Update ctakes-ytex to support MySQLversion 8.0.x database

ctakes-ytex/scripts/data/build.xml

@@ -531,7 +531,8 @@ ${sql.delimiter}
 		<copy file="${basedir}/conn.xml.template" tofile="${java.io.tmpdir}/conn.xml" overwrite="yes">
 			<filterset>
 				<filter token="db.driver" value="${db.driver}" />
-				<filter token="db.url" value="${db.url}" />
+                <!-- conn.xml needs to replace with ampersands escaped -->
+				<filter token="db.url" value="${xmldb.url}" />
 				<filter token="db.username" value="${db.username}" />
 				<filter token="db.password" value="${db.password}" />
 			</filterset>
@@ -599,4 +600,4 @@ ${sql.delimiter}
 			<param name="sqlcmd.script" value="index_tables${suffix}.sql" />
 		</antcall>
 	</target>
-</project>
+</project>

ctakes-ytex/scripts/data/mysql/kernel/create_tables.sql

@@ -159,17 +159,20 @@ create table feature_eval (
   index ix_feature_eval(corpus_name, cv_fold_id, type)
 ) engine=myisam comment 'evaluation of a set of features in a corpus';
 
-create table feature_rank (
-  feature_rank_id int auto_increment not null primary key,
-  feature_eval_id int not null comment 'fk feature_eval',
-  feature_name varchar(50) not null comment 'name of feature',
-  evaluation double not null default 0 comment 'measurement of feature worth',
-  rank int not null default 0 comment 'rank among all features',
-  unique index nk_feature_name(feature_eval_id, feature_name),
-  index ix_feature_rank(feature_eval_id, rank),
-  index ix_feature_evaluation(feature_eval_id, evaluation),
-  index fk_feature_eval(feature_eval_id)
-) engine=myisam comment 'evaluation of a feature in a corpus';
+-- update for MySQL 8.0.x
+CREATE TABLE `feature_rank` (
+  `feature_rank_id` int NOT NULL AUTO_INCREMENT,
+  `feature_eval_id` int NOT NULL COMMENT 'fk feature_eval',
+  `feature_name` varchar(50) NOT NULL COMMENT 'name of feature',
+  `evaluation` double NOT NULL DEFAULT '0' COMMENT 'measurement of feature worth',
+  `rank` int NOT NULL DEFAULT '0' COMMENT 'rank among all features',
+  PRIMARY KEY (`feature_rank_id`),
+  UNIQUE KEY `nk_feature_name` (`feature_eval_id`,`feature_name`),
+  INDEX `ix_feature_rank` (`feature_eval_id`,`rank`),
+  INDEX `ix_feature_evaluation` (`feature_eval_id`,`evaluation`),
+  INDEX `fk_feature_eval` (`feature_eval_id`)
+) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='evaluation of a feature in a corpus';
+
 
 CREATE TABLE feature_parchd (
   feature_parchd_id int(11) NOT NULL AUTO_INCREMENT,
@@ -211,18 +214,23 @@ create table hotspot_instance (
     unique index NK_hotspot_instance (corpus_name, experiment, label, instance_id)
 ) engine=myisam comment 'hotspot features for an instance';
 
-create table hotspot_sentence (
-    hotspot_sentence_id int auto_increment not null primary key,
-    hotspot_instance_id int not null comment 'fk hotspot_instance',
-    anno_base_id int not null comment 'fk anno_sentence',
-    evaluation double not null default 0 comment 'max eval from hotspot',
-    rank int not null default 0 comment 'min rank from hotspot',
-    unique index NK_hotspot_sentence (hotspot_instance_id, anno_base_id),
-    index FK_hotspot_instance_id (hotspot_instance_id),
-	index FK_anno_base_id (anno_base_id),
-    INDEX IX_evaluation (hotspot_instance_id, evaluation),
-    INDEX IX_rank (hotspot_instance_id, rank)
-) engine = myisam comment 'sentences that contain hotspots at specified threshold';
+
+-- update for MySQL 8.0.x
+CREATE TABLE `hotspot_sentence` (
+  `hotspot_sentence_id` int NOT NULL AUTO_INCREMENT,
+  `hotspot_instance_id` int NOT NULL COMMENT 'fk hotspot_instance',
+  `anno_base_id` int NOT NULL COMMENT 'fk anno_sentence',
+  `evaluation` double NOT NULL DEFAULT '0' COMMENT 'max eval from hotspot',
+  `rank` int NOT NULL DEFAULT '0' COMMENT 'min rank from hotspot',
+  PRIMARY KEY (`hotspot_sentence_id`),
+  UNIQUE KEY `NK_hotspot_sentence` (`hotspot_instance_id`,`anno_base_id`),
+  INDEX `FK_hotspot_instance_id` (`hotspot_instance_id`),
+  INDEX `FK_anno_base_id` (`anno_base_id`),
+  INDEX `IX_evaluation` (`hotspot_instance_id`,`evaluation`),
+  INDEX `IX_rank` (`hotspot_instance_id`,`rank`)
+) ENGINE=MyISAM DEFAULT CHARSET=utf8 COMMENT='sentences that contain hotspots at specified threshold';
+
+
 
 create table corpus_doc (
 	corpus_name varchar(50) not null comment 'corpus name',

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/conceptGraph/sct-msh-csp-aod.template.xml

@@ -24,8 +24,8 @@
         <entry key="ytex.conceptGraphQuery"><![CDATA[
         select distinct cui1, cui2 
         from @umls.schema@.MRREL 
-        where sab in ('SNOMEDCT', 'MSH' , 'CSP', 'AOD')
+        where sab in ('SNOMEDCT_US', 'MSH' , 'CSP', 'AOD')
         and rel in ('PAR', 'RB')
         order by cui1, cui2
         ]]></entry>
-</properties>
+</properties>

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/conceptGraph/sct-rxnorm.template.xml

@@ -24,8 +24,8 @@
         <entry key="ytex.conceptGraphQuery"><![CDATA[
         select distinct cui1, cui2 
         from @umls.schema@.MRREL 
-        where sab in ('SNOMEDCT', 'RXNORM')
+        where sab in ('SNOMEDCT_US', 'RXNORM')
         and rel in ('PAR', 'RB')
         order by cui1, cui2
         ]]></entry>
-</properties>
+</properties>

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/conceptGraph/sct-umls.template.xml

@@ -24,8 +24,8 @@
         <entry key="ytex.conceptGraphQuery"><![CDATA[
         select distinct cui1, cui2 
         from @umls.schema@.MRREL 
-        where sab in ('SNOMEDCT')
+        where sab in ('SNOMEDCT_US')
         and rel in ('PAR')
         order by cui1, cui2
         ]]></entry>
-</properties>
+</properties>

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/ytex.properties.mssql.example

@@ -8,6 +8,10 @@ db.schema=dbo
 # with the values of db.host and db.name respectively
 db.url=jdbc:sqlserver://localhost;databaseName=YTEX;integratedSecurity=true
 
+# The xmldb.url should be a duplicate of db.url with the exception of replacing an & with &
+# This is a stopgap to allow conn.xml.template to not break in the SAX parser
+xmldb.url=jdbc:sqlserver://localhost;databaseName=YTEX;integratedSecurity=true
+
 # assume windows integrated authentication, change if necessary
 db.username=
 db.password=

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/ytex.properties.mysql.example

@@ -6,7 +6,12 @@ db.username=ytex
 db.password=ytex
 
 # jdbc url for database.  schema name must match db.schema
-db.url=jdbc:mysql://localhost:3306/ytex?autoReconnect=true
+db.url=jdbc:mysql://localhost:3306/ytex?autoReconnect=TRUE&serverTimezone=US/Eastern&useUnicode=true&characterEncoding=utf8&useSSL=false&allowPublicKeyRetrieval=true
+
+# The xmldb.url should be a duplicate of db.url with the exception of replacing an & with &
+# This is a stopgap to allow conn.xml.template to not break in the SAX parser
+xmldb.url=jdbc:mysql://localhost:3306/ytex?autoReconnect=TRUE&serverTimezone=US/Eastern&useUnicode=true&characterEncoding=utf8&useSSL=false&allowPublicKeyRetrieval=true
+
 
 # the schema where umls is installed
 # if not specified, will default to schema from ytex

ctakes-ytex/src/main/resources/org/apache/ctakes/ytex/ytex.properties.orcl.example

@@ -3,6 +3,10 @@
 # another format that works is e.g.: jdbc:oracle:thin:ytex/ytex@localhost:1521:orcl
 db.url=jdbc:oracle:thin:@localhost:1521:orcl
 
+# The xmldb.url should be a duplicate of db.url with the exception of replacing an & with &
+# This is a stopgap to allow conn.xml.template to not break in the SAX parser
+xmldb.url=jdbc:oracle:thin:@localhost:1521:orcl
+
 # oracle username and password
 # user needs connect, resource, and create view privileges
 db.username=ytex_test

ctakes-ytex/src/test/resources/org/apache/ctakes/ytex/ytex.hsql.properties.template

@@ -8,6 +8,7 @@ db.password=
 db.directory=@ytex.hsql.db@
 # jdbc url for database.  schema name must match db.schema
 db.url=jdbc:hsqldb:file://@ytex.hsql.db@;shutdown=true
+xmldb.url=jdbc:hsqldb:file://@ytex.hsql.db@;shutdown=true
 
 # the schema where umls is installed
 # if not specified, will default to schema from ytex

ctakes-ytex/src/test/resources/org/apache/ctakes/ytex/ytex.hsqldb.properties

@@ -26,6 +26,7 @@ db.schema=ytex
 # jdbc url for database.  Replace localhost and YTEX_TEST 
 # with the values of db.host and db.name respectively
 db.url=jdbc:hsqldb:hsql://localhost;databaseName=YTEX_TEST;integratedSecurity=false
+xmldb.url=jdbc:hsqldb:hsql://localhost;databaseName=YTEX_TEST;integratedSecurity=false
 
 # assume windows integrated authentication, change if necessary
 db.username=ytex_test

pom.xml

@@ -147,7 +147,7 @@
 		<maven-surefire-plugin.version>3.2.3</maven-surefire-plugin.version>
 		<maven-failsafe-plugin.version>3.2.3</maven-failsafe-plugin.version>
 		<maven-assembly-plugin.version>3.6.0</maven-assembly-plugin.version>
-		<mysql-connector.version>5.1.26</mysql-connector.version>
+		<mysql-connector.version>8.0.33</mysql-connector.version>
 		<scala-library.version>2.11.7</scala-library.version>
 		<scala-tools.version>0.4.0</scala-tools.version>
 		<servlet-jsp-api.version>2.2</servlet-jsp-api.version>