#!/bin/sh
#
# https://www.romanzolotarev.com/bin/ssg
# Copyright 2018 Roman Zolotarev <hi@romanzolotarev.com>
#
# 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.
#

CONF_FILE="$PWD/_ssg.conf"
# shellcheck disable=SC1090
[ -f "$CONF_FILE" ] && . "$CONF_FILE"
[ -n "$DOCS" ] || { echo 'to build set DOCS in _ssg.conf'; exit 1; }
[ -n "$ROOT" ] || { echo 'to build set ROOT in _ssg.conf'; exit 1; }

##########################################################################

DOCUMENT_ROOT=$(readlink -fn "$DOCS")
TEMP_DIR=$(mktemp -d)
# shellcheck disable=SC2064
trap 'clean_up' EXIT
trap exit HUP INT TERM
[ "$2" = '--clean' ] && RSYNC_FLAGS='--delete-excluded' || RSYNC_FLAGS=''

INDEX_HTML_FILE="$TEMP_DIR/index.html"
RSS_FILE="$TEMP_DIR/rss.xml"
RSS_URL="$ROOT/rss.xml"
SITEMAP="$TEMP_DIR/sitemap.xml"
SITEMAP_HTML="$TEMP_DIR/sitemap.html"

CSS_FILE="$PWD/_styles.css"
JS_FILE="$PWD/_scripts.js"
HEADER_FILE="$PWD/_header.html"
FOOTER_FILE="$PWD/_footer.html"
[ -f "$CSS_FILE" ] && CSS="<style>$(cat "$CSS_FILE")</style>"
[ -f "$JS_FILE" ] && JS="<script>$(cat "$JS_FILE")</script>"
[ -f "$HEADER_FILE" ] && HEADER="$(cat "$HEADER_FILE")"
[ -f "$FOOTER_FILE" ] && FOOTER="$(cat "$FOOTER_FILE")"

##########################################################################

usage() {
	echo 'usage: DOCS=<target_directory>'
	echo
	echo '       ssg build [--clean]'
	echo '         | watch [--clean]'
	exit 1
}

copy_to_temp_dir() {
	rsync -a --delete-excluded \
		--exclude '.*' \
		--exclude '_*' \
		'.' "$TEMP_DIR"
}

copy_to_document_root() {
	[ "$(dirname "$DOCUMENT_ROOT")" = "$PWD" ] &&
		self="/$(basename "$DOCUMENT_ROOT")/" ||
		self="$DOCUMENT_ROOT"
	rsync -a $RSYNC_FLAGS \
		--exclude "$self" \
		--exclude '.*' \
		--exclude '_*' \
		"$TEMP_DIR/" "$DOCUMENT_ROOT"
}

md_to_html() {
	find "$TEMP_DIR" -type f -name '*.md'|
		while read -r file; do
			lowdown -D html-skiphtml -D smarty -d metadata \
				"$file" > "${file%\.md}.html" &&
				rm "$file"
		done
}

# filter first 20 lines with links and link titles (dates)
# shellcheck disable=SC2016
fst_h1='/<[h1]*( id=".*")?>/{gsub(/<[^>]*>/,"");print($0);exit;}'
a='^<li>.*<a href="\(.*\)" title="\([^<]*\)">.*<\/a>.*<\/li>.*'

line_to_rss_item() {
	url=$(echo "$line"|sed "s/$a/\\1/g")
	date=$(echo "$line"|sed "s/$a/\\2/g")
	file="${TEMP_DIR}${url}"
	[ ! -f "$file" ] && return

	title="$(awk "$fst_h1" "$file")"

	# replace relative URIs with absolute URIs
	href='s#href="#href="'"$ROOT"'/#g'
	src='s#src="#src="'"$ROOT"'#g'
	article=$(sed "$href;$src" "$file")

	printf "%s" "$(cat << EOF

<item>
<title>$title</title>
<guid>${ROOT}$url</guid>
<link>${ROOT}$url</link>
<pubDate>$date 00:00:00 +0000</pubDate>
<description><![CDATA[$article]]></description>
</item>
EOF
)"|sed 's/\&nbsp;/ /g' >> "$RSS_FILE"
}

index_to_rss() {
	date_rfc_822=$(date "+%a, %d %b %Y %H:%M:%S %z")
	cat > "$RSS_FILE" << EOF
<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
<channel>
<atom:link href="$RSS_URL" rel="self" type="application/rss+xml" />
<title>$WEBSITE_TITLE</title>
<description>$RSS_DESCRIPTION</description>
<link>$ROOT/</link>
<lastBuildDate>$date_rfc_822</lastBuildDate>
<managingEditor>$RSS_AUTHOR</managingEditor>
EOF
	grep "$a" "$INDEX_HTML_FILE" |
	head -n20 |
	while read -r line; do line_to_rss_item "$line"; done
	echo '</channel></rss>' >> "$RSS_FILE"
}

wrap_html() {
	# generate sorted sitemap
	find_h1_tag='/<[h1]*( id=".*")?>/'
	# shellcheck disable=SC2016
	tag_content='{gsub(/<[^>]*>/,"");print(FILENAME"===="$0);exit;}'
	sitemap="$(
		find "$TEMP_DIR" -type f -name '*.html'|
		while read -r file; do
			awk "${find_h1_tag}${tag_content}" "$file"
		done|sort
	)"
        [ -z "$sitemap" ] && { echo && return; }
	# save sitemap in html and xml formats
	date=$(date +%Y-%m-%dT%H:%M:%S%z)
	echo '<table>' > "$SITEMAP_HTML"
	cat > "$SITEMAP" << EOF
<?xml version="1.0" encoding="UTF-8"?>
<urlset
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9
http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
EOF
	echo "$sitemap"|while read -r line; do
		page=${line%====*}
		url=${page#$TEMP_DIR}
		case "$url" in
			/index.html) title='Home';;
			*) title="${line#*====}";;
		esac
		{
		printf '<tr><td><code>'
		printf '<a href="%s">%s</a>' "$url" "${url#/*}"
		printf '</code></td><td>%s</td></tr>\n' "$title"
		} >> "$SITEMAP_HTML"
		cat >> "$SITEMAP" << EOF
<url>
<loc>${ROOT}$url</loc>
<lastmod>$date</lastmod>
<priority>1.0</priority>
</url>
EOF
	done
	echo '</urlset>' >> "$SITEMAP"
	# generate html pages
	echo "$sitemap"|
		while read -r line; do
		page=${line%====*}
		url=${page#$TEMP_DIR}
                article=$(cat "$page")
		case "$url" in
			/index.html)
				title='Home'
				head_title="$WEBSITE_TITLE"
				;;
			*)
				title="${line#*====}"
				head_title="$title - $WEBSITE_TITLE"
				;;
		esac
		# merge page with html template
		cat > "$page" <<EOF
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<link rel="alternate" type="application/atom+xml" href="/rss.xml">
<link rel="icon" type="image/png" href="/favicon.png">
<title>$head_title</title>
$CSS
$JS
</head>
<body>
$HEADER
$article
$FOOTER
</body>
</html>
EOF
	done
	echo "$date $(echo "$sitemap"|wc -l|tr -d ' ')pp"
}

clean_up() { rm -rf "$TEMP_DIR"; }

##########################################################################

case "$1" in

build)
	ls index.* >/dev/null 2>&1 ||
		{ echo 'no index.* found in the directory'; exit 1; }
	[ ! -x "$(which rsync)" ] &&
		{ echo 'rsync(1) should be installed'; exit 1; }
	[ ! -x "$(which lowdown)" ] &&
		{ echo 'lowdown(1) should be installed'; exit 1; }
	printf 'building %s %s ' "$DOCUMENT_ROOT" "$2"
	copy_to_temp_dir
	md_to_html
	index_to_rss
	wrap_html
	copy_to_document_root
	clean_up
	;;

watch)
	cmd="entr -d env DOCS=$DOCS $(basename "$0") build $2"
	pgrep -qf "$cmd" && { echo "already watching $DOCS"; exit 1; }
	echo "watching $PWD"
	[ ! -x "$(which entr)" ] &&
		{ echo 'entr(1) should be installed'; exit 1; }
	while true; do
		find "$PWD" -type f \
			\( -name "$(basename "$0")" \
			-or -name '*.conf' \
			-or -name '*.md' \
			-or -name '*.html' \
			-or -name '*.css' \
			-or -name '*.js' \
			-or -name '*.txt' \
			-or -name '*.jpg' \
			-or -name '*.png' \)\
			! -name ".*" \
			! -path "*/.*" \
			! -path "${DOCUMENT_ROOT}*" |
			$cmd
	done
	;;

*) usage;;

esac