Example of the differences from the regular expression matches

regex-examples.R

x <- c("apple", "banana", "orange", "pear", "grape")
p <- "[aeoiu][^(aeiou)]"

 regexpr(p, x) # integer vector
#> [1] 1 2 1 3 3
#> attr(,"match.length")
#> [1] 2 2 2 2 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
 regexec(p, x) # list of integer values
#> [[1]]
#> [1] 1
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[2]]
#> [1] 2
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[3]]
#> [1] 1
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[4]]
#> [1] 3
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[5]]
#> [1] 3
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
gregexpr(p, x) # list of integer vectors
#> [[1]]
#> [1] 1
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[2]]
#> [1] 2 4
#> attr(,"match.length")
#> [1] 2 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[3]]
#> [1] 1 3
#> attr(,"match.length")
#> [1] 2 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[4]]
#> [1] 3
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
#> 
#> [[5]]
#> [1] 3
#> attr(,"match.length")
#> [1] 2
#> attr(,"index.type")
#> [1] "chars"
#> attr(,"useBytes")
#> [1] TRUE
gregexec(p, x) # list of integer matrix/array
#> [[1]]
#>      [,1]
#> [1,]    1
#> attr(,"match.length")
#>      [,1]
#> [1,]    2
#> attr(,"useBytes")
#> [1] TRUE
#> attr(,"index.type")
#> [1] "chars"
#> 
#> [[2]]
#>      [,1] [,2]
#> [1,]    2    4
#> attr(,"match.length")
#>      [,1] [,2]
#> [1,]    2    2
#> attr(,"useBytes")
#> [1] TRUE
#> attr(,"index.type")
#> [1] "chars"
#> 
#> [[3]]
#>      [,1] [,2]
#> [1,]    1    3
#> attr(,"match.length")
#>      [,1] [,2]
#> [1,]    2    2
#> attr(,"useBytes")
#> [1] TRUE
#> attr(,"index.type")
#> [1] "chars"
#> 
#> [[4]]
#>      [,1]
#> [1,]    3
#> attr(,"match.length")
#>      [,1]
#> [1,]    2
#> attr(,"useBytes")
#> [1] TRUE
#> attr(,"index.type")
#> [1] "chars"
#> 
#> [[5]]
#>      [,1]
#> [1,]    3
#> attr(,"match.length")
#>      [,1]
#> [1,]    2
#> attr(,"useBytes")
#> [1] TRUE
#> attr(,"index.type")
#> [1] "chars"

regmatches(x,  regexpr(p, x)) # character vector
#> [1] "ap" "an" "or" "ar" "ap"
regmatches(x,  regexec(p, x)) # list of characters
#> [[1]]
#> [1] "ap"
#> 
#> [[2]]
#> [1] "an"
#> 
#> [[3]]
#> [1] "or"
#> 
#> [[4]]
#> [1] "ar"
#> 
#> [[5]]
#> [1] "ap"
regmatches(x, gregexpr(p, x)) # list of character vectors 
#> [[1]]
#> [1] "ap"
#> 
#> [[2]]
#> [1] "an" "an"
#> 
#> [[3]]
#> [1] "or" "an"
#> 
#> [[4]]
#> [1] "ar"
#> 
#> [[5]]
#> [1] "ap"
regmatches(x, gregexec(p, x)) # list of character matrix arrays
#> [[1]]
#>      [,1]
#> [1,] "ap"
#> 
#> [[2]]
#>      [,1] [,2]
#> [1,] "an" "an"
#> 
#> [[3]]
#>      [,1] [,2]
#> [1,] "or" "an"
#> 
#> [[4]]
#>      [,1]
#> [1,] "ar"
#> 
#> [[5]]
#>      [,1]
#> [1,] "ap"