Skip to content

Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance

added image link in search results This should be a help to make a preview of search results. The image is computed from the list of embedded images, it is always the first image in that list. In rss-type results the image is presented like <media:content medium="image" url="https://abc.xyz/logo.png"/> as defined in http://www.rssboard.org/media-rss#media-content

Michael Peter Christen7f395ef93731
diff --git a/htroot/yacysearchitem.java b/htroot/yacysearchitem.java
index 431ce4030..0baf4ed34 100644
--- a/htroot/yacysearchitem.java
+++ b/htroot/yacysearchitem.java
@@ -153,7 +153,7 @@ public class yacysearchitem {
prop.putJSON("content_title-json", result.title());
prop.putHTML("content_showPictures_link", resultUrlstring);
//prop.putHTML("content_link", resultUrlstring);
-
+
// START interaction
if (sb.getConfigBool("proxyURL.useforresults", false) && sb.getConfigBool("proxyURL", false)) {
String modifyURL = resultUrlstring;
@@ -199,6 +199,19 @@ public class yacysearchitem {
prop.put("content_favicon", 1);
}
prop.putHTML("content_favicon_faviconUrl", processFaviconURL(ImageViewer.hasFullViewingRights(header, sb), faviconURL));
+
+ if (result.limage() == 0) {
+ if (faviconURL == null) {
+ prop.put("content_image", 0);
+ } else {
+ prop.put("content_image", 1);
+ prop.putXML("content_image_url", faviconURL.toNormalform(true));
+ }
+ } else {
+ prop.put("content_image", 1);
+ prop.putXML("content_image_url", result.imageURL());
+ }
+
prop.put("content_urlhash", urlhash);
prop.put("content_ranking", Float.toString(result.score()));
Date[] events = result.events();
diff --git a/htroot/yacysearchitem.json b/htroot/yacysearchitem.json
index 59f04c10f..822af6f93 100644
--- a/htroot/yacysearchitem.json
+++ b/htroot/yacysearchitem.json
@@ -5,6 +5,7 @@
"code": "#[code]#",
"description": "#[description-json]#",
"pubDate": "#[date822]#",
+ #(image)#::"image": "#[url]#",#(/image)#
#(showEvent)#::"eventDate": "#[date822]#",#(/showEvent)#
"size": "#[size]#",
"sizename": "#[sizename]#",
diff --git a/htroot/yacysearchitem.xml b/htroot/yacysearchitem.xml
index c8dfb7e87..30989e0df 100644
--- a/htroot/yacysearchitem.xml
+++ b/htroot/yacysearchitem.xml
@@ -3,6 +3,7 @@
<link>#[link]#</link>
<description>#[description-xml]#</description>
<pubDate>#[date822]#</pubDate>
+#(image)#::<media:content medium="image" url="#[url]#"/>#(/image)#
#(showEvent)#::<ev:startdate>#[date822]#</ev:startdate><ev:enddate>#[date822]#</ev:enddate>#(/showEvent)#
<dc:publisher><![CDATA[#[publisher]#]]></dc:publisher>
<dc:creator><![CDATA[#[creator]#]]></dc:creator>
diff --git a/source/net/yacy/cora/federate/solr/responsewriter/OpensearchResponseWriter.java b/source/net/yacy/cora/federate/solr/responsewriter/OpensearchResponseWriter.java
index 1027f48f6..d7bdc0f1c 100644
--- a/source/net/yacy/cora/federate/solr/responsewriter/OpensearchResponseWriter.java
+++ b/source/net/yacy/cora/federate/solr/responsewriter/OpensearchResponseWriter.java
@@ -40,6 +40,8 @@ import net.yacy.cora.lod.vocabulary.DublinCore;
import net.yacy.cora.lod.vocabulary.Geo;
import net.yacy.cora.lod.vocabulary.YaCyMetadata;
import net.yacy.cora.protocol.HeaderFramework;
+import net.yacy.crawler.retrieval.Response;
+import net.yacy.search.schema.CollectionConfiguration;
import net.yacy.search.schema.CollectionSchema;
import org.apache.lucene.document.Document;
@@ -159,6 +161,7 @@ public class OpensearchResponseWriter implements QueryResponseWriter {
SolrIndexSearcher searcher = request.getSearcher();
DocIterator iterator = response.iterator();
String urlhash = null;
+ MultiProtocolURL url = null;
for (int i = 0; i < responseCount; i++) {
openTag(writer, "item");
int id = iterator.nextDoc();
@@ -168,6 +171,8 @@ public class OpensearchResponseWriter implements QueryResponseWriter {
List<String> texts = new ArrayList<String>();
List<String> descriptions = new ArrayList<String>();
String title = "";
+ List<Object> images_protocol_obj = new ArrayList<>();
+ List<String> images_stub = new ArrayList<>();
for (int j = 0; j < fieldc; j++) {
IndexableField value = fields.get(j);
String fieldName = value.name();
@@ -184,7 +189,7 @@ public class OpensearchResponseWriter implements QueryResponseWriter {
String u = value.stringValue();
solitaireTag(writer, RSSMessage.Token.link.name(), u);
try {
- MultiProtocolURL url = new MultiProtocolURL(u);
+ url = new MultiProtocolURL(u);
solitaireTag(writer, YaCyMetadata.host.getURIref(), url.getHost());
solitaireTag(writer, YaCyMetadata.path.getURIref(), url.getPath());
solitaireTag(writer, YaCyMetadata.file.getURIref(), url.getFileName());
@@ -232,6 +237,26 @@ public class OpensearchResponseWriter implements QueryResponseWriter {
texts.add(value.stringValue());
continue;
}
+ if (CollectionSchema.images_protocol_sxt.getSolrFieldName().equals(fieldName)) {
+ images_protocol_obj.add(value.stringValue());
+ continue;
+ }
+ if (CollectionSchema.images_urlstub_sxt.getSolrFieldName().equals(fieldName)) {
+ images_stub.add(value.stringValue());
+ continue;
+ }
+ }
+
+ if (Math.min(images_protocol_obj.size(), images_stub.size()) > 0) {
+ List<String> images_protocol = CollectionConfiguration.indexedList2protocolList(images_protocol_obj, images_protocol_obj.size());
+ String imageurl = images_protocol.get(0) + "://" + images_stub.get(0);
+ writer.write("<media:content medium=\"image\" url=\"");
+ XML.escapeCharData(imageurl, writer); writer.write("\"/>\n");
+ } else {
+ if (url != null && Response.docTypeExt(MultiProtocolURL.getFileExtension(url.getFile()).toLowerCase()) == Response.DT_IMAGE) {
+ writer.write("<media:content medium=\"image\" url=\"");
+ XML.escapeCharData(url.toNormalform(true), writer); writer.write("\"/>\n");
+ }
}
// compute snippet from texts
diff --git a/source/net/yacy/cora/federate/solr/responsewriter/YJsonResponseWriter.java b/source/net/yacy/cora/federate/solr/responsewriter/YJsonResponseWriter.java
index b56637078..6a2fcccd6 100644
--- a/source/net/yacy/cora/federate/solr/responsewriter/YJsonResponseWriter.java
+++ b/source/net/yacy/cora/federate/solr/responsewriter/YJsonResponseWriter.java
@@ -35,6 +35,8 @@ import net.yacy.cora.federate.solr.responsewriter.OpensearchResponseWriter.ResHe
import net.yacy.cora.protocol.HeaderFramework;
import net.yacy.cora.util.ConcurrentLog;
import net.yacy.cora.util.JSONObject;
+import net.yacy.crawler.retrieval.Response;
+import net.yacy.search.schema.CollectionConfiguration;
import net.yacy.search.schema.CollectionSchema;
import org.apache.lucene.document.Document;
@@ -141,6 +143,9 @@ public class YJsonResponseWriter implements QueryResponseWriter {
List<String> descriptions = new ArrayList<String>();
String title = "";
StringBuilder path = new StringBuilder(80);
+ List<Object> images_protocol_obj = new ArrayList<>();
+ List<String> images_stub = new ArrayList<>();
+
for (int j = 0; j < fieldc; j++) {
IndexableField value = fields.get(j);
String fieldName = value.name();
@@ -193,9 +198,32 @@ public class YJsonResponseWriter implements QueryResponseWriter {
solitaireTag(writer, "sizename", sizemb > 0 ? (Integer.toString(sizemb) + " mbyte") : sizekb > 0 ? (Integer.toString(sizekb) + " kbyte") : (Integer.toString(size) + " byte"));
continue;
}
+ if (CollectionSchema.last_modified.getSolrFieldName().equals(fieldName)) {
+ Date d = new Date(Long.parseLong(value.stringValue()));
+ solitaireTag(writer, "pubDate", HeaderFramework.formatRFC1123(d));
+ continue;
+ }
+ if (CollectionSchema.images_protocol_sxt.getSolrFieldName().equals(fieldName)) {
+ images_protocol_obj.add(value.stringValue());
+ continue;
+ }
+ if (CollectionSchema.images_urlstub_sxt.getSolrFieldName().equals(fieldName)) {
+ images_stub.add(value.stringValue());
+ continue;
+ }
//missing: "code","faviconCode"
}
+
+ if (Math.min(images_protocol_obj.size(), images_stub.size()) > 0) {
+ List<String> images_protocol = CollectionConfiguration.indexedList2protocolList(images_protocol_obj, images_protocol_obj.size());
+ String imageurl = images_protocol.get(0) + "://" + images_stub.get(0);
+ solitaireTag(writer, "image", imageurl);
+ } else {
+ if (url != null && Response.docTypeExt(MultiProtocolURL.getFileExtension(url.getFile()).toLowerCase()) == Response.DT_IMAGE) {
+ solitaireTag(writer, "image", url.toNormalform(true));
+ }
+ }
// compute snippet from texts
solitaireTag(writer, "path", path.toString());
diff --git a/source/net/yacy/kelondro/data/meta/URIMetadataNode.java b/source/net/yacy/kelondro/data/meta/URIMetadataNode.java
index f63c80a6a..2adf4fdc8 100644
--- a/source/net/yacy/kelondro/data/meta/URIMetadataNode.java
+++ b/source/net/yacy/kelondro/data/meta/URIMetadataNode.java
@@ -451,6 +451,20 @@ public class URIMetadataNode extends SolrDocument /* implements Comparable<URIMe
return getInt(CollectionSchema.wordcount_i);
}
+ /**
+ * in case that images are embedded in the document, get one image which can be used as thumbnail
+ * @return
+ */
+ public String imageURL() {
+ if (limage() == 0) throw new UnsupportedOperationException();
+ List<String> images_protocol = CollectionConfiguration.indexedList2protocolList(getFieldValues(CollectionSchema.images_protocol_sxt.getSolrFieldName()), limage());
+ List<String> images_stub = getStringList(CollectionSchema.images_urlstub_sxt);
+ int c = Math.min(images_protocol.size(), images_stub.size());
+ if (c == 0) throw new UnsupportedOperationException();
+ String url = images_protocol.get(0) + "://" + images_stub.get(0);
+ return url;
+ }
+
public int llocal() {
return getInt(CollectionSchema.inboundlinkscount_i);
}