annotate bin/ModifyTextFilesFormat.pl @ 3:90ea638ce878 draft default tip

Uploaded
author deepakjadmin
date Wed, 20 Jan 2016 09:11:59 -0500
parents 2abf0d43254d
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
1 #!/usr/bin/perl -w
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
2 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
3 # $RCSfile: ModifyTextFilesFormat.pl,v $
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
4 # $Date: 2015/02/28 20:46:20 $
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
5 # $Revision: 1.34 $
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
6 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
7 # Author: Manish Sud <msud@san.rr.com>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
8 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
10 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
11 # This file is part of MayaChemTools.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
12 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
14 # the terms of the GNU Lesser General Public License as published by the Free
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
15 # Software Foundation; either version 3 of the License, or (at your option) any
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
16 # later version.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
17 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
18 # MayaChemTools is distributed in the hope that it will be useful, but without
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
19 # any warranty; without even the implied warranty of merchantability of fitness
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
20 # for a particular purpose. See the GNU Lesser General Public License for more
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
21 # details.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
22 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
23 # You should have received a copy of the GNU Lesser General Public License
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
26 # Boston, MA, 02111-1307, USA.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
27 #
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
28
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
29 use strict;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
30 use FindBin; use lib "$FindBin::Bin/../lib";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
31 use Getopt::Long;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
32 use File::Basename;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
33 use Text::ParseWords;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
34 use Benchmark;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
35 use FileUtil;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
36 use TextUtil;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
37
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
38 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
39
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
40 # Autoflush STDOUT
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
41 $| = 1;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
42
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
43 # Starting message...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
44 $ScriptName = basename $0;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
45 print "\n$ScriptName:Starting...\n\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
46 $StartTime = new Benchmark;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
47
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
48 # Get the options and setup script...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
49 SetupScriptUsage();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
50 if ($Options{help} || @ARGV < 1) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
51 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
52 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
53
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
54 my(@TextFilesList);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
55 @TextFilesList = ExpandFileNames(\@ARGV, "csv tsv");
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
56
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
57 # Process options...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
58 print "Processing options...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
59 my(%OptionsInfo);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
60 ProcessOptions();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
61
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
62 print "Checking input text file(s)...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
63 my(%TextFilesInfo);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
64 RetrieveTextFilesInfo();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
65
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
66 # Generate output files...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
67 my($FileIndex);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
68 if (@TextFilesList > 1) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
69 print "\nProcessing text files...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
70 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
71 for $FileIndex (0 .. $#TextFilesList) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
72 if ($TextFilesInfo{FileOkay}[$FileIndex]) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
73 print "\nProcessing file $TextFilesList[$FileIndex]...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
74 ModifyTextFileFormat($FileIndex);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
75 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
76 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
77 print "\n$ScriptName:Done...\n\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
78
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
79 $EndTime = new Benchmark;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
80 $TotalTime = timediff ($EndTime, $StartTime);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
81 print "Total time: ", timestr($TotalTime), "\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
82
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
83 ###############################################################################
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
84
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
85 # Modify text file format...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
86 sub ModifyTextFileFormat {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
87 my($Index) = @_;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
88 my($TextFile, $NewTextFile, $InDelim, $Line, @Words);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
89
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
90 $TextFile = $TextFilesList[$Index];
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
91
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
92 $NewTextFile = $TextFilesInfo{OutFile}[$Index];
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
93 $InDelim = $TextFilesInfo{InDelim}[$Index];
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
94
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
95 print "Generating new $NewTextFile file...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
96
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
97 open NEWTEXTFILE, ">$NewTextFile" or die "Error: Can't open $NewTextFile !$ \n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
98 open TEXTFILE, "$TextFile" or die "Error: Can't open $TextFile: $! \n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
99
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
100 while ($Line = GetTextLine(\*TEXTFILE)) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
101 @Words = quotewords($InDelim, 0, $Line);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
102 $Line = JoinWords(\@Words, $OptionsInfo{OutDelim}, $OptionsInfo{OutQuote});
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
103 print NEWTEXTFILE "$Line\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
104 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
105
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
106 close NEWTEXTFILE;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
107 close TEXTFILE;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
108 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
109
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
110 # Retrieve information about input text files...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
111 sub RetrieveTextFilesInfo {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
112 my($Index, $TextFile, $NewTextFile, $FileDir, $FileName, $FileExt, $InDelim, $OutFileExt);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
113
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
114 %TextFilesInfo = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
115 @{$TextFilesInfo{FileOkay}} = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
116 @{$TextFilesInfo{InDelim}} = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
117 @{$TextFilesInfo{OutFile}} = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
118
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
119 FILELIST: for $Index (0 .. $#TextFilesList) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
120 $TextFile = $TextFilesList[$Index];
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
121
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
122 $TextFilesInfo{FileOkay}[$Index] = 0;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
123 $TextFilesInfo{InDelim}[$Index] = "";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
124 $TextFilesInfo{OutFile}[$Index] = "";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
125
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
126 if (!(-e $TextFile)) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
127 warn "Warning: Ignoring file $TextFile: It doesn't exist\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
128 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
129 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
130 if (!CheckFileType($TextFile, "csv tsv")) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
131 warn "Warning: Ignoring file $TextFile: It's not a csv or tsv file\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
132 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
133 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
134 if (!open TEXTFILE, "$TextFile") {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
135 warn "Warning: Ignoring file $TextFile: Couldn't open it: $! \n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
136 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
137 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
138 close TEXTFILE;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
139
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
140 ($FileDir, $FileName, $FileExt) = ParseFileName($TextFile);
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
141
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
142 if ($FileExt =~ /^tsv$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
143 $InDelim = "\t";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
144 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
145 else {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
146 $InDelim = "\,";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
147 if ($OptionsInfo{InDelim} !~ /^(comma|semicolon)$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
148 warn "Warning: Ignoring file $TextFile: The value specified, $OptionsInfo{InDelim}, for option \"--indelim\" is not valid for csv files\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
149 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
150 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
151 if ($OptionsInfo{InDelim} =~ /^semicolon$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
152 $InDelim = "\;";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
153 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
154 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
155
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
156 if (lc($InDelim) eq lc($OptionsInfo{OutDelim})) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
157 warn "Warning: Ignoring file $TextFile: The value specified, $Options{outdelim}, for option \"--outdelim\" is same as input delimiter\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
158 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
159 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
160
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
161 $OutFileExt = ($Options{outdelim} =~ /^tab$/i ) ? "tsv" : "csv";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
162
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
163 $NewTextFile = $FileName;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
164 if ($OptionsInfo{OutFileRoot} && (@TextFilesList == 1)) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
165 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($OptionsInfo{OutFileRoot});
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
166 if ($RootFileName && $RootFileExt) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
167 $NewTextFile = $RootFileName;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
168 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
169 else {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
170 $NewTextFile = $OptionsInfo{OutFileRoot};
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
171 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
172 $NewTextFile .= ".$OutFileExt";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
173 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
174 else {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
175 $NewTextFile .= "FormatModified" . ".$OutFileExt";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
176 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
177
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
178 if (!$OptionsInfo{Overwrite}) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
179 if (-e $NewTextFile) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
180 warn "Warning: Ignoring file $TextFile: New Text file, $NewTextFile, already exists\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
181 next FILELIST;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
182 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
183 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
184
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
185 $TextFilesInfo{FileOkay}[$Index] = 1;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
186 $TextFilesInfo{InDelim}[$Index] = $InDelim;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
187 $TextFilesInfo{OutFile}[$Index] = $NewTextFile;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
188 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
189
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
190 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
191
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
192 # Process option values...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
193 sub ProcessOptions {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
194 %OptionsInfo = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
195
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
196 $OptionsInfo{InDelim} = $Options{indelim};
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
197
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
198 $OptionsInfo{OutFileRoot} = $Options{root} ? $Options{root} : undef;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
199 $OptionsInfo{Overwrite} = $Options{overwrite} ? $Options{overwrite} : undef;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
200
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
201 $OptionsInfo{OutDelim} = ($Options{outdelim} =~ /^tab$/i ) ? "\t" : (($Options{outdelim} =~ /^semicolon$/i) ? "\;" : "\,");
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
202 $OptionsInfo{OutQuote} = ($Options{quote} =~ /^yes$/i) ? 1 : 0;
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
203
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
204 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
205
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
206 # Setup script usage and retrieve command line arguments specified using various options...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
207 sub SetupScriptUsage {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
208
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
209 # Retrieve all the options...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
210 %Options = ();
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
211
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
212 $Options{indelim} = "comma";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
213 $Options{outdelim} = "tab";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
214 $Options{quote} = "yes";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
215
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
216 if (!GetOptions(\%Options, "help|h", "indelim=s", "outdelim=s", "overwrite|o", "quote|q=s", "root|r=s", "workingdir|w=s")) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
217 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
218 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
219 if ($Options{workingdir}) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
220 if (! -d $Options{workingdir}) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
221 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
222 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
223 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
224 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
225 if ($Options{indelim} !~ /^(comma|semicolon)$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
226 die "Error: The value specified, $Options{indelim}, for option \"--indelim\" is not valid. Allowed values: comma or semicolon\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
227 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
228 if ($Options{outdelim} !~ /^(comma|semicolon|tab)$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
229 die "Error: The value specified, $Options{outdelim}, for option \"--outdelim\" is not valid. Allowed values: comma, tab, or semicolon\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
230 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
231 if ($Options{quote} !~ /^(yes|no)$/i) {
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
232 die "Error: The value specified, $Options{quote}, for option \"-q --quote\" is not valid. Allowed values: yes or no\n";
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
233 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
234 }
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
235
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
236 __END__
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
237
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
238 =head1 NAME
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
239
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
240 ModifyTextFilesFormat.pl - Change CSV Textfile(s) into TSV Textfile(s) and vice versa
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
241
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
242 =head1 SYNOPSIS
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
243
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
244 ModifyTextFilesFormat.pl TextFile(s)...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
245
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
246 ModifyTextFilesFormat.pl [B<-h, --help>] [B<--indelim> comma | semicolon]
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
247 [B<--outdelim> comma | tab | semicolon] [B<-q, --quote> yes | no] [B<-r, --root> rootname]
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
248 [B<-w, --workingdir> dirname] TextFile(s)...
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
249
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
250 =head1 DESCRIPTION
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
251
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
252 Interchange CSV and TSV I<TextFile(s)> format. Mutiple file names are separated by spaces.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
253 The valid file extensions are I<.csv> and I<.tsv> for comma/semicolon and tab delimited
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
254 text files respectively. All other file names are ignored. All the text files in a current
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
255 directory can be specified by I<*.csv>, I<*.tsv>, or the current directory name. The
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
256 B<--indelim> option determines the format of I<TextFile(s)>. Any file which doesn't
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
257 correspond to the format indicated by B<--indelim> option is ignored.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
258
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
259 =head1 OPTIONS
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
260
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
261 =over 4
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
262
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
263 =item B<-h, --help>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
264
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
265 Print this help message.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
266
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
267 =item B<--indelim> I<comma | semicolon>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
268
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
269 Input delimiter for CSV I<TextFile(s)>. Possible values: I<comma or semicolon>.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
270 Default value: I<comma>. For TSV files, this option is ignored and I<tab> is used as a
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
271 delimiter.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
272
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
273 =item B<-o, --overwrite>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
274
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
275 Overwrite existing files.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
276
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
277 =item B<--outdelim> I<comma | tab | semicolon>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
278
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
279 Output text file delimiter. Possible values: I<comma, tab, or semicolon>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
280 Default value: I<comma>.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
281
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
282 =item B<-q, --quote> I<yes | no>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
283
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
284 Put quotes around column values in output text file. Possible values: I<yes or
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
285 no>. Default value: I<yes>.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
286
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
287 =item B<-r, --root> I<rootname>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
288
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
289 New text file name is generated using the root: <Root>.<Ext>. Default new file
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
290 name: <InitialTextFileName>FormatModified.<Ext>. The csv, and tsv
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
291 <Ext> values are used for comma/semicolon, and tab delimited text files
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
292 respectively. This option is ignored for multiple input files.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
293
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
294 =item B<-w, --workingdir> I<dirname>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
295
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
296 Location of working directory. Default: current directory.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
297
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
298 =back
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
299
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
300 =head1 EXAMPLES
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
301
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
302 To convert Sample*.csv into TSV files, type:
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
303
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
304 % ModifyTextFilesFormat.pl --outdelim tab -q no -o Sample*.csv
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
305
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
306 To convert Sample1.tsv into NewSample1.csv without any quotes around column
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
307 data values, type:
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
308
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
309 % ModifyTextFilesFormat.pl --outdelim comma - q no
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
310 -r NewSample1 -o Sample1.tsv
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
311
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
312 =head1 AUTHOR
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
313
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
314 Manish Sud <msud@san.rr.com>
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
315
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
316 =head1 SEE ALSO
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
317
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
318 ModifyNewLineChar.pl
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
319
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
320 =head1 COPYRIGHT
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
321
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
322 Copyright (C) 2015 Manish Sud. All rights reserved.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
323
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
324 This file is part of MayaChemTools.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
325
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
326 MayaChemTools is free software; you can redistribute it and/or modify it under
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
327 the terms of the GNU Lesser General Public License as published by the Free
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
328 Software Foundation; either version 3 of the License, or (at your option)
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
329 any later version.
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
330
2abf0d43254d Uploaded
deepakjadmin
parents:
diff changeset
331 =cut