'\" See the file "license.terms" for information on usage and redistribution
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
'\"
-'\" RCS: @(#) $Id: scan.n,v 1.9 2002/07/01 18:24:39 jenglish 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.
+.TH scan n 8.4 Tcl "Tcl Built-In Commands"
+.\" 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
+.\" # Start an argument description
.de AP
.ie !"\\$4"" .TP \\$4
.el \{\
.\}
.ta \\n()Au \\n()Bu
.ie !"\\$3"" \{\
-\&\\$1 \\fI\\$2\\fP (\\$3)
+\&\\$1 \\fI\\$2\\fP (\\$3)
.\".b
.\}
.el \{\
.\}
.\}
..
-'\" # define tabbing values for .AP
+.\" # define tabbing values for .AP
.de AS
.nr )A 10n
.if !"\\$1"" .nr )A \\w'\\$1'u+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
+.\" # BS - start boxed text
+.\" # ^y = starting y location
+.\" # ^b = 1
.de BS
.br
.mk ^y
.if n \l'\\n(.lu\(ul'
.if n .fi
..
-'\" # BE - end boxed text (draw box now)
+.\" # BE - end boxed text (draw box now)
.de BE
.nf
.ti 0
.br
.nr ^b 0
..
-'\" # VS - start vertical sidebar
-'\" # ^Y = starting y location
-'\" # ^v = 1 (for troff; for nroff this doesn't matter)
+.\" # 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
+.\" # VE - end of vertical sidebar
.de VE
.ie n 'mc
.el \{\
.\}
.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.
+.\" # 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
.mk ^Y
.\}
..
-'\" # DS - begin display
+.\" # DS - begin display
.de DS
.RS
.nf
.sp
..
-'\" # DE - end display
+.\" # DE - end display
.de DE
.fi
.RE
.sp
..
-'\" # SO - start of list of standard options
+.\" # 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
+.\" # 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.
+See the \\*(So manual entry for details on the standard options.
..
-'\" # OP - start of full description for a single option
+.\" # OP - start of full description for a single option
.de OP
.LP
.nf
.fi
.IP
..
-'\" # CS - begin code excerpt
+.\" # CS - begin code excerpt
.de CS
.RS
.nf
.ta .25i .5i .75i 1i
..
-'\" # CE - end code excerpt
+.\" # CE - end code excerpt
.de CE
.fi
.RE
..
+.\" # UL - underline word
.de UL
\\$1\l'|0\(ul'\\$2
..
-.TH scan n 8.4 Tcl "Tcl Built-In Commands"
+.\" # 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
'\" Note: do not modify the .SH NAME line immediately below!
.SH NAME
.SH SYNOPSIS
\fBscan \fIstring format \fR?\fIvarName varName ...\fR?
.BE
-
.SH INTRODUCTION
.PP
-This command parses fields from an input string in the same fashion as the
-ANSI C \fBsscanf\fR procedure and returns a count of the number of
+This command parses substrings from an input string in a fashion similar
+to the ANSI C \fBsscanf\fR procedure and returns a count of the number of
conversions performed, or -1 if the end of the input string is reached
before any conversions have been performed. \fIString\fR gives the input
to be parsed and \fIformat\fR indicates how to parse it, using \fB%\fR
conversion specifiers as in \fBsscanf\fR. Each \fIvarName\fR gives the
-name of a variable; when a field is scanned from \fIstring\fR the result is
-converted back into a string and assigned to the corresponding variable.
+name of a variable; when a substring is scanned from \fIstring\fR that
+matches a conversion specifier, the substring is assigned to the
+corresponding variable.
If no \fIvarName\fR variables are specified, then \fBscan\fR works in an
inline manner, returning the data that would otherwise be stored in the
variables as a list. In the inline case, an empty string is returned when
the end of the input string is reached before any conversions have been
performed.
-
.SH "DETAILS ON SCANNING"
.PP
\fBScan\fR operates by scanning \fIstring\fR and \fIformat\fR together.
If the next character in \fIformat\fR is a blank or tab then it
matches any number of white space characters in \fIstring\fR (including
zero).
-Otherwise, if it isn't a \fB%\fR character then it
+Otherwise, if it is not a \fB%\fR character then it
must match the next character of \fIstring\fR.
When a \fB%\fR is encountered in \fIformat\fR, it indicates
the start of a conversion specifier.
-.VS 8.4
A conversion specifier contains up to four fields after the \fB%\fR:
-a \fB*\fR, which indicates that the converted value is to be discarded
-instead of assigned to a variable; a XPG3 position specifier; a number
-indicating a maximum field width; a field size modifier; and a
+a XPG3 position specifier (or a \fB*\fR to indicate the converted
+value is to be discarded instead of assigned to any variable); a number
+indicating a maximum substring width; a size modifier; and a
conversion character.
-.VE 8.4
All of these fields are optional except for the conversion character.
The fields that are present must appear in the order given above.
.PP
When \fBscan\fR finds a conversion specifier in \fIformat\fR, it
first skips any white-space characters in \fIstring\fR (unless the
-specifier is \fB[\fR or \fBc\fR).
+conversion character is \fB[\fR or \fBc\fR).
Then it converts the next input characters according to the
conversion specifier and stores the result in the variable given
by the next argument to \fBscan\fR.
+.SS "OPTIONAL POSITIONAL SPECIFIER"
.PP
If the \fB%\fR is followed by a decimal number and a \fB$\fR, as in
-``\fB%2$d\fR'', then the variable to use is not taken from the next
+.QW \fB%2$d\fR ,
+then the variable to use is not taken from the next
sequential argument. Instead, it is taken from the argument indicated
by the number, where 1 corresponds to the first \fIvarName\fR. If
there are any positional specifiers in \fIformat\fR then all of the
list must correspond to exactly one conversion specifier or an error
is generated, or in the inline case, any position can be specified
at most once and the empty positions will be filled in with empty strings.
+.SS "OPTIONAL SIZE MODIFIER"
+.PP
+The size modifier field is used only when scanning a substring into
+one of Tcl's integer values. The size modifier field dictates the
+integer range acceptable to be stored in a variable, or, for the inline
+case, in a position in the result list.
+The syntactically valid values for the size modifier are \fBh\fR, \fBL\fR,
+\fBl\fR, and \fBll\fR. The \fBh\fR size modifier value is equivalent
+to the absence of a size modifier in the the conversion specifier.
+Either one indicates the integer range to be stored is limited to
+the same range produced by the \fBint()\fR function of the \fBexpr\fR
+command. The \fBL\fR size modifier is equivalent to the \fBl\fR size
+modifier. Either one indicates the integer range to be stored is
+limited to the same range produced by the \fBwide()\fR function of
+the \fBexpr\fR command. The \fBll\fR size modifier indicates that
+the integer range to be stored is unlimited.
+.SS "MANDATORY CONVERSION CHARACTER"
.PP
The following conversion characters are supported:
-.TP 10
+.TP
\fBd\fR
-The input field must be a decimal integer.
-It is read in and the value is stored in the variable as a decimal string.
-.VS 8.4
-If the \fBl\fR or \fBL\fR field size modifier is given, the scanned
-value will have an internal representation that is at least 64-bits in
-size.
-.VE 8.4
-.TP 10
+.
+The input substring must be a decimal integer.
+It is read in and the integer value is stored in the variable,
+truncated as required by the size modifier value.
+.TP
\fBo\fR
-The input field must be an octal integer. It is read in and the
-value is stored in the variable as a decimal string.
-.VS 8.4
-If the \fBl\fR or \fBL\fR field size modifier is given, the scanned
-value will have an internal representation that is at least 64-bits in
-size.
-If the value exceeds MAX_INT (017777777777 on platforms using 32-bit
-integers when the \fBl\fR and \fBL\fR modifiers are not given), it
-will be truncated to a signed integer. Hence, 037777777777 will
-appear as -1 on a 32-bit machine by default.
-.VE 8.4
-.TP 10
-\fBx\fR
-The input field must be a hexadecimal integer. It is read in
-and the value is stored in the variable as a decimal string.
-.VS 8.4
-If the \fBl\fR or \fBL\fR field size modifier is given, the scanned
-value will have an internal representation that is at least 64-bits in
-size.
-If the value exceeds MAX_INT (0x7FFFFFFF on platforms using 32-bit
-integers when the \fBl\fR and \fBL\fR modifiers are not given), it
-will be truncated to a signed integer. Hence, 0xFFFFFFFF will appear
-as -1 on a 32-bit machine.
-.VE 8.4
-.TP 10
+.
+The input substring must be an octal integer. It is read in and the
+integer value is stored in the variable,
+truncated as required by the size modifier value.
+.TP
+\fBx\fR or \fBX\fR
+.
+The input substring must be a hexadecimal integer.
+It is read in and the integer value is stored in the variable,
+truncated as required by the size modifier value.
+.TP
+\fBb\fR
+.
+The input substring must be a binary integer.
+It is read in and the integer value is stored in the variable,
+truncated as required by the size modifier value.
+.TP
\fBu\fR
-The input field must be a decimal integer. The value is stored in the
-variable as an unsigned decimal integer string.
-.VS 8.4
-If the \fBl\fR or \fBL\fR field size modifier is given, the scanned
-value will have an internal representation that is at least 64-bits in
-size.
-.VE 8.4
-.TP 10
-\fBi\fR
-The input field must be an integer. The base (i.e. decimal, octal, or
-hexadecimal) is determined in the same fashion as described in
-\fBexpr\fR. The value is stored in the variable as a decimal string.
-.VS 8.4
-If the \fBl\fR or \fBL\fR field size modifier is given, the scanned
-value will have an internal representation that is at least 64-bits in
-size.
-.VE 8.4
-.TP 10
+.
+The input substring must be a decimal integer.
+The integer value is truncated as required by the size modifier
+value, and the corresponding unsigned value for that truncated
+range is computed and stored in the variable as a decimal string.
+The conversion makes no sense without reference to a truncation range,
+so the size modifier \fBll\fR is not permitted in combination
+with conversion character \fBu\fR.
+.TP
+\fBi\fR
+.
+The input substring must be an integer. The base (i.e. decimal, binary,
+octal, or hexadecimal) is determined in the same fashion as described in
+\fBexpr\fR. The integer value is stored in the variable,
+truncated as required by the size modifier value.
+.TP
\fBc\fR
-A single character is read in and its binary value is stored in
-the variable as a decimal string.
+.
+A single character is read in and its Unicode value is stored in
+the variable as an integer value.
Initial white space is not skipped in this case, so the input
-field may be a white-space character.
-This conversion is different from the ANSI standard in that the
-input field always consists of a single character and no field
-width may be specified.
-.TP 10
+substring may be a white-space character.
+.TP
\fBs\fR
-The input field consists of all the characters up to the next
+.
+The input substring consists of all the characters up to the next
white-space character; the characters are copied to the variable.
-.TP 10
-\fBe\fR or \fBf\fR or \fBg\fR
-The input field must be a floating-point number consisting
+.TP
+\fBe\fR or \fBf\fR or \fBg\fR or \fBE\fR or \fBG\fR
+.
+The input substring must be a floating-point number consisting
of an optional sign, a string of decimal digits possibly
containing a decimal point, and an optional exponent consisting
of an \fBe\fR or \fBE\fR followed by an optional sign and a string of
decimal digits.
-It is read in and stored in the variable as a floating-point string.
-.TP 10
+It is read in and stored in the variable as a floating-point value.
+.TP
\fB[\fIchars\fB]\fR
-The input field consists of any number of characters in
-\fIchars\fR.
+.
+The input substring consists of one or more characters in \fIchars\fR.
The matching string is stored in the variable.
If the first character between the brackets is a \fB]\fR then
it is treated as part of \fIchars\fR rather than the closing
character between \fIa\fR and \fIb\fR (inclusive) will match.
If the first or last character between the brackets is a \fB\-\fR, then
it is treated as part of \fIchars\fR rather than indicating a range.
-.TP 10
+.TP
\fB[^\fIchars\fB]\fR
-The input field consists of any number of characters not in
-\fIchars\fR.
+.
+The input substring consists of one or more characters not in \fIchars\fR.
The matching string is stored in the variable.
If the character immediately following the \fB^\fR is a \fB]\fR then it is
treated as part of the set rather than the closing bracket for
character between \fIa\fR and \fIb\fR (inclusive) will be excluded
from the set.
If the first or last character between the brackets is a \fB\-\fR, then
-it is treated as part of \fIchars\fR rather than indicating a range.
-.TP 10
+it is treated as part of \fIchars\fR rather than indicating a range value.
+.TP
\fBn\fR
+.
No input is consumed from the input string. Instead, the total number
of characters scanned from the input string so far is stored in the variable.
-.LP
+.PP
The number of characters read from the input for a conversion is the
largest number that makes sense for that particular conversion (e.g.
as many decimal digits as possible for \fB%d\fR, as
many octal digits as possible for \fB%o\fR, and so on).
-The input field for a given conversion terminates either when a
-white-space character is encountered or when the maximum field
+The input substring for a given conversion terminates either when a
+white-space character is encountered or when the maximum substring
width has been reached, whichever comes first.
If a \fB*\fR is present in the conversion specifier
then no variable is assigned and the next scan argument is not consumed.
-
.SH "DIFFERENCES FROM ANSI SSCANF"
.PP
The behavior of the \fBscan\fR command is the same as the behavior of
the ANSI C \fBsscanf\fR procedure except for the following differences:
.IP [1]
-\fB%p\fR conversion specifier is not currently supported.
+\fB%p\fR conversion specifier is not supported.
.IP [2]
For \fB%c\fR conversions a single character value is
converted to a decimal string, which is then assigned to the
corresponding \fIvarName\fR;
-no field width may be specified for this conversion.
+no substring width may be specified for this conversion.
.IP [3]
-.VS 8.4
The \fBh\fR modifier is always ignored and the \fBl\fR and \fBL\fR
modifiers are ignored when converting real values (i.e. type
-\fBdouble\fR is used for the internal representation).
-.VE 8.4
+\fBdouble\fR is used for the internal representation). The \fBll\fR
+modifier has no \fBsscanf\fR counterpart.
.IP [4]
If the end of the input string is reached before any conversions have been
performed and no variables are given, an empty string is returned.
-
+.SH EXAMPLES
+.PP
+Convert a UNICODE character to its numeric value:
+.PP
+.CS
+set char "x"
+set value [\fBscan\fR $char %c]
+.CE
+.PP
+Parse a simple color specification of the form \fI#RRGGBB\fR using
+hexadecimal conversions with substring sizes:
+.PP
+.CS
+set string "#08D03F"
+\fBscan\fR $string "#%2x%2x%2x" r g b
+.CE
+.PP
+Parse a \fIHH:MM\fR time string, noting that this avoids problems with
+octal numbers by forcing interpretation as decimals (if we did not
+care, we would use the \fB%i\fR conversion instead):
+.PP
+.CS
+set string "08:08" ;# *Not* octal!
+if {[\fBscan\fR $string "%d:%d" hours minutes] != 2} {
+ error "not a valid time string"
+}
+# We have to understand numeric ranges ourselves...
+if {$minutes < 0 || $minutes > 59} {
+ error "invalid number of minutes"
+}
+.CE
+.PP
+Break a string up into sequences of non-whitespace characters (note
+the use of the \fB%n\fR conversion so that we get skipping over
+leading whitespace correct):
+.PP
+.CS
+set string " a string {with braced words} + leading space "
+set words {}
+while {[\fBscan\fR $string %s%n word length] == 2} {
+ lappend words $word
+ set string [string range $string $length end]
+}
+.CE
+.PP
+Parse a simple coordinate string, checking that it is complete by
+looking for the terminating character explicitly:
+.PP
+.CS
+set string "(5.2,-4e-2)"
+# Note that the spaces before the literal parts of
+# the scan pattern are significant, and that ")" is
+# the Unicode character \eu0029
+if {
+ [\fBscan\fR $string " (%f ,%f %c" x y last] != 3
+ || $last != 0x0029
+} then {
+ error "invalid coordinate string"
+}
+puts "X=$x, Y=$y"
+.CE
+.PP
+An interactive session demonstrating the truncation of integer
+values determined by size modifiers:
+.PP
+.CS
+\fI%\fR set tcl_platform(wordSize)
+4
+\fI%\fR scan 20000000000000000000 %d
+2147483647
+\fI%\fR scan 20000000000000000000 %ld
+9223372036854775807
+\fI%\fR scan 20000000000000000000 %lld
+20000000000000000000
+.CE
.SH "SEE ALSO"
format(n), sscanf(3)
-
.SH KEYWORDS
conversion specifier, parse, scan
+'\" Local Variables:
+'\" mode: nroff
+'\" End:
OSDN Git Service
