RubyGems - simple_bioc - Versions diffs - 0.0.2 → 0.0.3 - Mend

simple_bioc 0.0.2 → 0.0.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (20) hide show

checksums.yaml +4 -4
data/README.md +17 -3
data/Rakefile +2 -1
data/html/BioCReader.html +40 -30
data/html/BioCWriter.html +14 -12
data/html/README_md.html +31 -5
data/html/SimpleBioC/NodeBase.html +3 -3
data/html/SimpleBioC.html +48 -9
data/html/created.rid +7 -7
data/html/index.html +26 -3
data/html/js/search_index.js +1 -1
data/html/table_of_contents.html +5 -2
data/lib/simple_bioc/bioc_reader.rb +24 -14
data/lib/simple_bioc/bioc_writer.rb +4 -2
data/lib/simple_bioc/version.rb +1 -1
data/lib/simple_bioc.rb +29 -5
data/simple_bioc.gemspec +1 -1
data/spec/file_check_spec.rb +13 -0
data/spec/simple_bioc_spec.rb +21 -10
metadata +8 -4

checksums.yaml CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7cb0f3556fb61a2f2f802cef37678522bc0195f1
-  data.tar.gz: 9ecd0c5f1ab4fccd5313076f057bf979d192533f
+  metadata.gz: ac0961af71c5744bc71ea16221f5325af35e4583
+  data.tar.gz: 9f407b566a8dc6687d53f8145fc600f3d73039eb
 SHA512:
-  metadata.gz: 02c83c1d490001ccc56098e6370b74068d6b24e4ed167bad7b474f2d01cdaa605de44593a6c6090141cafefbe442e71203b4dcf0d994f1c8465d4fe97643363f
-  data.tar.gz: 48a386b80cba3bd6fa754592b74d1b83d2e7c15f43b898fc72fda6c7d92f43d61a6576ec4375a928c6237e38495c9e31c3e65542a385c6db4ad6c172ea9302db
+  metadata.gz: ab77aa143472f5959a0ea97702ae68dba76bb6b75542086a065b625216234d8912a52d83a087f6acf3c553f0ee8adf5050ebafd94833171d9dd84d7a34124e0a
+  data.tar.gz: b02aa1b1d73ff1d0c6ed2650c0170ff88e22fd01a6e6df7d9508cf365e548bd6bf0413616a80a765b2fc35f9d3e1da2d20edf41cece737ceeb26577d39068251

data/README.md CHANGED Viewed

@@ -1,4 +1,4 @@
-# SimpleBioc
+# SimpleBioC
 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/](http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/))
@@ -24,7 +24,7 @@ Or install it yourself as:
     $ gem install simple_bioc
-## Usages
+## Simple Usages
 Include library
@@ -35,7 +35,7 @@ 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](https://github.com/dongseop/simple_bioc/blob/master/html/index.html) and [the BioC DTD](http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCDTD.html).
+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).
     puts collection.documents[2].passages[0].text
@@ -43,6 +43,20 @@ Build XML text from data
     puts SimpleBioC::to_xml(collection)
+## Options
+### Specify set of &lt;document&gt;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").
+    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.
+    puts SimpleBioC::to_xml(collection, {save_with:0})
 ## Sample

data/Rakefile CHANGED Viewed

@@ -1,6 +1,7 @@
 require "bundler/gem_tasks"
 require 'rspec/core/rake_task'
 require 'rdoc/task'
+require 'yard'
 task :default => [:spec]
 RSpec::Core::RakeTask.new do |t|
@@ -10,4 +11,4 @@ end
 Rake::RDocTask.new do |rd|
   rd.main = "README.md"
   rd.rdoc_files.include("README.md", "lib/**/*.rb")
-end
+end

data/html/BioCReader.html CHANGED Viewed

@@ -173,7 +173,7 @@
         <div class="method-heading">
           <span class="method-name">read</span><span
-            class="method-args">(path)</span>
+            class="method-args">(path, options)</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -189,7 +189,7 @@
           <div class="method-source-code" id="read-source">
             <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 7</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read</span>(<span class="ruby-identifier">path</span>)
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read</span>(<span class="ruby-identifier">path</span>, <span class="ruby-identifier">options</span>)
   <span class="ruby-identifier">collection</span> = <span class="ruby-keyword">nil</span>
   <span class="ruby-constant">File</span>.<span class="ruby-identifier">open</span>(<span class="ruby-identifier">path</span>) <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">file</span><span class="ruby-operator">|</span>
     <span class="ruby-identifier">xml_doc</span>  = <span class="ruby-constant">Nokogiri</span><span class="ruby-operator">::</span><span class="ruby-constant">XML</span>(<span class="ruby-identifier">file</span>) <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">config</span><span class="ruby-operator">|</span>
@@ -200,7 +200,7 @@
       <span class="ruby-identifier">fail</span> <span class="ruby-string">&#39;Wrong format&#39;</span>
     <span class="ruby-keyword">end</span>
     <span class="ruby-identifier">collection</span> = <span class="ruby-constant">SimpleBioC</span><span class="ruby-operator">::</span><span class="ruby-constant">Collection</span>.<span class="ruby-identifier">new</span>
-    <span class="ruby-identifier">read_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>)
+    <span class="ruby-identifier">read_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>, <span class="ruby-identifier">options</span>)
   <span class="ruby-keyword">end</span>
   <span class="ruby-identifier">collection</span>
@@ -219,7 +219,7 @@
         <div class="method-heading">
           <span class="method-name">read_annotation</span><span
-            class="method-args">(xml, annotation)</span>
+            class="method-args">(xml, annotation, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -234,12 +234,13 @@
           <div class="method-source-code" id="read_annotation-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 80</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_annotation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">annotation</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 86</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_annotation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">annotation</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">annotation</span>.<span class="ruby-identifier">id</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;id&quot;</span>]
   <span class="ruby-identifier">annotation</span>.<span class="ruby-identifier">text</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;text&quot;</span>)
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">annotation</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">annotation</span>, <span class="ruby-string">&quot;location&quot;</span>)
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_annotation-source -->
@@ -255,7 +256,7 @@
         <div class="method-heading">
           <span class="method-name">read_collection</span><span
-            class="method-args">(xml, collection)</span>
+            class="method-args">(xml, collection, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -271,12 +272,12 @@
           <div class="method-source-code" id="read_collection-source">
             <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 47</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>)
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">collection</span>.<span class="ruby-identifier">source</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;source&quot;</span>)
   <span class="ruby-identifier">collection</span>.<span class="ruby-identifier">date</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;date&quot;</span>)
   <span class="ruby-identifier">collection</span>.<span class="ruby-identifier">key</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;key&quot;</span>)
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>)
-  <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>, <span class="ruby-string">&quot;document&quot;</span>)
+  <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>, <span class="ruby-string">&quot;document&quot;</span>, <span class="ruby-identifier">options</span>)
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_collection-source -->
@@ -292,7 +293,7 @@
         <div class="method-heading">
           <span class="method-name">read_document</span><span
-            class="method-args">(xml, document)</span>
+            class="method-args">(xml, document, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -308,12 +309,16 @@
           <div class="method-source-code" id="read_document-source">
             <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 55</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_document</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>)
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_document</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">document</span>.<span class="ruby-identifier">id</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;id&quot;</span>)
+  <span class="ruby-keyword">if</span> <span class="ruby-identifier">options</span>[<span class="ruby-value">:documents</span>].<span class="ruby-identifier">kind_of?</span>(<span class="ruby-constant">Array</span>) <span class="ruby-operator">&amp;&amp;</span> <span class="ruby-operator">!</span><span class="ruby-identifier">options</span>[<span class="ruby-value">:documents</span>].<span class="ruby-identifier">include?</span>(<span class="ruby-identifier">document</span>.<span class="ruby-identifier">id</span>)
+    <span class="ruby-keyword">return</span> <span class="ruby-keyword">false</span>
+  <span class="ruby-keyword">end</span>
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>, <span class="ruby-string">&quot;passage&quot;</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>, <span class="ruby-string">&quot;relation&quot;</span>)
   <span class="ruby-identifier">document</span>.<span class="ruby-identifier">adjust_ref</span>
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_document-source -->
@@ -396,7 +401,7 @@
         <div class="method-heading">
           <span class="method-name">read_location</span><span
-            class="method-args">(xml, location)</span>
+            class="method-args">(xml, location, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -411,10 +416,11 @@
           <div class="method-source-code" id="read_location-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 93</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_location</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">location</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 101</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_location</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">location</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">location</span>.<span class="ruby-identifier">offset</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;offset&quot;</span>]
   <span class="ruby-identifier">location</span>.<span class="ruby-identifier">length</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;length&quot;</span>]
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_location-source -->
@@ -430,7 +436,7 @@
         <div class="method-heading">
           <span class="method-name">read_node</span><span
-            class="method-args">(xml, node)</span>
+            class="method-args">(xml, node, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -445,10 +451,11 @@
           <div class="method-source-code" id="read_node-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 98</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_node</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">node</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 107</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_node</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">node</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">node</span>.<span class="ruby-identifier">refid</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;refid&quot;</span>]
   <span class="ruby-identifier">node</span>.<span class="ruby-identifier">role</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;role&quot;</span>]
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_node-source -->
@@ -464,7 +471,7 @@
         <div class="method-heading">
           <span class="method-name">read_passage</span><span
-            class="method-args">(xml, passage)</span>
+            class="method-args">(xml, passage, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -479,14 +486,15 @@
           <div class="method-source-code" id="read_passage-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 63</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_passage</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 67</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_passage</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">passage</span>.<span class="ruby-identifier">text</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;text&quot;</span>)
   <span class="ruby-identifier">passage</span>.<span class="ruby-identifier">offset</span> = <span class="ruby-identifier">read_int</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;offset&quot;</span>)
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>, <span class="ruby-string">&quot;sentence&quot;</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>, <span class="ruby-string">&quot;annotation&quot;</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>, <span class="ruby-string">&quot;relation&quot;</span>)
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_passage-source -->
@@ -502,7 +510,7 @@
         <div class="method-heading">
           <span class="method-name">read_recursive</span><span
-            class="method-args">(xml, obj, name)</span>
+            class="method-args">(xml, obj, name, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -518,12 +526,12 @@
           <div class="method-source-code" id="read_recursive-source">
             <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 38</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">obj</span>, <span class="ruby-identifier">name</span>)
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">obj</span>, <span class="ruby-identifier">name</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">target_class</span> = <span class="ruby-constant">SimpleBioC</span>.<span class="ruby-identifier">const_get</span>(<span class="ruby-identifier">name</span>.<span class="ruby-identifier">capitalize</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">xpath</span>(<span class="ruby-identifier">name</span>).<span class="ruby-identifier">each</span> <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">node</span><span class="ruby-operator">|</span>
     <span class="ruby-identifier">instance</span> = <span class="ruby-identifier">target_class</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">obj</span>)
-    <span class="ruby-identifier">send</span>(<span class="ruby-value">:&quot;read_#{name}&quot;</span>, <span class="ruby-identifier">node</span>, <span class="ruby-identifier">instance</span>)
-    <span class="ruby-identifier">obj</span>.<span class="ruby-identifier">instance_variable_get</span>(<span class="ruby-value">:&quot;@#{name}s&quot;</span>)  <span class="ruby-operator">&lt;&lt;</span> <span class="ruby-identifier">instance</span>
+    <span class="ruby-identifier">ret</span> = <span class="ruby-identifier">send</span>(<span class="ruby-value">:&quot;read_#{name}&quot;</span>, <span class="ruby-identifier">node</span>, <span class="ruby-identifier">instance</span>, <span class="ruby-identifier">options</span>)
+    <span class="ruby-identifier">obj</span>.<span class="ruby-identifier">instance_variable_get</span>(<span class="ruby-value">:&quot;@#{name}s&quot;</span>)  <span class="ruby-operator">&lt;&lt;</span> <span class="ruby-identifier">instance</span> <span class="ruby-keyword">if</span> <span class="ruby-identifier">ret</span>
   <span class="ruby-keyword">end</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_recursive-source -->
@@ -540,7 +548,7 @@
         <div class="method-heading">
           <span class="method-name">read_relation</span><span
-            class="method-args">(xml, relation)</span>
+            class="method-args">(xml, relation, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -555,11 +563,12 @@
           <div class="method-source-code" id="read_relation-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 87</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_relation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">relation</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 94</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_relation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">relation</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">relation</span>.<span class="ruby-identifier">id</span> = <span class="ruby-identifier">xml</span>[<span class="ruby-string">&quot;id&quot;</span>]
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">relation</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">relation</span>, <span class="ruby-string">&quot;node&quot;</span>)
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_relation-source -->
@@ -575,7 +584,7 @@
         <div class="method-heading">
           <span class="method-name">read_sentence</span><span
-            class="method-args">(xml, sentence)</span>
+            class="method-args">(xml, sentence, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -590,13 +599,14 @@
           <div class="method-source-code" id="read_sentence-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 72</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_sentence</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_reader.rb, line 77</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">read_sentence</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>, <span class="ruby-identifier">options</span> = {})
   <span class="ruby-identifier">sentence</span>.<span class="ruby-identifier">text</span> = <span class="ruby-identifier">read_text</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;text&quot;</span>)
   <span class="ruby-identifier">sentence</span>.<span class="ruby-identifier">offset</span> = <span class="ruby-identifier">read_int</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-string">&quot;offset&quot;</span>)
   <span class="ruby-identifier">read_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>, <span class="ruby-string">&quot;annotation&quot;</span>)
   <span class="ruby-identifier">read_recursive</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>, <span class="ruby-string">&quot;relation&quot;</span>)
+  <span class="ruby-keyword">true</span>
 <span class="ruby-keyword">end</span></pre>
           </div><!-- read_sentence-source -->

data/html/BioCWriter.html CHANGED Viewed

@@ -167,7 +167,7 @@
         <div class="method-heading">
           <span class="method-name">write</span><span
-            class="method-args">(collection)</span>
+            class="method-args">(collection, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -183,11 +183,13 @@
           <div class="method-source-code" id="write-source">
             <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 6</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">write</span>(<span class="ruby-identifier">collection</span>)
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">write</span>(<span class="ruby-identifier">collection</span>, <span class="ruby-identifier">options</span> = {})
+  <span class="ruby-identifier">options</span>[<span class="ruby-value">:save_with</span>] = <span class="ruby-value">1</span> <span class="ruby-keyword">if</span> <span class="ruby-identifier">options</span>[<span class="ruby-value">:save_with</span>].<span class="ruby-identifier">nil?</span>
   <span class="ruby-identifier">builder</span> = <span class="ruby-constant">Nokogiri</span><span class="ruby-operator">::</span><span class="ruby-constant">XML</span><span class="ruby-operator">::</span><span class="ruby-constant">Builder</span>.<span class="ruby-identifier">new</span>(<span class="ruby-value">:encoding</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-string">&#39;UTF-8&#39;</span>) <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">xml</span><span class="ruby-operator">|</span>
+    <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">doc</span>.<span class="ruby-identifier">create_internal_subset</span>( <span class="ruby-string">&#39;collection&#39;</span>, <span class="ruby-keyword">nil</span>, <span class="ruby-string">&#39;BioC.dtd&#39;</span> )
     <span class="ruby-identifier">write_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>)
   <span class="ruby-keyword">end</span>
-  <span class="ruby-identifier">builder</span>.<span class="ruby-identifier">to_xml</span>
+  <span class="ruby-identifier">builder</span>.<span class="ruby-identifier">to_xml</span>(<span class="ruby-identifier">options</span>)
 <span class="ruby-keyword">end</span></pre>
           </div><!-- write-source -->
@@ -218,7 +220,7 @@
           <div class="method-source-code" id="write_annotation-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 61</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 63</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_annotation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">annotation</span>)
   <span class="ruby-keyword">if</span> <span class="ruby-identifier">annotation</span>.<span class="ruby-identifier">id</span>.<span class="ruby-identifier">nil?</span>
     <span class="ruby-identifier">attribute</span> = <span class="ruby-keyword">nil</span>
@@ -260,7 +262,7 @@
           <div class="method-source-code" id="write_collection-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 21</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 23</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_collection</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">collection</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">collection</span> {
     <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">source</span> <span class="ruby-identifier">collection</span>.<span class="ruby-identifier">source</span>
@@ -299,7 +301,7 @@
           <div class="method-source-code" id="write_document-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 31</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 33</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_document</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">document</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">document</span> {
     <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">id_</span> <span class="ruby-identifier">document</span>.<span class="ruby-identifier">id</span>
@@ -337,7 +339,7 @@
           <div class="method-source-code" id="write_infon-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 13</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 15</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">obj</span>)
   <span class="ruby-identifier">obj</span>.<span class="ruby-identifier">infons</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">k</span>, <span class="ruby-identifier">v</span><span class="ruby-operator">|</span>
     <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">infon</span>(<span class="ruby-value">:key</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-identifier">k</span>) {
@@ -374,7 +376,7 @@
           <div class="method-source-code" id="write_location-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 86</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 88</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_location</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">location</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">location</span>(<span class="ruby-value">:offset</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-identifier">location</span>.<span class="ruby-identifier">offset</span>, <span class="ruby-value">:length</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-identifier">location</span>.<span class="ruby-identifier">length</span>)
 <span class="ruby-keyword">end</span></pre>
@@ -407,7 +409,7 @@
           <div class="method-source-code" id="write_node-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 90</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 92</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_node</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">node</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">node_</span>(<span class="ruby-value">:refid</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-identifier">node</span>.<span class="ruby-identifier">refid</span>, <span class="ruby-value">:role</span> =<span class="ruby-operator">&gt;</span> <span class="ruby-identifier">node</span>.<span class="ruby-identifier">role</span>)
 <span class="ruby-keyword">end</span></pre>
@@ -440,7 +442,7 @@
           <div class="method-source-code" id="write_passage-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 40</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 42</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_passage</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">passage</span> {
     <span class="ruby-identifier">write_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">passage</span>)
@@ -480,7 +482,7 @@
           <div class="method-source-code" id="write_relation-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 74</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 76</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_relation</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">relation</span>)
   <span class="ruby-keyword">if</span> <span class="ruby-identifier">relation</span>.<span class="ruby-identifier">id</span>.<span class="ruby-identifier">nil?</span>
     <span class="ruby-identifier">attribute</span> = <span class="ruby-keyword">nil</span>
@@ -521,7 +523,7 @@
           <div class="method-source-code" id="write_sentence-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 51</span>
+            <pre><span class="ruby-comment"># File lib/simple_bioc/bioc_writer.rb, line 53</span>
 <span class="ruby-keyword">def</span> <span class="ruby-identifier">write_sentence</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>)
   <span class="ruby-identifier">xml</span>.<span class="ruby-identifier">sentence</span> {
     <span class="ruby-identifier">write_infon</span>(<span class="ruby-identifier">xml</span>, <span class="ruby-identifier">sentence</span>)

data/html/README_md.html CHANGED Viewed

@@ -48,10 +48,13 @@
   <nav class="section">
     <h3 class="section-header">Table of Contents</h3>
     <ul>
-      <li><a href="#label-SimpleBioc">SimpleBioc</a>
+      <li><a href="#label-SimpleBioC">SimpleBioC</a>
       <li><a href="#label-Feature%3A">Feature:</a>
       <li><a href="#label-Installation">Installation</a>
-      <li><a href="#label-Usages">Usages</a>
+      <li><a href="#label-Simple+Usages">Simple Usages</a>
+      <li><a href="#label-Options">Options</a>
+      <li><a href="#label-Specify+set+of+%3Cdocument%3Es+to+parse">Specify set of &lt;document&gt;s to parse</a>
+      <li><a href="#label-No+whitespace+in+output">No whitespace in output</a>
       <li><a href="#label-Sample">Sample</a>
       <li><a href="#label-Contributing">Contributing</a>
       <li><a href="#label-LICENSE">LICENSE</a>
@@ -108,7 +111,7 @@
 <div id="documentation" class="description">
-<h1 id="label-SimpleBioc">SimpleBioc<span><a href="#label-SimpleBioc">&para;</a> <a href="#documentation">&uarr;</a></span></h1>
+<h1 id="label-SimpleBioC"><a href="SimpleBioC.html">SimpleBioC</a><span><a href="#label-SimpleBioC">&para;</a> <a href="#documentation">&uarr;</a></span></h1>
 <p><a href="SimpleBioC.html">SimpleBioC</a> is a simple parser / builder for
 BioC data format. BioC is a simple XML format to share text documents and
@@ -140,7 +143,7 @@ BioC DTD</p>
 <pre>$ gem install simple_bioc</pre>
-<h2 id="label-Usages">Usages<span><a href="#label-Usages">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
+<h2 id="label-Simple+Usages">Simple Usages<span><a href="#label-Simple+Usages">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
 <p>Include library</p>
@@ -152,7 +155,11 @@ BioC DTD</p>
 <pre>collection = SimpleBioC::from_xml(filename)</pre>
 <p>Traverse &amp; Manipulate Data. Data structure are almost the same as the
-DTD. Please refer <a href="http://">library documents</a>.</p>
+DTD. Please refer <a
+href="http://rubydoc.info/gems/simple_bioc/0.0.2/frames">library
+documents</a> and <a
+href="http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCDTD.html">the
+BioC DTD</a>.</p>
 <pre>puts collection.documents[2].passages[0].text</pre>
@@ -160,6 +167,25 @@ DTD. Please refer <a href="http://">library documents</a>.</p>
 <pre>puts SimpleBioC::to_xml(collection)</pre>
+<h2 id="label-Options">Options<span><a href="#label-Options">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
+<h3 id="label-Specify+set+of+%3Cdocument%3Es+to+parse">Specify set of &lt;document&gt;s to parse<span><a href="#label-Specify+set+of+%3Cdocument%3Es+to+parse">&para;</a> <a href="#documentation">&uarr;</a></span></h3>
+<p>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”).</p>
+<pre>collection = SimpleBioc::from_xml(filename, {documents: [&quot;1234&quot;, &quot;4567&quot;]})</pre>
+<h3 id="label-No+whitespace+in+output">No whitespace in output<span><a href="#label-No+whitespace+in+output">&para;</a> <a href="#documentation">&uarr;</a></span></h3>
+<p>By default, outputs of SimpleBioC::to_xml() will be formatted with
+whitespace. If you do not want this whitespace, you should pass
+&#39;save_with&#39; option with 0 to the to_xml() function.</p>
+<pre>puts SimpleBioC::to_xml(collection, {save_with:0})</pre>
 <h2 id="label-Sample">Sample<span><a href="#label-Sample">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
 <p>More samples can be found in Samples directory</p>

data/html/SimpleBioC/NodeBase.html CHANGED Viewed

@@ -131,9 +131,9 @@
   <div id="description" class="description">
-<p><a href="NodeBase.html">NodeBase</a> is not in BioC DTD. This is a super
-class of <a href="Annotation.html">Annotation</a> &amp; <a
-href="Relation.html">Relation</a></p>
+<p><a href="NodeBase.html">NodeBase</a> is not a BioC DTD entity. This is a
+super class of <a href="Annotation.html">Annotation</a> &amp; <a
+href="Relation.html">Relation</a>.</p>
   </div><!-- description -->

data/html/SimpleBioC.html CHANGED Viewed

@@ -177,7 +177,7 @@
         <div class="method-heading">
           <span class="method-name">from_xml</span><span
-            class="method-args">(file_path)</span>
+            class="method-args">(file_path, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -188,14 +188,33 @@
           <p>parse a BioC XML file in the given path and convert it into a collection
 instance</p>
+<h4 id="method-i-from_xml-label-Arguments">Arguments<span><a href="#method-i-from_xml-label-Arguments">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<ul><li>
+<p><code>file_path</code> - file path for parse</p>
+</li><li>
+<p><code>options</code> - (optional) additional options</p>
+</li></ul>
+<h4 id="method-i-from_xml-label-Options">Options<span><a href="#method-i-from_xml-label-Options">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<ul><li>
+<p><code>documents</code> - specify IDs of documents to parse. The result will
+include only the specified documents</p>
+</li></ul>
+<h4 id="method-i-from_xml-label-Examples">Examples<span><a href="#method-i-from_xml-label-Examples">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<pre>collection = SimpleBioC.from_xml(&quot;./xml/everything.xml&quot;)
+collection = SimpleBioC.from_xml(&quot;./xml/lemma.xml&quot;, {documents:[21785578, 21488974]})</pre>
           <div class="method-source-code" id="from_xml-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc.rb, line 10</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">from_xml</span>(<span class="ruby-identifier">file_path</span>)
-  <span class="ruby-constant">BioCReader</span>.<span class="ruby-identifier">read</span>(<span class="ruby-identifier">file_path</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc.rb, line 22</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">from_xml</span>(<span class="ruby-identifier">file_path</span>, <span class="ruby-identifier">options</span> = {})
+  <span class="ruby-identifier">options</span>[<span class="ruby-value">:documents</span>] = <span class="ruby-identifier">options</span>[<span class="ruby-value">:documents</span>].<span class="ruby-identifier">map</span>{<span class="ruby-operator">|</span><span class="ruby-identifier">e</span><span class="ruby-operator">|</span> <span class="ruby-identifier">e</span>.<span class="ruby-identifier">to_s</span>} <span class="ruby-keyword">if</span> <span class="ruby-identifier">options</span>[<span class="ruby-value">:documents</span>].<span class="ruby-identifier">kind_of?</span>(<span class="ruby-constant">Array</span>)
+  <span class="ruby-constant">BioCReader</span>.<span class="ruby-identifier">read</span>(<span class="ruby-identifier">file_path</span>, <span class="ruby-identifier">options</span>)
 <span class="ruby-keyword">end</span></pre>
           </div><!-- from_xml-source -->
@@ -211,7 +230,7 @@ instance</p>
         <div class="method-heading">
           <span class="method-name">to_xml</span><span
-            class="method-args">(collection)</span>
+            class="method-args">(collection, options = {})</span>
           <span class="method-click-advice">click to toggle source</span>
@@ -220,15 +239,35 @@ instance</p>
         <div class="method-description">
-          <p>convert a collection instance to a BioC XML text</p>
+          <p>convert a collection instance to a BioC XML text. Output will return as
+string</p>
+<h4 id="method-i-to_xml-label-Arguments">Arguments<span><a href="#method-i-to_xml-label-Arguments">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<ul><li>
+<p><code>collection</code> - <a
+href="SimpleBioC/Collection.html">Collection</a> instance to process</p>
+</li><li>
+<p><code>options</code> - (optional) additional options</p>
+</li></ul>
+<h4 id="method-i-to_xml-label-Options">Options<span><a href="#method-i-to_xml-label-Options">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<ul><li>
+<p><code>save_with</code> - SaveOption for Nokorigi. If you set this 0, output
+has no format (no indentation, no whitespace)</p>
+</li></ul>
+<h4 id="method-i-to_xml-label-Examples">Examples<span><a href="#method-i-to_xml-label-Examples">&para;</a> <a href="#documentation">&uarr;</a></span></h4>
+<pre>output = SimpleBioC.to_xml(collection)
+output = SimpleBioC.to_xml(collection, {save_with: 0})</pre>
           <div class="method-source-code" id="to_xml-source">
-            <pre><span class="ruby-comment"># File lib/simple_bioc.rb, line 15</span>
-<span class="ruby-keyword">def</span> <span class="ruby-identifier">to_xml</span>(<span class="ruby-identifier">collection</span>)
-  <span class="ruby-constant">BioCWriter</span>.<span class="ruby-identifier">write</span>(<span class="ruby-identifier">collection</span>)
+            <pre><span class="ruby-comment"># File lib/simple_bioc.rb, line 39</span>
+<span class="ruby-keyword">def</span> <span class="ruby-identifier">to_xml</span>(<span class="ruby-identifier">collection</span>, <span class="ruby-identifier">options</span> = {})
+  <span class="ruby-constant">BioCWriter</span>.<span class="ruby-identifier">write</span>(<span class="ruby-identifier">collection</span>, <span class="ruby-identifier">options</span>)
 <span class="ruby-keyword">end</span></pre>
           </div><!-- to_xml-source -->

data/html/created.rid CHANGED Viewed

@@ -1,15 +1,15 @@
-Fri, 06 Dec 2013 22:05:40 -0800
-README.md	Fri, 06 Dec 2013 21:17:11 -0800
-lib/simple_bioc.rb	Fri, 06 Dec 2013 20:53:53 -0800
+Sat, 21 Dec 2013 09:10:44 -0800
+README.md	Sat, 21 Dec 2013 09:10:35 -0800
+lib/simple_bioc.rb	Sat, 21 Dec 2013 08:58:11 -0800
 lib/simple_bioc/annotation.rb	Fri, 06 Dec 2013 20:52:11 -0800
-lib/simple_bioc/bioc_reader.rb	Fri, 06 Dec 2013 20:52:11 -0800
-lib/simple_bioc/bioc_writer.rb	Wed, 04 Dec 2013 02:22:25 -0800
+lib/simple_bioc/bioc_reader.rb	Sat, 21 Dec 2013 08:39:36 -0800
+lib/simple_bioc/bioc_writer.rb	Sat, 21 Dec 2013 08:09:06 -0800
 lib/simple_bioc/collection.rb	Fri, 06 Dec 2013 20:52:11 -0800
 lib/simple_bioc/document.rb	Fri, 06 Dec 2013 21:18:25 -0800
 lib/simple_bioc/location.rb	Fri, 06 Dec 2013 20:52:11 -0800
 lib/simple_bioc/node.rb	Fri, 06 Dec 2013 20:52:11 -0800
-lib/simple_bioc/node_base.rb	Fri, 06 Dec 2013 22:05:33 -0800
+lib/simple_bioc/node_base.rb	Fri, 06 Dec 2013 22:06:00 -0800
 lib/simple_bioc/passage.rb	Fri, 06 Dec 2013 20:52:11 -0800
 lib/simple_bioc/relation.rb	Fri, 06 Dec 2013 20:52:11 -0800
 lib/simple_bioc/sentence.rb	Fri, 06 Dec 2013 20:52:11 -0800
-lib/simple_bioc/version.rb	Fri, 06 Dec 2013 20:52:11 -0800
+lib/simple_bioc/version.rb	Fri, 06 Dec 2013 22:06:07 -0800

data/html/index.html CHANGED Viewed

@@ -91,7 +91,7 @@
 <div id="documentation" class="description">
-<h1 id="label-SimpleBioc">SimpleBioc<span><a href="#label-SimpleBioc">&para;</a> <a href="#documentation">&uarr;</a></span></h1>
+<h1 id="label-SimpleBioC"><a href="SimpleBioC.html">SimpleBioC</a><span><a href="#label-SimpleBioC">&para;</a> <a href="#documentation">&uarr;</a></span></h1>
 <p><a href="SimpleBioC.html">SimpleBioC</a> is a simple parser / builder for
 BioC data format. BioC is a simple XML format to share text documents and
@@ -123,7 +123,7 @@ BioC DTD</p>
 <pre>$ gem install simple_bioc</pre>
-<h2 id="label-Usages">Usages<span><a href="#label-Usages">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
+<h2 id="label-Simple+Usages">Simple Usages<span><a href="#label-Simple+Usages">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
 <p>Include library</p>
@@ -135,7 +135,11 @@ BioC DTD</p>
 <pre>collection = SimpleBioC::from_xml(filename)</pre>
 <p>Traverse &amp; Manipulate Data. Data structure are almost the same as the
-DTD. Please refer <a href="http://">library documents</a>.</p>
+DTD. Please refer <a
+href="http://rubydoc.info/gems/simple_bioc/0.0.2/frames">library
+documents</a> and <a
+href="http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCDTD.html">the
+BioC DTD</a>.</p>
 <pre>puts collection.documents[2].passages[0].text</pre>
@@ -143,6 +147,25 @@ DTD. Please refer <a href="http://">library documents</a>.</p>
 <pre>puts SimpleBioC::to_xml(collection)</pre>
+<h2 id="label-Options">Options<span><a href="#label-Options">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
+<h3 id="label-Specify+set+of+%3Cdocument%3Es+to+parse">Specify set of &lt;document&gt;s to parse<span><a href="#label-Specify+set+of+%3Cdocument%3Es+to+parse">&para;</a> <a href="#documentation">&uarr;</a></span></h3>
+<p>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”).</p>
+<pre>collection = SimpleBioc::from_xml(filename, {documents: [&quot;1234&quot;, &quot;4567&quot;]})</pre>
+<h3 id="label-No+whitespace+in+output">No whitespace in output<span><a href="#label-No+whitespace+in+output">&para;</a> <a href="#documentation">&uarr;</a></span></h3>
+<p>By default, outputs of SimpleBioC::to_xml() will be formatted with
+whitespace. If you do not want this whitespace, you should pass
+&#39;save_with&#39; option with 0 to the to_xml() function.</p>
+<pre>puts SimpleBioC::to_xml(collection, {save_with:0})</pre>
 <h2 id="label-Sample">Sample<span><a href="#label-Sample">&para;</a> <a href="#documentation">&uarr;</a></span></h2>
 <p>More samples can be found in Samples directory</p>

data/html/js/search_index.js CHANGED Viewed

	@@ -1 +1 @@
1	- var search_data = {"index":{"searchIndex":["biocreader","biocwriter","simplebioc","annotation","collection","document","location","node","nodebase","passage","relation","sentence","adjust_ref()","adjust_ref()","adjust_ref()","each_relation()","each_relation()","each_relation()","find_node()","find_node()","find_node()","from_xml()","new()","new()","new()","new()","new()","new()","new()","new()","new()","read()","read_annotation()","read_collection()","read_document()","read_infon()","read_int()","read_location()","read_node()","read_passage()","read_recursive()","read_relation()","read_sentence()","read_text()","to_c()","to_c()","to_c()","to_c()","to_s()","to_s()","to_s()","to_s()","to_xml()","write()","write_annotation()","write_collection()","write_document()","write_infon()","write_location()","write_node()","write_passage()","write_relation()","write_sentence()","readme"],"longSearchIndex":["biocreader","biocwriter","simplebioc","simplebioc::annotation","simplebioc::collection","simplebioc::document","simplebioc::location","simplebioc::node","simplebioc::nodebase","simplebioc::passage","simplebioc::relation","simplebioc::sentence","simplebioc::document#adjust_ref()","simplebioc::node#adjust_ref()","simplebioc::relation#adjust_ref()","simplebioc::document#each_relation()","simplebioc::passage#each_relation()","simplebioc::sentence#each_relation()","simplebioc::document#find_node()","simplebioc::passage#find_node()","simplebioc::sentence#find_node()","simplebioc#from_xml()","simplebioc::annotation::new()","simplebioc::collection::new()","simplebioc::document::new()","simplebioc::location::new()","simplebioc::node::new()","simplebioc::nodebase::new()","simplebioc::passage::new()","simplebioc::relation::new()","simplebioc::sentence::new()","biocreader#read()","biocreader#read_annotation()","biocreader#read_collection()","biocreader#read_document()","biocreader#read_infon()","biocreader#read_int()","biocreader#read_location()","biocreader#read_node()","biocreader#read_passage()","biocreader#read_recursive()","biocreader#read_relation()","biocreader#read_sentence()","biocreader#read_text()","simplebioc::collection#to_c()","simplebioc::node#to_c()","simplebioc::relation#to_c()","simplebioc::sentence#to_c()","simplebioc::annotation#to_s()","simplebioc::document#to_s()","simplebioc::location#to_s()","simplebioc::passage#to_s()","simplebioc#to_xml()","biocwriter#write()","biocwriter#write_annotation()","biocwriter#write_collection()","biocwriter#write_document()","biocwriter#write_infon()","biocwriter#write_location()","biocwriter#write_node()","biocwriter#write_passage()","biocwriter#write_relation()","biocwriter#write_sentence()",""],"info":[["BioCReader","","BioCReader.html","",""],["BioCWriter","","BioCWriter.html","",""],["SimpleBioC","","SimpleBioC.html","","<p>SimpleBioC main library\n"],["SimpleBioC::Annotation","","SimpleBioC/Annotation.html","",""],["SimpleBioC::Collection","","SimpleBioC/Collection.html","",""],["SimpleBioC::Document","","SimpleBioC/Document.html","",""],["SimpleBioC::Location","","SimpleBioC/Location.html","",""],["SimpleBioC::Node","","SimpleBioC/Node.html","",""],["SimpleBioC::NodeBase","","SimpleBioC/NodeBase.html","","<p>NodeBase is not in BioC DTD. This is a super class of Annotation &amp~~;\nRelation\~~n"],["SimpleBioC::Passage","","SimpleBioC/Passage.html","",""],["SimpleBioC::Relation","","SimpleBioC/Relation.html","",""],["SimpleBioC::Sentence","","SimpleBioC/Sentence.html","",""],["adjust_ref","SimpleBioC::Document","SimpleBioC/Document.html#method-i-adjust_ref","()",""],["adjust_ref","SimpleBioC::Node","SimpleBioC/Node.html#method-i-adjust_ref","()",""],["adjust_ref","SimpleBioC::Relation","SimpleBioC/Relation.html#method-i-adjust_ref","()",""],["each_relation","SimpleBioC::Document","SimpleBioC/Document.html#method-i-each_relation","()",""],["each_relation","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-each_relation","()",""],["each_relation","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-each_relation","()",""],["find_node","SimpleBioC::Document","SimpleBioC/Document.html#method-i-find_node","(id)",""],["find_node","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-find_node","(id)",""],["find_node","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-find_node","(id)",""],["from_xml","SimpleBioC","SimpleBioC.html#method-i-from_xml","(file_path)","<p>parse a BioC XML file in the given path and convert it into a collection\ninstance\n"],["new","SimpleBioC::Annotation","SimpleBioC/Annotation.html#method-c-new","(parent)",""],["new","SimpleBioC::Collection","SimpleBioC/Collection.html#method-c-new","()",""],["new","SimpleBioC::Document","SimpleBioC/Document.html#method-c-new","(parent)",""],["new","SimpleBioC::Location","SimpleBioC/Location.html#method-c-new","(parent)",""],["new","SimpleBioC::Node","SimpleBioC/Node.html#method-c-new","(parent)",""],["new","SimpleBioC::NodeBase","SimpleBioC/NodeBase.html#method-c-new","(parent)",""],["new","SimpleBioC::Passage","SimpleBioC/Passage.html#method-c-new","(parent)",""],["new","SimpleBioC::Relation","SimpleBioC/Relation.html#method-c-new","(parent)",""],["new","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-c-new","(parent)",""],["read","BioCReader","BioCReader.html#method-i-read","(path)",""],["read_annotation","BioCReader","BioCReader.html#method-i-read_annotation","(xml, annotation)",""],["read_collection","BioCReader","BioCReader.html#method-i-read_collection","(xml, collection)",""],["read_document","BioCReader","BioCReader.html#method-i-read_document","(xml, document)",""],["read_infon","BioCReader","BioCReader.html#method-i-read_infon","(xml, obj)",""],["read_int","BioCReader","BioCReader.html#method-i-read_int","(xml, name)",""],["read_location","BioCReader","BioCReader.html#method-i-read_location","(xml, location)",""],["read_node","BioCReader","BioCReader.html#method-i-read_node","(xml, node)",""],["read_passage","BioCReader","BioCReader.html#method-i-read_passage","(xml, passage)",""],["read_recursive","BioCReader","BioCReader.html#method-i-read_recursive","(xml, obj, name)",""],["read_relation","BioCReader","BioCReader.html#method-i-read_relation","(xml, relation)",""],["read_sentence","BioCReader","BioCReader.html#method-i-read_sentence","(xml, sentence)",""],["read_text","BioCReader","BioCReader.html#method-i-read_text","(xml, name)",""],["to_c","SimpleBioC::Collection","SimpleBioC/Collection.html#method-i-to_c","()",""],["to_c","SimpleBioC::Node","SimpleBioC/Node.html#method-i-to_c","()",""],["to_c","SimpleBioC::Relation","SimpleBioC/Relation.html#method-i-to_c","()",""],["to_c","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-to_c","()",""],["to_s","SimpleBioC::Annotation","SimpleBioC/Annotation.html#method-i-to_s","()",""],["to_s","SimpleBioC::Document","SimpleBioC/Document.html#method-i-to_s","()",""],["to_s","SimpleBioC::Location","SimpleBioC/Location.html#method-i-to_s","()",""],["to_s","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-to_s","()",""],["to_xml","SimpleBioC","SimpleBioC.html#method-i-to_xml","(collection)","<p>convert a collection instance to a BioC XML text\n"],["write","BioCWriter","BioCWriter.html#method-i-write","(collection)",""],["write_annotation","BioCWriter","BioCWriter.html#method-i-write_annotation","(xml, annotation)",""],["write_collection","BioCWriter","BioCWriter.html#method-i-write_collection","(xml, collection)",""],["write_document","BioCWriter","BioCWriter.html#method-i-write_document","(xml, document)",""],["write_infon","BioCWriter","BioCWriter.html#method-i-write_infon","(xml, obj)",""],["write_location","BioCWriter","BioCWriter.html#method-i-write_location","(xml, location)",""],["write_node","BioCWriter","BioCWriter.html#method-i-write_node","(xml, node)",""],["write_passage","BioCWriter","BioCWriter.html#method-i-write_passage","(xml, passage)",""],["write_relation","BioCWriter","BioCWriter.html#method-i-write_relation","(xml, relation)",""],["write_sentence","BioCWriter","BioCWriter.html#method-i-write_sentence","(xml, sentence)",""],["README","","README_md.html","","<p>~~SimpleBioc~~\n<p>SimpleBioC is a simple parser / builder for BioC data format. BioC is a\nsimple XML format to …\n"]]}}
1	+ var search_data = {"index":{"searchIndex":["biocreader","biocwriter","simplebioc","annotation","collection","document","location","node","nodebase","passage","relation","sentence","adjust_ref()","adjust_ref()","adjust_ref()","each_relation()","each_relation()","each_relation()","find_node()","find_node()","find_node()","from_xml()","new()","new()","new()","new()","new()","new()","new()","new()","new()","read()","read_annotation()","read_collection()","read_document()","read_infon()","read_int()","read_location()","read_node()","read_passage()","read_recursive()","read_relation()","read_sentence()","read_text()","to_c()","to_c()","to_c()","to_c()","to_s()","to_s()","to_s()","to_s()","to_xml()","write()","write_annotation()","write_collection()","write_document()","write_infon()","write_location()","write_node()","write_passage()","write_relation()","write_sentence()","readme"],"longSearchIndex":["biocreader","biocwriter","simplebioc","simplebioc::annotation","simplebioc::collection","simplebioc::document","simplebioc::location","simplebioc::node","simplebioc::nodebase","simplebioc::passage","simplebioc::relation","simplebioc::sentence","simplebioc::document#adjust_ref()","simplebioc::node#adjust_ref()","simplebioc::relation#adjust_ref()","simplebioc::document#each_relation()","simplebioc::passage#each_relation()","simplebioc::sentence#each_relation()","simplebioc::document#find_node()","simplebioc::passage#find_node()","simplebioc::sentence#find_node()","simplebioc#from_xml()","simplebioc::annotation::new()","simplebioc::collection::new()","simplebioc::document::new()","simplebioc::location::new()","simplebioc::node::new()","simplebioc::nodebase::new()","simplebioc::passage::new()","simplebioc::relation::new()","simplebioc::sentence::new()","biocreader#read()","biocreader#read_annotation()","biocreader#read_collection()","biocreader#read_document()","biocreader#read_infon()","biocreader#read_int()","biocreader#read_location()","biocreader#read_node()","biocreader#read_passage()","biocreader#read_recursive()","biocreader#read_relation()","biocreader#read_sentence()","biocreader#read_text()","simplebioc::collection#to_c()","simplebioc::node#to_c()","simplebioc::relation#to_c()","simplebioc::sentence#to_c()","simplebioc::annotation#to_s()","simplebioc::document#to_s()","simplebioc::location#to_s()","simplebioc::passage#to_s()","simplebioc#to_xml()","biocwriter#write()","biocwriter#write_annotation()","biocwriter#write_collection()","biocwriter#write_document()","biocwriter#write_infon()","biocwriter#write_location()","biocwriter#write_node()","biocwriter#write_passage()","biocwriter#write_relation()","biocwriter#write_sentence()",""],"info":[["BioCReader","","BioCReader.html","",""],["BioCWriter","","BioCWriter.html","",""],["SimpleBioC","","SimpleBioC.html","","<p>SimpleBioC main library\n"],["SimpleBioC::Annotation","","SimpleBioC/Annotation.html","",""],["SimpleBioC::Collection","","SimpleBioC/Collection.html","",""],["SimpleBioC::Document","","SimpleBioC/Document.html","",""],["SimpleBioC::Location","","SimpleBioC/Location.html","",""],["SimpleBioC::Node","","SimpleBioC/Node.html","",""],["SimpleBioC::NodeBase","","SimpleBioC/NodeBase.html","","<p>NodeBase is not a BioC DTD entity. This is a super class of Annotation\n& Relation.\n"],["SimpleBioC::Passage","","SimpleBioC/Passage.html","",""],["SimpleBioC::Relation","","SimpleBioC/Relation.html","",""],["SimpleBioC::Sentence","","SimpleBioC/Sentence.html","",""],["adjust_ref","SimpleBioC::Document","SimpleBioC/Document.html#method-i-adjust_ref","()",""],["adjust_ref","SimpleBioC::Node","SimpleBioC/Node.html#method-i-adjust_ref","()",""],["adjust_ref","SimpleBioC::Relation","SimpleBioC/Relation.html#method-i-adjust_ref","()",""],["each_relation","SimpleBioC::Document","SimpleBioC/Document.html#method-i-each_relation","()",""],["each_relation","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-each_relation","()",""],["each_relation","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-each_relation","()",""],["find_node","SimpleBioC::Document","SimpleBioC/Document.html#method-i-find_node","(id)",""],["find_node","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-find_node","(id)",""],["find_node","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-find_node","(id)",""],["from_xml","SimpleBioC","SimpleBioC.html#method-i-from_xml","(file_path, options = {})","<p>parse a BioC XML file in the given path and convert it into a collection\ninstance\n<p>Arguments\n<p><code>file_path</code> - …\n"],["new","SimpleBioC::Annotation","SimpleBioC/Annotation.html#method-c-new","(parent)",""],["new","SimpleBioC::Collection","SimpleBioC/Collection.html#method-c-new","()",""],["new","SimpleBioC::Document","SimpleBioC/Document.html#method-c-new","(parent)",""],["new","SimpleBioC::Location","SimpleBioC/Location.html#method-c-new","(parent)",""],["new","SimpleBioC::Node","SimpleBioC/Node.html#method-c-new","(parent)",""],["new","SimpleBioC::NodeBase","SimpleBioC/NodeBase.html#method-c-new","(parent)",""],["new","SimpleBioC::Passage","SimpleBioC/Passage.html#method-c-new","(parent)",""],["new","SimpleBioC::Relation","SimpleBioC/Relation.html#method-c-new","(parent)",""],["new","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-c-new","(parent)",""],["read","BioCReader","BioCReader.html#method-i-read","(path, options)",""],["read_annotation","BioCReader","BioCReader.html#method-i-read_annotation","(xml, annotation, options = {})",""],["read_collection","BioCReader","BioCReader.html#method-i-read_collection","(xml, collection, options = {})",""],["read_document","BioCReader","BioCReader.html#method-i-read_document","(xml, document, options = {})",""],["read_infon","BioCReader","BioCReader.html#method-i-read_infon","(xml, obj)",""],["read_int","BioCReader","BioCReader.html#method-i-read_int","(xml, name)",""],["read_location","BioCReader","BioCReader.html#method-i-read_location","(xml, location, options = {})",""],["read_node","BioCReader","BioCReader.html#method-i-read_node","(xml, node, options = {})",""],["read_passage","BioCReader","BioCReader.html#method-i-read_passage","(xml, passage, options = {})",""],["read_recursive","BioCReader","BioCReader.html#method-i-read_recursive","(xml, obj, name, options = {})",""],["read_relation","BioCReader","BioCReader.html#method-i-read_relation","(xml, relation, options = {})",""],["read_sentence","BioCReader","BioCReader.html#method-i-read_sentence","(xml, sentence, options = {})",""],["read_text","BioCReader","BioCReader.html#method-i-read_text","(xml, name)",""],["to_c","SimpleBioC::Collection","SimpleBioC/Collection.html#method-i-to_c","()",""],["to_c","SimpleBioC::Node","SimpleBioC/Node.html#method-i-to_c","()",""],["to_c","SimpleBioC::Relation","SimpleBioC/Relation.html#method-i-to_c","()",""],["to_c","SimpleBioC::Sentence","SimpleBioC/Sentence.html#method-i-to_c","()",""],["to_s","SimpleBioC::Annotation","SimpleBioC/Annotation.html#method-i-to_s","()",""],["to_s","SimpleBioC::Document","SimpleBioC/Document.html#method-i-to_s","()",""],["to_s","SimpleBioC::Location","SimpleBioC/Location.html#method-i-to_s","()",""],["to_s","SimpleBioC::Passage","SimpleBioC/Passage.html#method-i-to_s","()",""],["to_xml","SimpleBioC","SimpleBioC.html#method-i-to_xml","(collection, options = {})","<p>convert a collection instance to a BioC XML text. Output will return as\nstring\n<p>Arguments\n<p><code>collection</code> - …\n"],["write","BioCWriter","BioCWriter.html#method-i-write","(collection, options = {})",""],["write_annotation","BioCWriter","BioCWriter.html#method-i-write_annotation","(xml, annotation)",""],["write_collection","BioCWriter","BioCWriter.html#method-i-write_collection","(xml, collection)",""],["write_document","BioCWriter","BioCWriter.html#method-i-write_document","(xml, document)",""],["write_infon","BioCWriter","BioCWriter.html#method-i-write_infon","(xml, obj)",""],["write_location","BioCWriter","BioCWriter.html#method-i-write_location","(xml, location)",""],["write_node","BioCWriter","BioCWriter.html#method-i-write_node","(xml, node)",""],["write_passage","BioCWriter","BioCWriter.html#method-i-write_passage","(xml, passage)",""],["write_relation","BioCWriter","BioCWriter.html#method-i-write_relation","(xml, relation)",""],["write_sentence","BioCWriter","BioCWriter.html#method-i-write_sentence","(xml, sentence)",""],["README","","README_md.html","","<p>SimpleBioC\n<p>SimpleBioC is a simple parser / builder for BioC data format. BioC is a\nsimple XML format to …\n"]]}}

data/html/table_of_contents.html CHANGED Viewed

@@ -30,10 +30,13 @@
     <img class="toc-toggle" src="images/transparent.png" alt="" title="toggle headings">
     <ul class="initially-hidden">
-      <li><a href="README_md.html#label-SimpleBioc">SimpleBioc</a>
+      <li><a href="README_md.html#label-SimpleBioC">SimpleBioC</a>
       <li><a href="README_md.html#label-Feature%3A">Feature:</a>
       <li><a href="README_md.html#label-Installation">Installation</a>
-      <li><a href="README_md.html#label-Usages">Usages</a>
+      <li><a href="README_md.html#label-Simple+Usages">Simple Usages</a>
+      <li><a href="README_md.html#label-Options">Options</a>
+      <li><a href="README_md.html#label-Specify+set+of+%3Cdocument%3Es+to+parse">Specify set of &lt;document&gt;s to parse</a>
+      <li><a href="README_md.html#label-No+whitespace+in+output">No whitespace in output</a>
       <li><a href="README_md.html#label-Sample">Sample</a>
       <li><a href="README_md.html#label-Contributing">Contributing</a>
       <li><a href="README_md.html#label-LICENSE">LICENSE</a>

data/lib/simple_bioc/bioc_reader.rb CHANGED Viewed

@@ -4,7 +4,7 @@ Dir[File.dirname(__FILE__) + '/*.rb'].each {|file| require file }
 module BioCReader
   module_function
-  def read(path)
+  def read(path, options)
     collection = nil
     File.open(path) do |file|
       xml_doc  = Nokogiri::XML(file) do |config|
@@ -15,7 +15,7 @@ module BioCReader
         fail 'Wrong format'
       end
       collection = SimpleBioC::Collection.new
-      read_collection(xml, collection)
+      read_collection(xml, collection, options)
     end
     collection
@@ -35,68 +35,78 @@ module BioCReader
     xml.xpath("infon").each{ |i| obj.infons[i["key"]] = i.content}
   end
-  def read_recursive(xml, obj, name)
+  def read_recursive(xml, obj, name, options = {})
     target_class = SimpleBioC.const_get(name.capitalize)
     xml.xpath(name).each do |node|
       instance = target_class.new(obj)
-      send(:"read_#{name}", node, instance)
-      obj.instance_variable_get(:"@#{name}s")  << instance
+      ret = send(:"read_#{name}", node, instance, options)
+      obj.instance_variable_get(:"@#{name}s")  << instance if ret
     end
   end
-  def read_collection(xml, collection)
+  def read_collection(xml, collection, options = {})
     collection.source = read_text(xml, "source")
     collection.date = read_text(xml, "date")
     collection.key = read_text(xml, "key")
     read_infon(xml, collection)
-    read_recursive(xml, collection, "document")
+    read_recursive(xml, collection, "document", options)
   end
-  def read_document(xml, document)
+  def read_document(xml, document, options = {})
     document.id = read_text(xml, "id")
+    if options[:documents].kind_of?(Array) && !options[:documents].include?(document.id)
+      return false
+    end
     read_infon(xml, document)
     read_recursive(xml, document, "passage")
     read_recursive(xml, document, "relation")
     document.adjust_ref
+    true
   end
-  def read_passage(xml, passage)
+  def read_passage(xml, passage, options = {})
     passage.text = read_text(xml, "text")
     passage.offset = read_int(xml, "offset")
     read_infon(xml, passage)
     read_recursive(xml, passage, "sentence")
     read_recursive(xml, passage, "annotation")
     read_recursive(xml, passage, "relation")
+    true
   end
-  def read_sentence(xml, sentence)
+  def read_sentence(xml, sentence, options = {})
     sentence.text = read_text(xml, "text")
     sentence.offset = read_int(xml, "offset")
     read_infon(xml, sentence)
     read_recursive(xml, sentence, "annotation")
     read_recursive(xml, sentence, "relation")
+    true
   end
-  def read_annotation(xml, annotation)
+  def read_annotation(xml, annotation, options = {})
     annotation.id = xml["id"]
     annotation.text = read_text(xml, "text")
     read_infon(xml, annotation)
     read_recursive(xml, annotation, "location")
+    true
   end
-  def read_relation(xml, relation)
+  def read_relation(xml, relation, options = {})
     relation.id = xml["id"]
     read_infon(xml, relation)
     read_recursive(xml, relation, "node")
+    true
   end
-  def read_location(xml, location)
+  def read_location(xml, location, options = {})
     location.offset = xml["offset"]
     location.length = xml["length"]
+    true
   end
-  def read_node(xml, node)
+  def read_node(xml, node, options = {})
     node.refid = xml["refid"]
     node.role = xml["role"]
+    true
   end
 end

data/lib/simple_bioc/bioc_writer.rb CHANGED Viewed

@@ -3,11 +3,13 @@ Dir[File.dirname(__FILE__) + '/*.rb'].each {|file| require file }
 module BioCWriter
   module_function
-  def write(collection)
+  def write(collection, options = {})
+    options[:save_with] = 1 if options[:save_with].nil?
     builder = Nokogiri::XML::Builder.new(:encoding => 'UTF-8') do |xml|
+      xml.doc.create_internal_subset( 'collection', nil, 'BioC.dtd' )
       write_collection(xml, collection)
     end
-    builder.to_xml
+    builder.to_xml(options)
   end
   def write_infon(xml, obj)

data/lib/simple_bioc/version.rb CHANGED Viewed

@@ -1,3 +1,3 @@
 module SimpleBioC
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/simple_bioc.rb CHANGED Viewed

@@ -1,3 +1,4 @@
+# @author Dongseop Kwon
 require "simple_bioc/version"
 require "simple_bioc/bioc_reader"
 require "simple_bioc/bioc_writer"
@@ -7,12 +8,35 @@ module SimpleBioC
   module_function
   # parse a BioC XML file in the given path and convert it into a collection instance
-  def from_xml(file_path)
-    BioCReader.read(file_path)
+  #
+  # ==== Arguments
+  # * +file_path+ - file path for parse
+  # * +options+ - (optional) additional options
+  #
+  # ==== Options
+  # * +documents+ - specify IDs of documents to parse. The result will include only the specified documents
+  #
+  # ==== Examples
+  #    collection = SimpleBioC.from_xml("./xml/everything.xml")
+  #    collection = SimpleBioC.from_xml("./xml/lemma.xml", {documents:[21785578, 21488974]})
+  def from_xml(file_path, options = {})
+    options[:documents] = options[:documents].map{|e| e.to_s} if options[:documents].kind_of?(Array)
+    BioCReader.read(file_path, options)
   end
-  # convert a collection instance to a BioC XML text
-  def to_xml(collection)
-    BioCWriter.write(collection)
+  # convert a collection instance to a BioC XML text. Output will return as string
+  #
+  # ==== Arguments
+  # * +collection+ - Collection instance to process
+  # * +options+ - (optional) additional options
+  #
+  # ==== Options
+  # * +save_with+ - SaveOption for Nokorigi. If you set this 0, output has no format (no indentation, no whitespace)
+  #
+  # ==== Examples
+  #    output = SimpleBioC.to_xml(collection)
+  #    output = SimpleBioC.to_xml(collection, {save_with: 0})
+  def to_xml(collection, options = {})
+    BioCWriter.write(collection, options)
   end
 end

data/simple_bioc.gemspec CHANGED Viewed

@@ -8,7 +8,7 @@ Gem::Specification.new do |spec|
   spec.version       = SimpleBioC::VERSION
   spec.authors       = ["Dongseop Kwon"]
   spec.email         = ["dongseop@gmail.com"]
-  spec.description   = "Simple BioC parser/builder for ruby. BioC is a 'A Minimalist Approach to Interoperability for Biomedical Text Processing' (http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCHome.html)"
+  spec.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/)"
   spec.summary       = "Simple BioC parser/builder for ruby"
   spec.homepage      = "https://github.com/dongseop/simple_bioc"
   spec.license       = "MIT"

data/spec/file_check_spec.rb ADDED Viewed

@@ -0,0 +1,13 @@
+require 'simple_bioc'
+require 'test_xml/spec'
+describe "File Check" do
+  it "should be load successfully" do
+    Dir["./xml/*.xml"].each do |file_path|
+      puts file_path
+      collection = SimpleBioC.from_xml(file_path)
+      output = SimpleBioC.to_xml(collection)
+      expected = File.read(file_path)
+      expect(output).to equal_xml(expected)
+    end
+  end
+end

data/spec/simple_bioc_spec.rb CHANGED Viewed

@@ -1,14 +1,25 @@
-# bowling_spec.rb
 require 'simple_bioc'
 require 'test_xml/spec'
-describe BioCReader do
-  it "should be load successfully" do
-    Dir["./xml/*.xml"].each do |file_path|
-      puts file_path
-      collection = SimpleBioC.from_xml(file_path)
-      output = SimpleBioC.to_xml(collection)
-      expected = File.read(file_path)
-      expect(output).to equal_xml(expected)
-    end
+describe "Simple function" do
+  it "should have a DTD declaration" do
+    collection = SimpleBioC.from_xml("./xml/everything.xml")
+    output = SimpleBioC.to_xml(collection)
+    output.should include('<!DOCTYPE collection SYSTEM "BioC.dtd">')
+  end
+  it "should no space when save_with = 0" do
+    collection = SimpleBioC.from_xml("./xml/everything.xml")
+    output = SimpleBioC.to_xml(collection, {save_with: 0})
+    output.should include('<collection><source>Made up file to test that everything is allowed and processed. Has text in the passage.</source><date>20130426</date><key>everything.key</key><infon key="collection-infon-key">collection-infon-value</infon><document><id>1</id><infon key="document-infon-key">document-infon-value</infon><passage><infon key="passage-infon-key">passage-infon-value</infon><offset>0</offset><text>text of passage</text><annotation id="P1"><infon key="annotation-infon-key">annotation-infon-value</infon><text>annotation text</text><location offset="1" length="2"/></annotation><relation id="RP1"><infon key="passage-relation-infon-key">passage-relation-infon-value</infon><node refid="RP1" role="passage-relation"/></relation></passage><relation id="D1"><infon key="document-relation-infon-key">document-relation-infon-value</infon><node refid="RD1" role="document-relation"/></relation></document></collection>')
+  end
+  it "should process only one document by options" do
+    collection = SimpleBioC.from_xml("./xml/lemma.xml", {documents:[21785578, 21488974]})
+    output = SimpleBioC.to_xml(collection, {save_with: 0})
+    output.scan("<document>").size.should equal 2
+    output.should include("<document><id>21785578</id>")
+    output.should include("<document><id>21488974</id>")
+    output.should_not include("<document><id>21660417</id>")
+    output.should_not include("<document><id>21951408</id>")
   end
 end

metadata CHANGED Viewed

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_bioc
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors:
 - Dongseop Kwon
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2013-12-07 00:00:00.000000000 Z
+date: 2013-12-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -80,8 +80,9 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: 0.1.6
-description: Simple BioC parser/builder for ruby. BioC is a 'A Minimalist Approach
-  to Interoperability for Biomedical Text Processing' (http://www.ncbi.nlm.nih.gov/CBBresearch/Dogan/BioC/BioCHome.html)
+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/)
 email:
 - dongseop@gmail.com
 executables: []
@@ -158,6 +159,7 @@ files:
 - samples/print_annotation.rb
 - samples/sample1.rb
 - simple_bioc.gemspec
+- spec/file_check_spec.rb
 - spec/simple_bioc_spec.rb
 - xml/BioC.dtd
 - xml/PMID-8557975-simplified-sentences-tokens.xml
@@ -200,4 +202,6 @@ signing_key:
 specification_version: 4
 summary: Simple BioC parser/builder for ruby
 test_files:
+- spec/file_check_spec.rb
 - spec/simple_bioc_spec.rb
+has_rdoc: