From 7d82d5ece36bcce89455268e95532e70f003c932 Mon Sep 17 00:00:00 2001
From: Aadhavan Srinivasan <aadhavan@twomorecents.org>
Date: Mon, 8 Jan 2024 22:14:14 -0500
Subject: [PATCH] Working on generating index page; moved the generation of a
 sorted file list to a separate function

---
 build.sh | 41 ++++++++++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)

diff --git a/build.sh b/build.sh
index c02b324..e596747 100755
--- a/build.sh
+++ b/build.sh
@@ -108,10 +108,35 @@ md_to_html() {
 	done
 }
 
-gen_index_page() { # Generate an index page (site map) that includes links to the other pages
+
+gen_sorted_file_list() { # Generate a list of the HTMl files, sorted by when they were last modified (read from the contents of the HTML file)
 	files=$(find $BASE_PATH/output -name "*.html")
+	echo "$files" > $BASE_PATH/temp/file_listing.txt # Write file list to a temp file
 
 	for file in $files; do
+		date_mod+=$(cat "$file" | grep "date-published" | awk -F'[<>]' '{print $3}' \
+			| cut -d' ' -f '1,2' --complement | tr -d "," | awk '{print $2" "$1" "$3}' \
+			| date -f - +"%s")
+
+		# Explanation:
+#			Line 1 extracts the published date from the HTML file
+#			Line 2 re-arranges this information, and converts it into DD MM YY format
+#			Line 3 converts this into a UNIX timestamp
+
+		date_mod+=$'\n'
+	done
+
+	date_mod=$(echo "$date_mod" | head -n -1) # Remove last (empty) line from variable
+	echo "$date_mod" > $BASE_PATH/temp/date_mod.txt # Write the corresponding 'date modified' timestamps to a temp file
+
+	paste $BASE_PATH/temp/file_listing.txt $BASE_PATH/temp/date_mod.txt > $BASE_PATH/temp/new_file_list.txt # Combine file list and date modified into a single file
+
+	sorted_file_list=$(sort -k 2 $BASE_PATH/temp/new_file_list.txt) # Sort the data in the file, and store it into a variable
+	sorted_file_list=$(echo "$sorted_file_list" | awk '{print $1}') # Store only the first column (the file path) in the variable
+}
+
+gen_index_page() { # Generate an index page (site map) that includes links to the other pages
+	for file in $1; do
 		title=$(cat $file | grep "<title>" | head -n 1 | awk -F'[<>]' '{print $3}') # Find the title of the web page
 		suffix=" - Two More Cents"
 		title=${title%"$suffix"} # Remove the website name from it
@@ -119,13 +144,18 @@ gen_index_page() { # Generate an index page (site map) that includes links to th
 		pub_date=$(cat $file | grep "date-published" | head -n 1 | awk -F'[<>]' '{print $3}') # Find the date published
 		prefix="Published on " # Find date published of webpage
 		pub_date=${pub_date#"$prefix"} # Remove the prefix from it
-		pub_date=${awk "{print $1 $3}" "$pub_date"} # Extract the month and year
-
-		echo "$title $pub_date"
+		pub_date=$(echo "$pub_date" | tr -d "," | awk '{print $2" "$1" "$3}' | date -f - +"%m/%d/%Y") # Re-arrange the date and convert to mm/dd/yy
 
 		file_path=$(realpath --relative-to="${BASE_PATH}/output" $file)
 
+		echo "$pub_date - $file_path"
+		index_file_list+="<li><time>${pub_date}</time> - <a href=\"$file_path\">$title</a></li>"
+		index_file_list+=$'\n'
 	done
+
+	index_file_list=$(echo "$index_file_list" | head -n -1) # Remove last (empty) line from variable
+
+	
 }
 
 clean_up() {
@@ -138,5 +168,6 @@ setup_temp_dir
 setup_output_dir
 del_files_in_output
 md_to_html
-gen_index_page
+gen_sorted_file_list # Sets the 'sorted_file_list' variable
+gen_index_page "$sorted_file_list" # Uses the 'sorted_file_list' variable
 clean_up