biblicit 2.2.0 → 2.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/biblicit/version.rb +1 -1
- data/parscit/lib/HeaderParse/API/ParserMethods.pm +0 -1
- data/parscit/lib/HeaderParse/Config/API_Config.pm +5 -8
- data/parscit/lib/ParsCit/Config.pm +1 -1
- data/parscit/lib/ParsCit/Tr2crfpp.pm +9 -14
- data/parscit/lib/ParsHed/Config.pm +1 -1
- data/parscit/lib/ParsHed/Tr2crfpp.pm +10 -7
- data/parscit/lib/ParsHed/Tr2crfpp_token.pm +7 -10
- data/parscit/lib/SectLabel/AAMatching.pm +6 -2
- data/parscit/lib/SectLabel/Config.pm +1 -1
- data/parscit/lib/SectLabel/Controller.pm +4 -2
- data/parscit/lib/SectLabel/Tr2crfpp.pm +4 -2
- metadata +4 -4
data/lib/biblicit/version.rb
CHANGED
@@ -17,7 +17,6 @@ package HeaderParse::API::ParserMethods;
|
|
17
17
|
|
18
18
|
use utf8;
|
19
19
|
use Data::Dumper;
|
20
|
-
use FindBin;
|
21
20
|
use HeaderParse::API::NamePatternMatch;
|
22
21
|
use HeaderParse::API::MultiClassChunking; #default to use all export by this module
|
23
22
|
use HeaderParse::API::LoadInformation;
|
@@ -12,7 +12,6 @@
|
|
12
12
|
#
|
13
13
|
package HeaderParse::Config::API_Config;
|
14
14
|
|
15
|
-
use FindBin qw($Bin);
|
16
15
|
require Exporter;
|
17
16
|
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
|
18
17
|
|
@@ -26,17 +25,15 @@ else {
|
|
26
25
|
$Classifier = "svm_classify5"; # assume on path
|
27
26
|
}
|
28
27
|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
if ($FindBin::Bin =~ /(.*)/) { $path = $1; }
|
33
|
-
}
|
28
|
+
use File::Basename;
|
29
|
+
my $dir = dirname(__FILE__);
|
30
|
+
my $parscitHome = "$dir/../../../";
|
34
31
|
|
35
|
-
$Resource_Dir = "$
|
32
|
+
$Resource_Dir = "$parscitHome/resources/headerParse";
|
36
33
|
$Database_Dir = "$Resource_Dir/database/";
|
37
34
|
$Data_Dir = "$Resource_Dir/data/";
|
38
35
|
$offlineD = "$Resource_Dir/models/";
|
39
|
-
$Tmp_Dir = "$
|
36
|
+
$Tmp_Dir = "$parscitHome/tmp";
|
40
37
|
|
41
38
|
$nMinHeaderLength = 50;
|
42
39
|
$nMaxHeaderLength = 2500;
|
@@ -15,7 +15,7 @@ $serverPort = 10555;
|
|
15
15
|
$URI = 'http://citeseerx.org/algorithms/parscit/wsdl';
|
16
16
|
|
17
17
|
## Tr2crfpp
|
18
|
-
## Paths relative to ParsCit root dir
|
18
|
+
## Paths relative to ParsCit root dir
|
19
19
|
$tmpDir = "tmp";
|
20
20
|
$dictFile = "resources/parsCitDict.txt";
|
21
21
|
$crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "crfpp/crf_test";
|
@@ -12,25 +12,20 @@ package ParsCit::Tr2crfpp;
|
|
12
12
|
use utf8;
|
13
13
|
use strict 'vars';
|
14
14
|
|
15
|
-
use FindBin;
|
16
15
|
use Encode ();
|
17
16
|
|
18
17
|
use ParsCit::Config;
|
19
18
|
|
20
|
-
|
21
|
-
my $
|
22
|
-
$
|
23
|
-
|
24
|
-
my $dict_file = $ParsCit::Config::dictFile;
|
25
|
-
$dict_file = "$FindBin::Bin/../$dict_file";
|
26
|
-
|
27
|
-
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$FindBin::Bin/../$ParsCit::Config::crf_test";
|
19
|
+
use File::Basename;
|
20
|
+
my $dir = dirname(__FILE__);
|
21
|
+
my $parscitHome = "$dir/../../";
|
28
22
|
|
29
|
-
|
30
|
-
$
|
31
|
-
|
32
|
-
my $
|
33
|
-
$
|
23
|
+
### USER customizable section
|
24
|
+
my $tmp_dir = "$parscitHome/$ParsCit::Config::tmpDir";
|
25
|
+
my $dict_file = "$parscitHome/$ParsCit::Config::dictFile";
|
26
|
+
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$parscitHome/$ParsCit::Config::crf_test";
|
27
|
+
my $model_file = "$parscitHome/$ParsCit::Config::modelFile";
|
28
|
+
my $split_model_file = "$parscitHome/$ParsCit::Config::splitModelFile";
|
34
29
|
### END user customizable section
|
35
30
|
|
36
31
|
###
|
@@ -4,7 +4,7 @@ $algorithmName = "ParsHed";
|
|
4
4
|
$algorithmVersion = "110505";
|
5
5
|
|
6
6
|
## Tr2crfpp
|
7
|
-
## Paths relative to ParsCit root dir
|
7
|
+
## Paths relative to ParsCit root dir
|
8
8
|
$tmpDir = "tmp";
|
9
9
|
$dictFile = "resources/parsCitDict.txt";
|
10
10
|
$keywordFile = "resources/parsHed/keywords";
|
@@ -10,28 +10,31 @@ package ParsHed::Tr2crfpp;
|
|
10
10
|
|
11
11
|
use strict 'vars';
|
12
12
|
use utf8;
|
13
|
-
use FindBin;
|
14
13
|
use ParsHed::Config;
|
15
14
|
use Encode ();
|
16
15
|
|
16
|
+
use File::Basename;
|
17
|
+
my $dir = dirname(__FILE__);
|
18
|
+
my $parscitHome = "$dir/../../";
|
19
|
+
|
17
20
|
### USER customizable section
|
18
21
|
|
19
22
|
my $tmpDir = $ParsHed::Config::tmpDir;
|
20
|
-
$tmpDir = "$
|
23
|
+
$tmpDir = "$parscitHome/$tmpDir";
|
21
24
|
|
22
25
|
my $dictFile = $ParsHed::Config::dictFile;
|
23
|
-
$dictFile = "$
|
26
|
+
$dictFile = "$parscitHome/$dictFile";
|
24
27
|
|
25
28
|
my $keywordFile = $ParsHed::Config::keywordFile;
|
26
|
-
$keywordFile = "$
|
29
|
+
$keywordFile = "$parscitHome/$keywordFile";
|
27
30
|
|
28
31
|
my $bigramFile = $ParsHed::Config::bigramFile;
|
29
|
-
$bigramFile = "$
|
32
|
+
$bigramFile = "$parscitHome/$bigramFile";
|
30
33
|
|
31
|
-
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$
|
34
|
+
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$parscitHome/$ParsHed::Config::crf_test";
|
32
35
|
|
33
36
|
my $modelFile = $ParsHed::Config::modelFile;
|
34
|
-
$modelFile = "$
|
37
|
+
$modelFile = "$parscitHome/$modelFile";
|
35
38
|
|
36
39
|
### END user customizable section
|
37
40
|
|
@@ -10,22 +10,19 @@ package ParsHed::Tr2crfpp_token;
|
|
10
10
|
|
11
11
|
use strict 'vars';
|
12
12
|
use utf8;
|
13
|
-
use FindBin;
|
14
13
|
use ParsHed::Config;
|
15
14
|
use Encode ();
|
16
15
|
|
17
16
|
### USER customizable section
|
18
17
|
|
19
|
-
|
20
|
-
$
|
18
|
+
use File::Basename;
|
19
|
+
my $dir = dirname(__FILE__);
|
20
|
+
my $parscitHome = "$dir/../../";
|
21
21
|
|
22
|
-
my $
|
23
|
-
$dictFile = "$
|
24
|
-
|
25
|
-
my $
|
26
|
-
|
27
|
-
my $modelFile = $ParsHed::Config::oldModelFile;
|
28
|
-
$modelFile = "$FindBin::Bin/../$modelFile";
|
22
|
+
my $tmpDir = "$parscitHome/$ParsHed::Config::tmpDir";
|
23
|
+
my $dictFile = "$parscitHome/$ParsHed::Config::dictFile";
|
24
|
+
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$parscitHome/$ParsHed::Config::crf_test";
|
25
|
+
my $modelFile = "$parscitHome/$ParsHed::Config::oldModelFile";
|
29
26
|
|
30
27
|
### END user customizable section
|
31
28
|
|
@@ -21,10 +21,14 @@ use Class::Struct;
|
|
21
21
|
use SectLabel::Config;
|
22
22
|
use ParsCit::PostProcess;
|
23
23
|
|
24
|
+
use File::Basename;
|
25
|
+
my $dir = dirname(__FILE__);
|
26
|
+
my $parscitHome = "$dir/../../";
|
27
|
+
|
24
28
|
# Dictionary
|
25
29
|
my %dict = ();
|
26
30
|
# CRF++
|
27
|
-
my $crft = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$
|
31
|
+
my $crft = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$parscitHome/$SectLabel::Config::crf_test";
|
28
32
|
|
29
33
|
# Matching features of each author, including
|
30
34
|
# Signals
|
@@ -77,7 +81,7 @@ sub AAMatching
|
|
77
81
|
my $aff_lines = Omni::Traversal::OmniCollector($doc, $aff_addrs, $need_object);
|
78
82
|
|
79
83
|
# Dictionary
|
80
|
-
ReadDict($
|
84
|
+
ReadDict($parscitHome . $SectLabel::Config::dictFile);
|
81
85
|
|
82
86
|
# Authors
|
83
87
|
my ($aut_features, $aut_rc_features) = AuthorFeatureExtraction($aut_lines, $aut_addrs);
|
@@ -17,7 +17,9 @@ require 'dumpvar.pl';
|
|
17
17
|
use strict;
|
18
18
|
|
19
19
|
# Dependencies
|
20
|
-
use
|
20
|
+
use File::Basename;
|
21
|
+
my $dir = dirname(__FILE__);
|
22
|
+
my $parscitHome = "$dir/../../";
|
21
23
|
|
22
24
|
# Local libraries
|
23
25
|
use SectLabel::Config;
|
@@ -25,7 +27,7 @@ use SectLabel::Tr2crfpp;
|
|
25
27
|
use SectLabel::PostProcess;
|
26
28
|
use CSXUtil::SafeText qw(cleanXML);
|
27
29
|
|
28
|
-
my $generic_sect_path = $
|
30
|
+
my $generic_sect_path = $parscitHome . "bin/sectLabel/genericSectExtract.rb";
|
29
31
|
|
30
32
|
###
|
31
33
|
# Main API method for generating an XML document including all
|
@@ -13,14 +13,16 @@ use utf8;
|
|
13
13
|
use strict 'vars';
|
14
14
|
|
15
15
|
# Dependencies
|
16
|
-
use FindBin;
|
17
16
|
use Encode ();
|
17
|
+
use File::Basename;
|
18
|
+
my $dir = dirname(__FILE__);
|
19
|
+
my $parscitHome = "$dir/../../";
|
18
20
|
|
19
21
|
# Local libraries
|
20
22
|
use SectLabel::Config;
|
21
23
|
|
22
24
|
### USER customizable section
|
23
|
-
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$
|
25
|
+
my $crf_test = $ENV{'CRFPP_HOME'} ? "$ENV{'CRFPP_HOME'}/bin/crf_test" : "$parscitHome/$SectLabel::Config::crf_test";
|
24
26
|
### END user customizable section
|
25
27
|
|
26
28
|
my %dict = ();
|
metadata
CHANGED
@@ -2,14 +2,14 @@
|
|
2
2
|
name: biblicit
|
3
3
|
version: !ruby/object:Gem::Version
|
4
4
|
prerelease:
|
5
|
-
version: 2.2.
|
5
|
+
version: 2.2.1
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
8
8
|
- David Judd
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-05-
|
12
|
+
date: 2013-05-08 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
prerelease: false
|
@@ -435,7 +435,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
435
435
|
- !ruby/object:Gem::Version
|
436
436
|
segments:
|
437
437
|
- 0
|
438
|
-
hash:
|
438
|
+
hash: 782848681955337634
|
439
439
|
version: '0'
|
440
440
|
none: false
|
441
441
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
@@ -444,7 +444,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
444
444
|
- !ruby/object:Gem::Version
|
445
445
|
segments:
|
446
446
|
- 0
|
447
|
-
hash:
|
447
|
+
hash: 782848681955337634
|
448
448
|
version: '0'
|
449
449
|
none: false
|
450
450
|
requirements:
|