handle文件：
# -*- coding: utf-8 -*-
import re
def lines(file):
"""
把原文件尾加一行空行
"""
for line in file:
yield line
yield '
'
def blocks(file):
"""
把文件分段
"""
block=[]
for line in lines(file):
if line.strip():
block.append(line)
elif block:
yield ''.join(block).strip()
block=[]
class Handler:
"""
处理从Parser调用的方法的对象。
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()方法会用于正则表达式替换中。当使用了'emphasis'这样的名字调用时，他会返回合适的替换函数.
"""
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:match.group(0)
return result
return substitution
class HTMLRenderer(Handler):
"""
用于生成HTML的具体处理程序
HTMLRenderer内的方法都可以通过超类处理程序的start(),end(),sub()
方法来访问 他们实现了用于HTML文档的基本标签
"""
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
rules文件：
# -*- coding:utf-8 -*-
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，最多70个字符，并且不以冒号结束。
"""
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，但前提是它是大标题
"""
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):
"""
列表项是以连字号开始的段落.作为格式化的一部分 要移除连字号。
"""
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):
"""
列表从不是列表项的块和随后的列表项之间。在最后一个连续列表项之后结束
"""
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):
"""
段落只是其他规则并没有覆盖到的块
"""
type='paragraph'
def condition(self,block):
return True
markup文件：
# -*- coding:utf-8 -*-
import sys,re
from handle import *
from util import *
from rules import *
class Parser:
"""
语法分析器读取文本文件，应用规则并且控制处理程序
"""
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):
"""
在构造函数中增加规则和过滤器的具体语法分析器
"""
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-zA-Z/]+)','url')
self.addFilter(r'([.a-zA-Z]+@[.a-zA-z]+[a-zA-Z]+)','mail')
handler=HTMLRenderer()
parser=BasicTextParser(handler)
parser.parse(sys.stdin)
目标文件：
Welcome to world Wide Spam,Inc.
These are the corporate web pages of *World Wide Spam*, Inc. We hope
you find your stay enjoyable, and that you will sample many of our
products.
A short history of the company
World Wide Spam was started in the summer of 2000. The business
concept was to ride the dot-com wave and make money both through
bulk email and by selling canned meat online.
After receiving several complaints from customers who weren't
satisfied by their bulk email. World Wide Spam altered their profile,
and focused 100% on canned goods. Today, they rank as the world's
13,892nd online supplier of SPAM.
Destinations
From this page you may visit several of our interesting web pages:
- What is SPAM?(http://wwspam.fu/whatisspam)
- How do they make it?(http://wwspam.fu/howtomakeit)
- Why should I eat it?(http://wwspam.fu/whyeatit)
How to gei in touch with us
You can get in touch with us in *many* ways: By phone(555-1234), by
email (wwspam@wwspam.fu) or by visiting our customer feedback page
(http://wwspam.fu/feedback)
生成文件：
<html><head><title>...</title></head><body>
<h1>
Welcome to world Wide Spam,Inc.
</h1>
<p>
These are the corporate web pages of <em>World Wide Spam</em>, Inc. We hope
you find your stay enjoyable, and that you will sample many of our
products.
</p>
<p>
A short history of the company
World Wide Spam was started in the summer of 2000. The business
concept was to ride the dot-com wave and make money both through
bulk email and by selling canned meat online.
</p>
<p>
After receiving several complaints from customers who weren't
satisfied by their bulk email. World Wide Spam altered their profile,
and focused 100% on canned goods. Today, they rank as the world's
13,892nd online supplier of SPAM.
</p>
<p>
Destinations
From this page you may visit several of our interesting web pages:
</p>
<ul>
<li>
What is SPAM?(<a href="http://wwspam.fu/whatisspam">http://wwspam.fu/whatisspam</a>)
</li>
<li>
How do they make it?(<a href="http://wwspam.fu/howtomakeit">http://wwspam.fu/howtomakeit</a>)
</li>
<li>
Why should I eat it?(<a href="http://wwspam.fu/whyeatit">http://wwspam.fu/whyeatit</a>)
</li>
</ul>
<h2>
How to gei in touch with us
</h2>
<p>
You can get in touch with us in <em>many</em> ways: By phone(555-1234), by
email (<a href="mailto:wwspam@wwspam.fu">wwspam@wwspam.fu</a>) or by visiting our customer feedback page
(<a href="http://wwspam.fu/feedback">http://wwspam.fu/feedback</a>)
</p>
</body></html>