coreseek中LibMMsg中文分词

最新推荐文章于 2019-02-19 16:45:00 发布

ms_X0828

最新推荐文章于 2019-02-19 16:45:00 发布

阅读量4.6k

点赞数

分类专栏： PHP 文章标签： buffer function 搜狗 c file 输入法

本文链接：https://blog.csdn.net/ms_X0828/article/details/7679991

版权

PHP 专栏收录该内容

29 篇文章 0 订阅

订阅专栏

mmseg -u unigram.txt

该命令执行后，将会在unigram.txt所在目录中产生一个名为unigram.txt.uni的文件，将该文件改名为uni.lib，完成词典的构造。需要注意的是，unigram.txt需要预先准备，并且编码格式必须为UTF-8编码
在unigram.txt中的格式为：

...

帮助 1

x:1

否 12

x:12

...

其中，每条记录分两行。其中，第一行为词项，其格式为：[词条]\t[词频率]。特别提醒，有的编辑器会使用4到8个空格代表\t，这将导致该词条无法解析。需要注意的是，对于单个字后面跟这个字作单字成词的频率，这个频率需要在大量的预先切分好的语料库中进行统计，用户增加或删除词时，一般不需要修改这个数值；对于非单字词，词频率处必须为1。第二行为占位项，是由于LibMMSeg库的代码是从Coreseek其他的分词算法库（N-gram模型）中改造而来的，在原来的应用中，第二行为该词在各种词性下的分布频率。LibMMSeg的用户只需要简单的在第二行处填"x:1"即可. 用户可以通过修改词典文件增加自己的自定义词，以提高分词法在某一具体领域的切分精度.可以到你的搜狗输入法中得到对应的词库

在搜狗中得到的词库文件为:

'a 啊
'a'di'da'si 阿迪达斯
'a'du 阿杜

为了将搜狗的词库和coreseek自带的词库合并代码如下：

//默认的词库
$default = $defaultFrequency = array();
$unHandle = fopen("unigram_test.txt", "r");
$i = 0;
while( !feof($unHandle) ){
	$buffer = fgets($unHandle);
	if( $i % 2 == 0 ){
		$temp = explode(" ", $buffer);
		$default[] = $temp[0];
	}else{
		$temp = explode(":", $buffer);
		$defaultFrequency[] = str_replace(array("\r","\n"), '', $temp[1]);
	}
	$i++;
}
fclose($unHandle);

//搜狗词库
$handle = fopen("ciku.txt", "r");
while( !feof($handle) ){
	$buffer = fgets($handle);
	$temp = explode(" ", $buffer);
	$str = str_replace(array("\r","\n"), '',$temp[1]);
	if( !in_array($str, $default) ){
		$default[] = $str;
	}
}
fclose($handle);
$defaultFrequency = array_pad($defaultFrequency,count($default),1);
foreach ( $default as $key=>$val ){
	if( $val ){
		file_put_contents("newciku.txt", $val."\t".$defaultFrequency[$key]."\n"."x:".$defaultFrequency[$key]."\n",FILE_APPEND);
	}
}

问题:用”刘德华”搜索的时候可以得到数据用”德华”搜索没有得到对应的数据.原因是我的词库中没有”德华”.遇到这样的情况我们只能将它加入到词库中.但是有时候这样的词我们是不能够保证都加进去的.那么在配置indexer的时候可以用到”一元切分模式”. 配置如下:

#charset_dictpath    =  D:/coreseek/coreseek-4.1-win32/etc
#charset_type        = zh_cn.utf-8
#ngram_len		= 0
charset_type        = utf-8
ngram_len		= 1
ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,\
                U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,\
                U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,\
                U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF    
charset_table = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
                A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6,\
                U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101,\
                U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109,\
                U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F,\
                U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, \
                U+0116->U+0117,U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D,\
                U+011D,U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, \
                U+0134->U+0135,U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, \
                U+013C,U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, \
                U+0143->U+0144,U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, \
                U+014B,U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, \
                U+0152->U+0153,U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159,\
                U+0159,U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, \
                U+0160->U+0161,U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, \
                U+0167,U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, \
                U+016E->U+016F,U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175,\
                U+0175,U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, \
                U+017B->U+017C,U+017C, U+017D->U+017E, U+017E, U+0410..U+042F->U+0430..U+044F, \
                U+0430..U+044F,U+05D0..U+05EA, U+0531..U+0556->U+0561..U+0586, U+0561..U+0587, \
                U+0621..U+063A, U+01B9,U+01BF, U+0640..U+064A, U+0660..U+0669, U+066E, U+066F, \
                U+0671..U+06D3, U+06F0..U+06FF,U+0904..U+0939, U+0958..U+095F, U+0960..U+0963, \
                U+0966..U+096F, U+097B..U+097F,U+0985..U+09B9, U+09CE, U+09DC..U+09E3, U+09E6..U+09EF, \
                U+0A05..U+0A39, U+0A59..U+0A5E,U+0A66..U+0A6F, U+0A85..U+0AB9, U+0AE0..U+0AE3, \
                U+0AE6..U+0AEF, U+0B05..U+0B39,U+0B5C..U+0B61, U+0B66..U+0B6F, U+0B71, U+0B85..U+0BB9, \
                U+0BE6..U+0BF2, U+0C05..U+0C39,U+0C66..U+0C6F, U+0C85..U+0CB9, U+0CDE..U+0CE3, \
                U+0CE6..U+0CEF, U+0D05..U+0D39, U+0D60,U+0D61, U+0D66..U+0D6F, U+0D85..U+0DC6, \
                U+1900..U+1938, U+1946..U+194F, U+A800..U+A805,U+A807..U+A822, U+0386->U+03B1, \
                U+03AC->U+03B1, U+0388->U+03B5, U+03AD->U+03B5,U+0389->U+03B7, U+03AE->U+03B7, \
                U+038A->U+03B9, U+0390->U+03B9, U+03AA->U+03B9,U+03AF->U+03B9, U+03CA->U+03B9, \
                U+038C->U+03BF, U+03CC->U+03BF, U+038E->U+03C5,U+03AB->U+03C5, U+03B0->U+03C5, \
                U+03CB->U+03C5, U+03CD->U+03C5, U+038F->U+03C9,U+03CE->U+03C9, U+03C2->U+03C3, \
                U+0391..U+03A1->U+03B1..U+03C1,U+03A3..U+03A9->U+03C3..U+03C9, U+03B1..U+03C1, \
                U+03C3..U+03C9, U+0E01..U+0E2E,U+0E30..U+0E3A, U+0E40..U+0E45, U+0E47, U+0E50..U+0E59, \
                U+A000..U+A48F, U+4E00..U+9FBF,U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF, \
                U+2F800..U+2FA1F, U+2E80..U+2EFF,U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF, \
                U+3040..U+309F, U+30A0..U+30FF,U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF, \
                U+3130..U+318F, U+A000..U+A48F,U+A490..U+A4CF

问题增加同义词和复合词的搜索功能我们可以到同义词和复合词的词库下载thesaurus.lib文件放到和uni.lib一致的目录

下面随便的说一下BuildExcerpts函数的用法:

原型: function BuildExcerpts ( $docs, $index, $words, $opts=array() )

$docs为你的数据,$index为你的索引名称,$words为你的搜索词,$opts为配置属性

如果你的索引从两个字段进行搜索,title和description,那么你需要从的数据中得到这两个字段的数据再来进行高亮显示简单代码如下：

<?php
header("Content-type:text/html;charset='gbk'");
//注意文件的编码格式需要保存为为UTF-8格式

$words = "华";
$index = 'main';

$db = new DBConn($host,$username,$password,$dbname,$charset);

$cl = new SphinxClient ();
$cl->SetServer ( '127.0.0.1', 9312);
//以下设置用于返回数组形式的结果
$cl->SetArrayResult ( true );
//取从头开始的前20条数据，0,20类似SQl语句的LIMIT 0,20
$cl->SetLimits(0,30);

$cl->SetSortMode(SPH_SORT_ATTR_DESC,"pubDate");

$cl->SetMatchMode(SPH_MATCH_ALL);
//在做索引时，没有进行 sql_attr_类型 设置的字段，可以作为“搜索字符串”，进行全文搜索
$res = $cl->Query ( $words, "*" );    //"*"表示在所有索引里面同时搜索，"索引名称（例如test或者test,test2）"则表示搜索指定的

$opts = array(
	"before_match"		=> "<b style='color:red;'>",
	"after_match"		=> "</b>",
	"chunk_separator"	=> " ... ",
	"limit"				=> 200,
	"around"			=> 6,
	"single_passages"	=>true,
	"exact_phrase"		=>true,
	"weight_order"		=>true
);

if( $res['total'] !=0 ){
	echo iconv("utf-8", "gbk", "总条数为:").$res['total']."<br/>";
	if( $res['matches'] ){
		$ids = array();
		foreach ( $res['matches'] as $key=>$val ){
			$ids[]=$val['id'];
		}
		$result = $db->query("select * from st_info where id in (".implode(",", $ids).")");
		$result = $db->fetch_array($result);
		$result = myBuildExcerpts($result,array('title','description'),$cl,$index, $words,$opts);
		
		$result = sortData($result,$ids);
		foreach ( $result as $val ){
			echo "title:".$val['title'].iconv("utf-8", "gbk", "时间为:").date("Y-m-d H:i:s",$val['pubDate'])."<br/>";
			echo "description:". $val['description'] ."<br/>";
			echo "<hr>";
		}
	}
}else{
	print_r($cl->GetLastError());
	print_r($cl->GetLastWarning());
}
function sortData($data,$res){
	$result = array();
	foreach ( $res as $val ){
		foreach ( $data as $key=>$dataVal ){
			if( $dataVal['id'] == $val ){
				$result[] = $dataVal;
			}
		}
	}
	return $result;
}

function myBuildExcerpts($result,$key,&$c,$index,$words,$opt){
	if( !is_array( $result ) || count( $result ) < 1 ) return false;
	if( !is_array($key) ){
		$key = array($key);
	}
	$resultTemp = $result[0];
	if( !is_array( $resultTemp ) ) return false;
	foreach ( $key as $k ){
		if( !array_key_exists($k, $resultTemp) ){
			return false;
		}
		foreach ( $result as $val ){
			$docs[] = iconv("gbk","utf-8",$val[$k]);
		}
		$docs = &$c->BuildExcerpts($docs, $index, $words,$opt);
		foreach ( $docs as $dKey=>$v ){
			$result[$dKey][$k] = iconv("utf-8", "gbk", $v);
		}
		unset($docs);
	}
	return $result;
}

注意搜索时候的编码问题,最好统一