-
Notifications
You must be signed in to change notification settings - Fork 37
/
build.gradle
191 lines (170 loc) · 7.76 KB
/
build.gradle
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
plugins {
id "de.undercouch.download" version "1.2"
id 'java'
id 'eclipse'
id 'application'
id 'maven'
}
// Meta information
mainClassName = System.getProperty("mainClass")
version = "0.4.0"
group = "edu.uncc"
sourceCompatibility = 1.8
// Dependencies and where to get them (some are nonstandard)
repositories {
mavenCentral()
maven {url "https://repo.eclipse.org/content/groups/releases/"}
// maven {url "https://googledrive.com/host/0B8wOEC5-v5lXak1WSF9YRkdOZGc/"}
flatDir {dirs "lib"}
flatDir {dirs "data/lib"}
}
dependencies {
// Machine learning
compile group: "com.googlecode.jcsv", name: "jcsv", version: "1.4.0"
compile 'nz.ac.waikato.cms.weka:weka-stable:3.6.10'
// A native library used by weka
compile name: 'libsvm'
compile group: "com.github.spullara.cli-parser", name: "cli-parser", version: "1.1"
// Statistics
compile group: "com.googlecode.json-simple", name: "json-simple", version: "1.1"
compile group: "org.apache.httpcomponents", name: "fluent-hc", version: "4.3.1"
compile group: "org.eclipse.jgit", name: "org.eclipse.jgit", version: "3.2.0.201312181205-r"
// Search Engines
compile group: "org.apache.lucene", name: "lucene-core", version: "5.0.0"
compile group: "org.apache.lucene", name: "lucene-queryparser", version: "5.0.0"
compile group: "org.apache.lucene", name: "lucene-analyzers-common", version: "5.0.0"
compile group: "org.apache.lucene", name: "lucene-highlighter", version: "5.0.0"
compile 'org.apache.lucene:lucene-backward-codecs:5.0.0'
compile group: "lemurproject.indri", name: "indri", version: "5.7"
compile group: "com.google.api-client", name: "google-api-client", version: "1.17.0-rc"
compile 'com.google.apis:google-api-services-customsearch:v1-rev34-1.17.0-rc'
compile "com.google.http-client:google-http-client-jackson2:1.17.0-rc"
compile "org.apache.abdera:abdera-parser:1.1.1"
compile "org.jsoup:jsoup:1.7.3"
// Approximate String Matching
compile 'org.apache.commons:commons-lang3:3.3.2'
compile 'commons-dbutils:commons-dbutils:1.6'
// Indri native library
// natives "libindri-jni:libindri-jni:5.6"
//// Persistence Libraries
// Sqlite native library (but it comes in a jar)
compile "org.xerial:sqlite-jdbc:3.8.7"
// PostgreSQL
compile 'org.postgresql:postgresql:9.3-1101-jdbc41'
// LMDB (for fast concurrent kv-storage)
compile 'org.deephacks.lmdbjni:lmdbjni:0.4.4'
compile 'org.deephacks.lmdbjni:lmdbjni-linux64:0.4.4'
compile 'org.deephacks.lmdbjni:lmdbjni-osx64:0.4.4'
//compile 'org.deephacks.lmdbjni:lmdbjni-win64:0.4.4'
// Leveldb for fast writes
compile 'org.fusesource.leveldbjni:leveldbjni-all:1.8'
// High performance primitive collections
compile 'com.carrotsearch:hppc:0.6.1'
//// NLP Libraries
// OpenNLP
compile "org.apache.opennlp:opennlp-tools:1.5.3"
// Stanford CoreNLP
compile 'edu.stanford.nlp:stanford-corenlp:3.5.1'
compile 'edu.stanford.nlp:stanford-corenlp:3.5.1:models'
// SRParser models are necessary but too large for maven
compile name: 'stanford-srparser-2014-08-28-models'
// WebDAV
compile 'com.github.lookfirst:sardine:5.1'
//compile 'org.slf4j:slf4j-simple:1.6.1'
// UIMA for Java
compile group:'org.apache.uima', name: 'uimaj-core', version: '2.3.1'
// lightweight web framework
compile 'javax.servlet:javax.servlet-api:3.1.0' // included because of a mismatch betwen groovy and spark
compile "com.sparkjava:spark-core:2.3"
compile "org.java-websocket:Java-WebSocket:1.3.0"
// multimaps and many other tools
compile "com.google.guava:guava:17.0"
compile "junit:junit:4.12"
// Jena for SPARQL connections
compile "org.apache.jena:jena-tdb:1.1.1"
// This is necessary for full text search
// But it also installs a .pom as a .jar as one of its transiitives
// and that makes Eclipse croak. So we will have to edit the classpath file
compile "org.apache.jena:jena-text:1.1.1"
compile 'xom:xom:+'
compile "xalan:xalan:+"
// Prolog interface for dependency tree matching
compile 'jpl:jpl:3.1.4-alpha'
compile 'it.unibo.alice.tuprolog:tuprolog:2.1.1'
// Persistent Data Structures for sane transactional semantics
compile "org.functionaljava:functionaljava-java8:4.2"
// LZ4 for efficiently compressing text
compile 'net.jpountz.lz4:lz4:1.3'
// Boilerpipe for extracting text from web pages
compile 'com.syncthemall:boilerpipe:1.2.2'
// Crawler-commons to extract text in a robots.txt friendly way
compile 'com.google.code.crawler-commons:crawler-commons:0.5'
// Semantic Vectors for improved Lucene scoring
compile 'pitt.search:semanticvectors:5.8'
// GSON for cache persistence
compile 'com.google.code.gson:gson:2.3.1'
}
task environment << {
download {
onlyIfNewer true
src 'http://nlp.stanford.edu/software/stanford-srparser-2014-08-28-models.jar'
dest 'lib'
}
download {
src 'https://dl.dropboxusercontent.com/u/92563044/watsonsim/data-snapshot.tar.gz' // ~50GB uncompressed, varies
src 'https://dl.dropboxusercontent.com/u/92563044/watsonsim/data-snapshot.pgdump' // ~50GB uncompressed, varies
src 'https://dl.dropboxusercontent.com/u/92563044/watsonsim/indri-5.8.tar.gz' // ~50MB
src 'http://apache.osuosl.org/jena/binaries/jena-fuseki-1.1.1-distribution.tar.gz' // ~50MB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/dbpedia_2014.owl.bz2' // ~2 MB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/en/instance_types_en.nt.bz2' // ~4 GB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/en/labels_en.nt.bz2' // ~1 GB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/en/instance_types_heuristic_en.nt.bz2' // ~ 1 GB
src 'http://wifo5-04.informatik.uni-mannheim.de/downloads/datasets/genders_en.nt.bz2' // 31 MB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/en/disambiguations_en.nt.bz2' // 194 MB
src 'http://data.dws.informatik.uni-mannheim.de/dbpedia/2014/en/short_abstracts_en.nt.bz2' // 1.8 GB
dest 'downloads'
}
copy {
from '/usr/share/java/libsvm.jar'
into 'lib'
}
}
run {
// Allow reading from stdin
standardInput = System.in
// Find Indri
systemProperty "java.library.path", file("$projectDir/lib:$projectDir/data/lib")
//jvmArgs "-XX:-UseCompressedOops"
jvmArgs "-XX:hashCode=5"
//jvmArgs "-Xns:100m"
//jvmArgs "-Xgcprio:throughput"
main "edu.uncc.cs.watsonsim.$target"
}
task(train, type:JavaExec) {
// Find Indri
main "edu.uncc.cs.watsonsim.scripts.ParallelStats"
systemProperty "java.library.path", file("$projectDir/lib:$projectDir/data/lib")
}
task(run_index, type: JavaExec) {
// Find Indri
systemProperty "java.library.path", file("$projectDir/lib:$projectDir/data/lib")
main "edu.uncc.cs.watsonsim.sources.DBIndexer"
}
test {
systemProperty "java.library.path", file("$projectDir/lib:$projectDir/data/lib")
testLogging {
exceptionFormat = 'full'
}
}
eclipse {
classpath {
file.withXml {provider ->
provider.asNode().findAll { it.@path.contains("indri") }.each {
it.appendNode('attributes')
it.children().each {
it.appendNode('attribute', [name: 'org.eclipse.jdt.launching.CLASSPATH_ATTR_LIBRARY_PATH_ENTRY', value: "$projectDir/lib"])
}
}
}
}
}