biblicit 2.2.3 → 2.3.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/biblicit/parscit.rb +22 -5
- data/lib/biblicit/version.rb +1 -1
- data/lib/biblicit.rb +1 -0
- data/parscit/bin/citeExtract.pl +9 -1
- metadata +18 -23
data/lib/biblicit/parscit.rb
CHANGED
@@ -17,14 +17,31 @@ module ParsCit
|
|
17
17
|
attr_reader :result
|
18
18
|
|
19
19
|
def initialize(in_txt, opts={})
|
20
|
-
|
21
|
-
|
20
|
+
parse_modes = if (opts.fetch :include_citations, false)
|
21
|
+
{ extract_all: [:citeseer, :parshed, :citations] }
|
22
|
+
else
|
23
|
+
{
|
24
|
+
extract_header_svm_only: [:citeseer],
|
25
|
+
extract_header_crf_only: [:parshed]
|
26
|
+
}
|
27
|
+
end
|
28
|
+
|
29
|
+
ENV['SVM_LIGHT_HOME'] ||= "#{File.dirname(`which svm_classify`)}"
|
22
30
|
ENV['CRFPP_HOME'] ||= "#{File.dirname(`which crf_test`)}/../"
|
23
31
|
ENV['PARSCIT_TMPDIR'] ||= "/tmp/"
|
24
32
|
|
25
|
-
|
26
|
-
|
27
|
-
|
33
|
+
@result = {}
|
34
|
+
|
35
|
+
parse_modes.map do |mode, keys|
|
36
|
+
outf = Tempfile.new mode.to_s
|
37
|
+
pid = spawn("#{PERL_DIR}/bin/citeExtract.pl -q -m #{mode} #{in_txt.path}", out: outf.path)
|
38
|
+
[pid, outf, keys]
|
39
|
+
end.each do |pid, outf, keys|
|
40
|
+
Process.wait pid
|
41
|
+
output = File.read outf
|
42
|
+
outf.unlink
|
43
|
+
@result.merge! parse(Nokogiri::XML output).slice(*keys)
|
44
|
+
end
|
28
45
|
end
|
29
46
|
|
30
47
|
private
|
data/lib/biblicit/version.rb
CHANGED
data/lib/biblicit.rb
CHANGED
data/parscit/bin/citeExtract.pl
CHANGED
@@ -86,7 +86,7 @@ sub Help
|
|
86
86
|
print STDERR "\t-q\tQuiet Mode (don't echo license)\n";
|
87
87
|
|
88
88
|
# Thang v100401: add new mode (extract_section), and -i <inputType>
|
89
|
-
print STDERR "\t-m <mode> \tMode (extract_citations, extract_header, extract_section, extract_meta, extract_all, default: extract_citations)\n";
|
89
|
+
print STDERR "\t-m <mode> \tMode (extract_citations, extract_header, extract_header_svm_only, extract_header_crf_only, extract_section, extract_meta, extract_all, default: extract_citations)\n";
|
90
90
|
print STDERR "\t-i <inputType> \tType (raw, xml, default: raw)\n";
|
91
91
|
print STDERR "\t-e <exportType>\tExport citations into multiple types (ads|bib|end|isi|ris|wordbib). Multiple types could be specified by contatenating with \"-\" e.g., bib-end-ris. Output files will be named as outfile.exportFormat, with outfile being the input argument, and exportFormat being each individual format supplied by -e option.\n";
|
92
92
|
print STDERR "\t-t\tUse token level model instead\n";
|
@@ -281,6 +281,14 @@ sub ParseMode
|
|
281
281
|
{
|
282
282
|
return ($PARSHED | $SVM);
|
283
283
|
}
|
284
|
+
elsif ($arg eq "extract_header_svm_only")
|
285
|
+
{
|
286
|
+
return $SVM;
|
287
|
+
}
|
288
|
+
elsif ($arg eq "extract_header_crf_only")
|
289
|
+
{
|
290
|
+
return $PARSHED;
|
291
|
+
}
|
284
292
|
elsif ($arg eq "extract_citations")
|
285
293
|
{
|
286
294
|
return $PARSCIT;
|
metadata
CHANGED
@@ -2,25 +2,25 @@
|
|
2
2
|
name: biblicit
|
3
3
|
version: !ruby/object:Gem::Version
|
4
4
|
prerelease:
|
5
|
-
version: 2.
|
5
|
+
version: 2.3.0
|
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-
|
12
|
+
date: 2013-06-13 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
|
-
prerelease: false
|
16
|
-
name: activesupport
|
17
|
-
type: :runtime
|
18
15
|
version_requirements: !ruby/object:Gem::Requirement
|
19
16
|
requirements:
|
20
17
|
- - ! '>='
|
21
18
|
- !ruby/object:Gem::Version
|
22
19
|
version: '0'
|
23
20
|
none: false
|
21
|
+
name: activesupport
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
24
|
requirement: !ruby/object:Gem::Requirement
|
25
25
|
requirements:
|
26
26
|
- - ! '>='
|
@@ -28,15 +28,15 @@ dependencies:
|
|
28
28
|
version: '0'
|
29
29
|
none: false
|
30
30
|
- !ruby/object:Gem::Dependency
|
31
|
-
prerelease: false
|
32
|
-
name: nokogiri
|
33
|
-
type: :runtime
|
34
31
|
version_requirements: !ruby/object:Gem::Requirement
|
35
32
|
requirements:
|
36
33
|
- - ! '>='
|
37
34
|
- !ruby/object:Gem::Version
|
38
35
|
version: '0'
|
39
36
|
none: false
|
37
|
+
name: nokogiri
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
40
|
requirement: !ruby/object:Gem::Requirement
|
41
41
|
requirements:
|
42
42
|
- - ! '>='
|
@@ -44,15 +44,15 @@ dependencies:
|
|
44
44
|
version: '0'
|
45
45
|
none: false
|
46
46
|
- !ruby/object:Gem::Dependency
|
47
|
-
prerelease: false
|
48
|
-
name: rake
|
49
|
-
type: :development
|
50
47
|
version_requirements: !ruby/object:Gem::Requirement
|
51
48
|
requirements:
|
52
49
|
- - ! '>='
|
53
50
|
- !ruby/object:Gem::Version
|
54
51
|
version: '0'
|
55
52
|
none: false
|
53
|
+
name: rake
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
56
|
requirement: !ruby/object:Gem::Requirement
|
57
57
|
requirements:
|
58
58
|
- - ! '>='
|
@@ -60,15 +60,15 @@ dependencies:
|
|
60
60
|
version: '0'
|
61
61
|
none: false
|
62
62
|
- !ruby/object:Gem::Dependency
|
63
|
-
prerelease: false
|
64
|
-
name: rspec
|
65
|
-
type: :development
|
66
63
|
version_requirements: !ruby/object:Gem::Requirement
|
67
64
|
requirements:
|
68
65
|
- - ! '>='
|
69
66
|
- !ruby/object:Gem::Version
|
70
67
|
version: '0'
|
71
68
|
none: false
|
69
|
+
name: rspec
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
72
|
requirement: !ruby/object:Gem::Requirement
|
73
73
|
requirements:
|
74
74
|
- - ! '>='
|
@@ -76,15 +76,15 @@ dependencies:
|
|
76
76
|
version: '0'
|
77
77
|
none: false
|
78
78
|
- !ruby/object:Gem::Dependency
|
79
|
-
prerelease: false
|
80
|
-
name: pry
|
81
|
-
type: :development
|
82
79
|
version_requirements: !ruby/object:Gem::Requirement
|
83
80
|
requirements:
|
84
81
|
- - ! '>='
|
85
82
|
- !ruby/object:Gem::Version
|
86
83
|
version: '0'
|
87
84
|
none: false
|
85
|
+
name: pry
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
88
|
requirement: !ruby/object:Gem::Requirement
|
89
89
|
requirements:
|
90
90
|
- - ! '>='
|
@@ -432,18 +432,12 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
432
432
|
requirements:
|
433
433
|
- - ! '>='
|
434
434
|
- !ruby/object:Gem::Version
|
435
|
-
segments:
|
436
|
-
- 0
|
437
|
-
hash: 3256160240819012702
|
438
435
|
version: '0'
|
439
436
|
none: false
|
440
437
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
441
438
|
requirements:
|
442
439
|
- - ! '>='
|
443
440
|
- !ruby/object:Gem::Version
|
444
|
-
segments:
|
445
|
-
- 0
|
446
|
-
hash: 3256160240819012702
|
447
441
|
version: '0'
|
448
442
|
none: false
|
449
443
|
requirements:
|
@@ -469,3 +463,4 @@ test_files:
|
|
469
463
|
- spec/fixtures/txt/sample1.txt
|
470
464
|
- spec/fixtures/txt/sample2.txt
|
471
465
|
- spec/spec_helper.rb
|
466
|
+
has_rdoc:
|