path: root/doc/Utf.3

'\"
'\" Copyright (c) 1997 Sun Microsystems, Inc.
'\"
'\" See the file "license.terms" for information on usage and redistribution
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
'\"
.TH Utf 3 "8.1" Tcl "Tcl Library Procedures"
.so man.macros
.BS
.SH NAME
Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UtfToChar16, Tcl_UtfToWChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_Char16ToUtfDString, Tcl_UtfToWCharDString, Tcl_UtfToChar16DString, Tcl_WCharToUtfDString, Tcl_WCharLen, Tcl_Char16Len, 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 TUTF-8 encoded byte sequences
.SH SYNOPSIS
.nf
\fB#include <tcl.h>\fR
.sp
typedef ... \fBTcl_UniChar\fR;
.sp
Tcl_Size
\fBTcl_UniCharToUtf\fR(\fIch, buf\fR)
.sp
Tcl_Size
\fBTcl_UtfToUniChar\fR(\fIsrc, chPtr\fR)
.sp
Tcl_Size
\fBTcl_UtfToChar16\fR(\fIsrc, uPtr\fR)
.sp
Tcl_Size
\fBTcl_UtfToWChar\fR(\fIsrc, wPtr\fR)
.sp
char *
\fBTcl_UniCharToUtfDString\fR(\fIuniStr, numUniChars, dsPtr\fR)
.sp
char *
\fBTcl_Char16ToUtfDString\fR(\fIutf16, numUtf16, dsPtr\fR)
.sp
char *
\fBTcl_WCharToUtfDString\fR(\fIwcharStr, numWChars, dsPtr\fR)
.sp
Tcl_UniChar *
\fBTcl_UtfToUniCharDString\fR(\fIsrc, numBytes, dsPtr\fR)
.sp
unsigned short *
\fBTcl_UtfToChar16DString\fR(\fIsrc, numBytes, dsPtr\fR)
.sp
wchar_t *
\fBTcl_UtfToWCharDString\fR(\fIsrc, numBytes, dsPtr\fR)
.sp
Tcl_Size
\fBTcl_Char16Len\fR(\fIutf16\fR)
.sp
Tcl_Size
\fBTcl_WCharLen\fR(\fIwcharStr\fR)
.sp
Tcl_Size
\fBTcl_UniCharLen\fR(\fIuniStr\fR)
.sp
int
\fBTcl_UniCharNcmp\fR(\fIucs, uct, uniLength\fR)
.sp
int
\fBTcl_UniCharNcasecmp\fR(\fIucs, uct, uniLength\fR)
.sp
int
\fBTcl_UniCharCaseMatch\fR(\fIuniStr, uniPattern, nocase\fR)
.sp
int
\fBTcl_UtfNcmp\fR(\fIcs, ct, length\fR)
.sp
int
\fBTcl_UtfNcasecmp\fR(\fIcs, ct, length\fR)
.sp
int
\fBTcl_UtfCharComplete\fR(\fIsrc, numBytes\fR)
.sp
Tcl_Size
\fBTcl_NumUtfChars\fR(\fIsrc, numBytes\fR)
.sp
const char *
\fBTcl_UtfFindFirst\fR(\fIsrc, ch\fR)
.sp
const char *
\fBTcl_UtfFindLast\fR(\fIsrc, ch\fR)
.sp
const char *
\fBTcl_UtfNext\fR(\fIsrc\fR)
.sp
const char *
\fBTcl_UtfPrev\fR(\fIsrc, start\fR)
.sp
int
\fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR)
.sp
const char *
\fBTcl_UtfAtIndex\fR(\fIsrc, index\fR)
.sp
Tcl_Size
\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR)
.fi
.SH ARGUMENTS
.AS "const Tcl_UniChar" *uniPattern in/out
.AP char *buf out
Buffer in which the TUTF-8 representation of the Tcl_UniChar is stored.  At most
\fBTCL_UTF_MAX\fR bytes are stored in the buffer.
.AP int ch in
The Unicode character to be converted or examined.
.AP Tcl_UniChar *chPtr out
Filled with the Tcl_UniChar represented by the head of the TUTF-8 byte sequence.
.AP unsigned short *uPtr out
Filled with the utf-16 represented by the head of the TUTF-8 byte sequence.
.AP wchar_t *wPtr out
Filled with the wchar_t represented by the head of the TUTF-8 byte sequence.
.AP "const char" *src in
Pointer to a TUTF-8 byte sequence.
.AP "const char" *cs in
Pointer to a TUTF-8 byte sequence.
.AP "const char" *ct in
Pointer to a TUTF-8 byte sequence.
.AP "const Tcl_UniChar" *uniStr in
A sequence of \fBTcl_UniChar\fR units with null-termination optional
depending on function.
.AP "const Tcl_UniChar" *ucs in
A null-terminated sequence of \fBTcl_UniChar\fR.
.AP "const Tcl_UniChar" *uct in
A null-terminated sequence of \fBTcl_UniChar\fR.
.AP "const Tcl_UniChar" *uniPattern in
A null-terminated sequence of \fBTcl_UniChar\fR.
.AP "const unsigned short" *utf16 in
A sequence of UTF-16 units with null-termination optional
depending on function.
.AP "const wchar_t" *wcharStr in
A sequence of \fBwchar_t\fR units with null-termination optional
depending on function.
.AP Tcl_Size numBytes in
The length of the TUTF-8 input in bytes.  If
negative, the length includes all bytes until the first null byte.
.AP Tcl_Size numUtf16 in
The length of the input in UTF-16 units.
If negative, the length includes all bytes until the first null.
.AP Tcl_Size numUniChars in
The length of the input in Tcl_UniChar units.
If negative, the length includes all bytes until the first null.
.AP Tcl_Size numWChars in
The length of the input in wchar_t units.
If negative, the length includes all bytes until the first null.
.AP "Tcl_DString" *dsPtr in/out
A pointer to a previously initialized \fBTcl_DString\fR.
.AP "const char" *start in
Pointer to the beginning of a TUTF-8 byte sequence.
.AP Tcl_Size index in
The index of a character (not byte) in the TUTF-8 byte sequence.
.AP int *readPtr out
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.
.AP int nocase in
Specifies whether the match should be done case-sensitive (0) or
case-insensitive (1).
.BE

.SH DESCRIPTION
.PP
N.B. The use of the term \fITUTF-8\fR in this documentation refers to the
modified UTF-8 encoding used internally by Tcl. This differs from the UTF-8
encoding defined in the Unicode standard with respect to the encoding of the NUL
character U+0000 which Tcl encodes internally as the byte sequence 0xC0 0x80 and
not a single 0x00 byte as per the standard. The term \fITUTF-8 byte sequence\fR
refers to a byte sequence representing one or more Unicode code points encoded
in TUTF-8. The term \fIcharacter\fR refers to a Unicode code
point and is used interchangeably with it.
.PP
The routines described here convert between TUTF-8 encoded byte sequences and
other representation forms.
.PP
The \fBTcl_UniChar\fR type is an C integer type wide enough to hold a single
Unicode code point value. A TUTF-8 byte sequence encoding a single code point may
have a maximum length of 4 bytes, defined as the C preprocessor symbol
\fBTCL_UTF_MAX\fR. This is also the maximum number of bytes that
\fBTcl_UtfToUniChar\fR can consume in a single call.
.PP
\fBTcl_UniCharToUtf\fR encodes the character \fIch\fR as a TUTF-8 byte sequence,
storing it starting at \fIbuf\fR.  The return value is the number of bytes stored
in \fIbuf\fR. The character \fIch\fR can be or'ed with the value TCL_COMBINE
to enable special behavior, compatible with Tcl 8.x. Then, if ch is a high
surrogate (range U+D800 - U+DBFF), the return value will be 1 and a single
byte in the range 0xF0 - 0xF4 will be stored. If \fIch\fR is a low surrogate
(range U+DC00 - U+DFFF), an attempt is made to combine the result with
the earlier produced bytes, resulting in a 4-byte TUTF-8 byte sequence.
.PP
\fBTcl_UtfToUniChar\fR reads a TUTF-8 byte sequence
starting at \fIsrc\fR and encoding a single code point,
and stores it as a Tcl_UniChar in \fI*chPtr\fR.  The return value is the
number of bytes read from \fIsrc\fR.  The caller must ensure that the
source buffer is long enough such that this routine does not run off the
end and dereference non-existent or random memory; if the source buffer
is known to be null-terminated, this will not happen.  If the input starts
with a byte in the range 0x80 - 0x9F, \fBTcl_UtfToUniChar\fR assumes the
cp1252 encoding, stores the corresponding Tcl_UniChar in \fI*chPtr\fR
and returns 1. If the input is otherwise
not in proper TUTF-8 format, \fBTcl_UtfToUniChar\fR will store the first
byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x00A0 and
0x00FF and return 1.
.PP
\fBTcl_UniCharToUtfDString\fR converts the input in the form of a
sequence of \fBTcl_UniChar\fR code points to TUTF-8, appending the result to the
previously initialized output \fBTcl_DString\fR. The return value is a pointer
to the TUTF-8 encoded representation of the \fBappended\fR string.
.PP
\fBTcl_UtfToUniCharDString\fR converts the input in the form of
a TUTF-8 byte sequence to a \fBTcl_UniChar\fR sequence
appending the result in the previously initialized \fBTcl_DString\fR.
The return value is a pointer to the appended result which is also
terminated with a \fBTcl_UniChar\fR NUL character.
.PP
\fBTcl_WCharToUtfDString\fR and \fBTcl_UtfToWCharDString\fR are similar to
\fBTcl_UniCharToUtfDString\fR and \fBTcl_UtfToUniCharDString\fR except they
operate on sequences of \fBwchar_t\fR instead of \fBTcl_UniChar\fR.
.PP
\fBTcl_Char16ToUtfDString\fR and \fBTcl_UtfToChar16DString\fR are similar to
\fBTcl_UniCharToUtfDString\fR and \fBTcl_UtfToUniCharDString\fR except they
operate on sequences of \fBUTF-16\fR units instead of \fBTcl_UniChar\fR.
.PP
\fBTcl_Char16Len\fR corresponds to \fBstrlen\fR for UTF-16
characters.  It accepts a null-terminated UTF-16 sequence and returns
the number of UTF-16 units until the null.
.PP
\fBTcl_WCharLen\fR corresponds to \fBstrlen\fR for \fBwchar_t\fR
characters.  It accepts a null-terminated \fBwchar_t\fR sequence and returns
the number of \fBwchar_t\fR units until the null.
.PP
\fBTcl_UniCharLen\fR corresponds to \fBstrlen\fR for Tcl_UniChar
characters.  It accepts a null-terminated Tcl_UniChar string and returns
the number of Tcl_UniChar's (not bytes) in that string.
.PP
\fBTcl_UniCharNcmp\fR and \fBTcl_UniCharNcasecmp\fR correspond to \fBstrncmp\fR
and \fBstrncasecmp\fR, respectively, for Tcl_UniChar code points. They accept
two null-terminated Tcl_UniChar strings and the number of Tcl_UniChar code
points to compare. Both strings are assumed to be at least \fIuniLength\fR
characters long. \fBTcl_UniCharNcmp\fR compares the code points in two strings
in order according to the Unicode character ordering. It returns an integer
greater than, equal to, or less than 0 if the first string is greater than,
equal to, or less than the second string respectively. \fBTcl_UniCharNcasecmp\fR
is the case insensitive variant of \fBTcl_UniCharNcmp\fR.
.PP
\fBTcl_UniCharCaseMatch\fR is the Unicode equivalent to
\fBTcl_StringCaseMatch\fR.  It accepts a null-terminated Tcl_UniChar string,
a Tcl_UniChar pattern, a boolean value specifying whether the match should
be case sensitive and returns whether the string matches the pattern.
.PP
\fBTcl_UtfNcmp\fR corresponds to \fBstrncmp\fR and accepts two null-terminated
TUTF-8 encoded strings each of which should represent a sequence of at least
\fIlength\fR code points. \fBTcl_UtfNcmp\fR compares the code points represented
by each of the encoded strings in order.
It returns an integer greater than, equal to, or less than 0 if the
first string is greater than, equal to, or less than the second string
respectively.
.PP
\fBTcl_UtfNcasecmp\fR corresponds to \fBstrncasecmp\fR for TUTF-8 encoded
strings.  It is similar to \fBTcl_UtfNcmp\fR except comparisons ignore
differences in case when comparing upper, lower or title case
characters.
.PP
\fBTcl_UtfCharComplete\fR returns 1 if the source TUTF-8 byte sequence \fIsrc\fR
of \fInumBytes\fR bytes is long enough to be decoded by
\fBTcl_UtfToUniChar\fR/\fBTcl_UtfNext\fR, or 0 otherwise.  This function
does not guarantee that the TUTF-8 byte sequence 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 TUTF-8 byte sequences. It
returns the number of Tcl_UniChars that are represented by the TUTF-8 byte
sequence \fIsrc\fR. The length of the source string is \fIlength\fR bytes. If
the length is negative, all bytes up to the first null byte are used.
.PP
\fBTcl_UtfFindFirst\fR corresponds to \fBstrchr\fR for TUTF-8 byte sequences.
It returns a pointer to the first occurrence of the Unicode character \fIch\fR
in the null-terminated TUTF-8 byte sequence \fIsrc\fR. The null terminator is
considered part of the byte sequence.
.PP
\fBTcl_UtfFindLast\fR corresponds to \fBstrrchr\fR for TUTF-8 byte sequences.
It returns a pointer to the last occurrence of the Unicode character \fIch\fR
in the null-terminated TUTF-8 byte sequence \fIsrc\fR. The null terminator is
considered part of the byte sequence.
.PP
Given \fIsrc\fR, a pointer to some location in a TUTF-8 byte sequence,
\fBTcl_UtfNext\fR returns a pointer to the start of the TUTF-8 byte sequence
corresponding to the next character
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. \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 TUTF-8
byte sequence that begins at \fIstart\fR. If the byte sequence is made
up entirely of complete and well-formed characters, and \fIsrc\fR points to
the lead byte of one of those characters (or to the location one byte past the
end of the string), then repeated calls of \fBTcl_UtfPrev\fR will return
pointers to the lead bytes of each character in the string, one character at a
time, terminating when it returns \fIstart\fR.
.PP
When the conditions of completeness and well-formedness may not be satisfied,
a more precise description of the function of \fBTcl_UtfPrev\fR is necessary.
It always returns a pointer greater than or equal to \fIstart\fR; that is,
always a pointer to a location in the string. It always returns a pointer to
a byte that begins a character when scanning for characters beginning
from \fIstart\fR. When \fIsrc\fR is greater than \fIstart\fR, it
always returns a pointer less than \fIsrc\fR and greater than or
equal to (\fIsrc\fR - 4).  The character that begins
at the returned pointer is the first one that either includes the
byte \fIsrc[-1]\fR, or might include it if the right trail bytes are
present at \fIsrc\fR and greater. \fBTcl_UtfPrev\fR never reads the
byte \fIsrc[0]\fR nor the byte \fIstart[-1]\fR nor the byte
\fIsrc[-5]\fR.
.PP
\fBTcl_UniCharAtIndex\fR corresponds to a C string array dereference or the
Pascal Ord() function.  It returns the Unicode code point represented at the
specified character (not byte) \fIindex\fR in the TUTF-8 byte sequence
\fIsrc\fR.  The source string must contain at least \fIindex\fR
characters.  If \fIindex\fR is negative it returns -1.
.PP
\fBTcl_UtfAtIndex\fR returns a pointer to the specified character (not
byte) \fIindex\fR in the TUTF-8 byte sequence \fIsrc\fR.  The source must
contain at least \fIindex\fR characters.  This is equivalent to calling
\fBTcl_UtfToUniChar\fR \fIindex\fR times.  If \fIindex\fR is negative,
the return pointer points to the first character in the source.
.PP
\fBTcl_UtfBackslash\fR is a utility procedure used by several of the Tcl
commands.  It parses a backslash sequence and stores the properly formed
TUTF-8 encoding of the character represented by the backslash sequence in the output
buffer \fIdst\fR.  At most \fBTCL_UTF_MAX\fR 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.
See the \fBTcl\fR manual entry for information on the valid backslash
sequences.  All of the sequences described in the Tcl manual entry are
supported by \fBTcl_UtfBackslash\fR.

.SH KEYWORDS
utf, unicode, backslash