path: root/tests/utf.test

# This file contains a collection of tests for tclUtf.c
# Sourcing this file into Tcl runs the tests and generates output for
# errors.  No output means no errors were found.
#
# Copyright (c) 1997 Sun Microsystems, Inc.
# Copyright (c) 1998-1999 by Scriptics Corporation.
#
# See the file "license.terms" for information on usage and redistribution
# of this file, and for a DISCLAIMER OF ALL WARRANTIES.

if {[lsearch [namespace children] ::tcltest] == -1} {
    package require tcltest 2
    namespace import -force ::tcltest::*
}

::tcltest::loadTestedCommands
catch [list package require -exact Tcltest [info patchlevel]]

testConstraint testbytestring [llength [info commands testbytestring]]

catch {unset x}

# Some tests require support for 4-byte UTF-8 sequences
testConstraint fullutf [expr {[string length \U010000] == 1}]

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 testbytestring -body {
    expr {"\U014E4E" eq [testbytestring "\xF0\x94\xB9\x8E"]}
} -result 1
test utf-1.8 {Tcl_UniCharToUtf: 3 byte sequence, high surrogate} testbytestring {
    expr {"\uD842" eq [testbytestring "\xED\xA1\x82"]}
} 1
test utf-1.9 {Tcl_UniCharToUtf: 3 byte sequence, low surrogate} testbytestring {
    expr {"\uDC42" eq [testbytestring "\xED\xB1\x82"]}
} 1
test utf-1.10 {Tcl_UniCharToUtf: 3 byte sequence, high surrogate} testbytestring {
    expr {[format %c 0xD842] eq [testbytestring "\xED\xA1\x82"]}
} 1
test utf-1.11 {Tcl_UniCharToUtf: 3 byte sequence, low surrogate} testbytestring {
    expr {[format %c 0xDC42] eq [testbytestring "\xED\xB1\x82"]}
} 1
test utf-1.12 {Tcl_UniCharToUtf: 4 byte sequence, high/low surrogate} testbytestring {
    expr {"\uD842\uDC42" eq [testbytestring "\xF0\xA0\xA1\x82"]}
} 1
test utf-1.13 {Tcl_UniCharToUtf: Invalid surrogate} testbytestring {
    expr {"\UD842" 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} testbytestring {
    string length [testbytestring "\x82\x83\x84"]
} {3}
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} testbytestring {
    string length [testbytestring "\xC2\xA2"]
} {1}
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} testbytestring {
    string length [testbytestring "\xE2\xA2"]
} {2}
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: 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} {
} {}

testConstraint testnumutfchars [llength [info commands testnumutfchars]]
testConstraint testfindfirst [llength [info commands testfindfirst]]
testConstraint testfindlast [llength [info commands testfindlast]]

test utf-4.1 {Tcl_NumUtfChars: zero length} testnumutfchars {
    testnumutfchars ""
} {0}
test utf-4.2 {Tcl_NumUtfChars: length 1} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "\xC2\xA2"]
} {1}
test utf-4.3 {Tcl_NumUtfChars: long string} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "abc\xC2\xA2\xE4\xB9\x8E\xA2\x4E"]
} {7}
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 "" 0
} {0}
test utf-4.6 {Tcl_NumUtfChars: length 1, calc len} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "\xC2\xA2"] end
} {1}
test utf-4.7 {Tcl_NumUtfChars: long string, calc len} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "abc\xC2\xA2\xE4\xB9\x8E\uA2\x4E"] end
} {7}
test utf-4.8 {Tcl_NumUtfChars: #u0000, calc len} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "\xC0\x80"] end
} {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"] end-1
} {2}
test utf-4.10 {Tcl_NumUtfChars: #u0000, calc len, overcomplete} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring "\x00"] end+1
} {2}
test utf-4.11 {Tcl_NumUtfChars: 3 bytes of 4-byte UTF-8 characater} {testnumutfchars testbytestring} {
    testnumutfchars [testbytestring \xf0\x9f\x92\xa9] end-1
} {3}
test utf-4.12 {Tcl_NumUtfChars: #4-byte UTF-8 character} {testnumutfchars testbytestring fullutf} {
    testnumutfchars [testbytestring \xf0\x9f\x92\xa9] end
} {1}

test utf-5.1 {Tcl_UtfFindFirst} {testfindfirst testbytestring} {
    testfindfirst [testbytestring "abcbc"] 98
} {bcbc}
test utf-5.2 {Tcl_UtfFindLast} {testfindlast testbytestring} {
    testfindlast [testbytestring "abcbc"] 98
} {bc}

test utf-6.1 {Tcl_UtfNext} {
} {}

test utf-7.1 {Tcl_UtfPrev} {
} {}

test utf-8.1 {Tcl_UniCharAtIndex: index = 0} {
    string index abcd 0
} {a}
test utf-8.2 {Tcl_UniCharAtIndex: index = 0} {
    string index \u4E4E\u25A 0
} "\u4E4E"
test utf-8.3 {Tcl_UniCharAtIndex: index > 0} {
    string index abcd 2
} {c}
test utf-8.4 {Tcl_UniCharAtIndex: index > 0} {
    string index \u4E4E\u25A\xFF\u543 2
} "\uFF"
test utf-8.5 {Tcl_UniCharAtIndex: high surrogate} {
    string index \uD842 0
} "\uD842"
test utf-8.6 {Tcl_UniCharAtIndex: low surrogate} {
    string index \uDC42 0
} "\uDC42"

test utf-9.1 {Tcl_UtfAtIndex: index = 0} {
    string range abcd 0 2
} {abc}
test utf-9.2 {Tcl_UtfAtIndex: index > 0} {
    string range \u4E4E\u25A\xFF\u543klmnop 1 5
} "\u25A\xFF\u543kl"


test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
    set x \n
} {
}
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
test utf-10.6 {Tcl_UtfBackslash: stops after 5 hex chars} testbytestring {
    expr {"\U1E2165" eq "[testbytestring \xF0\x9E\x88\x96]5"}
} 1
test utf-10.7 {Tcl_UtfBackslash: stops after 6 hex chars} testbytestring {
    expr {"\U10E2165" eq "[testbytestring \xF4\x8E\x88\x96]5"}
} 1
proc bsCheck {char num} {
    global errNum
    test utf-10.$errNum {backslash substitution} {
	scan $char %c value
	set value
    } $num
    incr errNum
}
set errNum 8
bsCheck \b	8
bsCheck \e	101
bsCheck \f	12
bsCheck \n	10
bsCheck \r	13
bsCheck \t	9
bsCheck \v	11
bsCheck \{	123
bsCheck \}	125
bsCheck \[	91
bsCheck \]	93
bsCheck \$	36
bsCheck \ 	32
bsCheck \;	59
bsCheck \\	92
bsCheck \Ca	67
bsCheck \Ma	77
bsCheck \CMa	67
# 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
bsCheck \x	120
bsCheck \xa	10
bsCheck \xA	10
bsCheck \x41	65
bsCheck \x541	84
bsCheck \u	117
bsCheck \uk	117
bsCheck \u41	65
bsCheck \ua	10
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
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 {}
} {}
test utf-11.2 {Tcl_UtfToUpper} {
    string toupper abc
} ABC
test utf-11.3 {Tcl_UtfToUpper} {
    string toupper \xE3AB
} \xC3AB
test utf-11.4 {Tcl_UtfToUpper} {
    string toupper \u01E3AB
} \u01E2AB
test utf-11.5 {Tcl_UtfToUpper Georgian (new in Unicode 11)} {
    string toupper \u10D0\u1C90
} \u1C90\u1C90
test utf-11.6 {Tcl_UtfToUpper low/high surrogate)} {
    string toupper \uDC24\uD824
} \uDC24\uD824

test utf-12.1 {Tcl_UtfToLower} {
    string tolower {}
} {}
test utf-12.2 {Tcl_UtfToLower} {
    string tolower ABC
} abc
test utf-12.3 {Tcl_UtfToLower} {
    string tolower \xC3AB
} \xE3ab
test utf-12.4 {Tcl_UtfToLower} {
    string tolower \u01E2AB
} \u01E3ab
test utf-12.5 {Tcl_UtfToLower Georgian (new in Unicode 11)} {
    string tolower \u10D0\u1C90
} \u10D0\u10D0
test utf-12.6 {Tcl_UtfToUpper low/high surrogate)} {
    string tolower \uDC24\uD824
} \uDC24\uD824

test utf-13.1 {Tcl_UtfToTitle} {
    string totitle {}
} {}
test utf-13.2 {Tcl_UtfToTitle} {
    string totitle abc
} Abc
test utf-13.3 {Tcl_UtfToTitle} {
    string totitle \xE3AB
} \xC3ab
test utf-13.4 {Tcl_UtfToTitle} {
    string totitle \u01F3AB
} \u01F2ab
test utf-13.5 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
    string totitle \u10D0\u1C90
} \u10D0\u1C90
test utf-13.6 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
    string totitle \u1C90\u10D0
} \u1C90\u10D0
test utf-13.7 {Tcl_UtfToTitle low/high surrogate)} {
    string totitle \uDC24\uD824
} \uDC24\uD824

test utf-14.1 {Tcl_UtfNcasecmp} {
    string compare -nocase a b
} -1
test utf-14.2 {Tcl_UtfNcasecmp} {
    string compare -nocase b a
} 1
test utf-14.3 {Tcl_UtfNcasecmp} {
    string compare -nocase B a
} 1
test utf-14.4 {Tcl_UtfNcasecmp} {
    string compare -nocase aBcB abca
} 1

test utf-15.1 {Tcl_UniCharToUpper, negative delta} {
    string toupper aA
} AA
test utf-15.2 {Tcl_UniCharToUpper, positive delta} {
    string toupper \u0178\xFF
} \u0178\u0178
test utf-15.3 {Tcl_UniCharToUpper, no delta} {
    string toupper !
} !

test utf-16.1 {Tcl_UniCharToLower, negative delta} {
    string tolower aA
} aa
test utf-16.2 {Tcl_UniCharToLower, positive delta} {
    string tolower \u0178\xFF\uA78D\u01C5\U10400
} \xFF\xFF\u0265\u01C6\U10428

test utf-17.1 {Tcl_UniCharToLower, no delta} {
    string tolower !
} !

test utf-18.1 {Tcl_UniCharToTitle, add one for title} {
    string totitle \u01C4
} \u01C5
test utf-18.2 {Tcl_UniCharToTitle, subtract one for title} {
    string totitle \u01C6
} \u01C5
test utf-18.3 {Tcl_UniCharToTitle, subtract delta for title (positive)} {
    string totitle \u017F
} \x53
test utf-18.4 {Tcl_UniCharToTitle, subtract delta for title (negative)} {
    string totitle \xFF
} \u0178
test utf-18.5 {Tcl_UniCharToTitle, no delta} {
    string totitle !
} !

test utf-19.1 {TclUniCharLen} -body {
    list [regexp \\d abc456def foo] $foo
} -cleanup {
    unset -nocomplain foo
} -result {1 4}

test utf-20.1 {TclUniCharNcmp} {
} {}

test utf-21.1 {TclUniCharIsAlnum} {
    # 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 7 compliance
    list [regexp {^[[:alnum:]]+$} \u1040\u021F\u0220] [regexp {^\w+$} \u1040\u021F\u0220_\u203F\u2040\u2054\uFE33\uFE34\uFE4D\uFE4E\uFE4F\uFF3F]
} {1 1}
test utf-21.3 {unicode print char in regc_locale.c} {
    # this returns 1 with Unicode 7 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 \xA0
} {0}
test utf-21.7 {unicode graph char in regc_locale.c} {
    # [Bug 3464428]
    regexp {[[:graph:]]} \x20\xA0\u2028\u2029
} {0}
test utf-21.8 {TclUniCharIsPrint} {
    # [Bug 3464428]
    string is print \x09
} {0}
test utf-21.9 {unicode print char in regc_locale.c} {
    # [Bug 3464428]
    regexp {[[:print:]]} \x09
} {0}
test utf-21.10 {unicode print char in regc_locale.c} {
    # [Bug 3464428]
    regexp {[[:print:]]} \x09
} {0}
test utf-21.11 {TclUniCharIsControl} {
    # [Bug 3464428]
    string is control \x00\x1F\xAD\u0605\u061C\u180E\u2066\uFEFF
} {1}
test utf-21.12 {unicode control char in regc_locale.c} {
    # [Bug 3464428], [Bug a876646efe]
    regexp {^[[:cntrl:]]*$} \x00\x1F\xAD\u0605\u061C\u180E\u2066\uFEFF
} {1}

test utf-22.1 {TclUniCharIsWordChar} {
    string wordend "xyz123_bar fg" 0
} 10
test utf-22.2 {TclUniCharIsWordChar} {
    string wordend "x\u5080z123_bar\u203C fg" 0
} 10

test utf-23.1 {TclUniCharIsAlpha} {
    # 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 7 compliance
    regexp {^[[:alpha:]]+$} \u021F\u0220\u037F\u052F
} {1}

test utf-24.1 {TclUniCharIsDigit} {
    # 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 7 compliance
    list [regexp {^[[:digit:]]+$} \u1040\uABF0] [regexp {^\d+$} \u1040\uABF0]
} {1 1}

test utf-24.3 {TclUniCharIsSpace} {
    # this returns 1 with Unicode 7/TIP 413 compliance
    string is space \x85\u1680\u180E\u200B\u202F\u2060
} {1}
test utf-24.4 {unicode space char in regc_locale.c} {
    # this returns 1 with Unicode 7/TIP 413 compliance
    list [regexp {^[[:space:]]+$} \x85\u1680\u180E\u200B\u202F\u2060] [regexp {^\s+$} \x85\u1680\u180E\u200B\u202F\u2060]
} {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 maxchars 1
	teststringobj maxchars 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 maxchars 1
	teststringobj maxchars 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 maxchars 1
	teststringobj maxchars 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 maxchars 1
	teststringobj maxchars 2
	string compare -nocase [teststringobj get 1] [teststringobj get 2]
    } \
    -cleanup {
	testobj freeallvars
    } \
    -result 1

# cleanup
::tcltest::cleanupTests
return

# Local Variables:
# mode: tcl
# End: