异-8859-1

如果您知道输入流的编码是ISO-8859-1或ASCII，这里有一种非常高效的方法来实现这一点。它（1）避免了StringWriter的内部StringBuffer中存在的不必要的同步，（2）避免了InputStreamReader的开销，（3）最小化了必须复制StringBuilder的内部字符数组的次数。

public static String iso_8859_1(InputStream is) throws IOException {
    StringBuilder chars = new StringBuilder(Math.max(is.available(), 4096));
    byte[] buffer = new byte[4096];
    int n;
    while ((n = is.read(buffer)) != -1) {
        for (int i = 0; i < n; i++) {
            chars.append((char)(buffer[i] & 0xFF));
        }
    }
    return chars.toString();
}

UTF-8型

对于使用UTF-8编码的流，可以使用相同的通用策略：

public static String utf8(InputStream is) throws IOException {
    StringBuilder chars = new StringBuilder(Math.max(is.available(), 4096));
    byte[] buffer = new byte[4096];
    int n;
    int state = 0;
    while ((n = is.read(buffer)) != -1) {
        for (int i = 0; i < n; i++) {
            if ((state = nextStateUtf8(state, buffer[i])) >= 0) {
                chars.appendCodePoint(state);
            } else if (state == -1) { //error
                state = 0;
                chars.append('\uFFFD'); //replacement char
            }
        }
    }
    return chars.toString();
}

其中nextStateUtf8（）函数定义如下：

/**
 * Returns the next UTF-8 state given the next byte of input and the current state.
 * If the input byte is the last byte in a valid UTF-8 byte sequence,
 * the returned state will be the corresponding unicode character (in the range of 0 through 0x10FFFF).
 * Otherwise, a negative integer is returned. A state of -1 is returned whenever an
 * invalid UTF-8 byte sequence is detected.
 */
static int nextStateUtf8(int currentState, byte nextByte) {
    switch (currentState & 0xF0000000) {
        case 0:
            if ((nextByte & 0x80) == 0) { //0 trailing bytes (ASCII)
                return nextByte;
            } else if ((nextByte & 0xE0) == 0xC0) { //1 trailing byte
                if (nextByte == (byte) 0xC0 || nextByte == (byte) 0xC1) { //0xCO & 0xC1 are overlong
                    return -1;
                } else {
                    return nextByte & 0xC000001F;
                }
            } else if ((nextByte & 0xF0) == 0xE0) { //2 trailing bytes
                if (nextByte == (byte) 0xE0) { //possibly overlong
                    return nextByte & 0xA000000F;
                } else if (nextByte == (byte) 0xED) { //possibly surrogate
                    return nextByte & 0xB000000F;
                } else {
                    return nextByte & 0x9000000F;
                }
            } else if ((nextByte & 0xFC) == 0xF0) { //3 trailing bytes
                if (nextByte == (byte) 0xF0) { //possibly overlong
                    return nextByte & 0x80000007;
                } else {
                    return nextByte & 0xE0000007;
                }
            } else if (nextByte == (byte) 0xF4) { //3 trailing bytes, possibly undefined
                return nextByte & 0xD0000007;
            } else {
                return -1;
            }
        case 0xE0000000: //3rd-to-last continuation byte
            return (nextByte & 0xC0) == 0x80 ? currentState << 6 | nextByte & 0x9000003F : -1;
        case 0x80000000: //3rd-to-last continuation byte, check overlong
            return (nextByte & 0xE0) == 0xA0 || (nextByte & 0xF0) == 0x90 ? currentState << 6 | nextByte & 0x9000003F : -1;
        case 0xD0000000: //3rd-to-last continuation byte, check undefined
            return (nextByte & 0xF0) == 0x80 ? currentState << 6 | nextByte & 0x9000003F : -1;
        case 0x90000000: //2nd-to-last continuation byte
            return (nextByte & 0xC0) == 0x80 ? currentState << 6 | nextByte & 0xC000003F : -1;
        case 0xA0000000: //2nd-to-last continuation byte, check overlong
            return (nextByte & 0xE0) == 0xA0 ? currentState << 6 | nextByte & 0xC000003F : -1;
        case 0xB0000000: //2nd-to-last continuation byte, check surrogate
            return (nextByte & 0xE0) == 0x80 ? currentState << 6 | nextByte & 0xC000003F : -1;
        case 0xC0000000: //last continuation byte
            return (nextByte & 0xC0) == 0x80 ? currentState << 6 | nextByte & 0x3F : -1;
        default:
            return -1;
    }
}

自动检测编码

如果您的输入流是使用ASCII、ISO-8859-1或UTF-8编码的，但您不确定是哪一种，我们可以使用与上一种方法类似的方法，但使用额外的编码检测组件在返回字符串之前自动检测编码。

public static String autoDetect(InputStream is) throws IOException {
    StringBuilder chars = new StringBuilder(Math.max(is.available(), 4096));
    byte[] buffer = new byte[4096];
    int n;
    int state = 0;
    boolean ascii = true;
    while ((n = is.read(buffer)) != -1) {
        for (int i = 0; i < n; i++) {
            if ((state = nextStateUtf8(state, buffer[i])) > 0x7F)
                ascii = false;
            chars.append((char)(buffer[i] & 0xFF));
        }
    }

    if (ascii || state < 0) { //probably not UTF-8
        return chars.toString();
    }
    //probably UTF-8
    int pos = 0;
    char[] charBuf = new char[2];
    for (int i = 0, len = chars.length(); i < len; i++) {
        if ((state = nextStateUtf8(state, (byte)chars.charAt(i))) >= 0) {
            boolean hi = Character.toChars(state, charBuf, 0) == 2;
            chars.setCharAt(pos++, charBuf[0]);
            if (hi) {
                chars.setCharAt(pos++, charBuf[1]);
            }
        }
    }
    return chars.substring(0, pos);
}

如果您的输入流的编码既不是ISO-8859-1，也不是ASCII，也不是UTF-8，那么我就遵从已经存在的其他答案。

此代码段位于\sdk\samples\android-19\connection\NetworkConnect\NetworkConnectSample\src\main\java.com\example\android\NetworkConnect\MainActivity.java中，该代码段根据Apache许可证2.0版授权，由Google编写。

/** Reads an InputStream and converts it to a String.
 * @param stream InputStream containing HTML from targeted site.
 * @param len Length of string that this method returns.
 * @return String concatenated according to len parameter.
 * @throws java.io.IOException
 * @throws java.io.UnsupportedEncodingException
 */
private String readIt(InputStream stream, int len) throws IOException, UnsupportedEncodingException {
    Reader reader = null;
    reader = new InputStreamReader(stream, "UTF-8");
    char[] buffer = new char[len];
    reader.read(buffer);
    return new String(buffer);
}

就reduce和concat而言，它可以在Java 8中表示为：

String fromFile = new BufferedReader(new   
InputStreamReader(inputStream)).lines().reduce(String::concat).get();

InputStream is = Context.openFileInput(someFileName); // whatever format you have

ByteArrayOutputStream bos = new ByteArrayOutputStream();

byte[] b = new byte[8192];
for (int bytesRead; (bytesRead = is.read(b)) != -1;) {
    bos.write(b, 0, bytesRead);
}

String output = bos.toString(someEncoding);

下面是如何仅使用JDK使用字节数组缓冲区来实现这一点。这实际上就是commons-ioIOUItils.copy（）方法的工作原理。如果要从Reader而不是InputStream复制，可以用char[]替换byte[]。

import java.io.ByteArrayOutputStream;
import java.io.InputStream;

...

InputStream is = ....
ByteArrayOutputStream baos = new ByteArrayOutputStream(8192);
byte[] buffer = new byte[8192];
int count = 0;
try {
  while ((count = is.read(buffer)) != -1) {
    baos.write(buffer, 0, count);
  }
}
finally {
  try {
    is.close();
  }
  catch (Exception ignore) {
  }
}

String charset = "UTF-8";
String inputStreamAsString = baos.toString(charset);

Use:

InputStream in = /* Your InputStream */;
StringBuilder sb = new StringBuilder();
BufferedReader br = new BufferedReader(new InputStreamReader(in));
String read;

while ((read=br.readLine()) != null) {
    //System.out.println(read);
    sb.append(read);
}

br.close();
return sb.toString();