external/cde
1
0
Fork 0
mirror of git://git.code.sf.net/p/cdesktopenv/code synced 2025-02-24 23:14:14 +00:00
Code Issues Releases Wiki Activity
cde/src/cmd/ksh93/tests/locale.sh
Martijn Dekker 2182ecfa08 Fix compile/regress fails on compiling without SHOPT_* options 
Many compile-time options were broken so that they could not be
turned off without causing compile errors and/or regression test
failures. This commit now allows the following to be disabled:

SHOPT_2DMATCH    # two dimensional ${.sh.match} for ${var//pat/str}
SHOPT_BGX        # one SIGCHLD trap per completed job
SHOPT_BRACEPAT   # C-shell {...,...} expansions (, required)
SHOPT_ESH        # emacs/gmacs edit mode
SHOPT_HISTEXPAND # csh-style history file expansions
SHOPT_MULTIBYTE  # multibyte character handling
SHOPT_NAMESPACE  # allow namespaces
SHOPT_STATS      # add .sh.stats variable
SHOPT_VSH        # vi edit mode

The following still break ksh when disabled:

SHOPT_FIXEDARRAY # fixed dimension indexed array
SHOPT_RAWONLY    # make viraw the only vi mode
SHOPT_TYPEDEF    # enable typeset type definitions

Compiling without SHOPT_RAWONLY just gives four regression test
failures in pty.sh, but turning off SHOPT_FIXEDARRAY and
SHOPT_TYPEDEF causes compilation to fail. I've managed to tweak the
code to make it compile without those two options, but then dozens
of regression test failures occur, often in things nothing directly
to do with those options. It looks like the separation between the
code for these options and the rest was never properly maintained.
Making it possible to disable SHOPT_FIXEDARRAY and SHOPT_TYPEDEF
may involve major refactoring and testing and may not be worth it.

This commit has far too many tweaks to list. Notables fixes are:

src/cmd/ksh93/data/builtins.c,
src/cmd/ksh93/data/options.c:
- Do not compile in the shell options and documentation for
  disabled features (braceexpand, emacs/gmacs, vi/viraw), so the
  shell is not left with no-op options and inaccurate self-doc.

src/cmd/ksh93/data/lexstates.c:
- Comment the state tables to associte them with their IDs.
- In the ST_MACRO table (sh_lexstate9[]), do not make the S_BRACE
  state for position 123 (ASCII for '{') conditional upon
  SHOPT_BRACEPAT (brace expansion), otherwise disabling this causes
  glob patterns of the form {3}(x) (matching 3 x'es) to stop
  working as well -- and that is ksh globbing, not brace expansion.

src/cmd/ksh93/edit/edit.c: ed_read():
- Fixed a bug: SIGWINCH was not handled by the gmacs edit mode.

src/cmd/ksh93/sh/name.c: nv_putval():
- The -L/-R left/right adjustment options to typeset do not count
  zero-width characters. This is the behaviour with SHOPT_MULTIBYTE
  enabled, regardless of locale. Of course, what a zero-width
  character is depends on the locale, but control characters are
  always considered zero-width. So, to avoid a regression, add some
  fallback code for non-SHOPT_MULTIBYTE builds that skips ASCII
  control characters (as per iscntrl(3)) so they are still
  considered to have zero width.

src/cmd/ksh93/tests/shtests:
- Export the SHOPT_* macros from SHOPT.sh to the tests as
  environment variables, so the tests can check for them and decide
  whether or how to run tests based on the compile-time options
  that the tested binary was presumably compiled with.
- Do not run the C.UTF-8 tests if SHOPT_MULTIBYTE is not enabled.

src/cmd/ksh93/tests/*.sh:
- Add a bunch of checks for SHOPT_* env vars. Since most should
  have a value 0 (off) or 1 (on), the form ((SHOPT_FOO)) is a
  convenient way to use them as arithmetic booleans.

.github/workflows/ci.yml:
- Make GitHub do more testing: run two locale tests (Dutch and
  Japanese UTF-8 locales), then disable all the SHOPTs that we can
  currently disable, recompile ksh, and run the tests again.
2021-02-08 22:02:45 +00:00

356 lines
12 KiB
Bash
Executable file
Raw Blame History

########################################################################
# #
# This software is part of the ast package #
# Copyright (c) 1982-2012 AT&T Intellectual Property #
# and is licensed under the #
# Eclipse Public License, Version 1.0 #
# by AT&T Intellectual Property #
# #
# A copy of the License is available at #
# http://www.eclipse.org/org/documents/epl-v10.html #
# (with md5 checksum b35adb5213ca9657e911e9befb180842) #
# #
# Information and Software Systems Research #
# AT&T Research #
# Florham Park NJ #
# #
# David Korn <dgk@research.att.com> #
# #
########################################################################
function err_exit
{
print -u2 -n "\t"
print -u2 -r ${Command}[$1]: "${@:2}"
let Errors+=1
}
alias err_exit='err_exit $LINENO'
Command=${0##*/}
integer Errors=0
[[ -d $tmp && -w $tmp && $tmp == "$PWD" ]] || { err\_exit "$LINENO" '$tmp not set; run this from shtests. Aborting.'; exit 1; }
unset LANG ${!LC_*}
a=$($SHELL -c '/' 2>&1 | sed -e "s,.*: *,," -e "s, *\[.*,,")
b=$($SHELL -c '(LC_ALL=debug / 2>/dev/null); /' 2>&1 | sed -e "s,.*: *,," -e "s, *\[.*,,")
[[ "$b" == "$a" ]] || err_exit "locale not restored after subshell -- expected '$a', got '$b'"
b=$($SHELL -c '(LC_ALL=debug; / 2>/dev/null); /' 2>&1 | sed -e "s,.*: *,," -e "s, *\[.*,,")
[[ "$b" == "$a" ]] || err_exit "locale not restored after subshell -- expected '$a', got '$b'"
if((SHOPT_MULTIBYTE)); then
# test shift-jis \x81\x40 ... \x81\x7E encodings
# (shift char followed by 7 bit ascii)
typeset -i16 chr
for locale in $(command -p locale -a 2>/dev/null | grep -i jis)
do export LC_ALL=$locale
for ((chr=0x40; chr<=0x7E; chr++))
do c=${chr#16#}
for s in \\x81\\x$c \\x$c
do b="$(printf "$s")"
eval n=\$\'$s\'
[[ $b == "$n" ]] || err_exit "LC_ALL=$locale printf difference for \"$s\" -- expected '$n', got '$b'"
u=$(print -- $b)
q=$(print -- "$b")
[[ $u == "$q" ]] || err_exit "LC_ALL=$locale quoted print difference for \"$s\" -- $b => '$u' vs \"$b\" => '$q'"
done
done
done
fi # SHOPT_MULTIBYTE
# this locale is supported by ast on all platforms
# EU for { decimal_point="," thousands_sep="." }
if((SHOPT_MULTIBYTE)); then
locale=C_EU.UTF-8
else
locale=C_EU
fi
export LC_ALL=C
# test multibyte value/trace format -- $'\303\274' is UTF-8 u-umlaut
c=$(LC_ALL=C $SHELL -c "printf $':%2s:\n' $'\303\274'")
u=$(LC_ALL=$locale $SHELL -c "printf $':%2s:\n' $'\303\274'" 2>/dev/null)
if [[ "$c" != "$u" ]]
then LC_ALL=$locale
x=$'+2+ typeset item.text\
+3+ item.text=\303\274\
+4+ print -- \303\274\
\303\274\
+5+ eval $\'arr[0]=(\\n\\ttext=\\303\\274\\n)\'
+2+ arr[0].text=ü\
+6+ print -- \303\274\
ü\
+7+ eval txt=$\'(\\n\\ttext=\\303\\274\\n)\'
+2+ txt.text=\303\274\
+8+ print -- \'(\' text=$\'\\303\\274\' \')\'\
( text=\303\274 )'
u=$(LC_ALL=$locale PS4='+$LINENO+ ' $SHELL -x -c "
item=(typeset text)
item.text=$'\303\274'
print -- \"\${item.text}\"
eval \"arr[0]=\$item\"
print -- \"\${arr[0].text}\"
eval \"txt=\${arr[0]}\"
print -- \$txt
" 2>&1)
[[ "$u" == "$x" ]] || err_exit LC_ALL=$locale multibyte value/trace format failed
x=$'00fc\n20ac'
u=$(LC_ALL=$locale $SHELL -c $'printf "%04x\n" \$\'\"\303\274\"\' \$\'\"\xE2\x82\xAC\"\'')
[[ $u == $x ]] || err_exit LC_ALL=$locale multibyte %04x printf format failed
fi
if (( $($SHELL -c $'export LC_ALL='$locale$'; print -r "\342\202\254\342\202\254\342\202\254\342\202\254w\342\202\254\342\202\254\342\202\254\342\202\254" | wc -m' 2>/dev/null) == 10 ))
then LC_ALL=$locale $SHELL -c b1=$'"\342\202\254\342\202\254\342\202\254\342\202\254w\342\202\254\342\202\254\342\202\254\342\202\254"; [[ ${b1:4:1} == w ]]' || err_exit 'multibyte ${var:offset:len} not working correctly'
fi
#$SHELL -c 'export LANG='$locale'; printf "\u[20ac]\u[20ac]" > $tmp/two_euro_chars.txt'
printf $'\342\202\254\342\202\254' > $tmp/two_euro_chars.txt
if((SHOPT_MULTIBYTE)); then
exp="6 2 6"
else
exp="6 6 6"
fi # SHOPT_MULTIBYTE
set -- $($SHELL -c "
if builtin wc 2>/dev/null || builtin -f cmd wc 2>/dev/null
then unset LC_CTYPE
export LANG=$locale
export LC_ALL=C
wc -C < $tmp/two_euro_chars.txt
unset LC_ALL
wc -C < $tmp/two_euro_chars.txt
export LC_ALL=C
wc -C < $tmp/two_euro_chars.txt
fi
")
got=$*
[[ $got == $exp ]] || err_exit "builtin wc LC_ALL default failed -- expected '$exp', got '$got'"
# multibyte char straddling buffer boundary
{
unset i
integer i
for ((i = 0; i < 163; i++))
do print "#234567890123456789012345678901234567890123456789"
done
printf $'%-.*c\n' 15 '#'
for ((i = 0; i < 2; i++))
do print $': "\xe5\xae\x9f\xe8\xa1\x8c\xe6\xa9\x9f\xe8\x83\xbd\xe3\x82\x92\xe8\xa1\xa8\xe7\xa4\xba\xe3\x81\x97\xe3\x81\xbe\xe3\x81\x99\xe3\x80\x82" :'
done
} > ko.dat
LC_ALL=$locale $SHELL < ko.dat 2> /dev/null || err_exit "script with multibyte char straddling buffer boundary fails"
# exp LC_ALL LC_NUMERIC LANG
set -- \
2,5 $locale C '' \
2.5 C $locale '' \
2,5 $locale '' C \
2,5 '' $locale C \
2.5 C '' $locale \
2.5 '' C $locale \
unset a b c
unset LC_ALL LC_NUMERIC LANG
integer a b c
while (( $# >= 4 ))
do exp=$1
unset H V
typeset -A H
typeset -a V
[[ $2 ]] && V[0]="export LC_ALL=$2;"
[[ $3 ]] && V[1]="export LC_NUMERIC=$3;"
[[ $4 ]] && V[2]="export LANG=$4;"
for ((a = 0; a < 3; a++))
do for ((b = 0; b < 3; b++))
do if (( b != a ))
then for ((c = 0; c < 3; c++))
do if (( c != a && c != b ))
then T=${V[$a]}${V[$b]}${V[$c]}
if [[ ! ${H[$T]} ]]
then H[$T]=1
got=$($SHELL -c "${T}print \$(( $exp ))" 2>&1)
[[ $got == $exp ]] || err_exit "${T} sequence failed -- expected '$exp', got '$got'"
fi
fi
done
fi
done
done
shift 4
done
# setocale(LC_ALL,"") after setlocale() initialization
printf 'f1\357\274\240f2\n' > input1
printf 't2\357\274\240f1\n' > input2
printf '\357\274\240\n' > delim
print "export LC_ALL=$locale
builtin cut || exit
cut -f 1 -d \$(cat delim) input1 input2 > out" > script
$SHELL -c 'unset LANG ${!LC_*}; $SHELL ./script' ||
err_exit "'cut' builtin failed -- exit code $?"
exp=$'f1\nt2'
got="$(<out)"
[[ $got == "$exp" ]] || err_exit "LC_ALL test script failed -- expected '$exp', got '$got'"
# multibyte identifiers
if((SHOPT_MULTIBYTE)); then
exp=OK
got=$(set +x; LC_ALL=C.UTF-8 $SHELL -c $'\u[5929]=OK; print ${\u[5929]}' 2>&1)
[[ $got == "$exp" ]] || err_exit "multibyte variable definition/expansion failed -- expected '$exp', got '$got'"
got=$(set +x; LC_ALL=C.UTF-8 $SHELL -c $'function \u[5929]\n{\nprint OK;\n}; \u[5929]' 2>&1)
[[ $got == "$exp" ]] || err_exit "multibyte ksh function definition/execution failed -- expected '$exp', got '$got'"
got=$(set +x; LC_ALL=C.UTF-8 $SHELL -c $'\u[5929]()\n{\nprint OK;\n}; \u[5929]' 2>&1)
[[ $got == "$exp" ]] || err_exit "multibyte posix function definition/execution failed -- expected '$exp', got '$got'"
fi # SHOPT_MULTIBYTE
# this locale is supported by ast on all platforms
# mainly used to debug multibyte and message translation code
# however wctype is not supported but that's ok for these tests
locale=debug
if((SHOPT_MULTIBYTE)); then
if [[ "$(LC_ALL=$locale $SHELL <<- \+EOF+
x=a<1z>b<2yx>c
print ${#x}
+EOF+)" != 5
]]
then err_exit '${#x} not working with multibyte locales'
fi
fi # SHOPT_MULTIBYTE
dir=_not_found_
exp=2
for cmd in \
"cd $dir; export LC_ALL=debug; cd $dir" \
"cd $dir; LC_ALL=debug cd $dir" \
do got=$($SHELL -c "$cmd" 2>&1 | sort -u | wc -l)
(( ${got:-0} == $exp )) || err_exit "'$cmd' sequence failed -- error message not localized"
done
exp=121
for lc in LANG LC_MESSAGES LC_ALL
do for cmd in "($lc=$locale;cd $dir)" "$lc=$locale;cd $dir;unset $lc" "function tst { typeset $lc=$locale;cd $dir; }; tst"
do tst="$lc=C;cd $dir;$cmd;cd $dir;:"
$SHELL -c "unset LANG \${!LC_*}; $SHELL -c '$tst'" > out 2>&1 ||
err_exit "'$tst' failed -- exit status $?"
integer id=0
unset msg
typeset -A msg
got=
while read -r line
do line=${line##*:}
if [[ ! ${msg[$line]} ]]
then msg[$line]=$((++id))
fi
got+=${msg[$line]}
done < out
[[ $got == $exp ]] || err_exit "'$tst' failed -- expected '$exp', got '$got'"
done
done
if((SHOPT_MULTIBYTE)); then
exp=123
got=$(LC_ALL=debug $SHELL -c "a<2A@>z=$exp; print \$a<2A@>z")
[[ $got == $exp ]] || err_exit "multibyte debug locale \$a<2A@>z failed -- expected '$exp', got '$got'"
fi # SHOPT_MULTIBYTE
unset LC_ALL LC_MESSAGES
export LANG=debug
function message
{
print -r $"An error occurred."
}
exp=$'(libshell,3,46)\nAn error occurred.\n(libshell,3,46)'
alt=$'(debug,message,libshell,An error occurred.)\nAn error occurred.\n(debug,message,libshell,An error occurred.)'
got=$(message; LANG=C message; message)
[[ $got == "$exp" || $got == "$alt" ]] || {
EXP=$(printf %q "$exp")
ALT=$(printf %q "$alt")
GOT=$(printf %q "$got")
err_exit "LANG change not seen by function -- expected $EXP or $ALT, got $GOT"
}
a_thing=fish
got=$(print -r aa$"\\ahello \" /\\${a_thing}/\\"zz)
exp='aa(debug,'$Command',libshell,\ahello " /\fish/\)zz'
[[ $got == "$exp" ]] || err_exit "$\"...\" containing expansions fails: expected $exp, got $got"
exp='(debug,'$Command',libshell,This is a string\n)'
typeset got=$"This is a string\n"
[[ $got == "$exp" ]] || err_exit "$\"...\" in assignment expansion fails: expected $exp got $got"
unset LANG
LC_ALL=C
x=$"hello"
[[ $x == hello ]] || err_exit 'assignment of message strings not working'
# tests for multibyte character at buffer boundary
{
print 'cat << \\EOF'
for ((i=1; i < 164; i++))
do print 123456789+123456789+123456789+123456789+123456789
done
print $'next character is multibyte<2b|>c<3d|\>foo'
for ((i=1; i < 10; i++))
do print 123456789+123456789+123456789+123456789+123456789
done
print EOF
} > script$$.1
chmod +x script$$.1
x=$( LC_ALL=debug $SHELL ./script$$.1)
[[ ${#x} == 8641 ]] || err_exit 'here doc contains wrong number of chars with multibyte locale'
[[ $x == *$'next character is multibyte<2b|>c<3d|\>foo'* ]] || err_exit "here_doc doesn't contain line with multibyte chars"
x=$(LC_ALL=debug $SHELL -c 'x="a<2b|>c";print -r -- ${#x}')
if((SHOPT_MULTIBYTE)); then
(( x == 3 )) || err_exit 'character length of multibyte character should be 3'
else
(( x == 7 )) || err_exit 'character length of multibyte character should be 7 with SHOPT_MULTIBYTE disabled'
fi # SHOPT_MULTIBYTE
x=$(LC_ALL=debug $SHELL -c 'typeset -R10 x="a<2b|>c";print -r -- "${x}"')
[[ $x == ' a<2b|>c' ]] || err_exit 'typeset -R10 should begin with three spaces'
x=$(LC_ALL=debug $SHELL -c 'typeset -L10 x="a<2b|>c";print -r -- "${x}"')
[[ $x == 'a<2b|>c ' ]] || err_exit 'typeset -L10 should end in three spaces'
if false && # Disable this test because it really test the OS-provided en_US.UTF-8 locale data, which may be broken.
$SHELL -c "export LC_ALL=en_US.UTF-8; c=$'\342\202\254'; [[ \${#c} == 1 ]]" 2>/dev/null
then LC_ALL=en_US.UTF-8
unset i p1 p2 x
for i in 9 b c d 20 2000 2001 2002 2003 2004 2005 2006 2008 2009 200a 2028 2029 3000 # 1680 1803 2007 202f 205f
do if ! eval "[[ \$'\\u[$i]' == [[:space:]] ]]"
then x+=,$i
fi
done
if [[ $x ]]
then if [[ $x == ,*,* ]]
then p1=s p2="are not space characters"
else p1= p2="is not a space character"
fi
err_exit "unicode char$p1 ${x#?} $p2 in locale $LC_ALL"
fi
unset x
x=$(printf "hello\u[20ac]\xee world")
[[ $(print -r -- "$x") == $'hello\u[20ac]\xee world' ]] || err_exit '%q with unicode and non-unicode not working'
if [[ $(whence od) ]]
then got='68656c6c6fe282acee20776f726c640a'
[[ $(print -r -- "$x" | od -An -tx1 \
| awk 'BEGIN { ORS=""; } { for (i=1; i<=NF; i++) print $i; }') \
== "$got" ]] \
|| err_exit "incorrect string from printf %q"
fi
fi
exit $((Errors<125?Errors:125))
Reference in a new issue View git blame Copy permalink