From 3854a6fa6c323d1c09aa71a0626c9eef62709294 Mon Sep 17 00:00:00 2001
From: Bjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com>
Date: Wed, 25 May 2022 10:56:14 +0200
Subject: Fix Plainify edge cases

This commit replaces the main part of `helpers.StripHTML` with Go's implementation in its html/template package.

It's a little slower, but correctness is more important:

```bash
BenchmarkStripHTMLOld-10    	  680316	      1764 ns/op	     728 B/op	       4 allocs/op
BenchmarkStripHTMLNew-10    	  384520	      3099 ns/op	    2089 B/op	      10 allocs/op
```

Fixes #9199
Fixes #9909
Closes #9410
---
 helpers/content.go      | 40 ----------------------------------------
 helpers/content_test.go | 38 --------------------------------------
 2 files changed, 78 deletions(-)

(limited to 'helpers')

diff --git a/helpers/content.go b/helpers/content.go
index 835663b76..d04e34a07 100644
--- a/helpers/content.go
+++ b/helpers/content.go
@@ -34,7 +34,6 @@ import (
 
 	"github.com/gohugoio/hugo/markup"
 
-	bp "github.com/gohugoio/hugo/bufferpool"
 	"github.com/gohugoio/hugo/config"
 )
 
@@ -104,45 +103,6 @@ func NewContentSpec(cfg config.Provider, logger loggers.Logger, contentFs afero.
 	return spec, nil
 }
 
-var stripHTMLReplacer = strings.NewReplacer("\n", " ", "</p>", "\n", "<br>", "\n", "<br />", "\n")
-
-// StripHTML accepts a string, strips out all HTML tags and returns it.
-func StripHTML(s string) string {
-	// Shortcut strings with no tags in them
-	if !strings.ContainsAny(s, "<>") {
-		return s
-	}
-	s = stripHTMLReplacer.Replace(s)
-
-	// Walk through the string removing all tags
-	b := bp.GetBuffer()
-	defer bp.PutBuffer(b)
-	var inTag, isSpace, wasSpace bool
-	for _, r := range s {
-		if !inTag {
-			isSpace = false
-		}
-
-		switch {
-		case r == '<':
-			inTag = true
-		case r == '>':
-			inTag = false
-		case unicode.IsSpace(r):
-			isSpace = true
-			fallthrough
-		default:
-			if !inTag && (!isSpace || (isSpace && !wasSpace)) {
-				b.WriteRune(r)
-			}
-		}
-
-		wasSpace = isSpace
-
-	}
-	return b.String()
-}
-
 // stripEmptyNav strips out empty <nav> tags from content.
 func stripEmptyNav(in []byte) []byte {
 	return bytes.Replace(in, []byte("<nav>\n</nav>\n\n"), []byte(``), -1)
diff --git a/helpers/content_test.go b/helpers/content_test.go
index 4b67b44f0..54b7ef3f9 100644
--- a/helpers/content_test.go
+++ b/helpers/content_test.go
@@ -52,44 +52,6 @@ func TestTrimShortHTML(t *testing.T) {
 	}
 }
 
-func TestStripHTML(t *testing.T) {
-	type test struct {
-		input, expected string
-	}
-	data := []test{
-		{"<h1>strip h1 tag <h1>", "strip h1 tag "},
-		{"<p> strip p tag </p>", " strip p tag "},
-		{"</br> strip br<br>", " strip br\n"},
-		{"</br> strip br2<br />", " strip br2\n"},
-		{"This <strong>is</strong> a\nnewline", "This is a newline"},
-		{"No Tags", "No Tags"},
-		{`<p>Summary Next Line.
-<figure >
-
-        <img src="/not/real" />
-
-
-</figure>
-.
-More text here.</p>
-
-<p>Some more text</p>`, "Summary Next Line.  . More text here.\nSome more text\n"},
-	}
-	for i, d := range data {
-		output := StripHTML(d.input)
-		if d.expected != output {
-			t.Errorf("Test %d failed. Expected %q got %q", i, d.expected, output)
-		}
-	}
-}
-
-func BenchmarkStripHTML(b *testing.B) {
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		StripHTML(tstHTMLContent)
-	}
-}
-
 func TestStripEmptyNav(t *testing.T) {
 	c := qt.New(t)
 	cleaned := stripEmptyNav([]byte("do<nav>\n</nav>\n\nbedobedo"))
-- 
cgit v1.2.3