rbbt 1.2.5 → 2.0.0

data/test/rbbt/ner/test_abner.rb

@@ -1,17 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/ner/abner'
-require 'test/unit'
-
-class TestAbner < Test::Unit::TestCase
-
-  def test_extract
-      ner = Abner.new
-
-      mentions = ner.extract(" The P-ITIM-compelled multi-phosphoprotein complex binds to and activates SHP-2, which in turn dephosphorylates SHIP and Shc and probably other substrates.")
-      ["SHP-2", "SHIP", "Shc"].each{|mention| 
-        assert(mentions.include? mention)
-      }
-
-  end
-
-end

data/test/rbbt/ner/test_banner.rb

@@ -1,17 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/ner/banner'
-require 'test/unit'
-
-class TestBanner < Test::Unit::TestCase
-
-  def test_extract
-      ner = Banner.new
-
-      mentions = ner.extract(" The P-ITIM-compelled multi-phosphoprotein complex binds to and activates SHP-2, which in turn dephosphorylates SHIP and Shc and probably other substrates.")
-      ["SHP - 2", "SHIP", "Shc"].each{|mention| 
-        assert(mentions.include? mention)
-      }
-
-  end
-
-end

data/test/rbbt/ner/test_dictionaryNER.rb

@@ -1,122 +0,0 @@
-require 'rbbt'
-require 'rbbt/util/tmpfile'
-require 'rbbt/util/open'
-require 'rbbt/ner/dictionaryNER'
-require 'test/unit'
-
-class TestDictionaryNER < Test::Unit::TestCase
-
-  def setup
-    @dictionary  =<<-EOT
-DICT1\tWord1 Word2\tWord1
-DICT2\tWord3-Word4\tWord4
-    EOT
-
-    @dict = {
-      "word1" => [{'word2' => ['DICT1'] }, 'DICT1'],
-      "word3" => [{'word4' => ['DICT2'] }],
-      "word4" => ['DICT2'],
-    }
-  end
-
-  def test_simplify
-    assert_equal('word1', DictionaryNER.simplify( "Word1"))
-    assert_equal('ACL', DictionaryNER.simplify("ACL"))
-  end
-
-  def test_chunk
-    assert_equal(["Word1","Word2"], DictionaryNER.chunk('Word1-Word2'))
-    assert_equal(["Word1-1"], DictionaryNER.chunk('Word1-1'))
-  end
-
-  def test_match
-
-    [
-      
-      ["Word1", {"word1" => ["D1"]}, {"Word1" => ["D1"]}],
-      
-      ["Word1 Word1", {"word1" => ["D1"]}, {"Word1" => ["D1"]}],
-      
-      ["Word2 Word1 Word3", {"word1" => ["D1"]}, {"Word1" => ["D1"]} ],
-
-      ["Word2 Word1 Word4", {"word1" => ["D1","D2"]}, {"Word1" => ["D1","D2"]} ],
-
-      ["Word2 Word1 Word4", 
-        {"word1" => [{'word2' => ['D1']}]}, 
-        {} ],
-
-      [
-        "Word2 Word1 Word4", 
-        {"word1" => [ {'word4' => ['D1']} ] }, 
-        {"Word1 Word4" => ["D1"]}, 
-      ],
-
-      [
-        "Word2 Word1 Word4", 
-        {"word1" => [ {'word4' => ['D1']} ], "word4" => ['D2'] }, 
-        {"Word1 Word4" => ["D1"], "Word4" => ['D2']}, 
-      ],
-
-
-    ].each{|match_info|
-      text   = match_info[0]
-      dict   = match_info[1]
-      result = match_info[2]
-      assert_equal(result, DictionaryNER.match(dict, text))
-    }
-
-  end
-
-  def test_add_name
-    
-    [
-      
-      ["Word1", {"word1" => ['code']}],
-
-      ["Word1 Word2", {"word1" => [{"word2" => ['code']}]}],
-
-      ["Cerebellar stroke syndrome", {"cerebellar" => [{'stroke' => [{'syndrome' => ['code']}]}]}]
-
-    ].each{|info|
-      name = info[0]
-      result = info[1]
-
-      dict = {}
-      DictionaryNER.add_name(dict, name, 'code')
-      assert_equal(result, dict)
-    }
-
-  end
-
-  def test_load
-    assert_equal(@dict, DictionaryNER.load(@dictionary))
-  end
-
-  def test_class
-    ner = DictionaryNER.new(@dictionary)
-
-    [
-      [ "Word1 Word2", ["Word1 Word2", "Word1"] ],
-      [ "foo Word1 Word2 foo", ["Word1 Word2", "Word1"] ],
-      [ "Word1-Word2", ["Word1 Word2", "Word1"] ],
-      [ "Word1\nWord2", ["Word1 Word2", "Word1"] ],
-    ].each{|info|
-      text = info[0]
-      keys = info[1]
-
-      assert_equal(keys.sort, ner.match(text).keys.sort)
-    }
-  end
-
-  def test_load_from_file
-    tmpfile = TmpFile.tmp_file
-
-    Open.write(tmpfile, @dictionary)
-
-    ner = DictionaryNER.new(tmpfile)
-
-    assert(ner.match("Word1").any?)
-  end
-
-end
-

data/test/rbbt/ner/test_regexpNER.rb

@@ -1,33 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt'
-require 'rbbt/util/tmpfile'
-require 'rbbt/ner/regexpNER'
-require 'test/unit'
-
-class TestRegExpNER < Test::Unit::TestCase
-
-  def test_class
-    text = "a bc d e f g h i j k  l m n o p q one two"
-
-    lexicon =<<-EOF
-C1,a,x,xx,xxx
-C2,bc,y,yy,yyy
-C3,i,z,zz,zzz,m,one two
-    EOF
-
-    file = TmpFile.tmp_file
-    File.open(file, 'w'){|f| f.write lexicon}
-
-    r = RegExpNER.new(file, :sep => ',', :stopwords => false)
-    assert_equal(['a', 'bc', 'i', 'm','one two'].sort,r.match_hash(text).values.flatten.sort)
-
-    r = RegExpNER.new(file, :sep => ',', :stopwords => true)
-    assert_equal(['bc', 'm','one two'].sort,r.match_hash(text).values.flatten.sort)
-
-
-    FileUtils.rm file
-  end
-
-end
-
-

data/test/rbbt/ner/test_rner.rb

@@ -1,126 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt'
-require 'rbbt/ner/rner'
-require 'test/unit'
-
-class TestRNer < Test::Unit::TestCase
-
-  def setup
-    @parser = NERFeatures.new do
-      isLetters     /^[A-Z]+$/i 
-      context prefix_3      /^(...)/ 
-      downcase do |w| w.downcase end
-
-      context %w(downcase)
-    end
-  end
-
-  def test_config
-    config = <<-EOC
-  isLetters(/^[A-Z]+$/i)
-  context(prefix_3(/^(...)/))
-  downcase { |w| w.downcase }
-  context(["downcase"])
-    EOC
-
-    assert(@parser.config == config)
-  end
-
-  def test_reverse
-    assert_equal("protein P53", NERFeatures.reverse("P53 protein"))
-    assert_equal(
-       ". LH of assay - radioimmuno serum the with compared was LH urinary for ) GONAVIS - HI ( test hemagglutination direct new A", 
-     NERFeatures.reverse(
-       "A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum\n radioimmuno-assay of LH."
-      ))
-  end
-
-  def test_features
-    assert(@parser.features("abCdE"),["abCdE",true,'abc','abcde'])
-  end
-
-  def test_template
-    template =<<-EOT
-UisLetters: %x[0,1]
-Uprefix_3: %x[0,2]
-Uprefix_3#1: %x[1,2]
-Uprefix_3#-1: %x[-1,2]
-Udowncase: %x[0,3]
-Udowncase#1: %x[1,3]
-Udowncase#-1: %x[-1,3]
-B
-    EOT
-    
-    assert(@parser.template == template)
-  end
-
-  def test_tokens
-    assert( NERFeatures.tokens("A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum\n radioimmuno-assay of LH.")==
-           ["A", "new", "direct", "hemagglutination", "test", "(", "HI", "-", "GONAVIS", ")", "for", "urinary", "LH", "was", "compared", "with", "the", "serum", "radioimmuno", "-", "assay", "of", "LH", "."])
-
-
-  end
-  def test_text_features
- 
-    assert(@parser.text_features("abCdE 1234") == [["abCdE",true, "abC", "abcde"], ["1234",false, "123", "1234"]])
-    assert(@parser.text_features("abCdE 1234",true) == [["abCdE",true, "abC", "abcde",1], ["1234",false, "123", "1234",2]])
-    assert(@parser.text_features("abCdE 1234",false) == [["abCdE",true, "abC", "abcde",0], ["1234",false, "123", "1234",0]])
-   
-  end
-
-  def test_tagged_features
-    assert_equal(
-      [["phosphorilation",true, "pho", "phosphorilation", 0], 
-        ["of",true, false, "of", 0], 
-        ["GENE1",false, "GEN", "gene1", 1],
-        [".", false, false, ".", 0]],
-      @parser.tagged_features("phosphorilation of GENE1.",['GENE1']))
-
-      assert_equal(
-        [["GENE1",false, "GEN", "gene1", 1],
-          ["phosphorilation",true, "pho", "phosphorilation", 0]], 
-      @parser.tagged_features("GENE1 phosphorilation",['GENE1']))
-
- 
-    assert_equal(
-           [["phosphorilation",true, "pho", "phosphorilation", 0], 
-            ["of",true, false, "of", 0], 
-            ["GENE",true, "GEN", "gene", 1],
-            ["1",false, false, "1", 2],
-            [".", false, false, ".", 0]],
-      @parser.tagged_features("phosphorilation of GENE 1.",['GENE 1']))
-  end
-
-  def test_tagged_features_reverse
-    @parser.reverse = true
-    assert_equal(
-      [
-        ["GENE1",false, "GEN", "gene1", 1],
-        ["of",true, false, "of", 0], 
-        ["phosphorilation",true, "pho", "phosphorilation", 0]
-    ],
-    @parser.tagged_features("phosphorilation of GENE1",['GENE1']))
-
-    assert_equal(
-          [
-            [".", false, false, ".", 0],
-            ["1",false, false, "1", 1],
-            ["GENE",true, "GEN", "gene", 2],
-            ["of",true, false, "of", 0], 
-            ["phosphorilation",true, "pho", "phosphorilation", 0]
-        ],
-    @parser.tagged_features("phosphorilation of GENE 1.",['GENE 1']))
-  end
-
-
-  def test_NER_default
-    parser = NERFeatures.new
-
-    assert(parser.template =~ /UisLetter/)
-  end
-
-  def test_CRFPP_install
-    assert(require File.join(Rbbt.datadir, 'third_party/crf++/ruby/CRFPP'))
-  end
-
-end

data/test/rbbt/ner/test_rnorm.rb

@@ -1,47 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/ner/rnorm'
-require 'rbbt/util/open'
-require 'rbbt/util/tmpfile'
-require 'test/unit' 
- 
-class TestRNORM < Test::Unit::TestCase
- 
-  def setup 
-    tmp = TmpFile.tmp_file("test-rnorm-")
-    lexicon =<<-EOT
-S000000029	YAL031C	GIP4	FUN21
-S000000030	YAL032C	PRP45	FUN20
-S000000031	YAL033W	POP5	FUN53 
-S000000374	YBR170C	NPL4	HRD4
-S000000375	GENE1	BBB	CCC
-S000000376	AAA	GENE1	DDD
-	EOT
-
-    Open.write(tmp, lexicon)
-
-    @norm = Normalizer.new(tmp) 
-    FileUtils.rm tmp
-  end
-
-  def test_match
-     assert_equal(["S000000029"], @norm.match("FUN21"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 2"))
-     assert_equal(["S000000030", "S000000029", "S000000031"], @norm.match("FUN 21")) 
-     assert_equal([], @norm.match("GER4"))
-
-     @norm.match("FUN21")
-  end 
-
-  def test_select
-    assert_equal(["S000000029"], @norm.select(["S000000030", "S000000029", "S000000031"],"FUN 21"))
-  end
-
-  def test_resolve
-    assert_equal(["S000000029"], @norm.resolve("FUN 21"))
-  end
-
-  def test_order
-    assert_equal(["S000000375"], @norm.resolve("GENE1"))
-  end
-end

data/test/rbbt/sources/test_biocreative.rb

@@ -1,38 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/sources/biocreative'
-require 'test/unit'
-
-class TestBiocreative < Test::Unit::TestCase
-
-  def test_BC2GM
-    assert(Biocreative.BC2GM(:test)['BC2GM000008491'][:text] == "Phenotypic analysis demonstrates that trio and Abl cooperate in regulating axon outgrowth in the embryonic central nervous system (CNS).")
-    assert(Biocreative.BC2GM(:test)['BC2GM000008491'][:mentions] == ["trio", "Abl"] )
-  end
-
-  def test_position
-    mention   = "IgA"
-    text      = "Early complement components, C1q and C4, and IgA secretory piece were absent."
-    pos       = [[38, 40]]
-    assert(Biocreative.position(text,mention) == pos)
-
-    mention   = "tyrosine-specific phosphatase"
-    text      = "When expressed in Escherichia coli, SH-PTP2 displays tyrosine-specific phosphatase activity."
-    pos       = [[46, 73]]
-    assert(Biocreative.position(text,mention) == pos)
-
-    mention   = "tyrosine - specific phosphatase"
-    text      = "When expressed in Escherichia coli, SH-PTP2 displays tyrosine-specific phosphatase activity."
-    pos       = [[46, 73]]
-    assert(Biocreative.position(text,mention) == pos)
-
-    mention   = "LH"
-    text      = "A new direct hemagglutination test (HI-GONAVIS) for urinary LH was compared with the serum radioimmuno-assay of LH."
-    pos       = [[52, 53],[96, 97]]
-    assert(Biocreative.position(text,mention) == pos)
-
-  end
-
-
-end
-
-

data/test/rbbt/sources/test_biomart.rb

@@ -1,31 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/sources/biomart'
-require 'test/unit'
-
-class TestBioMart < Test::Unit::TestCase
-
-  def test_get
-    assert_raise BioMart::QueryError do 
-      BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],['with_unknownattr'])
-    end
-
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['protein_id'],[])
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-
-    data = BioMart.get('scerevisiae_gene_ensembl','entrezgene', ['external_gene_id'],[], data )
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
-
-  end
-
-  def test_query
-    data = BioMart.query('scerevisiae_gene_ensembl','entrezgene', ['protein_id','refseq_peptide','external_gene_id','ensembl_gene_id'],[])
-
-    assert(data['856452']['protein_id'].include? 'AAB68382')
-    assert(data['856452']['external_gene_id'].include? 'CUP1-2')
-
- end
-
-end
-
-

data/test/rbbt/sources/test_entrez.rb

@@ -1,49 +0,0 @@
-require File.dirname(__FILE__) + '/../../test_helper'
-require 'rbbt/sources/entrez'
-require 'test/unit'
-
-class TestEntrez < Test::Unit::TestCase
-
-  def test_entrez2native
-    tax   = 4932
-    fix   = proc{|code| code.sub(/SGD:S0/,'S0') }
-    check = proc{|code| code.match(/^S0/)}
-
-    lexicon = Entrez.entrez2native(tax, 5, fix, check)
-    assert(lexicon['855611'].include? 'S000005056') 
-  end
-
-  def test_entrez2pubmed
-    tax = 4932
-
-    data = Entrez.entrez2pubmed(tax)
-    assert(data['850320'].include? '15102838') 
-  end
-
-  def test_getonline
-    geneids = 9129
-
-    assert_match(/PRP3 pre-mRNA processing factor/s, Entrez.get_online(geneids))
-
-    geneids = [9129,9]
-    assert_match(/PRP3 pre-mRNA processing factor/s, Entrez.get_online(geneids)[9129])
-  end
-
-  def test_getgene
-    geneids = 9129
-    assert_equal([["PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"]], Entrez.get_gene(geneids).description)
-
-    geneids = [9129,728049]
-    assert_equal([["PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"]], Entrez.get_gene(geneids)[9129].description)
-
-  end
-
-  def test_similarity
-    assert(Entrez.gene_text_similarity(9129, "PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)") > 0)
-    assert_equal(0, Entrez.gene_text_similarity("NON EXISTEN GENEID", "PRP3 pre-mRNA processing factor 3 homolog (S. cerevisiae)"))
-
-  end
-
-end
-
-