iconvdata/tst-table.sh

   1 #!/bin/sh
   2 # Copyright (C) 2000-2012 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 run_program_prefix=$3
  27 charset=$4
  28 charmap=$5
  29
  30 GCONV_PATH=${common_objpfx}iconvdata
  31 export GCONV_PATH
  32 LC_ALL=C
  33 export LC_ALL
  34
  35 set -e
  36
  37 # Get the charmap.
  38 ./tst-table-charmap.sh ${charmap:-$charset} \
  39   < ../localedata/charmaps/${charmap:-$charset} \
  40   > ${objpfx}tst-${charset}.charmap.table
  41 # When the charset is GB18030, truncate this table because for this encoding,
  42 # the tst-table-from and tst-table-to programs scan the Unicode BMP only.
  43 if test ${charset} = GB18030; then
  44   grep '0x....$' < ${objpfx}tst-${charset}.charmap.table \
  45     > ${objpfx}tst-${charset}.truncated.table
  46   mv ${objpfx}tst-${charset}.truncated.table ${objpfx}tst-${charset}.charmap.table
  47 fi
  48
  49 # Precomputed expexted differences between the charmap and iconv forward.
  50 precomposed=${charset}.precomposed
  51
  52 # Precompute expected differences between the charmap and iconv backward.
  53 if test ${charset} = EUC-TW; then
  54   irreversible=${objpfx}tst-${charset}.irreversible
  55   (grep '^0x8EA1' ${objpfx}tst-${charset}.charmap.table
  56    cat ${charset}.irreversible
  57   ) > ${irreversible}
  58 else
  59   irreversible=${charset}.irreversible
  60 fi
  61
  62 # iconv in one direction.
  63 ${run_program_prefix} \
  64 ${objpfx}tst-table-from ${charset} \
  65   > ${objpfx}tst-${charset}.table
  66
  67 # iconv in the other direction.
  68 ${run_program_prefix} \
  69 ${objpfx}tst-table-to ${charset} | sort \
  70   > ${objpfx}tst-${charset}.inverse.table
  71
  72 # Difference between the charmap and iconv backward.
  73 diff ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table | \
  74   grep '^[<>]' | sed -e 's,^. ,,' > ${objpfx}tst-${charset}.irreversible.table
  75
  76 # Check 1: charmap and iconv forward should be identical, except for
  77 # precomposed characters.
  78 if test -f ${precomposed}; then
  79   cat ${objpfx}tst-${charset}.table ${precomposed} | sort | uniq -u \
  80     > ${objpfx}tst-${charset}.tmp.table
  81   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.tmp.table ||
  82   exit 1
  83 else
  84   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.table ||
  85   exit 1
  86 fi
  87
  88 # Check 2: the difference between the charmap and iconv backward.
  89 if test -f ${irreversible}; then
  90   cat ${objpfx}tst-${charset}.charmap.table ${irreversible} | sort | uniq -u \
  91     > ${objpfx}tst-${charset}.tmp.table
  92   cmp -s ${objpfx}tst-${charset}.tmp.table ${objpfx}tst-${charset}.inverse.table ||
  93   exit 1
  94 else
  95   cmp -s ${objpfx}tst-${charset}.charmap.table ${objpfx}tst-${charset}.inverse.table ||
  96   exit 1
  97 fi
  98
  99 exit 0