diff options
Diffstat (limited to 'usr/man/mann/scan.n')
| -rwxr-xr-x | usr/man/mann/scan.n | 533 |
1 files changed, 533 insertions, 0 deletions
diff --git a/usr/man/mann/scan.n b/usr/man/mann/scan.n new file mode 100755 index 000000000..11679e2f5 --- /dev/null +++ b/usr/man/mann/scan.n @@ -0,0 +1,533 @@ +'\" +'\" Copyright (c) 1993 The Regents of the University of California. +'\" Copyright (c) 1994-1996 Sun Microsystems, Inc. +'\" Copyright (c) 2000 Scriptics Corporation. +'\" +'\" See the file "license.terms" for information on usage and redistribution +'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. +'\" +.\" 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 "" +.. +.TH scan n 8.4 Tcl "Tcl Built-In Commands" +.BS +'\" Note: do not modify the .SH NAME line immediately below! +.SH NAME +scan \- Parse string using conversion specifiers in the style of sscanf +.SH SYNOPSIS +\fBscan \fIstring format \fR?\fIvarName varName ...\fR? +.BE +.SH INTRODUCTION +.PP +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 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 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. +A conversion specifier contains up to four fields after the \fB%\fR: +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. +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 +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. +.PP +If the \fB%\fR is followed by a decimal number and a \fB$\fR, as in +.QW \fB%2$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 +specifiers must be positional. Every \fIvarName\fR on the argument +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. +.PP +.VS 8.5 +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. +.VE 8.5 +.PP +The following conversion characters are supported: +.TP 10 +\fBd\fR +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 10 +\fBo\fR +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 10 +\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 10 +\fBu\fR +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 10 +\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 10 +\fBc\fR +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 +substring may be a white-space character. +.TP 10 +\fBs\fR +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 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 value. +.TP 10 +\fB[\fIchars\fB]\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 +bracket for the set. +If \fIchars\fR +contains a sequence of the form \fIa\fB\-\fIb\fR then any +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 +\fB[^\fIchars\fB]\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 +the set. +If \fIchars\fR +contains a sequence of the form \fIa\fB\-\fIb\fR then any +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 value. +.TP 10 +\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 +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 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 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 substring width may be specified for this conversion. +.IP [3] +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). 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 +Convert a UNICODE character to its numeric value: +.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: +.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): +.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): +.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: +.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 +.VS 8.5 +An interactive session demonstrating the truncation of integer +values determined by size modifiers: +.CS +% set tcl_platform(wordSize) +4 +% scan 20000000000000000000 %d +2147483647 +% scan 20000000000000000000 %ld +9223372036854775807 +% scan 20000000000000000000 %lld +20000000000000000000 +.CE +.VE 8.5 +.SH "SEE ALSO" +format(n), sscanf(3) +.SH KEYWORDS +conversion specifier, parse, scan |