Deploying to gh-pages from @ 39c3824 🚀

_modules/pandasaurus_cxg/graph_generator/graph_generator.html

@@ -78,7 +78,6 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator</h1><div cla
 
 <span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="nn">plt</span>
 <span class="kn">import</span> <span class="nn">networkx</span> <span class="k">as</span> <span class="nn">nx</span>
-<span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
 <span class="kn">from</span> <span class="nn">pandasaurus.graph.graph_generator</span> <span class="kn">import</span> <span class="n">GraphGenerator</span> <span class="k">as</span> <span class="n">graphgen</span>
 <span class="kn">from</span> <span class="nn">rdflib</span> <span class="kn">import</span> <span class="n">OWL</span><span class="p">,</span> <span class="n">RDF</span><span class="p">,</span> <span class="n">RDFS</span><span class="p">,</span> <span class="n">BNode</span><span class="p">,</span> <span class="n">Graph</span><span class="p">,</span> <span class="n">Literal</span><span class="p">,</span> <span class="n">Namespace</span><span class="p">,</span> <span class="n">URIRef</span>
 <span class="kn">from</span> <span class="nn">rdflib.plugins.sparql</span> <span class="kn">import</span> <span class="n">prepareQuery</span>
@@ -92,9 +91,11 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator</h1><div cla
     <span class="n">add_edge</span><span class="p">,</span>
     <span class="n">add_node</span><span class="p">,</span>
     <span class="n">add_outgoing_edges_to_subgraph</span><span class="p">,</span>
+    <span class="n">citation_field_name</span><span class="p">,</span>
     <span class="n">colour_mapping</span><span class="p">,</span>
     <span class="n">find_and_rotate_center_layout</span><span class="p">,</span>
     <span class="n">generate_subgraph</span><span class="p">,</span>
+    <span class="n">parse_citation_field_into_dict</span><span class="p">,</span>
     <span class="n">remove_special_characters</span><span class="p">,</span>
     <span class="n">select_node_with_property</span><span class="p">,</span>
 <span class="p">)</span>
@@ -206,6 +207,17 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator</h1><div cla
         <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">uns</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
             <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
                 <span class="k">continue</span>
+            <span class="k">if</span> <span class="n">key</span> <span class="o">==</span> <span class="n">citation_field_name</span><span class="p">:</span>
+                <span class="n">citation_dict</span> <span class="o">=</span> <span class="n">parse_citation_field_into_dict</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
+                <span class="k">for</span> <span class="n">citation_key</span><span class="p">,</span> <span class="n">citation_value</span> <span class="ow">in</span> <span class="n">citation_dict</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
+                    <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">(</span>
+                        <span class="p">(</span>
+                            <span class="n">dataset_class</span><span class="p">,</span>
+                            <span class="n">URIRef</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ns</span><span class="p">[</span><span class="n">citation_key</span><span class="p">]),</span>
+                            <span class="n">Literal</span><span class="p">(</span><span class="n">citation_value</span><span class="p">),</span>
+                        <span class="p">)</span>
+                    <span class="p">)</span>
+
             <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">dataset_class</span><span class="p">,</span> <span class="n">URIRef</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">ns</span><span class="p">[</span><span class="n">key</span><span class="p">]),</span> <span class="n">Literal</span><span class="p">(</span><span class="n">value</span><span class="p">)))</span>
         <span class="n">has_source</span> <span class="o">=</span> <span class="n">URIRef</span><span class="p">(</span><span class="n">HAS_SOURCE</span><span class="p">[</span><span class="s2">&quot;iri&quot;</span><span class="p">])</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">has_source</span><span class="p">,</span> <span class="n">RDFS</span><span class="o">.</span><span class="n">label</span><span class="p">,</span> <span class="n">Literal</span><span class="p">(</span><span class="n">HAS_SOURCE</span><span class="p">[</span><span class="s2">&quot;label&quot;</span><span class="p">])))</span>

_modules/pandasaurus_cxg/graph_generator/graph_generator_utils.html

@@ -72,6 +72,7 @@
 
   <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator_utils</h1><div class="highlight"><pre>
 <span></span><span class="kn">import</span> <span class="nn">re</span>
+<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
 
 <span class="kn">import</span> <span class="nn">networkx</span> <span class="k">as</span> <span class="nn">nx</span>
 <span class="kn">from</span> <span class="nn">rdflib</span> <span class="kn">import</span> <span class="n">OWL</span><span class="p">,</span> <span class="n">RDF</span><span class="p">,</span> <span class="n">RDFS</span><span class="p">,</span> <span class="n">BNode</span><span class="p">,</span> <span class="n">Graph</span><span class="p">,</span> <span class="n">Literal</span><span class="p">,</span> <span class="n">Namespace</span><span class="p">,</span> <span class="n">URIRef</span>
@@ -87,6 +88,8 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator_utils</h1><d
     <span class="s2">&quot;http://purl.obolibrary.org/obo/PCL_0010001&quot;</span><span class="p">:</span> <span class="s2">&quot;cyan&quot;</span><span class="p">,</span>
 <span class="p">}</span>
 
+<span class="n">citation_field_name</span> <span class="o">=</span> <span class="s2">&quot;citation&quot;</span>
+
 
 <span class="k">def</span> <span class="nf">add_edge</span><span class="p">(</span><span class="n">nx_graph</span><span class="p">:</span> <span class="n">nx</span><span class="o">.</span><span class="n">Graph</span><span class="p">,</span> <span class="n">subject</span><span class="p">,</span> <span class="n">predicate</span><span class="p">,</span> <span class="n">obj</span><span class="p">):</span>
     <span class="n">edge_data</span> <span class="o">=</span> <span class="p">{</span>
@@ -205,6 +208,38 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator_utils</h1><d
 
 <span class="k">def</span> <span class="nf">remove_special_characters</span><span class="p">(</span><span class="n">input_string</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
     <span class="k">return</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">&quot;[^a-zA-Z0-9_]&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">,</span> <span class="n">input_string</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="p">,</span> <span class="s2">&quot;_&quot;</span><span class="p">))</span>
+
+
+<div class="viewcode-block" id="parse_citation_field_into_dict">
+<a class="viewcode-back" href="../../../pandasaurus_cxg/graph_generator/graph_generator_utils.html#pandasaurus_cxg.graph_generator.graph_generator_utils.parse_citation_field_into_dict">[docs]</a>
+<span class="k">def</span> <span class="nf">parse_citation_field_into_dict</span><span class="p">(</span><span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
+<span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
+<span class="sd">    Parses a citation string into a dictionary by extracting key citation fields.</span>
+
+<span class="sd">    Args:</span>
+<span class="sd">        value: The string containing citation fields and values.</span>
+
+<span class="sd">    Returns:</span>
+<span class="sd">        A dictionary with keys such as &#39;Publication&#39;, &#39;Dataset Version&#39;, and &#39;Collection&#39;,</span>
+<span class="sd">          and corresponding values extracted from the input string.</span>
+<span class="sd">    &quot;&quot;&quot;</span>
+    <span class="c1"># Split the input string on the key terms</span>
+    <span class="n">parts</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="p">)</span>
+    <span class="n">keys</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;Publication:&quot;</span><span class="p">,</span> <span class="s2">&quot;Version:&quot;</span><span class="p">,</span> <span class="s2">&quot;Collection:&quot;</span><span class="p">]</span>
+    <span class="n">key_indices</span> <span class="o">=</span> <span class="p">[</span><span class="n">parts</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys</span> <span class="k">if</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">parts</span><span class="p">]</span>
+    <span class="c1"># Break down into key-value pairs</span>
+    <span class="n">key_value_pairs</span> <span class="o">=</span> <span class="p">{}</span>
+    <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">index</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">key_indices</span><span class="p">):</span>
+        <span class="n">current_value</span> <span class="o">=</span> <span class="s2">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">parts</span><span class="p">[</span><span class="n">index</span> <span class="o">+</span> <span class="mi">1</span> <span class="p">:</span> <span class="n">index</span> <span class="o">+</span> <span class="mi">2</span><span class="p">])</span>
+        <span class="n">key_value_pairs</span><span class="o">.</span><span class="n">update</span><span class="p">(</span>
+            <span class="p">{</span>
+                <span class="s2">&quot;download_link&quot;</span>
+                <span class="k">if</span> <span class="n">parts</span><span class="p">[</span><span class="n">index</span><span class="p">][:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s2">&quot;version&quot;</span>
+                <span class="k">else</span> <span class="n">parts</span><span class="p">[</span><span class="n">index</span><span class="p">][:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">():</span> <span class="n">current_value</span>
+            <span class="p">}</span>
+        <span class="p">)</span>
+    <span class="k">return</span> <span class="n">key_value_pairs</span></div>
+
 </pre></div>
 
            </div>

genindex.html

@@ -271,6 +271,8 @@ <h2 id="P">P</h2>
         <li><a href="pandasaurus_cxg/utils/exception.html#module-pandasaurus_cxg.utils.exceptions">module</a>
 </li>
       </ul></li>
+      <li><a href="pandasaurus_cxg/graph_generator/graph_generator_utils.html#pandasaurus_cxg.graph_generator.graph_generator_utils.parse_citation_field_into_dict">parse_citation_field_into_dict() (in module pandasaurus_cxg.graph_generator.graph_generator_utils)</a>
+</li>
   </ul></td>
 </tr></table>
 

pandasaurus_cxg/graph_generator/graph_generator_utils.html

@@ -134,6 +134,24 @@ <h2>Documentation<a class="headerlink" href="#documentation" title="Link to this
 </dl>
 </dd></dl>
 
+<dl class="py function">
+<dt class="sig sig-object py" id="pandasaurus_cxg.graph_generator.graph_generator_utils.parse_citation_field_into_dict">
+<span class="sig-prename descclassname"><span class="pre">pandasaurus_cxg.graph_generator.graph_generator_utils.</span></span><span class="sig-name descname"><span class="pre">parse_citation_field_into_dict</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="../../_modules/pandasaurus_cxg/graph_generator/graph_generator_utils.html#parse_citation_field_into_dict"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#pandasaurus_cxg.graph_generator.graph_generator_utils.parse_citation_field_into_dict" title="Link to this definition"></a></dt>
+<dd><p>Parses a citation string into a dictionary by extracting key citation fields.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters<span class="colon">:</span></dt>
+<dd class="field-odd"><p><strong>value</strong> – The string containing citation fields and values.</p>
+</dd>
+<dt class="field-even">Returns<span class="colon">:</span></dt>
+<dd class="field-even"><p><dl class="simple">
+<dt>A dictionary with keys such as ‘Publication’, ‘Dataset Version’, and ‘Collection’,</dt><dd><p>and corresponding values extracted from the input string.</p>
+</dd>
+</dl>
+</p>
+</dd>
+</dl>
+</dd></dl>
+
 </section>
 </section>