%global githash f70b1a403faf49a2a6d9a97ee3cadbcafd614c5a Name: cleartk Version: 2.0.0 Release: 1%{?dist} Summary: Machine learning components for Apache UIMA License: BSD URL: http://cleartk.github.io/cleartk/ # Remove prebuilt libraries # sh cleartk-repack.sh < githash > Source0: %{name}-%{githash}-clean.tar.xz Source1: cleartk-repack.sh BuildRequires: maven-local BuildRequires: mvn(com.google.guava:guava) BuildRequires: mvn(com.lexicalscope.jewelcli:jewelcli) BuildRequires: mvn(commons-io:commons-io) BuildRequires: mvn(de.bwaldvogel:liblinear) BuildRequires: mvn(de.tudarmstadt.ukp.dkpro.core:de.tudarmstadt.ukp.dkpro.core.api.resources-asl) BuildRequires: mvn(junit:junit) BuildRequires: mvn(org.apache.opennlp:opennlp-maxent) BuildRequires: mvn(org.apache.opennlp:opennlp-tools) BuildRequires: mvn(org.apache.opennlp:opennlp-uima) BuildRequires: mvn(org.apache.uima:jcasgen-maven-plugin) BuildRequires: mvn(org.apache.uima:uimaj-core) BuildRequires: mvn(org.apache.uima:uimaj-document-annotation) BuildRequires: mvn(org.apache.uima:uimafit-core) BuildRequires: mvn(org.jdom:jdom2) BuildRequires: mvn(tw.edu.ntu.csie:libsvm) # https://gil.fedorapeople.org/crfsuite-0.12-1.fc22.src.rpm # Requires: crfsuite BuildArch: noarch %description ClearTK is a framework for developing machine learning and natural language processing components within the Apache Unstructured Information Management Architecture. %package javadoc Summary: Javadoc for %{name} %description javadoc This package contains javadoc for %{name}. %prep %setup -q -n %{name}-%{githash} %pom_remove_plugin -r :maven-assembly-plugin # org.chboston.cnlp:libsvm-java-kernel:0.1.0 %pom_disable_module cleartk-ml-libsvm-tk # cc.mallet:mallet:2.0.7 %pom_disable_module cleartk-ml-mallet # nz.ac.waikato.cms.weka:weka-dev:3.7.11 %pom_disable_module cleartk-ml-weka # edu.berkeley.nlp:berkeleyparser:r32 %pom_disable_module cleartk-berkeleyparser # com.clearnlp:clearnlp:2.0.1, # com.clearnlp:clearnlp-dictionary:1.0, # com.clearnlp:clearnlp-general-en-pos:1.1, # com.clearnlp:clearnlp-general-en-dep:1.2, # com.clearnlp:clearnlp-general-en-srl:1.1 %pom_disable_module cleartk-clearnlp # org.maltparser:maltparser:1.8 %pom_disable_module cleartk-maltparser # org.apache.lucene:lucene-snowball:3.0.3 %pom_disable_module cleartk-snowball # edu.stanford.nlp:stanford-corenlp:3.2.0, # edu.stanford.nlp:stanford-corenlp:models:3.2.0 %pom_disable_module cleartk-stanford-corenlp # Use (also) above modules %pom_disable_module cleartk-examples # package org.jdom2 does not exist %pom_change_dep org.jdom: :jdom2 cleartk-corpus # Disable lucene support %pom_remove_dep -r :cleartk-snowball sed -i '/DefaultSnowballStemmer/d' \ cleartk-summarization/src/main/java/org/cleartk/summarization/SumBasic.java \ cleartk-timeml/src/main/java/org/cleartk/timeml/TimeMlAnnotate.java \ cleartk-timeml/src/main/java/org/cleartk/timeml/eval/TempEval201*.java \ cleartk-timeml/src/main/java/org/cleartk/timeml/tlink/VerbClauseTemporal*.java # These tests fail for unavailable resources # :[110,9] exception org.apache.uima.UIMAException is never thrown in body of corresponding try statement rm -r cleartk-util/src/test/java/org/cleartk/util/AnnotationUtilTest.java # AssertionError # expected:<[a-test1.txt.5.xmi, b-test2.dat.11.xmi, a-test1.txt.7.xmi, a-test1.txt.2.xmi, a-test1.txt.3.xmi, b-test2.dat.9.xmi, a-test1.txt.8.xmi, a-test1.txt.6.xmi, b-test2.dat.10.xmi, a-test1.txt.4.xmi, a-test1.txt.1.xmi, b-test2.dat.12.xmi]> but was:<[a-test1.txt.5.xmi, a-test1.txt.7.xmi, b-test2.dat.4.xmi, a-test1.txt.8.xmi, b-test2.dat.2.xmi, a-test1.txt.11.xmi, a-test1.txt.6.xmi, a-test1.txt.9.xmi, a-test1.txt.12.xmi, b-test2.dat.3.xmi, a-test1.txt.10.xmi, b-test2.dat.1.xmi]> rm -r cleartk-util/src/test/java/org/cleartk/util/cr/linereader/LineReaderXmiWriterTest.java rm -r cleartk-ml/src/test/java/org/cleartk/ml/feature/selection/MutualInformationTest.java # IOException: Cannot run program "svm_learn", "svm_rank_learn" rm -r cleartk-ml-svmlight/src/test/java/org/cleartk/ml/svmlight/RunSvmLightTest.java # MissingResourceException: No classifier jar found at eventannotator/model.jar rm -r cleartk-timeml/src/test/java/org/cleartk/timeml/event/EventAnnotatorsTest.java \ cleartk-timeml/src/test/java/org/cleartk/timeml/TimeMlAnnotateTest.java # cleartk-ml-crfsuite/src/main/resources/crfsuite/*/bin/crfsuite* rm -r cleartk-ml-crfsuite/src/test/java/org/cleartk/ml/crfsuite/CrfSuiteClassifierTest.java # cleartk-opennlp-tools/src/main/resources/models/en-token.bin # cleartk-opennlp-tools/src/main/resources/models/en-pos-maxent.bin # cleartk-opennlp-tools/src/main/resources/models/en-sent.bin # cleartk-opennlp-tools/src/main/resources/models/en-parser-chunking.bin # cleartk-opennlp-tools/src/test/resources/data/parser/craft_test/craft_test.bin rm -r cleartk-opennlp-tools/src/test/java/org/cleartk/opennlp/tools/ParserAnnotatorTest.java \ cleartk-opennlp-tools/src/test/java/org/cleartk/opennlp/tools/PosTaggerAnnotatorTest.java \ cleartk-opennlp-tools/src/test/java/org/cleartk/opennlp/tools/PosTaggerTest.java \ cleartk-opennlp-tools/src/test/java/org/cleartk/opennlp/tools/SentenceAnnotatorTest.java \ cleartk-opennlp-tools/src/test/java/org/cleartk/opennlp/tools/TokenizerTest.java %build %mvn_build %install %mvn_install %files -f .mfiles %doc README %license LICENSE %files javadoc -f .mfiles-javadoc %license LICENSE %changelog * Thu Sep 03 2015 gil cattaneo 2.0.0-1 - initial rpm