Initial commit of OpenSPARC T2 architecture model.

[OpenSPARC-T2-SAM] / sam-t2 / devtools / v8plus / man / man3 / Tcl_UtfFindFirst.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.
'\" 
'\" RCS: @(#) $Id: Utf.3,v 1.13.2.2 2003/07/18 22:15:45 dkf Exp $
'\" 
'\" The 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
'\"	Start of list of standard options for a Tk widget.  The
'\"	options follow on successive lines, in four 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.
'\"
'\" RCS: @(#) $Id: man.macros,v 1.4 2000/08/25 06:18:32 ericm Exp $
'\"
'\"	# 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
.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 \\fBoptions\\fR 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
..
.de UL
\\$1\l'|0\(ul'\\$2
..
.TH Utf 3 "8.1" Tcl "Tcl Library Procedures"
.BS
.SH NAME
Tcl_UniChar, Tcl_UniCharCaseMatch, Tcl_UniCharNcasecmp, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_UniCharLen, Tcl_UniCharNcmp, 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
.sp
typedef ... Tcl_UniChar;
.sp
int
\fBTcl_UniCharToUtf\fR(\fIch, buf\fR)
.sp
int
\fBTcl_UtfToUniChar\fR(\fIsrc, chPtr\fR)
.VS 8.4
.sp
char *
\fBTcl_UniCharToUtfDString\fR(\fIuniStr, numChars, dstPtr\fR)
.sp
Tcl_UniChar *
\fBTcl_UtfToUniCharDString\fR(\fIsrc, len, dstPtr\fR)
.VE 8.4
.sp
int
\fBTcl_UniCharLen\fR(\fIuniStr\fR)
.sp
int
\fBTcl_UniCharNcmp\fR(\fIuniStr, uniStr, num\fR)
.VS 8.4
.sp
int
\fBTcl_UniCharNcasecmp\fR(\fIuniStr, uniStr, num\fR)
.sp
int
\fBTcl_UniCharCaseMatch\fR(\fIuniStr, uniPattern, nocase\fR)
.VE 8.4
.sp
int
\fBTcl_UtfNcmp\fR(\fIsrc, src, num\fR)
.sp
int
\fBTcl_UtfNcasecmp\fR(\fIsrc, src, num\fR)
.sp
int
\fBTcl_UtfCharComplete\fR(\fIsrc, len\fR)
.sp
int 
\fBTcl_NumUtfChars\fR(\fIsrc, len\fR)
.VS 8.4
.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)
.VE 8.4
.sp
Tcl_UniChar
\fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR)
.VS 8.4
.sp
CONST char *
\fBTcl_UtfAtIndex\fR(\fIsrc, index\fR)
.VE 8.4
.sp
int
\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR)
.SH ARGUMENTS
.AS "CONST Tcl_UniChar" numChars in/out
.AP char *buf out
Buffer in which the UTF-8 representation of the Tcl_UniChar is stored.  At most
TCL_UTF_MAX bytes are stored in the buffer.
.AP int ch in
The Tcl_UniChar 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 "CONST char" *src in
Pointer to a UTF-8 string.
.AP "CONST Tcl_UniChar" *uniStr in
A null-terminated Unicode string.
.AP "CONST Tcl_UniChar" *uniPattern in
A null-terminated Unicode string.
.AP int len 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.
.AP int numChars in
The length of the Unicode string in characters.  Must be greater than or
equal to 0.
.AP "Tcl_DString" *dstPtr in/out
A pointer to a previously-initialized \fBTcl_DString\fR.
.AP "unsigned long" num in
The number of characters to compare.
.AP "CONST char" *start in
Pointer to the beginning of a UTF-8 string.
.AP int index in
The index of a character (not byte) in the UTF-8 string.
.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 TCL_UTF_MAX bytes are stored in the buffer.
.VS 8.4
.AP int nocase in
Specifies whether the match should be done case-sensitive (0) or
case-insensitive (1).
.VE 8.4
.BE

.SH DESCRIPTION
.PP
These routines convert between UTF-8 strings and Tcl_UniChars.  A
Tcl_UniChar is a Unicode character represented as an unsigned, fixed-size
quantity.  A UTF-8 character is a Unicode character represented as
a varying-length sequence of up to TCL_UTF_MAX bytes.  A multibyte UTF-8
sequence consists of a lead byte followed by some number of trail bytes.
.PP
\fBTCL_UTF_MAX\fR is the maximum number of bytes that it takes to
represent one Unicode character in the UTF-8 representation.
.PP
\fBTcl_UniCharToUtf\fR stores the Tcl_UniChar \fIch\fR as a UTF-8 string
in starting at \fIbuf\fR.  The return value is the number of bytes stored
in \fIbuf\fR.
.PP
\fBTcl_UtfToUniChar\fR reads one UTF-8 character starting at \fIsrc\fR
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 is
not in proper UTF-8 format, \fBTcl_UtfToUniChar\fR will store the first
byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x0000 and
0x00ff and return 1.  
.PP
\fBTcl_UniCharToUtfDString\fR converts the given Unicode string
to UTF-8, storing the result in a previously-initialized \fBTcl_DString\fR.
You must specify the length of the given Unicode string.
The return value is a pointer to the UTF-8 representation of the
Unicode string.  Storage for the return value is appended to the
end of the \fBTcl_DString\fR.
.PP
\fBTcl_UtfToUniCharDString\fR converts the given UTF-8 string to Unicode,
storing the result in the previously-initialized \fBTcl_DString\fR.
you may either specify the length of the given UTF-8 string or "-1",
in which case \fBTcl_UtfToUniCharDString\fR uses \fBstrlen\fR to
calculate the length.  The return value is a pointer to the Unicode
representation of the UTF-8 string.  Storage for the return value
is appended to the end of the \fBTcl_DString\fR.  The Unicode string
is terminated with a Unicode null character.
.PP
\fBTcl_UniCharLen\fR corresponds to \fBstrlen\fR for Unicode
characters.  It accepts a null-terminated Unicode string and returns
the number of Unicode characters (not bytes) in that string.
.PP
\fBTcl_UniCharNcmp\fR and \fBTcl_UniCharNcasecmp\fR correspond to
\fBstrncmp\fR and \fBstrncasecmp\fR, respectively, for Unicode characters.
They accepts two null-terminated Unicode strings and the number of characters
to compare.  Both strings are assumed to be at least \fIlen\fR characters
long. \fBTcl_UniCharNcmp\fR  compares the two strings character-by-character
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 Unicode case insensitive version.
.PP
.VS 8.4
\fBTcl_UniCharCaseMatch\fR is the Unicode equivalent to
\fBTcl_StringCaseMatch\fR.  It accepts a null-terminated Unicode string,
a Unicode pattern, and a boolean value specifying whether the match should
be case sensitive and returns whether the string matches the pattern.
.VE 8.4
.PP
\fBTcl_UtfNcmp\fR corresponds to \fBstrncmp\fR for UTF-8 strings. It
accepts two null-terminated UTF-8 strings and the number of characters
to compare.  (Both strings are assumed to be at least \fIlen\fR
characters long.)  \fBTcl_UtfNcmp\fR compares the two strings
character-by-character 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.
.PP
\fBTcl_UtfNcasecmp\fR corresponds to \fBstrncasecmp\fR for UTF-8
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 UTF-8 string \fIsrc\fR
of length \fIlen\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 Tcl_UniChar 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
\fIsrc\fR.  The length of the source string is \fIlen\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 UTF-8 strings.  It
returns a pointer to the first occurrence of the Tcl_UniChar \fIch\fR
in the null-terminated UTF-8 string \fIsrc\fR.  The null terminator is
considered part of the UTF-8 string.  
.PP
\fBTcl_UtfFindLast\fR corresponds to \fBstrrchr\fR for UTF-8 strings.  It
returns a pointer to the last occurrence of the Tcl_UniChar \fIch\fR
in the null-terminated UTF-8 string \fIsrc\fR.  The null terminator is
considered part of the UTF-8 string.  
.PP
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.
.PP
Given \fIsrc\fR, a pointer to some location in a UTF-8 string (or to a
null byte immediately following such a string), \fBTcl_UtfPrev\fR
returns a pointer to the closest preceding byte that starts a UTF-8
character.
This function will not back up to a position before \fIstart\fR,
the start of the UTF-8 string.  If \fIsrc\fR was already at \fIstart\fR, the
return value will be \fIstart\fR.
.PP
\fBTcl_UniCharAtIndex\fR corresponds to a C string array dereference or the
Pascal Ord() function.  It returns the Tcl_UniChar represented at the
specified character (not byte) \fIindex\fR in the UTF-8 string
\fIsrc\fR.  The source string must contain at least \fIindex\fR
characters.  Behavior is undefined if a negative \fIindex\fR is given.
.PP
\fBTcl_UtfAtIndex\fR returns a pointer to the specified character (not
byte) \fIindex\fR in the UTF-8 string \fIsrc\fR.  The source string must
contain at least \fIindex\fR characters.  This is equivalent to calling 
\fBTcl_UtfNext\fR \fIindex\fR times.  If a negative \fIindex\fR is given,
the return pointer points to the first character in the source string.
.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
UTF-8 character represented by the backslash sequence in the output
buffer \fIdst\fR.  At most TCL_UTF_MAX 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.
.PP
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