本文整理汇总了Java中org.apache.lucene.util.UnicodeUtil.UNI_SUR_LOW_START属性的典型用法代码示例。如果您正苦于以下问题：Java UnicodeUtil.UNI_SUR_LOW_START属性的具体用法？Java UnicodeUtil.UNI_SUR_LOW_START怎么用？Java UnicodeUtil.UNI_SUR_LOW_START使用的例子？那么, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类org.apache.lucene.util.UnicodeUtil的用法示例。
在下文中一共展示了UnicodeUtil.UNI_SUR_LOW_START属性的2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: testAllUnicodeChars
public void testAllUnicodeChars() throws Throwable {
CharsRefBuilder utf16 = new CharsRefBuilder();
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);
}
BytesRef utf8 = new BytesRef(CharBuffer.wrap(chars, 0, len));
String s1 = new String(chars, 0, len);
String s2 = new String(utf8.bytes, 0, utf8.length, StandardCharsets.UTF_8);
assertEquals("codepoint " + ch, s1, s2);
utf16.copyUTF8Bytes(utf8.bytes, 0, utf8.length);
assertEquals("codepoint " + ch, s1, utf16.toString());
byte[] b = s1.getBytes(StandardCharsets.UTF_8);
assertEquals(utf8.length, b.length);
for(int j=0;j<utf8.length;j++)
assertEquals(utf8.bytes[j], b[j]);
}
}
示例2: testAllUnicodeChars
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]);
}
}