{"adoption": {"forks": 257, "observed_at": "2026-08-28T04:04:33.309280+00:00", "stars": 1376}, "canonical_url": "https://ross.abutalabs.com/products/jieba-php", "card": {"archived": false, "artifact_type": "library", "description": "\"結巴\"中文分詞：做最好的 PHP 中文分詞、中文斷詞組件。 / \"Jieba\" (Chinese for \"to stutter\") Chinese text segmentation: built to be the best PHP Chinese word segmentation module.", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "parser", "search-engine"], "health_score": 68, "homepage": null, "language": "PHP", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["fukuball/jieba-php"], "name": "fukuball/jieba-php", "platform": ["php", "cross-platform"], "pushed_at": "2025-12-16T03:39:39+00:00", "repo": "fukuball/jieba-php", "stars": 1376, "tags": ["chinese-text-segmentation", "word-segmentation", "jieba", "cjk", "traditional-chinese", "tf-idf", "pos-tagging", "hmm", "natural-language-processing", "search"], "topics": ["nlp", "natural-language-processing", "chinese-text-segmentation", "machine-learning"], "urls": [], "use_cases": ["segment chinese text into words in php", "tokenize chinese sentences for search indexing", "extract keywords from chinese text with tf-idf", "part-of-speech tagging for chinese text", "support traditional chinese word segmentation", "add custom domain words to a chinese dictionary", "preprocess chinese text for nlp pipelines"], "what_it_is": "A PHP library for Chinese word segmentation (jieba), ported from the Python jieba project and now independently maintained. It supports precise, full, and search-engine segmentation modes, traditional Chinese, custom dictionaries, TF-IDF keyword extraction, and part-of-speech tagging.", "when_to_avoid": ["you need state-of-the-art segmentation accuracy that LLM-based tokenizers provide", "your stack is not PHP (use the original Python jieba or other ports)", "memory-constrained environments, since the dictionary requires a large memory limit"], "when_to_choose": ["you need fast, cheap, dependency-light Chinese segmentation in a PHP application", "you need search-engine-mode tokenization for building inverted indexes", "you need traditional Chinese or custom dictionary support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/jieba-php", "repo": "fukuball/jieba-php", "role": "main", "score": 48}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:33.309280+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:40:29.957647+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cfc67b57a09beb2f59694fabb9e4255b34907a70e8910b3f8b2360fabdfbc419", "fetched_at": "2026-08-28T04:04:33.309280+00:00", "kind": "readme", "missing": false, "url": "https://github.com/fukuball/jieba-php"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 57, "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": 4150, "days_push": 260, "days_rel": 410, "gap_med": null, "n_releases_24m": 1}, "score": 48, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}