Initial commit

[~bandali/bndl.org] / ssng

#!/bin/sh

# Copyright (C) 2018  Amin Bandali <amin@aminb.org>

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.

# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <https://www.gnu.org/licenses/>.

# ssng is a fork of Roman Zolotarev's ssg. See end of file for ssg's
# license notice.

: "${WEBSITE_TITLE:=Roman Zolotarev}"
: "${SERVER_NAME:=www.romanzolotarev.com}"
: "${SERVER_PROTO:=https}"
: "${RSS_AUTHOR:=hi@romanzolotarev.com (Roman Zolotarev)}"
: "${RSS_DESCRIPTION:=Personal website}"
: "${COPYRIGHT_YEAR:=2016}"

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

[ -n "$DOCS" ] || { echo "export DOCS <target_directory>"; exit 1; }
DOCUMENT_ROOT=$(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="$TEMP_DIR/index.html"
CSS_FILE="$TEMP_DIR/styles.css"
RSS_FILE="$TEMP_DIR/rss.xml"
RSS_URL="$SERVER_PROTO://$SERVER_NAME/rss.xml"
SITEMAP="$TEMP_DIR/sitemap.xml"

ANNOUNCEMENT_FILE="$PWD/announcement.html"
FOOTER_FILE="$PWD/footer.html"
HEADER_FILE="$PWD/header.html"
[ -f "$ANNOUNCEMENT_FILE" ] &&
	ANNOUNCEMENT_TEXT=$(cat "$ANNOUNCEMENT_FILE")
[ -f "$HEADER_FILE"       ] &&
	HEADER=$(cat "$HEADER_FILE") ||
	HEADER=$(cat << EOF
<a href="/">Home</a> -
<a href="/twitter.html">Twitter</a>
EOF
)
[ -f "$FOOTER_FILE"       ] &&
	FOOTER=$(cat "$FOOTER_FILE") ||
	FOOTER=$(cat << EOF
Copyright $COPYRIGHT_YEAR&ndash;$(date +%Y)
<a href="/about.html">$WEBSITE_TITLE</a>
EOF
)

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

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 "$TEMP_DIR" -type f -name '*.md'|
		while read -r file; do
			lowdown -D html-skiphtml -d metadata \
				"$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" "$file")"
	# replace relative URIs with absolute URIs
	article=$(sed "s/\\([hrefsc]*\\)=\"\\//\\1=\"$prefix/g" "$file")
	echo $(cat << EOF
<item>
<title>$title</title>
<guid>$SERVER_PROTO://${SERVER_NAME}$url</guid>
<link>$SERVER_PROTO://${SERVER_NAME}$url</link>
<pubDate>$date 00:00:00 +0000</pubDate>
<description><![CDATA[$article]]></description>
</item>
EOF
)|sed 's/\&nbsp;/\&#160;/'>>"$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>$RSS_DESCRIPTION</description>
<link>$SERVER_PROTO://$SERVER_NAME/</link>
<lastBuildDate>$date_rfc_822</lastBuildDate>
<managingEditor>$RSS_AUTHOR</managingEditor>
EOF

	prefix="$SERVER_PROTO:\\/\\/$SERVER_NAME\\/"
	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
	)"
	# save sitemap in html and xml formats
	date=$(date +%Y-%m-%dT%H:%M:%S%z)
	cat > "$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
		cat >> "$SITEMAP" << EOF
<url>
<loc>$SERVER_PROTO://${SERVER_NAME}$url</loc>
<lastmod>$date</lastmod>
<priority>1.0</priority>
</url>
EOF
	done
	echo '</urlset>' >> "$SITEMAP"
	# generate html pages
	styles=$(cat "$CSS_FILE")
	[ -n "$ANNOUNCEMENT_TEXT" ] &&
		announcement="$(cat << EOF
<div class="announcement">
<div class="announcement__text">$ANNOUNCEMENT_TEXT</div>
</div>
EOF
)"
echo "$sitemap"|
		while read -r line; do
		page=${line%====*}
		url=${page#$TEMP_DIR}
		article=$(cat "$page")
		case "$url" in
			/index.html)
				title='Home'
				head_title="$WEBSITE_TITLE"
				header__home=''
				;;
			*)
				title="${line#*====}"
				head_title="$title - $WEBSITE_TITLE"
				header__home="$HEADER"
				;;
		esac
		# merge page with html template
		cat > "$page" <<EOF
<!DOCTYPE html><html lang="en">
<head><title>$head_title</title>
<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">
<style>$styles</style>
</head>
<body>
<script>
!function(t){
  t.addEventListener('DOMContentLoaded', function () {
    var l = t.querySelector('#light-off');
    if (l === null) { console.log('Lights-out...'); }
    else {
      l.checked = t.cookie.match(/lightOff=true/) !== null;
      l.addEventListener('change', function () {
        t.cookie = 'lightOff=' + JSON.stringify(l.checked) + ';path=/';
      });
    }
  })
}(document);
</script>
<input class="light-off" type="checkbox" id="light-off">
<div class="page">
$announcement
<div class="header">
<div class="header__left">$header__home</div>
<div class="header__right">
<label for="light-off" class="light-off-button"></label>
</div>
</div>
<div class="article">$article</div>
<div class="footer">$FOOTER</div>
</div>
</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 \
			\( -name "$(basename "$0")" \
			-or -name '*.md' \
			-or -name '*.html' \
			-or -name '*.css' \
			-or -name '*.txt' \
			-or -name '*.jpeg' \
			-or -name '*.png' \)\
			! -name ".*" \
			! -path "*/.*" \
			! -path "${DOCUMENT_ROOT}*" |
			$cmd
	done
	;;

*) usage;;

esac


## ssg's license: ##

# 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.