diff options
| author | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-05-24 22:29:07 (GMT) |
|---|---|---|
| committer | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-05-24 22:29:07 (GMT) |
| commit | 2b1daf9bb29fdba966f86c054d96d564b7539684 (patch) | |
| tree | c4b280ca118cf116e1a091789e63044e09ba7df2 | |
| parent | 017257e0ef3f20643166931986ea36eeee97f049 (diff) | |
| download | tcl-2b1daf9bb29fdba966f86c054d96d564b7539684.zip tcl-2b1daf9bb29fdba966f86c054d96d564b7539684.tar.gz tcl-2b1daf9bb29fdba966f86c054d96d564b7539684.tar.bz2 | |
Put back "string bytelength", not _that_ important for this TIP.
Document that Tcl_UtfCharComplete() can be used now to protect Tcl_UtfNext()
| -rw-r--r-- | doc/Utf.3 | 11 | ||||
| -rw-r--r-- | generic/tclCmdMZ.c | 4 | ||||
| -rw-r--r-- | library/init.tcl | 4 |
3 files changed, 8 insertions, 11 deletions
@@ -233,10 +233,10 @@ characters. .PP \fBTcl_UtfCharComplete\fR returns 1 if the source UTF-8 string \fIsrc\fR of \fIlength\fR bytes is long enough to be decoded by -\fBTcl_UtfToUniChar\fR, or 0 otherwise. This function does not guarantee -that the UTF-8 string is properly formed. This routine is used by -procedures that are operating on a byte at a time and need to know if a -full Unicode character has been seen. +\fBTcl_UtfToUniChar\fR/\fBTcl_UtfNext\fR, or 0 otherwise. This function +does not guarantee that the UTF-8 string is properly formed. This routine +is used by procedures that are operating on a byte at a time and need to +know if a full Unicode character has been seen. .PP \fBTcl_NumUtfChars\fR corresponds to \fBstrlen\fR for UTF-8 strings. It returns the number of Tcl_UniChars that are represented by the UTF-8 string @@ -257,7 +257,8 @@ Given \fIsrc\fR, a pointer to some location in a UTF-8 string, \fBTcl_UtfNext\fR returns a pointer to the next UTF-8 character in the string. The caller must not ask for the next character after the last character in the string if the string is not terminated by a null -character. +character. \fBTcl_UtfCharComplete\fR can be used in that case to +make sure enough bytes are available before calling \fBTcl_UtfNext\fR. .PP \fBTcl_UtfPrev\fR is used to step backward through but not beyond the UTF-8 string that begins at \fIstart\fR. If the UTF-8 string is made diff --git a/generic/tclCmdMZ.c b/generic/tclCmdMZ.c index 88bf2ec..bbd03d8 100644 --- a/generic/tclCmdMZ.c +++ b/generic/tclCmdMZ.c @@ -3093,7 +3093,6 @@ StringCatCmd( * *---------------------------------------------------------------------- */ -#if !defined(TCL_NO_DEPRECATED) && TCL_MAJOR_VERSION < 9 static int StringBytesCmd( TCL_UNUSED(ClientData), @@ -3112,7 +3111,6 @@ StringBytesCmd( Tcl_SetObjResult(interp, Tcl_NewWideIntObj(length)); return TCL_OK; } -#endif /* *---------------------------------------------------------------------- @@ -3569,9 +3567,7 @@ TclInitStringCmd( Tcl_Interp *interp) /* Current interpreter. */ { static const EnsembleImplMap stringImplMap[] = { -#if !defined(TCL_NO_DEPRECATED) && TCL_MAJOR_VERSION < 9 {"bytelength", StringBytesCmd, TclCompileBasic1ArgCmd, NULL, NULL, 0}, -#endif {"cat", StringCatCmd, TclCompileStringCatCmd, NULL, NULL, 0}, {"compare", StringCmpCmd, TclCompileStringCmpCmd, NULL, NULL, 0}, {"equal", StringEqualCmd, TclCompileStringEqualCmd, NULL, NULL, 0}, diff --git a/library/init.tcl b/library/init.tcl index 8ebd29e6..4ea22d8 100644 --- a/library/init.tcl +++ b/library/init.tcl @@ -209,9 +209,9 @@ proc unknown args { set errInfo [dict get $opts -errorinfo] set errCode [dict get $opts -errorcode] set cinfo $args - if {[string length $cinfo] > 150} { + if {[string bytelength $cinfo] > 150} { set cinfo [string range $cinfo 0 150] - while {[string length $cinfo] > 150} { + while {[string bytelength $cinfo] > 150} { set cinfo [string range $cinfo 0 end-1] } append cinfo ... |