From c84384e6608368a13a774d6d33a8cc32da7cf209 Mon Sep 17 00:00:00 2001
From: tobi <31960611+tsmethurst@users.noreply.github.com>
Date: Tue, 19 Jul 2022 15:21:17 +0200
Subject: [bugfix] html escape special characters in text instead of totally
 removing them (#719)

* remove minify dependency

* tidy up some tests

* remove pre + postformat funcs

* rework sanitization + formatting

* update tests

* add some more markdown tests
---
 internal/text/sanitize.go | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'internal/text/sanitize.go')

diff --git a/internal/text/sanitize.go b/internal/text/sanitize.go
index d4faabbb1..96b7ef994 100644
--- a/internal/text/sanitize.go
+++ b/internal/text/sanitize.go
@@ -19,7 +19,9 @@
 package text
 
 import (
+	"html"
 	"regexp"
+	"strings"
 
 	"github.com/microcosm-cc/bluemonday"
 )
@@ -59,7 +61,8 @@ func SanitizeHTML(in string) string {
 // SanitizePlaintext runs text through basic sanitization. This removes
 // any html elements that were in the string, and returns clean plaintext.
 func SanitizePlaintext(in string) string {
-	content := preformat(in)
+	content := html.UnescapeString(in)
 	content = removeHTML(content)
-	return postformat(content)
+	content = html.UnescapeString(content)
+	return strings.TrimSpace(content)
 }
-- 
cgit v1.2.3