DRY: Use Charset statics to eliminate exceptions

This commit is contained in:
Tamir Duberstein 2015-03-31 20:01:43 -07:00
parent e84893f676
commit 210de285d7
20 changed files with 75 additions and 119 deletions

View File

@ -262,6 +262,18 @@ public abstract class ByteString implements Iterable<Byte>, Serializable {
return new LiteralByteString(text.getBytes(charsetName));
}
/**
* Encodes {@code text} into a sequence of bytes using the named charset
* and returns the result as a {@code ByteString}.
*
* @param text source string
* @param charset encode using this charset
* @return new {@code ByteString}
*/
public static ByteString copyFrom(String text, Charset charset) {
return new LiteralByteString(text.getBytes(charset));
}
/**
* Encodes {@code text} into a sequence of UTF-8 bytes and returns the
* result as a {@code ByteString}.

View File

@ -373,14 +373,14 @@ public final class CodedInputStream {
if (size <= (bufferSize - bufferPos) && size > 0) {
// Fast path: We already have the bytes in a contiguous buffer, so
// just copy directly from it.
final String result = new String(buffer, bufferPos, size, "UTF-8");
final String result = new String(buffer, bufferPos, size, ByteString.UTF_8);
bufferPos += size;
return result;
} else if (size == 0) {
return "";
} else {
// Slow path: Build a byte array first then copy it.
return new String(readRawBytesSlowPath(size), "UTF-8");
return new String(readRawBytesSlowPath(size), ByteString.UTF_8);
}
}
@ -409,7 +409,7 @@ public final class CodedInputStream {
if (!Utf8.isValidUtf8(bytes, pos, pos + size)) {
throw InvalidProtocolBufferException.invalidUtf8();
}
return new String(bytes, pos, size, "UTF-8");
return new String(bytes, pos, size, ByteString.UTF_8);
}
/** Read a {@code group} field value from the stream. */

View File

@ -420,7 +420,7 @@ public final class CodedOutputStream {
// Unfortunately there does not appear to be any way to tell Java to encode
// UTF-8 directly into our buffer, so we have to let it create its own byte
// array and then copy.
final byte[] bytes = value.getBytes("UTF-8");
final byte[] bytes = value.getBytes(ByteString.UTF_8);
writeRawVarint32(bytes.length);
writeRawBytes(bytes);
}
@ -827,13 +827,9 @@ public final class CodedOutputStream {
* {@code string} field.
*/
public static int computeStringSizeNoTag(final String value) {
try {
final byte[] bytes = value.getBytes("UTF-8");
return computeRawVarint32Size(bytes.length) +
bytes.length;
} catch (UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported.", e);
}
final byte[] bytes = value.getBytes(ByteString.UTF_8);
return computeRawVarint32Size(bytes.length) +
bytes.length;
}
/**

View File

@ -319,12 +319,7 @@ public final class Descriptors {
}
final byte[] descriptorBytes;
try {
descriptorBytes = descriptorData.toString().getBytes("ISO-8859-1");
} catch (UnsupportedEncodingException e) {
throw new RuntimeException(
"Standard encoding ISO-8859-1 not supported by JVM.", e);
}
descriptorBytes = descriptorData.toString().getBytes(Internal.ISO_8859_1);
FileDescriptorProto proto;
try {

View File

@ -33,6 +33,7 @@ package com.google.protobuf;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.util.AbstractList;
import java.util.AbstractMap;
import java.util.AbstractSet;
@ -51,6 +52,9 @@ import java.util.Set;
* @author kenton@google.com (Kenton Varda)
*/
public class Internal {
protected static final Charset ISO_8859_1 = Charset.forName("ISO-8859-1");
/**
* Helper called by generated code to construct default values for string
* fields.
@ -80,14 +84,7 @@ public class Internal {
* generated code calls this automatically.
*/
public static String stringDefaultValue(String bytes) {
try {
return new String(bytes.getBytes("ISO-8859-1"), "UTF-8");
} catch (UnsupportedEncodingException e) {
// This should never happen since all JVMs are required to implement
// both of the above character sets.
throw new IllegalStateException(
"Java VM does not support a standard character set.", e);
}
return new String(bytes.getBytes(ISO_8859_1), ByteString.UTF_8);
}
/**
@ -99,14 +96,7 @@ public class Internal {
* embed raw bytes as a string literal with ISO-8859-1 encoding.
*/
public static ByteString bytesDefaultValue(String bytes) {
try {
return ByteString.copyFrom(bytes.getBytes("ISO-8859-1"));
} catch (UnsupportedEncodingException e) {
// This should never happen since all JVMs are required to implement
// ISO-8859-1.
throw new IllegalStateException(
"Java VM does not support a standard character set.", e);
}
return ByteString.copyFrom(bytes.getBytes(ISO_8859_1));
}
/**
* Helper called by generated code to construct default values for bytes
@ -115,14 +105,7 @@ public class Internal {
* This is like {@link #bytesDefaultValue}, but returns a byte array.
*/
public static byte[] byteArrayDefaultValue(String bytes) {
try {
return bytes.getBytes("ISO-8859-1");
} catch (UnsupportedEncodingException e) {
// This should never happen since all JVMs are required to implement
// ISO-8859-1.
throw new IllegalStateException(
"Java VM does not support a standard character set.", e);
}
return bytes.getBytes(ISO_8859_1);
}
/**
@ -161,7 +144,7 @@ public class Internal {
* without loss. More precisely, returns {@code true} whenever:
* <pre> {@code
* Arrays.equals(byteString.toByteArray(),
* new String(byteString.toByteArray(), "UTF-8").getBytes("UTF-8"))
* new String(byteString.toByteArray(), ByteString.UTF_8).getBytes(ByteString.UTF_8))
* }</pre>
*
* <p>This method rejects "overlong" byte sequences, as well as
@ -197,22 +180,14 @@ public class Internal {
* Helper method to get the UTF-8 bytes of a string.
*/
public static byte[] toByteArray(String value) {
try {
return value.getBytes("UTF-8");
} catch (UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported?", e);
}
return value.getBytes(ByteString.UTF_8);
}
/**
* Helper method to convert a byte array to a string using UTF-8 encoding.
*/
public static String toStringUtf8(byte[] bytes) {
try {
return new String(bytes, "UTF-8");
} catch (UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported?", e);
}
return new String(bytes, ByteString.UTF_8);
}
/**

View File

@ -46,7 +46,7 @@ package com.google.protobuf;
* <p>The byte sequences considered valid by this class are exactly
* those that can be roundtrip converted to Strings and back to bytes
* using the UTF-8 charset, without loss: <pre> {@code
* Arrays.equals(bytes, new String(bytes, "UTF-8").getBytes("UTF-8"))
* Arrays.equals(bytes, new String(bytes, ByteString.UTF_8).getBytes(ByteString.UTF_8))
* }</pre>
*
* <p>See the Unicode Standard,</br>

View File

@ -62,7 +62,7 @@ public class BoundedByteStringTest extends LiteralByteStringTest {
@Override
public void testToString() throws UnsupportedEncodingException {
String testString = "I love unicode \u1234\u5678 characters";
LiteralByteString unicode = new LiteralByteString(testString.getBytes(UTF_8));
LiteralByteString unicode = new LiteralByteString(testString.getBytes(ByteString.UTF_8));
ByteString chopped = unicode.substring(2, unicode.size() - 6);
assertEquals(classUnderTest + ".substring() must have the expected type",
classUnderTest, getActualClassName(chopped));

View File

@ -36,11 +36,12 @@ import junit.framework.TestCase;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Iterator;
@ -56,7 +57,7 @@ import java.util.Random;
*/
public class ByteStringTest extends TestCase {
private static final String UTF_16 = "UTF-16";
private static final Charset UTF_16 = Charset.forName("UTF-16");
static byte[] getTestBytes(int size, long seed) {
Random random = new Random(seed);
@ -139,7 +140,7 @@ public class ByteStringTest extends TestCase {
public void testCopyFrom_Utf8() throws UnsupportedEncodingException {
String testString = "I love unicode \u1234\u5678 characters";
ByteString byteString = ByteString.copyFromUtf8(testString);
byte[] testBytes = testString.getBytes("UTF-8");
byte[] testBytes = testString.getBytes(ByteString.UTF_8);
assertTrue("copyFromUtf8 string must respect the charset",
isArrayRange(byteString.toByteArray(), testBytes, 0, testBytes.length));
}
@ -400,7 +401,7 @@ public class ByteStringTest extends TestCase {
public void testToStringUtf8() throws UnsupportedEncodingException {
String testString = "I love unicode \u1234\u5678 characters";
byte[] testBytes = testString.getBytes("UTF-8");
byte[] testBytes = testString.getBytes(ByteString.UTF_8);
ByteString byteString = ByteString.copyFrom(testBytes);
assertEquals("copyToStringUtf8 must respect the charset",
testString, byteString.toStringUtf8());

View File

@ -321,7 +321,7 @@ public class CodedOutputStreamTest extends TestCase {
final int BUFFER_SIZE = 4 * 1024;
ByteArrayOutputStream outputStream = new ByteArrayOutputStream(BUFFER_SIZE);
CodedOutputStream codedStream = CodedOutputStream.newInstance(outputStream);
byte[] value = "abcde".getBytes("UTF-8");
byte[] value = "abcde".getBytes(ByteString.UTF_8);
for (int i = 0; i < 1024; ++i) {
codedStream.writeRawBytes(value, 0, value.length);
}
@ -367,7 +367,7 @@ public class CodedOutputStreamTest extends TestCase {
}
public void testWriteByteBuffer() throws Exception {
byte[] value = "abcde".getBytes("UTF-8");
byte[] value = "abcde".getBytes(ByteString.UTF_8);
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
CodedOutputStream codedStream = CodedOutputStream.newInstance(outputStream);
ByteBuffer byteBuffer = ByteBuffer.wrap(value, 0, 1);

View File

@ -286,7 +286,7 @@ public class DescriptorsTest extends TestCase {
d = TestExtremeDefaultValues.getDescriptor();
assertEquals(
ByteString.copyFrom(
"\0\001\007\b\f\n\r\t\013\\\'\"\u00fe".getBytes("ISO-8859-1")),
"\0\001\007\b\f\n\r\t\013\\\'\"\u00fe".getBytes(Internal.ISO_8859_1)),
d.findFieldByName("escaped_bytes").getDefaultValue());
assertEquals(-1, d.findFieldByName("large_uint32").getDefaultValue());
assertEquals(-1L, d.findFieldByName("large_uint64").getDefaultValue());

View File

@ -220,8 +220,8 @@ class IsValidUtf8TestUtil {
}
ByteString bs = ByteString.copyFrom(bytes);
boolean isRoundTrippable = bs.isValidUtf8();
String s = new String(bytes, "UTF-8");
byte[] bytesReencoded = s.getBytes("UTF-8");
String s = new String(bytes, ByteString.UTF_8);
byte[] bytesReencoded = s.getBytes(ByteString.UTF_8);
boolean bytesEqual = Arrays.equals(bytes, bytesReencoded);
if (bytesEqual != isRoundTrippable) {
@ -313,10 +313,10 @@ class IsValidUtf8TestUtil {
void testBytesUsingByteBuffers(
int numBytes, long expectedCount, long start, long lim)
throws UnsupportedEncodingException {
CharsetDecoder decoder = Charset.forName("UTF-8").newDecoder()
CharsetDecoder decoder = ByteString.UTF_8.newDecoder()
.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE);
CharsetEncoder encoder = Charset.forName("UTF-8").newEncoder()
CharsetEncoder encoder = ByteString.UTF_8.newEncoder()
.onMalformedInput(CodingErrorAction.REPLACE)
.onUnmappableCharacter(CodingErrorAction.REPLACE);
byte[] bytes = new byte[numBytes];

View File

@ -293,7 +293,7 @@ public class LiteralByteStringTest extends TestCase {
public void testToString() throws UnsupportedEncodingException {
String testString = "I love unicode \u1234\u5678 characters";
LiteralByteString unicode = new LiteralByteString(testString.getBytes(UTF_8));
LiteralByteString unicode = new LiteralByteString(testString.getBytes(ByteString.UTF_8));
String roundTripString = unicode.toString(UTF_8);
assertEquals(classUnderTest + " unicode must match", testString, roundTripString);
}
@ -307,7 +307,7 @@ public class LiteralByteStringTest extends TestCase {
public void testToString_returnsCanonicalEmptyString() throws UnsupportedEncodingException{
assertSame(classUnderTest + " must be the same string references",
ByteString.EMPTY.toString(UTF_8), new LiteralByteString(new byte[]{}).toString(UTF_8));
ByteString.EMPTY.toString(ByteString.UTF_8), new LiteralByteString(new byte[]{}).toString(ByteString.UTF_8));
}
public void testToString_raisesException() throws UnsupportedEncodingException{

View File

@ -149,7 +149,7 @@ public class RopeByteStringTest extends LiteralByteStringTest {
RopeByteString ropeByteString =
RopeByteString.newInstanceForTest(ByteString.EMPTY, ByteString.EMPTY);
assertSame(classUnderTest + " must be the same string references",
ByteString.EMPTY.toString(UTF_8), ropeByteString.toString(UTF_8));
ByteString.EMPTY.toString(ByteString.UTF_8), ropeByteString.toString(ByteString.UTF_8));
}
public void testToString_raisesException() throws UnsupportedEncodingException{

View File

@ -276,11 +276,7 @@ public final class TestUtil {
/** Helper to convert a String to ByteString. */
static ByteString toBytes(String str) {
try {
return ByteString.copyFrom(str.getBytes("UTF-8"));
} catch(java.io.UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported.", e);
}
return ByteString.copyFrom(str.getBytes(ByteString.UTF_8));
}
/**

View File

@ -243,8 +243,8 @@ public class TextFormatTest extends TestCase {
* characters. The characters are converted directly to bytes, *not*
* encoded using UTF-8.
*/
private ByteString bytes(String str) throws Exception {
return ByteString.copyFrom(str.getBytes("ISO-8859-1"));
private ByteString bytes(String str) {
return ByteString.copyFrom(str.getBytes(Internal.ISO_8859_1));
}
/**

View File

@ -229,7 +229,7 @@ public class UnknownFieldSetLiteTest extends TestCase {
public void testMalformedBytes() throws Exception {
try {
Foo.parseFrom("this is a malformed protocol buffer".getBytes("UTF-8"));
Foo.parseFrom("this is a malformed protocol buffer".getBytes(ByteString.UTF_8));
fail();
} catch (InvalidProtocolBufferException e) {
// Expected.

View File

@ -190,12 +190,12 @@ public final class CodedInputByteBufferNano {
if (size <= (bufferSize - bufferPos) && size > 0) {
// Fast path: We already have the bytes in a contiguous buffer, so
// just copy directly from it.
final String result = new String(buffer, bufferPos, size, "UTF-8");
final String result = new String(buffer, bufferPos, size, InternalNano.UTF_8);
bufferPos += size;
return result;
} else {
// Slow path: Build a byte array first then copy it.
return new String(readRawBytes(size), "UTF-8");
return new String(readRawBytes(size), InternalNano.UTF_8);
}
}

View File

@ -291,7 +291,7 @@ public final class CodedOutputByteBufferNano {
// Unfortunately there does not appear to be any way to tell Java to encode
// UTF-8 directly into our buffer, so we have to let it create its own byte
// array and then copy.
final byte[] bytes = value.getBytes("UTF-8");
final byte[] bytes = value.getBytes(InternalNano.UTF_8);
writeRawVarint32(bytes.length);
writeRawBytes(bytes);
}
@ -603,13 +603,9 @@ public final class CodedOutputByteBufferNano {
* {@code string} field.
*/
public static int computeStringSizeNoTag(final String value) {
try {
final byte[] bytes = value.getBytes("UTF-8");
return computeRawVarint32Size(bytes.length) +
bytes.length;
} catch (UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported.");
}
final byte[] bytes = value.getBytes(InternalNano.UTF_8);
return computeRawVarint32Size(bytes.length) +
bytes.length;
}
/**

View File

@ -34,9 +34,10 @@ import com.google.protobuf.nano.MapFactories.MapFactory;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.nio.charset.Charset;
import java.util.Arrays;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Map;
/**
* The classes contained within are used internally by the Protocol Buffer
@ -67,6 +68,8 @@ public final class InternalNano {
public static final int TYPE_SINT32 = 17;
public static final int TYPE_SINT64 = 18;
protected static final Charset UTF_8 = Charset.forName("UTF-8");
protected static final Charset ISO_8859_1 = Charset.forName("ISO-8859-1");
private InternalNano() {}
@ -111,14 +114,7 @@ public final class InternalNano {
* generated code calls this automatically.
*/
public static String stringDefaultValue(String bytes) {
try {
return new String(bytes.getBytes("ISO-8859-1"), "UTF-8");
} catch (UnsupportedEncodingException e) {
// This should never happen since all JVMs are required to implement
// both of the above character sets.
throw new IllegalStateException(
"Java VM does not support a standard character set.", e);
}
return new String(bytes.getBytes(ISO_8859_1), InternalNano.UTF_8);
}
/**
@ -130,14 +126,7 @@ public final class InternalNano {
* embed raw bytes as a string literal with ISO-8859-1 encoding.
*/
public static byte[] bytesDefaultValue(String bytes) {
try {
return bytes.getBytes("ISO-8859-1");
} catch (UnsupportedEncodingException e) {
// This should never happen since all JVMs are required to implement
// ISO-8859-1.
throw new IllegalStateException(
"Java VM does not support a standard character set.", e);
}
return bytes.getBytes(ISO_8859_1);
}
/**
@ -145,11 +134,7 @@ public final class InternalNano {
* UnsupportedEncodingException to a RuntimeException.
*/
public static byte[] copyFromUtf8(final String text) {
try {
return text.getBytes("UTF-8");
} catch (UnsupportedEncodingException e) {
throw new RuntimeException("UTF-8 not supported?");
}
return text.getBytes(InternalNano.UTF_8);
}
/**

View File

@ -458,7 +458,7 @@ public class NanoTest extends TestCase {
assertFalse(msg.optionalBytes.length > 0);
msg.optionalBytes = InternalNano.copyFromUtf8("hello");
assertTrue(msg.optionalBytes.length > 0);
assertEquals("hello", new String(msg.optionalBytes, "UTF-8"));
assertEquals("hello", new String(msg.optionalBytes, InternalNano.UTF_8));
msg.clear();
assertFalse(msg.optionalBytes.length > 0);
msg.clear()
@ -476,7 +476,7 @@ public class NanoTest extends TestCase {
TestAllTypesNano newMsg = TestAllTypesNano.parseFrom(result);
assertTrue(newMsg.optionalBytes.length > 0);
assertEquals("bye", new String(newMsg.optionalBytes, "UTF-8"));
assertEquals("bye", new String(newMsg.optionalBytes, InternalNano.UTF_8));
}
public void testNanoOptionalGroup() throws Exception {
@ -1346,14 +1346,14 @@ public class NanoTest extends TestCase {
InternalNano.copyFromUtf8("bye"),
InternalNano.copyFromUtf8("boo")
};
assertEquals("bye", new String(msg.repeatedBytes[1], "UTF-8"));
assertEquals("boo", new String(msg.repeatedBytes[2], "UTF-8"));
assertEquals("bye", new String(msg.repeatedBytes[1], InternalNano.UTF_8));
assertEquals("boo", new String(msg.repeatedBytes[2], InternalNano.UTF_8));
msg.clear();
assertEquals(0, msg.repeatedBytes.length);
msg.clear()
.repeatedBytes = new byte[][] { InternalNano.copyFromUtf8("boo") };
assertEquals(1, msg.repeatedBytes.length);
assertEquals("boo", new String(msg.repeatedBytes[0], "UTF-8"));
assertEquals("boo", new String(msg.repeatedBytes[0], InternalNano.UTF_8));
msg.clear();
assertEquals(0, msg.repeatedBytes.length);
@ -1385,8 +1385,8 @@ public class NanoTest extends TestCase {
newMsg = TestAllTypesNano.parseFrom(result);
assertEquals(2, newMsg.repeatedBytes.length);
assertEquals("hello", new String(newMsg.repeatedBytes[0], "UTF-8"));
assertEquals("world", new String(newMsg.repeatedBytes[1], "UTF-8"));
assertEquals("hello", new String(newMsg.repeatedBytes[0], InternalNano.UTF_8));
assertEquals("world", new String(newMsg.repeatedBytes[1], InternalNano.UTF_8));
}
public void testNanoRepeatedGroup() throws Exception {
@ -2277,9 +2277,9 @@ public class NanoTest extends TestCase {
assertTrue(52.0e3 == msg.defaultDouble);
assertEquals(true, msg.defaultBool);
assertEquals("hello", msg.defaultString);
assertEquals("world", new String(msg.defaultBytes, "UTF-8"));
assertEquals("world", new String(msg.defaultBytes, InternalNano.UTF_8));
assertEquals("dünya", msg.defaultStringNonascii);
assertEquals("dünyab", new String(msg.defaultBytesNonascii, "UTF-8"));
assertEquals("dünyab", new String(msg.defaultBytesNonascii, InternalNano.UTF_8));
assertEquals(TestAllTypesNano.BAR, msg.defaultNestedEnum);
assertEquals(NanoOuterClass.FOREIGN_NANO_BAR, msg.defaultForeignEnum);
assertEquals(UnittestImportNano.IMPORT_NANO_BAR, msg.defaultImportEnum);
@ -2385,7 +2385,7 @@ public class NanoTest extends TestCase {
assertEquals(TestAllTypesNanoHas.FOO, newMsg.optionalNestedEnum);
assertEquals(41, newMsg.defaultInt32);
assertEquals("hello", newMsg.defaultString);
assertEquals("world", new String(newMsg.defaultBytes, "UTF-8"));
assertEquals("world", new String(newMsg.defaultBytes, InternalNano.UTF_8));
assertEquals(TestAllTypesNanoHas.BAR, newMsg.defaultNestedEnum);
assertEquals(Float.NaN, newMsg.defaultFloatNan);
assertEquals(0, newMsg.id);
@ -2567,7 +2567,7 @@ public class NanoTest extends TestCase {
assertEquals(TestNanoAccessors.FOO, newMsg.getOptionalNestedEnum());
assertEquals(41, newMsg.getDefaultInt32());
assertEquals("hello", newMsg.getDefaultString());
assertEquals("world", new String(newMsg.getDefaultBytes(), "UTF-8"));
assertEquals("world", new String(newMsg.getDefaultBytes(), InternalNano.UTF_8));
assertEquals(TestNanoAccessors.BAR, newMsg.getDefaultNestedEnum());
assertEquals(Float.NaN, newMsg.getDefaultFloatNan());
assertEquals(0, newMsg.id);