summaryrefslogtreecommitdiffstats
path: root/tests/utf.test
diff options
context:
space:
mode:
authorjan.nijtmans <nijtmans@users.sourceforge.net>2021-03-30 07:11:18 (GMT)
committerjan.nijtmans <nijtmans@users.sourceforge.net>2021-03-30 07:11:18 (GMT)
commit1f1f43fcd2bfa68c8bff1a9d6dbb8ecab4be43e7 (patch)
tree35749cc38881de41be58b2c55c3e82de9cdc342c /tests/utf.test
parentc8617b374b29d14c8be0900f1623ca3120468b62 (diff)
downloadtcl-1f1f43fcd2bfa68c8bff1a9d6dbb8ecab4be43e7.zip
tcl-1f1f43fcd2bfa68c8bff1a9d6dbb8ecab4be43e7.tar.gz
tcl-1f1f43fcd2bfa68c8bff1a9d6dbb8ecab4be43e7.tar.bz2
Thanks to TIP #587, convert many escapes in the testcases into the actual (UTF-8) character.
Diffstat (limited to 'tests/utf.test')
-rw-r--r--tests/utf.test308
1 files changed, 154 insertions, 154 deletions
diff --git a/tests/utf.test b/tests/utf.test
index b4e34d6..3262214 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -49,7 +49,7 @@ 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]}
+ expr {"ไนŽ" 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]}
@@ -57,10 +57,10 @@ test utf-1.5 {Tcl_UniCharToUtf: overflowed Tcl_UniChar} testbytestring {
test utf-1.6 {Tcl_UniCharToUtf: negative Tcl_UniChar} testbytestring {
expr {[format %c -1] eq [testbytestring \xEF\xBF\xBD]}
} 1
-test utf-1.7.0 {Tcl_UniCharToUtf: 4 byte sequences} {fullutf Uesc testbytestring} {
+test utf-1.7.0 {Tcl_UniCharToUtf: 4 byte sequences} {fullutf testbytestring} {
expr {"\U014E4E" eq [testbytestring \xF0\x94\xB9\x8E]}
} 1
-test utf-1.7.1 {Tcl_UniCharToUtf: 4 byte sequences} {ucs2 Uesc testbytestring} {
+test utf-1.7.1 {Tcl_UniCharToUtf: 4 byte sequences} {Uesc ucs2 testbytestring} {
expr {"\U014E4E" eq [testbytestring \xF0\x94\xB9\x8E]}
} 0
test utf-1.8 {Tcl_UniCharToUtf: 3 byte sequence, high surrogate} testbytestring {
@@ -81,7 +81,7 @@ test utf-1.12 {Tcl_UniCharToUtf: 4 byte sequence, high/low surrogate} {pairsTo4b
test utf-1.13.0 {Tcl_UniCharToUtf: Invalid surrogate} {Uesc ucs2} {
expr {"\UD842" eq "\uD842"}
} 1
-test utf-1.13.1 {Tcl_UniCharToUtf: Invalid surrogate} {Uesc testbytestring fullutf} {
+test utf-1.13.1 {Tcl_UniCharToUtf: Invalid surrogate} {fullutf testbytestring} {
expr {"\UD842" eq [testbytestring \xEF\xBF\xBD]}
} 1
@@ -106,22 +106,22 @@ test utf-2.6 {Tcl_UtfToUniChar: lead (3-byte) followed by 1 trail} testbytestrin
test utf-2.7 {Tcl_UtfToUniChar: lead (3-byte) followed by 2 trail} testbytestring {
string length [testbytestring \xE4\xB9\x8E]
} 1
-test utf-2.8.0 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {testbytestring ucs2} {
+test utf-2.8.0 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {ucs2 testbytestring} {
string length [testbytestring \xF0\x90\x80\x80]
} 2
-test utf-2.8.1 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {Uesc utf16} {
- string length \U010000
+test utf-2.8.1 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} utf16 {
+ string length ๐€€
} 2
-test utf-2.8.2 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {Uesc ucs4} {
- string length \U010000
+test utf-2.8.2 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} ucs4 {
+ string length ๐€€
} 1
-test utf-2.9.0 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {testbytestring ucs2} {
+test utf-2.9.0 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {ucs2 testbytestring} {
string length [testbytestring \xF4\x8F\xBF\xBF]
} 2
-test utf-2.9.1 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {Uesc utf16} {
+test utf-2.9.1 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} utf16 {
string length \U10FFFF
} 2
-test utf-2.9.2 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} {Uesc ucs4} {
+test utf-2.9.2 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail} ucs4 {
string length \U10FFFF
} 1
test utf-2.10 {Tcl_UtfToUniChar: lead (4-byte) followed by 3 trail, underflow} testbytestring {
@@ -354,7 +354,7 @@ test utf-6.50 {Tcl_UtfNext} {testutfnext testbytestring} {
testutfnext [testbytestring \xE8\xA0]G
} 1
test utf-6.51 {Tcl_UtfNext} testutfnext {
- testutfnext \u8820
+ testutfnext ่  
} 3
test utf-6.52 {Tcl_UtfNext} {testutfnext testbytestring} {
testutfnext [testbytestring \xE8\xA0\xD0]
@@ -387,22 +387,22 @@ test utf-6.61 {Tcl_UtfNext} {testutfnext testbytestring} {
testutfnext [testbytestring \xF2\xA0\xF8]
} 1
test utf-6.62 {Tcl_UtfNext} testutfnext {
- testutfnext \u8820G
+ testutfnext ่  G
} 3
test utf-6.63 {Tcl_UtfNext} {testutfnext testbytestring} {
- testutfnext \u8820[testbytestring \xA0]
+ testutfnext ่  [testbytestring \xA0]
} 3
test utf-6.64 {Tcl_UtfNext} {testutfnext testbytestring} {
- testutfnext \u8820[testbytestring \xD0]
+ testutfnext ่  [testbytestring \xD0]
} 3
test utf-6.65 {Tcl_UtfNext} {testutfnext testbytestring} {
- testutfnext \u8820[testbytestring \xE8]
+ testutfnext ่  [testbytestring \xE8]
} 3
test utf-6.66 {Tcl_UtfNext} {testutfnext testbytestring} {
- testutfnext \u8820[testbytestring \xF2]
+ testutfnext ่  [testbytestring \xF2]
} 3
test utf-6.67 {Tcl_UtfNext} {testutfnext testbytestring} {
- testutfnext \u8820[testbytestring \xF8]
+ testutfnext ่  [testbytestring \xF8]
} 3
test utf-6.68 {Tcl_UtfNext} {testutfnext testbytestring} {
testutfnext [testbytestring \xF2\xA0\xA0]G
@@ -565,7 +565,7 @@ test utf-7.6 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xE8]
} 1
test utf-7.6.1 {Tcl_UtfPrev} {testutfprev testbytestring} {
- testutfprev A\u8820[testbytestring \xA0] 2
+ testutfprev A่  [testbytestring \xA0] 2
} 1
test utf-7.6.2 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xE8\xF8\xA0\xA0] 2
@@ -619,7 +619,7 @@ test utf-7.11 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xE8\xA0]
} 1
test utf-7.11.1 {Tcl_UtfPrev} {testutfprev testbytestring} {
- testutfprev A\u8820[testbytestring \xA0] 3
+ testutfprev A่  [testbytestring \xA0] 3
} 1
test utf-7.11.2 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xE8\xA0\xF8\xA0] 3
@@ -673,13 +673,13 @@ test utf-7.15.5 {Tcl_UtfPrev} {testutfprev testbytestring fullutf} {
testutfprev A[testbytestring \xF2\xA0\xA0\xF8] 4
} 1
test utf-7.16 {Tcl_UtfPrev} testutfprev {
- testutfprev A\u8820
+ testutfprev A่  
} 1
test utf-7.16.1 {Tcl_UtfPrev} {testutfprev testbytestring} {
- testutfprev A\u8820[testbytestring \xA0] 4
+ testutfprev A่  [testbytestring \xA0] 4
} 1
test utf-7.16.2 {Tcl_UtfPrev} {testutfprev testbytestring} {
- testutfprev A\u8820[testbytestring \xF8] 4
+ testutfprev A่  [testbytestring \xF8] 4
} 1
test utf-7.17 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xD0\xA0\xA0]
@@ -709,7 +709,7 @@ test utf-7.20.1 {Tcl_UtfPrev} {testutfprev testbytestring fullutf} {
testutfprev A[testbytestring \xF2\xA0\xA0\xA0]
} 1
test utf-7.21 {Tcl_UtfPrev} {testutfprev testbytestring} {
- testutfprev A\u8820[testbytestring \xA0]
+ testutfprev A่  [testbytestring \xA0]
} 4
test utf-7.22 {Tcl_UtfPrev} {testutfprev testbytestring} {
testutfprev A[testbytestring \xD0\xA0\xA0\xA0]
@@ -805,7 +805,7 @@ test utf-7.47 {Tcl_UtfPrev, pointing to 3th byte of 3-byte valid sequence} {test
testutfprev [testbytestring \xE8\xA0]
} 0
test utf-7.47.1 {Tcl_UtfPrev, pointing to 3th byte of 3-byte valid sequence} testutfprev {
- testutfprev \u8820 2
+ testutfprev ่   2
} 0
test utf-7.47.2 {Tcl_UtfPrev, pointing to 3th byte of 3-byte invalid sequence} {testutfprev testbytestring} {
testutfprev [testbytestring \xE8\xA0\x00] 2
@@ -848,14 +848,14 @@ 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 ไนŽษš 0
+} ไนŽ
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
-} \xFF
+ string index ไนŽษšรฟีƒ 2
+} รฟ
test utf-8.5.0 {Tcl_UniCharAtIndex: high surrogate} ucs2 {
string index \uD842 0
} \uD842
@@ -872,116 +872,116 @@ test utf-8.7.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
string index \uD83D\uDE00G 0
} \uD83D
test utf-8.7.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
- string index \uD83D\uDE00G 0
-} \U1F600
+ string index ๐Ÿ˜€G 0
+} ๐Ÿ˜€
test utf-8.7.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
- string index \uD83D\uDE00G 0
-} \U1F600
+ string index ๐Ÿ˜€G 0
+} ๐Ÿ˜€
test utf-8.8.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
string index \uD83D\uDE00G 1
} \uDE00
test utf-8.8.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
- string index \uD83D\uDE00G 1
+ string index ๐Ÿ˜€G 1
} G
test utf-8.8.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
- string index \uD83D\uDE00G 1
+ string index ๐Ÿ˜€G 1
} {}
test utf-8.9.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
string index \uD83D\uDE00G 2
} G
test utf-8.9.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
- string index \uD83D\uDE00G 2
+ string index ๐Ÿ˜€G 2
} {}
test utf-8.9.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
- string index \uD83D\uDE00G 2
+ string index ๐Ÿ˜€G 2
} G
-test utf-8.10.0 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs2} {
- string index \U1F600G 0
+test utf-8.10.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
+ string index ๐Ÿ˜€G 0
} \uFFFD
-test utf-8.10.1 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs4} {
- string index \U1F600G 0
-} \U1F600
-test utf-8.10.2 {Tcl_UniCharAtIndex: Emoji} {Uesc utf16} {
- string index \U1F600G 0
-} \U1F600
-test utf-8.11.0 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs2} {
- string index \U1F600G 1
+test utf-8.10.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
+ string index ๐Ÿ˜€G 0
+} ๐Ÿ˜€
+test utf-8.10.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
+ string index ๐Ÿ˜€G 0
+} ๐Ÿ˜€
+test utf-8.11.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
+ string index ๐Ÿ˜€G 1
} G
-test utf-8.11.1 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs4} {
- string index \U1F600G 1
+test utf-8.11.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
+ string index ๐Ÿ˜€G 1
} G
-test utf-8.11.2 {Tcl_UniCharAtIndex: Emoji} {Uesc utf16} {
- string index \U1F600G 1
+test utf-8.11.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
+ string index ๐Ÿ˜€G 1
} {}
-test utf-8.12.0 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs2} {
- string index \U1F600G 2
+test utf-8.12.0 {Tcl_UniCharAtIndex: Emoji} ucs2 {
+ string index ๐Ÿ˜€G 2
} {}
-test utf-8.12.1 {Tcl_UniCharAtIndex: Emoji} {Uesc ucs4} {
- string index \U1F600G 2
+test utf-8.12.1 {Tcl_UniCharAtIndex: Emoji} ucs4 {
+ string index ๐Ÿ˜€G 2
} {}
-test utf-8.12.2 {Tcl_UniCharAtIndex: Emoji} {Uesc utf16} {
- string index \U1F600G 2
+test utf-8.12.2 {Tcl_UniCharAtIndex: Emoji} utf16 {
+ string index ๐Ÿ˜€G 2
} G
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 ไนŽษšรฟีƒklmnop 1 5
+} ษšรฟีƒkl
test utf-9.3.0 {Tcl_UtfAtIndex: index = 0, Emoji} ucs2 {
string range \uD83D\uDE00G 0 0
} \uD83D
test utf-9.3.1 {Tcl_UtfAtIndex: index = 0, Emoji} ucs4 {
- string range \uD83D\uDE00G 0 0
-} \U1F600
+ string range ๐Ÿ˜€G 0 0
+} ๐Ÿ˜€
test utf-9.3.2 {Tcl_UtfAtIndex: index = 0, Emoji} utf16 {
- string range \uD83D\uDE00G 0 0
-} \U1F600
+ string range ๐Ÿ˜€G 0 0
+} ๐Ÿ˜€
test utf-9.4.0 {Tcl_UtfAtIndex: index > 0, Emoji} ucs2 {
string range \uD83D\uDE00G 1 1
} \uDE00
test utf-9.4.1 {Tcl_UtfAtIndex: index > 0, Emoji} ucs4 {
- string range \uD83D\uDE00G 1 1
+ string range ๐Ÿ˜€G 1 1
} G
test utf-9.4.2 {Tcl_UtfAtIndex: index > 0, Emoji} utf16 {
- string range \uD83D\uDE00G 1 1
+ string range ๐Ÿ˜€G 1 1
} {}
test utf-9.5.0 {Tcl_UtfAtIndex: index > 0, Emoji} ucs2 {
string range \uD83D\uDE00G 2 2
} G
test utf-9.5.1 {Tcl_UtfAtIndex: index > 0, Emoji} ucs4 {
- string range \uD83D\uDE00G 2 2
+ string range ๐Ÿ˜€G 2 2
} {}
test utf-9.5.2 {Tcl_UtfAtIndex: index > 0, Emoji} utf16 {
- string range \uD83D\uDE00G 2 2
+ string range ๐Ÿ˜€G 2 2
} G
-test utf-9.6.0 {Tcl_UtfAtIndex: index = 0, Emoji} {Uesc ucs2} {
- string range \U1f600G 0 0
+test utf-9.6.0 {Tcl_UtfAtIndex: index = 0, Emoji} ucs2 {
+ string range ๐Ÿ˜€G 0 0
} \uFFFD
-test utf-9.6.1 {Tcl_UtfAtIndex: index = 0, Emoji} {Uesc ucs4} {
- string range \U1f600G 0 0
-} \U1F600
-test utf-9.6.2 {Tcl_UtfAtIndex: index = 0, Emoji} {Uesc utf16} {
- string range \U1f600G 0 0
-} \U1F600
-test utf-9.7.0 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc ucs2} {
- string range \U1f600G 1 1
+test utf-9.6.1 {Tcl_UtfAtIndex: index = 0, Emoji} ucs4 {
+ string range ๐Ÿ˜€G 0 0
+} ๐Ÿ˜€
+test utf-9.6.2 {Tcl_UtfAtIndex: index = 0, Emoji} utf16 {
+ string range ๐Ÿ˜€G 0 0
+} ๐Ÿ˜€
+test utf-9.7.0 {Tcl_UtfAtIndex: index > 0, Emoji} ucs2 {
+ string range ๐Ÿ˜€G 1 1
} G
-test utf-9.7.1 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc ucs4} {
- string range \U1f600G 1 1
+test utf-9.7.1 {Tcl_UtfAtIndex: index > 0, Emoji} ucs4 {
+ string range ๐Ÿ˜€G 1 1
} G
-test utf-9.7.2 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc utf16} {
- string range \U1f600G 1 1
+test utf-9.7.2 {Tcl_UtfAtIndex: index > 0, Emoji} utf16 {
+ string range ๐Ÿ˜€G 1 1
} {}
-test utf-9.8.0 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc ucs2} {
- string range \U1f600G 2 2
+test utf-9.8.0 {Tcl_UtfAtIndex: index > 0, Emoji} ucs2 {
+ string range ๐Ÿ˜€G 2 2
} {}
-test utf-9.8.1 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc ucs4} {
- string range \U1f600G 2 2
+test utf-9.8.1 {Tcl_UtfAtIndex: index > 0, Emoji} ucs4 {
+ string range ๐Ÿ˜€G 2 2
} {}
-test utf-9.8.2 {Tcl_UtfAtIndex: index > 0, Emoji} {Uesc utf16} {
- string range \U1f600G 2 2
+test utf-9.8.2 {Tcl_UtfAtIndex: index > 0, Emoji} utf16 {
+ string range ๐Ÿ˜€G 2 2
} G
test utf-10.1 {Tcl_UtfBackslash: dst == NULL} {
@@ -1000,10 +1000,10 @@ test utf-10.4 {Tcl_UtfBackslash: stops at first non-hex} testbytestring {
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} {Uesc fullutf testbytestring} {
+test utf-10.6 {Tcl_UtfBackslash: stops after 5 hex chars} {fullutf testbytestring} {
expr {"\U1E2165" eq "[testbytestring \xF0\x9E\x88\x96]5"}
} 1
-test utf-10.7 {Tcl_UtfBackslash: stops after 6 hex chars} {Uesc fullutf testbytestring} {
+test utf-10.7 {Tcl_UtfBackslash: stops after 6 hex chars} {fullutf testbytestring} {
expr {"\U10E2165" eq "[testbytestring \xF4\x8E\x88\x96]5"}
} 1
@@ -1066,13 +1066,13 @@ bsCheck \U4E21 20001 Uesc
bsCheck \U004E21 20001 Uesc
bsCheck \U00004E21 20001 Uesc
bsCheck \U0000004E21 78 Uesc
-bsCheck \U00110000 69632 {Uesc fullutf}
-bsCheck \U01100000 69632 {Uesc fullutf}
-bsCheck \U11000000 69632 {Uesc fullutf}
-bsCheck \U0010FFFF 1114111 {Uesc fullutf}
-bsCheck \U010FFFF0 1114111 {Uesc fullutf}
-bsCheck \U10FFFF00 1114111 {Uesc fullutf}
-bsCheck \UFFFFFFFF 1048575 {Uesc fullutf}
+bsCheck \U00110000 69632 fullutf
+bsCheck \U01100000 69632 fullutf
+bsCheck \U11000000 69632 fullutf
+bsCheck \U0010FFFF 1114111 fullutf
+bsCheck \U010FFFF0 1114111 fullutf
+bsCheck \U10FFFF00 1114111 fullutf
+bsCheck \UFFFFFFFF 1048575 fullutf
test utf-11.1 {Tcl_UtfToUpper} {
string toupper {}
@@ -1084,17 +1084,17 @@ test utf-11.3 {Tcl_UtfToUpper} {
string toupper \xE3gh
} \xC3GH
test utf-11.4 {Tcl_UtfToUpper} {
- string toupper \u01E3gh
-} \u01E2GH
+ string toupper วฃgh
+} วขGH
test utf-11.5 {Tcl_UtfToUpper Georgian (new in Unicode 11)} {
- string toupper \u10D0\u1C90
-} \u1C90\u1C90
-test utf-11.6 {Tcl_UtfToUpper beyond U+FFFF} {Uesc fullutf} {
- string toupper \U10428
-} \U10400
+ string toupper แƒแฒ
+} แฒแฒ
+test utf-11.6 {Tcl_UtfToUpper beyond U+FFFF} fullutf {
+ string toupper ๐จ
+} ๐€
test utf-11.7 {Tcl_UtfToUpper beyond U+FFFF} fullutf {
- string toupper \uD801\uDC28
-} \uD801\uDC00
+ string toupper ๐จ
+} ๐€
test utf-11.8 {Tcl_UtfToUpper low/high surrogate)} {
string toupper \uDC24\uD824
} \uDC24\uD824
@@ -1106,23 +1106,23 @@ test utf-12.2 {Tcl_UtfToLower} {
string tolower ABC
} abc
test utf-12.3 {Tcl_UtfToLower} {
- string tolower \xC3GH
-} \xE3gh
+ string tolower รƒGH
+} รฃgh
test utf-12.4 {Tcl_UtfToLower} {
- string tolower \u01E2GH
-} \u01E3gh
+ string tolower วขGH
+} วฃgh
test utf-12.5 {Tcl_UtfToLower Georgian (new in Unicode 11)} {
- string tolower \u10D0\u1C90
-} \u10D0\u10D0
+ string tolower แƒแฒ
+} แƒแƒ
test utf-12.6 {Tcl_UtfToLower low/high surrogate)} {
string tolower \uDC24\uD824
} \uDC24\uD824
-test utf-12.7 {Tcl_UtfToLower beyond U+FFFF} {Uesc fullutf} {
- string tolower \U10400
-} \U10428
+test utf-12.7 {Tcl_UtfToLower beyond U+FFFF} fullutf {
+ string tolower ๐€
+} ๐จ
test utf-12.8 {Tcl_UtfToLower beyond U+FFFF} fullutf {
- string tolower \uD801\uDC00
-} \uD801\uDC28
+ string tolower ๐€
+} ๐จ
test utf-13.1 {Tcl_UtfToTitle} {
string totitle {}
@@ -1131,26 +1131,26 @@ test utf-13.2 {Tcl_UtfToTitle} {
string totitle abc
} Abc
test utf-13.3 {Tcl_UtfToTitle} {
- string totitle \xE3GH
-} \xC3gh
+ string totitle รฃGH
+} รƒgh
test utf-13.4 {Tcl_UtfToTitle} {
- string totitle \u01F3AB
-} \u01F2ab
+ string totitle วณAB
+} วฒab
test utf-13.5 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
- string totitle \u10D0\u1C90
-} \u10D0\u1C90
+ string totitle แƒแฒ
+} แƒแฒ
test utf-13.6 {Tcl_UtfToTitle Georgian (new in Unicode 11)} {
- string totitle \u1C90\u10D0
-} \u1C90\u10D0
+ string totitle แฒแƒ
+} แฒแƒ
test utf-13.7 {Tcl_UtfToTitle low/high surrogate)} {
string totitle \uDC24\uD824
} \uDC24\uD824
-test utf-13.8 {Tcl_UtfToTitle beyond U+FFFF} {Uesc fullutf} {
- string totitle \U10428\U10400
-} \U10400\U10428
+test utf-13.8 {Tcl_UtfToTitle beyond U+FFFF} fullutf {
+ string totitle ๐จ๐€
+} ๐€๐จ
test utf-13.9 {Tcl_UtfToTitle beyond U+FFFF} fullutf {
- string totitle \uD801\uDC28\uD801\uDC00
-} \uD801\uDC00\uD801\uDC28
+ string totitle ๐จ๐€
+} ๐€๐จ
test utf-14.1 {Tcl_UtfNcasecmp} {
string compare -nocase a b
@@ -1169,8 +1169,8 @@ 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
+ string toupper ลธรฟ
+} ลธลธ
test utf-15.3 {Tcl_UniCharToUpper, no delta} {
string toupper !
} !
@@ -1179,25 +1179,25 @@ 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
-} \xFF\xFF\u0265\u01C6
+ string tolower ลธรฟ๊žว…
+} รฟรฟษฅว†
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 ว„
+} ว…
test utf-18.2 {Tcl_UniCharToTitle, subtract one for title} {
- string totitle \u01C6
-} \u01C5
+ string totitle ว†
+} ว…
test utf-18.3 {Tcl_UniCharToTitle, subtract delta for title (positive)} {
- string totitle \u017F
-} \x53
+ string totitle ลฟ
+} S
test utf-18.4 {Tcl_UniCharToTitle, subtract delta for title (negative)} {
- string totitle \xFF
-} \u0178
+ string totitle รฟ
+} ลธ
test utf-18.5 {Tcl_UniCharToTitle, no delta} {
string totitle !
} !
@@ -1223,23 +1223,23 @@ test utf-20.2 {[4c591fa487] TclUniCharNcmp/TclUtfNcmp} {
test utf-21.1 {TclUniCharIsAlnum} {
# this returns 1 with Unicode 7 compliance
- string is alnum \u1040\u021F\u0220
+ string is alnum แ€ศŸศ 
} 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:]]+$} แ€ศŸศ ] [regexp {^\w+$} แ€ศŸศ _โ€ฟโ€โ”๏ธณ๏ธด๏น๏นŽ๏น๏ผฟ]
} {1 1}
test utf-21.3 {unicode print char in regc_locale.c} {
# this returns 1 with Unicode 7 compliance
- regexp {^[[:print:]]+$} \uFBC1
+ regexp {^[[:print:]]+$} ๏ฏ
} 1
test utf-21.4 {TclUniCharIsGraph} {
# [Bug 3464428]
- string is graph \u0120
+ string is graph ฤ 
} 1
test utf-21.5 {unicode graph char in regc_locale.c} {
# [Bug 3464428]
- regexp {^[[:graph:]]+$} \u0120
+ regexp {^[[:graph:]]+$} ฤ 
} 1
test utf-21.6 {TclUniCharIsGraph} {
# [Bug 3464428]
@@ -1274,25 +1274,25 @@ 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 "xๅ‚€z123_barโ€ผ 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 ศŸศ อฟิฏ
} 1
test utf-23.2 {unicode alpha char in regc_locale.c} {
# this returns 1 with Unicode 7 compliance
- regexp {^[[:alpha:]]+$} \u021F\u0220\u037F\u052F
+ regexp {^[[:alpha:]]+$} ศŸศ อฟิฏ
} 1
test utf-24.1 {TclUniCharIsDigit} {
# this returns 1 with Unicode 7 compliance
- string is digit \u1040\uABF0
+ string is digit แ€๊ฏฐ
} 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:]]+$} แ€๊ฏฐ] [regexp {^\d+$} แ€๊ฏฐ]
} {1 1}
test utf-24.3 {TclUniCharIsSpace} {
@@ -1339,9 +1339,9 @@ UniCharCaseCmpTest > b a
UniCharCaseCmpTest > B a
UniCharCaseCmpTest > aBcB abca
UniCharCaseCmpTest < \uFFFF [format %c 0x10000] ucs4
-UniCharCaseCmpTest < \uFFFF \U10000 {Uesc ucs4}
+UniCharCaseCmpTest < \uFFFF \U10000 ucs4
UniCharCaseCmpTest > [format %c 0x10000] \uFFFF ucs4
-UniCharCaseCmpTest > \U10000 \uFFFF {Uesc ucs4}
+UniCharCaseCmpTest > \U10000 \uFFFF ucs4
test utf-26.1 {Tcl_UniCharDString} -setup {