AMR/R/translate.R

148 lines
6.3 KiB
R
Raw Normal View History

2018-11-05 13:20:32 +01:00
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
2018-11-05 13:20:32 +01:00
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
2018-11-05 13:20:32 +01:00
# #
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. #
# #
# 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. #
2020-07-08 14:48:06 +02:00
# Visit our website for more info: https://msberends.github.io/AMR. #
2018-11-05 13:20:32 +01:00
# ==================================================================== #
2019-05-10 16:44:59 +02:00
#' Translate strings from AMR package
2018-11-05 13:20:32 +01:00
#'
2020-05-16 13:05:47 +02:00
#' For language-dependent output of AMR functions, like [mo_name()], [mo_gramstain()], [mo_type()] and [ab_name()].
#' @inheritSection lifecycle Stable lifecycle
2020-07-08 14:48:06 +02:00
#' @details Strings will be translated to foreign languages if they are defined in a local translation file. Additions to this file can be suggested at our repository. The file can be found here: <https://github.com/msberends/AMR/blob/master/data-raw/translations.tsv>.
2019-05-10 16:44:59 +02:00
#'
2020-07-08 14:48:06 +02:00
#' Currently supported languages are (besides English): `r paste(sort(gsub(";.*", "", ISOcodes::ISO_639_2[which(ISOcodes::ISO_639_2$Alpha_2 %in% unique(AMR:::translations_file$lang)), "Name"])), collapse = ", ")`. Please note that currently not all these languages have translations available for all antimicrobial agents and colloquial microorganism names.
#'
2020-07-08 14:48:06 +02:00
#' Please suggest your own translations [by creating a new issue on our repository](https://github.com/msberends/AMR/issues/new?title=Translations).
2019-05-10 16:44:59 +02:00
#'
2020-05-16 13:05:47 +02:00
#' This file will be read by all functions where a translated output can be desired, like all [mo_property()] functions ([mo_name()], [mo_gramstain()], [mo_type()], etc.).
2019-05-10 16:44:59 +02:00
#'
#' The system language will be used at default, if that language is supported. The system language can be overwritten with `Sys.setenv(AMR_locale = yourlanguage)`.
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2019-05-10 16:44:59 +02:00
#' @rdname translate
#' @name translate
2018-11-05 13:20:32 +01:00
#' @export
2019-05-10 16:44:59 +02:00
#' @examples
#' # The 'language' parameter of below functions
#' # will be set automatically to your system language
#' # with get_locale()
#'
#' # English
#' mo_name("CoNS", language = "en")
2019-05-10 16:44:59 +02:00
#' #> "Coagulase-negative Staphylococcus (CoNS)"
#'
#' # German
#' mo_name("CoNS", language = "de")
2019-05-10 16:44:59 +02:00
#' #> "Koagulase-negative Staphylococcus (KNS)"
#'
#' # Dutch
#' mo_name("CoNS", language = "nl")
2019-05-10 16:44:59 +02:00
#' #> "Coagulase-negatieve Staphylococcus (CNS)"
#'
#' # Spanish
#' mo_name("CoNS", language = "es")
2019-05-10 16:44:59 +02:00
#' #> "Staphylococcus coagulasa negativo (SCN)"
#'
#' # Italian
#' mo_name("CoNS", language = "it")
2019-05-10 16:44:59 +02:00
#' #> "Staphylococcus negativo coagulasi (CoNS)"
#'
#' # Portuguese
#' mo_name("CoNS", language = "pt")
2019-05-10 16:44:59 +02:00
#' #> "Staphylococcus coagulase negativo (CoNS)"
2018-11-05 13:20:32 +01:00
get_locale <- function() {
if (!is.null(getOption("AMR_locale", default = NULL))) {
2019-05-10 16:44:59 +02:00
return(getOption("AMR_locale"))
2018-11-05 13:20:32 +01:00
}
2020-05-16 13:05:47 +02:00
2018-11-05 13:20:32 +01:00
lang <- Sys.getlocale("LC_COLLATE")
# Check the locale settings for a start with one of these languages:
# grepl() with ignore.case = FALSE is faster than %like%
2018-11-12 15:07:43 +01:00
if (grepl("^(English|en_|EN_)", lang, ignore.case = FALSE)) {
# as first option to optimise speed
2018-11-05 13:20:32 +01:00
"en"
2018-11-12 15:07:43 +01:00
} else if (grepl("^(German|Deutsch|de_|DE_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"de"
2018-11-12 15:07:43 +01:00
} else if (grepl("^(Dutch|Nederlands|nl_|NL_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"nl"
2020-05-16 13:05:47 +02:00
} else if (grepl("^(Spanish|Espa.+ol|es_|ES_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"es"
2018-11-12 15:07:43 +01:00
} else if (grepl("^(Italian|Italiano|it_|IT_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"it"
2020-05-16 13:05:47 +02:00
} else if (grepl("^(French|Fran.+ais|fr_|FR_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"fr"
2020-05-16 13:05:47 +02:00
} else if (grepl("^(Portuguese|Portugu.+s|pt_|PT_)", lang, ignore.case = FALSE)) {
2018-11-05 13:20:32 +01:00
"pt"
2018-11-12 15:07:43 +01:00
} else {
2018-11-15 12:42:35 +01:00
# other language -> set to English
2018-11-12 15:07:43 +01:00
"en"
2018-11-05 13:20:32 +01:00
}
}
# translate strings based on inst/translations.tsv
translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE) {
2020-05-16 13:05:47 +02:00
if (is.null(language)) {
return(from)
}
if (language %in% c("en", "", NA)) {
return(from)
}
df_trans <- translations_file # internal data file
stop_ifnot(language %in% df_trans$lang,
"unsupported language: '", language, "' - use one of: ",
paste0("'", sort(unique(df_trans$lang)), "'", collapse = ", "),
call = FALSE)
2020-07-08 14:48:06 +02:00
df_trans <- subset(df_trans, lang == language)
if (only_unknown == TRUE) {
2020-07-08 14:48:06 +02:00
df_trans <- subset(df_trans, pattern %like% "unknown")
}
# default case sensitive if value if 'ignore.case' is missing:
df_trans$ignore.case[is.na(df_trans$ignore.case)] <- FALSE
# default not using regular expressions (fixed = TRUE) if 'fixed' is missing:
df_trans$fixed[is.na(df_trans$fixed)] <- TRUE
# check if text to look for is in one of the patterns
any_form_in_patterns <- tryCatch(any(from %like% paste0("(", paste(df_trans$pattern, collapse = "|"), ")")),
error = function(e) {
warning("Translation not possible. Please open an issue on GitHub (https://github.com/msberends/AMR/issues).", call. = FALSE)
return(FALSE)
})
if (NROW(df_trans) == 0 | !any_form_in_patterns) {
return(from)
}
2019-10-11 17:21:02 +02:00
for (i in seq_len(nrow(df_trans))) {
from <- gsub(x = from,
pattern = df_trans$pattern[i],
replacement = df_trans$replacement[i],
fixed = df_trans$fixed[i],
ignore.case = df_trans$ignore.case[i])
}
# force UTF-8 for diacritics
base::enc2utf8(from)
}