# <A brief description of your program>
#
# CS150 Spring 2020 Lab 11
#
# Name: 
# Section: 
#
# Creativity:
# 

# Import required R packages (suppressing conflict messages)
library(plyr, warn.conflicts=FALSE)
library(stringr, warn.conflicts=FALSE)
library(ggplot2, warn.conflicts=FALSE)


# Split strings on word boundaries, removing any punctuation
# Args:
#   strings: A vector of strings
# Returns a vector of strings (the words)
split_and_strip <- function(strings) {
  # str_subset removes any empty strings, or strings that contain only whitespace.
  # \S is the character class for non white-space characters
  unlist(str_split(str_subset(strings, "\\S+"), boundary("word")))
}


# Read file into a vector of cleaned and normalized words
# Args:
#   filename: Filename to analyze as a string
# Returns a vector of cleaned and normalized words
file_to_words <- function(filename) {
  # TODO: Fill in
}

# Create a ranked data frame of words and their counts
# Args:
#   words: Vector of cleaned words
# Returns a data.frame of words and counts in descending order of count
count_and_rank <- function(words) {
  # TODO: Fill in
}

# Prompt the user for a file name and construct ranks data.frame
filename <- readline(prompt="Enter a filename: ")
words <- file_to_words(filename)
counts <- count_and_rank(words)

# Print 10 most common words and generate a log-log plot count vs. rank

# TODO: Your code here