Commit 7a84eca1 authored by jerome's avatar jerome

mode doc for entitys to scrape them two times

parent 365d7233
......@@ -74,14 +74,16 @@ Refer to comments in the code to understand the used algorithm.
</xsl:for-each>
<xsl:apply-templates select="facsimile" />
<xsl:apply-templates select="//body/listBibl" />
<xsl:apply-templates select="//name/@ref" mode="doc"/>
</doc>
<xsl:apply-templates select="//name/@ref"/>
<xsl:apply-templates select="text" mode="page_splitting" />
</add>
</xsl:template>
<xsl:template match="@ref">
<xsl:template match="name/@ref">
<xsl:if test=". != 'gnd:_' and ./parent::name/text() and ./parent::name/@type and starts-with(., 'gnd:') ">
<doc>
<field name="entity_name">
......@@ -353,6 +355,15 @@ Refer to comments in the code to understand the used algorithm.
</xsl:template>
<!--################### text/body ##########################-->
<xsl:template match="//name/@ref" mode="doc">
<xsl:for-each select="//name/@ref">
<xsl:if test=". != 'gnd:_' and ./parent::name/text() and ./parent::name/@type and starts-with(., 'gnd:') ">
<field name="entitys_in_documents">
<xsl:value-of select="."/>
</field>
</xsl:if>
</xsl:for-each>
</xsl:template>
<xsl:template match="facsimile">
......
#Written by CorePropertiesLocator
#Wed Apr 22 14:25:24 UTC 2020
#Wed Apr 22 14:53:10 UTC 2020
schema=schema.xml
dataDir=data
name=gfloffline
name=gfl
config=solrconfig.xml
#Written by CorePropertiesLocator
#Wed Apr 22 14:25:24 UTC 2020
#Wed Apr 22 14:53:10 UTC 2020
schema=schema.xml
dataDir=data
name=gfl
name=gfloffline
config=solrconfig.xml
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment