gcc/spellcheck.h

   1 /* Find near-matches for strings and identifiers.
   2    Copyright (C) 2015-2016 Free Software Foundation, Inc.
   3
   4 This file is part of GCC.
   5
   6 GCC is free software; you can redistribute it and/or modify it under
   7 the terms of the GNU General Public License as published by the Free
   8 Software Foundation; either version 3, or (at your option) any later
   9 version.
  10
  11 GCC is distributed in the hope that it will be useful, but WITHOUT ANY
  12 WARRANTY; without even the implied warranty of MERCHANTABILITY or
  13 FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  14 for more details.
  15
  16 You should have received a copy of the GNU General Public License
  17 along with GCC; see the file COPYING3.  If not see
  18 <http://www.gnu.org/licenses/>.  */
  19
  20 #ifndef GCC_SPELLCHECK_H
  21 #define GCC_SPELLCHECK_H
  22
  23 typedef unsigned int edit_distance_t;
  24 const edit_distance_t MAX_EDIT_DISTANCE = UINT_MAX;
  25
  26 /* spellcheck.c  */
  27 extern edit_distance_t
  28 levenshtein_distance (const char *s, int len_s,
  29                       const char *t, int len_t);
  30
  31 extern edit_distance_t
  32 levenshtein_distance (const char *s, const char *t);
  33
  34 extern const char *
  35 find_closest_string (const char *target,
  36                      const auto_vec<const char *> *candidates);
  37
  38 /* A traits class for describing a string-like type usable by
  39    class best_match.
  40    Specializations should provide the implementations of the following:
  41
  42      static size_t get_length (TYPE);
  43      static const char *get_string (TYPE);
  44
  45    get_string should return a non-NULL ptr, which does not need to be
  46    0-terminated.  */
  47
  48 template <typename TYPE>
  49 struct edit_distance_traits {};
  50
  51 /* A type for use when determining the best match against a string,
  52    expressed as a template so that we can match against various
  53    string-like types (const char *, frontend identifiers, and preprocessor
  54    macros).
  55
  56    This type accumulates the best possible match against GOAL_TYPE for
  57    a sequence of elements of CANDIDATE_TYPE, whilst minimizing the
  58    number of calls to levenshtein_distance and to
  59    edit_distance_traits<T>::get_length.  */
  60
  61 template <typename GOAL_TYPE, typename CANDIDATE_TYPE>
  62 class best_match
  63 {
  64  public:
  65   typedef GOAL_TYPE goal_t;
  66   typedef CANDIDATE_TYPE candidate_t;
  67   typedef edit_distance_traits<goal_t> goal_traits;
  68   typedef edit_distance_traits<candidate_t> candidate_traits;
  69
  70   /* Constructor.  */
  71
  72   best_match (goal_t goal)
  73   : m_goal (goal_traits::get_string (goal)),
  74     m_goal_len (goal_traits::get_length (goal)),
  75     m_best_candidate (NULL),
  76     m_best_distance (MAX_EDIT_DISTANCE)
  77   {}
  78
  79   /* Compare the edit distance between CANDIDATE and m_goal,
  80      and if it's the best so far, record it.  */
  81
  82   void consider (candidate_t candidate)
  83   {
  84     size_t candidate_len = candidate_traits::get_length (candidate);
  85
  86     /* Calculate a lower bound on the candidate's distance to the goal,
  87        based on the difference in lengths; it will require at least
  88        this many insertions/deletions.  */
  89     edit_distance_t min_candidate_distance
  90       = abs ((ssize_t)candidate_len - (ssize_t)m_goal_len);
  91
  92     /* If the candidate's length is sufficiently different to that
  93        of the goal string, then the number of insertions/deletions
  94        may be >= the best distance so far.  If so, we can reject
  95        the candidate immediately without needing to compute
  96        the exact distance, since it won't be an improvement.  */
  97     if (min_candidate_distance >= m_best_distance)
  98       return;
  99
 100     /* If the candidate will be unable to beat the criterion in
 101        get_best_meaningful_candidate, reject it without computing
 102        the exact distance.  */
 103     unsigned int cutoff = MAX (m_goal_len, candidate_len) / 2;
 104     if (min_candidate_distance > cutoff)
 105       return;
 106
 107     /* Otherwise, compute the distance and see if the candidate
 108        has beaten the previous best value.  */
 109     edit_distance_t dist
 110       = levenshtein_distance (m_goal, m_goal_len,
 111                               candidate_traits::get_string (candidate),
 112                               candidate_len);
 113     if (dist < m_best_distance)
 114       {
 115         m_best_distance = dist;
 116         m_best_candidate = candidate;
 117         m_best_candidate_len = candidate_len;
 118       }
 119   }
 120
 121   /* Get the best candidate so far, but applying a filter to ensure
 122      that we return NULL if none of the candidates are close to the goal,
 123      to avoid offering nonsensical suggestions to the user.  */
 124
 125   candidate_t get_best_meaningful_candidate () const
 126   {
 127     /* If more than half of the letters were misspelled, the suggestion is
 128        likely to be meaningless.  */
 129     if (m_best_candidate)
 130       {
 131         unsigned int cutoff = MAX (m_goal_len, m_best_candidate_len) / 2;
 132         if (m_best_distance > cutoff)
 133           return NULL;
 134     }
 135     return m_best_candidate;
 136   }
 137
 138  private:
 139   const char *m_goal;
 140   size_t m_goal_len;
 141   candidate_t m_best_candidate;
 142   edit_distance_t m_best_distance;
 143   size_t m_best_candidate_len;
 144 };
 145
 146 #endif  /* GCC_SPELLCHECK_H  */