/// <summary>
/// Creates a new <seealso cref="HyphenationCompoundWordTokenFilter"/> instance.
/// </summary>
/// <param name="matchVersion">
/// Lucene version to enable correct Unicode 4.0 behavior in the
/// dictionaries if Version > 3.0. See <a
/// href="CompoundWordTokenFilterBase.html#version"
/// >CompoundWordTokenFilterBase</a> for details. </param>
/// <param name="input">
/// the <seealso cref="TokenStream"/> to process </param>
/// <param name="hyphenator">
/// the hyphenation pattern tree to use for hyphenation </param>
/// <param name="dictionary">
/// the word dictionary to match against. </param>
/// <param name="minWordSize">
/// only words longer than this get processed </param>
/// <param name="minSubwordSize">
/// only subwords longer than this get to the output stream </param>
/// <param name="maxSubwordSize">
/// only subwords shorter than this get to the output stream </param>
/// <param name="onlyLongestMatch">
/// Add only the longest matching subword to the stream </param>
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input, HyphenationTree hyphenator, CharArraySet dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, bool onlyLongestMatch)
: base(matchVersion, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch)
{
this.hyphenator = hyphenator;
}
/// <summary>
/// Creates a new <seealso cref="HyphenationCompoundWordTokenFilter"/> instance.
/// </summary>
/// <param name="matchVersion">
/// Lucene version to enable correct Unicode 4.0 behavior in the
/// dictionaries if Version > 3.0. See <a
/// href="CompoundWordTokenFilterBase.html#version"
/// >CompoundWordTokenFilterBase</a> for details. </param>
/// <param name="input">
/// the <seealso cref="TokenStream"/> to process </param>
/// <param name="hyphenator">
/// the hyphenation pattern tree to use for hyphenation </param>
/// <param name="dictionary">
/// the word dictionary to match against. </param>
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input, HyphenationTree hyphenator, CharArraySet dictionary)
: this(matchVersion, input, hyphenator, dictionary, DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE, false)
{
}
/// <summary>
/// Create a hyphenator tree
/// </summary>
/// <param name="hyphenationSource"> the InputSource pointing to the XML grammar </param>
/// <returns> An object representing the hyphenation patterns </returns>
/// <exception cref="IOException"> If there is a low-level I/O error. </exception>
public static HyphenationTree getHyphenationTree(InputSource hyphenationSource)
{
var tree = new HyphenationTree();
tree.loadPatterns(hyphenationSource);
return tree;
}
/// <summary>
/// Create a HyphenationCompoundWordTokenFilter with no dictionary.
/// <para>
/// Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, int, int, int)
/// HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
/// DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE }
/// </para>
/// </summary>
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input, HyphenationTree hyphenator)
: this(matchVersion, input, hyphenator, DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE)
{
}
/// <summary>
/// Create a HyphenationCompoundWordTokenFilter with no dictionary.
/// <para>
/// Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, CharArraySet, int, int, int, boolean)
/// HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
/// null, minWordSize, minSubwordSize, maxSubwordSize }
/// </para>
/// </summary>
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input, HyphenationTree hyphenator, int minWordSize, int minSubwordSize, int maxSubwordSize)
: this(matchVersion, input, hyphenator, null, minWordSize, minSubwordSize, maxSubwordSize, false)
{
}
public virtual void Inform(ResourceLoader loader)
{
InputStream stream = null;
try
{
if (dictFile != null) // the dictionary can be empty.
{
dictionary = getWordSet(loader, dictFile, false);
}
// TODO: Broken, because we cannot resolve real system id
// ResourceLoader should also supply method like ClassLoader to get resource URL
stream = loader.openResource(hypFile);
InputSource @is = new InputSource(stream);
@is.Encoding = encoding; // if it's null let xml parser decide
@is.SystemId = hypFile;
hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(@is);
}
finally
{
IOUtils.closeWhileHandlingException(stream);
}
}