From ad64906c8869ebbe6c903c4c41c912a3e9432253 Mon Sep 17 00:00:00 2001
From: Gabor Szadovszky <gabor@apache.org>
Date: Thu, 24 Jun 2021 13:52:08 +0200
Subject: [PATCH] PARQUET-2043: Fail for undeclared dependencies

The purpose of this change is to fail the build if some classes are
used from not direct dependencies. Only classes from direct
dependencies shall be used.
Also fixed some references that broke this rule.
---
 parquet-arrow/pom.xml                         | 20 ------
 parquet-avro/pom.xml                          | 24 ++++---
 parquet-benchmarks/pom.xml                    | 43 +++++++++----
 parquet-cli/pom.xml                           | 62 ++++++++++++++++++-
 parquet-column/pom.xml                        | 10 +++
 parquet-common/pom.xml                        |  6 --
 parquet-encoding/pom.xml                      |  6 ++
 parquet-format-structures/pom.xml             | 12 +---
 parquet-hadoop-bundle/pom.xml                 | 15 +++++
 parquet-hadoop/pom.xml                        | 50 +++++++++++++--
 .../SchemaControlEncryptionTest.java          | 15 +++--
 parquet-jackson/pom.xml                       | 15 +++++
 parquet-pig-bundle/pom.xml                    | 15 +++++
 parquet-pig/pom.xml                           | 32 +++++++---
 parquet-protobuf/pom.xml                      | 16 ++++-
 parquet-scala/pom.xml                         |  6 ++
 parquet-thrift/pom.xml                        | 42 +++++++++----
 pom.xml                                       | 55 ++++++++++++++++
 18 files changed, 353 insertions(+), 91 deletions(-)

diff --git a/parquet-arrow/pom.xml b/parquet-arrow/pom.xml
index 76e018165e..81d6e7ab49 100644
--- a/parquet-arrow/pom.xml
+++ b/parquet-arrow/pom.xml
@@ -42,26 +42,6 @@
       <artifactId>arrow-vector</artifactId>
       <version>${arrow.version}</version>
     </dependency>
-    <dependency>
-      <groupId>org.apache.arrow</groupId>
-      <artifactId>arrow-memory</artifactId>
-      <version>${arrow.version}</version>
-    </dependency>
-    <dependency>
-      <groupId>org.apache.arrow</groupId>
-      <artifactId>arrow-format</artifactId>
-      <version>${arrow.version}</version>
-    </dependency>
-    <dependency>
-      <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-common</artifactId>
-      <version>${project.version}</version>
-    </dependency>
-    <dependency>
-      <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-encoding</artifactId>
-      <version>${project.version}</version>
-    </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-column</artifactId>
diff --git a/parquet-avro/pom.xml b/parquet-avro/pom.xml
index 2679ea06e5..c4d12e484f 100644
--- a/parquet-avro/pom.xml
+++ b/parquet-avro/pom.xml
@@ -45,7 +45,7 @@
     </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-format-structures</artifactId>
+      <artifactId>parquet-common</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
@@ -53,6 +53,11 @@
       <artifactId>avro</artifactId>
       <version>${avro.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
     <dependency>
       <groupId>it.unimi.dsi</groupId>
       <artifactId>fastutil</artifactId>
@@ -61,14 +66,17 @@
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>${hadoop.version}</version>
       <scope>provided</scope>
-      <exclusions>
-        <exclusion>
-          <groupId>org.slf4j</groupId>
-          <artifactId>slf4j-log4j12</artifactId>
-        </exclusion>
-      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-core</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
     </dependency>
     <dependency>
       <groupId>com.google.guava</groupId>
diff --git a/parquet-benchmarks/pom.xml b/parquet-benchmarks/pom.xml
index 91f7106a20..673ff86c6a 100644
--- a/parquet-benchmarks/pom.xml
+++ b/parquet-benchmarks/pom.xml
@@ -37,26 +37,24 @@
   </properties>
 
   <dependencies>
+    <dependency>
+       <groupId>org.apache.parquet</groupId>
+       <artifactId>parquet-hadoop</artifactId>
+       <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-encoding</artifactId>
+      <artifactId>parquet-column</artifactId>
       <version>${project.version}</version>
     </dependency>
     <dependency>
-       <groupId>org.apache.parquet</groupId>
-       <artifactId>parquet-hadoop</artifactId>
-       <version>${project.version}</version>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-common</artifactId>
+      <version>${project.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>${hadoop.version}</version>
-      <exclusions>
-        <exclusion>
-          <groupId>org.slf4j</groupId>
-          <artifactId>slf4j-log4j12</artifactId>
-        </exclusion>
-      </exclusions>
     </dependency>
     <dependency>
        <groupId>org.openjdk.jmh</groupId>
@@ -79,6 +77,11 @@
       <artifactId>fastutil</artifactId>
       <version>${fastutil.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
   </dependencies>
 
   <build>
@@ -119,6 +122,24 @@
           </execution>
         </executions>
       </plugin>
+      <!--
+        - Skip analyzing dependencies in this module so we can pack everything (including hadoop classes) to an uber
+        - jar so benchmarks can be executed easily
+        -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <goals>
+              <goal>analyze-only</goal>
+            </goals>
+            <configuration>
+              <skip>true</skip>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
 </project>
diff --git a/parquet-cli/pom.xml b/parquet-cli/pom.xml
index 9c7dc13c1c..64a4549204 100644
--- a/parquet-cli/pom.xml
+++ b/parquet-cli/pom.xml
@@ -38,6 +38,26 @@
       <artifactId>parquet-avro</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-format-structures</artifactId>
+      <version>${project.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-common</artifactId>
+      <version>${project.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-column</artifactId>
+      <version>${project.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-hadoop</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.avro</groupId>
       <artifactId>avro</artifactId>
@@ -47,6 +67,7 @@
       <groupId>com.github.luben</groupId>
       <artifactId>zstd-jni</artifactId>
       <version>${zstd-jni.version}</version>
+      <scope>runtime</scope>
     </dependency>
     <dependency>
       <groupId>org.slf4j</groupId>
@@ -67,12 +88,23 @@
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-jackson</artifactId>
       <version>${project.version}</version>
+      <scope>runtime</scope>
     </dependency>
     <dependency>
       <groupId>${jackson.groupId}</groupId>
       <artifactId>jackson-databind</artifactId>
       <version>${jackson-databind.version}</version>
     </dependency>
+    <dependency>
+      <groupId>${jackson.groupId}</groupId>
+      <artifactId>jackson-core</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>${jackson.groupId}</groupId>
+      <artifactId>jackson-annotations</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
     <dependency>
       <groupId>com.beust</groupId>
       <artifactId>jcommander</artifactId>
@@ -93,7 +125,35 @@
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>${hadoop.version}</version>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>com.google.code.findbugs</groupId>
+      <artifactId>jsr305</artifactId>
+      <version>${jsr305.version}</version>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>log4j</groupId>
+      <artifactId>log4j</artifactId>
+      <version>1.2.17</version>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>commons-io</groupId>
+      <artifactId>commons-io</artifactId>
+      <version>2.4</version>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>commons-logging</groupId>
+      <artifactId>commons-logging</artifactId>
+      <version>1.1.3</version>
       <scope>provided</scope>
     </dependency>
   </dependencies>
diff --git a/parquet-column/pom.xml b/parquet-column/pom.xml
index a80fe0b1b8..ab10a5f37d 100644
--- a/parquet-column/pom.xml
+++ b/parquet-column/pom.xml
@@ -70,6 +70,16 @@
       <artifactId>zero-allocation-hashing</artifactId>
       <version>${net.openhft.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.yetus</groupId>
+      <artifactId>audience-annotations</artifactId>
+      <version>${yetus.audience-annotations.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
 
     <dependency>
       <groupId>com.carrotsearch</groupId>
diff --git a/parquet-common/pom.xml b/parquet-common/pom.xml
index c090fcba60..1a0f2f9f5e 100644
--- a/parquet-common/pom.xml
+++ b/parquet-common/pom.xml
@@ -61,12 +61,6 @@
       <version>${slf4j.version}</version>
       <scope>test</scope>
     </dependency>
-
-    <dependency>
-      <groupId>org.apache.yetus</groupId>
-      <artifactId>audience-annotations</artifactId>
-      <version>0.12.0</version>
-    </dependency>
   </dependencies>
 
   <build>
diff --git a/parquet-encoding/pom.xml b/parquet-encoding/pom.xml
index e5485ca96c..2b27c19eaa 100644
--- a/parquet-encoding/pom.xml
+++ b/parquet-encoding/pom.xml
@@ -42,6 +42,12 @@
       <version>${project.version}</version>
     </dependency>
 
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
+
     <dependency>
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-simple</artifactId>
diff --git a/parquet-format-structures/pom.xml b/parquet-format-structures/pom.xml
index a48ef96981..ce72ed5353 100644
--- a/parquet-format-structures/pom.xml
+++ b/parquet-format-structures/pom.xml
@@ -47,7 +47,7 @@
          <executions>
            <execution>
              <id>unpack</id>
-             <phase>generate-sources</phase>
+             <phase>initialize</phase>
              <goals>
                <goal>unpack</goal>
              </goals>
@@ -151,21 +151,11 @@
   </reports>
 
   <dependencies>
-    <dependency>
-      <groupId>org.slf4j</groupId>
-      <artifactId>slf4j-api</artifactId>
-      <version>${slf4j.version}</version>
-    </dependency>
     <dependency>
       <groupId>org.apache.thrift</groupId>
       <artifactId>libthrift</artifactId>
       <version>${format.thrift.version}</version>
     </dependency>
-    <dependency>
-      <groupId>javax.annotation</groupId>
-      <artifactId>javax.annotation-api</artifactId>
-      <version>1.3.2</version>
-     </dependency>
   </dependencies>
 
   <profiles>
diff --git a/parquet-hadoop-bundle/pom.xml b/parquet-hadoop-bundle/pom.xml
index 2aae6e5d5c..d15792f241 100644
--- a/parquet-hadoop-bundle/pom.xml
+++ b/parquet-hadoop-bundle/pom.xml
@@ -84,6 +84,21 @@
           </execution>
         </executions>
       </plugin>
+      <!-- Skip analyzing dependencies in this module so we can depend on modules without any code references -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <goals>
+              <goal>analyze-only</goal>
+            </goals>
+            <configuration>
+              <skip>true</skip>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
 
diff --git a/parquet-hadoop/pom.xml b/parquet-hadoop/pom.xml
index 8e42d42096..d676efac51 100644
--- a/parquet-hadoop/pom.xml
+++ b/parquet-hadoop/pom.xml
@@ -46,6 +46,11 @@
       <artifactId>parquet-format-structures</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-common</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-column</artifactId>
@@ -56,19 +61,29 @@
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-core</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-annotations</artifactId>
       <version>${hadoop.version}</version>
       <scope>provided</scope>
-      <exclusions>
-        <exclusion>
-          <groupId>org.slf4j</groupId>
-          <artifactId>slf4j-log4j12</artifactId>
-        </exclusion>
-      </exclusions>
     </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-jackson</artifactId>
       <version>${project.version}</version>
+      <scope>runtime</scope>
     </dependency>
     <dependency>
       <groupId>${jackson.groupId}</groupId>
@@ -127,6 +142,28 @@
       <version>4.6.0</version>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>commons-io</groupId>
+      <artifactId>commons-io</artifactId>
+      <version>2.4</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>net.openhft</groupId>
+      <artifactId>zero-allocation-hashing</artifactId>
+      <version>${net.openhft.version}</version>
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.yetus</groupId>
+      <artifactId>audience-annotations</artifactId>
+      <version>${yetus.audience-annotations.version}</version>
+    </dependency>
   </dependencies>
 
   <build>
@@ -159,6 +196,7 @@
           <groupId>com.github.rdblue</groupId>
           <artifactId>brotli-codec</artifactId>
           <version>${brotli-codec.version}</version>
+          <scope>runtime</scope>
           <optional>true</optional>
         </dependency>
       </dependencies>
diff --git a/parquet-hadoop/src/test/java/org/apache/parquet/crypto/propertiesfactory/SchemaControlEncryptionTest.java b/parquet-hadoop/src/test/java/org/apache/parquet/crypto/propertiesfactory/SchemaControlEncryptionTest.java
index 17fda97d19..862ae672c6 100644
--- a/parquet-hadoop/src/test/java/org/apache/parquet/crypto/propertiesfactory/SchemaControlEncryptionTest.java
+++ b/parquet-hadoop/src/test/java/org/apache/parquet/crypto/propertiesfactory/SchemaControlEncryptionTest.java
@@ -19,8 +19,6 @@
 
 package org.apache.parquet.crypto.propertiesfactory;
 
-import org.apache.commons.logging.Log;
-import org.apache.commons.logging.LogFactory;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.Path;
 import org.apache.parquet.column.ColumnDescriptor;
@@ -28,7 +26,6 @@
 import org.apache.parquet.crypto.ParquetCipher;
 import org.apache.parquet.example.data.Group;
 import org.apache.parquet.example.data.simple.SimpleGroup;
-import org.apache.parquet.format.EncryptionAlgorithm;
 import org.apache.parquet.hadoop.ParquetReader;
 import org.apache.parquet.hadoop.ParquetWriter;
 import org.apache.parquet.hadoop.api.WriteSupport;
@@ -39,6 +36,8 @@
 import org.apache.parquet.schema.PrimitiveType;
 import org.junit.Before;
 import org.junit.Test;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.IOException;
 import java.nio.file.Files;
@@ -58,13 +57,13 @@
 
 public class SchemaControlEncryptionTest {
 
-  private final static Log LOG = LogFactory.getLog(SchemaControlEncryptionTest.class);
+  private final static Logger LOG = LoggerFactory.getLogger(SchemaControlEncryptionTest.class);
   private final static int numRecord = 1000;
   private Random rnd = new Random(5);
-  
+
   // In the test We use a map to tell WriteSupport which columns to be encrypted with what key. In real use cases, people
-  // can find whatever easy way to do so basing on how do they get these information, for example people can choose to 
-  // store in HMS, or other metastore. 
+  // can find whatever easy way to do so basing on how do they get these information, for example people can choose to
+  // store in HMS, or other metastore.
   private Map<String, Map<String, Object>> cryptoMetadata = new HashMap<>();
   private Map<String, Object[]> testData = new HashMap<>();
 
@@ -122,7 +121,7 @@ private void runTest(Configuration conf ) throws Exception {
     encryptParquetFile(file, conf);
     decryptParquetFileAndValid(file, conf);
   }
-  
+
   private void markEncryptColumns() {
     Map<String, Object> ageMetadata = new HashMap<>();
     ageMetadata.put("columnKeyMetaData", "age_key_id");
diff --git a/parquet-jackson/pom.xml b/parquet-jackson/pom.xml
index 1aa6fe2071..8121832813 100644
--- a/parquet-jackson/pom.xml
+++ b/parquet-jackson/pom.xml
@@ -90,6 +90,21 @@
           </execution>
         </executions>
       </plugin>
+      <!-- Skip analyzing dependencies in this module so we can depend on jackson without any code references -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <goals>
+              <goal>analyze-only</goal>
+            </goals>
+            <configuration>
+              <skip>true</skip>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
   <profiles>
diff --git a/parquet-pig-bundle/pom.xml b/parquet-pig-bundle/pom.xml
index e9fa806c88..63661d497e 100644
--- a/parquet-pig-bundle/pom.xml
+++ b/parquet-pig-bundle/pom.xml
@@ -74,6 +74,21 @@
           </execution>
         </executions>
       </plugin>
+      <!-- Skip analyzing dependencies in this module so we can depend on parquet-pig without any code references -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <goals>
+              <goal>analyze-only</goal>
+            </goals>
+            <configuration>
+              <skip>true</skip>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>
 
diff --git a/parquet-pig/pom.xml b/parquet-pig/pom.xml
index eaf4e15866..87f37333d3 100644
--- a/parquet-pig/pom.xml
+++ b/parquet-pig/pom.xml
@@ -48,9 +48,15 @@
     </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-format-structures</artifactId>
+      <artifactId>parquet-common</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-jackson</artifactId>
+      <version>${project.version}</version>
+      <scope>runtime</scope>
+    </dependency>
     <dependency>
       <groupId>org.apache.pig</groupId>
       <artifactId>pig</artifactId>
@@ -65,20 +71,27 @@
       <scope>provided</scope>
     </dependency>
     <dependency>
-      <groupId>org.apache.parquet</groupId>
-      <artifactId>parquet-jackson</artifactId>
-      <version>${project.version}</version>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-core</artifactId>
+      <version>${hadoop.version}</version>
+      <scope>provided</scope>
     </dependency>
     <dependency>
-      <groupId>${jackson.groupId}</groupId>
-      <artifactId>jackson-core</artifactId>
-      <version>${jackson.version}</version>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <version>${hadoop.version}</version>
+      <scope>provided</scope>
     </dependency>
     <dependency>
       <groupId>${jackson.groupId}</groupId>
       <artifactId>jackson-databind</artifactId>
       <version>${jackson-databind.version}</version>
     </dependency>
+    <dependency>
+      <groupId>${jackson.groupId}</groupId>
+      <artifactId>jackson-annotations</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-column</artifactId>
@@ -110,6 +123,11 @@
       <version>${slf4j.version}</version>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
   </dependencies>
 
   <build>
diff --git a/parquet-protobuf/pom.xml b/parquet-protobuf/pom.xml
index d897c02421..c6ae71c6f6 100644
--- a/parquet-protobuf/pom.xml
+++ b/parquet-protobuf/pom.xml
@@ -87,9 +87,23 @@
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>${hadoop.version}</version>
       <scope>provided</scope>
     </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-core</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-simple</artifactId>
diff --git a/parquet-scala/pom.xml b/parquet-scala/pom.xml
index e33d6f40bd..4420cfe2c0 100644
--- a/parquet-scala/pom.xml
+++ b/parquet-scala/pom.xml
@@ -64,6 +64,12 @@
       <version>3.0.1</version>
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>org.scalactic</groupId>
+      <artifactId>scalactic_${scala.binary.version}</artifactId>
+      <version>3.0.1</version>
+      <scope>test</scope>
+    </dependency>
     <dependency>
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-simple</artifactId>
diff --git a/parquet-thrift/pom.xml b/parquet-thrift/pom.xml
index 07020de222..7f08ca6176 100644
--- a/parquet-thrift/pom.xml
+++ b/parquet-thrift/pom.xml
@@ -47,17 +47,25 @@
       <artifactId>parquet-hadoop</artifactId>
       <version>${project.version}</version>
     </dependency>
+    <dependency>
+      <groupId>org.apache.parquet</groupId>
+      <artifactId>parquet-common</artifactId>
+      <version>${project.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>${hadoop.version}</version>
       <scope>provided</scope>
-      <exclusions>
-        <exclusion>
-          <groupId>org.slf4j</groupId>
-          <artifactId>slf4j-log4j12</artifactId>
-        </exclusion>
-      </exclusions>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-mapreduce-client-core</artifactId>
+      <scope>provided</scope>
+    </dependency>
+    <dependency>
+      <groupId>org.apache.hadoop</groupId>
+      <artifactId>hadoop-common</artifactId>
+      <scope>provided</scope>
     </dependency>
     <dependency>
       <groupId>com.twitter.elephantbird</groupId>
@@ -87,16 +95,22 @@
       <groupId>org.apache.parquet</groupId>
       <artifactId>parquet-jackson</artifactId>
       <version>${project.version}</version>
+      <scope>runtime</scope>
     </dependency>
     <dependency>
       <groupId>${jackson.groupId}</groupId>
-      <artifactId>jackson-core</artifactId>
-      <version>${jackson.version}</version>
+      <artifactId>jackson-databind</artifactId>
+      <version>${jackson-databind.version}</version>
     </dependency>
     <dependency>
       <groupId>${jackson.groupId}</groupId>
-      <artifactId>jackson-databind</artifactId>
-      <version>${jackson-databind.version}</version>
+      <artifactId>jackson-annotations</artifactId>
+      <version>${jackson.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>com.google.guava</groupId>
+      <artifactId>guava</artifactId>
+      <version>${guava.version}</version>
     </dependency>
     <dependency>
       <groupId>org.apache.parquet</groupId>
@@ -135,6 +149,11 @@
       <version>${thrift.version}</version>
       <scope>provided</scope>
     </dependency>
+    <dependency>
+      <groupId>org.slf4j</groupId>
+      <artifactId>slf4j-api</artifactId>
+      <version>${slf4j.version}</version>
+    </dependency>
     <dependency>
       <groupId>org.slf4j</groupId>
       <artifactId>slf4j-simple</artifactId>
@@ -155,7 +174,6 @@
       <type>test-jar</type>
       <scope>test</scope>
     </dependency>
-
   </dependencies>
 
   <dependencyManagement>
diff --git a/pom.xml b/pom.xml
index 090ae96269..f143b08e87 100644
--- a/pom.xml
+++ b/pom.xml
@@ -101,12 +101,14 @@
     <mockito.version>1.10.19</mockito.version>
     <net.openhft.version>0.9</net.openhft.version>
     <exec-maven-plugin.version>1.6.0</exec-maven-plugin.version>
+    <yetus.audience-annotations.version>0.13.0</yetus.audience-annotations.version>
 
     <!-- parquet-cli dependencies -->
     <opencsv.version>2.3</opencsv.version>
     <jcommander.version>1.72</jcommander.version>
     <zstd-jni.version>1.5.0-1</zstd-jni.version>
     <commons-text.version>1.8</commons-text.version>
+    <jsr305.version>3.0.2</jsr305.version>
 
     <!-- properties for the profiles -->
     <surefire.logLevel>INFO</surefire.logLevel>
@@ -147,6 +149,44 @@
     </dependency>
   </dependencies>
 
+  <dependencyManagement>
+    <dependencies>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-mapreduce-client-core</artifactId>
+        <version>${hadoop.version}</version>
+        <exclusions>
+          <exclusion>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-log4j12</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-client</artifactId>
+        <version>${hadoop.version}</version>
+        <exclusions>
+          <exclusion>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-log4j12</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hadoop</groupId>
+        <artifactId>hadoop-common</artifactId>
+        <version>${hadoop.version}</version>
+        <exclusions>
+          <exclusion>
+            <groupId>org.slf4j</groupId>
+            <artifactId>slf4j-log4j12</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+    </dependencies>
+  </dependencyManagement>
+
   <reporting>
     <plugins>
       <plugin>
@@ -490,6 +530,21 @@
           </execution>
         </executions>
       </plugin>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-dependency-plugin</artifactId>
+        <executions>
+          <execution>
+            <goals>
+              <goal>analyze-only</goal>
+            </goals>
+            <configuration>
+              <failOnWarning>true</failOnWarning>
+              <ignoreNonCompile>true</ignoreNonCompile>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
   </build>