#ifndef INDEX_SEARCHER_HDR #define INDEX_SEARCHER_HDR #include #include #include #include #include "concordia/common/config.hpp" #include "concordia/matched_pattern_fragment.hpp" #include "concordia/hash_generator.hpp" #include "concordia/concordia_exception.hpp" #include "concordia/concordia_searcher.hpp" #include "concordia/anubis_search_result.hpp" #include /*! Class for searching the index with a sentence. In all searches the sentence is first hashed and then used as a query. IndexSearcher performs the simpleSearch on its own, but uses a ConcordiaSearcher object to carry out concordiaSearch. */ class IndexSearcher { public: /*! Constructor. */ explicit IndexSearcher(); /*! Destructor. */ virtual ~IndexSearcher(); /*! Performs a simple substring lookup in RAM-based index. For more info see \ref tutorial1_2. \param hashGenerator hash generator to be used to convert input sentence to a hash \param T hashed index to search in \param markers markers array for the needs of searching \param SA suffix array for the needs of searching \param pattern string pattern to be searched in the index. \returns matched pattern fragment, containing occurences of the pattern in the index \throws ConcordiaException */ MatchedPatternFragment simpleSearch( boost::shared_ptr hashGenerator, boost::shared_ptr > T, boost::shared_ptr > markers, boost::shared_ptr > SA, const std::string & pattern, bool byWhitespace = false) throw(ConcordiaException); SUFFIX_MARKER_TYPE countOccurences( boost::shared_ptr hashGenerator, boost::shared_ptr > T, boost::shared_ptr > markers, boost::shared_ptr > SA, const std::string & pattern) throw(ConcordiaException); /*! \deprecated Finds the examples from the index, whose resemblance to the pattern is maximal. This method may perform very slow, try using concordiaSearch instead. \param config concordia config object (to read the anubis threshold parameter) \param hashGenerator hash generator to be used to convert input sentence to a hash \param T hashed index to search in \param markers markers array for the needs of searching \param SA suffix array for the needs of searching \param pattern string pattern to be searched in the index. \param byWhitespace whether to tokenize the pattern by white space \returns vector of results \throws ConcordiaException */ std::vector anubisSearch( boost::shared_ptr config, boost::shared_ptr hashGenerator, boost::shared_ptr > T, boost::shared_ptr > markers, boost::shared_ptr > SA, const std::string & pattern) throw(ConcordiaException); /*! Performs concordia lookup on the RAM-based index. This is a unique library functionality, designed to facilitate Computer-Aided Translation. For more info see \ref tutorial1_3. \param hashGenerator hash generator to be used to convert input sentence to a hash \param T hashed index to search in \param markers markers array for the needs of searching \param SA suffix array for the needs of searching \param pattern pattern to be searched in the index. \param byWhitespace whether to tokenize the pattern by white space \returns result of the search \throws ConcordiaException */ boost::shared_ptr concordiaSearch( boost::shared_ptr hashGenerator, boost::shared_ptr > T, boost::shared_ptr > markers, boost::shared_ptr > SA, const std::string & pattern, bool byWhitespace = false) throw(ConcordiaException); private: boost::shared_ptr _concordiaSearcher; }; #endif