rivet/rivet.sh

#!/bin/sh

# Copyright (c) 2020 Alessandro Mauri
# 
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
# 
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

set -e
unset SKIP_FOOTER
unset SKIP_HEADER
unset SKIP_LIST
unset VERBOSE
unset PRINT_HELP
unset SKIP_SITEMAP

usage() {
	printf "Usage: rivet [-hovelfsu] [-p string] [-o destdir] srcdir domain\n"
	printf "\t-h: prints this message\n"
	printf "\t-o [destdir]: specifies the output direcotory to be [destdir]\n"
	printf "\t-p: [string]: Rename the \"Pages\" section to [string]\n"
	printf "\t-v: Makes the script verbose\n"
	printf "\t-e: Do not prepend _header.html to .html files\n"
	printf "\t-f: Do not prepend _footer.html to .html files\n"
	printf "\t-l: Do not generate \"Pages\" section in index.html\n"
	printf "\t-s: Do not generate sitemap.xml\n"
	printf "\t-u: Makes all references to the url 'http' instead of 'https'\n"
	exit 2
}

convert() {
	tmpfile="tmpconvfile.tmp"
	infile="$1"
	outfile="${infile%???}.html"
	cp "$infile" "$tmpfile"
	# TODO: convert links to .md to .html
	lowdown -s -Thtml -o "$outfile" "$tmpfile"
	rm -f "$tmpfile" "$infile"
}

# Check dependencies
if ! command -v lowdown > /dev/null; then
    echo "lowdown is not installed"
    exit
fi

destdir='dst'
prefix='https'
linksec='Pages'
while getopts 'o:vhelfsup:' c
do
	case "$c" in
		o) destdir=${OPTARG%%\/} ;;
		v) VERBOSE=true ;;
		h) PRINT_HELP=true ;;
		e) SKIP_HEADER=true ;;
		l) SKIP_LIST=true ;;
		f) SKIP_FOOTER=true ;;
		s) SKIP_SITEMAP=true ;;
		u) prefix='http' ;;
		p) linksec="$OPTARG" ;;
		*) ;;
	esac
done
shift $((OPTIND - 1))
if ! [ "$1" ] || ! [ "$2" ]; then
	echo "Not enough arguments"
	usage
fi

src="$1"
srcdir=${src%%\/}
unset src
headerfile=$srcdir/_header.html
footerfile=$srcdir/_footer.html
filelist=filelist.tmp

# Check if index.md is present
if ! [ -e "$srcdir"/index.md ]; then
	echo "Missing index.md in $srcdir"
	exit 1
fi

# Check header and footer files
if ! [ -e "$headerfile" ]; then
	echo "Missing _header.html in $srcdir"
	exit 1
fi
if ! [ -e "$footerfile" ]; then
	echo "Missing _footer.html in $srcdir"
	exit 1
fi
# Remove junk from {header,footer} files
sed -i 's/<header.*>//' "$headerfile"
sed -i 's/<\/header>//' "$headerfile"
sed -i 's/<footer.*>//' "$footerfile"
sed -i 's/<\/footer>//' "$footerfile"

# Remove any junk from the domain eg. [https://]domain.com[/]
url="$(echo "$2" |
	sed -e 's/^https*:\/\///' |
	sed -e 's/\/$//' |
	sed -e 's/[]\/$*.^[]/\\&/g')"

if [ "$PRINT_HELP" ]; then
	usage
fi
if [ "$VERBOSE" ]; then
	set -x
fi

if ! [ -d "$srcdir" ]; then
	echo "Error: missing source direcotry"
	usage
fi

rm -rf "$destdir"
mkdir -p "$destdir"
cp -r "$srcdir"/* "$destdir"
rm -f "$destdir"/_header.html "$destdir"/_footer.html

# Generate an ordered (by open time) file list
find "$srcdir" -type f -name "*.md" -exec ls -1t {} + > "$filelist"
sed -i "s,^\/*[^\/]*\/,$destdir/," "$filelist"

# Convert markdown files
while IFS="" read -r file; do
	convert "$file"
done < "$filelist"
sed -i 's/\.md$/\.html/' "$filelist"

# Prepare the header
if ! [ "$SKIP_HEADER" ]; then
	find "$destdir" -name "*.html" |
	while IFS="" read -r file; do
		sed -i "/<head>/r $headerfile"  "$file"
	done
fi
# Prepate the footer
if ! [ "$SKIP_FOOTER" ]; then
	tmpfoot="tmpfootfile.tmp"
	cp "$footerfile" "$tmpfoot"
	sed -i '1s/^/<footer>/' "$tmpfoot"
	echo '</footer>' >> "$tmpfoot"
	find "$destdir" -name "*.html" |
	while IFS="" read -r file; do
		sed -i "/<\/body>/r $tmpfoot" "$file"
	done
	rm -f "$tmpfoot"
fi

# Prepare the sitemap & file list
if ! [ "$SKIP_SITEMAP" ] || ! [ "$SKIP_LIST" ]; then
	linklist="linklist.tmp"
	rm -f "$linklist" "$destdir"/sitemap.xml
	while IFS="" read -r file; do
		echo "${file#$destdir/}" >> "$linklist"
	done < "$filelist"

	if ! [ "$SKIP_LIST" ]; then
		tmpfile="linkindex.tmp"
		rm -f "$tmpfile"
		cat << EOF >> "$tmpfile"
<div id="map">
<h2 id="Pages">$linksec</h2>
EOF
		while IFS="" read -r line; do
			if echo "$line" | grep -q 'index\.html'; then
				continue
			fi
			title="$(grep -e '^<title>.*<\/title>' "$destdir"/"$line" |
			sed -e 's/<title>//' -e 's/<\/title>//')"
			if ! [ "$title" ] || echo "$title" | grep -q 'Untitled article'; then
				title=${line%?????}
			fi
			printf "<p><a href=\"%s\">%s</a></p>\n" "$line" "$title" >> "$tmpfile"
		done < "$linklist"
		echo '</div>' >> "$tmpfile"
		sed -i '/<\/body>/i REPLACE' "$destdir"/index.html
		sed -i "/^REPLACE/r $tmpfile" "$destdir"/index.html
		sed -i 's/^REPLACE//' "$destdir"/index.html
		rm -f "$tmpfile"
	fi

	if ! [ "$SKIP_SITEMAP" ]; then
		sed -i -e "s/^/$prefix:\/\/$url\//" "$linklist"
		cat << EOF >>  "$destdir"/sitemap.xml
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
</urlset> 
EOF
		while IFS="" read -r line; do
			sed -i "/<\/urlset>/i \
			<url><loc>$line<\/loc><\/url>" "$destdir"/sitemap.xml
		done < "$linklist"
		sed -i 's/^<url>/\t<url>/' "$destdir"/sitemap.xml
	fi
	rm -f "$linklist" "$filelist"
fi

exit