{"adoption": {"forks": 456, "observed_at": "2026-08-28T04:05:01.989952+00:00", "stars": 1549}, "canonical_url": "https://ross.abutalabs.com/products/apache-spark-internals", "card": {"archived": false, "artifact_type": "learning-resource", "description": "The Internals of Apache Spark", "domain": ["big-data", "microservices", "tutorials"], "enriched": true, "function": ["documentation"], "health_score": 96, "homepage": "https://books.japila.pl/apache-spark-internals", "language": "Shell", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["japila-books/apache-spark-internals"], "name": "japila-books/apache-spark-internals", "platform": ["jvm", "python"], "pushed_at": "2026-07-18T21:39:41+00:00", "repo": "japila-books/apache-spark-internals", "stars": 1549, "tags": ["apache-spark", "spark-core", "online-book", "internals", "deep-dive", "data-engineering"], "topics": ["apache-spark", "spark", "book", "internals"], "urls": [], "use_cases": ["understand how Spark Core works internally", "learn Spark internals before a data engineering interview", "deep dive into Spark execution architecture", "study Spark source code behavior", "reference Spark Core concepts while debugging Spark jobs"], "what_it_is": "An open-source online book, 'The Internals of Spark Core', that deep-dives into Apache Spark's internal architecture and source code. It is part of Jacek Laskowski's 'The Internals Of' book series and is published via GitHub Pages.", "when_to_avoid": ["you need a beginner tutorial for getting started with Spark", "you need official API documentation", "you need hands-on exercises or a structured course"], "when_to_choose": ["you want a free, in-depth explanation of Spark Core internals", "you are an experienced Spark user moving to advanced/architecture topics", "you want a book-style reference tied to a specific Spark version"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/apache-spark-internals", "repo": "japila-books/apache-spark-internals", "role": "main", "score": 83}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:01.989952+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:23.020561+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "477d47e724a2a143c64f918ea6147c1b30b245a39532bce2084ebe58a1805ae6", "fetched_at": "2026-08-28T04:05:01.989952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/japila-books/apache-spark-internals"}, {"content_hash": "ea282025d4952ed1a69aadb6fd54919f83efaf1d707cce203b727ff244e596b2", "fetched_at": "2026-08-29T11:31:04.511023+00:00", "kind": "homepage", "missing": false, "url": "https://books.japila.pl/apache-spark-internals"}, {"content_hash": "2d482243b4940d1e951a10a482ada67f5013cbd99e5d07ee07af73d07c2eb2f6", "fetched_at": "2026-08-29T11:31:04.513605+00:00", "kind": "site_page", "missing": false, "url": "https://books.japila.pl/apache-spark-internals/features"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 100, "rhythm": 61}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4020, "days_push": 46, "days_rel": 46, "gap_med": 281, "n_releases_24m": 4}, "score": 83, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}