aboutsummaryrefslogtreecommitdiff
path: root/bagel/src
diff options
context:
space:
mode:
authorMatei Zaharia <matei@eecs.berkeley.edu>2012-10-13 19:05:11 -0700
committerMatei Zaharia <matei@eecs.berkeley.edu>2012-10-13 19:05:11 -0700
commit4be12d97ec4a6ca0acaf324799156e219732a11e (patch)
tree1cf716a530e02243080e4acab9e05e7895a9e15e /bagel/src
parent19910c00c3d7fd306e1d77b308b5c033ccfa91f5 (diff)
downloadspark-4be12d97ec4a6ca0acaf324799156e219732a11e.tar.gz
spark-4be12d97ec4a6ca0acaf324799156e219732a11e.tar.bz2
spark-4be12d97ec4a6ca0acaf324799156e219732a11e.zip
Some doc fixes, including showing version number in nav bar again
Diffstat (limited to 'bagel/src')
-rw-r--r--bagel/src/main/scala/spark/bagel/examples/WikipediaPageRank.scala5
1 files changed, 5 insertions, 0 deletions
diff --git a/bagel/src/main/scala/spark/bagel/examples/WikipediaPageRank.scala b/bagel/src/main/scala/spark/bagel/examples/WikipediaPageRank.scala
index f37ee01fd2..03843019c0 100644
--- a/bagel/src/main/scala/spark/bagel/examples/WikipediaPageRank.scala
+++ b/bagel/src/main/scala/spark/bagel/examples/WikipediaPageRank.scala
@@ -8,6 +8,11 @@ import spark.bagel.Bagel._
import scala.xml.{XML,NodeSeq}
+/**
+ * Run PageRank on XML Wikipedia dumps from http://wiki.freebase.com/wiki/WEX. Uses the "articles"
+ * files from there, which contains one line per wiki article in a tab-separated format
+ * (http://wiki.freebase.com/wiki/WEX/Documentation#articles).
+ */
object WikipediaPageRank {
def main(args: Array[String]) {
if (args.length < 5) {