annotate mayachemtools/bin/ModifyTextFilesFormat.pl @ 9:ab29fa5c8c1f draft default tip

Uploaded
author deepakjadmin
date Thu, 15 Dec 2016 14:18:03 -0500
parents 73ae111cf86f
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
1 #!/usr/bin/perl -w
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
2 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
3 # $RCSfile: ModifyTextFilesFormat.pl,v $
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
4 # $Date: 2015/02/28 20:46:20 $
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
5 # $Revision: 1.34 $
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
6 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
7 # Author: Manish Sud <msud@san.rr.com>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
8 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
10 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
11 # This file is part of MayaChemTools.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
12 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
14 # the terms of the GNU Lesser General Public License as published by the Free
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
15 # Software Foundation; either version 3 of the License, or (at your option) any
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
16 # later version.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
17 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
18 # MayaChemTools is distributed in the hope that it will be useful, but without
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
19 # any warranty; without even the implied warranty of merchantability of fitness
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
20 # for a particular purpose. See the GNU Lesser General Public License for more
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
21 # details.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
22 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
23 # You should have received a copy of the GNU Lesser General Public License
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
26 # Boston, MA, 02111-1307, USA.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
27 #
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
28
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
29 use strict;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
30 use FindBin; use lib "$FindBin::Bin/../lib";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
31 use Getopt::Long;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
32 use File::Basename;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
33 use Text::ParseWords;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
34 use Benchmark;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
35 use FileUtil;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
36 use TextUtil;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
37
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
38 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
39
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
40 # Autoflush STDOUT
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
41 $| = 1;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
42
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
43 # Starting message...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
44 $ScriptName = basename $0;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
45 print "\n$ScriptName:Starting...\n\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
46 $StartTime = new Benchmark;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
47
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
48 # Get the options and setup script...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
49 SetupScriptUsage();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
50 if ($Options{help} || @ARGV < 1) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
51 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
52 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
53
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
54 my(@TextFilesList);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
55 @TextFilesList = ExpandFileNames(\@ARGV, "csv tsv");
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
56
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
57 # Process options...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
58 print "Processing options...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
59 my(%OptionsInfo);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
60 ProcessOptions();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
61
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
62 print "Checking input text file(s)...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
63 my(%TextFilesInfo);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
64 RetrieveTextFilesInfo();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
65
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
66 # Generate output files...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
67 my($FileIndex);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
68 if (@TextFilesList > 1) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
69 print "\nProcessing text files...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
70 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
71 for $FileIndex (0 .. $#TextFilesList) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
72 if ($TextFilesInfo{FileOkay}[$FileIndex]) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
73 print "\nProcessing file $TextFilesList[$FileIndex]...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
74 ModifyTextFileFormat($FileIndex);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
75 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
76 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
77 print "\n$ScriptName:Done...\n\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
78
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
79 $EndTime = new Benchmark;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
80 $TotalTime = timediff ($EndTime, $StartTime);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
81 print "Total time: ", timestr($TotalTime), "\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
82
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
83 ###############################################################################
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
84
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
85 # Modify text file format...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
86 sub ModifyTextFileFormat {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
87 my($Index) = @_;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
88 my($TextFile, $NewTextFile, $InDelim, $Line, @Words);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
89
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
90 $TextFile = $TextFilesList[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
91
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
92 $NewTextFile = $TextFilesInfo{OutFile}[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
93 $InDelim = $TextFilesInfo{InDelim}[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
94
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
95 print "Generating new $NewTextFile file...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
96
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
97 open NEWTEXTFILE, ">$NewTextFile" or die "Error: Can't open $NewTextFile !$ \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
98 open TEXTFILE, "$TextFile" or die "Error: Can't open $TextFile: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
99
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
100 while ($Line = GetTextLine(\*TEXTFILE)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
101 @Words = quotewords($InDelim, 0, $Line);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
102 $Line = JoinWords(\@Words, $OptionsInfo{OutDelim}, $OptionsInfo{OutQuote});
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
103 print NEWTEXTFILE "$Line\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
104 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
105
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
106 close NEWTEXTFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
107 close TEXTFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
108 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
109
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
110 # Retrieve information about input text files...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
111 sub RetrieveTextFilesInfo {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
112 my($Index, $TextFile, $NewTextFile, $FileDir, $FileName, $FileExt, $InDelim, $OutFileExt);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
113
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
114 %TextFilesInfo = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
115 @{$TextFilesInfo{FileOkay}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
116 @{$TextFilesInfo{InDelim}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
117 @{$TextFilesInfo{OutFile}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
118
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
119 FILELIST: for $Index (0 .. $#TextFilesList) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
120 $TextFile = $TextFilesList[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
121
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
122 $TextFilesInfo{FileOkay}[$Index] = 0;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
123 $TextFilesInfo{InDelim}[$Index] = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
124 $TextFilesInfo{OutFile}[$Index] = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
125
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
126 if (!(-e $TextFile)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
127 warn "Warning: Ignoring file $TextFile: It doesn't exist\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
128 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
129 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
130 if (!CheckFileType($TextFile, "csv tsv")) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
131 warn "Warning: Ignoring file $TextFile: It's not a csv or tsv file\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
132 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
133 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
134 if (!open TEXTFILE, "$TextFile") {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
135 warn "Warning: Ignoring file $TextFile: Couldn't open it: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
136 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
137 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
138 close TEXTFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
139
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
140 ($FileDir, $FileName, $FileExt) = ParseFileName($TextFile);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
141
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
142 if ($FileExt =~ /^tsv$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
143 $InDelim = "\t";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
144 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
145 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
146 $InDelim = "\,";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
147 if ($OptionsInfo{InDelim} !~ /^(comma|semicolon)$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
148 warn "Warning: Ignoring file $TextFile: The value specified, $OptionsInfo{InDelim}, for option \"--indelim\" is not valid for csv files\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
149 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
150 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
151 if ($OptionsInfo{InDelim} =~ /^semicolon$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
152 $InDelim = "\;";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
153 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
154 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
155
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
156 if (lc($InDelim) eq lc($OptionsInfo{OutDelim})) {
73ae111cf86f 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";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
158 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
159 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
160
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
161 $OutFileExt = ($Options{outdelim} =~ /^tab$/i ) ? "tsv" : "csv";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
162
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
163 $NewTextFile = $FileName;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
164 if ($OptionsInfo{OutFileRoot} && (@TextFilesList == 1)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
165 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($OptionsInfo{OutFileRoot});
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
166 if ($RootFileName && $RootFileExt) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
167 $NewTextFile = $RootFileName;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
168 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
169 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
170 $NewTextFile = $OptionsInfo{OutFileRoot};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
171 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
172 $NewTextFile .= ".$OutFileExt";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
173 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
174 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
175 $NewTextFile .= "FormatModified" . ".$OutFileExt";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
176 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
177
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
178 if (!$OptionsInfo{Overwrite}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
179 if (-e $NewTextFile) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
180 warn "Warning: Ignoring file $TextFile: New Text file, $NewTextFile, already exists\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
181 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
182 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
183 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
184
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
185 $TextFilesInfo{FileOkay}[$Index] = 1;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
186 $TextFilesInfo{InDelim}[$Index] = $InDelim;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
187 $TextFilesInfo{OutFile}[$Index] = $NewTextFile;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
188 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
189
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
190 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
191
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
192 # Process option values...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
193 sub ProcessOptions {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
194 %OptionsInfo = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
195
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
196 $OptionsInfo{InDelim} = $Options{indelim};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
197
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
198 $OptionsInfo{OutFileRoot} = $Options{root} ? $Options{root} : undef;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
199 $OptionsInfo{Overwrite} = $Options{overwrite} ? $Options{overwrite} : undef;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
200
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
201 $OptionsInfo{OutDelim} = ($Options{outdelim} =~ /^tab$/i ) ? "\t" : (($Options{outdelim} =~ /^semicolon$/i) ? "\;" : "\,");
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
202 $OptionsInfo{OutQuote} = ($Options{quote} =~ /^yes$/i) ? 1 : 0;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
203
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
204 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
205
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
206 # Setup script usage and retrieve command line arguments specified using various options...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
207 sub SetupScriptUsage {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
208
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
209 # Retrieve all the options...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
210 %Options = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
211
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
212 $Options{indelim} = "comma";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
213 $Options{outdelim} = "tab";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
214 $Options{quote} = "yes";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
215
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
216 if (!GetOptions(\%Options, "help|h", "indelim=s", "outdelim=s", "overwrite|o", "quote|q=s", "root|r=s", "workingdir|w=s")) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
217 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
218 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
219 if ($Options{workingdir}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
220 if (! -d $Options{workingdir}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
221 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
222 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
223 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
224 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
225 if ($Options{indelim} !~ /^(comma|semicolon)$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
226 die "Error: The value specified, $Options{indelim}, for option \"--indelim\" is not valid. Allowed values: comma or semicolon\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
227 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
228 if ($Options{outdelim} !~ /^(comma|semicolon|tab)$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
229 die "Error: The value specified, $Options{outdelim}, for option \"--outdelim\" is not valid. Allowed values: comma, tab, or semicolon\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
230 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
231 if ($Options{quote} !~ /^(yes|no)$/i) {
73ae111cf86f 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";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
233 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
234 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
235
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
236 __END__
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
237
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
238 =head1 NAME
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
239
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
240 ModifyTextFilesFormat.pl - Change CSV Textfile(s) into TSV Textfile(s) and vice versa
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
241
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
242 =head1 SYNOPSIS
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
243
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
244 ModifyTextFilesFormat.pl TextFile(s)...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
245
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
246 ModifyTextFilesFormat.pl [B<-h, --help>] [B<--indelim> comma | semicolon]
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
247 [B<--outdelim> comma | tab | semicolon] [B<-q, --quote> yes | no] [B<-r, --root> rootname]
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
248 [B<-w, --workingdir> dirname] TextFile(s)...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
249
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
250 =head1 DESCRIPTION
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
251
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
252 Interchange CSV and TSV I<TextFile(s)> format. Mutiple file names are separated by spaces.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
253 The valid file extensions are I<.csv> and I<.tsv> for comma/semicolon and tab delimited
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
254 text files respectively. All other file names are ignored. All the text files in a current
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
255 directory can be specified by I<*.csv>, I<*.tsv>, or the current directory name. The
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
256 B<--indelim> option determines the format of I<TextFile(s)>. Any file which doesn't
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
257 correspond to the format indicated by B<--indelim> option is ignored.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
258
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
259 =head1 OPTIONS
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
260
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
261 =over 4
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
262
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
263 =item B<-h, --help>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
264
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
265 Print this help message.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
266
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
267 =item B<--indelim> I<comma | semicolon>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
268
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
269 Input delimiter for CSV I<TextFile(s)>. Possible values: I<comma or semicolon>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
270 Default value: I<comma>. For TSV files, this option is ignored and I<tab> is used as a
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
271 delimiter.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
272
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
273 =item B<-o, --overwrite>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
274
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
275 Overwrite existing files.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
276
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
277 =item B<--outdelim> I<comma | tab | semicolon>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
278
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
279 Output text file delimiter. Possible values: I<comma, tab, or semicolon>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
280 Default value: I<comma>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
281
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
282 =item B<-q, --quote> I<yes | no>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
283
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
284 Put quotes around column values in output text file. Possible values: I<yes or
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
285 no>. Default value: I<yes>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
286
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
287 =item B<-r, --root> I<rootname>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
288
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
289 New text file name is generated using the root: <Root>.<Ext>. Default new file
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
290 name: <InitialTextFileName>FormatModified.<Ext>. The csv, and tsv
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
291 <Ext> values are used for comma/semicolon, and tab delimited text files
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
292 respectively. This option is ignored for multiple input files.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
293
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
294 =item B<-w, --workingdir> I<dirname>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
295
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
296 Location of working directory. Default: current directory.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
297
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
298 =back
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
299
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
300 =head1 EXAMPLES
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
301
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
302 To convert Sample*.csv into TSV files, type:
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
303
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
304 % ModifyTextFilesFormat.pl --outdelim tab -q no -o Sample*.csv
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
305
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
306 To convert Sample1.tsv into NewSample1.csv without any quotes around column
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
307 data values, type:
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
308
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
309 % ModifyTextFilesFormat.pl --outdelim comma - q no
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
310 -r NewSample1 -o Sample1.tsv
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
311
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
312 =head1 AUTHOR
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
313
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
314 Manish Sud <msud@san.rr.com>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
315
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
316 =head1 SEE ALSO
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
317
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
318 ModifyNewLineChar.pl
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
319
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
320 =head1 COPYRIGHT
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
321
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
322 Copyright (C) 2015 Manish Sud. All rights reserved.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
323
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
324 This file is part of MayaChemTools.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
325
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
326 MayaChemTools is free software; you can redistribute it and/or modify it under
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
327 the terms of the GNU Lesser General Public License as published by the Free
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
328 Software Foundation; either version 3 of the License, or (at your option)
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
329 any later version.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
330
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
331 =cut