2018-07-04 17:20:03 +02:00
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
# https://gitlab.com/msberends/AMR #
2018-07-04 17:20:03 +02:00
# #
# LICENCE #
2019-01-02 23:24:07 +01:00
# (c) 2019 Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
2018-07-04 17:20:03 +02:00
# #
2019-01-02 23:24:07 +01:00
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# #
# This R package was created for academic research and was publicly #
# released in the hope that it will be useful, but it comes WITHOUT #
# ANY WARRANTY OR LIABILITY. #
2019-04-05 18:47:39 +02:00
# Visit our website for more info: https://msberends.gitlab.io/AMR. #
2018-07-04 17:20:03 +02:00
# ==================================================================== #
#' Pattern Matching
#'
2019-09-15 22:57:30 +02:00
#' Convenient wrapper around \code{\link[base]{grep}} to match a pattern: \code{a \%like\% b}. It always returns a \code{logical} vector and is always case-insensitive (use \code{a \%like_case\% b} for case-sensitive matching). Also, \code{pattern} (\code{b}) can be as long as \code{x} (\code{a}) to compare items of each index in both vectors, or can both have the same length to iterate over all cases.
2018-07-04 17:20:03 +02:00
#' @inheritParams base::grepl
#' @return A \code{logical} vector
#' @name like
#' @rdname like
#' @export
#' @details Using RStudio? This function can also be inserted from the Addins menu and can have its own Keyboard Shortcut like Ctrl+Shift+L or Cmd+Shift+L (see Tools > Modify Keyboard Shortcuts...).
2019-08-11 19:07:26 +02:00
#' @source Idea from the \href{https://github.com/Rdatatable/data.table/blob/master/R/like.R}{\code{like} function from the \code{data.table} package}, but made it case insensitive at default and let it support multiple patterns. Also, if the regex fails the first time, it tries again with \code{perl = TRUE}.
2018-07-04 17:20:03 +02:00
#' @seealso \code{\link[base]{grep}}
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2018-07-04 17:20:03 +02:00
#' @examples
#' # simple test
#' a <- "This is a test"
#' b <- "TEST"
#' a %like% b
#' #> TRUE
#' b %like% a
#' #> FALSE
#'
#' # also supports multiple patterns, length must be equal to x
#' a <- c("Test case", "Something different", "Yet another thing")
#' b <- c("case", "diff", "yet")
#' a %like% b
#' #> TRUE TRUE TRUE
#'
#' # get frequencies of bacteria whose name start with 'Ent' or 'ent'
#' library(dplyr)
2019-08-27 16:45:42 +02:00
#' example_isolates %>%
2019-11-06 14:43:23 +01:00
#' filter(mo_genus(mo) %like% '^ent') %>%
#' freq(mo_fullname(mo))
2019-09-15 22:57:30 +02:00
like <- function ( x , pattern , ignore.case = TRUE ) {
2018-07-04 17:20:03 +02:00
if ( length ( pattern ) > 1 ) {
if ( length ( x ) != length ( pattern ) ) {
2019-09-12 15:08:53 +02:00
if ( length ( x ) == 1 ) {
x <- rep ( x , length ( pattern ) )
}
# return TRUE for every 'x' that matches any 'pattern', FALSE otherwise
2019-09-15 22:57:30 +02:00
res <- sapply ( pattern , function ( pttrn ) base :: grepl ( pttrn , x , ignore.case = ignore.case ) )
2019-09-12 15:08:53 +02:00
res2 <- as.logical ( rowSums ( res ) )
# get only first item of every hit in pattern
res2 [duplicated ( res ) ] <- FALSE
res2 [rowSums ( res ) == 0 ] <- NA
return ( res2 )
2018-07-04 17:20:03 +02:00
} else {
# x and pattern are of same length, so items with each other
res <- vector ( length = length ( pattern ) )
2019-10-11 17:21:02 +02:00
for ( i in seq_len ( length ( res ) ) ) {
2018-07-04 17:20:03 +02:00
if ( is.factor ( x [i ] ) ) {
2019-09-15 22:57:30 +02:00
res [i ] <- as.integer ( x [i ] ) %in% base :: grep ( pattern [i ] , levels ( x [i ] ) , ignore.case = ignore.case )
2018-07-04 17:20:03 +02:00
} else {
2019-09-15 22:57:30 +02:00
res [i ] <- base :: grepl ( pattern [i ] , x [i ] , ignore.case = ignore.case )
2018-07-04 17:20:03 +02:00
}
}
return ( res )
}
}
# the regular way how grepl works; just one pattern against one or more x
if ( is.factor ( x ) ) {
2019-09-15 22:57:30 +02:00
as.integer ( x ) %in% base :: grep ( pattern , levels ( x ) , ignore.case = ignore.case )
2018-07-04 17:20:03 +02:00
} else {
2019-09-15 22:57:30 +02:00
tryCatch ( base :: grepl ( pattern , x , ignore.case = ignore.case ) ,
2019-08-06 14:39:22 +02:00
error = function ( e ) ifelse ( test = grepl ( " Invalid regexp" , e $ message ) ,
# try with perl = TRUE:
2019-09-15 22:57:30 +02:00
yes = return ( base :: grepl ( pattern , x , ignore.case = ignore.case , perl = TRUE ) ) ,
2019-08-06 14:39:22 +02:00
no = stop ( e $ message ) ) )
2018-07-04 17:20:03 +02:00
}
}
#' @rdname like
#' @export
2019-09-15 22:57:30 +02:00
" %like%" <- function ( x , pattern ) {
like ( x , pattern , ignore.case = TRUE )
}
#' @rdname like
#' @export
" %like_case%" <- function ( x , pattern ) {
like ( x , pattern , ignore.case = FALSE )
}