Last active
August 29, 2015 14:02
-
-
Save clemsos/b0f094c772e2fdb0da01 to your computer and use it in GitHub Desktop.
Convert scientific citations in plain text to Latex
This file contains hidden or 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
#!/usr/bin/python | |
# convert citations into latex format | |
# | |
# (Nivre et al., 2007) | |
# (Sagae and Tsujii 2007) | |
# Nivre (2007) | |
# (Chen et al., 2007; Dredze et al., 2007). | |
# | |
# \cite{Nivre2007} | |
import fileinput | |
import re | |
import os | |
myfile="chapters/_chapitre2.tex" | |
# with open(myfile,"rw") as chap: | |
for line in fileinput.input(myfile, inplace=True): | |
# for line in chap: | |
# Regexp from http://stackoverflow.com/a/16826935/887594 | |
author = "(?:[A-Z][A-Za-z'`-]+)" | |
etal = "(?:et al.?)" | |
additional = "(?:,? (?:(?:and |& )?" + author + "|" + etal + "))" | |
year_num = "(?:19|20)[0-9][0-9]" | |
page_num = "(?:, p.? [0-9]+)?" # Always optional | |
year = "(?:, *"+year_num+page_num+"| *\("+year_num+page_num+"\))" | |
regex = "(" + author + additional+"*" + year + ")" | |
matches = re.findall(regex, line) | |
l="" | |
if len(matches): | |
for quote in matches: | |
if len(quote.split(','))!=1: | |
q="("+quote+")" | |
c="\cite{"+quote.split(',')[0]+quote.split(',')[1][1:]+"}" | |
# print(c,q) | |
l=line.replace(q, c) | |
line=l | |
print line, | |
print "quote converted to Latex" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment