java读取UTF-8文本文件第一个字符多出一个问号解决方法
2017-10-24 11:20
501 查看
1.创建工具类
[java] view
plain copy
import java.io.*;
public class UnicodeReader extends Reader {
PushbackInputStream internalIn;
InputStreamReader internalIn2 = null;
String defaultEnc;
private static final int BOM_SIZE = 4;
UnicodeReader(InputStream in, String defaultEnc) {
internalIn = new PushbackInputStream(in, BOM_SIZE);
this.defaultEnc = defaultEnc;
}
public String getDefaultEncoding() {
return defaultEnc;
}
public String getEncoding() {
if (internalIn2 == null) return null;
return internalIn2.getEncoding();
}
protected void init() throws IOException {
if (internalIn2 != null) return;
String encoding;
byte bom[] = new byte[BOM_SIZE];
int n, unread;
n = internalIn.read(bom, 0, bom.length);
if ( (bom[0] == (byte)0x00) && (bom[1] == (byte)0x00) &&
(bom[2] == (byte)0xFE) && (bom[3] == (byte)0xFF) ) {
encoding = "UTF-32BE";
unread = n - 4;
} else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) &&
(bom[2] == (byte)0x00) && (bom[3] == (byte)0x00) ) {
encoding = "UTF-32LE";
unread = n - 4;
} else if ( (bom[0] == (byte)0xEF) && (bom[1] == (byte)0xBB) &&
(bom[2] == (byte)0xBF) ) {
encoding = "UTF-8";
unread = n - 3;
} else if ( (bom[0] == (byte)0xFE) && (bom[1] == (byte)0xFF) ) {
encoding = "UTF-16BE";
unread = n - 2;
} else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) ) {
encoding = "UTF-16LE";
unread = n - 2;
} else {
// Unicode BOM mark not found, unread all bytes
encoding = defaultEnc;
unread = n;
}
//System.out.println("read=" + n + ", unread=" + unread);
if (unread > 0) internalIn.unread(bom, (n - unread), unread);
// Use given encoding
if (encoding == null) {
internalIn2 = new InputStreamReader(internalIn);
} else {
internalIn2 = new InputStreamReader(internalIn, encoding);
}
}
public void close() throws IOException {
init();
internalIn2.close();
}
public int read(char[] cbuf, int off, int len) throws IOException {
init();
return internalIn2.read(cbuf, off, len);
}
}
2.使用工具类读取文件
[java] view
plain copy
BufferedReader br = new BufferedReader(
new UnicodeReader(
new FileInputStream(sqlFile),
Charset.defaultCharset().name()));
3.出现有问号的编写
File f = new File("./utf.txt");
FileInputStream in = new FileInputStream(f);
// 指定读取文件时以UTF-8的格式读取
BufferedReader br = new BufferedReader(new InputStreamReader(in, "UTF-8"));
String line = br.readLine();
while(line != null)
{
System.out.println(line);
line = br.readLine();
}
只需编写工具类,将new InputStreamReader(in, "UTF-8")替换成
new UnicodeReader(new FileInputStream(sqlFile),Charset.defaultCharset().name())就可以解决该问题。
[java] view
plain copy
import java.io.*;
public class UnicodeReader extends Reader {
PushbackInputStream internalIn;
InputStreamReader internalIn2 = null;
String defaultEnc;
private static final int BOM_SIZE = 4;
UnicodeReader(InputStream in, String defaultEnc) {
internalIn = new PushbackInputStream(in, BOM_SIZE);
this.defaultEnc = defaultEnc;
}
public String getDefaultEncoding() {
return defaultEnc;
}
public String getEncoding() {
if (internalIn2 == null) return null;
return internalIn2.getEncoding();
}
protected void init() throws IOException {
if (internalIn2 != null) return;
String encoding;
byte bom[] = new byte[BOM_SIZE];
int n, unread;
n = internalIn.read(bom, 0, bom.length);
if ( (bom[0] == (byte)0x00) && (bom[1] == (byte)0x00) &&
(bom[2] == (byte)0xFE) && (bom[3] == (byte)0xFF) ) {
encoding = "UTF-32BE";
unread = n - 4;
} else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) &&
(bom[2] == (byte)0x00) && (bom[3] == (byte)0x00) ) {
encoding = "UTF-32LE";
unread = n - 4;
} else if ( (bom[0] == (byte)0xEF) && (bom[1] == (byte)0xBB) &&
(bom[2] == (byte)0xBF) ) {
encoding = "UTF-8";
unread = n - 3;
} else if ( (bom[0] == (byte)0xFE) && (bom[1] == (byte)0xFF) ) {
encoding = "UTF-16BE";
unread = n - 2;
} else if ( (bom[0] == (byte)0xFF) && (bom[1] == (byte)0xFE) ) {
encoding = "UTF-16LE";
unread = n - 2;
} else {
// Unicode BOM mark not found, unread all bytes
encoding = defaultEnc;
unread = n;
}
//System.out.println("read=" + n + ", unread=" + unread);
if (unread > 0) internalIn.unread(bom, (n - unread), unread);
// Use given encoding
if (encoding == null) {
internalIn2 = new InputStreamReader(internalIn);
} else {
internalIn2 = new InputStreamReader(internalIn, encoding);
}
}
public void close() throws IOException {
init();
internalIn2.close();
}
public int read(char[] cbuf, int off, int len) throws IOException {
init();
return internalIn2.read(cbuf, off, len);
}
}
2.使用工具类读取文件
[java] view
plain copy
BufferedReader br = new BufferedReader(
new UnicodeReader(
new FileInputStream(sqlFile),
Charset.defaultCharset().name()));
3.出现有问号的编写
File f = new File("./utf.txt");
FileInputStream in = new FileInputStream(f);
// 指定读取文件时以UTF-8的格式读取
BufferedReader br = new BufferedReader(new InputStreamReader(in, "UTF-8"));
String line = br.readLine();
while(line != null)
{
System.out.println(line);
line = br.readLine();
}
只需编写工具类,将new InputStreamReader(in, "UTF-8")替换成
new UnicodeReader(new FileInputStream(sqlFile),Charset.defaultCharset().name())就可以解决该问题。
相关文章推荐
- java读取UTF-8文本文件第一个字符多出一个问号解决方法
- java读取UTF-8文本文件第一个字符多出一个问号解决方法
- [置顶] java读取UTF-8文本文件第一个字符多出一个问号解决方法
- Java读取UTF-8格式文件第一行出现乱码——问号“?”及解决 And Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式文件第一行出现乱码——问号“?”及解决 And Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决;Java读带有BOM的UTF-8文件乱码原因及解决方法
- Java读取Unicode文件(UTF-8等)时碰到的BOM首字符问题,及处理方法
- java读取UTF-8的txt文件发现开头的一个字符问题
- Java读取Unicode文件(UTF-8等)时碰到的BOM首字符问题,及处理方法
- java读取UTF-8的txt文件发现开头的一个字符问题
- Java读取Unicode文件(UTF-8等)时碰到的BOM首字符问题,及处理方法
- windows java读取utf-8编码文件时出现第一个字符为未知字符"?" 的解决方案
- Java读取UTF-8格式txt文件第一行出现乱码——问号“?”及解决