diff options
| author | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-05-01 14:20:21 (GMT) |
|---|---|---|
| committer | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-05-01 14:20:21 (GMT) |
| commit | c0381fd712c458f3b4ee476e00d0857bec4cf5cc (patch) | |
| tree | 073e28ab81f4331a3b1b9dceea126f1e278bce76 /generic/tclInt.h | |
| parent | a3d900f322a935841622ac0c8d81a45c91a16e65 (diff) | |
| parent | 9eaf82b745ac07bc55f7238813c449fc5a447cf8 (diff) | |
| download | tcl-c0381fd712c458f3b4ee476e00d0857bec4cf5cc.zip tcl-c0381fd712c458f3b4ee476e00d0857bec4cf5cc.tar.gz tcl-c0381fd712c458f3b4ee476e00d0857bec4cf5cc.tar.bz2 | |
Fix first part of [ed29806baf]: Tcl_UtfToUniChar reads more than TCL_UTF_MAX bytes.
Tcl_UtfToUniChar() now never reads more than TCL_UTF_MAX bytes any more.
Since the UtfToUtf encoder/decoder now uses TclUtfToUCS4() it doesn't join 2 surrogates as 2 x 3-byte sequences any more. Actually, it shouldn't, because such sequences are invalid UTF-8.
Therefore, added the ucs2 constraint to testcase encoding-15.4. Let's see how TIP #573 goes, this TIP should make this change official.
Other callers of Tcl_UtfToUniChar() needs to be revised for the same problem. Most callers will need to change Tcl_UtfToUniChar() -> TclUtfToUCS4() and Tcl_UtfCharComplete() -> TclUCS4Complete(), but that's not done yet.
Diffstat (limited to 'generic/tclInt.h')
| -rw-r--r-- | generic/tclInt.h | 9 |
1 files changed, 6 insertions, 3 deletions
diff --git a/generic/tclInt.h b/generic/tclInt.h index 2ff644e..9ef1065 100644 --- a/generic/tclInt.h +++ b/generic/tclInt.h @@ -3252,8 +3252,11 @@ MODULE_SCOPE int TclUtfCasecmp(const char *cs, const char *ct); MODULE_SCOPE int TclUtfCount(int ch); #if TCL_UTF_MAX > 3 # define TclUtfToUCS4 Tcl_UtfToUniChar +# define TclUCS4Complete Tcl_UtfCharComplete #else - MODULE_SCOPE int TclUtfToUCS4(const char *src, int *ucs4Ptr); + MODULE_SCOPE int TclUtfToUCS4(const char *src, int *ucs4Ptr); +# define TclUCS4Complete(src, length) (((unsigned)((unsigned char)*(src) - 0xF0) < 5) \ + ? ((length) >= 4) : Tcl_UtfCharComplete((src), (length))) #endif MODULE_SCOPE Tcl_Obj * TclpNativeToNormalized(ClientData clientData); MODULE_SCOPE Tcl_Obj * TclpFilesystemPathType(Tcl_Obj *pathPtr); @@ -4655,8 +4658,8 @@ MODULE_SCOPE const TclFileAttrProcs tclpFileAttrProcs[]; #if TCL_UTF_MAX > 3 #define TclUtfToUniChar(str, chPtr) \ - ((((unsigned char) *(str)) < 0x80) ? \ - ((*(chPtr) = (unsigned char) *(str)), 1) \ + (((UCHAR(*(str))) < 0x80) ? \ + ((*(chPtr) = UCHAR(*(str))), 1) \ : Tcl_UtfToUniChar(str, chPtr)) #else #define TclUtfToUniChar(str, chPtr) \ |