diff options
Diffstat (limited to 'tests/utf.test')
-rw-r--r-- | tests/utf.test | 184 |
1 files changed, 118 insertions, 66 deletions
diff --git a/tests/utf.test b/tests/utf.test index e8ee374..422ab08 100644 --- a/tests/utf.test +++ b/tests/utf.test @@ -13,51 +13,74 @@ if {[lsearch [namespace children] ::tcltest] == -1} { namespace import -force ::tcltest::* } +::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"] +# Some tests require support for 4-byte UTF-8 sequences +testConstraint fullutf [expr {[format %c 0x010000] != "\ufffd"}] + +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-1.7 {Tcl_UniCharToUtf: 4 byte sequences} -constraints {fullutf testbytestring} -body { + expr {"\U014e4e" eq [testbytestring "\xf0\x94\xb9\x8e"]} +} -result 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: lead (4-byte) followed by 3 trail} -constraints {fullutf testbytestring} -body { + string length [testbytestring "\xF0\x90\x80\x80"] +} -result {1} +test utf-2.9 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} -constraints {fullutf testbytestring} -body { + string length [testbytestring "\xF4\x8F\xBF\xBF"] +} -result {1} +test utf-2.10 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail, underflow} testbytestring { + string length [testbytestring "\xF0\x8F\xBF\xBF"] +} {4} +test utf-2.11 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail, overflow} testbytestring { + string length [testbytestring "\xF4\x90\x80\x80"] } {4} +test utf-2.12 {Tcl_UtfToUniChar: longer UTF sequences not supported} testbytestring { + string length [testbytestring "\xF8\xA2\xA2\xA2\xA2"] +} {5} test utf-3.1 {Tcl_UtfCharComplete} { } {} @@ -66,27 +89,34 @@ 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 + testnumutfchars "" 0 } {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"] 2 } {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"] 10 } {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"] 2 } {1} +# Bug [2738427]: Tcl_NumUtfChars(...) no overflow check +test utf-4.9 {Tcl_NumUtfChars: #u20AC, calc len, incomplete} {testnumutfchars testbytestring} { + testnumutfchars [testbytestring "\xE2\x82\xAC"] 2 +} {2} +test utf-4.10 {Tcl_NumUtfChars: #u0000, calc len, overcomplete} {testnumutfchars testbytestring} { + testnumutfchars [testbytestring "\x00"] 2 +} {2} test utf-5.1 {Tcl_UtfFindFirsts} { } {} @@ -122,18 +152,18 @@ 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} { @@ -171,7 +201,7 @@ 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 @@ -180,6 +210,26 @@ 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 \U0000004e21 78 +if {[testConstraint fullutf]} { + bsCheck \U00110000 69632 + bsCheck \U01100000 69632 + bsCheck \U11000000 69632 + bsCheck \U0010FFFF 1114111 + bsCheck \U010FFFF0 1114111 + bsCheck \U10FFFF00 1114111 + bsCheck \UFFFFFFFF 1048575 +} test utf-11.1 {Tcl_UtfToUpper} { string toupper {} @@ -247,8 +297,8 @@ test utf-16.1 {Tcl_UniCharToLower, negative delta} { string tolower aA } aa test utf-16.2 {Tcl_UniCharToLower, positive delta} { - string tolower \u0178\u00ff\uA78D\u01c5 -} \u00ff\u00ff\u0265\u01c6 + string tolower \u0178\u00ff\uA78D\u01c5\U10400 +} \u00ff\u00ff\u0265\u01c6\U10428 test utf-17.1 {Tcl_UniCharToLower, no delta} { string tolower ! @@ -270,9 +320,11 @@ 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] $foo -} {1 4} +} -cleanup { + unset -nocomplain foo +} -result {1 4} test utf-20.1 {TclUniCharNcmp} { } {} @@ -352,12 +404,12 @@ test utf-24.2 {unicode digit char in regc_locale.c} { } {1 1} test utf-24.3 {TclUniCharIsSpace} { - # this returns 1 with Unicode 7 compliance - string is space \u1680\u180e\u202f + # this returns 1 with Unicode 7/TIP 413 compliance + string is space \u0085\u1680\u180e\u200b\u202f\u2060 } {1} test utf-24.4 {unicode space char in regc_locale.c} { - # this returns 1 with Unicode 7 compliance - list [regexp {^[[:space:]]+$} \u1680\u180e\u202f] [regexp {^\s+$} \u1680\u180e\u202f] + # this returns 1 with Unicode 7/TIP 413 compliance + list [regexp {^[[:space:]]+$} \u0085\u1680\u180e\u200b\u202f\u2060] [regexp {^\s+$} \u0085\u1680\u180e\u200b\u202f\u2060] } {1 1} testConstraint teststringobj [llength [info commands teststringobj]] |