merge trunk

1 files changed, 77 insertions, 73 deletions

diff --git a/tests/utf.test b/tests/utf.test
index ebab967..ceb1af7 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -16,50 +16,52 @@ if {[lsearch [namespace children] ::tcltest] == -1} {
 ::tcltest::loadTestedCommands
 catch [list package require -exact Tcltest [info patchlevel]]
 
+testConstraint testbytestring [llength [info commands testbytestring]]
+
 catch {unset x}
 
-test utf-1.1 {Tcl_UniCharToUtf: 1 byte sequences} {
-    set x \x01
-} [bytestring "\x01"]
-test utf-1.2 {Tcl_UniCharToUtf: 2 byte sequences} {
-    set x "\x00"
-} [bytestring "\xc0\x80"]
-test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} {
-    set x "\xe0"
-} [bytestring "\xc3\xa0"]
-test utf-1.4 {Tcl_UniCharToUtf: 3 byte sequences} {
-    set x "\u4e4e"
-} [bytestring "\xe4\xb9\x8e"]
-test utf-1.5 {Tcl_UniCharToUtf: overflowed Tcl_UniChar} {
-    format %c 0x110000
-} [bytestring "\xef\xbf\xbd"]
-test utf-1.6 {Tcl_UniCharToUtf: negative Tcl_UniChar} {
-    format %c -1
-} [bytestring "\xef\xbf\xbd"]
+test utf-1.1 {Tcl_UniCharToUtf: 1 byte sequences} testbytestring {
+    expr {"\x01" eq [testbytestring "\x01"]}
+} 1
+test utf-1.2 {Tcl_UniCharToUtf: 2 byte sequences} testbytestring {
+    expr {"\x00" eq [testbytestring "\xc0\x80"]}
+} 1
+test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} testbytestring {
+    expr {"\xe0" eq [testbytestring "\xc3\xa0"]}
+} 1
+test utf-1.4 {Tcl_UniCharToUtf: 3 byte sequences} testbytestring {
+    expr {"\u4e4e" eq [testbytestring "\xe4\xb9\x8e"]}
+} 1
+test utf-1.5 {Tcl_UniCharToUtf: overflowed Tcl_UniChar} testbytestring {
+    expr {[format %c 0x110000] eq [testbytestring "\xef\xbf\xbd"]}
+} 1
+test utf-1.6 {Tcl_UniCharToUtf: negative Tcl_UniChar} testbytestring {
+    expr {[format %c -1] eq [testbytestring "\xef\xbf\xbd"]}
+} 1
 
 test utf-2.1 {Tcl_UtfToUniChar: low ascii} {
     string length "abc"
 } {3}
-test utf-2.2 {Tcl_UtfToUniChar: naked trail bytes} {
-    string length [bytestring "\x82\x83\x84"]
+test utf-2.2 {Tcl_UtfToUniChar: naked trail bytes} testbytestring {
+    string length [testbytestring "\x82\x83\x84"]
 } {3}
-test utf-2.3 {Tcl_UtfToUniChar: lead (2-byte) followed by non-trail} {
-    string length [bytestring "\xC2"]
+test utf-2.3 {Tcl_UtfToUniChar: lead (2-byte) followed by non-trail} testbytestring {
+    string length [testbytestring "\xC2"]
 } {1}
-test utf-2.4 {Tcl_UtfToUniChar: lead (2-byte) followed by trail} {
-    string length [bytestring "\xC2\xa2"]
+test utf-2.4 {Tcl_UtfToUniChar: lead (2-byte) followed by trail} testbytestring {
+    string length [testbytestring "\xC2\xa2"]
 } {1}
-test utf-2.5 {Tcl_UtfToUniChar: lead (3-byte) followed by non-trail} {
-    string length [bytestring "\xE2"]
+test utf-2.5 {Tcl_UtfToUniChar: lead (3-byte) followed by non-trail} testbytestring {
+    string length [testbytestring "\xE2"]
 } {1}
-test utf-2.6 {Tcl_UtfToUniChar: lead (3-byte) followed by 1 trail} {
-    string length [bytestring "\xE2\xA2"]
+test utf-2.6 {Tcl_UtfToUniChar: lead (3-byte) followed by 1 trail} testbytestring {
+    string length [testbytestring "\xE2\xA2"]
 } {2}
-test utf-2.7 {Tcl_UtfToUniChar: lead (3-byte) followed by 2 trail} {
-    string length [bytestring "\xE4\xb9\x8e"]
+test utf-2.7 {Tcl_UtfToUniChar: lead (3-byte) followed by 2 trail} testbytestring {
+    string length [testbytestring "\xE4\xb9\x8e"]
 } {1}
-test utf-2.8 {Tcl_UtfToUniChar: longer UTF sequences not supported} {
-    string length [bytestring "\xF4\xA2\xA2\xA2"]
+test utf-2.8 {Tcl_UtfToUniChar: longer UTF sequences not supported} testbytestring {
+    string length [testbytestring "\xF4\xA2\xA2\xA2"]
 } {4}
 
 test utf-3.1 {Tcl_UtfCharComplete} {
@@ -69,26 +71,26 @@ testConstraint testnumutfchars [llength [info commands testnumutfchars]]
 test utf-4.1 {Tcl_NumUtfChars: zero length} testnumutfchars {
     testnumutfchars ""
 } {0}
-test utf-4.2 {Tcl_NumUtfChars: length 1} testnumutfchars {
-    testnumutfchars [bytestring "\xC2\xA2"]
+test utf-4.2 {Tcl_NumUtfChars: length 1} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "\xC2\xA2"]
 } {1}
-test utf-4.3 {Tcl_NumUtfChars: long string} testnumutfchars {
-    testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"]
+test utf-4.3 {Tcl_NumUtfChars: long string} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"]
 } {7}
-test utf-4.4 {Tcl_NumUtfChars: #u0000} testnumutfchars {
-    testnumutfchars [bytestring "\xC0\x80"]
+test utf-4.4 {Tcl_NumUtfChars: #u0000} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "\xC0\x80"]
 } {1}
 test utf-4.5 {Tcl_NumUtfChars: zero length, calc len} testnumutfchars {
     testnumutfchars "" 1
 } {0}
-test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} testnumutfchars {
-    testnumutfchars [bytestring "\xC2\xA2"] 1
+test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "\xC2\xA2"] 1
 } {1}
-test utf-4.7 {Tcl_NumUtfChars: long string, calc len} testnumutfchars {
-    testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] 1
+test utf-4.7 {Tcl_NumUtfChars: long string, calc len} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] 1
 } {7}
-test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} testnumutfchars {
-    testnumutfchars [bytestring "\xC0\x80"] 1
+test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} {testnumutfchars testbytestring} {
+    testnumutfchars [testbytestring "\xC0\x80"] 1
 } {1}
 
 test utf-5.1 {Tcl_UtfFindFirsts} {
@@ -125,18 +127,18 @@ test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
     set x \n
 } {
 }
-test utf-10.2 {Tcl_UtfBackslash: \u subst} {
-    set x \ua2
-} [bytestring "\xc2\xa2"]
-test utf-10.3 {Tcl_UtfBackslash: longer \u subst} {
-    set x \u4e21
-} [bytestring "\xe4\xb8\xa1"]
-test utf-10.4 {Tcl_UtfBackslash: stops at first non-hex} {
-    set x \u4e2k
-} "[bytestring \xd3\xa2]k"
-test utf-10.5 {Tcl_UtfBackslash: stops after 4 hex chars} {
-    set x \u4e216
-} "[bytestring \xe4\xb8\xa1]6"
+test utf-10.2 {Tcl_UtfBackslash: \u subst} testbytestring {
+    expr {"\ua2" eq [testbytestring "\xc2\xa2"]}
+} 1
+test utf-10.3 {Tcl_UtfBackslash: longer \u subst} testbytestring {
+    expr {"\u4e21" eq [testbytestring "\xe4\xb8\xa1"]}
+} 1
+test utf-10.4 {Tcl_UtfBackslash: stops at first non-hex} testbytestring {
+    expr {"\u4e2k" eq "[testbytestring \xd3\xa2]k"}
+} 1
+test utf-10.5 {Tcl_UtfBackslash: stops after 4 hex chars} testbytestring {
+    expr {"\u4e216" eq "[testbytestring \xe4\xb8\xa1]6"}
+} 1
 proc bsCheck {char num} {
     global errNum
     test utf-10.$errNum {backslash substitution} {
@@ -285,23 +287,25 @@ test utf-18.5 {Tcl_UniCharToTitle, no delta} {
     string totitle !
 } !
 
-test utf-19.1 {TclUniCharLen} {
+test utf-19.1 {TclUniCharLen} -body {
     list [regexp \\d abc456def foo] $foo
-} {1 4}
+} -cleanup {
+    unset -nocomplain foo
+} -result {1 4}
 
 test utf-20.1 {TclUniCharNcmp} {
 } {}
 
 test utf-21.1 {TclUniCharIsAlnum} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     string is alnum \u1040\u021f\u0220
 } {1}
 test utf-21.2 {unicode alnum char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     list [regexp {^[[:alnum:]]+$} \u1040\u021f\u0220] [regexp {^\w+$} \u1040\u021f\u0220]
 } {1 1}
 test utf-21.3 {unicode print char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     regexp {^[[:print:]]+$} \ufbc1
 } 1
 test utf-21.4 {TclUniCharIsGraph} {
@@ -334,11 +338,11 @@ test utf-21.10 {unicode print char in regc_locale.c} {
 } {0}
 test utf-21.11 {TclUniCharIsControl} {
     # [Bug 3464428]
-    string is control \u00ad
+    string is control \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
 } {1}
 test utf-21.12 {unicode control char in regc_locale.c} {
     # [Bug 3464428], [Bug a876646efe]
-    regexp {^[[:cntrl:]]*$} \u0000\u001f\u00ad
+    regexp {^[[:cntrl:]]*$} \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
 } {1}
 
 test utf-22.1 {TclUniCharIsWordChar} {
@@ -349,30 +353,30 @@ test utf-22.2 {TclUniCharIsWordChar} {
 } 10
 
 test utf-23.1 {TclUniCharIsAlpha} {
-    # this returns 1 with Unicode 6 compliance
-    string is alpha \u021f\u0220
+    # this returns 1 with Unicode 7 compliance
+    string is alpha \u021f\u0220\u037f\u052f
 } {1}
 test utf-23.2 {unicode alpha char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
-    regexp {^[[:alpha:]]+$} \u021f\u0220
+    # this returns 1 with Unicode 7 compliance
+    regexp {^[[:alpha:]]+$} \u021f\u0220\u037f\u052f
 } {1}
 
 test utf-24.1 {TclUniCharIsDigit} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     string is digit \u1040\uabf0
 } {1}
 test utf-24.2 {unicode digit char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     list [regexp {^[[:digit:]]+$} \u1040\uabf0] [regexp {^\d+$} \u1040\uabf0]
 } {1 1}
 
 test utf-24.3 {TclUniCharIsSpace} {
-    # this returns 1 with Unicode 6 compliance
-    string is space \u1680\u180e
+    # this returns 1 with Unicode 7/TIP 413 compliance
+    string is space \u0085\u1680\u180e\u200b\u202f\u2060
 } {1}
 test utf-24.4 {unicode space char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
-    list [regexp {^[[:space:]]+$} \u1680\u180e] [regexp {^\s+$} \u1680\u180e]
+    # this returns 1 with Unicode 7/TIP 413 compliance
+    list [regexp {^[[:space:]]+$} \u0085\u1680\u180e\u200b\u202f\u2060] [regexp {^\s+$} \u0085\u1680\u180e\u200b\u202f\u2060]
 } {1 1}
 
 testConstraint teststringobj [llength [info commands teststringobj]]