rbbt-text 1.3.6 → 1.3.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 110d05d205305e48b17ca63a91f8fef66ba6cb0d24639031614521c463dfde8f
-  data.tar.gz: 97df4097eb1a0cb645f4f6a0eeec9138f296760e09fcdc85a5ebebe6996640d0
+  metadata.gz: e1b07b2646ecdc51599e2a2356fd18708e88d819944910a07930f67ec3fc012d
+  data.tar.gz: 03bcbe61f41d830668b50fcfc253fa2b43285774040f61fb3fb0a58f80e9dfd3
 SHA512:
-  metadata.gz: bc3c92ae7b5268f02b232f04d28a2b6491740a618c9a9f3d78a099d51ed03dee489ebb805485c82552fc38d8164a4eb75a8e19a6d1df53aaac536e99287009fb
-  data.tar.gz: 1bb1594b9cd5831455e1a7e2454932b57fdd7da4401bc2596146dc1669fa6783931df3042c9deed6a3cf032c59d8697500a470a8aeba859061868cd8ab8b4ab8
+  metadata.gz: ae6de2dd809642ca38276ff82e243efeb193cf432bc78aea92e772ab21ff489f23224b9e93de726dcacdb06910716f1107171433cc39e7b022ba14ee4ed284f6
+  data.tar.gz: 82768060a28248d459031030b6ba49b500b63a9d3ae2199ccdf1417fd3b1f66ce0d962db17875615ee36bb3b5879d8ccbbdec892942f544fa08481b4551a1003

data/LICENSE

@@ -0,0 +1,20 @@
+Copyright (c) 2010-2022 Miguel Vázquez García
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/lib/rbbt/document/corpus/pubmed.rb

@@ -4,10 +4,11 @@ module Document::Corpus
   PUBMED_NAMESPACE="PMID"
   def add_pmid(pmid, type = nil, update = false)
     type = :abstract if type.nil?
-    if update == false
+
+    if ! (update || Array === pmid)
       id = [PUBMED_NAMESPACE, pmid, type].collect{|e| e.to_s}*":"
       documents = self.documents(id)
-      return documents if documents.any?
+      return documents.first if documents.any?
     end
 
     pmids = Array === pmid ? pmid : [pmid]
@@ -27,7 +28,14 @@ module Document::Corpus
       document
     end
 
-    Document.setup(res)
+    if Array === pmid
+      corpus = res.first.corpus if res.first
+      Document.setup(res, :corpus => corpus)
+    else
+      res = res.first
+    end
+
+    res
   end
   
   def add_pubmed_query(query, max = 3000, type = nil)
@@ -35,8 +43,8 @@ module Document::Corpus
     add_pmid(pmids, type)
   end
 
-  self.claim "PMID" do |id, type|
+  self.claim "PMID" do |id,type,update|
     Log.debug "Claiming #{id}"
-    self.add_pmid(id, type).first
+    self.add_pmid(id, type,update)
   end
 end

data/lib/rbbt/document/corpus.rb

@@ -20,9 +20,9 @@ module Document::Corpus
   
   def docids(*prefix)
     prefix = prefix * ":" 
-    prefix += ":" unless prefix == :all || prefix[-1] == ":"
+    prefix += ":" unless prefix == :all || prefix == "all" || prefix[-1] == ":"
     docids = self.read_and_close do
-      prefix == :all ? self.keys : self.prefix(prefix)
+      prefix == "all" ? self.keys : self.prefix(prefix)
     end
     DocID.setup(docids, :corpus => self)
   end
@@ -34,7 +34,7 @@ module Document::Corpus
   def [](*args)
     docid, *rest = args
 
-    res = self.read_and_close do
+    res = self.with_read do
       super(*args)
     end
     
@@ -44,7 +44,7 @@ module Document::Corpus
     namespace, id, type  = docid.split(":")
 
     if res.nil?
-      if Document::Corpus.claims.include?(namespace.to_s)
+      if Document::Corpus.claims && Document::Corpus.claims.include?(namespace.to_s)
         res = self.instance_exec(id, type, &Document::Corpus.claims[namespace.to_s])
       end
     end

data/lib/rbbt/document.rb

@@ -22,9 +22,7 @@ module DocID
     if Array === self
       namespace, id, type = nil, nil, nil
       docs = self.collect do |docid|
-        text = self.corpus[docid]
-        namespace, id, type = docid.split(":")
-        text
+        self.corpus[docid]
       end
       Document.setup(docs, :corpus => corpus)
     else

data/lib/rbbt/ner/oscar3.rb

@@ -1,6 +1,5 @@
 require 'rbbt'
 require 'rjb'
-require 'libxml'
 require 'rbbt/ner/NER'
 require 'rbbt/util/log'
 

data/lib/rbbt/ner/oscar4.rb

@@ -1,6 +1,5 @@
 require 'rbbt'
 require 'rjb'
-require 'libxml'
 require 'rbbt/segment'
 require 'rbbt/ner/NER'
 require 'rbbt/util/log'

data/lib/rbbt/ner/rnorm/tokens.rb

@@ -172,6 +172,7 @@ class Tokenizer
 
   #{{{ Token Types
   GREEK_RE = "(?:" + $greek.keys.select{|w| w.length > 3}.collect{|w| w.downcase}.join("|") + ")"
+  GREEK_LETTER_RE = "(?:" + $inverse_greek.keys.select{|w| w.length == 1}.collect{|w| w.upcase}.join("|") + ")"
   def tokenize(word)
     return word.
       gsub(/([^IVX])I$/,'\1|I|').     # Separate last roman number
@@ -180,6 +181,7 @@ class Tokenizer
       gsub(/([A-Z]{2,})([a-z])/,'\1-\2').
       gsub(/^(#{GREEK_RE})/,'\1-').
       gsub(/(#{GREEK_RE})$/,'-\1').
+      gsub(/(#{GREEK_LETTER_RE})$/,'-\1').
       split( /[^\w.]+/).  # Split by separator char
       select{|t|  !t.empty? }
   end
@@ -204,7 +206,7 @@ class Tokenizer
   end
 
   #{{{ Comparisons
-
+  
   def evaluate_tokens(list1, list2)
     @operations.inject(0){|acc, o|
       acc + o.eval(list1, list2)

data/lib/rbbt/ner/rnorm.rb

@@ -18,6 +18,10 @@ class Normalizer
     values.select{|p| p[1] == best}
   end
 
+  def token_evaluate(mention, name)
+    @tokens.evaluate(mention, name)
+  end
+
   # Compares the tokens and gives each candidate a score based on the
   # commonalities and differences amongst the tokens.
   def token_score(code, mention)
@@ -31,7 +35,7 @@ class Normalizer
               when mention.downcase.gsub(/\s/,'') == name.downcase.gsub(/\s/,'')
                 80
               else
-                @tokens.evaluate(mention, name)
+                token_evaluate(mention, name)
               end
       [value, name]
     }.sort_by{|value, name| value }.last

data/lib/rbbt/nlp/spaCy.rb

@@ -153,8 +153,8 @@ module SpaCy
 
     chunk_index = Segment.index(SpaCy.chunk_segments(text, lang))
 
-    source_id = chunk_index[source.offset].first || source.segid
-    target_id = chunk_index[target.offset].first || target.segid
+    source_id = chunk_index[source.offset.to_i].first || source.segid
+    target_id = chunk_index[target.offset.to_i].first || target.segid
 
     path = Paths.dijkstra(graph, source_id, [target_id])
 

data/lib/rbbt/segment/transformed.rb

@@ -70,7 +70,15 @@ module Transformed
     orig_length = self.length
 
     offset = self.respond_to?(:offset) ? self.offset.to_i : 0
-    segments = segments.select{|s| s.offset.to_i >= offset && s.offset.to_i <= offset + self.length - 1 }
+
+    segments = segments.select do |s| 
+      shift = shift s.range
+      s_offset = s.offset.to_i
+      s_offset += shift.first if shift
+
+      s_offset >= offset && 
+        s_offset <= offset + self.length - 1 
+    end
 
     Segment.clean_sort(segments).each do |segment|
       next if segment.offset.nil?

data/share/install/software/OpenNLP

@@ -1,6 +1,7 @@
 #!/bin/bash
 
 name='OpenNLP'
-url="http://apache.rediris.es/opennlp/opennlp-1.9.3/apache-opennlp-1.9.3-bin.tar.gz"
+url="http://apache.rediris.es/opennlp/opennlp-1.9.4/apache-opennlp-1.9.4-bin.tar.gz"
 
-install_jar $name $url
+install_src $name $url
+(cd $OPT_DIR/jars; ln -s $OPT_DIR/$name/lib/*.jar .)

data/test/rbbt/document/corpus/test_pubmed.rb

@@ -7,7 +7,7 @@ class TestCorpusPubmed < Test::Unit::TestCase
   def test_add_pmid
     corpus = Document::Corpus.setup({})
 
-    document = corpus.add_pmid("33359141", :abstract).first
+    document = corpus.add_pmid("33359141", :abstract, true)
     title = document.to(:title)
     assert title.include?("COVID-19")
   end

data/test/rbbt/ner/rnorm/test_tokens.rb

@@ -0,0 +1,11 @@
+require File.join(File.expand_path(File.dirname(__FILE__)), '../../..', 'test_helper.rb')
+require 'rbbt/ner/rnorm'
+
+class TestRNorm < Test::Unit::TestCase
+  def test_evaluate
+    t = Tokenizer.new
+    assert t.evaluate("PDGFRA","PDGFRalpha") > 0
+    iii t.evaluate("JUNB","JunB")
+  end
+end
+

data/test/rbbt/ner/test_rnorm.rb

@@ -43,4 +43,9 @@ S000000376	AAA	GENE1	DDD
   def test_order
     assert_equal(["S000000375"], @norm.resolve("GENE1"))
   end
+
+  def test_token_evaluate
+    iii @norm.token_evaluate("PDGFRA","PDGFRalpha")
+  end
+
 end

data/test/rbbt/segment/test_transformed.rb

@@ -393,43 +393,26 @@ This is another sentence. Among the nonstructural proteins, the leader protein (
     end
   end
 
-  def ___test_transform
-    a = "This sentence mentions the TP53 gene and the CDK5 protein"
+  def test_transform_sorter_end
+    a = "The transcription factors farnesoid X receptor, small heterodimer partner, liver receptor homolog-1, and liver X receptor comprise the signaling cascade network that regulates the expression and secretion of apoM."
     original = a.dup
 
-    gene1 = "TP53"
+    gene1 = "liver receptor homolog-1"
     gene1.extend Segment
     gene1.offset = a.index gene1
 
-    gene2 = "CDK5"
+    gene2 = "apoM"
     gene2.extend Segment
     gene2.offset = a.index gene2
 
     assert_equal gene1, a[gene1.range]
     assert_equal gene2, a[gene2.range]
     
-    c = a.dup
-
-    c[gene2.range] = "GN"
-    assert_equal c, Transformed.transform(a,[gene2], "GN")
-    c[gene1.range] = "GN"
-    assert_equal c, Transformed.transform(a,[gene1], "GN")
-
-    iii a.transformation_offset_differences
-    raise
-    assert_equal gene2.offset, a.transformation_offset_differences.first.first.first
-    assert_equal gene1.offset, a.transformation_offset_differences.last.first.first
-
-
-    gene3 = "GN gene"
-    gene3.extend Segment
-    gene3.offset = a.index gene3
-
-    assert_equal gene3, a[gene3.range]
-
-    a.restore([gene3])
-    assert_equal original, a
-    assert_equal "TP53 gene", a[gene3.range]
+    Transformed.with_transform(a, [gene1], "[TF]") do 
+      Transformed.with_transform(a, [gene2], "[TG]") do 
+        assert_equal "The transcription factors farnesoid X receptor, small heterodimer partner, [TF], and liver X receptor comprise the signaling cascade network that regulates the expression and secretion of [TG].", a
+      end
+    end
 
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-text
 version: !ruby/object:Gem::Version
-  version: 1.3.6
+  version: 1.3.8
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-06-25 00:00:00.000000000 Z
+date: 2022-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util
@@ -38,20 +38,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: libxml-ruby
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: json
   requirement: !ruby/object:Gem::Requirement
@@ -72,8 +58,10 @@ email: miguel.vazquez@fdi.ucm.es
 executables:
 - get_ppis.rb
 extensions: []
-extra_rdoc_files: []
+extra_rdoc_files:
+- LICENSE
 files:
+- LICENSE
 - bin/get_ppis.rb
 - lib/rbbt/bow/bow.rb
 - lib/rbbt/bow/dictionary.rb
@@ -139,6 +127,7 @@ files:
 - test/rbbt/document/test_annotation.rb
 - test/rbbt/document/test_corpus.rb
 - test/rbbt/entity/test_document.rb
+- test/rbbt/ner/rnorm/test_tokens.rb
 - test/rbbt/ner/test_NER.rb
 - test/rbbt/ner/test_abner.rb
 - test/rbbt/ner/test_banner.rb
@@ -205,6 +194,7 @@ test_files:
 - test/rbbt/ner/test_patterns.rb
 - test/rbbt/ner/test_NER.rb
 - test/rbbt/ner/test_abner.rb
+- test/rbbt/ner/rnorm/test_tokens.rb
 - test/rbbt/ner/test_rnorm.rb
 - test/rbbt/ner/test_regexpNER.rb
 - test/rbbt/ner/test_ngram_prefix_dictionary.rb