{"adoption": {"forks": 331, "observed_at": "2026-08-28T04:07:00.412552+00:00", "stars": 2549}, "canonical_url": "https://ross.abutalabs.com/products/pdfpig", "card": {"archived": false, "artifact_type": "library", "description": "Read and extract text and other content from PDFs in C# (port of PDFBox)", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "image-processing", "pdf-viewer"], "health_score": 100, "homepage": "https://github.com/UglyToad/PdfPig/wiki", "language": "C#", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["UglyToad/PdfPig"], "name": "UglyToad/PdfPig", "platform": ["dotnet", "cross-platform", "windows"], "pushed_at": "2026-08-26T17:44:21+00:00", "repo": "UglyToad/PdfPig", "stars": 2549, "tags": ["pdfbox-port", "text-extraction", "layout-analysis", "document-processing", "csharp", "netstandard", "alto-xml", "hocr", "pagexml", "natural-language-processing", "linux", "macos"], "topics": ["pdfbox", "pdf", "pdf-document", "csharp", "netstandard", "pdf-extractor", "pdf-document-processor", "pdf-files", "alto-xml", "hocr", "layout-analysis", "document-analysis", "page-xml", "pdf-generation"], "urls": [], "use_cases": ["extract text from pdf files in c#", "parse pdf documents in .net", "get word positions and letters from a pdf", "extract images from pdf pages", "read pdf forms and annotations", "perform document layout analysis on pdfs", "export pdf page content to alto or hocr", "create simple pdf documents programmatically"], "what_it_is": "PdfPig is a C#/.NET library for reading and extracting text, images, annotations, forms, and metadata from PDF files, ported from Apache PDFBox. It also provides document layout analysis tools and basic PDF creation capabilities.", "when_to_avoid": ["you need to extract tables directly (use Tabula Sharp or Camelot Sharp instead)", "you need to convert HTML or other formats to PDF", "you need to fill or modify PDF form values (forms are read-only)", "you need advanced PDF generation features beyond basic text and paths"], "when_to_choose": ["you need a permissive Apache-2.0 alternative to iText 7 (AGPL) or commercial libraries like SpirePDF", "you need letter-level position and size data for layout analysis", "you work in .NET and need PDF text/content extraction without native dependencies", "you need to read encrypted PDFs with a password"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdfpig", "repo": "UglyToad/PdfPig", "role": "main", "score": 91}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:00.412552+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:23:59.833930+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f9d693d93f47bf5bd69d0c200d0b50ef89bd597cf8a259e5f52414dccffa5e14", "fetched_at": "2026-08-28T04:07:00.412552+00:00", "kind": "readme", "missing": false, "url": "https://github.com/UglyToad/PdfPig"}, {"content_hash": "d83b9cad128561610deb10c79289dd2c1350513a01cc75061f6d1059586c08f4", "fetched_at": "2026-08-29T10:06:35.220220+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/UglyToad/PdfPig/wiki"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 75}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3219, "days_push": 7, "days_rel": 11, "gap_med": 94, "n_releases_24m": 8}, "score": 91, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}