diff two text files line-by-line in java without loading entire file in memory

DiffTextFilesUtil.java

import com.google.common.collect.Sets;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.LineIterator;

import java.io.File;
import java.io.IOException;
import java.util.HashSet;
import java.util.Set;

public class DiffTextFilesUtil {
  static public int CHUNK_SIZE = 100000;

  static public class DiffResult {
    public Set<String> addedVals = new HashSet<>();
    public Set<String> removedVals = new HashSet<>();
  }

  /**
   * Gets diff result of two sorted files with each other.
   * @param lhs left hand file - sort this using com.google.code.externalsortinginjava:externalsortinginjava:0.2.5
   * @param rhs right hand file - sort this using com.google.code.externalsortinginjava:externalsortinginjava:0.2.5
   * @return DiffResult.addedVals were added from lhs to rhs. DiffResult.removedVals were removed from lhs to rhs.
   * @throws IOException
   */
  public static DiffResult diff(File lhs, File rhs) throws IOException {

    DiffResult diffResult = new DiffResult();

    LineIterator lhsIter = FileUtils.lineIterator(lhs);
    LineIterator rhsIter = FileUtils.lineIterator(rhs);

    String lhsTop = null;
    String rhsTop = null;
    while (lhsIter.hasNext()) {
      int ct = CHUNK_SIZE;

      Set<String> setLhs = Sets.newHashSet();
      Set<String> setRhs = Sets.newHashSet();
      while (lhsIter.hasNext() && --ct > 0) {
        lhsTop = lhsIter.nextLine();
        setLhs.add(lhsTop);
      }
      while (rhsIter.hasNext()) {
        if (rhsTop != null && rhsTop.compareTo(lhsTop) > 0) {
          break;
        } else if (rhsTop != null && rhsTop.compareTo(lhsTop) == 0) {
          setRhs.add(rhsTop);
          rhsTop = null;
          break;
        } else if (rhsTop != null) {
          setRhs.add(rhsTop);
        }
        rhsTop = rhsIter.next();
      }
      if (rhsTop != null) {
        setRhs.add(rhsTop);
      }
      Sets.difference(setLhs, setRhs).copyInto(diffResult.removedVals);
      Sets.difference(setRhs, setLhs).copyInto(diffResult.addedVals);
    }
    return diffResult;
  }
}

DiffTextFilesUtilTest.java

import com.google.common.collect.Lists;
import org.apache.commons.io.FileUtils;
import org.junit.Assert;
import org.junit.Test;

import java.io.File;
import java.util.List;

public class DiffTextFilesUtilTest {
  @Test
  public void testDiffTextFiles() throws Exception {

    List<String> strsLhs = Lists.newArrayList();

    for (int i=0; i<20000; ++i) {
      strsLhs.add(String.format("val%06d", i));
    }

    List<String> strsRhs = Lists.newArrayList();

    for (int i=0; i<20000; ++i) {
      if (i % 25 == 0) {
        strsRhs.add(String.format("val%06dxx", i));
      } else if (i % 33 != 0) {
        strsRhs.add(String.format("val%06d", i));
      }
    }

    File tmp1 = File.createTempFile("tempfile-lhs", ".csv");
    File tmp2 = File.createTempFile("tempfile-rhs", ".csv");

    FileUtils.writeLines(tmp1, strsLhs);
    FileUtils.writeLines(tmp2, strsRhs);

    DiffTextFilesUtil.DiffResult diffResult = DiffTextFilesUtil.diff(
      tmp1,
      tmp2);

    Assert.assertEquals(diffResult.addedVals.size(), 800);

    for (String addedVal : diffResult.addedVals) {
      Assert.assertTrue(addedVal.contains("xx"));
      addedVal = addedVal.replace("val", "");
      addedVal = addedVal.replace("xx", "");
      int remValInt = Integer.parseInt(addedVal);
      Assert.assertEquals(remValInt + " % 25 == " + remValInt % 25 + " should be 0 ", remValInt % 25, 0);
    }

    Assert.assertEquals(diffResult.removedVals.size(), 1382);

    for (String remVal : diffResult.removedVals) {
      remVal = remVal.replace("val", "");
      int remValInt = Integer.parseInt(remVal);
      if (remValInt % 25 != 0) {
        Assert.assertEquals(remVal + " % 33 == " + remValInt % 33 + " should be 0 ", remValInt % 33, 0);
      }
    }
  }
}