c9cb4d022244f4c7173f59db074f29455f7b4f84
[~bandali/bndl.org] / ssng
1 #!/bin/sh
2
3 # Copyright (C) 2018 Amin Bandali <amin@aminb.org>
4
5 # This program is free software: you can redistribute it and/or modify
6 # it under the terms of the GNU General Public License as published by
7 # the Free Software Foundation, either version 3 of the License, or
8 # (at your option) any later version.
9
10 # This program is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
14
15 # You should have received a copy of the GNU General Public License
16 # along with this program. If not, see <https://www.gnu.org/licenses/>.
17
18 # ssng is a fork of Roman Zolotarev's ssg. See end of file for ssg's
19 # license notice.
20
21 : "${WEBSITE_TITLE:=Roman Zolotarev}"
22 : "${SERVER_NAME:=www.romanzolotarev.com}"
23 : "${SERVER_PROTO:=https}"
24 : "${RSS_AUTHOR:=hi@romanzolotarev.com (Roman Zolotarev)}"
25 : "${RSS_DESCRIPTION:=Personal website}"
26 : "${COPYRIGHT_YEAR:=2016}"
27
28 ##########################################################################
29
30 [ -n "$DOCS" ] || { echo "export DOCS <target_directory>"; exit 1; }
31 DOCUMENT_ROOT=$(readlink -fn "$DOCS")
32 TEMP_DIR=$(mktemp -d)
33 # shellcheck disable=SC2064
34 trap 'clean_up' EXIT
35 trap exit HUP INT TERM
36 [ "$2" = '--clean' ] && RSYNC_FLAGS='--delete-excluded' || RSYNC_FLAGS=''
37
38 INDEX_HTML_FILE="$TEMP_DIR/index.html"
39 CSS_FILE="$TEMP_DIR/styles.css"
40 RSS_FILE="$TEMP_DIR/rss.xml"
41 RSS_URL="$SERVER_PROTO://$SERVER_NAME/rss.xml"
42 SITEMAP="$TEMP_DIR/sitemap.xml"
43
44 ANNOUNCEMENT_FILE="$PWD/announcement.html"
45 FOOTER_FILE="$PWD/footer.html"
46 HEADER_FILE="$PWD/header.html"
47 [ -f "$ANNOUNCEMENT_FILE" ] &&
48 ANNOUNCEMENT_TEXT=$(cat "$ANNOUNCEMENT_FILE")
49 [ -f "$HEADER_FILE" ] &&
50 HEADER=$(cat "$HEADER_FILE") ||
51 HEADER=$(cat << EOF
52 <a href="/">Home</a> -
53 <a href="/twitter.html">Twitter</a>
54 EOF
55 )
56 [ -f "$FOOTER_FILE" ] &&
57 FOOTER=$(cat "$FOOTER_FILE") ||
58 FOOTER=$(cat << EOF
59 Copyright $COPYRIGHT_YEAR&ndash;$(date +%Y)
60 <a href="/about.html">$WEBSITE_TITLE</a>
61 EOF
62 )
63
64 ##########################################################################
65
66 usage() {
67 echo 'usage: DOCS=<target_directory>'
68 echo
69 echo ' ssg build [--clean]'
70 echo ' | watch [--clean]'
71 exit 1
72 }
73
74 copy_to_temp_dir() {
75 rsync -a --delete-excluded \
76 --exclude '.*' \
77 --exclude '_*' \
78 '.' "$TEMP_DIR"
79 }
80
81 copy_to_document_root() {
82 [ "$(dirname "$DOCUMENT_ROOT")" = "$PWD" ] &&
83 self="/$(basename "$DOCUMENT_ROOT")/" ||
84 self="$DOCUMENT_ROOT"
85 rsync -a $RSYNC_FLAGS \
86 --exclude "$self" \
87 --exclude '.*' \
88 --exclude '_*' \
89 "$TEMP_DIR/" "$DOCUMENT_ROOT"
90 }
91
92 md_to_html() {
93 find "$TEMP_DIR" -type f -name '*.md'|
94 while read -r file; do
95 lowdown -D html-skiphtml -d metadata \
96 "$file" > "${file%\.md}.html" &&
97 rm "$file"
98 done
99 }
100
101
102 # filter first 20 lines with links and link titles (dates)
103 # shellcheck disable=SC2016
104 fst_h1='/<[h1]*( id=".*")?>/{gsub(/<[^>]*>/,"");print($0);exit;}'
105 a='^<li><a href="\(.*\)" title="\([^<]*\)">[^<]*<\/a>.*<\/li>.*'
106
107 line_to_rss_item() {
108 url=$(echo "$line"|sed "s/$a/\\1/g")
109 date=$(echo "$line"|sed "s/$a/\\2/g")
110 file="${TEMP_DIR}${url}"
111 [ ! -f "$file" ] && return
112
113 title="$(awk "$fst_h1" "$file")"
114 # replace relative URIs with absolute URIs
115 article=$(sed "s/\\([hrefsc]*\\)=\"\\//\\1=\"$prefix/g" "$file")
116 echo $(cat << EOF
117 <item>
118 <title>$title</title>
119 <guid>$SERVER_PROTO://${SERVER_NAME}$url</guid>
120 <link>$SERVER_PROTO://${SERVER_NAME}$url</link>
121 <pubDate>$date 00:00:00 +0000</pubDate>
122 <description><![CDATA[$article]]></description>
123 </item>
124 EOF
125 )|sed 's/\&nbsp;/\&#160;/'>>"$RSS_FILE"
126 }
127
128 index_to_rss() {
129 date_rfc_822=$(date "+%a, %d %b %Y %H:%M:%S %z")
130 cat > "$RSS_FILE" << EOF
131 <?xml version="1.0" encoding="utf-8"?>
132 <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
133 <channel>
134 <atom:link href="$RSS_URL" rel="self" type="application/rss+xml" />
135 <title>$WEBSITE_TITLE</title>
136 <description>$RSS_DESCRIPTION</description>
137 <link>$SERVER_PROTO://$SERVER_NAME/</link>
138 <lastBuildDate>$date_rfc_822</lastBuildDate>
139 <managingEditor>$RSS_AUTHOR</managingEditor>
140 EOF
141
142 prefix="$SERVER_PROTO:\\/\\/$SERVER_NAME\\/"
143 grep "$a" "$INDEX_HTML_FILE" |
144 head -n20 |
145 while read -r line; do line_to_rss_item "$line"; done
146 echo '</channel></rss>' >> "$RSS_FILE"
147 }
148
149 wrap_html() {
150 # generate sorted sitemap
151 find_h1_tag='/<[h1]*( id=".*")?>/'
152 # shellcheck disable=SC2016
153 tag_content='{gsub(/<[^>]*>/,"");print(FILENAME"===="$0);exit;}'
154 sitemap="$(
155 find "$TEMP_DIR" -type f -name '*.html'|
156 while read -r file; do
157 awk "${find_h1_tag}${tag_content}" "$file"
158 done|
159 sort
160 )"
161 # save sitemap in html and xml formats
162 date=$(date +%Y-%m-%dT%H:%M:%S%z)
163 cat > "$SITEMAP" << EOF
164 <?xml version="1.0" encoding="UTF-8"?>
165 <urlset
166 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
167 xsi:schemaLocation="http://www.sitemaps.org/schemas/sitemap/0.9
168 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd"
169 xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
170 EOF
171 echo "$sitemap"|while read -r line; do
172 page=${line%====*}
173 url=${page#$TEMP_DIR}
174 case "$url" in
175 /index.html) title='Home';;
176 *) title="${line#*====}";;
177 esac
178 cat >> "$SITEMAP" << EOF
179 <url>
180 <loc>$SERVER_PROTO://${SERVER_NAME}$url</loc>
181 <lastmod>$date</lastmod>
182 <priority>1.0</priority>
183 </url>
184 EOF
185 done
186 echo '</urlset>' >> "$SITEMAP"
187 # generate html pages
188 styles=$(cat "$CSS_FILE")
189 [ -n "$ANNOUNCEMENT_TEXT" ] &&
190 announcement="$(cat << EOF
191 <div class="announcement">
192 <div class="announcement__text">$ANNOUNCEMENT_TEXT</div>
193 </div>
194 EOF
195 )"
196 echo "$sitemap"|
197 while read -r line; do
198 page=${line%====*}
199 url=${page#$TEMP_DIR}
200 article=$(cat "$page")
201 case "$url" in
202 /index.html)
203 title='Home'
204 head_title="$WEBSITE_TITLE"
205 header__home=''
206 ;;
207 *)
208 title="${line#*====}"
209 head_title="$title - $WEBSITE_TITLE"
210 header__home="$HEADER"
211 ;;
212 esac
213 # merge page with html template
214 cat > "$page" <<EOF
215 <!DOCTYPE html><html lang="en">
216 <head><title>$head_title</title>
217 <meta charset="utf-8">
218 <meta name="viewport" content="width=device-width, initial-scale=1">
219 <link rel="alternate" type="application/atom+xml" href="/rss.xml">
220 <link rel="icon" type="image/png" href="/favicon.png">
221 <style>$styles</style>
222 </head>
223 <body>
224 <script>
225 !function(t){
226 t.addEventListener('DOMContentLoaded', function () {
227 var l = t.querySelector('#light-off');
228 if (l === null) { console.log('Lights-out...'); }
229 else {
230 l.checked = t.cookie.match(/lightOff=true/) !== null;
231 l.addEventListener('change', function () {
232 t.cookie = 'lightOff=' + JSON.stringify(l.checked) + ';path=/';
233 });
234 }
235 })
236 }(document);
237 </script>
238 <input class="light-off" type="checkbox" id="light-off">
239 <div class="page">
240 $announcement
241 <div class="header">
242 <div class="header__left">$header__home</div>
243 <div class="header__right">
244 <label for="light-off" class="light-off-button"></label>
245 </div>
246 </div>
247 <div class="article">$article</div>
248 <div class="footer">$FOOTER</div>
249 </div>
250 </body>
251 </html>
252 EOF
253 done
254 echo "$date $(echo "$sitemap"|wc -l|tr -d ' ')pp"
255 }
256
257 clean_up() { rm -rf "$TEMP_DIR"; }
258
259 ##########################################################################
260
261 case "$1" in
262
263 build)
264 ls index.* >/dev/null 2>&1 ||
265 { echo 'no index.* found in the directory'; exit 1; }
266 [ ! -x "$(which rsync)" ] &&
267 { echo 'rsync(1) should be installed'; exit 1; }
268 [ ! -x "$(which lowdown)" ] &&
269 { echo 'lowdown(1) should be installed'; exit 1; }
270 printf 'building %s %s ' "$DOCUMENT_ROOT" "$2"
271 copy_to_temp_dir
272 md_to_html
273 index_to_rss
274 wrap_html
275 copy_to_document_root
276 clean_up
277 ;;
278
279 watch)
280 cmd="entr -d env DOCS=$DOCS $(basename "$0") build $2"
281 pgrep -qf "$cmd" && { echo "already watching $DOCS"; exit 1; }
282 echo "watching $PWD"
283 [ ! -x "$(which entr)" ] &&
284 { echo 'entr(1) should be installed'; exit 1; }
285 while true; do
286 find "$PWD" -type f \
287 \( -name "$(basename "$0")" \
288 -or -name '*.md' \
289 -or -name '*.html' \
290 -or -name '*.css' \
291 -or -name '*.txt' \
292 -or -name '*.jpeg' \
293 -or -name '*.png' \)\
294 ! -name ".*" \
295 ! -path "*/.*" \
296 ! -path "${DOCUMENT_ROOT}*" |
297 $cmd
298 done
299 ;;
300
301 *) usage;;
302
303 esac
304
305
306 ## ssg's license: ##
307
308 # https://www.romanzolotarev.com/bin/ssg
309 # Copyright 2018 Roman Zolotarev <hi@romanzolotarev.com>
310 #
311 # Permission to use, copy, modify, and/or distribute this software for any
312 # purpose with or without fee is hereby granted, provided that the above
313 # copyright notice and this permission notice appear in all copies.
314 #
315 # THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
316 # WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
317 # MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
318 # ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
319 # WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
320 # ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
321 # OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.