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 #
2020-01-05 17:22:09 +01:00
# (c) 2018-2020 Berends MS, Luz CF et al. #
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. #
# #
2020-01-05 17:22:09 +01:00
# We created this package for both routine data analysis and academic #
# research and it 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
#'
2020-04-14 14:12:31 +02:00
#' Convenient wrapper around [grep()] to match a pattern: `x %like% pattern`. It always returns a [`logical`] vector and is always case-insensitive (use `x %like_case% pattern` for case-sensitive matching). Also, `pattern` can be as long as `x` to compare items of each index in both vectors, or they both can have the same length to iterate over all cases.
2020-01-05 17:22:09 +01:00
#' @inheritSection lifecycle Stable lifecycle
2019-11-29 19:43:23 +01:00
#' @param x a character vector where matches are sought, or an object which can be coerced by [as.character()] to a character vector.
#' @param pattern a character string containing a regular expression (or [`character`] string for `fixed = TRUE`) to be matched in the given character vector. Coerced by [as.character()] to a character string if possible. If a [`character`] vector of length 2 or more is supplied, the first element is used with a warning.
#' @param ignore.case if `FALSE`, the pattern matching is *case sensitive* and if `TRUE`, case is ignored during matching.
2019-11-28 22:32:17 +01:00
#' @return A [`logical`] vector
2018-07-04 17:20:03 +02:00
#' @name like
#' @rdname like
#' @export
2020-05-16 13:05:47 +02:00
#' @details
#' The `%like%` function:
#' * Is case insensitive (use `%like_case%` for case-sensitive matching)
#' * Supports multiple patterns
#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed
#' * Tries again with `perl = TRUE` if regex fails
2020-04-14 14:12:31 +02:00
#'
#' 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...`).
2020-05-16 13:05:47 +02:00
#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/master/R/like.R)
2019-11-28 22:32:17 +01:00
#' @seealso [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")
2020-02-14 19:54:13 +01:00
#' b <- c( "case", "diff", "yet")
2018-07-04 17:20:03 +02:00
#' a %like% b
#' #> TRUE TRUE TRUE
#'
2020-05-16 13:05:47 +02:00
#' # get isolates whose name start with 'Ent' or 'ent'
2020-05-16 21:40:50 +02:00
#' \dontrun{
2018-07-04 17:20:03 +02:00
#' library(dplyr)
2019-08-27 16:45:42 +02:00
#' example_isolates %>%
2020-05-16 13:05:47 +02:00
#' filter(mo_name(mo) %like% "^ent") %>%
#' freq(mo)
2020-05-16 21:40:50 +02:00
#' }
2019-09-15 22:57:30 +02:00
like <- function ( x , pattern , ignore.case = TRUE ) {
2020-05-16 13:05:47 +02:00
# set to fixed if no regex found
fixed <- all ( ! grepl ( " [$.^*?+}{|)(]" , pattern ) )
if ( ignore.case == TRUE ) {
# set here, otherwise if fixed = TRUE, this warning will be thrown: argument 'ignore.case = TRUE' will be ignored
x <- tolower ( x )
pattern <- tolower ( pattern )
}
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
2020-05-16 13:05:47 +02:00
res <- sapply ( pattern , function ( pttrn ) base :: grepl ( pttrn , x , ignore.case = FALSE , fixed = fixed ) )
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 ] ) ) {
2020-05-16 13:05:47 +02:00
res [i ] <- as.integer ( x [i ] ) %in% base :: grep ( pattern [i ] , levels ( x [i ] ) , ignore.case = FALSE , fixed = fixed )
2018-07-04 17:20:03 +02:00
} else {
2020-05-16 13:05:47 +02:00
res [i ] <- base :: grepl ( pattern [i ] , x [i ] , ignore.case = FALSE , fixed = fixed )
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 ) ) {
2020-05-16 13:05:47 +02:00
as.integer ( x ) %in% base :: grep ( pattern , levels ( x ) , ignore.case = FALSE , fixed = fixed )
2018-07-04 17:20:03 +02:00
} else {
2020-05-16 13:05:47 +02:00
tryCatch ( base :: grepl ( pattern , x , ignore.case = FALSE , fixed = fixed ) ,
2019-11-29 19:43:23 +01:00
error = function ( e ) ifelse ( grepl ( " Invalid regexp" , e $ message ) ,
2019-08-06 14:39:22 +02:00
# try with perl = TRUE:
2019-11-29 19:43:23 +01:00
return ( base :: grepl ( pattern = pattern , x = x ,
2020-05-16 13:05:47 +02:00
ignore.case = FALSE ,
fixed = fixed ,
perl = TRUE ) ) ,
2019-11-29 19:43:23 +01:00
# stop otherwise
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 )
}