#!/bin/sh
#
# ISC License (ISC)
#
# Copyright (c) 2021-2024 Paul W. Rankin <rnkn@rnkn.xyz>
#
# Permission to use, copy, modify, and/or distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

# Configuration:

# SITE_URL          your URL
# SITE_AUTHOR       your name
# SITE_EMAIL        your email
# SITE_TITLE        title for html pages
# BLOG_TITLE        title of generated blog page
# BLOG_DATE_FMT     date format for blog index as per strftime(3)
# SITE_TZ           site timezone offset with separator as per ISO 8601
# TITLE_SEP         separator between SITE_TITLE and page titles
# SRC_DIR           directory of source files to convert
# STATIC_DIR        directory of static source files
# HTML_TMPL         location of m4 template for html files
# FEED_TMPL         location of m4 template for atom file
# HTML_DIR          output directory
# BLOG_INDEX        output location of generated blog page, relative to HTML_DIR
# FEED              output location of generated atom file, relative to HTML_DIR

prog=$(basename "$0")

site_url="${SITE_URL:-https://rnkn.xyz}"
site_author="${SITE_AUTHOR:-Paul W. Rankin}"
site_email="${SITE_EMAIL:-rnkn@rnkn.xyz}"
site_title="${SITE_TITLE:-Paul W. Rankin}"
blog_title="${BLOG_TITLE:-Blog}"
blog_date_fmt="${BLOG_DATE_FMT:-+%d %b %Y}"
site_tz="${SITE_TZ:-+10:00}"
title_sep="${TITLE_SEP:- &ndash; }"

src_dir="${SRC_DIR:-src}"
static_dir="${STATIC_DIR:-static}"
html_tmpl="${HTML_TMPL:-index.html.in}"
feed_tmpl="${FEED_TMPL:-feed.xml.in}"
db="${DB:-$(mktemp)}"

html_dir="${HTML_DIR:-html}"
blog_dir="${BLOG_DIR:-words}"
blog_index="${BLOG_INDEX:-${blog_dir}/index.html}"
feed="${FEED:-feed.xml}"
sitemap="${SITEMAP:-${html_dir}/sitemap.txt}"

usage() {
	cat <<EOF
usage: $prog [ -dfv ]
EOF
	exit 1
}

# get_src(extension)
# returns: list of files
get_src() {
	find "$src_dir" -type f -name "*.$1"
}

# make_db(markdownfile1, markdownfile2, ...)
# returns: TSV of ISO date, formatted date, URL path, title for each
# Markdown file
make_db() {
	while read -r file; do
		date=$(lowdown -X date "$file" 2>/dev/null || echo NULL)
		title=$(lowdown -X title "$file" 2>/dev/null || echo NULL)
		build="${file%.md}.html"
		path="${build#$src_dir}"; path="${path#/}"
		# requires Unix date *not* GNUdate
		fmt_date=$(date -jf %F "$date" "$blog_date_fmt" 2>/dev/null || echo NULL)
		printf '%s\t%s\t%s\t%s\n' "$date" "$fmt_date" "$path" "$title"
	done | sort -r
}

# make_index(database)
# returns: formatted HTML table
make_index() {
	rows=$(
		awk -F \\t -v dir="$blog_dir" '$1 != "NULL" && $3 ~ "^"dir \
			   { printf "<tr><td>%s</td><td><a href=\"/%s\">%s</a></td></tr>\n", $2, $3, $4 }' < "$1")
	printf '<table>\n<tbody>\n%s\n</tbody>\n</table>\n' "$rows"
}

# convert_md(markdownfile)
# returns: formatted HTML
convert_md() {
	src="$1"
	dst="${src%.md}.html"
	[ "$verbose" -eq 1 ] && echo "converting $src > $dst"
	lowdown -Thtml --html-no-skiphtml --html-no-escapehtml --html-no-owasp \
			< "$src" > "$dst"
}

# make_htmlpage(htmlfile)
# returns: formatted standalone HTML
make_htmlpage() {
	src="$1"
	dst="${src#$src_dir}"; dst="${dst#/}"
	mkdir -p $(dirname "${html_dir}/${dst}")

	if [ "$src" == "${src_dir}/${blog_index}" ]; then
		title="$blog_title"
	else
		title=$(awk -F \\t -v dst="$dst" '$3 == dst { print $4 }' < "$db")
		date=$(awk -F \\t -v dst="$dst" '$3 == dst { print $2 }' < "$db")
	fi

	if [ "$title" == NULL ] || [ -z "$title" ]; then
		title="$site_title"
	else
		title="${site_title}${title_sep}${title}"
	fi

	[ "$date" == NULL ] && unset date

	[ "$verbose" -eq 1 ] && echo "generating ${html_dir}/${dst}"
	m4 -D__TITLE__="$title" \
	   -D__DATE__="$date" \
	   -D__CONTENT__="$src" \
	   -P < "$html_tmpl" > "${html_dir}/${dst}"

	unset title
	unset date
}

# make_feed_entries(database)
# returns: formatted XML
make_feed_entries() {
	< "$1" awk -F \\t -v dir="$blog_dir" '$1 != "NULL" && $3 ~ "^"dir' |
	    while read -r line; do
		    date=$(echo "$line" | awk -F \\t '{ print $1 }')
		    path=$(echo "$line" | awk -F \\t '{ print $3 }')
		    title=$(echo "$line" | awk -F \\t '{ print $4 }')
			cat <<EOF
<entry>
	<title>${title}</title>
	<link href="${site_url}/${path}"/>
	<id>${site_url}/${path}</id>
	<updated>${date}T00:00:00${site_tz}</updated>
	<content type="html"><![CDATA[
		$(cat ${src_dir}/${path})
	]]></content>
</entry>
EOF
		done
}

# make_feed(feedcontent)
# returns: formatted XML Atom feed
make_feed() {
	src="$1"
	m4 -D__TITLE__="$site_title" \
	   -D__AUTHOR__="$site_author" \
	   -D__EMAIL__="$site_email" \
	   -D__SITE_URL__="$site_url" \
	   -D__PATH__="$feed" \
	   -D__DATE__=$(date "+%FT%R:%S${site_tz}") \
	   -D__CONTENT__="$src" \
	   -P < "$feed_tmpl"
}

main() {
	verbose=0; force=0; debug=0
	while getopts 'dfv' opt
	do
		case "$opt" in
			(d)     debug=1 ;;
			(f)     force=1 ;;
			(v)     verbose=1 ;;
			(*)     usage ;;
		esac
	done

	[ "$verbose" -eq 1 ] && echo "-> generating blog db..."
	get_src "md" | make_db > "$db"

	[ "$verbose" -eq 1 ] && echo "-> converting Markdown to HTML..."
	get_src "md" | while read -r file; do
		convert_md "$file"
	done

	[ "$verbose" -eq 1 ] && echo "-> generating blog index ${src_dir}/${blog_index}"
	mkdir -p "${src_dir}/${blog_dir}"
	make_index "$db"> "${src_dir}/${blog_index}"

	mkdir -p "$html_dir"
	if [ "$force" -eq 1 ]; then
		[ "$verbose" -eq 1 ] && echo "-> cleaning destination $html_dir"
		rm -rf "$html_dir/"*
	fi

	[ "$verbose" -eq 1 ] && echo "-> generating HTML pages..."
	get_src "html" | while read -r file; do
		make_htmlpage "$file"
	done

	[ "$verbose" -eq 1 ] && echo "-> generating Atom feed ${html_dir}/${feed}"
	feed_tmp=$(mktemp)
	make_feed_entries "$db" > "$feed_tmp"
	make_feed "$feed_tmp" > "${html_dir}/${feed}"

	[ "$verbose" -eq 1 ] && echo "-> copying static files into $html_dir"
	cp -Rp "$static_dir"/* "$html_dir"

	[ "$verbose" -eq 1 ] && echo "-> generating $sitemap"
	find "$html_dir" -type f -name '*.html' | while read -r file; do
		path="${file#$html_dir}"; path="${path#/}"
		echo "${site_url}/${path}"
	done > "$sitemap"

	if [ ! "$debug" -eq 1 ]; then
		[ "$verbose" -eq 1 ] && echo "-> removing temporary files..."
		rm -rf "${src_dir}/${blog_index}" "$db" "$feed_tmp"
		get_src "md" | while read -r file; do
			target="${file%.md}.html"
			if [ -e "$target" ]; then
				[ "$verbose" -eq 1 ] && echo "removing $target"
				rm -rf "$target"
			fi
		done
	fi
}

main "$@"

# Local Variables:
# indent-tabs-mode: t
# End: