diff options
author | Jari Vetoniemi <jari.vetoniemi@indooratlas.com> | 2020-03-16 18:49:26 +0900 |
---|---|---|
committer | Jari Vetoniemi <jari.vetoniemi@indooratlas.com> | 2020-03-30 00:39:06 +0900 |
commit | fcbf63e62c627deae76c1b8cb8c0876c536ed811 (patch) | |
tree | 64cb17de3f41a2b6fef2368028fbd00349946994 /jni/iconv/tests/check-subst |
Fresh start
Diffstat (limited to 'jni/iconv/tests/check-subst')
-rwxr-xr-x | jni/iconv/tests/check-subst | 140 |
1 files changed, 140 insertions, 0 deletions
diff --git a/jni/iconv/tests/check-subst b/jni/iconv/tests/check-subst new file mode 100755 index 0000000..c17b11a --- /dev/null +++ b/jni/iconv/tests/check-subst @@ -0,0 +1,140 @@ +#!/bin/sh +# Check of --unicode-subst, --byte-subst, --widechar-subst options. +set -e +iconv=../src/iconv_no_i18n +# Make sure the charset.alias file is found. +CHARSETALIASDIR=../lib +export CHARSETALIASDIR + +options_ascii='--unicode-subst=<U+%04X> --byte-subst=<0x%02x> --widechar-subst=<%08x>' +options_utf8='--unicode-subst=«U+%04X» --byte-subst=«0x%02x» --widechar-subst=«%08x»' + +# Test of --byte-subst with an ASCII substitution. + +cat > tmp-in <<\EOF +Böse Bübchen +EOF +$iconv $options_ascii -f ASCII -t ASCII < tmp-in > tmp-out +cat > tmp-ok <<\EOF +B<0xc3><0xb6>se B<0xc3><0xbc>bchen +EOF +cmp tmp-out tmp-ok + +# Test of --byte-subst with a non-ASCII substitution. + +if test "`(locale charmap) 2>/dev/null`" = UTF-8; then + cat > tmp-in <<\EOF +Böse Bübchen +EOF + $iconv $options_utf8 -f ASCII -t UTF-8 2>/dev/null < tmp-in > tmp-out + cat > tmp-ok <<\EOF +B«0xc3»«0xb6»se B«0xc3»«0xbc»bchen +EOF + cmp tmp-out tmp-ok +fi + +if test "`(locale charmap) 2>/dev/null`" = UTF-8; then + cat > tmp-in <<\EOF +Böse Bübchen +EOF + $iconv $options_utf8 -f ASCII -t ISO-8859-1 2>/dev/null < tmp-in > tmp-out + $iconv -f ISO-8859-1 -t UTF-8 < tmp-out > tmp-out2 + cat > tmp-ok <<\EOF +B«0xc3»«0xb6»se B«0xc3»«0xbc»bchen +EOF + cmp tmp-out2 tmp-ok +fi + +# Test of --byte-subst with a very long substitution. + +cat > tmp-in <<\EOF +Böse Bübchen +EOF +$iconv --byte-subst='<0x%010000x>' -f ASCII -t ASCII < tmp-in > tmp-out +# This printf command crashes on Solaris 10. +if printf 'B<0x%010000x><0x%010000x>se B<0x%010000x><0x%010000x>bchen\n' 0xC3 0xB6 0xC3 0xBC > tmp-ok 2>/dev/null; then + cmp tmp-out tmp-ok +fi + +# Test of --unicode-subst with an ASCII substitution. + +cat > tmp-in <<\EOF +Böse Bübchen +EOF +$iconv $options_ascii -f UTF-8 -t ASCII < tmp-in > tmp-out +cat > tmp-ok <<\EOF +B<U+00F6>se B<U+00FC>bchen +EOF +cmp tmp-out tmp-ok + +cat > tmp-in <<\EOF +Russian (Русский) +EOF +$iconv $options_ascii -f UTF-8 -t ISO-8859-1 2>/dev/null < tmp-in | $iconv -f ISO-8859-1 -t UTF-8 > tmp-out +cat > tmp-ok <<\EOF +Russian (<U+0420><U+0443><U+0441><U+0441><U+043A><U+0438><U+0439>) +EOF +cmp tmp-out tmp-ok + +# Test of --unicode-subst with a non-ASCII substitution. + +if test "`(locale charmap) 2>/dev/null`" = UTF-8; then + cat > tmp-in <<\EOF +Russian (Русский) +EOF + $iconv $options_utf8 -f UTF-8 -t ISO-8859-1 2>/dev/null < tmp-in > tmp-out + $iconv -f ISO-8859-1 -t UTF-8 < tmp-out > tmp-out2 + cat > tmp-ok <<\EOF +Russian («U+0420»«U+0443»«U+0441»«U+0441»«U+043A»«U+0438»«U+0439») +EOF + cmp tmp-out2 tmp-ok +fi + +# Test of --unicode-subst with a very long substitution. + +cat > tmp-in <<\EOF +Böse Bübchen +EOF +$iconv --unicode-subst='<U+%010000X>' -f UTF-8 -t ASCII < tmp-in > tmp-out +# This printf command crashes on Solaris 10. +if printf 'B<U+%010000X>se B<U+%010000X>bchen\n' 0x00F6 0x00FC > tmp-ok 2>/dev/null; then + cmp tmp-out tmp-ok +fi + +cat > tmp-in <<\EOF +Böse Bübchen +EOF +$iconv --byte-subst='<0x%010000x>' -f ASCII -t ASCII < tmp-in > tmp-out +# This printf command crashes on Solaris 10. +if printf 'B<0x%010000x><0x%010000x>se B<0x%010000x><0x%010000x>bchen\n' 0xC3 0xB6 0xC3 0xBC > tmp-ok 2>/dev/null; then + cmp tmp-out tmp-ok +fi + +# Test of --widechar-subst: +# wcrtomb() doesn't exist on FreeBSD 4.0 and is broken on MacOS X 10.3. +# So far this has been tested only on a glibc system with !__STDC_ISO_10646__. + +if false && test "`(locale charmap) 2>/dev/null`" = UTF-8; then + cat > tmp-in <<\EOF +Russian (Русский) +EOF + $iconv -f char -t wchar_t < tmp-in > tmp-inw + LC_ALL=C $iconv $options_ascii -f wchar_t -t ASCII < tmp-inw > tmp-out1 + LC_ALL=de_DE.ISO-8859-1 $iconv $options_ascii -f wchar_t -t ASCII < tmp-inw > tmp-out2 + cat > tmp-ok <<\EOF +Russian (<00000420><00000443><00000441><00000441><0000043a><00000438><00000439>) +EOF + cmp tmp-out1 tmp-ok + cmp tmp-out2 tmp-ok + if test "`(LC_ALL=de_DE.ISO-8859-1 locale charmap) 2>/dev/null`" = ISO-8859-1; then + options_latin1=`echo " $options_utf8" | $iconv -f UTF-8 -t ISO-8859-1` + LC_ALL=de_DE.ISO-8859-1 $iconv $options_latin1 -f wchar_t -t UTF-8 < tmp-inw > tmp-out1 + cat > tmp-ok <<\EOF +Russian («00000420»«00000443»«00000441»«00000441»«0000043a»«00000438»«00000439») +EOF + cmp tmp-out1 tmp-ok + fi +fi + +rm -f tmp-in* tmp-out* tmp-ok +exit 0 |