xapian-core/queryparser/queryparser_internal.h

   1 /** @file
   2  * @brief The non-lemon-generated parts of the QueryParser class.
   3  */
   4 /* Copyright (C) 2005-2023 Olly Betts
   5  * Copyright (C) 2010 Adam Sjøgren
   6  *
   7  * This program is free software; you can redistribute it and/or
   8  * modify it under the terms of the GNU General Public License as
   9  * published by the Free Software Foundation; either version 2 of the
  10  * License, or (at your option) any later version.
  11  *
  12  * This program is distributed in the hope that it will be useful,
  13  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  * GNU General Public License for more details.
  16  *
  17  * You should have received a copy of the GNU General Public License
  18  * along with this program; if not, write to the Free Software
  19  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  20  * USA
  21  */
  22
  23 #ifndef XAPIAN_INCLUDED_QUERYPARSER_INTERNAL_H
  24 #define XAPIAN_INCLUDED_QUERYPARSER_INTERNAL_H
  25
  26 #include "xapian/intrusive_ptr.h"
  27 #include <xapian/database.h>
  28 #include <xapian/query.h>
  29 #include <xapian/queryparser.h>
  30 #include <xapian/stem.h>
  31
  32 #include <list>
  33 #include <map>
  34
  35 class State;
  36
  37 typedef enum { NON_BOOLEAN, BOOLEAN, BOOLEAN_EXCLUSIVE } filter_type;
  38
  39 /** Information about how to handle a field prefix in the query string. */
  40 struct FieldInfo {
  41     /// The type of this field.
  42     filter_type type;
  43
  44     std::string grouping;
  45
  46     /// Field prefix strings.
  47     std::vector<std::string> prefixes;
  48
  49     /// Field processor.  Currently only one is supported.
  50     Xapian::Internal::opt_intrusive_ptr<Xapian::FieldProcessor> proc;
  51
  52     FieldInfo(filter_type type_, const std::string& prefix,
  53               const std::string& grouping_ = std::string())
  54         : type(type_), grouping(grouping_)
  55     {
  56         prefixes.push_back(prefix);
  57     }
  58
  59     FieldInfo(filter_type type_, Xapian::FieldProcessor* proc_,
  60               const std::string& grouping_ = std::string())
  61         : type(type_), grouping(grouping_), proc(proc_)
  62     {
  63     }
  64 };
  65
  66 namespace Xapian {
  67
  68 class Utf8Iterator;
  69
  70 struct RangeProc {
  71     Xapian::Internal::opt_intrusive_ptr<RangeProcessor> proc;
  72     std::string grouping;
  73     bool default_grouping;
  74
  75     RangeProc(RangeProcessor * range_proc, const std::string* grouping_)
  76         : proc(range_proc),
  77           grouping(grouping_ ? *grouping_ : std::string()),
  78           default_grouping(grouping_ == NULL) { }
  79 };
  80
  81 class QueryParser::Internal : public Xapian::Internal::intrusive_base {
  82     friend class QueryParser;
  83     friend class ::State;
  84     Stem stemmer;
  85     stem_strategy stem_action = STEM_SOME;
  86     Xapian::Internal::opt_intrusive_ptr<const Stopper> stopper;
  87     Query::op default_op = Query::OP_OR;
  88     const char* errmsg = nullptr;
  89     Database db;
  90     std::list<std::string> stoplist;
  91     std::multimap<std::string, std::string> unstem;
  92
  93     // Map "from" -> "A" ; "subject" -> "C" ; "newsgroups" -> "G" ;
  94     // "foobar" -> "XFOO". FIXME: it does more than this now!
  95     std::map<std::string, FieldInfo> field_map;
  96
  97     std::list<RangeProc> rangeprocs;
  98
  99     std::string corrected_query;
 100
 101     Xapian::termcount max_wildcard_expansion = 0;
 102
 103     Xapian::termcount max_partial_expansion = 100;
 104
 105     Xapian::termcount max_fuzzy_expansion = 0;
 106
 107     int max_wildcard_type = Xapian::Query::WILDCARD_LIMIT_ERROR;
 108
 109     int max_partial_type = Xapian::Query::WILDCARD_LIMIT_MOST_FREQUENT;
 110
 111     int max_fuzzy_type = Xapian::Query::WILDCARD_LIMIT_ERROR;
 112
 113     unsigned min_wildcard_prefix_len = 0;
 114
 115     unsigned min_partial_prefix_len = 2;
 116
 117     void add_prefix(const std::string& field, const std::string& prefix);
 118
 119     void add_prefix(const std::string& field, Xapian::FieldProcessor* proc);
 120
 121     void add_boolean_prefix(const std::string& field,
 122                             const std::string& prefix,
 123                             const std::string* grouping);
 124
 125     void add_boolean_prefix(const std::string& field,
 126                             Xapian::FieldProcessor* proc,
 127                             const std::string* grouping);
 128
 129     std::string parse_term(Utf8Iterator& it, const Utf8Iterator& end,
 130                            bool try_word_break, unsigned flags,
 131                            bool& needs_word_break, bool& was_acronym,
 132                            size_t& first_wildcard,
 133                            size_t& char_count,
 134                            unsigned& edit_distance);
 135
 136   public:
 137     Internal() { }
 138
 139     Query parse_query(const std::string& query_string,
 140                       unsigned int flags,
 141                       const std::string& default_prefix);
 142 };
 143
 144 }
 145
 146 #endif // XAPIAN_INCLUDED_QUERYPARSER_INTERNAL_H