Java library for keywords extraction from input text

An updated and ready-to-use version of the code proposed above.
This code is compatible with Apache Lucene 5.x…6.x.

CardKeyword class:

import java.util.HashSet;
import java.util.Set;

/**
 * Keyword card with stem form, terms dictionary and frequency rank
 */
class CardKeyword implements Comparable<CardKeyword> {

    /**
     * Stem form of the keyword
     */
    private final String stem;

    /**
     * Terms dictionary
     */
    private final Set<String> terms = new HashSet<>();

    /**
     * Frequency rank
     */
    private int frequency;

    /**
     * Build keyword card with stem form
     *
     * @param stem
     */
    public CardKeyword(String stem) {
        this.stem = stem;
    }

    /**
     * Add term to the dictionary and update its frequency rank
     *
     * @param term
     */
    public void add(String term) {
        this.terms.add(term);
        this.frequency++;
    }

    /**
     * Compare two keywords by frequency rank
     *
     * @param keyword
     * @return int, which contains comparison results
     */
    @Override
    public int compareTo(CardKeyword keyword) {
        return Integer.valueOf(keyword.frequency).compareTo(this.frequency);
    }

    /**
     * Get stem's hashcode
     *
     * @return int, which contains stem's hashcode
     */
    @Override
    public int hashCode() {
        return this.getStem().hashCode();
    }

    /**
     * Check if two stems are equal
     *
     * @param o
     * @return boolean, true if two stems are equal
     */
    @Override
    public boolean equals(Object o) {

        if (this == o) return true;

        if (!(o instanceof CardKeyword)) return false;

        CardKeyword that = (CardKeyword) o;

        return this.getStem().equals(that.getStem());
    }

    /**
     * Get stem form of keyword
     *
     * @return String, which contains getStemForm form
     */
    public String getStem() {
        return this.stem;
    }

    /**
     * Get terms dictionary of the stem
     *
     * @return Set<String>, which contains set of terms of the getStemForm
     */
    public Set<String> getTerms() {
        return this.terms;
    }

    /**
     * Get stem frequency rank
     *
     * @return int, which contains getStemForm frequency
     */
    public int getFrequency() {
        return this.frequency;
    }
}

KeywordsExtractor class:

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.en.EnglishAnalyzer;
import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter;
import org.apache.lucene.analysis.standard.ClassicFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;

import java.io.IOException;
import java.io.StringReader;
import java.util.*;

/**
 * Keywords extractor functionality handler
 */
class KeywordsExtractor {

    /**
     * Get list of keywords with stem form, frequency rank, and terms dictionary
     *
     * @param fullText
     * @return List<CardKeyword>, which contains keywords cards
     * @throws IOException
     */
    static List<CardKeyword> getKeywordsList(String fullText) throws IOException {

        TokenStream tokenStream = null;

        try {
            // treat the dashed words, don't let separate them during the processing
            fullText = fullText.replaceAll("-+", "-0");

            // replace any punctuation char but apostrophes and dashes with a space
            fullText = fullText.replaceAll("[\\p{Punct}&&[^'-]]+", " ");

            // replace most common English contractions
            fullText = fullText.replaceAll("(?:'(?:[tdsm]|[vr]e|ll))+\\b", "");

            StandardTokenizer stdToken = new StandardTokenizer();
            stdToken.setReader(new StringReader(fullText));

            tokenStream = new StopFilter(new ASCIIFoldingFilter(new ClassicFilter(new LowerCaseFilter(stdToken))), EnglishAnalyzer.getDefaultStopSet());
            tokenStream.reset();

            List<CardKeyword> cardKeywords = new LinkedList<>();

            CharTermAttribute token = tokenStream.getAttribute(CharTermAttribute.class);

            while (tokenStream.incrementToken()) {

                String term = token.toString();
                String stem = getStemForm(term);

                if (stem != null) {
                    CardKeyword cardKeyword = find(cardKeywords, new CardKeyword(stem.replaceAll("-0", "-")));
                    // treat the dashed words back, let look them pretty
                    cardKeyword.add(term.replaceAll("-0", "-"));
                }
            }

            // reverse sort by frequency
            Collections.sort(cardKeywords);

            return cardKeywords;
        } finally {
            if (tokenStream != null) {
                try {
                    tokenStream.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    /**
     * Get stem form of the term
     *
     * @param term
     * @return String, which contains the stemmed form of the term
     * @throws IOException
     */
    private static String getStemForm(String term) throws IOException {

        TokenStream tokenStream = null;

        try {
            StandardTokenizer stdToken = new StandardTokenizer();
            stdToken.setReader(new StringReader(term));

            tokenStream = new PorterStemFilter(stdToken);
            tokenStream.reset();

            // eliminate duplicate tokens by adding them to a set
            Set<String> stems = new HashSet<>();

            CharTermAttribute token = tokenStream.getAttribute(CharTermAttribute.class);

            while (tokenStream.incrementToken()) {
                stems.add(token.toString());
            }

            // if stem form was not found or more than 2 stems have been found, return null
            if (stems.size() != 1) {
                return null;
            }

            String stem = stems.iterator().next();

            // if the stem form has non-alphanumerical chars, return null
            if (!stem.matches("[a-zA-Z0-9-]+")) {
                return null;
            }

            return stem;
        } finally {
            if (tokenStream != null) {
                try {
                    tokenStream.close();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    /**
     * Find sample in collection
     *
     * @param collection
     * @param sample
     * @param <T>
     * @return <T> T, which contains the found object within collection if exists, otherwise the initially searched object
     */
    private static <T> T find(Collection<T> collection, T sample) {

        for (T element : collection) {
            if (element.equals(sample)) {
                return element;
            }
        }

        collection.add(sample);

        return sample;
    }
}

The call of function:

String text = "…";
List<CardKeyword> keywordsList = KeywordsExtractor.getKeywordsList(text);

Here is a possible solution using Apache Lucene. I didn't use the last version but the 3.6.2 one, since this is the one I know the best. Besides the /lucene-core-x.x.x.jar, don't forget to add the /contrib/analyzers/common/lucene-analyzers-x.x.x.jar from the downloaded archive to your project: it contains the language-specific analyzers (especially the English one in your case).

Note that this will only find the frequencies of the input text words based on their respective stem. Comparing these frequencies with the English language statistics shall be done afterwards (this answer may help by the way).


The data model

One keyword for one stem. Different words may have the same stem, hence the terms set. The keyword frequency is incremented every time a new term is found (even if it has been already found - a set automatically removes duplicates).

public class Keyword implements Comparable<Keyword> {

  private final String stem;
  private final Set<String> terms = new HashSet<String>();
  private int frequency = 0;

  public Keyword(String stem) {
    this.stem = stem;
  }

  public void add(String term) {
    terms.add(term);
    frequency++;
  }

  @Override
  public int compareTo(Keyword o) {
    // descending order
    return Integer.valueOf(o.frequency).compareTo(frequency);
  }

  @Override
  public boolean equals(Object obj) {
    if (this == obj) {
      return true;
    } else if (!(obj instanceof Keyword)) {
      return false;
    } else {
      return stem.equals(((Keyword) obj).stem);
    }
  }

  @Override
  public int hashCode() {
    return Arrays.hashCode(new Object[] { stem });
  }

  public String getStem() {
    return stem;
  }

  public Set<String> getTerms() {
    return terms;
  }

  public int getFrequency() {
    return frequency;
  }

}

Utilities

To stem a word:

public static String stem(String term) throws IOException {

  TokenStream tokenStream = null;
  try {

    // tokenize
    tokenStream = new ClassicTokenizer(Version.LUCENE_36, new StringReader(term));
    // stem
    tokenStream = new PorterStemFilter(tokenStream);

    // add each token in a set, so that duplicates are removed
    Set<String> stems = new HashSet<String>();
    CharTermAttribute token = tokenStream.getAttribute(CharTermAttribute.class);
    tokenStream.reset();
    while (tokenStream.incrementToken()) {
      stems.add(token.toString());
    }

    // if no stem or 2+ stems have been found, return null
    if (stems.size() != 1) {
      return null;
    }
    String stem = stems.iterator().next();
    // if the stem has non-alphanumerical chars, return null
    if (!stem.matches("[a-zA-Z0-9-]+")) {
      return null;
    }

    return stem;

  } finally {
    if (tokenStream != null) {
      tokenStream.close();
    }
  }

}

To search into a collection (will be used by the list of potential keywords):

public static <T> T find(Collection<T> collection, T example) {
  for (T element : collection) {
    if (element.equals(example)) {
      return element;
    }
  }
  collection.add(example);
  return example;
}

Core

Here is the main input method:

public static List<Keyword> guessFromString(String input) throws IOException {

  TokenStream tokenStream = null;
  try {

    // hack to keep dashed words (e.g. "non-specific" rather than "non" and "specific")
    input = input.replaceAll("-+", "-0");
    // replace any punctuation char but apostrophes and dashes by a space
    input = input.replaceAll("[\\p{Punct}&&[^'-]]+", " ");
    // replace most common english contractions
    input = input.replaceAll("(?:'(?:[tdsm]|[vr]e|ll))+\\b", "");

    // tokenize input
    tokenStream = new ClassicTokenizer(Version.LUCENE_36, new StringReader(input));
    // to lowercase
    tokenStream = new LowerCaseFilter(Version.LUCENE_36, tokenStream);
    // remove dots from acronyms (and "'s" but already done manually above)
    tokenStream = new ClassicFilter(tokenStream);
    // convert any char to ASCII
    tokenStream = new ASCIIFoldingFilter(tokenStream);
    // remove english stop words
    tokenStream = new StopFilter(Version.LUCENE_36, tokenStream, EnglishAnalyzer.getDefaultStopSet());

    List<Keyword> keywords = new LinkedList<Keyword>();
    CharTermAttribute token = tokenStream.getAttribute(CharTermAttribute.class);
    tokenStream.reset();
    while (tokenStream.incrementToken()) {
      String term = token.toString();
      // stem each term
      String stem = stem(term);
      if (stem != null) {
        // create the keyword or get the existing one if any
        Keyword keyword = find(keywords, new Keyword(stem.replaceAll("-0", "-")));
        // add its corresponding initial token
        keyword.add(term.replaceAll("-0", "-"));
      }
    }

    // reverse sort by frequency
    Collections.sort(keywords);

    return keywords;

  } finally {
    if (tokenStream != null) {
      tokenStream.close();
    }
  }

}

Example

Using the guessFromString method on the Java wikipedia article introduction part, here are the first 10 most frequent keywords (i.e. stems) that were found:

java         x12    [java]
compil       x5     [compiled, compiler, compilers]
sun          x5     [sun]
develop      x4     [developed, developers]
languag      x3     [languages, language]
implement    x3     [implementation, implementations]
applic       x3     [application, applications]
run          x3     [run]
origin       x3     [originally, original]
gnu          x3     [gnu]

Iterate over the output list to know which were the original found words for each stem by getting the terms sets (displayed between brackets [...] in the above example).


What's next

Compare the stem frequency / frequencies sum ratios with the English language statistics ones, and keep me in the loop if your managed it: I could be quite interested too :)