AMR/R/like.R

145 lines
6.1 KiB
R
Raw Normal View History

# ==================================================================== #
# TITLE #
2022-10-05 09:12:22 +02:00
# AMR: An R Package for Working with Antimicrobial Resistance Data #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
# #
2022-10-05 09:12:22 +02:00
# CITE AS #
# Berends MS, Luz CF, Friedrich AW, Sinha BNM, Albers CJ, Glasner C #
# (2022). AMR: An R Package for Working with Antimicrobial Resistance #
# Data. Journal of Statistical Software, 104(3), 1-31. #
# doi:10.18637/jss.v104.i03 #
# #
2020-10-08 11:16:03 +02:00
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
2022-08-28 10:31:50 +02:00
# 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/ #
# ==================================================================== #
2021-04-07 08:37:42 +02:00
#' Vectorised 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.
2021-05-12 18:15:03 +02:00
#' @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] vector containing regular expressions (or a [character] string for `fixed = TRUE`) to be matched in the given [character] vector. Coerced by [as.character()] to a [character] string if possible.
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.
2021-04-07 08:37:42 +02:00
#' @return A [logical] vector
#' @name like
#' @rdname like
#' @export
2020-05-16 13:05:47 +02:00
#' @details
#' These [like()] and `%like%`/`%unlike%` functions:
#' * Are case-insensitive (use `%like_case%`/`%unlike_case%` for case-sensitive matching)
#' * Support multiple patterns
#' * Check if `pattern` is a valid regular expression and sets `fixed = TRUE` if not, to greatly improve speed (vectorised over `pattern`)
#' * Always use compatibility with Perl unless `fixed = TRUE`, to greatly improve speed
2022-08-28 10:31:50 +02:00
#'
#' Using RStudio? The `%like%`/`%unlike%` functions can also be directly inserted in your code from the Addins menu and can have its own keyboard shortcut like `Shift+Ctrl+L` or `Shift+Cmd+L` (see menu `Tools` > `Modify Keyboard Shortcuts...`). If you keep pressing your shortcut, the inserted text will be iterated over `%like%` -> `%unlike%` -> `%like_case%` -> `%unlike_case%`.
2021-04-16 11:41:05 +02:00
#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R), although altered as explained in *Details*.
#' @seealso [grepl()]
2022-08-21 16:37:20 +02:00
#' @examples
#' a <- "This is a test"
#' b <- "TEST"
#' a %like% b
#' b %like% a
2022-08-28 10:31:50 +02:00
#'
#' # also supports multiple patterns
#' a <- c("Test case", "Something different", "Yet another thing")
2022-08-28 10:31:50 +02:00
#' b <- c("case", "diff", "yet")
#' a %like% b
#' a %unlike% b
2022-08-28 10:31:50 +02:00
#'
#' a[1] %like% b
#' a %like% b[1]
2022-08-28 10:31:50 +02:00
#'
#' \donttest{
2022-08-27 20:49:37 +02:00
#' # get isolates whose name start with 'Entero' (case-insensitive)
#' example_isolates[which(mo_name() %like% "^entero"), ]
2022-08-28 10:31:50 +02:00
#'
#' if (require("dplyr")) {
#' example_isolates %>%
2021-04-07 08:37:42 +02:00
#' filter(mo_name() %like% "^ent")
#' }
#' }
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)
2022-08-28 10:31:50 +02:00
if (all(is.na(x))) {
return(rep(FALSE, length(x)))
}
2021-04-16 11:41:05 +02:00
# set to fixed if no valid regex (vectorised)
fixed <- !is_valid_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)
}
2021-04-16 11:41:05 +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)) {
2022-08-28 10:31:50 +02:00
stop_(
"arguments `x` and `pattern` must be of same length, or either one must be 1 ",
"(`x` has length ", length(x), " and `pattern` has length ", length(pattern), ")"
)
}
unlist(
2022-10-05 09:12:22 +02:00
Map(
f = grepl,
2022-08-28 10:31:50 +02:00
x = x,
pattern = pattern,
fixed = fixed,
perl = !fixed,
MoreArgs = list(ignore.case = FALSE),
USE.NAMES = FALSE
)
2021-04-07 08:37:42 +02:00
)
}
}
#' @rdname like
#' @export
"%like%" <- function(x, pattern) {
like(x, pattern, ignore.case = TRUE)
}
#' @rdname like
#' @export
"%unlike%" <- function(x, pattern) {
!like(x, pattern, ignore.case = TRUE)
}
#' @rdname like
#' @export
"%like_case%" <- function(x, pattern) {
like(x, pattern, ignore.case = FALSE)
}
#' @rdname like
#' @export
"%unlike_case%" <- function(x, pattern) {
!like(x, pattern, ignore.case = FALSE)
}