From de5089d1e76557f67d962f19bd4324b7c70baaf8 Mon Sep 17 00:00:00 2001 From: Amir Hormati Date: Fri, 14 Aug 2026 10:05:02 -0700 Subject: [PATCH] okf: write stackoverflow bundle tags as YAML lists Eight files gave `tags:` a bare comma-separated string, which YAML reads as one plain scalar, not a sequence. A JavaScript string is iterable, so the Documents Layout expanded each one into a Dataplex label per character, and these files round-tripped corrupted while the other 24 in the bundle were fine. Co-Authored-By: Claude Opus 4.7 --- okf/bundles/stackoverflow/datasets/stackoverflow.md | 2 +- okf/bundles/stackoverflow/tables/posts_answers.md | 2 +- okf/bundles/stackoverflow/tables/posts_moderator_nomination.md | 2 +- okf/bundles/stackoverflow/tables/posts_questions.md | 2 +- okf/bundles/stackoverflow/tables/posts_wiki_placeholder.md | 2 +- okf/bundles/stackoverflow/tables/stackoverflow_posts.md | 2 +- okf/bundles/stackoverflow/tables/users.md | 2 +- okf/bundles/stackoverflow/tables/votes.md | 2 +- 8 files changed, 8 insertions(+), 8 deletions(-) diff --git a/okf/bundles/stackoverflow/datasets/stackoverflow.md b/okf/bundles/stackoverflow/datasets/stackoverflow.md index 04eb99ae..426fcee2 100644 --- a/okf/bundles/stackoverflow/datasets/stackoverflow.md +++ b/okf/bundles/stackoverflow/datasets/stackoverflow.md @@ -5,7 +5,7 @@ title: Stack Overflow Public Dataset description: This dataset contains a public archive of Stack Overflow data, including posts, users, and tags. It was last updated on 2022-11-25 and is no longer actively updated. -tags: Stack Overflow, Q&A, developer, programming, public dataset +tags: [Stack Overflow, Q&A, developer, programming, public dataset] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:46:36+00:00' diff --git a/okf/bundles/stackoverflow/tables/posts_answers.md b/okf/bundles/stackoverflow/tables/posts_answers.md index 1fdc02a6..5aada0b1 100644 --- a/okf/bundles/stackoverflow/tables/posts_answers.md +++ b/okf/bundles/stackoverflow/tables/posts_answers.md @@ -4,7 +4,7 @@ resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datas title: Posts Answers description: Contains Stack Overflow answers, including their content, scores, and associated metadata. -tags: stackoverflow, answers, posts, Q&A +tags: [stackoverflow, answers, posts, Q&A] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:48:04+00:00' diff --git a/okf/bundles/stackoverflow/tables/posts_moderator_nomination.md b/okf/bundles/stackoverflow/tables/posts_moderator_nomination.md index 5671f380..c385d92e 100644 --- a/okf/bundles/stackoverflow/tables/posts_moderator_nomination.md +++ b/okf/bundles/stackoverflow/tables/posts_moderator_nomination.md @@ -4,7 +4,7 @@ resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datas title: Posts Moderator Nomination description: Contains posts related to moderator nominations on the Stack Overflow platform. -tags: stackoverflow, posts, moderator, nomination +tags: [stackoverflow, posts, moderator, nomination] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:48:22+00:00' diff --git a/okf/bundles/stackoverflow/tables/posts_questions.md b/okf/bundles/stackoverflow/tables/posts_questions.md index 5c7ec6c8..6d4b96b3 100644 --- a/okf/bundles/stackoverflow/tables/posts_questions.md +++ b/okf/bundles/stackoverflow/tables/posts_questions.md @@ -3,7 +3,7 @@ type: BigQuery Table resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datasets/stackoverflow/tables/posts_questions title: Stack Overflow Posts Questions description: Contains all question posts from Stack Overflow. -tags: stackoverflow, posts, questions +tags: [stackoverflow, posts, questions] generated: at: '2026-07-10T22:49:19+00:00' by: reference_agent/gemini-2.5-flash diff --git a/okf/bundles/stackoverflow/tables/posts_wiki_placeholder.md b/okf/bundles/stackoverflow/tables/posts_wiki_placeholder.md index da5ed916..71c41b65 100644 --- a/okf/bundles/stackoverflow/tables/posts_wiki_placeholder.md +++ b/okf/bundles/stackoverflow/tables/posts_wiki_placeholder.md @@ -4,7 +4,7 @@ resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datas title: Stack Overflow Posts Wiki Placeholder description: Placeholder table for various Wiki-style posts within the Stack Overflow dataset. -tags: stackoverflow, posts, wiki, placeholder, community +tags: [stackoverflow, posts, wiki, placeholder, community] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:59:18+00:00' diff --git a/okf/bundles/stackoverflow/tables/stackoverflow_posts.md b/okf/bundles/stackoverflow/tables/stackoverflow_posts.md index 147bffc7..2b10f297 100644 --- a/okf/bundles/stackoverflow/tables/stackoverflow_posts.md +++ b/okf/bundles/stackoverflow/tables/stackoverflow_posts.md @@ -4,7 +4,7 @@ resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datas title: Stack Overflow Posts (Deprecated) description: A deprecated table containing Stack Overflow posts. Use the posts_answers or posts_questions tables instead. -tags: stackoverflow, posts, deprecated +tags: [stackoverflow, posts, deprecated] status: deprecated generated: by: reference_agent/gemini-2.5-flash diff --git a/okf/bundles/stackoverflow/tables/users.md b/okf/bundles/stackoverflow/tables/users.md index 08efa285..0f909674 100644 --- a/okf/bundles/stackoverflow/tables/users.md +++ b/okf/bundles/stackoverflow/tables/users.md @@ -3,7 +3,7 @@ type: BigQuery Table resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datasets/stackoverflow/tables/users title: Stack Overflow Users description: Contains information about registered users on the Stack Overflow platform. -tags: stackoverflow, users, community, reputation +tags: [stackoverflow, users, community, reputation] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:51:02+00:00' diff --git a/okf/bundles/stackoverflow/tables/votes.md b/okf/bundles/stackoverflow/tables/votes.md index 3114e123..0f29b07b 100644 --- a/okf/bundles/stackoverflow/tables/votes.md +++ b/okf/bundles/stackoverflow/tables/votes.md @@ -3,7 +3,7 @@ type: BigQuery Table resource: https://bigquery.googleapis.com/v2/projects/bigquery-public-data/datasets/stackoverflow/tables/votes title: Stack Overflow Votes description: Records all votes cast on Stack Overflow posts. -tags: Stack Overflow, votes, posts, community +tags: [Stack Overflow, votes, posts, community] generated: by: reference_agent/gemini-2.5-flash at: '2026-07-10T22:51:18+00:00'