/// <summary> Returns version-dependent default for enablePositionIncrements. Analyzers
/// that embed StopFilter use this method when creating the StopFilter. Prior
/// to 2.9, this returns {@link #getEnablePositionIncrementsDefault}. On 2.9
/// or later, it returns true.
/// </summary>
public static bool GetEnablePositionIncrementsVersionDefault(Version matchVersion)
{
if (matchVersion.OnOrAfter(Version.LUCENE_29))
{
return true;
}
else
{
return ENABLE_POSITION_INCREMENTS_DEFAULT;
}
}
private void Init(System.IO.TextReader input, Version matchVersion)
{
if (matchVersion.OnOrAfter(Version.LUCENE_24))
{
Init(input, true);
}
else
{
Init(input, false);
}
}
/// <summary> Parses a query, searching on the fields specified. Use this if you need
/// to specify certain fields as required, and others as prohibited.
/// <p/>
///
/// <pre>
/// Usage:
/// <code>
/// String[] query = {"query1", "query2", "query3"};
/// String[] fields = {"filename", "contents", "description"};
/// BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
/// BooleanClause.Occur.MUST,
/// BooleanClause.Occur.MUST_NOT};
/// MultiFieldQueryParser.parse(query, fields, flags, analyzer);
/// </code>
/// </pre>
/// <p/>
/// The code above would construct a query:
///
/// <pre>
/// <code>
/// (filename:query1) +(contents:query2) -(description:query3)
/// </code>
/// </pre>
///
/// </summary>
/// <param name="matchVersion">Lucene version to match; this is passed through to
/// QueryParser.
/// </param>
/// <param name="queries">Queries string to parse
/// </param>
/// <param name="fields">Fields to search on
/// </param>
/// <param name="flags">Flags describing the fields
/// </param>
/// <param name="analyzer">Analyzer to use
/// </param>
/// <throws> ParseException </throws>
/// <summary> if query parsing fails
/// </summary>
/// <throws> IllegalArgumentException </throws>
/// <summary> if the length of the queries, fields, and flags array differ
/// </summary>
public static Query Parse(Version matchVersion, System.String[] queries, System.String[] fields, BooleanClause.Occur[] flags, Analyzer analyzer)
{
if (!(queries.Length == fields.Length && queries.Length == flags.Length))
{
throw new System.ArgumentException("queries, fields, and flags array have have different length");
}
BooleanQuery bQuery = new BooleanQuery();
for (int i = 0; i < fields.Length; i++)
{
QueryParser qp = new QueryParser(matchVersion, fields[i], analyzer);
Query q = qp.Parse(queries[i]);
if (q != null && (!(q is BooleanQuery) || ((BooleanQuery)q).GetClauses().Length > 0))
{
bQuery.Add(q, flags[i]);
}
}
return(bQuery);
}
private void Init(Version matchVersion)
{
SetOverridesTokenStreamMethod(typeof(StandardAnalyzer));
if (matchVersion.OnOrAfter(Version.LUCENE_29))
{
enableStopPositionIncrements = true;
}
else
{
useDefaultStopPositionIncrements = true;
}
if (matchVersion.OnOrAfter(Version.LUCENE_24))
{
replaceInvalidAcronym = defaultReplaceInvalidAcronym;
}
else
{
replaceInvalidAcronym = false;
}
}
/// <summary> Creates a MultiFieldQueryParser. Allows passing of a map with term to
/// Boost, and the boost to apply to each term.
///
/// <p/>
/// It will, when parse(String query) is called, construct a query like this
/// (assuming the query consists of two terms and you specify the two fields
/// <code>title</code> and <code>body</code>):
/// <p/>
///
/// <code>
/// (title:term1 body:term1) (title:term2 body:term2)
/// </code>
///
/// <p/>
/// When setDefaultOperator(AND_OPERATOR) is set, the result will be:
/// <p/>
///
/// <code>
/// +(title:term1 body:term1) +(title:term2 body:term2)
/// </code>
///
/// <p/>
/// When you pass a boost (title=>5 body=>10) you can get
/// <p/>
///
/// <code>
/// +(title:term1^5.0 body:term1^10.0) +(title:term2^5.0 body:term2^10.0)
/// </code>
///
/// <p/>
/// In other words, all the query's terms must appear, but it doesn't matter
/// in what fields they appear.
/// <p/>
/// </summary>
public MultiFieldQueryParser(Version matchVersion, System.String[] fields, Analyzer analyzer, System.Collections.IDictionary boosts) : this(matchVersion, fields, analyzer)
{
this.boosts = boosts;
}
/// <summary> Creates a new StandardTokenizer with a given
/// {@link org.apache.lucene.util.AttributeSource.AttributeFactory}
/// </summary>
public StandardTokenizer(Version matchVersion, AttributeFactory factory, System.IO.TextReader input):base(factory)
{
InitBlock();
this.scanner = new StandardTokenizerImpl(input);
Init(input, matchVersion);
}
private void Init(System.IO.TextReader input, Version matchVersion)
{
if (matchVersion.OnOrAfter(Version.LUCENE_24))
{
Init(input, true);
}
else
{
Init(input, false);
}
}
/// <summary> Builds an analyzer which removes words in ENGLISH_STOP_WORDS.</summary>
public StopAnalyzer(Version matchVersion)
{
stopWords = ENGLISH_STOP_WORDS_SET;
useDefaultStopPositionIncrement = false;
enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
}
/// <summary> Constructs a query parser.
///
/// </summary>
/// <param name="matchVersion">Lucene version to match. See <a href="#version">above</a>)
/// </param>
/// <param name="f">the default field for query terms.
/// </param>
/// <param name="a">used to find terms in the query text.
/// </param>
public QueryParser(Version matchVersion, System.String f, Analyzer a):this(new FastCharStream(new System.IO.StringReader("")))
{
analyzer = a;
field = f;
if (matchVersion.OnOrAfter(Version.LUCENE_29))
{
enablePositionIncrements = true;
}
else
{
enablePositionIncrements = false;
}
}
/// <summary>Builds an analyzer with the given stop words.</summary>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
/// <param name="stopWords">stop words
/// </param>
public StandardAnalyzer(Version matchVersion, System.Collections.Hashtable stopWords)
{
stopSet = stopWords;
Init(matchVersion);
}
/// <summary> Creates a new StandardTokenizer with a given
/// {@link org.apache.lucene.util.AttributeSource.AttributeFactory}
/// </summary>
public StandardTokenizer(Version matchVersion, AttributeFactory factory, System.IO.TextReader input) : base(factory)
{
InitBlock();
this.scanner = new StandardTokenizerImpl(input);
Init(input, matchVersion);
}
/// <summary>Builds an analyzer with the default stop words ({@link
/// #STOP_WORDS}).
/// </summary>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
public StandardAnalyzer(Version matchVersion) : this(matchVersion, STOP_WORDS_SET)
{
}
/// <summary>Builds an analyzer with the stop words from the given reader.</summary>
/// <seealso cref="WordlistLoader.GetWordSet(Reader)">
/// </seealso>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
/// <param name="stopwords">Reader to read stop words from
/// </param>
public StandardAnalyzer(Version matchVersion, System.IO.TextReader stopwords)
{
stopSet = WordlistLoader.GetWordSet(stopwords);
Init(matchVersion);
}
/// <summary>Builds an analyzer with the stop words from the given reader. </summary>
/// <seealso cref="WordlistLoader.GetWordSet(Reader)">
/// </seealso>
/// <param name="matchVersion">See <a href="#Version">above</a>
/// </param>
/// <param name="stopwords">Reader to load stop words from
/// </param>
public StopAnalyzer(Version matchVersion, System.IO.TextReader stopwords)
{
stopWords = WordlistLoader.GetWordSet(stopwords);
this.enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
useDefaultStopPositionIncrement = false;
}
/// <summary> Builds an analyzer which removes words in ENGLISH_STOP_WORDS.</summary>
public StopAnalyzer(Version matchVersion)
{
stopWords = ENGLISH_STOP_WORDS_SET;
useDefaultStopPositionIncrement = false;
enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
}
/// <summary>Builds an analyzer with the stop words from the given set.</summary>
public StopAnalyzer(Version matchVersion, System.Collections.Hashtable stopWords)
{
this.stopWords = stopWords;
useDefaultStopPositionIncrement = false;
enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
}
private void Init(Version matchVersion)
{
SetOverridesTokenStreamMethod(typeof(StandardAnalyzer));
if (matchVersion.OnOrAfter(Version.LUCENE_29))
{
enableStopPositionIncrements = true;
}
else
{
useDefaultStopPositionIncrements = true;
}
if (matchVersion.OnOrAfter(Version.LUCENE_24))
{
replaceInvalidAcronym = defaultReplaceInvalidAcronym;
}
else
{
replaceInvalidAcronym = false;
}
}
/// <summary>Builds an analyzer with the stop words from the given reader.</summary>
/// <seealso cref="WordlistLoader.GetWordSet(Reader)">
/// </seealso>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
/// <param name="stopwords">Reader to read stop words from
/// </param>
public StandardAnalyzer(Version matchVersion, System.IO.TextReader stopwords)
{
stopSet = WordlistLoader.GetWordSet(stopwords);
Init(matchVersion);
}
/// <summary> Creates a MultiFieldQueryParser.
///
/// <p/>
/// It will, when parse(String query) is called, construct a query like this
/// (assuming the query consists of two terms and you specify the two fields
/// <code>title</code> and <code>body</code>):
/// <p/>
///
/// <code>
/// (title:term1 body:term1) (title:term2 body:term2)
/// </code>
///
/// <p/>
/// When setDefaultOperator(AND_OPERATOR) is set, the result will be:
/// <p/>
///
/// <code>
/// +(title:term1 body:term1) +(title:term2 body:term2)
/// </code>
///
/// <p/>
/// In other words, all the query's terms must appear, but it doesn't matter
/// in what fields they appear.
/// <p/>
/// </summary>
public MultiFieldQueryParser(Version matchVersion, System.String[] fields, Analyzer analyzer) : base(matchVersion, null, analyzer)
{
this.fields = fields;
}
/// <summary>Builds an analyzer with the stop words from the given reader. </summary>
/// <seealso cref="WordlistLoader.GetWordSet(Reader)">
/// </seealso>
/// <param name="matchVersion">See <a href="#Version">above</a>
/// </param>
/// <param name="stopwords">Reader to load stop words from
/// </param>
public StopAnalyzer(Version matchVersion, System.IO.TextReader stopwords)
{
stopWords = WordlistLoader.GetWordSet(stopwords);
this.enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
useDefaultStopPositionIncrement = false;
}
/// <summary> Creates a MultiFieldQueryParser. Allows passing of a map with term to
/// Boost, and the boost to apply to each term.
///
/// <p/>
/// It will, when parse(String query) is called, construct a query like this
/// (assuming the query consists of two terms and you specify the two fields
/// <code>title</code> and <code>body</code>):
/// <p/>
///
/// <code>
/// (title:term1 body:term1) (title:term2 body:term2)
/// </code>
///
/// <p/>
/// When setDefaultOperator(AND_OPERATOR) is set, the result will be:
/// <p/>
///
/// <code>
/// +(title:term1 body:term1) +(title:term2 body:term2)
/// </code>
///
/// <p/>
/// When you pass a boost (title=>5 body=>10) you can get
/// <p/>
///
/// <code>
/// +(title:term1^5.0 body:term1^10.0) +(title:term2^5.0 body:term2^10.0)
/// </code>
///
/// <p/>
/// In other words, all the query's terms must appear, but it doesn't matter
/// in what fields they appear.
/// <p/>
/// </summary>
public MultiFieldQueryParser(Version matchVersion, System.String[] fields, Analyzer analyzer, System.Collections.IDictionary boosts):this(matchVersion, fields, analyzer)
{
this.boosts = boosts;
}
/// <summary>Builds an analyzer with the default stop words ({@link
/// #STOP_WORDS}).
/// </summary>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
public StandardAnalyzer(Version matchVersion):this(matchVersion, STOP_WORDS_SET)
{
}
/// <summary>Builds an analyzer with the given stop words.</summary>
/// <param name="matchVersion">Lucene version to match See {@link
/// <a href="#version">above</a>}
/// </param>
/// <param name="stopWords">stop words
/// </param>
public StandardAnalyzer(Version matchVersion, System.Collections.Hashtable stopWords)
{
stopSet = stopWords;
Init(matchVersion);
}
/// <summary> Creates a MultiFieldQueryParser.
///
/// <p/>
/// It will, when parse(String query) is called, construct a query like this
/// (assuming the query consists of two terms and you specify the two fields
/// <code>title</code> and <code>body</code>):
/// <p/>
///
/// <code>
/// (title:term1 body:term1) (title:term2 body:term2)
/// </code>
///
/// <p/>
/// When setDefaultOperator(AND_OPERATOR) is set, the result will be:
/// <p/>
///
/// <code>
/// +(title:term1 body:term1) +(title:term2 body:term2)
/// </code>
///
/// <p/>
/// In other words, all the query's terms must appear, but it doesn't matter
/// in what fields they appear.
/// <p/>
/// </summary>
public MultiFieldQueryParser(Version matchVersion, System.String[] fields, Analyzer analyzer):base(matchVersion, null, analyzer)
{
this.fields = fields;
}
/// <summary> Parses a query, searching on the fields specified. Use this if you need
/// to specify certain fields as required, and others as prohibited.
/// <p/>
///
/// <pre>
/// Usage:
/// <code>
/// String[] query = {"query1", "query2", "query3"};
/// String[] fields = {"filename", "contents", "description"};
/// BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
/// BooleanClause.Occur.MUST,
/// BooleanClause.Occur.MUST_NOT};
/// MultiFieldQueryParser.parse(query, fields, flags, analyzer);
/// </code>
/// </pre>
/// <p/>
/// The code above would construct a query:
///
/// <pre>
/// <code>
/// (filename:query1) +(contents:query2) -(description:query3)
/// </code>
/// </pre>
///
/// </summary>
/// <param name="matchVersion">Lucene version to match; this is passed through to
/// QueryParser.
/// </param>
/// <param name="queries">Queries string to parse
/// </param>
/// <param name="fields">Fields to search on
/// </param>
/// <param name="flags">Flags describing the fields
/// </param>
/// <param name="analyzer">Analyzer to use
/// </param>
/// <throws> ParseException </throws>
/// <summary> if query parsing fails
/// </summary>
/// <throws> IllegalArgumentException </throws>
/// <summary> if the length of the queries, fields, and flags array differ
/// </summary>
public static Query Parse(Version matchVersion, System.String[] queries, System.String[] fields, BooleanClause.Occur[] flags, Analyzer analyzer)
{
if (!(queries.Length == fields.Length && queries.Length == flags.Length))
throw new System.ArgumentException("queries, fields, and flags array have have different length");
BooleanQuery bQuery = new BooleanQuery();
for (int i = 0; i < fields.Length; i++)
{
QueryParser qp = new QueryParser(matchVersion, fields[i], analyzer);
Query q = qp.Parse(queries[i]);
if (q != null && (!(q is BooleanQuery) || ((BooleanQuery) q).GetClauses().Length > 0))
{
bQuery.Add(q, flags[i]);
}
}
return bQuery;
}
/// <summary>Builds an analyzer with the stop words from the given set.</summary>
public StopAnalyzer(Version matchVersion, System.Collections.Hashtable stopWords)
{
this.stopWords = stopWords;
useDefaultStopPositionIncrement = false;
enablePositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
}
