Update HtmlMinify.php

ProVisionBG · Jan 18, 2017 · 2d87c49 · 2d87c49
1 parent 6dca30e
commit 2d87c49
Showing 1 changed file with 123 additions and 14 deletions.
diff --git a/app/Http/Middleware/HtmlMinify.php b/app/Http/Middleware/HtmlMinify.php
@@ -48,20 +48,46 @@ public function handle($request, Closure $next)
         if ($this->isAResponseObject($response) && $this->isAnHtmlResponse($response) && !Administration::routeInAdministration()) {
             $output = $response->getContent();
 
-            /* remove comments */
-            $output = preg_replace('%/\*(?:(?!\*/|/\*).)*+(?:/\*(?:(?!\*/|/\*).)*+\*/(?:(?!\*/|/\*).)*+)*+.*?\*/%s', '', $output);
-            $output = preg_replace('/<!--.*?-->/simx', '', $output);
-            /* remove tabs, spaces, newlines, etc. */
-            $output = str_replace(array(
-                "\r\n",
-                "\r",
-                "\n",
-                "\t",
-                '     ',
-                '    '
-            ), '', $output);
-
-            $output = trim($output);
+            //convert encoding to utf8
+            $output = mb_convert_encoding($output, 'utf8');
+
+            if (strpos($output, '<pre>') !== false) {
+                $replace = array(
+                    '/<!--[^\[](.*?)[^\]]-->/s' => '',
+                    "/<\?php/" => '<?php ',
+                    "/\r/" => '',
+                    "/>\n</" => '><',
+                    "/>\s+\n</" => '><',
+                    "/>\n\s+</" => '><'
+                );
+            } else {
+                $replace = array(
+                    '/<!--[^\[](.*?)[^\]]-->/s' => '',
+                    "/<\?php/" => '<?php ',
+                    "/\n([\S])/" => '$1',
+                    "/\r/" => '',
+                    "/\n/" => '',
+                    "/\t/" => '',
+                    "/ +/" => ' '
+                );
+            }
+
+            // Remove htmlcomment;
+            $additionaly = array(
+                // strip whitespaces after tags, except space
+                '/\>[^\S ]+/s' => '>',
+                // strip whitespaces before tags, except space
+                '/[^\S ]+\</s' => '<',
+                // shorten multiple whitespace sequences
+                '/(\s)+/s' => '\\1',
+                // Remove htmlcomment
+                '!/\*.*?\*/!s' => '',
+                '/\n\s*\n/' => ''
+            );
+
+            $output = preg_replace(array_keys($replace), array_values($replace), $output);
+            $output = preg_replace(array_keys($additionaly), array_values($additionaly), $output);
+            $output = $output = $this->compress($output);
 
             $output .= "\n\n" . '<!--
 			
@@ -111,4 +137,87 @@ protected function isAnHtmlResponse(Response $response)
         $type = $response->headers->get('Content-Type');
         return strtolower(strtok($type, ';')) === 'text/html';
     }
+
+    function compress($buffer)
+    {
+        /**
+         * To remove useless whitespace from generated HTML, except for Javascript.
+         * [Regex Source]
+         * https://github.com/bcit-ci/codeigniter/wiki/compress-html-output
+         * http://stackoverflow.com/questions/5312349/minifying-final-html-output-using-regular-expressions-with-codeigniter
+         */
+        $regexRemoveWhiteSpace = '%# Collapse ws everywhere but in blacklisted elements.
+        (?>             # Match all whitespaces other than single space.
+          [^\S ]\s*     # Either one [\t\r\n\f\v] and zero or more ws,
+        | \s{2,}        # or two or more consecutive-any-whitespace.
+        ) # Note: The remaining regex consumes no text at all...
+        (?=             # Ensure we are not in a blacklist tag.
+          (?:           # Begin (unnecessary) group.
+            (?:         # Zero or more of...
+              [^<]++    # Either one or more non-"<"
+            | <         # or a < starting a non-blacklist tag.
+              (?!/?(?:textarea|pre)\b)
+            )*+         # (This could be "unroll-the-loop"ified.)
+          )             # End (unnecessary) group.
+          (?:           # Begin alternation group.
+            <           # Either a blacklist start tag.
+            (?>textarea|pre)\b
+          | \z          # or end of file.
+          )             # End alternation group.
+        )  # If we made it here, we are not in a blacklist tag.
+        %ix';
+
+        $regexRemoveWhiteSpace = '%(?>[^\S ]\s*| \s{2,})(?=(?:(?:[^<]++| <(?!/?(?:textarea|pre)\b))*+)(?:<(?>textarea|pre)\b|\z))%ix';
+        $re = '%# Collapse whitespace everywhere but in blacklisted elements.
+        (?>             # Match all whitespans other than single space.
+          [^\S ]\s*     # Either one [\t\r\n\f\v] and zero or more ws,
+        | \s{2,}        # or two or more consecutive-any-whitespace.
+        ) # Note: The remaining regex consumes no text at all...
+        (?=             # Ensure we are not in a blacklist tag.
+          [^<]*+        # Either zero or more non-"<" {normal*}
+          (?:           # Begin {(special normal*)*} construct
+            <           # or a < starting a non-blacklist tag.
+            (?!/?(?:textarea|pre|script)\b)
+            [^<]*+      # more non-"<" {normal*}
+          )*+           # Finish "unrolling-the-loop"
+          (?:           # Begin alternation group.
+            <           # Either a blacklist start tag.
+            (?>textarea|pre|script)\b
+          | \z          # or end of file.
+          )             # End alternation group.
+        )  # If we made it here, we are not in a blacklist tag.
+        %Six';
+
+        // $new_buffer = preg_replace('/<!--(.*|\n)-->/Uis', " ", sanitize_output($buffer));
+        // $new_buffer = preg_replace('/\s+/', " ", sanitize_output($new_buffer));
+        $new_buffer = mb_ereg_replace($regexRemoveWhiteSpace, " ", $this->sanitize_output($buffer));
+
+        // We are going to check if processing has working
+        if ($new_buffer === null) {
+            $new_buffer = $buffer;
+        }
+
+        return $new_buffer;
+    }
+
+    function sanitize_output($buffer)
+    {
+        $search = array(
+            '/\>[^\S ]+/s', // strip whitespaces after tags, except space
+            '/[^\S ]+\</s', // strip whitespaces before tags, except space
+            '/(\s)+/s', // shorten multiple whitespace sequences
+            '!/\*.*?\*/!s', // Remove htmlcomment
+            '/\n\s*\n/'
+        ); // Remove htmlcomment
+
+        $replace = array(
+            '>',
+            '<',
+            '\\1',
+            '',
+            ''
+        );
+        $buffer = preg_replace($search, $replace, $buffer);
+        return $buffer;
+    }
 }