R stringr: Basic 1

Library

library(stringr)
library(dplyr)

Data

x <- c("why", "video", "cross", "extra", "deal", "authority")

length,collapse,sub string

str_length(x)
str_c(x, collapse = ", ")
str_sub(x, 1, 2)

[aeiou] pattern

str_detect(x, "[aeiou]")
str_count(x, "[aeiou]")
str_subset(x, "[aeiou]")
str_extract(x, "[aeiou]")
str_replace(x, "[aeiou]", "?")

Whitespace

‘str_pad’

x <- c("abc", "defghi")
str_pad(x, 10) # default pads on left

str_pad(x, 10, "both")

str_pad(x, 4)

‘trunc’ & ‘str_pad’

x <- c("Short", "This is a long string")

x %>% 
  str_trunc(10) %>% 
  str_pad(10, "right")

‘trim’

x <- c("  a   ", "b   ",  "   c")
str_trim(x)
str_trim(x, "left")

wraping

jabberwocky <- str_c(
  "`Twas brillig, and the slithy toves ",
  "did gyre and gimble in the wabe: ",
  "All mimsy were the borogoves, ",
  "and the mome raths outgrabe. "
)
cat(str_wrap(jabberwocky, width = 40))
#> `Twas brillig, and the slithy toves did
#> gyre and gimble in the wabe: All mimsy
#> were the borogoves, and the mome raths
#> outgrabe.

Locale sensitive

x <- "I like horses."
str_to_upper(x)
str_to_title(x)
str_to_lower(x)

String ordering and sorting

x <- c("y", "i", "k")
str_order(x)
str_sort(x)

Pattern matching

strings <- c(
  "apple", 
  "219 733 8965", 
  "329-293-8753", 
  "Work: 579-499-7527; Home: 543.355.3679"
)
phone <- "([2-9][0-9]{2})[- .]([0-9]{3})[- .]([0-9]{4})"
str_detect(strings, phone)
str_subset(strings, phone)
str_count(strings, phone)
str_extract(strings, phone)
str_extract_all(strings, phone, simplify = TRUE)

replace value

str_replace(strings, phone, "XXX-XXX-XXXX")
str_replace_all(strings, phone, "XXX-XXX-XXXX")

Split

str_split("a-b-c", "-")

[[1]]
[1] "a" "b" "c"

str_split_fixed("a-b-c", "-", n = 2)

     [,1] [,2] 
[1,] "a"  "b-c"

x <- "This is a sentence."
str_split(x, "")

[[1]]
 [1] "T" "h" "i" "s" " " "i" "s" " " "a" " " "s" "e" "n" "t" "e" "n" "c" "e" "."

str_count(x, "")

[1] 19

Combining strings

str_c("x", "y")
str_c("x", "y", "z")
str_c("x", "y", sep = ", ")
x <- c("abc", NA)
str_c("|-", x, "-|")
str_c("|-", str_replace_na(x), "-|")
str_c("prefix-", c("a", "b", "c"), "-suffix")



name <- "Hadley"
time_of_day <- "morning"
birthday <- FALSE

str_c(
  "Good ", time_of_day, " ", name,
  if (birthday) " and HAPPY BIRTHDAY",
  "."
)

str_c(c("x", "y", "z"), collapse = ", ")

Basic matches

x <- c("apple", "banana", "pear")
str_view(x, "an")
str_view(x, ".a.") #., which matches any character
str_view(x, "^a")  # ^ to match the start of the string.
str_view(x, "a$")  $ to match the end of the string.

epression

matches any digit. : matches any whitespace (e.g. space, tab, newline). [abc]: matches a, b, or c. [^abc]: matches anything except a, b, or c.