|
|
楼主 |
发表于 2015-1-8 20:43:11
|
显示全部楼层
#handlers.pyclass 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 substitution(match):
result=self.callback('sub_',name,match)
if result is None: match.group(0)
return result
return substitution
class 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)
-------------------
#rules.py
class Rule:
def action(self,block,handler):
handler.start(self.type)
handler.feed(block)
handler.end(self.type)
return True
class 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 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=[]
--------------------
#makeup.py
import re,sys
from handlers import *
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)
---------------
#test_input.txt
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 to 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 get 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).
---------------------------
这是完整的代码，在公司弄得报错来着，我到家又执行了次好了。。。。。！不过还是谢谢你！~
|
|
( 粤ICP备18085999号-1 | 粤公网安备 44051102000585号)
狗仔卡
发表于 2015-1-8 17:28:58
置顶卡
千斤顶
显身卡
发表于 2015-1-8 18:53:33
