locale/weight.h

   1 /* Copyright (C) 1996-2018 Free Software Foundation, Inc.
   2    This file is part of the GNU C Library.
   3    Written by Ulrich Drepper, <drepper@cygnus.com>.
   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 #ifndef _WEIGHT_H_
  20 #define _WEIGHT_H_      1
  21
  22 #include <libc-diag.h>
  23
  24 /* Find index of weight.  */
  25 static inline int32_t __attribute__ ((always_inline))
  26 findidx (const int32_t *table,
  27          const int32_t *indirect,
  28          const unsigned char *extra,
  29          const unsigned char **cpp, size_t len)
  30 {
  31   int_fast32_t i = table[*(*cpp)++];
  32   const unsigned char *cp;
  33   const unsigned char *usrc;
  34
  35   if (i >= 0)
  36     /* This is an index into the weight table.  Cool.  */
  37     return i;
  38
  39   /* Oh well, more than one sequence starting with this byte.
  40      Search for the correct one.  */
  41   cp = &extra[-i];
  42   usrc = *cpp;
  43   --len;
  44   while (1)
  45     {
  46       size_t nhere;
  47
  48       /* The first thing is the index.  */
  49       i = *((const int32_t *) cp);
  50       cp += sizeof (int32_t);
  51
  52       /* Next is the length of the byte sequence.  These are always
  53          short byte sequences so there is no reason to call any
  54          function (even if they are inlined).  */
  55       nhere = *cp++;
  56
  57       if (i >= 0)
  58         {
  59           /* It is a single character.  If it matches we found our
  60              index.  Note that at the end of each list there is an
  61              entry of length zero which represents the single byte
  62              sequence.  The first (and here only) byte was tested
  63              already.  */
  64           size_t cnt;
  65
  66           /* With GCC 5.3 when compiling with -Os the compiler warns
  67              that seq2.back_us, which becomes usrc, might be used
  68              uninitialized.  This can't be true because we pass a length
  69              of -1 for len at the same time which means that this loop
  70              never executes.  */
  71           DIAG_PUSH_NEEDS_COMMENT;
  72           DIAG_IGNORE_Os_NEEDS_COMMENT (5, "-Wmaybe-uninitialized");
  73           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  74             if (cp[cnt] != usrc[cnt])
  75               break;
  76           DIAG_POP_NEEDS_COMMENT;
  77
  78           if (cnt == nhere)
  79             {
  80               /* Found it.  */
  81               *cpp += nhere;
  82               return i;
  83             }
  84
  85           /* Up to the next entry.  */
  86           cp += nhere;
  87           if (!LOCFILE_ALIGNED_P (1 + nhere))
  88             cp += LOCFILE_ALIGN - (1 + nhere) % LOCFILE_ALIGN;
  89         }
  90       else
  91         {
  92           /* This is a range of characters.  First decide whether the
  93              current byte sequence lies in the range.  */
  94           size_t cnt;
  95           size_t offset = 0;
  96
  97           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  98             if (cp[cnt] != usrc[cnt])
  99               break;
 100
 101           if (cnt != nhere)
 102             {
 103               if (cnt == len || cp[cnt] > usrc[cnt])
 104                 {
 105                   /* Cannot be in this range.  */
 106                   cp += 2 * nhere;
 107                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 108                     cp += (LOCFILE_ALIGN
 109                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 110                   continue;
 111                 }
 112
 113               /* Test against the end of the range.  */
 114               for (cnt = 0; cnt < nhere; ++cnt)
 115                 if (cp[nhere + cnt] != usrc[cnt])
 116                   break;
 117
 118               if (cnt != nhere && cp[nhere + cnt] < usrc[cnt])
 119                 {
 120                   /* Cannot be in this range.  */
 121                   cp += 2 * nhere;
 122                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 123                     cp += (LOCFILE_ALIGN
 124                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 125                   continue;
 126                 }
 127
 128               /* This range matches the next characters.  Now find
 129                  the offset in the indirect table.  */
 130               for (cnt = 0; cp[cnt] == usrc[cnt]; ++cnt);
 131
 132               do
 133                 {
 134                   offset <<= 8;
 135                   /* With GCC 7 when compiling with -Os the compiler
 136                      warns that seq1.back_us and seq2.back_us, which
 137                      become usrc, might be used uninitialized.  This
 138                      is impossible for the same reason as described
 139                      above.  */
 140                   DIAG_PUSH_NEEDS_COMMENT;
 141                   DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
 142                   offset += usrc[cnt] - cp[cnt];
 143                   DIAG_POP_NEEDS_COMMENT;
 144                 }
 145               while (++cnt < nhere);
 146             }
 147
 148           *cpp += nhere;
 149           return indirect[-i + offset];
 150         }
 151     }
 152
 153   /* NOTREACHED */
 154   return 0x43219876;
 155 }
 156
 157 #endif  /* weight.h */