pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/benchmark/conf/indexLineFile.alg b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/indexLineFile.alg
new file mode 100644 (file)
index 0000000..2624ea3
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/indexLineFile.alg
@@ -0,0 +1,53 @@
+#/**
+# * 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 file indexes documents contained in a single text file, one per
+# line.  See createLineFile.alg for how to create this file.  The
+# benefit of this is it removes the IO cost of opening one file per
+# document to let you more accurately measure time spent analyzing and
+# indexing your documents vs time spent creating the documents.
+#
+# To use this, you must first run the createLineFile.alg, then cd to
+# contrib/benchmark and then run:
+#
+#   ant run-task -Dtask.alg=conf/indexLineFile.alg
+#
+
+analyzer=org.apache.lucene.analysis.SimpleAnalyzer
+
+# Feed that knows how to process the line file format:
+content.source=org.apache.lucene.benchmark.byTask.feeds.LineDocSource
+
+# File that contains one document per line:
+docs.file=work/reuters.lines.txt
+
+# Process documents only once:
+content.source.forever=false
+
+# -------------------------------------------------------------------------------------
+
+# Reset the system, create a new index, index all docs from the line
+# file, close the index, produce a report.
+
+ResetSystemErase
+CreateIndex
+{AddDoc}: *
+CloseIndex
+
+RepSumByPref AddDoc