view docs/scripts/man1/SplitSDFiles.1 @ 0:4816e4a8ae95 draft default tip

Uploaded

.\" 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 "SPLITSDFILES 1"
.TH SPLITSDFILES 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"
SplitSDFiles.pl \- Split SDFile(s) into multiple SD files
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
SplitSDFiles.pl SDFile(s)...
.PP
SplitSDFiles.pl [\fB\-c, \-\-CmpdsMode\fR DataField | MolName | RootPrefix]
[\fB\-d, \-\-DataField\fR DataFieldName] [\fB\-h, \-\-help\fR] [\fB\-m, \-\-mode\fR Cmpds | Files]
[\fB\-n, \-\-numfiles\fR number] [\fB\-\-numcmpds\fR number] [\fB\-o, \-\-overwrite\fR]
[\fB\-r, \-\-root\fR rootname] [\fB\-w,\-\-workingdir\fR dirname] SDFile(s)...
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Split \fISDFile(s)\fR into multiple \s-1SD\s0 files. Each new SDFile contains a compound
subset of similar size from the initial file. Multiple \fISDFile(s)\fR names are separated
by space. The valid file extensions are \fI.sdf\fR and \fI.sd\fR. All other file names are
ignored. All the \s-1SD\s0 files in a current directory can be specified either by \fI*.sdf\fR
or the current directory name.
.SH "OPTIONS"
.IX Header "OPTIONS"
.IP "\fB\-c, \-\-CmpdsMode\fR \fIDataField | MolName | RootPrefix\fR" 4
.IX Item "-c, --CmpdsMode DataField | MolName | RootPrefix"
This option is only used during \fICmpds\fR value of <\-m, \-\-mode> option with
specified \fB\-\-numcmpds\fR value of 1.
.Sp
Specify how to generate new file names during \fICmpds\fR value of <\-m, \-\-mode>
option: use \fISDFile(s)\fR datafield value or molname line for a specific compound;
generate a sequential \s-1ID\s0 using root prefix specified by \fB\-r, \-\-root\fR option.
.Sp
Possible values: \fIDataField | MolName | RootPrefix | RootPrefix\fR.
Default: \fIRootPrefix\fR.
.Sp
For empty \fIMolName\fR and \fIDataField\fR values during these specified modes, file
name is automatically generated using \fIRootPrefix\fR.
.Sp
For \fIRootPrefix\fR value of \fB\-c, \-\-CmpdsMode\fR option, new file names are
generated using by appending compound record number to value of \fB\-r, \-\-root\fR option.
For example: \fIRootName\fRCmd<RecordNumber>.sdf.
.Sp
Allowed characters in file names are: a\-zA\-Z0\-9_. All other characters in datafield
values, molname line, and root prefix are ignore during generation of file names.
.IP "\fB\-d, \-\-DataField\fR \fIDataFieldName\fR" 4
.IX Item "-d, --DataField DataFieldName"
This option is only used during \fIDataField\fR value of <\-c, \-\-CmpdsMode> option.
.Sp
Specify \fISDFile(s)\fR datafield label name whose value is used for generation of new file
for a specific compound. Default value: \fINone\fR.
.IP "\fB\-h, \-\-help\fR" 4
.IX Item "-h, --help"
Print this help message.
.IP "\fB\-m, \-\-mode\fR \fICmpds | Files\fR" 4
.IX Item "-m, --mode Cmpds | Files"
Specify how to split \fISDFile(s)\fR: split into files with each file containing specified
number of compounds or split into a specified number of files.
.Sp
Possible values: \fICmpds | Files\fR. Default: \fIFiles\fR.
.Sp
For \fICmpds\fR value of \fB\-m, \-\-mode\fR option, value of \fB\-\-numcmpds\fR option
determines the number of new files. And value of \fB\-n, \-\-numfiles\fR option is
used to figure out the number of new files for \fIFiles\fR value of \fB\-m, \-\-mode\fR option.
.IP "\fB\-n, \-\-numfiles\fR \fInumber\fR" 4
.IX Item "-n, --numfiles number"
Number of new files to generate for each \fISDFile(s)\fR. Default: \fI2\fR.
.Sp
This value is only used during \fIFiles\fR value of \fB\-m, \-\-mode\fR option.
.IP "\fB\-\-numcmpds\fR \fInumber\fR" 4
.IX Item "--numcmpds number"
Number of compounds in each new file corresponding to each \fISDFile(s)\fR.
Default: \fI1\fR.
.Sp
This value is only used during \fICmpds\fR value of \fB\-m, \-\-mode\fR option.
.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 names are generated using the root: <Root>Part<Count>.sdf.
Default new file names: <InitialSDFileName> Part<Count>.sdf. This option
is ignored for multiple input files.
.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 split each \s-1SD\s0 file into 5 new \s-1SD\s0 files, type:
.PP
.Vb 2
\&    % SplitSDFiles.pl \-n 5 \-o Sample1.sdf Sample2.sdf
\&    % SplitSDFiles.pl \-n 5 \-o *.sdf
.Ve
.PP
To split Sample1.sdf into 10 new NewSample*.sdf files, type:
.PP
.Vb 1
\&    % SplitSDFiles.pl \-m Files \-n 10 \-r NewSample \-o Sample1.sdf
.Ve
.PP
To split Sample1.sdf into new NewSample*.sdf files containing maximum of 5 compounds
in each file, type:
.PP
.Vb 1
\&    % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 5 \-r NewSample \-o Sample1.sdf
.Ve
.PP
To split Sample1.sdf into new \s-1SD\s0 files containing one compound each with new file
names corresponding to molname line, type:
.PP
.Vb 1
\&    % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 1 \-c MolName \-o Sample1.sdf
.Ve
.PP
To split Sample1.sdf into new \s-1SD\s0 files containing one compound each with new file
names corresponding to value of datafield MolID, type:
.PP
.Vb 2
\&    % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 1 \-c DataField \-d MolID
\&      \-o Sample1.sdf
.Ve
.SH "AUTHOR"
.IX Header "AUTHOR"
Manish Sud <[e-mail]>
.SH "SEE ALSO"
.IX Header "SEE ALSO"
InfoSDFiles.pl, JoinSDFiles.pl, MolFilesToSD.pl, SDToMolFiles.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.