0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
2 .\"
|
|
3 .\" Standard preamble:
|
|
4 .\" ========================================================================
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
6 .if t .sp .5v
|
|
7 .if n .sp
|
|
8 ..
|
|
9 .de Vb \" Begin verbatim text
|
|
10 .ft CW
|
|
11 .nf
|
|
12 .ne \\$1
|
|
13 ..
|
|
14 .de Ve \" End verbatim text
|
|
15 .ft R
|
|
16 .fi
|
|
17 ..
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
23 .\" nothing in troff, for use with C<>.
|
|
24 .tr \(*W-
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
26 .ie n \{\
|
|
27 . ds -- \(*W-
|
|
28 . ds PI pi
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
31 . ds L" ""
|
|
32 . ds R" ""
|
|
33 . ds C` ""
|
|
34 . ds C' ""
|
|
35 'br\}
|
|
36 .el\{\
|
|
37 . ds -- \|\(em\|
|
|
38 . ds PI \(*p
|
|
39 . ds L" ``
|
|
40 . ds R" ''
|
|
41 'br\}
|
|
42 .\"
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
45 .el .ds Aq '
|
|
46 .\"
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
50 .\" output yourself in some meaningful fashion.
|
|
51 .ie \nF \{\
|
|
52 . de IX
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
54 ..
|
|
55 . nr % 0
|
|
56 . rr F
|
|
57 .\}
|
|
58 .el \{\
|
|
59 . de IX
|
|
60 ..
|
|
61 .\}
|
|
62 .\"
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
65 . \" fudge factors for nroff and troff
|
|
66 .if n \{\
|
|
67 . ds #H 0
|
|
68 . ds #V .8m
|
|
69 . ds #F .3m
|
|
70 . ds #[ \f1
|
|
71 . ds #] \fP
|
|
72 .\}
|
|
73 .if t \{\
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
75 . ds #V .6m
|
|
76 . ds #F 0
|
|
77 . ds #[ \&
|
|
78 . ds #] \&
|
|
79 .\}
|
|
80 . \" simple accents for nroff and troff
|
|
81 .if n \{\
|
|
82 . ds ' \&
|
|
83 . ds ` \&
|
|
84 . ds ^ \&
|
|
85 . ds , \&
|
|
86 . ds ~ ~
|
|
87 . ds /
|
|
88 .\}
|
|
89 .if t \{\
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
96 .\}
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
107 . \" corrections for vroff
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
112 \{\
|
|
113 . ds : e
|
|
114 . ds 8 ss
|
|
115 . ds o a
|
|
116 . ds d- d\h'-1'\(ga
|
|
117 . ds D- D\h'-1'\(hy
|
|
118 . ds th \o'bp'
|
|
119 . ds Th \o'LP'
|
|
120 . ds ae ae
|
|
121 . ds Ae AE
|
|
122 .\}
|
|
123 .rm #[ #] #H #V #F C
|
|
124 .\" ========================================================================
|
|
125 .\"
|
|
126 .IX Title "SPLITSDFILES 1"
|
|
127 .TH SPLITSDFILES 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
129 .\" way too many mistakes in technical documents.
|
|
130 .if n .ad l
|
|
131 .nh
|
|
132 .SH "NAME"
|
|
133 SplitSDFiles.pl \- Split SDFile(s) into multiple SD files
|
|
134 .SH "SYNOPSIS"
|
|
135 .IX Header "SYNOPSIS"
|
|
136 SplitSDFiles.pl SDFile(s)...
|
|
137 .PP
|
|
138 SplitSDFiles.pl [\fB\-c, \-\-CmpdsMode\fR DataField | MolName | RootPrefix]
|
|
139 [\fB\-d, \-\-DataField\fR DataFieldName] [\fB\-h, \-\-help\fR] [\fB\-m, \-\-mode\fR Cmpds | Files]
|
|
140 [\fB\-n, \-\-numfiles\fR number] [\fB\-\-numcmpds\fR number] [\fB\-o, \-\-overwrite\fR]
|
|
141 [\fB\-r, \-\-root\fR rootname] [\fB\-w,\-\-workingdir\fR dirname] SDFile(s)...
|
|
142 .SH "DESCRIPTION"
|
|
143 .IX Header "DESCRIPTION"
|
|
144 Split \fISDFile(s)\fR into multiple \s-1SD\s0 files. Each new SDFile contains a compound
|
|
145 subset of similar size from the initial file. Multiple \fISDFile(s)\fR names are separated
|
|
146 by space. The valid file extensions are \fI.sdf\fR and \fI.sd\fR. All other file names are
|
|
147 ignored. All the \s-1SD\s0 files in a current directory can be specified either by \fI*.sdf\fR
|
|
148 or the current directory name.
|
|
149 .SH "OPTIONS"
|
|
150 .IX Header "OPTIONS"
|
|
151 .IP "\fB\-c, \-\-CmpdsMode\fR \fIDataField | MolName | RootPrefix\fR" 4
|
|
152 .IX Item "-c, --CmpdsMode DataField | MolName | RootPrefix"
|
|
153 This option is only used during \fICmpds\fR value of <\-m, \-\-mode> option with
|
|
154 specified \fB\-\-numcmpds\fR value of 1.
|
|
155 .Sp
|
|
156 Specify how to generate new file names during \fICmpds\fR value of <\-m, \-\-mode>
|
|
157 option: use \fISDFile(s)\fR datafield value or molname line for a specific compound;
|
|
158 generate a sequential \s-1ID\s0 using root prefix specified by \fB\-r, \-\-root\fR option.
|
|
159 .Sp
|
|
160 Possible values: \fIDataField | MolName | RootPrefix | RootPrefix\fR.
|
|
161 Default: \fIRootPrefix\fR.
|
|
162 .Sp
|
|
163 For empty \fIMolName\fR and \fIDataField\fR values during these specified modes, file
|
|
164 name is automatically generated using \fIRootPrefix\fR.
|
|
165 .Sp
|
|
166 For \fIRootPrefix\fR value of \fB\-c, \-\-CmpdsMode\fR option, new file names are
|
|
167 generated using by appending compound record number to value of \fB\-r, \-\-root\fR option.
|
|
168 For example: \fIRootName\fRCmd<RecordNumber>.sdf.
|
|
169 .Sp
|
|
170 Allowed characters in file names are: a\-zA\-Z0\-9_. All other characters in datafield
|
|
171 values, molname line, and root prefix are ignore during generation of file names.
|
|
172 .IP "\fB\-d, \-\-DataField\fR \fIDataFieldName\fR" 4
|
|
173 .IX Item "-d, --DataField DataFieldName"
|
|
174 This option is only used during \fIDataField\fR value of <\-c, \-\-CmpdsMode> option.
|
|
175 .Sp
|
|
176 Specify \fISDFile(s)\fR datafield label name whose value is used for generation of new file
|
|
177 for a specific compound. Default value: \fINone\fR.
|
|
178 .IP "\fB\-h, \-\-help\fR" 4
|
|
179 .IX Item "-h, --help"
|
|
180 Print this help message.
|
|
181 .IP "\fB\-m, \-\-mode\fR \fICmpds | Files\fR" 4
|
|
182 .IX Item "-m, --mode Cmpds | Files"
|
|
183 Specify how to split \fISDFile(s)\fR: split into files with each file containing specified
|
|
184 number of compounds or split into a specified number of files.
|
|
185 .Sp
|
|
186 Possible values: \fICmpds | Files\fR. Default: \fIFiles\fR.
|
|
187 .Sp
|
|
188 For \fICmpds\fR value of \fB\-m, \-\-mode\fR option, value of \fB\-\-numcmpds\fR option
|
|
189 determines the number of new files. And value of \fB\-n, \-\-numfiles\fR option is
|
|
190 used to figure out the number of new files for \fIFiles\fR value of \fB\-m, \-\-mode\fR option.
|
|
191 .IP "\fB\-n, \-\-numfiles\fR \fInumber\fR" 4
|
|
192 .IX Item "-n, --numfiles number"
|
|
193 Number of new files to generate for each \fISDFile(s)\fR. Default: \fI2\fR.
|
|
194 .Sp
|
|
195 This value is only used during \fIFiles\fR value of \fB\-m, \-\-mode\fR option.
|
|
196 .IP "\fB\-\-numcmpds\fR \fInumber\fR" 4
|
|
197 .IX Item "--numcmpds number"
|
|
198 Number of compounds in each new file corresponding to each \fISDFile(s)\fR.
|
|
199 Default: \fI1\fR.
|
|
200 .Sp
|
|
201 This value is only used during \fICmpds\fR value of \fB\-m, \-\-mode\fR option.
|
|
202 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
203 .IX Item "-o, --overwrite"
|
|
204 Overwrite existing files.
|
|
205 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
206 .IX Item "-r, --root rootname"
|
|
207 New \s-1SD\s0 file names are generated using the root: <Root>Part<Count>.sdf.
|
|
208 Default new file names: <InitialSDFileName> Part<Count>.sdf. This option
|
|
209 is ignored for multiple input files.
|
|
210 .IP "\fB\-w,\-\-workingdir\fR \fIdirname\fR" 4
|
|
211 .IX Item "-w,--workingdir dirname"
|
|
212 Location of working directory. Default: current directory.
|
|
213 .SH "EXAMPLES"
|
|
214 .IX Header "EXAMPLES"
|
|
215 To split each \s-1SD\s0 file into 5 new \s-1SD\s0 files, type:
|
|
216 .PP
|
|
217 .Vb 2
|
|
218 \& % SplitSDFiles.pl \-n 5 \-o Sample1.sdf Sample2.sdf
|
|
219 \& % SplitSDFiles.pl \-n 5 \-o *.sdf
|
|
220 .Ve
|
|
221 .PP
|
|
222 To split Sample1.sdf into 10 new NewSample*.sdf files, type:
|
|
223 .PP
|
|
224 .Vb 1
|
|
225 \& % SplitSDFiles.pl \-m Files \-n 10 \-r NewSample \-o Sample1.sdf
|
|
226 .Ve
|
|
227 .PP
|
|
228 To split Sample1.sdf into new NewSample*.sdf files containing maximum of 5 compounds
|
|
229 in each file, type:
|
|
230 .PP
|
|
231 .Vb 1
|
|
232 \& % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 5 \-r NewSample \-o Sample1.sdf
|
|
233 .Ve
|
|
234 .PP
|
|
235 To split Sample1.sdf into new \s-1SD\s0 files containing one compound each with new file
|
|
236 names corresponding to molname line, type:
|
|
237 .PP
|
|
238 .Vb 1
|
|
239 \& % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 1 \-c MolName \-o Sample1.sdf
|
|
240 .Ve
|
|
241 .PP
|
|
242 To split Sample1.sdf into new \s-1SD\s0 files containing one compound each with new file
|
|
243 names corresponding to value of datafield MolID, type:
|
|
244 .PP
|
|
245 .Vb 2
|
|
246 \& % SplitSDFiles.pl \-m Cmpds \-\-numcmpds 1 \-c DataField \-d MolID
|
|
247 \& \-o Sample1.sdf
|
|
248 .Ve
|
|
249 .SH "AUTHOR"
|
|
250 .IX Header "AUTHOR"
|
|
251 Manish Sud <msud@san.rr.com>
|
|
252 .SH "SEE ALSO"
|
|
253 .IX Header "SEE ALSO"
|
|
254 InfoSDFiles.pl, JoinSDFiles.pl, MolFilesToSD.pl, SDToMolFiles.pl
|
|
255 .SH "COPYRIGHT"
|
|
256 .IX Header "COPYRIGHT"
|
|
257 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
258 .PP
|
|
259 This file is part of MayaChemTools.
|
|
260 .PP
|
|
261 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
262 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
263 Software Foundation; either version 3 of the License, or (at your option)
|
|
264 any later version.
|