{"adoption": {"forks": 150, "observed_at": "2026-08-28T04:03:38.239982+00:00", "stars": 1114}, "canonical_url": "https://ross.abutalabs.com/products/mammoth", "card": {"archived": false, "artifact_type": "library", "description": "Convert Word documents (.docx files) to HTML", "domain": ["files", "web-development", "developer-tools"], "enriched": true, "function": ["parser", "pdf"], "health_score": 78, "homepage": null, "language": "Python", "license": "BSD-2-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["mwilliamson/python-mammoth", "mwilliamson/mammoth.js"], "name": "Mammoth", "platform": ["python", "jvm", "dotnet", "browser", "cli", "cross-platform"], "pushed_at": "2026-08-09T13:59:23+00:00", "repo": "mwilliamson/python-mammoth", "stars": 1114, "tags": ["docx", "html-conversion", "word-documents", "document-conversion", "semantic-html", "nodejs"], "topics": [], "urls": [], "use_cases": ["convert docx to html", "extract clean html from word documents", "migrate word content to a cms or blog", "convert google docs exports to html", "programmatically parse docx files into semantic markup", "batch convert word documents to html from the command line"], "what_it_is": "Mammoth is a library and CLI tool that converts .docx Word documents (from Word, Google Docs, LibreOffice) into clean, semantic HTML by mapping document styles to HTML elements rather than copying visual formatting. It is available for JavaScript/Node.js, Python, Java, .NET, and WordPress, with a browser demo included.", "when_to_avoid": ["you need faithful reproduction of complex Word formatting and layout", "you must process untrusted documents without sanitizing the output, since Mammoth performs no sanitisation", "your documents rely heavily on text boxes, complex tables, or exotic styling"], "when_to_choose": ["you want simple, semantic HTML instead of a pixel-perfect copy of Word styling", "your documents use styles (headings, lists, tables) to convey structure", "you need conversion across multiple platforms (Node, Python, JVM, .NET, browser)"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/mwilliamson/python-mammoth", "repo": "mwilliamson/python-mammoth", "role": "main", "score": 75}, {"path": "/repos/mwilliamson/mammoth.js", "repo": "mwilliamson/mammoth.js", "role": "sdk", "score": 66}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.239982+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:46:18.568389+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1a4fcce486f2f302ecf5b4f02118d3b3983403c7a402940f38b0a7f182c0d864", "fetched_at": "2026-08-28T04:03:38.239982+00:00", "kind": "readme", "missing": false, "url": "https://github.com/mwilliamson/python-mammoth"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "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": 4658, "days_push": 24, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 75, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}