xapian-applications/omega/utf8truncate.cc

   1 /* utf8truncate.cc: truncate a utf-8 string, ideally without splitting words.
   2  *
   3  * Copyright (C) 2007 Olly Betts
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with this program; if not, write to the Free Software
  17  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
  18  */
  19
  20 #include <config.h>
  21
  22 #include "utf8truncate.h"
  23 #include <string>
  24
  25 using namespace std;
  26
  27 bool
  28 utf8_truncate(string & value, string::size_type maxlen)
  29 {
  30     if (value.size() <= maxlen) return false;
  31
  32     string::size_type len = maxlen;
  33     // Skip back to (and past) the last whitespace.
  34     while (len && static_cast<unsigned char>(value[len - 1]) > 32) --len;
  35     while (len && static_cast<unsigned char>(value[len - 1]) <= 32) --len;
  36
  37     // If the first word is too long, truncate it.
  38     if (!len) {
  39         len = maxlen;
  40         // Skip back to before any UTF-8 character which spans the cut point.
  41         // We can just look at the byte after the cut point - if it's a
  42         // "sequence start" byte then we're OK, otherwise step back until we
  43         // get to a "sequence start" byte.
  44         while (len && (value[len] & 0xc0) == 0x80) --len;
  45     }
  46     value.resize(len);
  47
  48     return true;
  49 }