Refactor lexer instantiation logic with exceptions and forced line tracking.

Signed-off-by: Edward Z. Yang <edwardzyang@thewritingpot.com>

NEWS

@@ -10,6 +10,8 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
 ==========================
 
 3.1.2, unknown release date
+# Using %Core.CollectErrors forces line number/column tracking on, whereas
+  previously you could theoretically turn it off.
 ! %Output.AttrSort for when you need your attributes in alphabetical order to
   deal with a bug in FCKEditor. Requested by frank farmer.
 ! Enable HTML comments when %HTML.Trusted is on. Requested by Waldo Jaquith.
@@ -49,6 +51,9 @@ NEWS ( CHANGELOG and HISTORY )                                     HTMLPurifier
   not collapsed by URIFilter_MakeAbsolute.
 - Fix bug with anonymous modules operating on SafeEmbed or SafeObject elements
   by reordering their addition.
+- Will now throw exception on many error conditions during lexer creation; also
+  throw an exception when MaintainLineNumbers is true, but a non-tracksLineNumbers
+  is being used.
 . Strategy_MakeWellFormed now operates in-place, saving memory and allowing
   for more interesting filter-backtracking
 . New HTMLPurifier_Injector->rewind() functionality, allows injectors to rewind

library/HTMLPurifier/Lexer.php

@@ -42,6 +42,12 @@
 class HTMLPurifier_Lexer
 {
     
+    /**
+     * Whether or not this lexer implements line-number/column-number tracking.
+     * If it does, set to true.
+     */
+    public $tracksLineNumbers = false;
+    
     // -- STATIC ----------------------------------------------------------
     
     /**
@@ -70,20 +76,19 @@ class HTMLPurifier_Lexer
             $lexer = $config->get('Core', 'LexerImpl');
         }
         
+        $needs_tracking =
+            $config->get('Core', 'MaintainLineNumbers') ||
+            $config->get('Core', 'CollectErrors');
+        
+        $inst = null;
         if (is_object($lexer)) {
-            return $lexer;
+            $inst = $lexer;
-        }
+        } else {
             
             if (is_null($lexer)) { do {
                 // auto-detection algorithm
                 
-            // once PHP DOM implements native line numbers, or we
+                if ($needs_tracking) {
-            // hack out something using XSLT, remove this stipulation
-            $line_numbers = $config->get('Core', 'MaintainLineNumbers');
-            if (
-                $line_numbers === true ||
-                ($line_numbers === null && $config->get('Core', 'CollectErrors'))
-            ) {
                     $lexer = 'DirectLex';
                     break;
                 }
@@ -101,14 +106,28 @@ class HTMLPurifier_Lexer
             // instantiate recognized string names
             switch ($lexer) {
                 case 'DOMLex':
-                return new HTMLPurifier_Lexer_DOMLex();
+                    $inst = new HTMLPurifier_Lexer_DOMLex();
+                    break;
                 case 'DirectLex':
-                return new HTMLPurifier_Lexer_DirectLex();
+                    $inst = new HTMLPurifier_Lexer_DirectLex();
+                    break;
                 case 'PH5P':
-                return new HTMLPurifier_Lexer_PH5P();
+                    $inst = new HTMLPurifier_Lexer_PH5P();
+                    break;
                 default:
-                trigger_error("Cannot instantiate unrecognized Lexer type " . htmlspecialchars($lexer), E_USER_ERROR);
+                    throw new HTMLPurifier_Exception("Cannot instantiate unrecognized Lexer type " . htmlspecialchars($lexer));
             }
+        }
+        
+        if (!$inst) throw new HTMLPurifier_Exception('No lexer was instantiated');
+        
+        // once PHP DOM implements native line numbers, or we
+        // hack out something using XSLT, remove this stipulation
+        if ($needs_tracking && !$inst->tracksLineNumbers) {
+            throw new HTMLPurifier_Exception('Cannot use lexer that does not support line numbers with Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)');
+        }
+        
+        return $inst;
         
     }
     

library/HTMLPurifier/Lexer/DirectLex.php

@@ -13,6 +13,8 @@
 class HTMLPurifier_Lexer_DirectLex extends HTMLPurifier_Lexer
 {
     
+    public $tracksLineNumbers = true;
+    
     /**
      * Whitespace characters for str(c)spn.
      */

tests/HTMLPurifier/LexerTest.php

@@ -29,6 +29,25 @@ class HTMLPurifier_LexerTest extends HTMLPurifier_Harness
         $this->assertIsA($lexer, 'HTMLPurifier_Lexer_DirectLex');
     }
     
+    function test_create_objectLexerImpl() {
+        $this->config->set('Core', 'LexerImpl', new HTMLPurifier_Lexer_DirectLex());
+        $lexer = HTMLPurifier_Lexer::create($this->config);
+        $this->assertIsA($lexer, 'HTMLPurifier_Lexer_DirectLex');
+    }
+    
+    function test_create_unknownLexer() {
+        $this->config->set('Core', 'LexerImpl', 'AsdfAsdf');
+        $this->expectException(new HTMLPurifier_Exception('Cannot instantiate unrecognized Lexer type AsdfAsdf'));
+        HTMLPurifier_Lexer::create($this->config);
+    }
+    
+    function test_create_incompatibleLexer() {
+        $this->config->set('Core', 'LexerImpl', 'DOMLex');
+        $this->config->set('Core', 'MaintainLineNumbers', true);
+        $this->expectException(new HTMLPurifier_Exception('Cannot use lexer that does not support line numbers with Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)'));
+        HTMLPurifier_Lexer::create($this->config);
+    }
+    
     // HTMLPurifier_Lexer->parseData() -----------------------------------------
     
     function assertParseData($input, $expect = true) {