summaryrefslogtreecommitdiffstats
path: root/tests/utf.test
diff options
context:
space:
mode:
Diffstat (limited to 'tests/utf.test')
-rw-r--r--tests/utf.test196
1 files changed, 101 insertions, 95 deletions
diff --git a/tests/utf.test b/tests/utf.test
index dc1a435..f830110 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -27,34 +27,40 @@ 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"]}
+ expr {"\x00" eq [testbytestring "\xC0\x80"]}
} 1
test utf-1.3 {Tcl_UniCharToUtf: 2 byte sequences} testbytestring {
- expr {"\xe0" eq [testbytestring "\xc3\xa0"]}
+ expr {"\xE0" eq [testbytestring "\xC3\xA0"]}
} 1
test utf-1.4 {Tcl_UniCharToUtf: 3 byte sequences} testbytestring {
- expr {"\u4e4e" eq [testbytestring "\xe4\xb9\x8e"]}
+ 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"]}
+ 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"]}
+ 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"]}
+ 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"]}
+ 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"]}
+ 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"]}
+ 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"]}
+ 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} {
@@ -67,7 +73,7 @@ test utf-2.3 {Tcl_UtfToUniChar: lead (2-byte) followed by non-trail} testbytestr
string length [testbytestring "\xC2"]
} {1}
test utf-2.4 {Tcl_UtfToUniChar: lead (2-byte) followed by trail} testbytestring {
- string length [testbytestring "\xC2\xa2"]
+ string length [testbytestring "\xC2\xA2"]
} {1}
test utf-2.5 {Tcl_UtfToUniChar: lead (3-byte) followed by non-trail} testbytestring {
string length [testbytestring "\xE2"]
@@ -76,7 +82,7 @@ test utf-2.6 {Tcl_UtfToUniChar: lead (3-byte) followed by 1 trail} testbytestrin
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"]
+ string length [testbytestring "\xE4\xB9\x8E"]
} {1}
test utf-2.8 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} -constraints {tip389 testbytestring} -body {
string length [testbytestring "\xF0\x90\x80\x80"]
@@ -150,27 +156,27 @@ 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"
+ 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"
+ string index \u4E4E\u25A\xFF\u543 2
+} "\uFF"
test utf-8.5 {Tcl_UniCharAtIndex: high surrogate} {
- string index \ud842 0
-} "\ud842"
+ string index \uD842 0
+} "\uD842"
test utf-8.6 {Tcl_UniCharAtIndex: low surrogate} {
- string index \udc42 0
-} "\udc42"
+ 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"
+ string range \u4E4E\u25A\xFF\u543klmnop 1 5
+} "\u25A\xFF\u543kl"
test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
@@ -178,22 +184,22 @@ test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
} {
}
test utf-10.2 {Tcl_UtfBackslash: \u subst} testbytestring {
- expr {"\ua2" eq [testbytestring "\xc2\xa2"]}
+ expr {"\uA2" eq [testbytestring "\xC2\xA2"]}
} 1
test utf-10.3 {Tcl_UtfBackslash: longer \u subst} testbytestring {
- expr {"\u4e21" eq [testbytestring "\xe4\xb8\xa1"]}
+ 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"}
+ 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"}
+ 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"}
+ 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"}
+ expr {"\U10E2165" eq "[testbytestring \xF4\x8E\x88\x96]5"}
} 1
proc bsCheck {char num} {
global errNum
@@ -239,8 +245,8 @@ bsCheck \u41 65
bsCheck \ua 10
bsCheck \uA 10
bsCheck \340 224
-bsCheck \ua1 161
-bsCheck \u4e21 20001
+bsCheck \uA1 161
+bsCheck \u4E21 20001
bsCheck \741 60
bsCheck \U 85
bsCheck \Uk 85
@@ -248,10 +254,10 @@ 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 \U4E21 20001
+bsCheck \U004E21 20001
+bsCheck \U00004E21 20001
+bsCheck \U0000004E21 78
bsCheck \U00110000 69632
bsCheck \U01100000 69632
bsCheck \U11000000 69632
@@ -267,17 +273,17 @@ test utf-11.2 {Tcl_UtfToUpper} {
string toupper abc
} ABC
test utf-11.3 {Tcl_UtfToUpper} {
- string toupper \u00e3ab
-} \u00c3AB
+ string toupper \xE3AB
+} \xC3AB
test utf-11.4 {Tcl_UtfToUpper} {
- string toupper \u01e3ab
-} \u01e2AB
+ string toupper \u01E3AB
+} \u01E2AB
test utf-11.5 {Tcl_UtfToUpper Georgian (new in Unicode 11)} {
- string toupper \u10d0\u1c90
-} \u1c90\u1c90
+ string toupper \u10D0\u1C90
+} \u1C90\u1C90
test utf-11.6 {Tcl_UtfToUpper low/high surrogate)} {
- string toupper \udc24\ud824
-} \udc24\ud824
+ string toupper \uDC24\uD824
+} \uDC24\uD824
test utf-12.1 {Tcl_UtfToLower} {
string tolower {}
@@ -286,17 +292,17 @@ test utf-12.2 {Tcl_UtfToLower} {
string tolower ABC
} abc
test utf-12.3 {Tcl_UtfToLower} {
- string tolower \u00c3AB
-} \u00e3ab
+ string tolower \xC3AB
+} \xE3ab
test utf-12.4 {Tcl_UtfToLower} {
- string tolower \u01e2AB
-} \u01e3ab
+ string tolower \u01E2AB
+} \u01E3ab
test utf-12.5 {Tcl_UtfToLower Georgian (new in Unicode 11)} {
- string tolower \u10d0\u1c90
-} \u10d0\u10d0
+ string tolower \u10D0\u1C90
+} \u10D0\u10D0
test utf-12.6 {Tcl_UtfToUpper low/high surrogate)} {
- string tolower \udc24\ud824
-} \udc24\ud824
+ string tolower \uDC24\uD824
+} \uDC24\uD824
test utf-13.1 {Tcl_UtfToTitle} {
string totitle {}
@@ -305,20 +311,20 @@ test utf-13.2 {Tcl_UtfToTitle} {
string totitle abc
} Abc
test utf-13.3 {Tcl_UtfToTitle} {
- string totitle \u00e3ab
-} \u00c3ab
+ string totitle \xE3AB
+} \xC3ab
test utf-13.4 {Tcl_UtfToTitle} {
- string totitle \u01f3ab
-} \u01f2ab
+ string totitle \u01F3AB
+} \u01F2ab
test utf-13.5 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
- string totitle \u10d0\u1c90
-} \u10d0\u1c90
+ string totitle \u10D0\u1C90
+} \u10D0\u1C90
test utf-13.6 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
- string totitle \u1c90\u10d0
-} \u1c90\u10d0
+ string totitle \u1C90\u10D0
+} \u1C90\u10D0
test utf-13.7 {Tcl_UtfToTitle low/high surrogate)} {
- string totitle \udc24\ud824
-} \udc24\ud824
+ string totitle \uDC24\uD824
+} \uDC24\uD824
test utf-14.1 {Tcl_UtfNcasecmp} {
string compare -nocase a b
@@ -337,7 +343,7 @@ test utf-15.1 {Tcl_UniCharToUpper, negative delta} {
string toupper aA
} AA
test utf-15.2 {Tcl_UniCharToUpper, positive delta} {
- string toupper \u0178\u00ff
+ string toupper \u0178\xFF
} \u0178\u0178
test utf-15.3 {Tcl_UniCharToUpper, no delta} {
string toupper !
@@ -347,24 +353,24 @@ 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\U10400
-} \u00ff\u00ff\u0265\u01c6\U10428
+ 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
+ string totitle \u01C4
+} \u01C5
test utf-18.2 {Tcl_UniCharToTitle, subtract one for title} {
- string totitle \u01c6
-} \u01c5
+ string totitle \u01C6
+} \u01C5
test utf-18.3 {Tcl_UniCharToTitle, subtract delta for title (positive)} {
- string totitle \u017f
-} \u0053
+ string totitle \u017F
+} \x53
test utf-18.4 {Tcl_UniCharToTitle, subtract delta for title (negative)} {
- string totitle \u00ff
+ string totitle \xFF
} \u0178
test utf-18.5 {Tcl_UniCharToTitle, no delta} {
string totitle !
@@ -381,15 +387,15 @@ test utf-20.1 {TclUniCharNcmp} {
test utf-21.1 {TclUniCharIsAlnum} {
# this returns 1 with Unicode 7 compliance
- string is alnum \u1040\u021f\u0220
+ 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]
+ 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:]]+$} \ufbc1
+ regexp {^[[:print:]]+$} \uFBC1
} 1
test utf-21.4 {TclUniCharIsGraph} {
# [Bug 3464428]
@@ -401,65 +407,65 @@ test utf-21.5 {unicode graph char in regc_locale.c} {
} {1}
test utf-21.6 {TclUniCharIsGraph} {
# [Bug 3464428]
- string is graph \u00a0
+ string is graph \xA0
} {0}
test utf-21.7 {unicode graph char in regc_locale.c} {
# [Bug 3464428]
- regexp {[[:graph:]]} \u0020\u00a0\u2028\u2029
+ regexp {[[:graph:]]} \x20\xA0\u2028\u2029
} {0}
test utf-21.8 {TclUniCharIsPrint} {
# [Bug 3464428]
- string is print \u0009
+ string is print \x09
} {0}
test utf-21.9 {unicode print char in regc_locale.c} {
# [Bug 3464428]
- regexp {[[:print:]]} \u0009
+ regexp {[[:print:]]} \x09
} {0}
test utf-21.10 {unicode print char in regc_locale.c} {
# [Bug 3464428]
- regexp {[[:print:]]} \u0009
+ regexp {[[:print:]]} \x09
} {0}
test utf-21.11 {TclUniCharIsControl} {
# [Bug 3464428]
- string is control \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
+ 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:]]*$} \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
+ regexp {^[[:cntrl:]]*$} \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
+ 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
+ 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:]]+$} \u021f\u0220\u037f\u052f
+ regexp {^[[:alpha:]]+$} \u021F\u0220\u037F\u052F
} {1}
test utf-24.1 {TclUniCharIsDigit} {
# this returns 1 with Unicode 7 compliance
- string is digit \u1040\uabf0
+ 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]
+ 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 \u0085\u1680\u180e\u200b\u202f\u2060
+ 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:]]+$} \u0085\u1680\u180e\u200b\u202f\u2060] [regexp {^\s+$} \u0085\u1680\u180e\u200b\u202f\u2060]
+ 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]]
@@ -471,8 +477,8 @@ test utf-25.1 {Tcl_UniCharNcasecmp} -constraints teststringobj \
-body {
teststringobj set 1 a
teststringobj set 2 b
- teststringobj getunicode 1
- teststringobj getunicode 2
+ teststringobj maxchars 1
+ teststringobj maxchars 2
string compare -nocase [teststringobj get 1] [teststringobj get 2]
} \
-cleanup {
@@ -486,8 +492,8 @@ test utf-25.2 {Tcl_UniCharNcasecmp} -constraints teststringobj \
-body {
teststringobj set 1 b
teststringobj set 2 a
- teststringobj getunicode 1
- teststringobj getunicode 2
+ teststringobj maxchars 1
+ teststringobj maxchars 2
string compare -nocase [teststringobj get 1] [teststringobj get 2]
} \
-cleanup {
@@ -501,8 +507,8 @@ test utf-25.3 {Tcl_UniCharNcasecmp} -constraints teststringobj \
-body {
teststringobj set 1 B
teststringobj set 2 a
- teststringobj getunicode 1
- teststringobj getunicode 2
+ teststringobj maxchars 1
+ teststringobj maxchars 2
string compare -nocase [teststringobj get 1] [teststringobj get 2]
} \
-cleanup {
@@ -517,8 +523,8 @@ test utf-25.4 {Tcl_UniCharNcasecmp} -constraints teststringobj \
-body {
teststringobj set 1 aBcB
teststringobj set 2 abca
- teststringobj getunicode 1
- teststringobj getunicode 2
+ teststringobj maxchars 1
+ teststringobj maxchars 2
string compare -nocase [teststringobj get 1] [teststringobj get 2]
} \
-cleanup {
generated by cgit v0.12 at 2025-04-04 00:57:31 (GMT)