(v1.6.0.9003) like() fix

.github/workflows/check.yaml

@@ -65,10 +65,10 @@ jobs:
           - {os: ubuntu-20.04,   r: '3.6',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           - {os: ubuntu-20.04,   r: '3.5',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           - {os: ubuntu-20.04,   r: '3.4',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
-          - {os: ubuntu-20.04,   r: '3.3',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
+          - {os: ubuntu-20.04,   r: '3.3',     allowfail: false  rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           # - {os: ubuntu-20.04,   r: '3.2',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           # - {os: ubuntu-20.04,   r: '3.1',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
-          - {os: ubuntu-20.04,   r: '3.0',     allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
+          - {os: ubuntu-20.04,   r: '3.0',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           
           - {os: ubuntu-16.04,   r: 'devel',   allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           - {os: ubuntu-16.04,   r: 'release', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
@@ -77,10 +77,10 @@ jobs:
           - {os: ubuntu-16.04,   r: '3.6',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           - {os: ubuntu-16.04,   r: '3.5',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           - {os: ubuntu-16.04,   r: '3.4',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.3',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: '3.3',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           # - {os: ubuntu-16.04,   r: '3.2',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           # - {os: ubuntu-16.04,   r: '3.1',     allowfail: true,  rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
-          - {os: ubuntu-16.04,   r: '3.0',     allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
+          - {os: ubuntu-16.04,   r: '3.0',     allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
           
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 1.6.0.9002
+Version: 1.6.0.9003
-Date: 2021-04-12
+Date: 2021-04-16
 Title: Antimicrobial Resistance Data Analysis
 Authors@R: c(
     person(role = c("aut", "cre"), 

NEWS.md

@@ -1,5 +1,5 @@
-# AMR 1.6.0.9002
+# AMR 1.6.0.9003
-## <small>Last updated: 12 April 2021</small>
+## <small>Last updated: 16 April 2021</small>
 
 ### New
 * Function `custom_eucast_rules()` that brings support for custom AMR rules in `eucast_rules()`
@@ -13,6 +13,7 @@
 * Fix for minor translation errors
 * Printing of microbial codes in a `data.frame` or `tibble` now gives a warning if the data contains old microbial codes (from a previous AMR package version)
 * `first_isolate()` can now take a vector of values for `col_keyantibiotics` and can have an episode length of `Inf`
+* `like()` (and `%like%`) now checks if `pattern` is a *valid* regular expression
 * Fixed an installation error on R-3.0
 
 # AMR 1.6.0

R/aa_helper_functions.R

@@ -211,10 +211,20 @@ search_type_in_df <- function(x, type, info = TRUE) {
   found
 }
 
-is_possibly_regex <- function(x) {
+is_valid_regex <- function(x) {
-  tryCatch(vapply(FUN.VALUE = character(1), strsplit(x, ""),
+  regex_at_all <- tryCatch(vapply(FUN.VALUE = logical(1),
-                  function(y) any(y %in% c("$", "(", ")", "*", "+", "-", ".", "?", "[", "]", "^", "{", "|", "}", "\\"), na.rm = TRUE)),
+                                  X = strsplit(x, ""),
-           error = function(e) rep(TRUE, length(x)))
+                                  FUN = function(y) any(y %in% c("$", "(", ")", "*", "+", "-",
+                                                                 ".", "?", "[", "]", "^", "{", 
+                                                                 "|", "}", "\\"),
+                                                        na.rm = TRUE)),
+                           error = function(e) rep(TRUE, length(x)))
+  regex_valid <- vapply(FUN.VALUE = logical(1),
+                        X = c("[.", "."),
+                        FUN = function(y) !"try-error" %in% class(try(grepl(y, ""),
+                                                                      silent = TRUE)),
+                        USE.NAMES = FALSE)
+  regex_at_all & regex_valid
 }
 
 stop_ifnot_installed <- function(package) {

R/like.R

@@ -28,21 +28,21 @@
 #' 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
 #' @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.
+#' @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.
 #' @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
 #' @details
-#' The `%like%` function:
+#' This `%like%` function:
 #' * Is case-insensitive (use `%like_case%` for case-sensitive matching)
 #' * Supports multiple patterns
-#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed
+#' * Checks if `pattern` is a valid regular expression and sets `fixed = TRUE` if not, to greatly improve speed (vectorised over `pattern`)
 #' * Always uses compatibility with Perl unless `fixed = TRUE`, to greatly improve speed
 #' 
 #' 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...`).
-#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R)
+#' @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()]
 #' @inheritSection AMR Read more on Our Website!
 #' @examples
@@ -80,8 +80,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
     return(rep(FALSE, length(x)))
   }
 
-  # set to fixed if no regex found
+  # set to fixed if no valid regex (vectorised)
-  fixed <- !any(is_possibly_regex(pattern))
+  fixed <- !is_valid_regex(pattern)
+
   if (ignore.case == TRUE) {
     # set here, otherwise if fixed = TRUE, this warning will be thrown: argument `ignore.case = TRUE` will be ignored
     x <- tolower(x)
@@ -105,7 +106,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
       mapply(FUN = grepl,
              x = x,
              pattern = pattern,
-             MoreArgs = list(ignore.case = FALSE, fixed = fixed, perl = !fixed),
+             fixed = fixed,
+             perl = !fixed,
+             MoreArgs = list(ignore.case = FALSE),
              SIMPLIFY = FALSE,
              USE.NAMES = FALSE)
     )

R/mo_matching_score.R

@@ -44,7 +44,7 @@
 #' * \ifelse{html}{\out{<i>p<sub>n</sub></i> is the human pathogenic prevalence group of <i>n</i>, as described below;}}{p_n is the human pathogenic prevalence group of \eqn{n}, as described below;}
 #' * \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 #' 
-#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
+#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*, *Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
 #' 
 #' All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., `"E. coli"` will return the microbial ID of *Escherichia coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Escherichia coli"), 3)`}, a highly prevalent microorganism found in humans) and not *Entamoeba coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Entamoeba coli"), 3)`}, a less prevalent microorganism in humans), although the latter would alphabetically come first. 
 #' @export

docs/404.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="https://msberends.github.io/AMR//index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/LICENSE-text.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/articles/index.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/authors.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -236,13 +236,13 @@
       <small class="dont-index">Source: <a href='https://github.com/msberends/AMR/blob/master/inst/CITATION'><code>inst/CITATION</code></a></small>
     </div>
 
-    <p>Berends MS, Luz CF et al. (2019). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622</p>
+    <p>Berends MS, Luz CF et al. (2021). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622</p>
     <pre>@Article{,
   title = {AMR - An R Package for Working with Antimicrobial Resistance Data},
   author = {M S Berends and C F Luz and A W Friedrich and B N M Sinha and C J Albers and C Glasner},
   journal = {bioRxiv},
   publisher = {Cold Spring Harbor Laboratory},
-  year = {2019},
+  year = {2021},
   url = {https://doi.org/10.1101/810622},
 }</pre>
 

docs/index.html

@@ -42,7 +42,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/news/index.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -236,13 +236,13 @@
       <small>Source: <a href='https://github.com/msberends/AMR/blob/master/NEWS.md'><code>NEWS.md</code></a></small>
     </div>
 
-    <div id="amr-1609002" class="section level1">
+    <div id="amr-1609003" class="section level1">
-<h1 class="page-header" data-toc-text="1.6.0.9002">
+<h1 class="page-header" data-toc-text="1.6.0.9003">
-<a href="#amr-1609002" class="anchor"></a>AMR 1.6.0.9002<small> Unreleased </small>
+<a href="#amr-1609003" class="anchor"></a>AMR 1.6.0.9003<small> Unreleased </small>
 </h1>
-<div id="last-updated-12-april-2021" class="section level2">
+<div id="last-updated-16-april-2021" class="section level2">
 <h2 class="hasAnchor">
-<a href="#last-updated-12-april-2021" class="anchor"></a><small>Last updated: 12 April 2021</small>
+<a href="#last-updated-16-april-2021" class="anchor"></a><small>Last updated: 16 April 2021</small>
 </h2>
 <div id="new" class="section level3">
 <h3 class="hasAnchor">
@@ -270,6 +270,8 @@
 <li>
 <code><a href="../reference/first_isolate.html">first_isolate()</a></code> can now take a vector of values for <code>col_keyantibiotics</code> and can have an episode length of <code>Inf</code>
 </li>
+<li>
+<code><a href="../reference/like.html">like()</a></code> (and <code><a href="../reference/like.html">%like%</a></code>) now checks if <code>pattern</code> is a <em>valid</em> regular expression</li>
 <li>Fixed an installation error on R-3.0</li>
 </ul>
 </div>

docs/pkgdown.yml

@@ -12,7 +12,7 @@ articles:
   datasets: datasets.html
   resistance_predict: resistance_predict.html
   welcome_to_AMR: welcome_to_AMR.html
-last_built: 2021-04-12T12:24Z
+last_built: 2021-04-16T09:40Z
 urls:
   reference: https://msberends.github.io/AMR//reference
   article: https://msberends.github.io/AMR//articles

docs/reference/as.mo.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -399,7 +399,7 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
 <li><p><i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.</p></li>
 </ul>
 
-<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>,<em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
+<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>, <em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
 <p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., <code>"E. coli"</code> will return the microbial ID of <em>Escherichia coli</em> (\(m = 0.688\), a highly prevalent microorganism found in humans) and not <em>Entamoeba coli</em> (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.</p>
     <h2 class="hasAnchor" id="catalogue-of-life"><a class="anchor" href="#catalogue-of-life"></a>Catalogue of Life</h2>
 

docs/reference/first_isolate.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9001</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/reference/get_episode.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9001</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/reference/index.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

docs/reference/like.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9001</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -257,7 +257,7 @@
     </tr>
     <tr>
       <th>pattern</th>
-      <td><p>a character string containing a regular expression (or <a href='https://rdrr.io/r/base/character.html'>character</a> string for <code>fixed = TRUE</code>) to be matched in the given character vector. Coerced by <code><a href='https://rdrr.io/r/base/character.html'>as.character()</a></code> to a character string if possible.  If a <a href='https://rdrr.io/r/base/character.html'>character</a> vector of length 2 or more is supplied, the first element is used with a warning.</p></td>
+      <td><p>a character vector containing regular expressions (or a <a href='https://rdrr.io/r/base/character.html'>character</a> string for <code>fixed = TRUE</code>) to be matched in the given character vector. Coerced by <code><a href='https://rdrr.io/r/base/character.html'>as.character()</a></code> to a character string if possible.</p></td>
     </tr>
     <tr>
       <th>ignore.case</th>
@@ -267,16 +267,16 @@
 
     <h2 class="hasAnchor" id="source"><a class="anchor" href="#source"></a>Source</h2>
 
-    <p>Idea from the <a href='https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R'><code>like</code> function from the <code>data.table</code> package</a></p>
+    <p>Idea from the <a href='https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R'><code>like</code> function from the <code>data.table</code> package</a>, although altered as explained in <em>Details</em>.</p>
     <h2 class="hasAnchor" id="value"><a class="anchor" href="#value"></a>Value</h2>
 
     <p>A <a href='https://rdrr.io/r/base/logical.html'>logical</a> vector</p>
     <h2 class="hasAnchor" id="details"><a class="anchor" href="#details"></a>Details</h2>
 
-    <p>The <code>%like%</code> function:</p><ul>
+    <p>This <code>%like%</code> function:</p><ul>
 <li><p>Is case-insensitive (use <code>%like_case%</code> for case-sensitive matching)</p></li>
 <li><p>Supports multiple patterns</p></li>
-<li><p>Checks if <code>pattern</code> is a regular expression and sets <code>fixed = TRUE</code> if not, to greatly improve speed</p></li>
+<li><p>Checks if <code>pattern</code> is a valid regular expression and sets <code>fixed = TRUE</code> if not, to greatly improve speed (vectorised over <code>pattern</code>)</p></li>
 <li><p>Always uses compatibility with Perl unless <code>fixed = TRUE</code>, to greatly improve speed</p></li>
 </ul>
 

docs/reference/mo_matching_score.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -272,7 +272,7 @@
 <li><p><i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.</p></li>
 </ul>
 
-<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>,<em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
+<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>, <em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
 <p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., <code>"E. coli"</code> will return the microbial ID of <em>Escherichia coli</em> (\(m = 0.688\), a highly prevalent microorganism found in humans) and not <em>Entamoeba coli</em> (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.</p>
     <h2 class="hasAnchor" id="stable-lifecycle"><a class="anchor" href="#stable-lifecycle"></a>Stable Lifecycle</h2>
 

docs/reference/mo_property.html

@@ -82,7 +82,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 
@@ -376,7 +376,7 @@ The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>stable</s
 <li><p><i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.</p></li>
 </ul>
 
-<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>,<em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
+<p>The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. <strong>Group 1</strong> (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is <em>Enterococcus</em>, <em>Staphylococcus</em> or <em>Streptococcus</em>. This group consequently contains all common Gram-negative bacteria, such as <em>Pseudomonas</em> and <em>Legionella</em> and all species within the order Enterobacterales. <strong>Group 2</strong> consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is <em>Absidia</em>, <em>Acremonium</em>, <em>Actinotignum</em>, <em>Alternaria</em>, <em>Anaerosalibacter</em>, <em>Apophysomyces</em>, <em>Arachnia</em>, <em>Aspergillus</em>, <em>Aureobacterium</em>, <em>Aureobasidium</em>, <em>Bacteroides</em>, <em>Basidiobolus</em>, <em>Beauveria</em>, <em>Blastocystis</em>, <em>Branhamella</em>, <em>Calymmatobacterium</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Catabacter</em>, <em>Chaetomium</em>, <em>Chryseobacterium</em>, <em>Chryseomonas</em>, <em>Chrysonilia</em>, <em>Cladophialophora</em>, <em>Cladosporium</em>, <em>Conidiobolus</em>, <em>Cryptococcus</em>, <em>Curvularia</em>, <em>Exophiala</em>, <em>Exserohilum</em>, <em>Flavobacterium</em>, <em>Fonsecaea</em>, <em>Fusarium</em>, <em>Fusobacterium</em>, <em>Hendersonula</em>, <em>Hypomyces</em>, <em>Koserella</em>, <em>Lelliottia</em>, <em>Leptosphaeria</em>, <em>Leptotrichia</em>, <em>Malassezia</em>, <em>Malbranchea</em>, <em>Mortierella</em>, <em>Mucor</em>, <em>Mycocentrospora</em>, <em>Mycoplasma</em>, <em>Nectria</em>, <em>Ochroconis</em>, <em>Oidiodendron</em>, <em>Phoma</em>, <em>Piedraia</em>, <em>Pithomyces</em>, <em>Pityrosporum</em>, <em>Prevotella</em>, <em>Pseudallescheria</em>, <em>Rhizomucor</em>, <em>Rhizopus</em>, <em>Rhodotorula</em>, <em>Scolecobasidium</em>, <em>Scopulariopsis</em>, <em>Scytalidium</em>, <em>Sporobolomyces</em>, <em>Stachybotrys</em>, <em>Stomatococcus</em>, <em>Treponema</em>, <em>Trichoderma</em>, <em>Trichophyton</em>, <em>Trichosporon</em>, <em>Tritirachium</em> or <em>Ureaplasma</em>. <strong>Group 3</strong> consists of all other microorganisms.</p>
 <p>All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., <code>"E. coli"</code> will return the microbial ID of <em>Escherichia coli</em> (\(m = 0.688\), a highly prevalent microorganism found in humans) and not <em>Entamoeba coli</em> (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.</p>
     <h2 class="hasAnchor" id="catalogue-of-life"><a class="anchor" href="#catalogue-of-life"></a>Catalogue of Life</h2>
 

docs/survey.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9002</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0.9003</span>
       </span>
     </div>
 

inst/CITATION

@@ -6,9 +6,9 @@ citEntry(
   author       = "M S Berends and C F Luz and A W Friedrich and B N M Sinha and C J Albers and C Glasner",
   journal      = "bioRxiv",
   publisher    = "Cold Spring Harbor Laboratory",
-  year         = 2019,
+  year         = 2021,
   url          = "https://doi.org/10.1101/810622",
-  textVersion  = "Berends MS, Luz CF et al. (2019). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622"
+  textVersion  = "Berends MS, Luz CF et al. (2021). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622"
 )
 
-citFooter("The mentioned article is a preprinted version of a manuscript we sent to a journal. Many thanks for using our open-source method to work with microbial and antimicrobial data!")
+citFooter("This preprint was accepted for publication in the Journal of Statistical Software, but we are awaiting the actual publication. Many thanks for using our open-source method to work with microbial and antimicrobial data!")

man/as.mo.Rd

@@ -157,7 +157,7 @@ where:
 \item \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 }
 
-The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
+The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
 
 All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }

man/like.Rd

@@ -6,7 +6,7 @@
 \alias{\%like_case\%}
 \title{Vectorised Pattern Matching with Keyboard Shortcut}
 \source{
-Idea from the \href{https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R}{\code{like} function from the \code{data.table} package}
+Idea from the \href{https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R}{\code{like} function from the \code{data.table} package}, although altered as explained in \emph{Details}.
 }
 \usage{
 like(x, pattern, ignore.case = TRUE)
@@ -18,7 +18,7 @@ x \%like_case\% pattern
 \arguments{
 \item{x}{a character vector where matches are sought, or an object which can be coerced by \code{\link[=as.character]{as.character()}} to a character vector.}
 
-\item{pattern}{a character string containing a regular expression (or \link{character} string for \code{fixed = TRUE}) to be matched in the given character vector. Coerced by \code{\link[=as.character]{as.character()}} to a character string if possible.  If a \link{character} vector of length 2 or more is supplied, the first element is used with a warning.}
+\item{pattern}{a character vector containing regular expressions (or a \link{character} string for \code{fixed = TRUE}) to be matched in the given character vector. Coerced by \code{\link[=as.character]{as.character()}} to a character string if possible.}
 
 \item{ignore.case}{if \code{FALSE}, the pattern matching is \emph{case sensitive} and if \code{TRUE}, case is ignored during matching.}
 }
@@ -29,11 +29,11 @@ A \link{logical} vector
 Convenient wrapper around \code{\link[=grepl]{grepl()}} to match a pattern: \code{x \%like\% pattern}. It always returns a \code{\link{logical}} vector and is always case-insensitive (use \code{x \%like_case\% pattern} for case-sensitive matching). Also, \code{pattern} can be as long as \code{x} to compare items of each index in both vectors, or they both can have the same length to iterate over all cases.
 }
 \details{
-The \verb{\%like\%} function:
+This \verb{\%like\%} function:
 \itemize{
 \item Is case-insensitive (use \verb{\%like_case\%} for case-sensitive matching)
 \item Supports multiple patterns
-\item Checks if \code{pattern} is a regular expression and sets \code{fixed = TRUE} if not, to greatly improve speed
+\item Checks if \code{pattern} is a valid regular expression and sets \code{fixed = TRUE} if not, to greatly improve speed (vectorised over \code{pattern})
 \item Always uses compatibility with Perl unless \code{fixed = TRUE}, to greatly improve speed
 }
 

man/mo_matching_score.Rd

@@ -30,7 +30,7 @@ where:
 \item \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 }
 
-The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
+The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
 
 All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }

man/mo_property.Rd

@@ -160,7 +160,7 @@ where:
 \item \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 }
 
-The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
+The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms.
 
 All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
 }

tests/testthat/test-eucast_rules.R

@@ -38,7 +38,7 @@ test_that("EUCAST rules work", {
                  "reference.version",
                  "note"))
   MOs_mentioned <- unique(eucast_rules_file$this_value)
-  MOs_mentioned <- sort(trimws(unlist(strsplit(MOs_mentioned[!is_possibly_regex(MOs_mentioned)], ",", fixed = TRUE))))
+  MOs_mentioned <- sort(trimws(unlist(strsplit(MOs_mentioned[!is_valid_regex(MOs_mentioned)], ",", fixed = TRUE))))
   MOs_test <- suppressWarnings(suppressMessages(mo_name(MOs_mentioned)))
   expect_length(MOs_mentioned[MOs_test != MOs_mentioned], 0)