{"adoption": {"forks": 588, "observed_at": "2026-08-28T04:05:02.358853+00:00", "stars": 1552}, "canonical_url": "https://ross.abutalabs.com/products/mongo-hadoop", "card": {"archived": true, "artifact_type": "library", "description": "MongoDB Connector for Hadoop", "domain": ["databases", "big-data"], "enriched": true, "function": ["etl", "database-driver", "serialization"], "health_score": 10, "homepage": null, "language": "Java", "license": null, "license_family": "other", "maturity": "abandoned", "member_repos": ["mongodb/mongo-hadoop"], "name": "mongodb/mongo-hadoop", "platform": ["jvm", "self-hosted"], "pushed_at": "2022-01-28T19:28:04+00:00", "repo": "mongodb/mongo-hadoop", "stars": 1552, "tags": ["mongodb", "hadoop", "mapreduce", "bson", "spark", "hive", "pig", "end-of-life", "data-engineering"], "topics": [], "urls": [], "use_cases": ["read data from mongodb into hadoop mapreduce jobs", "write mapreduce output to mongodb", "process bson backup files from s3 or hdfs with spark", "query mongodb collections with hadoop streaming in python", "use mongodb documents in hive or pig", "export hadoop results as bson for mongorestore"], "what_it_is": "A Java library that lets MongoDB (or BSON backup files) serve as an input source or output destination for Hadoop MapReduce jobs, with integrations for Pig, Hive, Spark, Flume, and Hadoop Streaming. It is officially end-of-life with no further development or maintenance.", "when_to_avoid": ["starting any new project, since the connector is end-of-life", "you need support, bugfixes, or compatibility with modern hadoop, spark, or mongodb versions", "you want an actively maintained mongodb-to-big-data integration"], "when_to_choose": ["you maintain a legacy hadoop 1.x/2.x stack already using this connector", "you need to bridge old mapreduce, pig, or hive jobs with mongodb or bson files"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mongo-hadoop", "repo": "mongodb/mongo-hadoop", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.358853+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:12.995350+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "225e57adc111b0e49e6153a8d5bc74626219e6b3afe779d1f68f3778bdad90ba", "fetched_at": "2026-08-28T04:05:02.358853+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mongodb/mongo-hadoop"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5854, "days_push": 1678, "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}}