From d815b0f64ee7b735a794a0429e5c806672168ee5 Mon Sep 17 00:00:00 2001
From: Looly <loolly@gmail.com>
Date: Wed, 2 Jun 2021 08:40:50 +0800
Subject: [PATCH] fix io bug

---
 CHANGELOG.md                                  |  3 +-
 .../cn/hutool/core/io/CharsetDetector.java    | 73 +++++++++++--------
 .../hutool/core/io/CharsetDetectorTest.java   | 19 +++++
 3 files changed, 62 insertions(+), 33 deletions(-)
 create mode 100644 hutool-core/src/test/java/cn/hutool/core/io/CharsetDetectorTest.java

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2a8a9001b..210afeaf5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,13 +3,14 @@
 
 -------------------------------------------------------------------------------------------------------------
 
-# 5.6.7 (2021-05-29)
+# 5.6.7 (2021-06-02)
 
 ### 🐣新特性
 * 【core   】     CharSequenceUtil增加join重载（issue#I3TFJ5@Gitee）
 
 ### 🐞Bug修复
 * 【core   】     修复FileUtil.normalize去掉末尾空格问题（issue#1603@Github）
+* 【core   】     修复CharsetDetector流关闭问题（issue#1603@Github）
 
 -------------------------------------------------------------------------------------------------------------
 
diff --git a/hutool-core/src/main/java/cn/hutool/core/io/CharsetDetector.java b/hutool-core/src/main/java/cn/hutool/core/io/CharsetDetector.java
index 0f5c31862..04a8da001 100644
--- a/hutool-core/src/main/java/cn/hutool/core/io/CharsetDetector.java
+++ b/hutool-core/src/main/java/cn/hutool/core/io/CharsetDetector.java
@@ -1,17 +1,15 @@
 package cn.hutool.core.io;
 
+import cn.hutool.core.convert.Convert;
 import cn.hutool.core.util.ArrayUtil;
 
-import java.io.BufferedInputStream;
+import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
 import java.nio.ByteBuffer;
 import java.nio.charset.CharacterCodingException;
 import java.nio.charset.Charset;
 import java.nio.charset.CharsetDecoder;
-import java.nio.charset.UnsupportedCharsetException;
-import java.util.ArrayList;
-import java.util.List;
 
 /**
  * 编码探测器
@@ -28,29 +26,34 @@ public class CharsetDetector {
 
 	static {
 		String[] names = {
-				"US-ASCII",
 				"UTF-8",
 				"GBK",
 				"GB2312",
-				"BIG5",
 				"GB18030",
 				"UTF-16BE",
 				"UTF-16LE",
 				"UTF-16",
-				"UNICODE"};
-		final List<Charset> list = new ArrayList<>();
-		for (String name : names) {
-			try {
-				list.add(Charset.forName(name));
-			} catch (UnsupportedCharsetException ignore) {
-				//ignore
-			}
-		}
-		DEFAULT_CHARSETS = list.toArray(new Charset[0]);
+				"BIG5",
+				"UNICODE",
+				"US-ASCII"};
+		DEFAULT_CHARSETS = Convert.convert(Charset[].class, names);
 	}
 
 	/**
-	 * 探测编码
+	 * 探测文件编码
+	 *
+	 * @param file       文件
+	 * @param charsets 需要测试用的编码，null或空使用默认的编码数组
+	 * @return 编码
+	 * @since 5.6.7
+	 */
+	public static Charset detect(File file, Charset... charsets) {
+		return detect(FileUtil.getInputStream(file), charsets);
+	}
+
+	/**
+	 * 探测编码<br>
+	 * 注意：此方法会读取流的一部分，然后关闭流，如重复使用流，请使用使用支持reset方法的流
 	 *
 	 * @param in       流，使用后关闭此流
 	 * @param charsets 需要测试用的编码，null或空使用默认的编码数组
@@ -60,34 +63,40 @@ public class CharsetDetector {
 		if (ArrayUtil.isEmpty(charsets)) {
 			charsets = DEFAULT_CHARSETS;
 		}
-		for (Charset charset : charsets) {
-			charset = detectCharset(in, charset);
-			if (null != charset) {
-				return charset;
+
+		final byte[] buffer = new byte[512];
+		try {
+			while (in.read(buffer) > -1) {
+				for (Charset charset : charsets) {
+					final CharsetDecoder decoder = charset.newDecoder();
+					if (identify(buffer, decoder)) {
+						return charset;
+					}
+				}
 			}
+		} catch (IOException e) {
+			throw new IORuntimeException(e);
+		} finally {
+			IoUtil.close(in);
 		}
 		return null;
 	}
 
 	/**
-	 * 判断编码
+	 * 判断编码，判断后会关闭流
 	 *
 	 * @param in      流
 	 * @param charset 编码
 	 * @return 编码
 	 */
-	private static Charset detectCharset(InputStream in, Charset charset) {
-		try (BufferedInputStream input = IoUtil.toBuffered(in)) {
-			CharsetDecoder decoder = charset.newDecoder();
+	private static Charset detectCharset(InputStream in, Charset charset) throws IOException {
+		CharsetDecoder decoder = charset.newDecoder();
 
-			byte[] buffer = new byte[512];
-			while (input.read(buffer) > -1) {
-				if (identify(buffer, decoder)) {
-					return charset;
-				}
+		final byte[] buffer = new byte[512];
+		while (in.read(buffer) > -1) {
+			if (identify(buffer, decoder)) {
+				return charset;
 			}
-		} catch (IOException e) {
-			throw new IORuntimeException(e);
 		}
 		return null;
 	}
diff --git a/hutool-core/src/test/java/cn/hutool/core/io/CharsetDetectorTest.java b/hutool-core/src/test/java/cn/hutool/core/io/CharsetDetectorTest.java
new file mode 100644
index 000000000..6fcb72d8e
--- /dev/null
+++ b/hutool-core/src/test/java/cn/hutool/core/io/CharsetDetectorTest.java
@@ -0,0 +1,19 @@
+package cn.hutool.core.io;
+
+import cn.hutool.core.io.resource.ResourceUtil;
+import cn.hutool.core.util.CharsetUtil;
+import org.junit.Assert;
+import org.junit.Test;
+
+import java.nio.charset.Charset;
+
+public class CharsetDetectorTest {
+
+	@Test
+	public void detectTest(){
+		// 测试多个Charset对同一个流的处理是否有问题
+		final Charset detect = CharsetDetector.detect(ResourceUtil.getStream("test.xml"),
+				CharsetUtil.CHARSET_GBK, CharsetUtil.CHARSET_UTF_8);
+		Assert.assertEquals(CharsetUtil.CHARSET_UTF_8, detect);
+	}
+}