Correctly match newlines whitin htmltags. (#122)

* Correctly match newlines in tags. * Revert regex to current implementation while adding the PCRE_DOTALL modifier. --------- Co-authored-by: Anne Zijlstra <[email protected]>
caxy · Jan 22, 2025 · acd361c · acd361c
1 parent 88f817a
commit acd361c
Show file tree

Hide file tree

Showing 2 changed files with 26 additions and 1 deletion.
diff --git a/lib/Caxy/HtmlDiff/AbstractDiff.php b/lib/Caxy/HtmlDiff/AbstractDiff.php
@@ -433,7 +433,7 @@ protected function convertHtmlToListOfWords(string $text) : array
         // Normalize no-break-spaces to regular spaces
         $text = str_replace("\xc2\xa0", ' ', $text);
 
-        preg_match_all('/<.+?>|[^<]+/mu', $text, $sentencesAndTags, PREG_SPLIT_NO_EMPTY);
+        preg_match_all('/<.+?>|[^<]+/mus', $text, $sentencesAndTags, PREG_SPLIT_NO_EMPTY);
 
         foreach ($sentencesAndTags[0] as $sentenceOrHtmlTag) {
             if ($sentenceOrHtmlTag === '') {

diff --git a/tests/fixtures/HtmlDiff/multiline-tag.html b/tests/fixtures/HtmlDiff/multiline-tag.html
@@ -0,0 +1,25 @@
+<options>
+    <option type="boolean" name="setKeepNewLines" value="true" />
+    <option type="boolean" name="setPurifierEnabled" value="false" />
+</options>
+
+<oldText>
+	<li
+		attribute="value">
+		value
+	</li>
+</oldText>
+
+<newText>
+	<li
+		attribute="value">
+		newvalue
+	</li>
+</newText>
+
+<expected>
+	<li
+		attribute="value">
+		<del class="diffmod">value</del><ins class="diffmod">newvalue</ins>
+	</li>
+</expected>