iconvdata/tst-table.sh

   1 #!/bin/sh
   2 # Copyright (C) 2000-2022 Free Software Foundation, Inc.
   3 # This file is part of the GNU C Library.
   4 #
   5
   6 # The GNU C Library is free software; you can redistribute it and/or
   7 # modify it under the terms of the GNU Lesser General Public
   8 # License as published by the Free Software Foundation; either
   9 # version 2.1 of the License, or (at your option) any later version.
  10
  11 # The GNU C Library is distributed in the hope that it will be useful,
  12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14 # Lesser General Public License for more details.
  15
  16 # You should have received a copy of the GNU Lesser General Public
  17 # License along with the GNU C Library; if not, see
  18 # <https://www.gnu.org/licenses/>.
  19
  20 # Checks that the iconv() implementation (in both directions) for a
  21 # stateless encoding agrees with the charmap table.
  22
  23 common_objpfx=$1
  24 objpfx=$2
  25 test_program_prefix=$3
  26 charset=$4
  27 charmap=$5
  28
  29 # sort is used on the build system.
  30 LC_ALL=C
  31 export LC_ALL
  32
  33 set -e
  34
  35 # Get the charmap.
  36 ./tst-table-charmap.sh ${charmap:-$charset} \
  37   < ../localedata/charmaps/${charmap:-$charset} \
  38   > ${objpfx}tst-${charset}.charmap.table
  39 # When the charset is GB18030, truncate this table because for this encoding,
  40 # the tst-table-from and tst-table-to programs scan the Unicode BMP only.
  41 if test ${charset} = GB18030; then
  42   grep '0x....$' < ${objpfx}tst-${charset}.charmap.table \
  43     > ${objpfx}tst-${charset}.truncated.table
  44   mv ${objpfx}tst-${charset}.truncated.table ${objpfx}tst-${charset}.charmap.table
  45 fi
  46
  47 # Precomputed expexted differences between the charmap and iconv forward.
  48 precomposed=${charset}.precomposed
  49
  50 # Precompute expected differences between the charmap and iconv backward.
  51 if test ${charset} = EUC-TW; then
  52   irreversible=${objpfx}tst-${charset}.irreversible
  53   (grep '^0x8EA1' ${objpfx}tst-${charset}.charmap.table
  54    cat ${charset}.irreversible
  55   ) > ${irreversible}
  56 else
  57   irreversible=${charset}.irreversible
  58 fi
  59
  60 # iconv in one direction.
  61 ${test_program_prefix} \
  62 ${objpfx}tst-table-from ${charset} \
  63   > ${objpfx}tst-${charset}.table
  64
  65 # iconv in the other direction.
  66 ${test_program_prefix} \
  67 ${objpfx}tst-table-to ${charset} | sort \
  68   > ${objpfx}tst-${charset}.inverse.table
  69
  70 # Difference between the charmap and iconv backward.
  71 diff ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table | \
  72   grep '^[<>]' | sed -e 's,^. ,,' > ${objpfx}tst-${charset}.irreversible.table
  73
  74 # Check 1: charmap and iconv forward should be identical, except for
  75 # precomposed characters.
  76 if test -f ${precomposed}; then
  77   cat ${objpfx}tst-${charset}.table ${precomposed} | sort | uniq -u \
  78     > ${objpfx}tst-${charset}.tmp.table
  79   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.tmp.table ||
  80   exit 1
  81 else
  82   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.table ||
  83   exit 1
  84 fi
  85
  86 # Check 2: the difference between the charmap and iconv backward.
  87 if test -f ${irreversible}; then
  88   cat ${objpfx}tst-${charset}.charmap.table ${irreversible} | sort | uniq -u \
  89     > ${objpfx}tst-${charset}.tmp.table
  90   cmp -s ${objpfx}tst-${charset}.tmp.table ${objpfx}tst-${charset}.inverse.table ||
  91   exit 1
  92 else
  93   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table ||
  94   exit 1
  95 fi
  96
  97 exit 0