From 5f3fb9afece2125cbeba79d61a8d88460b7878d7 Mon Sep 17 00:00:00 2001
From: Joshua Rahm <joshua.rahm@colorado.edu>
Date: Tue, 27 Jan 2015 18:40:32 -0700
Subject: initial commit

---
 .../src/com/modulus/common/strings/Tokenizer.java  | 48 ++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 project/JavaCommon/src/com/modulus/common/strings/Tokenizer.java

(limited to 'project/JavaCommon/src/com/modulus/common/strings/Tokenizer.java')

diff --git a/project/JavaCommon/src/com/modulus/common/strings/Tokenizer.java b/project/JavaCommon/src/com/modulus/common/strings/Tokenizer.java
new file mode 100644
index 0000000..80363cd
--- /dev/null
+++ b/project/JavaCommon/src/com/modulus/common/strings/Tokenizer.java
@@ -0,0 +1,48 @@
+package com.modulus.common.strings;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+/**
+ * Class that tokenizes strings based on which groups
+ * the characters fit into.
+ * 
+ * If the group is -1, then that tells the tokenizer to
+ * not include those tokens and instead delete the characters
+ * that belong to that group in the process of splitting.
+ * 
+ * @author jrahm
+ *
+ */
+public abstract class Tokenizer {
+	
+	public String[] tokenize(String str){
+		if(str.length() == 0)
+			return new String[]{};
+		
+		List<String> tokens = new ArrayList<String>();
+		StringBuffer buffer = new StringBuffer();
+		
+		int curGroup = groupOf(str.charAt(0));
+		for(int i = 0;i < str.length();i++){
+			char ch = str.charAt(i);
+			
+			int temp = groupOf(ch);
+			if(temp != curGroup && curGroup != -1){
+				curGroup = temp;
+				tokens.add(buffer.toString());
+				
+				buffer = new StringBuffer();
+			}
+			
+			if(temp != -1)
+				buffer.append(ch);
+		}
+		tokens.add(buffer.toString());
+		
+		return tokens.toArray(new String[tokens.size()]);
+	}
+	
+	public abstract int groupOf(char ch);
+}
-- 
cgit