a solution to parsing CSV records that contain embedded commas in quotes
I've seen so many people looking to use StringTokenizer or Split to parse a quoted CSV file, only to fail to handle embedded ','s in quoted fields. So i'm throwing in my 2-cents with my solution that anyone can use freely.
It's small, comes with a little test program and utilizes the String.split function.
Enjoy,
Todd Blackley
tblackley@att.net
www.pawsource.org
/*
Copyright (c) 2005 Todd Blackley
The above copyright notice shall be included in all copies or substantial
portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
*/
package com.pawsource.model;
import java.util.*;
public class Csv
{
publicCsv()
{}
publicvoidtest1()
{
LinkedListlist= new LinkedList();
for (int i=0;i<1000000;i++)
list.add(new String(Integer.toString(i)));
for (Iterator iter = list.iterator(); iter.hasNext();)
{
Strings = (String)iter.next();
System.out.println(s);
}
}
publicStringtoCSV(ArrayList aList)
{
StringBufferbuffer= new StringBuffer();
for (int i=0;i<aList.size();i++)
{
Stringtext = (String)aList.get(i);
booleanneedQuotes= text.indexOf(",")==-1?false:true;
if (needQuotes)buffer.append("\"");
buffer.append(text);
if (needQuotes)buffer.append("\"");
if (i><aList.size()-1)
buffer.append(",");
}
return buffer.toString();
}
publicArrayListparseCSV(String aBuffer)
{
String[]orig= aBuffer.split(",");
ArrayListtokens= new ArrayList();
intindex= 0;
while (index><orig.length)
{
if (orig[index].startsWith("\""))
{
intorigIndex= index;
tokens.add(orig[index].substring(1,orig[index].length()));
while (orig[index].endsWith("\"")==false && ++index><orig.length)
{
tokens.set(origIndex,tokens.get(origIndex)+ "," + orig[index]);
}
if (index><orig.length)
{
Stringtemp = (String)tokens.get(origIndex);
tokens.set(origIndex,temp.substring(0,temp.length()-1));
}
}
else
tokens.add(orig[index]);
index++;
}
return tokens;
}
public static void main(String[] args)
{
Csvtest = new Csv();
System.out.println("Start...");
Stringbuffer= "1,2,,4,\"5,6,7,8\",9,10";
ArrayListtokens = test.parseCSV(buffer);
for (int i=0;i<tokens.size();i++)
{
System.out.println("Token :" + tokens.get(i));
}
System.out.println("CVS :" + test.toCSV(tokens));
System.out.println("Finish...");
}
}>
