-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
LUCENE-2181: add a benchmark for collation
git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@898491 13f79535-47bb-0310-9956-ffa450edef68
- Loading branch information
Showing
10 changed files
with
671 additions
and
4 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,63 @@ | ||
| #!/usr/bin/perl | ||
| # | ||
| # 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. | ||
| # | ||
| # ---------- | ||
| # bm2jira.pl | ||
| # | ||
| # Converts Lucene contrib-benchmark output produced using the | ||
| # benchmark.collation.alg file into a JIRA-formatted table. | ||
| # | ||
|
|
||
| use strict; | ||
| use warnings; | ||
|
|
||
| my %min_elapsed = (); | ||
|
|
||
| while (<>) { | ||
| if (/(\S+)(Keyword|JDK|ICU)_\d+\s*([^\s{].*)/) { | ||
| my $lang = $1; | ||
| my $analyzer = $2; | ||
| my $stats = $3; | ||
| my ($elapsed) = $stats =~ /(?:[\d,.]+[-\s]*){4}([.\d]+)/; | ||
| $min_elapsed{$analyzer}{$lang} = $elapsed | ||
| unless (defined($min_elapsed{$analyzer}{$lang}) | ||
| && $elapsed >= $min_elapsed{$analyzer}{$lang}); | ||
| } | ||
| } | ||
|
|
||
| # Print out platform info | ||
| print "JAVA:\n", `java -version 2>&1`, "\nOS:\n"; | ||
| if ($^O =~ /win/i) { | ||
| print "$^O\n"; | ||
| eval { | ||
| require Win32; | ||
| print Win32::GetOSName(), "\n", Win32::GetOSVersion(), "\n"; | ||
| }; | ||
| die "Error loading Win32: $@" if ($@); | ||
| } else { | ||
| print `uname -a 2>&1`; | ||
| } | ||
|
|
||
| print "\n||Language||java.text||ICU4J||KeywordAnalyzer||ICU4J Improvement||\n"; | ||
|
|
||
| for my $lang (sort keys %{$min_elapsed{ICU}}) { | ||
| my $ICU = $min_elapsed{ICU}{$lang}; | ||
| my $JDK = $min_elapsed{JDK}{$lang}; | ||
| my $keyword = $min_elapsed{Keyword}{$lang}; | ||
| my $improved = int(100 * ($JDK - $ICU) / ($ICU - $keyword) + 0.5); | ||
| printf "|$lang|${JDK}s|${ICU}s|${keyword}s|\%d%%|\n", $improved; | ||
| } |
91 changes: 91 additions & 0 deletions
91
contrib/benchmark/scripts/compare.collation.benchmark.tables.pl
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,91 @@ | ||
| #!/usr/bin/perl | ||
| # | ||
| # 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. | ||
| # | ||
| # ------------------------------------------ | ||
| # compare.collation.benchmark.jira.tables.pl | ||
| # | ||
| # Takes as cmdline parameters two JIRA-formatted benchmark results, as produced | ||
| # by bm2jira.pl (located in the same directory as this script), and outputs a | ||
| # third JIRA-formatted comparison table, showing the differences between two | ||
| # benchmarking runs' java.text and ICU4J columns, after accounting for the | ||
| # KeywordAnalyzer column; the "ICU4J Improvement" column is ignored. | ||
| # | ||
| # The difference is calculated as a percentage: | ||
| # | ||
| # 100 * (patched-rate - unpatched-rate / unpatched-rate) | ||
| # | ||
| # where the (un)patched-rate is: | ||
| # | ||
| # 1 / ( elapsed-(un)patched-time - elapsed-KeywordAnalyzer-time) | ||
| # | ||
|
|
||
| use strict; | ||
| use warnings; | ||
|
|
||
| my $usage = "Usage: $0 <unpatched-file> <patched-file>\n"; | ||
|
|
||
| die $usage unless ($#ARGV == 1 && -f $ARGV[0] && -f $ARGV[1]); | ||
|
|
||
| my %stats = (); | ||
|
|
||
| open UNPATCHED, "<$ARGV[0]" || die "ERROR opening '$ARGV[0]': $!"; | ||
| while (<UNPATCHED>) { | ||
| # ||Language||java.text||ICU4J||KeywordAnalyzer||ICU4J Improvement|| | ||
| # |English|4.51s|2.47s|1.47s|204%| | ||
| next unless (/^\|([^|]+)\|([^|s]+)s\|([^|s]+)s\|([^|s]+)s/); | ||
| my ($lang, $jdk_elapsed, $icu_elapsed, $keyword_analyzer_elapsed) | ||
| = ($1, $2, $3, $4); | ||
| $stats{unpatched}{$lang}{jdk} = $jdk_elapsed; | ||
| $stats{unpatched}{$lang}{icu} = $icu_elapsed; | ||
| $stats{unpatched}{$lang}{keyword_analyzer} = $keyword_analyzer_elapsed; | ||
| } | ||
| close UNPATCHED; | ||
|
|
||
| open PATCHED, "<$ARGV[1]" || die "ERROR opening '$ARGV[1]': $!"; | ||
| while (<PATCHED>) { | ||
| # ||Language||java.text||ICU4J||KeywordAnalyzer||ICU4J Improvement|| | ||
| # |English|4.51s|2.47s|1.47s|204%| | ||
| next unless (/^\|([^|]+)\|([^|s]+)s\|([^|s]+)s\|([^|s]+)s/); | ||
| my ($lang, $jdk_elapsed, $icu_elapsed, $keyword_analyzer_elapsed) | ||
| = ($1, $2, $3, $4); | ||
| $stats{patched}{$lang}{jdk} = $jdk_elapsed; | ||
| $stats{patched}{$lang}{icu} = $icu_elapsed; | ||
| $stats{patched}{$lang}{keyword_analyzer} = $keyword_analyzer_elapsed; | ||
| } | ||
| close PATCHED; | ||
|
|
||
| print "||Language||java.text improvement||ICU4J improvement||\n"; | ||
| for my $lang (sort keys %{$stats{unpatched}}) { | ||
| my $keyword_analyzer1 = $stats{unpatched}{$lang}{keyword_analyzer}; | ||
| my $jdk1 = $stats{unpatched}{$lang}{jdk}; | ||
| my $jdk_diff1 = $jdk1 - $keyword_analyzer1; | ||
| my $icu1 = $stats{unpatched}{$lang}{icu}; | ||
| my $icu_diff1 = $icu1 - $keyword_analyzer1; | ||
|
|
||
| my $keyword_analyzer2 = $stats{patched}{$lang}{keyword_analyzer}; | ||
| my $jdk2 = $stats{patched}{$lang}{jdk}; | ||
| my $jdk_diff2 = $jdk2 - $keyword_analyzer2; | ||
| my $icu2 = $stats{patched}{$lang}{icu}; | ||
| my $icu_diff2 = $icu2 - $keyword_analyzer2; | ||
|
|
||
| my $jdk_impr | ||
| = int((1./$jdk_diff2 - 1./$jdk_diff1) / (1./$jdk_diff1) * 1000 + 5) / 10; | ||
| my $icu_impr | ||
| = int((1./$icu_diff2 - 1./$icu_diff1) / (1./$icu_diff1) * 1000 + 5) / 10; | ||
|
|
||
| printf "|$lang|%2.1f%%|%2.1f%%|\n", $jdk_impr, $icu_impr; | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.