P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-11 12:22:01 +02:00
Code Releases Activity

styled, unit test fix

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2022-08-28 10:31:50 +02:00
parent 4cb1db4554
commit 4d050aef7c
147 changed files with 10897 additions and 8169 deletions
Download Patch File Download Diff File Expand all files Collapse all files

127
R/italicise_taxonomy.R
View File

@ -9,7 +9,7 @@
# (c) 2018-2022 Berends MS, Luz CF et al. #
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
@ -24,21 +24,21 @@
# ==================================================================== #
#' Italicise Taxonomic Families, Genera, Species, Subspecies
#'
#'
#' According to the binomial nomenclature, the lowest four taxonomic levels (family, genus, species, subspecies) should be printed in italics. This function finds taxonomic names within strings and makes them italic.
#' @param string a [character] (vector)
#' @param type type of conversion of the taxonomic names, either "markdown" or "ansi", see *Details*
#' @details
#' @details
#' This function finds the taxonomic names and makes them italic based on the [microorganisms] data set.
#'
#'
#' The taxonomic names can be italicised using markdown (the default) by adding `*` before and after the taxonomic names, or using ANSI colours by adding `\033[3m` before and `\033[23m` after the taxonomic names. If multiple ANSI colours are not available, no conversion will occur.
#'
#'
#' This function also supports abbreviation of the genus if it is followed by a species, such as "E. coli" and "K. pneumoniae ozaenae".
#' @export
#' @examples
#' italicise_taxonomy("An overview of Staphylococcus aureus isolates")
#' italicise_taxonomy("An overview of S. aureus isolates")
#'
#'
#' cat(italicise_taxonomy("An overview of S. aureus isolates", type = "ansi"))
italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
if (missing(type)) {
@ -46,7 +46,7 @@ italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
}
meet_criteria(string, allow_class = "character")
meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("markdown", "ansi"))
if (type == "markdown") {
before <- "*"
after <- "*"
@ -57,57 +57,70 @@ italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
before <- "\033[3m"
after <- "\033[23m"
}
vapply(FUN.VALUE = character(1),
string,
function(s) {
s_split <- unlist(strsplit(s, " "))
search_strings <- gsub("[^a-zA-Z-]", "", s_split)
ind_species <- search_strings != "" &
search_strings %in% MO_lookup[which(MO_lookup$rank %in% c("family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp.")),
"species",
drop = TRUE]
ind_fullname <- search_strings != "" &
search_strings %in% c(MO_lookup[which(MO_lookup$rank %in% c("family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp.")),
"fullname",
drop = TRUE],
MO_lookup[which(MO_lookup$rank %in% c("family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp.")),
"subspecies",
drop = TRUE])
# also support E. coli, add "E." to indices
has_previous_genera_abbr <- s_split[which(ind_species) - 1] %like_case% "^[A-Z][.]?$"
ind_species <- c(which(ind_species), which(ind_species)[has_previous_genera_abbr] - 1)
ind <- c(ind_species, which(ind_fullname))
s_split[ind] <- paste0(before, s_split[ind], after)
s_paste <- paste(s_split, collapse = " ")
# clean up a bit
s_paste <- gsub(paste0(after, " ", before), " ", s_paste, fixed = TRUE)
s_paste
},
USE.NAMES = FALSE)
vapply(
FUN.VALUE = character(1),
string,
function(s) {
s_split <- unlist(strsplit(s, " "))
search_strings <- gsub("[^a-zA-Z-]", "", s_split)
ind_species <- search_strings != "" &
search_strings %in% MO_lookup[which(MO_lookup$rank %in% c(
"family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp."
)),
"species",
drop = TRUE
]
ind_fullname <- search_strings != "" &
search_strings %in% c(
MO_lookup[which(MO_lookup$rank %in% c(
"family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp."
)),
"fullname",
drop = TRUE
],
MO_lookup[which(MO_lookup$rank %in% c(
"family",
"genus",
"species",
"subspecies",
"infraspecies",
"subsp."
)),
"subspecies",
drop = TRUE
]
)
# also support E. coli, add "E." to indices
has_previous_genera_abbr <- s_split[which(ind_species) - 1] %like_case% "^[A-Z][.]?$"
ind_species <- c(which(ind_species), which(ind_species)[has_previous_genera_abbr] - 1)
ind <- c(ind_species, which(ind_fullname))
s_split[ind] <- paste0(before, s_split[ind], after)
s_paste <- paste(s_split, collapse = " ")
# clean up a bit
s_paste <- gsub(paste0(after, " ", before), " ", s_paste, fixed = TRUE)
s_paste
},
USE.NAMES = FALSE
)
}
#' @rdname italicise_taxonomy