fixes

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 1.8.1.9051
-Date: 2022-09-17
+Version: 1.8.1.9052
+Date: 2022-09-18
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)
     data analysis and to work with microbial and antimicrobial properties by

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 1.8.1.9051
+# AMR 1.8.1.9052
 
 This version will eventually become v2.0! We're happy to reach a new major milestone soon!
 

R/aa_helper_functions.R

@@ -1489,4 +1489,8 @@ if (getRversion() < "4.0.0") {
   }
 }
 
+# for tinytest unit tests, that call AMR:::xxx():
+strrep <- strrep
+
+
 # nolint end

R/aa_helper_pm_functions.R

@@ -601,7 +601,7 @@ pm_near <- function(x, y, tol = .Machine$double.eps^0.5) {
 pm_pull <- function(.data, var = -1) {
   var_deparse <- pm_deparse_var(var)
   col_names <- colnames(.data)
-  if (!(var_deparse %in% col_names) && grepl("^[[:digit:]]+L|[[:digit:]]", var_deparse)) {
+  if (!(var_deparse %in% col_names) & grepl("^[[:digit:]]+L|[[:digit:]]", var_deparse)) {
     var <- as.integer(gsub("L", "", var_deparse))
     var <- pm_if_else(var < 1L, rev(col_names)[abs(var)], col_names[var])
   } else if (var_deparse %in% col_names) {

R/mo.R

@@ -35,6 +35,7 @@
 #' This excludes enterococci at default (who are in group D), use `Lancefield = "all"` to also categorise all enterococci as group D.
 #' @param minimum_matching_score a numeric value to set as the lower limit for the [MO matching score][mo_matching_score()]. When left blank, this will be determined automatically based on the character length of `x`, its [taxonomic kingdom][microorganisms] and [human pathogenicity][mo_matching_score()].
 #' @param allow_uncertain a number between `0` (or `"none"`) and `3` (or `"all"`), or `TRUE` (= `2`) or `FALSE` (= `0`) to indicate whether the input should be checked for less probable results, see *Details*
+#' @param keep_synonyms a [logical] to indicate if old, previously valid taxonomic names must be preserved and not be corrected to currently accepted names. The default is `FALSE` to always return the currently accepted names.
 #' @param reference_df a [data.frame] to be used for extra reference when translating `x` to a valid [`mo`]. See [set_mo_source()] and [get_mo_source()] to automate the usage of your own codes (e.g. used in your analysis or organisation).
 #' @param ignore_pattern a regular expression (case-insensitive) of which all matches in `x` must return `NA`. This can be convenient to exclude known non-relevant input and can also be set with the option `AMR_ignore_pattern`, e.g. `options(AMR_ignore_pattern = "(not reported|contaminated flora)")`.
 #' @param language language to translate text like "no growth", which defaults to the system language (see [get_AMR_locale()])

man/as.mo.Rd

@@ -49,6 +49,8 @@ This excludes enterococci at default (who are in group D), use \code{Lancefield
 
 \item{allow_uncertain}{a number between \code{0} (or \code{"none"}) and \code{3} (or \code{"all"}), or \code{TRUE} (= \code{2}) or \code{FALSE} (= \code{0}) to indicate whether the input should be checked for less probable results, see \emph{Details}}
 
+\item{keep_synonyms}{a \link{logical} to indicate if old, previously valid taxonomic names must be preserved and not be corrected to currently accepted names. The default is \code{FALSE} to always return the currently accepted names.}
+
 \item{reference_df}{a \link{data.frame} to be used for extra reference when translating \code{x} to a valid \code{\link{mo}}. See \code{\link[=set_mo_source]{set_mo_source()}} and \code{\link[=get_mo_source]{get_mo_source()}} to automate the usage of your own codes (e.g. used in your analysis or organisation).}
 
 \item{ignore_pattern}{a regular expression (case-insensitive) of which all matches in \code{x} must return \code{NA}. This can be convenient to exclude known non-relevant input and can also be set with the option \code{AMR_ignore_pattern}, e.g. \code{options(AMR_ignore_pattern = "(not reported|contaminated flora)")}.}

man/microorganisms.Rd

@@ -9,7 +9,7 @@ A \link[tibble:tibble]{tibble} with 63,472 observations and 22 variables:
 \itemize{
 \item \code{mo}\cr ID of microorganism as used by this package
 \item \code{fullname}\cr Full name, like \code{"Escherichia coli"}. For the taxonomic ranks genus, species and subspecies, this is the 'pasted' text of genus, species, and subspecies. For all taxonomic ranks higher than genus, this is the name of the taxon.
-\item \code{status} \cr Status of the taxon, either "accepted", "synomym" or "synonym"
+\item \code{status} \cr Status of the taxon, either "accepted" or "synonym"
 \item \code{kingdom}, \code{phylum}, \code{class}, \code{order}, \code{family}, \code{genus}, \code{species}, \code{subspecies}\cr Taxonomic rank of the microorganism
 \item \code{rank}\cr Text of the taxonomic rank of the microorganism, such as \code{"species"} or \code{"genus"}
 \item \code{ref}\cr Author(s) and year of related scientific publication. This contains only the \emph{first surname} and year of the \emph{latest} authors, e.g. "Wallis \emph{et al.} 2006 \emph{emend.} Smith and Jones 2018" becomes "Smith \emph{et al.}, 2018". This field is directly retrieved from the source specified in the column \code{source}. Moreover, accents were removed to comply with CRAN that only allows ASCII characters, e.g. "Váňová" becomes "Vanova".