diff options
| -rw-r--r-- | generic/tclCmdMZ.c | 23 | ||||
| -rw-r--r-- | tests/split.test | 3 |
2 files changed, 23 insertions, 3 deletions
diff --git a/generic/tclCmdMZ.c b/generic/tclCmdMZ.c index 2195aa1..ad1dd5f 100644 --- a/generic/tclCmdMZ.c +++ b/generic/tclCmdMZ.c @@ -309,7 +309,7 @@ Tcl_RegexpObjCmd( eflags = 0; } else if (offset > stringLength) { eflags = TCL_REG_NOTBOL; - } else if (Tcl_GetUniChar(objPtr, offset-1) == (Tcl_UniChar)'\n') { + } else if (Tcl_GetUniChar(objPtr, offset-1) == '\n') { eflags = 0; } else { eflags = TCL_REG_NOTBOL; @@ -1216,13 +1216,22 @@ Tcl_SplitObjCmd( Tcl_InitHashTable(&charReuseTable, TCL_ONE_WORD_KEYS); for ( ; stringPtr < end; stringPtr += len) { + int fullchar; len = TclUtfToUniChar(stringPtr, &ch); + fullchar = ch; + +#if TCL_UTF_MAX == 4 + if (!len) { + len += TclUtfToUniChar(stringPtr, &ch); + fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000; + } +#endif /* * Assume Tcl_UniChar is an integral type... */ - hPtr = Tcl_CreateHashEntry(&charReuseTable, INT2PTR((int) ch), + hPtr = Tcl_CreateHashEntry(&charReuseTable, INT2PTR(fullchar), &isNew); if (isNew) { TclNewStringObj(objPtr, stringPtr, len); @@ -1814,8 +1823,16 @@ StringIsCmd( } end = string1 + length1; for (; string1 < end; string1 += length2, failat++) { + int fullchar; length2 = TclUtfToUniChar(string1, &ch); - if (!chcomp(ch)) { + fullchar = ch; +#if TCL_UTF_MAX == 4 + if (!length2) { + length2 = TclUtfToUniChar(string1, &ch); + fullchar = (((fullchar & 0x3ff) << 10) | (ch & 0x3ff)) + 0x10000; + } +#endif + if (!chcomp(fullchar)) { result = 0; break; } diff --git a/tests/split.test b/tests/split.test index 585fef5..2d180e0 100644 --- a/tests/split.test +++ b/tests/split.test @@ -70,6 +70,9 @@ test split-1.13 {basic split commands} { test split-1.14 {basic split commands} { split ",12,,,34,56," {,} } {{} 12 {} {} 34 56 {}} +test split-1.15 {basic split commands} -body { + split "a\U01f4a9b" {} +} -result "a \U01f4a9 b" test split-2.1 {split errors} { list [catch split msg] $msg $errorCode |