From acb58f1c2ee6e32dee8142eaec4f2cfeee585a0d Mon Sep 17 00:00:00 2001
From: Gabor Gyorvari <scr34m@gmail.com>
Date: Wed, 11 Jan 2017 19:10:59 +0100
Subject: [PATCH] New ignore argument to exclude files and folders with glob
 style matching

---
 README.md | 17 ++++++++-------
 scan.php  | 63 ++++++++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 65 insertions(+), 15 deletions(-)

diff --git a/README.md b/README.md
index d8ff30d..832af26 100644
--- a/README.md
+++ b/README.md
@@ -9,15 +9,18 @@ How to use?
 
 ```
 $ php ./scan.php -h
-Usage scan.php -d <directory> [-e=.php] [--hide-ok] [--hide-whitelist]
-    -d                Directory for searching
-    -e=.php           Extension
-    --hide-ok         Hide OK aka not infected messages
-    --hide-whitelist  Hide whitelisted messages
-    --extra-check     Adds GoogleBot and htaccess to Scan List
-    --follow-symlink  Follow symlinked directories 
+Usage scan.php -d <directory> [-i=<directory|file>] [-e=.php] [--hide-ok] [--hide-whitelist]
+    -d                    Directory for searching
+    -e=.php               Extension
+    -i=<directory|file>   Directory of file to igonre
+    --hide-ok             Hide OK aka not infected messages
+    --hide-whitelist      Hide whitelisted messages
+    --extra-check         Adds GoogleBot and htaccess to Scan List
+    --follow-symlink      Follow symlinked directories
 ```
 
+Ignore argument could be used multiple times and accept glob style matching ex.: "cache*", "??-cache.php" or "/cache" etc.
+
 Whitelisting
 ------------
 
diff --git a/scan.php b/scan.php
index b0614b7..45be34a 100644
--- a/scan.php
+++ b/scan.php
@@ -28,6 +28,7 @@ class MalwareScanner
     private $flagHideWhitelist = false;
     private $extraCheck = false;
     private $whitelist = array();
+    private $ignore = array();
     private $stat = array(
         'directories' => 0,
         'files_scanned' => 0,
@@ -37,7 +38,7 @@ class MalwareScanner
 
     public function __construct()
     {
-        $options = getopt('hd:e::', array('hide-ok', 'hide-whitelist', 'extra-check', 'follow-symlink'));
+        $options = getopt('hd:e::i::', array('hide-ok', 'hide-whitelist', 'extra-check', 'follow-symlink'));
         if (isset($options['h'])) {
             $this->showHelp();
         } else {
@@ -48,6 +49,9 @@ class MalwareScanner
                 }
                 $this->extension = strtolower($ext);
             }
+            if (isset($options['i'])) {
+                $this->ignore = is_array($options['i']) ? $options['i'] : array($options['i']);
+            }
             if (isset($options['hide-ok'])) {
                 $this->flagHideOk = true;
             }
@@ -110,6 +114,9 @@ class MalwareScanner
             if ($file == '.' || $file == '..') {
                 continue;
             }
+            if ($this->isIgnored($dir . $file)) {
+                continue;
+            }
             if (!$this->followSymlink && is_link($dir . $file)) {
                 continue;
             }
@@ -384,6 +391,45 @@ class MalwareScanner
         return true;
     }
 
+    private function isIgnored($pathname)
+    {
+        foreach ($this->ignore as $pattern) {
+            $match = $this->pathMatches($pathname, $pattern);
+            if ($match) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * @see http://stackoverflow.com/a/13914119
+     */
+    private function pathMatches($path, $pattern, $ignoreCase = false)
+    {
+        $expr = preg_replace_callback(
+            '/[\\\\^$.[\\]|()?*+{}\\-\\/]/',
+            function ($matches) {
+                switch ($matches[0]) {
+                    case '*':
+                        return '.*';
+                    case '?':
+                        return '.';
+                    default:
+                        return '\\' . $matches[0];
+                }
+            },
+            $pattern
+        );
+
+        $expr = '/' . $expr . '/';
+        if ($ignoreCase) {
+            $expr .= 'i';
+        }
+
+        return (bool)preg_match($expr, $path);
+    }
+
     private function out($color, $serv, $text)
     {
         echo $color . ' ' . $serv . ' ' . self::ANSI_OFF . $text . PHP_EOL;
@@ -391,13 +437,14 @@ class MalwareScanner
 
     private function showHelp()
     {
-        echo 'Usage scan.php -d <directory> [-e=.php] [--hide-ok] [--hide-whitelist]' . PHP_EOL;
-        echo '    -d                Directory for searching' . PHP_EOL;
-        echo '    -e=.php           Extension' . PHP_EOL;
-        echo '    --hide-ok         Hide OK aka not infected messages' . PHP_EOL;
-        echo '    --hide-whitelist  Hide whitelisted messages' . PHP_EOL;
-        echo '    --extra-check     Adds GoogleBot and htaccess to Scan List' . PHP_EOL;
-        echo '    --follow-symlink  Follow symlinked directories' . PHP_EOL;
+        echo 'Usage scan.php -d <directory> [-i=<directory|file>] [-e=.php] [--hide-ok] [--hide-whitelist]' . PHP_EOL;
+        echo '    -d                    Directory for searching' . PHP_EOL;
+        echo '    -e=.php               Extension' . PHP_EOL;
+        echo '    -i=<directory|file>   Directory of file to igonre' . PHP_EOL;
+        echo '    --hide-ok             Hide OK aka not infected messages' . PHP_EOL;
+        echo '    --hide-whitelist      Hide whitelisted messages' . PHP_EOL;
+        echo '    --extra-check         Adds GoogleBot and htaccess to Scan List' . PHP_EOL;
+        echo '    --follow-symlink      Follow symlinked directories' . PHP_EOL;
     }
 
 }