man/mann/string.n

'\"
'\" Copyright (c) 1993 The Regents of the University of California.
'\" Copyright (c) 1994-1996 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: string.n,v 1.17 2002/07/05 07:23:45 hobbs 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 string n 8.1 Tcl "Tcl Built-In Commands"
.BS
'\" Note:  do not modify the .SH NAME line immediately below!
.SH NAME
string \- Manipulate strings
.SH SYNOPSIS
\fBstring \fIoption arg \fR?\fIarg ...?\fR
.BE

.SH DESCRIPTION
.PP
Performs one of several string operations, depending on \fIoption\fR.
The legal \fIoption\fRs (which may be abbreviated) are:
.TP
\fBstring bytelength \fIstring\fR
Returns a decimal string giving the number of bytes used to represent
\fIstring\fR in memory.  Because UTF\-8 uses one to three bytes to
represent Unicode characters, the byte length will not be the same as
the character length in general.  The cases where a script cares about
the byte length are rare.  In almost all cases, you should use the
\fBstring length\fR operation (including determining the length of a
Tcl ByteArray object).  Refer to the \fBTcl_NumUtfChars\fR manual
entry for more details on the UTF\-8 representation.
.TP
\fBstring compare\fR ?\fB\-nocase\fR? ?\fB\-length int\fR? \fIstring1 string2\fR
Perform a character-by-character comparison of strings \fIstring1\fR
and \fIstring2\fR.  Returns \-1, 0, or 1, depending on whether
\fIstring1\fR is lexicographically less than, equal to, or greater
than \fIstring2\fR.  If \fB\-length\fR is specified, then only the
first \fIlength\fR characters are used in the comparison.  If
\fB\-length\fR is negative, it is ignored.  If \fB\-nocase\fR is
specified, then the strings are compared in a case-insensitive manner.
.TP
\fBstring equal\fR ?\fB\-nocase\fR? ?\fB-length int\fR? \fIstring1 string2\fR
Perform a character-by-character comparison of strings \fIstring1\fR
and \fIstring2\fR.  Returns 1 if \fIstring1\fR and \fIstring2\fR are
identical, or 0 when not.  If \fB\-length\fR is specified, then only
the first \fIlength\fR characters are used in the comparison.  If
\fB\-length\fR is negative, it is ignored.  If \fB\-nocase\fR is
specified, then the strings are compared in a case-insensitive manner.
.TP
\fBstring first \fIstring1 string2\fR ?\fIstartIndex\fR?
Search \fIstring2\fR for a sequence of characters that exactly match
the characters in \fIstring1\fR.  If found, return the index of the
first character in the first such match within \fIstring2\fR.  If not
found, return \-1.  If \fIstartIndex\fR is specified (in any of the
forms accepted by the \fBindex\fR method), then the search is
constrained to start with the character in \fIstring2\fR specified by
the index.  For example,
.RS
.CS
\fBstring first a 0a23456789abcdef 5\fR
.CE
will return \fB10\fR, but
.CS
\fBstring first a 0123456789abcdef 11\fR
.CE
will return \fB\-1\fR.
.RE
.TP
\fBstring index \fIstring charIndex\fR
Returns the \fIcharIndex\fR'th character of the \fIstring\fR argument.
A \fIcharIndex\fR of 0 corresponds to the first character of the
string.  \fIcharIndex\fR may be specified as follows:
.RS
.IP \fIinteger\fR 10
The char specified at this integral index.
.IP \fBend\fR 10
The last char of the string.
.IP \fBend\-\fIinteger\fR 10
The last char of the string minus the specified integer offset
(e.g. \fBend\-1\fR would refer to the "c" in "abcd").
.PP
If \fIcharIndex\fR is less than 0 or greater than or equal to the
length of the string then an empty string is returned.
.RE
.TP
\fBstring is \fIclass\fR ?\fB\-strict\fR? ?\fB\-failindex \fIvarname\fR? \fIstring\fR
Returns 1 if \fIstring\fR is a valid member of the specified character
class, otherwise returns 0.  If \fB\-strict\fR is specified, then an
empty string returns 0, otherwise and empty string will return 1 on
any class.  If \fB\-failindex\fR is specified, then if the function
returns 0, the index in the string where the class was no longer valid
will be stored in the variable named \fIvarname\fR.  The \fIvarname\fR
will not be set if the function returns 1.  The following character
classes are recognized (the class name can be abbreviated):
.RS
.IP \fBalnum\fR 10
Any Unicode alphabet or digit character.
.IP \fBalpha\fR 10
Any Unicode alphabet character.
.IP \fBascii\fR 10
Any character with a value less than \\u0080 (those that are in the
7\-bit ascii range).
.IP \fBboolean\fR 10
Any of the forms allowed to \fBTcl_GetBoolean\fR.
.IP \fBcontrol\fR 10
Any Unicode control character.
.IP \fBdigit\fR 10
Any Unicode digit character.  Note that this includes characters
outside of the [0\-9] range.
.IP \fBdouble\fR 10
Any of the valid forms for a double in Tcl, with optional surrounding
whitespace.  In case of under/overflow in the value, 0 is returned and
the \fIvarname\fR will contain \-1.
.IP \fBfalse\fR 10
Any of the forms allowed to \fBTcl_GetBoolean\fR where the value is
false.
.IP \fBgraph\fR 10
Any Unicode printing character, except space.
.IP \fBinteger\fR 10
Any of the valid forms for an integer in Tcl, with optional
surrounding whitespace.  In case of under/overflow in the value, 0 is
returned and the \fIvarname\fR will contain \-1.
.IP \fBlower\fR 10
Any Unicode lower case alphabet character.
.IP \fBprint\fR 10
Any Unicode printing character, including space.
.IP \fBpunct\fR 10
Any Unicode punctuation character.
.IP \fBspace\fR 10
Any Unicode space character.
.IP \fBtrue\fR 10
Any of the forms allowed to \fBTcl_GetBoolean\fR where the value is
true.
.IP \fBupper\fR 10
Any upper case alphabet character in the Unicode character set.
.IP \fBwordchar\fR 10
Any Unicode word character.  That is any alphanumeric character, and
any Unicode connector punctuation characters (e.g. underscore).
.IP \fBxdigit\fR 10
Any hexadecimal digit character ([0\-9A\-Fa\-f]).
.PP
In the case of \fBboolean\fR, \fBtrue\fR and \fBfalse\fR, if the
function will return 0, then the \fIvarname\fR will always be set to
0, due to the varied nature of a valid boolean value.
.RE
.TP
\fBstring last \fIstring1 string2\fR ?\fIlastIndex\fR?
Search \fIstring2\fR for a sequence of characters that exactly match
the characters in \fIstring1\fR.  If found, return the index of the
first character in the last such match within \fIstring2\fR.  If there
is no match, then return \-1.  If \fIlastIndex\fR is specified (in any
of the forms accepted by the \fBindex\fR method), then only the
characters in \fIstring2\fR at or before the specified \fIlastIndex\fR
will be considered by the search.  For example,
.RS
.CS
\fBstring last a 0a23456789abcdef 15\fR
.CE
will return \fB10\fR, but
.CS
\fBstring last a 0a23456789abcdef 9\fR
.CE
will return \fB1\fR.
.RE
.TP
\fBstring length \fIstring\fR
Returns a decimal string giving the number of characters in
\fIstring\fR.  Note that this is not necessarily the same as the
number of bytes used to store the string.  If the object is a
ByteArray object (such as those returned from reading a binary encoded
channel), then this will return the actual byte length of the object.
.TP
\fBstring map\fR ?\fB\-nocase\fR? \fIcharMap string\fR
Replaces characters in \fIstring\fR based on the key-value pairs in
\fIcharMap\fR.  \fIcharMap\fR is a list of \fIkey value key value ...\fR
as in the form returned by \fBarray get\fR.  Each instance of a
key in the string will be replaced with its corresponding value.  If
\fB\-nocase\fR is specified, then matching is done without regard to
case differences. Both \fIkey\fR and \fIvalue\fR may be multiple
characters.  Replacement is done in an ordered manner, so the key
appearing first in the list will be checked first, and so on.
\fIstring\fR is only iterated over once, so earlier key replacements
will have no affect for later key matches.  For example,
.RS
.CS
\fBstring map {abc 1 ab 2 a 3 1 0} 1abcaababcabababc\fR
.CE
will return the string \fB01321221\fR.
.RE
.TP
\fBstring match\fR ?\fB\-nocase\fR? \fIpattern\fR \fIstring\fR
See if \fIpattern\fR matches \fIstring\fR; return 1 if it does, 0 if
it doesn't.  If \fB\-nocase\fR is specified, then the pattern attempts
to match against the string in a case insensitive manner.  For the two
strings to match, their contents must be identical except that the
following special sequences may appear in \fIpattern\fR:
.RS
.IP \fB*\fR 10
Matches any sequence of characters in \fIstring\fR, including a null
string.
.IP \fB?\fR 10
Matches any single character in \fIstring\fR.
.IP \fB[\fIchars\fB]\fR 10
Matches any character in the set given by \fIchars\fR.  If a sequence
of the form \fIx\fB\-\fIy\fR appears in \fIchars\fR, then any
character between \fIx\fR and \fIy\fR, inclusive, will match.  When
used with \fB\-nocase\fR, the end points of the range are converted to
lower case first.  Whereas {[A\-z]} matches '_' when matching
case-sensitively ('_' falls between the 'Z' and 'a'), with
\fB\-nocase\fR this is considered like {[A\-Za\-z]} (and probably what
was meant in the first place).
.IP \fB\e\fIx\fR 10
Matches the single character \fIx\fR.  This provides a way of avoiding
the special interpretation of the characters \fB*?[]\e\fR in
\fIpattern\fR.
.RE
.TP
\fBstring range \fIstring first last\fR
Returns a range of consecutive characters from \fIstring\fR, starting
with the character whose index is \fIfirst\fR and ending with the
character whose index is \fIlast\fR. An index of 0 refers to the first
character of the string.  \fIfirst\fR and \fIlast\fR may be specified
as for the \fBindex\fR method.  If \fIfirst\fR is less than zero then
it is treated as if it were zero, and if \fIlast\fR is greater than or
equal to the length of the string then it is treated as if it were
\fBend\fR.  If \fIfirst\fR is greater than \fIlast\fR then an empty
string is returned.
.TP
\fBstring repeat \fIstring count\fR
Returns \fIstring\fR repeated \fIcount\fR number of times.
.TP
\fBstring replace \fIstring first last\fR ?\fInewstring\fR?
Removes a range of consecutive characters from \fIstring\fR, starting
with the character whose index is \fIfirst\fR and ending with the
character whose index is \fIlast\fR.  An index of 0 refers to the
first character of the string.  \fIFirst\fR and \fIlast\fR may be
specified as for the \fBindex\fR method.  If \fInewstring\fR is
specified, then it is placed in the removed character range.  If
\fIfirst\fR is less than zero then it is treated as if it were zero,
and if \fIlast\fR is greater than or equal to the length of the string
then it is treated as if it were \fBend\fR.  If \fIfirst\fR is greater
than \fIlast\fR or the length of the initial string, or \fIlast\fR is
less than 0, then the initial string is returned untouched.
.TP
\fBstring tolower \fIstring\fR ?\fIfirst\fR? ?\fIlast\fR?
Returns a value equal to \fIstring\fR except that all upper (or title)
case letters have been converted to lower case.  If \fIfirst\fR is
specified, it refers to the first char index in the string to start
modifying.  If \fIlast\fR is specified, it refers to the char index in
the string to stop at (inclusive).  \fIfirst\fR and \fIlast\fR may be
specified as for the \fBindex\fR method.
.TP
\fBstring totitle \fIstring\fR ?\fIfirst\fR? ?\fIlast\fR?
Returns a value equal to \fIstring\fR except that the first character
in \fIstring\fR is converted to its Unicode title case variant (or
upper case if there is no title case variant) and the rest of the
string is converted to lower case.  If \fIfirst\fR is specified, it
refers to the first char index in the string to start modifying.  If
\fIlast\fR is specified, it refers to the char index in the string to
stop at (inclusive).  \fIfirst\fR and \fIlast\fR may be specified as
for the \fBindex\fR method.
.TP
\fBstring toupper \fIstring\fR ?\fIfirst\fR? ?\fIlast\fR?
Returns a value equal to \fIstring\fR except that all lower (or title)
case letters have been converted to upper case.  If \fIfirst\fR is
specified, it refers to the first char index in the string to start
modifying.  If \fIlast\fR is specified, it refers to the char index in
the string to stop at (inclusive).  \fIfirst\fR and \fIlast\fR may be
specified as for the \fBindex\fR method.
.TP
\fBstring trim \fIstring\fR ?\fIchars\fR?
Returns a value equal to \fIstring\fR except that any leading or
trailing characters from the set given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
.TP
\fBstring trimleft \fIstring\fR ?\fIchars\fR?
Returns a value equal to \fIstring\fR except that any leading
characters from the set given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
.TP
\fBstring trimright \fIstring\fR ?\fIchars\fR?
Returns a value equal to \fIstring\fR except that any trailing
characters from the set given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
.TP
\fBstring wordend \fIstring charIndex\fR
Returns the index of the character just after the last one in the word
containing character \fIcharIndex\fR of \fIstring\fR.  \fIcharIndex\fR
may be specified as for the \fBindex\fR method.  A word is
considered to be any contiguous range of alphanumeric (Unicode letters
or decimal digits) or underscore (Unicode connector punctuation)
characters, or any single character other than these.
.TP
\fBstring wordstart \fIstring charIndex\fR
Returns the index of the first character in the word containing
character \fIcharIndex\fR of \fIstring\fR.  \fIcharIndex\fR may be
specified as for the \fBindex\fR method.  A word is considered to be any
contiguous range of alphanumeric (Unicode letters or decimal digits)
or underscore (Unicode connector punctuation) characters, or any
single character other than these.

.SH "SEE ALSO"
expr(n), list(n)

.SH KEYWORDS
case conversion, compare, index, match, pattern, string, word, equal, ctype