{"adoption": {"forks": 115, "observed_at": "2026-08-28T04:04:08.433222+00:00", "stars": 1251}, "canonical_url": "https://ross.abutalabs.com/products/wiktextract", "card": {"archived": false, "artifact_type": "library", "description": "Wiktionary dump file parser and multilingual data extractor", "domain": ["machine-learning"], "enriched": true, "function": ["parser", "nlp", "data-generation", "etl"], "health_score": 78, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["tatuylonen/wiktextract"], "name": "tatuylonen/wiktextract", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-12T08:56:58+00:00", "repo": "tatuylonen/wiktextract", "stars": 1251, "tags": ["wiktionary", "wikitext", "dictionary-data", "jsonl", "lua-templates", "linguistics", "corpus-extraction", "natural-language-processing", "dictionaries", "data-engineering"], "topics": ["wiktionary", "wiktionary-parser", "multilingual", "dictionary", "extractor", "parser", "scribunto", "lua", "wikitext", "templates"], "urls": [], "use_cases": ["extract structured dictionary data from Wiktionary dumps", "build machine translation dictionaries", "get word senses and inflections for NLP", "download multilingual word data as JSONL", "parse wikitext and expand Lua templates from Wiktionary", "create pronunciation and translation datasets for many languages"], "what_it_is": "A Python package and CLI tool that parses Wiktionary XML dump files and extracts structured dictionary data (glosses, translations, pronunciations, inflections) into JSONL format. It expands templates and Lua macros for high extraction quality across many languages.", "when_to_avoid": ["you only need a simple word list without rich linguistic detail", "you cannot run long extractions (hours to days) and pre-built data from kaikki.org suffices", "you need a dictionary API rather than offline dump processing"], "when_to_choose": ["you need high-quality structured Wiktionary data with expanded templates and Lua macros", "you want multilingual dictionary data for NLP, machine translation, or language generation", "you need inflection tables, translations, and pronunciations in machine-readable JSONL"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/wiktextract", "repo": "tatuylonen/wiktextract", "role": "main", "score": 76}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.433222+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:07:41.946575+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7b34d1552dd7a8aa5f555722446961cb8e6b881f7126b44f57623ebea51f08c3", "fetched_at": "2026-08-28T04:04:08.433222+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatuylonen/wiktextract"}, {"content_hash": "eb47f99c75257cfa849d2c15a094bb5042f5b657199296d0517d32fb7b87339a", "fetched_at": "2026-08-29T12:18:39.003723+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/wiktextract/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2865, "days_push": 21, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 76, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}