{"adoption": {"forks": 6686, "observed_at": "2026-08-28T04:12:00.734900+00:00", "stars": 35130}, "canonical_url": "https://ross.abutalabs.com/products/jieba", "card": {"archived": false, "artifact_type": "library", "description": "结巴中文分词", "domain": ["localization"], "enriched": true, "function": ["nlp", "parser", "search-engine"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["fxsjy/jieba"], "name": "fxsjy/jieba", "platform": ["python", "cross-platform"], "pushed_at": "2024-08-21T09:23:45+00:00", "repo": "fxsjy/jieba", "stars": 35130, "tags": ["chinese-word-segmentation", "text-segmentation", "tokenization", "traditional-chinese", "custom-dictionary", "hmm", "natural-language-processing", "search"], "topics": [], "urls": [], "use_cases": ["segment chinese text into words in python", "tokenize chinese text for search engine indexing", "add custom domain words to a chinese tokenizer", "do part-of-speech tagging for chinese sentences", "split chinese text for text analysis", "handle traditional chinese text segmentation", "detect new or out-of-vocabulary words in chinese text"], "what_it_is": "Jieba is the most popular Python library for Chinese word segmentation, supporting precise, full, search-engine, and PaddlePaddle-based segmentation modes. It includes traditional Chinese support, custom dictionaries, part-of-speech tagging, and new word detection via an HMM model.", "when_to_avoid": ["you need segmentation for languages other than Chinese", "you need state-of-the-art neural segmentation and are willing to run larger deep learning models", "you need actively developed features - the project is largely in maintenance mode"], "when_to_choose": ["you need reliable, battle-tested Chinese word segmentation in Python", "you want multiple segmentation modes including a search-engine-friendly mode", "you need custom dictionaries or traditional Chinese support", "you want a lightweight pure-Python solution with no heavy dependencies"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/jieba", "repo": "fxsjy/jieba", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:00.734900+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:27:10.139366+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e66ae3a3402ff49aba325bafe095b329db6bef48069c36d0015b9abc049174d2", "fetched_at": "2026-08-28T04:12:00.734900+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fxsjy/jieba"}, {"content_hash": "67b4f069641bbd74b45dbf9adb2ea4a2516624bc75fa886a53aa724d91aca97f", "fetched_at": "2026-08-29T07:48:03.005944+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/jieba/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 5086, "days_push": 742, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}