[t] Convert most unicode:"" string literals to utf8:""

git-svn-id: https://svn.parrot.org/parrot/trunk@49513 d31e2699-5ff4-0310-a27c-f18f2fbe73fe

src/string/encoding/shared.c

@@ -1221,7 +1221,7 @@ unicode_upcase(PARROT_INTERP, ARGIN(const STRING *src))
 
     /*
      * XXX troubles:
-     *   t/op/string_cs_45  upcase unicode:"\u01f0"
+     *   t/op/string_cs_45  upcase utf8:"\u01f0"
      *   this creates \u004a \u030c J+NON-SPACING HACEK
      *   the string needs resizing, *if* the src buffer is
      *   too short. *But* with icu 3.2/3.4 the src string is

t/compilers/imcc/syn/objects.t

@@ -28,7 +28,7 @@
 .namespace ["Foo"]
 .namespace [ ]
 .namespace []
-.namespace [unicode:"»ö«"; ascii:"perl6"]
+.namespace [utf8:"»ö«"; ascii:"perl6"]
 
 .sub test
     $I0 = 42

t/compilers/imcc/syn/pcc.t

@@ -545,13 +545,13 @@ pir_output_is( <<'CODE', <<'OUT', 'Unicode allowed in method names, TT #730' );
 .sub 'main' :main
     $P0 = newclass 'Foo'
     $P1 = new $P0
-    $S0 = unicode:"foo\x{b1}"
+    $S0 = utf8:"foo\x{b1}"
     $P1.$S0(1)
-    $P1.unicode:"foo\x{b1}"(2)
+    $P1.utf8:"foo\x{b1}"(2)
 .end
 
 .namespace ['Foo']
-.sub unicode:"foo\x{b1}" :method
+.sub utf8:"foo\x{b1}" :method
     .param int count
     print 'ok '
     print count

t/compilers/imcc/syn/regressions.t

@@ -156,9 +156,9 @@ OUT
 pir_output_is( <<'CODE', <<'OUT', 'unicode lexical identifiers (TT #575)');
  .sub main :main
     $P0 = box 'hello world'
-    .lex unicode:"$\u03b2\u03bf\u03bf", $P0
+    .lex utf8:"$\u03b2\u03bf\u03bf", $P0
 
-    $P1 = find_lex unicode:"$\u03b2\u03bf\u03bf"
+    $P1 = find_lex utf8:"$\u03b2\u03bf\u03bf"
     say $P1
  .end
 CODE
@@ -167,12 +167,12 @@ OUT
 
 pir_output_is( <<'CODE', <<'OUT', 'unicode named identifiers (TT #654)');
  .sub 'main' :main
-    'foo'(1 :named(unicode:"\x{e4}"))
+    'foo'(1 :named(utf8:"\x{e4}"))
  .end
 
  # Perl 6:  sub foo(:$ä) { say "ok $ä"; }
  .sub 'foo'
-    .param int x :named(unicode:"\x{e4}")
+    .param int x :named(utf8:"\x{e4}")
     print "ok "
     say x
  .end

t/compilers/imcc/syn/subflags.t

@@ -97,7 +97,7 @@ test flags on PIR subs
     ## unicode nsentry
     .const 'Sub' $P60 = 'subid3'
     isa_ok($P60, 'Sub', 'subid3 found w/.const')
-    $P0 = get_global unicode:"nsentry\u2462"
+    $P0 = get_global utf8:"nsentry\u2462"
     $I0 = issame $P60, $P0
     ok($I0, "nsentry3 found in namespace")
 
@@ -176,7 +176,7 @@ test flags on PIR subs
 .end
 
 
-.sub 'anon3' :nsentry(unicode:"nsentry\u2462") :subid('subid3')
+.sub 'anon3' :nsentry(utf8:"nsentry\u2462") :subid('subid3')
     .return ('anon3')
 .end
 

t/library/string_utils.t

@@ -68,8 +68,8 @@ Tests for String/Utils.pbc
     test_radix_digits('[41,42]XYZ', 'x', 0, 'AB', 7, '\x[41,42]')
     test_radix_digits('[41,42]'   , 'x', 1, 'A' , 2, '\x41')
     test_radix_digits('[41,42]'   , 'x', 4, 'B',  2, '\x42')
-    test_radix_digits('2000'      , 'x', 0, unicode:"\u2000", 4, '\x2000')
-    test_radix_digits('1680'      , 'x', 0, unicode:"\u1680", 4, '\x1680')
+    test_radix_digits('2000'      , 'x', 0, utf8:"\u2000", 4, '\x2000')
+    test_radix_digits('1680'      , 'x', 0, utf8:"\u1680", 4, '\x1680')
 .end
 
 

t/op/string.t

@@ -875,15 +875,15 @@ WHILE:
 
     # Ascii - Non-ascii, same content
     set $S0, "hello"
-    set $S1, unicode:"hello"
+    set $S1, utf8:"hello"
     index $I1, $S0, $S1
     is( $I1, "0", 'index, 3-arg form' )
     index $I1, $S1, $S0
     is( $I1, "0", 'index, 3-arg form' )
 
     # Non-ascii, source shorter than searched
-    set $S0, unicode:"-o"
-    set $S1, unicode:"@INC"
+    set $S0, utf8:"-o"
+    set $S1, utf8:"@INC"
     index $I1, $S0, $S1
     is( $I1, "-1", 'index, 3-arg form' )
 .end
@@ -903,7 +903,7 @@ WHILE:
 
     # Ascii - Non-ascii, same content
     set $S0, "hello"
-    set $S1, unicode:"hello"
+    set $S1, utf8:"hello"
     index $I1, $S0, $S1, 0
     is( $I1, "0", 'index, 4-arg form' )
     index $I1, $S1, $S0, 0
@@ -922,8 +922,8 @@ WHILE:
 .end
 
 .sub index_trac_1482
-    $S0 = unicode:"bubuc"
-    $S1 = unicode:"buc"
+    $S0 = utf8:"bubuc"
+    $S1 = utf8:"buc"
 
     $I0 = index $S0, $S1, 0
     is ($I0, 2, 'index, 4-arg, partial-match causes failure: TT #1482')

t/op/string_cclass.t

@@ -309,7 +309,7 @@ push @{ $ws->{whitespace} } => @{ $ws->{whitespace_ascii} },
 
 sub string {
     my $which = shift;
-    'unicode:"' . join( '', @{ $ws->{$which} } ) . '"';
+    'utf8:"' . join( '', @{ $ws->{$which} } ) . '"';
 }
 
 my $all_ws = string('whitespace');
@@ -350,7 +350,7 @@ OUT
    .local int result, char, len, i
    .local string s
    s = $all_ws
-   s = unicode:"abc" . s
+   s = utf8:"abc" . s
    len = length s
    result = find_cclass .CCLASS_WHITESPACE, s, 0, len
    print result
@@ -366,7 +366,7 @@ OUT
    .local int result, char, len, i
    .local string s
    s = $all_ws
-   s .= unicode:"abc"
+   s .= utf8:"abc"
    len = length s
    result = find_not_cclass .CCLASS_WHITESPACE, s, 0, len
    print len
@@ -385,7 +385,7 @@ pir_output_is( <<"CODE", <<'OUT', "unicode 0-127 find_*_cclass whitespace" );
 .include "cclass.pasm"
    .local int result, char, len, i
    .local string s
-   s = unicode:"abc   def"
+   s = utf8:"abc   def"
    len = length s
    result = find_cclass .CCLASS_WHITESPACE, s, 0, len
    print len
@@ -403,7 +403,7 @@ OUT
 pir_output_is( <<'CODE', <<'OUT', "is_cclass, unicode first codepage" );
 .include "cclass.pasm"
 .sub main :main
-    $S1 = unicode:"ab\nC_X34.\0 \t!"
+    $S1 = utf8:"ab\nC_X34.\0 \t!"
     test1( $S1 )
 .end
 .sub test1

t/op/string_cs.t

@@ -473,7 +473,6 @@ SKIP: {
 CODE
 hello(5): ascii
 hello(5): utf8
-hello(5): utf8
 hello(10): utf16
 hello(10): ucs2
 OUTPUT
@@ -506,7 +505,6 @@ OUTPUT
 CODE
 (0): ascii
 (0): utf8
-(0): utf8
 (0): utf16
 (0): ucs2
 OUTPUT