Extracting the names from the Simpson’s Phone Directory

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

Question 3

a) Use the tools of this chapter to rearrange the vector so that all the elements conform to the standard first_name last_name.

library(stringr)
name <- str_extract_all(raw.data, "[[:alpha:]., ]{2,}")
name
## [[1]]
## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"
# Check for ",". If no comma, is first_name last_name, if yes comma, reverse to make first_name last-name
reverse <- function(full_name) {
    fl_name <- ifelse(str_detect(full_name,","),
                      paste( str_split(full_name, ", ")[[1]][[2]], str_split(full_name, ", ")[[1]][[1]] ),
                      full_name)
    str_split( str_replace(fl_name, "[[:alpha:]]{1,}\\. ", ""), " ")
}
Simpson_names <- lapply(name[[1]], reverse)
Simpson_names
## [[1]]
## [[1]][[1]]
## [1] "Moe"     "Szyslak"
## 
## 
## [[2]]
## [[2]][[1]]
## [1] "Montgomery" "Burns"     
## 
## 
## [[3]]
## [[3]][[1]]
## [1] "Timothy" "Lovejoy"
## 
## 
## [[4]]
## [[4]][[1]]
## [1] "Ned"      "Flanders"
## 
## 
## [[5]]
## [[5]][[1]]
## [1] "Homer"   "Simpson"
## 
## 
## [[6]]
## [[6]][[1]]
## [1] "Julius"  "Hibbert"

b) Construct a logical vector indicating whether a character has a title.

has_title <- function(full_name) !is.na(str_extract(full_name, "[[:alpha:]]{2,}\\."))
name
## [[1]]
## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"
lapply(name, has_title)
## [[1]]
## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

c) Construct a logical vector indicating whether a character has a second name

has_secname <- function(full_name) !is.na(str_extract(full_name, "\\b[[:alpha:]]{1,1}\\."))
has_secname <- function(full_name) !is.na(str_extract(full_name, "\\b[[:alpha:]]{1,1}\\."))
name
## [[1]]
## [1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"
lapply(name, has_secname)
## [[1]]
## [1] FALSE  TRUE FALSE FALSE FALSE FALSE

Question 4

Describe the types of strings that conform to the following regular expressions and construct an example that is matched by the regular expression.

a) [0-9]+\$

One or more numbers followed by a dollar sign

str_detect("12345$", "[0-9]+\\$")
## [1] TRUE

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

A lower case character string that is between 1 to 4 letters long

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

c) .*?\.txt$

0 or more (ungreedy) digits of any character followed by a . and txt with nothing after the txt In other words a name of a text file ending .txt

str_detect("jad34.txt", ".*?\\.txt$") # TRUE
## [1] TRUE

d) \d{2}/\d{2}/\d{4}

2 digits / 2 digits/ 4 digits which would match a date such as 09/16/2018

str_detect("01/01/2018","\\d{2}/\\d{2}/\\d{4}")
## [1] TRUE

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

A character string of any length between <> and </> as in an html tag. I really love regex!!!!!!!!!!! 
str_detect("<html>I really love regex!!!!!!!!!!!</html>","<(.+?)>.+?</\\1>")
## [1] TRUE