view mayachemtools/docs/scripts/man1/MergeTextFilesWithSD.1 @ 5:9a001a14a022 draft

Deleted selected files

.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.ie \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.el \{\
.    de IX
..
.\}
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "MERGETEXTFILESWITHSD 1"
.TH MERGETEXTFILESWITHSD 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
MergeTextFilesWithSD.pl \- Merge CSV or TSV TextFile(s) into SDFile
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
MergeTextFilesWithSD.pl  SDFile TextFile(s)...
.PP
MergeTextFilesWithSD.pl  [\fB\-h, \-\-help\fR] [\fB\-\-indelim\fR comma | semicolon]
[\fB\-c, \-\-columns\fR colnum,...;... | collabel,...;...] [\fB\-k, \-\-keys\fR colkeynum;... | colkeylabel;...]
[\fB\-m, \-\-mode\fR colnum | collabel] [\fB\-o, \-\-overwrite\fR] [\fB\-r, \-\-root\fR rootname]
[\fB\-s, \-\-sdkey\fR sdfieldname] [\fB\-w, \-\-workingdir\fR dirname] SDFile TextFile(s)...
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Merge multiple \s-1CSV\s0 or \s-1TSV\s0 \fITextFile(s)\fR into \fISDFile\fR. Unless \fB\-k \-\-keys\fR
option is used, data rows from all \fITextFile(s)\fR are added to \fISDFile\fR in a
sequential order, and the number of compounds in \fISDFile\fR is used to determine
how many rows of data are added from \fITextFile(s)\fR.
.PP
Multiple \fITextFile(s)\fR names are separated by spaces. The valid file extensions are \fI.csv\fR and
\&\fI.tsv\fR for comma/semicolon and tab delimited text files respectively. All other file names
are ignored. All the text files in a current directory can be specified by \fI*.csv\fR,
\&\fI*.tsv\fR, or the current directory name. The \fB\-\-indelim\fR option determines the
format of \fITextFile(s)\fR. Any file which doesn't correspond to the format indicated
by \fB\-\-indelim\fR option is ignored.
.SH "OPTIONS"
.IX Header "OPTIONS"
.IP "\fB\-h, \-\-help\fR" 4
.IX Item "-h, --help"
Print this help message.
.IP "\fB\-\-indelim\fR \fIcomma | semicolon\fR" 4
.IX Item "--indelim comma | semicolon"
Input delimiter for \s-1CSV\s0 \fITextFile(s)\fR. Possible values: \fIcomma or semicolon\fR.
Default value: \fIcomma\fR. For \s-1TSV\s0 files, this option is ignored and \fItab\fR is used as a
delimiter.
.IP "\fB\-c, \-\-columns\fR \fIcolnum,...;... | collabel,...;...\fR" 4
.IX Item "-c, --columns colnum,...;... | collabel,...;..."
This value is mode specific. It is a list of columns to merge into \fISDFile\fR
specified by column numbers or labels for each text file delimited by \*(L";\*(R".
All \fITextFile(s)\fR are merged into \fISDFile\fR.
.Sp
Default value: \fIall;all;...\fR. By default, all columns from TextFile(s) are
merged into \fISDFile\fR.
.Sp
For \fIcolnum\fR mode, input value format is: \fIcolnum,...;colnum,...;...\fR. Example:
.Sp
.Vb 1
\&    "1,2;1,3,4;7,8,9"
.Ve
.Sp
For \fIcollabel\fR mode, input value format is: \fIcollabel,...;collabel,...;...\fR. Example:
.Sp
.Vb 1
\&    "MW,SumNO;SumNHOH,ClogP,PSA;MolName,Mol_Id,Extreg"
.Ve
.IP "\fB\-k, \-\-keys\fR \fIcolkeynum;... | colkeylabel;...\fR" 4
.IX Item "-k, --keys colkeynum;... | colkeylabel;..."
This value is mode specific. It specifies column keys to use for merging
\&\fITextFile(s)\fR into \fISDFile\fR. The column keys, delimited by \*(L";\*(R", are specified by column
numbers or labels for \fITextFile(s)\fR.
.Sp
By default, data rows from \fITextFile(s)\fR are merged into \fISDFile\fR in the order they appear.
.Sp
For \fIcolnum\fR mode, input value format is:\fIcolkeynum, colkeynum;...\fR. Example:
.Sp
.Vb 1
\&    "1;3;7"
.Ve
.Sp
For \fIcollabel\fR mode, input value format is:\fIcolkeylabel, colkeylabel;...\fR. Example:
.Sp
.Vb 1
\&    "Mol_Id;Mol_Id;Cmpd_Id"
.Ve
.IP "\fB\-m, \-\-mode\fR \fIcolnum | collabel\fR" 4
.IX Item "-m, --mode colnum | collabel"
Specify how to merge \fITextFile(s)\fR into \fISDFile\fR: using column numbers or column labels.
Possible values: \fIcolnum or collabel\fR. Default value: \fIcolnum\fR.
.IP "\fB\-o, \-\-overwrite\fR" 4
.IX Item "-o, --overwrite"
Overwrite existing files.
.IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
.IX Item "-r, --root rootname"
New \s-1SD\s0 file name is generated using the root: <Root>.sdf. Default file name:
<InitialSDFileName>MergedWith<FirstTextFileName>1To<Count>.sdf.
.IP "\fB\-s, \-\-sdkey\fR \fIsdfieldname\fR" 4
.IX Item "-s, --sdkey sdfieldname"
\&\fISDFile\fR data field name used as a key to merge data from TextFile(s). By default,
data rows from \fITextFile(s)\fR are merged into \fISDFile\fR in the order they appear.
.IP "\fB\-w, \-\-workingdir\fR \fIdirname\fR" 4
.IX Item "-w, --workingdir dirname"
Location of working directory. Default: current directory.
.SH "EXAMPLES"
.IX Header "EXAMPLES"
To merge Sample1.csv and Sample2.csv into Sample.sdf and generate
NewSample.sdf, type:
.PP
.Vb 2
\&    % MergeTextFileswithSD.pl \-r NewSample \-o Sample.sdf
\&      Sample1.csv Sample2.csv
.Ve
.PP
To merge all Sample*.tsv into Sample.sdf and generate NewSample.sdf file, type:
.PP
.Vb 2
\&    % MergeTextFilesWithSD.pl \-r NewSample \-o Sample.sdf
\&      Sample*.tsv
.Ve
.PP
To merge column numbers \*(L"1,2\*(R" and \*(L"3,4,5\*(R" from Sample2.csv and Sample3.csv
into Sample.sdf and to generate NewSample.sdf, type:
.PP
.Vb 2
\&    % MergeTextFilesWithSD.pl \-r NewSample \-m colnum \-c "1,2;3,4,5"
\&      \-o Sample.sdf Sample1.csv Sample2.csv
.Ve
.PP
To merge column \*(L"Mol_ID,Formula,MolWeight\*(R" and \*(L"Mol_ID,ChemBankID,NAME\*(R"
from Sample1.csv and Sample2.csv into Sample.sdf using \*(L"Mol_ID\*(R" as \s-1SD\s0 and column keys
to generate NewSample.sdf, type:
.PP
.Vb 3
\&    % MergeTextFilesWithSD.pl \-r NewSample \-s Mol_ID \-k "Mol_ID;Mol_ID"
\&      \-m collabel \-c "Mol_ID,Formula,MolWeight;Mol_ID,ChemBankID,NAME"
\&      \-o Sample1.sdf Sample1.csv Sample2.csv
.Ve
.SH "AUTHOR"
.IX Header "AUTHOR"
Manish Sud <[e-mail]>
.SH "SEE ALSO"
.IX Header "SEE ALSO"
ExtractFromSDFiles.pl, FilterSDFiles.pl, InfoSDFiles.pl, JoinSDFiles.pl, JoinTextFiles.pl,
MergeTextFiles.pl, ModifyTextFilesFormat.pl, SplitSDFiles.pl, SplitTextFiles.pl
.SH "COPYRIGHT"
.IX Header "COPYRIGHT"
Copyright (C) 2015 Manish Sud. All rights reserved.
.PP
This file is part of MayaChemTools.
.PP
MayaChemTools is free software; you can redistribute it and/or modify it under
the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
Software Foundation; either version 3 of the License, or (at your option)
any later version.