locale/weightwc.h

   1 /* Copyright (C) 1996-2024 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 _WEIGHTWC_H_
  19 #define _WEIGHTWC_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 wint_t *extra,
  28          const wint_t **cpp, size_t len)
  29 {
  30   /* With GCC 7 when compiling with -Os the compiler warns that
  31      seq1.back_us and seq2.back_us, which become *cpp, might be used
  32      uninitialized.  This is impossible as this function cannot be
  33      called except in cases where those fields have been
  34      initialized.  */
  35   DIAG_PUSH_NEEDS_COMMENT;
  36   DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
  37   wint_t ch = *(*cpp)++;
  38   DIAG_POP_NEEDS_COMMENT;
  39   int32_t i = __collidx_table_lookup ((const char *) table, ch);
  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   const int32_t *cp = (const int32_t *) &extra[-i];
  48   --len;
  49   while (1)
  50     {
  51       size_t nhere;
  52       const int32_t *usrc = (const int32_t *) *cpp;
  53
  54       /* The first thing is the index.  */
  55       i = *cp++;
  56
  57       /* Next is the length of the byte sequence.  These are always
  58          short byte sequences so there is no reason to call any
  59          function (even if they are inlined).  */
  60       nhere = *cp++;
  61
  62       if (i >= 0)
  63         {
  64           /* It is a single character.  If it matches we found our
  65              index.  Note that at the end of each list there is an
  66              entry of length zero which represents the single byte
  67              sequence.  The first (and here only) byte was tested
  68              already.  */
  69           size_t cnt;
  70
  71           /* With GCC 5.3 when compiling with -Os the compiler warns
  72              that seq2.back_us, which becomes usrc, might be used
  73              uninitialized.  This can't be true because we pass a length
  74              of -1 for len at the same time which means that this loop
  75              never executes.  */
  76           DIAG_PUSH_NEEDS_COMMENT;
  77           DIAG_IGNORE_Os_NEEDS_COMMENT (5, "-Wmaybe-uninitialized");
  78           for (cnt = 0; cnt < nhere && cnt < len; ++cnt)
  79             if (cp[cnt] != usrc[cnt])
  80               break;
  81           DIAG_POP_NEEDS_COMMENT;
  82
  83           if (cnt == nhere)
  84             {
  85               /* Found it.  */
  86               *cpp += nhere;
  87               return i;
  88             }
  89
  90           /* Up to the next entry.  */
  91           cp += nhere;
  92         }
  93       else
  94         {
  95           /* This is a range of characters.  First decide whether the
  96              current byte sequence lies in the range.  */
  97           size_t cnt;
  98           size_t offset;
  99
 100           /* With GCC 7 when compiling with -Os the compiler warns
 101              that seq1.back_us and seq2.back_us, which become usrc,
 102              might be used uninitialized.  This is impossible for the
 103              same reason as described above.  */
 104           DIAG_PUSH_NEEDS_COMMENT;
 105           DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
 106           for (cnt = 0; cnt < nhere - 1 && cnt < len; ++cnt)
 107             if (cp[cnt] != usrc[cnt])
 108               break;
 109           DIAG_POP_NEEDS_COMMENT;
 110
 111           if (cnt < nhere - 1 || cnt == len)
 112             {
 113               cp += 2 * nhere;
 114               continue;
 115             }
 116
 117           /* With GCC 7 when compiling with -Os the compiler warns
 118              that seq1.back_us and seq2.back_us, which become usrc,
 119              might be used uninitialized.  This is impossible for the
 120              same reason as described above.  */
 121           DIAG_PUSH_NEEDS_COMMENT;
 122           DIAG_IGNORE_Os_NEEDS_COMMENT (7, "-Wmaybe-uninitialized");
 123           if (cp[nhere - 1] > usrc[nhere - 1])
 124             {
 125               cp += 2 * nhere;
 126               continue;
 127             }
 128           DIAG_POP_NEEDS_COMMENT;
 129
 130           if (cp[2 * nhere - 1] < usrc[nhere - 1])
 131             {
 132               cp += 2 * nhere;
 133               continue;
 134             }
 135
 136           /* This range matches the next characters.  Now find
 137              the offset in the indirect table.  */
 138           offset = usrc[nhere - 1] - cp[nhere - 1];
 139           *cpp += nhere;
 140
 141           return indirect[-i + offset];
 142         }
 143     }
 144
 145   /* NOTREACHED */
 146   return 0x43219876;
 147 }
 148
 149 #endif  /* weightwc.h */