xapian-core/api/keymaker.cc

   1 /** @file keymaker.cc
   2  * @brief Build key strings for MSet ordering or collapsing.
   3  */
   4 /* Copyright (C) 2007,2009,2011,2015 Olly Betts
   5  * Copyright (C) 2010 Richard Boulton
   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 #include <config.h>
  23
  24 #include "xapian/keymaker.h"
  25
  26 #include "xapian/document.h"
  27
  28 #include <string>
  29 #include <vector>
  30
  31 using namespace std;
  32
  33 namespace Xapian {
  34
  35 KeyMaker::~KeyMaker() { }
  36
  37 string
  38 MultiValueKeyMaker::operator()(const Xapian::Document & doc) const
  39 {
  40     string result;
  41
  42     auto i = slots.begin();
  43     // Don't crash if slots is empty.
  44     if (rare(i == slots.end())) return result;
  45
  46     size_t last_not_empty_forwards = 0;
  47     while (true) {
  48         // All values (except for the last if it's sorted forwards) need to
  49         // be adjusted.
  50         //
  51         // FIXME: allow Xapian::BAD_VALUENO to mean "relevance?"
  52         string v = doc.get_value(i->slot);
  53         bool reverse_sort = i->reverse;
  54
  55         if (v.empty()) {
  56             v = i->defvalue;
  57         }
  58
  59         if (reverse_sort || !v.empty())
  60             last_not_empty_forwards = result.size();
  61
  62         if (++i == slots.end() && !reverse_sort) {
  63             if (v.empty()) {
  64                 // Trim off all the trailing empty forwards values.
  65                 result.resize(last_not_empty_forwards);
  66             } else {
  67                 // No need to adjust the last value if it's sorted forwards.
  68                 result += v;
  69             }
  70             break;
  71         }
  72
  73         if (reverse_sort) {
  74             // For a reverse ordered value, we subtract each byte from '\xff',
  75             // except for '\0' which we convert to "\xff\0".  We insert
  76             // "\xff\xff" after the encoded value.
  77             for (string::const_iterator j = v.begin(); j != v.end(); ++j) {
  78                 unsigned char ch = static_cast<unsigned char>(*j);
  79                 result += char(255 - ch);
  80                 if (ch == 0) result += '\0';
  81             }
  82             result.append("\xff\xff", 2);
  83             if (i == slots.end()) break;
  84             last_not_empty_forwards = result.size();
  85         } else {
  86             // For a forward ordered value (unless it's the last value), we
  87             // convert any '\0' to "\0\xff".  We insert "\0\0" after the
  88             // encoded value.
  89             string::size_type j = 0, nul;
  90             while ((nul = v.find('\0', j)) != string::npos) {
  91                 ++nul;
  92                 result.append(v, j, nul - j);
  93                 result += '\xff';
  94                 j = nul;
  95             }
  96             result.append(v, j, string::npos);
  97             if (!v.empty())
  98                 last_not_empty_forwards = result.size();
  99             result.append("\0", 2);
 100         }
 101     }
 102     return result;
 103 }
 104
 105 }