fx19880617 commented on a change in pull request #6525:
URL: https://github.com/apache/incubator-pinot/pull/6525#discussion_r569288948
##########
File path:
pinot-spi/src/main/java/org/apache/pinot/spi/data/readers/GenericRow.java
##########
@@ -167,11 +167,62 @@ public boolean equals(Object obj) {
}
if (obj instanceof GenericRow) {
GenericRow that = (GenericRow) obj;
- return _fieldToValueMap.equals(that._fieldToValueMap) &&
_nullValueFields.equals(that._nullValueFields);
+ if (!_nullValueFields.containsAll(that._nullValueFields) ||
!that._nullValueFields
+ .containsAll(_nullValueFields)) {
+ return false;
+ }
+ return compareMap(_fieldToValueMap, that._fieldToValueMap);
}
return false;
}
+ private boolean compareMap(Map<String, Object> thisMap, Map<String, Object>
thatMap) {
+ if (thisMap.size() == thatMap.size()) {
Review comment:
Below is one example of a large nested record in the
`githubActivities.snappy.parquet` file:
```
{
"actor": {
"avatar_url":
"https://avatars.githubusercontent.com/u/5439615?",
"display_login": "johndmulhausen",
"gravatar_id": "",
"id": 5439615,
"login": "johndmulhausen",
"url": "https://api.github.com/users/johndmulhausen"
},
"created_at": "2016-07-07T00:00:34Z",
"id": "4243624603",
"org": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13629408?",
"gravatar_id": "",
"id": 13629408,
"login": "kubernetes",
"url": "https://api.github.com/orgs/kubernetes"
},
"payload": {
"action": "closed",
"number": 507,
"pull_request": {
"_links": {
"comments": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/507/comments"
},
"commits": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507/commits"
},
"html": {
"href":
"https://github.com/kubernetes/kubernetes.github.io/pull/507"
},
"issue": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/507"
},
"review_comment": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/comments{/number}"
},
"review_comments": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507/comments"
},
"self": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507"
},
"statuses": {
"href":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/statuses/0700c5ca798fce6d1f323ca70baa5ef45e82e491"
}
},
"additions": 38,
"assignees": {},
"base": {
"label": "kubernetes:master",
"ref": "master",
"repo": {
"archive_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/{archive_format}{/ref}",
"assignees_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/assignees{/user}",
"blobs_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/git/blobs{/sha}",
"branches_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/branches{/branch}",
"clone_url":
"https://github.com/kubernetes/kubernetes.github.io.git",
"collaborators_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/collaborators{/collaborator}",
"comments_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/comments{/number}",
"commits_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/commits{/sha}",
"compare_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/compare/{base}...{head}",
"contents_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/contents/{+path}",
"contributors_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/contributors",
"created_at": "2016-02-10T22:46:48Z",
"default_branch": "master",
"deployments_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/deployments",
"description": "Website/documentation
repo",
"downloads_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/downloads",
"events_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/events",
"fork": false,
"forks": 329,
"forks_count": 329,
"forks_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/forks",
"full_name":
"kubernetes/kubernetes.github.io",
"git_commits_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/git/commits{/sha}",
"git_refs_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/git/refs{/sha}",
"git_tags_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/git/tags{/sha}",
"git_url":
"git://github.com/kubernetes/kubernetes.github.io.git",
"has_downloads": true,
"has_issues": true,
"has_pages": true,
"has_wiki": true,
"hooks_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/hooks",
"html_url":
"https://github.com/kubernetes/kubernetes.github.io",
"id": 51478266,
"issue_comment_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/comments{/number}",
"issue_events_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/events{/number}",
"issues_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues{/number}",
"keys_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/keys{/key_id}",
"labels_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/labels{/name}",
"language": "HTML",
"languages_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/languages",
"merges_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/merges",
"milestones_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/milestones{/number}",
"name": "kubernetes.github.io",
"notifications_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/notifications{?since,all,participating}",
"open_issues": 289,
"open_issues_count": 289,
"owner": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13629408?v=3",
"events_url":
"https://api.github.com/users/kubernetes/events{/privacy}",
"followers_url":
"https://api.github.com/users/kubernetes/followers",
"following_url":
"https://api.github.com/users/kubernetes/following{/other_user}",
"gists_url":
"https://api.github.com/users/kubernetes/gists{/gist_id}",
"gravatar_id": "",
"html_url":
"https://github.com/kubernetes",
"id": 13629408,
"login": "kubernetes",
"organizations_url":
"https://api.github.com/users/kubernetes/orgs",
"received_events_url":
"https://api.github.com/users/kubernetes/received_events",
"repos_url":
"https://api.github.com/users/kubernetes/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/kubernetes/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/kubernetes/subscriptions",
"type": "Organization",
"url":
"https://api.github.com/users/kubernetes"
},
"private": false,
"pulls_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls{/number}",
"pushed_at": "2016-07-07T00:00:33Z",
"releases_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/releases{/id}",
"size": 39878,
"ssh_url":
"[email protected]:kubernetes/kubernetes.github.io.git",
"stargazers_count": 55,
"stargazers_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/stargazers",
"statuses_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/statuses/{sha}",
"subscribers_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/subscribers",
"subscription_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/subscription",
"svn_url":
"https://github.com/kubernetes/kubernetes.github.io",
"tags_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/tags",
"teams_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/teams",
"trees_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/git/trees{/sha}",
"updated_at": "2016-07-06T22:19:07Z",
"url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io",
"watchers": 55,
"watchers_count": 55
},
"sha":
"85eba1f0b3100abd75cb5c0355ff6a474f977a07",
"user": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13629408?v=3",
"events_url":
"https://api.github.com/users/kubernetes/events{/privacy}",
"followers_url":
"https://api.github.com/users/kubernetes/followers",
"following_url":
"https://api.github.com/users/kubernetes/following{/other_user}",
"gists_url":
"https://api.github.com/users/kubernetes/gists{/gist_id}",
"gravatar_id": "",
"html_url":
"https://github.com/kubernetes",
"id": 13629408,
"login": "kubernetes",
"organizations_url":
"https://api.github.com/users/kubernetes/orgs",
"received_events_url":
"https://api.github.com/users/kubernetes/received_events",
"repos_url":
"https://api.github.com/users/kubernetes/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/kubernetes/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/kubernetes/subscriptions",
"type": "Organization",
"url":
"https://api.github.com/users/kubernetes"
}
},
"body": "Mostly the same as
https://github.com/kubernetes/kubernetes/pull/25574",
"changed_files": 1,
"closed_at": "2016-07-07T00:00:33Z",
"comments": 2,
"comments_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/507/comments",
"commits": 1,
"commits_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507/commits",
"created_at": "2016-05-13T16:01:23Z",
"deletions": 0,
"diff_url":
"https://github.com/kubernetes/kubernetes.github.io/pull/507.diff",
"head": {
"label": "therc:patch-2",
"ref": "patch-2",
"repo": {
"archive_url":
"https://api.github.com/repos/therc/kubernetes.github.io/{archive_format}{/ref}",
"assignees_url":
"https://api.github.com/repos/therc/kubernetes.github.io/assignees{/user}",
"blobs_url":
"https://api.github.com/repos/therc/kubernetes.github.io/git/blobs{/sha}",
"branches_url":
"https://api.github.com/repos/therc/kubernetes.github.io/branches{/branch}",
"clone_url":
"https://github.com/therc/kubernetes.github.io.git",
"collaborators_url":
"https://api.github.com/repos/therc/kubernetes.github.io/collaborators{/collaborator}",
"comments_url":
"https://api.github.com/repos/therc/kubernetes.github.io/comments{/number}",
"commits_url":
"https://api.github.com/repos/therc/kubernetes.github.io/commits{/sha}",
"compare_url":
"https://api.github.com/repos/therc/kubernetes.github.io/compare/{base}...{head}",
"contents_url":
"https://api.github.com/repos/therc/kubernetes.github.io/contents/{+path}",
"contributors_url":
"https://api.github.com/repos/therc/kubernetes.github.io/contributors",
"created_at": "2016-03-14T21:11:34Z",
"default_branch": "master",
"deployments_url":
"https://api.github.com/repos/therc/kubernetes.github.io/deployments",
"description": "Website/documentation
repo",
"downloads_url":
"https://api.github.com/repos/therc/kubernetes.github.io/downloads",
"events_url":
"https://api.github.com/repos/therc/kubernetes.github.io/events",
"fork": true,
"forks": 0,
"forks_count": 0,
"forks_url":
"https://api.github.com/repos/therc/kubernetes.github.io/forks",
"full_name":
"therc/kubernetes.github.io",
"git_commits_url":
"https://api.github.com/repos/therc/kubernetes.github.io/git/commits{/sha}",
"git_refs_url":
"https://api.github.com/repos/therc/kubernetes.github.io/git/refs{/sha}",
"git_tags_url":
"https://api.github.com/repos/therc/kubernetes.github.io/git/tags{/sha}",
"git_url":
"git://github.com/therc/kubernetes.github.io.git",
"has_downloads": true,
"has_issues": false,
"has_pages": false,
"has_wiki": true,
"hooks_url":
"https://api.github.com/repos/therc/kubernetes.github.io/hooks",
"html_url":
"https://github.com/therc/kubernetes.github.io",
"id": 53892222,
"issue_comment_url":
"https://api.github.com/repos/therc/kubernetes.github.io/issues/comments{/number}",
"issue_events_url":
"https://api.github.com/repos/therc/kubernetes.github.io/issues/events{/number}",
"issues_url":
"https://api.github.com/repos/therc/kubernetes.github.io/issues{/number}",
"keys_url":
"https://api.github.com/repos/therc/kubernetes.github.io/keys{/key_id}",
"labels_url":
"https://api.github.com/repos/therc/kubernetes.github.io/labels{/name}",
"language": "HTML",
"languages_url":
"https://api.github.com/repos/therc/kubernetes.github.io/languages",
"merges_url":
"https://api.github.com/repos/therc/kubernetes.github.io/merges",
"milestones_url":
"https://api.github.com/repos/therc/kubernetes.github.io/milestones{/number}",
"name": "kubernetes.github.io",
"notifications_url":
"https://api.github.com/repos/therc/kubernetes.github.io/notifications{?since,all,participating}",
"open_issues": 0,
"open_issues_count": 0,
"owner": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13481082?v=3",
"events_url":
"https://api.github.com/users/therc/events{/privacy}",
"followers_url":
"https://api.github.com/users/therc/followers",
"following_url":
"https://api.github.com/users/therc/following{/other_user}",
"gists_url":
"https://api.github.com/users/therc/gists{/gist_id}",
"gravatar_id": "",
"html_url":
"https://github.com/therc",
"id": 13481082,
"login": "therc",
"organizations_url":
"https://api.github.com/users/therc/orgs",
"received_events_url":
"https://api.github.com/users/therc/received_events",
"repos_url":
"https://api.github.com/users/therc/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/therc/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/therc/subscriptions",
"type": "User",
"url":
"https://api.github.com/users/therc"
},
"private": false,
"pulls_url":
"https://api.github.com/repos/therc/kubernetes.github.io/pulls{/number}",
"pushed_at": "2016-05-13T16:01:15Z",
"releases_url":
"https://api.github.com/repos/therc/kubernetes.github.io/releases{/id}",
"size": 33202,
"ssh_url":
"[email protected]:therc/kubernetes.github.io.git",
"stargazers_count": 0,
"stargazers_url":
"https://api.github.com/repos/therc/kubernetes.github.io/stargazers",
"statuses_url":
"https://api.github.com/repos/therc/kubernetes.github.io/statuses/{sha}",
"subscribers_url":
"https://api.github.com/repos/therc/kubernetes.github.io/subscribers",
"subscription_url":
"https://api.github.com/repos/therc/kubernetes.github.io/subscription",
"svn_url":
"https://github.com/therc/kubernetes.github.io",
"tags_url":
"https://api.github.com/repos/therc/kubernetes.github.io/tags",
"teams_url":
"https://api.github.com/repos/therc/kubernetes.github.io/teams",
"trees_url":
"https://api.github.com/repos/therc/kubernetes.github.io/git/trees{/sha}",
"updated_at": "2016-03-14T21:11:36Z",
"url":
"https://api.github.com/repos/therc/kubernetes.github.io",
"watchers": 0,
"watchers_count": 0
},
"sha":
"0700c5ca798fce6d1f323ca70baa5ef45e82e491",
"user": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13481082?v=3",
"events_url":
"https://api.github.com/users/therc/events{/privacy}",
"followers_url":
"https://api.github.com/users/therc/followers",
"following_url":
"https://api.github.com/users/therc/following{/other_user}",
"gists_url":
"https://api.github.com/users/therc/gists{/gist_id}",
"gravatar_id": "",
"html_url": "https://github.com/therc",
"id": 13481082,
"login": "therc",
"organizations_url":
"https://api.github.com/users/therc/orgs",
"received_events_url":
"https://api.github.com/users/therc/received_events",
"repos_url":
"https://api.github.com/users/therc/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/therc/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/therc/subscriptions",
"type": "User",
"url":
"https://api.github.com/users/therc"
}
},
"html_url":
"https://github.com/kubernetes/kubernetes.github.io/pull/507",
"id": 70019391,
"issue_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/issues/507",
"locked": false,
"merge_commit_sha":
"a135f0a717803b35ec80563768d5abb4b45ac4d1",
"mergeable_state": "unknown",
"merged": true,
"merged_at": "2016-07-07T00:00:33Z",
"merged_by": {
"avatar_url":
"https://avatars.githubusercontent.com/u/5439615?v=3",
"events_url":
"https://api.github.com/users/johndmulhausen/events{/privacy}",
"followers_url":
"https://api.github.com/users/johndmulhausen/followers",
"following_url":
"https://api.github.com/users/johndmulhausen/following{/other_user}",
"gists_url":
"https://api.github.com/users/johndmulhausen/gists{/gist_id}",
"gravatar_id": "",
"html_url": "https://github.com/johndmulhausen",
"id": 5439615,
"login": "johndmulhausen",
"organizations_url":
"https://api.github.com/users/johndmulhausen/orgs",
"received_events_url":
"https://api.github.com/users/johndmulhausen/received_events",
"repos_url":
"https://api.github.com/users/johndmulhausen/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/johndmulhausen/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/johndmulhausen/subscriptions",
"type": "User",
"url":
"https://api.github.com/users/johndmulhausen"
},
"number": 507,
"patch_url":
"https://github.com/kubernetes/kubernetes.github.io/pull/507.patch",
"review_comment_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/comments{/number}",
"review_comments": 4,
"review_comments_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507/comments",
"state": "closed",
"statuses_url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/statuses/0700c5ca798fce6d1f323ca70baa5ef45e82e491",
"title": "Update service doc with AWS ELB SSL
annotations",
"updated_at": "2016-07-07T00:00:33Z",
"url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io/pulls/507",
"user": {
"avatar_url":
"https://avatars.githubusercontent.com/u/13481082?v=3",
"events_url":
"https://api.github.com/users/therc/events{/privacy}",
"followers_url":
"https://api.github.com/users/therc/followers",
"following_url":
"https://api.github.com/users/therc/following{/other_user}",
"gists_url":
"https://api.github.com/users/therc/gists{/gist_id}",
"gravatar_id": "",
"html_url": "https://github.com/therc",
"id": 13481082,
"login": "therc",
"organizations_url":
"https://api.github.com/users/therc/orgs",
"received_events_url":
"https://api.github.com/users/therc/received_events",
"repos_url":
"https://api.github.com/users/therc/repos",
"site_admin": false,
"starred_url":
"https://api.github.com/users/therc/starred{/owner}{/repo}",
"subscriptions_url":
"https://api.github.com/users/therc/subscriptions",
"type": "User",
"url": "https://api.github.com/users/therc"
}
}
},
"public": true,
"repo": {
"id": 51478266,
"name": "kubernetes/kubernetes.github.io",
"url":
"https://api.github.com/repos/kubernetes/kubernetes.github.io"
},
"type": "PullRequestEvent"
}
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]