diff options
Diffstat (limited to 'tests/utf.test')
| -rw-r--r-- | tests/utf.test | 223 |
1 files changed, 190 insertions, 33 deletions
diff --git a/tests/utf.test b/tests/utf.test index 3250097..ebab967 100644 --- a/tests/utf.test +++ b/tests/utf.test @@ -7,14 +7,15 @@ # # See the file "license.terms" for information on usage and redistribution # of this file, and for a DISCLAIMER OF ALL WARRANTIES. -# -# RCS: @(#) $Id: utf.test,v 1.5 1999/06/26 20:55:17 rjohnson Exp $ if {[lsearch [namespace children] ::tcltest] == -1} { - package require tcltest - namespace import ::tcltest::* + package require tcltest 2 + namespace import -force ::tcltest::* } +::tcltest::loadTestedCommands +catch [list package require -exact Tcltest [info patchlevel]] + catch {unset x} test utf-1.1 {Tcl_UniCharToUtf: 1 byte sequences} { @@ -29,6 +30,12 @@ test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} { 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-2.1 {Tcl_UtfToUniChar: low ascii} { string length "abc" @@ -58,15 +65,31 @@ test utf-2.8 {Tcl_UtfToUniChar: longer UTF sequences not supported} { test utf-3.1 {Tcl_UtfCharComplete} { } {} -test utf-4.1 {Tcl_NumUtfChars: zero length} { - string length "" +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"] +} {1} +test utf-4.3 {Tcl_NumUtfChars: long string} testnumutfchars { + testnumutfchars [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] +} {7} +test utf-4.4 {Tcl_NumUtfChars: #u0000} testnumutfchars { + testnumutfchars [bytestring "\xC0\x80"] +} {1} +test utf-4.5 {Tcl_NumUtfChars: zero length, calc len} testnumutfchars { + testnumutfchars "" 1 } {0} -test utf-4.2 {Tcl_NumUtfChars: length 1} { - string length [bytestring "\xC2\xA2"] +test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} testnumutfchars { + testnumutfchars [bytestring "\xC2\xA2"] 1 } {1} -test utf-4.3 {Tcl_NumUtfChars: long string} { - string length [bytestring "abc\xC2\xA2\xe4\xb9\x8e\uA2\u4e4e"] +test utf-4.7 {Tcl_NumUtfChars: long string, calc len} testnumutfchars { + testnumutfchars [bytestring "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 +} {1} test utf-5.1 {Tcl_UtfFindFirsts} { } {} @@ -141,7 +164,9 @@ bsCheck \\ 92 bsCheck \Ca 67 bsCheck \Ma 77 bsCheck \CMa 67 -bsCheck \8a 8 +# prior to 8.3, this returned 8, as \8 as accepted as an +# octal value - but it isn't! [Bug: 3975] +bsCheck \8a 56 bsCheck \14 12 bsCheck \141 97 bsCheck b\0 98 @@ -149,7 +174,7 @@ bsCheck \x 120 bsCheck \xa 10 bsCheck \xA 10 bsCheck \x41 65 -bsCheck \x541 65 +bsCheck \x541 84 bsCheck \u 117 bsCheck \uk 117 bsCheck \u41 65 @@ -158,6 +183,18 @@ bsCheck \uA 10 bsCheck \340 224 bsCheck \ua1 161 bsCheck \u4e21 20001 +bsCheck \741 60 +bsCheck \U 85 +bsCheck \Uk 85 +bsCheck \U41 65 +bsCheck \Ua 10 +bsCheck \UA 10 +bsCheck \Ua1 161 +bsCheck \U4e21 20001 +bsCheck \U004e21 20001 +bsCheck \U00004e21 20001 +bsCheck \U00110000 65533 +bsCheck \Uffffffff 65533 test utf-11.1 {Tcl_UtfToUpper} { string toupper {} @@ -225,8 +262,9 @@ test utf-16.1 {Tcl_UniCharToLower, negative delta} { string tolower aA } aa test utf-16.2 {Tcl_UniCharToLower, positive delta} { - string tolower \u0178\u00ff -} \u00ff\u00ff + string tolower \u0178\u00ff\uA78D\u01c5 +} \u00ff\u00ff\u0265\u01c6 + test utf-17.1 {Tcl_UniCharToLower, no delta} { string tolower ! } ! @@ -255,7 +293,53 @@ test utf-20.1 {TclUniCharNcmp} { } {} test utf-21.1 {TclUniCharIsAlnum} { -} {} + # this returns 1 with Unicode 6 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 + 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 + regexp {^[[:print:]]+$} \ufbc1 +} 1 +test utf-21.4 {TclUniCharIsGraph} { + # [Bug 3464428] + string is graph \u0120 +} {1} +test utf-21.5 {unicode graph char in regc_locale.c} { + # [Bug 3464428] + regexp {^[[:graph:]]+$} \u0120 +} {1} +test utf-21.6 {TclUniCharIsGraph} { + # [Bug 3464428] + string is graph \u00a0 +} {0} +test utf-21.7 {unicode graph char in regc_locale.c} { + # [Bug 3464428] + regexp {[[:graph:]]} \u0020\u00a0\u2028\u2029 +} {0} +test utf-21.8 {TclUniCharIsPrint} { + # [Bug 3464428] + string is print \u0009 +} {0} +test utf-21.9 {unicode print char in regc_locale.c} { + # [Bug 3464428] + regexp {[[:print:]]} \u0009 +} {0} +test utf-21.10 {unicode print char in regc_locale.c} { + # [Bug 3464428] + regexp {[[:print:]]} \u0009 +} {0} +test utf-21.11 {TclUniCharIsControl} { + # [Bug 3464428] + string is control \u00ad +} {1} +test utf-21.12 {unicode control char in regc_locale.c} { + # [Bug 3464428], [Bug a876646efe] + regexp {^[[:cntrl:]]*$} \u0000\u001f\u00ad +} {1} test utf-22.1 {TclUniCharIsWordChar} { string wordend "xyz123_bar fg" 0 @@ -263,29 +347,102 @@ test utf-22.1 {TclUniCharIsWordChar} { test utf-22.2 {TclUniCharIsWordChar} { string wordend "x\u5080z123_bar\u203c fg" 0 } 10 - + test utf-23.1 {TclUniCharIsAlpha} { -} {} + # this returns 1 with Unicode 6 compliance + string is alpha \u021f\u0220 +} {1} +test utf-23.2 {unicode alpha char in regc_locale.c} { + # this returns 1 with Unicode 6 compliance + regexp {^[[:alpha:]]+$} \u021f\u0220 +} {1} test utf-24.1 {TclUniCharIsDigit} { -} {} - -test utf-24.2 {TclUniCharIsSpace} { -} {} + # this returns 1 with Unicode 6 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 + 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 +} {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] +} {1 1} + +testConstraint teststringobj [llength [info commands teststringobj]] + +test utf-25.1 {Tcl_UniCharNcasecmp} -constraints teststringobj \ + -setup { + testobj freeallvars + } \ + -body { + teststringobj set 1 a + teststringobj set 2 b + teststringobj getunicode 1 + teststringobj getunicode 2 + string compare -nocase [teststringobj get 1] [teststringobj get 2] + } \ + -cleanup { + testobj freeallvars + } \ + -result -1 +test utf-25.2 {Tcl_UniCharNcasecmp} -constraints teststringobj \ + -setup { + testobj freeallvars + } \ + -body { + teststringobj set 1 b + teststringobj set 2 a + teststringobj getunicode 1 + teststringobj getunicode 2 + string compare -nocase [teststringobj get 1] [teststringobj get 2] + } \ + -cleanup { + testobj freeallvars + } \ + -result 1 +test utf-25.3 {Tcl_UniCharNcasecmp} -constraints teststringobj \ + -setup { + testobj freeallvars + } \ + -body { + teststringobj set 1 B + teststringobj set 2 a + teststringobj getunicode 1 + teststringobj getunicode 2 + string compare -nocase [teststringobj get 1] [teststringobj get 2] + } \ + -cleanup { + testobj freeallvars + } \ + -result 1 + +test utf-25.4 {Tcl_UniCharNcasecmp} -constraints teststringobj \ + -setup { + testobj freeallvars + } \ + -body { + teststringobj set 1 aBcB + teststringobj set 2 abca + teststringobj getunicode 1 + teststringobj getunicode 2 + string compare -nocase [teststringobj get 1] [teststringobj get 2] + } \ + -cleanup { + testobj freeallvars + } \ + -result 1 # cleanup ::tcltest::cleanupTests return - - - - - - - - - - - - +# Local Variables: +# mode: tcl +# End: |