Assignment3 StringR

library(stringr)
raw.data <- "555-1239Moe Szyslak(636) 555-0113Burns, C. Montgomery555-6542Rev. Timothy Lovejoy555 8904Ned Flanders636-555-3226Simpson, Homer5553642Dr. Julius Hibbert"
name <- unlist(str_extract_all(raw.data, "[[:alpha:].,, ]{2,}"))

Problem 3

Rearrange vector as first name last name

nameFirstLast <- sapply(strsplit(name, ", "),function(x){paste(rev(x),collapse=" ")})
print(nameFirstLast)

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

Logic vector whether a character has a title

str_detect(name, c("Dr.|Rev.")) 

## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE

Logic vector whether a character has a second name (abbreviated first name)

str_detect(name, "[A-Z][.]")

## [1] FALSE  TRUE FALSE FALSE FALSE FALSE

Problem 4

a

#[0-9]+\$ Any number between 0-9, 1 or more times at the end of a line.

111

b

#\b[a-z]{1,4}\b A word starts with any lowercase letter a-z and is between 1-4 letters long.

cat

c

#.*?\.txt$ Any character followed by “.txt” at the end of the line. This is a lazy format so the program stops at the first “.txt”.

blah.txt

d

#\d{2}/\d{2}/\d{4} Two digits 0-9, a forward slash, two digits 0-9, a forward slash, then four digits 0-9

09/15/2019

e

#<(.+?)>.+?</\1> Opening tag with any character in lazy format, any character in lazy format, closing tag matching the opening tag.

#