Analyzer: cleanup, documentation, do not re-read lexicon file

1 files changed, 24 insertions, 31 deletions

diff --git a/src/main/Analyzor.java b/src/main/Analyzor.java
index cf01563..0fe880a 100644
--- a/src/main/Analyzor.java
+++ b/src/main/Analyzor.java
@@ -1,13 +1,7 @@
-/*

- * To change this license header, choose License Headers in Project Properties.

- * To change this template file, choose Tools | Templates

- * and open the template in the editor.

- */

 package main;

 

 import database.NamedPreparedStatement;

 import database.QueryUtils;

-import java.io.File;

 import java.io.FileNotFoundException;

 import java.io.IOException;

 import java.sql.Connection;

@@ -16,18 +10,15 @@ import java.sql.ResultSet;
 import java.sql.SQLException;

 import java.util.HashMap;

 import java.util.Scanner;

-import java.util.logging.Level;

-import java.util.logging.Logger;

 

 /**

- *

- * @author s123188

+ * Analyze tweets with a lexicon.

  */

 public class Analyzor {

 

     //maps for the lexicons

-    HashMap<String, Double> unimap = new HashMap<String, Double>(); // Map for uni

-    HashMap<String, Double> bimap = new HashMap<String, Double>(); // Map for bi

+    HashMap<String, Double> unimap = new HashMap<>(); // Map for uni

+    HashMap<String, Double> bimap = new HashMap<>(); // Map for bi

 

     //the resultset of the query or the import

     ResultSet data;

@@ -39,26 +30,29 @@ public class Analyzor {
 

     //reads the lexicons

     void readLexicon() throws FileNotFoundException {

-

-        File uniFile = new File("unigrams-pmilexicon.txt"); // get uni

-        File biFile = new File("bigrams-pmilexicon.txt"); // get bi

-

-        Scanner uniScanner = new Scanner(uniFile);

-        Scanner biScanner = new Scanner(biFile);

-

-        //Fill the map of unigrams

-        while (uniScanner.hasNext()) {

-            unimap.put(uniScanner.next(), Double.parseDouble(uniScanner.next()));

-            if (uniScanner.hasNextLine()) {

-                uniScanner.nextLine();

-            }

+        if (!unimap.isEmpty()) {

+            // data is already read.

+            return;

         }

+        // A unigram is in the format (WS = whitespace):

+        // word <WS> rating <WS> ??? <WS> ??

+        // A bigram has an two WS-separated words instead of one.

+        try (Scanner uniScanner = new Scanner("unigrams-pmilexicon.txt");

+                Scanner biScanner = new Scanner("bigrams-pmilexicon.txt");) {

+            //Fill the map of unigrams

+            while (uniScanner.hasNext()) {

+                unimap.put(uniScanner.next(), uniScanner.nextDouble());

+                if (uniScanner.hasNextLine()) {

+                    uniScanner.nextLine();

+                }

+            }

 

-        //fill the map of bigrams

-        while (biScanner.hasNext()) {

-            bimap.put(biScanner.next() + " " + biScanner.next(), Double.parseDouble(biScanner.next()));

-            if (biScanner.hasNextLine()) {

-                biScanner.nextLine();

+            //fill the map of bigrams

+            while (biScanner.hasNext()) {

+                bimap.put(biScanner.next() + " " + biScanner.next(), biScanner.nextDouble());

+                if (biScanner.hasNextLine()) {

+                    biScanner.nextLine();

+                }

             }

         }

     }

@@ -66,7 +60,6 @@ public class Analyzor {
     //query the database

     //fills the ResultSet data

     void query(String query) throws SQLException {

-

         PreparedStatement statement;

         //make a connection to the database and execute the query

         statement = connection.prepareStatement(query);