From 258fd070ef99854922a61d1979d2ce26cf8eb8db Mon Sep 17 00:00:00 2001
From: Bryan Roessler <bryanroessler@gmail.com>
Date: Mon, 22 Jul 2024 16:33:35 -0400
Subject: [PATCH] Make functional

---
 workflow/script-run-workflow | 84 ++++++++++++++++++++++--------------
 1 file changed, 52 insertions(+), 32 deletions(-)

diff --git a/workflow/script-run-workflow b/workflow/script-run-workflow
index 9ef33075..98fa4c2f 100755
--- a/workflow/script-run-workflow
+++ b/workflow/script-run-workflow
@@ -138,7 +138,6 @@ parse_input() {
   fi
 }
 
-
 # @section Helper functions
 # @internal
 module() { 
@@ -188,9 +187,9 @@ install_dependencies() {
   debug "Running: ${FUNCNAME[0]}" "$@"
 
   # Dependency arrays
-  depends_rpm=(graphviz pandoc pdftk-java gd-devel)
-  depends_deb=(graphviz pandoc pdftk-java libgd-dev)
-  depends_brew=(graphiz pandoc gd pdftk-java)
+  depends_rpm=(graphviz pandoc pdftk-java gd-devel shdoc)
+  depends_deb=(graphviz pandoc pdftk-java libgd-dev shdoc)
+  depends_brew=(graphiz pandoc gd pdftk-java shdoc)
   depends_perl=(File::Map ExtUtils::PkgConfig GD GO::TermFinder)
   depends_r=(BiocManager ontologyIndex ggrepel tidyverse sos openxlsx ggplot2 
     plyr extrafont gridExtra gplots stringr plotly ggthemes pandoc rmarkdown)
@@ -501,11 +500,8 @@ py_gtf() {
     shopt -u nullglob
 
     for s in "${set2[@]}"; do
-      echo "$PERL analyze_v2.pl -an gene_association.sgd -as P -o gene_ontology_edit.obo -b $set1 $s"
-      echo "TODO: analyze_v2.pl should be translated"
-      "$PERL" analyze_v2.pl -an gene_association.sgd -as P -o gene_ontology_edit.obo -b "$set1" "$s"
-      echo "$PERL terms2tsv_v4.pl $s.terms > $s.tsv"
-      echo "TODO: terms2tsv_v4.pl should be translated"
+      pl_analyze "$set1" "$s"
+      pl_terms2tsv "$s"
 		  "$PERL" terms2tsv_v4.pl "$s.terms" > "$s.tsv"
     done
 
@@ -518,36 +514,59 @@ py_gtf() {
     popd || return 1
   }
 
-
-  
-  # @description Perl analyze submodule
-  # @arg $1 string "Set 1"
-  # @arg $@ string
-  pl_analyze() {
-    :
-
-
-  }
-
-
-  pl_terms2tsv() {
-    :
-
-
-
-  }
-
-
-
   # Perform operations in each directory
   for d in "$process_dir" "$function_dir" "$component_dir"; do 
     set1="ORF_List_Without_DAmPs.txt"
     out_file="${d##*/}Results.txt" # Use the dirname to create each Results filename
     _process "$d" & # parallelize
   done
-
 }
 
+
+submodule pl_analyze
+# @description Perl analyze submodule
+# This seems weird to me because we're just overwriting the same data for all set2 members
+# https://metacpan.org/dist/GO-TermFinder/view/examples/analyze.pl
+# Is there a reason you need a custom version and not the original from cpan?
+# @arg $1 string Set 1
+# @arg $2 string Set 2
+pl_analyze() {
+  script="analyze_v2.pl"
+  an="gene_association.sgd"
+  out_file="gene_ontology_edit.obo"
+  debug "$PERL $script -an $an -as P -o $out_file -b $1 $2"
+  "$PERL" "$script" -an "$an" -as P -o "$out_file" -b "$1" "$2"
+}
+
+
+submodule pl_terms2tsv
+# @description Perl terms2tsv submodule
+# Probably should be translated to shell/python
+# @arg $1 string Set 2
+pl_terms2tsv() {
+  script="terms2tsv_v4.pl"
+  debug "$PERL $script $1.terms > $1.tsv"
+  "$PERL" "$script" "$1.terms" > "$1.tsv"
+}
+
+
+submodule documentation
+# @section Documentation
+# @description Generates markdown documentation from this script using shdoc
+documentation() {
+  debug "Running: ${FUNCNAME[0]}"
+
+  # Print markdown to stdout
+  shdoc < "$SCRIPT"
+
+  # Create markdown file
+  shdoc < "$SCRIPT" > documentation.md
+  
+}
+
+
+
+
 # @description Compile GTF in R
 r_compile_gtf() {
   debug "Running: ${FUNCNAME[0]}"
@@ -564,7 +583,8 @@ main() {
   debug "Running: ${FUNCNAME[0]}" "$@"
   
   # Where are we located?
-  SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+  SCRIPT=$(realpath -s "${BASH_SOURCE[0]}")
+  SCRIPT_DIR=$(dirname "$SCRIPT")
 
   # Set the automatic project directory prefix
   PROJECT_PREFIX="$(whoami)_$(date +%y_%m_%d)"