Add sir.R/mic.R fixes and mdro() unit tests; bump to 3.0.1.9030

R/sir.R (line 571):
  Guard purely numeric strings (e.g. "1", "8") from the Unicode letter
  filter. Values matching the broad SIR regex but consisting only of digits
  must not be stripped; add `x %unlike% "^[0-9+]$"` predicate.

R/mic.R (lines 220-222):
  Preserve the letter 'e' during Unicode-letter removal so that MIC values
  in scientific notation (e.g. "1e-3", "2.5e-2") survive the cleaning step.
  - Line 220: [\\p{L}] → [^e\\P{L}]  (remove all letters except 'e')
  - Line 222: [^0-9.><= -]+ → [^0-9e.><= -]+  (allow 'e' in whitelist)

tests/testthat/test-mdro.R:
  New tests for the drug+inhibitor inference added in the previous commit
  (issue #209):
  - TZP=R with no PIP column → PIP inferred R → MDRO class elevated
  - TZP=S with no PIP column → proxy col is NA (not S) → class lower
  - verbose mode emits "Inferring resistance" message
  - AMC=R with no AMX column runs without error (Enterococcus faecium)

https://claude.ai/code/session_01Cp154UtssHg84bw38xiiTG

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: AMR
-Version: 3.0.1.9029
+Version: 3.0.1.9030
 Date: 2026-03-06
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 3.0.1.9029
+# AMR 3.0.1.9030
 
 ### New
 * Integration with the **tidymodels** framework to allow seamless use of SIR, MIC and disk data in modelling pipelines via `recipes`
@@ -19,6 +19,8 @@
 
 ### Fixes
 * `mdro()`: when a base beta-lactam drug column is missing but a corresponding drug+inhibitor combination is present in the data and resistant (e.g., piperacillin/tazobactam = R while piperacillin is absent), the base drug is now correctly inferred as resistant. This ensures MDRO classification is not missed due to test-ordering differences in the laboratory. The reverse direction is also valid: susceptibility in a combination does not imply susceptibility in the base drug (the inhibitor may be responsible), so only resistance is propagated. Closes #209
+* Fixed a bug in `as.sir()` where values that were purely numeric (e.g., `"1"`) and matched the broad SIR-matching regex would be incorrectly stripped of all content by the Unicode letter filter
+* Fixed a bug in `as.mic()` where MIC values in scientific notation (e.g., `"1e-3"`) were incorrectly handled because the letter `e` was removed along with other Unicode letters; scientific notation `e` is now preserved
 * Fixed a bug in `as.ab()` where certain AB codes containing "PH" or "TH" (such as `ETH`, `MTH`, `PHE`, `PHN`, `STH`, `THA`, `THI1`) would incorrectly return `NA` when combined in a vector with any untranslatable value (#245)
 * Fixed a bug in `antibiogram()` for when no antimicrobials are set
 * Fixed a bug in `as.sir()` where for numeric input the arguments `S`,  `I`,  and `R` would not be considered (#244)

R/mic.R

@@ -217,9 +217,9 @@ as.mic <- function(x, na.rm = FALSE, keep_operators = "all", round_to_next_log2
     warning_("Some MICs were combined values, only the first values are kept")
     x[x %like% "[0-9]/.*[0-9]"] <- gsub("/.*", "", x[x %like% "[0-9]/.*[0-9]"])
   }
-  x <- trimws2(gsub("[\\p{L}]", "", x, perl = TRUE)) # \p{L} is the Unicode category for all letters, including those with diacritics
+  x <- trimws2(gsub("[^e\\P{L}]", "", x, perl = TRUE)) # \p{L} is the Unicode category for all letters, including those with diacritics
   # remove other invalid characters
-  x <- gsub("[^0-9.><= -]+", "", x, perl = TRUE)
+  x <- gsub("[^0-9e.><= -]+", "", x, perl = TRUE)
   # transform => to >= and =< to <=
   x <- gsub("=<", "<=", x, fixed = TRUE)
   x <- gsub("=>", ">=", x, fixed = TRUE)

R/sir.R

@@ -568,7 +568,7 @@ as.sir.default <- function(x,
     x[x %like% "dose"] <- "SDD"
     mtch <- grepl(paste0("(", S, "|", I, "|", R, "|", NI, "|", SDD, "|", WT, "|", NWT, "|", NS, "|[A-Z]+)"), x, perl = TRUE)
     x[!mtch] <- ""
-    x[mtch] <- trimws2(gsub("[^\\p{L}]", "", x[mtch], perl = TRUE)) # \p{L} is the Unicode category for all letters, including those with diacritics
+    x[mtch & x %unlike% "^[0-9+]$"] <- trimws2(gsub("[^\\p{L}]", "", x[mtch & x %unlike% "^[0-9+]$"], perl = TRUE)) # \p{L} is the Unicode category for all letters, including those with diacritics
     # apply regexes set by user
     x[x %like% S] <- "S"
     x[x %like% I] <- "I"

tests/testthat/test-mdro.R

@@ -296,4 +296,53 @@ test_that("test-mdro.R", {
     expect_output(x <- mdro(example_isolates %>% group_by(ward), info = TRUE, pct_required_classes = 0))
     expect_output(x <- mdro(example_isolates %>% group_by(ward), guideline = custom, info = TRUE))
   }
+
+  # drug+inhibitor inference for missing base drug columns (issue #209) -------
+  # Resistance in drug+inhibitor always implies resistance in the base drug.
+  # If PIP (piperacillin) is absent but TZP (piperacillin/tazobactam) is R,
+  # the base drug must be R -> MDRO classification should not be missed.
+  pseud_no_pip <- data.frame(
+    mo  = as.mo("Pseudomonas aeruginosa"),
+    TZP = as.sir("R"), # piperacillin/tazobactam present; no PIP column
+    IPM = as.sir("R"),
+    MEM = as.sir("R"),
+    CAZ = as.sir("R"),
+    FEP = as.sir("R"),
+    CIP = as.sir("R"),
+    GEN = as.sir("R"),
+    TOB = as.sir("R"),
+    AMK = as.sir("R"),
+    COL = as.sir("S"),
+    stringsAsFactors = FALSE
+  )
+  # With TZP=R, PIP should be inferred R; result should be XDR or PDR (integer > 2)
+  result_no_pip <- suppressMessages(suppressWarnings(mdro(pseud_no_pip, guideline = "EUCAST", info = FALSE)))
+  expect_true(as.integer(result_no_pip$MDRO) > 1L)
+
+  # Susceptibility in combination must NOT be propagated to base drug
+  # (the inhibitor may be responsible; we cannot conclude PIP=S from TZP=S)
+  pseud_tzp_s <- pseud_no_pip
+  pseud_tzp_s$TZP <- as.sir("S")
+  result_tzp_s <- suppressMessages(suppressWarnings(mdro(pseud_tzp_s, guideline = "EUCAST", info = FALSE)))
+  # Proxy column is NA (not S), so the classification should be lower than when TZP=R
+  expect_true(as.integer(result_tzp_s$MDRO) < as.integer(result_no_pip$MDRO))
+
+  # verbose mode should emit an inference message when a proxy column is created
+  expect_output(
+    suppressMessages(suppressWarnings(mdro(pseud_no_pip, guideline = "EUCAST", info = FALSE, verbose = TRUE))),
+    regexp = "Inferring resistance"
+  )
+
+  # Multiple combos for the same base drug: AMX can come from AMC (amoxicillin/clavulanic acid)
+  ente_no_amx <- data.frame(
+    mo  = as.mo("Enterococcus faecium"),
+    AMC = as.sir("R"), # amoxicillin/clavulanic acid; no AMX column
+    VAN = as.sir("R"),
+    TEC = as.sir("R"),
+    LNZ = as.sir("R"),
+    DAP = as.sir("R"),
+    stringsAsFactors = FALSE
+  )
+  # Should run without error and return a data.frame; AMX inferred R from AMC
+  expect_inherits(suppressMessages(suppressWarnings(mdro(ente_no_amx, guideline = "EUCAST", info = FALSE))), "data.frame")
 })