diff options
Diffstat (limited to 'tests/encoding.test')
| -rw-r--r-- | tests/encoding.test | 76 |
1 files changed, 56 insertions, 20 deletions
diff --git a/tests/encoding.test b/tests/encoding.test index c99dc71..fffcdd5 100644 --- a/tests/encoding.test +++ b/tests/encoding.test @@ -297,7 +297,7 @@ test encoding-11.11 {encoding: extended Unicode UTF-32} { test encoding-12.1 {LoadTableEncoding: normal encoding} { set x [encoding convertto iso8859-3 Ġ] - append x [encoding convertto iso8859-3 Õ] + append x [encoding convertto -nocomplain iso8859-3 Õ] append x [encoding convertfrom iso8859-3 Õ] } "Õ?Ġ" test encoding-12.2 {LoadTableEncoding: single-byte encoding} { @@ -346,67 +346,67 @@ test encoding-15.5 {UtfToUtfProc emoji character input} { } "4 😂" test encoding-15.6 {UtfToUtfProc emoji character output} { set x \uDE02\uD83D\uDE02\uD83D - set y [encoding convertto utf-8 \uDE02\uD83D\uDE02\uD83D] + set y [encoding convertto -nocomplain utf-8 \uDE02\uD83D\uDE02\uD83D] binary scan $y H* z list [string length $y] $z } {10 edb882f09f9882eda0bd} test encoding-15.7 {UtfToUtfProc emoji character output} { set x \uDE02\uD83D\uD83D - set y [encoding convertto utf-8 \uDE02\uD83D\uD83D] + set y [encoding convertto -nocomplain utf-8 \uDE02\uD83D\uD83D] binary scan $y H* z list [string length $x] [string length $y] $z } {3 9 edb882eda0bdeda0bd} test encoding-15.8 {UtfToUtfProc emoji character output} { set x \uDE02\uD83Dé - set y [encoding convertto utf-8 \uDE02\uD83Dé] + set y [encoding convertto -nocomplain utf-8 \uDE02\uD83Dé] binary scan $y H* z list [string length $x] [string length $y] $z } {3 8 edb882eda0bdc3a9} test encoding-15.9 {UtfToUtfProc emoji character output} { set x \uDE02\uD83DX - set y [encoding convertto utf-8 \uDE02\uD83DX] + set y [encoding convertto -nocomplain utf-8 \uDE02\uD83DX] binary scan $y H* z list [string length $x] [string length $y] $z } {3 7 edb882eda0bd58} test encoding-15.10 {UtfToUtfProc high surrogate character output} { set x \uDE02é - set y [encoding convertto utf-8 \uDE02é] + set y [encoding convertto -nocomplain utf-8 \uDE02é] binary scan $y H* z list [string length $x] [string length $y] $z } {2 5 edb882c3a9} test encoding-15.11 {UtfToUtfProc low surrogate character output} { set x \uDA02é - set y [encoding convertto utf-8 \uDA02é] + set y [encoding convertto -nocomplain utf-8 \uDA02é] binary scan $y H* z list [string length $x] [string length $y] $z } {2 5 eda882c3a9} test encoding-15.12 {UtfToUtfProc high surrogate character output} { set x \uDE02Y - set y [encoding convertto utf-8 \uDE02Y] + set y [encoding convertto -nocomplain utf-8 \uDE02Y] binary scan $y H* z list [string length $x] [string length $y] $z } {2 4 edb88259} test encoding-15.13 {UtfToUtfProc low surrogate character output} { set x \uDA02Y - set y [encoding convertto utf-8 \uDA02Y] + set y [encoding convertto -nocomplain utf-8 \uDA02Y] binary scan $y H* z list [string length $x] [string length $y] $z } {2 4 eda88259} test encoding-15.14 {UtfToUtfProc high surrogate character output} { set x \uDE02 - set y [encoding convertto utf-8 \uDE02] + set y [encoding convertto -nocomplain utf-8 \uDE02] binary scan $y H* z list [string length $x] [string length $y] $z } {1 3 edb882} test encoding-15.15 {UtfToUtfProc low surrogate character output} { set x \uDA02 - set y [encoding convertto utf-8 \uDA02] + set y [encoding convertto -nocomplain utf-8 \uDA02] binary scan $y H* z list [string length $x] [string length $y] $z } {1 3 eda882} test encoding-15.16 {UtfToUtfProc: Invalid 4-byte UTF-8, see [ed29806ba]} { set x \xF0\xA0\xA1\xC2 - set y [encoding convertfrom utf-8 \xF0\xA0\xA1\xC2] + set y [encoding convertfrom -nocomplain utf-8 \xF0\xA0\xA1\xC2] list [string length $x] $y } "4 \xF0\xA0\xA1\xC2" test encoding-15.17 {UtfToUtfProc emoji character output} { @@ -487,10 +487,10 @@ test encoding-17.2 {UtfToUcs2Proc} -body { encoding convertfrom utf-16 [encoding convertto ucs-2 "\U460DC"] } -result "\uFFFD" test encoding-17.3 {UtfToUtf16Proc} -body { - encoding convertto utf-16be "\uDCDC" + encoding convertto -nocomplain utf-16be "\uDCDC" } -result "\xFF\xFD" test encoding-17.4 {UtfToUtf16Proc} -body { - encoding convertto utf-16le "\uD8D8" + encoding convertto -nocomplain utf-16le "\uD8D8" } -result "\xFD\xFF" test encoding-17.5 {UtfToUtf16Proc} -body { encoding convertto utf-32le "\U460DC" @@ -615,26 +615,62 @@ test encoding-24.4 {Parse valid or invalid utf-8} { string length [encoding convertfrom utf-8 "\xC0\x80"] } 1 test encoding-24.5 {Parse valid or invalid utf-8} { - string length [encoding convertfrom utf-8 "\xC0\x81"] + string length [encoding convertfrom -nocomplain utf-8 "\xC0\x81"] } 2 test encoding-24.6 {Parse valid or invalid utf-8} { - string length [encoding convertfrom utf-8 "\xC1\xBF"] + string length [encoding convertfrom -nocomplain utf-8 "\xC1\xBF"] } 2 test encoding-24.7 {Parse valid or invalid utf-8} { string length [encoding convertfrom utf-8 "\xC2\x80"] } 1 test encoding-24.8 {Parse valid or invalid utf-8} { - string length [encoding convertfrom utf-8 "\xE0\x80\x80"] + string length [encoding convertfrom -nocomplain utf-8 "\xE0\x80\x80"] } 3 test encoding-24.9 {Parse valid or invalid utf-8} { - string length [encoding convertfrom utf-8 "\xE0\x9F\xBF"] + string length [encoding convertfrom -nocomplain utf-8 "\xE0\x9F\xBF"] } 3 test encoding-24.10 {Parse valid or invalid utf-8} { string length [encoding convertfrom utf-8 "\xE0\xA0\x80"] } 1 test encoding-24.11 {Parse valid or invalid utf-8} { - string length [encoding convertfrom utf-8 "\xEF\xBF\xBF"] + string length [encoding convertfrom -nocomplain utf-8 "\xEF\xBF\xBF"] } 1 +test encoding-24.12 {Parse valid or invalid utf-8} -body { + encoding convertfrom utf-8 "\xC0\x81" +} -returnCodes 1 -result {unexpected byte sequence starting at index 0: '\xC0'} +test encoding-24.13 {Parse valid or invalid utf-8} -body { + encoding convertfrom utf-8 "\xC1\xBF" +} -returnCodes 1 -result {unexpected byte sequence starting at index 0: '\xC1'} +test encoding-24.14 {Parse valid or invalid utf-8} { + string length [encoding convertfrom utf-8 "\xC2\x80"] +} 1 +test encoding-24.15 {Parse valid or invalid utf-8} -body { + encoding convertfrom utf-8 "Z\xE0\x80" +} -returnCodes 1 -result {unexpected byte sequence starting at index 1: '\xE0'} +test encoding-24.16 {Parse valid or invalid utf-8} -constraints testbytestring -body { + encoding convertto utf-8 [testbytestring "Z\u4343\x80"] +} -returnCodes 1 -result {expected byte sequence but character 1 was '䍃' (U+004343)} +test encoding-24.17 {Parse valid or invalid utf-8} -constraints testbytestring -body { + encoding convertto utf-8 [testbytestring "Z\xE0\x80"] +} -result "Z\xC3\xA0\xE2\x82\xAC" +test encoding-24.18 {Parse valid or invalid utf-8} -constraints testbytestring -body { + encoding convertto utf-8 [testbytestring "Z\xE0\x80xxxxxx"] +} -result "Z\xC3\xA0\xE2\x82\xACxxxxxx" +test encoding-24.19 {Parse valid or invalid utf-8} -body { + encoding convertto utf-8 "ZX\uD800" +} -returnCodes 1 -match glob -result "unexpected character at index 2: 'U+00D800'" +test encoding-24.20 {Parse with -nocomplain but without providing encoding} { + string length [encoding convertfrom -nocomplain "\x20"] +} 1 +test encoding-24.21 {Parse with -nocomplain but without providing encoding} { + string length [encoding convertto -nocomplain "\x20"] +} 1 +test encoding-24.22 {Syntax error, two encodings} -body { + encoding convertfrom iso8859-1 utf-8 "ZX\uD800" +} -returnCodes 1 -result {wrong # args: should be "::tcl::encoding::convertfrom ?-nocomplain? ?encoding? data"} +test encoding-24.23 {Syntax error, two encodings} -body { + encoding convertto iso8859-1 utf-8 "ZX\uD800" +} -returnCodes 1 -result {wrong # args: should be "::tcl::encoding::convertto ?-nocomplain? ?encoding? data"} file delete [file join [temporaryDirectory] iso2022.txt] @@ -792,7 +828,7 @@ test encoding-28.0 {all encodings load} -body { if {$name ne "unicode"} { incr count } - encoding convertto $name $string + encoding convertto -nocomplain $name $string # discard the cached internal representation of Tcl_Encoding # Unfortunately, without this, encoding 2-1 fails. |