Solving problems 3 and 4 from Chapter 8 of “Automated Data Collection in R”
library(stringr)
#Copy the introductory example
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,}"))
#3)a Rearrange as per first_name last_name standard
##I am aware this is not the most linear way to proceed. Create a new vector by replacing content before "," with content after ","
## Replace vector components by index
NameReverse <- str_c(str_trim(str_replace_all(unlist(str_extract_all(name, ",(.*)")),",", "" )), str_trim(str_replace_all(unlist(str_extract_all(name, "[[:upper:]]\\w+,")),",", "" )), sep= " ")
indexword<- grep(",", name)
indexword
## [1] 2 5
name[2]<-NameReverse[1]
name[5]<-NameReverse[2]
name
## [1] "Moe Szyslak" "C. Montgomery Burns" "Rev. Timothy Lovejoy"
## [4] "Ned Flanders" "Homer Simpson" "Dr. Julius Hibbert"
#3)b What strings contain a title (boolean and results)?
titlelog<- unlist(str_detect(name, "[[:alpha:]]{2,3}\\."))
titlelog
## [1] FALSE FALSE TRUE FALSE FALSE TRUE
titleresults<- grep("[[:alpha:]]{2,3}\\.", name, value=T)
titleresults
## [1] "Rev. Timothy Lovejoy" "Dr. Julius Hibbert"
#3)c What strings contain a second name?
##Looking for Initial followed by "."
secnamelog<-unlist(str_detect(name, "[[:upper:]]{1}\\."))
secnamelog
## [1] FALSE TRUE FALSE FALSE FALSE FALSE
secnameresults<- grep("[[:upper:]]{1}\\.", name, value=T)
secnameresults
## [1] "C. Montgomery Burns"
#4) Describe the types of strings that conform to the following regular expressions and construct an example that is matched by the regular expression.
first<- str_extract("1000$", "[0-9]+\\$")
##"$" is escaped, therefore it must be interpreted literally rather than as end of the word. A price tag can be a fitting example.
second<-str_extract("luca", "\\b[a-z]{1,4}\\b")
## String containing between 1 and 4 lower case characters
third<-str_extract("filename1 and 2.txt", ".*?\\.txt$")
##String ending in ".txt". As the preceeding item is optional, also a string reading just ".txt" will fit.
fourth<-str_extract("10/19/1981", "\\d{2}/\\d{2}/\\d{4}")
##Date format (2 digits/2 digits/4 digits)
fifth <-str_extract( "<whatever 543> whatever 123 </whatever 543>","<(.+?)>.+?</\\1>")
## The "<", ">" symbols are not preceeded by "\\", therefore they will be literally rendered. "\\1" at the end stands for repetition.