orc-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From omal...@apache.org
Subject [1/3] orc git commit: ORC-72 Add benchmark between Avro, JSON, ORC, and Parquet.
Date Fri, 14 Apr 2017 01:40:41 GMT
Repository: orc
Updated Branches:
  refs/heads/master 73946aa6c -> ce5213b2a


http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/bench/src/main/resources/github.schema
----------------------------------------------------------------------
diff --git a/java/bench/src/main/resources/github.schema b/java/bench/src/main/resources/github.schema
new file mode 100644
index 0000000..3b7dd15
--- /dev/null
+++ b/java/bench/src/main/resources/github.schema
@@ -0,0 +1,702 @@
+struct<
+  actor:struct <
+    avatar_url: string,
+    gravatar_id: string,
+    id: int,
+    login: string,
+    url: string>,
+  created_at:timestamp,
+  id:binary,
+  org:struct <
+    avatar_url: string,
+    gravatar_id: string,
+    id: int,
+    login: string,
+    url: string>,
+  payload:struct <
+    action: string,
+    before: binary,
+    comment: struct <
+      _links: struct <
+        html: struct <
+          href: string>,
+        pull_request: struct <
+          href: string>,
+        self: struct <
+          href: string>>,
+      body: string,
+      commit_id: binary,
+      created_at: timestamp,
+      diff_hunk: string,
+      html_url: string,
+      id: int,
+      issue_url: string,
+      line: int,
+      original_commit_id: binary,
+      original_position: int,
+      path: string,
+      position: int,
+      pull_request_url: string,
+      updated_at: timestamp,
+      url: string,
+      user: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>>,
+    commits: array <struct <
+        author: struct <
+          email: string,
+          name: string>,
+        distinct: boolean,
+        message: string,
+        sha: binary,
+        url: string>>,
+    description: string,
+    distinct_size: int,
+    forkee: struct <
+      archive_url: string,
+      assignees_url: string,
+      blobs_url: string,
+      branches_url: string,
+      clone_url: string,
+      collaborators_url: string,
+      comments_url: string,
+      commits_url: string,
+      compare_url: string,
+      contents_url: string,
+      contributors_url: string,
+      created_at: timestamp,
+      default_branch: string,
+      description: string,
+      downloads_url: string,
+      events_url: string,
+      fork: boolean,
+      forks: int,
+      forks_count: int,
+      forks_url: string,
+      full_name: string,
+      git_commits_url: string,
+      git_refs_url: string,
+      git_tags_url: string,
+      git_url: string,
+      has_downloads: boolean,
+      has_issues: boolean,
+      has_pages: boolean,
+      has_wiki: boolean,
+      homepage: string,
+      hooks_url: string,
+      html_url: string,
+      id: int,
+      issue_comment_url: string,
+      issue_events_url: string,
+      issues_url: string,
+      keys_url: string,
+      labels_url: string,
+      language: string,
+      languages_url: string,
+      merges_url: string,
+      milestones_url: string,
+      mirror_url: string,
+      name: string,
+      notifications_url: string,
+      open_issues: int,
+      open_issues_count: int,
+      owner: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>,
+      private: boolean,
+      public: boolean,
+      pulls_url: string,
+      pushed_at: timestamp,
+      releases_url: string,
+      size: int,
+      ssh_url: string,
+      stargazers_count: int,
+      stargazers_url: string,
+      statuses_url: string,
+      subscribers_url: string,
+      subscription_url: string,
+      svn_url: string,
+      tags_url: string,
+      teams_url: string,
+      trees_url: string,
+      updated_at: timestamp,
+      url: string,
+      watchers: int,
+      watchers_count: int>,
+    head: binary,
+    issue: struct <
+      assignee: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>,
+      body: string,
+      closed_at: timestamp,
+      comments: int,
+      comments_url: string,
+      created_at: timestamp,
+      events_url: string,
+      html_url: string,
+      id: int,
+      labels: array <struct <
+          color: binary,
+          name: string,
+          url: string>>,
+      labels_url: string,
+      locked: boolean,
+      milestone: struct <
+        closed_at: timestamp,
+        closed_issues: int,
+        created_at: timestamp,
+        creator: struct <
+          avatar_url: string,
+          events_url: string,
+          followers_url: string,
+          following_url: string,
+          gists_url: string,
+          gravatar_id: string,
+          html_url: string,
+          id: int,
+          login: string,
+          organizations_url: string,
+          received_events_url: string,
+          repos_url: string,
+          site_admin: boolean,
+          starred_url: string,
+          subscriptions_url: string,
+          type: string,
+          url: string>,
+        description: string,
+        due_on: timestamp,
+        html_url: string,
+        id: int,
+        labels_url: string,
+        number: int,
+        open_issues: int,
+        state: string,
+        title: string,
+        updated_at: timestamp,
+        url: string>,
+      number: int,
+      pull_request: struct <
+        diff_url: string,
+        html_url: string,
+        patch_url: string,
+        url: string>,
+      state: string,
+      title: string,
+      updated_at: timestamp,
+      url: string,
+      user: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>>,
+    master_branch: string,
+    member: struct <
+      avatar_url: string,
+      events_url: string,
+      followers_url: string,
+      following_url: string,
+      gists_url: string,
+      gravatar_id: string,
+      html_url: string,
+      id: int,
+      login: string,
+      organizations_url: string,
+      received_events_url: string,
+      repos_url: string,
+      site_admin: boolean,
+      starred_url: string,
+      subscriptions_url: string,
+      type: string,
+      url: string>,
+    number: int,
+    pages: array <struct <
+        action: string,
+        html_url: string,
+        page_name: string,
+        sha: binary,
+        summary: string,
+        title: string>>,
+    pull_request: struct <
+      _links: struct <
+        comments: struct <
+          href: string>,
+        commits: struct <
+          href: string>,
+        html: struct <
+          href: string>,
+        issue: struct <
+          href: string>,
+        review_comment: struct <
+          href: string>,
+        review_comments: struct <
+          href: string>,
+        self: struct <
+          href: string>,
+        statuses: struct <
+          href: string>>,
+      additions: int,
+      assignee: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>,
+      base: struct <
+        label: string,
+        ref: string,
+        repo: struct <
+          archive_url: string,
+          assignees_url: string,
+          blobs_url: string,
+          branches_url: string,
+          clone_url: string,
+          collaborators_url: string,
+          comments_url: string,
+          commits_url: string,
+          compare_url: string,
+          contents_url: string,
+          contributors_url: string,
+          created_at: timestamp,
+          default_branch: string,
+          description: string,
+          downloads_url: string,
+          events_url: string,
+          fork: boolean,
+          forks: int,
+          forks_count: int,
+          forks_url: string,
+          full_name: string,
+          git_commits_url: string,
+          git_refs_url: string,
+          git_tags_url: string,
+          git_url: string,
+          has_downloads: boolean,
+          has_issues: boolean,
+          has_pages: boolean,
+          has_wiki: boolean,
+          homepage: string,
+          hooks_url: string,
+          html_url: string,
+          id: int,
+          issue_comment_url: string,
+          issue_events_url: string,
+          issues_url: string,
+          keys_url: string,
+          labels_url: string,
+          language: string,
+          languages_url: string,
+          merges_url: string,
+          milestones_url: string,
+          mirror_url: string,
+          name: string,
+          notifications_url: string,
+          open_issues: int,
+          open_issues_count: int,
+          owner: struct <
+            avatar_url: string,
+            events_url: string,
+            followers_url: string,
+            following_url: string,
+            gists_url: string,
+            gravatar_id: string,
+            html_url: string,
+            id: int,
+            login: string,
+            organizations_url: string,
+            received_events_url: string,
+            repos_url: string,
+            site_admin: boolean,
+            starred_url: string,
+            subscriptions_url: string,
+            type: string,
+            url: string>,
+          private: boolean,
+          pulls_url: string,
+          pushed_at: timestamp,
+          releases_url: string,
+          size: int,
+          ssh_url: string,
+          stargazers_count: int,
+          stargazers_url: string,
+          statuses_url: string,
+          subscribers_url: string,
+          subscription_url: string,
+          svn_url: string,
+          tags_url: string,
+          teams_url: string,
+          trees_url: string,
+          updated_at: timestamp,
+          url: string,
+          watchers: int,
+          watchers_count: int>,
+        sha: binary,
+        user: struct <
+          avatar_url: string,
+          events_url: string,
+          followers_url: string,
+          following_url: string,
+          gists_url: string,
+          gravatar_id: string,
+          html_url: string,
+          id: int,
+          login: string,
+          organizations_url: string,
+          received_events_url: string,
+          repos_url: string,
+          site_admin: boolean,
+          starred_url: string,
+          subscriptions_url: string,
+          type: string,
+          url: string>>,
+      body: string,
+      changed_files: int,
+      closed_at: timestamp,
+      comments: int,
+      comments_url: string,
+      commits: int,
+      commits_url: string,
+      created_at: timestamp,
+      deletions: int,
+      diff_url: string,
+      head: struct <
+        label: string,
+        ref: string,
+        repo: struct <
+          archive_url: string,
+          assignees_url: string,
+          blobs_url: string,
+          branches_url: string,
+          clone_url: string,
+          collaborators_url: string,
+          comments_url: string,
+          commits_url: string,
+          compare_url: string,
+          contents_url: string,
+          contributors_url: string,
+          created_at: timestamp,
+          default_branch: string,
+          description: string,
+          downloads_url: string,
+          events_url: string,
+          fork: boolean,
+          forks: int,
+          forks_count: int,
+          forks_url: string,
+          full_name: string,
+          git_commits_url: string,
+          git_refs_url: string,
+          git_tags_url: string,
+          git_url: string,
+          has_downloads: boolean,
+          has_issues: boolean,
+          has_pages: boolean,
+          has_wiki: boolean,
+          homepage: string,
+          hooks_url: string,
+          html_url: string,
+          id: int,
+          issue_comment_url: string,
+          issue_events_url: string,
+          issues_url: string,
+          keys_url: string,
+          labels_url: string,
+          language: string,
+          languages_url: string,
+          merges_url: string,
+          milestones_url: string,
+          mirror_url: string,
+          name: string,
+          notifications_url: string,
+          open_issues: int,
+          open_issues_count: int,
+          owner: struct <
+            avatar_url: string,
+            events_url: string,
+            followers_url: string,
+            following_url: string,
+            gists_url: string,
+            gravatar_id: string,
+            html_url: string,
+            id: int,
+            login: string,
+            organizations_url: string,
+            received_events_url: string,
+            repos_url: string,
+            site_admin: boolean,
+            starred_url: string,
+            subscriptions_url: string,
+            type: string,
+            url: string>,
+          private: boolean,
+          pulls_url: string,
+          pushed_at: timestamp,
+          releases_url: string,
+          size: int,
+          ssh_url: string,
+          stargazers_count: int,
+          stargazers_url: string,
+          statuses_url: string,
+          subscribers_url: string,
+          subscription_url: string,
+          svn_url: string,
+          tags_url: string,
+          teams_url: string,
+          trees_url: string,
+          updated_at: timestamp,
+          url: string,
+          watchers: int,
+          watchers_count: int>,
+        sha: binary,
+        user: struct <
+          avatar_url: string,
+          events_url: string,
+          followers_url: string,
+          following_url: string,
+          gists_url: string,
+          gravatar_id: string,
+          html_url: string,
+          id: int,
+          login: string,
+          organizations_url: string,
+          received_events_url: string,
+          repos_url: string,
+          site_admin: boolean,
+          starred_url: string,
+          subscriptions_url: string,
+          type: string,
+          url: string>>,
+      html_url: string,
+      id: int,
+      issue_url: string,
+      locked: boolean,
+      merge_commit_sha: string,
+      mergeable: boolean,
+      mergeable_state: string,
+      merged: boolean,
+      merged_at: timestamp,
+      merged_by: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>,
+      milestone: struct <
+        closed_at: timestamp,
+        closed_issues: int,
+        created_at: timestamp,
+        creator: struct <
+          avatar_url: string,
+          events_url: string,
+          followers_url: string,
+          following_url: string,
+          gists_url: string,
+          gravatar_id: string,
+          html_url: string,
+          id: int,
+          login: string,
+          organizations_url: string,
+          received_events_url: string,
+          repos_url: string,
+          site_admin: boolean,
+          starred_url: string,
+          subscriptions_url: string,
+          type: string,
+          url: string>,
+        description: string,
+        due_on: timestamp,
+        html_url: string,
+        id: int,
+        labels_url: string,
+        number: int,
+        open_issues: int,
+        state: string,
+        title: string,
+        updated_at: timestamp,
+        url: string>,
+      number: int,
+      patch_url: string,
+      review_comment_url: string,
+      review_comments: int,
+      review_comments_url: string,
+      state: string,
+      statuses_url: string,
+      title: string,
+      updated_at: timestamp,
+      url: string,
+      user: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>>,
+    push_id: int,
+    pusher_type: string,
+    ref: string,
+    ref_type: string,
+    release: struct <
+      assets: array <struct <
+          browser_download_url: string,
+          content_type: string,
+          created_at: timestamp,
+          download_count: int,
+          id: int,
+          label: string,
+          name: string,
+          size: int,
+          state: string,
+          updated_at: timestamp,
+          uploader: struct <
+            avatar_url: string,
+            events_url: string,
+            followers_url: string,
+            following_url: string,
+            gists_url: string,
+            gravatar_id: string,
+            html_url: string,
+            id: int,
+            login: string,
+            organizations_url: string,
+            received_events_url: string,
+            repos_url: string,
+            site_admin: boolean,
+            starred_url: string,
+            subscriptions_url: string,
+            type: string,
+            url: string>,
+          url: string>>,
+      assets_url: string,
+      author: struct <
+        avatar_url: string,
+        events_url: string,
+        followers_url: string,
+        following_url: string,
+        gists_url: string,
+        gravatar_id: string,
+        html_url: string,
+        id: int,
+        login: string,
+        organizations_url: string,
+        received_events_url: string,
+        repos_url: string,
+        site_admin: boolean,
+        starred_url: string,
+        subscriptions_url: string,
+        type: string,
+        url: string>,
+      body: string,
+      created_at: timestamp,
+      draft: boolean,
+      html_url: string,
+      id: int,
+      name: string,
+      prerelease: boolean,
+      published_at: timestamp,
+      tag_name: string,
+      tarball_url: string,
+      target_commitish: string,
+      upload_url: string,
+      url: string,
+      zipball_url: string>,
+    size: int>,
+  public: boolean,
+  repo: struct <
+    id: int,
+    name: string,
+    url: string>,
+  type: string
+>
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/bench/src/main/resources/log4j.properties
----------------------------------------------------------------------
diff --git a/java/bench/src/main/resources/log4j.properties b/java/bench/src/main/resources/log4j.properties
new file mode 100644
index 0000000..363917c
--- /dev/null
+++ b/java/bench/src/main/resources/log4j.properties
@@ -0,0 +1,6 @@
+log4j.rootLogger=WARN, CONSOLE
+
+# CONSOLE is set to be a ConsoleAppender using a PatternLayout
+log4j.appender.CONSOLE=org.apache.log4j.ConsoleAppender
+log4j.appender.CONSOLE.layout=org.apache.log4j.PatternLayout
+log4j.appender.CONSOLE.layout.ConversionPattern=[%-5p] %m%n
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/bench/src/main/resources/sales.schema
----------------------------------------------------------------------
diff --git a/java/bench/src/main/resources/sales.schema b/java/bench/src/main/resources/sales.schema
new file mode 100644
index 0000000..df96409
--- /dev/null
+++ b/java/bench/src/main/resources/sales.schema
@@ -0,0 +1,56 @@
+struct<
+  sales_id:bigint,
+  customer_id:bigint,
+  col3:bigint,
+  item_category:bigint,
+  item_count:bigint,
+  change_ts:timestamp,
+  store_location:string,
+  associate_id:string,
+  col9:bigint,
+  rebate_id:string,
+  create_ts:timestamp,
+  col13:bigint,
+  size:string,
+  col14:bigint,
+  fulfilled:boolean,
+  global_id:string,
+  col17:string,
+  col18:string,
+  col19:bigint,
+  has_rebate:boolean,
+  col21:array<
+    struct<
+      sub1:bigint,
+      sub2:string,
+      sub3:string,
+      sub4:bigint,
+      sub5:bigint,
+      sub6:string>>,
+  vendor_id:string,
+  country:string,
+  backend_version:string,
+  col41:bigint,
+  col42:bigint,
+  col43:bigint,
+  col44:bigint,
+  col45:bigint,
+  col46:bigint,
+  col47:bigint,
+  col48:bigint,
+  col49:string,
+  col50:string,
+  col51:bigint,
+  col52:bigint,
+  col53:bigint,
+  col54:bigint,
+  col55:string,
+  col56:timestamp,
+  col57:timestamp,
+  md5:bigint,
+  col59:bigint,
+  col69:timestamp,
+  col61:string,
+  col62:string,
+  col63:timestamp,
+  col64:bigint>

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/bench/src/main/resources/taxi.schema
----------------------------------------------------------------------
diff --git a/java/bench/src/main/resources/taxi.schema b/java/bench/src/main/resources/taxi.schema
new file mode 100644
index 0000000..5eb7c0f
--- /dev/null
+++ b/java/bench/src/main/resources/taxi.schema
@@ -0,0 +1,21 @@
+struct<
+  vendor_id:int,
+  pickup_time: timestamp,
+  dropoff_time: timestamp,
+  passenger_count: int,
+  trip_distance: double,
+  pickup_longitude: double,
+  pickup_latitude: double,
+  ratecode_id: int,
+  store_and_fwd_flag: string,
+  dropoff_longitude: double,
+  dropoff_latitude: double,
+  payment_type: int,
+  fare_amount: decimal(8,2),
+  extra: decimal(8,2),
+  mta_tax: decimal(8,2),
+  tip_amount: decimal(8,2),
+  tolls_amount: decimal(8,2),
+  improvement_surcharge : decimal(8,2),
+  total_amount: decimal(8,2)
+>
\ No newline at end of file

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/core/src/java/org/apache/orc/TypeDescription.java
----------------------------------------------------------------------
diff --git a/java/core/src/java/org/apache/orc/TypeDescription.java b/java/core/src/java/org/apache/orc/TypeDescription.java
index cced414..b0857f0 100644
--- a/java/core/src/java/org/apache/orc/TypeDescription.java
+++ b/java/core/src/java/org/apache/orc/TypeDescription.java
@@ -749,7 +749,7 @@ public class TypeDescription
     return startId;
   }
 
-  private TypeDescription(Category category) {
+  public TypeDescription(Category category) {
     this.category = category;
     if (category.isPrimitive) {
       children = null;

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/pom.xml
----------------------------------------------------------------------
diff --git a/java/pom.xml b/java/pom.xml
index 7bebd1f..02af938 100644
--- a/java/pom.xml
+++ b/java/pom.xml
@@ -60,6 +60,7 @@
     <module>core</module>
     <module>mapreduce</module>
     <module>tools</module>
+    <module>bench</module>
   </modules>
 
   <properties>
@@ -69,7 +70,9 @@
     <test.tmp.dir>${project.build.directory}/testing-tmp</test.tmp.dir>
     <example.dir>${project.basedir}/../../examples</example.dir>
 
+    <avro.version>1.8.1</avro.version>
     <hadoop.version>2.6.4</hadoop.version>
+    <hive.version>2.1.1</hive.version>
     <storage-api.version>2.2.1</storage-api.version>
     <zookeeper.version>3.4.6</zookeeper.version>
   </properties>
@@ -271,6 +274,11 @@
         <version>11.0.2</version>
       </dependency>
       <dependency>
+	<groupId>com.fasterxml.jackson.core</groupId>
+	<artifactId>jackson-core</artifactId>
+	<version>2.8.4</version>
+      </dependency>
+      <dependency>
         <groupId>com.google.protobuf</groupId>
         <artifactId>protobuf-java</artifactId>
         <version>2.5.0</version>
@@ -296,6 +304,22 @@
         <version>0.3</version>
       </dependency>
       <dependency>
+        <groupId>org.apache.avro</groupId>
+        <artifactId>avro</artifactId>
+        <version>${avro.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.avro</groupId>
+        <artifactId>avro-mapred</artifactId>
+        <classifier>hadoop2</classifier>
+        <version>${avro.version}</version>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.commons</groupId>
+        <artifactId>commons-csv</artifactId>
+        <version>1.4</version>
+      </dependency>
+      <dependency>
         <groupId>org.apache.hadoop</groupId>
         <artifactId>hadoop-common</artifactId>
         <version>${hadoop.version}</version>
@@ -363,6 +387,52 @@
         </exclusions>
       </dependency>
       <dependency>
+        <groupId>org.apache.hive</groupId>
+        <artifactId>hive-common</artifactId>
+        <version>${hive.version}</version>
+        <exclusions>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-storage-api</artifactId>
+          </exclusion>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-orc</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hive</groupId>
+        <artifactId>hive-exec</artifactId>
+        <version>${hive.version}</version>
+        <classifier>core</classifier>
+        <exclusions>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-storage-api</artifactId>
+          </exclusion>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-orc</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+      <dependency>
+        <groupId>org.apache.hive</groupId>
+        <artifactId>hive-serde</artifactId>
+        <version>${hive.version}</version>
+        <exclusions>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-storage-api</artifactId>
+          </exclusion>
+          <exclusion>
+	    <groupId>org.apache.hive</groupId>
+	    <artifactId>hive-orc</artifactId>
+          </exclusion>
+        </exclusions>
+      </dependency>
+      <dependency>
         <groupId>org.apache.hadoop</groupId>
         <artifactId>hadoop-hdfs</artifactId>
         <version>${hadoop.version}</version>
@@ -462,6 +532,11 @@
 	</exclusions>
       </dependency>
       <dependency>
+        <groupId>org.apache.parquet</groupId>
+        <artifactId>parquet-hadoop-bundle</artifactId>
+        <version>1.8.2</version>
+      </dependency>
+      <dependency>
         <groupId>org.codehaus.jettison</groupId>
         <artifactId>jettison</artifactId>
         <version>1.1</version>
@@ -473,10 +548,26 @@
 	</exclusions>
       </dependency>
       <dependency>
+        <groupId>org.jodd</groupId>
+        <artifactId>jodd-core</artifactId>
+        <version>3.5.2</version>
+	<scope>runtime</scope>
+      </dependency>
+      <dependency>
+        <groupId>org.openjdk.jmh</groupId>
+        <artifactId>jmh-core</artifactId>
+        <version>1.18</version>
+      </dependency>
+      <dependency>
         <groupId>org.slf4j</groupId>
         <artifactId>slf4j-api</artifactId>
         <version>1.7.5</version>
       </dependency>
+      <dependency>
+        <groupId>org.slf4j</groupId>
+        <artifactId>slf4j-simple</artifactId>
+        <version>1.7.5</version>
+      </dependency>
 
       <!-- test inter-project -->
       <dependency>

http://git-wip-us.apache.org/repos/asf/orc/blob/ce5213b2/java/tools/src/assembly/uber.xml
----------------------------------------------------------------------
diff --git a/java/tools/src/assembly/uber.xml b/java/tools/src/assembly/uber.xml
index 2c45350..014eab9 100644
--- a/java/tools/src/assembly/uber.xml
+++ b/java/tools/src/assembly/uber.xml
@@ -19,15 +19,12 @@
   <includeBaseDirectory>false</includeBaseDirectory>
   <dependencySets>
     <dependencySet>
+      <outputDirectory>/</outputDirectory>
+      <useProjectArtifact>true</useProjectArtifact>
       <unpack>true</unpack>
       <scope>runtime</scope>
     </dependencySet>
   </dependencySets>
-  <fileSets>
-    <fileSet>
-      <directory>${project.build.outputDirectory}</directory>
-    </fileSet>
-  </fileSets>
   <containerDescriptorHandlers>
     <containerDescriptorHandler>
       <handlerName>metaInf-services</handlerName>


Mime
View raw message