|
0
|
1 #!/usr/bin/perl -w
|
|
|
2 #
|
|
|
3 # $RCSfile: SplitTextFiles.pl,v $
|
|
|
4 # $Date: 2015/02/28 20:46:21 $
|
|
|
5 # $Revision: 1.33 $
|
|
|
6 #
|
|
|
7 # Author: Manish Sud <msud@san.rr.com>
|
|
|
8 #
|
|
|
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
10 #
|
|
|
11 # This file is part of MayaChemTools.
|
|
|
12 #
|
|
|
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
14 # the terms of the GNU Lesser General Public License as published by the Free
|
|
|
15 # Software Foundation; either version 3 of the License, or (at your option) any
|
|
|
16 # later version.
|
|
|
17 #
|
|
|
18 # MayaChemTools is distributed in the hope that it will be useful, but without
|
|
|
19 # any warranty; without even the implied warranty of merchantability of fitness
|
|
|
20 # for a particular purpose. See the GNU Lesser General Public License for more
|
|
|
21 # details.
|
|
|
22 #
|
|
|
23 # You should have received a copy of the GNU Lesser General Public License
|
|
|
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
|
|
|
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
|
|
|
26 # Boston, MA, 02111-1307, USA.
|
|
|
27 #
|
|
|
28
|
|
|
29 use strict;
|
|
|
30 use FindBin; use lib "$FindBin::Bin/../lib";
|
|
|
31 use Getopt::Long;
|
|
|
32 use File::Basename;
|
|
|
33 use Text::ParseWords;
|
|
|
34 use Benchmark;
|
|
|
35 use FileUtil;
|
|
|
36 use TextUtil;
|
|
|
37
|
|
|
38 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
|
|
|
39
|
|
|
40 # Autoflush STDOUT
|
|
|
41 $| = 1;
|
|
|
42
|
|
|
43 # Starting message...
|
|
|
44 $ScriptName = basename $0;
|
|
|
45 print "\n$ScriptName:Starting...\n\n";
|
|
|
46 $StartTime = new Benchmark;
|
|
|
47
|
|
|
48 # Get the options and setup script...
|
|
|
49 SetupScriptUsage();
|
|
|
50 if ($Options{help} || @ARGV < 1) {
|
|
|
51 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
|
|
|
52 }
|
|
|
53
|
|
|
54 my(@TextFilesList);
|
|
|
55 @TextFilesList = ExpandFileNames(\@ARGV, "csv tsv");
|
|
|
56
|
|
|
57 # Process options...
|
|
|
58 print "Processing options...\n";
|
|
|
59 my(%OptionsInfo);
|
|
|
60 ProcessOptions();
|
|
|
61
|
|
|
62 print "Checking input text file(s)...\n";
|
|
|
63 my(%TextFilesInfo);
|
|
|
64 RetrieveTextFilesInfo();
|
|
|
65
|
|
|
66 # Generate output files...
|
|
|
67 my($FileIndex);
|
|
|
68 if (@TextFilesList > 1) {
|
|
|
69 print "\nProcessing text files...\n";
|
|
|
70 }
|
|
|
71 for $FileIndex (0 .. $#TextFilesList) {
|
|
|
72 if ($TextFilesInfo{FileOkay}[$FileIndex]) {
|
|
|
73 print "\nProcessing file $TextFilesList[$FileIndex]...\n";
|
|
|
74 SplitTextFile($FileIndex);
|
|
|
75 }
|
|
|
76 }
|
|
|
77
|
|
|
78 print "\n$ScriptName:Done...\n\n";
|
|
|
79
|
|
|
80 $EndTime = new Benchmark;
|
|
|
81 $TotalTime = timediff ($EndTime, $StartTime);
|
|
|
82 print "Total time: ", timestr($TotalTime), "\n";
|
|
|
83
|
|
|
84 ###############################################################################
|
|
|
85
|
|
|
86 # Split a Text file...
|
|
|
87 #
|
|
|
88 sub SplitTextFile {
|
|
|
89 my($FileIndex) = @_;
|
|
|
90 my($TextFile, $LineCount, $MaxLinesPerFile, $MaxNumOfFiles);
|
|
|
91
|
|
|
92 $TextFile = $TextFilesList[$FileIndex];
|
|
|
93
|
|
|
94 if (!open TEXTFILE, "$TextFile") {
|
|
|
95 warn "Warning: Ignoring file $TextFile: Couldn't open it: $! \n";
|
|
|
96 return;
|
|
|
97 }
|
|
|
98
|
|
|
99 $MaxNumOfFiles = $OptionsInfo{NumOfFiles};
|
|
|
100
|
|
|
101 # Count number of lines to figure out maximum number of lines per file...
|
|
|
102 $LineCount = 0;
|
|
|
103 while (<TEXTFILE>) {
|
|
|
104 $LineCount++;
|
|
|
105 }
|
|
|
106 close TEXTFILE;
|
|
|
107
|
|
|
108 if ($LineCount < $MaxNumOfFiles) {
|
|
|
109 warn "Warning: Ignoring file $TextFile: Total number of lines, $LineCount, is smaller than\nnumber of new files, $MaxNumOfFiles\n";
|
|
|
110 return;
|
|
|
111 }
|
|
|
112
|
|
|
113 $MaxLinesPerFile = int $LineCount / $MaxNumOfFiles;
|
|
|
114
|
|
|
115 GenerateTextFiles($FileIndex, $MaxNumOfFiles, $MaxLinesPerFile);
|
|
|
116 }
|
|
|
117
|
|
|
118 # Generate new Text files...
|
|
|
119 #
|
|
|
120 sub GenerateTextFiles {
|
|
|
121 my($FileIndex, $NumOfFiles, $NumOfLinesPerFile) = @_;
|
|
|
122 my($TextFile, $LineCount, $NewFileIndex, $NewFileName, $MaxLinesCount, $InDelim, $OutDelim, $OutQuote, $ColLabelsLine, $Line, @ColLabels, @Words, @NewTextFilesList);
|
|
|
123
|
|
|
124 # Setup new file names list...
|
|
|
125 @NewTextFilesList = ();
|
|
|
126 for $NewFileIndex (1 .. $NumOfFiles) {
|
|
|
127 $NewFileName = $TextFilesInfo{OutFileRoot}[$FileIndex] . "Part${NewFileIndex}." . $TextFilesInfo{OutFileExt}[$FileIndex];
|
|
|
128 if (!$OptionsInfo{OverwriteFiles}) {
|
|
|
129 if (-e $NewFileName) {
|
|
|
130 warn "Warning: Ignoring file $TextFile: New Text file, $NewFileName, already exists\n";
|
|
|
131 return;
|
|
|
132 }
|
|
|
133 }
|
|
|
134 push @NewTextFilesList, $NewFileName;
|
|
|
135 }
|
|
|
136
|
|
|
137 $TextFile = $TextFilesList[$FileIndex];
|
|
|
138
|
|
|
139 if (!open TEXTFILE, "$TextFile") {
|
|
|
140 warn "Warning: Ignoring file $TextFile: Couldn't open it: $! \n";
|
|
|
141 return;
|
|
|
142 }
|
|
|
143
|
|
|
144 $InDelim = $TextFilesInfo{InDelim}[$FileIndex];
|
|
|
145
|
|
|
146 $OutDelim = $OptionsInfo{OutDelim};
|
|
|
147 $OutQuote = $OptionsInfo{OutQuote};
|
|
|
148
|
|
|
149 $MaxLinesCount = $NumOfLinesPerFile;
|
|
|
150 $LineCount = 0;
|
|
|
151 $NewFileIndex = 1;
|
|
|
152
|
|
|
153 open NEWTEXTFILE, ">$NewTextFilesList[$NewFileIndex - 1]" or die "Error: Can't open $NewTextFilesList[$NewFileIndex -1]: $! \n";
|
|
|
154 print "Generating $NewTextFilesList[$NewFileIndex - 1] file...\n";
|
|
|
155
|
|
|
156 if ($OptionsInfo{Label}) {
|
|
|
157 if ($OptionsInfo{Fast}) {
|
|
|
158 $ColLabelsLine = GetTextLine(\*TEXTFILE);
|
|
|
159 }
|
|
|
160 else {
|
|
|
161 $Line = GetTextLine(\*TEXTFILE);
|
|
|
162 @ColLabels = quotewords($InDelim, 0, $Line);
|
|
|
163 $ColLabelsLine = JoinWords(\@ColLabels, $OutDelim, $OutQuote);
|
|
|
164 }
|
|
|
165 print NEWTEXTFILE "$ColLabelsLine\n";
|
|
|
166 }
|
|
|
167
|
|
|
168 while ($Line = GetTextLine(\*TEXTFILE)) {
|
|
|
169 $LineCount++;
|
|
|
170
|
|
|
171 if (!$Options{fast}) {
|
|
|
172 @Words = quotewords($InDelim, 0, $Line);
|
|
|
173 $Line = JoinWords(\@Words, $OutDelim, $OutQuote);
|
|
|
174 }
|
|
|
175 print NEWTEXTFILE "$Line\n";
|
|
|
176
|
|
|
177 if ($NewFileIndex <= $NumOfFiles) {
|
|
|
178 if ($LineCount >= $MaxLinesCount) {
|
|
|
179 if ($NewFileIndex < $NumOfFiles) {
|
|
|
180 close NEWTEXTFILE;
|
|
|
181 }
|
|
|
182 $NewFileIndex++;
|
|
|
183 $MaxLinesCount = $NumOfLinesPerFile * $NewFileIndex;
|
|
|
184
|
|
|
185 if ($NewFileIndex <= $NumOfFiles) {
|
|
|
186 open NEWTEXTFILE, ">$NewTextFilesList[$NewFileIndex - 1]" or die "Error: Can't open $NewTextFilesList[$NewFileIndex -1]: $! \n";
|
|
|
187 print "Generating $NewTextFilesList[$NewFileIndex - 1] file...\n";
|
|
|
188
|
|
|
189 if ($OptionsInfo{Label}) {
|
|
|
190 print NEWTEXTFILE "$ColLabelsLine\n";
|
|
|
191 }
|
|
|
192 }
|
|
|
193 }
|
|
|
194 }
|
|
|
195 }
|
|
|
196 close NEWTEXTFILE;
|
|
|
197 close TEXTFILE;
|
|
|
198 }
|
|
|
199
|
|
|
200 # Retrieve information about Text files...
|
|
|
201 sub RetrieveTextFilesInfo {
|
|
|
202 my($Index, $TextFile, $InDelim, $FileDir, $FileName, $FileExt, $OutFileRoot, $OutFileExt);
|
|
|
203
|
|
|
204 %TextFilesInfo = ();
|
|
|
205 @{$TextFilesInfo{FileOkay}} = ();
|
|
|
206 @{$TextFilesInfo{InDelim}} = ();
|
|
|
207 @{$TextFilesInfo{OutFileRoot}} = ();
|
|
|
208 @{$TextFilesInfo{OutFileExt}} = ();
|
|
|
209
|
|
|
210 FILELIST: for $Index (0 .. $#TextFilesList) {
|
|
|
211 $TextFilesInfo{FileOkay}[$Index] = 0;
|
|
|
212 $TextFilesInfo{InDelim}[$Index] = "";
|
|
|
213 $TextFilesInfo{OutFileRoot}[$Index] = "";
|
|
|
214 $TextFilesInfo{OutFileExt}[$Index] = "";
|
|
|
215
|
|
|
216 $TextFile = $TextFilesList[$Index];
|
|
|
217 if (!(-e $TextFile)) {
|
|
|
218 warn "Warning: Ignoring file $TextFile: It doesn't exist\n";
|
|
|
219 next FILELIST;
|
|
|
220 }
|
|
|
221 if (!CheckFileType($TextFile, "csv tsv")) {
|
|
|
222 warn "Warning: Ignoring file $TextFile: It's not a Text file\n";
|
|
|
223 next FILELIST;
|
|
|
224 }
|
|
|
225 if (! open TEXTFILE, "$TextFile") {
|
|
|
226 warn "Warning: Ignoring file $TextFile: Couldn't open it: $! \n";
|
|
|
227 next FILELIST;
|
|
|
228 }
|
|
|
229 close TEXTFILE;
|
|
|
230
|
|
|
231 ($FileDir, $FileName, $FileExt) = ParseFileName($TextFile);
|
|
|
232
|
|
|
233 # Setup input delimiter...
|
|
|
234 $InDelim = '';
|
|
|
235 if (!$OptionsInfo{Fast}) {
|
|
|
236 if ($FileExt =~ /^tsv$/i) {
|
|
|
237 $InDelim = "\t";
|
|
|
238 }
|
|
|
239 else {
|
|
|
240 $InDelim = "\,";
|
|
|
241 if ($OptionsInfo{InDelim} !~ /^(comma|semicolon)$/i) {
|
|
|
242 warn "Warning: Ignoring file $TextFile: The value specified, $OptionsInfo{InDelim}, for option \"--indelim\" is not valid for csv files\n";
|
|
|
243 next FILELIST;
|
|
|
244 }
|
|
|
245 if ($OptionsInfo{InDelim} =~ /^semicolon$/i) {
|
|
|
246 $InDelim = "\;";
|
|
|
247 }
|
|
|
248 }
|
|
|
249 }
|
|
|
250
|
|
|
251 # Setup output file root...
|
|
|
252 $OutFileExt = $OptionsInfo{Fast} ? $FileExt : (($Options{outdelim} =~ /^tab$/i ) ? "tsv" : "csv");
|
|
|
253
|
|
|
254 if ($OptionsInfo{OutFileRoot} && (@TextFilesList == 1)) {
|
|
|
255 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($OptionsInfo{OutFileRoot});
|
|
|
256 if ($RootFileName && $RootFileExt) {
|
|
|
257 $FileName = $RootFileName;
|
|
|
258 }
|
|
|
259 else {
|
|
|
260 $FileName = $OptionsInfo{OutFileRoot};
|
|
|
261 }
|
|
|
262 $OutFileRoot = $FileName;
|
|
|
263 }
|
|
|
264 else {
|
|
|
265 $OutFileRoot = $FileName;
|
|
|
266 }
|
|
|
267
|
|
|
268 $TextFilesInfo{FileOkay}[$Index] = 1;
|
|
|
269 $TextFilesInfo{InDelim}[$Index] = $InDelim;
|
|
|
270 $TextFilesInfo{OutFileRoot}[$Index] = $OutFileRoot;
|
|
|
271 $TextFilesInfo{OutFileExt}[$Index] = $OutFileExt;
|
|
|
272 }
|
|
|
273 }
|
|
|
274
|
|
|
275 # Process option values...
|
|
|
276 sub ProcessOptions {
|
|
|
277
|
|
|
278 %OptionsInfo = ();
|
|
|
279
|
|
|
280 $OptionsInfo{Fast} = defined $Options{fast} ? $Options{fast} : undef;
|
|
|
281
|
|
|
282 $OptionsInfo{InDelim} = $Options{indelim};
|
|
|
283 $OptionsInfo{Label} = ($Options{label} =~ /^yes$/i) ? 1 : 0;
|
|
|
284
|
|
|
285 $OptionsInfo{NumOfFiles} = $Options{numfiles};
|
|
|
286
|
|
|
287 $OptionsInfo{OutFileRoot} = $Options{root} ? $Options{root} : undef;
|
|
|
288 $OptionsInfo{OverwriteFiles} = $Options{overwrite} ? $Options{overwrite} : undef;
|
|
|
289
|
|
|
290 $OptionsInfo{OutDelim} = ($Options{outdelim} =~ /^tab$/i ) ? "\t" : (($Options{outdelim} =~ /^semicolon$/i) ? "\;" : "\,");
|
|
|
291 $OptionsInfo{OutQuote} = ($Options{quote} =~ /^yes$/i) ? 1 : 0;
|
|
|
292 }
|
|
|
293
|
|
|
294 # Setup script usage and retrieve command line arguments specified using various options...
|
|
|
295 sub SetupScriptUsage {
|
|
|
296
|
|
|
297 # Retrieve all the options...
|
|
|
298 %Options = ();
|
|
|
299 $Options{label} = "yes";
|
|
|
300 $Options{numfiles} = 2;
|
|
|
301 $Options{indelim} = "comma";
|
|
|
302 $Options{outdelim} = "comma";
|
|
|
303 $Options{quote} = "yes";
|
|
|
304 if (!GetOptions(\%Options, "fast|f", "help|h", "indelim=s", "label|l=s", "numfiles|n=i", "outdelim=s", "overwrite|o", "quote|q=s", "root|r=s", "workingdir|w=s")) {
|
|
|
305 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
|
|
|
306 }
|
|
|
307 if ($Options{workingdir}) {
|
|
|
308 if (! -d $Options{workingdir}) {
|
|
|
309 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
|
|
|
310 }
|
|
|
311 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
|
|
|
312 }
|
|
|
313 if ($Options{numfiles} < 2) {
|
|
|
314 die "Error: The value specified, $Options{numfiles}, for option \"-n --numfiles\" is not valid. Allowed values: >= 2 \n";
|
|
|
315 }
|
|
|
316 if ($Options{indelim} !~ /^(comma|semicolon)$/i) {
|
|
|
317 die "Error: The value specified, $Options{indelim}, for option \"--indelim\" is not valid. Allowed values: comma or semicolon\n";
|
|
|
318 }
|
|
|
319 if ($Options{outdelim} !~ /^(comma|semicolon|tab)$/i) {
|
|
|
320 die "Error: The value specified, $Options{outdelim}, for option \"--outdelim\" is not valid. Allowed values: comma, tab, or semicolon\n";
|
|
|
321 }
|
|
|
322 if ($Options{quote} !~ /^(yes|no)$/i) {
|
|
|
323 die "Error: The value specified, $Options{quote}, for option \"-q --quote\" is not valid. Allowed values: yes or no\n";
|
|
|
324 }
|
|
|
325 if ($Options{label} !~ /^(yes|no)$/i) {
|
|
|
326 die "Error: The value specified, $Options{label}, for option \"-l --label\" is not valid. Allowed values: yes or no\n";
|
|
|
327 }
|
|
|
328 }
|
|
|
329
|
|
|
330 __END__
|
|
|
331
|
|
|
332 =head1 NAME
|
|
|
333
|
|
|
334 SplitTextFiles.pl - Split CSV or TSV TextFile(s) into multiple text files
|
|
|
335
|
|
|
336 =head1 SYNOPSIS
|
|
|
337
|
|
|
338 SplitTextFiles.pl TextFile(s)...
|
|
|
339
|
|
|
340 SplitTextFiles.pl [B<-f, --fast>] [B<-h, --help>] [B<--indelim> comma | semicolon]
|
|
|
341 [B<-l, --label> yes | no] [B<-n, --numfiles> number] [B<-o, --overwrite>]
|
|
|
342 [B<--outdelim> comma | tab | semicolon] [B<-q, --quote> yes | no]
|
|
|
343 [B<-r, --root> rootname] [B<-w, --workingdir> dirname] TextFile(s)...
|
|
|
344
|
|
|
345 =head1 DESCRIPTION
|
|
|
346
|
|
|
347 Split CSV or TSV I<TextFile(s)> into multiple text files. Each new text file contains
|
|
|
348 a subset of similar number of lines from the initial file. The file names are separated
|
|
|
349 by space. The valid file extensions are I<.csv> and I<.tsv> for comma/semicolon and
|
|
|
350 tab delimited text files respectively. All other file names are ignored. All the text
|
|
|
351 files in a current directory can be specified by I<*.csv>, I<*.tsv>, or the current
|
|
|
352 directory name. The B<--indelim> option determines the format of I<TextFile(s)>.
|
|
|
353 Any file which doesn't correspond to the format indicated by B<--indelim> option
|
|
|
354 is ignored.
|
|
|
355
|
|
|
356 =head1 OPTIONS
|
|
|
357
|
|
|
358 =over 4
|
|
|
359
|
|
|
360 =item B<-f, --fast>
|
|
|
361
|
|
|
362 In this mode, B<--indelim, --outdelim>, and B<-q --quote> options are ignored. The
|
|
|
363 format of input and output file(s) are assumed to be similar. And the text lines
|
|
|
364 from input I<TextFile(s)> are just transferred to output file(s) without any processing.
|
|
|
365
|
|
|
366 =item B<-h, --help>
|
|
|
367
|
|
|
368 Print this help message.
|
|
|
369
|
|
|
370 =item B<--indelim> I<comma | semicolon>
|
|
|
371
|
|
|
372 Input delimiter for CSV I<TextFile(s)>. Possible values: I<comma or semicolon>.
|
|
|
373 Default value: I<comma>. For TSV files, this option is ignored and I<tab> is used as a
|
|
|
374 delimiter.
|
|
|
375
|
|
|
376 =item B<-l, --label> I<yes | no>
|
|
|
377
|
|
|
378 First line contains column labels. Possible values: I<yes or no>. Default value: I<yes>.
|
|
|
379
|
|
|
380 =item B<-n, --numfiles> I<number>
|
|
|
381
|
|
|
382 Number of new files to generate for each TextFile(s). Default: I<2>.
|
|
|
383
|
|
|
384 =item B<-o, --overwrite>
|
|
|
385
|
|
|
386 Overwrite existing files.
|
|
|
387
|
|
|
388 =item B<--outdelim> I<comma | tab | semicolon>
|
|
|
389
|
|
|
390 Output text file delimiter. Possible values: I<comma, tab, or semicolon>.
|
|
|
391 Default value: I<comma>
|
|
|
392
|
|
|
393 =item B<-q, --quote> I<yes | no>
|
|
|
394
|
|
|
395 Put quotes around column values in output text file. Possible values: I<yes or
|
|
|
396 no>. Default value: I<yes>.
|
|
|
397
|
|
|
398 =item B<-r, --root> I<rootname>
|
|
|
399
|
|
|
400 New text file names are generated using the root: <Root>Part<Count>.<Ext>.
|
|
|
401 Default new file names: <InitialTextFileName>Part<Count>.<Ext>. The csv, and tsv
|
|
|
402 <Ext> values are used for comma/semicolon, and tab delimited text files
|
|
|
403 respectively.This option is ignored for multiple input files.
|
|
|
404
|
|
|
405 =item B<-w, --workingdir> I<dirname>
|
|
|
406
|
|
|
407 Location of working directory. Default: current directory.
|
|
|
408
|
|
|
409 =back
|
|
|
410
|
|
|
411 =head1 EXAMPLES
|
|
|
412
|
|
|
413 To split each CSV text files into 4 different text files type:
|
|
|
414
|
|
|
415 % SplitTextFiles.pl -n 5 -o Sample1.csv Sample2.csv
|
|
|
416 % SplitTextFiles.pl -n 5 -o *.csv
|
|
|
417
|
|
|
418 To split Sample1.tsv into 10 different CSV text files, type:
|
|
|
419
|
|
|
420 % SplitTextFiles.pl -n 10 --outdelim comma -o Sample1.tsv
|
|
|
421
|
|
|
422 =head1 AUTHOR
|
|
|
423
|
|
|
424 Manish Sud <msud@san.rr.com>
|
|
|
425
|
|
|
426 =head1 SEE ALSO
|
|
|
427
|
|
|
428 JoinTextFiles.pl, MergeTextFiles.pl, ModifyTextFilesFormat.pl
|
|
|
429
|
|
|
430 =head1 COPYRIGHT
|
|
|
431
|
|
|
432 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
433
|
|
|
434 This file is part of MayaChemTools.
|
|
|
435
|
|
|
436 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
437 the terms of the GNU Lesser General Public License as published by the Free
|
|
|
438 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
439 any later version.
|
|
|
440
|
|
|
441 =cut
|
