Basic operations on character strings

length() versus nchar() 

some_great_rock_bands <- c("Led Zeppelin","Pink Floyd","Queen")

length(some_great_rock_bands)

[1] 3

nchar(some_great_rock_bands)

[1] 12 10  5

Character vector subsets versus substrings 

some_great_rock_bands <- c("Led Zeppelin","Pink Floyd","Queen")

some_great_rock_bands[1:2]

[1] "Led Zeppelin" "Pink Floyd"  

substr(some_great_rock_bands,start=1,stop=2)

[1] "Le" "Pi" "Qu"

substr(some_great_rock_bands,start=6,stop=15)

[1] "eppelin" "Floyd"   ""

Finding patterns within character strings and character vectors 

some_great_rock_bands <- c("Led Zeppelin","Pink Floyd","Queen")

grep("Zeppelin",some_great_rock_bands) # Just the indices

[1] 1

grep("Zeppelin",some_great_rock_bands, value=TRUE) # the elements

[1] "Led Zeppelin"

grepl("Zeppelin",some_great_rock_bands)

[1]  TRUE FALSE FALSE

grep("[ei]n$",some_great_rock_bands,value=TRUE)

[1] "Led Zeppelin" "Queen"

Replacing patterns within character strings and character vectors 

some_great_rock_bands <- c("Led Zeppelin","Pink Floyd","Queen")

sub("e","i",some_great_rock_bands)

[1] "Lid Zeppelin" "Pink Floyd"   "Quien"       

gsub("e","i",some_great_rock_bands)

[1] "Lid Zippilin" "Pink Floyd"   "Quiin"       

gsub("([aeiouy]+)","[\\1]",some_great_rock_bands)

[1] "L[e]d Z[e]pp[e]l[i]n" "P[i]nk Fl[oy]d"       "Q[uee]n"