Validate and fix feeds, persist link-check cache

Makefile

@@ -56,9 +56,13 @@ validate-html:
 htmlproofer:
 	htmlproofer $(OUTPUT_DIR) --disable-external --report-invalid-tags --report-missing-names --report-missing-doctype --report-eof-tags --report-mismatched-tags --check-html --check-opengraph --check-favicon --empty-alt-ignore --file-ignore $(OUTPUT_DIR)/search/index.html --url-ignore '../music.txt'
 
+# basic checks for generated HTML and broken links. Persist the broken
+# link cache remotely so we can run this in CI.
 .PHONY: htmltest
 htmltest:
+	rsync $(RSYNCFLAGS) deploy@seirdy.one:/home/deploy/refcache.json linter-configs/htmltest/refcache.json 
 	htmltest -c linter-configs/htmltest.yml $(OUTPUT_DIR)
+	rsync $(RSYNCFLAGS) linter-configs/htmltest/refcache.json deploy@seirdy.one:/home/deploy/refcache.json
 
 .PHONY: hint
 hint: hugo .hintrc-local

Makefile.online

@@ -24,6 +24,8 @@ lighthouse:
 	rm -rf $(CHROME_PROFILE)
 redbot:
 	redbot_cli -a $(URL)
+.PHONY: hint-online lighthouse redbot
+
 axe:
 	axe $(URLS) --chrome-options $(CHROME_FLAGS_COMMA) --chromedriver-path=$(CHROMEDRIVER_PATH) --show-errors
 axe-ff:
@@ -32,7 +34,17 @@ equal-access:
 	@echo $(URLS) | tr ' ' '\n' >urls.txt
 	achecker --reportLevels violation,recommendation,potentialrecommendation urls.txt
 	rm urls.txt
+.PHONY: axe axe-ff equal-access
 
-all: lighthouse hint-online
+.validate-feed-main:
+	scripts/bin/validate-feed $(HUGO_BASEURL)atom.xml
+.validate-feed-posts:
+	scripts/bin/validate-feed $(HUGO_BASEURL)posts/atom.xml
+.validate-feed-notes:
+	scripts/bin/validate-feed $(HUGO_BASEURL)notes/atom.xml
+validate-feeds: .validate-feed-main .validate-feed-posts .validate-feed-notes
+.PHONY: validate-feeds .validate-feed-main .validate-feed-posts .validate-feed-notes
+
+.PHONY: all-extra
+all-extra: axe htmltest validate-json equal-access htmlproofer lint-css validate-feeds
 
-.PHONY: hint-online lighthouse redbot all

layouts/_default/list.atom.xml

@@ -60,7 +60,7 @@
 					{{- if .Params.replyURI -}}
 						{{- partial "reply-context" .Params | replaceRE `(?: )?(?:item(type|scope|prop|id|ref)="[^"]*"|class="language-figure")` "" | safeHTML }}
 					{{- end -}}
-					{{ partial "processed-content.html" . | replaceRE `(?: )?(?:item(type|scope|prop|id|ref)="[^"]*"|class="language-figure")` "" | safeHTML }}
+					{{ partial "processed-content.html" . | replaceRE `(?: )?(?:item(type|scope|prop|id|ref)="[^"]*"|class="language-figure")` "" | replaceRE `<meta content="true" ?/>` "" | safeHTML }}
 			</div>
 		</content>
 		{{- $type := "article" -}}

layouts/_default/rss.xml

@@ -44,7 +44,7 @@
       <pubDate>{{ .Date.Format "Mon, 02 Jan 2006 15:04:05 -0700" | safeHTML }}</pubDate>
       {{ with .Site.Author.email }}<author>{{.}}{{ with $.Site.Author.name }} ({{.}}){{end}}</author>{{end}}
       <guid>{{ .Permalink }}</guid>
-      <description>{{- .Content | replaceRE `(?: )?(?:item(type|scope|prop|id|ref)="[^"]*"|class="language-figure")` "" | html -}}</description>
+      <description xml:base="{{ .Permalink }}">{{- .Content | replaceRE `(?: )?(?:item(type|scope|prop|id|ref)="[^"]*"|class="language-figure")` "" | replaceRE `<meta content="true" ?/>` "" | html -}}</description>
     </item>
     {{ end }}
   </channel>

scripts/bin/check-whole-site

@@ -5,7 +5,7 @@ set -e -u
 # the name of this program
 progname="$(basename "${0}")"
 
-help_text="Usage:
+help_text="Usage: $progname [BASEURL]
 
 Validate the site's markup, CSS, and accessibility.
 
@@ -20,13 +20,10 @@ accessibility on every page in the sitemap.
 
 Options:
   -h            Print this help and exit
-  -b            Base URL of site
 "
 
 # TODO: add the following:
-# - check broken internal links
+# - validate JSON schema (web app manifest, webfinger)
-# - check broken webring links
-# - validate JSON (web app manifest, webfinger)
 
 usage() {
 	printf '%s' "${help_text}"
@@ -40,18 +37,12 @@ bad_option() {
 	exit 1
 }
 
-base_url='http://localhost:8089/'
-
 while getopts "hb" flags; do
 	case ${flags} in
 		h)
 			usage
 			exit 0
 			;;
-		b)
-			base_url="$1"
-			shift
-			;;
 		*)
 			bad_option "${flags}" 'invalid option'
 			exit 1
@@ -59,8 +50,10 @@ while getopts "hb" flags; do
 	esac
 done
 
+base_url="${1-http://localhost:8089}"
+
 # HTML validation is already parallelized, so run that single-threaded.
 make -j1 HUGO_FLAGS=-DF HUGO_BASEURL="$base_url" clean hugo xhtmlize validate-html
-make -j2 -f Makefile.online htmltest validate-json axe equal-access lint-css htmlproofer URLS="$(curl "$base_url/sitemap.xml" | htmlq loc -t | rg -v '/search/$' | tr '\n' ' ')"
+make -j2 -f Makefile.online HUGO_BASEURL="$base_url" all-extra URLS="$(curl -sSL "$base_url/sitemap.xml" | htmlq loc -t | rg -v '/search/$' | tr '\n' ' ')"
 
 # vi:ft=sh

scripts/bin/validate-feed

@@ -0,0 +1,76 @@
+#!/usr/bin/env dash
+
+set -u
+
+# the name of this program
+progname="$(basename "${0}")"
+
+help_text="Usage: ${progname} [options...] URL
+
+Validate the given feed URL, excluding false-positives
+
+Options:
+  -h            Print this help and exit
+"
+
+usage() {
+	printf '%s' "${help_text}"
+}
+
+# when the user passess bad args, send a msg to stderr and exit
+# usage: bad_option <option> <reason>
+bad_option() {
+	echo "${progname}: option ${1}: ${2}" >&2
+	usage >&2
+	exit 1
+}
+
+while getopts "ho" flags; do
+	case ${flags} in
+		h)
+			usage
+			exit 0
+			;;
+		*)
+			bad_option "${flags}" 'invalid option'
+			exit 1
+			;;
+	esac
+done
+
+url="$1"
+
+
+find_rel_mention_count() {
+	curl -s "$url" | grep -cF 'rel="mentioned"'
+}
+
+rel_mention_count="$(find_rel_mention_count)"
+
+run_validator() {
+	"$GHQ_ROOT/github.com/w3c/feedvalidator/src/demo.py" "$url"
+}
+
+validate_feed() {
+	rel_mention_string="Unregistered link relationship \($rel_mention_count occurrence"
+	if [ "$rel_mention_count" = '1' ]; then
+		rel_mention_string="Unregistered link relationship"
+	fi
+
+	full_regex="Use of unknown namespace|Self reference doesn't match|should not contain (role|aria-labelledby|aria-label|aria-describedby) attribute|$rel_mention_string|entries with the same value|Validating $url"
+
+	run_validator \
+		| grep -Ev "$full_regex"
+}
+
+validator_output="$(validate_feed)"
+if [ "$validator_output" = '' ]; then
+	echo "Feed is valid"
+	exit 0
+else
+	echo "Feed errors found!" 1>&2
+	echo "$validator_output"
+	exit 1
+fi
+
+# vi:ft=sh