|
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 "EXTRACTFROMTEXTFILES 1"
|
|
|
127 .TH EXTRACTFROMTEXTFILES 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 ExtractFromTextFiles.pl \- Extract specific data from TextFile(s)
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 ExtractFromTextFiles.pl TextFile(s)...
|
|
|
137 .PP
|
|
|
138 ExtractFromTextFiles.pl [\fB\-c, \-\-colmode\fR colnum | collabel] [\fB\-\-categorycol \fR number | string]
|
|
|
139 [\fB\-\-columns\fR \*(L"colnum,[colnum]...\*(R" | \*(L"collabel,[collabel]...\*(R"] [\fB\-h, \-\-help\fR]
|
|
|
140 [\fB\-\-indelim\fR \fIcomma | semicolon\fR] [\fB\-m, \-\-mode \fR \fIcolumns | rows | categories\fR]
|
|
|
141 [\fB\-o, \-\-overwrite\fR] [\fB\-\-outdelim\fR \fIcomma | tab | semicolon\fR] [\fB\-q, \-\-quote\fR \fIyes | no\fR]
|
|
|
142 [\fB\-\-rows\fR \*(L"colid,value,criteria...\*(R" | \*(L"colid,value...\*(R" | \*(L"colid,mincolvalue,maxcolvalue\*(R" | \*(L"rownum,rownum,...\*(R" | colid | \*(L"minrownum,maxrownum\*(R"]
|
|
|
143 [ \fB\-\-rowsmode\fR rowsbycolvalue | rowsbycolvaluelist | rowsbycolvaluerange | rowbymincolvalue | rowbymaxcolvalue | rownums | rownumrange]
|
|
|
144 [\fB\-r, \-\-root\fR \fIrootname\fR] [\fB\-w, \-\-workingdir\fR \fIdirname\fR] TextFile(s)...
|
|
|
145 .SH "DESCRIPTION"
|
|
|
146 .IX Header "DESCRIPTION"
|
|
|
147 Extract column(s)/row(s) data from \fITextFile(s)\fR identified by column numbers or labels. Or categorize
|
|
|
148 data using a specified column category. During categorization, a summary text file is
|
|
|
149 generated containing category name and count; an additional text file, containing data for
|
|
|
150 for each category, is also generated. The file names are separated by space. The
|
|
|
151 valid file extensions are \fI.csv\fR and \fI.tsv\fR for comma/semicolon and tab delimited
|
|
|
152 text files respectively. All other file names are ignored. All the text files in a
|
|
|
153 current directory can be specified by \fI*.csv\fR, \fI*.tsv\fR, or the current directory
|
|
|
154 name. The \fB\-\-indelim\fR option determines the format of \fITextFile(s)\fR. Any file
|
|
|
155 which doesn't correspond to the format indicated by \fB\-\-indelim\fR option is ignored.
|
|
|
156 .SH "OPTIONS"
|
|
|
157 .IX Header "OPTIONS"
|
|
|
158 .IP "\fB\-c, \-\-colmode\fR \fIcolnum | collabel\fR" 4
|
|
|
159 .IX Item "-c, --colmode colnum | collabel"
|
|
|
160 Specify how columns are identified in \fITextFile(s)\fR: using column number or column
|
|
|
161 label. Possible values: \fIcolnum or collabel\fR. Default value: \fIcolnum\fR.
|
|
|
162 .IP "\fB\-\-categorycol \fR \fInumber | string\fR" 4
|
|
|
163 .IX Item "--categorycol number | string"
|
|
|
164 Column used to categorize data. Default value: First column.
|
|
|
165 .Sp
|
|
|
166 For \fIcolnum\fR value of \fB\-c, \-\-colmode\fR option, input value is a column number.
|
|
|
167 Example: \fI1\fR.
|
|
|
168 .Sp
|
|
|
169 For \fIcollabel\fR value of \fB\-c, \-\-colmode\fR option, input value is a column label.
|
|
|
170 Example: \fIMol_ID\fR.
|
|
|
171 .ie n .IP "\fB\-\-columns\fR \fI""colnum,[colnum]..."" | ""collabel,[collabel]...""\fR" 4
|
|
|
172 .el .IP "\fB\-\-columns\fR \fI``colnum,[colnum]...'' | ``collabel,[collabel]...''\fR" 4
|
|
|
173 .IX Item "--columns colnum,[colnum]... | collabel,[collabel]..."
|
|
|
174 List of comma delimited columns to extract. Default value: First column.
|
|
|
175 .Sp
|
|
|
176 For \fIcolnum\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
177 \&\fIcolnum,colnum,...\fR. Example: \fI1,3,5\fR
|
|
|
178 .Sp
|
|
|
179 For \fIcollabel\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
180 \&\fIcollabel,collabel,..\fR. Example: \fIMol_ID,MolWeight\fR
|
|
|
181 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
182 .IX Item "-h, --help"
|
|
|
183 Print this help message.
|
|
|
184 .IP "\fB\-\-indelim\fR \fIcomma | semicolon\fR" 4
|
|
|
185 .IX Item "--indelim comma | semicolon"
|
|
|
186 Input delimiter for \s-1CSV\s0 \fITextFile(s)\fR. Possible values: \fIcomma or semicolon\fR.
|
|
|
187 Default value: \fIcomma\fR. For \s-1TSV\s0 files, this option is ignored and \fItab\fR is used as a
|
|
|
188 delimiter.
|
|
|
189 .IP "\fB\-m, \-\-mode \fR \fIcolumns | rows | categories\fR" 4
|
|
|
190 .IX Item "-m, --mode columns | rows | categories"
|
|
|
191 Specify what to extract from \fITextFile(s)\fR. Possible values: \fIcolumns, rows,
|
|
|
192 or categories\fR. Default value: \fIcolumns\fR.
|
|
|
193 .Sp
|
|
|
194 For \fIcolumns\fR mode, data for appropriate columns specified by \fB\-\-columns\fR option
|
|
|
195 is extracted from \fITextFile(s)\fR and placed into new text files.
|
|
|
196 .Sp
|
|
|
197 For \fIrows\fR mode, appropriate rows specified in conjuction with \fB\-\-rowsmode\fR and
|
|
|
198 \&\fBrows\fR options are extracted from \fITextFile(s)\fR and placed into new text files.
|
|
|
199 .Sp
|
|
|
200 For \fIcategories\fR mode, coulmn specified by \fB\-\-categorycol\fR is
|
|
|
201 used to categorize data, and a summary text file is generated
|
|
|
202 containing category name and count; an additional text file, containing data for
|
|
|
203 for each category, is also generated.
|
|
|
204 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
205 .IX Item "-o, --overwrite"
|
|
|
206 Overwrite existing files.
|
|
|
207 .IP "\fB\-\-outdelim\fR \fIcomma | tab | semicolon\fR." 4
|
|
|
208 .IX Item "--outdelim comma | tab | semicolon."
|
|
|
209 Output text file delimiter. Possible values: \fIcomma, tab, or semicolon\fR.
|
|
|
210 Default value: \fIcomma\fR
|
|
|
211 .IP "\fB\-q, \-\-quote\fR \fIyes | no\fR" 4
|
|
|
212 .IX Item "-q, --quote yes | no"
|
|
|
213 Put quotes around column values in output text file. Possible values: \fIyes or
|
|
|
214 no\fR. Default value: \fIyes\fR.
|
|
|
215 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
216 .IX Item "-r, --root rootname"
|
|
|
217 New file name is generated using the root: <Root>.<Ext>. Default for new file
|
|
|
218 names: <TextFile>CategoriesSummary.<Ext>, <TextFile>ExtractedColumns.<Ext>, and
|
|
|
219 <TextFile>ExtractedRows.<Ext> for \fIcategories\fR, \fIcolumns\fR, and \fIrows\fR mode
|
|
|
220 respectively. And <TextFile>Category<CategoryName>.<Ext>
|
|
|
221 for each category retrieved from each text file. The output file type determines <Ext>
|
|
|
222 value: csv and tsv for \s-1CSV\s0, and \s-1TSV\s0 files respectively.
|
|
|
223 .Sp
|
|
|
224 This option is ignored for multiple input files.
|
|
|
225 .ie n .IP "\fB\-\-rows\fR \fI""colid,value,criteria..."" | ""colid,value..."" | ""colid,mincolvalue,maxcolvalue"" | ""rownum,rownum,..."" | colid | ""minrownum,maxrownum""\fR" 4
|
|
|
226 .el .IP "\fB\-\-rows\fR \fI``colid,value,criteria...'' | ``colid,value...'' | ``colid,mincolvalue,maxcolvalue'' | ``rownum,rownum,...'' | colid | ``minrownum,maxrownum''\fR" 4
|
|
|
227 .IX Item "--rows colid,value,criteria... | colid,value... | colid,mincolvalue,maxcolvalue | rownum,rownum,... | colid | minrownum,maxrownum"
|
|
|
228 This value is \fB\-\-rowsmode\fR specific. In general, it's a list of comma separated column ids and
|
|
|
229 associated mode specific value. Based on Column ids specification, column label or number, is
|
|
|
230 controlled by \fB\-c, \-\-colmode\fR option.
|
|
|
231 .Sp
|
|
|
232 First line containing column labels is always written out. And value comparisons assume
|
|
|
233 numerical column data.
|
|
|
234 .Sp
|
|
|
235 For \fIrowsbycolvalue\fR mode, input value format contains these triplets:
|
|
|
236 \&\fIcolid,value, criteria...\fR. Possible values for criteria: \fIle, ge or eq\fR.
|
|
|
237 Examples:
|
|
|
238 .Sp
|
|
|
239 .Vb 2
|
|
|
240 \& MolWt,450,le
|
|
|
241 \& MolWt,450,le,LogP,5,le,SumNumNO,10,le,SumNHOH,5,le
|
|
|
242 .Ve
|
|
|
243 .Sp
|
|
|
244 For \fIrowsbycolvaluelist\fR mode, input value format is: \fIcolid,value...\fR. Examples:
|
|
|
245 .Sp
|
|
|
246 .Vb 2
|
|
|
247 \& Mol_ID,20
|
|
|
248 \& Mol_ID,20,1002,1115
|
|
|
249 .Ve
|
|
|
250 .Sp
|
|
|
251 For \fIrowsbycolvaluerange\fR mode, input value format is: \fIcolid,mincolvalue,maxcolvalue\fR. Examples:
|
|
|
252 .Sp
|
|
|
253 .Vb 1
|
|
|
254 \& MolWt,100,450
|
|
|
255 .Ve
|
|
|
256 .Sp
|
|
|
257 For \fIrowbymincolvalue, rowbymaxcolvalue\fR modes, input value format is: \fIcolid\fR.
|
|
|
258 .Sp
|
|
|
259 For \fIrownum\fR mode, input value format is: \fIrownum\fR. Default value: \fI2\fR.
|
|
|
260 .Sp
|
|
|
261 For \fIrownumrange\fR mode, input value format is: \fIminrownum, maxrownum\fR. Examples:
|
|
|
262 .Sp
|
|
|
263 .Vb 1
|
|
|
264 \& 10,40
|
|
|
265 .Ve
|
|
|
266 .IP "\fB\-\-rowsmode\fR \fIrowsbycolvalue | rowsbycolvaluelist | rowsbycolvaluerange | rowbymincolvalue | rowbymaxcolvalue | rownums | rownumrange\fR" 4
|
|
|
267 .IX Item "--rowsmode rowsbycolvalue | rowsbycolvaluelist | rowsbycolvaluerange | rowbymincolvalue | rowbymaxcolvalue | rownums | rownumrange"
|
|
|
268 Specify how to extract rows from \fITextFile(s)\fR. Possible values: \fIrowsbycolvalue, rowsbycolvaluelist, rowsbycolvaluerange,
|
|
|
269 rowbymincolvalue, rowbymaxcolvalue, rownum, rownumrange\fR. Default value: \fIrownum\fR.
|
|
|
270 .Sp
|
|
|
271 Use \fB\-\-rows\fR option to list rows criterion used for extraction of rows from
|
|
|
272 \&\fITextFile(s)\fR.
|
|
|
273 .IP "\fB\-w, \-\-workingdir\fR \fIdirname\fR" 4
|
|
|
274 .IX Item "-w, --workingdir dirname"
|
|
|
275 Location of working directory. Default: current directory.
|
|
|
276 .SH "EXAMPLES"
|
|
|
277 .IX Header "EXAMPLES"
|
|
|
278 To extract first column from a text file and generate a new \s-1CSV\s0 text file NewSample1.csv,
|
|
|
279 type:
|
|
|
280 .PP
|
|
|
281 .Vb 1
|
|
|
282 \& % ExtractFromTextFiles.pl \-r NewSample1 \-o Sample1.csv
|
|
|
283 .Ve
|
|
|
284 .PP
|
|
|
285 To extract columns Mol_ID, MolWeight, and \s-1NAME\s0 from Sample1.csv and generate a new
|
|
|
286 textfile NewSample1.tsv with no quotes, type:
|
|
|
287 .PP
|
|
|
288 .Vb 3
|
|
|
289 \& % ExtractFromTextFiles.pl \-m columns \-c collabel \-\-columns "Mol_ID,
|
|
|
290 \& MolWeight,NAME" \-\-outdelim tab \-\-quote no \-r NewSample1
|
|
|
291 \& \-o Sample1.csv
|
|
|
292 .Ve
|
|
|
293 .PP
|
|
|
294 To extract rows containing values for MolWeight column of less than 450 from
|
|
|
295 Sample1.csv and generate a new textfile NewSample1.csv, type:
|
|
|
296 .PP
|
|
|
297 .Vb 3
|
|
|
298 \& % ExtractFromTextFiles.pl \-m rows \-\-rowsmode rowsbycolvalue
|
|
|
299 \& \-c collabel \-\-rows MolWeight,450,le \-r NewSample1
|
|
|
300 \& \-o Sample1.csv
|
|
|
301 .Ve
|
|
|
302 .PP
|
|
|
303 To extract rows containing values for MolWeight column between 400 and 500 from
|
|
|
304 Sample1.csv and generate a new textfile NewSample1.csv, type:
|
|
|
305 .PP
|
|
|
306 .Vb 3
|
|
|
307 \& % ExtractFromTextFiles.pl \-m rows \-\-rowsmode rowsbycolvaluerange
|
|
|
308 \& \-c collabel \-\-rows MolWeight,450,500 \-r NewSample1
|
|
|
309 \& \-o Sample1.csv
|
|
|
310 .Ve
|
|
|
311 .PP
|
|
|
312 To extract a row containing minimum value for column MolWeight from Sample1.csv and generate
|
|
|
313 a new textfile NewSample1.csv, type:
|
|
|
314 .PP
|
|
|
315 .Vb 3
|
|
|
316 \& % ExtractFromTextFiles.pl \-m rows \-\-rowsmode rowbymincolvalue
|
|
|
317 \& \-c collabel \-\-rows MolWeight \-r NewSample1
|
|
|
318 \& \-o Sample1.csv
|
|
|
319 .Ve
|
|
|
320 .SH "AUTHOR"
|
|
|
321 .IX Header "AUTHOR"
|
|
|
322 Manish Sud <msud@san.rr.com>
|
|
|
323 .SH "SEE ALSO"
|
|
|
324 .IX Header "SEE ALSO"
|
|
|
325 JoinTextFiles.pl, MergeTextFilesWithSD.pl, ModifyTextFilesFormat.pl, SplitTextFiles.pl
|
|
|
326 .SH "COPYRIGHT"
|
|
|
327 .IX Header "COPYRIGHT"
|
|
|
328 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
329 .PP
|
|
|
330 This file is part of MayaChemTools.
|
|
|
331 .PP
|
|
|
332 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
333 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
334 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
335 any later version.
|
