mirror of
https://github.com/wassname/FanFicFare.git
synced 2026-09-11 11:52:07 +08:00
Remove BBCode, not used by adapter_fimfictionnet anymore.
This commit is contained in:
Jim Miller
@@ -28,8 +28,6 @@ from .. import BeautifulSoup as bs
|
||||
from ..htmlcleanup import stripHTML
|
||||
from .. import exceptions as exceptions
|
||||
|
||||
from ..bbcodeutils.bbcodeparser import bbcodeparser
|
||||
|
||||
from base_adapter import BaseSiteAdapter, makeDate
|
||||
|
||||
def getClass():
|
||||
@@ -182,14 +180,6 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
|
||||
self.setCoverImage(self.url,coverurl)
|
||||
|
||||
self.setDescription(self.url,soup.find("div", {"class":"description"}))
|
||||
# if "description" in storyMetadata and storyMetadata["description"]:
|
||||
# # the fimfic API gives bbcode for desc, not html.
|
||||
# # btw, bbcode honors newlines, html doesn't. change newlines to br tags.
|
||||
# self.setDescription(self.url,
|
||||
# bbcodeparser().parse(storyMetadata["description"]).html(doDeepCopy=False).replace('\r','').replace('\n','<br />'))
|
||||
# elif "short_description" in storyMetadata and storyMetadata["short_description"]:
|
||||
# self.setDescription(self.url,
|
||||
# bbcodeparser().parse(storyMetadata["short_description"]).html(doDeepCopy=False).replace('\r','').replace('\n','<br />'))
|
||||
|
||||
# Dates are in Unix time
|
||||
# Take the publish date from the first chapter posted
|
||||
|
||||
@@ -1,325 +0,0 @@
|
||||
#!/usr/bin/python
|
||||
# -*- coding: UTF-8 -*-
|
||||
#
|
||||
# Author: Pau Sanchez (contact@pausanchez.com)
|
||||
# Version: v1.0
|
||||
# Last Modified: 2010/09/15
|
||||
#
|
||||
# For the latest version check out:
|
||||
# http://www.codigomanso.com/en/projects
|
||||
#
|
||||
# My blog:
|
||||
# http://www.codigomanso.com/en/ - English Version
|
||||
# http://www.codigomanso.com/es/ - Spanish Version
|
||||
#
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
import urllib
|
||||
|
||||
class bbcode2html:
|
||||
'''
|
||||
This class gets a parsed BBCode and transforms it to valid HTML
|
||||
|
||||
Useful functions of this class:
|
||||
html
|
||||
convertToHTML
|
||||
|
||||
Example:
|
||||
> parser = bbcodeparser ()
|
||||
> parser.parse ('[b]bold[/b]')
|
||||
> bbcode2html (parser).html()
|
||||
<b>bold</b>
|
||||
|
||||
# This is faster for huge strings but changes the parser object internally
|
||||
> bbcode2html (parser).html(doDeepCopy = False)
|
||||
<b>bold</b>
|
||||
'''
|
||||
def __init__ (self, parser):
|
||||
self._parser = parser
|
||||
return
|
||||
|
||||
def html (self, allowClassAttr = False, doDeepCopy = True, parser = None):
|
||||
'''
|
||||
Convert current parsed code to HTML
|
||||
|
||||
Example:
|
||||
code = bbcodeparser ('[b]bold[/b]')
|
||||
code.html() -> '<b>bold</b>'
|
||||
'''
|
||||
if parser is None:
|
||||
parser = self._parser
|
||||
|
||||
tokens = parser
|
||||
if instanceof (parser, bbcodeparser):
|
||||
tokens = parser.getTokens()
|
||||
|
||||
return bbcode2html.convertToHTML (tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
|
||||
|
||||
@staticmethod
|
||||
def htmlString (string):
|
||||
toReplace = {
|
||||
u'<' : '<',
|
||||
u'>' : '>',
|
||||
u'"' : """,
|
||||
u'&' : "&"
|
||||
}
|
||||
for entity in toReplace:
|
||||
string = string.replace(entity, toReplace[entity])
|
||||
return string
|
||||
|
||||
@staticmethod
|
||||
def getValidTags ():
|
||||
simpleTags = ['b', 'u', 'i', 'sup', 'sub', 'ul', 'ol', 'li', 'table', 'tr', 'th', 'td', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6']
|
||||
validTags = {
|
||||
'p' : { 'color' : 'color', 'size' : 'size', 'font' : 'font' },
|
||||
'color' : { 'color' : 'color' },
|
||||
'size' : { 'size' : 'size' },
|
||||
'font' : { 'font' : 'font' },
|
||||
'img' : { 'alt' : 'alt', 'title' : 'title', 'width' : 'width' , 'height' : 'height', 'img' : 'img'},
|
||||
'url' : { 'href' : 'href', 'url' : 'href', 'link' : 'href', 'title' : 'title' },
|
||||
's' : { },
|
||||
'code' : { },
|
||||
'quote' : { },
|
||||
'list' : { 'list' : 'type' },
|
||||
'email' : { 'email': 'href'},
|
||||
'google' : { 'google': 'google'},
|
||||
'wikipedia' : { 'wikipedia' : 'wikipedia', 'language' : 'language', 'lang' : 'lang'}
|
||||
}
|
||||
|
||||
for tag in simpleTags:
|
||||
validTags[tag] = { }
|
||||
return validTags
|
||||
|
||||
@staticmethod
|
||||
def convertToHTML (tokens, allowClassAttr = False, validTags = None, doDeepCopy = True):
|
||||
'''
|
||||
Convert internally parsed BBCode to XHTML
|
||||
|
||||
@doDeepCopy
|
||||
True: it does a deep copy of tokens so this list will remain unchanged
|
||||
False: tokens will be modified internally, but the output will be produced like 5x faster
|
||||
it's a good idea to use False only when this is the last operation
|
||||
'''
|
||||
# do a deep copy
|
||||
if doDeepCopy:
|
||||
import copy
|
||||
tokens = copy.deepcopy (tokens)
|
||||
|
||||
# filter invalid tags and attributes
|
||||
if validTags is None:
|
||||
validTags = bbcode2html.getValidTags()
|
||||
|
||||
bbcode2html._filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr)
|
||||
|
||||
# Start to convert
|
||||
index = 0
|
||||
tokenLength = len (tokens)
|
||||
|
||||
# use a list for the output (an order of magnitude faster than using string concatenation)
|
||||
htmlList = []
|
||||
lastListOpener = []
|
||||
|
||||
while index < tokenLength:
|
||||
|
||||
if isinstance (tokens [index], basestring):
|
||||
htmlList.append (bbcode2html.htmlString (tokens [index]))
|
||||
index += 1
|
||||
continue
|
||||
|
||||
token = tokens[index]
|
||||
tag = token['tag'] # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
|
||||
tagName = (tag[1:] if tag[0] == '/' else tag)
|
||||
tagOpener = (u'/' if tag[0] == '/' else u'')
|
||||
tokenArgs = (token['args'] if 'args' in token else {})
|
||||
|
||||
# opening or closing simple tag COLOR / SIZE
|
||||
if (tagName in ['p', 'color', 'size', 'font']):
|
||||
style = ''
|
||||
style += ((u' color: ' + tokenArgs['color'] + u';') if ('color' in tokenArgs) else '')
|
||||
style += ((u' font-size: ' + tokenArgs['size'] + u'pt;') if ('size' in tokenArgs) else '')
|
||||
style += ((u' font-family: ' + tokenArgs['font'] + u';') if ('font' in tokenArgs) else '')
|
||||
style = style.strip()
|
||||
|
||||
pArgs = {}
|
||||
if style != '':
|
||||
pArgs ['style'] = style
|
||||
|
||||
if 'class' in tokenArgs:
|
||||
pArgs ['class'] = tokenArgs['class']
|
||||
|
||||
if ('args' not in token) and (tagName != 'p'):
|
||||
if (tagOpener == '/'): # if closing tag, close it
|
||||
htmlList.append (u'</span>')
|
||||
index += 1
|
||||
continue
|
||||
|
||||
if tagName != 'p':
|
||||
tag = tagOpener + u'span'
|
||||
|
||||
htmlList.append (bbcode2html.xml (tag, pArgs))
|
||||
|
||||
# IMG tag
|
||||
elif tag == 'img' and (index+2 < tokenLength):
|
||||
if 'img' in tokenArgs:
|
||||
# has the form of <width>x<height> ?
|
||||
sizeMatch = re.match (u'^\s*(\d+)[xX](\d+)\s*$', tokenArgs['img'])
|
||||
if sizeMatch is not None:
|
||||
tokenArgs['width'] = sizeMatch.group(1)
|
||||
tokenArgs['height'] = sizeMatch.group(2)
|
||||
# then assume is the alternative text
|
||||
else:
|
||||
tokenArgs['alt'] = tokenArgs['img']
|
||||
del tokenArgs['img']
|
||||
|
||||
# add the source of the image
|
||||
tokenArgs ['src'] = tokens[index+1]
|
||||
|
||||
# [img]http://www.whatever.com/pic.jpg[/img]
|
||||
htmlList.append (
|
||||
bbcode2html.xml ('img', tokenArgs, soloTag=True)
|
||||
)
|
||||
index += 2 # skip next token and closing tag
|
||||
|
||||
# URL tag
|
||||
elif tag == 'url':
|
||||
if ('args' not in token) and (index+2 < tokenLength):
|
||||
# [url]http://www.google.com[/url]
|
||||
htmlList.append (bbcode2html.xml ('a', { 'href' : tokens[index+1] }))
|
||||
else:
|
||||
# [url=http://www.google.com]Google[/url]
|
||||
# [url link=http://www.google.com title="This is Google"]Google[/url]
|
||||
htmlList.append (bbcode2html.xml ('a', tokenArgs))
|
||||
|
||||
# URL closing tag (sometimes needed)
|
||||
elif (tag == '/url') or (tag == '/email'):
|
||||
htmlList.append (u'</a>')
|
||||
|
||||
# Email tag
|
||||
elif tag == 'email':
|
||||
if ('args' not in token) and (index+2 < tokenLength):
|
||||
# [email]asdf@asdf.com]
|
||||
htmlList.append (bbcode2html.xml ('a', { 'href' : u'mailto:' + tokens[index+1].strip() }))
|
||||
else:
|
||||
# [email=asdf@asfd.com]john smith[/email]
|
||||
if 'href' in tokenArgs:
|
||||
tokenArgs['href'] = u'mailto:' + tokenArgs['href']
|
||||
htmlList.append (bbcode2html.xml ('a', tokenArgs))
|
||||
|
||||
elif tagName == 'list':
|
||||
if tagOpener == '/':
|
||||
htmlList.append (bbcode2html.xml (u'/' + lastListOpener.pop()))
|
||||
else:
|
||||
if ('type' not in tokenArgs):
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'ul', tokenArgs))
|
||||
lastListOpener.append ('ul')
|
||||
else:
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'ol', tokenArgs))
|
||||
lastListOpener.append ('ol')
|
||||
|
||||
elif tagName == '*':
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'li', tokenArgs))
|
||||
|
||||
elif (tagName == 's'):
|
||||
tokenArgs['style'] = 'text-decoration: line-through;'
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'span', tokenArgs))
|
||||
|
||||
elif (tagName == 'code'):
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'pre', tokenArgs))
|
||||
|
||||
elif (tagName == 'quote'):
|
||||
htmlList.append (bbcode2html.xml (tagOpener + u'blockquote', tokenArgs))
|
||||
|
||||
elif (tagName == 'google'):
|
||||
htmlList.append (
|
||||
bbcode2html.xml (
|
||||
tagOpener + u'a',
|
||||
{'href' : 'http://www.google.com/search?q=' + urllib.quote_plus (tokens[index+1])},
|
||||
tokens[index+1]
|
||||
)
|
||||
)
|
||||
index += 2
|
||||
|
||||
elif (tagName == 'wikipedia'):
|
||||
subdomain = 'www'
|
||||
for arg in ['lang', 'language', 'wikipedia']:
|
||||
if arg in tokenArgs:
|
||||
subdomain = tokenArgs[arg]
|
||||
|
||||
htmlList.append (
|
||||
bbcode2html.xml (
|
||||
tagOpener + u'a',
|
||||
{'href' : 'http://' + subdomain + '.wikipedia.org/wiki/' + tokens[index+1].replace (' ', '_')},
|
||||
tokens[index+1]
|
||||
)
|
||||
)
|
||||
index += 2
|
||||
|
||||
elif (tagName in validTags):
|
||||
htmlList.append (
|
||||
bbcode2html.xml (tag, tokenArgs)
|
||||
)
|
||||
|
||||
else:
|
||||
# ignore this tag
|
||||
pass
|
||||
|
||||
index += 1
|
||||
|
||||
return ''.join (htmlList)
|
||||
|
||||
@staticmethod
|
||||
def _filterInvalidTagsAndAttributes (tokens, validTags, allowClassAttr):
|
||||
'''
|
||||
Helper function to filter out invalid attributes from the tokens list
|
||||
'''
|
||||
# add 'class' attribute as valid (mapping 'class' itself)
|
||||
if allowClassAttr:
|
||||
for attr in validTags:
|
||||
validTags[attr]['class'] = 'class'
|
||||
|
||||
# remove invalid attributes from tokens
|
||||
for tindex in range(0, len(tokens)):
|
||||
if isinstance (tokens[tindex], dict) and ('args' in tokens[tindex]) and (tokens[tindex]['tag'] in validTags):
|
||||
validList = validTags[tokens[tindex]['tag']]
|
||||
|
||||
filteredArgs = {}
|
||||
for arg in tokens[tindex]['args']:
|
||||
if arg in validList:
|
||||
# rename the argument
|
||||
filteredArgs[validList[arg]] = tokens[tindex]['args'][arg]
|
||||
else:
|
||||
pass # do not include this arg in the filteredArgs
|
||||
|
||||
tokens[tindex]['args'] = filteredArgs
|
||||
|
||||
return
|
||||
|
||||
@staticmethod
|
||||
def xml (tag, attrs = {}, text = None, soloTag = False):
|
||||
'''
|
||||
Helper function to produce valid XML output
|
||||
'''
|
||||
xml = u'<' + tag.lower()
|
||||
|
||||
# make sure we sort attributes alphabetically (for deterministic output)
|
||||
# Faster but non-deterministic:
|
||||
# for (key, value) in attrs.iteritems():
|
||||
# xml += u' ' + key + u'="' + value + u'"'
|
||||
for key in sorted (attrs.keys()):
|
||||
xml += u' ' + key + u'="' + attrs[key] + u'"'
|
||||
|
||||
# close tag
|
||||
if text is None:
|
||||
if soloTag:
|
||||
xml += u' />'
|
||||
else:
|
||||
xml += u'>'
|
||||
else:
|
||||
xml += u'>' + text + u'</' + tag.lower() + '>'
|
||||
|
||||
return xml
|
||||
|
||||
|
||||
|
||||
@@ -1,77 +0,0 @@
|
||||
#!/usr/bin/python
|
||||
# -*- coding: UTF-8 -*-
|
||||
#
|
||||
# Author: Pau Sanchez (contact@pausanchez.com)
|
||||
# Version: v1.0
|
||||
# Last Modified: 2010/09/15
|
||||
#
|
||||
# For the latest version check out:
|
||||
# http://www.codigomanso.com/en/projects
|
||||
#
|
||||
# My blog:
|
||||
# http://www.codigomanso.com/en/ - English Version
|
||||
# http://www.codigomanso.com/es/ - Spanish Version
|
||||
#
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
import hashlib
|
||||
|
||||
class bbcodebuilder:
|
||||
'''
|
||||
This class helps to build BBCode programmatically.
|
||||
|
||||
The function names are used as the tag name, then the first parameter
|
||||
is the string that goes inside the tags and any extra parameter is
|
||||
appended as a parameter to the tag
|
||||
|
||||
Examples:
|
||||
> bbcode = bbcodebuilder() # create a instance!
|
||||
|
||||
> print bbcode.b ('bold')
|
||||
[b]bold[/b]
|
||||
|
||||
> print bbcode.color ('this goes in red', 'red')
|
||||
[color=red]this goes in red[/color]
|
||||
|
||||
> print bbcode.url ('Google', 'http://www.google.com')
|
||||
[url=http://www.google.com]Google[/url]
|
||||
|
||||
> print bbcode.alist('item 1', 'item 2')
|
||||
[list=a]
|
||||
[*]item 1
|
||||
[*]item 2
|
||||
[/list]
|
||||
|
||||
|
||||
This solution is based on the recipe found on:
|
||||
http://code.activestate.com/recipes/576831-simple-bbcode-support/
|
||||
'''
|
||||
|
||||
def __getattr__(self, name):
|
||||
'''
|
||||
This is a generic getter that returns a function which gets the first parameter
|
||||
as the string that goes between the tags, and extra parameters as tag parameters.
|
||||
|
||||
The name of the attribute is used as the tag name
|
||||
'''
|
||||
class bbcodebuilder_helper:
|
||||
def __init__(self, name):
|
||||
self._name = name
|
||||
|
||||
def __call__(self, string, *args):
|
||||
return u'[{0}{1}]{2}[/{0}]'.format(self._name, (u'=' + u','.join(map(str, args))) if args else u'', string)
|
||||
|
||||
return bbcodebuilder_helper (name)
|
||||
|
||||
def list(self, *items):
|
||||
return u'[list]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
|
||||
|
||||
def nlist(self, *items):
|
||||
return u'[list=1]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
|
||||
|
||||
def alist(self, *items):
|
||||
return u'[list=a]' + u''.join(map(lambda item: u"\n [*]" + item, items)) + u"\n[/list]"
|
||||
|
||||
|
||||
@@ -1,258 +0,0 @@
|
||||
#!/usr/bin/python
|
||||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Author: Pau Sanchez (contact@pausanchez.com)
|
||||
# Version: v1.0
|
||||
# Last Modified: 2010/09/15
|
||||
#
|
||||
# For the latest version check out:
|
||||
# http://www.codigomanso.com/en/projects
|
||||
#
|
||||
# My blog:
|
||||
# http://www.codigomanso.com/en/ - English Version
|
||||
# http://www.codigomanso.com/es/ - Spanish Version
|
||||
#
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
import hashlib
|
||||
|
||||
class bbcodeparser:
|
||||
'''
|
||||
This class parses BBCode into a internal structure to allow later processing and
|
||||
conversion to HTML.
|
||||
|
||||
The parser tries to fix invalid code (like unclosed tags)
|
||||
|
||||
Useful URLs:
|
||||
http://en.wikipedia.org/wiki/BBCode
|
||||
http://www.bbcode.org/reference.php
|
||||
|
||||
Example:
|
||||
> bbcode = bbcodeparser ()
|
||||
> bbcode.parse ('[b]text in bold[/b]').html()
|
||||
<b>text in bold</b>
|
||||
|
||||
# dump HTML
|
||||
> bbcode.parse ('[p][color=red]text in red').html()
|
||||
<p><span style="color:red;">text in red</span></p>
|
||||
|
||||
# dump fixed BBCode
|
||||
> bbcode.parse ('[p][color=red]text in red').bbcode()
|
||||
[p][color=red]text in red[/color][/p]
|
||||
|
||||
> bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode()
|
||||
This [b][i]code[/i][/b] will be fixed
|
||||
|
||||
# dump fixed bbcode
|
||||
> str (bbcodeparse ('This [b][i]code[/b] will be fixed[/invalid]'))
|
||||
This [b][i]code[/i][/b] will be fixed
|
||||
'''
|
||||
_bbcode = ''
|
||||
_tokens = []
|
||||
|
||||
def __init__ (self, bbcode = '', fixInvalidCode = True):
|
||||
''' Initialize and parse bbcode string (if any is given)
|
||||
'''
|
||||
self.parse (bbcode, fixInvalidCode)
|
||||
return
|
||||
|
||||
def __str__ (self):
|
||||
return self.bbcode()
|
||||
|
||||
def parse (self, bbcode = None, fixInvalidCode = True):
|
||||
'''
|
||||
It will parse and return the token list, trying to fix tags if
|
||||
fixInvalidCode is True
|
||||
|
||||
It will return the current object to allow chaining
|
||||
|
||||
Example:
|
||||
code = bbcode()
|
||||
code.parse ('<b>bold</b>', True) ->
|
||||
code.parse ('<b>bold<i>italics</b>', True) -> internally will add the missing '</i>'
|
||||
'''
|
||||
if bbcode is not None:
|
||||
self._bbcode = bbcode
|
||||
self._tokens = self.tokenize (bbcode)
|
||||
if fixInvalidCode:
|
||||
self._tokens = self.fixWrongTags (self._tokens)
|
||||
|
||||
return self
|
||||
|
||||
# return ALL tokens
|
||||
def getTokens (self):
|
||||
return self._tokens
|
||||
|
||||
def bbcode (self):
|
||||
'''
|
||||
Dump BBCode again. This is useful for dumping valid BBCode
|
||||
'''
|
||||
bbcode = []
|
||||
for token in self._tokens:
|
||||
if token is None:
|
||||
continue
|
||||
|
||||
if isinstance (token, basestring):
|
||||
bbcode.append (token.replace (u'[', u'\[').replace (u']', u'\]'))
|
||||
continue
|
||||
|
||||
tag = token['tag'] # opening or closing simple tag. e.g: 'b', '/b', '/u', ...
|
||||
tagOpener = (u'/' if tag[0] == u'/' else u'')
|
||||
|
||||
if (tagOpener == '/') or ('args' not in token):
|
||||
bbcode.append (u'[' + tag + u']')
|
||||
else:
|
||||
# process args
|
||||
argstr = ''
|
||||
|
||||
# the arg with the same name as the tag repersents the '=whatever'
|
||||
if tag in token['args']:
|
||||
if re.match ('\s|"', token['args'][tag]) is None:
|
||||
argstr = u'=' + token['args'][tag]
|
||||
else:
|
||||
argstr = u'="' + token['args'][tag].replace (u'"', u'\"') + u'"'
|
||||
|
||||
for (k,v) in token['args'].iteritems():
|
||||
if k == tag: # already processed
|
||||
continue
|
||||
argstr += ' ' + k + u'="' + v.replace (u'"', u'\"') + u'"'
|
||||
|
||||
bbcode.append (u'[' + tag + argstr + ']')
|
||||
|
||||
return u''.join (bbcode)
|
||||
|
||||
def html (self, allowClassAttr = False, doDeepCopy = True):
|
||||
'''
|
||||
Convert current parsed code to HTML
|
||||
|
||||
@allowClassAttr
|
||||
Is something like [b class="asdf"] allowed?
|
||||
|
||||
@doDeepCopy
|
||||
True: it does a deep copy of tokens so this list will remain unchanged
|
||||
False: tokens will be modified internally, but the output will be produced like 5x faster
|
||||
it's a good idea to use False when the string parsed is huge and this is the
|
||||
last operation on the string
|
||||
|
||||
Example:
|
||||
code = bbcode ('[b]bold[/b]')
|
||||
code.html() -> '<b>bold</b>'
|
||||
'''
|
||||
from bbcode2html import bbcode2html
|
||||
return bbcode2html.convertToHTML (self._tokens, allowClassAttr = allowClassAttr, doDeepCopy = doDeepCopy)
|
||||
|
||||
|
||||
@staticmethod
|
||||
def fixWrongTags (inTokenList):
|
||||
''' Add missing tokens that have not been closed properly and try to fix some scenarios
|
||||
'''
|
||||
opened = []
|
||||
outTokenList = []
|
||||
for token in inTokenList:
|
||||
# normal string... do nothing
|
||||
if isinstance(token, basestring):
|
||||
outTokenList.append (token)
|
||||
else:
|
||||
# if starts with '/' is closing a tag
|
||||
if token['tag'][0] == '/':
|
||||
while (len (opened) > 0) and (opened[-1] != token['tag'][1:]):
|
||||
outTokenList.append ({'tag' : '/' + opened[-1] })
|
||||
del opened[-1]
|
||||
|
||||
if len(opened):
|
||||
del opened[-1]
|
||||
outTokenList.append (token)
|
||||
|
||||
# opening tag
|
||||
else:
|
||||
# if I open the same tag I opened before, close it, and open it again
|
||||
if (len(opened) > 0) and (token['tag'] == opened[-1]):
|
||||
outTokenList.append ({'tag' : '/' + opened[-1] })
|
||||
else:
|
||||
opened.append (token['tag'])
|
||||
outTokenList.append (token)
|
||||
|
||||
# close all elements that have not been closed
|
||||
while len(opened):
|
||||
outTokenList.append ({'tag' : '/' + opened[-1] })
|
||||
del opened[-1]
|
||||
|
||||
return outTokenList
|
||||
|
||||
@staticmethod
|
||||
def tokenize(code):
|
||||
'''
|
||||
Tokenize BBCode tags and parameters
|
||||
|
||||
Return the token list using a internal format. See the example:
|
||||
[
|
||||
{ 'tag' : 'p', 'args' : { 'font' : 'arial' } },
|
||||
'This is ',
|
||||
{ 'tag' : 'url', 'args' : {'url' : 'http://www.google.com'} },
|
||||
'a link to google',
|
||||
{ 'tag' : '/url' },
|
||||
{ 'tag' : '/p' }
|
||||
]
|
||||
'''
|
||||
re_tags = re.compile (r'(\[[^]]+\])', re.DOTALL | re.UNICODE)
|
||||
re_tagName = re.compile (r'\[([^]=\s]+)([^]]*)\]', re.DOTALL | re.UNICODE)
|
||||
#re_tagArgs = re.compile (r'\s*([^=]*)=(("([^"]+)")|([^\s]+))', re.DOTALL | re.UNICODE)
|
||||
re_tagArgs = re.compile (r'\s*([\w]*)=(("([^"]+)")|([^\s]+))', re.DOTALL | re.UNICODE)
|
||||
|
||||
# get a unique name and replace escaped braces encode utf8 to
|
||||
# prevent CLI/Web from barfing on unicode chars. Not sure why
|
||||
# this even needs to be 'unique' like this, but that's the way
|
||||
# they wrote it.
|
||||
unique = hashlib.md5(code.encode('utf8')).hexdigest()
|
||||
code = code.replace ('\[', unique+'_OPEN_BRACE')
|
||||
code = code.replace ('\]', unique+'_CLOSE_BRACE')
|
||||
|
||||
splitted = re_tags.split(code)
|
||||
|
||||
outTokenList = []
|
||||
for token in splitted:
|
||||
if len(token) == 0:
|
||||
continue
|
||||
|
||||
if token[0] == '[':
|
||||
match = re_tagName.match (token)
|
||||
if match:
|
||||
tagName = match.group(1)
|
||||
tagArgs = match.group(2)
|
||||
|
||||
tagToken = { 'tag' : tagName.lower() }
|
||||
|
||||
# parse arguments (if any)
|
||||
if len(tagArgs) > 0:
|
||||
allArgs = re_tagArgs.findall(tagArgs)
|
||||
|
||||
tagArgs = {}
|
||||
for arg in allArgs:
|
||||
# if the argument has no name, use the tagName itself
|
||||
argName = (arg[0] if arg[0] != '' else tagName)
|
||||
argValue = (arg[3] if (arg[1][0] == '"') else arg[4])
|
||||
|
||||
tagArgs[argName.lower()] = argValue.replace ('\"', '"')
|
||||
|
||||
tagToken['args'] = tagArgs
|
||||
|
||||
outTokenList.append (tagToken)
|
||||
|
||||
# no match, append the text as it is
|
||||
else:
|
||||
outTokenList.append (token)
|
||||
# append the text as it is
|
||||
else:
|
||||
outTokenList.append (token)
|
||||
|
||||
# restore escaped braces back (once code is parsed)
|
||||
restoredTokenList = []
|
||||
for token in outTokenList:
|
||||
if isinstance (token, basestring):
|
||||
token = token.replace (unique+'_OPEN_BRACE', '[').replace (unique+'_CLOSE_BRACE', ']')
|
||||
restoredTokenList.append (token)
|
||||
|
||||
return restoredTokenList
|
||||
|
||||
@@ -1,81 +0,0 @@
|
||||
AUTHOR
|
||||
Pau Sanchez
|
||||
http://www.codigomanso.com/
|
||||
|
||||
VERSION:
|
||||
bbcodeutils v1.0
|
||||
|
||||
LICENSE
|
||||
This code is licensed under Creative Commons Attribution 3.0
|
||||
http://creativecommons.org/licenses/by/3.0/
|
||||
|
||||
You can use this python module or any part of the code you want as long as you add
|
||||
my name as a contributor to your project.
|
||||
|
||||
DESCRIPTION
|
||||
This module can be used to produce HTML from BBCode, to generate BBCode or to fix invalid BBCode.
|
||||
|
||||
The classes are:
|
||||
- bbcodeparser
|
||||
- bbcodebuilder
|
||||
- bbcode2html
|
||||
|
||||
You can use bbcodeparser to parse BBCode and to produce output in any format you want.
|
||||
|
||||
Open the python file to find more information and examples of use of each class. It can
|
||||
be a good idea to check the test.py for examples
|
||||
|
||||
To run the unit tests:
|
||||
> python test.py
|
||||
|
||||
To run the performance test:
|
||||
> python test.py BBCodeTests.performanceTest
|
||||
|
||||
|
||||
EXAMPLES OF BBCode:
|
||||
|
||||
[b] -> bold
|
||||
[u] -> underline
|
||||
[i] -> italic
|
||||
|
||||
[center] -> center the text inside
|
||||
[color=XXX] -> change color of text
|
||||
[size=XXX] -> change size of text
|
||||
|
||||
Lists:
|
||||
[ul] -> unordered list
|
||||
[ol] -> ordered list
|
||||
[li] -> list item
|
||||
|
||||
[list] -> start unordered list
|
||||
[*] -> list item
|
||||
[list=1] -> start a list of numbers
|
||||
[list=a] -> start a list of alphabetic characters
|
||||
|
||||
Advanced:
|
||||
[url] -> link to url
|
||||
[url=http://link/url/]text[/url]
|
||||
[url link=http://link/url/ title="This is the title"]text[/url]
|
||||
|
||||
[img]http://to/image[/img]
|
||||
[img=230x330]http://to/image[/img]
|
||||
[img="Alt text here"]http://to/image[/img]
|
||||
[img="Alt text here" width=320 height=240]http://to/image[/img]
|
||||
|
||||
[email]asdf@asdf.com[/email]
|
||||
[email=john@asdf.com]John Smith[/email]
|
||||
|
||||
[google]search this[/google]
|
||||
[wikipedia]Tom Hanks[/wikipedia]
|
||||
[wikipedia lang=es]Tom Hanks[/wikipedia]
|
||||
|
||||
Tables:
|
||||
[table]
|
||||
[tr]
|
||||
[th]
|
||||
[td]
|
||||
|
||||
Advanced:
|
||||
[google]
|
||||
[wikipedia]
|
||||
|
||||
@@ -1,420 +0,0 @@
|
||||
#!/usr/bin/python
|
||||
# -*- coding: UTF-8 -*-
|
||||
#
|
||||
# Author: Pau Sanchez (contact@pausanchez.com)
|
||||
# Version: v1.0
|
||||
# Last Modified: 2010/09/15
|
||||
#
|
||||
# For the latest version check out:
|
||||
# http://www.codigomanso.com/en/projects
|
||||
#
|
||||
# My blog:
|
||||
# http://www.codigomanso.com/en/ - English Version
|
||||
# http://www.codigomanso.com/es/ - Spanish Version
|
||||
#
|
||||
|
||||
from bbcodeparser import bbcodeparser
|
||||
from bbcodebuilder import bbcodebuilder
|
||||
|
||||
import random
|
||||
import unittest
|
||||
|
||||
class BBCodeTests(unittest.TestCase):
|
||||
def setUp (self):
|
||||
self.bbcode = bbcodeparser()
|
||||
return
|
||||
|
||||
def testConstructor (self):
|
||||
self.assertEqual (bbcodeparser ('whatever').html(), 'whatever')
|
||||
self.assertEqual (bbcodeparser ('[b]bold[/b]').html(), '<b>bold</b>')
|
||||
self.assertEqual (str (bbcodeparser ('[b]bold[/b]')), '[b]bold[/b]')
|
||||
return
|
||||
|
||||
def testBold (self):
|
||||
self.assertEqual (self.bbcode.parse ('whatever').html(), 'whatever')
|
||||
self.assertEqual (self.bbcode.parse ('[b]bold[/b]').html(), '<b>bold</b>')
|
||||
self.assertEqual (self.bbcode.parse ('[B]bold[/b]').html(), '<b>bold</b>')
|
||||
self.assertEqual (self.bbcode.parse ('this is [B]bold[/B]').html(), 'this is <b>bold</b>')
|
||||
return
|
||||
|
||||
def testItalic (self):
|
||||
self.assertEqual (self.bbcode.parse ('[i]italic[/i]').html(), '<i>italic</i>')
|
||||
return
|
||||
|
||||
def testUnderline (self):
|
||||
self.assertEqual (self.bbcode.parse ('[u]italic[/u]').html(), '<u>italic</u>')
|
||||
return
|
||||
|
||||
def testURLs (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[url]http://www.google.com[/url]').html(),
|
||||
'<a href="http://www.google.com">http://www.google.com</a>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[url=http://www.google.com]Google[/url]').html(),
|
||||
'<a href="http://www.google.com">Google</a>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[url="http://www.google.com"]Google[/url]').html(),
|
||||
'<a href="http://www.google.com">Google</a>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[url="http://www.google.com" title="Search Engine"]Google[/url]').html(),
|
||||
'<a href="http://www.google.com" title="Search Engine">Google</a>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[url link="http://www.google.com"]Google[/url]').html(),
|
||||
'<a href="http://www.google.com">Google</a>'
|
||||
)
|
||||
return
|
||||
|
||||
def testPTag (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p color=#0000ff]blue[/p]').html(),
|
||||
u'<p style="color: #0000ff;">blue</p>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p size=12]12pt font[/p]').html(),
|
||||
u'<p style="font-size: 12pt;">12pt font</p>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p font=arial]arial[/p]').html(),
|
||||
u'<p style="font-family: arial;">arial</p>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p font=arial color=blue size=14]blue 14pt arial').html(),
|
||||
u'<p style="color: blue; font-size: 14pt; font-family: arial;">blue 14pt arial</p>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p class=whatever]text[/p]').html(),
|
||||
u'<p>text</p>'
|
||||
)
|
||||
return
|
||||
|
||||
def testColorTag (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[color=#0000ff]blue[/color]').html(),
|
||||
u'<span style="color: #0000ff;">blue</span>'
|
||||
)
|
||||
return
|
||||
|
||||
def testSizeTag (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[size=12]12pt font[/size]').html(),
|
||||
u'<span style="font-size: 12pt;">12pt font</span>'
|
||||
)
|
||||
return
|
||||
|
||||
def testEmail(self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[email]asdf@asdf.com[/email]').html(),
|
||||
u'<a href="mailto:asdf@asdf.com">asdf@asdf.com</a>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[email=john@smith.com]John Smith[/email]').html(),
|
||||
u'<a href="mailto:john@smith.com">John Smith</a>'
|
||||
)
|
||||
return
|
||||
|
||||
def testImgTag (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[img]http://www.codigomanso.com/image.jpg[/img]').html(),
|
||||
u'<img src="http://www.codigomanso.com/image.jpg" />'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[img="This is the ALT of the image"]http://www.codigomanso.com/image.jpg[/img]').html(),
|
||||
u'<img alt="This is the ALT of the image" src="http://www.codigomanso.com/image.jpg" />'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[img=320x200]http://www.codigomanso.com/image.jpg[/img]').html(),
|
||||
u'<img height="200" src="http://www.codigomanso.com/image.jpg" width="320" />'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[img=320x200 title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
|
||||
u'<img height="200" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[img="whatever" width=320 height="212" title="Image Test"]http://www.codigomanso.com/image.jpg[/img]').html(),
|
||||
u'<img alt="whatever" height="212" src="http://www.codigomanso.com/image.jpg" title="Image Test" width="320" />'
|
||||
)
|
||||
return
|
||||
|
||||
def testGoogleURL (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[google]asdf[/google]').html(),
|
||||
u'<a href="http://www.google.com/search?q=asdf">asdf</a>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[google]Tom Hanks[/google]').html(),
|
||||
u'<a href="http://www.google.com/search?q=Tom+Hanks">Tom Hanks</a>'
|
||||
)
|
||||
return
|
||||
|
||||
def testWikipediaURL (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[wikipedia]Tom Hanks[/wikipedia]').html(),
|
||||
u'<a href="http://www.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[wikipedia language=en]Tom Hanks[/wikipedia]').html(),
|
||||
u'<a href="http://en.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[wikipedia lang=es]Tom Hanks[/wikipedia]').html(),
|
||||
u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[wikipedia=es]Tom Hanks[/wikipedia]').html(),
|
||||
u'<a href="http://es.wikipedia.org/wiki/Tom_Hanks">Tom Hanks</a>'
|
||||
)
|
||||
return
|
||||
|
||||
def testListTags (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[ul][li]item 1[/li][li]item 2[/li][/ul]').html(),
|
||||
u'<ul><li>item 1</li><li>item 2</li></ul>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[ol][li]item 1[/li][li]item 2[/li][/ol]').html(),
|
||||
u'<ol><li>item 1</li><li>item 2</li></ol>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[list][li]item 1[/li][li]item 2[/li][/list]').html(),
|
||||
u'<ul><li>item 1</li><li>item 2</li></ul>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[list][*]item 1[*]item 2[/list]').html(),
|
||||
u'<ul><li>item 1</li><li>item 2</li></ul>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[list=1][li]item 1[/li][li]item 2[/li][/list]').html(),
|
||||
u'<ol type="1"><li>item 1</li><li>item 2</li></ol>'
|
||||
)
|
||||
return
|
||||
|
||||
def testInvalidCode (self):
|
||||
self.assertEqual (self.bbcode.parse ('[invalid]valid text[/invalid]').html(), 'valid text')
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[b]bold and [i]italics[/b]').html(),
|
||||
'<b>bold and <i>italics</i></b>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[/b]invalid[/b][/p]').html(),
|
||||
'invalid'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p][b]bold').html(),
|
||||
'<p><b>bold</b></p>'
|
||||
)
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[p][b]a <b>').html(),
|
||||
'<p><b>a <b></b></p>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[ol][li]item 1[li]item 2[/li][/ol]').html(),
|
||||
u'<ol><li>item 1</li><li>item 2</li></ol>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[b]\[b\] stands for [b]bold[/b]').html(),
|
||||
u'<b>[b] stands for </b><b>bold</b>'
|
||||
)
|
||||
return
|
||||
|
||||
def testEscapedBrackets (self):
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('\[b\]not bold\[/b\]').html(),
|
||||
u'[b]not bold[/b]'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('[b]\[b\] stands for bold[/b]').html(),
|
||||
u'<b>[b] stands for bold</b>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('\[b\][b]stands for bold[/b]').html(),
|
||||
u'[b]<b>stands for bold</b>'
|
||||
)
|
||||
|
||||
self.assertEqual (
|
||||
self.bbcode.parse ('\[b\][b]stands for bold[/b] just like <b> in HTML').html(),
|
||||
u'[b]<b>stands for bold</b> just like <b> in HTML'
|
||||
)
|
||||
|
||||
def testBigExample (self):
|
||||
inputText = """check this out
|
||||
|
||||
[h1 class=circle]heading[/h1]
|
||||
|
||||
[p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
|
||||
[/p]
|
||||
|
||||
fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
|
||||
[img]http://www.codigomanso.com/b.jpg[/img]
|
||||
[url]http://www.codigomanso.com/[/url]
|
||||
[url=http://www.codigomanso.com/]Codigo Manso[/url]
|
||||
[uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
|
||||
|
||||
[ul]
|
||||
[Li]item 1[/Li]
|
||||
[li]item 2[/LI]
|
||||
[/UL]
|
||||
|
||||
[list=1 ]
|
||||
[*]item 1
|
||||
[*]item 2
|
||||
[/list]
|
||||
|
||||
[table class="big"]
|
||||
[tr]
|
||||
[th]big[/th]
|
||||
[/tr]
|
||||
[/table]
|
||||
[invalid class="extra"]whatever[/invalid]"""
|
||||
|
||||
out = self.bbcode.parse (inputText).html(allowClassAttr = True)
|
||||
self.assertEquals (out, '''check this out
|
||||
|
||||
<h1 class="circle">heading</h1>
|
||||
|
||||
<p style="color: blue; font-size: 14pt; font-family: verdana, Times New Roman;">This is <b> bold </b> and this <i>italic</i> and this is <span style="color: red;">red</span> and this is <span style="color: red;">also red</span>.
|
||||
</p>
|
||||
|
||||
fix <b><i>bold <span style="font-family: verdana;"><span style="font-size: 12pt;">and</span></span> italic</i></b>
|
||||
<img src="http://www.codigomanso.com/b.jpg" />
|
||||
<a href="http://www.codigomanso.com/">http://www.codigomanso.com/</a>
|
||||
<a href="http://www.codigomanso.com/">Codigo Manso</a>
|
||||
<a href="http://www.codigomanso.com" title="Codigo Manso Blog">Codigo Manso</a>
|
||||
|
||||
<ul>
|
||||
<li>item 1</li>
|
||||
<li>item 2</li>
|
||||
</ul>
|
||||
|
||||
<ol type="1">
|
||||
<li>item 1
|
||||
</li><li>item 2
|
||||
</li></ol>
|
||||
|
||||
<table class="big">
|
||||
<tr>
|
||||
<th>big</th>
|
||||
</tr>
|
||||
</table>
|
||||
whatever''')
|
||||
|
||||
|
||||
def testBBCodeDumper (self):
|
||||
self.assertEquals (
|
||||
self.bbcode.parse ('[b]bold[/b]').bbcode(),
|
||||
'[b]bold[/b]'
|
||||
)
|
||||
|
||||
self.assertEquals (
|
||||
self.bbcode.parse ('[color=red]text in red[/color]').bbcode(),
|
||||
'[color=red]text in red[/color]'
|
||||
)
|
||||
self.assertEquals (
|
||||
self.bbcode.parse ('[p][color=red]text in red').bbcode(),
|
||||
'[p][color=red]text in red[/color][/p]'
|
||||
)
|
||||
|
||||
self.assertEquals (
|
||||
self.bbcode.parse ('This [b][i]code[/b] will be fixed[/invalid]').bbcode(),
|
||||
'This [b][i]code[/i][/b] will be fixed'
|
||||
)
|
||||
|
||||
self.assertEquals (
|
||||
self.bbcode.parse ('\[[url]http://www.codigomanso.com/en[/url]\]').bbcode(),
|
||||
"\[[url]http://www.codigomanso.com/en[/url]\]"
|
||||
)
|
||||
|
||||
def performanceTest(self):
|
||||
'''
|
||||
This test checks the performance of parse and html operations
|
||||
|
||||
To run this test type:
|
||||
> python test.py BBCodeTests.performanceTest
|
||||
'''
|
||||
inputText = """check this out
|
||||
|
||||
[h1 class=circle]heading[/h1]
|
||||
|
||||
[p size=14 color=blue font="verdana, Times New Roman"]This is [b] bold [/b] and this [i]italic[/i] and this is [color=red]red[/color] and this is [color="red"]also red[/color].
|
||||
[/p]
|
||||
|
||||
fix [b][i]bold [font=verdana][size=12]and[/size][/font] italic[/b]
|
||||
[img]http://www.codigomanso.com/b.jpg[/img]
|
||||
[url]http://www.codigomanso.com/[/url]
|
||||
[url=http://www.codigomanso.com/]Codigo Manso[/url]
|
||||
[uRl link=http://www.codigomanso.com title="Codigo Manso Blog"]Codigo Manso[/url]
|
||||
|
||||
[ul]
|
||||
[Li]item 1[/Li]
|
||||
[li]item 2[/LI]
|
||||
[/UL]
|
||||
|
||||
[list=1 ]
|
||||
[*]item 1
|
||||
[*]item 2
|
||||
[/list]
|
||||
|
||||
[table class="big"]
|
||||
[tr]
|
||||
[th]big[/th]
|
||||
[/tr]
|
||||
[/table]
|
||||
[invalid class="extra"]whatever[/invalid]"""
|
||||
|
||||
import time
|
||||
start = time.time()
|
||||
|
||||
for i in range(0, 12):
|
||||
inputText += inputText
|
||||
|
||||
print "len(inputText) = %.2f MB (took %.2f seconds)" % (len(inputText)/(1024.0*1024.0), time.time() - start)
|
||||
|
||||
bbcode = bbcodeparser()
|
||||
start = time.time()
|
||||
bbcode.parse (inputText)
|
||||
total = (time.time() - start)
|
||||
print "time (bbcode.parse()) = %f" % total
|
||||
print " >> %.2f chars/second" % (len(inputText) / total)
|
||||
|
||||
start = time.time()
|
||||
bbcode.html(doDeepCopy = False)
|
||||
total = (time.time() - start)
|
||||
print "time (bbcode.html()) = %f" % total
|
||||
print " >> %.2f chars/second" % (len(inputText) / total)
|
||||
return
|
||||
|
||||
def testCodeBuilder (self):
|
||||
bbcode = bbcodebuilder ()
|
||||
self.assertEquals (bbcode.b ('bold'), u'[b]bold[/b]')
|
||||
self.assertEquals (bbcode.color ('this goes in red', 'red'), u'[color=red]this goes in red[/color]')
|
||||
self.assertEquals (bbcode.url ('Google', 'http://www.google.com'), u'[url=http://www.google.com]Google[/url]')
|
||||
self.assertEquals (bbcode.alist('item 1', 'item 2'), u"[list=a]\n [*]item 1\n [*]item 2\n[/list]")
|
||||
return
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user