feat: include GitHub handles (#3857)

emlimlf · web-flow · commit a956c677a5a4 · 2026-02-19T18:20:04.000+08:00
Signed-off-by: Efren Lim &lt;elim@linuxfoundation.org&gt;
diff --git a/services/libs/tinybird/datasources/leaderboards_copy_ds.datasource b/services/libs/tinybird/datasources/leaderboards_copy_ds.datasource
@@ -16,7 +16,7 @@ DESCRIPTION >
     - `previousPeriodValue` is the comparison metric from the previous period (0 for non-temporal leaderboards).
     - `collectionsSlugs` list of collection slugs the project belongs to.
     - `isLF` indicates whether the project is a LF project (1 = true, 0 = false).
-    - `githubHandle` is the GitHub username for contributor leaderboards (empty string for non-contributor leaderboards).
+    - `githubHandleArray` is the array of GitHub usernames for contributor leaderboards (empty array for non-contributor leaderboards).
 
 TAGS "Analytics, Leaderboards, Project rankings"
 
@@ -33,7 +33,7 @@ SCHEMA >
     `previousPeriodValue` Float64,
     `collectionsSlugs` Array(String),
     `isLF` UInt8,
-    `githubHandle` String,
+    `githubHandleArray` Array(String),
     `status` String,
     `totalCount` UInt64
 
diff --git a/services/libs/tinybird/datasources/members_sorted.datasource b/services/libs/tinybird/datasources/members_sorted.datasource
@@ -13,7 +13,7 @@ DESCRIPTION >
     - `displayName` is the member's preferred display name across platforms.
     - `score` is the computed activity/engagement score for the member.
     - `publicName` is the denormalized public display name for efficient queries.
-    - `githubHandle` is the member's GitHub username from memberIdentities (empty string if not available).
+    - `githubHandleArray` is the member's GitHub usernames from memberIdentities (empty array if not available).
 
 SCHEMA >
     `id` String,
@@ -31,7 +31,7 @@ SCHEMA >
     `displayName` String,
     `score` Int32,
     `publicName` String,
-    `githubHandle` String
+    `githubHandleArray` Array(String)
 
 ENGINE MergeTree
 ENGINE_PARTITION_KEY toYear(joinedAt)
diff --git a/services/libs/tinybird/pipes/contributor_dependency.pipe b/services/libs/tinybird/pipes/contributor_dependency.pipe
@@ -14,7 +14,7 @@ DESCRIPTION >
     - `activity_type`: Optional string filter for single activity type (e.g., 'authored-commit')
     - `activity_types`: Optional array of activity types (e.g., ['authored-commit', 'co-authored-commit'])
     - `onlyContributions`: Optional boolean, defaults to 1 (contributions only), set to 0 for all activities
-    - Response: `id`, `displayName`, `githubHandle`, `contributionCount`, `contributionPercentage`, `roles`, `contributionPercentageRunningTotal`, `totalContributorCount`
+    - Response: `id`, `displayName`, `githubHandleArray`, `contributionCount`, `contributionPercentage`, `roles`, `contributionPercentageRunningTotal`, `totalContributorCount`
 
 NODE contributions_percentage_running_total
 SQL >
@@ -24,7 +24,7 @@ SQL >
             SELECT
                 id,
                 displayName,
-                githubHandle,
+                githubHandleArray,
                 contributionCount,
                 contributionPercentage,
                 roles,
diff --git a/services/libs/tinybird/pipes/contributors_leaderboard.pipe b/services/libs/tinybird/pipes/contributors_leaderboard.pipe
@@ -18,7 +18,7 @@ DESCRIPTION >
     - `offset`: Optional integer for result pagination, defaults to 0
     - Response:
     - Count mode (`count=true`): `count` (total number of contributors)
-    - Data mode (default): `id`, `avatar`, `displayName`, `githubHandle`, `contributionCount`, `contributionPercentage`, `roles`
+    - Data mode (default): `id`, `avatar`, `displayName`, `githubHandleArray`, `contributionCount`, `contributionPercentage`, `roles`
 
 NODE memberId_aggregates
 SQL >
@@ -55,7 +55,7 @@ SQL >
             m.id,
             m.avatar,
             case when is_non_lf.result then m.publicName else m.displayName end as displayName,
-            m.githubHandle,
+            m.githubHandleArray,
             ma.contributionCount,
             ma.contributionPercentage,
             mr.roles
diff --git a/services/libs/tinybird/pipes/leaderboards.pipe b/services/libs/tinybird/pipes/leaderboards.pipe
@@ -22,7 +22,7 @@ SQL >
         previousPeriodValue,
         collectionsSlugs,
         isLF,
-        githubHandle,
+        githubHandleArray,
         status,
         totalCount
     FROM leaderboards_copy_ds
diff --git a/services/libs/tinybird/pipes/leaderboards_avg_commits_per_author.pipe b/services/libs/tinybird/pipes/leaderboards_avg_commits_per_author.pipe
@@ -49,7 +49,7 @@ SQL >
         0.0 as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_avg_commits_per_author_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_codebase_size.pipe b/services/libs/tinybird/pipes/leaderboards_codebase_size.pipe
@@ -41,7 +41,7 @@ SQL >
         0.0 as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_codebase_size_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_commits.pipe b/services/libs/tinybird/pipes/leaderboards_commits.pipe
@@ -60,7 +60,7 @@ SQL >
         cast(coalesce(pp.commits, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_commits_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_forks.pipe b/services/libs/tinybird/pipes/leaderboards_forks.pipe
@@ -39,7 +39,7 @@ SQL >
         cast(coalesce(m.previousForks, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_forks_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_issue_response.pipe b/services/libs/tinybird/pipes/leaderboards_issue_response.pipe
@@ -61,7 +61,7 @@ SQL >
         cast(coalesce(pp.averageResponseTimeSeconds, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_issue_response_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_members.pipe b/services/libs/tinybird/pipes/leaderboards_members.pipe
@@ -8,7 +8,7 @@ DESCRIPTION >
     Retrieves all members from the populated datasource
 
 SQL >
-    SELECT id, displayName, avatar, githubHandle FROM members_sorted
+    SELECT id, displayName, avatar, githubHandleArray FROM members_sorted
 
 NODE leaderboards_member_activity_types
 DESCRIPTION >
@@ -69,7 +69,7 @@ SQL >
         cast(coalesce(pp.memberActivityCount, 0) as Float64) as previousPeriodValue,
         arrayDistinct(arrayFlatten(groupArray(proj.collectionsSlugs))) as collectionsSlugs,
         toUInt8(0) as isLF,
-        p.githubHandle as githubHandle,
+        p.githubHandleArray as githubHandleArray,
         '' as status,
         count() OVER () as totalCount
     FROM leaderboards_members_data p
@@ -79,7 +79,12 @@ SQL >
     LEFT JOIN leaderboards_members_projects proj ON proj.segmentId = sid
     WHERE c.memberActivityCount > 0
     GROUP BY
-        p.id, p.displayName, p.avatar, p.githubHandle, c.memberActivityCount, pp.memberActivityCount
+        p.id,
+        p.displayName,
+        p.avatar,
+        p.githubHandleArray,
+        c.memberActivityCount,
+        pp.memberActivityCount
     ORDER BY value DESC
     LIMIT 100
 
diff --git a/services/libs/tinybird/pipes/leaderboards_merge_time.pipe b/services/libs/tinybird/pipes/leaderboards_merge_time.pipe
@@ -56,7 +56,7 @@ SQL >
         cast(coalesce(pp.averageMergeTimeSeconds, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_merge_time_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_organizations.pipe b/services/libs/tinybird/pipes/leaderboards_organizations.pipe
@@ -74,7 +74,7 @@ SQL >
         cast(coalesce(pp.organizationActivityCount, 0) as Float64) as previousPeriodValue,
         arrayDistinct(arrayFlatten(groupArray(proj.collectionsSlugs))) as collectionsSlugs,
         toUInt8(0) as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         '' as status,
         count() OVER () as totalCount
     FROM leaderboards_organizations_data p
diff --git a/services/libs/tinybird/pipes/leaderboards_package_downloads.pipe b/services/libs/tinybird/pipes/leaderboards_package_downloads.pipe
@@ -83,7 +83,7 @@ SQL >
         cast(coalesce(pp.downloads, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_package_downloads_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_project_active_contributors.pipe b/services/libs/tinybird/pipes/leaderboards_project_active_contributors.pipe
@@ -65,7 +65,7 @@ SQL >
         cast(coalesce(pp.contributor_count, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_project_active_contributors_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_project_active_organizations.pipe b/services/libs/tinybird/pipes/leaderboards_project_active_organizations.pipe
@@ -65,7 +65,7 @@ SQL >
         cast(coalesce(pp.organization_count, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_project_active_organizations_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_resolution_rate.pipe b/services/libs/tinybird/pipes/leaderboards_resolution_rate.pipe
@@ -37,7 +37,7 @@ SQL >
         0.0 as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_resolution_rate_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_small_project_commit.pipe b/services/libs/tinybird/pipes/leaderboards_small_project_commit.pipe
@@ -41,7 +41,7 @@ SQL >
         0.0 as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_small_project_commit_projects p
diff --git a/services/libs/tinybird/pipes/leaderboards_stars.pipe b/services/libs/tinybird/pipes/leaderboards_stars.pipe
@@ -39,7 +39,7 @@ SQL >
         cast(coalesce(m.previousStars, 0) as Float64) as previousPeriodValue,
         p.collectionsSlugs as collectionsSlugs,
         p.isLF as isLF,
-        '' as githubHandle,
+        [] as githubHandleArray,
         p.status as status,
         count() OVER () as totalCount
     FROM leaderboards_stars_projects p
diff --git a/services/libs/tinybird/pipes/members_sorted_copy_pipe.pipe b/services/libs/tinybird/pipes/members_sorted_copy_pipe.pipe
@@ -1,19 +1,19 @@
 DESCRIPTION >
     Filters out `isBot = true` and `isTeamMember=true` members. Also possible to use more granular sorting keys in the destination datasource `members_sorted` Copy pipe runs every hour
 
-NODE github_usernames
+NODE github_usernames_array
 SQL >
-    SELECT memberId, argMax(value, createdAt) AS githubHandle
+    SELECT memberId, groupArray(value) AS githubHandleArray
     FROM memberIdentities FINAL
-    WHERE platform = 'github' AND type = 'username' AND verified = 1 AND isNull(deletedAt)
+    WHERE platform = 'github' AND type = 'username' AND verified = 1 AND isNull (deletedAt)
     GROUP BY memberId
 
 NODE members_pre_filter
 SQL >
-    SELECT members.*, pub.publicName, coalesce(gh.githubHandle, '') AS githubHandle
+    SELECT members.*, pub.publicName, coalesce(gha.githubHandleArray, []) AS githubHandleArray
     FROM members FINAL
     LEFT JOIN members_public_names_ds pub ON pub.memberId = members.id
-    LEFT JOIN github_usernames gh ON gh.memberId = members.id
+    LEFT JOIN github_usernames_array gha ON gha.memberId = members.id
     WHERE
         NOT isBot
         AND NOT isTeamMember
