simple_bioc 0.0.23 → 0.0.24

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7d747ee4c88ad72429a1f73385d8a25d2c297260
-  data.tar.gz: 15d2973d3bfd51bdce07d67830c336755ef843d3
+  metadata.gz: 6adbc57804c5758eb35f41ed1f4094feb7a3ea2f
+  data.tar.gz: 4fed4c229116b2955d80741efb08754db6620c78
 SHA512:
-  metadata.gz: 797d456eb13b99d3b80e8290042ef628c917f67f356a46c99637af62c8d29d23a0564bc5ece632ee009549121a034117b5dfcc6864f96a08fd3f871e325fb8c4
-  data.tar.gz: 7743f9e0f76f5eb8935e0c36abd04cebfe2f3a79363b5b662344cf05e68397a0fa2426d61591796dbc407758145cf9a0838fb4ceac9392a2ad32a9ae15d1a151
+  metadata.gz: 85fc7d5ad789c553afcc86d97200b4c78424fbfeca3c96880618d3928a5034cfdab571242b0732d2ffbdec7eb13147c988aabe10e1fa7cac3ade1e94dfc3af34
+  data.tar.gz: 00733eac042e12a046ce8e4c4d5813c1f42ee33898c8ea64e38bbad7484c3129c10f1417bc9387b962a9006c566c92e99dd88bcf74b3183dcdb3acfbdfe5b26f

data/README.md

@@ -7,6 +7,7 @@ SimpleBioC is a simple parser / builder for BioC data format. BioC is a simple X
  * Parse & convert a BioC document to an object instance compatible to BioC DTD
  * Use plain ruby objects for simplicity
  * Build a BioC document from an object instance
+ * Convert BioC to PubAnnotation JSON
  
 
 ## Installation
@@ -36,40 +37,41 @@ Parse with a file name (path)
     collection = SimpleBioC::from_xml(filename)
   
 Traverse & Manipulate Data. Data structure are almost the same as the DTD. Please refer [library documents](http://rubydoc.info/gems/simple_bioc/0.0.2/frames) and [the BioC DTD](http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCDTD.html).
-
+```ruby
     puts collection.documents[2].passages[0].text
-  
+```
 Build XML text from data
-
+```ruby
     puts SimpleBioC::to_xml(collection)
-
+```
 Convert PubAnnotation JSON from data
 
+```ruby
     puts SimpleBioC::to_pubann(collection, {
       sourcedb: 'PubMed', 
       target: 'http://pubannotation.org/docs/sourcedb/PubMed/sourceid/18034444', 
       project: 'Ab3P-abbreviations'
     }))
-
+```
 ## Options
 
 ### Specify set of <document>s to parse
 
 You can parse only a set of document elements in a large xml document instead of parsing all the document elements. It may decrease the processing time. For example, the following code will return a collection with two documents ("1234", "4567").
-    
+```ruby   
     collection = SimpleBioc::from_xml(filename, {documents: ["1234", "4567"]})
-
+```
 ### No whitespace in output
 
 By default, outputs of SimpleBioC::to_xml() will be formatted with whitespace. If you do not want this whitespace, you should pass 'save_with' option with 0 to the to_xml() function.
-
+```ruby
     puts SimpleBioC::to_xml(collection, {save_with:0})
-
+```
 
 ## Sample
 
 More samples can be found in Samples directory
-
+```ruby
     require 'simple_bioc'
 
     # Sample1: parse, traverse, manipulate, and build BioC data
@@ -103,7 +105,25 @@ More samples can be found in Samples directory
     # build BioC document from data
     xml = SimpleBioC.to_xml(collection)
     puts xml
-
+```
+
+## Sample2: PubAnnotation Converter (convert_pubann.rb)
+```ruby
+# convert document to PubAnnotation JSON
+require 'simple_bioc'
+
+if ARGF.argv.size < 1
+  puts "usage: ruby convert_pubann.rb {filepath}"
+  exit
+end
+
+collection = SimpleBioC::from_xml(ARGF.argv[0])
+puts SimpleBioC::to_pubann(collection, {
+  sourcedb: 'PubMed', 
+  target: 'http://pubannotation.org/docs/sourcedb/PubMed/sourceid/18034444', 
+  project: 'Ab3P-abbreviations'
+})
+```
 
 ## Contributing
 

data/lib/simple_bioc/pub_ann_writer.rb

@@ -25,8 +25,8 @@ module PubAnnWriter
     json.denotations document.all_annotations do |a|
       a.locations.each do |l|
         json.span do 
-          json.begin l.offset
-          json.end l.offset + l.length
+          json.begin l.offset.to_i
+          json.end l.offset.to_i + l.length.to_i
         end
         json.obj a.infons.map{|k,v| v}.join(",")
         json.id a.id unless a.id.nil?

data/lib/simple_bioc/version.rb

@@ -1,3 +1,3 @@
 module SimpleBioC
-  VERSION = "0.0.23"
+  VERSION = "0.0.24"
 end

data/samples/convert_pubann.rb

@@ -1,15 +1,14 @@
-# print_annotation: print all annotations in the given file
-
+# convert document to PubAnnotation JSON
 require 'simple_bioc'
 
 if ARGF.argv.size < 1
-  puts "usage: ruby print_annotation.rb {filepath}"
+  puts "usage: ruby convert_pubann.rb {filepath}"
   exit
 end
 
 collection = SimpleBioC::from_xml(ARGF.argv[0])
-puts SimpleBioC::to_xml(collection, {
+puts SimpleBioC::to_pubann(collection, {
   sourcedb: 'PubMed', 
   target: 'http://pubannotation.org/docs/sourcedb/PubMed/sourceid/18034444', 
   project: 'Ab3P-abbreviations'
-})
+})

data/simple_bioc.gemspec

@@ -22,10 +22,9 @@ Gem::Specification.new do |spec|
   spec.add_dependency "jbuilder", "~> 2.3"
 
   spec.add_development_dependency "bundler", "~> 1.3"
-  spec.add_development_dependency "rake", "~> 10.3"
-  spec.add_development_dependency "yard", "~> 0.8"
+  spec.add_development_dependency "rake", ">= 12.3.3"
+  spec.add_development_dependency "yard", ">= 0.9.20"
   spec.add_development_dependency "rspec", "~> 3.2"
   spec.add_development_dependency("test_xml", ["~> 0.1"])
   spec.add_development_dependency "json-compare", "~> 0.1"
-  spec.add_development_dependency "yajl-ruby", "~> 1.2"
 end

data/spec/pubann_spec.rb

@@ -1,5 +1,4 @@
 require 'simple_bioc'
-require 'yajl'
 require 'json-compare'
 require 'test_xml/spec'
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_bioc
 version: !ruby/object:Gem::Version
-  version: 0.0.23
+  version: 0.0.24
 platform: ruby
 authors:
 - Dongseop Kwon
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-08-05 00:00:00.000000000 Z
+date: 2020-05-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -56,30 +56,30 @@ dependencies:
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.3'
+        version: 12.3.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.3'
+        version: 12.3.3
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.9.20
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: 0.9.20
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -122,20 +122,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.1'
-- !ruby/object:Gem::Dependency
-  name: yajl-ruby
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.2'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.2'
 description: SimpleBioC is a simple parser / builder for BioC data format. BioC is
   a simple XML format to share text documents and annotations. You can find more information
   about BioC from the official BioC web site (http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/)
@@ -295,7 +281,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.6.13
 signing_key: 
 specification_version: 4
 summary: Simple BioC parser/builder for ruby
@@ -303,4 +289,3 @@ test_files:
 - spec/file_check_spec.rb
 - spec/pubann_spec.rb
 - spec/simple_bioc_spec.rb
-has_rdoc: