annotate mayachemtools/bin/SortSDFiles.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: SortSDFiles.pl,v $
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
4 # $Date: 2015/02/28 20:46:21 $
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
5 # $Revision: 1.26 $
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 "$FindBin::Bin/../lib";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
31 use Getopt::Long;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
32 use File::Basename;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
33 use Text::ParseWords;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
34 use Benchmark;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
35 use FileUtil;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
36 use SDFileUtil;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
37 use TextUtil;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
38
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
39 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
40
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
41 # Autoflush STDOUT
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
42 $| = 1;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
43
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
44 # Starting message...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
45 $ScriptName = basename($0);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
46 print "\n$ScriptName: Starting...\n\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
47 $StartTime = new Benchmark;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
48
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
49 # Get the options and setup script...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
50 SetupScriptUsage();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
51 if ($Options{help} || @ARGV < 1) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
52 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
53 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
54
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
55 my(@SDFilesList);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
56 @SDFilesList = ExpandFileNames(\@ARGV, "sdf sd");
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
57
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 SD file(s)...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
63 my(%SDFilesInfo);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
64 RetrieveSDFilesInfo();
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 (@SDFilesList > 1) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
69 print "\nProcessing SD files...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
70 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
71 for $FileIndex (0 .. $#SDFilesList) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
72 if ($SDFilesInfo{FileOkay}[$FileIndex]) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
73 print "\nProcessing file $SDFilesList[$FileIndex]...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
74 SortSDFile($FileIndex);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
75 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
76 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
77 print "\n$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 # Sort it out...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
86 sub SortSDFile {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
87 my($Index) = @_;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
88 my($SDFile, $NewSDFile, $KeyDataFieldName);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
89
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
90 $SDFile = $SDFilesList[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
91 $NewSDFile = $SDFilesInfo{OutFile}[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
92 $KeyDataFieldName = $SDFilesInfo{KeyDataFieldName}[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
93
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
94 print "Generating new SD file $NewSDFile...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
95 open NEWSDFILE, ">$NewSDFile" or die "Error: Couldn't open $NewSDFile: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
96 open SDFILE, "$SDFile" or die "Error: Can't open $SDFile: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
97
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
98 # Go over all compound records and store 'em using key value as hash...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
99 my(%KeyToCompundRecordsMap, @InvalidCompoundRecords, $CmpdCount, $CmpdString, @CmpdLines, %DataFieldValues, $KeyDataFieldValue);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
100 %KeyToCompundRecordsMap = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
101 @InvalidCompoundRecords = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
102 $CmpdCount = 0;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
103
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
104 COMPOUND: while ($CmpdString = ReadCmpdString(\*SDFILE)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
105 $CmpdCount++;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
106 @CmpdLines = split "\n", $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
107 %DataFieldValues = GetCmpdDataHeaderLabelsAndValues(\@CmpdLines);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
108 #Make sure data field value is okay...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
109 if (!(IsNotEmpty($DataFieldValues{$KeyDataFieldName}) && ($DataFieldValues{$KeyDataFieldName} !~ /\n/))) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
110 push @InvalidCompoundRecords, $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
111 if ($OptionsInfo{DetailLevel} >= 3 ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
112 print "Ignoring compound record $CmpdCount: Contains empty value for key data field $KeyDataFieldName :\n $CmpdString\n\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
113 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
114 elsif ($OptionsInfo{DetailLevel} >= 2) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
115 print "Ignoring compound record $CmpdCount: Contains empty value for key data field $KeyDataFieldName...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
116 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
117 next COMPOUND;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
118 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
119 $KeyDataFieldValue = $DataFieldValues{$KeyDataFieldName};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
120 if ($OptionsInfo{KeyData} =~ /^numeric$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
121 if (!IsFloat($KeyDataFieldValue)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
122 push @InvalidCompoundRecords, $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
123 if ($OptionsInfo{DetailLevel} >= 3 ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
124 print "Ignoring compound record $CmpdCount: Contains non-numerical value for key data field $KeyDataFieldName :\n $CmpdString\n\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
125 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
126 elsif ($OptionsInfo{DetailLevel} >= 2) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
127 print "Ignoring compound record $CmpdCount: Contains non-numerical value for key data field $KeyDataFieldName...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
128 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
129 next COMPOUND;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
130 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
131 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
132 if (exists($KeyToCompundRecordsMap{$KeyDataFieldValue})) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
133 # Append to existing coompund data...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
134 $KeyToCompundRecordsMap{$KeyDataFieldValue} .= "\n" . $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
135 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
136 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
137 $KeyToCompundRecordsMap{$KeyDataFieldValue} = $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
138 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
139 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
140
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
141 if ($OptionsInfo{Sort} =~ /^ascending$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
142 if ($OptionsInfo{KeyData} =~ /^alphanumeric$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
143 for $KeyDataFieldValue (sort { lc($a) cmp lc($b) } keys %KeyToCompundRecordsMap ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
144 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
145 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
146 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
147 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
148 for $KeyDataFieldValue (sort { $a <=> $b } keys %KeyToCompundRecordsMap ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
149 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
150 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
151 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
152 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
153 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
154 if ($OptionsInfo{KeyData} =~ /^alphanumeric$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
155 for $KeyDataFieldValue (sort { lc($b) cmp lc($a) } keys %KeyToCompundRecordsMap ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
156 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
157 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
158 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
159 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
160 for $KeyDataFieldValue (sort { $b <=> $a } keys %KeyToCompundRecordsMap ) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
161 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
162 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
163 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
164 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
165 # Append the records containing data not appropriate for sorting...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
166 if (@InvalidCompoundRecords) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
167 print "Placing ", scalar(@InvalidCompoundRecords)," compound record(s) with invalid data field key data the end...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
168 for $CmpdString (@InvalidCompoundRecords) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
169 print NEWSDFILE "$CmpdString\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
170 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
171 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
172 close NEWSDFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
173 close SDFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
174 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
175
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
176 # Retrieve information about input SD files...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
177 sub RetrieveSDFilesInfo {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
178 my($Index, $SDFile, $FileDir, $FileName, $FileExt, $OutFileRoot, $OutFile, $DataFieldName);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
179
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
180 %SDFilesInfo = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
181
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
182 @{$SDFilesInfo{FileOkay}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
183 @{$SDFilesInfo{OutFile}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
184 @{$SDFilesInfo{KeyDataFieldName}} = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
185
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
186 FILELIST: for $Index (0 .. $#SDFilesList) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
187 $SDFile = $SDFilesList[$Index];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
188 $SDFilesInfo{FileOkay}[$Index] = 0;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
189 $SDFilesInfo{OutFile}[$Index] = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
190 $SDFilesInfo{KeyDataFieldName}[$Index] = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
191
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
192 if (!(-e $SDFile)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
193 warn "Warning: Ignoring file $SDFile: It doesn't exist\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
194 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
195 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
196 if (!CheckFileType($SDFile, "sd sdf")) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
197 warn "Warning: Ignoring file $SDFile: It's not a SD file\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
198 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
199 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
200 $FileDir = ""; $FileName = ""; $FileExt = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
201 ($FileDir, $FileName, $FileExt) = ParseFileName($SDFile);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
202 if ($Options{root} && (@SDFilesList == 1)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
203 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($Options{root});
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
204 if ($RootFileName && $RootFileExt) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
205 $FileName = $RootFileName;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
206 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
207 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
208 $FileName = $Options{root};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
209 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
210 $OutFileRoot = $FileName;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
211 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
212 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
213 $OutFileRoot = $FileName . "SortedByDataField";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
214 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
215
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
216 $OutFile = $OutFileRoot . ".$FileExt";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
217 if (lc($OutFile) eq lc($SDFile)) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
218 warn "Warning: Ignoring file $SDFile:Output file name, $OutFile, is same as input SD file name, $SDFile\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
219 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
220 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
221 if (!$Options{overwrite}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
222 if (-e $OutFile) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
223 warn "Warning: Ignoring file $SDFile: The file $OutFile already exists\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
224 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
225 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
226 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
227 # Setup data field name...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
228 if ($OptionsInfo{SpecifiedDataFieldName}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
229 $DataFieldName = $OptionsInfo{SpecifiedDataFieldName};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
230 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
231 else {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
232 my($CmpdString, @CmpdLines, @DataFieldNames);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
233 @DataFieldNames = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
234 if (!open(SDFILE, "$SDFile")) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
235 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
236 next FILELIST;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
237 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
238 $CmpdString = ReadCmpdString(\*SDFILE);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
239 close SDFILE;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
240
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
241 @CmpdLines = split "\n", $CmpdString;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
242 @DataFieldNames = GetCmpdDataHeaderLabels(\@CmpdLines);
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
243 $DataFieldName = $DataFieldNames[0];
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
244 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
245
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
246 $SDFilesInfo{FileOkay}[$Index] = 1;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
247 $SDFilesInfo{OutFile}[$Index] = "$OutFile";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
248 $SDFilesInfo{KeyDataFieldName}[$Index] = $DataFieldName;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
249 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
250 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
251
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
252 # Process option values...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
253 sub ProcessOptions {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
254 $OptionsInfo{DetailLevel} = $Options{detail};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
255
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
256 $OptionsInfo{Key} = defined $Options{key} ? $Options{key} : undef;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
257 $OptionsInfo{SpecifiedDataFieldName} = "";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
258 if (defined $Options{key}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
259 $OptionsInfo{SpecifiedDataFieldName} = $Options{key};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
260 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
261
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
262 $OptionsInfo{KeyData} = $Options{keydata};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
263 $OptionsInfo{Sort} = $Options{sort};
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
264
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
265 $OptionsInfo{Overwrite} = defined $Options{overwrite} ? $Options{overwrite} : undef;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
266 $OptionsInfo{Root} = defined $Options{root} ? $Options{root} : undef;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
267 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
268
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
269 # Setup script usage and retrieve command line arguments specified using various options...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
270 sub SetupScriptUsage {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
271
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
272 # Retrieve all the options...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
273 %Options = ();
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
274 $Options{detail} = 1;
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
275 $Options{sort} = "ascending";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
276 $Options{keydata} = "numeric";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
277 if (!GetOptions(\%Options, "detail|d=i", "help|h", "key|k=s", "keydata=s", "overwrite|o", "root|r=s", "sort|s=s", "workingdir|w=s")) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
278 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
279 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
280 if ($Options{workingdir}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
281 if (! -d $Options{workingdir}) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
282 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
283 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
284 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
285 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
286 if ($Options{keydata} !~ /^(numeric|alphanumeric)$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
287 die "Error: The value specified, $Options{keydata}, for option \"--keydata\" is not valid. Allowed values: numeric or alphanumeric\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
288 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
289 if ($Options{sort} !~ /^(ascending|descending)$/i) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
290 die "Error: The value specified, $Options{sort}, for option \"-s --sort\" is not valid. Allowed values: ascending or descending\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
291 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
292 if (!IsPositiveInteger($Options{detail})) {
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
293 die "Error: The value specified, $Options{detail}, for option \"-d --detail\" is not valid. Allowed values: > 0\n";
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
294 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
295 }
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
296
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
297 __END__
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
298
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
299 =head1 NAME
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
300
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
301 SortSDFiles.pl - Sort SDFile(s) using values for a data field
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
302
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
303 =head1 SYNOPSIS
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
304
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
305 SortSDFiles.pl SDFile(s)...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
306
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
307 SortSDFiles.pl [B<-d, --detail> infolevel] [B<-h, --help>] [B<-k, --key> I<SD data field name>]
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
308 [B<--keydata> numeric | alphanumeric] [B<-o, --overwrite>] [B<-r, --root> rootname]
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
309 [B<-s, --sort> ascending | descending] [B<-w, --workingdir> dirname] SDFile(s)...
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
310
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
311 =head1 DESCRIPTION
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
312
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
313 Sort I<SDFile(s)> using values for a specified data field name key. Only one SD
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
314 data field name key can be specified for sorting. In an event of conflict during sorting
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
315 process, two similar values for a SD data field name key are simply transferred to
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
316 output files in order of their presence in input files. Additionally, compound records
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
317 with no data field name, empty field values, or field values containing multiple lines
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
318 are simply placed at the end. The file names are separated by space.The valid file
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
319 extensions are I<.sdf> and I<.sd>. All other file names are ignored. All the SD files in a
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
320 current directory can be specified either by I<*.sdf> or the current directory name.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
321
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
322 =head1 OPTIONS
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
323
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
324 =over 4
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
325
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
326 =item B<-d, --detail> I<infolevel>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
327
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
328 Level of information to print about compound records being ignored. Default: I<1>. Possible
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
329 values: I<1, 2 or 3>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
330
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
331 =item B<-h, --help>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
332
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
333 Print this help message.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
334
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
335 =item B<-k, --key> I<SD data field name>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
336
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
337 I<SDFile(s)> data field name used for sorting compound records. Default value: I<first
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
338 data field name>. Compound records with no I<sdfieldname>, empty field values, field
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
339 values containing multiple lines, or field values inappropriate for sorting are simply placed
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
340 at the end.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
341
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
342 =item B<--keydata> I<numeric | alphanumeric>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
343
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
344 Data type for I<sdfieldname> values. Possible values: I<numeric or alphanumeric>. Default
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
345 value: I<numeric>. For I<alphanumeric> data values, comparison is case insensitive.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
346
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
347 =item B<-o, --overwrite>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
348
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
349 Overwrite existing files.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
350
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
351 =item B<-r, --root> I<rootname>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
352
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
353 New SD file name is generated using the root: <Root>.<Ext>. Default new file
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
354 name: <InitialSDFileName>SortedByDataField.<Ext>. This option is ignored for multiple
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
355 input files.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
356
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
357 =item B<-s, --sort> I<ascending | descending>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
358
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
359 Sorting order for SD data field values. Possible values: I<ascending or descending>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
360 Default value: I<ascending>.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
361
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
362 =item B<-w, --workingdir> I<dirname>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
363
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
364 Location of working directory. Default: current directory.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
365
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
366 =back
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
367
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
368 =head1 EXAMPLES
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
369
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
370 To perform numerical sort in ascending order using first data field values and
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
371 generate a new SD file NewSample1.sdf, type:
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
372
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
373 % SortSDFiles.pl -o -r NewSample1 Sample1.sdf
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
374
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
375 To perform numerical sort in descending order using MolWeight data field and
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
376 generate a new SD text file NewSample1.sdf, type:
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
377
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
378 % SortSDFiles.pl -k MolWeight --keydata numeric -s descending
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
379 -r NewSample1 -o Sample1.sdf
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
380
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
381 =head1 AUTHOR
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
382
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
383 Manish Sud <msud@san.rr.com>
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
384
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
385 =head1 SEE ALSO
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
386
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
387 JoinSDFiles.pl, MergeTextFilesWithSD.pl, SplitSDFiles.pl, SDFilesToHTML.pl
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
388
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
389 =head1 COPYRIGHT
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
390
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
391 Copyright (C) 2015 Manish Sud. All rights reserved.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
392
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
393 This file is part of MayaChemTools.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
394
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
395 MayaChemTools is free software; you can redistribute it and/or modify it under
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
396 the terms of the GNU Lesser General Public License as published by the Free
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
397 Software Foundation; either version 3 of the License, or (at your option)
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
398 any later version.
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
399
73ae111cf86f Uploaded
deepakjadmin
parents:
diff changeset
400 =cut