Java Code Examples for org.apache.lucene.index.Term#field()

@CheckForNull
@Override
@SuppressWarnings("StringEquality")
public Void convert(@NonNull final Index.WithTermFrequencies.TermFreq param) throws Stop {
    final Term term = param.getTerm();
    if (fieldName != term.field()) {
        throw new Stop();
    }
    final int docCount = param.getFreq();
    final String encBinName = term.text();
    final String binName = encBinName.substring(
        0,
        encBinName.length() - postfixLen);
    final int dotIndex = binName.lastIndexOf('.');  //NOI18N
    final String pkgName = dotIndex == -1 ? "" : binName.substring(0, dotIndex);    //NOI18N
    final Integer typeCount = typeFreq.get(binName);
    final Integer pkgCount = pkgFreq.get(pkgName);
    typeFreq.put(binName, typeCount == null ? docCount : docCount + typeCount);
    pkgFreq.put(pkgName, pkgCount == null ? docCount : docCount + pkgCount);
    return null;
}
 

/**
 * Create a new FuzzyQuery that will match terms with an edit distance 
 * of at most <code>maxEdits</code> to <code>term</code>.
 * If a <code>prefixLength</code> &gt; 0 is specified, a common prefix
 * of that length is also required.
 * 
 * @param term the term to search for
 * @param maxEdits must be {@code >= 0} and {@code <=} {@link LevenshteinAutomata#MAXIMUM_SUPPORTED_DISTANCE}.
 * @param prefixLength length of common (non-fuzzy) prefix
 * @param maxExpansions the maximum number of terms to match. If this number is
 *  greater than {@link IndexSearcher#getMaxClauseCount} when the query is rewritten,
 *  then the maxClauseCount will be used instead.
 * @param transpositions true if transpositions should be treated as a primitive
 *        edit operation. If this is false, comparisons will implement the classic
 *        Levenshtein algorithm.
 */
public FuzzyQuery(Term term, int maxEdits, int prefixLength, int maxExpansions, boolean transpositions) {
  super(term.field());
  
  if (maxEdits < 0 || maxEdits > LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE) {
    throw new IllegalArgumentException("maxEdits must be between 0 and " + LevenshteinAutomata.MAXIMUM_SUPPORTED_DISTANCE);
  }
  if (prefixLength < 0) {
    throw new IllegalArgumentException("prefixLength cannot be negative.");
  }
  if (maxExpansions <= 0) {
    throw new IllegalArgumentException("maxExpansions must be positive.");
  }
  
  this.term = term;
  this.maxEdits = maxEdits;
  this.prefixLength = prefixLength;
  this.transpositions = transpositions;
  this.maxExpansions = maxExpansions;
  setRewriteMethod(new MultiTermQuery.TopTermsBlendedFreqScoringRewrite(maxExpansions));
}
 

/**
 * Create a {@link DisjunctionMatchesIterator} over a list of terms
 *
 * Only terms that have at least one match in the given document will be included
 */
static MatchesIterator fromTerms(LeafReaderContext context, int doc, Query query, String field, List<Term> terms) throws IOException {
  Objects.requireNonNull(field);
  for (Term term : terms) {
    if (Objects.equals(field, term.field()) == false) {
      throw new IllegalArgumentException("Tried to generate iterator from terms in multiple fields: expected [" + field + "] but got [" + term.field() + "]");
    }
  }
  return fromTermsEnum(context, doc, query, field, asBytesRefIterator(terms));
}
 

/** Phrase positions are relative. */
public void testPhraseRelativePositions() throws Exception {
  Term t1 = randomTerm();
  Term t2 = randomTerm();
  PhraseQuery q1 = new PhraseQuery(t1.field(), t1.bytes(), t2.bytes());
  PhraseQuery.Builder builder = new PhraseQuery.Builder();
  builder.add(t1, 10000);
  builder.add(t2, 10001);
  PhraseQuery q2 = builder.build();
  assertSameScores(q1, q2);
}
 

/** "A A A"~N ⊆ "A A A"~N+1 */
public void testRepetitiveIncreasingSloppiness3() throws Exception {
  Term t = randomTerm();
  for (int i = 0; i < 10; i++) {
    PhraseQuery q1 = new PhraseQuery(i, t.field(), t.bytes(), t.bytes(), t.bytes());
    PhraseQuery q2 = new PhraseQuery(i + 1, t.field(), t.bytes(), t.bytes(), t.bytes());
    assertSubsetOf(q1, q2);
    assertSubsetOf(q1, q2);
  }
}
 

/** Adds a term to the end of the query phrase. */
 public void add(Term term) {
   if (terms.size() == 0)
     field = term.field();
   else if (term.field() != field)
     throw new IllegalArgumentException
("All phrase terms must be in the same field: " + term);

   terms.addElement(term);
 }
 

/** "A B"~∞ = +A +B if A != B */
public void testSloppyPhraseVersusBooleanAnd() throws Exception {
  Term t1 = randomTerm();
  Term t2 = null;
  // semantics differ from SpanNear: SloppyPhrase handles repeats,
  // so we must ensure t1 != t2
  do {
    t2 = randomTerm();
  } while (t1.equals(t2));
  PhraseQuery q1 = new PhraseQuery(Integer.MAX_VALUE, t1.field(), t1.bytes(), t2.bytes());
  BooleanQuery.Builder q2 = new BooleanQuery.Builder();
  q2.add(new TermQuery(t1), Occur.MUST);
  q2.add(new TermQuery(t2), Occur.MUST);
  assertSameSet(q1, q2.build());
}
 

/** "A B"~N ⊆ "A B"~N+1 */
public void testIncreasingSloppiness() throws Exception {
  Term t1 = randomTerm();
  Term t2 = randomTerm();
  for (int i = 0; i < 10; i++) {
    PhraseQuery q1 = new PhraseQuery(i, t1.field(), t1.bytes(), t2.bytes());
    PhraseQuery q2 = new PhraseQuery(i + 1, t1.field(), t1.bytes(), t2.bytes());
    assertSubsetOf(q1, q2);
  }
}
 

/** Adds a term to the end of the query phrase. */
 public void add(Term term) {
   if (terms.size() == 0)
     field = term.field();
   else if (term.field() != field)
     throw new IllegalArgumentException
("All phrase terms must be in the same field: " + term);

   terms.addElement(term);
 }
 

/** "A B" ⊆ (+A +B) */
public void testExactPhraseVersusBooleanAnd() throws Exception {
  Term t1 = randomTerm();
  Term t2 = randomTerm();
  PhraseQuery q1 = new PhraseQuery(t1.field(), t1.bytes(), t2.bytes());
  BooleanQuery.Builder q2 = new BooleanQuery.Builder();
  q2.add(new TermQuery(t1), Occur.MUST);
  q2.add(new TermQuery(t2), Occur.MUST);
  assertSubsetOf(q1, q2.build());
}
 

/**
 * Adds a single term at the next position in the phrase.
 */
public Builder addTerm(Term term) {
  if (!term.field().equals(field)) {
    throw new IllegalArgumentException(term.getClass().getSimpleName()
        + " field \"" + term.field() + "\" cannot be different from the "
        + PhraseWildcardQuery.class.getSimpleName() + " field \"" + field + "\"");
  }
  phraseTerms.add(new SingleTerm(term, phraseTerms.size()));
  return this;
}
 

/** "A B" ⊆ "A B"~1 */
public void testPhraseVersusSloppyPhrase() throws Exception {
  Term t1 = randomTerm();
  Term t2 = randomTerm();
  PhraseQuery q1 = new PhraseQuery(t1.field(), t1.bytes(), t2.bytes());
  PhraseQuery q2 = new PhraseQuery(1, t1.field(), t1.bytes(), t2.bytes());
  assertSubsetOf(q1, q2);
}
 

/** "A B" ⊆ "A (B C)" */
public void testExactPhraseVersusMultiPhrase() throws Exception {
  Term t1 = randomTerm();
  Term t2 = randomTerm();
  PhraseQuery q1 = new PhraseQuery(t1.field(), t1.bytes(), t2.bytes());
  Term t3 = randomTerm();
  MultiPhraseQuery.Builder q2b = new MultiPhraseQuery.Builder();
  q2b.add(t1);
  q2b.add(new Term[] { t2, t3 });
  assertSubsetOf(q1, q2b.build());
}
 

/** Constructs a query for terms matching <code>term</code>. */
public CrateRegexQuery(Term term, int flags) {
    super(term.field());
    this.term = term;
    this.flags = flags;
}
 

/** Constructs a query for terms matching <code>term</code>. */
public CrateRegexQuery(Term term) {
    super(term.field());
    this.term = term;
    this.flags = 0;
}
 

private String getKey(Term term) {
  return term.field() + term.text();
}
 

DumbRegexpQuery(Term term, int flags) {
  super(term.field());
  RegExp re = new RegExp(term.text(), flags);
  automaton = re.toAutomaton();
}
 

private static Query buildRandomQuery(int level) {
  if (level == 10) {
    // at most 10 levels
    return new MatchAllDocsQuery();
  }
  switch (random().nextInt(6)) {
    case 0:
      return new TermQuery(randomTerm());
    case 1:
      BooleanQuery.Builder bq = new BooleanQuery.Builder();
      final int numClauses = TestUtil.nextInt(random(), 1, 3);
      int numShould = 0;
      for (int i = 0; i < numClauses; ++i) {
        final Occur occur = RandomPicks.randomFrom(random(), Occur.values());
        bq.add(buildRandomQuery(level + 1), occur);
        if (occur == Occur.SHOULD) {
          numShould++;
        }
      }
      bq.setMinimumNumberShouldMatch(TestUtil.nextInt(random(), 0, numShould));
      return bq.build();
    case 2:
      Term t1 = randomTerm();
      Term t2 = randomTerm();
      PhraseQuery pq = new PhraseQuery(random().nextInt(2), t1.field(), t1.bytes(), t2.bytes());
      return pq;
    case 3:
      return new MatchAllDocsQuery();
    case 4:
      return new ConstantScoreQuery(buildRandomQuery(level + 1));
    case 5:
      List<Query> disjuncts = new ArrayList<>();
      final int numQueries = TestUtil.nextInt(random(), 1, 3);
      for (int i = 0; i < numQueries; ++i) {
        disjuncts.add(buildRandomQuery(level + 1));
      }
      return new DisjunctionMaxQuery(disjuncts, random().nextFloat());
    default:
      throw new AssertionError();
  }
}
 

DumbPrefixQuery(Term term) {
  super(term.field());
  prefix = term.bytes();
}
 

/**
 * Create a new AutomatonQuery from an {@link Automaton}.
 * 
 * @param term Term containing field and possibly some pattern structure. The
 *        term text is ignored.
 * @param automaton Automaton to run, terms that are accepted are considered a
 *        match.
 * @param maxDeterminizedStates maximum number of states in the resulting
 *   automata.  If the automata would need more than this many states
 *   TooComplextToDeterminizeException is thrown.  Higher number require more
 *   space but can process more complex automata.
 * @param isBinary if true, this automaton is already binary and
 *   will not go through the UTF32ToUTF8 conversion
 */
public AutomatonQuery(final Term term, Automaton automaton, int maxDeterminizedStates, boolean isBinary) {
  super(term.field());
  this.term = term;
  this.automaton = automaton;
  this.automatonIsBinary = isBinary;
  // TODO: we could take isFinite too, to save a bit of CPU in CompiledAutomaton ctor?:
  this.compiled = new CompiledAutomaton(automaton, null, true, maxDeterminizedStates, isBinary);

  this.ramBytesUsed = BASE_RAM_BYTES + term.ramBytesUsed() + automaton.ramBytesUsed() + compiled.ramBytesUsed();
}