solr读取文件的问题

今天在用solr读取数据库连接，然后根据链接通过web服务器取文件，本以为很简单的问题，弄了一天。

主要参考了这几篇文章：https://issues.apache.org/jira/browse/SOLR-4184

http://blog.sina.com.cn/s/blog_986e726b0101f7lx.html

https://issues.apache.org/jira/browse/SOLR-2896?jql=project%20%3D%20SOLR%20AND%20text%20~%20%22onerror%22

<script><![CDATA[
        id = 1;
        function GenerateId(row) {
            row.put('id', (id ++).toFixed());
			var url = row.get('FJLJ');
			var index = url.lastIndexOf("/");
			var fileName = encodeURI(url.substring(index+1));//这儿主要是最后要取得文件含中文时，在第二个entity执行之前转码
			url = url.substring(0,index+1)+fileName;
			row.put('FJLJ', url);
            return row;
        }  
       ]]>
    </script>

这是第二个entity：

<entity processor="TikaEntityProcessor" name="onlineTxtFile" onError="skip"  //主要是onerror 当下载文件出错时跳过此错误
			url="http://192.168.15.40:8080/zdfzxxglpt/servlets/solrServlet?url=${fjb1.FJLJ}" dataSource="binURLDataSource" format="text">  
                <field column="Author" name="author" />  
                <field column="title"  name="title" />  
                <field column="text"  name="text"/>  
            </entity>

还有查询txt时，当中文很少时可以读出乱码，中文很多时直接读不出来

try {
			bis = new BufferedInputStream(new FileInputStream(new File(dirPath)));
			bos = new BufferedOutputStream(response.getOutputStream());
			byte[] b = new byte[1024];
			int length;
			while ((length = bis.read(b)) > 0) {
				if(url.endsWith("txt")){
					String block = new String(b,"gbk"); //当为txt时重新设置编码，虽然感觉这样写很不好，但终归是出效果了
					b = block.getBytes("utf-8");
				}
				bos.write(b, 0, length);
			}
			bos.flush();
		}

还有一些oracle字段查出来大写等等

<field column="FJID" name="id"/>

这是一个完整的entity，注意pk值大写：

<entity name="fjb" query="select t1.fjid,t1.fjgs,t1.uptime,t1.fjlj from DFZ_FJB t1 join dfz_zlsbb t2 on t1.ywid=t2.zlid where t2.zt!='1' and t1.zt is null" pk="ID" transformer="DateFormatTransformer,ClobTransformer,script:GenerateId"  dataSource="oracle"
                deltaQuery="select t1.fjid as id  from DFZ_FJB t1 join dfz_zlsbb t2 on t1.ywid=t2.zlid where t2.zt!='1' and t1.zt is null and t1.uptime > '${dataimporter.fjb.last_index_time}'"
				deletedPkQuery="select t1.fjid as id FROM DFZ_FJB t1 WHERE t1.zt='2' and t1.uptime > '${dataimporter.fjb.last_index_time}'"
				deltaImportQuery="select t1.fjid,t1.fjgs,t1.uptime,t1.fjlj from DFZ_FJB t1 where t1.fjid='${dataimporter.delta.ID}'">
            <field column="FJID" name="id"/>
			<field column="fjgs"  /> 
			<field column="uptime"  /> 
			<field column="fjlj" />
			<entity processor="TikaEntityProcessor" name="onlineTxtFile" onError="skip" url="http://192.168.15.40:8080/Lzdfzxxglpt/servlets/solrServlet?url=${fjb.FJLJ}" dataSource="binURLDataSource" format="text">  
                <field column="Author" name="author" meta="true"/>  
                <field column="title"  name="title" meta="true"/>  
                <field column="text"  name="text"/>  
            </entity>  
        </entity>