mail')


handler = HTMLRenderer()
parser = BasicTextParser(handler)
f= open(r'D://python27/input.txt')
parser.parse(f)






posted on 2012-03-06 15:47  lzhenf  阅读(2379)  评论(0编辑  收藏  举报