added support for excel and sqlite. bumped version to 1.3 RC1

5 files changed, 61 insertions, 24 deletions

diff --git a/ChangeLog b/ChangeLog
index 67b9191..f04ac65 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,13 @@
+2015-01-10  dmg  <dmg@uvic.ca>
+
+	* Bumped to version 1.3 RC 1
+
+	* ninka-sqlite.pl, ninka-excel.pl: prepared them for release
+
+	* ninka.pl: fixed bug in finding the path of where ninka was being executed from (reported by Ryan Biesemeyer)
+
+	* Fixed quotes in perl (René bScheibe)
+
 2015-01-05  dmg  <dmg@uvic.ca>
 
 	* filter/criticalword.dict: MIT+no-false-attribs license missing one sentence
diff --git a/README.TXT b/README.TXT
index 565465c..6dc14d9 100644
--- a/README.TXT
+++ b/README.TXT
@@ -1,4 +1,6 @@
-* Contact information. 
+-*-org-*-
+
+* Contact information.
 
 Any feedback will be appreciated. You can email us at Daniel M. German
 <dmg@uvic.ca> and Yuki Manabe <y-manabe@ist.osaka-u.ac.jp>
@@ -25,11 +27,16 @@ http://turingmachine.org/~dmg/papers/dmg2010ninka.pdf
 If you use Ninka for research purposes, we would appreciate you cite
 the above paper.
 
+* Contributors
+
+- Anthony Kohan for writing the excel and sqlite backends.
+- Armijn Hemel from Tjaldur Software Governance Solutions  for multiple bug reports and suggestions
+
 * License
- 
+
   Except for the directories comments and splitter, Ninka is licensed
   under the GPLv2+
- 
+
     Copyright (C) 2009-2010  Yuki Manabe and Daniel M. German
 
     This program is free software: you can redistribute it and/or modify
@@ -69,7 +76,7 @@ Perl version 5
 Ninka uses a pipe model (see below). Each step of the "pipe" creates a
 file, but
 
-ninka.pl [options] [filename] 
+ninka.pl [options] [filename]
 
 Available options
   -v verbose
@@ -107,26 +114,26 @@ It will create five files:
      - Licenses
      - Unmatched sentences in *.senttok that were not matched
 
-   
+
 
 
 * Ninka model
 
 Ninka uses a pipe-model. Each stage of the pipe does something very specific:
 
- 1. Comment extractor. 
+ 1. Comment extractor.
 
     - directory: extComments
 
     - command: extComments.pl, might use comments (included in distribution)
-    
+
     - Purpose: Extracts top comments of source code. If no
           comment extractor is known for the language, then extracts top lines from source (currently 700)
 
     - Creates <filename>.comments file
 
 2. Split sentences in comments
- 
+
      - directory: splitter
 
      - command: splitter.pl
@@ -151,7 +158,7 @@ Ninka uses a pipe-model. Each stage of the pipe does something very specific:
 4. Tokenizes sentences
 
      - Directory senttok
- 
+
      - command: senttok.pl
 
      - Purpose: It creates a file that corresponds to the recognized
@@ -168,7 +175,7 @@ Ninka uses a pipe-model. Each stage of the pipe does something very specific:
      - Purpose: looks at the sequence of sentence tokens and outputs the licenses found
 
      - Output: <filename>.license
-      
+
 The script ninka.pl takes care of all these steps, and optionally removes
 intermediary files, and writes to the stdout the licenses found.
 
diff --git a/ninka-excel.pl b/ninka-excel.pl
index c06c830..71adddf 100644..100755
--- a/ninka-excel.pl
+++ b/ninka-excel.pl
@@ -1,6 +1,6 @@
 #!/usr/bin/perl
 #
-#    Copyright (C) 2014  Anthony Kohan and Daniel M. German
+#    Copyright (C) 2014,2015  Anthony Kohan and Daniel M. German
 #
 #    This program is free software; you can redistribute it and/or
 #    modify it under the terms of the GNU General Public License as
@@ -27,8 +27,10 @@ use Spreadsheet::WriteExcel;
 
 
 if(scalar(@ARGV) != 2){
+    print STDERR "Ninka 1.3. sqlite wrapper\n";
+    print STDERR "Processes package file (.tar.gz, zip, jar. etc) and outputs to excel file\n";
     print STDERR "Incorrect number of arguments\n";
-    print STDERR "Correct usage is: perl ninka-wrapper <path to package file> <database name>\n";
+    print STDERR "Correct usage is: $0 <path to package file> <excel-file>\n";
     exit 1;
 }
 
diff --git a/ninka-sqlite.pl b/ninka-sqlite.pl
index 49b7576..65d746a 100644..100755
--- a/ninka-sqlite.pl
+++ b/ninka-sqlite.pl
@@ -1,4 +1,20 @@
 #!/usr/bin/perl
+#
+#    Copyright (C) 2014,2015  Anthony Kohan and Daniel M. German
+#
+#    This program is free software; you can redistribute it and/or
+#    modify it under the terms of the GNU General Public License as
+#    published by the Free Software Foundation; either version 2 of
+#    the License, or (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+#    General Public License for more details.
+#
+#    You should have received a copy of the GNU General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+#
 
 use strict;
 use Switch;
@@ -8,9 +24,13 @@ use File::Find;
 use File::Basename;
 use Scalar::Util qw(looks_like_number);
 
+
+
 if(scalar(@ARGV) != 2){
+    print STDERR "Ninka 1.3. sqlite wrapper\n";
+    print STDERR "Processes package file (.tar.gz, zip, jar. etc) and outputs to sqlite file\n";
     print STDERR "Incorrect number of arguments\n";
-    print STDERR "Correct usage is: perl ninka-wrapper <path to package file> <database name>\n";
+    print STDERR "Correct usage is: $0 <path to package file> <database name>\n";
     exit 1;
 }
 
diff --git a/ninka.pl b/ninka.pl
index b2fcd9a..3987a41 100755
--- a/ninka.pl
+++ b/ninka.pl
@@ -18,10 +18,11 @@
 
 use strict;
 use Getopt::Std;
+use File::Basename;
 
 my %opts = ();
 if (!getopts ("vfCcSsGgTtLd",\%opts) or scalar(@ARGV) == 0) {
-print STDERR "Ninka version 1.2
+print STDERR "Ninka version 1.3
 
 Usage $0 -fCtTvcgsGd <filename>
 
@@ -42,7 +43,7 @@ Usage $0 -fCtTvcgsGd <filename>
 
   -L force creation of matching
 
-  -d delete intermediate files  
+  -d delete intermediate files
 
 \n";
 
@@ -55,14 +56,12 @@ my $verbose = exists $opts{v};
 my $delete = exists $opts{d};
 #$delete = 1;
 
-my $path = $0;
+my $path = dirname($0);
 
-$path =~ s/\/+[^\/]+$//;
 if ($path eq "") {
     $path = "./";
 }
 
-
 my $force = exists $opts{f};
 my $forceGood = exists $opts{G};
 my $forceSentences = exists $opts{S};
@@ -97,23 +96,23 @@ if (not (-f $original)) {
 }
 
 
-Do_File_Process($original, $commentsFile, ($force or $forceComments), 
+Do_File_Process($original, $commentsFile, ($force or $forceComments),
                 "$path/extComments/extComments.pl -c1 ${f}",
                 "Creating comments file",
                 exists $opts{c});
 
 
-Do_File_Process($commentsFile, $sentencesFile, ($force or $forceSentences), 
+Do_File_Process($commentsFile, $sentencesFile, ($force or $forceSentences),
                 "$path/splitter/splitter.pl ${commentsFile}",
                 "Splitting sentences", exists $opts{s}
     );
 
-Do_File_Process( $sentencesFile, $goodsentFile, ($force or $forceGood), 
+Do_File_Process( $sentencesFile, $goodsentFile, ($force or $forceGood),
                  "$path/filter/filter.pl ${sentencesFile}",
                  "Filtering good sentences", exists $opts{s}
     );
 
-Do_File_Process($goodsentFile, $sentokFile, ($force or $forceSentok), 
+Do_File_Process($goodsentFile, $sentokFile, ($force or $forceSentok),
                 "$path/senttok/senttok.pl ${goodsentFile} > ${sentokFile}",
                 "Matching sentences against rules", exists $opts{t}
     );
@@ -147,7 +146,7 @@ sub Do_File_Process
         print "Running ${cmd}:" if ($verbose);
         execute($cmd);
     } else {
-        print "File [$output] newer than input [$input], not creating:" if ($verbose);    
+        print "File [$output] newer than input [$input], not creating:" if ($verbose);
     }
     if ($end) {
         print "Existing after $message" if $verbose;
@@ -180,4 +179,3 @@ sub newer
         return 1;
     }
 }
-