{"adoption": {"forks": 221, "observed_at": "2026-08-28T04:04:01.556460+00:00", "stars": 1218}, "canonical_url": "https://ross.abutalabs.com/products/data-warehouse-learning", "card": {"archived": false, "artifact_type": "learning-resource", "description": "【2026最新版】 大数据 数据分析 电商系统 实时数仓 离线数仓 数据湖 建设方案及实战代码，涉及组件 #flink #paimon #doris #seatunnel #dolphinscheduler #datart #dinky #hudi #iceberg。", "domain": ["big-data", "analytics", "e-commerce", "tutorials"], "enriched": true, "function": ["etl", "streaming", "database", "data-visualization", "workflow-automation"], "health_score": 68, "homepage": null, "language": "Java", "license": "Artistic-2.0", "license_family": "other", "maturity": "active", "member_repos": ["MrSuiChuan/data-warehouse-learning"], "name": "MrSuiChuan/data-warehouse-learning", "platform": ["jvm", "cloud"], "pushed_at": "2026-04-26T04:21:27+00:00", "repo": "MrSuiChuan/data-warehouse-learning", "stars": 1218, "tags": ["data-warehouse", "real-time-data-warehouse", "offline-data-warehouse", "data-lake", "flink", "doris", "paimon", "hudi", "iceberg", "seatunnel", "dolphinscheduler", "dinky", "datart", "superset", "kafka", "mysql", "ecommerce-analytics", "chinese", "data-engineering", "docker", "linux"], "topics": ["datart", "dinky", "dolphinscheduler", "doris", "flink", "hudi", "iceberg", "paimon", "seatunnel"], "urls": [], "use_cases": ["learn to build a real-time data warehouse with flink and doris", "ecommerce data warehouse tutorial with example code", "compare paimon hudi and iceberg for data lakehouse", "practice offline data warehouse layering ods dwd dws ads", "learn seatunnel and dolphinscheduler for data sync and scheduling", "big data analytics project for portfolio", "build streaming etl pipelines with flinksql cdc"], "what_it_is": "A Chinese-language educational project teaching real-time and offline data warehouse construction for an e-commerce system, with hands-on code using Flink, Doris, Paimon, Hudi, Iceberg, SeaTunnel, DolphinScheduler, Dinky, and Datart. It covers the full ODS→DWD/DIM→DWS→ADS layered architecture with both batch and streaming pipelines.", "when_to_avoid": ["you need production-ready warehouse code for your own business", "you want a maintained library or framework rather than a tutorial project", "you do not read Chinese documentation"], "when_to_choose": ["you want a complete end-to-end data warehouse project with runnable code", "you are learning modern Chinese big-data stack components like Doris, Paimon, and Dinky", "you need reference implementations of both real-time and offline warehouse patterns on the same business logic"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/data-warehouse-learning", "repo": "MrSuiChuan/data-warehouse-learning", "role": "main", "score": 61}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:01.556460+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:17:01.930594+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8df71caa1b665db297dbae2fdc2a5eab92d8a0dc8d63d01e399bbf9235e5d5b7", "fetched_at": "2026-08-28T04:04:01.556460+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MrSuiChuan/data-warehouse-learning"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 79, "longevity": 65, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 914, "days_push": 129, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 61, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}