wctype/wchar-lookup.h

   1 /* Copyright (C) 2000 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, write to the Free
  17    Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
  18    02111-1307 USA.  */
  19
  20 #include <stdint.h>
  21
  22 /* Tables indexed by a wide character are compressed through the use
  23    of a multi-level lookup.  The compression effect comes from blocks
  24    that don't need particular data and from blocks that can share their
  25    data.  */
  26
  27 /* Bit tables are accessed by cutting wc in four blocks of bits:
  28    - the high 32-q-p bits,
  29    - the next q bits,
  30    - the next p bits,
  31    - the next 5 bits.
  32
  33             +------------------+-----+-----+-----+
  34      wc  =  +     32-q-p-5     |  q  |  p  |  5  |
  35             +------------------+-----+-----+-----+
  36
  37    p and q are variable.  For 16-bit Unicode it is sufficient to
  38    choose p and q such that q+p+5 <= 16.
  39
  40    The table contains the following uint32_t words:
  41    - q+p+5,
  42    - s = upper exclusive bound for wc >> (q+p+5),
  43    - p+5,
  44    - 2^q-1,
  45    - 2^p-1,
  46    - 1st-level table: s offsets, pointing into the 2nd-level table,
  47    - 2nd-level table: k*2^q offsets, pointing into the 3rd-level table,
  48    - 3rd-level table: j*2^p words, each containing 32 bits of data.
  49 */
  50
  51 static __inline int
  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 wcwidth_table_lookup (const char *table, uint32_t wc)
  84 {
  85   uint32_t shift1 = ((const uint32_t *) table)[0];
  86   uint32_t index1 = wc >> shift1;
  87   uint32_t bound = ((const uint32_t *) table)[1];
  88   if (index1 < bound)
  89     {
  90       uint32_t lookup1 = ((const uint32_t *) table)[5 + index1];
  91       if (lookup1 != 0)
  92         {
  93           uint32_t shift2 = ((const uint32_t *) table)[2];
  94           uint32_t mask2 = ((const uint32_t *) table)[3];
  95           uint32_t index2 = (wc >> shift2) & mask2;
  96           uint32_t lookup2 = ((const uint32_t *)(table + lookup1))[index2];
  97           if (lookup2 != 0)
  98             {
  99               uint32_t mask3 = ((const uint32_t *) table)[4];
 100               uint32_t index3 = wc & mask3;
 101               uint8_t lookup3 = ((const uint8_t *)(table + lookup2))[index3];
 102
 103               return lookup3;
 104             }
 105         }
 106     }
 107   return 0xff;
 108 }
 109
 110 /* Mapping tables are similar to bit tables, except that the
 111    addressing unit is a single signed 32-bit word, containing the
 112    difference between the desired result and the argument, and no 5
 113    bits are used as a word index.  */
 114
 115 static __inline uint32_t
 116 wctrans_table_lookup (const char *table, uint32_t wc)
 117 {
 118   uint32_t shift1 = ((const uint32_t *) table)[0];
 119   uint32_t index1 = wc >> shift1;
 120   uint32_t bound = ((const uint32_t *) table)[1];
 121   if (index1 < bound)
 122     {
 123       uint32_t lookup1 = ((const uint32_t *) table)[5 + index1];
 124       if (lookup1 != 0)
 125         {
 126           uint32_t shift2 = ((const uint32_t *) table)[2];
 127           uint32_t mask2 = ((const uint32_t *) table)[3];
 128           uint32_t index2 = (wc >> shift2) & mask2;
 129           uint32_t lookup2 = ((const uint32_t *)(table + lookup1))[index2];
 130           if (lookup2 != 0)
 131             {
 132               uint32_t mask3 = ((const uint32_t *) table)[4];
 133               uint32_t index3 = wc & mask3;
 134               int32_t lookup3 = ((const int32_t *)(table + lookup2))[index3];
 135
 136               return wc + lookup3;
 137             }
 138         }
 139     }
 140   return wc;
 141 }