| 1 | // License: GPL. See LICENSE file for details. |
|---|
| 2 | package org.openstreetmap.josm.io; |
|---|
| 3 | |
|---|
| 4 | import java.io.InputStream; |
|---|
| 5 | import java.io.InputStreamReader; |
|---|
| 6 | import java.io.IOException; |
|---|
| 7 | import java.io.PushbackInputStream; |
|---|
| 8 | import java.io.UnsupportedEncodingException; |
|---|
| 9 | |
|---|
| 10 | /** |
|---|
| 11 | * Detects the different UTF encodings from byte order mark |
|---|
| 12 | */ |
|---|
| 13 | public class UTFInputStreamReader extends InputStreamReader { |
|---|
| 14 | /** |
|---|
| 15 | * converts input stream to reader |
|---|
| 16 | * @param defaultEncoding Used, when no BOM was recognized. Can be null. |
|---|
| 17 | * @return A reader with the correct encoding. Starts to read after the BOM. |
|---|
| 18 | */ |
|---|
| 19 | public static UTFInputStreamReader create(InputStream input, String defaultEncoding) throws IOException { |
|---|
| 20 | byte bom[] = new byte[4]; |
|---|
| 21 | String encoding = defaultEncoding; |
|---|
| 22 | int unread; |
|---|
| 23 | PushbackInputStream pushbackStream = new PushbackInputStream(input, 4); |
|---|
| 24 | int n = pushbackStream.read(bom, 0, 4); |
|---|
| 25 | |
|---|
| 26 | if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB) && (bom[2] == (byte) 0xBF)) { |
|---|
| 27 | encoding = "UTF-8"; |
|---|
| 28 | unread = n - 3; |
|---|
| 29 | } else if ((bom[0] == (byte) 0x00) && (bom[1] == (byte) 0x00) && (bom[2] == (byte) 0xFE) && (bom[3] == (byte) 0xFF)) { |
|---|
| 30 | encoding = "UTF-32BE"; |
|---|
| 31 | unread = n - 4; |
|---|
| 32 | } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE) && (bom[2] == (byte) 0x00) && (bom[3] == (byte) 0x00)) { |
|---|
| 33 | encoding = "UTF-32LE"; |
|---|
| 34 | unread = n - 4; |
|---|
| 35 | } else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) { |
|---|
| 36 | encoding = "UTF-16BE"; |
|---|
| 37 | unread = n - 2; |
|---|
| 38 | } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) { |
|---|
| 39 | encoding = "UTF-16LE"; |
|---|
| 40 | unread = n - 2; |
|---|
| 41 | } else { |
|---|
| 42 | unread = n; |
|---|
| 43 | } |
|---|
| 44 | |
|---|
| 45 | if (unread > 0) { |
|---|
| 46 | pushbackStream.unread(bom, (n - unread), unread); |
|---|
| 47 | } else if (unread < -1) { |
|---|
| 48 | pushbackStream.unread(bom, 0, 0); |
|---|
| 49 | } |
|---|
| 50 | |
|---|
| 51 | if (encoding == null) { |
|---|
| 52 | return new UTFInputStreamReader(pushbackStream); |
|---|
| 53 | } else { |
|---|
| 54 | return new UTFInputStreamReader(pushbackStream, encoding); |
|---|
| 55 | } |
|---|
| 56 | } |
|---|
| 57 | |
|---|
| 58 | private UTFInputStreamReader(InputStream in) { |
|---|
| 59 | super(in); |
|---|
| 60 | } |
|---|
| 61 | private UTFInputStreamReader(InputStream in, String cs) throws UnsupportedEncodingException { |
|---|
| 62 | super(in, cs); |
|---|
| 63 | } |
|---|
| 64 | } |
|---|
