wctype/wchar-lookup.h

   1 /* Copyright (C) 2000-2017 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Contributed by Bruno Haible <haible@clisp.cons.org>, 2000.
   4
   5    The GNU C Library is free software; you can redistribute it and/or
   6    modify it under the terms of the GNU Lesser General Public
   7    License as published by the Free Software Foundation; either
   8    version 2.1 of the License, or (at your option) any later version.
   9
  10    The GNU C Library is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public
  16    License along with the GNU C Library; if not, see
  17    <http://www.gnu.org/licenses/>.  */
  18
  19 #include <stdint.h>
  20
  21 /* Tables indexed by a wide character are compressed through the use
  22    of a multi-level lookup.  The compression effect comes from blocks
  23    that don't need particular data and from blocks that can share their
  24    data.  */
  25
  26 /* Bit tables are accessed by cutting wc in four blocks of bits:
  27    - the high 32-q-p bits,
  28    - the next q bits,
  29    - the next p bits,
  30    - the next 5 bits.
  31
  32             +------------------+-----+-----+-----+
  33      wc  =  +     32-q-p-5     |  q  |  p  |  5  |
  34             +------------------+-----+-----+-----+
  35
  36    p and q are variable.  For 16-bit Unicode it is sufficient to
  37    choose p and q such that q+p+5 <= 16.
  38
  39    The table contains the following uint32_t words:
  40    - q+p+5,
  41    - s = upper exclusive bound for wc >> (q+p+5),
  42    - p+5,
  43    - 2^q-1,
  44    - 2^p-1,
  45    - 1st-level table: s offsets, pointing into the 2nd-level table,
  46    - 2nd-level table: k*2^q offsets, pointing into the 3rd-level table,
  47    - 3rd-level table: j*2^p words, each containing 32 bits of data.
  48 */
  49
  50 static __inline int
  51 __attribute ((always_inline))
  52 wctype_table_lookup (const char *table, uint32_t wc)
  53 {
  54   uint32_t shift1 = ((const uint32_t *) table)[0];
  55   uint32_t index1 = wc >> shift1;
  56   uint32_t bound = ((const uint32_t *) table)[1];
  57   if (index1 < bound)
  58     {
  59       uint32_t lookup1 = ((const uint32_t *) table)[5 + index1];
  60       if (lookup1 != 0)
  61         {
  62           uint32_t shift2 = ((const uint32_t *) table)[2];
  63           uint32_t mask2 = ((const uint32_t *) table)[3];
  64           uint32_t index2 = (wc >> shift2) & mask2;
  65           uint32_t lookup2 = ((const uint32_t *)(table + lookup1))[index2];
  66           if (lookup2 != 0)
  67             {
  68               uint32_t mask3 = ((const uint32_t *) table)[4];
  69               uint32_t index3 = (wc >> 5) & mask3;
  70               uint32_t lookup3 = ((const uint32_t *)(table + lookup2))[index3];
  71
  72               return (lookup3 >> (wc & 0x1f)) & 1;
  73             }
  74         }
  75     }
  76   return 0;
  77 }
  78
  79 /* Byte tables are similar to bit tables, except that the addressing
  80    unit is a single byte, and no 5 bits are used as a word index.  */
  81
  82 static __inline int
  83 __attribute ((always_inline))
  84 wcwidth_table_lookup (const char *table, uint32_t wc)
  85 {
  86   uint32_t shift1 = ((const uint32_t *) table)[0];
  87   uint32_t index1 = wc >> shift1;
  88   uint32_t bound = ((const uint32_t *) table)[1];
  89   if (index1 < bound)
  90     {
  91       uint32_t lookup1 = ((const uint32_t *) table)[5 + index1];
  92       if (lookup1 != 0)
  93         {
  94           uint32_t shift2 = ((const uint32_t *) table)[2];
  95           uint32_t mask2 = ((const uint32_t *) table)[3];
  96           uint32_t index2 = (wc >> shift2) & mask2;
  97           uint32_t lookup2 = ((const uint32_t *)(table + lookup1))[index2];
  98           if (lookup2 != 0)
  99             {
 100               uint32_t mask3 = ((const uint32_t *) table)[4];
 101               uint32_t index3 = wc & mask3;
 102               uint8_t lookup3 = ((const uint8_t *)(table + lookup2))[index3];
 103
 104               return lookup3;
 105             }
 106         }
 107     }
 108   return 0xff;
 109 }
 110
 111 /* Mapping tables are similar to bit tables, except that the
 112    addressing unit is a single signed 32-bit word, containing the
 113    difference between the desired result and the argument, and no 5
 114    bits are used as a word index.  */
 115
 116 static __inline uint32_t
 117 __attribute ((always_inline))
 118 wctrans_table_lookup (const char *table, uint32_t wc)
 119 {
 120   uint32_t shift1 = ((const uint32_t *) table)[0];
 121   uint32_t index1 = wc >> shift1;
 122   uint32_t bound = ((const uint32_t *) table)[1];
 123   if (index1 < bound)
 124     {
 125       uint32_t lookup1 = ((const uint32_t *) table)[5 + index1];
 126       if (lookup1 != 0)
 127         {
 128           uint32_t shift2 = ((const uint32_t *) table)[2];
 129           uint32_t mask2 = ((const uint32_t *) table)[3];
 130           uint32_t index2 = (wc >> shift2) & mask2;
 131           uint32_t lookup2 = ((const uint32_t *)(table + lookup1))[index2];
 132           if (lookup2 != 0)
 133             {
 134               uint32_t mask3 = ((const uint32_t *) table)[4];
 135               uint32_t index3 = wc & mask3;
 136               int32_t lookup3 = ((const int32_t *)(table + lookup2))[index3];
 137
 138               return wc + lookup3;
 139             }
 140         }
 141     }
 142   return wc;
 143 }