AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-5407 remove UTF32.java and make the test depend on icu4j charsets

Browse Source 
X-SVN-Rev: 20542
This commit is contained in:
Ram Viswanadha 2006-10-20 22:54:22 +00:00
parent 78af2c2195
commit 444fd811e9
9 changed files with 29 additions and 277 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
icu4j/src/com/ibm/icu/charset/CharsetICU.java
View File

@ -61,7 +61,9 @@ public abstract class CharsetICU extends Charset{
short unicodeMask; /* +79: 1 bit 0: has supplementary bit 1: has single surrogates */
byte subChar1; /* +80: 1 single-byte substitution character for IBM MBCS (0 if none) */
byte reserved[/*19*/]; /* +81: 19 to round out the structure */
boolean writeBOM = false; /* only used by UTF-16, UTF-32 */
/**
*
* @param icuCanonicalName
@ -101,8 +103,8 @@ public abstract class CharsetICU extends Charset{
algorithmicCharsets.put("HZ", "com.ibm.icu.charset.CharsetHZ" );
algorithmicCharsets.put("imapmailboxname", "com.ibm.icu.charset.CharsetIMAP" );
algorithmicCharsets.put("ISCII", "com.ibm.icu.charset.CharsetISCII" );
algorithmicCharsets.put("iso2022", "com.ibm.icu.charset.CharsetISO2022" );*/
/*algorithmicCharsets.put("lmbcs1", "com.ibm.icu.charset.CharsetLMBCS1" );
algorithmicCharsets.put("iso2022", "com.ibm.icu.charset.CharsetISO2022" );
algorithmicCharsets.put("lmbcs1", "com.ibm.icu.charset.CharsetLMBCS1" );
algorithmicCharsets.put("lmbcs11", "com.ibm.icu.charset.CharsetLMBCS11" );
algorithmicCharsets.put("lmbcs16", "com.ibm.icu.charset.CharsetLMBCS16" );
algorithmicCharsets.put("lmbcs17", "com.ibm.icu.charset.CharsetLMBCS17" );
@ -219,11 +221,13 @@ public abstract class CharsetICU extends Charset{
*/
public static Charset forNameICU(String charsetName) throws IllegalCharsetNameException, UnsupportedCharsetException {
CharsetProviderICU icuProvider = new CharsetProviderICU();
Charset cs = icuProvider.charsetForName(charsetName);
CharsetICU cs = (CharsetICU) icuProvider.charsetForName(charsetName);
if (cs != null) {
cs.writeBOM = true;
return cs;
}
return Charset.forName(charsetName);
}
}

2
icu4j/src/com/ibm/icu/charset/CharsetUTF16.java
View File

@ -265,7 +265,7 @@ class CharsetUTF16 extends CharsetICU {
}
char c;
/* write the BOM if necessary */
if(fromUnicodeStatus==NEED_TO_WRITE_BOM) {
if(fromUnicodeStatus==NEED_TO_WRITE_BOM && writeBOM) {
byte bom[]={ (byte)0xfe, (byte)0xff };
cr = fromUWriteBytes(this,bom, 0, bom.length, target, offsets, -1);
if(cr.isError()){

2
icu4j/src/com/ibm/icu/charset/CharsetUTF16LE.java
View File

@ -269,7 +269,7 @@ class CharsetUTF16LE extends CharsetICU {
}
char c;
/* write the BOM if necessary */
if(fromUnicodeStatus==NEED_TO_WRITE_BOM) {
if(fromUnicodeStatus==NEED_TO_WRITE_BOM && writeBOM) {
byte bom[]={ (byte)0xff, (byte)0xfe };
cr = fromUWriteBytes(this,bom, 0, bom.length, target, offsets, -1);
if(cr.isError()){

2
icu4j/src/com/ibm/icu/charset/CharsetUTF32.java
View File

@ -175,7 +175,7 @@ class CharsetUTF32 extends CharsetICU {
}
/* write the BOM if necessary */
if(fromUnicodeStatus==NEED_TO_WRITE_BOM) {
if(fromUnicodeStatus==NEED_TO_WRITE_BOM && writeBOM) {
byte[] bom={ 0, 0, (byte)0xfe, (byte)0xff };
cr = fromUWriteBytes(this, bom, 0, bom.length, target, offsets, -1);
if(cr.isError()){

4
icu4j/src/com/ibm/icu/charset/CharsetUTF32LE.java
View File

@ -175,7 +175,7 @@ class CharsetUTF32LE extends CharsetICU {
}
/* write the BOM if necessary */
if(fromUnicodeStatus==NEED_TO_WRITE_BOM) {
if(fromUnicodeStatus==NEED_TO_WRITE_BOM && writeBOM) {
byte[] bom={ (byte)0xff, (byte)0xfe, 0, 0 };
cr = fromUWriteBytes(this, bom, 0, bom.length, target, offsets, -1);
if(cr.isError()){
@ -183,7 +183,7 @@ class CharsetUTF32LE extends CharsetICU {
}
fromUnicodeStatus=0;
}
int ch, ch2;
int indexToWrite;
byte temp[] = new byte[4];

19
icu4j/src/com/ibm/icu/dev/test/charset/TestCharset.java
View File

@ -47,7 +47,6 @@ public class TestCharset extends TestFmwk {
(byte) 0x00,(byte) 0x0d,
(byte) 0x00,(byte) 0x0a };
static final byte[] expectedByteStr ={
(byte) 0xFE,(byte) 0xFF,
(byte) 0x00,(byte) 'a',
(byte) 0x00,(byte) 'b',
(byte) 0x00,(byte) 'c',
@ -147,8 +146,8 @@ public class TestCharset extends TestFmwk {
bs1.limit(bs1.position());
bs1.position(0);
ByteBuffer newBS = ByteBuffer.allocate(bs1.capacity());
newBS.put((byte)0xFE);
newBS.put((byte)0xFF);
//newBS.put((byte)0xFE);
//newBS.put((byte)0xFF);
newBS.put(bs1);
bs1.position(0);
smBufDecode(d1, "UTF-16", bs1, us);
@ -157,8 +156,8 @@ public class TestCharset extends TestFmwk {
bs2.limit(bs2.position());
bs2.position(0);
newBS.clear();
newBS.put((byte)0xFF);
newBS.put((byte)0xFE);
//newBS.put((byte)0xFF);
//newBS.put((byte)0xFE);
newBS.put(bs2);
bs2.position(0);
smBufDecode(d2, "UTF16-LE", bs2, us);
@ -216,29 +215,33 @@ public class TestCharset extends TestFmwk {
if(us.length()==0){
continue;
}
ByteBuffer newBS = ByteBuffer.allocate(bs1.capacity());
/*
newBS.put((byte)0x00);
newBS.put((byte)0x00);
newBS.put((byte)0xFE);
newBS.put((byte)0xFF);
newBS.put(bs1);
*/
newBS.put(bs1);
bs1.position(0);
smBufDecode(d1, "UTF-32", bs1, us);
smBufEncode(e1, "UTF-32", us, newBS);
newBS.clear();
/*
newBS.put((byte)0xFF);
newBS.put((byte)0xFE);
newBS.put((byte)0x00);
newBS.put((byte)0x00);
*/
newBS.put(bs2);
bs2.position(0);
smBufDecode(d2, "UTF-32LE", bs2, us);
smBufEncode(e2, "UTF-32LE", us, newBS);
}
}

10
icu4j/src/com/ibm/icu/dev/test/charsetdet/TestCharsetDetector.java
View File

@ -142,11 +142,11 @@ public class TestCharsetDetector extends TestFmwk
CharsetDetector det = new CharsetDetector();
byte[] bytes;
if (enc.startsWith("UTF-32")) {
UTF32 utf32 = UTF32.getInstance(enc);
//if (enc.startsWith("UTF-32")) {
// UTF32 utf32 = UTF32.getInstance(enc);
bytes = utf32.toBytes(testString);
} else {
// bytes = utf32.toBytes(testString);
//} else {
String from = enc;
while (true) {
@ -172,7 +172,7 @@ public class TestCharsetDetector extends TestFmwk
break;
}
}
//}
det.setText(bytes);
checkMatch(det, testString, enc, lang, id);

253
icu4j/src/com/ibm/icu/impl/UTF32.java
View File

@ -1,253 +0,0 @@
/*
*******************************************************************************
* Copyright (C) 2005-2006, International Business Machines Corporation and *
* others. All Rights Reserved. *
*******************************************************************************
*
*/
package com.ibm.icu.impl;
import com.ibm.icu.text.UTF16;
/**
* This class converts between an array of bytes in UTF-32 encoding (BE or LE) and
* Java Strings.
*
* @internal
*/
public abstract class UTF32
{
/**
* This method packs a 32-bit Unicode code point into the byte array. It is
* implemented by subclasses that implement the BE and LE encodings.
*
* @param bytes the destination byte array
* @param codePoint the 32-bit Unicode code point
* @param out the destination index in <code>bytes</code>.
*
* @internal
*/
abstract protected void pack(byte[] bytes, int codePoint, int out);
/**
* This method unpacks bytes from the encoded byte array into a 32-bit
* Unicode code point. It is implmeented by subclasses that implmeent the BE and LE encodings.
*
* @param bytes the source byte array.
* @param index the index of the first source byte.
* @return the 32-bit Unicode code point.
*
* @internal
*/
abstract protected int unpack(byte[] bytes, int index);
/**
* Convert a Java String into an array of UTF-32 encoded bytes. Calls
* the <code>pack</code> method to do the encoding.
*
* @param utf16 the source Java String.
* @return an array of UTF-32 encoded bytes.
*
* @internal
*/
public byte[] toBytes(String utf16)
{
int codePoints = UTF16.countCodePoint(utf16);
byte[] bytes = new byte[codePoints * 4];
int out = 0;
for (int cp = 0; cp < codePoints; out += 4) {
int codePoint = UTF16.charAt(utf16, cp);
pack(bytes, codePoint, out);
cp += UTF16.getCharCount(codePoint);
}
return bytes;
}
/**
* This method converts a sequence of UTF-32 encoded bytes into
* a Java String. It calls the <code>unpack</code> method to implement
* the encoding.
*
* @param bytes the source byte array.
* @param offset the starting offset in the byte array.
* @param count the number of bytes to process.
* @return the Java String.
*
* @internal
*/
public String fromBytes(byte[] bytes, int offset, int count)
{
StringBuffer buffer = new StringBuffer();
int limit = offset + count;
for (int cp = offset; cp < limit; cp += 4) {
int codePoint = unpack(bytes, cp);
UTF16.append(buffer, codePoint);
}
return buffer.toString();
}
/**
* A convenience method that converts an entire byte array
* into a Java String.
*
* @param bytes the source byte array.
* @return the Java String.
*
* @internal
*/
public String fromBytes(byte[] bytes)
{
return fromBytes(bytes, 0, bytes.length);
}
/**
* Get an instance that implements UTF-32BE encoding.
*
* @return the instance.
*
* @internal
*/
static public UTF32 getBEInstance()
{
if (beInstance == null) {
beInstance = new BE();
}
return beInstance;
}
/**
* Get an instance that implemnts the UTF-32LE encoding.
*
* @return the instance.
*
* @internal
*/
static public UTF32 getLEInstance()
{
if (leInstance == null) {
leInstance = new LE();
}
return leInstance;
}
/**
* Get an instance that implements either UTF-32BE or UTF32-LE,
* depending on the encoding name suppled.
*
* @param encoding the encoding name - must be <code>"UTF-32BE"</code> or <code>"UTF-32LE"</code>.
* @return the instance.
*
* @internal
*/
static public UTF32 getInstance(String encoding)
{
if (encoding.equals("UTF-32BE")) {
return getBEInstance();
}
if (encoding.equals("UTF-32LE")) {
return getLEInstance();
}
return null;
}
/**
* This sublcass implements the UTF-32BE encoding via the
* <code>pack</code> and <code>unpack</code> methods.
*
* @internal
*/
static class BE extends UTF32
{
/**
* This method packs a 32-bit Unicode code point into the byte array using
* the UTF-32BE encoding.
*
* @param bytes the destination byte array
* @param codePoint the 32-bit Unicode code point
* @param out the destination index in <code>bytes</code>.
*
* @internal
*/
public void pack(byte[] bytes, int codePoint, int out)
{
bytes[out + 0] = (byte) ((codePoint >> 24) & 0xFF);
bytes[out + 1] = (byte) ((codePoint >> 16) & 0xFF);
bytes[out + 2] = (byte) ((codePoint >> 8) & 0xFF);
bytes[out + 3] = (byte) ((codePoint >> 0) & 0xFF);
}
/**
* This method unpacks bytes from the UTF-32BE encoded byte array into a 32-bit
* Unicode code point.
*
* @param bytes the source byte array.
* @param index the index of the first source byte.
* @return the 32-bit Unicode code point.
*
* @internal
*/
public int unpack(byte[] bytes, int index)
{
return (bytes[index + 0] & 0xFF) << 24 | (bytes[index + 1] & 0xFF) << 16 |
(bytes[index + 2] & 0xFF) << 8 | (bytes[index + 3] & 0xFF);
}
}
/**
* This sublcass implements the UTF-32LE encoding via the
* <code>pack</code> and <code>unpack</code> methods.
*
* @internal
*/
static class LE extends UTF32
{
/**
* This method packs a 32-bit Unicode code point into the byte array using
* the UTF-32LE encoding.
*
* @param bytes the destination byte array
* @param codePoint the 32-bit Unicode code point
* @param out the destination index in <code>bytes</code>.
*
* @internal
*/
public void pack(byte[] bytes, int codePoint, int out)
{
bytes[out + 3] = (byte) ((codePoint >> 24) & 0xFF);
bytes[out + 2] = (byte) ((codePoint >> 16) & 0xFF);
bytes[out + 1] = (byte) ((codePoint >> 8) & 0xFF);
bytes[out + 0] = (byte) ((codePoint >> 0) & 0xFF);
}
/**
* This method unpacks bytes from the UTF-32LE encoded byte array into a 32-bit
* Unicode code point.
*
* @param bytes the source byte array.
* @param index the index of the first source byte.
* @return the 32-bit Unicode code point.
*
* @internal
*/
public int unpack(byte[] bytes, int index)
{
return (bytes[index + 3] & 0xFF) << 24 | (bytes[index + 2] & 0xFF) << 16 |
(bytes[index + 1] & 0xFF) << 8 | (bytes[index + 0] & 0xFF);
}
}
private static UTF32 beInstance = null;
private static UTF32 leInstance = null;
}

2
icu4j/src/com/ibm/icu/text/UnicodeSet.java
View File

@ -28,8 +28,6 @@ import com.ibm.icu.util.VersionInfo;
import com.ibm.icu.text.BreakIterator;
import java.util.Map;
import java.util.HashMap;
import java.util.MissingResourceException;
import java.util.TreeSet;
import java.util.Iterator;