#!/usr/bin/python
 
import re
 
def convertLinks(str):
    #crazy regex from Shag, based on http://flanders.co.nz/2009/11/08/a-good-url-regular-expression-repost/
 
    prog = re.compile(r'(?#FQURL)(?:(?#Protocol)(?:(?:ht|f)tp(?:s?)\:\/\/)(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)*(?#TopLevel Domains)(?:[a-z]+\.?))(?#Port)(?::[\d]{1,5})?\.?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/|)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?|(?#BareURL)(?#Username:Password)(?:\w+:\w+@)?(?#Subdomains)(?:(?:[-\w]+\.)+(?#TopLevel Domains)(?:com|org|net|gov|mil|biz|info|mobi|name|aero|jobs|museum|travel|[a-z]{2}))(?#Port)(?::[\d]{1,5})?\.?(?#Directories)(?:(?:(?:\/(?:[-\w~!$+|.,=]|%[a-f\d]{2})+)+|\/|)+|\?|#)?(?#Query)(?:(?:\?(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)(?:&(?:[-\w~!$+|.,*:]|%[a-f\d{2}])+=?(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)*)*(?#Anchor)(?:#(?:[-\w~!$+|.,*:=]|%[a-f\d]{2})*)?)')
 
    return prog.sub(r'<a href="\g&lt;0&gt;">\g&lt;0&gt;</a>', str)
 
#single url
print convertLinks('http://tikirobot.net\n')
 
#string
print convertLinks('See http://tikirobot.net for more info.\n')
 
#string w/ anchor
print convertLinks('See http://tikirobot.net/#foo for more info.\n')
 
#two urls in a string
print convertLinks('See http://tikirobot.net or http://wikipedia.org for more info.\n')
 
#some test urls from flanders.co.nz
print convertLinks('This is a google search: http://www.google.com/search?q=good+url+regex&amp;rls=com.microsoft:*&amp;ie=UTF-8&amp;oe=UTF-8&amp;startIndex=&amp;startPage=1\n')
 
print convertLinks('ftp://joe:password@ftp.filetransferprotocal.com is a ftp url\n')
 
print convertLinks('There is a bare url google.ru somewhere in this sentence\n')
 
#test cases from shag
print convertLinks('query string: https://some-url.com/?query=&amp;name=joe&amp;filter=*.*\n')
 
print convertLinks('both a query string and an anchor with no host name separator slash: https://some-url.com?query=&amp;name=joe?filter=*.*#some_anchor\n')
 
print convertLinks('both a query string and an anchor: https://some-url.com/?query=&amp;name=joe&amp;filter=*.*#some_anchor\n')
 
print convertLinks('DNS name with a concluding period: http://some-url.com./\n')
 
print convertLinks('DNS name with a concluding period and query string: http://some-url.com./?foo=bar\n')
 
print convertLinks('single-component DNS name plus root: http://to./\n')
 
print convertLinks('single-component DNS name: http://to/\n')
 
print convertLinks('words with slashes: unread/unregistered\n')

# pyAWS no longer works with the AWS signed request requirement
# Sign an AWS REST request using the method described here
# http://docs.amazonwebservices.com/AWSECommerceService/latest/DG/index.html?RequestAuthenticationArticle.html
#_______________________________________________________________________________
def getSignedUrl(accessKey, secretKey, params):
 
    #Step 0: add accessKey, Service, Timestamp, and Version to params
    params['AWSAccessKeyId'] = accessKey
    params['Service']        = 'AWSECommerceService'
 
    #Amazon adds hundredths of a second to the timestamp (always .000), so we do too.
    #(see http://associates-amazon.s3.amazonaws.com/signed-requests/helper/index.html)
    params['Timestamp']      = time.strftime("%Y-%m-%dT%H:%M:%S.000Z", time.gmtime())
    params['Version']        = '2009-03-31'
 
    #Step 1a: sort params
    paramsList = params.items()
    paramsList.sort()
 
    #Step 1b-d: create canonicalizedQueryString
    # This code comes from http://blog.umlungu.co.uk/blog/2009/jul/12/pyaws-adding-request-authentication/
    # and the resulting discussion
    canonicalizedQueryString = '&'.join(['%s=%s' % (k,urllib.quote(str(v))) for (k,v) in paramsList if v])
 
    #Step 2: create string to sign
    host          = 'ecs.amazonaws.com'
    requestUri    = '/onca/xml'
    stringToSign  = 'GET\n'
    stringToSign += host +'\n'
    stringToSign += requestUri+'\n'
    stringToSign += canonicalizedQueryString.encode('utf-8')
 
    #Step 3: create HMAC
    digest = hmac.new(secretKey, stringToSign, hashlib.sha256).digest()
 
    #Step 4: base64 the hmac
    sig = base64.b64encode(digest)
 
    #Step 5: append signature to query
    url  = 'http://' + host + requestUri + '?'
    url += canonicalizedQueryString + "&Signature=" + urllib.quote(sig)
 
    return url

#4.5GB archive listing using tar
time tar tvf fifteenthcensus00reel2149_jp2.tar 
 
(output suppressed, timing stable whether file cache is warmed or not)
 
real	2m1.876s
user	0m0.444s
sys	0m7.740s
 
#4.5GB archive listing using 7z with cold file cache
time 7z l fifteenthcensus00reel2149_jp2.tar 
 
(output suppressed)
 
real	0m10.419s
user	0m0.080s
sys	0m0.124s
5:28 PM
 
#4.5GB archive listing using 7z with hot file cache
time 7z l fifteenthcensus00reel2149_jp2.tar 
 
(output suppressed)
 
real	0m0.145s
user	0m0.052s
sys	0m0.040s
 
 
#extraction of last file in a 4.5GB archive using tar
time tar xvf fifteenthcensus00reel2149_jp2.tar fifteenthcensus00reel2149_jp2/fifteenthcensus00reel2149_0185.jp2
 
real	2m3.545s
user	0m0.436s
sys	0m7.824s
 
#extraction of last file in a 4.5GB archive using 7z and a hot file cache
time 7z e fifteenthcensus00reel2149_jp2.tar fifteenthcensus00reel2149_jp2/fifteenthcensus00reel2149_0185.jp2
 
real	0m0.104s
user	0m0.036s
sys	0m0.036s