DIH处理包含回车符换行符html标签内容的文本

数据样例：2010-03-19 10:18:06130010543234203guqun09-12月-12liuyin18-6月 -14<P style="MARGIN-TOP: 0px; TEXT-JUSTIFY: inter-ideograph; FONT-SIZE: 12pt; MARGIN-BOTTOM: 0px; TEXT-INDENT: 2em; LINE-HEIGHT: 1.5; FONT-FAMILY: 宋体; TEXT-ALIGN: justify">天翼分享是基于中国电信CDMA网络，为天翼客户提供视频、音频等多媒体信息分享服务的移动互联网产品。多媒体信息可以是客户自己录制的视频、拍摄的照片、制作的动漫或MTV等，也可以是中国电信提供的优质多媒体信息内容。

第一种方法：

使用ScriptTransformer处理回车符、换行符。

数据源：

<dataSource name="jdbc" driver="oracle.jdbc.driver.OracleDriver"

    url="jdbc:oracle:thin:@127.0.0.1:1521:ORCLLI" user="kms_user" password="kms_user" />

ScriptTransformer脚本模块：

<script>

    <![CDATA[

    function regex(row) {

        var content = row.get('CONTENT');

        var regex = "\\t|\r|\n"

        var p = java.util.regex.Pattern.compile(regex);

        var m = p.matcher(content)

        row.put('CONTENT', m.replaceAll(""));

        return row;

    }

    ]]>

</script>

document：

<entity name="tm_details" query="select t.docid as id,t.tempid,t.cruser as userid,t.crtime,t.content from TM_DETAILS t  where t.type=2 and  t.docid=10479"

            transformer="ClobTransformer,HTMLStripTransformer,script:regex,DateFormatTransformer">

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

            <field column="TEMPID" name="tempid" />

            <entity name="template" query="select te.name from kmstemplate  te where te.id=${tm_details.TEMPID}">

                <field column="NAME" name="template"/>

            </entity>

            <entity   name="user" query="select msg.name  from tb_sys_loginmsg msg where msg.login_id='${tm_details.USERID}'" >

                <field column="NAME" name="cruser"/>

            </entity>

            <field column="CRTIME" name="crtime"  dateTimeFormat="yyyy-MM-dd HH:mm:ss"/>

            <entity name="doc" query="select rtrim(d.doctitle,'.htm') as title  from kmsdocument d where d.docid=${tm_details.ID}">

                <field column="TITLE" name="title" clob="true"/>

            </entity>

            <field column="CONTENT" name="content"  clob="true"  stripHTML="true"/>

        </entity>

    </document>

第二种方法：采用RegexTransformer：

document：

<entity name="tm_details" query="select t.docid as id,t.tempid,t.cruser as userid,t.crtime,t.content from TM_DETAILS t  where t.type=2 and  t.docid=10479"

            transformer="ClobTransformer,HTMLStripTransformer,RegexTransformer,DateFormatTransformer">

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

            <field column="TEMPID" name="tempid" />

            <entity name="template" query="select te.name from kmstemplate  te where te.id=${tm_details.TEMPID}">

                <field column="NAME" name="template"/>

            </entity>

            <entity   name="user" query="select msg.name  from tb_sys_loginmsg msg where msg.login_id='${tm_details.USERID}'" >

                <field column="NAME" name="cruser"/>

            </entity>

            <field column="CRTIME" name="crtime"  dateTimeFormat="yyyy-MM-dd HH:mm:ss"/>

            <entity name="doc" query="select rtrim(d.doctitle,'.htm') as title  from kmsdocument d where d.docid=${tm_details.ID}">

                <field column="TITLE" name="title" clob="true"/>

            </entity>

            <field column="CONTENT" name="content"  clob="true"  stripHTML="true" regex="\\t|\r|\n" replaceWith=""/>

        </entity>

    </document>

巴特西

DIH处理包含回车符换行符html标签内容的文本

最新文章

热门文章