Assignment 3

Exercise 3

library(stringr)

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

3 part 1 Rearrange vector to look like first_name last_name

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"

name_order = gsub(" [A-Z]{1}\\. " , " " , name)
first_last = gsub("(\\w+),\\s(\\w+)", "\\2 \\1", name_order)
first_last

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

3 part 2 Create logical vector indicating title (Rev or Dr)

title = unlist(str_detect(name,"[[:alpha:]]{2,}[.]"))
data.frame(first_last,title)

##             first_last title
## 1          Moe Szyslak FALSE
## 2     Montgomery Burns FALSE
## 3 Rev. Timothy Lovejoy  TRUE
## 4         Ned Flanders FALSE
## 5        Homer Simpson FALSE
## 6   Dr. Julius Hibbert  TRUE

3 part 3 Create logical vector indicating if second name?

name_two = str_detect(name," [A-z]{1}\\. ")
data.frame(name, first_last, title, name_two)

##                   name           first_last title name_two
## 1          Moe Szyslak          Moe Szyslak FALSE    FALSE
## 2 Burns, C. Montgomery     Montgomery Burns FALSE     TRUE
## 3 Rev. Timothy Lovejoy Rev. Timothy Lovejoy  TRUE    FALSE
## 4         Ned Flanders         Ned Flanders FALSE    FALSE
## 5       Simpson, Homer        Homer Simpson FALSE    FALSE
## 6   Dr. Julius Hibbert   Dr. Julius Hibbert  TRUE    FALSE

Exercise 4

Describe the types of strings. Below I have constructed examples for the given expressions involving passwords and determining if the criteria from each string allow each password to hold.

4 part 1 [0-9]+\$

String containing a pattern of one or more numbers with a dollar sign

passwords = c("3Ccwk4DRd", "KXX7$GUxm.txt", "fHk$FgWEF", "3w8zm4Xs", "D98$EAcHw")
hold = str_detect(passwords, "[0-9]+\\$")
data.frame(passwords, hold)

##       passwords  hold
## 1     3Ccwk4DRd FALSE
## 2 KXX7$GUxm.txt  TRUE
## 3     fHk$FgWEF FALSE
## 4      3w8zm4Xs FALSE
## 5     D98$EAcHw  TRUE

4 part 2 \b[a-z]{1,4}\b

String containing up to four lower case letters, so long as those lower case letters are word edges

passwords = c("3C.cwk.4DRd", "3w8zm4Xs", "V386$h68A", "wrCyQQcw")
hold = str_detect(passwords, "\\b[a-z]{1,4}\\b")
data.frame(passwords, hold)

##     passwords  hold
## 1 3C.cwk.4DRd  TRUE
## 2    3w8zm4Xs FALSE
## 3   V386$h68A FALSE
## 4    wrCyQQcw FALSE

4 part 3 .*?\txt$

String pattern ending in “.txt”

hold = str_detect(passwords, ".*?\\.txt$")
data.frame(passwords, hold)

##     passwords  hold
## 1 3C.cwk.4DRd FALSE
## 2    3w8zm4Xs FALSE
## 3   V386$h68A FALSE
## 4    wrCyQQcw FALSE

4 part 4 \d{2}/\d{2}/\d{4}

String containing pattern of two digits followed by a front slash, two more digits, another front slash and finally four digits.

passwords = c("02\02\0202", "45689587", "56/85/1538", "87-98-4585")
hold = str_detect(passwords, "\\d{2}/\\d{2}/\\d{4}")
data.frame(passwords, hold)

##     passwords  hold
## 1 02\002\0202 FALSE
## 2    45689587 FALSE
## 3  56/85/1538  TRUE
## 4  87-98-4585 FALSE

4 part 5 <(.+?)>.+?</\1>

String pattern containing tags.

passwords = c("<nope>yep</no>", "KXX7$GUxm.txt", "<tag>hi</tag>", "fHk$FgWEF")
hold = str_detect(passwords, "<(.+?)>.+?</\\1>")
data.frame(passwords, hold)

##        passwords  hold
## 1 <nope>yep</no> FALSE
## 2  KXX7$GUxm.txt FALSE
## 3  <tag>hi</tag>  TRUE
## 4      fHk$FgWEF FALSE

Exercise 9

Crack the code.

code = "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

cracked = unlist(str_extract_all(code, "[[A-Z].!]"))
paste(cracked, collapse = "")

## [1] "CONGRATULATIONS.YOU.ARE.A.SUPERNERD!"

Answer to the code.

newcode = "clcopTow1zmstc0d87wnkig7HvdicpIuggvhryn92Sjuwczi8hqrfp.xs5Ij5dwpn0Sanwo.wisdij7Tj8kpf03HE5.dr3coc0bt7yczjatCaootj55t3Oj3ne6c4OfekLr1w1EwwojigSd6vrfTrbz2.2bkEnbhzgv4X9i05zTcropRwAgnb.CqoR65fEa1otfb7wDm24k6t3sI9zqe5fy89n6Td5t9kc4f!905gmc4gxo5nhkgr"
RosettaStone = unlist(str_extract_all(newcode, "[[:upper:].!]"))
answer = paste(RosettaStone, collapse = "")