Created
June 3, 2015 00:38
-
-
Save paultopia/9e39cb37021f9f44658d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys, re, argparse, string, codecs | |
parser = argparse.ArgumentParser() | |
parser.add_argument("citearg", help="the file containing the citations from footnotes etc.") | |
parser.add_argument("refarg", help="the file containing reference list") | |
manuFiles = parser.parse_args() | |
def makeCorpoi(citefile, reffile): | |
citebox = open(citefile, 'r') | |
refbox = open(reffile, 'r') | |
citecorpus = citebox.read() | |
refcorpus = refbox.read() | |
citebox.close() | |
refbox.close() | |
corpoi = [str(citecorpus), str(refcorpus)] | |
return corpoi | |
def conv2ASCII(bigstring): | |
def convHandler(error): | |
return ('1FOREIGN', error.start + 1) | |
codecs.register_error('foreign', convHandler) | |
bigstring = bigstring.encode('ascii', 'foreign') | |
return bigstring | |
# stringstring = str(bigstring) | |
# return stringstring | |
def makeCiteList(citefile): | |
citepattern = r'[\s(][A-Z1][A-Za-z1]*-?[A-Za-z1]*[ ,]? \(?\d\d\d\d[a-z]?[\s.,)]' | |
rawCitelist = re.findall(citepattern, citefile) | |
cleanCitelist = cleanup(rawCitelist) | |
finalCiteList = list(set(cleanCitelist)) | |
return(finalCiteList) | |
def checkCites(citefile, reffile): | |
corpoi = makeCorpoi(citefile, reffile) | |
citecorpus = corpoi[0] | |
citecorpus = conv2ASCII(citecorpus) | |
citelist = makeCiteList(citecorpus) | |
# and a bunch of irrelevant stuff | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment