1
# Licensed to the Apache Software Foundation (ASF) under one or more
2
# contributor license agreements. See the NOTICE file distributed with
3
# this work for additional information regarding copyright ownership.
4
# The ASF licenses this file to You under the Apache License, Version 2.0
5
# (the "License"); you may not use this file except in compliance with
6
# the License. You may obtain a copy of the License at
8
# http://www.apache.org/licenses/LICENSE-2.0
10
# Unless required by applicable law or agreed to in writing, software
11
# distributed under the License is distributed on an "AS IS" BASIS,
12
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13
# See the License for the specific language governing permissions and
14
# limitations under the License.
16
content.source=org.apache.lucene.benchmark.byTask.feeds.LineDocSource
17
content.source.encoding=UTF-8
19
doc.body.tokenized=true
20
docs.file=work/top100k-out/top.fr.wikipedia.words.txt
21
content.source.forever=false
25
-NewAnalyzer(KeywordAnalyzer)
26
-SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
28
{ "FrenchKeyword" { ReadTokens > : * ResetInputs } : 10
30
-NewAnalyzer(KeywordAnalyzer)
31
-SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
33
{ "GermanKeyword" { ReadTokens > : * ResetInputs } : 10
35
-NewAnalyzer(KeywordAnalyzer)
36
-SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
38
{ "UkrainianKeyword" { ReadTokens > : * ResetInputs } : 10
40
-NewAnalyzer(KeywordAnalyzer)
41
-SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
43
{ "EnglishKeyword" { ReadTokens > : * ResetInputs } : 10
47
-SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
49
{ "FrenchJDK" { ReadTokens > : * ResetInputs } : 10
53
-SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
55
{ "GermanJDK" { ReadTokens > : * ResetInputs } : 10
59
-SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
61
{ "UkrainianJDK" { ReadTokens > : * ResetInputs } : 10
65
-SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
67
{ "EnglishJDK" { ReadTokens > : * ResetInputs } : 10
70
-NewCollationAnalyzer(impl:icu)
71
-SetProp(docs.file,work/top100k-out/top.fr.wikipedia.words.txt)
73
{ "FrenchICU" { ReadTokens > : * ResetInputs } : 10
76
-NewCollationAnalyzer(impl:icu)
77
-SetProp(docs.file,work/top100k-out/top.de.wikipedia.words.txt)
79
{ "GermanICU" { ReadTokens > : * ResetInputs } : 10
82
-NewCollationAnalyzer(impl:icu)
83
-SetProp(docs.file,work/top100k-out/top.uk.wikipedia.words.txt)
85
{ "UkrainianICU" { ReadTokens > : * ResetInputs } : 10
88
-NewCollationAnalyzer(impl:icu)
89
-SetProp(docs.file,work/top100k-out/top.en.wikipedia.words.txt)
91
{ "EnglishICU" { ReadTokens > : * ResetInputs } : 10