27// * A {@link TokenFilter} that decomposes compound words found in many Germanic languages.
28// * <p>
29// * "Donaudampfschiff" becomes Donau, dampf, schiff so that you can find
30// * "Donaudampfschiff" even when you only enter "schiff". It uses a hyphenation
31// * grammar and a word dictionary to achieve this.
32// * </p>
33// */
34//public class HyphenationCompoundWordTokenFilter : CompoundWordTokenFilterBase
35//{
36// private HyphenationTree hyphenator;
37
38// /*
39// *
40// * @param input the {@link TokenStream} to process
41// * @param hyphenator the hyphenation pattern tree to use for hyphenation
42// * @param dictionary the word dictionary to match against
43// * @param minWordSize only words longer than this get processed
44// * @param minSubwordSize only subwords longer than this get to the output
45// * stream
46// * @param maxSubwordSize only subwords shorter than this get to the output
47// * stream
48// * @param onlyLongestMatch Add only the longest matching subword to the stream
49// */
50// public HyphenationCompoundWordTokenFilter(TokenStream input, HyphenationTree hyphenator, String[] dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, bool onlyLongestMatch)
70// * @param input the {@link TokenStream} to process
71// * @param hyphenator the hyphenation pattern tree to use for hyphenation
72// * @param dictionary the word dictionary to match against. If this is a {@link org.apache.lucene.analysis.CharArraySet CharArraySet} it must have set ignoreCase=false and only contain
73// * lower case strings.
74// */
75// public HyphenationCompoundWordTokenFilter(TokenStream input,
84// * @param input the {@link TokenStream} to process
85// * @param hyphenator the hyphenation pattern tree to use for hyphenation
86// * @param dictionary the word dictionary to match against. If this is a {@link org.apache.lucene.analysis.CharArraySet CharArraySet} it must have set ignoreCase=false and only contain
87// * lower case strings.
88// * @param minWordSize only words longer than this get processed
89// * @param minSubwordSize only subwords longer than this get to the output
90// * stream
91// * @param maxSubwordSize only subwords shorter than this get to the output
92// * stream
93// * @param onlyLongestMatch Add only the longest matching subword to the stream
94// */
95// public HyphenationCompoundWordTokenFilter(TokenStream input,
96// HyphenationTree hyphenator, ISet<string> dictionary, int minWordSize,
97// int minSubwordSize, int maxSubwordSize, bool onlyLongestMatch)