|
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 "MERGETEXTFILESWITHSD 1"
|
|
|
127 .TH MERGETEXTFILESWITHSD 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 MergeTextFilesWithSD.pl \- Merge CSV or TSV TextFile(s) into SDFile
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 MergeTextFilesWithSD.pl SDFile TextFile(s)...
|
|
|
137 .PP
|
|
|
138 MergeTextFilesWithSD.pl [\fB\-h, \-\-help\fR] [\fB\-\-indelim\fR comma | semicolon]
|
|
|
139 [\fB\-c, \-\-columns\fR colnum,...;... | collabel,...;...] [\fB\-k, \-\-keys\fR colkeynum;... | colkeylabel;...]
|
|
|
140 [\fB\-m, \-\-mode\fR colnum | collabel] [\fB\-o, \-\-overwrite\fR] [\fB\-r, \-\-root\fR rootname]
|
|
|
141 [\fB\-s, \-\-sdkey\fR sdfieldname] [\fB\-w, \-\-workingdir\fR dirname] SDFile TextFile(s)...
|
|
|
142 .SH "DESCRIPTION"
|
|
|
143 .IX Header "DESCRIPTION"
|
|
|
144 Merge multiple \s-1CSV\s0 or \s-1TSV\s0 \fITextFile(s)\fR into \fISDFile\fR. Unless \fB\-k \-\-keys\fR
|
|
|
145 option is used, data rows from all \fITextFile(s)\fR are added to \fISDFile\fR in a
|
|
|
146 sequential order, and the number of compounds in \fISDFile\fR is used to determine
|
|
|
147 how many rows of data are added from \fITextFile(s)\fR.
|
|
|
148 .PP
|
|
|
149 Multiple \fITextFile(s)\fR names are separated by spaces. The valid file extensions are \fI.csv\fR and
|
|
|
150 \&\fI.tsv\fR for comma/semicolon and tab delimited text files respectively. All other file names
|
|
|
151 are ignored. All the text files in a current directory can be specified by \fI*.csv\fR,
|
|
|
152 \&\fI*.tsv\fR, or the current directory name. The \fB\-\-indelim\fR option determines the
|
|
|
153 format of \fITextFile(s)\fR. Any file which doesn't correspond to the format indicated
|
|
|
154 by \fB\-\-indelim\fR option is ignored.
|
|
|
155 .SH "OPTIONS"
|
|
|
156 .IX Header "OPTIONS"
|
|
|
157 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
158 .IX Item "-h, --help"
|
|
|
159 Print this help message.
|
|
|
160 .IP "\fB\-\-indelim\fR \fIcomma | semicolon\fR" 4
|
|
|
161 .IX Item "--indelim comma | semicolon"
|
|
|
162 Input delimiter for \s-1CSV\s0 \fITextFile(s)\fR. Possible values: \fIcomma or semicolon\fR.
|
|
|
163 Default value: \fIcomma\fR. For \s-1TSV\s0 files, this option is ignored and \fItab\fR is used as a
|
|
|
164 delimiter.
|
|
|
165 .IP "\fB\-c, \-\-columns\fR \fIcolnum,...;... | collabel,...;...\fR" 4
|
|
|
166 .IX Item "-c, --columns colnum,...;... | collabel,...;..."
|
|
|
167 This value is mode specific. It is a list of columns to merge into \fISDFile\fR
|
|
|
168 specified by column numbers or labels for each text file delimited by \*(L";\*(R".
|
|
|
169 All \fITextFile(s)\fR are merged into \fISDFile\fR.
|
|
|
170 .Sp
|
|
|
171 Default value: \fIall;all;...\fR. By default, all columns from TextFile(s) are
|
|
|
172 merged into \fISDFile\fR.
|
|
|
173 .Sp
|
|
|
174 For \fIcolnum\fR mode, input value format is: \fIcolnum,...;colnum,...;...\fR. Example:
|
|
|
175 .Sp
|
|
|
176 .Vb 1
|
|
|
177 \& "1,2;1,3,4;7,8,9"
|
|
|
178 .Ve
|
|
|
179 .Sp
|
|
|
180 For \fIcollabel\fR mode, input value format is: \fIcollabel,...;collabel,...;...\fR. Example:
|
|
|
181 .Sp
|
|
|
182 .Vb 1
|
|
|
183 \& "MW,SumNO;SumNHOH,ClogP,PSA;MolName,Mol_Id,Extreg"
|
|
|
184 .Ve
|
|
|
185 .IP "\fB\-k, \-\-keys\fR \fIcolkeynum;... | colkeylabel;...\fR" 4
|
|
|
186 .IX Item "-k, --keys colkeynum;... | colkeylabel;..."
|
|
|
187 This value is mode specific. It specifies column keys to use for merging
|
|
|
188 \&\fITextFile(s)\fR into \fISDFile\fR. The column keys, delimited by \*(L";\*(R", are specified by column
|
|
|
189 numbers or labels for \fITextFile(s)\fR.
|
|
|
190 .Sp
|
|
|
191 By default, data rows from \fITextFile(s)\fR are merged into \fISDFile\fR in the order they appear.
|
|
|
192 .Sp
|
|
|
193 For \fIcolnum\fR mode, input value format is:\fIcolkeynum, colkeynum;...\fR. Example:
|
|
|
194 .Sp
|
|
|
195 .Vb 1
|
|
|
196 \& "1;3;7"
|
|
|
197 .Ve
|
|
|
198 .Sp
|
|
|
199 For \fIcollabel\fR mode, input value format is:\fIcolkeylabel, colkeylabel;...\fR. Example:
|
|
|
200 .Sp
|
|
|
201 .Vb 1
|
|
|
202 \& "Mol_Id;Mol_Id;Cmpd_Id"
|
|
|
203 .Ve
|
|
|
204 .IP "\fB\-m, \-\-mode\fR \fIcolnum | collabel\fR" 4
|
|
|
205 .IX Item "-m, --mode colnum | collabel"
|
|
|
206 Specify how to merge \fITextFile(s)\fR into \fISDFile\fR: using column numbers or column labels.
|
|
|
207 Possible values: \fIcolnum or collabel\fR. Default value: \fIcolnum\fR.
|
|
|
208 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
209 .IX Item "-o, --overwrite"
|
|
|
210 Overwrite existing files.
|
|
|
211 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
212 .IX Item "-r, --root rootname"
|
|
|
213 New \s-1SD\s0 file name is generated using the root: <Root>.sdf. Default file name:
|
|
|
214 <InitialSDFileName>MergedWith<FirstTextFileName>1To<Count>.sdf.
|
|
|
215 .IP "\fB\-s, \-\-sdkey\fR \fIsdfieldname\fR" 4
|
|
|
216 .IX Item "-s, --sdkey sdfieldname"
|
|
|
217 \&\fISDFile\fR data field name used as a key to merge data from TextFile(s). By default,
|
|
|
218 data rows from \fITextFile(s)\fR are merged into \fISDFile\fR in the order they appear.
|
|
|
219 .IP "\fB\-w, \-\-workingdir\fR \fIdirname\fR" 4
|
|
|
220 .IX Item "-w, --workingdir dirname"
|
|
|
221 Location of working directory. Default: current directory.
|
|
|
222 .SH "EXAMPLES"
|
|
|
223 .IX Header "EXAMPLES"
|
|
|
224 To merge Sample1.csv and Sample2.csv into Sample.sdf and generate
|
|
|
225 NewSample.sdf, type:
|
|
|
226 .PP
|
|
|
227 .Vb 2
|
|
|
228 \& % MergeTextFileswithSD.pl \-r NewSample \-o Sample.sdf
|
|
|
229 \& Sample1.csv Sample2.csv
|
|
|
230 .Ve
|
|
|
231 .PP
|
|
|
232 To merge all Sample*.tsv into Sample.sdf and generate NewSample.sdf file, type:
|
|
|
233 .PP
|
|
|
234 .Vb 2
|
|
|
235 \& % MergeTextFilesWithSD.pl \-r NewSample \-o Sample.sdf
|
|
|
236 \& Sample*.tsv
|
|
|
237 .Ve
|
|
|
238 .PP
|
|
|
239 To merge column numbers \*(L"1,2\*(R" and \*(L"3,4,5\*(R" from Sample2.csv and Sample3.csv
|
|
|
240 into Sample.sdf and to generate NewSample.sdf, type:
|
|
|
241 .PP
|
|
|
242 .Vb 2
|
|
|
243 \& % MergeTextFilesWithSD.pl \-r NewSample \-m colnum \-c "1,2;3,4,5"
|
|
|
244 \& \-o Sample.sdf Sample1.csv Sample2.csv
|
|
|
245 .Ve
|
|
|
246 .PP
|
|
|
247 To merge column \*(L"Mol_ID,Formula,MolWeight\*(R" and \*(L"Mol_ID,ChemBankID,NAME\*(R"
|
|
|
248 from Sample1.csv and Sample2.csv into Sample.sdf using \*(L"Mol_ID\*(R" as \s-1SD\s0 and column keys
|
|
|
249 to generate NewSample.sdf, type:
|
|
|
250 .PP
|
|
|
251 .Vb 3
|
|
|
252 \& % MergeTextFilesWithSD.pl \-r NewSample \-s Mol_ID \-k "Mol_ID;Mol_ID"
|
|
|
253 \& \-m collabel \-c "Mol_ID,Formula,MolWeight;Mol_ID,ChemBankID,NAME"
|
|
|
254 \& \-o Sample1.sdf Sample1.csv Sample2.csv
|
|
|
255 .Ve
|
|
|
256 .SH "AUTHOR"
|
|
|
257 .IX Header "AUTHOR"
|
|
|
258 Manish Sud <msud@san.rr.com>
|
|
|
259 .SH "SEE ALSO"
|
|
|
260 .IX Header "SEE ALSO"
|
|
|
261 ExtractFromSDFiles.pl, FilterSDFiles.pl, InfoSDFiles.pl, JoinSDFiles.pl, JoinTextFiles.pl,
|
|
|
262 MergeTextFiles.pl, ModifyTextFilesFormat.pl, SplitSDFiles.pl, SplitTextFiles.pl
|
|
|
263 .SH "COPYRIGHT"
|
|
|
264 .IX Header "COPYRIGHT"
|
|
|
265 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
266 .PP
|
|
|
267 This file is part of MayaChemTools.
|
|
|
268 .PP
|
|
|
269 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
270 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
271 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
272 any later version.
|
