function index($datapath, $dbpath) { // Create or open the database we're going to be writing to. $db = new XapianWritableDatabase($dbpath, Xapian::DB_CREATE_OR_OPEN); // Set up a TermGenerator that we'll use in indexing $termgenerator = new XapianTermGenerator(); $termgenerator->set_stemmer(new XapianStem('en')); // open the file $fH = open_file($datapath); // Read the header row in $headers = get_csv_headers($fH); while (($row = parse_csv_row($fH, $headers)) !== false) { // mapping from field name to value using first row headers // We're just going to use id_NUMBER, TITLE and DESCRIPTION $description = $row['DESCRIPTION']; $title = $row['TITLE']; $identifier = $row['id_NUMBER']; $collection = $row['COLLECTION']; $maker = $row['MAKER']; // we make a document and tell the term generator to use this $doc = new XapianDocument(); $termgenerator->set_document($doc); // index each field with a suitable prefix $termgenerator->index_text($title, 1, 'S'); $termgenerator->index_text($description, 1, 'XD'); // index fields without prefixes for general search $termgenerator->index_text($title); $termgenerator->increase_termpos(); $termgenerator->index_text($description); ### Start of new indexing code. // index the MATERIALS field, splitting on semicolons $materials = explode(";", $row['MATERIALS']); foreach ($materials as $material) { $material = strtolower(trim($material)); if ($material != '') { $doc->add_boolean_term('XM' . $material); } } ### End of new indexing code. // store all the fields for display purposes $doc->set_data(json_encode($row)); // we use the identifier to ensure each object ends up // in the database only once no matter how many times // we run the indexer $idterm = "Q" . $identifier; $doc->add_term($idterm); $db->replace_document($idterm, $doc); } }
function index($datapath, $dbpath) { // Create or open the database we're going to be writing to. $db = new XapianWritableDatabase($dbpath, Xapian::DB_CREATE_OR_OPEN); // Set up a TermGenerator that we'll use in indexing. $termgenerator = new XapianTermGenerator(); $termgenerator->set_stemmer(new XapianStem('english')); // Open the file. $fH = open_file($datapath); // Read the header row in. $headers = get_csv_headers($fH); while (($row = parse_csv_row($fH, $headers)) !== false) { // '$row' maps field name to value. The field names come from the // first row of the CSV file. // // We're just going to use DESCRIPTION, TITLE and id_NUMBER. $description = $row['DESCRIPTION']; $title = $row['TITLE']; $identifier = $row['id_NUMBER']; // We make a document and tell the term generator to use this. $doc = new XapianDocument(); $termgenerator->set_document($doc); // Index each field with a suitable prefix. $termgenerator->index_text($title, 1, 'S'); $termgenerator->index_text($description, 1, 'XD'); // Index fields without prefixes for general search. $termgenerator->index_text($title); $termgenerator->increase_termpos(); $termgenerator->index_text($description); // Store all the fields for display purposes. $doc->set_data(json_encode($row)); // We use the identifier to ensure each object ends up in the // database only once no matter how many times we run the // indexer. $idterm = "Q" . $identifier; $doc->add_boolean_term($idterm); $db->replace_document($idterm, $doc); } }
$indexer = new XapianTermGenerator(); $stemmer = new XapianStem("english"); $indexer->set_stemmer($stemmer); $para = ''; $lines = file("php://stdin"); foreach ($lines as $line) { $line = rtrim($line); if ($line == "" && $para != "") { // We've reached the end of a paragraph, so index it. $doc = new XapianDocument(); $doc->set_data($para); $indexer->set_document($doc); $indexer->index_text($para); // Add the document to the database. $database->add_document($doc); $para = ""; } else { if ($para != "") { $para .= " "; } $para .= $line; } } // Set the database handle to Null to ensure that it gets closed // down cleanly or uncommitted changes may be lost.
$values[$term] = $k->get_termfreq(); } $expected = array("ABB" => 1, "ABC" => 1, "ABC" => 1, "ABCD" => 1, "ABCÿ" => 1); if ($values != $expected) { print "Unexpected matchspy values():\n"; var_dump($values); var_dump($expected); print "\n"; exit(1); } # Regression test for SWIG bug - it was generating "return $r;" in wrapper # functions which didn't set $r. $indexer = new XapianTermGenerator(); $doc = new XapianDocument(); $indexer->set_document($doc); $indexer->index_text("I ask nothing in return"); $indexer->index_text_without_positions("Tea time"); $indexer->index_text("Return in time"); $s = ''; foreach ($doc->termlist_begin() as $term) { $s .= $term . ' '; } if ($s !== 'ask i in nothing return tea time ') { print "PHP Iterator wrapping of TermIterator doesn't work ({$s})\n"; exit(1); } $s = ''; foreach ($doc->termlist_begin() as $k => $term) { $s .= $term . ':' . $k->get_wdf() . ' '; } if ($s !== 'ask:1 i:1 in:2 nothing:1 return:2 tea:1 time:2 ') {
$query = XapianQuery::MatchNothing(); if ($query->get_description() != 'Xapian::Query()') { print "Unexpected \$query->get_description():\n"; print $query->get_description() . "\n"; exit(1); } $matchspy = new XapianValueCountMatchSpy(0); $enquire->add_matchspy($matchspy); $enquire->get_mset(0, 10); $beg = $matchspy->values_begin(); $end = $matchspy->values_end(); $values = array(); while (!$beg->equals($end)) { $values[$beg->get_term()] = $beg->get_termfreq(); $beg->next(); } $expected = array("ABB" => 1, "ABC" => 1, "ABC" => 1, "ABCD" => 1, "ABCÿ" => 1); if ($values != $expected) { print "Unexpected matchspy values():\n"; var_dump($values); var_dump($expected); print "\n"; exit(1); } # Regression test for SWIG bug - it was generating "return $r;" in wrapper # functions which didn't set $r. $indexer = new XapianTermGenerator(); $doc = new XapianDocument(); $indexer->set_document($doc); $indexer->index_text("I ask nothing in return"); $indexer->index_text_without_positions("Tea time");
$text = trim($text); if (!$text) { continue; } $noise = 0; if ($text != 'I' && !preg_match('#[a-z!.]#', $text) && $color == 'white') { $noise = 1; } $id = "{$series}-{$epid}-{$rowcount}"; $doc = new XapianDocument(); $indexer->set_document($doc); $doc->set_data($text); $doc->add_term("A{$align}"); $doc->add_term("B{$begin}"); $doc->add_term("C{$color}"); $doc->add_term("E{$epid}"); $doc->add_term("I{$rowcount}"); $doc->add_term("N{$noise}"); $doc->add_term("Q{$id}"); $doc->add_term("S{$series}"); $doc->add_value(0, Xapian::sortable_serialise($beginN)); $doc->add_value(1, sprintf("%d%02d", $series, $epid)); $indexer->index_text($text); $db->add_document($doc); $rowcount++; } $lasttextarr = $safetextarr; } } } $db = null;
/** * Index file contents * * @param array $lines The array of the file contents, each entry corresponds to a new line (included) */ protected function _index($lines, $file_path) { if (empty($lines)) { return false; } // Open the database for update, creating a new database if necessary. $database = new XapianWritableDatabase(self::$_database_path, Xapian::DB_CREATE_OR_OPEN); $indexer = new XapianTermGenerator(); $stemmer = new XapianStem("english"); $indexer->set_stemmer($stemmer); $para = ''; //$lines = file($path); foreach ($lines as $line) { $line = rtrim($line); if ($line == "" && $para != "") { // We've reached the end of a paragraph, so index it. $doc = new XapianDocument(); $doc->set_data($para); $doc->add_value('file', $file_path); //add meta-information to the entry $indexer->set_document($doc); $indexer->index_text($para); // Add the document to the database. $database->add_document($doc); $para = ""; } else { if ($para != "") { $para .= " "; } $para .= $line; } } // Set the database handle to Null to ensure that it gets closed // down cleanly or uncommitted changes may be lost. $database = Null; }