{"adoption": {"forks": 435, "observed_at": "2026-08-28T04:03:24.879599+00:00", "stars": 1057}, "canonical_url": "https://ross.abutalabs.com/products/spark-csv", "card": {"archived": true, "artifact_type": "library", "description": "CSV Data Source for Apache Spark 1.x", "domain": ["big-data", "files", "developer-tools"], "enriched": true, "function": ["parser", "serialization", "database"], "health_score": 10, "homepage": "http://databricks.com/", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["databricks/spark-csv"], "name": "databricks/spark-csv", "platform": ["jvm", "cross-platform"], "pushed_at": "2018-12-13T09:50:29+00:00", "repo": "databricks/spark-csv", "stars": 1057, "tags": ["csv", "spark", "spark-sql", "dataframes", "apache-spark", "deprecated", "scala-library", "data-engineering"], "topics": [], "urls": [], "use_cases": ["parse csv files as spark dataframes", "query csv data with spark sql", "load csv with custom delimiter and quote characters", "infer column types from csv files", "handle malformed csv rows with permissive or failfast parsing", "read csv files from hdfs or s3 in spark"], "what_it_is": "A Scala library providing a CSV data source for Apache Spark 1.x, allowing CSV files to be read and queried as Spark SQL DataFrames with configurable parsing options. Its functionality has been inlined into Apache Spark 2.x, so the package is in maintenance mode accepting only critical bug fixes.", "when_to_avoid": ["you use Spark 2.x or later, where CSV support is built in", "you need active development or new features"], "when_to_choose": ["you are stuck on Apache Spark 1.x and need CSV support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spark-csv", "repo": "databricks/spark-csv", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:24.879599+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:57:56.612388+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "786b048b62032a5d13a1e6c0a107dbe0e26fc714faf364f34daed83bafcbc63d", "fetched_at": "2026-08-28T04:03:24.879599+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-csv"}, {"content_hash": "cb7b033b67a1616bafdd946b8333d9ac4e4d3a2dd22051da41dc89b8d2331bfc", "fetched_at": "2026-08-29T12:59:32.336070+00:00", "kind": "homepage", "missing": false, "url": "http://databricks.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4292, "days_push": 2820, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}