diff options
Diffstat (limited to 'doc/binary.n')
| -rw-r--r-- | doc/binary.n | 164 |
1 files changed, 130 insertions, 34 deletions
diff --git a/doc/binary.n b/doc/binary.n index ff800f0..014704d 100644 --- a/doc/binary.n +++ b/doc/binary.n @@ -1,5 +1,6 @@ '\" '\" Copyright (c) 1997 by Sun Microsystems, Inc. +'\" Copyright (c) 2008 by Donal K. Fellows '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. @@ -11,6 +12,12 @@ .SH NAME binary \- Insert and extract fields from binary strings .SH SYNOPSIS +.VS 8.6 +\fBbinary decode \fIformat\fR ?\fI\-option value ...\fR? \fIdata\fR +.br +\fBbinary encode \fIformat\fR ?\fI\-option value ...\fR? \fIdata\fR +.br +.VE 8.6 \fBbinary format \fIformatString \fR?\fIarg arg ...\fR? .br \fBbinary scan \fIstring formatString \fR?\fIvarName varName ...\fR? @@ -18,12 +25,110 @@ binary \- Insert and extract fields from binary strings .SH DESCRIPTION .PP This command provides facilities for manipulating binary data. The -first form, \fBbinary format\fR, creates a binary string from normal +subcommand \fBbinary format\fR creates a binary string from normal Tcl values. For example, given the values 16 and 22, on a 32-bit architecture, it might produce an 8-byte binary string consisting of -two 4-byte integers, one for each of the numbers. The second form of -the command, \fBbinary scan\fR, does the opposite: it extracts data +two 4-byte integers, one for each of the numbers. The subcommand +\fBbinary scan\fR, does the opposite: it extracts data from a binary string and returns it as ordinary Tcl string values. +.VS 8.6 +The \fBbinary encode\fR and \fBbinary decode\fR subcommands convert +binary data to or from string encodings such as base64 (used in MIME +messages for example). +.VE 8.6 +.PP +Note that other operations on binary data, such as taking a subsequence of it, +getting its length, or reinterpreting it as a string in some encoding, are +done by other Tcl commands (respectively \fBstring range\fR, +\fBstring length\fR and \fBencoding convertfrom\fR in the example cases). A +binary string in Tcl is merely one where all the characters it contains are in +the range \eu0000\-\eu00FF. +.SH "BINARY ENCODE AND DECODE" +.VS 8.6 +.PP +When encoding binary data as a readable string, the starting binary data is +passed to the \fBbinary encode\fR command, together with the name of the +encoding to use and any encoding-specific options desired. Data which has been +encoded can be converted back to binary form using \fBbinary decode\fR. The +following formats and options are supported. +.TP +\fBbase64\fR +. +The \fBbase64\fR binary encoding is commonly used in mail messages and XML +documents, and uses mostly upper and lower case letters and digits. It has the +distinction of being able to be rewrapped arbitrarily without losing +information. +.RS +.PP +During encoding, the following options are supported: +.TP +\fB\-maxlen \fIlength\fR +. +Indicates that the output should be split into lines of no more than +\fIlength\fR characters. By default, lines are not split. +.TP +\fB\-wrapchar \fIcharacter\fR +. +Indicates that, when lines are split because of the \fB\-maxlen\fR option, +\fIcharacter\fR should be used to separate lines. By default, this is a +newline character, +.QW \en . +.PP +During decoding, the following options are supported: +.TP +\fB\-strict\fR +. +Instructs the decoder to throw an error if it encounters whitespace characters. Otherwise it ignores them. +.RE +.TP +\fBhex\fR +. +The \fBhex\fR binary encoding converts each byte to a pair of hexadecimal +digits in big-endian form. +.RS +.PP +No options are supported during encoding. During decoding, the following +options are supported: +.TP +\fB\-strict\fR +. +Instructs the decoder to throw an error if it encounters whitespace characters. Otherwise it ignores them. +.RE +.TP +\fBuuencode\fR +. +The \fBuuencode\fR binary encoding used to be common for transfer of data +between Unix systems and on USENET, but is less common these days, having been +largely superseded by the \fBbase64\fR binary encoding. +.RS +.PP +During encoding, the following options are supported (though changing them may +produce files that other implementations of decoders cannot process): +.TP +\fB\-maxlen \fIlength\fR +. +Indicates that the output should be split into lines of no more than +\fIlength\fR characters. By default, lines are split every 61 characters, and +this must be in the range 3 to 85 due to limitations in the encoding. +.TP +\fB\-wrapchar \fIcharacter\fR +. +Indicates that, when lines are split because of the \fB\-maxlen\fR option, +\fIcharacter\fR should be used to separate lines. By default, this is a +newline character, +.QW \en . +.PP +During decoding, the following options are supported: +.TP +\fB\-strict\fR +. +Instructs the decoder to throw an error if it encounters unexpected whitespace +characters. Otherwise it ignores them. +.PP +Note that neither the encoder nor the decoder handle the header and footer of +the uuencode format. +.RE +.VE 8.6 .SH "BINARY FORMAT" .PP The \fBbinary format\fR command generates a binary string whose layout @@ -42,7 +147,7 @@ is a non-negative decimal integer or \fB*\fR, which normally indicates that all of the items in the value are to be used. If the number of arguments does not match the number of fields in the format string that consume arguments, then an error is generated. The flag character -is ignored for for \fBbinary format\fR. +is ignored for \fBbinary format\fR. .PP Here is a small example to clarify the relation between the field specifiers and the arguments: @@ -210,13 +315,11 @@ will return a string equivalent to \fB\ex00\ex03\exff\exfd\ex01\ex02\fR. .RE .IP \fBt\fR 5 -.VS 8.5 This form (mnemonically \fItiny\fR) is the same as \fBs\fR and \fBS\fR except that it stores the 16-bit integers in the output string in the native byte order of the machine where the Tcl script is running. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBi\fR 5 This form is the same as \fBc\fR except that it stores one or more 32-bit integers in little-endian byte order in the output string. The @@ -242,14 +345,12 @@ will return a string equivalent to \fB\ex00\ex00\ex00\ex03\exff\exff\exff\exfd\ex00\ex01\ex00\ex00\fR .RE .IP \fBn\fR 5 -.VS 8.5 This form (mnemonically \fInumber\fR or \fInormal\fR) is the same as \fBi\fR and \fBI\fR except that it stores the 32-bit integers in the output string in the native byte order of the machine where the Tcl script is running. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBw\fR 5 This form is the same as \fBc\fR except that it stores one or more 64-bit integers in little-endian byte order in the output string. The @@ -273,14 +374,12 @@ For example, will return the string \fBBigEndian\fR .RE .IP \fBm\fR 5 -.VS 8.5 This form (mnemonically the mirror of \fBw\fR) is the same as \fBw\fR and \fBW\fR except that it stores the 64-bit integers in the output string in the native byte order of the machine where the Tcl script is running. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBf\fR 5 This form is the same as \fBc\fR except that it stores one or more one or more single-precision floating point numbers in the machine's native @@ -302,18 +401,14 @@ will return a string equivalent to \fB\excd\excc\excc\ex3f\ex9a\ex99\ex59\ex40\fR. .RE .IP \fBr\fR 5 -.VS 8.5 This form (mnemonically \fIreal\fR) is the same as \fBf\fR except that it stores the single-precision floating point numbers in little-endian order. This conversion only produces meaningful output when used on machines which use the IEEE floating point representation (very common, but not universal.) -.VE 8.5 .IP \fBR\fR 5 -.VS 8.5 This form is the same as \fBr\fR except that it stores the single-precision floating point numbers in big-endian order. -.VE 8.5 .IP \fBd\fR 5 This form is the same as \fBf\fR except that it stores one or more one or more double-precision floating point numbers in the machine's native @@ -327,18 +422,14 @@ will return a string equivalent to \fB\ex9a\ex99\ex99\ex99\ex99\ex99\exf9\ex3f\fR. .RE .IP \fBq\fR 5 -.VS 8.5 This form (mnemonically the mirror of \fBd\fR) is the same as \fBd\fR except that it stores the double-precision floating point numbers in little-endian order. This conversion only produces meaningful output when used on machines which use the IEEE floating point representation (very common, but not universal.) -.VE 8.5 .IP \fBQ\fR 5 -.VS 8.5 This form is the same as \fBq\fR except that it stores the double-precision floating point numbers in big-endian order. -.VE 8.5 .IP \fBx\fR 5 Stores \fIcount\fR null bytes in the output string. If \fIcount\fR is not specified, stores one null byte. If \fIcount\fR is \fB*\fR, @@ -543,9 +634,10 @@ reverse (low-to-high) order within each byte. For example, .CE will return \fB2\fR with \fB706\fR stored in \fIvar1\fR and \fB502143\fR stored in \fIvar2\fR. -.RE +.PP Note that most code that wishes to parse the hexadecimal digits from multiple bytes in order should use the \fBH\fR format. +.RE .IP \fBc\fR 5 The data is turned into \fIcount\fR 8-bit signed integers and stored in the corresponding variable as a list. If \fIcount\fR is \fB*\fR, @@ -595,13 +687,11 @@ will return \fB2\fR with \fB5 7\fR stored in \fIvar1\fR and \fB\-16\fR stored in \fIvar2\fR. .RE .IP \fBt\fR 5 -.VS 8.5 The data is interpreted as \fIcount\fR 16-bit signed integers represented in the native byte order of the machine running the Tcl script. It is otherwise identical to \fBs\fR and \fBS\fR. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBi\fR 5 The data is interpreted as \fIcount\fR 32-bit signed integers represented in little-endian byte order. The integers are stored in @@ -635,13 +725,11 @@ will return \fB2\fR with \fB5 7\fR stored in \fIvar1\fR and \fB\-16\fR stored in \fIvar2\fR. .RE .IP \fBn\fR 5 -.VS 8.5 The data is interpreted as \fIcount\fR 32-bit signed integers represented in the native byte order of the machine running the Tcl script. It is otherwise identical to \fBi\fR and \fBI\fR. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBw\fR 5 The data is interpreted as \fIcount\fR 64-bit signed integers represented in little-endian byte order. The integers are stored in @@ -671,13 +759,11 @@ will return \fB2\fR with \fB21474836487\fR stored in \fIvar1\fR and \fB\-16\fR stored in \fIvar2\fR. .RE .IP \fBm\fR 5 -.VS 8.5 The data is interpreted as \fIcount\fR 64-bit signed integers represented in the native byte order of the machine running the Tcl script. It is otherwise identical to \fBw\fR and \fBW\fR. To determine what the native byte order of the machine is, refer to the \fBbyteOrder\fR element of the \fBtcl_platform\fR array. -.VE 8.5 .IP \fBf\fR 5 The data is interpreted as \fIcount\fR single-precision floating point numbers in the machine's native representation. The floating point @@ -698,19 +784,15 @@ will return \fB1\fR with \fB1.6000000238418579\fR stored in \fIvar1\fR. .RE .IP \fBr\fR 5 -.VS 8.5 This form is the same as \fBf\fR except that the data is interpreted as \fIcount\fR single-precision floating point number in little-endian order. This conversion is not portable to the minority of systems not using IEEE floating point representations. -.VE 8.5 .IP \fBR\fR 5 -.VS 8.5 This form is the same as \fBf\fR except that the data is interpreted as \fIcount\fR single-precision floating point number in big-endian order. This conversion is not portable to the minority of systems not using IEEE floating point representations. -.VE 8.5 .IP \fBd\fR 5 This form is the same as \fBf\fR except that the data is interpreted as \fIcount\fR double-precision floating point numbers in the @@ -724,19 +806,15 @@ will return \fB1\fR with \fB1.6000000000000001\fR stored in \fIvar1\fR. .RE .IP \fBq\fR 5 -.VS 8.5 This form is the same as \fBd\fR except that the data is interpreted as \fIcount\fR double-precision floating point number in little-endian order. This conversion is not portable to the minority of systems not using IEEE floating point representations. -.VE 8.5 .IP \fBQ\fR 5 -.VS 8.5 This form is the same as \fBd\fR except that the data is interpreted as \fIcount\fR double-precision floating point number in big-endian order. This conversion is not portable to the minority of systems not using IEEE floating point representations. -.VE 8.5 .IP \fBx\fR 5 Moves the cursor forward \fIcount\fR bytes in \fIstring\fR. If \fIcount\fR is \fB*\fR or is larger than the number of bytes after the @@ -778,6 +856,7 @@ will return \fB2\fR with \fB1 2\fR stored in \fIvar1\fR and \fB020304\fR stored in \fIvar2\fR. .RE .SH "PORTABILITY ISSUES" +.PP The \fBr\fR, \fBR\fR, \fBq\fR and \fBQ\fR conversions will only work reliably for transferring data between computers which are all using IEEE floating point representations. This is very common, but not @@ -785,8 +864,10 @@ universal. To transfer floating-point numbers portably between all architectures, use their textual representation (as produced by \fBformat\fR) instead. .SH EXAMPLES +.PP This is a procedure to write a Tcl string to a binary-encoded channel as UTF-8 data preceded by a length word: +.PP .CS proc \fIwriteString\fR {channel string} { set data [encoding convertto utf-8 $string] @@ -797,6 +878,7 @@ proc \fIwriteString\fR {channel string} { .PP This procedure reads a string from a channel that was written by the previously presented \fIwriteString\fR procedure: +.PP .CS proc \fIreadString\fR {channel} { if {![\fBbinary scan\fR [read $channel 4] I length]} { @@ -806,7 +888,21 @@ proc \fIreadString\fR {channel} { return [encoding convertfrom utf-8 $data] } .CE +.PP +This converts the contents of a file (named in the variable \fIfilename\fR) to +base64 and prints them: +.PP +.CS +set f [open $filename rb] +set data [read $f] +close $f +puts [\fBbinary encode\fR base64 \-maxlen 64 $data] +.CE .SH "SEE ALSO" -format(n), scan(n), tclvars(n) +encoding(n), format(n), scan(n), string(n), tcl_platform(n) .SH KEYWORDS binary, format, scan +'\" Local Variables: +'\" mode: nroff +'\" fill-column: 78 +'\" End: |