utils.R

# A helper method for printing to the console.
p <- function(...) {
  cat("[run_analysis.R]", ..., "\n")
}

#this function downloads and extract the zip file if doesn't exit.
downloadExtractData <- function(url, zipFile, targetFile){
  if(!file.exists(zipFile)){
    #download file.
    tryCatch({
      download.file(url, destfile = zipFile, method = 'curl')
      unzip(zipFile, files=targetFile)
    }, error = function(e) {
          p("Cannot download or extract specified File.", zipFile)
    })
  }
}

# Extracts the required data and return the cleaned target data.
prepareData <- function() {
  url <- 'https://d396qusza40orc.cloudfront.net/exdata%2Fdata%2Fhousehold_power_consumption.zip'
  zipFile <- 'exdata-data-household_power_consumption.zip'
  targetFile <- 'household_power_consumption.txt'
  
  downloadExtractData(url, zipFile, targetFile)
  
  # Specify column data types.
  cols <- c("character", "character", rep("numeric", 7))
  
  # Read in the required rows.
  ds <- read.table(targetFile, header=T, sep=';', na.strings="?", colClasses=cols)
  ds <- ds[(ds$Date == "1/2/2007") | (ds$Date == "2/2/2007"),]
  #Alternative : ds <- ds[ds$Date %in% c("1/2/2007", "2/2/2007"),]
  
  # Prepare vector with the date and time 
  dateTime <- paste(ds$Date, ds$Time, sep=' ')
  # Convert Date and Time and add dateTime to the dataset.
  ds$DateTime <- strptime(dateTime, format="%d/%m/%Y %H:%M:%S")
  
  # Return the data.
  ds
}

#This function cache the data
getData <- function(){
  if(!exists('cached')){
    cached <<- prepareData()
  }
  cached
}