Improved file read time

Author: jhy

CHANGES

@@ -9,6 +9,9 @@ jsoup changelog
 
  * Improved the performance of Element.html() by 1.7x
 
+ * Improved file read time by 2x, giving around a 10% speed improvement to file parses.
+   <https://github.com/jhy/jsoup/issues/248>
+
  * Tightened the scope of what characters are escaped in attributes and textnodes, to align with the spec. Also, when
    using the extended escape entities map, only escape a character if the current output charset does not support it.
    This produces smaller, more legible HTML, with greated control over the output (by setting charset and escape mode).

src/main/java/org/jsoup/helper/DataUtil.java

@@ -32,15 +32,8 @@ private DataUtil() {}
      * @throws IOException on IO error
      */
     public static Document load(File in, String charsetName, String baseUri) throws IOException {
-        FileInputStream inStream = null;
-        try {
-            inStream = new FileInputStream(in);
-            ByteBuffer byteData = readToByteBuffer(inStream);
-            return parseByteData(byteData, charsetName, baseUri, Parser.htmlParser());
-        } finally {
-            if (inStream != null)
-                inStream.close();
-        }
+        ByteBuffer byteData = readFileToByteBuffer(in);
+        return parseByteData(byteData, charsetName, baseUri, Parser.htmlParser());
     }
 
     /**
@@ -160,6 +153,19 @@ static ByteBuffer readToByteBuffer(InputStream inStream) throws IOException {
         return readToByteBuffer(inStream, 0);
     }
 
+    static ByteBuffer readFileToByteBuffer(File file) throws IOException {
+        RandomAccessFile randomAccessFile = null;
+        try {
+            randomAccessFile = new RandomAccessFile(file, "r");
+            byte[] bytes = new byte[(int) randomAccessFile.length()];
+            randomAccessFile.readFully(bytes);
+            return ByteBuffer.wrap(bytes);
+        } finally {
+            if (randomAccessFile != null)
+                randomAccessFile.close();
+        }
+    }
+
     /**
      * Parse out a charset from a content type header. If the charset is not supported, returns null (so the default
      * will kick in.)