sphinxapi.php

做搜索的

<?php

//
// $Id$
//

//
// Copyright (c) 2001-2008, Andrew Aksyonoff. All rights reserved.
//
// This program is free software; you can redistribute it and/or modify
// it under the terms of the GNU General Public License. You should have
// received a copy of the GPL license along with this program; if you
// did not, you can find it at http://www.gnu.org/
//

/////////////////////////////////////////////////////////////////////////////
// PHP version of Sphinx searchd client (PHP API)
/////////////////////////////////////////////////////////////////////////////

/// known searchd commands
define ( "SEARCHD_COMMAND_SEARCH",	0 );
define ( "SEARCHD_COMMAND_EXCERPT",	1 );
define ( "SEARCHD_COMMAND_UPDATE",	2 );
define ( "SEARCHD_COMMAND_KEYWORDS",3 );

/// current client-side command implementation versions
define ( "VER_COMMAND_SEARCH",		0x113 );
define ( "VER_COMMAND_EXCERPT",		0x100 );
define ( "VER_COMMAND_UPDATE",		0x101 );
define ( "VER_COMMAND_KEYWORDS",	0x100 );

/// known searchd status codes
define ( "SEARCHD_OK",				0 );
define ( "SEARCHD_ERROR",			1 );
define ( "SEARCHD_RETRY",			2 );
define ( "SEARCHD_WARNING",			3 );

/// known match modes
define ( "SPH_MATCH_ALL",			0 );
define ( "SPH_MATCH_ANY",			1 );
define ( "SPH_MATCH_PHRASE",		2 );
define ( "SPH_MATCH_BOOLEAN",		3 );
define ( "SPH_MATCH_EXTENDED",		4 );
define ( "SPH_MATCH_FULLSCAN",		5 );
define ( "SPH_MATCH_EXTENDED2",		6 );	// extended engine V2 (TEMPORARY, WILL BE REMOVED)

/// known ranking modes (ext2 only)
define ( "SPH_RANK_PROXIMITY_BM25",	0 );	///< default mode, phrase proximity major factor and BM25 minor one
define ( "SPH_RANK_BM25",			1 );	///< statistical mode, BM25 ranking only (faster but worse quality)
define ( "SPH_RANK_NONE",			2 );	///< no ranking, all matches get a weight of 1
define ( "SPH_RANK_WORDCOUNT",		3 );	///< simple word-count weighting, rank is a weighted sum of per-field keyword occurence counts

/// known sort modes
define ( "SPH_SORT_RELEVANCE",		0 );
define ( "SPH_SORT_ATTR_DESC",		1 );
define ( "SPH_SORT_ATTR_ASC",		2 );
define ( "SPH_SORT_TIME_SEGMENTS", 	3 );
define ( "SPH_SORT_EXTENDED", 		4 );
define ( "SPH_SORT_EXPR", 			5 );

/// known filter types
define ( "SPH_FILTER_VALUES",		0 );
define ( "SPH_FILTER_RANGE",		1 );
define ( "SPH_FILTER_FLOATRANGE",	2 );

/// known attribute types
define ( "SPH_ATTR_INTEGER",		1 );
define ( "SPH_ATTR_TIMESTAMP",		2 );
define ( "SPH_ATTR_ORDINAL",		3 );
define ( "SPH_ATTR_BOOL",			4 );
define ( "SPH_ATTR_FLOAT",			5 );
define ( "SPH_ATTR_MULTI",			0x40000000 );

/// known grouping functions
define ( "SPH_GROUPBY_DAY",			0 );
define ( "SPH_GROUPBY_WEEK",		1 );
define ( "SPH_GROUPBY_MONTH",		2 );
define ( "SPH_GROUPBY_YEAR",		3 );
define ( "SPH_GROUPBY_ATTR",		4 );
define ( "SPH_GROUPBY_ATTRPAIR",	5 );


/// portably pack numeric to 64 unsigned bits, network order
function sphPack64 ( $v )
{
	assert ( is_numeric($v) );

	// x64 route
	if ( PHP_INT_SIZE>=8 )
	{
		$i = (int)$v;
		return pack ( "NN", $i>>32, $i&((1<<32)-1) );
	}

	// x32 route, bcmath
	$x = "4294967296";
	if ( function_exists("bcmul") )
	{
		$h = bcdiv ( $v, $x, 0 );
		$l = bcmod ( $v, $x );
		return pack ( "NN", (float)$h, (float)$l ); // conversion to float is intentional; int would lose 31st bit
	}

	// x32 route, 15 or less decimal digits
	// we can use float, because its actually double and has 52 precision bits
	if ( strlen($v)<=15 )
	{
		$f = (float)$v;
		$h = (int)($f/$x);
		$l = (int)($f-$x*$h);
		return pack ( "NN", $h, $l );
	}

	// x32 route, 16 or more decimal digits
	// well, let me know if you *really* need this
	die ( "INTERNAL ERROR: packing more than 15-digit numeric on 32-bit PHP is not implemented yet (contact support)" );
}


/// portably unpack 64 unsigned bits, network order to numeric
function sphUnpack64 ( $v )
{
	list($h,$l) = array_values ( unpack ( "N*N*", $v ) );

	// x64 route
	if ( PHP_INT_SIZE>=8 )
	{
		if ( $h<0 ) $h += (1<<32); // because php 5.2.2 to 5.2.5 is totally fucked up again
		if ( $l<0 ) $l += (1<<32);
		return ($h<<32) + $l;
	}

	// x32 route
	$h = sprintf ( "%u", $h );
	$l = sprintf ( "%u", $l );
	$x = "4294967296";

	// bcmath
	if ( function_exists("bcmul") )
		return bcadd ( $l, bcmul ( $x, $h ) );

	// no bcmath, 15 or less decimal digits
	// we can use float, because its actually double and has 52 precision bits
	if ( $h<1048576 )
	{
		$f = ((float)$h)*$x + (float)$l;
		return sprintf ( "%.0f", $f ); // builtin conversion is only about 39-40 bits precise!
	}

	// x32 route, 16 or more decimal digits
	// well, let me know if you *really* need this
	die ( "INTERNAL ERROR: unpacking more than 15-digit numeric on 32-bit PHP is not implemented yet (contact support)" );
}


/// sphinx searchd client class
class SphinxClient
{
	var $_host;			///< searchd host (default is "localhost")
	var $_port;			///< searchd port (default is 3312)
	var $_offset;		///< how many records to seek from result-set start (default is 0)
	var $_limit;		///< how many records to return from result-set starting at offset (default is 20)
	var $_mode;			///< query matching mode (default is SPH_MATCH_ALL)
	var $_weights;		///< per-field weights (default is 1 for all fields)
	var $_sort;			///< match sorting mode (default is SPH_SORT_RELEVANCE)
	var $_sortby;		///< attribute to sort by (defualt is "")
	var $_min_id;		///< min ID to match (default is 0, which means no limit)
	var $_max_id;		///< max ID to match (default is 0, which means no limit)
	var $_filters;		///< search filters
	var $_groupby;		///< group-by attribute name
	var $_groupfunc;	///< group-by function (to pre-process group-by attribute value with)
	var $_groupsort;	///< group-by sorting clause (to sort groups in result set with)
	var $_groupdistinct;///< group-by count-distinct attribute
	var $_maxmatches;	///< max matches to retrieve
	var $_cutoff;		///< cutoff to stop searching at (default is 0)
	var $_retrycount;	///< distributed retries count
	var $_retrydelay;	///< distributed retries delay
	var $_anchor;		///< geographical anchor point
	var $_indexweights;	///< per-index weights
	var $_ranker;		///< ranking mode (default is SPH_RANK_PROXIMITY_BM25)
	var $_maxquerytime;	///< max query time, milliseconds (default is 0, do not limit)
	var $_fieldweights;	///< per-field-name weights

	var $_error;		///< last error message
	var $_warning;		///< last warning message

	var $_reqs;			///< requests array for multi-query
	var $_mbenc;		///< stored mbstring encoding
	var $_arrayresult;	///< whether $result["matches"] should be a hash or an array

	/////////////////////////////////////////////////////////////////////////////
	// common stuff
	/////////////////////////////////////////////////////////////////////////////

	/// create a new client object and fill defaults
	function SphinxClient ()
	{
		// per-client-object settings
		$this->_host		= "localhost";
		$this->_port		= 3312;

		// per-query settings
		$this->_offset		= 0;
		$this->_limit		= 20;
		$this->_mode		= SPH_MATCH_ALL;
		$this->_weights		= array ();
		$this->_sort		= SPH_SORT_RELEVANCE;
		$this->_sortby		= "";
		$this->_min_id		= 0;
		$this->_max_id		= 0;
		$this->_filters		= array ();
		$this->_groupby		= "";
		$this->_groupfunc	= SPH_GROUPBY_DAY;
		$this->_groupsort	= "@group desc";
		$this->_groupdistinct= "";
		$this->_maxmatches	= 1000;
		$this->_cutoff		= 0;
		$this->_retrycount	= 0;
		$this->_retrydelay	= 0;
		$this->_anchor		= array ();
		$this->_indexweights= array ();
		$this->_ranker		= SPH_RANK_PROXIMITY_BM25;
		$this->_maxquerytime= 0;
		$this->_fieldweights= array();

		$this->_error		= ""; // per-reply fields (for single-query case)
		$this->_warning		= "";
		$this->_reqs		= array ();	// requests storage (for multi-query case)
		$this->_mbenc		= "";
		$this->_arrayresult	= false;
	}

	/// get last error message (string)
	function GetLastError ()
	{
		return $this->_error;
	}

	/// get last warning message (string)
	function GetLastWarning ()
	{
		return $this->_warning;
	}

	/// set searchd host name (string) and port (integer)
	function SetServer ( $host, $port )
	{
		assert ( is_string($host) );
		assert ( is_int($port) );
		$this->_host = $host;
		$this->_port = $port;
	}

	/////////////////////////////////////////////////////////////////////////////

	/// enter mbstring workaround mode
	function _MBPush ()
	{
		$this->_mbenc = "";
		if ( ini_get ( "mbstring.func_overload" ) & 2 )
		{
			$this->_mbenc = mb_internal_encoding();
			mb_internal_encoding ( "latin1" );
		}
    }

	/// leave mbstring workaround mode
	function _MBPop ()
	{
		if ( $this->_mbenc )
			mb_internal_encoding ( $this->_mbenc );
	}

	/// connect to searchd server
	function _Connect ()
	{
		return fopen('php://stdout', 'w');
	}
	
	function _OldConnect()
	{
		if (!( $fp = @fsockopen ( $this->_host, $this->_port ) ) )
		{
			$this->_error = "connection to {$this->_host}:{$this->_port} failed";
			return false;
		}

		// check version
		list(,$v) = unpack ( "N*", fread ( $fp, 4 ) );
		$v = (int)$v;
		if ( $v<1 )
		{
			fclose ( $fp );
			$this->_error = "expected searchd protocol version 1+, got version '$v'";
			return false;
		}

		// all ok, send my version
		fwrite ( $fp, pack ( "N", 1 ) );
		return $fp;
	}

	/// get and check response packet from searchd server
	function _GetResponse ( $fp, $client_ver )
	{
		return false;
	}
	
	function _OldGetResponse ( $fp, $client_ver )
	{
		$response = "";
		$len = 0;

		$header = fread ( $fp, 8 );
		if ( strlen($header)==8 )
		{
			list ( $status, $ver, $len ) = array_values ( unpack ( "n2a/Nb", $header ) );
			$left = $len;
			while ( $left>0 && !feof($fp) )
			{
				$chunk = fread ( $fp, $left );
				if ( $chunk )
				{
					$response .= $chunk;
					$left -= strlen($chunk);
				}
			}
		}
		fclose ( $fp );

		// check response
		$read = strlen ( $response );
		if ( !$response || $read!=$len )
		{
			$this->_error = $len
				? "failed to read searchd response (status=$status, ver=$ver, len=$len, read=$read)"
				: "received zero-sized searchd response";
			return false;
		}

		// check status
		if ( $status==SEARCHD_WARNING )
		{
			list(,$wlen) = unpack ( "N*", substr ( $response, 0, 4 ) );
			$this->_warning = substr ( $response, 4, $wlen );
			return substr ( $response, 4+$wlen );
		}
		if ( $status==SEARCHD_ERROR )
		{
			$this->_error = "searchd error: " . substr ( $response, 4 );
			return false;
		}
		if ( $status==SEARCHD_RETRY )
		{
			$this->_error = "temporary searchd error: " . substr ( $response, 4 );
			return false;
		}
		if ( $status!=SEARCHD_OK )
		{
			$this->_error = "unknown status code '$status'";
			return false;
		}

		// check version
		if ( $ver<$client_ver )
		{
			$this->_warning = sprintf ( "searchd command v.%d.%d older than client's v.%d.%d, some options might not work",
				$ver>>8, $ver&0xff, $client_ver>>8, $client_ver&0xff );
		}

		return $response;
	}

	/////////////////////////////////////////////////////////////////////////////
	// searching
	/////////////////////////////////////////////////////////////////////////////

	/// set offset and count into result set,
	/// and optionally set max-matches and cutoff limits
	function SetLimits ( $offset, $limit, $max=0, $cutoff=0 )
	{
		assert ( is_int($offset) );
		assert ( is_int($limit) );
		assert ( $offset>=0 );
		assert ( $limit>0 );
		assert ( $max>=0 );
		$this->_offset = $offset;
		$this->_limit = $limit;
		if ( $max>0 )
			$this->_maxmatches = $max;
		if ( $cutoff>0 )
			$this->_cutoff = $cutoff;
	}