'\" '\" Copyright (c) 1998 by Scriptics Corporation. '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" '\" RCS: @(#) $Id: encoding.n,v 1.1.1.1 2007/07/10 15:04:23 duncan 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 1.1.1.1 2007/07/10 15:04:23 duncan 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 encoding n "8.1" Tcl "Tcl Built-In Commands" .BS .SH NAME encoding \- Manipulate encodings .SH SYNOPSIS \fBencoding \fIoption\fR ?\fIarg arg ...\fR? .BE .SH INTRODUCTION .PP Strings in Tcl are encoded using 16-bit Unicode characters. Different operating system interfaces or applications may generate strings in other encodings such as Shift-JIS. The \fBencoding\fR command helps to bridge the gap between Unicode and these other formats. .SH DESCRIPTION .PP Performs one of several encoding related operations, depending on \fIoption\fR. The legal \fIoption\fRs are: .TP \fBencoding convertfrom\fR ?\fIencoding\fR? \fIdata\fR Convert \fIdata\fR to Unicode from the specified \fIencoding\fR. The characters in \fIdata\fR are treated as binary data where the lower 8-bits of each character is taken as a single byte. The resulting sequence of bytes is treated as a string in the specified \fIencoding\fR. If \fIencoding\fR is not specified, the current system encoding is used. .TP \fBencoding convertto\fR ?\fIencoding\fR? \fIstring\fR Convert \fIstring\fR from Unicode to the specified \fIencoding\fR. The result is a sequence of bytes that represents the converted string. Each byte is stored in the lower 8-bits of a Unicode character. If \fIencoding\fR is not specified, the current system encoding is used. .TP \fBencoding names\fR Returns a list containing the names of all of the encodings that are currently available. .TP \fBencoding system\fR ?\fIencoding\fR? Set the system encoding to \fIencoding\fR. If \fIencoding\fR is omitted then the command returns the current system encoding. The system encoding is used whenever Tcl passes strings to system calls. .SH EXAMPLE .PP It is common practice to write script files using a text editor that produces output in the euc-jp encoding, which represents the ASCII characters as singe bytes and Japanese characters as two bytes. This makes it easy to embed literal strings that correspond to non-ASCII characters by simply typing the strings in place in the script. However, because the \fBsource\fR command always reads files using the current system encoding, Tcl will only source such files correctly when the encoding used to write the file is the same. This tends not to be true in an internationalized setting. For example, if such a file was sourced in North America (where the ISO8859-1 is normally used), each byte in the file would be treated as a separate character that maps to the 00 page in Unicode. The resulting Tcl strings will not contain the expected Japanese characters. Instead, they will contain a sequence of Latin-1 characters that correspond to the bytes of the original string. The \fBencoding\fR command can be used to convert this string to the expected Japanese Unicode characters. For example, .CS set s [\fBencoding convertfrom\fR euc-jp "\\xA4\\xCF"] .CE would return the Unicode string "\\u306F", which is the Hiragana letter HA. .SH "SEE ALSO" Tcl_GetEncoding(3) .SH KEYWORDS encoding