Add integration testing for clickhouse sql

db-scripts/src/main/resources/clickhouse-test.sql

@@ -0,0 +1,121 @@
+create table cna_discrete
+(
+ sample_unique_id varchar(255),
+ alteration int(11),
+ hugo_gene_symbol varchar(255),
+ gene_panel_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ genetic_profile_stable_id varchar(255),
+ PRIMARY KEY (sample_unique_id, alteration, hugo_gene_symbol, cancer_study_identifier)
+);
+
+create table genetic_profile
+(
+ sample_unique_id varchar(255),
+ genetic_alteration_type varchar(255),
+ datatype varchar(255),
+ value varchar(255),
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (sample_unique_id, genetic_alteration_type, datatype, value, cancer_study_identifier)
+);
+
+create table genetic_profile_counts
+(
+ sample_unique_id varchar(255),
+ profile_name varchar(255),
+ genetic_profile_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ count int(11)
+);
+
+create table genomic_event
+(
+ sample_unique_id varchar(255),
+ variant varchar(255),
+ hugo_gene_symbol varchar(255),
+ gene_panel_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ genetic_profile_stable_id varchar(255),
+ PRIMARY KEY (sample_unique_id, variant, hugo_gene_symbol, cancer_study_identifier, genetic_profile_stable_id)
+);
+
+create table mutation
+(
+ sample_unique_id varchar(255),
+ variant varchar(255),
+ hugo_gene_symbol varchar(255),
+ gene_panel_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ genetic_profile_stable_id varchar(255),
+ PRIMARY KEY (sample_unique_id, variant, hugo_gene_symbol, cancer_study_identifier)
+);
+
+create table patient_clinical_attribute_categorical
+(
+ patient_unique_id varchar(255),
+ attribute_name varchar(255),
+ attribute_value varchar(255),
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier)
+);
+
+create table patient_clinical_attribute_numeric
+(
+ patient_unique_id varchar(255),
+ attribute_name varchar(255),
+ attribute_value float,
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier)
+);
+
+create table sample
+(
+ sample_unique_id varchar(255),
+ sample_stable_id varchar(255),
+ patient_unique_id varchar(255),
+ patient_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ sample_unique_id_base64 varchar(255),
+ patient_unique_id_base64 varchar(255),
+ PRIMARY KEY (sample_unique_id, patient_unique_id, cancer_study_identifier)
+);
+
+create table sample_clinical_attribute_categorical
+(
+ patient_unique_id varchar(255),
+ sample_unique_id varchar(255),
+ attribute_name varchar(255),
+ attribute_value varchar(255),
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (patient_unique_id, sample_unique_id, attribute_name, attribute_value, cancer_study_identifier)
+);
+
+create table sample_clinical_attribute_numeric
+(
+ patient_unique_id varchar(255),
+ sample_unique_id varchar(255),
+ attribute_name varchar(255),
+ attribute_value float,
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (patient_unique_id, sample_unique_id, attribute_name, attribute_value, cancer_study_identifier)
+);
+
+create table sample_list
+(
+ sample_unique_id varchar(255),
+ sample_list_stable_id varchar(255),
+ name varchar(255),
+ cancer_study_identifier varchar(255),
+ PRIMARY KEY (sample_unique_id, sample_list_stable_id, name, cancer_study_identifier)
+);
+
+create table structural_variant
+(
+ sample_unique_id varchar(255),
+ hugo_symbol_gene1 varchar(255),
+ hugo_symbol_gene2 varchar(255),
+ gene_panel_stable_id varchar(255),
+ cancer_study_identifier varchar(255),
+ genetic_profile_stable_id varchar(255),
+ PRIMARY KEY (sample_unique_id, hugo_symbol_gene1, hugo_symbol_gene2, cancer_study_identifier)
+);

persistence/persistence-mybatis/src/test/java/org/cbioportal/persistence/mybatiscolumnstore/StudyViewMyBatisRepositoryTest.java

@@ -0,0 +1,50 @@
+package org.cbioportal.persistence.mybatiscolumnstore;
+
+import org.cbioportal.model.AlterationCountByGene;
+import org.cbioportal.model.Sample;
+import org.cbioportal.webparam.StudyViewFilter;
+import org.junit.Assert;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.beans.factory.annotation.Configurable;
+import org.springframework.test.context.ContextConfiguration;
+import org.springframework.test.context.junit4.SpringJUnit4ClassRunner;
+
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+
+@RunWith(SpringJUnit4ClassRunner.class)
+@ContextConfiguration("/testContextDatabaseCH.xml")
+@Configurable
+public class StudyViewMyBatisRepositoryTest {
+
+ @Autowired
+ private StudyViewMyBatisRepository studyViewMyBatisRepository;
+
+ @Test
+ public void getFilteredSamples() {
+ StudyViewFilter studyViewFilter = new StudyViewFilter();
+
+ List<String> studyIds = new ArrayList<>();
+ studyIds.add("msk_ch_2020");
+ studyViewFilter.setStudyIds(studyIds);
+
+ List<Sample> samples = studyViewMyBatisRepository.getFilteredSamplesFromColumnstore(studyViewFilter);
+ Assert.assertEquals(3, samples.size());
+ }
+
+ @Test
+ public void getMutatedGenes() {
+ StudyViewFilter studyViewFilter = new StudyViewFilter();
+
+ List<String> studyIds = new ArrayList<>();
+ studyIds.add("msk_ch_2020");
+ studyViewFilter.setStudyIds(studyIds);
+
+ List<AlterationCountByGene> mutations = studyViewMyBatisRepository.getMutatedGenes(studyViewFilter);
+ Assert.assertEquals(2, mutations.size());
+ }
+
+}

persistence/persistence-mybatis/src/test/resources/clickhouseTestSql.sql

@@ -0,0 +1,20 @@
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000004', 'AGE', 39.739902, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000004', 'TIME_FROM_DX_TO_SEQ', 991, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000004', 'TIME_TO_BLOOD_DRAW_FROM_TX', 609, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000015', 'AGE', 44.440792, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000015', 'TIME_FROM_DX_TO_SEQ', 2558, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000015', 'TIME_TO_BLOOD_DRAW_FROM_TX', 5, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000023', 'AGE', 61.319645, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000023', 'TIME_FROM_DX_TO_SEQ', 245, 'msk_ch_2020');
+INSERT INTO patient_clinical_attribute_numeric (patient_unique_id, attribute_name, attribute_value, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000023', 'TIME_TO_BLOOD_DRAW_FROM_TX', 166, 'msk_ch_2020');
+
+INSERT INTO sample (sample_unique_id, sample_unique_id_base64, sample_stable_id, patient_unique_id, patient_unique_id_base64, patient_stable_id, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000004-N01', '', 'P-0000004-N01', 'msk_ch_2020_P-0000004', '', 'P-0000004', 'msk_ch_2020');
+INSERT INTO sample (sample_unique_id, sample_unique_id_base64, sample_stable_id, patient_unique_id, patient_unique_id_base64, patient_stable_id, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000015-N01', '', 'P-0000015-N01', 'msk_ch_2020_P-0000015', '', 'P-0000015', 'msk_ch_2020');
+INSERT INTO sample (sample_unique_id, sample_unique_id_base64, sample_stable_id, patient_unique_id, patient_unique_id_base64, patient_stable_id, cancer_study_identifier) VALUES ('msk_ch_2020_P-0000023-N01', '', 'P-0000023-N01', 'msk_ch_2020_P-0000023', '', 'P-0000023', 'msk_ch_2020');
+-- 
+INSERT INTO genomic_event (sample_unique_id, variant, hugo_gene_symbol, gene_panel_stable_id, cancer_study_identifier, genetic_profile_stable_id) VALUES ('msk_ch_2020_P-0000004-N01', 'p.R1051Q', 'KDR', '', 'msk_ch_2020', 'msk_ch_2020_mutations');
+INSERT INTO genomic_event (sample_unique_id, variant, hugo_gene_symbol, gene_panel_stable_id, cancer_study_identifier, genetic_profile_stable_id) VALUES ('msk_ch_2020_P-0000004-N01', 'p.T1884I', 'TET2', '', 'msk_ch_2020', 'msk_ch_2020_mutations');
+
+INSERT INTO mutation (sample_unique_id, variant, hugo_gene_symbol, gene_panel_stable_id, cancer_study_identifier, genetic_profile_stable_id) VALUES ('msk_ch_2020_P-0000004-N01', 'p.R1051Q', 'KDR', '', 'msk_ch_2020', 'msk_ch_2020_mutations');
+INSERT INTO mutation (sample_unique_id, variant, hugo_gene_symbol, gene_panel_stable_id, cancer_study_identifier, genetic_profile_stable_id) VALUES ('msk_ch_2020_P-0000004-N01', 'p.T1884I', 'TET2', '', 'msk_ch_2020', 'msk_ch_2020_mutations');
+

persistence/persistence-mybatis/src/test/resources/testContextDatabaseCH.xml

@@ -0,0 +1,65 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<!--
+ Copyright (c) 2016 Memorial Sloan-Kettering Cancer Center.
+
+ This library is distributed in the hope that it will be useful, but WITHOUT
+ ANY WARRANTY, WITHOUT EVEN THE IMPLIED WARRANTY OF MERCHANTABILITY OR FITNESS
+ FOR A PARTICULAR PURPOSE. The software and documentation provided hereunder
+ is on an "as is" basis, and Memorial Sloan-Kettering Cancer Center has no
+ obligations to provide maintenance, support, updates, enhancements or
+ modifications. In no event shall Memorial Sloan-Kettering Cancer Center be
+ liable to any party for direct, indirect, special, incidental or
+ consequential damages, including lost profits, arising out of the use of this
+ software and its documentation, even if Memorial Sloan-Kettering Cancer
+ Center has been advised of the possibility of such damage.
+
+ This file is part of cBioPortal.
+
+ cBioPortal is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero General Public License as
+ published by the Free Software Foundation, either version 3 of the
+ License.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Affero General Public License for more details.
+
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+-->
+
+<beans
+ xmlns="http://www.springframework.org/schema/beans"
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+ xmlns:util="http://www.springframework.org/schema/util"
+ xmlns:context="http://www.springframework.org/schema/context"
+ xsi:schemaLocation="http://www.springframework.org/schema/beans
+ http://www.springframework.org/schema/beans/spring-beans.xsd
+ http://www.springframework.org/schema/context
+ http://www.springframework.org/schema/context/spring-context.xsd
+ http://www.springframework.org/schema/util
+ http://www.springframework.org/schema/util/spring-util.xsd">
+ <bean id="dbcpDataSource" class="org.springframework.jdbc.datasource.DriverManagerDataSource">
+ <property name="url" value="jdbc:h2:mem:;MODE=MySQL;DATABASE_TO_UPPER=false;INIT=RUNSCRIPT FROM 'classpath:clickhouse-test.sql'\;RUNSCRIPT FROM 'classpath:clickhouseTestSql.sql'"/>
+ </bean>
+
+
+ <bean id="sqlSessionFactory" class="org.mybatis.spring.SqlSessionFactoryBean">
+ <property name="dataSource" ref="dbcpDataSource"/>
+ <property name="typeAliasesPackage" value="org.mskcc.cbio.portal.model"/>
+ <property name="typeHandlersPackage" value="org.cbioportal.persistence.mybatis.typehandler"/>
+ </bean>
+
+ <bean id="transactionManager" class="org.springframework.jdbc.datasource.DataSourceTransactionManager">
+ <property name="dataSource" ref="dbcpDataSource" />
+ </bean>
+
+ <bean class="org.mybatis.spring.mapper.MapperScannerConfigurer">
+ <property name="basePackage" value="org.cbioportal.persistence.mybatiscolumnstore"/>
+ </bean>
+
+ <context:component-scan base-package="org.cbioportal.persistence.mybatiscolumnstore"/>
+
+</beans>