Character strings

Install required packages

wants <- c("DescTools")
has   <- wants %in% rownames(installed.packages())
if(any(!has)) install.packages(wants[!has])

randVals <- round(rnorm(5), 2)
toString(randVals)

[1] "-1.04, -0.24, 0.22, 0.81, -1.08"

formatC(c(1, 2.345), width=5, format="f")

[1] "1.0000" "2.3450"

length("ABCDEF")

[1] 1

nchar("ABCDEF")

[1] 6

nchar(c("A", "BC", "DEF"))

[1] 1 2 3

paste("group", LETTERS[1:5], sep="_")

[1] "group_A" "group_B" "group_C" "group_D" "group_E"

paste(1:5, palette()[1:5], sep=": ")

[1] "1: black"  "2: red"    "3: green3" "4: blue"   "5: cyan"

paste(1:5, letters[1:5], sep=".", collapse=" ")

[1] "1.a 2.b 3.c 4.d 5.e"

Beware of the way NA and NULL are treated in paste().

paste(1, NA, 2, NULL, 3, character(0), sep="_")

[1] "1_NA_2__3_"

N     <- 20
gName <- "A"
mVal  <- 14.2
sprintf("For %d particpants in group %s, the mean was %f", N, gName, mVal)

[1] "For 20 particpants in group A, the mean was 14.200000"

sprintf("%.3f", 1.23456)

[1] "1.235"

cVar <- "A string"
cat(cVar, "with\n", 4, "\nwords\n", sep="+")

A string+with
+4+
words

print(cVar, quote=FALSE)

[1] A string

noquote(cVar)

[1] A string

tolower(c("A", "BC", "DEF"))

[1] "a"   "bc"  "def"

toupper(c("ghi", "jk", "i"))

[1] "GHI" "JK"  "I"

abbreviate("AfairlyLongString", minlength=6)

AfairlyLongString 
         "AfrlLS"

library(DescTools)
StrRev(c("Lorem", "ipsum", "dolor", "sit"))

[1] "meroL" "muspi" "rolod" "tis"

substring(c("ABCDEF", "GHIJK", "LMNO", "PQR"), first=4, last=5)

[1] "DE" "JK" "O"  ""

strsplit(c("abc_def_ghi", "jkl_mno"), split="_")

[[1]]
[1] "abc" "def" "ghi"

[[2]]
[1] "jkl" "mno"

strsplit("Xylophon", split=NULL)

[[1]]
[1] "X" "y" "l" "o" "p" "h" "o" "n"

match(c("abc", "de", "f", "h"), c("abcde", "abc", "de", "fg", "ih"))

[1]  2  3 NA NA

pmatch(c("abc", "de", "f", "h"), c("abcde", "abc", "de", "fg", "ih"))

[1]  2  3  4 NA

See ?regex

grep( "A[BC][[:blank:]]", c("AB ", "AB", "AC ", "A "))

[1] 1 3

grepl("A[BC][[:blank:]]", c("AB ", "AB", "AC ", "A "))

[1]  TRUE FALSE  TRUE FALSE

pat    <- "[[:upper:]]+"
txt    <- c("abcDEFG", "ABCdefg", "abcdefg")
(start <- regexpr(pat, txt))

[1]  4  1 -1
attr(,"match.length")
[1]  4  3 -1
attr(,"useBytes")
[1] TRUE

len <- attr(start, "match.length")
end <- start + len - 1
substring(txt, start, end)

[1] "DEFG" "ABC"  ""

glob2rx("asdf*.txt")

[1] "^asdf.*\\.txt$"

charVec <- c("ABCDEF", "GHIJK", "LMNO", "PQR")
substring(charVec, 4, 5) <- c("..", "xx", "++", "**"); charVec

[1] "ABC..F" "GHIxx"  "LMN+"   "PQR"

sub("em", "XX", "Lorem ipsum dolor sit Lorem ipsum")

[1] "LorXX ipsum dolor sit Lorem ipsum"

gsub("em", "XX", "Lorem ipsum dolor sit Lorem ipsum")

[1] "LorXX ipsum dolor sit LorXX ipsum"

gsub("^[[:alpha:]]+-([[:digit:]]+)-[[:alpha:]]+$", "\\1", "abc-412-def")

[1] "412"

obj1 <- parse(text="3 + 4")
obj2 <- parse(text=c("vec <- c(1, 2, 3)", "vec^2"))
eval(obj1)

[1] 7

eval(obj2)

[1] 1 4 9

Package stringr provides more functions for efficiently and consistently handling character strings.

try(detach(package:DescTools))