java读取UTF-8文本文件第一个字符多出一个问号解决方法
2017-07-27 18:31
721 查看
转载来源:http://akini.mbnet.fi/java/unicodereader/
转载至:http://akini.mbnet.fi/java/unicodereader/UnicodeInputStream.java.txt
转载至:http://akini.mbnet.fi/java/unicodereader/UnicodeInputStream.java.txt
package com.bigdata.ai.util; /** version: 1.1 / 2007-01-25 - changed BOM recognition ordering (longer boms first) Original pseudocode : Thomas Weidenfeller Implementation tweaked: Aki Nieminen http://www.unicode.org/unicode/faq/utf_bom.html BOMs: 00 00 FE FF = UTF-32, big-endian FF FE 00 00 = UTF-32, little-endian EF BB BF = UTF-8, FE FF = UTF-16, big-endian FF FE = UTF-16, little-endian Win2k Notepad: Unicode format = UTF-16LE ***/ import java.io.*; /** * Generic unicode textreader, which will use BOM mark * to identify the encoding to be used. If BOM is not found * then use a given default or system encoding. */ public class UnicodeReader extends Reader { PushbackInputStream internalIn; InputStreamReader internalIn2 = null; String defaultEnc; private static final int BOM_SIZE = 4; /** * * @param in inputstream to be read * @param defaultEnc default encoding if stream does not have * BOM marker. Give NULL to use system-level default. */ public UnicodeReader(InputStream in, String defaultEnc) { internalIn = new PushbackInputStream(in, BOM_SIZE); this.defaultEnc = defaultEnc; } public String getDefaultEncoding() { return defaultEnc; } /** * Get stream encoding or NULL if stream is uninitialized. * Call init() or read() method to initialize it. */ public String getEncoding() { if (internalIn2 == null) return null; return internalIn2.getEncoding(); } /** * Read-ahead four bytes and check for BOM marks. Extra bytes are * unread back to the stream, only BOM bytes are skipped. */ 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); } } package com.bigdata.ai.util; /** version: 1.1 / 2007-01-25 - changed BOM recognition ordering (longer boms first) Original pseudocode : Thomas Weidenfeller Implementation tweaked: Aki Nieminen http://www.unicode.org/unicode/faq/utf_bom.html BOMs in byte length ordering: 00 00 FE FF = UTF-32, big-endian FF FE 00 00 = UTF-32, little-endian EF BB BF = UTF-8, FE FF = UTF-16, big-endian FF FE = UTF-16, little-endian Win2k Notepad: Unicode format = UTF-16LE ***/ import java.io.*; /** * This inputstream will recognize unicode BOM marks * and will skip bytes if getEncoding() method is called * before any of the read(...) methods. * * Usage pattern: String enc = "ISO-8859-1"; // or NULL to use systemdefault FileInputStream fis = new FileInputStream(file); UnicodeInputStream uin = new UnicodeInputStream(fis, enc); enc = uin.getEncoding(); // check and skip possible BOM bytes InputStreamReader in; if (enc == null) in = new InputStreamReader(uin); else in = new InputStreamReader(uin, enc); */ public class UnicodeInputStream extends InputStream { PushbackInputStream internalIn; boolean isInited = false; String defaultEnc; String encoding; private static final int BOM_SIZE = 4; UnicodeInputStream(InputStream in, String defaultEnc) { internalIn = new PushbackInputStream(in, BOM_SIZE); this.defaultEnc = defaultEnc; } public String getDefaultEncoding() { return defaultEnc; } public String getEncoding() { if (!isInited) { try { init(); } catch (IOException ex) { IllegalStateException ise = new IllegalStateException("Init method failed."); ise.initCause(ise); throw ise; } } return encoding; } /** * Read-ahead four bytes and check for BOM marks. Extra bytes are * unread back to the stream, only BOM bytes are skipped. */ protected void init() throws IOException { if (isInited) return; 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); isInited = true; } public void close() throws IOException { //init(); isInited = true; internalIn.close(); } public int read() throws IOException { //init(); isInited = true; return internalIn.read(); } }
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