Merge 8.7. Documentation improvements and code cleanup. Approaching finish.

2 files changed, 25 insertions, 9 deletions

diff --git a/doc/Encoding.3 b/doc/Encoding.3
index a642281..2d2461e 100644
--- a/doc/Encoding.3
+++ b/doc/Encoding.3
@@ -264,8 +264,8 @@ If you want compatibility with earlier Tcl releases than 8.7, use
 \fBTcl_UtfToUniCharDString\fR resp. \fBTcl_UniCharToUtfDString\fR as
 replacement, and make sure you compile your extension with -DTCL_UTF_MAX=3.
 Beware: Those replacement functions don't initialize their Tcl_DString (you'll
-have to do that yourself), and \fBTcl_UniCharToUtfDString\fR doesn't accept -1
-as length parameter (but \fBTcl_WCharToUtfDString\fR does!).
+have to do that yourself), and \fBTcl_UniCharToUtfDString\fR from Tcl 8.6
+doesn't accept -1 as length parameter.
 .PP
 \fBTcl_GetEncodingName\fR is roughly the inverse of \fBTcl_GetEncoding\fR.
 Given an \fIencoding\fR, the return value is the \fIname\fR argument that
diff --git a/doc/Utf.3 b/doc/Utf.3
index 4879e79..b70bb01 100644
--- a/doc/Utf.3
+++ b/doc/Utf.3
@@ -8,7 +8,7 @@
 .so man.macros
 .BS
 .SH NAME
-Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_WCharToUtfDString, Tcl_UtfToWCharDString, Tcl_UniCharLen, Tcl_UniCharNcmp, Tcl_UniCharNcasecmp, Tcl_UniCharCaseMatch, Tcl_UtfNcmp, Tcl_UtfNcasecmp, Tcl_UtfCharComplete, Tcl_NumUtfChars, Tcl_UtfFindFirst, Tcl_UtfFindLast, Tcl_UtfNext, Tcl_UtfPrev, Tcl_UniCharAtIndex, Tcl_UtfAtIndex, Tcl_UtfBackslash \- routines for manipulating UTF-8 strings
+Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UtfToChar16, Tcl_UtfToWChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_WCharToUtfDString, Tcl_UtfToWCharDString, Tcl_Char16ToUtfDString, Tcl_UtfToChar16DString, Tcl_UniCharLen, Tcl_UniCharNcmp, Tcl_UniCharNcasecmp, Tcl_UniCharCaseMatch, Tcl_UtfNcmp, Tcl_UtfNcasecmp, Tcl_UtfCharComplete, Tcl_NumUtfChars, Tcl_UtfFindFirst, Tcl_UtfFindLast, Tcl_UtfNext, Tcl_UtfPrev, Tcl_UniCharAtIndex, Tcl_UtfAtIndex, Tcl_UtfBackslash \- routines for manipulating UTF-8 strings
 .SH SYNOPSIS
 .nf
 \fB#include <tcl.h>\fR
@@ -21,16 +21,28 @@ int
 int
 \fBTcl_UtfToUniChar\fR(\fIsrc, chPtr\fR)
 .sp
+int
+\fBTcl_UtfToChar16\fR(\fIsrc, uPtr\fR)
+.sp
+int
+\fBTcl_UtfToWChar\fR(\fIsrc, wPtr\fR)
+.sp
 char *
 \fBTcl_UniCharToUtfDString\fR(\fIuniStr, uniLength, dsPtr\fR)
 .sp
 char *
-\fBTcl_WCharToUtfDString\fR(\fIutf16Str, uniLength, dsPtr\fR)
+\fBTcl_Char16ToUtfDString\fR(\fIuStr, uniLength, dsPtr\fR)
+.sp
+char *
+\fBTcl_WCharToUtfDString\fR(\fIwStr, uniLength, dsPtr\fR)
 .sp
 Tcl_UniChar *
 \fBTcl_UtfToUniCharDString\fR(\fIsrc, length, dsPtr\fR)
 .sp
 unsigned short *
+\fBTcl_UtfToChar16DString\fR(\fIsrc, length, dsPtr\fR)
+.sp
+wchar_t *
 \fBTcl_UtfToWCharDString\fR(\fIsrc, length, dsPtr\fR)
 .sp
 int
@@ -86,8 +98,10 @@ Buffer in which the UTF-8 representation of the Tcl_UniChar is stored.  At most
 The Unicode character to be converted or examined.
 .AP Tcl_UniChar *chPtr out
 Filled with the Tcl_UniChar represented by the head of the UTF-8 string.
-.AP unsigned short *utf16Ptr out
+.AP unsigned short *uPtr out
 Filled with the utf-16 represented by the head of the UTF-8 string.
+.AP wchar_t *wPtr out
+Filled with the wchar_t represented by the head of the UTF-8 string.
 .AP "const char" *src in
 Pointer to a UTF-8 string.
 .AP "const char" *cs in
@@ -102,8 +116,10 @@ A null-terminated Unicode string.
 A null-terminated Unicode string.
 .AP "const Tcl_UniChar" *uniPattern in
 A null-terminated Unicode string.
-.AP "const unsigned short" *utf16Str in
-A null-terminated utf-16 string.
+.AP "const unsigned short" *uStr in
+A null-terminated UTF-16 string.
+.AP "const wchar_t" *wStr in
+A null-terminated wchar_t string.
 .AP int length in
 The length of the UTF-8 string in bytes (not UTF-8 characters).  If
 negative, all bytes up to the first null byte are used.
@@ -122,7 +138,7 @@ If non-NULL, filled with the number of bytes in the backslash sequence,
 including the backslash character.
 .AP char *dst out
 Buffer in which the bytes represented by the backslash sequence are stored.
-At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer.
+At most 4 bytes are stored in the buffer.
 .AP int nocase in
 Specifies whether the match should be done case-sensitive (0) or
 case-insensitive (1).
@@ -260,7 +276,7 @@ the return pointer points to the first character in the source string.
 \fBTcl_UtfBackslash\fR is a utility procedure used by several of the Tcl
 commands.  It parses a backslash sequence and stores the properly formed
 UTF-8 character represented by the backslash sequence in the output
-buffer \fIdst\fR.  At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer.
+buffer \fIdst\fR.  At most 4 bytes are stored in the buffer.
 \fBTcl_UtfBackslash\fR modifies \fI*readPtr\fR to contain the number
 of bytes in the backslash sequence, including the backslash character.
 The return value is the number of bytes stored in the output buffer.