From a8547a5f8ef7b2f608ab963a4917668c2055cd6b5bd26cb87d3afba2aed912b7 Mon Sep 17 00:00:00 2001
From: Techognito <techognito@noreply.localhost>
Date: Fri, 15 Aug 2025 19:15:19 +0200
Subject: [PATCH] More improvements to the cleaner

- It will now get sort all rolltables in seperate files (including the last one)
- WIP improving search for titles not being a 100% match (e.g. "Male
  Names Table #1" needs to match "Male Names -Table #1")
- todo still is cleanting up the seperate files being made, might add as
  step1 file instead
---
 step-0-Cleaner.sh | 55 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 39 insertions(+), 16 deletions(-)

diff --git a/step-0-Cleaner.sh b/step-0-Cleaner.sh
index 9314264..55f0ec6 100644
--- a/step-0-Cleaner.sh
+++ b/step-0-Cleaner.sh
@@ -1,40 +1,63 @@
 #!/bin/bash
-infile=""
-outfile=""
-titleFile=""
-outpath=""
+infile="bookofrandomtables1.txt"
+cleanFile="clean-$infile"
+titleFile="titles-$infile"
+outpath='./Step-1'
 
 getTitles() {
-	cat $infile | \
-		grep -A $(wc -l $_ | \
+	cat $cleanFile | \
+		grep -A $(wc -l $infile | \
 		awk '{print $1}') "Table of Contents" | \
-		grep -B $(wc -l $_ | \
+		grep -B $(wc -l $infile | \
 		awk '{print $1}') "How to Use this Book" | \
 		grep -E "[\ \#\-\,\&\'\`\´\’\–A-Za-z0-9_]{1,999}\.{1,}" | \
 		grep -v "Credits" | \
 		grep -v "How to Use this Book" | \
-		grep -Eo "^[\ \#\ffi\-\,\&\'\`\´\’\–A-Za-z0-9_]{1,999}[^.]" > $titleFile
+		grep -Eo "^[\ \#\-\,\&\'\`\´\’\–A-Za-z0-9_]{1,999}[^.]" > $titleFile
 }
 
 fixScan(){
-	sed -E s/ffi/ffi/gm $infile
+	sed s/ffi/ffi/gm $infile > $cleanFile
 }
 
 GetListFromTitle() {
 	local titlecount=$(wc -l $titleFile | awk '{print $1}')
-	local currentlineinum=1
-	while [ $currentlinenum -lt $titlecount ]; do
-		local currentline=$(sed -n "$currentlinenum p")
-		(($currentlinenum++))
-		local nextline=$(sed -n "$currentlinenum p")
-		grep -A $(wc - l $infile | awk '{print $1}') "$currentline" $infile | \
-		grep -B $(wc - l $infile | awk '{print $1}') "$nextline" > "$path/$currentline.txt"
+	local currentlinenum=1
+	while (( $currentlinenum < $titlecount )); do
+		echo "$currentlinenum / $titlecount"
+	#	sed -n "$currentlinenum p" $titleFile
+	#	
+		local currentline=$(sed -n "$currentlinenum p" $titleFile)
+		echo "CurrentLineNum: $currentlinenum"
+		local tableNum=$currentlinenum
+		currentlinenum=$(( $currentlinenum + 1 ))
+		echo "CurrentLineNum After+1: $currentlinenum"
+		local nextline=$(sed -n "$currentlinenum p" $titleFile)
+		echo $currentline
+		echo $nextline
+		cat $infile | \
+			grep -A $(wc -l $infile | awk '{print $1}') "Good adventuring" | \
+			grep -A $(wc -l $infile | awk '{print $1}') "$currentline" | \
+			grep -B $(wc -l $infile | awk '{print $1}') "$nextline" > "$outpath/$tableNum-$currentline.txt"
 	done
+	local currentline=$(sed -n "$currentlinenum p" $titleFile)
+	cat $inline | grep -A $(wc -l $inline | awk '{print $1}') $currentline > "$outpath/$tableNum-$currentline.txt"
 }
 
 
+function dumpOfAllMyRandomCommandsAndStuff() {
+	# command for turning string variable into array variable
+	echo $filter; for i in $filter; do array+=("$i"); echo $i; done; echo ${array[@]}
+	
+}
 
 
 echo "Fixing spelling from certain pdftotext bugs"
 fixScan
 
+echo "Getting Titles"
+getTitles
+
+mkdir $outpath
+echo "Creating lists"
+GetListFromTitle