Problems 4.Describe the types of strings that conform to the following regular expressions and construct an example that is matched by the regular expression. (a) [0-9]+\$ (b) \b[a-z]{1,4}\b (c) .*?\.txt$ (d) \d{2}/\d{2}/\d{4} (e) <(.+?)>.+?</\1>
here is the code
library(stringr)
# (a) [0-9]+\\$
# [0-9]+\\$ represents digits followed by character $
# example matched by the regular expression [0-9]+\\$
cool <- c(rnorm(10, mean = 20, sd = 2))
cool_char <- as.character(cool)
cool_var <- paste(cool_char[c(2,4,6,8,10)],"$", sep="")
x <- c("$12345678912$34$", "234$", "6$8", "$0058","0058$")
cool_com <- c(cool_char[1:3],cool_var[1],c(cool_char[4:6],cool_var[2]),c(cool_char[7:9],cool_var[3]),c(cool_char[10:12],cool_var[4:5]),x)
cool_ext <- unlist(str_extract_all(cool_com, "[0-9]+\\$"))
# (b) \\b[a-z]{1,4}\\b
# \\b[a-z]{1,4}\\b represents word less than 4 lower case letters
# example matched by the regular expression \\b[a-z]{1,4}\\b
set.seed(1)
words1 <- stringi::stri_rand_strings(5, 3, pattern="[a-z]")
set.seed(2)
words2 <- stringi::stri_rand_strings(5, 3, pattern="[a-zA-Z0-9]")
set.seed(3)
words3 <- stringi::stri_rand_strings(5, 5,pattern="[a-z]")
set.seed(4)
words4 <- stringi::stri_rand_strings(5, 5,pattern="[a-zA-Z0-9]")
set.seed(5)
words5 <- stringi::stri_rand_strings(5, 7,pattern="[a-z]")
set.seed(6)
words6 <- stringi::stri_rand_strings(5, 7,pattern="[a-zA-Z0-9]")
word_com <- c(words1, words2, words3,words4, words5, words6)
words_lessthan4 <- grepl ("\\b[a-z]{1,4}\\b",word_com)
# (c) .*?\\.txt$
# (c) .*?\\.txt$ represents any characters followed by .txtat the end"
# example matched by the regular expression .*?\\.txt$
txt <-c("txt.notfun","do.txt", "some.txt", "fun.txt","exp.txt")
mosaic <- c(txt,word_com,txt)
txttest <- grepl (".*?\\.txt$",mosaic)
txttest_value <- unlist(str_extract_all(mosaic,".*?\\.txt$"))
# (d) \\d{2}/\\d{2}/\\d{4}
# \\d{2}/\\d{2}/\\d{4} represents 2 digits forward slash 2 digits forward slash 4 digits
# example matched by the regular expression \\d{2}/\\d{2}/\\d{4}
eg1 <- sample(10000000:10000100,10,replace=T)
eg2 <- sample(100000000:100000100,10,replace=T)
eg <- c(eg1,eg2)
a <- 3
b <- 6
eg3 <- paste(substr(eg, 1, a-1), "/", substr(eg, a, nchar(eg)), sep = "")
eg4 <- paste(substr(eg3, 1, b-1), "/", substr(eg3, b, nchar(eg3)), sep = "")
eg5 <- paste(substr(eg3, 1, a+1), "/", substr(eg3, a+2, nchar(eg)), sep = "")
eg_com <- c(eg4,eg5, "12/34/0","5678/34/12","12/34/567890")
patterntest <- grepl("\\d{2}/\\d{2}/\\d{4}", eg_5_com)
patterntest_value <- unlist(str_extract_all(eg_com,"\\d{2}/\\d{2}/\\d{4}"))
# (e) <(.+?)>.+?</\\1>
# <(.+?)>.+?</\\1> represents any characters between <> followed by any characters followed by < and one forward slash, then the pattern what ever comes in previous (.+?)in between < and > will be check the further match one more time
#
scramble <- c( "<1180abc>0</1180abc>","<01234lastone></\\1>","<24005yu45ABC>AND</\\1>","<A happy face> is </A happy face>")
test <- grepl ("<(.+?)>.+?</\\1>", scramble)
test_value <- unlist(str_extract_all(scramble,"<(.+?)>.+?</\\1>"))