Merge pull request #41 from matecat/fix-apostrophe-in-simil-html

Fix single/double quote in strings (removed obsolete code)
matecat · Nov 28, 2023 · bbeee5e · bbeee5e
2 parents 02ef243 + 453adbb
commit bbeee5e
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 8 deletions.
diff --git a/src/Filters/Html/HtmlParser.php b/src/Filters/Html/HtmlParser.php
@@ -124,10 +124,12 @@ public function transform( $segment ) {
             } elseif ( $state == static::STATE_HTML ) {
                 switch ( $char ) {
                     case '<':
-                        // ignore '<' if inside a quote
-                        if ( $in_quote_char ) {
-                            break;
-                        }
+                        // is not possible to have angle brackets inside a tag, this case can not happen
+                        // this code would ignore '>' if inside a quote, useless
+                        // for more info see https://www.w3.org/TR/xml/#charsets
+//                        if ( $in_quote_char ) {
+//                            break;
+//                        }
 
                         // if we found a second less than symbol the first one IS NOT a tag,
                         // treat the html_buffer as plain text and attach to the output
@@ -136,10 +138,12 @@ public function transform( $segment ) {
                         break;
 
                     case '>':
-                        // ignore '>' if inside a quote
-                        if ( $in_quote_char ) {
-                            break;
-                        }
+                        // is not possible to have angle brackets inside a tag, this case can not happen
+                        // this code would ignore '>' if inside a quote, useless
+                        // for more info see https://www.w3.org/TR/xml/#charsets
+//                        if ( $in_quote_char ) {
+//                            break;
+//                        }
 
                         if ( in_array( substr( $html_buffer, 0, 8 ), [ '<script ', '<style', '<script', '<style ' ] ) ) {
                             $html_buffer .= $char;

diff --git a/tests/MateCatSubFilteringTest.php b/tests/MateCatSubFilteringTest.php
@@ -41,6 +41,16 @@ public function testSimpleString() {
         $this->assertEquals( $segmentL1, $filter->fromLayer2ToLayer1( $segmentL2 ) );
     }
 
+    public function testHTMLStringWithApostrophe()
+    {
+        $filter = $this->getFilterInstance();
+
+        $segment   = "&lt;Value&gt; &lt;![CDATA[Visitez Singapour et détendez-vous sur l'île de Langkawi]]&gt; &lt;/Value&gt;";
+        $segmentL1 = $filter->fromLayer0ToLayer1( $segment );
+
+        $this->assertEquals( $segment, $filter->fromLayer1ToLayer0( $segmentL1 ) );
+    }
+
     /**
      * @throws Exception
      */