'\"
'\" Copyright (c) 2025 Ashok P. Nadkarni
'\"
'\" See the file "license.terms" for information on usage and redistribution
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
'\"
.TH Tcl_UtfToNormalized 3 "9.1" Tcl "Tcl Library Procedures"
.\" The -*- nroff -*- definitions below are for supplemental macros used
.\" in Tcl/Tk manual entries.
.\"
.\" .AP type name in/out ?indent?
.\"	Start paragraph describing an argument to a library procedure.
.\"	type is type of argument (int, etc.), in/out is either "in", "out",
.\"	or "in/out" to describe whether procedure reads or modifies arg,
.\"	and indent is equivalent to second arg of .IP (shouldn't ever be
.\"	needed;  use .AS below instead)
.\"
.\" .AS ?type? ?name?
.\"	Give maximum sizes of arguments for setting tab stops.  Type and
.\"	name are examples of largest possible arguments that will be passed
.\"	to .AP later.  If args are omitted, default tab stops are used.
.\"
.\" .BS
.\"	Start box enclosure.  From here until next .BE, everything will be
.\"	enclosed in one large box.
.\"
.\" .BE
.\"	End of box enclosure.
.\"
.\" .CS
.\"	Begin code excerpt.
.\"
.\" .CE
.\"	End code excerpt.
.\"
.\" .VS ?version? ?br?
.\"	Begin vertical sidebar, for use in marking newly-changed parts
.\"	of man pages.  The first argument is ignored and used for recording
.\"	the version when the .VS was added, so that the sidebars can be
.\"	found and removed when they reach a certain age.  If another argument
.\"	is present, then a line break is forced before starting the sidebar.
.\"
.\" .VE
.\"	End of vertical sidebar.
.\"
.\" .DS
.\"	Begin an indented unfilled display.
.\"
.\" .DE
.\"	End of indented unfilled display.
.\"
.\" .SO ?manpage?
.\"	Start of list of standard options for a Tk widget. The manpage
.\"	argument defines where to look up the standard options; if
.\"	omitted, defaults to "options". The options follow on successive
.\"	lines, in three columns separated by tabs.
.\"
.\" .SE
.\"	End of list of standard options for a Tk widget.
.\"
.\" .OP cmdName dbName dbClass
.\"	Start of description of a specific option.  cmdName gives the
.\"	option's name as specified in the class command, dbName gives
.\"	the option's name in the option database, and dbClass gives
.\"	the option's class in the option database.
.\"
.\" .UL arg1 arg2
.\"	Print arg1 underlined, then print arg2 normally.
.\"
.\" .QW arg1 ?arg2?
.\"	Print arg1 in quotes, then arg2 normally (for trailing punctuation).
.\"
.\" .PQ arg1 ?arg2?
.\"	Print an open parenthesis, arg1 in quotes, then arg2 normally
.\"	(for trailing punctuation) and then a closing parenthesis.
.\"
.\"	# Set up traps and other miscellaneous stuff for Tcl/Tk man pages.
.if t .wh -1.3i ^B
.nr ^l \n(.l
.ad b
.\"	# Start an argument description
.de AP
.ie !"\\$4"" .TP \\$4
.el \{\
.   ie !"\\$2"" .TP \\n()Cu
.   el          .TP 15
.\}
.ta \\n()Au \\n()Bu
.ie !"\\$3"" \{\
\&\\$1 \\fI\\$2\\fP (\\$3)
.\".b
.\}
.el \{\
.br
.ie !"\\$2"" \{\
\&\\$1	\\fI\\$2\\fP
.\}
.el \{\
\&\\fI\\$1\\fP
.\}
.\}
..
.\"	# define tabbing values for .AP
.de AS
.nr )A 10n
.if !"\\$1"" .nr )A \\w'\\$1'u+3n
.nr )B \\n()Au+15n
.\"
.if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n
.nr )C \\n()Bu+\\w'(in/out)'u+2n
..
.AS Tcl_Interp Tcl_CreateInterp in/out
.\"	# BS - start boxed text
.\"	# ^y = starting y location
.\"	# ^b = 1
.de BS
.br
.mk ^y
.nr ^b 1u
.if n .nf
.if n .ti 0
.if n \l'\\n(.lu\(ul'
.if n .fi
..
.\"	# BE - end boxed text (draw box now)
.de BE
.nf
.ti 0
.mk ^t
.ie n \l'\\n(^lu\(ul'
.el \{\
.\"	Draw four-sided box normally, but don't draw top of
.\"	box if the box started on an earlier page.
.ie !\\n(^b-1 \{\
\h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul'
.\}
.el \}\
\h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul'
.\}
.\}
.fi
.br
.nr ^b 0
..
.\"	# VS - start vertical sidebar
.\"	# ^Y = starting y location
.\"	# ^v = 1 (for troff;  for nroff this doesn't matter)
.de VS
.if !"\\$2"" .br
.mk ^Y
.ie n 'mc \s12\(br\s0
.el .nr ^v 1u
..
.\"	# VE - end of vertical sidebar
.de VE
.ie n 'mc
.el \{\
.ev 2
.nf
.ti 0
.mk ^t
\h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n'
.sp -1
.fi
.ev
.\}
.nr ^v 0
..
.\"	# Special macro to handle page bottom:  finish off current
.\"	# box/sidebar if in box/sidebar mode, then invoked standard
.\"	# page bottom macro.
.de ^B
.ev 2
'ti 0
'nf
.mk ^t
.if \\n(^b \{\
.\"	Draw three-sided box if this is the box's first page,
.\"	draw two sides but no top otherwise.
.ie !\\n(^b-1 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c
.el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c
.\}
.if \\n(^v \{\
.nr ^x \\n(^tu+1v-\\n(^Yu
\kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c
.\}
.bp
'fi
.ev
.if \\n(^b \{\
.mk ^y
.nr ^b 2
.\}
.if \\n(^v \{\
.mk ^Y
.\}
..
.\"	# DS - begin display
.de DS
.RS
.nf
.sp
..
.\"	# DE - end display
.de DE
.fi
.RE
.sp
..
.\"	# SO - start of list of standard options
.de SO
'ie '\\$1'' .ds So \\fBoptions\\fR
'el .ds So \\fB\\$1\\fR
.SH "STANDARD OPTIONS"
.LP
.nf
.ta 5.5c 11c
.ft B
..
.\"	# SE - end of list of standard options
.de SE
.fi
.ft R
.LP
See the \\*(So manual entry for details on the standard options.
..
.\"	# OP - start of full description for a single option
.de OP
.LP
.nf
.ta 4c
Command-Line Name:	\\fB\\$1\\fR
Database Name:	\\fB\\$2\\fR
Database Class:	\\fB\\$3\\fR
.fi
.IP
..
.\"	# CS - begin code excerpt
.de CS
.RS
.nf
.ta .25i .5i .75i 1i
..
.\"	# CE - end code excerpt
.de CE
.fi
.RE
..
.\"	# UL - underline word
.de UL
\\$1\l'|0\(ul'\\$2
..
.\"	# QW - apply quotation marks to word
.de QW
.ie '\\*(lq'"' ``\\$1''\\$2
.\"" fix emacs highlighting
.el \\*(lq\\$1\\*(rq\\$2
..
.\"	# PQ - apply parens and quotation marks to word
.de PQ
.ie '\\*(lq'"' (``\\$1''\\$2)\\$3
.\"" fix emacs highlighting
.el (\\*(lq\\$1\\*(rq\\$2)\\$3
..
.\"	# QR - quoted range
.de QR
.ie '\\*(lq'"' ``\\$1''\\-``\\$2''\\$3
.\"" fix emacs highlighting
.el \\*(lq\\$1\\*(rq\\-\\*(lq\\$2\\*(rq\\$3
..
.\"	# MT - "empty" string
.de MT
.QW ""
..
.BS
.SH NAME
Tcl_UtfToNormalized, Tcl_UtfToNormalizedDString \- procedures for Unicode normalization
.SH SYNOPSIS
.nf
\fB#include <tcl.h>\fR
.sp
int
\fBTcl_UtfToNormalized\fR(\fIinterp, src, numBytes, normForm, profile, dst, dstLen, dstWrotePtr\fR)
.sp
int
\fBTcl_UtfToNormalizedDString\fR(\fIinterp, src, numBytes, normForm, profile, dstPtr\fR)
.fi
.SH ARGUMENTS
.AP Tcl_Interp *interp in
Interpreter to use for error reporting, or NULL if no error reporting is
desired.
.AP "const char" *src in
An array of bytes in Tcl's internal UTF-8 based encoding.
.AP Tcl_Size numBytes in
Length of \fIsrc\fR in bytes.  If the length is negative,
the length includes all bytes until the first nul byte.
.AP char *dst out
Buffer in which the converted result will be stored.  No more than
\fIdstLen\fR bytes will be stored in \fIdst\fR.
.AP Tcl_Size dstLen in
The size of the output buffer \fIdst\fR in bytes.
.AP Tcl_Size *dstWrotePtr out
Filled with the number of bytes in the normalized string. This number
does not include the terminating nul character.
May be NULL.
.AP Tcl_UnicodeNormalizationForm normForm in
Must be one of the \fBTcl_UnicodeNormalizationForm\fR members
\fBTCL_NFC\fR, \fBTCL_NFD\fR, \fBTCL_NFKC\fR or \fBTCL_NFKD\fR specifying
the Unicode normalization type.
.AP int profile in/out
The encoding profile as described in the \fBTcl_GetEncoding\fR documentation.
Must be either \fBTCL_ENCODING_PROFILE_STRICT\fR
or \fBTCL_ENCODING_PROFILE_REPLACE\fR.
.AP Tcl_DString *dstPtr out
Pointer to an uninitialized or free \fBTcl_DString\fR in which the converted
result, which is also encoded in Tcl's internal UTF-8 encoding, will be stored.
The function initializes the storage and caller must call
\fBTcl_DStringFree\fR on success.
.BE
.SH DESCRIPTION
.PP
The \fBTcl_UtfToNormalized\fR and \fBTcl_UtfToNormalizedDString\fR functions
transform the passed string into one of the standard normalization forms defined
in the Unicode standard. The normalization form is specified via the
\fInormForm\fR argument which must have one of the values \fBTCL_NFC\fR,
\fBTCL_NFD\fR, \fBTCL_NFKC\fR or \fBTCL_NFKD\fR corresponding to the Unicode
normalization forms \fBNormalization Form C\fR (NFC), \fBNormalization Form D\fR
(NFD), \fBNormalization Form KC\fR (NFKC) and \fBNormalization Form KD\fR (NFKD)
respectively. For details on the above normalization forms, refer to Section
3.11 of the Unicode standard
(https://www.unicode.org/versions/Unicode16.0.0/core-spec/chapter-3/).
.PP
The \fBTcl_UtfToNormalized\fR function stores the normalized result
in the buffer provided by the caller through the \fIdst\fR argument. The
result is nul terminated but the nul is not included in the count of
stored bytes returned in \fIdstWrotePtr\fR. The function returns \fBTCL_OK\fR
on success, TCL_CONVERT_NOSPACE if there is insufficient room in the output
buffer and TCL_ERROR in case of other failures. In the latter two cases,
an error message is stored in \fIinterp\fR if it is not NULL.
.PP
The \fBTcl_UtfToNormalizedDString\fR function stores the normalized result
in \fIdstPtr\fR which must eventually be freed by caller through
\fBTcl_DStringFree\fR. The function returns \fBTCL_OK\fR on success and
TCL_ERROR on failure with an error message in \fIinterp\fR if it is not NULL.
.SH "SEE ALSO"
unicode(n)
.SH KEYWORDS
utf, Unicode, normalize