[HUDI-1950] Fix Azure CI failure in TestParquetUtils (#2984)

* fix azure pipeline configs

* add pentaho.org in maven repositories

* Make sure file paths with scheme in TestParquetUtils

* add azure build status to README

README.md

@@ -22,6 +22,7 @@ Hudi manages the storage of large analytical datasets on DFS (Cloud stores, HDFS
 <https://hudi.apache.org/>
 
 [![Build Status](https://travis-ci.com/apache/hudi.svg?branch=master)](https://travis-ci.com/apache/hudi)
+[![Build Status](https://dev.azure.com/apache-hudi-ci-org/apache-hudi-ci/_apis/build/status/apachehudi-ci.hudi-mirror?branchName=master)](https://dev.azure.com/apache-hudi-ci-org/apache-hudi-ci/_build/latest?definitionId=3&branchName=master)
 [![License](https://img.shields.io/badge/license-Apache%202-4EB1BA.svg)](https://www.apache.org/licenses/LICENSE-2.0.html)
 [![Maven Central](https://maven-badges.herokuapp.com/maven-central/org.apache.hudi/hudi/badge.svg)](http://search.maven.org/#search%7Cga%7C1%7Cg%3A%22org.apache.hudi%22)
 [![Join on Slack](https://img.shields.io/badge/slack-%23hudi-72eff8?logo=slack&color=48c628&label=Join%20on%20Slack)](https://join.slack.com/t/apache-hudi/shared_invite/enQtODYyNDAxNzc5MTg2LTE5OTBlYmVhYjM0N2ZhOTJjOWM4YzBmMWU2MjZjMGE4NDc5ZDFiOGQ2N2VkYTVkNzU3ZDQ4OTI1NmFmYWQ0NzE)

azure-pipelines.yml

@@ -34,16 +34,8 @@ stages:
     jobs:
       - job: unit_tests_spark_client
         steps:
-          - task: Maven@3
+          - script: |
-            inputs:
+              mvn $(MAVEN_OPTS) clean install -DskipTests
-              mavenPomFile: 'pom.xml'
-              goals: 'clean install'
-              options: -DskipTests
-              publishJUnitResults: false
-              javaHomeOption: 'JDKVersion'
-              jdkVersionOption: '1.8'
-              jdkArchitectureOption: 'x64'
-              mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
           - task: Cache@2
             inputs:
               key: 'maven | "$(Agent.OS)" | **/pom.xml'
@@ -66,16 +58,8 @@ stages:
               mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
       - job: unit_tests_utilities
         steps:
-          - task: Maven@3
+          - script: |
-            inputs:
+              mvn $(MAVEN_OPTS) clean install -DskipTests
-              mavenPomFile: 'pom.xml'
-              goals: 'clean install'
-              options: -DskipTests
-              publishJUnitResults: false
-              javaHomeOption: 'JDKVersion'
-              jdkVersionOption: '1.8'
-              jdkArchitectureOption: 'x64'
-              mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
           - task: Cache@2
             inputs:
               key: 'maven | "$(Agent.OS)" | **/pom.xml'
@@ -98,16 +82,8 @@ stages:
               mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
       - job: unit_tests_other_modules
         steps:
-          - task: Maven@3
+          - script: |
-            inputs:
+              mvn $(MAVEN_OPTS) clean install -DskipTests
-              mavenPomFile: 'pom.xml'
-              goals: 'clean install'
-              options: -DskipTests
-              publishJUnitResults: false
-              javaHomeOption: 'JDKVersion'
-              jdkVersionOption: '1.8'
-              jdkArchitectureOption: 'x64'
-              mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
           - task: Cache@2
             inputs:
               key: 'maven | "$(Agent.OS)" | **/pom.xml'
@@ -130,18 +106,8 @@ stages:
               mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
       - job: functional_tests
         steps:
-          - task: Maven@3
+          - script: |
-            inputs:
+              mvn $(MAVEN_OPTS) -Pfunctional-tests test
-              mavenPomFile: 'pom.xml'
-              goals: 'test'
-              options: -Pfunctional-tests
-              publishJUnitResults: false
-              testResultsFiles: '**/surefire-reports/TEST-*.xml'
-              testRunTitle: 'functional tests'
-              javaHomeOption: 'JDKVersion'
-              jdkVersionOption: '1.8'
-              jdkArchitectureOption: 'x64'
-              mavenOptions: '-Xmx2g $(MAVEN_OPTS)'
       - job: integration_tests
         steps:
           - script: |

hudi-common/src/test/java/org/apache/hudi/common/util/TestParquetUtils.java

@@ -58,7 +58,7 @@ import static org.junit.jupiter.api.Assertions.assertTrue;
  */
 public class TestParquetUtils extends HoodieCommonTestHarness {
 
-  private ParquetUtils parquetUtils = new ParquetUtils();
+  private ParquetUtils parquetUtils;
 
   public static List<Arguments> bloomFilterTypeCodes() {
     return Arrays.asList(
@@ -70,6 +70,7 @@ public class TestParquetUtils extends HoodieCommonTestHarness {
   @BeforeEach
   public void setup() {
     initPath();
+    parquetUtils = new ParquetUtils();
   }
 
   @ParameterizedTest
@@ -80,7 +81,7 @@ public class TestParquetUtils extends HoodieCommonTestHarness {
       rowKeys.add(UUID.randomUUID().toString());
     }
 
-    String filePath = Paths.get(basePath, "test.parquet").toString();
+    String filePath = Paths.get(basePath, "test.parquet").toUri().toString();
     writeParquetFile(typeCode, filePath, rowKeys);
 
     // Read and verify
@@ -110,7 +111,7 @@ public class TestParquetUtils extends HoodieCommonTestHarness {
       }
     }
 
-    String filePath = Paths.get(basePath, "test.parquet").toString();
+    String filePath = Paths.get(basePath, "test.parquet").toUri().toString();
     writeParquetFile(typeCode, filePath, rowKeys);
 
     // Read and verify
@@ -136,7 +137,7 @@ public class TestParquetUtils extends HoodieCommonTestHarness {
       expected.add(new HoodieKey(rowKey, partitionPath));
     }
 
-    String filePath = basePath + "/test.parquet";
+    String filePath = Paths.get(basePath, "test.parquet").toUri().toString();
     Schema schema = HoodieAvroUtils.getRecordKeyPartitionPathSchema();
     writeParquetFile(typeCode, filePath, rowKeys, schema, true, partitionPath);
 
@@ -152,7 +153,7 @@ public class TestParquetUtils extends HoodieCommonTestHarness {
 
   @Test
   public void testReadCounts() throws Exception {
-    String filePath = basePath + "/test.parquet";
+    String filePath = Paths.get(basePath, "test.parquet").toUri().toString();
     List<String> rowKeys = new ArrayList<>();
     for (int i = 0; i < 123; i++) {
       rowKeys.add(UUID.randomUUID().toString());

pom.xml

@@ -1051,6 +1051,10 @@
       <id>confluent</id>
       <url>https://packages.confluent.io/maven/</url>
     </repository>
+    <repository>
+      <id>pentaho.org</id>
+      <url>https://public.nexus.pentaho.org/repository/proxy-public-3rd-party-release/</url>
+    </repository>
   </repositories>
 
   <profiles>