(v1.5.0.9023) mo properties speed improvement

.github/workflows/check.yaml

@@ -53,9 +53,11 @@ jobs:
           - {os: macOS-latest,   r: 'devel',   allowfail: false}
           - {os: macOS-latest,   r: 'release', allowfail: false}
           - {os: macOS-latest,   r: 'oldrel',  allowfail: false}
+          
           - {os: windows-latest, r: 'devel',   allowfail: false}
           - {os: windows-latest, r: 'release', allowfail: false}
           - {os: windows-latest, r: 'oldrel',  allowfail: false}
+          
           - {os: ubuntu-20.04,   r: 'devel',   allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           - {os: ubuntu-20.04,   r: 'release', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
           - {os: ubuntu-20.04,   r: 'oldrel',  allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"}
@@ -66,7 +68,8 @@ jobs:
           - {os: ubuntu-20.04,   r: '3.3',     allowfail: true,  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: false, 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-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"}
           - {os: ubuntu-16.04,   r: 'oldrel',  allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"}
@@ -77,7 +80,7 @@ jobs:
           - {os: ubuntu-16.04,   r: '3.3',     allowfail: true,  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: false, 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"}
           
     env:
       R_REMOTES_NO_ERRORS_FROM_WARNINGS: true
@@ -159,7 +162,7 @@ jobs:
           _R_CHECK_LENGTH_1_CONDITION_: verbose
           _R_CHECK_LENGTH_1_LOGIC2_: verbose
         run: |
-          R CMD check data-raw/AMR_*.tar.gz --no-manual --no-build-vignettes
+          R CMD check data-raw/AMR_latest.tar.gz --no-manual --no-build-vignettes
 
       - name: Show testthat output
         if: always()

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 1.5.0.9020
+Version: 1.5.0.9023
-Date: 2021-02-18
+Date: 2021-02-21
 Title: Antimicrobial Resistance Data Analysis
 Authors@R: c(
     person(role = c("aut", "cre"), 

NEWS.md

@@ -1,5 +1,5 @@
-# AMR 1.5.0.9020
+# AMR 1.5.0.9023
-## <small>Last updated: 18 February 2021</small>
+## <small>Last updated: 21 February 2021</small>
 
 ### New
 * Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the `eucast_rules()` function and in `as.rsi()` to interpret MIC and disk diffusion values. This is now the default guideline in this package.
@@ -58,6 +58,8 @@
 * Functions `print()` and `summary()` on a Principal Components Analysis object (`pca()`) now print additional group info if the original data was grouped using `dplyr::group_by()`
 * Improved speed and reliability of `guess_ab_col()`. As this also internally improves the reliability of `first_isolate()` and `mdro()`, this might have a slight impact on the results of those functions.
 * Fix for `mo_name()` when used in other languages than English
+* The `like()` function (and its fast alias `%like%`) now always use Perl compatibility, improving speed for many functions in this package (e.g., `as.mo()` is now up to 4 times faster)
+* *Staphylococcus cornubiensis* is now correctly categorised as coagulase-positive
 
 ### Other
 * Big documentation updates

R/aa_helper_functions.R

@@ -112,7 +112,7 @@ check_dataset_integrity <- function() {
     require("AMR")
   })
   stop_if(!valid_microorganisms | !valid_antibiotics,
-          "the data set `microorganisms` or `antibiotics` was overwritten in your environment because another package with the same object names was loaded _after_ the AMR package, preventing the AMR package from working correctly. Please load the AMR package last.")
+          "the data set `microorganisms` or `antibiotics` was overwritten in your environment because another package with the same object name(s) was loaded _after_ the AMR package, preventing the AMR package from working correctly. Please load the AMR package last.")
   invisible(TRUE)
 }
 
@@ -538,7 +538,7 @@ meet_criteria <- function(object,
   if (!is.null(pkg_env$meet_criteria_error_txt)) {
     error_txt <- pkg_env$meet_criteria_error_txt
     pkg_env$meet_criteria_error_txt <- NULL
-    stop(error_txt, call. = FALSE)
+    stop(error_txt, call. = FALSE) # don't use stop_() here, pkg may not be loaded yet
   }
   pkg_env$meet_criteria_error_txt <- NULL
 
@@ -867,7 +867,13 @@ font_grey <- function(..., collapse = " ") {
   try_colour(..., before = "\033[38;5;249m", after = "\033[39m", collapse = collapse)
 }
 font_grey_bg <- function(..., collapse = " ") {
-  try_colour(..., before = "\033[48;5;254m", after = "\033[49m", collapse = collapse)
+  if (tryCatch(rstudioapi::getThemeInfo()$dark == TRUE, error = function(e) FALSE)) {
+    # similar to HTML #444444
+    try_colour(..., before = "\033[48;5;238m", after = "\033[49m", collapse = collapse)  
+  } else {
+    # similar to HTML #eeeeee
+    try_colour(..., before = "\033[48;5;254m", after = "\033[49m", collapse = collapse)
+  }
 }
 font_green_bg <- function(..., collapse = " ") {
   try_colour(..., before = "\033[42m", after = "\033[49m", collapse = collapse)
@@ -1077,6 +1083,14 @@ percentage <- function(x, digits = NULL, ...) {
                     digits = digits, ...)
 }
 
+time_start_tracking <- function() {
+  pkg_env$time_start <- round(as.numeric(Sys.time()) * 1000)
+}
+
+time_track <- function(name = NULL) {
+  paste("(until now:", trimws(round(as.numeric(Sys.time()) * 1000) - pkg_env$time_start), "ms)")
+}
+
 # prevent dependency on package 'backports'
 # these functions were not available in previous versions of R (last checked: R 4.0.3)
 # see here for the full list: https://github.com/r-lib/backports

R/eucast_rules.R

@@ -896,7 +896,7 @@ eucast_rules <- function(x,
     target_value <- eucast_rules_df[i, "to_value", drop = TRUE]
     
     if (is.na(source_antibiotics)) {
-      rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value),
+      rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value),
                        error = function(e) integer(0))
     } else {
       source_antibiotics <- get_antibiotic_columns(source_antibiotics, x)
@@ -906,17 +906,17 @@ eucast_rules <- function(x,
       if (length(source_antibiotics) == 0) {
         rows <- integer(0)
       } else if (length(source_antibiotics) == 1) {
-        rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
+        rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
                                 & as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]),
                           error = function(e) integer(0))
       } else if (length(source_antibiotics) == 2) {
-        rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
+        rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
                                 & as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]
                                 & as.rsi_no_warning(x[, source_antibiotics[2L]]) == source_value[2L]),
                           error = function(e) integer(0))
         # nolint start
       # } else if (length(source_antibiotics) == 3) {
-      #   rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
+      #   rows <-  tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
       #                           & as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]
       #                           & as.rsi_no_warning(x[, source_antibiotics[2L]]) == source_value[2L]
       #                           & as.rsi_no_warning(x[, source_antibiotics[3L]]) == source_value[3L]),

R/globals.R

@@ -26,6 +26,7 @@
 globalVariables(c(".rowid",
                   "ab",
                   "ab_txt",
+                  "affect_mo_name",
                   "angle",
                   "antibiotic",
                   "antibiotics",

R/like.R

@@ -39,7 +39,7 @@
 #' * 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
-#' * Tries again with `perl = TRUE` if regex fails
+#' * Always uses compatibility with Perl
 #' 
 #' 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/master/R/like.R)
@@ -99,7 +99,7 @@ like <- function(x, pattern, ignore.case = TRUE) {
         if (is.factor(x[i])) {
           res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed)
         } else {
-          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed)
+          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
         }
       }
       res <- vapply(FUN.VALUE = logical(1), pattern, function(pttrn) grepl(pttrn, x, ignore.case = FALSE, fixed = fixed))
@@ -112,9 +112,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
       # x and pattern are of same length, so items with each other
       for (i in seq_len(length(res))) {
         if (is.factor(x[i])) {
-          res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed)
+          res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed, perl = !fixed)
         } else {
-          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed)
+          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
         }
       }
       return(res)
@@ -123,22 +123,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
   
   # the regular way how grepl works; just one pattern against one or more x
   if (is.factor(x)) {
-    as.integer(x) %in% grep(pattern, levels(x), ignore.case = FALSE, fixed = fixed)
+    as.integer(x) %in% grep(pattern, levels(x), ignore.case = FALSE, fixed = fixed, perl = !fixed)
   } else {
-    tryCatch(grepl(pattern, x, ignore.case = FALSE, fixed = fixed),
+    grepl(pattern, x, ignore.case = FALSE, fixed = fixed, perl = !fixed)
-             error = function(e) {
-               if (grepl("invalid reg(ular )?exp", e$message, ignore.case = TRUE)) {
-                 # try with perl = TRUE:
-                 return(grepl(pattern = pattern, 
-                                    x = x,
-                                    ignore.case = FALSE, 
-                                    fixed = fixed,
-                                    perl = TRUE))
-               } else {
-                 # stop otherwise
-                 stop(e$message)
-               }
-             })
   }
 }
 
@@ -157,15 +144,3 @@ like <- function(x, pattern, ignore.case = TRUE) {
   meet_criteria(pattern, allow_NA = FALSE)
   like(x, pattern, ignore.case = FALSE)
 }
-
-"%like_perl%" <- function(x, pattern) {
-  meet_criteria(x, allow_NA = TRUE)
-  meet_criteria(pattern, allow_NA = FALSE)
-  # convenient for e.g. matching all Klebsiella and Raoultella, but not 
-  # K. aerogenes: fullname %like_perl% "^(Klebsiella(?! aerogenes)|Raoultella)"
-  grepl(x = tolower(x),
-        pattern = tolower(pattern),
-        perl = TRUE,
-        fixed = FALSE,
-        ignore.case = TRUE)
-}

R/mo.R

@@ -178,13 +178,6 @@ as.mo <- function(x,
     return(set_clean_class(x, new_class = c("mo", "character")))
   }
 
-  if (tryCatch(all(x == "" | gsub(".*(unknown ).*", "unknown name", tolower(x), perl = TRUE) %in% MO_lookup$fullname_lower, na.rm = TRUE)
-               & isFALSE(Becker)
-               & isFALSE(Lancefield), error = function(e) FALSE)) {
-    # to improve speed, special case for taxonomically correct full names (case-insensitive)
-    return(MO_lookup[match(gsub(".*(unknown ).*", "unknown name", tolower(x), perl = TRUE), MO_lookup$fullname_lower), "mo", drop = TRUE])
-  }
-
   # start off with replaced language-specific non-ASCII characters with ASCII characters
   x <- parse_and_convert(x)
   # replace mo codes used in older package versions
@@ -198,6 +191,13 @@ as.mo <- function(x,
   x[trimws2(x) %like% translate_AMR("no .*growth", language = language)] <- NA_character_
   x[trimws2(x) %like% paste0("^(", translate_AMR("no|not", language = language), ") [a-z]+")] <- "UNKNOWN"
   uncertainty_level <- translate_allow_uncertain(allow_uncertain)
+  
+  if (tryCatch(all(x == "" | gsub(".*(unknown ).*", "unknown name", tolower(x), perl = TRUE) %in% MO_lookup$fullname_lower, na.rm = TRUE)
+               & isFALSE(Becker)
+               & isFALSE(Lancefield), error = function(e) FALSE)) {
+    # to improve speed, special case for taxonomically correct full names (case-insensitive)
+    return(MO_lookup[match(gsub(".*(unknown ).*", "unknown name", tolower(x), perl = TRUE), MO_lookup$fullname_lower), "mo", drop = TRUE])
+  }
 
   if (!is.null(reference_df)
       && check_validity_mo_source(reference_df)
@@ -277,6 +277,10 @@ exec_as.mo <- function(x,
 
   check_dataset_integrity()
   
+  if (isTRUE(debug) && initial_search == TRUE) {
+    time_start_tracking()
+  }
+  
   lookup <- function(needle,
                      column = property,
                      haystack = reference_data_to_use,
@@ -295,7 +299,8 @@ exec_as.mo <- function(x,
     # `column` can be NULL for all columns, or a selection
     # returns a character (vector) - if `column` > length 1 then with columns as names
     if (isTRUE(debug_mode)) {
-      cat(font_silver("looking up: ", substitute(needle), collapse = ""))
+      cat(font_silver("Looking up: ", substitute(needle), collapse = ""), 
+          "\n           ", time_track())
     }
     if (length(column) == 1) {
       res_df <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
@@ -313,7 +318,7 @@ exec_as.mo <- function(x,
         NA_character_
       } else {
         if (isTRUE(debug_mode)) {
-          cat(font_green(paste0(" **MATCH** (", NROW(res_df), " results)\n")))
+          cat(font_green(paste0(" MATCH (", NROW(res_df), " results)\n")))
         }
         if ((length(res) > n | uncertainty > 1) & uncertainty != -1) {
           # save the other possible results as well, but not for forced certain results (then uncertainty == -1)
@@ -327,16 +332,20 @@ exec_as.mo <- function(x,
         res[seq_len(min(n, length(res)))]
       }
     } else {
-      if (isTRUE(debug_mode)) {
-        cat("\n")
-      }
       if (is.null(column)) {
         column <- names(haystack)
       }
       res <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
       res <- res[seq_len(min(n, nrow(res))), column, drop = TRUE]
       if (NROW(res) == 0) {
+        if (isTRUE(debug_mode)) {
+          cat(font_red(" (no rows)\n"))
+        }
         res <- rep(NA_character_, length(column))
+      } else {
+        if (isTRUE(debug_mode)) {
+          cat(font_green(paste0(" MATCH (", NROW(res), " rows)\n")))
+        }
       }
       res <- as.character(res)
       names(res) <- column
@@ -394,7 +403,7 @@ exec_as.mo <- function(x,
     check_validity_mo_source(reference_df)
     reference_df <- repair_reference_df(reference_df)
   }
-
+  
   # all empty
   if (all(identical(trimws(x_input), "") | is.na(x_input) | length(x) == 0)) {
     if (property == "mo") {
@@ -471,12 +480,12 @@ exec_as.mo <- function(x,
     x_backup[x_backup_untouched == "Fungi"] <- "Fungi" # is literally the kingdom
     
     # Fill in fullnames and MO codes at once
-    known_names <- x_backup %in% MO_lookup$fullname
+    known_names <- tolower(x_backup) %in% MO_lookup$fullname_lower
-    x[known_names] <- MO_lookup[match(x_backup[known_names], MO_lookup$fullname), property, drop = TRUE]
+    x[known_names] <- MO_lookup[match(tolower(x_backup)[known_names], MO_lookup$fullname_lower), property, drop = TRUE]
-    known_codes <- x_backup %in% MO_lookup$mo
+    known_codes <- toupper(x_backup) %in% MO_lookup$mo
-    x[known_codes] <- MO_lookup[match(x_backup[known_codes], MO_lookup$mo), property, drop = TRUE]
+    x[known_codes] <- MO_lookup[match(toupper(x_backup)[known_codes], MO_lookup$mo), property, drop = TRUE]
     already_known <- known_names | known_codes
-    
+
     # now only continue where the right taxonomic output is not already known
     if (any(!already_known)) {
       x_known <- x[already_known]
@@ -757,21 +766,24 @@ exec_as.mo <- function(x,
           # Streptococci, like GBS = Group B Streptococci (B_STRPT_GRPB)
           x[i] <- lookup(mo == toupper(gsub("g([abcdfghk])s",
                                             "B_STRPT_GRP\\1",
-                                            x_backup_without_spp[i])), uncertainty = -1)
+                                            x_backup_without_spp[i],
+                                            perl = TRUE)), uncertainty = -1)
           next
         }
         if (x_backup_without_spp[i] %like_case% "(streptococ|streptokok).* [abcdfghk]$") {
           # Streptococci in different languages, like "estreptococos grupo B"
           x[i] <- lookup(mo == toupper(gsub(".*(streptococ|streptokok|estreptococ).* ([abcdfghk])$",
                                             "B_STRPT_GRP\\2",
-                                            x_backup_without_spp[i])), uncertainty = -1)
+                                            x_backup_without_spp[i],
+                                            perl = TRUE)), uncertainty = -1)
           next
         }
         if (x_backup_without_spp[i] %like_case% "group [abcdfghk] (streptococ|streptokok|estreptococ)") {
           # Streptococci in different languages, like "Group A Streptococci"
           x[i] <- lookup(mo == toupper(gsub(".*group ([abcdfghk]) (streptococ|streptokok|estreptococ).*",
                                             "B_STRPT_GRP\\1",
-                                            x_backup_without_spp[i])), uncertainty = -1)
+                                            x_backup_without_spp[i],
+                                            perl = TRUE)), uncertainty = -1)
           next
         }
         if (x_backup_without_spp[i] %like_case% "haemoly.*strep") {
@@ -834,7 +846,7 @@ exec_as.mo <- function(x,
             # Salmonella Group A to Z, just return S. species for now
             x[i] <- lookup(genus == "Salmonella", uncertainty = -1)
             next
-          } else if (grepl("[sS]almonella [A-Z][a-z]+ ?.*", x_backup[i], ignore.case = FALSE) &
+          } else if (x_backup[i] %like_case% "[sS]almonella [A-Z][a-z]+ ?.*" &
                      !x_backup[i] %like% "t[iy](ph|f)[iy]") {
             # Salmonella with capital letter species like "Salmonella Goettingen" - they're all S. enterica
             # except for S. typhi, S. paratyphi, S. typhimurium
@@ -1099,7 +1111,7 @@ exec_as.mo <- function(x,
                 cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (3) look for genus only, part of name\n"))
               }
               if (nchar(g.x_backup_without_spp) > 4 & !b.x_trimmed %like_case% " ") {
-                if (!grepl("^[A-Z][a-z]+", b.x_trimmed, ignore.case = FALSE)) {
+                if (!b.x_trimmed %like_case% "^[A-Z][a-z]+") {
                   if (isTRUE(debug)) {
                     message("Running '", paste(b.x_trimmed, "species"), "'")
                   }
@@ -1414,6 +1426,10 @@ exec_as.mo <- function(x,
         close(progress)
       }
       
+      if (isTRUE(debug) && initial_search == TRUE) {
+        cat("Ended search", time_track(), "\n")
+      }
+      
       
       # handling failures ----
       failures <- failures[!failures %in% c(NA, NULL, NaN)]
@@ -1571,6 +1587,10 @@ exec_as.mo <- function(x,
     }
   }
   
+  if (isTRUE(debug) && initial_search == TRUE) {
+    cat("Finished function", time_track(), "\n")
+  }
+
   x
 }
 
@@ -1835,7 +1855,7 @@ print.mo_uncertainties <- function(x, ...) {
                                    width = 0.98 * getOption("width")),
                            collapse = "")
       # after strwrap, make taxonomic names italic
-      candidates <- gsub("([A-Za-z]+)", font_italic("\\1"), candidates)
+      candidates <- gsub("([A-Za-z]+)", font_italic("\\1"), candidates, perl = TRUE)
       candidates <- gsub(paste(font_italic(c("Also", "matched"), collapse = NULL), collapse = " "),
                          "Also matched",
                          candidates, fixed = TRUE)
@@ -1959,13 +1979,13 @@ parse_and_convert <- function(x) {
       if (NCOL(x) > 2) {
         stop("a maximum of two columns is allowed", call. = FALSE)
       } else if (NCOL(x) == 2) {
-        # support Tidyverse selection like: df %pm>% select(colA, colB)
+        # support Tidyverse selection like: df %>% select(colA, colB)
         # paste these columns together
         x <- as.data.frame(x, stringsAsFactors = FALSE)
         colnames(x) <- c("A", "B")
         x <- paste(x$A, x$B)
       } else {
-        # support Tidyverse selection like: df %pm>% select(colA)
+        # support Tidyverse selection like: df %>% select(colA)
         x <- as.data.frame(x, stringsAsFactors = FALSE)[[1]]
       }
     }
@@ -1973,6 +1993,8 @@ parse_and_convert <- function(x) {
     parsed <- iconv(x, to = "UTF-8")
     parsed[is.na(parsed) & !is.na(x)] <- iconv(x[is.na(parsed) & !is.na(x)], from = "Latin1", to = "ASCII//TRANSLIT")
     parsed <- gsub('"', "", parsed, fixed = TRUE)
+    parsed <- gsub(" +", " ", parsed, perl = TRUE)
+    parsed <- trimws(parsed)
   }, error = function(e) stop(e$message, call. = FALSE)) # this will also be thrown when running `as.mo(no_existing_object)`
   parsed
 }

R/mo_property.R

@@ -694,22 +694,22 @@ mo_property <- function(x, property = "fullname", language = get_locale(), ...)
 
 mo_validate <- function(x, property, language, ...) {
   check_dataset_integrity()
-  
-  if (tryCatch(all(x[!is.na(x)] %in% MO_lookup$mo) & length(list(...)) == 0, error = function(e) FALSE)) {
-    # special case for mo_* functions where class is already <mo>
-    return(MO_lookup[match(x, MO_lookup$mo), property, drop = TRUE])
-  }
-  
   dots <- list(...)
   Becker <- dots$Becker
-  if (is.null(Becker)) {
+  if (is.null(Becker) | property %in% c("kingdom", "phylum", "class", "order", "family", "genus")) {
     Becker <- FALSE
   }
   Lancefield <- dots$Lancefield
-  if (is.null(Lancefield)) {
+  if (is.null(Lancefield) | property %in% c("kingdom", "phylum", "class", "order", "family", "genus")) {
     Lancefield <- FALSE
   }
+  has_Becker_or_Lancefield <- Becker %in% c(TRUE, "all") | Lancefield %in% c(TRUE, "all")
   
+  if (tryCatch(all(x[!is.na(x)] %in% MO_lookup$mo) & !has_Becker_or_Lancefield, error = function(e) FALSE)) {
+    # special case for mo_* functions where class is already <mo>
+    return(MO_lookup[match(x, MO_lookup$mo), property, drop = TRUE])
+  }
+
   # try to catch an error when inputting an invalid argument
   # so the 'call.' can be set to FALSE
   tryCatch(x[1L] %in% MO_lookup[1, property, drop = TRUE],
@@ -722,8 +722,7 @@ mo_validate <- function(x, property, language, ...) {
     # because it's already a valid MO
     x <- exec_as.mo(x, property = property, initial_search = FALSE, language = language, ...)
   } else if (!all(x %in% MO_lookup[, property, drop = TRUE])
-             | Becker %in% c(TRUE, "all")
+             | has_Becker_or_Lancefield) {
-             | Lancefield %in% c(TRUE, "all")) {
     x <- exec_as.mo(x, property = property, language = language, ...)
   }
   

data-raw/_internals.R

@@ -51,18 +51,19 @@ create_species_cons_cops <- function(type = c("CoNS", "CoPS")) {
                                            "lentus", "lugdunensis", "massiliensis", "microti",
                                            "muscae", "nepalensis", "pasteuri", "petrasii",
                                            "pettenkoferi", "piscifermentans", "pseudoxylosus",
-                                           "rostri", "saccharolyticus", "saprophyticus",
+                                           "pulvereri", "rostri", "saccharolyticus", "saprophyticus",
                                            "sciuri", "simulans", "stepanovicii", "succinus",
-                                           "vitulinus", "warneri", "xylosus")
+                                           "vitulinus", "vitulus", "warneri", "xylosus")
                    | (MO_staph$species == "schleiferi" & MO_staph$subspecies %in% c("schleiferi", ""))),
              "mo", drop = TRUE]
   } else if (type == "CoPS") {
     MO_staph[which(MO_staph$species %in% c("coagulase-positive",
-                                           "simiae", "agnetis",
+                                           "agnetis", "argenteus",
+                                           "cornubiensis",
                                            "delphini", "lutrae",
                                            "hyicus", "intermedius",
                                            "pseudintermedius", "pseudointermedius",
-                                           "schweitzeri", "argenteus")
+                                           "schweitzeri", "simiae")
                    | (MO_staph$species == "schleiferi" & MO_staph$subspecies == "coagulans")),
              "mo", drop = TRUE]
   }

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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</span>
       </span>
     </div>
 

docs/articles/benchmarks.html

@@ -39,7 +39,7 @@
       </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">1.5.0</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</span>
       </span>
     </div>
 
@@ -225,36 +225,22 @@
   <span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VISA"</span><span class="op">)</span>, <span class="co"># Vancomycin Intermediate S. aureus</span>
   <span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VRSA"</span><span class="op">)</span>, <span class="co"># Vancomycin Resistant S. aureus</span>
   times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
-<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
+<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
-<span class="co">#                                   expr    min     lq   mean median     uq  max</span>
+<span class="co">#                                   expr   min    lq  mean median    uq max neval</span>
-<span class="co">#                           as.mo("sau")   13.0   14.0   25.0   15.0   44.0   65</span>
+<span class="co">#                           as.mo("sau")  11.0  12.0  27.0   13.0  49.0  51    10</span>
-<span class="co">#                          as.mo("stau")  120.0  130.0  140.0  140.0  160.0  160</span>
+<span class="co">#                          as.mo("stau")  53.0  57.0  76.0   74.0  93.0 100    10</span>
-<span class="co">#                          as.mo("STAU")  120.0  130.0  150.0  160.0  160.0  180</span>
+<span class="co">#                          as.mo("STAU")  53.0  54.0  69.0   56.0  58.0 190    10</span>
-<span class="co">#                        as.mo("staaur")   13.0   13.0   14.0   14.0   14.0   15</span>
+<span class="co">#                        as.mo("staaur")  11.0  12.0  21.0   13.0  42.0  44    10</span>
-<span class="co">#                        as.mo("STAAUR")   13.0   14.0   17.0   15.0   15.0   43</span>
+<span class="co">#                        as.mo("STAAUR")  11.0  12.0  16.0   13.0  14.0  48    10</span>
-<span class="co">#                     as.mo("S. aureus")   30.0   32.0   45.0   34.0   62.0   68</span>
+<span class="co">#                     as.mo("S. aureus")  27.0  27.0  38.0   32.0  35.0  75    10</span>
-<span class="co">#                      as.mo("S aureus")   31.0   34.0   42.0   35.0   61.0   63</span>
+<span class="co">#                      as.mo("S aureus")  27.0  29.0  38.0   30.0  36.0  73    10</span>
-<span class="co">#         as.mo("Staphylococcus aureus")    2.5    2.6    2.8    2.8    2.9    3</span>
+<span class="co">#         as.mo("Staphylococcus aureus")   3.1   3.2   6.9    3.5   3.7  38    10</span>
-<span class="co">#  as.mo("Staphylococcus aureus (MRSA)") 1200.0 1200.0 1200.0 1200.0 1200.0 1200</span>
+<span class="co">#  as.mo("Staphylococcus aureus (MRSA)") 250.0 260.0 270.0  260.0 280.0 290    10</span>
-<span class="co">#       as.mo("Sthafilokkockus aaureuz")  550.0  560.0  570.0  560.0  570.0  610</span>
+<span class="co">#       as.mo("Sthafilokkockus aaureuz") 160.0 200.0 200.0  200.0 210.0 230    10</span>
-<span class="co">#                          as.mo("MRSA")   13.0   13.0   17.0   15.0   15.0   42</span>
+<span class="co">#                          as.mo("MRSA")  10.0  11.0  12.0   11.0  13.0  14    10</span>
-<span class="co">#                          as.mo("VISA")   21.0   22.0   26.0   23.0   23.0   52</span>
+<span class="co">#                          as.mo("VISA")  19.0  20.0  26.0   22.0  24.0  61    10</span>
-<span class="co">#                          as.mo("VRSA")   21.0   23.0   35.0   24.0   52.0   54</span>
+<span class="co">#                          as.mo("VRSA")  19.0  20.0  24.0   21.0  22.0  56    10</span></code></pre></div>
-<span class="co">#  neval</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span>
-<span class="co">#     10</span></code></pre></div>
 <p><img src="benchmarks_files/figure-html/unnamed-chunk-4-1.png" width="562.5"></p>
 <p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. It is clear that accepted taxonomic names are extremely fast, but some variations can take up to 500-1000 times as much time.</p>
 <p>To improve performance, two important calculations take almost no time at all: <strong>repetitive results</strong> and <strong>already precalculated results</strong>.</p>
@@ -281,11 +267,11 @@
 <span class="co"># now let's see:</span>
 <span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span><span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="va">x</span><span class="op">)</span>,
                          times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
-<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
+<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#        expr min  lq mean median  uq max neval</span>
-<span class="co">#  mo_name(x) 141 180  218    207 245 312    10</span></code></pre></div>
+<span class="co">#  mo_name(x) 137 146  178    172 193 282    10</span></code></pre></div>
-<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.207 seconds. You only lose time on your unique input values.</p>
+<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.172 seconds. You only lose time on your unique input values.</p>
 </div>
 <div id="precalculated-results" class="section level3">
 <h3 class="hasAnchor">
@@ -296,13 +282,13 @@
                          B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"S. aureus"</span><span class="op">)</span>,
                          C <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"Staphylococcus aureus"</span><span class="op">)</span>,
                          times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
-<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
+<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#  expr   min    lq  mean median    uq   max neval</span>
-<span class="co">#     A  8.76  8.96  9.39   9.31  9.86 10.10    10</span>
+<span class="co">#     A  7.12  7.56  7.89    7.7  8.39  8.69    10</span>
-<span class="co">#     B 27.60 28.20 33.00  28.90 29.40 71.20    10</span>
+<span class="co">#     B 23.90 24.50 35.10   24.8 27.40 77.50    10</span>
-<span class="co">#     C  2.28  2.32  2.47   2.45  2.48  2.85    10</span></code></pre></div>
+<span class="co">#     C  1.73  1.84  1.95    1.9  2.09  2.36    10</span></code></pre></div>
-<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0025 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
+<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0019 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
 <div class="sourceCode" id="cb5"><pre class="downlit sourceCode r">
 <code class="sourceCode R"><span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span>A <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_species</a></span><span class="op">(</span><span class="st">"aureus"</span><span class="op">)</span>,
                          B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_genus</a></span><span class="op">(</span><span class="st">"Staphylococcus"</span><span class="op">)</span>,
@@ -313,17 +299,17 @@
                          G <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_phylum</a></span><span class="op">(</span><span class="st">"Firmicutes"</span><span class="op">)</span>,
                          H <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_kingdom</a></span><span class="op">(</span><span class="st">"Bacteria"</span><span class="op">)</span>,
                          times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
-<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
+<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#  expr  min   lq mean median   uq  max neval</span>
-<span class="co">#     A 1.91 1.95 2.06   1.99 2.09 2.62    10</span>
+<span class="co">#     A 1.54 1.57 1.73   1.69 1.88 2.00    10</span>
-<span class="co">#     B 1.83 1.91 2.09   2.04 2.20 2.45    10</span>
+<span class="co">#     B 1.51 1.52 1.75   1.70 1.86 2.41    10</span>
-<span class="co">#     C 1.79 1.90 2.03   1.99 2.22 2.30    10</span>
+<span class="co">#     C 1.55 1.60 1.70   1.70 1.81 1.86    10</span>
-<span class="co">#     D 1.90 2.01 2.18   2.12 2.25 2.71    10</span>
+<span class="co">#     D 1.55 1.59 1.71   1.66 1.83 1.94    10</span>
-<span class="co">#     E 1.91 2.02 2.14   2.08 2.15 2.81    10</span>
+<span class="co">#     E 1.50 1.55 1.68   1.61 1.78 2.10    10</span>
-<span class="co">#     F 1.86 1.92 2.00   2.01 2.06 2.16    10</span>
+<span class="co">#     F 1.51 1.62 1.75   1.79 1.82 2.02    10</span>
-<span class="co">#     G 1.81 1.96 2.09   2.08 2.22 2.41    10</span>
+<span class="co">#     G 1.52 1.53 1.68   1.60 1.80 2.02    10</span>
-<span class="co">#     H 1.90 1.93 2.05   2.00 2.22 2.29    10</span></code></pre></div>
+<span class="co">#     H 1.53 1.54 1.63   1.60 1.67 1.84    10</span></code></pre></div>
 <p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> anyway, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.</p>
 </div>
 <div id="results-in-other-languages" class="section level3">
@@ -348,16 +334,16 @@
                          fr <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"fr"</span><span class="op">)</span>,
                          pt <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"pt"</span><span class="op">)</span>,
                          times <span class="op">=</span> <span class="fl">100</span><span class="op">)</span>
-<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
+<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
-<span class="co">#  expr   min    lq  mean median    uq   max neval</span>
+<span class="co">#  expr   min    lq  mean median    uq    max neval</span>
-<span class="co">#    en 17.45 18.01 19.69  18.53 19.14 55.30   100</span>
+<span class="co">#    en 17.38 17.71 25.63  18.11 19.75  81.61   100</span>
-<span class="co">#    de 20.58 21.54 26.69  22.08 23.96 67.16   100</span>
+<span class="co">#    de 20.14 20.61 24.87  20.91 21.57  85.23   100</span>
-<span class="co">#    nl 33.79 34.67 39.13  35.39 36.72 74.60   100</span>
+<span class="co">#    nl 25.02 25.46 28.40  25.83 26.58  78.47   100</span>
-<span class="co">#    es 20.71 21.42 24.36  21.88 22.65 58.57   100</span>
+<span class="co">#    es 19.90 20.41 24.86  20.77 21.78  81.38   100</span>
-<span class="co">#    it 20.65 21.18 26.50  21.53 22.68 61.96   100</span>
+<span class="co">#    it 20.01 20.44 24.40  20.80 21.57  76.08   100</span>
-<span class="co">#    fr 20.68 21.27 25.05  21.64 22.37 58.82   100</span>
+<span class="co">#    fr 19.85 20.23 29.97  20.89 23.56 192.40   100</span>
-<span class="co">#    pt 20.69 21.44 24.36  21.94 22.99 59.66   100</span></code></pre></div>
+<span class="co">#    pt 19.90 20.26 26.53  20.75 22.56  85.69   100</span></code></pre></div>
 <p>Currently supported are German, Dutch, Spanish, Italian, French and Portuguese.</p>
 </div>
   </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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</span>
       </span>
     </div>
 

docs/index.html

@@ -43,7 +43,7 @@
       </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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</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-1509020" class="section level1">
+    <div id="amr-1509023" class="section level1">
-<h1 class="page-header" data-toc-text="1.5.0.9020">
+<h1 class="page-header" data-toc-text="1.5.0.9023">
-<a href="#amr-1509020" class="anchor"></a>AMR 1.5.0.9020<small> Unreleased </small>
+<a href="#amr-1509023" class="anchor"></a>AMR 1.5.0.9023<small> Unreleased </small>
 </h1>
-<div id="last-updated-18-february-2021" class="section level2">
+<div id="last-updated-21-february-2021" class="section level2">
 <h2 class="hasAnchor">
-<a href="#last-updated-18-february-2021" class="anchor"></a><small>Last updated: 18 February 2021</small>
+<a href="#last-updated-21-february-2021" class="anchor"></a><small>Last updated: 21 February 2021</small>
 </h2>
 <div id="new" class="section level3">
 <h3 class="hasAnchor">
@@ -326,6 +326,9 @@
 </li>
 <li>Improved speed and reliability of <code><a href="../reference/guess_ab_col.html">guess_ab_col()</a></code>. As this also internally improves the reliability of <code><a href="../reference/first_isolate.html">first_isolate()</a></code> and <code><a href="../reference/mdro.html">mdro()</a></code>, this might have a slight impact on the results of those functions.</li>
 <li>Fix for <code><a href="../reference/mo_property.html">mo_name()</a></code> when used in other languages than English</li>
+<li>The <code><a href="../reference/like.html">like()</a></code> function (and its fast alias <code><a href="../reference/like.html">%like%</a></code>) now always use Perl compatibility, improving speed for many functions in this package (e.g., <code><a href="../reference/as.mo.html">as.mo()</a></code> is now up to 4 times faster)</li>
+<li>
+<em>Staphylococcus cornubiensis</em> is now correctly categorised as coagulase-positive</li>
 </ul>
 </div>
 <div id="other" class="section level3">

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: 2021-02-18T22:21Z
+last_built: 2021-02-21T22:18Z
 urls:
   reference: https://msberends.github.io/AMR//reference
   article: https://msberends.github.io/AMR//articles

docs/reference/antibiotic_class_selectors.html

@@ -83,7 +83,7 @@
       </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">1.5.0.9019</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</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">1.5.0.9016</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
       </span>
     </div>
 
@@ -277,7 +277,7 @@
 <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>Tries again with <code>perl = TRUE</code> if regex fails</p></li>
+<li><p>Always uses compatibility with Perl</p></li>
 </ul>
 
 <p>Using RStudio? The text <code>%like%</code> can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like <code>Ctrl+Shift+L</code> or <code>Cmd+Shift+L</code> (see <code>Tools</code> &gt; <code>Modify Keyboard Shortcuts...</code>).</p>

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">1.5.0.9020</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9023</span>
       </span>
     </div>
 

man/like.Rd

@@ -34,7 +34,7 @@ The \verb{\%like\%} function:
 \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 Tries again with \code{perl = TRUE} if regex fails
+\item Always uses compatibility with Perl
 }
 
 Using RStudio? The text \verb{\%like\%} can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like \code{Ctrl+Shift+L} or \code{Cmd+Shift+L} (see \code{Tools} > \verb{Modify Keyboard Shortcuts...}).

tests/testthat/test-data.R

@@ -86,3 +86,13 @@ test_that("CoL version info works", {
   
   expect_output(print(catalogue_of_life_version()))
 })
+
+test_that("CoNS/CoPS are up to date", {
+  uncategorised <- subset(microorganisms,
+                          genus == "Staphylococcus" &
+                            !species %in% c("", "aureus") &
+                            !mo %in% c(MO_CONS, MO_COPS))
+  expect(NROW(uncategorised) == 0,
+         failure_message = paste0("Staphylococcal species not categorised as CoNS/CoPS: S. ",
+                                  uncategorised$species, " (", uncategorised$mo, ")"))
+})

vignettes/benchmarks.Rmd

@@ -19,7 +19,7 @@ knitr::opts_chunk$set(
   fig.width = 7.5,
   fig.height = 4.5,
   dpi = 75
-) 
+)
 ```
 
 One of the most important features of this package is the complete microbial taxonomic database, supplied by the [Catalogue of Life](http://catalogueoflife.org). We created a function `as.mo()` that transforms any user input value to a valid microbial ID by using intelligent rules combined with the taxonomic tree of Catalogue of Life.