xapian-core/backends/byte_length_strings.h

   1 /** @file byte_length_strings.h
   2  * @brief Handle decoding lists of strings with byte lengths
   3  */
   4 /* Copyright (C) 2004,2005,2006,2007,2008,2009,2010 Olly Betts
   5  *
   6  * This program is free software; you can redistribute it and/or
   7  * modify it under the terms of the GNU General Public License as
   8  * published by the Free Software Foundation; either version 2 of the
   9  * License, or (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License
  17  * along with this program; if not, write to the Free Software
  18  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
  19  * USA
  20  */
  21
  22 #ifndef XAPIAN_INCLUDED_BYTE_LENGTH_STRINGS_H
  23 #define XAPIAN_INCLUDED_BYTE_LENGTH_STRINGS_H
  24
  25 #include <xapian/error.h>
  26
  27 #include <string>
  28
  29 // We XOR the length values with this so that they are more likely to coincide
  30 // with lower case ASCII letters, which are likely to be common.  This means
  31 // that zlib should do a better job of compressing tag values - in tests, this
  32 // gave 5% better compression.
  33 #define MAGIC_XOR_VALUE 96
  34
  35 class ByteLengthPrefixedStringItor {
  36     const unsigned char * p;
  37     size_t left;
  38
  39     ByteLengthPrefixedStringItor(const unsigned char * p_, size_t left_)
  40         : p(p_), left(left_) { }
  41
  42   public:
  43     explicit ByteLengthPrefixedStringItor(const std::string & s)
  44         : p(reinterpret_cast<const unsigned char *>(s.data())),
  45           left(s.size()) { }
  46
  47     std::string operator*() const {
  48         size_t len = *p ^ MAGIC_XOR_VALUE;
  49         return std::string(reinterpret_cast<const char *>(p + 1), len);
  50     }
  51
  52     ByteLengthPrefixedStringItor operator++(int) {
  53         const unsigned char * old_p = p;
  54         size_t old_left = left;
  55         operator++();
  56         return ByteLengthPrefixedStringItor(old_p, old_left);
  57     }
  58
  59     ByteLengthPrefixedStringItor & operator++() {
  60         if (!left) {
  61             throw Xapian::DatabaseCorruptError("Bad synonym data (none left)");
  62         }
  63         size_t add = (*p ^ MAGIC_XOR_VALUE) + 1;
  64         if (left < add) {
  65             throw Xapian::DatabaseCorruptError("Bad synonym data (too little left)");
  66         }
  67         p += add;
  68         left -= add;
  69         return *this;
  70     }
  71
  72     bool at_end() const {
  73         return left == 0;
  74     }
  75 };
  76
  77 struct ByteLengthPrefixedStringItorGt {
  78     /// Return true if and only if a's string is strictly greater than b's.
  79     bool operator()(const ByteLengthPrefixedStringItor *a,
  80                     const ByteLengthPrefixedStringItor *b) const {
  81         return (**a > **b);
  82     }
  83 };
  84
  85 #endif // XAPIAN_INCLUDED_BYTE_LENGTH_STRINGS_H