xapian-core/languages/steminternal.h

   1 /** @file
   2  *  @brief Base class for implementations of stemming algorithms
   3  */
   4 /* Copyright (C) 2007,2009,2010,2016 Olly Betts
   5  * Copyright (C) 2010 Evgeny Sizikov
   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 USA
  20  */
  21
  22 #ifndef XAPIAN_INCLUDED_STEMINTERNAL_H
  23 #define XAPIAN_INCLUDED_STEMINTERNAL_H
  24
  25 #include <xapian/stem.h>
  26
  27 #include "alignment_cast.h"
  28
  29 #include <cstdlib>
  30 #include <string>
  31
  32 typedef unsigned char symbol;
  33
  34 #define HEAD (2 * sizeof(int))
  35
  36 typedef int (*among_function)(Xapian::StemImplementation *);
  37
  38 struct among {
  39     int s_size;         /* length of search string (in symbols) */
  40     unsigned s;         /* offset in pool to search string */
  41     int substring_i;    /* index to longest matching substring */
  42     int result;         /* result of the lookup */
  43 };
  44
  45 inline void lose_s(symbol * p) {
  46     if (p) std::free(reinterpret_cast<char *>(p) - HEAD);
  47 }
  48
  49 namespace Xapian {
  50
  51 class SnowballStemImplementation : public StemImplementation {
  52     int slice_check();
  53
  54   protected:
  55     symbol * p;
  56     int c, l, lb, bra, ket;
  57
  58     static int
  59     SIZE(const symbol* p)
  60     {
  61         return alignment_cast<const int *>(p)[-1];
  62     }
  63
  64     static void
  65     SET_SIZE(symbol* p, int n)
  66     {
  67         alignment_cast<int *>(p)[-1] = n;
  68     }
  69
  70     static int
  71     CAPACITY(const symbol* p)
  72     {
  73         return alignment_cast<const int *>(p)[-2];
  74     }
  75
  76     static void
  77     SET_CAPACITY(symbol* p, int n)
  78     {
  79         alignment_cast<int *>(p)[-2] = n;
  80     }
  81
  82     static int skip_utf8(const symbol * p, int c, int lb, int l, int n);
  83
  84     static symbol * increase_size(symbol * p, int n);
  85
  86     static symbol * create_s();
  87
  88     int get_utf8(int * slot);
  89     int get_b_utf8(int * slot);
  90
  91     int in_grouping_U(const unsigned char * s, int min, int max, int repeat);
  92     int in_grouping_b_U(const unsigned char * s, int min, int max, int repeat);
  93     int out_grouping_U(const unsigned char * s, int min, int max, int repeat);
  94     int out_grouping_b_U(const unsigned char * s, int min, int max, int repeat);
  95
  96     int eq_s(int s_size, const symbol * s);
  97     int eq_s_b(int s_size, const symbol * s);
  98     int eq_v(const symbol * v) { return eq_s(SIZE(v), v); }
  99     int eq_v_b(const symbol * v) { return eq_s_b(SIZE(v), v); }
 100
 101     int find_among(const symbol *pool, const struct among * v, int v_size,
 102                    const unsigned char * fnum, const among_function * f);
 103     int find_among_b(const symbol *pool, const struct among * v, int v_size,
 104                      const unsigned char * fnum, const among_function * f);
 105
 106     int replace_s(int c_bra, int c_ket, int s_size, const symbol * s);
 107     int slice_from_s(int s_size, const symbol * s);
 108     int slice_from_v(const symbol * v) { return slice_from_s(SIZE(v), v); }
 109
 110     int slice_del() { return slice_from_s(0, 0); }
 111
 112     void insert_s(int c_bra, int c_ket, int s_size, const symbol * s);
 113     void insert_v(int c_bra, int c_ket, const symbol * v) {
 114         insert_s(c_bra, c_ket, SIZE(v), v);
 115     }
 116
 117     symbol * slice_to(symbol * v);
 118     symbol * assign_to(symbol * v);
 119
 120     int len_utf8(const symbol * v);
 121
 122 #if 0
 123     void debug(int number, int line_count);
 124 #endif
 125
 126   public:
 127     /// Perform initialisation common to all Snowball stemmers.
 128     SnowballStemImplementation()
 129         : p(create_s()), c(0), l(0), lb(0), bra(0), ket(0) { }
 130
 131     /// Perform cleanup common to all Snowball stemmers.
 132     virtual ~SnowballStemImplementation();
 133
 134     /// Stem the specified word.
 135     virtual std::string operator()(const std::string & word);
 136
 137     /// Virtual method implemented by the subclass to actually do the work.
 138     virtual int stem() = 0;
 139 };
 140
 141 }
 142
 143 #endif // XAPIAN_INCLUDED_STEMINTERNAL_H