Removes direct use of FileInputStream to prevent GC overhead

https://bugs.openjdk.java.net/browse/JDK-8080225
albfernandez · Dec 6, 2017 · aedaf63 · aedaf63
1 parent 02eaa48
commit aedaf63
Show file tree

Hide file tree

Showing 8 changed files with 45 additions and 15 deletions.
diff --git a/README.md b/README.md
@@ -82,7 +82,7 @@ public class TestDetector
   public static void main(String[] args)
   {
     byte[] buf = new byte[4096];
-    java.io.FileInputStream fis = new java.io.FileInputStream("test.txt");
+    java.io.InputStream fis = java.nio.file.Files.newInputStream(java.nio.file.Paths.get("test.txt"));
 
     // (1)
     UniversalDetector detector = new UniversalDetector();
@@ -152,7 +152,7 @@ public class TestCreateReaderFromFile {
 		java.io.Reader reader = null;
 		try {
 			java.io.File file = new java.io.File(args[0]);
-			reader = ReaderFactory.createReaderFromFile(file);
+			reader = ReaderFactory.createBufferedReader(file);
 
 			// Do whatever you want with the reader
 		}

diff --git a/src/main/java/org/mozilla/universalchardet/ReaderFactory.java b/src/main/java/org/mozilla/universalchardet/ReaderFactory.java
@@ -29,12 +29,14 @@
 package org.mozilla.universalchardet;
 
 import java.io.BufferedInputStream;
+import java.io.BufferedReader;
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.IOException;
 import java.io.InputStreamReader;
 import java.io.Reader;
 import java.nio.charset.Charset;
+import java.nio.file.Files;
+import java.nio.file.Path;
 import java.util.Objects;
 
 /**
@@ -50,22 +52,45 @@ private ReaderFactory() {
 	 * @param file The file to read from
 	 * @param defaultCharset defaultCharset to use if can't be determined
 	 */
-	public static Reader createReaderFromFile(File file, Charset defaultCharset) throws IOException {
+
+	public static BufferedReader createBufferedReader(File file, Charset defaultCharset) throws IOException {
 		Charset cs = Objects.requireNonNull(defaultCharset, "defaultCharset must be not null");
 		String detectedEncoding = UniversalDetector.detectCharset(file);
 		if (detectedEncoding != null) {
 			cs = Charset.forName(detectedEncoding);
 		}
 		if (!cs.toString().contains("UTF")) {
-			return new InputStreamReader(new BufferedInputStream(new FileInputStream(file)), cs);
+			return Files.newBufferedReader(file.toPath(), cs);			
 		}
-		return new InputStreamReader(new UnicodeBOMInputStream(new BufferedInputStream(new FileInputStream(file))), cs);
+		Path path = file.toPath();
+		return new BufferedReader(new InputStreamReader(new UnicodeBOMInputStream(new BufferedInputStream(Files.newInputStream(path))), cs));
+	}
+	/**
+	 * Create a reader from a file with correct encoding. If charset cannot be determined, 
+	 * it uses the system default charset.
+	 * @param file The file to read from
+	 */
+	public static BufferedReader createBufferedReader(File file) throws IOException {
+		return createBufferedReader(file, Charset.defaultCharset());
+	}
+
+	/**
+	 * Create a reader from a file with correct encoding
+	 * @param file The file to read from
+	 * @param defaultCharset defaultCharset to use if can't be determined
+	 * @deprecated Use {@link #createBufferedReader(File, Charset)}
+	 */
+	@Deprecated
+	public static Reader createReaderFromFile(File file, Charset defaultCharset) throws IOException {
+		return createBufferedReader(file, defaultCharset);
 	}
 	/**
 	 * Create a reader from a file with correct encoding. If charset cannot be determined, 
 	 * it uses the system default charset.
 	 * @param file The file to read from
+	 * @deprecated Use {@link #createBufferedReader(File)}
 	 */
+	@Deprecated
 	public static Reader createReaderFromFile(File file) throws IOException {
 		return createReaderFromFile(file, Charset.defaultCharset());
 	}

diff --git a/src/main/java/org/mozilla/universalchardet/UniversalDetector.java b/src/main/java/org/mozilla/universalchardet/UniversalDetector.java
@@ -43,9 +43,11 @@
 
 package org.mozilla.universalchardet;
 
+import java.io.BufferedInputStream;
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.IOException;
+import java.io.InputStream;
+import java.nio.file.Files;
 
 import org.mozilla.universalchardet.prober.CharsetProber;
 import org.mozilla.universalchardet.prober.EscCharsetProber;
@@ -325,7 +327,7 @@ public void reset()
 
     public static String detectCharset(File file) throws IOException {
 
-        try (FileInputStream fis = new FileInputStream(file)) {		
+        try (InputStream fis = new BufferedInputStream(Files.newInputStream(file.toPath()))) {		
 
         	byte[] buf = new byte[4096];
 

diff --git a/src/test/java/org/mozilla/universalchardet/BOMTest.java b/src/test/java/org/mozilla/universalchardet/BOMTest.java
@@ -32,7 +32,7 @@ private String getFirstLine(String testFileName) throws IOException{
         File file = new File(fileName);
         BufferedReader reader = null;
         try {
-        	reader = new BufferedReader(ReaderFactory.createReaderFromFile(file));
+        	reader = ReaderFactory.createBufferedReader(file);
         	// return first line
         	return reader.readLine();
         }

diff --git a/src/test/java/org/mozilla/universalchardet/BasicStreamEncodingDetectionTest.java b/src/test/java/org/mozilla/universalchardet/BasicStreamEncodingDetectionTest.java
@@ -1,8 +1,9 @@
 package org.mozilla.universalchardet;
 
+import java.io.BufferedInputStream;
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.IOException;
+import java.nio.file.Files;
 
 import org.junit.Assert;
 import org.junit.Test;
@@ -64,7 +65,7 @@ private String getFileEncoding(String testFileName) throws IOException{
         EncodingDetectorInputStream edis = null;
         EncodingDetectorOutputStream edos = null;
         try {
-        	edis = new EncodingDetectorInputStream(new FileInputStream(file));        
+        	edis = new EncodingDetectorInputStream(new BufferedInputStream(Files.newInputStream(file.toPath())));        
 	        edos = new EncodingDetectorOutputStream(NullOutputStream.NULL_OUTPUT_STREAM);
 	        byte[] buffer = new byte[1024];
 	        int read = 0;

diff --git a/src/test/java/org/mozilla/universalchardet/ReaderTest.java b/src/test/java/org/mozilla/universalchardet/ReaderTest.java
@@ -47,7 +47,7 @@ private String getSecondLine(String testFileName) throws IOException{
         File file = new File(fileName);
         BufferedReader reader = null;
         try {
-        	reader = new BufferedReader(ReaderFactory.createReaderFromFile(file));
+        	reader = ReaderFactory.createBufferedReader(file);
         	// Skip first line
         	reader.readLine();
         	// return second line

diff --git a/src/test/java/org/mozilla/universalchardet/example/TestCreateReaderFromFile.java b/src/test/java/org/mozilla/universalchardet/example/TestCreateReaderFromFile.java
@@ -13,7 +13,7 @@ public static void main (String[] args) throws java.io.IOException {
 		java.io.Reader reader = null;
 		try {
 			java.io.File file = new java.io.File(args[0]);
-			reader = ReaderFactory.createReaderFromFile(file);
+			reader = ReaderFactory.createBufferedReader(file);
 
 			// Do whatever you want with the reader
 		}

diff --git a/src/test/java/org/mozilla/universalchardet/example/TestDetector.java b/src/test/java/org/mozilla/universalchardet/example/TestDetector.java
@@ -37,7 +37,9 @@
  * ***** END LICENSE BLOCK ***** */
 package org.mozilla.universalchardet.example;
 
-import java.io.FileInputStream;
+import java.io.InputStream;
+import java.nio.file.Files;
+import java.nio.file.Paths;
 
 import org.mozilla.universalchardet.UniversalDetector;
 
@@ -50,7 +52,7 @@ public static void main(String[] args) throws java.io.IOException {
 
 		byte[] buf = new byte[4096];
 		String fileName = args[0];
-		try (FileInputStream fis = new FileInputStream(fileName)) {
+		try (InputStream fis = Files.newInputStream(Paths.get(fileName))) {
 
 			// (1)
 			UniversalDetector detector = new UniversalDetector();