{"adoption": {"forks": 503, "observed_at": "2026-08-28T04:07:00.632955+00:00", "stars": 2555}, "canonical_url": "https://ross.abutalabs.com/products/parquet-format", "card": {"archived": false, "artifact_type": "dataset", "description": "Apache Parquet Format", "domain": ["big-data", "analytics", "databases", "files"], "enriched": true, "function": ["serialization", "compression", "file-system", "documentation"], "health_score": 98, "homepage": "https://parquet.apache.org/", "language": "Thrift", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["apache/parquet-format"], "name": "apache/parquet-format", "platform": ["cross-platform", "jvm", "python", "cpp", "rust", "go"], "pushed_at": "2026-08-19T11:32:55+00:00", "repo": "apache/parquet-format", "stars": 2555, "tags": ["columnar-storage", "file-format-specification", "thrift", "hadoop-ecosystem", "data-lake", "olap", "data-engineering"], "topics": ["parquet", "apache", "parquet-format"], "urls": [], "use_cases": ["implement a parquet reader or writer in a new language", "understand the parquet file format specification", "generate thrift code for parquet metadata structures", "check how nested data is encoded in parquet", "verify compatibility of a parquet implementation against the spec"], "what_it_is": "The official specification repository for the Apache Parquet columnar data file format, including the Thrift definitions of the metadata structures needed to read and write Parquet files. It defines the format itself rather than providing an implementation, which live in language-specific projects like parquet-java.", "when_to_avoid": ["you just want to read or write Parquet files in an application - use a language implementation like parquet-java, pyarrow, or parquet-rs instead", "you need a runnable library or CLI tool - this repository contains only specifications and Thrift definitions"], "when_to_choose": ["you are building or validating a Parquet implementation and need the authoritative format spec", "you need the Thrift IDL definitions to generate metadata serialization code", "you want to understand Parquet encoding, compression, or nested data layout at the format level"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/parquet-format", "repo": "apache/parquet-format", "role": "main", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.632955+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:23:43.678692+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b82cd77a9897e51b10c98a569ed947765e7e6472278e20b881f0a5edf7b25e40", "fetched_at": "2026-08-28T04:07:00.632955+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/parquet-format"}, {"content_hash": "5d7913adb12e4181740fd39ad9f395433f56a2bc1b6626b5691f1415f4fd472c", "fetched_at": "2026-08-29T10:06:21.130711+00:00", "kind": "homepage", "missing": false, "url": "https://parquet.apache.org/"}, {"content_hash": "ffd29d8c787e8b3768ecefc44bfaf9f6424547f978f5a9a9fe35cca34e28f51d", "fetched_at": "2026-08-29T10:06:21.167841+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/docs"}, {"content_hash": "062c8b637316371cda2cceccafd35d6fde3979e10fe70f7a914c229dd804f4cc", "fetched_at": "2026-08-29T10:06:21.199737+00:00", "kind": "site_page", "missing": false, "url": "https://parquet.apache.org/blog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 100, "rhythm": 56}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4467, "days_push": 14, "days_rel": 81, "gap_med": 224.0, "n_releases_24m": 3}, "score": 84, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}