Extract and replace subsequences from a bstr sequences

Extract and replace subsequences from a bstr sequences

bstr_sub(bstrobj, start = 1L, end = -1L)

bstr_sub(bstrobj, start = 1L, end = -1L, omit_na = FALSE) <- value

bstr_sub_replace(..., replacement, value = replacement)

Arguments

bstrobj	bstr class object or character vector
start	start
end	end
omit_na	Single logical value. If `TRUE`, missing values in any of the arguments provided will result in an unchanged input.
value	replacement string
...	arguments to be passed to bstr_sub<-
replacement	alias of value [wherever applicable]

Examples

temp <- bstr_rand_seq(1, 10, seed = 1)
c(
  temp,
  bstr_sub(temp, 1, 5),
  bstr_sub(temp, 5),
  bstr_sub(temp, end = 5),
  bstr_sub(temp, 1:2, c(6,2))
)
#> class: bstr,character 
#> number of sequences: 6 
#> [1]      no name 1      : NTdvKuxigD                               10 
#> [2]      no name 1      : NTdvK                                     5 
#> [3]      no name 1      : KuxigD                                    6 
#> [4]      no name 1      : NTdvK                                     5 
#> [5]      no name 1      : NTdvKu                                    6 
#> [6]         <NA>        : T                                         1 

# Negative indices
c(
  temp,
  bstr_sub(temp, -1),
  bstr_sub(temp, -7),
  bstr_sub(temp, end = -7)
)
#> class: bstr,character 
#> number of sequences: 4 
#> [1]      no name 1      : NTdvKuxigD                               10 
#> [2]      no name 1      : D                                         1 
#> [3]      no name 1      : vKuxigD                                   7 
#> [4]      no name 1      : NTdv                                      4 

# Alternatively, you can pass in a two colum matrix, as in the
# output from stringr::str_locate_all
temp <- bstr("abcde fghij")
pos <- stringr::str_locate_all(temp, "[aefi]")[[1]]
bstr_sub(temp, pos)
#> class: bstr,character 
#> number of sequences: 4 
#> [1]      no name 1      : a                                        1 
#> [2]         <NA>        : e                                        1 
#> [3]         <NA>        : f                                        1 
#> [4]         <NA>        : i                                        1 
bstr_sub(temp, pos[, 1], pos[, 2])
#> class: bstr,character 
#> number of sequences: 4 
#> [1]      no name 1      : a                                        1 
#> [2]         <NA>        : e                                        1 
#> [3]         <NA>        : f                                        1 
#> [4]         <NA>        : i                                        1 

# Vectorisation
bstr_sub(temp, seq_len(bstr_length(temp)))
#> class: bstr,character 
#> number of sequences: 11 
#> [1]      no name 1      : abcde fghij                              11 
#> [2]         <NA>        : bcde fghij                               10 
#> [3]         <NA>        : cde fghij                                 9 
#> [4]         <NA>        : de fghij                                  8 
#> [5]         <NA>        : e fghij                                   7 
#> [6]         <NA>        :  fghij                                    6 
bstr_sub(temp, end = seq_len(bstr_length(temp)))
#> class: bstr,character 
#> number of sequences: 11 
#> [1]      no name 1      : a                                        1 
#> [2]         <NA>        : ab                                       2 
#> [3]         <NA>        : abc                                      3 
#> [4]         <NA>        : abcd                                     4 
#> [5]         <NA>        : abcde                                    5 
#> [6]         <NA>        : abcde                                    6 

# Replacement form
x <- "BBCDEF"
bstr_sub(x, 1, 1) <- "A"; x
#> class: bstr,character 
#> number of sequences: 1 
#> [1]      no name 1      : ABCDEF                                   6 
bstr_sub(x, -1, -1) <- "K"; x
#> class: bstr,character 
#> number of sequences: 1 
#> [1]      no name 1      : ABCDEK                                   6 
bstr_sub(x, -2, -2) <- "GHIJ"; x
#> class: bstr,character 
#> number of sequences: 1 
#> [1]      no name 1      : ABCDGHIJK                                9 
bstr_sub(x, 2, -2) <- ""; x
#> class: bstr,character 
#> number of sequences: 1 
#> [1]      no name 1      : AK                                       2 

# If you want to keep the original if some argument is NA,
# use omit_na = TRUE
x1 <- x2 <- x3 <- x4 <- bstr("AAA")
bstr_sub(x1, 1, NA) <- "B"
bstr_sub(x2, 1, 2) <- NA
bstr_sub(x3, 1, NA, omit_na = TRUE) <- "B"
bstr_sub(x4, 1, 2, omit_na = TRUE) <- NA
c(x1, x2, x3, x4)
#> class: bstr,character 
#> number of sequences: 4 
#> [1]      no name 1      : <NA>                                     NA 
#> [2]      no name 1      : <NA>                                     NA 
#> [3]      no name 1      : AAA                                      NA 
#> [4]      no name 1      : AAA                                      NA