Index: conf/schema.xml
===================================================================
--- conf/schema.xml (revision 1406748)
+++ conf/schema.xml (working copy)
@@ -114,6 +114,9 @@
+
+
+
id
content
Index: src/java/org/apache/nutch/indexer/solr/SolrWriter.java
===================================================================
--- src/java/org/apache/nutch/indexer/solr/SolrWriter.java (revision 1406748)
+++ src/java/org/apache/nutch/indexer/solr/SolrWriter.java (working copy)
@@ -66,8 +66,8 @@
inputDoc.addField(solrMapping.mapKey(e.getKey()), val2);
String sCopy = solrMapping.mapCopyKey(e.getKey());
- if (sCopy != e.getKey()) {
- inputDoc.addField(sCopy, val2);
+ if (!sCopy.equals(e.getKey())) {
+ inputDoc.addField(sCopy, val2);
}
}
}
Index: src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
===================================================================
--- src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java (revision 1406749)
+++ src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java (working copy)
@@ -143,7 +143,7 @@
// NUTCH-1010 ContentLength not trimmed
String trimmed = contentLength.toString().trim();
if (!trimmed.isEmpty())
- doc.add("contentLength", trimmed);
+ doc.add("contentLength", trimmed);
}
return doc;
@@ -171,7 +171,7 @@
*/
private NutchDocument addType(NutchDocument doc, WebPage page, String url) {
String mimeType = null;
- Utf8 contentType = page.getFromHeaders(new Utf8(HttpHeaders.CONTENT_TYPE));
+ Utf8 contentType = page.getContentType();
if (contentType == null) {
// Note by Jerome Charron on 20050415:
// Content Type not solved by a previous plugin
@@ -200,7 +200,7 @@
// Check if we need to split the content type in sub parts
if (conf.getBoolean("moreIndexingFilter.indexMimeTypeParts", true)) {
- String[] parts = getParts(contentType.toString());
+ String[] parts = getParts(mimeType);
for(String part: parts) {
doc.add("type", part);