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   /* With GCC 8 when compiling with -Os the compiler warns that
  31      seq1.back_us and seq2.back_us might be used uninitialized.
  32      This uninitialized use is impossible for the same reason
  33      as described in comments in locale/weightwc.h.  */
  34   DIAG_PUSH_NEEDS_COMMENT;
  35   DIAG_IGNORE_Os_NEEDS_COMMENT (8, "-Wmaybe-uninitialized");
  36   int32_t i = table[*(*cpp)++];
  37   DIAG_POP_NEEDS_COMMENT;
  38   const unsigned char *cp;
  39   const unsigned char *usrc;
  40
  41   if (i >= 0)
  42     /* This is an index into the weight table.  Cool.  */
  43     return i;
  44
  45   /* Oh well, more than one sequence starting with this byte.
  46      Search for the correct one.  */
  47   cp = &extra[-i];
  48   usrc = *cpp;
  49   --len;
  50   while (1)
  51     {
  52       size_t nhere;
  53
  54       /* The first thing is the index.  */
  55       i = *((const int32_t *) cp);
  56       cp += sizeof (int32_t);
  57
  58       /* Next is the length of the byte sequence.  These are always
  59          short byte sequences so there is no reason to call any
  60          function (even if they are inlined).  */
  61       nhere = *cp++;
  62
  63       if (i >= 0)
  64         {
  65           /* It is a single character.  If it matches we found our
  66              index.  Note that at the end of each list there is an
  67              entry of length zero which represents the single byte
  68              sequence.  The first (and here only) byte was tested
  69              already.  */
  70           size_t cnt;
  71
  72           /* With GCC 5.3 when compiling with -Os the compiler warns
  73              that seq2.back_us, which becomes usrc, might be used
  74              uninitialized.  This can't be true because we pass a length
  75              of -1 for len at the same time which means that this loop
  76              never executes.  */
  77           DIAG_PUSH_NEEDS_COMMENT;
  78           DIAG_IGNORE_Os_NEEDS_COMMENT (5, "-Wmaybe-uninitialized");
  79           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  80             if (cp[cnt] != usrc[cnt])
  81               break;
  82           DIAG_POP_NEEDS_COMMENT;
  83
  84           if (cnt == nhere)
  85             {
  86               /* Found it.  */
  87               *cpp += nhere;
  88               return i;
  89             }
  90
  91           /* Up to the next entry.  */
  92           cp += nhere;
  93           if (!LOCFILE_ALIGNED_P (1 + nhere))
  94             cp += LOCFILE_ALIGN - (1 + nhere) % LOCFILE_ALIGN;
  95         }
  96       else
  97         {
  98           /* This is a range of characters.  First decide whether the
  99              current byte sequence lies in the range.  */
 100           size_t cnt;
 101           size_t offset = 0;
 102
 103           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
 104             if (cp[cnt] != usrc[cnt])
 105               break;
 106
 107           if (cnt != nhere)
 108             {
 109               if (cnt == len || cp[cnt] > usrc[cnt])
 110                 {
 111                   /* Cannot be in this range.  */
 112                   cp += 2 * nhere;
 113                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 114                     cp += (LOCFILE_ALIGN
 115                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 116                   continue;
 117                 }
 118
 119               /* Test against the end of the range.  */
 120               for (cnt = 0; cnt < nhere; ++cnt)
 121                 if (cp[nhere + cnt] != usrc[cnt])
 122                   break;
 123
 124               if (cnt != nhere && cp[nhere + cnt] < usrc[cnt])
 125                 {
 126                   /* Cannot be in this range.  */
 127                   cp += 2 * nhere;
 128                   if (!LOCFILE_ALIGNED_P (1 + 2 * nhere))
 129                     cp += (LOCFILE_ALIGN
 130                            - (1 + 2 * nhere) % LOCFILE_ALIGN);
 131                   continue;
 132                 }
 133
 134               /* This range matches the next characters.  Now find
 135                  the offset in the indirect table.  */
 136               for (cnt = 0; cp[cnt] == usrc[cnt]; ++cnt);
 137
 138               do
 139                 {
 140                   offset <<= 8;
 141                   /* With GCC 7 when compiling with -Os the compiler
 142                      warns that seq1.back_us and seq2.back_us, which
 143                      become usrc, might be used uninitialized.  This
 144                      is impossible for the same reason as described
 145                      above.  */
 146                   DIAG_PUSH_NEEDS_COMMENT;
 147                   DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
 148                   offset += usrc[cnt] - cp[cnt];
 149                   DIAG_POP_NEEDS_COMMENT;
 150                 }
 151               while (++cnt < nhere);
 152             }
 153
 154           *cpp += nhere;
 155           return indirect[-i + offset];
 156         }
 157     }
 158
 159   /* NOTREACHED */
 160   return 0x43219876;
 161 }
 162
 163 #endif  /* weight.h */