3. Extract Alpha RegEx

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,}"))
name
[1] "Moe Szyslak"          "Burns, C. Montgomery" "Rev. Timothy Lovejoy"
[4] "Ned Flanders"         "Simpson, Homer"       "Dr. Julius Hibbert"
  1. Use the tools of this chapter to rearrange the vector so that all elements conform to the standard first_name last_name.
  2. Construct a logical vector indicating whether a character has a title (i.e., Rev. and Dr.).
  3. Construct a logical vector indicating whether a character has a second name.
### Function to extract last names
get_last <- function(list){
    last <- str_extract(list, '[[:alpha:]]{1,}\\,|\\b [[:alpha:]]{2,}')
    last <- str_extract(last, "[[:alpha:]]{1,}")
    last
}

### Function to extract first names
get_first <- function(list) {
    first <- str_extract(list, '[[:alpha:]]{1,} |\\. [[:alpha:]]{1,}|\\, [[:alpha:]]{2,}')
    first <- str_extract(first, "[[:alpha:]]{1,}")
    first
}

# Create df
allNameInDF <- data.frame(first = get_first(name), 
                      last = get_last(name))

allNameInDF$fullname <- paste0(allNameInDF$first, " ", allNameInDF$last)

# Find if title exists
allNameInDF$title <- str_detect(name, 'Dr.|Rev.')

# Find if Middle name exists
allNameInDF$MiddleName <- str_detect(name, ' [:alpha:]{1}\\. ')

# Print DF
allNameInDF
       first     last         fullname title MiddleName
1        Moe  Szyslak      Moe Szyslak FALSE      FALSE
2 Montgomery    Burns Montgomery Burns FALSE       TRUE
3    Timothy  Lovejoy  Timothy Lovejoy  TRUE      FALSE
4        Ned Flanders     Ned Flanders FALSE      FALSE
5      Homer  Simpson    Homer Simpson FALSE      FALSE
6     Julius  Hibbert   Julius Hibbert  TRUE      FALSE

4. RegEx Construction

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

a)

This regex will return a string of one or more numbers followed by a ‘$’ sign.

#(a) [0-9]+\\$
a <- "892$xp09$.2*.2$oa$"
unlist(str_extract_all(a, '[0-9]+\\$'))
[1] "892$" "09$"  "2$"

b)

This regex will return a string of one to four lowercase alpha characters so long as they are bounded by non-word characters. Note that digits are considered to be word characters, thus the “two” does not show up because the “3” is not a boundary, and is not [a-z].

#(b) \b[a-z]{1,4}\\b
b <- "u-one 3two.three FOUR%four$;etc U pp Er"
unlist(str_extract_all(b, '\\b[a-z]{1,4}\\b'))
[1] "u"    "one"  "four" "etc"  "pp"

c)

This regex will return any string that ends with ‘.txt’. If it does not end with .txt, it will not return anything.

#(c) .*?\\.txt$
c <- "This$$is Ending with .txt"
c2 <- "this .txt is not ending with txt"
unlist(str_extract_all(c, '.*?\\.txt$'))
[1] "This$$is Ending with .txt"

d) dd/dd/dddd

This regex will return any string in the form ‘dd/dd/dddd’ where ‘d’ is a digit. This is a common form for dates.

#(d) \\d{2}/\\d{2}/\\d{4}
d <- "09/10/2016 10/12/2014 2015/01/02"
unlist(str_extract_all(d, '\\d{2}/\\d{2}/\\d{4}'))
[1] "09/10/2016" "10/12/2014"

e)

This regex returns any string that starts with a <text> and ends with </text>.

#(e) <(.+?)>.+?</\\1>
e <- "<div>HTML tags </div> <ol><li>This is LI Tag</li><li>Again LI Tag</li></ol>"
unlist(str_extract_all(e, '<(.+?)>.+?</\\1>'))
[1] "<div>HTML tags </div>"                                
[2] "<ol><li>This is LI Tag</li><li>Again LI Tag</li></ol>"