#!/usr/bin/env python
# coding: utf-8

# # Generating Concordances
# 
# This notebook shows how you can generate a concordance using lists.

# First we see what text files we have. 

# In[1]:


ls *.txt


# We are going to use the "Hume Enquiry.txt" from the Gutenberg Project. You can use whatever text you want. We print the first 50 characters to check.

# In[2]:


theText2Use = "Hume Treatise.txt"
with open(theText2Use, "r") as fileToRead:
    fileRead = fileToRead.read()
    
print("This string has", len(fileRead), "characters.")
print(fileRead[:50])


# ## Tokenization
# 
# Now we tokenize the text producing a list called "listOfTokens" and check the first words. This eliminate punctuation and lowercases the words.

# In[3]:


import re
listOfTokens = re.findall(r'\b\w[\w-]*\b', fileRead.lower())
print(listOfTokens[:10])


# ## Input
# 
# Now we get the word you want a concordance for an the context wanted.

# In[4]:


word2find = input("What word do you want collocates for? ").lower() # Ask for the word to search for
context = input("How much context do you want? ")# This asks for the context of words on either side to grab


# In[5]:


type(context)


# In[7]:


contextInt = int(context)
type(contextInt)


# In[9]:


len(listOfTokens)


# ## Main function
# 
# Here is the main function that does the work populating a new list with the lines of concordance. We check the first 5 concordance lines.

# In[10]:


def makeConc(word2conc,list2FindIn,context2Use,concList):

    end = len(list2FindIn)
    for location in range(end):
        if list2FindIn[location] == word2conc:
            # Here we check whether we are at the very beginning or end
            if (location - context2Use) < 0:
                beginCon = 0
            else:
                beginCon = location - context2Use
                
            if (location + context2Use) > end:
                endCon = end
            else:
                endCon = location + context2Use + 1
                
            theContext = (list2FindIn[beginCon:endCon])
            concordanceLine = ' '.join(theContext)
            # print(str(location) + ": " + concordanceLine)
            concList.append(str(location) + ": " + concordanceLine)

theConc = []
makeConc(word2find,listOfTokens,int(context),theConc)
theConc[-5:]


# ## Output
# 
# Finally, we output to a text file.

# In[11]:


nameOfResults = word2find.capitalize() + ".Concordance.txt"

with open(nameOfResults, "w") as fileToWrite:
    for line in theConc:
        fileToWrite.write(line + "\n")
    
print("Done")


# Here we check that the file was created.

# In[12]:


ls *.Concordance.txt


# ---
# [CC BY-SA](https://creativecommons.org/licenses/by-sa/4.0/) From [The Art of Literary Text Analysis](ArtOfLiteraryTextAnalysis.ipynb) by [Stéfan Sinclair](http://stefansinclair.name) &amp; [Geoffrey Rockwell](http://geoffreyrockwell.com)<br >Created September 30th, 2016 (Jupyter 4.2.1)

# In[ ]: