From 879deb56f0666e66e0075df510f6a779373243d5 Mon Sep 17 00:00:00 2001
From: Peter Wu <peter@lekensteyn.nl>
Date: Thu, 15 May 2014 16:08:11 +0200
Subject: Lowercase bigrams and unigrams

---
 src/main/Analyzor.java | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'src')

diff --git a/src/main/Analyzor.java b/src/main/Analyzor.java
index 0fe880a..00e3442 100644
--- a/src/main/Analyzor.java
+++ b/src/main/Analyzor.java
@@ -41,7 +41,8 @@ public class Analyzor {
                 Scanner biScanner = new Scanner("bigrams-pmilexicon.txt");) {
             //Fill the map of unigrams
             while (uniScanner.hasNext()) {
-                unimap.put(uniScanner.next(), uniScanner.nextDouble());
+                String words = uniScanner.next();
+                unimap.put(words.toLowerCase(), uniScanner.nextDouble());
                 if (uniScanner.hasNextLine()) {
                     uniScanner.nextLine();
                 }
@@ -49,7 +50,8 @@ public class Analyzor {
 
             //fill the map of bigrams
             while (biScanner.hasNext()) {
-                bimap.put(biScanner.next() + " " + biScanner.next(), biScanner.nextDouble());
+                String words = biScanner.next() + " " + biScanner.next();
+                bimap.put(words.toLowerCase(), biScanner.nextDouble());
                 if (biScanner.hasNextLine()) {
                     biScanner.nextLine();
                 }
-- 
cgit v1.2.1