add unit tests to fa2domain

DESCRIPTION

@@ -27,7 +27,7 @@ Depends:
     R (>= 4.4.0)
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 VignetteBuilder: knitr
 Imports: 
     ape,
@@ -83,4 +83,7 @@ Imports:
     XVector,
     yaml
 Suggests:
-    knitr
+    knitr,
+    testthat,
+    mockery,
+    readr

R/fa2domain.R

@@ -35,6 +35,16 @@ runIPRScan <- function(
         # destPartition = "LocalQ",
         # destQoS = "shortjobs"
     ) {
+    # Validate inputs
+    if (is.null(filepath_fasta) || filepath_fasta == "") {
+        stop("filepath_fasta cannot be NULL or empty")
+    }
+    if (is.null(filepath_out) || filepath_out == "") {
+        stop("filepath_out cannot be NULL or empty")
+    }
+    if (!all(appl %in% c("Pfam", "Gene3D"))) {
+        stop("Invalid IPRscan analyses specified")
+    }
     # construct interproscan command
     cmd_iprscan <- stringr::str_glue(
         "iprscan -i {filepath_fasta} -b {filepath_out} --cpu 4 -f TSV ",
@@ -55,14 +65,10 @@ runIPRScan <- function(
 #' (based upon the global variable written in
 #' molevol_scripts/R/colnames_molevol.R)
 #'
-#' @return [chr] interproscan column names used throughout molevolvr
+#' @return [chr] interproscan column names used throughout MolEvolvR
 getIPRScanColNames <- function() {
-    column_names <- c(
-        "AccNum", "SeqMD5Digest", "SLength", "Analysis",
-        "DB.ID", "SignDesc", "StartLoc", "StopLoc", "Score",
-        "Status", "RunDate", "IPRAcc", "IPRDesc"
-    )
-    return(column_names)
+    data("ipr_colnames", package = "MolEvolvR", envir = environment())
+    ipr_colnames
 }
 
 #' construct column types for reading interproscan output TSVs
@@ -296,7 +302,7 @@ getDomainsFromFA <- function(
                 if (verbose) {
                     msg <- stringr::str_glue(
                         "accession number: {header} had no domains for the ",
-                        "selected analyes: {paste(analysis, collapse = ',')}\n"
+                        "selected analyses: {paste(analysis, collapse = ',')}\n"
                     )
                     warning(msg)
                 }

R/ipr_colnames.R

@@ -0,0 +1,28 @@
+#' InterProScan Column Names
+#'
+#' A character vector containing the expected column names from an
+#' InterProScan output table. This dataset is useful for validating,
+#' parsing, or reconstructing data frames produced by InterProScan.
+#'
+#' @format A character vector with 13 elements:
+#' \describe{
+#'   \item{AccNum}{Accession number of the sequence.}
+#'   \item{SeqMD5Digest}{MD5 digest of the sequence.}
+#'   \item{SLength}{Length of the sequence.}
+#'   \item{Analysis}{Type of analysis or database used (e.g., Pfam, SMART).}
+#'   \item{DB.ID}{Database-specific identifier.}
+#'   \item{SignDesc}{Description of the signature or domain.}
+#'   \item{StartLoc}{Start position of the match on the sequence.}
+#'   \item{StopLoc}{Stop position of the match on the sequence.}
+#'   \item{Score}{Score assigned to the match (if applicable).}
+#'   \item{Status}{Status of the analysis (e.g., OK, WARNING).}
+#'   \item{RunDate}{Date the InterProScan analysis was run.}
+#'   \item{IPRAcc}{InterPro accession number.}
+#'   \item{IPRDesc}{InterPro entry description.}
+#' }
+#'
+#' @source Generated internally to represent standard InterProScan output fields.
+#' @examples
+#' data(ipr_colnames)
+#' ipr_colnames
+"ipr_colnames"

tests/testthat.R

@@ -0,0 +1,4 @@
+library(testthat)
+library(MolEvolvR)
+
+test_check("MolEvolvR")