Merge pull request #233 from browngraphicslab/text_box_ab

Text box ab

1 files changed, 35 insertions, 0 deletions

diff --git a/solr-8.1.1/example/example-DIH/solr/atom/conf/atom-data-config.xml b/solr-8.1.1/example/example-DIH/solr/atom/conf/atom-data-config.xml
new file mode 100644
index 000000000..b7de812d0
--- /dev/null
+++ b/solr-8.1.1/example/example-DIH/solr/atom/conf/atom-data-config.xml
@@ -0,0 +1,35 @@
+<dataConfig>
+  <dataSource type="URLDataSource"/>
+  <document>
+
+    <entity name="stackoverflow"
+            url="https://stackoverflow.com/feeds/tag/solr"
+            processor="XPathEntityProcessor"
+            forEach="/feed|/feed/entry"
+            transformer="HTMLStripTransformer,RegexTransformer">
+
+      <!-- Pick this value up from the feed level and apply to all documents -->
+      <field column="lastchecked_dt" xpath="/feed/updated" commonField="true"/>
+
+      <!-- Keep only the final numeric part of the URL -->
+      <field column="id" xpath="/feed/entry/id" regex=".*/" replaceWith=""/>
+
+      <field column="title"    xpath="/feed/entry/title"/>
+      <field column="author"   xpath="/feed/entry/author/name"/>
+      <field column="category" xpath="/feed/entry/category/@term"/>
+      <field column="link"     xpath="/feed/entry/link[@rel='alternate']/@href"/>
+
+      <!-- Use transformers to convert HTML into plain text.
+        There is also an UpdateRequestProcess to trim remaining spaces.
+      -->
+      <field column="summary" xpath="/feed/entry/summary" stripHTML="true" regex="( |\n)+" replaceWith=" "/>
+
+      <!-- Ignore namespaces when matching XPath -->
+      <field column="rank" xpath="/feed/entry/rank"/>
+
+      <field column="published_dt" xpath="/feed/entry/published"/>
+      <field column="updated_dt" xpath="/feed/entry/updated"/>
+    </entity>
+
+  </document>
+</dataConfig>