diff options
| -rw-r--r-- | tests/atlocal.in | 4 | ||||
| -rw-r--r-- | tests/testsuite.at | 28 |
2 files changed, 27 insertions, 5 deletions
diff --git a/tests/atlocal.in b/tests/atlocal.in index 090a604..47137bb 100644 --- a/tests/atlocal.in +++ b/tests/atlocal.in @@ -13,3 +13,7 @@ SCITECOPATH=@abs_top_srcdir@/lib # Glib debug options G_SLICE=debug-blocks G_ENABLE_DIAGNOSTIC=1 + +# For the Unicode tests - makes sure that UTF-8 characters +# are accepted on command lines. +LC_ALL=C.UTF-8 diff --git a/tests/testsuite.at b/tests/testsuite.at index 6ea95ab..3e121fb 100644 --- a/tests/testsuite.at +++ b/tests/testsuite.at @@ -79,11 +79,20 @@ AT_CHECK([$SCITECO -e "[[a 23Ub ]]b Qb\"N(0/0)'"], 0, ignore, ignore) AT_CHECK([$SCITECO -e "[[\$ @FG'..' ]]\$ :Q\$-1Q\$-^^r\"=(0/0)'"], 0, ignore, ignore) AT_CLEANUP -AT_SETUP([8-bit cleanlyness]) -AT_CHECK([$SCITECO -e "0:@EUa/f^@^@/ :Qa-4\"N(0/0)' Ga Z= Z-4\"N(0/0)'"], 0, ignore, ignore) -AT_CHECK([$SCITECO -e "129@I// -A-129\"N(0/0)'"], 0, ignore, ignore) -AT_CHECK([$SCITECO -e "129@^Ua// 0Qa-129\"N(0/0)'"], 0, ignore, ignore) -AT_CHECK([$SCITECO -e "@^Ua/^^/ 129:@^Ua// Ma-129\"N(0/0)'"], 0, ignore, ignore) +AT_SETUP([8-bit cleanliness]) +AT_CHECK([$SCITECO -e "0@I//J 0A\"N(0/0)' :@S/^@/\"F(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -e "@EQa//0EE 1U*0EE 0:@EUa/f^@^@/ :Qa-4\"N(0/0)' Ga Z-4\"N(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -e "0EE 129@I// -A-129\"N(0/0)' HXa @EQa// EE\"N(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -8e "129@:^Ua// 0Qa-129\"N(0/0)'"], 0, ignore, ignore) +# FIXME: This will fail once we have an UTF-8-only parser. +AT_CHECK([$SCITECO -8e "@:^Ua/^^/ 129:@^Ua// Ma-129\"N(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -e "1EE 167Ua @I/^EUa/ .-1\"N(0/0)'"], 0, ignore, ignore) +AT_CLEANUP + +AT_SETUP([Unicode]) +AT_CHECK([$SCITECO -e "8594@I/Здравствуй, мир!/ Z-17\"N(0/0)' J0A-8594\"N(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -e "8594@^Ua/Здравствуй, мир!/ :Qa-17\"N(0/0)' 0Qa-8594\"N(0/0)'"], 0, ignore, ignore) +AT_CHECK([$SCITECO -e "@I/Здравствуй, мир!/ JW .-10\"N(0/0)' ^E-20\"N(0/0)' 204:EE .-10\"N(0/0)'"], 0, ignore, ignore) AT_CLEANUP AT_SETUP([Automatic EOL normalization]) @@ -192,3 +201,12 @@ AT_SKIP_IF([case $host in *-*-*bsd* | *-*-darwin*) true;; *) false;; esac]) AT_CHECK([$SCITECO -e "@^Um{U.a Q.a-100000\"<%.aMm'} 0Mm"], 0, ignore, ignore) AT_XFAIL_IF(true) AT_CLEANUP + +AT_SETUP([Unicode glitches]) +# While TECO code must always be UTF-8, strings after string building +# can be in single-byte encodings as well. +# This might already work after introducing the Unicode-aware parser. +# If not, it should be fixed. +AT_CHECK([$SCITECO -8e "164Ua Ga@I//J :@S/^EUa/\"F(0/0)'"], 0, ignore, ignore) +AT_XFAIL_IF(true) +AT_CLEANUP |