|
0
|
1 #!/usr/bin/perl -w
|
|
|
2 #
|
|
|
3 # $RCSfile: SortSDFiles.pl,v $
|
|
|
4 # $Date: 2015/02/28 20:46:21 $
|
|
|
5 # $Revision: 1.26 $
|
|
|
6 #
|
|
|
7 # Author: Manish Sud <msud@san.rr.com>
|
|
|
8 #
|
|
|
9 # Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
10 #
|
|
|
11 # This file is part of MayaChemTools.
|
|
|
12 #
|
|
|
13 # MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
14 # the terms of the GNU Lesser General Public License as published by the Free
|
|
|
15 # Software Foundation; either version 3 of the License, or (at your option) any
|
|
|
16 # later version.
|
|
|
17 #
|
|
|
18 # MayaChemTools is distributed in the hope that it will be useful, but without
|
|
|
19 # any warranty; without even the implied warranty of merchantability of fitness
|
|
|
20 # for a particular purpose. See the GNU Lesser General Public License for more
|
|
|
21 # details.
|
|
|
22 #
|
|
|
23 # You should have received a copy of the GNU Lesser General Public License
|
|
|
24 # along with MayaChemTools; if not, see <http://www.gnu.org/licenses/> or
|
|
|
25 # write to the Free Software Foundation Inc., 59 Temple Place, Suite 330,
|
|
|
26 # Boston, MA, 02111-1307, USA.
|
|
|
27 #
|
|
|
28
|
|
|
29 use strict;
|
|
|
30 use FindBin; use lib "$FindBin::Bin/../lib";
|
|
|
31 use Getopt::Long;
|
|
|
32 use File::Basename;
|
|
|
33 use Text::ParseWords;
|
|
|
34 use Benchmark;
|
|
|
35 use FileUtil;
|
|
|
36 use SDFileUtil;
|
|
|
37 use TextUtil;
|
|
|
38
|
|
|
39 my($ScriptName, %Options, $StartTime, $EndTime, $TotalTime);
|
|
|
40
|
|
|
41 # Autoflush STDOUT
|
|
|
42 $| = 1;
|
|
|
43
|
|
|
44 # Starting message...
|
|
|
45 $ScriptName = basename($0);
|
|
|
46 print "\n$ScriptName: Starting...\n\n";
|
|
|
47 $StartTime = new Benchmark;
|
|
|
48
|
|
|
49 # Get the options and setup script...
|
|
|
50 SetupScriptUsage();
|
|
|
51 if ($Options{help} || @ARGV < 1) {
|
|
|
52 die GetUsageFromPod("$FindBin::Bin/$ScriptName");
|
|
|
53 }
|
|
|
54
|
|
|
55 my(@SDFilesList);
|
|
|
56 @SDFilesList = ExpandFileNames(\@ARGV, "sdf sd");
|
|
|
57
|
|
|
58 print "Processing options...\n";
|
|
|
59 my(%OptionsInfo);
|
|
|
60 ProcessOptions();
|
|
|
61
|
|
|
62 print "Checking input SD file(s)...\n";
|
|
|
63 my(%SDFilesInfo);
|
|
|
64 RetrieveSDFilesInfo();
|
|
|
65
|
|
|
66 # Generate output files...
|
|
|
67 my($FileIndex);
|
|
|
68 if (@SDFilesList > 1) {
|
|
|
69 print "\nProcessing SD files...\n";
|
|
|
70 }
|
|
|
71 for $FileIndex (0 .. $#SDFilesList) {
|
|
|
72 if ($SDFilesInfo{FileOkay}[$FileIndex]) {
|
|
|
73 print "\nProcessing file $SDFilesList[$FileIndex]...\n";
|
|
|
74 SortSDFile($FileIndex);
|
|
|
75 }
|
|
|
76 }
|
|
|
77 print "\n$ScriptName:Done...\n\n";
|
|
|
78
|
|
|
79 $EndTime = new Benchmark;
|
|
|
80 $TotalTime = timediff ($EndTime, $StartTime);
|
|
|
81 print "Total time: ", timestr($TotalTime), "\n";
|
|
|
82
|
|
|
83 ###############################################################################
|
|
|
84
|
|
|
85 # Sort it out...
|
|
|
86 sub SortSDFile {
|
|
|
87 my($Index) = @_;
|
|
|
88 my($SDFile, $NewSDFile, $KeyDataFieldName);
|
|
|
89
|
|
|
90 $SDFile = $SDFilesList[$Index];
|
|
|
91 $NewSDFile = $SDFilesInfo{OutFile}[$Index];
|
|
|
92 $KeyDataFieldName = $SDFilesInfo{KeyDataFieldName}[$Index];
|
|
|
93
|
|
|
94 print "Generating new SD file $NewSDFile...\n";
|
|
|
95 open NEWSDFILE, ">$NewSDFile" or die "Error: Couldn't open $NewSDFile: $! \n";
|
|
|
96 open SDFILE, "$SDFile" or die "Error: Can't open $SDFile: $! \n";
|
|
|
97
|
|
|
98 # Go over all compound records and store 'em using key value as hash...
|
|
|
99 my(%KeyToCompundRecordsMap, @InvalidCompoundRecords, $CmpdCount, $CmpdString, @CmpdLines, %DataFieldValues, $KeyDataFieldValue);
|
|
|
100 %KeyToCompundRecordsMap = ();
|
|
|
101 @InvalidCompoundRecords = ();
|
|
|
102 $CmpdCount = 0;
|
|
|
103
|
|
|
104 COMPOUND: while ($CmpdString = ReadCmpdString(\*SDFILE)) {
|
|
|
105 $CmpdCount++;
|
|
|
106 @CmpdLines = split "\n", $CmpdString;
|
|
|
107 %DataFieldValues = GetCmpdDataHeaderLabelsAndValues(\@CmpdLines);
|
|
|
108 #Make sure data field value is okay...
|
|
|
109 if (!(IsNotEmpty($DataFieldValues{$KeyDataFieldName}) && ($DataFieldValues{$KeyDataFieldName} !~ /\n/))) {
|
|
|
110 push @InvalidCompoundRecords, $CmpdString;
|
|
|
111 if ($OptionsInfo{DetailLevel} >= 3 ) {
|
|
|
112 print "Ignoring compound record $CmpdCount: Contains empty value for key data field $KeyDataFieldName :\n $CmpdString\n\n";
|
|
|
113 }
|
|
|
114 elsif ($OptionsInfo{DetailLevel} >= 2) {
|
|
|
115 print "Ignoring compound record $CmpdCount: Contains empty value for key data field $KeyDataFieldName...\n";
|
|
|
116 }
|
|
|
117 next COMPOUND;
|
|
|
118 }
|
|
|
119 $KeyDataFieldValue = $DataFieldValues{$KeyDataFieldName};
|
|
|
120 if ($OptionsInfo{KeyData} =~ /^numeric$/i) {
|
|
|
121 if (!IsFloat($KeyDataFieldValue)) {
|
|
|
122 push @InvalidCompoundRecords, $CmpdString;
|
|
|
123 if ($OptionsInfo{DetailLevel} >= 3 ) {
|
|
|
124 print "Ignoring compound record $CmpdCount: Contains non-numerical value for key data field $KeyDataFieldName :\n $CmpdString\n\n";
|
|
|
125 }
|
|
|
126 elsif ($OptionsInfo{DetailLevel} >= 2) {
|
|
|
127 print "Ignoring compound record $CmpdCount: Contains non-numerical value for key data field $KeyDataFieldName...\n";
|
|
|
128 }
|
|
|
129 next COMPOUND;
|
|
|
130 }
|
|
|
131 }
|
|
|
132 if (exists($KeyToCompundRecordsMap{$KeyDataFieldValue})) {
|
|
|
133 # Append to existing coompund data...
|
|
|
134 $KeyToCompundRecordsMap{$KeyDataFieldValue} .= "\n" . $CmpdString;
|
|
|
135 }
|
|
|
136 else {
|
|
|
137 $KeyToCompundRecordsMap{$KeyDataFieldValue} = $CmpdString;
|
|
|
138 }
|
|
|
139 }
|
|
|
140
|
|
|
141 if ($OptionsInfo{Sort} =~ /^ascending$/i) {
|
|
|
142 if ($OptionsInfo{KeyData} =~ /^alphanumeric$/i) {
|
|
|
143 for $KeyDataFieldValue (sort { lc($a) cmp lc($b) } keys %KeyToCompundRecordsMap ) {
|
|
|
144 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
|
|
|
145 }
|
|
|
146 }
|
|
|
147 else {
|
|
|
148 for $KeyDataFieldValue (sort { $a <=> $b } keys %KeyToCompundRecordsMap ) {
|
|
|
149 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
|
|
|
150 }
|
|
|
151 }
|
|
|
152 }
|
|
|
153 else {
|
|
|
154 if ($OptionsInfo{KeyData} =~ /^alphanumeric$/i) {
|
|
|
155 for $KeyDataFieldValue (sort { lc($b) cmp lc($a) } keys %KeyToCompundRecordsMap ) {
|
|
|
156 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
|
|
|
157 }
|
|
|
158 }
|
|
|
159 else {
|
|
|
160 for $KeyDataFieldValue (sort { $b <=> $a } keys %KeyToCompundRecordsMap ) {
|
|
|
161 print NEWSDFILE "$KeyToCompundRecordsMap{$KeyDataFieldValue}\n";
|
|
|
162 }
|
|
|
163 }
|
|
|
164 }
|
|
|
165 # Append the records containing data not appropriate for sorting...
|
|
|
166 if (@InvalidCompoundRecords) {
|
|
|
167 print "Placing ", scalar(@InvalidCompoundRecords)," compound record(s) with invalid data field key data the end...\n";
|
|
|
168 for $CmpdString (@InvalidCompoundRecords) {
|
|
|
169 print NEWSDFILE "$CmpdString\n";
|
|
|
170 }
|
|
|
171 }
|
|
|
172 close NEWSDFILE;
|
|
|
173 close SDFILE;
|
|
|
174 }
|
|
|
175
|
|
|
176 # Retrieve information about input SD files...
|
|
|
177 sub RetrieveSDFilesInfo {
|
|
|
178 my($Index, $SDFile, $FileDir, $FileName, $FileExt, $OutFileRoot, $OutFile, $DataFieldName);
|
|
|
179
|
|
|
180 %SDFilesInfo = ();
|
|
|
181
|
|
|
182 @{$SDFilesInfo{FileOkay}} = ();
|
|
|
183 @{$SDFilesInfo{OutFile}} = ();
|
|
|
184 @{$SDFilesInfo{KeyDataFieldName}} = ();
|
|
|
185
|
|
|
186 FILELIST: for $Index (0 .. $#SDFilesList) {
|
|
|
187 $SDFile = $SDFilesList[$Index];
|
|
|
188 $SDFilesInfo{FileOkay}[$Index] = 0;
|
|
|
189 $SDFilesInfo{OutFile}[$Index] = "";
|
|
|
190 $SDFilesInfo{KeyDataFieldName}[$Index] = "";
|
|
|
191
|
|
|
192 if (!(-e $SDFile)) {
|
|
|
193 warn "Warning: Ignoring file $SDFile: It doesn't exist\n";
|
|
|
194 next FILELIST;
|
|
|
195 }
|
|
|
196 if (!CheckFileType($SDFile, "sd sdf")) {
|
|
|
197 warn "Warning: Ignoring file $SDFile: It's not a SD file\n";
|
|
|
198 next FILELIST;
|
|
|
199 }
|
|
|
200 $FileDir = ""; $FileName = ""; $FileExt = "";
|
|
|
201 ($FileDir, $FileName, $FileExt) = ParseFileName($SDFile);
|
|
|
202 if ($Options{root} && (@SDFilesList == 1)) {
|
|
|
203 my ($RootFileDir, $RootFileName, $RootFileExt) = ParseFileName($Options{root});
|
|
|
204 if ($RootFileName && $RootFileExt) {
|
|
|
205 $FileName = $RootFileName;
|
|
|
206 }
|
|
|
207 else {
|
|
|
208 $FileName = $Options{root};
|
|
|
209 }
|
|
|
210 $OutFileRoot = $FileName;
|
|
|
211 }
|
|
|
212 else {
|
|
|
213 $OutFileRoot = $FileName . "SortedByDataField";
|
|
|
214 }
|
|
|
215
|
|
|
216 $OutFile = $OutFileRoot . ".$FileExt";
|
|
|
217 if (lc($OutFile) eq lc($SDFile)) {
|
|
|
218 warn "Warning: Ignoring file $SDFile:Output file name, $OutFile, is same as input SD file name, $SDFile\n";
|
|
|
219 next FILELIST;
|
|
|
220 }
|
|
|
221 if (!$Options{overwrite}) {
|
|
|
222 if (-e $OutFile) {
|
|
|
223 warn "Warning: Ignoring file $SDFile: The file $OutFile already exists\n";
|
|
|
224 next FILELIST;
|
|
|
225 }
|
|
|
226 }
|
|
|
227 # Setup data field name...
|
|
|
228 if ($OptionsInfo{SpecifiedDataFieldName}) {
|
|
|
229 $DataFieldName = $OptionsInfo{SpecifiedDataFieldName};
|
|
|
230 }
|
|
|
231 else {
|
|
|
232 my($CmpdString, @CmpdLines, @DataFieldNames);
|
|
|
233 @DataFieldNames = ();
|
|
|
234 if (!open(SDFILE, "$SDFile")) {
|
|
|
235 warn "Warning: Ignoring file $SDFile: Couldn't open it: $! \n";
|
|
|
236 next FILELIST;
|
|
|
237 }
|
|
|
238 $CmpdString = ReadCmpdString(\*SDFILE);
|
|
|
239 close SDFILE;
|
|
|
240
|
|
|
241 @CmpdLines = split "\n", $CmpdString;
|
|
|
242 @DataFieldNames = GetCmpdDataHeaderLabels(\@CmpdLines);
|
|
|
243 $DataFieldName = $DataFieldNames[0];
|
|
|
244 }
|
|
|
245
|
|
|
246 $SDFilesInfo{FileOkay}[$Index] = 1;
|
|
|
247 $SDFilesInfo{OutFile}[$Index] = "$OutFile";
|
|
|
248 $SDFilesInfo{KeyDataFieldName}[$Index] = $DataFieldName;
|
|
|
249 }
|
|
|
250 }
|
|
|
251
|
|
|
252 # Process option values...
|
|
|
253 sub ProcessOptions {
|
|
|
254 $OptionsInfo{DetailLevel} = $Options{detail};
|
|
|
255
|
|
|
256 $OptionsInfo{Key} = defined $Options{key} ? $Options{key} : undef;
|
|
|
257 $OptionsInfo{SpecifiedDataFieldName} = "";
|
|
|
258 if (defined $Options{key}) {
|
|
|
259 $OptionsInfo{SpecifiedDataFieldName} = $Options{key};
|
|
|
260 }
|
|
|
261
|
|
|
262 $OptionsInfo{KeyData} = $Options{keydata};
|
|
|
263 $OptionsInfo{Sort} = $Options{sort};
|
|
|
264
|
|
|
265 $OptionsInfo{Overwrite} = defined $Options{overwrite} ? $Options{overwrite} : undef;
|
|
|
266 $OptionsInfo{Root} = defined $Options{root} ? $Options{root} : undef;
|
|
|
267 }
|
|
|
268
|
|
|
269 # Setup script usage and retrieve command line arguments specified using various options...
|
|
|
270 sub SetupScriptUsage {
|
|
|
271
|
|
|
272 # Retrieve all the options...
|
|
|
273 %Options = ();
|
|
|
274 $Options{detail} = 1;
|
|
|
275 $Options{sort} = "ascending";
|
|
|
276 $Options{keydata} = "numeric";
|
|
|
277 if (!GetOptions(\%Options, "detail|d=i", "help|h", "key|k=s", "keydata=s", "overwrite|o", "root|r=s", "sort|s=s", "workingdir|w=s")) {
|
|
|
278 die "\nTo get a list of valid options and their values, use \"$ScriptName -h\" or\n\"perl -S $ScriptName -h\" command and try again...\n";
|
|
|
279 }
|
|
|
280 if ($Options{workingdir}) {
|
|
|
281 if (! -d $Options{workingdir}) {
|
|
|
282 die "Error: The value specified, $Options{workingdir}, for option \"-w --workingdir\" is not a directory name.\n";
|
|
|
283 }
|
|
|
284 chdir $Options{workingdir} or die "Error: Couldn't chdir $Options{workingdir}: $! \n";
|
|
|
285 }
|
|
|
286 if ($Options{keydata} !~ /^(numeric|alphanumeric)$/i) {
|
|
|
287 die "Error: The value specified, $Options{keydata}, for option \"--keydata\" is not valid. Allowed values: numeric or alphanumeric\n";
|
|
|
288 }
|
|
|
289 if ($Options{sort} !~ /^(ascending|descending)$/i) {
|
|
|
290 die "Error: The value specified, $Options{sort}, for option \"-s --sort\" is not valid. Allowed values: ascending or descending\n";
|
|
|
291 }
|
|
|
292 if (!IsPositiveInteger($Options{detail})) {
|
|
|
293 die "Error: The value specified, $Options{detail}, for option \"-d --detail\" is not valid. Allowed values: > 0\n";
|
|
|
294 }
|
|
|
295 }
|
|
|
296
|
|
|
297 __END__
|
|
|
298
|
|
|
299 =head1 NAME
|
|
|
300
|
|
|
301 SortSDFiles.pl - Sort SDFile(s) using values for a data field
|
|
|
302
|
|
|
303 =head1 SYNOPSIS
|
|
|
304
|
|
|
305 SortSDFiles.pl SDFile(s)...
|
|
|
306
|
|
|
307 SortSDFiles.pl [B<-d, --detail> infolevel] [B<-h, --help>] [B<-k, --key> I<SD data field name>]
|
|
|
308 [B<--keydata> numeric | alphanumeric] [B<-o, --overwrite>] [B<-r, --root> rootname]
|
|
|
309 [B<-s, --sort> ascending | descending] [B<-w, --workingdir> dirname] SDFile(s)...
|
|
|
310
|
|
|
311 =head1 DESCRIPTION
|
|
|
312
|
|
|
313 Sort I<SDFile(s)> using values for a specified data field name key. Only one SD
|
|
|
314 data field name key can be specified for sorting. In an event of conflict during sorting
|
|
|
315 process, two similar values for a SD data field name key are simply transferred to
|
|
|
316 output files in order of their presence in input files. Additionally, compound records
|
|
|
317 with no data field name, empty field values, or field values containing multiple lines
|
|
|
318 are simply placed at the end. The file names are separated by space.The valid file
|
|
|
319 extensions are I<.sdf> and I<.sd>. All other file names are ignored. All the SD files in a
|
|
|
320 current directory can be specified either by I<*.sdf> or the current directory name.
|
|
|
321
|
|
|
322 =head1 OPTIONS
|
|
|
323
|
|
|
324 =over 4
|
|
|
325
|
|
|
326 =item B<-d, --detail> I<infolevel>
|
|
|
327
|
|
|
328 Level of information to print about compound records being ignored. Default: I<1>. Possible
|
|
|
329 values: I<1, 2 or 3>.
|
|
|
330
|
|
|
331 =item B<-h, --help>
|
|
|
332
|
|
|
333 Print this help message.
|
|
|
334
|
|
|
335 =item B<-k, --key> I<SD data field name>
|
|
|
336
|
|
|
337 I<SDFile(s)> data field name used for sorting compound records. Default value: I<first
|
|
|
338 data field name>. Compound records with no I<sdfieldname>, empty field values, field
|
|
|
339 values containing multiple lines, or field values inappropriate for sorting are simply placed
|
|
|
340 at the end.
|
|
|
341
|
|
|
342 =item B<--keydata> I<numeric | alphanumeric>
|
|
|
343
|
|
|
344 Data type for I<sdfieldname> values. Possible values: I<numeric or alphanumeric>. Default
|
|
|
345 value: I<numeric>. For I<alphanumeric> data values, comparison is case insensitive.
|
|
|
346
|
|
|
347 =item B<-o, --overwrite>
|
|
|
348
|
|
|
349 Overwrite existing files.
|
|
|
350
|
|
|
351 =item B<-r, --root> I<rootname>
|
|
|
352
|
|
|
353 New SD file name is generated using the root: <Root>.<Ext>. Default new file
|
|
|
354 name: <InitialSDFileName>SortedByDataField.<Ext>. This option is ignored for multiple
|
|
|
355 input files.
|
|
|
356
|
|
|
357 =item B<-s, --sort> I<ascending | descending>
|
|
|
358
|
|
|
359 Sorting order for SD data field values. Possible values: I<ascending or descending>.
|
|
|
360 Default value: I<ascending>.
|
|
|
361
|
|
|
362 =item B<-w, --workingdir> I<dirname>
|
|
|
363
|
|
|
364 Location of working directory. Default: current directory.
|
|
|
365
|
|
|
366 =back
|
|
|
367
|
|
|
368 =head1 EXAMPLES
|
|
|
369
|
|
|
370 To perform numerical sort in ascending order using first data field values and
|
|
|
371 generate a new SD file NewSample1.sdf, type:
|
|
|
372
|
|
|
373 % SortSDFiles.pl -o -r NewSample1 Sample1.sdf
|
|
|
374
|
|
|
375 To perform numerical sort in descending order using MolWeight data field and
|
|
|
376 generate a new SD text file NewSample1.sdf, type:
|
|
|
377
|
|
|
378 % SortSDFiles.pl -k MolWeight --keydata numeric -s descending
|
|
|
379 -r NewSample1 -o Sample1.sdf
|
|
|
380
|
|
|
381 =head1 AUTHOR
|
|
|
382
|
|
|
383 Manish Sud <msud@san.rr.com>
|
|
|
384
|
|
|
385 =head1 SEE ALSO
|
|
|
386
|
|
|
387 JoinSDFiles.pl, MergeTextFilesWithSD.pl, SplitSDFiles.pl, SDFilesToHTML.pl
|
|
|
388
|
|
|
389 =head1 COPYRIGHT
|
|
|
390
|
|
|
391 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
392
|
|
|
393 This file is part of MayaChemTools.
|
|
|
394
|
|
|
395 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
396 the terms of the GNU Lesser General Public License as published by the Free
|
|
|
397 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
398 any later version.
|
|
|
399
|
|
|
400 =cut
|
