Adding corpus tests, which take roughly 35 minutes to run, but which …

…pass

bayes/pom.xml

@@ -1,37 +1,54 @@
-<?xml version="1.0"?>
-<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"
-         xmlns="http://maven.apache.org/POM/4.0.0"
-         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
-    <modelVersion>4.0.0</modelVersion>
-    <parent>
-        <artifactId>ml-parent</artifactId>
-        <groupId>com.enigmastation.ml</groupId>
-        <version>4.0-SNAPSHOT</version>
-    </parent>
-    <groupId>com.enigmastation.ml</groupId>
-    <artifactId>bayes</artifactId>
-    <version>4.0-SNAPSHOT</version>
-    <name>bayes</name>
-    <url>http://maven.apache.org</url>
-    <properties>
-        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-    </properties>
-    <dependencies>
-        <dependency>
-            <groupId>org.testng</groupId>
-            <artifactId>testng</artifactId>
-            <version>6.3.1</version>
-            <scope>test</scope>
-        </dependency>
-        <dependency>
-            <groupId>org.apache.lucene</groupId>
-            <artifactId>lucene-analyzers</artifactId>
-            <version>3.4.0</version>
-        </dependency>
-        <dependency>
-            <groupId>${parent.groupId}</groupId>
-            <artifactId>common</artifactId>
-            <version>${project.version}</version>
-        </dependency>
-    </dependencies>
-</project>
+<?xml version="1.0"?>
+<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"
+         xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+    <modelVersion>4.0.0</modelVersion>
+    <parent>
+        <artifactId>ml-parent</artifactId>
+        <groupId>com.enigmastation.ml</groupId>
+        <version>4.0-SNAPSHOT</version>
+    </parent>
+    <groupId>com.enigmastation.ml</groupId>
+    <artifactId>bayes</artifactId>
+    <version>4.0-SNAPSHOT</version>
+    <name>bayes</name>
+    <url>http://maven.apache.org</url>
+    <properties>
+        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    </properties>
+    <dependencies>
+        <!-- testing dependencies -->
+        <dependency>
+            <groupId>org.testng</groupId>
+            <artifactId>testng</artifactId>
+            <version>6.3.1</version>
+            <scope>test</scope>
+        </dependency>
+        <!-- I like javatar's tar archive much better than commons-compress' -->
+        <dependency>
+            <groupId>javatar</groupId>
+            <artifactId>javatar</artifactId>
+            <version>[2.5,)</version>
+            <scope>test</scope>
+        </dependency>
+        <!-- however, commons-compress has a much more clear BZip2 inputstream than ant does-->
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-compress</artifactId>
+            <version>1.2</version>
+            <scope>test</scope>
+        </dependency>
+
+        <!-- runtime dependencies -->
+        <dependency>
+            <groupId>org.apache.lucene</groupId>
+            <artifactId>lucene-analyzers</artifactId>
+            <version>3.4.0</version>
+        </dependency>
+        <dependency>
+            <groupId>${parent.groupId}</groupId>
+            <artifactId>common</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+    </dependencies>
+</project>

bayes/src/main/java/com/enigmastation/ml/bayes/impl/ThreadLocalMemoizer.java

@@ -0,0 +1,11 @@
+package com.enigmastation.ml.bayes.impl;
+
+/**
+ * Created by IntelliJ IDEA.
+ * User: joeo
+ * Date: 1/31/12
+ * Time: 9:26 AM
+ * To change this template use File | Settings | File Templates.
+ */
+public class ThreadLocalMemoizer {
+}

bayes/src/test/java/com/enigmastation/ml/bayes/CorpusTest.java

@@ -0,0 +1,11 @@
+package com.enigmastation.ml.bayes;
+
+/**
+ * Created by IntelliJ IDEA.
+ * User: joeo
+ * Date: 1/31/12
+ * Time: 6:01 AM
+ * To change this template use File | Settings | File Templates.
+ */
+public class CorpusTest {
+}