xapian-bindings/php4/docs/examples/simpleindex.php

   1 <?php
   2 /* $Id$
   3  * Index each paragraph in a textfile as a document
   4  *
   5  * ----START-LICENCE----
   6  * Copyright 2004 James Aylett
   7  *
   8  * This program is free software; you can redistribute it and/or
   9  * modify it under the terms of the GNU General Public License as
  10  * published by the Free Software Foundation; either version 2 of the
  11  * License, or (at your option) any later version.
  12  *
  13  * This program is distributed in the hope that it will be useful,
  14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16  * GNU General Public License for more details.
  17  *
  18  * You should have received a copy of the GNU General Public License
  19  * along with this program; if not, write to the Free Software
  20  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
  21  * USA
  22  * -----END-LICENCE-----
  23  */
  24
  25 define('MAX_PROB_TERM_LENGTH', 64);
  26
  27 function p_alnum($c)
  28 {
  29     return ctype_alnum($c);
  30 }
  31
  32 function p_notalnum($c)
  33 {
  34     return !ctype_alnum($c);
  35 }
  36
  37 function p_notplusminus($c)
  38 {
  39     return $c!='+' and $c!='-';
  40 }
  41
  42 function find_p($string, $start, $predicate)
  43 {
  44     while ($start < strlen($string) and
  45            !$predicate(substr($string, $start, 1))) {
  46         $start ++;
  47     }
  48     return $start;
  49 }
  50
  51 if (!isset($_SERVER['argv']) or count($_SERVER['argv']) != 2) {
  52     print "usage: {$_SERVER['argv'][0]} <path to database>\n";
  53     exit;
  54 }
  55
  56 $database = open_writable($_SERVER['argv'][1], DB_CREATE_OR_OPEN);
  57 if (!$database) {
  58     print "Died! :-(\n";
  59     exit;
  60 }
  61 $stemmer = new_Stem("english");
  62 $para = '';
  63 $lines = file("php://stdin");
  64 foreach ($lines as $line) {
  65     $line = rtrim($line);
  66     if ($line=="") {
  67         if ($para!="") {
  68             $doc = new_Document();
  69             Document_set_data($doc, $para);
  70             $pos = 0;
  71             /*
  72              * At each point, find the next alnum character (i), then
  73              * find the first non-alnum character after that (j). Find
  74              * the first non-plusminus character after that (k), and if
  75              * k is non-alnum (or is off the end of the para), set j=k.
  76              * The term generation string is [i,j), so len = j-i
  77              */
  78             $i = 0;
  79             $j = 0;
  80             while ($i<strlen($para)) {
  81                 $i = find_p($para, $j, 'p_alnum');
  82                 $j = find_p($para, $i, 'p_notalnum');
  83                 $k = find_p($para, $j, 'p_notplusminus');
  84                 if ($k==strlen($para) or !p_alnum(substr($para, $k, 1))) {
  85                     $j = $k;
  86                 }
  87                 if ($j-$i <= MAX_PROB_TERM_LENGTH and $j>$i) {
  88                     $term = stem_stem_word($stemmer, substr($para, $i, $j-$i));
  89                     Document_add_posting($doc, $term, $pos);
  90                     $pos ++;
  91                 }
  92                 $i = $j;
  93             }
  94             WritableDatabase_add_document($database, $doc);
  95             WritableDatabase_flush($database);
  96             $para = "";
  97         }
  98     } else {
  99         if ($para!="") {
 100             $para .= " ";
 101         }
 102         $para .= $line;
 103     }
 104 }
 105 delete_WritableDatabase($database);
 106 ?>