{"adoption": {"forks": 347, "observed_at": "2026-08-28T04:05:21.632617+00:00", "stars": 1681}, "canonical_url": "https://ross.abutalabs.com/products/scws", "card": {"archived": false, "artifact_type": "library", "description": "开源免费的简易中文分词系统，PHP分词的上乘之选！", "domain": ["developer-tools"], "enriched": true, "function": ["nlp", "search-engine", "parser", "cli"], "health_score": 27, "homepage": "http://www.xunsearch.com/scws/", "language": "PHP", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["hightman/scws"], "name": "hightman/scws", "platform": ["windows", "php", "cpp", "c", "cli"], "pushed_at": "2025-03-19T16:00:21+00:00", "repo": "hightman/scws", "stars": 1681, "tags": ["chinese-word-segmentation", "text-segmentation", "php-extension", "dictionary-based", "keyword-extraction", "full-text-search", "natural-language-processing", "search", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["segment Chinese text into words for search indexing", "extract keywords from Chinese documents in PHP", "tokenize Chinese text from the command line", "build a small Chinese full-text search engine", "split Chinese strings into words for NLP preprocessing", "embed a lightweight C segmentation library into an application"], "what_it_is": "SCWS (Simple Chinese Word Segmentation) is a dictionary-based mechanical Chinese word segmentation engine written in pure C, with no external dependencies, supporting GBK and UTF-8 encodings. It ships as a C library (libscws), a command-line tool, and a PHP extension for fast tokenization of Chinese text.", "when_to_avoid": ["you need state-of-the-art accuracy on complex modern Chinese text", "you want a pure PHP solution without compiling C extensions", "you need segmentation for languages other than Chinese"], "when_to_choose": ["you need fast, dependency-free Chinese word segmentation in C or PHP", "you are building a small search engine or keyword extractor for Chinese text", "you want a mature, lightweight tokenizer without heavy ML dependencies"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scws", "repo": "hightman/scws", "role": "main", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:21.632617+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:41:25.547504+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d83779d01988b9f1eb69bbbe0a07d39a21ead173a0f7f600ba7cf649a8b018ae", "fetched_at": "2026-08-28T04:05:21.632617+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hightman/scws"}, {"content_hash": "14e1ad8d42297ff96f0fc49b7cfe8d1a6684f8123544b9551c866282416683c4", "fetched_at": "2026-08-29T11:14:35.418093+00:00", "kind": "homepage", "missing": false, "url": "http://www.xunsearch.com/scws/"}, {"content_hash": "bfc8c7391ec379c33e79f83fbb7bd9a3446002c598eb3778e967968874d35cea", "fetched_at": "2026-08-29T11:14:35.427672+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/docs.php"}, {"content_hash": "1d8b5bbb1f6d14ce64ee9a0a4831cdf93b346772a24d38f28322ffeff4d50bee", "fetched_at": "2026-08-29T11:14:35.430869+00:00", "kind": "site_page", "missing": false, "url": "https://www.xunsearch.com/scws/about.php"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 12, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5578, "days_push": 532, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}