iconvdata/tst-table.sh

   1 #!/bin/sh
   2 # Copyright (C) 2000-2019 Free Software Foundation, Inc.
   3 # This file is part of the GNU C Library.
   4 # Contributed by Bruno Haible <haible@clisp.cons.org>, 2000.
   5 #
   6
   7 # The GNU C Library is free software; you can redistribute it and/or
   8 # modify it under the terms of the GNU Lesser General Public
   9 # License as published by the Free Software Foundation; either
  10 # version 2.1 of the License, or (at your option) any later version.
  11
  12 # The GNU C Library is distributed in the hope that it will be useful,
  13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  15 # Lesser General Public License for more details.
  16
  17 # You should have received a copy of the GNU Lesser General Public
  18 # License along with the GNU C Library; if not, see
  19 # <http://www.gnu.org/licenses/>.
  20
  21 # Checks that the iconv() implementation (in both directions) for a
  22 # stateless encoding agrees with the charmap table.
  23
  24 common_objpfx=$1
  25 objpfx=$2
  26 test_program_prefix=$3
  27 charset=$4
  28 charmap=$5
  29
  30 # sort is used on the build system.
  31 LC_ALL=C
  32 export LC_ALL
  33
  34 set -e
  35
  36 # Get the charmap.
  37 ./tst-table-charmap.sh ${charmap:-$charset} \
  38   < ../localedata/charmaps/${charmap:-$charset} \
  39   > ${objpfx}tst-${charset}.charmap.table
  40 # When the charset is GB18030, truncate this table because for this encoding,
  41 # the tst-table-from and tst-table-to programs scan the Unicode BMP only.
  42 if test ${charset} = GB18030; then
  43   grep '0x....$' < ${objpfx}tst-${charset}.charmap.table \
  44     > ${objpfx}tst-${charset}.truncated.table
  45   mv ${objpfx}tst-${charset}.truncated.table ${objpfx}tst-${charset}.charmap.table
  46 fi
  47
  48 # Precomputed expexted differences between the charmap and iconv forward.
  49 precomposed=${charset}.precomposed
  50
  51 # Precompute expected differences between the charmap and iconv backward.
  52 if test ${charset} = EUC-TW; then
  53   irreversible=${objpfx}tst-${charset}.irreversible
  54   (grep '^0x8EA1' ${objpfx}tst-${charset}.charmap.table
  55    cat ${charset}.irreversible
  56   ) > ${irreversible}
  57 else
  58   irreversible=${charset}.irreversible
  59 fi
  60
  61 # iconv in one direction.
  62 ${test_program_prefix} \
  63 ${objpfx}tst-table-from ${charset} \
  64   > ${objpfx}tst-${charset}.table
  65
  66 # iconv in the other direction.
  67 ${test_program_prefix} \
  68 ${objpfx}tst-table-to ${charset} | sort \
  69   > ${objpfx}tst-${charset}.inverse.table
  70
  71 # Difference between the charmap and iconv backward.
  72 diff ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table | \
  73   grep '^[<>]' | sed -e 's,^. ,,' > ${objpfx}tst-${charset}.irreversible.table
  74
  75 # Check 1: charmap and iconv forward should be identical, except for
  76 # precomposed characters.
  77 if test -f ${precomposed}; then
  78   cat ${objpfx}tst-${charset}.table ${precomposed} | sort | uniq -u \
  79     > ${objpfx}tst-${charset}.tmp.table
  80   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.tmp.table ||
  81   exit 1
  82 else
  83   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.table ||
  84   exit 1
  85 fi
  86
  87 # Check 2: the difference between the charmap and iconv backward.
  88 if test -f ${irreversible}; then
  89   cat ${objpfx}tst-${charset}.charmap.table ${irreversible} | sort | uniq -u \
  90     > ${objpfx}tst-${charset}.tmp.table
  91   cmp -s ${objpfx}tst-${charset}.tmp.table ${objpfx}tst-${charset}.inverse.table ||
  92   exit 1
  93 else
  94   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table ||
  95   exit 1
  96 fi
  97
  98 exit 0