pylucene 3.5.0-3

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

diff --git a/lucene-java-3.5.0/lucene/contrib/benchmark/conf/collation.alg b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/collation.alg
new file mode 100644 (file)
index 0000000..798befc
--- /dev/null
+++ b/lucene-java-3.5.0/lucene/contrib/benchmark/conf/collation.alg
@@ -0,0 +1,97 @@
+# 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.
+
+content.source=org.apache.lucene.benchmark.byTask.feeds.LineDocSource
+content.source.encoding=UTF-8
+doc.tokenized=false
+doc.body.tokenized=true
+docs.file=work/top100k-out/top.fr.wikipedia.words.txt
+content.source.forever=false
+log.step=100000
+
+{ "Rounds"
+    -NewAnalyzer(KeywordAnalyzer)
+    -SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
+    ResetInputs
+    { "FrenchKeyword" { ReadTokens > : * ResetInputs } : 10
+
+    -NewAnalyzer(KeywordAnalyzer)
+    -SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
+    ResetInputs
+    { "GermanKeyword" { ReadTokens > : * ResetInputs } : 10
+
+    -NewAnalyzer(KeywordAnalyzer)
+    -SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
+    ResetInputs
+    { "UkrainianKeyword" { ReadTokens > : * ResetInputs } : 10
+ 
+    -NewAnalyzer(KeywordAnalyzer)
+    -SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
+    ResetInputs
+    { "EnglishKeyword" { ReadTokens > : * ResetInputs } : 10
+ 
+    -NewLocale(fr)
+    -NewCollationAnalyzer
+    -SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
+    ResetInputs
+    { "FrenchJDK" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(de)
+    -NewCollationAnalyzer
+    -SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
+    ResetInputs
+    { "GermanJDK" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(uk)
+    -NewCollationAnalyzer
+    -SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
+    ResetInputs
+    { "UkrainianJDK" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(en)
+    -NewCollationAnalyzer
+    -SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
+    ResetInputs
+    { "EnglishJDK" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(fr)
+    -NewCollationAnalyzer(impl:icu)
+    -SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
+    ResetInputs
+    { "FrenchICU" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(de)
+    -NewCollationAnalyzer(impl:icu)
+    -SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
+    ResetInputs
+    { "GermanICU" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(uk)
+    -NewCollationAnalyzer(impl:icu)
+    -SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
+    ResetInputs
+    { "UkrainianICU" { ReadTokens > : * ResetInputs } : 10
+
+    -NewLocale(en)
+    -NewCollationAnalyzer(impl:icu)
+    -SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
+    ResetInputs
+    { "EnglishICU" { ReadTokens > : * ResetInputs } : 10
+
+    NewRound
+
+} : 5
+
+RepSumByNameRound