Problem 3

Copy the introductory example. The vector name stores the extracted names:

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

library(stringr)
name <- unlist(str_extract_all(raw.data, "[[:alpha:]., ]{2,}"))
phone <- str_extract_all(raw.data, "\\(?(\\d{3})\\)?(-| )?\\(?(\\d{3})?(-| )?(\\d{4})")

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

(a). rearrange the vector so that all elements conform to the standard first_name last_name.

Note: Please note that Montgomery is assumed the first name for “Burns, C.Montgomery”, although in reality “C.” probably the initial of the first name and Montgomery would be the middle name. The commented out code would generate the result that would add both the initial and the middle name (“C.Montgomery”) as as the first name.

revised_name <- name


for (i in 1:length(revised_name)) {
    if (str_detect(revised_name[i], ",") && str_detect(revised_name[i], 
        "\\.") == TRUE) {
        draft_first_name <- str_sub(revised_name[i], (str_locate(revised_name[i], 
            ",")[1] + 1), (str_length(revised_name[i])))
        first_name <- str_sub(draft_first_name, (str_locate(draft_first_name, 
            "\\.")[1] + 1))
        
        ## if first name would include initial & middle name first_name <-
        ## str_trim(draft_first_name,side=c('left'))
        
        last_name <- str_sub(revised_name[i], end = (str_locate(revised_name[i], 
            ",")[1] - 1))
        revised_name[i] <- str_c(first_name, last_name, sep = " ")
        ## print(revised_name[i])
    } else if (str_detect(revised_name[i], ",") == FALSE && str_detect(revised_name[i], 
        "\\.") == TRUE) {
        revised_name[i] <- str_trim(str_sub(revised_name[i], (str_locate(revised_name[i], 
            "\\."))[1] + 1), side = c("both"))
        ## print(revised_name[i])
    } else if (str_detect(revised_name[i], ",") == TRUE && str_detect(revised_name[i], 
        "\\.") == FALSE) {
        first_name <- str_sub(revised_name[i], (str_locate(revised_name[i], 
            ",")[1] + 1), (str_length(revised_name[i])))
        last_name <- str_sub(revised_name[i], end = (str_locate(revised_name[i], 
            ",")[1] - 1))
        revised_name[i] <- str_c(first_name, last_name, sep = " ")
        ## print(revised_name[i])
    }
}

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

(b). Construct a logical vector indicating whether a character has a title (i.e.,Rev. and Dr.).

## str_extract_all(name,'[[:alpha:]]{2,}\\.')
has_title <- str_detect(name, "[[:alpha:]]{2,}\\.")
print(has_title)
## [1] FALSE FALSE  TRUE FALSE FALSE  TRUE
  1. Construct a logical vector indicating whether a character has a second name.
## Having an initial (for example C.Montgomery) along with first
## and last names is an indication that name has a second name.

## below codes check for an initial in the name
has_second_name <- str_detect(name, "[[:blank:]]{1}[[:alpha:]]{1}\\.")
print(has_second_name)
## [1] FALSE  TRUE FALSE FALSE FALSE FALSE

Problem 4. Describe the types of strings that conform to the following regular expressions and construct an example that is matched by the regular expression.

  1. [0-9]+\$

This will match a patterm that has any single or more numbers in 0 to 9 that ends with $ symbol:

numvar <- c("15678$bc34", "ABC50078$", "200500ux$", "234000", "8$")
matchnum <- str_extract_all(numvar, "[0-9]+\\$")
print(matchnum)
## [[1]]
## [1] "15678$"
## 
## [[2]]
## [1] "50078$"
## 
## [[3]]
## character(0)
## 
## [[4]]
## character(0)
## 
## [[5]]
## [1] "8$"

Here it matched the parts of element 1, 2, and 5 where one or more continuous numbers ended with $.

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

This match a set of smallcap characters in with length of 1 through four.

charvar <- c("mmmkBCD", "mmmkk", "Ammkk", "mmk", "mmmk", "aBCDefghL")
matchchar <- str_extract_all(charvar, "\\b[a-z]{1,4}\\b")
print(matchchar)
## [[1]]
## character(0)
## 
## [[2]]
## character(0)
## 
## [[3]]
## character(0)
## 
## [[4]]
## [1] "mmk"
## 
## [[5]]
## [1] "mmmk"
## 
## [[6]]
## character(0)

Here only element 4 and 5 matched that are all smallcap with length of four or less.

  1. .*?\.txt$

This will match a pattern that ends with “.txt” , the patterns can have 0 or 1 or more characters before .txt

txtvar <- c("desCRIPTIONfile.txt", "probLEM5.txtBBC", "probLEM5.txt", 
    ".txt", "txt")
matchtxt <- str_extract_all(txtvar, ".*?\\.txt$")
print(matchtxt)
## [[1]]
## [1] "desCRIPTIONfile.txt"
## 
## [[2]]
## character(0)
## 
## [[3]]
## [1] "probLEM5.txt"
## 
## [[4]]
## [1] ".txt"
## 
## [[5]]
## character(0)

Here only element 1,3, and 4 have been matched that ended with .txt

  1. \d{2}/\d{2}/\d{4}

THis will match patterns of eight digits that are seperated by “/” (forward slash) after 2nd and 4th digits.

digitvar <- c("12/34/567834", "12/34/5678ABCD", "efGJh56/67/1123abc5945/4546again78/34/8902a", 
    "12/3423/567834")
str_extract_all(digitvar, "\\d{2}/\\d{2}/\\d{4}")
## [[1]]
## [1] "12/34/5678"
## 
## [[2]]
## [1] "12/34/5678"
## 
## [[3]]
## [1] "56/67/1123" "78/34/8902"
## 
## [[4]]
## character(0)
matchdigit <- str_extract_all(digitvar, "\\d{2}/\\d{2}/\\d{4}")
print(matchdigit)
## [[1]]
## [1] "12/34/5678"
## 
## [[2]]
## [1] "12/34/5678"
## 
## [[3]]
## [1] "56/67/1123" "78/34/8902"
## 
## [[4]]
## character(0)

It picks up parts from element 1,2,3 that conform to the regular expression. Note that it picked the first four digits after the second forward slash (/) in element 1 but looked for exactly two digits after the first forward slash (/) in element 4 and ultimately matched nothing from that element.

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

This will match patterns similar to html tags. It will match one or more characters between < > at the begining followed by any number of characters and finaly exact same characters after a forward slash (/) and beween < > at the end of the pattern. such as some characters 

htmlvar <- c("<title>Page Title</title>abcdfeml23434 ashgym", "<h1>This is a Heading</h1>")
matchhtml <- str_extract_all(htmlvar, "<(.+?)>.+?</\\1>")
print(matchhtml)
## [[1]]
## [1] "<title>Page Title</title>"
## 
## [[2]]
## [1] "<h1>This is a Heading</h1>"

Problem 9: The following code hides a secret message. Crack it with R and regular expressions

Answer:

secret_message <- "clcopCow1zmstc0d87wnkig7OvdicpNuggvhryn92Gjuwczi8hqrfpRxs5Aj5dwpn0TanwoUwisdij7Lj8kpf03AT5Idr3coc0bt7yczjatOaootj55t3Nj3ne6c4Sfek.r1w1YwwojigOd6vrfUrbz2.2bkAnbhzgv4R9i05zEcrop.wAgnb.SqoU65fPa1otfb7wEm24k6t3sR9zqe5fy89n6Nd5t9kc4fE905gmc4Rgxo5nhDk!gr"

## Examining all the lower case characters and numbers. conclusion:
## Does not seem to have anything meaningful
unclassified_ld <- unlist(str_extract_all(secret_message, "[[:lower:][:digit:]\\.]"))

## Examining all the numbers. conclusion: Does not seem to have
## anything meaningful
unclassified_d <- unlist(str_extract_all(secret_message, "[[:digit:]\\.]"))

## Examining all the upper case characters and numbers. conclusion:
## Does not seem to have anything meaningful
unclassified_Ud <- unlist(str_extract_all(secret_message, "[[:upper:][:digit:]\\.]"))

## Examining all the upper case characters. conclusion: It does
## seem to have a message
unclassified_U <- unlist(str_extract_all(secret_message, "[[:upper:]\\.]"))

## removing all the spaces
unclassified_U <- paste(unclassified_U, collapse = "")

## replacing all the dots by blank spaces and then inserting the
## first dot again.
unclassified <- str_replace(str_replace_all(unclassified_U, "\\.", 
    " "), " ", "\\. ")

print(unclassified)
## [1] "CONGRATULATIONS. YOU ARE A SUPERNERD"