fix: keep non-breaking spaces in text

Since the `u` flag was added to the whitespace regex in TextConverter
(7f03acf), `\s` also matches U+00A0, so ` ` and literal non-breaking
spaces were turned into regular spaces. Leave U+00A0 out of the collapse.

EmphasisConverter used trim(), which does not strip U+00A0, so a
non-breaking space at the edge of <em>/<strong> would now end up inside
the delimiters (`**Total:&nbsp;**`), where it stops them from flanking the
text. Strip it there too; like before, it becomes a regular space outside
the delimiters.

Fixes #258

src/Converter/EmphasisConverter.php

@@ -40,7 +40,11 @@ class EmphasisConverter implements ConverterInterface, ConfigurationAwareInterfa
         $tag   = $this->getNormTag($element);
         $value = $element->getValue();
 
-        if (! \trim($value)) {
+        // Unlike trim(), this also strips non-breaking spaces, which would keep the delimiters from flanking the text
+        $content = \preg_replace('~^\s+|\s+$~u', '', $value);
+        \assert(\is_string($content));
+
+        if (! $content) {
             return $value;
         }
 
@@ -50,8 +54,8 @@ class EmphasisConverter implements ConverterInterface, ConfigurationAwareInterfa
             $style = Coerce::toString($this->config->getOption('bold_style'));
         }
 
-        $prefix = \ltrim($value) !== $value ? ' ' : '';
-        $suffix = \rtrim($value) !== $value ? ' ' : '';
+        $prefix = \preg_match('~^\s~u', $value) === 1 ? ' ' : '';
+        $suffix = \preg_match('~\s$~u', $value) === 1 ? ' ' : '';
 
         /* If this node is immediately preceded or followed by one of the same type don't emit
          * the start or end $style, respectively. This prevents <em>foo</em><em>bar</em> from
@@ -60,7 +64,7 @@ class EmphasisConverter implements ConverterInterface, ConfigurationAwareInterfa
         $preStyle  = $this->getNormTag($element->getPreviousSibling()) === $tag ? '' : $style;
         $postStyle = $this->getNormTag($element->getNextSibling()) === $tag ? '' : $style;
 
-        return $prefix . $preStyle . \trim($value) . $postStyle . $suffix;
+        return $prefix . $preStyle . $content . $postStyle . $suffix;
     }
 
     /**

src/Converter/TextConverter.php

@@ -15,8 +15,8 @@ class TextConverter implements ConverterInterface
         // Remove leftover \n at the beginning of the line
         $markdown = \ltrim($markdown, "\n");
 
-        // Replace sequences of invisible characters with spaces
-        $markdown = \preg_replace('~\s+~u', ' ', $markdown);
+        // Replace sequences of invisible characters with spaces, keeping non-breaking spaces
+        $markdown = \preg_replace('~[^\S\x{00A0}]+~u', ' ', $markdown);
         \assert(\is_string($markdown));
 
         // Escape the following characters: '*', '_', '[', ']' and '\'

tests/HtmlConverterTest.php

@@ -378,6 +378,14 @@ EOT;
         $this->assertHtmlGivesMarkdown('<code>&lt;p&gt;Some sample HTML&lt;/p&gt;</code>', '`<p>Some sample HTML</p>`');
     }
 
+    public function testNonBreakingSpaces(): void
+    {
+        $this->assertHtmlGivesMarkdown('<p>This is a test and&nbsp;test</p>', "This is a test and\u{00A0}test");
+        $this->assertHtmlGivesMarkdown("<p>12,50\u{00A0}\u{00A0}€ \n total</p>", "12,50\u{00A0}\u{00A0}€ total");
+        $this->assertHtmlGivesMarkdown('<p><strong>Total:&nbsp;</strong>12,50&nbsp;€</p>', "**Total:** 12,50\u{00A0}€");
+        $this->assertHtmlGivesMarkdown('<p>a<em>&nbsp;</em>b</p>', "a\u{00A0}b");
+    }
+
     public function testSetOption(): void
     {
         $markdown = new HtmlConverter();