{ "info": { "author": "Thibault Cl\u00e9rice", "author_email": "leponteineptique@gmail.com", "bugtrack_url": null, "classifiers": [], "description": ".. image:: https://coveralls.io/repos/github/PonteIneptique/archives_org_latin_toolkit/badge.svg?branch=master\n :target: https://coveralls.io/github/PonteIneptique/archives_org_latin_toolkit?branch=master\n.. image:: https://travis-ci.org/PonteIneptique/archives_org_latin_toolkit.svg?branch=master\n :target: https://travis-ci.org/PonteIneptique/archives_org_latin_toolkit\n.. image:: https://badge.fury.io/py/archives_org_latin_toolkit.svg\n :target: https://badge.fury.io/py/archives_org_latin_toolkit\n.. image:: https://readthedocs.org/projects/archives-org-latin-toolkit/badge/?version=latest\n :alt: Documentation\n :target: https://archives-org-latin-toolkit.readthedocs.io\n.. image:: https://zenodo.org/badge/68894385.svg\n :target: https://zenodo.org/badge/latestdoi/68894385\n\nWhat ?\n######\n\nThis piece of software is intended to be used with the 11K Latin Texts produced by David Bamman ( http://www.cs.cmu.edu/~dbamman/latin.html ). \\\nIt supports only the plain text formats and the metadata github repo CSV file. This has been tested with *Python3* only. \\\nI welcome any new functions or backward compatibility support.\n\nHow to install ?\n################\n\n- **With development version:**\n - Clone the repository : :code:`git clone https://github.com/ponteineptique/archives_org_latin_toolkit.git`\n - Go to the directory : :code:`cd archives_org_latin_toolkit`\n - Install the source with develop option : :code:`python setup.py install`\n- **With pip:**\n - Install from pip : :code:`pip install archives_org_latin_toolkit`\n\nExample\n#######\n\nThe following example should run with the data in tests/test_data. The example can be run with :code:`python example.py`\n\n.. code-block:: python\n\n # We import the main classes from the module\n from archives_org_latin_toolkit import Repo, Metadata\n from pprint import pprint\n\n # We initiate a Metadata object and a Repo object\n metadata = Metadata(\"./test/test_data/latin_metadata.csv\")\n # We want the text to be set in lowercase\n repo = Repo(\"./test/test_data/archive_org_latin/\", metadata=metadata, lowercase=True)\n\n # We define a list of token we want to search for\n tokens = [\"ecclesiastico\", \"ecclesia\", \"ecclesiis\", \""\"]\n\n # We instantiate a result storage\n results = []\n\n # We iter over text having those tokens :\n # Note that we need to \"unzip\" the list\n for text_matching in repo.find(*tokens):\n\n # For each text, we iter over embeddings found in the text\n # We want 3 words left, 3 words right,\n # and we want to keep the original token (Default behaviour)\n for embedding in text_matching.find_embedding(*tokens, window=3, ignore_center=False):\n # We add it to the results\n results.append(embedding)\n\n # We print the result (list of list of strings)\n pprint(results)\n\n", "description_content_type": null, "docs_url": null, "download_url": "UNKNOWN", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "http://github.com/ponteineptique/archives_org_latin", "keywords": null, "license": "MIT", "maintainer": null, "maintainer_email": null, "name": "archives_org_latin_toolkit", "package_url": "https://pypi.org/project/archives_org_latin_toolkit/", "platform": "UNKNOWN", "project_url": "https://pypi.org/project/archives_org_latin_toolkit/", "project_urls": { "Download": "UNKNOWN", "Homepage": "http://github.com/ponteineptique/archives_org_latin" }, "release_url": "https://pypi.org/project/archives_org_latin_toolkit/0.0.2/", "requires_dist": null, "requires_python": null, "summary": "Tools to parse and search across http://www.cs.cmu.edu/~dbamman/latin.html", "version": "0.0.2" }, "last_serial": 2357162, "releases": { "0.0.1": [ { "comment_text": "", "digests": { "md5": "4ff522231b46815403f22f32dbc82b3a", "sha256": "94b9065c1f8444975096f5de1640166914dc565bb1cb8ad2f5f7385cf0fd6b18" }, "downloads": -1, "filename": "archives_org_latin_toolkit-0.0.1.tar.gz", "has_sig": false, "md5_digest": "4ff522231b46815403f22f32dbc82b3a", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 4990, "upload_time": "2016-09-22T08:53:48", "url": "https://files.pythonhosted.org/packages/ca/90/ad0f2446e9cbda1314ca0d3098275d9a0e9102ed1afedd28c78ecabd199a/archives_org_latin_toolkit-0.0.1.tar.gz" } ], "0.0.2": [ { "comment_text": "", "digests": { "md5": "88dc885a5eee93bb1563c775e3efe29d", "sha256": "130077d8d151059c19b076c09acdbbd22055d614dfbab7e46cc3df34d0d368fe" }, "downloads": -1, "filename": "archives_org_latin_toolkit-0.0.2.tar.gz", "has_sig": false, "md5_digest": "88dc885a5eee93bb1563c775e3efe29d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 5332, "upload_time": "2016-09-22T11:59:47", "url": "https://files.pythonhosted.org/packages/a9/b3/ba968b2bba1712c88303c0e0f67ef015f07ff330e71a532d1efe007dd586/archives_org_latin_toolkit-0.0.2.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "88dc885a5eee93bb1563c775e3efe29d", "sha256": "130077d8d151059c19b076c09acdbbd22055d614dfbab7e46cc3df34d0d368fe" }, "downloads": -1, "filename": "archives_org_latin_toolkit-0.0.2.tar.gz", "has_sig": false, "md5_digest": "88dc885a5eee93bb1563c775e3efe29d", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 5332, "upload_time": "2016-09-22T11:59:47", "url": "https://files.pythonhosted.org/packages/a9/b3/ba968b2bba1712c88303c0e0f67ef015f07ff330e71a532d1efe007dd586/archives_org_latin_toolkit-0.0.2.tar.gz" } ] }