add corpus parsing

corpus/src/main/java/com/dfsek/corpus/Read.java

@@ -0,0 +1,40 @@
+package com.dfsek.corpus;
+
+import io.vavr.collection.HashMap;
+import io.vavr.collection.List;
+import io.vavr.collection.Map;
+import io.vavr.collection.Stream;
+import org.apache.commons.io.IOUtils;
+
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.StringReader;
+import java.nio.charset.Charset;
+import java.util.Scanner;
+
+import static io.vavr.API.*;
+
+public class Read {
+    public static void main(String... args) throws IOException {
+        System.out.println("Parsing probabilities...");
+        String corpus = IOUtils.resourceToString("/corpus.8vim", Charset.defaultCharset());
+        long st = System.nanoTime();
+        Map<String, List<String>> probabilities = parseCorpus(corpus);
+        long e = System.nanoTime();
+        long diff = e - st;
+        System.out.println("Done (" + ((double) diff / 1000000) + "ms).");
+
+        Scanner s = new Scanner(System.in);
+        while (true) {
+            System.out.print("Start: ");
+            String start = s.nextLine();
+            System.out.println(probabilities.get(start));
+        }
+    }
+
+    private static Map<String, List<String>> parseCorpus(String in) {
+        return Stream.ofAll(new BufferedReader(new StringReader(in)).lines())
+                .map(s -> Tuple(s.substring(0, s.indexOf(':')), s.substring(s.indexOf(':'))))
+                .foldLeft(HashMap.empty(), (run, tup) -> run.put(tup._1(), List(tup._2()), List::appendAll));
+    }
+}