Mpo parser

CHANGELOG.rst

@@ -2,6 +2,13 @@
 Changelog
 =========
 
+----
+v0.4
+----
+
+- Disabling ``mv_store`` feature of H2.
+- Fixing various bugs in ``H2ScoreDistributionReader`` and ``H2ScoreDistributionWriter``.
+
 ----
 v0.3
 ----

README.md

@@ -11,14 +11,14 @@ A modern Java library for working with (biological) ontologies.
 
 - **Language/Platform:** Java >=8
 - **License:** BSD 3-Clause Clear
-- **Version:** 0.3
+- **Version:** 0.4
 - **Authors:**
     - Sebastian Bauer
     - Peter N. Robinson
     - Sebastian Koehler
     - Max Schubach
     - Manuel Holtgrewe
 - **Availability:**
-    - Maven module `ontolib-core` for dealing with (biological) ontologies ([Javadoc via javadoc.io](http://javadoc.io/doc/com.github.phenomics/ontolib-core/0.3)).
-    - Maven module `ontolib-io` for reading ontologies from OBO files ([Javadoc via javadoc.io](http://javadoc.io/doc/com.github.phenomics/ontolib-io/0.3)).
+    - Maven module `ontolib-core` for dealing with (biological) ontologies ([Javadoc via javadoc.io](http://javadoc.io/doc/com.github.phenomics/ontolib-core/0.4)).
+    - Maven module `ontolib-io` for reading ontologies from OBO files ([Javadoc via javadoc.io](http://javadoc.io/doc/com.github.phenomics/ontolib-io/0.4)).
     - Maven module `ontolib-cli` for performing empirical score distribution computation as a stand-alone program.

ontolib-cli/pom.xml

@@ -57,7 +57,7 @@
     <resources>
       <resource>
         <directory>src/main/resources</directory>
-        <!--Use filtering so that maven will replace placeholders with values 
+        <!--Use filtering so that maven will replace placeholders with values
           from the pom e.g. ${project.version} -->
         <filtering>true</filtering>
       </resource>
@@ -73,7 +73,7 @@
             <manifest>
               <addClasspath>true</addClasspath>
               <classpathPrefix>lib/</classpathPrefix>
-              <!-- set useUniqueVersions=false in order that the classpath 
+              <!-- set useUniqueVersions=false in order that the classpath
                 has the SNAPSHOT instead of the build number prefixed to the dependency -->
               <useUniqueVersions>false</useUniqueVersions>
               <mainClass>com.github.phenomics.ontolib.cli.Main</mainClass>
@@ -105,7 +105,7 @@
           </execution>
         </executions>
       </plugin>
-      <!-- Specify the resources which need to be made accessible to the 
+      <!-- Specify the resources which need to be made accessible to the
         user -->
       <plugin>
         <artifactId>maven-resources-plugin</artifactId>
@@ -122,7 +122,7 @@
               <resources>
                 <resource>
                   <directory>src/resources</directory>
-                  <!--Use filtering so that maven will replace placeholders 
+                  <!--Use filtering so that maven will replace placeholders
                     with values from the pom e.g. ${project.version} -->
                   <filtering>true</filtering>
                   <includes>
@@ -137,7 +137,7 @@
           </execution>
         </executions>
       </plugin>
-      <!--This plugin assembles the various elements together into a redistributable 
+      <!--This plugin assembles the various elements together into a redistributable
         zip/tar.gz file -->
       <plugin>
         <artifactId>maven-assembly-plugin</artifactId>

ontolib-core/pom.xml

@@ -22,7 +22,7 @@
     <resources>
       <resource>
         <directory>src/main/resources</directory>
-        <!--Use filtering so that maven will replace placeholders with values 
+        <!--Use filtering so that maven will replace placeholders with values
           from the pom e.g. ${project.version} -->
         <filtering>true</filtering>
       </resource>
@@ -51,7 +51,7 @@
         </executions>
       </plugin>
 
-      <!-- Specify the resources which need to be made accessible to the 
+      <!-- Specify the resources which need to be made accessible to the
         user -->
       <plugin>
         <artifactId>maven-resources-plugin</artifactId>
@@ -68,7 +68,7 @@
               <resources>
                 <resource>
                   <directory>src/main/resources</directory>
-                  <!--Use filtering so that maven will replace placeholders 
+                  <!--Use filtering so that maven will replace placeholders
                     with values from the pom e.g. ${project.version} -->
                   <filtering>true</filtering>
                   <includes>

ontolib-io/pom.xml

@@ -45,7 +45,7 @@
     <resources>
       <resource>
         <directory>src/main/resources</directory>
-        <!--Use filtering so that maven will replace placeholders with values 
+        <!--Use filtering so that maven will replace placeholders with values
           from the pom e.g. ${project.version} -->
         <filtering>true</filtering>
       </resource>
@@ -109,7 +109,7 @@
         </executions>
       </plugin>
 
-      <!-- Specify the resources which need to be made accessible to the 
+      <!-- Specify the resources which need to be made accessible to the
         user -->
       <plugin>
         <artifactId>maven-resources-plugin</artifactId>
@@ -126,7 +126,7 @@
               <resources>
                 <resource>
                   <directory>src/main/resources</directory>
-                  <!--Use filtering so that maven will replace placeholders 
+                  <!--Use filtering so that maven will replace placeholders
                     with values from the pom e.g. ${project.version} -->
                   <filtering>true</filtering>
                   <includes>

ontolib-io/src/main/java/com/github/phenomics/ontolib/io/obo/mpo/MpoOboFactory.java

@@ -140,7 +140,7 @@ public MpoTerm constructTerm(Stanza stanza) {
     final String creationDateStr =
         (creationDateEntry == null) ? null : creationDateEntry.getValue();
 
-    final SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS'Z'");
+    final SimpleDateFormat format = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss'Z'");
     Date creationDate = null;
     if (creationDateStr != null) {
       try {

ontolib-io/src/main/java/com/github/phenomics/ontolib/io/scoredist/H2ScoreDistributionReader.java

@@ -39,15 +39,15 @@ public class H2ScoreDistributionReader implements ScoreDistributionReader {
   private final Connection conn;
 
   /** H2 query for selecting all term counts. */
-  private final static String H2_SELECT_TERM_COUNTS = "SELECT DISTINCT (term_count) from %s";
+  private final static String H2_SELECT_TERM_COUNTS = "SELECT DISTINCT (num_terms) from %s";
 
   /** H2 query for selecting by term count. */
   private final static String H2_SELECT_BY_TERM_COUNT_STATEMENT =
-      "SELECT (term_count, object_id, scores, p_values) FROM % WHERE (term_count = ?)";
+      "SELECT num_terms, entrez_id, sample_size, scores, p_values FROM %s WHERE (num_terms = ?)";
 
   /** H2 query for selecting by term count and object ID. */
   private final static String H2_SELECT_BY_TERM_COUNT_AND_OBJECT_STATEMENT =
-      "SELECT (term_count, object_id, scores, p_values) FROM % WHERE (term_count = ? AND object_id = ?)";
+      "SELECT num_terms, entrez_id, sample_size, scores, p_values FROM %s WHERE (num_terms = ? AND entrez_id = ?)";
 
   /**
    * Create new reader object.
@@ -74,7 +74,8 @@ private Connection openConnection() throws OntoLibException {
     final Connection result;
     try {
       Class.forName("org.h2.Driver");
-      result = DriverManager.getConnection("jdbc:h2:" + pathDb, "", "");
+      result = DriverManager
+          .getConnection("jdbc:h2:" + pathDb + ";ACCESS_MODE_DATA=r;mv_store=false", "", "");
     } catch (ClassNotFoundException e) {
       throw new OntoLibException("H2 driver class could not be found", e);
     } catch (SQLException e) {
@@ -110,7 +111,7 @@ public ObjectScoreDistribution readForTermCountAndObject(int termCount, int obje
       }
     } catch (SQLException e) {
       throw new OntoLibException("Problem with getting object score distribution for termCount: "
-          + termCount + ", objectId: " + objectId);
+          + termCount + ", objectId: " + objectId, e);
     }
 
     throw new OntoLibException(

ontolib-io/src/main/java/com/github/phenomics/ontolib/io/scoredist/H2ScoreDistributionWriter.java

@@ -87,7 +87,7 @@ private Connection openConnection(boolean resetTableIfExists) throws OntoLibExce
     final Connection resultConn;
     try {
       Class.forName("org.h2.Driver");
-      resultConn = DriverManager.getConnection("jdbc:h2:" + pathDb, "", "");
+      resultConn = DriverManager.getConnection("jdbc:h2:" + pathDb + ";mv_store=false", "", "");
     } catch (ClassNotFoundException e) {
       throw new OntoLibException("H2 driver class could not be found", e);
     } catch (SQLException e) {
@@ -190,6 +190,7 @@ private void writeObjectScoreDistribution(int numTerms, ObjectScoreDistribution
       for (Entry<Double, Double> e : dist.getCumulativeFrequencies().entrySet()) {
         scores[i] = e.getKey();
         pValues[i] = e.getValue();
+        i += 1;
       }
     }
 

pom.xml

@@ -4,7 +4,7 @@
   <groupId>com.github.phenomics</groupId>
   <artifactId>OntoLib</artifactId>
   <packaging>pom</packaging>
-  <version>0.3</version>
+  <version>0.5-SNAPSHOT</version>
 
   <name>${project.groupId}:${project.artifactId}</name>
   <description>OntoLib contains data structures and algorithms for processing ontologies.</description>