lib/unicode.c

   1 /*
   2  * Copyright (c) 2009 Nicira Networks.
   3  *
   4  * Licensed under the Apache License, Version 2.0 (the "License");
   5  * you may not use this file except in compliance with the License.
   6  * You may obtain a copy of the License at:
   7  *
   8  *     http://www.apache.org/licenses/LICENSE-2.0
   9  *
  10  * Unless required by applicable law or agreed to in writing, software
  11  * distributed under the License is distributed on an "AS IS" BASIS,
  12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  13  * See the License for the specific language governing permissions and
  14  * limitations under the License.
  15  */
  16
  17 #include <config.h>
  18
  19 #include "unicode.h"
  20
  21 /* Returns the unicode code point corresponding to leading surrogate 'leading'
  22  * and trailing surrogate 'trailing'.  The return value will not make any
  23  * sense if 'leading' or 'trailing' are not in the correct ranges for leading
  24  * or trailing surrogates. */
  25 int
  26 utf16_decode_surrogate_pair(int leading, int trailing)
  27 {
  28     /*
  29      *  Leading surrogate:         110110wwwwxxxxxx
  30      * Trailing surrogate:         110111xxxxxxxxxx
  31      *         Code point: 000uuuuuxxxxxxxxxxxxxxxx
  32      */
  33     int w = (leading >> 6) & 0xf;
  34     int u = w + 1;
  35     int x0 = leading & 0x3f;
  36     int x1 = trailing & 0x3ff;
  37     return (u << 16) | (x0 << 10) | x1;
  38 }