"""Analyze the complete works of William Shakespeare.

Download and extract the bard's complete works from:
http://www.it.usyd.edu.au/~matty/Shakespeare/

Copy this script into its root directory and run.
This script will produce a frequency distribution of
the unique characters in Shakespeare's corpus, treating
consecutive whitespace as one.
"""

import os
import string

def readfile(fn):
    inf = open(fn)
    text = inf.read()
    inf.close()
    return text

class TextStat:
    def __init__(self):
        self._numfiles = 0
        self._numchars = 0
        self._chardict = {' ': 0}
    def parsefile(self, fn):
        ws = False
        for c in readfile(fn):
            if c in string.printable:
                if c in string.whitespace:
                    if ws == False:
                        self._chardict[' '] += 1
                        self._numchars += 1
                        ws = True
                else:
                    ws = False
                    self._numchars += 1
                    if c in self._chardict:
                        self._chardict[c] += 1
                    else:
                        self._chardict[c] = 1
        self._numfiles += 1
    def __str__(self):
        s = str(self._numchars) + " characters in " +str(self._numfiles) + " files.\n"
        s += str(len(self._chardict)) + " unique characters.\nFrequency distribution:\n"
        for k in sorted(self._chardict.keys()):
            s += str(k) + "\t" + str(self._chardict[k]) + "\n"
        return s
    

if __name__ == "__main__":
    T = TextStat()
    for base, dirs, files in os.walk(os.getcwd()):
        if base != os.getcwd():
            for f in files:
                T.parsefile(os.path.join(base, f))

    print T

### EOF ###