CC-2166: Packaging Improvements. Moved the Zend app into airtime_mvc. It is now installed to /var/www/airtime. Storage is now set to /srv/airtime/stor. Utils are now installed to /usr/lib/airtime/utils/. Added install/airtime-dircheck.php as a simple test to see if everything is install/uninstalled correctly.
This commit is contained in:
Paul Baranowski
parent
514777e8d2
commit
b11cbd8159
4546 changed files with 138 additions and 51 deletions
|
|
@ -0,0 +1,92 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: Common.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Define constant used to provide correct file processing order */
|
||||
/** @todo Section should be removed with ZF 2.0 release as obsolete */
|
||||
define('ZEND_SEARCH_LUCENE_COMMON_ANALYZER_PROCESSED', true);
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Token */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Token.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_TokenFilter */
|
||||
require_once 'Zend/Search/Lucene/Analysis/TokenFilter.php';
|
||||
|
||||
|
||||
/**
|
||||
* Common implementation of the Zend_Search_Lucene_Analysis_Analyzer interface.
|
||||
* There are several standard standard subclasses provided by Zend_Search_Lucene/Analysis
|
||||
* subpackage: Zend_Search_Lucene_Analysis_Analyzer_Common_Text, ZSearchHTMLAnalyzer, ZSearchXMLAnalyzer.
|
||||
*
|
||||
* @todo ZSearchHTMLAnalyzer and ZSearchXMLAnalyzer implementation
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
abstract class Zend_Search_Lucene_Analysis_Analyzer_Common extends Zend_Search_Lucene_Analysis_Analyzer
|
||||
{
|
||||
/**
|
||||
* The set of Token filters applied to the Token stream.
|
||||
* Array of Zend_Search_Lucene_Analysis_TokenFilter objects.
|
||||
*
|
||||
* @var array
|
||||
*/
|
||||
private $_filters = array();
|
||||
|
||||
/**
|
||||
* Add Token filter to the Analyzer
|
||||
*
|
||||
* @param Zend_Search_Lucene_Analysis_TokenFilter $filter
|
||||
*/
|
||||
public function addFilter(Zend_Search_Lucene_Analysis_TokenFilter $filter)
|
||||
{
|
||||
$this->_filters[] = $filter;
|
||||
}
|
||||
|
||||
/**
|
||||
* Apply filters to the token. Can return null when the token was removed.
|
||||
*
|
||||
* @param Zend_Search_Lucene_Analysis_Token $token
|
||||
* @return Zend_Search_Lucene_Analysis_Token
|
||||
*/
|
||||
public function normalize(Zend_Search_Lucene_Analysis_Token $token)
|
||||
{
|
||||
foreach ($this->_filters as $filter) {
|
||||
$token = $filter->normalize($token);
|
||||
|
||||
// resulting token can be null if the filter removes it
|
||||
if ($token === null) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
return $token;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,96 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: Text.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Text extends Zend_Search_Lucene_Analysis_Analyzer_Common
|
||||
{
|
||||
/**
|
||||
* Current position in a stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_position;
|
||||
|
||||
/**
|
||||
* Reset token stream
|
||||
*/
|
||||
public function reset()
|
||||
{
|
||||
$this->_position = 0;
|
||||
|
||||
if ($this->_input === null) {
|
||||
return;
|
||||
}
|
||||
|
||||
// convert input into ascii
|
||||
if (PHP_OS != 'AIX') {
|
||||
$this->_input = iconv($this->_encoding, 'ASCII//TRANSLIT', $this->_input);
|
||||
}
|
||||
$this->_encoding = 'ASCII';
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenization stream API
|
||||
* Get next token
|
||||
* Returns null at the end of stream
|
||||
*
|
||||
* @return Zend_Search_Lucene_Analysis_Token|null
|
||||
*/
|
||||
public function nextToken()
|
||||
{
|
||||
if ($this->_input === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
do {
|
||||
if (! preg_match('/[a-zA-Z]+/', $this->_input, $match, PREG_OFFSET_CAPTURE, $this->_position)) {
|
||||
// It covers both cases a) there are no matches (preg_match(...) === 0)
|
||||
// b) error occured (preg_match(...) === FALSE)
|
||||
return null;
|
||||
}
|
||||
|
||||
$str = $match[0][0];
|
||||
$pos = $match[0][1];
|
||||
$endpos = $pos + strlen($str);
|
||||
|
||||
$this->_position = $endpos;
|
||||
|
||||
$token = $this->normalize(new Zend_Search_Lucene_Analysis_Token($str, $pos, $endpos));
|
||||
} while ($token === null); // try again if token is skipped
|
||||
|
||||
return $token;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: CaseInsensitive.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common_Text */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common/Text.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_TokenFilter_LowerCase */
|
||||
require_once 'Zend/Search/Lucene/Analysis/TokenFilter/LowerCase.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Text_CaseInsensitive extends Zend_Search_Lucene_Analysis_Analyzer_Common_Text
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
$this->addFilter(new Zend_Search_Lucene_Analysis_TokenFilter_LowerCase());
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,95 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: TextNum.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_TextNum extends Zend_Search_Lucene_Analysis_Analyzer_Common
|
||||
{
|
||||
/**
|
||||
* Current position in a stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_position;
|
||||
|
||||
/**
|
||||
* Reset token stream
|
||||
*/
|
||||
public function reset()
|
||||
{
|
||||
$this->_position = 0;
|
||||
|
||||
if ($this->_input === null) {
|
||||
return;
|
||||
}
|
||||
|
||||
// convert input into ascii
|
||||
if (PHP_OS != 'AIX') {
|
||||
$this->_input = iconv($this->_encoding, 'ASCII//TRANSLIT', $this->_input);
|
||||
}
|
||||
$this->_encoding = 'ASCII';
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenization stream API
|
||||
* Get next token
|
||||
* Returns null at the end of stream
|
||||
*
|
||||
* @return Zend_Search_Lucene_Analysis_Token|null
|
||||
*/
|
||||
public function nextToken()
|
||||
{
|
||||
if ($this->_input === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
do {
|
||||
if (! preg_match('/[a-zA-Z0-9]+/', $this->_input, $match, PREG_OFFSET_CAPTURE, $this->_position)) {
|
||||
// It covers both cases a) there are no matches (preg_match(...) === 0)
|
||||
// b) error occured (preg_match(...) === FALSE)
|
||||
return null;
|
||||
}
|
||||
|
||||
$str = $match[0][0];
|
||||
$pos = $match[0][1];
|
||||
$endpos = $pos + strlen($str);
|
||||
|
||||
$this->_position = $endpos;
|
||||
|
||||
$token = $this->normalize(new Zend_Search_Lucene_Analysis_Token($str, $pos, $endpos));
|
||||
} while ($token === null); // try again if token is skipped
|
||||
|
||||
return $token;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: CaseInsensitive.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common_TextNum */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common/TextNum.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_TokenFilter_LowerCase */
|
||||
require_once 'Zend/Search/Lucene/Analysis/TokenFilter/LowerCase.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_TextNum_CaseInsensitive extends Zend_Search_Lucene_Analysis_Analyzer_Common_TextNum
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
$this->addFilter(new Zend_Search_Lucene_Analysis_TokenFilter_LowerCase());
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,126 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: Utf8.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8 extends Zend_Search_Lucene_Analysis_Analyzer_Common
|
||||
{
|
||||
/**
|
||||
* Current char position in an UTF-8 stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_position;
|
||||
|
||||
/**
|
||||
* Current binary position in an UTF-8 stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_bytePosition;
|
||||
|
||||
/**
|
||||
* Object constructor
|
||||
*
|
||||
* @throws Zend_Search_Lucene_Exception
|
||||
*/
|
||||
public function __construct()
|
||||
{
|
||||
if (@preg_match('/\pL/u', 'a') != 1) {
|
||||
// PCRE unicode support is turned off
|
||||
require_once 'Zend/Search/Lucene/Exception.php';
|
||||
throw new Zend_Search_Lucene_Exception('Utf8 analyzer needs PCRE unicode support to be enabled.');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset token stream
|
||||
*/
|
||||
public function reset()
|
||||
{
|
||||
$this->_position = 0;
|
||||
$this->_bytePosition = 0;
|
||||
|
||||
// convert input into UTF-8
|
||||
if (strcasecmp($this->_encoding, 'utf8' ) != 0 &&
|
||||
strcasecmp($this->_encoding, 'utf-8') != 0 ) {
|
||||
$this->_input = iconv($this->_encoding, 'UTF-8', $this->_input);
|
||||
$this->_encoding = 'UTF-8';
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenization stream API
|
||||
* Get next token
|
||||
* Returns null at the end of stream
|
||||
*
|
||||
* @return Zend_Search_Lucene_Analysis_Token|null
|
||||
*/
|
||||
public function nextToken()
|
||||
{
|
||||
if ($this->_input === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
do {
|
||||
if (! preg_match('/[\p{L}]+/u', $this->_input, $match, PREG_OFFSET_CAPTURE, $this->_bytePosition)) {
|
||||
// It covers both cases a) there are no matches (preg_match(...) === 0)
|
||||
// b) error occured (preg_match(...) === FALSE)
|
||||
return null;
|
||||
}
|
||||
|
||||
// matched string
|
||||
$matchedWord = $match[0][0];
|
||||
|
||||
// binary position of the matched word in the input stream
|
||||
$binStartPos = $match[0][1];
|
||||
|
||||
// character position of the matched word in the input stream
|
||||
$startPos = $this->_position +
|
||||
iconv_strlen(substr($this->_input,
|
||||
$this->_bytePosition,
|
||||
$binStartPos - $this->_bytePosition),
|
||||
'UTF-8');
|
||||
// character postion of the end of matched word in the input stream
|
||||
$endPos = $startPos + iconv_strlen($matchedWord, 'UTF-8');
|
||||
|
||||
$this->_bytePosition = $binStartPos + strlen($matchedWord);
|
||||
$this->_position = $endPos;
|
||||
|
||||
$token = $this->normalize(new Zend_Search_Lucene_Analysis_Token($matchedWord, $startPos, $endPos));
|
||||
} while ($token === null); // try again if token is skipped
|
||||
|
||||
return $token;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: CaseInsensitive.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8 */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common/Utf8.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_TokenFilter_LowerCaseUtf8 */
|
||||
require_once 'Zend/Search/Lucene/Analysis/TokenFilter/LowerCaseUtf8.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8_CaseInsensitive extends Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
parent::__construct();
|
||||
|
||||
$this->addFilter(new Zend_Search_Lucene_Analysis_TokenFilter_LowerCaseUtf8());
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,126 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: Utf8Num.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num extends Zend_Search_Lucene_Analysis_Analyzer_Common
|
||||
{
|
||||
/**
|
||||
* Current char position in an UTF-8 stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_position;
|
||||
|
||||
/**
|
||||
* Current binary position in an UTF-8 stream
|
||||
*
|
||||
* @var integer
|
||||
*/
|
||||
private $_bytePosition;
|
||||
|
||||
/**
|
||||
* Object constructor
|
||||
*
|
||||
* @throws Zend_Search_Lucene_Exception
|
||||
*/
|
||||
public function __construct()
|
||||
{
|
||||
if (@preg_match('/\pL/u', 'a') != 1) {
|
||||
// PCRE unicode support is turned off
|
||||
require_once 'Zend/Search/Lucene/Exception.php';
|
||||
throw new Zend_Search_Lucene_Exception('Utf8Num analyzer needs PCRE unicode support to be enabled.');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset token stream
|
||||
*/
|
||||
public function reset()
|
||||
{
|
||||
$this->_position = 0;
|
||||
$this->_bytePosition = 0;
|
||||
|
||||
// convert input into UTF-8
|
||||
if (strcasecmp($this->_encoding, 'utf8' ) != 0 &&
|
||||
strcasecmp($this->_encoding, 'utf-8') != 0 ) {
|
||||
$this->_input = iconv($this->_encoding, 'UTF-8', $this->_input);
|
||||
$this->_encoding = 'UTF-8';
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Tokenization stream API
|
||||
* Get next token
|
||||
* Returns null at the end of stream
|
||||
*
|
||||
* @return Zend_Search_Lucene_Analysis_Token|null
|
||||
*/
|
||||
public function nextToken()
|
||||
{
|
||||
if ($this->_input === null) {
|
||||
return null;
|
||||
}
|
||||
|
||||
do {
|
||||
if (! preg_match('/[\p{L}\p{N}]+/u', $this->_input, $match, PREG_OFFSET_CAPTURE, $this->_bytePosition)) {
|
||||
// It covers both cases a) there are no matches (preg_match(...) === 0)
|
||||
// b) error occured (preg_match(...) === FALSE)
|
||||
return null;
|
||||
}
|
||||
|
||||
// matched string
|
||||
$matchedWord = $match[0][0];
|
||||
|
||||
// binary position of the matched word in the input stream
|
||||
$binStartPos = $match[0][1];
|
||||
|
||||
// character position of the matched word in the input stream
|
||||
$startPos = $this->_position +
|
||||
iconv_strlen(substr($this->_input,
|
||||
$this->_bytePosition,
|
||||
$binStartPos - $this->_bytePosition),
|
||||
'UTF-8');
|
||||
// character postion of the end of matched word in the input stream
|
||||
$endPos = $startPos + iconv_strlen($matchedWord, 'UTF-8');
|
||||
|
||||
$this->_bytePosition = $binStartPos + strlen($matchedWord);
|
||||
$this->_position = $endPos;
|
||||
|
||||
$token = $this->normalize(new Zend_Search_Lucene_Analysis_Token($matchedWord, $startPos, $endPos));
|
||||
} while ($token === null); // try again if token is skipped
|
||||
|
||||
return $token;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
<?php
|
||||
/**
|
||||
* Zend Framework
|
||||
*
|
||||
* LICENSE
|
||||
*
|
||||
* This source file is subject to the new BSD license that is bundled
|
||||
* with this package in the file LICENSE.txt.
|
||||
* It is also available through the world-wide-web at this URL:
|
||||
* http://framework.zend.com/license/new-bsd
|
||||
* If you did not receive a copy of the license and are unable to
|
||||
* obtain it through the world-wide-web, please send an email
|
||||
* to license@zend.com so we can send you a copy immediately.
|
||||
*
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
* @version $Id: CaseInsensitive.php 20096 2010-01-06 02:05:09Z bkarwin $
|
||||
*/
|
||||
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num */
|
||||
require_once 'Zend/Search/Lucene/Analysis/Analyzer/Common/Utf8Num.php';
|
||||
|
||||
/** Zend_Search_Lucene_Analysis_TokenFilter_LowerCaseUtf8 */
|
||||
require_once 'Zend/Search/Lucene/Analysis/TokenFilter/LowerCaseUtf8.php';
|
||||
|
||||
|
||||
/**
|
||||
* @category Zend
|
||||
* @package Zend_Search_Lucene
|
||||
* @subpackage Analysis
|
||||
* @copyright Copyright (c) 2005-2010 Zend Technologies USA Inc. (http://www.zend.com)
|
||||
* @license http://framework.zend.com/license/new-bsd New BSD License
|
||||
*/
|
||||
|
||||
|
||||
class Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num_CaseInsensitive extends Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num
|
||||
{
|
||||
public function __construct()
|
||||
{
|
||||
parent::__construct();
|
||||
|
||||
$this->addFilter(new Zend_Search_Lucene_Analysis_TokenFilter_LowerCaseUtf8());
|
||||
}
|
||||
}
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue