Extract part of string before the first semicolon

The stringi package works very fast here:

stri_extract_first_regex(Type, "^[^;]+")
## [1] "SNSR_RMIN_PSX150Y_CSH"

I benchmarked on the 3 main approaches here:

Unit: milliseconds
      expr       min        lq      mean   median        uq      max neval
  SAPPLY() 254.88442 267.79469 294.12715 277.4518 325.91576 419.6435   100
     SUB() 182.64996 186.26583 192.99277 188.6128 197.17154 237.9886   100
 STRINGI()  89.45826  91.05954  94.11195  91.9424  94.58421 124.4689   100

enter image description here Here's the code for the Benchmarks:

library(stringi)
SAPPLY <- function() sapply(strsplit(Type, ";"), "[[", 1)
SUB <- function() sub(';.*$','', Type)
STRINGI <- function() stri_extract_first_regex(Type, "^[^;]+")

Type <- c("SNSR_RMIN_PSX150Y_CSH;SP_12;I0.00V50HX0HY3000")
Type <- rep(Type, 100000)

library(microbenchmark)
microbenchmark( 
    SAPPLY(),
    SUB(),
    STRINGI(),
times=100L)

You could try sub

sub(';.*$','', Type)
#[1] "SNSR_RMIN_PSX150Y_CSH"

It will match the pattern i.e. first occurence of ; to the end of the string and replace with ''

Or use

library(stringi)
stri_extract(Type, regex='[^;]*')
#[1] "SNSR_RMIN_PSX150Y_CSH"

you can also use strsplit

strsplit(Type, ";")[[1]][1]
[1] "SNSR_RMIN_PSX150Y_CSH"

When performance is important you can use substr in combination with regexpr from base.

substr(Type, 1, regexpr(";", Type, fixed=TRUE)-1)
#[1] "SNSR_RMIN_PSX150Y_CSH"

Timings: (Reusing the part from @tyler-rinker)

library(stringi)
SAPPLY <- function() sapply(strsplit(Type, ";"), "[[", 1)
SUB <- function() sub(';.*$','', Type)
SUB2 <- function() sub(';.*','', Type)
SUB3 <- function() sub('([^;]*).*','\\1', Type)
STRINGI <- function() stri_extract_first_regex(Type, "^[^;]+")
STRINGI2 <- function() stri_extract_first_regex(Type, "[^;]*")
SUBSTRREG <- function() substr(Type, 1, regexpr(";", Type)-1)
SUBSTRREG2 <- function() substr(Type, 1, regexpr(";", Type, fixed=TRUE)-1)
SUBSTRREG3 <- function() substr(Type, 1, regexpr(";", Type, fixed=TRUE, useBytes = TRUE)-1)

Type <- c("SNSR_RMIN_PSX150Y_CSH;SP_12;I0.00V50HX0HY3000")
Type <- rep(Type, 100000)

library(microbenchmark)
microbenchmark(SAPPLY(), SUB(), SUB2(), SUB3(), STRINGI()
 , STRINGI2(), SUBSTRREG(), SUBSTRREG2(), SUBSTRREG3())
#Unit: milliseconds
#         expr       min        lq      mean    median        uq       max neval
#     SAPPLY() 382.23750 395.92841 412.82508 410.05236 427.58816 460.28508   100
#        SUB() 111.92120 114.28939 116.41950 115.57371 118.15573 123.92400   100
#       SUB2()  94.27831  96.50462  98.14741  97.38199  99.15260 119.51090   100
#       SUB3() 167.77139 172.51271 175.07144 173.83121 176.27710 190.97815   100
#    STRINGI()  38.27645  39.33428  39.94134  39.71842  40.50182  42.55838   100
#   STRINGI2()  38.16736  39.19250  40.14904  39.63929  40.37686  56.03174   100
#  SUBSTRREG()  45.04828  46.39867  47.13018  46.85465  47.71985  51.07955   100
# SUBSTRREG2()  10.67439  11.02963  11.29290  11.12222  11.43964  13.64643   100
# SUBSTRREG3()  10.74220  10.95139  11.39466  11.06632  11.46908  27.72654   100

Tags:

String

R

Gsub