Week3-Assignment-RegEx

library(stringr)

raw.data <-"555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"   

3.Copy the intorductory vector name stores the extracted names

name <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))

3.1. Use the tools of this chapter to re-arrange the vector so that all of the elements conform to the standard first_name last_name

first_last <- function(x){
      
  if ( str_detect(x,",")){
    firstAndLast <- unlist(str_extract_all(x, "[[:alpha:]]{3,}")) 
    currentName <- paste(trimws(firstAndLast[2]),  firstAndLast[1])
  }  else if (str_detect(x, "^[:alpha:]{2,3}\\.") ) {
      firstAndLast <- unlist(str_extract_all(x, "[[:alpha:]]{4,}"))
      currentName <- paste(firstAndLast[1],  firstAndLast[2])
    } else {
      currentName <- x
      
    }
  currentName
}

standardNameFormat <- unname(sapply( name, first_last ))
standardNameFormat

## [1] "Moe Szyslak"      "Montgomery Burns" "Timothy Lovejoy" 
## [4] "Ned Flanders"     "Homer Simpson"    "Julius Hibbert"

3.2 Construct A logical Vector indicating whether a character has a title (Rev. or Dr.)

hasTitle <- str_detect(name, "^[:alpha:]{2,3}\\.") 

name

## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"

hasTitle

## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

3.2 Construct A logical Vector indicating whether a character has a second name

hasSecondName <- str_detect(name, "[:space:][:alpha:]{1}\\.[:space:][:alpha:]+") 

name

## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"

hasSecondName

## [1] FALSE  TRUE FALSE FALSE FALSE FALSE

4. Describe the types of strings that confom to the following regular expresstions and construct and example that is matched by the regular expression.

4.1 [0-9]+\$

One or more digits followed by a Dollar Sign

 str_detect ("1234$", "[0-9]+\\$")

## [1] TRUE

4.2 \b[a-z]{1,4}

The begining of a line starts with 1 to 4 occurrences of a lower case letter

str_detect ("a", "\\b[a-z]{1,4}")

## [1] TRUE

str_detect ("ab", "\\b[a-z]{1,4}")

## [1] TRUE

str_detect ("abc", "\\b[a-z]{1,4}")

## [1] TRUE

str_detect ("abcd", "\\b[a-z]{1,4}")

## [1] TRUE

4.3 .*?\.txt$

Anything with an optional space and then the line ends with “.txt”

str_detect("abc .txt", ".*?\\.txt$")

## [1] TRUE

str_detect("abc.txt", ".*?\\.txt$")

## [1] TRUE

4.4 \d{2/\d{2}/\d{4}}

Standard date format mm/dd/yyyy

str_detect("01/01/2016", "\\d{2}/\\d{2}/\\d{4}")

## [1] TRUE

4.5 <(.+?)>.+</\1>

This checks to see if you have HTML/XML tags that are properly closed with optional text between them.

str_detect("<foo>bar</foo>", "<(.+?)>.+</\\1>")

## [1] TRUE