{"adoption": {"forks": 213, "observed_at": "2026-08-28T04:05:10.745063+00:00", "stars": 1608}, "canonical_url": "https://ross.abutalabs.com/products/pdflayouttextstripper", "card": {"archived": false, "artifact_type": "library", "description": "Converts a pdf file into a text file while keeping the layout of the original pdf. Useful to extract the content from a table in a pdf file for instance. This is a subclass of PDFTextStripper class (from the Apache PDFBox library).", "domain": ["pdf", "files"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 20, "homepage": "https://jonathanlink.ch/PDFLayoutTextStripper.html", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["JonathanLink/PDFLayoutTextStripper"], "name": "JonathanLink/PDFLayoutTextStripper", "platform": ["jvm", "cross-platform", "cli"], "pushed_at": "2023-12-17T17:19:17+00:00", "repo": "JonathanLink/PDFLayoutTextStripper", "stars": 1608, "tags": ["pdfbox", "layout-preserving-text-extraction", "table-extraction", "form-extraction", "java-library", "data-engineering"], "topics": ["layout", "text", "java", "pdf", "extract", "data-extraction", "pdfbox"], "urls": [], "use_cases": ["extract table data from a pdf", "convert pdf to text keeping layout", "parse pdf forms into text", "extract bank statement data from pdf", "parse pdf timetables for an app", "pdf data extraction in java"], "what_it_is": "A Java library that converts PDF files to text while preserving the original layout, built as a subclass of Apache PDFBox's PDFTextStripper. It is particularly useful for extracting data from tables and forms embedded in PDF documents.", "when_to_avoid": ["you need plain text without layout fidelity (PDFBox's default stripper suffices)", "you need OCR for scanned/image-only PDFs", "you work outside the Java/JVM ecosystem"], "when_to_choose": ["you need layout-aware text extraction from PDFs on the JVM", "you want to pull tabular or form data out of PDFs programmatically", "you already use Apache PDFBox and need better text positioning"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdflayouttextstripper", "repo": "JonathanLink/PDFLayoutTextStripper", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.745063+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:51:19.862090+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "302c708b3f2e53843096fd43b7f75a3f455a407d250911ef14652a0dbf640b64", "fetched_at": "2026-08-28T04:05:10.745063+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JonathanLink/PDFLayoutTextStripper"}, {"content_hash": "a1b70c9a29cbdbcf7179157a51b1fec55d5b2681369824dfdbe871e29f4ddc93", "fetched_at": "2026-08-29T11:23:25.914928+00:00", "kind": "homepage", "missing": false, "url": "https://jonathanlink.ch/PDFLayoutTextStripper.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "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": 3979, "days_push": 990, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}