Convert curly quotes

src/com/jgaap/canonicizers/ConvertCurlyQuotes.java

@@ -0,0 +1,80 @@
+/*
+ * JGAAP -- a graphical program for stylometric authorship attribution
+ * Copyright (C) 2009,2011 by Patrick Juola
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+package com.jgaap.canonicizers;
+
+import com.jgaap.generics.Canonicizer;
+
+/**
+ * Converts Typographical quotes to the standard straight quotes in an attempt to standardize all
+ * quotation marks.
+ */
+public class ConvertCurlyQuotes extends Canonicizer{
+    @Override
+	public String displayName() {
+		return "Convert Curly Quotes";
+	}
+
+    @Override
+	public String tooltipText() {
+		return "Converts Curly Quotes (Smart Quotes) into nonslanted marks to standardize them.";
+	}
+
+	@Override
+	public String longDescription() {
+		return "Converts Curly Quotes (Smart Quotes) into nonslanted marks to standardize them. Curly Quotes typically in Word and PDF Documents.";
+	}
+
+	@Override
+	public boolean showInGUI() {
+		return true;
+	}
+
+    /**
+	 * Strip punctuation from input characters
+	 * 
+	 * @param procText
+	 *            array of characters to be processed.
+	 * @return array of processed characters.
+	 */
+	@Override
+	public char[] process(char[] procText) {
+		try{
+        	char curly_double1 = '\u201d';
+			char curly_double2 = '\u201c';
+			char curly_single1 = '\u2018';
+			char curly_single2 = '\u2019';
+			char target_single = '\'';
+			for(int i = 0; i < procText.length; i++){
+				//check for "Curly" quotes
+				if(procText[i] == curly_double1 || procText[i] == curly_double2){
+					procText[i] = '\u0022';
+				}
+				else if(procText[i] == curly_single1 || procText[i] == curly_single2){
+					procText[i] = target_single;
+				}
+
+			}
+			return procText;
+		}catch (Exception e){
+			return procText;
+		}
+
+
+	}
+}

src/com/jgaap/resources/abbreviation.list

@@ -2,4 +2,6 @@ Dr
 Miss
 Mr
 Mrs
-etc
+etc
+
+

unittests/com/jgaap/canonicizers/ConvertCurlyQuotesTest.java

@@ -0,0 +1,79 @@
+/*
+ * JGAAP -- a graphical program for stylometric authorship attribution
+ * Copyright (C) 2009,2011 by Patrick Juola
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+/**
+ * 
+ */
+
+package com.jgaap.canonicizers;
+
+import static org.junit.Assert.*;
+
+import java.nio.charset.Charset;
+import java.util.Arrays;
+
+import org.junit.Test;
+
+public class ConvertCurlyQuotesTest {
+
+    /**
+	 * Test method for
+	 * {@link com.jgaap.canonicizers.ConvertCurlyQuotes#process(char[])}
+	 * .
+	 */
+
+     @Test
+     public void testProcess(){
+        String example = "Here\u2019s a sentence with curly single quotes: \u2018Hello!\u2019 and straight single quotes: 'World'. " +
+                         "Also, curly double quotes: \u201CThis is a test.\u201D and straight double quotes: \"Another test.\" " +
+                         "Let\u2019s see how they appear when printed!";
+        char[] sample = example.toCharArray();
+        String expected_text = "Here's a sentence with curly single quotes: 'Hello!' and straight single quotes: 'World'. " +
+                          "Also, curly double quotes: \"This is a test.\" and straight double quotes: \"Another test.\" " + 
+                          "Let's see how they appear when printed!";
+        char[] expected = expected_text.toCharArray();
+        ConvertCurlyQuotes canon = new ConvertCurlyQuotes();
+
+        String[] encodings_that_support_curly_quotes = {
+            "GB2312",
+            "UTF-8",
+            "UTF-16"
+        };
+
+        for (String encoding : encodings_that_support_curly_quotes){
+            try{
+                // Convert the string to a byte array using the specified encoding
+				byte[] encodedBytes = example.getBytes(Charset.forName(encoding));
+
+				// Decode the byte array back into a string using the same encoding
+				String decodedText = new String(encodedBytes, Charset.forName(encoding));
+
+				// Convert the decoded text into a char array
+				char[] procText = decodedText.toCharArray();
+                char[] result = canon.process(procText);
+                assertTrue(Arrays.equals(expected, result));
+
+            }catch(Exception e){
+                System.out.println("Encoding conversion did not work for " + encoding);
+            }
+        }
+
+     }
+
+
+
+}