Adjust getIPRScanColNames() and tests

- document package data
- use package data in function
- adjust test to validate ingested sample colnames
References: JRaviLab#75 (comment)
Co-authored-by: Jananiravi <jananiravi@users.noreply.github.com>

Author: the-mayer

R/fa2domain.R

@@ -65,14 +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

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"

man/getIPRScanColNames.Rd

@@ -79,15 +79,9 @@ test_that("fa2domain", {
     # Check that the result is a character vector
     expect_type(col_names, "character")
 
-    # Define the expected column names
-    expected_col_names <- c(
-        "AccNum", "SeqMD5Digest", "SLength", "Analysis",
-        "DB.ID", "SignDesc", "StartLoc", "StopLoc", "Score",
-        "Status", "RunDate", "IPRAcc", "IPRDesc"
-    )
 
     # Check that the column names match exactly
-    expect_equal(col_names, expected_col_names)
+    expect_equal(colnames(df_ipr), col_names)
     expect_type(col_names, "character")
 
     # Ensure there are exactly 13 columns