`Helper\Html` support UTF-8 HTML input

Assume UTF-8 encoding. Not assuming UTF-8 would mangle text such as "русский"

Fixes #444

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 ### Fixed
 
 - Subtotal 9 in a group that has other subtotals 9 exclude the totals of the other subtotals in the range - [#332](https://github.com/PHPOffice/PhpSpreadsheet/issues/332)
+- `Helper\Html` support UTF-8 HTML input - [#444](https://github.com/PHPOffice/PhpSpreadsheet/issues/444)
 
 ## [1.2.1] - 2018-04-10
 

src/PhpSpreadsheet/Helper/Html.php

@@ -603,6 +603,13 @@ class Html
         $this->stringData = '';
     }
 
+    /**
+     * Parse HTML formatting and return the resulting RichText.
+     *
+     * @param string $html
+     *
+     * @return RichText
+     */
     public function toRichTextObject($html)
     {
         $this->initialise();
@@ -611,8 +618,8 @@ class Html
         $dom = new DOMDocument();
         //    Load the HTML file into the DOM object
         //  Note the use of error suppression, because typically this will be an html fragment, so not fully valid markup
-        @$dom->loadHTML($html);
-
+        $prefix = '<?xml encoding="UTF-8">';
+        @$dom->loadHTML($prefix . $html, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
         //    Discard excess white space
         $dom->preserveWhiteSpace = false;
 

tests/PhpSpreadsheetTests/Helper/HtmlTest.php

@@ -0,0 +1,33 @@
+<?php
+
+namespace PhpOffice\PhpSpreadsheetTests\Helper;
+
+use PhpOffice\PhpSpreadsheet\Helper\Html;
+use PHPUnit\Framework\TestCase;
+
+class HtmlTest extends TestCase
+{
+    /**
+     * @dataProvider providerUtf8EncodingSupport
+     *
+     * @param mixed $expected
+     * @param mixed $input
+     */
+    public function testUtf8EncodingSupport($expected, $input)
+    {
+        $html = new Html();
+        $actual = $html->toRichTextObject($input);
+
+        self::assertSame($expected, $actual->getPlainText());
+    }
+
+    public function providerUtf8EncodingSupport()
+    {
+        return [
+            ['foo', 'foo'],
+            ['können', 'können'],
+            ['русский', 'русский'],
+            ["foo\nbar", '<p>foo</p><p>bar</p>'],
+        ];
+    }
+}