这段代码展示了如何使用Java的UTF16类进行字符分解操作，特别是在处理代理对（surrogate pairs）时。通过检查代码单元是否低于最小值或具有无关数据，然后使用UTF16.isSurrogate方法判断是否为代理字符，进一步处理Unicode代理对。
import com.ibm.icu.text.UTF16; //导入方法依赖的package包/类
public int decompose(CharSequence s, int src, int limit,
ReorderingBuffer buffer) {
int minNoCP=minDecompNoCP;
int prevSrc;
int c=0;
int norm16=0;
// only for quick check
int prevBoundary=src;
int prevCC=0;
for(;;) {
// count code units below the minimum or with irrelevant data for the quick check
for(prevSrc=src; src!=limit;) {
if( (c=s.charAt(src))
isMostDecompYesAndZeroCC(norm16=normTrie.getFromU16SingleLead((char)c))
) {
++src;
} else if(!UTF16.isSurrogate((char)c)) {
break;
} else {
char c2;
if(UTF16Plus.isSurrogateLead(c)) {
if((src+1)!=limit && Character.isLowSurrogate(c2=s.charAt(src+1))) {
c=Character.toCodePoint((char)c, c2);
}
} else /* trail surrogate */ {
if(prevSrc
--src;
c=Character.toCodePoint(c2, (char)c);
}
}
if(isMostDecompYesAndZeroCC(norm16=getNorm16(c))) {
src+=Character.charCount(c);
} else {
break;
}
}
}
// copy these code units all at once
if(src!=prevSrc) {
if(buffer!=null) {
buffer.flushAndAppendZeroCC(s, prevSrc, src);
} else {
prevCC=0;
prevBoundary=src;
}
}
if(src==limit) {
break;
}
// Check one above-minimum, relevant code point.
src+=Character.charCount(c);
if(buffer!=null) {
decompose(c, norm16, buffer);
} else {
if(isDecompYes(norm16)) {
int cc=getCCFromYesOrMaybe(norm16);
if(prevCC<=cc || cc==0) {
prevCC=cc;
if(cc<=1) {
prevBoundary=src;
}
continue;
}
}
return prevBoundary; // "no" or cc out of order
}
}
return src;
}
扫一扫
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
