'\" 
'\" Copyright (c) 2001 by Andreas Kupries <a.kupries@westend.com>
'\" All rights reserved.
'\" 
'\" RCS: @(#) $Id: csv.n,v 1.8 2002/01/18 20:51:15 andreas_kupries 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 2000/03/06 21:34:53 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 4c 8c 12c
.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 csv n 1.0 Csv "CSV processing"
.BS
'\" Note:  do not modify the .SH NAME line immediately below!
.SH NAME
::csv \- Procedures to handle CSV data
.SH SYNOPSIS
\fBpackage require Tcl 8.3\fR
.sp
\fBpackage require csv ?0.2?\fR
.sp
\fB::csv::join\fR \fIvalues {sepChar ,}\fR
.sp
\fB::csv::joinlist\fR \fIvalues {sepChar ,}\fR
.sp
\fB::csv::read2matrix\fR \fIchan m {sepChar ,} {expand none}\fR
.sp
\fB::csv::read2queue\fR \fIchan q {sepChar ,}\fR
.sp
\fB::csv::report\fR \fIcmd matrix ?chan?\fR
.sp
\fB::csv::split\fR \fIline {sepChar ,}\fR
.sp
\fB::csv::split2matrix\fR \fIq line {sepChar ,} {expand none}\fR
.sp
\fB::csv::split2queue\fR \fIq line {sepChar ,}\fR
.sp
\fB::csv::writematrix\fR \fIm chan {sepChar ,}\fR
.sp
\fB::csv::writequeue\fR \fIq chan {sepChar ,}\fR
.sp
.BE
.SH DESCRIPTION
.PP
The \fB::csv\fR package provides commands to manipulate information in
CSV format (CSV = Comma Separated Values).
.SH COMMANDS
.PP
The following commands are available:
.TP
\fB::csv::join\fR \fIvalues {sepChar ,}\fR
Takes a list of values and returns a string in CSV format containing
these values. The separator character can be defined by the caller,
but this is optional. The default is ",".
.TP
\fB::csv::joinlist\fR \fIvalues {sepChar ,}\fR
Takes a list of lists of values and returns a string in CSV format
containing these values. The separator character can be defined by the
caller, but this is optional. The default is ",". Each element of the
outer list is considered a record, these are separated by newlines in
the result. The elements of each record are formatted as usual (via
\fB::csv::join\fR).
.TP
\fB::csv::read2matrix\fR \fIchan m {sepChar ,} {expand none}\fR
A wrapper around \fB::csv::split2matrix\fR (see below) reading from
CSV-formatted lines from the specified channel (until EOF) and adding
it to the given matrix. For an explanation of the \fIexpand\fR
argument see \fB::csv::split2matrix\fR.
.TP
\fB::csv::read2queue\fR \fIchan q {sepChar ,}\fR
A wrapper around \fB::csv::split2queue\fR (see below) reading from
CSV-formatted lines from the specified channel (until EOF) and adding
it to the given queue.
.TP
\fB::csv::report\fR \fIcmd matrix ?chan?\fR
A report command which can be used by the matrix methods
\fBformat 2string\fR and \fBformat 2chan\fR. For the latter this
command delegates the work to \fB::csv::writematrix\fR. \fIcmd\fR is
expected to be either "printmatrix" or "printmatrix2channel". The
channel argument, \fIchan\fR, has to be present for the latter and
must not be present for the first.
.TP
\fB::csv::split\fR \fIline {sepChar ,}\fR
converts a \fIline\fR in CSV format into a list of the values
contained in the line. The character used to separate the values from
each other can be defined by the caller, via \fIsepChar\fR, but this
is optional. The default is ",".
.TP
\fB::csv::split2matrix\fR \fIm line {sepChar ,} {expand none}\fR
The same as \fB::csv::split\fR, but appends the resulting list as a
new row to the matrix \fIm\fR, using the method \fBadd row\fR. The
expansion mode specified via \fIexpand\fR determines how the command
handles a matrix with less columns than contained in \fIline\fR. The
allowed modes are:
.RS
.TP
\fBnone\fR
This is the \fBdefault mode\fR. In this mode it is the responsibility
of the caller to ensure that the matrix has enough columns to contain
the full line. If there are not enough columns the list of values is
silently truncated at the end to fit.
.TP
\fBempty\fR
In this mode the command expands an empty matrix to hold all columns
of the specified line, but goes no further. The overall effect is that
the first of a series of lines determines the number of columns in the
matrix and all following lines are truncated to that size, as if mode
\fBnone\fR was set.
.TP
\fBauto\fR
In this mode the command expands the matrix as needed to hold all
columns contained in \Iline\fR. The overall effect is that after
adding a series of lines the matrix will have enough columns to hold
all columns of the longest line encountered so far.
.RE
.TP
\fB::csv::split2queue\fR \fIq line {sepChar ,}\fR
The same as \fB::csv::split\fR, but appending the resulting list as a
single item to the queue \fIq\fR, using the method \fBput\fR.
.TP
\fB::csv::writematrix\fR \fIm chan {sepChar ,}\fR
A wrapper around \fB::csv::join\fR taking all rows in the matrix
\fIm\fR and writing them CSV formatted into the channel \fIchan\fR.
.TP
\fB::csv::writequeue\fR \fIq chan {sepChar ,}\fR
A wrapper around \fB::csv::join\fR taking all items in the queue
\fIq\fR (assumes that they are lists) and writing them CSV formatted
into the channel \fIchan\fR.
.SH FORMAT
.PP
Each record of a csv file (comma-separated values, as exported e.g. by
Excel) is a set of ASCII values separated by ",". For other languages
it may be ";" however, although this is not important for this case
(The functions provided here allow any separator character).
.PP
If a value contains itself the separator ",", then it (the value) is
put between "".
.PP
If a value contains ", it is replaced by "".
.SH EXAMPLE
.PP
The record
.TP
*
123,"123,521.2","Mary says ""Hello, I am Mary"""
.PP
is parsed as follows:
.TP
a)
123
.TP
b)
123,521.2
.TP
c)
Mary says "Hello, I am Mary"
.SH SEE ALSO
.PP
matrix, queue
.SH KEYWORDS
.PP
csv, matrix queue, package, tcllib
'\" -*- nroff -*-