added prevalence column and alterted as.mo algorith to use it, added ab_name as alias

NAMESPACE

@@ -41,8 +41,8 @@ export(MDRO)
 export(MRGN)
 export(ab_atc)
 export(ab_certe)
+export(ab_name)
 export(ab_official)
-export(ab_official_nl)
 export(ab_property)
 export(ab_tradenames)
 export(ab_trivial_nl)

NEWS.md

@@ -37,7 +37,7 @@
   mo_fullname("S. group A") # when run on a on a Portuguese system
   # [1] "Streptococcus grupo A"
   ```
-* Function `ab_property` and its aliases: `ab_official`, `ab_tradenames`, `ab_certe`, `ab_umcg`, `ab_official_nl` and `ab_trivial_nl`
+* Function `ab_property` and its aliases: `ab_name`, `ab_tradenames`, `ab_certe`, `ab_umcg` and `ab_trivial_nl`
 * Introduction to AMR as a vignette
 
 #### Changed
@@ -47,7 +47,7 @@
   ```r
   ab_official("Bactroban")
   # [1] "Mupirocin"
-  ab_official(c("Bactroban", "Amoxil", "Zithromax", "Floxapen"))
+  ab_name(c("Bactroban", "Amoxil", "Zithromax", "Floxapen"))
   # [1] "Mupirocin" "Amoxicillin" "Azithromycin" "Flucloxacillin"
   ab_atc(c("Bactroban", "Amoxil", "Zithromax", "Floxapen"))
   # [1] "R01AX06" "J01CA04" "J01FA10" "J01CF05"
@@ -56,7 +56,7 @@
 * Function `ratio` is now deprecated and will be removed in a future release, as it is not really the scope of this package
 * Fix for `as.mic` for values ending in zeroes after a real number
 * Small fix where *B. fragilis* would not be found in the `microorganisms.umcg` data set
-* Fix for `is.rsi.eligible`, now ignores reading marks
+* Added `prevalence` column to the `microorganisms` data set
 * Added parameters `minimum` and `as_percent` to `portion_df`
 * Support for quasiquotation in the functions series `count_*` and `portions_*`, and `n_rsi`. This allows to check for more than 2 vectors or columns.
   ```r

R/ab_property.R

@@ -21,6 +21,7 @@
 #' Use these functions to return a specific property of an antibiotic from the \code{\link{antibiotics}} data set, based on their ATC code. Get such a code with \code{\link{as.atc}}.
 #' @param x a (vector of a) valid \code{\link{atc}} code or any text that can be coerced to a valid atc with \code{\link{as.atc}}
 #' @param property one of the column names of one of the \code{\link{antibiotics}} data set, like \code{"atc"} and \code{"official"}
+#' @param language language of the returned text, defaults to the systems language. Either one of \code{"en"} (English) or \code{"nl"} (Dutch).
 #' @rdname ab_property
 #' @return A vector of values. In case of \code{ab_tradenames}, if \code{x} is of length one, a vector will be returned. Otherwise a \code{\link{list}}, with \code{x} as names.
 #' @export
@@ -28,8 +29,8 @@
 #' @seealso \code{\link{antibiotics}}
 #' @examples
 #' ab_atc("amcl")         # J01CR02
-#' ab_official("amcl")    # Amoxicillin and beta-lactamase inhibitor
+#' ab_name("amcl")        # Amoxicillin and beta-lactamase inhibitor
-#' ab_official_nl("amcl") # Amoxicilline met enzymremmer
+#' ab_name("amcl", "nl")  # Amoxicilline met enzymremmer
 #' ab_trivial_nl("amcl")  # Amoxicilline/clavulaanzuur
 #' ab_certe("amcl")       # amcl
 #' ab_umcg("amcl")        # AMCL
@@ -56,15 +57,25 @@ ab_atc <- function(x) {
 
 #' @rdname ab_property
 #' @export
-ab_official <- function(x) {
+ab_official <- function(x, language = NULL) {
+
+  if (is.null(language)) {
+    language <- Sys.locale()
+  } else {
+    language <- tolower(language[1])
+  }
+  if (language %in% c("en", "")) {
     ab_property(x, "official")
+  } else if (language == "nl") {
+    ab_property(x, "official_nl")
+  } else {
+    stop("Unsupported language: '", language, "' - use one of: 'en', 'nl'", call. = FALSE)
+  }
 }
 
 #' @rdname ab_property
 #' @export
-ab_official_nl <- function(x) {
+ab_name <- ab_official
-  ab_property(x, "official_nl")
-}
 
 #' @rdname ab_property
 #' @export

R/data.R

@@ -122,8 +122,8 @@
 
 #' Data set with human pathogenic microorganisms
 #'
-#' A data set containing 2,630 (potential) human pathogenic microorganisms. MO codes can be looked up using \code{\link{guess_mo}}.
+#' A data set containing (potential) human pathogenic microorganisms. MO codes can be looked up using \code{\link{guess_mo}}.
-#' @format A \code{\link{tibble}} with 2,630 observations and 10 variables:
+#' @format A \code{\link{tibble}} with 2,642 observations and 11 variables:
 #' \describe{
 #'   \item{\code{mo}}{ID of microorganism}
 #'   \item{\code{bactsys}}{Bactsyscode of microorganism}
@@ -135,6 +135,7 @@
 #'   \item{\code{aerobic}}{Logical whether bacteria is aerobic}
 #'   \item{\code{type}}{Type of microorganism, like \code{"Bacteria"} and \code{"Fungus/yeast"}}
 #'   \item{\code{gramstain}}{Gram of microorganism, like \code{"Negative rods"}}
+#'   \item{\code{prevalence}}{A rounded integer based on prevalence of the microorganism. Used internally by \code{\link{as.mo}}, otherwise quite meaningless.}
 #' }
 #  source MOLIS (LIS of Certe) - \url{https://www.certe.nl}
 # new <- microorganisms %>% filter(genus == "Bacteroides") %>% .[1,]

R/globals.R

@@ -47,6 +47,7 @@ globalVariables(c(".",
                   "Pasted",
                   "patient_id",
                   "Percentage",
+                  "prevalence",
                   "R",
                   "real_first_isolate",
                   "S",

R/misc.R

@@ -155,6 +155,20 @@ tbl_parse_guess <- function(tbl,
   tbl
 }
 
+#' @importFrom dplyr case_when
+Sys.locale <- function() {
+  sys <- base::Sys.getlocale()
+  case_when(
+    sys %like% '(Deutsch|German|de_)'       ~ "de",
+    sys %like% '(Nederlands|Dutch|nl_)'     ~ "nl",
+    sys %like% '(Espa.ol|Spanish|es_)'      ~ "es",
+    sys %like% '(Fran.ais|French|fr_)'      ~ "fr",
+    sys %like% '(Portugu.s|Portuguese|pt_)' ~ "pt",
+    sys %like% '(Italiano|Italian|it_)'     ~ "it",
+    TRUE                                    ~ "en"
+  )
+}
+
 # transforms date format like "dddd d mmmm yyyy" to "%A %e %B %Y"
 date_generic <- function(format) {
   if (!grepl('%', format, fixed = TRUE)) {

R/mo.R

@@ -33,12 +33,12 @@
 #'
 #' Use the \code{\link{mo_property}} functions to get properties based on the returned code, see Examples.
 #'
-#' Some exceptions have been built in to get more logical results, based on prevalence of human pathogens. These are:
+#' Thus function uses Artificial Intelligence (AI) to help getting more logical results, based on type of input and known prevalence of human pathogens. For example:
 #' \itemize{
 #'   \item{\code{"E. coli"} will return the ID of \emph{Escherichia coli} and not \emph{Entamoeba coli}, although the latter would alphabetically come first}
-#'   \item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae}}
+#'   \item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae} for the same reason}
 #'   \item{Something like \code{"p aer"} will return the ID of \emph{Pseudomonas aeruginosa} and not \emph{Pasteurella aerogenes}}
-#'   \item{Something like \code{"stau"} or \code{"staaur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
+#'   \item{Something like \code{"stau"} or \code{"S aur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
 #' }
 #' Moreover, this function also supports ID's based on only Gram stain, when the species is not known. \cr
 #' For example, \code{"Gram negative rods"} and \code{"GNR"} will both return the ID of a Gram negative rod: \code{GNR}.
@@ -47,7 +47,7 @@
 #'
 #' [2] Lancefield RC \strong{A serological differentiation of human and other groups of hemolytic streptococci}. 1933. J Exp Med. 57(4): 571–95. \url{https://dx.doi.org/10.1084/jem.57.4.571}
 #' @export
-#' @importFrom dplyr %>% pull left_join
+#' @importFrom dplyr %>% pull left_join arrange
 #' @return Character (vector) with class \code{"mo"}. Unknown values will return \code{NA}.
 #' @seealso \code{\link{microorganisms}} for the dataframe that is being used to determine ID's.
 #' @examples
@@ -118,7 +118,10 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
     }
   }
 
-  MOs <- AMR::microorganisms %>% filter(!mo %like% '^_FAM') # dont search in those
+  MOs <- AMR::microorganisms %>%
+    arrange(prevalence) %>%    # more expected result on multiple findings
+    filter(!mo %like% '^_FAM', # don't search in those
+           (nchar(mo) > 3 | mo %in% c("GNR", "GPR", "GNC", "GPC")))      # no genera
   failures <- character(0)
   x_input <- x
 
@@ -144,11 +147,11 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
   x_withspaces_start <- paste0('^', x_withspaces)
   x_withspaces <- paste0('^', x_withspaces, '$')
 
-  # print(x)
+  # cat(paste0('x                  "', x, '"\n'))
-  # print(x_withspaces_all)
+  # cat(paste0('x_withspaces_all   "', x_withspaces_all, '"\n'))
-  # print(x_withspaces_start)
+  # cat(paste0('x_withspaces_start "', x_withspaces_start, '"\n'))
-  # print(x_withspaces)
+  # cat(paste0('x_withspaces       "', x_withspaces, '"\n'))
-  # print(x_backup)
+  # cat(paste0('x_backup           "', x_backup, '"\n'))
 
   for (i in 1:length(x)) {
     if (identical(x_trimmed[i], "")) {
@@ -201,7 +204,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
         next
       }
       if (toupper(x_trimmed[i]) == 'VRE') {
-        x[i] <- 'ENC'
+        x[i] <- 'ENCSPP'
         next
       }
       if (toupper(x_trimmed[i]) == 'MRPA') {
@@ -234,6 +237,13 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
       next
     }
 
+    # try any match with genus, keeping spaces, not ending with $ ----
+    found <- MOs[which(MOs$genus %like% x_withspaces_start[i] & MOs$mo %like% 'SPP$'),]$mo
+    if (length(found) > 0) {
+      x[i] <- found[1L]
+      next
+    }
+
     # try any match keeping spaces, not ending with $ ----
     found <- MOs[which(MOs$fullname %like% x_withspaces_start[i]),]$mo
     if (length(found) > 0) {
@@ -297,19 +307,6 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
 
   }
 
-  # avoid detection of Staphylococcus auricularis in case of S. aureus ----
-  x[x == "STAAUC" & toupper(x_backup) != "STAAUC" & !x_backup %like% 'auri'] <- "STAAUR"
-  # avoid detection of Entamoeba coli in case of E. coli ----
-  x[x == "ENMCOL" & toupper(x_backup) != "ENMCOL" & !x_backup %like% '^ent?'] <- "ESCCOL"
-  # avoid detection of Haematobacter influenzae in case of H. influenzae ----
-  x[x == "HABINF" & toupper(x_backup) != "HABINF" & !x_backup %like% '^haema'] <- "HAEINF"
-  # avoid detection of Pasteurella aerogenes in case of P. aeruginosa ----
-  x[x == "PASAER" & toupper(x_backup) != "PASAER" & !(x_backup %like% '^pas?' | x_backup %like% 'aero')] <- "PSEAER"
-  # avoid detection of Legionella non pneumophila in case of Legionella pneumophila ----
-  x[x == "LEGNON" & toupper(x_backup) != "LEGNON" & !x_backup %like% 'non'] <- "LEGPNE"
-  # avoid detection of Streptobacillus in case of Streptococcus ----
-  x[x == "STB" & toupper(x_backup) != "STB" & !x_backup %like% 'streptob'] <- "STC"
-
   failures <- failures[!failures %in% c(NA, NULL, NaN)]
   if (length(failures) > 0) {
     warning("These ", length(failures) , " values could not be coerced to a valid mo: ",
@@ -376,7 +373,9 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
 
   # for the returned genera without species, add species ----
   # like "ESC" -> "ESCSPP", but only where the input contained it
-  indices <- unique(x_input) %like% "[A-Z]{3}SPP" & !x %like% "[A-Z]{3}SPP"
+  indices <- nchar(unique(x)) == 3 & !x %like% "[A-Z]{3}SPP" & !x %in% c("GNR", "GPR", "GNC", "GPC",
+                                                                         "GNS", "GPS", "GNK", "GPK")
+  indices <- indices[!is.na(indices)]
   x[indices] <- paste0(x[indices], 'SPP')
 
   # left join the found results to the original input values (x_input)

R/mo_property.R

@@ -207,7 +207,7 @@ mo_property <- function(x, property = 'fullname', Becker = FALSE, Lancefield = F
 #' @importFrom dplyr %>% case_when
 mo_translate <- function(x, language) {
   if (is.null(language)) {
-    language <- mo_getlangcode()
+    language <- Sys.locale()
   } else {
     language <- tolower(language[1])
   }
@@ -350,17 +350,3 @@ mo_translate <- function(x, language) {
   )
 
 }
-
-#' @importFrom dplyr case_when
-mo_getlangcode <- function() {
-  sys <- base::Sys.getlocale()
-  case_when(
-    sys %like% '(Deutsch|German|de_)'       ~ "de",
-    sys %like% '(Nederlands|Dutch|nl_)'     ~ "nl",
-    sys %like% '(Espa.ol|Spanish|es_)'      ~ "es",
-    sys %like% '(Fran.ais|French|fr_)'      ~ "fr",
-    sys %like% '(Portugu.s|Portuguese|pt_)' ~ "pt",
-    sys %like% '(Italiano|Italian|it_)'     ~ "it",
-    TRUE                                    ~ "en"
-  )
-}

README.md

@@ -56,7 +56,7 @@ This `AMR` package basically does four important things:
      * You can also identify first *weighted* isolates of every patient, an adjusted version of the CLSI guideline. This takes into account key antibiotics of every strain and compares them.
    * Use `MDRO` (abbreviation of Multi Drug Resistant Organisms) to check your isolates for exceptional resistance with country-specific guidelines or EUCAST rules. Currently, national guidelines for Germany and the Netherlands are supported.
    * The data set `microorganisms` contains the family, genus, species, subspecies, colloquial name and Gram stain of almost 3,000 potential human pathogenic microorganisms (bacteria, fungi/yeasts and parasites). This enables resistance analysis of e.g. different antibiotics per Gram stain. The package also contains functions to look up values in this data set like `mo_genus`, `mo_family` or `mo_gramstain`. As they use `as.mo` internally, they also use artificial intelligence. For example, `mo_genus("MRSA")` and `mo_genus("S. aureus")` will both return `"Staphylococcus"`. They also come with support for German, Dutch, French, Italian, Spanish and Portuguese. These functions can be used to add new variables to your data.
-   * The data set `antibiotics` contains the ATC code, LIS codes, official name, trivial name and DDD of both oral and parenteral administration. It also contains a total of 298 trade names. Use functions like `ab_official` and `ab_tradenames` to look up values. As the `mo_*` functions use `as.mo` internally, the `ab_*` functions use `as.atc` internally so it uses AI to guess your expected result. For example, `ab_official("Fluclox")`, `ab_official("Floxapen")` and `ab_official("J01CF05")` will all return `"Flucloxacillin"`. These functions can again be used to add new variables to your data.
+   * The data set `antibiotics` contains the ATC code, LIS codes, official name, trivial name and DDD of both oral and parenteral administration. It also contains a total of 298 trade names. Use functions like `ab_name` and `ab_tradenames` to look up values. As the `mo_*` functions use `as.mo` internally, the `ab_*` functions use `as.atc` internally so it uses AI to guess your expected result. For example, `ab_name("Fluclox")`, `ab_name("Floxapen")` and `ab_name("J01CF05")` will all return `"Flucloxacillin"`. These functions can again be used to add new variables to your data.
 
 3. It **analyses the data** with convenient functions that use well-known methods.
 
@@ -388,7 +388,7 @@ antibiotics       # A tibble: 423 x 18
 
 # Dataset with bacteria codes and properties like gram stain and 
 # aerobic/anaerobic
-microorganisms    # A tibble: 2,630 x 10
+microorganisms    # A tibble: 2,642 x 11
 ```
 
 ## Copyright

man/ab_property.Rd

@@ -4,7 +4,7 @@
 \alias{ab_property}
 \alias{ab_atc}
 \alias{ab_official}
-\alias{ab_official_nl}
+\alias{ab_name}
 \alias{ab_trivial_nl}
 \alias{ab_certe}
 \alias{ab_umcg}
@@ -15,9 +15,9 @@ ab_property(x, property = "official")
 
 ab_atc(x)
 
-ab_official(x)
+ab_official(x, language = NULL)
 
-ab_official_nl(x)
+ab_name(x, language = NULL)
 
 ab_trivial_nl(x)
 
@@ -31,6 +31,8 @@ ab_tradenames(x)
 \item{x}{a (vector of a) valid \code{\link{atc}} code or any text that can be coerced to a valid atc with \code{\link{as.atc}}}
 
 \item{property}{one of the column names of one of the \code{\link{antibiotics}} data set, like \code{"atc"} and \code{"official"}}
+
+\item{language}{language of the returned text, defaults to the systems language. Either one of \code{"en"} (English) or \code{"nl"} (Dutch).}
 }
 \value{
 A vector of values. In case of \code{ab_tradenames}, if \code{x} is of length one, a vector will be returned. Otherwise a \code{\link{list}}, with \code{x} as names.
@@ -40,8 +42,8 @@ Use these functions to return a specific property of an antibiotic from the \cod
 }
 \examples{
 ab_atc("amcl")         # J01CR02
-ab_official("amcl")    # Amoxicillin and beta-lactamase inhibitor
+ab_name("amcl")        # Amoxicillin and beta-lactamase inhibitor
-ab_official_nl("amcl") # Amoxicilline met enzymremmer
+ab_name("amcl", "nl")  # Amoxicilline met enzymremmer
 ab_trivial_nl("amcl")  # Amoxicilline/clavulaanzuur
 ab_certe("amcl")       # amcl
 ab_umcg("amcl")        # AMCL

man/as.mo.Rd

@@ -40,12 +40,12 @@ Use this function to determine a valid ID based on a genus (and species). Determ
 
 Use the \code{\link{mo_property}} functions to get properties based on the returned code, see Examples.
 
-Some exceptions have been built in to get more logical results, based on prevalence of human pathogens. These are:
+Thus function uses Artificial Intelligence (AI) to help getting more logical results, based on type of input and known prevalence of human pathogens. For example:
 \itemize{
   \item{\code{"E. coli"} will return the ID of \emph{Escherichia coli} and not \emph{Entamoeba coli}, although the latter would alphabetically come first}
-  \item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae}}
+  \item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae} for the same reason}
   \item{Something like \code{"p aer"} will return the ID of \emph{Pseudomonas aeruginosa} and not \emph{Pasteurella aerogenes}}
-  \item{Something like \code{"stau"} or \code{"staaur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
+  \item{Something like \code{"stau"} or \code{"S aur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
 }
 Moreover, this function also supports ID's based on only Gram stain, when the species is not known. \cr
 For example, \code{"Gram negative rods"} and \code{"GNR"} will both return the ID of a Gram negative rod: \code{GNR}.

man/microorganisms.Rd

@@ -4,7 +4,7 @@
 \name{microorganisms}
 \alias{microorganisms}
 \title{Data set with human pathogenic microorganisms}
-\format{A \code{\link{tibble}} with 2,630 observations and 10 variables:
+\format{A \code{\link{tibble}} with 2,642 observations and 11 variables:
 \describe{
   \item{\code{mo}}{ID of microorganism}
   \item{\code{bactsys}}{Bactsyscode of microorganism}
@@ -16,12 +16,13 @@
   \item{\code{aerobic}}{Logical whether bacteria is aerobic}
   \item{\code{type}}{Type of microorganism, like \code{"Bacteria"} and \code{"Fungus/yeast"}}
   \item{\code{gramstain}}{Gram of microorganism, like \code{"Negative rods"}}
+  \item{\code{prevalence}}{A rounded integer based on prevalence of the microorganism. Used internally by \code{\link{as.mo}}, otherwise quite meaningless.}
 }}
 \usage{
 microorganisms
 }
 \description{
-A data set containing 2,630 (potential) human pathogenic microorganisms. MO codes can be looked up using \code{\link{guess_mo}}.
+A data set containing (potential) human pathogenic microorganisms. MO codes can be looked up using \code{\link{guess_mo}}.
 }
 \seealso{
 \code{\link{guess_mo}} \code{\link{antibiotics}} \code{\link{microorganisms.umcg}}

tests/testthat/test-ab_property.R

@@ -2,8 +2,9 @@ context("ab_property.R")
 
 test_that("ab_property works", {
   expect_equal(ab_certe("amox"), "amox")
-  expect_equal(ab_official("amox"), "Amoxicillin")
+  expect_equal(ab_name("amox", language = "en"), "Amoxicillin")
-  expect_equal(ab_official_nl("amox"), "Amoxicilline")
+  expect_equal(ab_name("amox", language = "nl"), "Amoxicilline")
+  expect_equal(ab_official("amox", language = "en"), "Amoxicillin")
   expect_equal(ab_trivial_nl("amox"), "Amoxicilline")
   expect_equal(ab_umcg("amox"), "AMOX")
   expect_equal(class(ab_tradenames("amox")), "character")
@@ -11,4 +12,6 @@ test_that("ab_property works", {
   expect_equal(ab_atc("amox"), as.character(as.atc("amox")))
 
   expect_error(ab_property("amox", "invalid property"))
+  expect_error(ab_name("amox", language = "INVALID"))
+  expect_output(print(ab_name("amox", language = NULL)))
 })

tests/testthat/test-mo.R

@@ -3,7 +3,7 @@ context("mo.R")
 test_that("as.mo works", {
 
   library(dplyr)
-  MOs <- AMR::microorganisms %>% filter(!is.na(mo))
+  MOs <- AMR::microorganisms %>% filter(!is.na(mo), nchar(mo) > 3)
   expect_identical(as.character(MOs$mo), as.character(as.mo(MOs$mo)))
 
   expect_identical(
@@ -12,18 +12,20 @@ test_that("as.mo works", {
 
   expect_equal(as.character(as.mo("Escherichia coli")), "ESCCOL")
   expect_equal(as.character(as.mo("Escherichia  coli")), "ESCCOL")
-  expect_equal(as.character(as.mo("Escherichia  species")), "ESC")
+  expect_equal(as.character(as.mo("Escherichia  species")), "ESCSPP")
+  expect_equal(as.character(as.mo("Escherichia")), "ESCSPP")
   expect_equal(as.character(as.mo(" ESCCOL ")), "ESCCOL")
+  expect_equal(as.character(as.mo("coli")), "ESCCOL") # not Campylobacter
   expect_equal(as.character(as.mo("klpn")), "KLEPNE")
-  expect_equal(as.character(as.mo("Klebsiella")), "KLE")
+  expect_equal(as.character(as.mo("Klebsiella")), "KLESPP")
   expect_equal(as.character(as.mo("K. pneu rhino")), "KLEPNERH") # K. pneumoniae subspp. rhinoscleromatis
-  expect_equal(as.character(as.mo("Bartonella")), "BAR")
+  expect_equal(as.character(as.mo("Bartonella")), "BARSPP")
   expect_equal(as.character(as.mo("C. difficile")), "CLODIF")
   expect_equal(as.character(as.mo("L. pneumophila")), "LEGPNE")
   expect_equal(as.character(as.mo("L. non pneumophila")), "LEGNON")
   expect_equal(as.character(as.mo("S. beta-haemolytic")), "STCHAE")
-  expect_equal(as.character(as.mo("Strepto")), "STC") # not Streptobacillus
+  expect_equal(as.character(as.mo("Strepto")), "STCSPP")
-  expect_equal(as.character(as.mo("Streptococcus")), "STC") # not Peptostreptoccus
+  expect_equal(as.character(as.mo("Streptococcus")), "STCSPP") # not Peptostreptoccus
 
   expect_equal(as.character(as.mo(c("GAS", "GBS"))), c("STCGRA", "STCGRB"))
 
@@ -39,7 +41,7 @@ test_that("as.mo works", {
   expect_equal(as.character(as.mo("bctfgr")), "BACFRA")
 
   expect_equal(as.character(as.mo("MRSE")), "STAEPI")
-  expect_equal(as.character(as.mo("VRE")), "ENC")
+  expect_equal(as.character(as.mo("VRE")), "ENCSPP")
   expect_equal(as.character(as.mo("MRPA")), "PSEAER")
   expect_equal(as.character(as.mo("PISP")), "STCPNE")
   expect_equal(as.character(as.mo("PRSP")), "STCPNE")
@@ -67,8 +69,9 @@ test_that("as.mo works", {
   expect_identical(as.character(guess_mo("S. epidermidis", Becker = FALSE)), "STAEPI")
   expect_identical(as.character(guess_mo("S. epidermidis", Becker = TRUE)),  "STACNS")
   expect_identical(as.character(guess_mo("STAEPI",         Becker = TRUE)),  "STACNS")
-  expect_identical(as.character(guess_mo("S. intermedius", Becker = FALSE)), "STAINT")
+  expect_identical(as.character(guess_mo("S. intermedius", Becker = FALSE)), "STCINT") # Strep (!) intermedius
-  expect_identical(as.character(guess_mo("S. intermedius", Becker = TRUE)),  "STACPS")
+  expect_identical(as.character(guess_mo("Sta intermedius",Becker = FALSE)), "STAINT")
+  expect_identical(as.character(guess_mo("Sta intermedius",Becker = TRUE)),  "STACPS")
   expect_identical(as.character(guess_mo("STAINT",         Becker = TRUE)),  "STACPS")
   # aureus must only be influenced if Becker = "all"
   expect_identical(as.character(guess_mo("STAAUR", Becker = FALSE)), "STAAUR")
@@ -103,8 +106,9 @@ test_that("as.mo works", {
       select(genus) %>%
       as.mo() %>%
       as.character(),
-    c("ESC", "ESC", "STA", "STA", "STA",
+    paste0(c("ESC", "ESC", "STA", "STA", "STA",
-      "STA", "STA", "STA", "STA", "STA"))
+             "STA", "STA", "STA", "STA", "STA"),
+           "SPP"))
 
   # select with two columns
   expect_identical(

tests/testthat/test-mo_property.R

@@ -18,7 +18,7 @@ test_that("mo_property works", {
 
   # test integrity
   library(dplyr)
-  MOs <- AMR::microorganisms %>% filter(!is.na(mo))
+  MOs <- AMR::microorganisms %>% filter(!is.na(mo), nchar(mo) > 3)
   expect_identical(MOs$fullname, mo_fullname(MOs$fullname, language = "en"))
 
   mo_clean <- MOs$mo