[svn:parrot] r49721 - trunk/t/op

[nwellnhof at svn.parrot.org]

Author: nwellnhof
Date: Fri Oct 29 01:15:43 2010
New Revision: 49721
URL: https://trac.parrot.org/parrot/changeset/49721

Log:
[t] Add some string tests

Modified:
   trunk/t/op/string.t
   trunk/t/op/string_cs.t

Modified: trunk/t/op/string.t
==============================================================================
--- trunk/t/op/string.t	Fri Oct 29 01:15:23 2010	(r49720)
+++ trunk/t/op/string.t	Fri Oct 29 01:15:43 2010	(r49721)
@@ -55,6 +55,7 @@
     substr_offset_zero_zero_length_string()
     exception_substr_offset_one_zero_length_string()
     exception_substr_neg_offset_zero_length_string()
+    exception_substr_oob_utf8()
     zero_length_substr_zero_length_string()
     zero_length_substr_zero_length_string()
     three_arg_substr_zero_length_string()
@@ -529,6 +530,14 @@
     .exception_is( "Cannot take substr outside string" )
 .end
 
+.sub exception_substr_oob_utf8
+    set $S0, utf8:"abc\uBEEFdef"
+    push_eh handler
+    substr $S1, $S0, 8, 5
+handler:
+    .exception_is( "Cannot take substr outside string" )
+.end
+
 .sub zero_length_substr_zero_length_string
     set $S0, ""
     substr $S1, $S0, 10, 0

Modified: trunk/t/op/string_cs.t
==============================================================================
--- trunk/t/op/string_cs.t	Fri Oct 29 01:15:23 2010	(r49720)
+++ trunk/t/op/string_cs.t	Fri Oct 29 01:15:43 2010	(r49721)
@@ -6,7 +6,7 @@
 use warnings;
 use lib qw( . lib ../lib ../../lib );
 use Test::More;
-use Parrot::Test tests => 50;
+use Parrot::Test tests => 53;
 use Parrot::Config;
 
 =head1 NAME
@@ -91,9 +91,13 @@
     set S0, iso-8859-1:"zAEIOU_ÄÖÜ\n"
     titlecase S1, S0
     print S1
+    set S0, iso-8859-1:"äAEIOU_ÄÖÜ\n"
+    titlecase S1, S0
+    print S1
     end
 CODE
 Zaeiou_äöü
+Äaeiou_äöü
 OUTPUT
 
 pasm_output_is( <<'CODE', <<OUTPUT, "is_whitespace" );
@@ -247,7 +251,7 @@
 0 2 5 7 ok
 OUTPUT
 
-pasm_output_is( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i" );
+pasm_output_is( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i ascii to iso-8859-1" );
     set S0, "abc"
     find_encoding I0, "iso-8859-1"
     trans_encoding S1, S0, I0
@@ -263,7 +267,23 @@
 iso-8859-1
 OUTPUT
 
-pasm_error_output_like( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i - lossy" );
+pasm_output_is( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i iso-8859-1 to ascii" );
+    set S0, iso-8859-1:"abc"
+    find_encoding I0, "ascii"
+    trans_encoding S1, S0, I0
+    print S1
+    print "\n"
+    encoding I0, S1
+    encodingname S2, I0
+    print S2
+    print "\n"
+    end
+CODE
+abc
+ascii
+OUTPUT
+
+pasm_error_output_like( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i iso-8859-1 to ascii - lossy" );
     set S1, iso-8859-1:"abcä"
     find_encoding I0, "ascii"
     trans_encoding S2, S1, I0
@@ -305,22 +325,6 @@
 binary
 OUTPUT
 
-pasm_output_is( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i ascii to iso-8859-1" );
-    set S0, ascii:"abc"
-    find_encoding I0, "iso-8859-1"
-    trans_encoding S1, S0, I0
-    print S1
-    print "\n"
-    encoding I0, S1
-    encodingname S2, I0
-    print S2
-    print "\n"
-    end
-CODE
-abc
-iso-8859-1
-OUTPUT
-
 pasm_output_is( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i iso-8859-1 to utf8" );
     set S0, iso-8859-1:"abc_ä_"
     find_encoding I0, "utf8"
@@ -365,6 +369,26 @@
 6
 OUTPUT
 
+pasm_error_output_like( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i utf-8 to iso-8859-1 - lossy" );
+    set S1, utf8:"abc\uBABE"
+    find_encoding I0, "iso-8859-1"
+    trans_encoding S2, S1, I0
+    print "never\n"
+    end
+CODE
+/lossy conversion to iso-8559-1/
+OUTPUT
+
+pasm_error_output_like( <<'CODE', <<OUTPUT, "trans_encoding_s_s_i utf-8 to ascii - lossy" );
+    set S1, utf8:"abc\xFC"
+    find_encoding I0, "ascii"
+    trans_encoding S2, S1, I0
+    print "never\n"
+    end
+CODE
+/can't convert unicode string to ascii/
+OUTPUT
+
 pir_output_is( <<'CODE', <<'OUTPUT', "bug #34661 literal" );
 .sub main :main
     $S0 = utf8:"\"]\nif I3 == "
@@ -786,7 +810,7 @@
 T\x{c3}\x{b6}tsch Leo
 OUTPUT
 
-    pir_output_is( <<'CODE', <<OUTPUT, "combose combined char" );
+    pir_output_is( <<'CODE', <<OUTPUT, "compose combined char" );
 .sub main :main
     set $S1, utf8:"___\u01f0___"
     length $I0, $S1
@@ -867,6 +891,29 @@
 x/\u0445\u0440\u0435\u043d\u044c_09-10.txt
 OUTPUT
 
+pir_output_is(<<'CODE', <<'OUTPUT', 'compare mixed encodings' );
+.sub 'main'
+    $S0 = iso-8859-1:"a\xFCb 1"
+    $S1 = utf8:"a\xFCb 2"
+    $I0 = islt $S0, $S1
+    say $I0
+    $I0 = isgt $S1, $S0
+    say $I0
+
+    $S0 = utf8:"a\uBABEb c\uBEEFd 1"
+    $S1 = ucs2:"a\uBABEb c\uBEEFd 2"
+    $I0 = islt $S0, $S1
+    say $I0
+    $I0 = isgt $S1, $S0
+    say $I0
+.end
+CODE
+1
+1
+1
+1
+OUTPUT
+
 # Local Variables:
 #   mode: cperl
 #   cperl-indent-level: 4