in indexer-reader/src/main/java/org/apache/maven/index/reader/ChunkWriter.java [123:164]
private static void writeUTF(final String str, final DataOutput dataOutput) throws IOException {
int strlen = str.length();
int utflen = 0;
int c;
// use charAt instead of copying String to char array
for (int i = 0; i < strlen; i++) {
c = str.charAt(i);
if ((c >= 0x0001) && (c <= 0x007F)) {
utflen++;
} else if (c > 0x07FF) {
utflen += 3;
} else {
utflen += 2;
}
}
dataOutput.writeInt(utflen);
byte[] bytearr = new byte[utflen];
int count = 0;
int i = 0;
for (; i < strlen; i++) {
c = str.charAt(i);
if (!((c >= 0x0001) && (c <= 0x007F))) {
break;
}
bytearr[count++] = (byte) c;
}
for (; i < strlen; i++) {
c = str.charAt(i);
if ((c >= 0x0001) && (c <= 0x007F)) {
bytearr[count++] = (byte) c;
} else if (c > 0x07FF) {
bytearr[count++] = (byte) (0xE0 | ((c >> 12) & 0x0F));
bytearr[count++] = (byte) (0x80 | ((c >> 6) & 0x3F));
bytearr[count++] = (byte) (0x80 | ((c) & 0x3F));
} else {
bytearr[count++] = (byte) (0xC0 | ((c >> 6) & 0x1F));
bytearr[count++] = (byte) (0x80 | ((c) & 0x3F));
}
}
dataOutput.write(bytearr, 0, utflen);
}