Line data    Source code

       1             : /**
       2             :  Copyright (c) 2024 Stappler LLC <admin@stappler.dev>
       3             : 
       4             :  Permission is hereby granted, free of charge, to any person obtaining a copy
       5             :  of this software and associated documentation files (the "Software"), to deal
       6             :  in the Software without restriction, including without limitation the rights
       7             :  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
       8             :  copies of the Software, and to permit persons to whom the Software is
       9             :  furnished to do so, subject to the following conditions:
      10             : 
      11             :  The above copyright notice and this permission notice shall be included in
      12             :  all copies or substantial portions of the Software.
      13             : 
      14             :  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
      15             :  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
      16             :  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
      17             :  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
      18             :  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
      19             :  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
      20             :  THE SOFTWARE.
      21             :  **/
      22             : 
      23             : #ifndef CORE_SEARCH_SPSEARCHQUERY_H_
      24             : #define CORE_SEARCH_SPSEARCHQUERY_H_
      25             : 
      26             : #include "SPSearchParser.h"
      27             : 
      28             : namespace STAPPLER_VERSIONIZED stappler::search {
      29             : 
      30             : enum class Normalization {
      31             :         Default = 0,
      32             :         DocLengthLog = 1, // divides the rank by 1 + the logarithm of the document length
      33             :         DocLength = 2, // divides the rank by the document length
      34             :         UniqueWordsCount = 8, // divides the rank by the number of unique words in document
      35             :         UniqueWordsCountLog = 16, // divides the rank by 1 + the logarithm of the number of unique words in document
      36             :         Self = 32 // divides the rank by itself + 1
      37             : };
      38             : 
      39             : SP_DEFINE_ENUM_AS_MASK(Normalization)
      40             : 
      41             : struct RankingValues {
      42             :         float A = 1.0f;
      43             :         float B = 0.4f;
      44             :         float C = 0.2f;
      45             :         float D = 0.1f;
      46             : 
      47             :         // Linearly interpolated from first to last word in document
      48             :         // (so, last word score will be RANK * positionFactor
      49             :         // word in a middle: (RANK * (1.0 + positionFactor) / 2.0)
      50             :         // 1.0 - do not apply position-based score
      51             :         //
      52             :         // Not implemented in PostgreSQL engine, has no effect
      53             :         float positionFactor = 1.0f;
      54             : 
      55        1150 :         float rank(SearchRank r) const {
      56        1150 :                 switch (r) {
      57          25 :                 case SearchRank::A: return A; break;
      58         525 :                 case SearchRank::B: return B; break;
      59          25 :                 case SearchRank::C: return C; break;
      60          25 :                 case SearchRank::D: return D; break;
      61         525 :                 case SearchRank::Unknown: return D; break;
      62             :                 }
      63          25 :                 return D;
      64             :         }
      65             : };
      66             : 
      67             : struct SearchVector {
      68             :         using MatchVector = Vector<Pair<size_t, SearchData::Rank>>;
      69             : 
      70             :         size_t documentLength = 0;
      71             :         Map<StringView, MatchVector> words;
      72             : 
      73        3300 :         bool empty() const { return words.empty(); }
      74             : };
      75             : 
      76             : struct SearchQuery {
      77             :         enum Block : uint8_t {
      78             :                 None,
      79             :                 Parentesis,
      80             :                 Quoted,
      81             :         };
      82             : 
      83             :         enum Format {
      84             :                 Stappler,
      85             :                 Postgresql,
      86             :         };
      87             : 
      88             :         Block block = None;
      89             :         SearchOp op = SearchOp::None;
      90             :         bool neg = false;
      91             :         uint32_t offset = 0;
      92             :         String value;
      93             :         StringView source;
      94             :         Vector<SearchQuery> args;
      95             : 
      96        3725 :         SearchQuery() = default;
      97             :         SearchQuery(StringView value, uint32_t offset = 1, StringView source = StringView());
      98             :         SearchQuery(SearchOp, StringView);
      99             : 
     100         550 :         bool empty() const { return (op == SearchOp::None && value.empty()) || (op != SearchOp::None && args.empty()); }
     101             : 
     102             :         void clear();
     103             :         void encode(const Callback<void(StringView)> &, Format = Stappler) const;
     104             : 
     105             :         void describe(std::ostream &stream, size_t depth = 0) const;
     106             :         void foreach(const Callback<void(StringView value, StringView source)> &) const;
     107             : 
     108             :         bool isMatch(const SearchVector &) const;
     109             : 
     110             :         // used with opaque index format from `Configuration::encodeSearchVectorData`
     111             :         bool isMatch(const BytesView &) const;
     112             : 
     113             :         float rankQuery(const SearchVector &, Normalization = Normalization::Default, RankingValues = RankingValues()) const;
     114             : 
     115             :         // used with opaque index format from `Configuration::encodeSearchVectorData`
     116             :         float rankQuery(const BytesView &, Normalization = Normalization::Default, RankingValues = RankingValues()) const;
     117             : 
     118             :         void normalize();
     119             : 
     120             :         void decompose(const Callback<void(StringView)> &positive, const Callback<void(StringView)> &negative) const;
     121             : };
     122             : 
     123             : }
     124             : 
     125             : #endif /* CORE_SEARCH_SPSEARCHQUERY_H_ */