Expand common (and some very uncommon) english contractions

contractions.py

"""
this code is not mine! i shamelessly copied it from http://stackoverflow.com/questions/19790188/expanding-english-language-contractions-in-python
all credits go to alko and arturomp @ stack overflow.

basically, it's a big find/replace.
"""

import re
cList = {
  "ain't": "am not",
  "aren't": "are not",
  "can't": "cannot",
  "can't've": "cannot have",
  "'cause": "because",
  "could've": "could have",
  "couldn't": "could not",
  "couldn't've": "could not have",
  "didn't": "did not",
  "doesn't": "does not",
  "don't": "do not",
  "hadn't": "had not",
  "hadn't've": "had not have",
  "hasn't": "has not",
  "haven't": "have not",
  "he'd": "he would",
  "he'd've": "he would have",
  "he'll": "he will",
  "he'll've": "he will have",
  "he's": "he is",
  "how'd": "how did",
  "how'd'y": "how do you",
  "how'll": "how will",
  "how's": "how is",
  "I'd": "I would",
  "I'd've": "I would have",
  "I'll": "I will",
  "I'll've": "I will have",
  "I'm": "I am",
  "I've": "I have",
  "isn't": "is not",
  "it'd": "it had",
  "it'd've": "it would have",
  "it'll": "it will",
  "it'll've": "it will have",
  "it's": "it is",
  "let's": "let us",
  "ma'am": "madam",
  "mayn't": "may not",
  "might've": "might have",
  "mightn't": "might not",
  "mightn't've": "might not have",
  "must've": "must have",
  "mustn't": "must not",
  "mustn't've": "must not have",
  "needn't": "need not",
  "needn't've": "need not have",
  "o'clock": "of the clock",
  "oughtn't": "ought not",
  "oughtn't've": "ought not have",
  "shan't": "shall not",
  "sha'n't": "shall not",
  "shan't've": "shall not have",
  "she'd": "she would",
  "she'd've": "she would have",
  "she'll": "she will",
  "she'll've": "she will have",
  "she's": "she is",
  "should've": "should have",
  "shouldn't": "should not",
  "shouldn't've": "should not have",
  "so've": "so have",
  "so's": "so is",
  "that'd": "that would",
  "that'd've": "that would have",
  "that's": "that is",
  "there'd": "there had",
  "there'd've": "there would have",
  "there's": "there is",
  "they'd": "they would",
  "they'd've": "they would have",
  "they'll": "they will",
  "they'll've": "they will have",
  "they're": "they are",
  "they've": "they have",
  "to've": "to have",
  "wasn't": "was not",
  "we'd": "we had",
  "we'd've": "we would have",
  "we'll": "we will",
  "we'll've": "we will have",
  "we're": "we are",
  "we've": "we have",
  "weren't": "were not",
  "what'll": "what will",
  "what'll've": "what will have",
  "what're": "what are",
  "what's": "what is",
  "what've": "what have",
  "when's": "when is",
  "when've": "when have",
  "where'd": "where did",
  "where's": "where is",
  "where've": "where have",
  "who'll": "who will",
  "who'll've": "who will have",
  "who's": "who is",
  "who've": "who have",
  "why's": "why is",
  "why've": "why have",
  "will've": "will have",
  "won't": "will not",
  "won't've": "will not have",
  "would've": "would have",
  "wouldn't": "would not",
  "wouldn't've": "would not have",
  "y'all": "you all",
  "y'alls": "you alls",
  "y'all'd": "you all would",
  "y'all'd've": "you all would have",
  "y'all're": "you all are",
  "y'all've": "you all have",
  "you'd": "you had",
  "you'd've": "you would have",
  "you'll": "you you will",
  "you'll've": "you you will have",
  "you're": "you are",
  "you've": "you have"
}

c_re = re.compile('(%s)' % '|'.join(cList.keys()))

def expandContractions(text, c_re=c_re):
    def replace(match):
        return cList[match.group(0)]
    return c_re.sub(replace, text)

# examples
print expandContractions('Don\'t you get it?')
print expandContractions('I ain\'t got time for y\'alls foolishness')
print expandContractions('You won\'t live to see tomorrow.')
print expandContractions('You\'ve got serious cojones coming in here like that.')
print expandContractions('I hadn\'t\'ve enough')

changing line 135 to return c_re.sub(replace, text.lower()) will result in a better demo of the function & dictionary

as it stands, the capital letters are preventing some of the contractions from being expanded

Also, it's a bit clearer if you use double quotes:
print(expandContractions("Don't you get it?"))
print(expandContractions("I ain't got time for y'alls foolishness"))
print(expandContractions("You won't live to see tomorrow."))
print(expandContractions("You've got serious cojones coming in here like that."))
print(expandContractions("I hadn't've enough"))

Also, maybe move all the contractions containing three parts above it two parts counterpart.
For example:
"hadn't've": "had not have",
"hadn't": "had not",
If you do not do this, you will get:
"I hadn't've enough" -> "I had not've enough" which is still not fully expanded.

Good point romusters. Here is some code to sort the contracts

import pandas as pd

cList = {.....}

# Also, move all the multiple contractions ahead of single contracts
#   "hadn't've" should be evaluated first to prevent this:
#       "I hadn't've enough" -> "I had not've enough" which is still not fully expanded.
df_cList = pd.DataFrame(list(cList.items()), columns = ['contraction', 'expansion'])
df_cList['apos_count'] = df_cList['contraction'].apply(lambda x: x.count("'"))
df_cList.sort_values('apos_count', ascending=False, inplace=True)

You will probably want to add word boundaries to the regex. I got some errors while trying to parse sentences that had some words like 'eight' or 'English' in it.
c_re = re.compile(r'\b(?:%s)\b' % '|'.join(cList.keys()))

Just used this dictionary in a competition on Kaggle. Thanks for compiling it.

Also, maybe move all the contractions containing three parts above it two parts counterpart.
For example:
"hadn't've": "had not have",
"hadn't": "had not",
If you do not do this, you will get:
"I hadn't've enough" -> "I had not've enough" which is still not fully expanded.

i've got serious cojones coming in here like that.
i've is not expanding to i have

changing line 135 to return c_re.sub(replace, text.lower()) will result in a better demo of the function & dictionary

as it stands, the capital letters are preventing some of the contractions from being expanded

If the text follows grammatical rules, only the word "I" should be in uppercase in which case the dictionary works fine.

So starting from the Wikipedia contractions page: https://en.wikipedia.org/wiki/Wikipedia:List_of_English_contractions
I did a little script to grab the dataset:

https://gist.github.com/loretoparisi/c221a9c55fb71a23ff4e7bba3b794425