From ea618c5e257a6aabded76e63567ec0e7b99ac6c4 Mon Sep 17 00:00:00 2001
From: Bryce Kwon <bryce@brycekwon.com>
Date: Mon, 24 Aug 2026 16:21:18 -1000
Subject: Renumber the test scripts into themed ranges

    t000x  the ground the suite stands on: git version, html validity,
           the cache
    t01xx  page content, one script per page
    t02xx  features that cut across pages: filters, submodule links,
           dates, limits
    t03xx  defence, the security regressions and the $HOME promise
    t04xx  the helper tools under tools/
---
 tests/t0002-html-validity.sh | 61 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)
 create mode 100755 tests/t0002-html-validity.sh

(limited to 'tests/t0002-html-validity.sh')

diff --git a/tests/t0002-html-validity.sh b/tests/t0002-html-validity.sh
new file mode 100755
index 0000000..842437c
--- /dev/null
+++ b/tests/t0002-html-validity.sh
@@ -0,0 +1,61 @@
+#!/bin/sh
+
+# Runs the tidy checker over one page of each kind cgit renders, so that markup
+# broken enough to confuse a browser is caught here rather than in the browser.
+# Only the shape of the markup matters, since what the pages actually say is
+# the business of the t01xx scripts. Tidy is optional and old versions of it
+# predate the elements cgit uses, so the whole file steps aside when a usable
+# one cannot be found.
+
+test_description='Validate html with tidy'
+. ./setup.sh
+
+test_url()
+{
+	tidy_options="-eq"
+	test -z "$NO_TIDY_WARNINGS" ||
+		tidy_options="$tidy_options --show-warnings no"
+	cgit_url "$1" >tidy-$test_count.tmp || return
+	# Tidy reads what it is given as a whole document, so the response
+	# headers are dropped before it sees the page.
+	strip_headers <tidy-$test_count.tmp >tidy-$test_count || return
+	"$tidy" $tidy_options tidy-$test_count
+	status=$?
+
+	# Tidy leaves with 1 for warnings and 2 for errors, and only an error is
+	# worth failing the test over.
+	if test $status = 2
+	then
+		false
+	else
+		:
+	fi
+}
+
+tidy=$(which tidy 2>/dev/null)
+test -n "$tidy" || {
+	skip_all='Skipping html validation tests: tidy not found'
+	test_done
+	exit
+}
+
+# Releases of tidy that predate HTML5 reject the semantic elements cgit emits,
+# header, nav, main and footer among them, reporting each as an error. Skip the
+# validation unless tidy is new enough to understand them.
+printf '<!DOCTYPE html>\n<html lang="en"><head><title>t</title></head><body><header>x</header></body></html>\n' \
+	| "$tidy" -q -e >/dev/null 2>&1
+test $? -ge 2 && {
+	skip_all='Skipping html validation tests: tidy is too old for HTML5'
+	test_done
+	exit
+}
+
+test_expect_success 'index page' 'test_url ""'
+test_expect_success 'foo' 'test_url "foo"'
+test_expect_success 'foo/log' 'test_url "foo/log"'
+test_expect_success 'foo/tree' 'test_url "foo/tree"'
+test_expect_success 'foo/tree/file-1' 'test_url "foo/tree/file-1"'
+test_expect_success 'foo/commit' 'test_url "foo/commit"'
+test_expect_success 'foo/diff' 'test_url "foo/diff"'
+
+test_done
-- 
cgit v2.8.0