本文整理汇总了Java中org.apache.lucene.util.UnicodeUtil.UTF16toUTF8方法的典型用法代码示例。如果您正苦于以下问题：Java UnicodeUtil.UTF16toUTF8方法的具体用法？Java UnicodeUtil.UTF16toUTF8怎么用？Java UnicodeUtil.UTF16toUTF8使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.apache.lucene.util.UnicodeUtil的用法示例。
在下文中一共展示了UnicodeUtil.UTF16toUTF8方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: evaluate
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public BytesRef evaluate(Input<Object>... args) {
Object stringValue = args[0].value();
if (stringValue == null) {
return null;
}
BytesRef inputByteRef = BytesRefs.toBytesRef(stringValue);
char[] ref = new char[inputByteRef.length];
int len = UnicodeUtil.UTF8toUTF16(inputByteRef.bytes, inputByteRef.offset, inputByteRef.length, ref);
charUtils.toLowerCase(ref, 0, len);
byte[] res = new byte[UnicodeUtil.MAX_UTF8_BYTES_PER_CHAR * len];
len = UnicodeUtil.UTF16toUTF8(ref, 0, len, res);
return new BytesRef(res, 0, len);
}
示例2: evaluate
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public BytesRef evaluate(Input<Object>... args) {
Object stringValue = args[0].value();
if (stringValue == null) {
return null;
}
BytesRef inputByteRef = BytesRefs.toBytesRef(stringValue);
char[] ref = new char[inputByteRef.length];
int len = UnicodeUtil.UTF8toUTF16(inputByteRef.bytes, inputByteRef.offset, inputByteRef.length, ref);
charUtils.toUpperCase(ref, 0, len);
byte[] res = new byte[UnicodeUtil.MAX_UTF8_BYTES_PER_CHAR * len];
len = UnicodeUtil.UTF16toUTF8(ref, 0, len, res);
return new BytesRef(res, 0, len);
}
示例3: testRandomUnicodeStrings
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
public void testRandomUnicodeStrings() throws Throwable {
char[] buffer = new char[20];
char[] expected = new char[20];
BytesRef utf8 = new BytesRef(20);
CharsRef utf16 = new CharsRef(20);
int num = atLeast(100000);
for (int iter = 0; iter < num; iter++) {
boolean hasIllegal = fillUnicode(buffer, expected, 0, 20);
UnicodeUtil.UTF16toUTF8(buffer, 0, 20, utf8);
if (!hasIllegal) {
byte[] b = new String(buffer, 0, 20).getBytes("UTF-8");
assertEquals(b.length, utf8.length);
for(int i=0;i<b.length;i++)
assertEquals(b[i], utf8.bytes[i]);
}
UnicodeUtil.UTF8toUTF16(utf8.bytes, 0, utf8.length, utf16);
assertEquals(utf16.length, 20);
for(int i=0;i<20;i++)
assertEquals(expected[i], utf16.chars[i]);
}
}
示例4: add
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
/**
* Adds an input string and it's stemmer override output to this builder.
*
* @param input the input char sequence
* @param output the stemmer override output char sequence
* @return <code>false</code> iff the input has already been added to this builder otherwise <code>true</code>.
*/
public boolean add(CharSequence input, CharSequence output) {
final int length = input.length();
if (ignoreCase) {
// convert on the fly to lowercase
charsSpare.grow(length);
final char[] buffer = charsSpare.chars;
for (int i = 0; i < length; ) {
i += Character.toChars(
Character.toLowerCase(
Character.codePointAt(input, i)), buffer, i);
}
UnicodeUtil.UTF16toUTF8(buffer, 0, length, spare);
} else {
UnicodeUtil.UTF16toUTF8(input, 0, length, spare);
}
if (hash.add(spare) >= 0) {
outputValues.add(output);
return true;
}
return false;
}
示例5: writeStr
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public void writeStr(String name, String val, boolean needsEscaping) throws IOException {
// serialized PHP strings don't need to be escaped at all, however the
// string size reported needs be the number of bytes rather than chars.
utf8 = ArrayUtil.grow(utf8, val.length() * UnicodeUtil.MAX_UTF8_BYTES_PER_CHAR);
final int nBytes = UnicodeUtil.UTF16toUTF8(val, 0, val.length(), utf8);
writer.write("s:");
writer.write(Integer.toString(nBytes));
writer.write(":\"");
writer.write(val);
writer.write("\";");
}
示例6: unmarshalStringSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
/**
* Unmarshals a string-based field value.
*/
protected static Object unmarshalStringSortValue(Object value) {
if (null == value) {
return null;
}
BytesRef spare = new BytesRef();
String stringVal = (String)value;
UnicodeUtil.UTF16toUTF8(stringVal, spare);
return spare;
}
示例7: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.int2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, bytes);
return bytes;
}
示例8: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.long2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, bytes);
return bytes;
}
示例9: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.float2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, bytes);
return bytes;
}
示例10: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.double2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, bytes);
return bytes;
}
示例11: testAllUnicodeChars
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
public void testAllUnicodeChars() throws Throwable {
BytesRef utf8 = new BytesRef(10);
CharsRef utf16 = new CharsRef(10);
char[] chars = new char[2];
for(int ch=0;ch<0x0010FFFF;ch++) {
if (ch == 0xd800)
// Skip invalid code points
ch = 0xe000;
int len = 0;
if (ch <= 0xffff) {
chars[len++] = (char) ch;
} else {
chars[len++] = (char) (((ch-0x0010000) >> 10) + UnicodeUtil.UNI_SUR_HIGH_START);
chars[len++] = (char) (((ch-0x0010000) & 0x3FFL) + UnicodeUtil.UNI_SUR_LOW_START);
}
UnicodeUtil.UTF16toUTF8(chars, 0, len, utf8);
String s1 = new String(chars, 0, len);
String s2 = new String(utf8.bytes, 0, utf8.length, "UTF-8");
assertEquals("codepoint " + ch, s1, s2);
UnicodeUtil.UTF8toUTF16(utf8.bytes, 0, utf8.length, utf16);
assertEquals("codepoint " + ch, s1, new String(utf16.chars, 0, utf16.length));
byte[] b = s1.getBytes("UTF-8");
assertEquals(utf8.length, b.length);
for(int j=0;j<utf8.length;j++)
assertEquals(utf8.bytes[j], b[j]);
}
}
示例12: writeStr
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public void writeStr(String name, String val, boolean needsEscaping) throws IOException {
// serialized PHP strings don't need to be escaped at all, however the
// string size reported needs be the number of bytes rather than chars.
UnicodeUtil.UTF16toUTF8(val, 0, val.length(), utf8);
int nBytes = utf8.length;
writer.write("s:");
writer.write(Integer.toString(nBytes));
writer.write(":\"");
writer.write(val);
writer.write("\";");
}
示例13: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.int2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, 0, sortableString.length(), bytes);
return bytes;
}
示例14: unmarshalSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
@Override
public Object unmarshalSortValue(Object value) {
if (null == value) {
return null;
}
String sortableString = NumberUtils.float2sortableStr(value.toString());
BytesRef bytes = new BytesRef();
UnicodeUtil.UTF16toUTF8(sortableString, 0, sortableString.length(), bytes);
return bytes;
}
示例15: unmarshalStringSortValue
import org.apache.lucene.util.UnicodeUtil; //导入方法依赖的package包/类
/**
* Unmarshals a string-based field value.
*/
protected static Object unmarshalStringSortValue(Object value) {
if (null == value) {
return null;
}
BytesRef spare = new BytesRef();
String stringVal = (String)value;
UnicodeUtil.UTF16toUTF8(stringVal, 0, stringVal.length(), spare);
return spare;
}