Make EncodingTester usable in testing parsed state

This change updates EncodingTester to make it test the result for cases
when the expected character encoding is not limited to what can be
determined by checking only the first 1024 bytes of the input stream.

Otherwise, without this change, EncodingTester is limited to only being
useful for testing the output of the meta prescan.

Author: sideshowbarker

test-src/nu/validator/htmlparser/test/EncodingTester.java

@@ -1,6 +1,6 @@
 /*
  * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2008 Mozilla Foundation
+ * Copyright (c) 2008-2020 Mozilla Foundation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a 
  * copy of this software and associated documentation files (the "Software"), 
@@ -36,10 +36,21 @@
 
 public class EncodingTester {
 
+    private int sniffingLimit = 16384;
+
     private final InputStream aggregateStream;
 
     private final StringBuilder builder = new StringBuilder();
 
+    /**
+     * @param aggregateStream
+     * @param sniffingLimit
+     */
+    public EncodingTester(InputStream aggregateStream, int sniffingLimit) {
+        this.sniffingLimit = sniffingLimit;
+        this.aggregateStream = aggregateStream;
+    }
+
     /**
      * @param aggregateStream
      */
@@ -59,7 +70,7 @@ private boolean runTest() throws IOException, SAXException {
         }
         UntilHashInputStream stream = new UntilHashInputStream(aggregateStream);
         HtmlInputStreamReader reader = new HtmlInputStreamReader(stream, null,
-                null, null, Heuristics.NONE);
+                null, null, Heuristics.NONE, sniffingLimit);
         Charset charset = reader.getCharset();
         stream.close();
         if (skipLabel()) {