From 9e2bef146e9d8a43c2025bc9d04df400330874d5 Mon Sep 17 00:00:00 2001 From: Matthew Holt Date: Thu, 17 Sep 2015 16:23:30 -0600 Subject: [PATCH] middleware: Added StripHTML to Context type --- middleware/context.go | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/middleware/context.go b/middleware/context.go index ade03e112..6c45d0337 100644 --- a/middleware/context.go +++ b/middleware/context.go @@ -131,6 +131,40 @@ func (c Context) Truncate(input string, length int) string { return input } +// StripHTML returns s without HTML tags. It is fairly naive +// but works with most valid HTML inputs. +func (c Context) StripHTML(s string) string { + var buf bytes.Buffer + var inTag, inQuotes bool + var tagStart int + for i, ch := range s { + if inTag { + if ch == '>' && !inQuotes { + inTag = false + } else if ch == '<' && !inQuotes { + // false start + buf.WriteString(s[tagStart:i]) + tagStart = i + } else if ch == '"' { + inQuotes = !inQuotes + } + continue + } + if ch == '<' { + inTag = true + tagStart = i + continue + } + buf.WriteRune(ch) + } + if inTag { + // false start + buf.WriteString(s[tagStart:]) + inTag = false + } + return buf.String() +} + // StripExt returns the input string without the extension, // which is the suffix starting with the final '.' character // but not before the final path separator ('/') character.