{"adoption": {"forks": 680, "observed_at": "2026-08-28T04:05:40.650492+00:00", "stars": 1818}, "canonical_url": "https://ross.abutalabs.com/products/word", "card": {"archived": false, "artifact_type": "library", "description": "Java分布式中文分词组件 - word分词", "domain": ["developer-tools"], "enriched": true, "function": ["nlp", "parser", "search-engine"], "health_score": 20, "homepage": null, "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["ysc/word"], "name": "ysc/word", "platform": ["jvm", "cross-platform"], "pushed_at": "2021-03-31T09:27:08+00:00", "repo": "ysc/word", "stars": 1818, "tags": ["chinese-word-segmentation", "text-similarity", "lucene-integration", "elasticsearch-plugin", "solr-integration", "ngram-model", "part-of-speech-tagging", "natural-language-processing", "search"], "topics": [], "urls": [], "use_cases": ["segment chinese text into words in java", "tokenize chinese for full-text search indexing", "extract named entities like person and place names from chinese text", "compute text similarity between chinese documents", "add chinese word segmentation to elasticsearch or solr", "count word frequency and tag part of speech in chinese text"], "what_it_is": "A Java distributed Chinese word segmentation library offering multiple dictionary-based segmentation algorithms with ngram-based disambiguation. It recognizes named entities, dates, and numbers, and integrates with Lucene, Solr, and ElasticSearch.", "when_to_avoid": ["you need segmentation for languages other than Chinese", "you require actively maintained software with recent updates", "you need deep-learning-based neural segmentation models"], "when_to_choose": ["you need Chinese word segmentation in a JVM application", "you want Lucene, Solr, or ElasticSearch integration out of the box", "you need custom user dictionaries and multiple segmentation algorithms"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/word", "repo": "ysc/word", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:40.650492+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:20:09.664728+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1ba4fd9cd635f08b672cfded8a7dcb7f0274b322edb6c95a6c9ac93e836e745e", "fetched_at": "2026-08-28T04:05:40.650492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ysc/word"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 4551, "days_push": 1981, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}