Created
August 16, 2014 15:19
-
-
Save ktraff/7609e9e277cbb8c48bd6 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 csv | |
import re | |
f = open('out.csv','w') | |
def title_case(s, exceptions=['a', 'an', 'of', 'the', 'is']): | |
word_list = re.split(' ', s) #re.split behaves as expected | |
final = [word_list[0].capitalize()] | |
for word in word_list[1:]: | |
final.append(word in exceptions and word or word.capitalize()) | |
return " ".join(final) | |
def parseFirstName(f_name, name, email): | |
""" Attempts to find the first name from full name and email and defaults to something reasonable if not successful. """ | |
if f_name: | |
# Remove everything but the first name. | |
return title_case(f_name.split(' ', 1)[0]) | |
elif name: | |
# Return everything except the last name. | |
tokens = name.split(' ') | |
f_name_tokens = tokens[:-1] | |
if f_name_tokens and f_name_tokens[-1] not in ['&', 'and']: | |
# Avoid the case "John & Jane" | |
return title_case(" ".join(f_name_tokens)) | |
else: | |
return title_case(" ".join(tokens)) | |
return "Reader" | |
with open('in.csv', 'r') as csvfile: | |
reader = csv.reader(csvfile, delimiter=',', quotechar='"') | |
f.write(",".join(reader.next()) + '\n') | |
for idx, row in enumerate(reader): | |
email = row[0] | |
f_name = row[1] | |
l_name = row[2] | |
name = row[3] | |
first_name = parseFirstName(f_name, name, email) | |
f.write(",".join([email, first_name, l_name, name] + row[4:]) + '\n') | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment