AMR/R/like.R

127 lines
5.5 KiB
R
Raw Normal View History

# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Data Analysis for R #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
# #
# LICENCE #
2020-12-27 00:30:28 +01:00
# (c) 2018-2021 Berends MS, Luz CF et al. #
2020-10-08 11:16:03 +02:00
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
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. #
# 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. #
2020-10-08 11:16:03 +02:00
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR data analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
#' Pattern Matching with Keyboard Shortcut
#'
#' Convenient wrapper around [grepl()] 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.
#' @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.
2019-11-29 19:43:23 +01:00
#' @param ignore.case if `FALSE`, the pattern matching is *case sensitive* and if `TRUE`, case is ignored during matching.
#' @return A [`logical`] vector
#' @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)
2020-05-16 13:05:47 +02:00
#' * Supports multiple patterns
#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed
2021-02-21 20:15:09 +01:00
#' * Always uses compatibility with Perl
2020-04-14 14:12:31 +02:00
#'
2020-11-23 21:50:27 +01:00
#' Using RStudio? The text `%like%` can also be directly inserted in your code 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)
#' @seealso [grepl()]
#' @inheritSection AMR Read more on Our Website!
#' @examples
#' # simple test
#' a <- "This is a test"
#' b <- "TEST"
#' a %like% b
#' #> TRUE
#' b %like% a
#' #> FALSE
#'
#' # also supports multiple patterns
#' a <- c("Test case", "Something different", "Yet another thing")
2020-02-14 19:54:13 +01:00
#' b <- c( "case", "diff", "yet")
#' a %like% b
#' #> TRUE TRUE TRUE
#' a[1] %like% b
#' #> TRUE FALSE FALSE
#' a %like% b[1]
#' #> TRUE FALSE FALSE
#'
2020-05-16 13:05:47 +02:00
#' # get isolates whose name start with 'Ent' or 'ent'
#' \donttest{
#' if (require("dplyr")) {
#' example_isolates %>%
#' filter(mo_name(mo) %like% "^ent")
#' }
2020-05-16 21:40:50 +02:00
#' }
like <- function(x, pattern, ignore.case = TRUE) {
meet_criteria(x, allow_NA = TRUE)
2020-10-21 14:40:00 +02:00
meet_criteria(pattern, allow_NA = FALSE)
meet_criteria(ignore.case, allow_class = "logical", has_length = 1)
if (all(is.na(x))) {
return(rep(FALSE, length(x)))
}
2020-05-16 13:05:47 +02:00
# set to fixed if no regex found
2020-09-24 00:30:11 +02:00
fixed <- !any(is_possibly_regex(pattern))
2020-05-16 13:05:47 +02:00
if (ignore.case == TRUE) {
# set here, otherwise if fixed = TRUE, this warning will be thrown: argument `ignore.case = TRUE` will be ignored
2020-05-16 13:05:47 +02:00
x <- tolower(x)
pattern <- tolower(pattern)
}
if (is.factor(x)) {
x <- as.character(x)
}
2020-07-13 09:17:24 +02:00
if (length(pattern) == 1) {
2021-02-21 20:15:09 +01:00
grepl(pattern, x, ignore.case = FALSE, fixed = fixed, perl = !fixed)
} else {
if (length(x) == 1) {
x <- rep(x, length(pattern))
} else if (length(pattern) != length(x)) {
stop_("arguments `x` and `pattern` must be of same length, or either one must be 1")
}
unlist(
Map(f = grepl,
pattern,
x,
MoreArgs = list(ignore.case = FALSE, fixed = fixed, perl = !fixed)),
use.names = FALSE)
}
}
#' @rdname like
#' @export
"%like%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
2020-10-21 15:28:48 +02:00
meet_criteria(pattern, allow_NA = FALSE)
like(x, pattern, ignore.case = TRUE)
}
#' @rdname like
#' @export
"%like_case%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
2020-10-21 14:40:00 +02:00
meet_criteria(pattern, allow_NA = FALSE)
like(x, pattern, ignore.case = FALSE)
}