locale/weight.h

   1 /* Copyright (C) 1996-2022 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3
   4    The GNU C Library is free software; you can redistribute it and/or
   5    modify it under the terms of the GNU Lesser General Public
   6    License as published by the Free Software Foundation; either
   7    version 2.1 of the License, or (at your option) any later version.
   8
   9    The GNU C Library is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  12    Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public
  15    License along with the GNU C Library; if not, see
  16    <https://www.gnu.org/licenses/>.  */
  17
  18 #ifndef _WEIGHT_H_
  19 #define _WEIGHT_H_      1
  20
  21 #include <libc-diag.h>
  22
  23 /* Find index of weight.  */
  24 static inline int32_t __attribute__ ((always_inline))
  25 findidx (const int32_t *table,
  26          const int32_t *indirect,
  27          const unsigned char *extra,
  28          const unsigned char **cpp, size_t len)
  29 {
  30   int_fast32_t i = table[*(*cpp)++];
  31   const unsigned char *cp;
  32   const unsigned char *usrc;
  33
  34   if (i >= 0)
  35     /* This is an index into the weight table.  Cool.  */
  36     return i;
  37
  38   /* Oh well, more than one sequence starting with this byte.
  39      Search for the correct one.  */
  40   cp = &extra[-i];
  41   usrc = *cpp;
  42   --len;
  43   while (1)
  44     {
  45       size_t nhere;
  46
  47       /* The first thing is the index.  */
  48       i = *((const int32_t *) cp);
  49       cp += sizeof (int32_t);
  50
  51       /* Next is the length of the byte sequence.  These are always
  52          short byte sequences so there is no reason to call any
  53          function (even if they are inlined).  */
  54       nhere = *cp++;
  55
  56       if (i >= 0)
  57         {
  58           /* It is a single character.  If it matches we found our
  59              index.  Note that at the end of each list there is an
  60              entry of length zero which represents the single byte
  61              sequence.  The first (and here only) byte was tested
  62              already.  */
  63           size_t cnt;
  64
  65           /* With GCC 5.3 when compiling with -Os the compiler warns
  66              that seq2.back_us, which becomes usrc, might be used
  67              uninitialized.  This can't be true because we pass a length
  68              of -1 for len at the same time which means that this loop
  69              never executes.  */
  70           DIAG_PUSH_NEEDS_COMMENT;
  71           DIAG_IGNORE_Os_NEEDS_COMMENT (5, "-Wmaybe-uninitialized");
  72           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  73             if (cp[cnt] != usrc[cnt])
  74               break;
  75           DIAG_POP_NEEDS_COMMENT;
  76
  77           if (cnt == nhere)
  78             {
  79               /* Found it.  */
  80               *cpp += nhere;
  81               return i;
  82             }
  83
  84           /* Up to the next entry.  */
  85           cp += nhere;
  86           if (!LOCFILE_ALIGNED_P (1 + nhere))
  87             cp += LOCFILE_ALIGN - (1 + nhere) % LOCFILE_ALIGN;
  88         }
  89       else
  90         {
  91           /* This is a range of characters.  First decide whether the
  92              current byte sequence lies in the range.  */
  93           size_t cnt;
  94           size_t offset = 0;
  95
  96           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  97             if (cp[cnt] != usrc[cnt])
  98               break;
  99
 100           if (cnt != nhere)
 101             {
 102               if (cnt == len || cp[cnt] > usrc[cnt])
 103                 {
 104                   /* Cannot be in this range.  */
 105                   cp += 2 * nhere;
 106                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 107                     cp += (LOCFILE_ALIGN
 108                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 109                   continue;
 110                 }
 111
 112               /* Test against the end of the range.  */
 113               for (cnt = 0; cnt < nhere; ++cnt)
 114                 if (cp[nhere + cnt] != usrc[cnt])
 115                   break;
 116
 117               if (cnt != nhere && cp[nhere + cnt] < usrc[cnt])
 118                 {
 119                   /* Cannot be in this range.  */
 120                   cp += 2 * nhere;
 121                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 122                     cp += (LOCFILE_ALIGN
 123                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 124                   continue;
 125                 }
 126
 127               /* This range matches the next characters.  Now find
 128                  the offset in the indirect table.  */
 129               for (cnt = 0; cp[cnt] == usrc[cnt]; ++cnt);
 130
 131               do
 132                 {
 133                   offset <<= 8;
 134                   /* With GCC 7 when compiling with -Os the compiler
 135                      warns that seq1.back_us and seq2.back_us, which
 136                      become usrc, might be used uninitialized.  This
 137                      is impossible for the same reason as described
 138                      above.  */
 139                   DIAG_PUSH_NEEDS_COMMENT;
 140                   DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
 141                   offset += usrc[cnt] - cp[cnt];
 142                   DIAG_POP_NEEDS_COMMENT;
 143                 }
 144               while (++cnt < nhere);
 145             }
 146
 147           *cpp += nhere;
 148           return indirect[-i + offset];
 149         }
 150     }
 151
 152   /* NOTREACHED */
 153   return 0x43219876;
 154 }
 155
 156 #endif  /* weight.h */