#load necessary packages
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,}"))#Match characters that come after commas or spaces
FirstName = unlist(str_extract_all(name,"[^,.]*$"))
#remove leading spaces
FirstName = str_trim(FirstName[FirstName != ""])
#Select the first set of characters for each string
FirstName = unlist(str_extract_all(FirstName,"^[[:alpha:]]+"))
#Match first set of characters that comes before a comma
LastName = unlist(str_extract_all(name,"^[^,]*"))
#Select last set of alphabet characters for each string
LastName = unlist(str_extract_all(LastName,"[[:alpha:]]+$"))
#put first and last names together
FullName = paste(FirstName,LastName, sep = " ")
data.frame(name,FullName)## name FullName
## 1 Moe Szyslak Moe Szyslak
## 2 Burns, C. Montgomery Montgomery Burns
## 3 Rev. Timothy Lovejoy Timothy Lovejoy
## 4 Ned Flanders Ned Flanders
## 5 Simpson, Homer Homer Simpson
## 6 Dr. Julius Hibbert Julius Hibbert#Flags true if name has two or more alphabet characters followed by a period
data.frame(name,HasTitle = str_detect(name,"[[:alpha:]]{2,}\\."))## name HasTitle
## 1 Moe Szyslak FALSE
## 2 Burns, C. Montgomery FALSE
## 3 Rev. Timothy Lovejoy TRUE
## 4 Ned Flanders FALSE
## 5 Simpson, Homer FALSE
## 6 Dr. Julius Hibbert TRUE#Flags true if name has one capital letter followed by a period
data.frame(name,HasSecondName = str_detect(name,"[A-Z]{1}\\."))## name HasSecondName
## 1 Moe Szyslak FALSE
## 2 Burns, C. Montgomery TRUE
## 3 Rev. Timothy Lovejoy FALSE
## 4 Ned Flanders FALSE
## 5 Simpson, Homer FALSE
## 6 Dr. Julius Hibbert FALSEThe regular expression [0-9]+\\$ matches at least one or more numbers followed by a literal dollar sign. However, it will not match any periods and will not match dollar signs at the beginning. This regular expression is probably meant to match US Dollars without change. If a decimal is placed in the string, it will match all numbers after the decimal.
#notice that $10 and 9 are not matched, while the 50$ is matched from 1.50$
unlist(str_extract_all(c("10$","2$","9999$","$10","1.50$","9"),"[0-9]+\\$"))## [1] "10$" "2$" "9999$" "50$"The regular expression \\b[a-z]{1,4}\\b matches one to four letter lowercase words that begin and end with lowercase letters.
unlist(str_extract_all("What words does this match? a b c? one two three?","\\b[a-z]{1,4}\\b"))## [1] "does" "this" "a" "b" "c" "one" "two"The regular expression .*?\\.txt$ matches strings that end in “.txt” even if there is nothing in front of the dot. It will also match spaces and other random characters.
unlist(str_extract_all(c("DataScience.txt",".txt","aa .txt", "#$%# .txt", "I have this long .txt file"),".*?\\.txt"))## [1] "DataScience.txt" ".txt" "aa .txt"
## [4] "#$%# .txt" "I have this long .txt"The regular expression \\d{2}/\\d{2}/\\d{4} will match two digits followed by a slash and then another two digits and another slash and then four digits. This is probably a date. Though, it will still match dates that are not valid.
#notice how dates without leading zeros are not matched
unlist(str_extract_all(c("01/01/2000","02/30/9999","00/00/0000","12/1/2018"),"\\d{2}/\\d{2}/\\d{4}"))## [1] "01/01/2000" "02/30/9999" "00/00/0000"The regular expression <(.+?)>.+?</\\1> matches any group of characters (as long as there is at least one character) between “<” and “>” and then matches any number of characters followed by the previous group of characters between “</” and “>”. This regular expression is probably used to match hmtl tags and their inner contents.
unlist(str_extract_all(c("<some html tag> I don't like html </some html tag>", "<a> Forgot the exit tag <a>", "< > Does it match empty tags? </ >"),"<(.+?)>.+?</\\1>"))## [1] "<some html tag> I don't like html </some html tag>"
## [2] "< > Does it match empty tags? </ >"