pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/benchmark/conf/tokenize.alg b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/tokenize.alg
new file mode 100644 (file)
index 0000000..57951ff
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/tokenize.alg
@@ -0,0 +1,36 @@
+#/**
+# * 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 reads all tokens out of a document but does not index them.
+# This is useful for benchmarking tokenizers.
+#
+# To use this, cd to contrib/benchmark and then run:
+#
+#   ant run-task -Dtask.alg=conf/tokenize.alg
+#
+
+content.source=org.apache.lucene.benchmark.byTask.feeds.ReutersContentSource
+content.source.forever=false
+
+
+#
+-------------------------------------------------------------------------------------
+
+{ReadTokens > : *
+RepSumByName