{"id":37085679,"url":"https://github.com/gambolputty/wiktionary-de-parser","last_synced_at":"2026-01-14T10:32:27.907Z","repository":{"id":45438300,"uuid":"180654378","full_name":"gambolputty/wiktionary-de-parser","owner":"gambolputty","description":"Extract data from German Wiktionary XML files.","archived":false,"fork":false,"pushed_at":"2025-11-16T13:48:42.000Z","size":426,"stargazers_count":26,"open_issues_count":3,"forks_count":8,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-11-16T14:41:26.470Z","etag":null,"topics":["data-extraction","dewiktionary","german","german-language","nlp","wiktionary","wiktionary-dump","wiktionary-parser"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gambolputty.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":"ggor","tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2019-04-10T19:57:39.000Z","updated_at":"2025-11-16T13:47:37.000Z","dependencies_parsed_at":"2024-02-09T23:31:28.268Z","dependency_job_id":"04ba808c-b73b-4be6-8884-59e40cfaf9c5","html_url":"https://github.com/gambolputty/wiktionary-de-parser","commit_stats":{"total_commits":115,"total_committers":3,"mean_commits":"38.333333333333336","dds":0.4,"last_synced_commit":"1927955a65947590f3978ca2367e926c0ad16b26"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gambolputty/wiktionary-de-parser","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gambolputty%2Fwiktionary-de-parser","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gambolputty%2Fwiktionary-de-parser/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gambolputty%2Fwiktionary-de-parser/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gambolputty%2Fwiktionary-de-parser/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gambolputty","download_url":"https://codeload.github.com/gambolputty/wiktionary-de-parser/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gambolputty%2Fwiktionary-de-parser/sbom","scorecard":{"id":417765,"data":{"date":"2025-08-11","repo":{"name":"github.com/gambolputty/wiktionary-de-parser","commit":"ded59062b2cf50449e934856fadd250ff03f1514"},"scorecard":{"version":"v5.2.1-40-gf6ed084d","commit":"f6ed084d17c9236477efd66e5b258b9d4cc7b389"},"score":2.4,"checks":[{"name":"Binary-Artifacts","score":10,"reason":"no binaries found in the repo","details":null,"documentation":{"short":"Determines if the project has generated executable (binary) artifacts in the source repository.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#binary-artifacts"}},{"name":"Dangerous-Workflow","score":-1,"reason":"no workflows found","details":null,"documentation":{"short":"Determines if the project's GitHub Action workflows avoid dangerous patterns.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#dangerous-workflow"}},{"name":"SAST","score":0,"reason":"no SAST tool detected","details":["Warn: no pull requests merged into dev branch"],"documentation":{"short":"Determines if the project uses static code analysis.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#sast"}},{"name":"Pinned-Dependencies","score":-1,"reason":"no dependencies found","details":null,"documentation":{"short":"Determines if the project has declared and pinned the dependencies of its build process.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#pinned-dependencies"}},{"name":"Token-Permissions","score":-1,"reason":"No tokens found","details":null,"documentation":{"short":"Determines if the project's workflows follow the principle of least privilege.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#token-permissions"}},{"name":"Maintained","score":0,"reason":"0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project is \"actively maintained\".","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#maintained"}},{"name":"Code-Review","score":0,"reason":"Found 0/30 approved changesets -- score normalized to 0","details":null,"documentation":{"short":"Determines if the project requires human code review before pull requests (aka merge requests) are merged.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#code-review"}},{"name":"Packaging","score":-1,"reason":"packaging workflow not detected","details":["Warn: no GitHub/GitLab publishing workflow detected."],"documentation":{"short":"Determines if the project is published as a package that others can easily download, install, easily update, and uninstall.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#packaging"}},{"name":"CII-Best-Practices","score":0,"reason":"no effort to earn an OpenSSF best practices badge detected","details":null,"documentation":{"short":"Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#cii-best-practices"}},{"name":"Security-Policy","score":0,"reason":"security policy file not detected","details":["Warn: no security policy file detected","Warn: no security file to analyze","Warn: no security file to analyze","Warn: no security file to analyze"],"documentation":{"short":"Determines if the project has published a security policy.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#security-policy"}},{"name":"License","score":10,"reason":"license file detected","details":["Info: project has a license file: LICENSE.txt:0","Info: FSF or OSI recognized license: MIT License: LICENSE.txt:0"],"documentation":{"short":"Determines if the project has defined a license.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#license"}},{"name":"Fuzzing","score":0,"reason":"project is not fuzzed","details":["Warn: no fuzzer integrations found"],"documentation":{"short":"Determines if the project uses fuzzing.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#fuzzing"}},{"name":"Signed-Releases","score":-1,"reason":"no releases found","details":null,"documentation":{"short":"Determines if the project cryptographically signs release artifacts.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#signed-releases"}},{"name":"Branch-Protection","score":0,"reason":"branch protection not enabled on development/release branches","details":["Warn: branch protection not enabled for branch 'main'"],"documentation":{"short":"Determines if the default and release branches are protected with GitHub's branch protection settings.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#branch-protection"}},{"name":"Vulnerabilities","score":5,"reason":"5 existing vulnerabilities detected","details":["Warn: Project is vulnerable to: GHSA-33p9-3p43-82vq","Warn: Project is vulnerable to: GHSA-9hjg-9r4m-mvj7","Warn: Project is vulnerable to: GHSA-7cx3-6m66-7c5m","Warn: Project is vulnerable to: GHSA-48p4-8xcf-vxj5","Warn: Project is vulnerable to: GHSA-pq67-6m6q-mj2v"],"documentation":{"short":"Determines if the project has open, known unfixed vulnerabilities.","url":"https://github.com/ossf/scorecard/blob/f6ed084d17c9236477efd66e5b258b9d4cc7b389/docs/checks.md#vulnerabilities"}}]},"last_synced_at":"2025-08-19T00:21:49.842Z","repository_id":45438300,"created_at":"2025-08-19T00:21:49.842Z","updated_at":"2025-08-19T00:21:49.842Z"},"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28417466,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T10:25:19.714Z","status":"ssl_error","status_checked_at":"2026-01-14T10:22:49.371Z","response_time":107,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["data-extraction","dewiktionary","german","german-language","nlp","wiktionary","wiktionary-dump","wiktionary-parser"],"created_at":"2026-01-14T10:32:27.320Z","updated_at":"2026-01-14T10:32:27.902Z","avatar_url":"https://github.com/gambolputty.png","language":"Python","funding_links":["https://ko-fi.com/ggor"],"categories":[],"sub_categories":[],"readme":"# wiktionary-de-parser\n\nA Python module to extract data from German Wiktionary XML files (for Python 3.11+).\n\n## Features\n\n- Extracts _IPA transcriptions_, _hyphenation_, _language_, _part of speech_ information (basic), _genus_ and _flexion tables_ of a word.\n- Yields per entry, not per page (a page can have multiple entries/ words can have different meanings)\n\n## Installation\n\n`pip install wiktionary-de-parser`\n\nOr with [Poetry](https://python-poetry.org/):\n\n`poetry add wiktionary-de-parser`\n\n## Usage\n\n### Loading the XML dump file\n```python\nfrom wiktionary_de_parser import WiktionaryParser\nfrom wiktionary_de_parser.dump_processor import WiktionaryDump\n\n# To download the dump file, specify the directory where the\n# dump file should be stored.\ndump = WiktionaryDump(dump_dir_path=\"directory-of-dump-file\")\n\n# This will download \"dewiktionary-latest-pages-articles-multistream.xml.bz2\" to\n# the directory specified in `dump_dir_path`.\ndump.download_dump()\n\n# Alternatively you can specify a different dump file to download.\ndump = WiktionaryDump(\n    dump_dir_path=\"directory-of-dump-file\",\n    dump_download_url=\"url-to-dump-file.xml.bz2\",\n)\ndump.download_dump()\n\n# If you already have the dump file locally, specify the path to the file.\ndump = WiktionaryDump(dump_file_path=\"path-to-dump-file.xml.bz2\")\ndump.download_dump()\n```\n\n### Parsing the dump file\n```python\nfrom pprint import pprint\nfrom wiktionary_de_parser import WiktionaryParser\n\n# ... (see above)\n\nparser = WiktionaryParser()\n\nfor page in dump.pages():\n    # Skip redirects\n    if page.redirect_to:\n        continue\n\n    if page.name == \"Abend\":\n        # Parse all entries for \"Abend\"\n        for entry in parser.entries_from_page(page):\n            results = parser.parse_entry(entry)\n            pprint(results)\n        break\n```\n\n## Output\nAll page entries for \"Abend\":\n\n```python\nParsedWiktionaryPageEntry(\n    name=\"Abend\",\n    hyphenation=[\"Abend\"],\n    flexion={\n        \"Genus\": \"m\",\n        \"Nominativ Singular\": \"Abend\",\n        \"Nominativ Plural\": \"Abende\",\n        \"Genitiv Singular\": \"Abends\",\n        \"Genitiv Plural\": \"Abende\",\n        \"Dativ Singular\": \"Abend\",\n        \"Dativ Plural\": \"Abenden\",\n        \"Akkusativ Singular\": \"Abend\",\n        \"Akkusativ Plural\": \"Abende\",\n    },\n    ipa=[\"ˈaːbn̩t\", \"ˈaːbm̩t\"],\n    language=Language(lang=\"Deutsch\", lang_code=\"de\"),\n    lemma=Lemma(lemma=\"Abend\", reference_type=\u003cReferenceType.NONE: 'none'\u003e),\n    pos={\"Substantiv\": []},\n    rhymes=[\"aːbn̩t\"],\n)\nParsedWiktionaryPageEntry(\n    name=\"Abend\",\n    hyphenation=[\"Abend\"],\n    flexion=None,\n    ipa=[\"ˈaːbn̩t\"],\n    language=Language(lang=\"Deutsch\", lang_code=\"de\"),\n    lemma=Lemma(lemma=\"Abend\", reference_type=\u003cReferenceType.NONE: 'none'\u003e),\n    pos={\"Substantiv\": [\"Nachname\"]},\n    rhymes=[\"aːbn̩t\"],\n)\nParsedWiktionaryPageEntry(\n    name=\"Abend\",\n    hyphenation=[\"Abend\"],\n    flexion=None,\n    ipa=[\"ˈaːbn̩t\", \"ˈaːbm̩t\"],\n    language=Language(lang=\"Deutsch\", lang_code=\"de\"),\n    lemma=Lemma(lemma=\"Abend\", reference_type=\u003cReferenceType.NONE: 'none'\u003e),\n    pos={\"Substantiv\": [\"Toponym\"]},\n    rhymes=[\"aːbn̩t\"],\n)\n\n```\n\n## Development\nThis project uses [Poetry](https://python-poetry.org/).\n\n1. Install [Poetry](https://python-poetry.org/).\n2. Clone this repository\n3. Run `poetry install` inside of the project folder to install dependencies.\n4. There is a `notebook.ipynb` to test the parser.\n5. Run `poetry run pytest` to run tests.\n\n## License\n\n[MIT](https://github.com/gambolputty/wiktionary-de-parser/blob/master/LICENSE.md) © Gregor Weichbrodt\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgambolputty%2Fwiktionary-de-parser","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgambolputty%2Fwiktionary-de-parser","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgambolputty%2Fwiktionary-de-parser/lists"}