Feature/vector support (#201)

* CDM-94 Add JaCoCo code coverage plugin and set for minimum coverage percentage or else fail the build
* Initil draft to support vectors
* Upgrade cassandra-all dependency to 5.0-alpha1
* Implement smoke test for vector cql data type support

Author: msmygit

.gitignore

@@ -7,3 +7,6 @@ dependency-reduced-pom.xml
 cassandra-data-migrator.iml
 SIT/local
 *.DS_Store
+.classpath
+.project
+.settings/*

README.md

@@ -1,6 +1,7 @@
 [![License Apache2](https://img.shields.io/hexpm/l/plug.svg)](http://www.apache.org/licenses/LICENSE-2.0)
 [![Star on Github](https://img.shields.io/github/stars/datastax/cassandra-data-migrator.svg?style=social)](https://github.com/datastax/cassandra-data-migrator/stargazers)
 ![GitHub release (with filter)](https://img.shields.io/github/v/release/datastax/cassandra-data-migrator?label=latest%20release&color=green&link=!%5BGitHub%20release%20(with%20filter)%5D(https%3A%2F%2Fimg.shields.io%2Fgithub%2Fv%2Frelease%2Fdatastax%2Fcassandra-data-migrator%3Flabel%3Dlatest%2520release%26color%3Dgreen))
+![Docker Pulls](https://img.shields.io/docker/pulls/datastax/cassandra-data-migrator)
 
 # cassandra-data-migrator
 

SIT/cdm-assert.sh

@@ -5,17 +5,17 @@ assertCmd="egrep 'JobSession.* Final ' \${OUTPUT_FILE} | sed 's/^.*Final //'"
 _usage() {
   cat <<EOF
 
-usage: $0 -f output_file -a assertFile [-d directory]
+usage: $0 -f output_file -a assert_file [-d directory]
 
 Required
   -f output_file   : a file with list of scenarios, same format as cdm.sh
-  -a assertFile    : a file with the assertions
+  -a assert_file    : a file with the assertions
 
 Optional
   -d directory     : directory in which output_file and assertFile may be found
 
 ==================
-assertFile Format
+assert_file Format
 ==================
 Expected to contain the "Final" job session summary information, generated similar to
     ${assertCmd}
@@ -66,7 +66,7 @@ else
 fi
 
 if [[ -z "$ASSERT_FILENAME" ]]; then
-  echo "missing -a assertFile"
+  echo "missing -a assert_file"
   argErrors=1
 else
   if [[ -z "${CONFIG_DIR}" ]]; then

SIT/smoke/04_counters/breakData.cql

@@ -9,7 +9,7 @@ DELETE FROM target.smoke_counters where key='record3';
 UPDATE origin.smoke_counters SET col2=col2+1 WHERE key='record4';
 UPDATE target.smoke_counters SET col2=col2+1 WHERE key='record4';
 
--- change by different amounts, they shouuld be brought into alignment with 
+-- change by different amounts, they should be brought into alignment with
 -- origin, even if that means going down
 UPDATE origin.smoke_counters SET col2=col2+1 WHERE key='record5';
 UPDATE target.smoke_counters SET col2=col2+2 WHERE key='record5';

SIT/smoke_inflight/06_vector/cdm.migrateData.assert

@@ -0,0 +1,4 @@
+Read Record Count: 2
+Skipped Record Count: 0
+Write Record Count: 2
+Error Record Count: 0

SIT/smoke_inflight/06_vector/cdm.txt

@@ -0,0 +1,2 @@
+migrateData com.datastax.cdm.job.Migrate /smoke/06_vector/migrate.properties
+validateData com.datastax.cdm.job.DiffData /smoke/06_vector/migrate.properties

SIT/smoke_inflight/06_vector/cdm.validateData.assert

@@ -0,0 +1,7 @@
+Read Record Count: 2
+Mismatch Record Count: 0
+Corrected Mismatch Record Count: 0
+Missing Record Count: 0
+Corrected Missing Record Count: 0
+Valid Record Count: 2
+Skipped Record Count: 0

SIT/smoke_inflight/06_vector/execute.sh

@@ -0,0 +1,9 @@
+#!/bin/bash -e
+
+workingDir="$1"
+cd "$workingDir"
+
+for scenario in $(cat cdm.txt | awk '{print $1}'); do
+  /local/cdm.sh -f cdm.txt -s $scenario -d "$workingDir" > "cdm.$scenario.out" 2>cdm.$scenario.err
+  /local/cdm-assert.sh -f "cdm.$scenario.out" -a "cdm.$scenario.assert" -d "$workingDir"
+done

SIT/smoke_inflight/06_vector/expected.cql

@@ -0,0 +1 @@
+SELECT * FROM target.smoke_vector;

SIT/smoke_inflight/06_vector/expected.out

@@ -0,0 +1,7 @@
+
+ col1 | embedding
+------+--------------------
+    1 |    [1.1, 2.2, 3.3]
+    2 | [4.4, -0.01, 0.99]
+
+(2 rows)