Starting with Unicode 6.3, the mongolian vowel separator (U+180e) is no longer a whitespace, but for Tcl it still is.

"NEL/Next Line" (U+0085) should have been a Unicode whitespace, but never was in Tcl. This is corrected in Tcl 8.6, but for legacy reasons not in Tcl 8.5.
Update documentation accordingly, and extend test-cases for Unicode 7 compliance.

3 files changed, 19 insertions, 18 deletions

diff --git a/doc/string.n b/doc/string.n
index f39d57c..7e427ab 100644
--- a/doc/string.n
+++ b/doc/string.n
@@ -161,7 +161,8 @@ Any Unicode printing character, including space.
 .IP \fBpunct\fR 12
 Any Unicode punctuation character.
 .IP \fBspace\fR 12
-Any Unicode space character.
+Any Unicode whitespace character or mongolian vowel separator (U+180e),
+but not NEL/Next Line (U+0085).
 .IP \fBtrue\fR 12
 Any of the forms allowed to \fBTcl_GetBoolean\fR where the value is
 true.
diff --git a/generic/regc_locale.c b/generic/regc_locale.c
index 8dba520..e056078 100644
--- a/generic/regc_locale.c
+++ b/generic/regc_locale.c
@@ -381,8 +381,8 @@ static const crange spaceRangeTable[] = {
 #define NUM_SPACE_RANGE (sizeof(spaceRangeTable)/sizeof(crange))
 
 static const chr spaceCharTable[] = {
-    0x20, 0xa0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f, 0x2060,
-    0x3000, 0xfeff
+    0x20, 0xa0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f,
+    0x3000
 };
 
 #define NUM_SPACE_CHAR (sizeof(spaceCharTable)/sizeof(chr))
diff --git a/tests/utf.test b/tests/utf.test
index 35c5f73..30200c1 100644
--- a/tests/utf.test
+++ b/tests/utf.test
@@ -278,15 +278,15 @@ test utf-20.1 {TclUniCharNcmp} {
 } {}
 
 test utf-21.1 {TclUniCharIsAlnum} {
-    # this returns 1 with Unicode 6 compliance
+    # 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 6 compliance
+    # this returns 1 with Unicode 7 compliance
     list [regexp {^[[:alnum:]]+$} \u1040\u021f\u0220] [regexp {^\w+$} \u1040\u021f\u0220]
 } {1 1}
 test utf-21.3 {unicode print char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
+    # this returns 1 with Unicode 7 compliance
     regexp {^[[:print:]]+$} \ufbc1
 } 1
 test utf-21.4 {TclUniCharIsGraph} {
@@ -319,11 +319,11 @@ test utf-21.10 {unicode print char in regc_locale.c} {
 } {0}
 test utf-21.11 {TclUniCharIsControl} {
     # [Bug 3464428]
-    string is control \u00ad
+    string is control \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
 } {1}
 test utf-21.12 {unicode control char in regc_locale.c} {
     # [Bug 3464428], [Bug a876646efe]
-    regexp {^[[:cntrl:]]*$} \u0000\u001f\u00ad
+    regexp {^[[:cntrl:]]*$} \u0000\u001f\u00ad\u0605\u061c\u180e\u2066\ufeff
 } {1}
 
 test utf-22.1 {TclUniCharIsWordChar} {
@@ -334,30 +334,30 @@ test utf-22.2 {TclUniCharIsWordChar} {
 } 10
 
 test utf-23.1 {TclUniCharIsAlpha} {
-    # this returns 1 with Unicode 6 compliance
-    string is alpha \u021f\u0220
+    # 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 6 compliance
-    regexp {^[[:alpha:]]+$} \u021f\u0220
+    # this returns 1 with Unicode 7 compliance
+    regexp {^[[:alpha:]]+$} \u021f\u0220\u037f\u052f
 } {1}
 
 test utf-24.1 {TclUniCharIsDigit} {
-    # this returns 1 with Unicode 6 compliance
+    # 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 6 compliance
+    # 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 6 compliance
-    string is space \u1680\u180e
+    # this returns 1 with Unicode 7 compliance
+    string is space \u1680\u180e\u202f
 } {1}
 test utf-24.4 {unicode space char in regc_locale.c} {
-    # this returns 1 with Unicode 6 compliance
-    list [regexp {^[[:space:]]+$} \u1680\u180e] [regexp {^\s+$} \u1680\u180e]
+    # this returns 1 with Unicode 7 compliance
+    list [regexp {^[[:space:]]+$} \u1680\u180e\u202f] [regexp {^\s+$} \u1680\u180e\u202f]
 } {1 1}
 
 testConstraint teststringobj [llength [info commands teststringobj]]