pylucene 3.5.0-3

[pylucene.git] / lucene-java-3.5.0 / lucene / contrib / benchmark / conf / extractWikipedia.alg

diff --git a/lucene-java-3.5.0/lucene/contrib/benchmark/conf/extractWikipedia.alg b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/extractWikipedia.alg
new file mode 100644 (file)
index 0000000..f0df54d
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/extractWikipedia.alg
@@ -0,0 +1,44 @@
+#/**
+# * Licensed to the Apache Software Foundation (ASF) under one or more
+# * contributor license agreements.  See the NOTICE file distributed with
+# * this work for additional information regarding copyright ownership.
+# * The ASF licenses this file to You under the Apache License, Version 2.0
+# * (the "License"); you may not use this file except in compliance with
+# * the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+# -------------------------------------------------------------------------------------
+
+#
+# This alg will process the Wikipedia documents feed to produce a
+# single file that contains all documents, one per line.
+#
+# To use this, first cd to contrib/benchmark and then run:
+#
+#   ant run-task -Dtask.alg=conf/extractWikipedia.alg
+#
+# Then, to index the documents in the line file, see
+# indexLineFile.alg.
+#
+
+# Where to get documents from:
+content.source=org.apache.lucene.benchmark.byTask.feeds.EnwikiContentSource
+docs.file=temp/enwiki-20070527-pages-articles.xml
+
+# Where to write the line file output:
+line.file.out=work/enwiki.txt
+
+# Stop after processing the document feed once:
+content.source.forever=false
+
+# -------------------------------------------------------------------------------------
+
+# Process all documents, appending each one to the line file:
+{WriteLineDoc() > : *