{
"info": {
"author": "Philip Koehn, Josh Schroeder, Digital Silk Road, Linas Valiukas",
"author_email": "lvaliukas@cyber.law.harvard.edu",
"bugtrack_url": null,
"classifiers": [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"Intended Audience :: Information Technology",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: GNU Lesser General Public License v3 (LGPLv3)",
"Natural Language :: Catalan",
"Natural Language :: Czech",
"Natural Language :: Danish",
"Natural Language :: Dutch",
"Natural Language :: English",
"Natural Language :: Finnish",
"Natural Language :: French",
"Natural Language :: German",
"Natural Language :: Greek",
"Natural Language :: Hungarian",
"Natural Language :: Icelandic",
"Natural Language :: Italian",
"Natural Language :: Latvian",
"Natural Language :: Norwegian",
"Natural Language :: Polish",
"Natural Language :: Portuguese",
"Natural Language :: Portuguese (Brazilian)",
"Natural Language :: Romanian",
"Natural Language :: Russian",
"Natural Language :: Slovak",
"Natural Language :: Slovenian",
"Natural Language :: Spanish",
"Natural Language :: Swedish",
"Natural Language :: Turkish",
"Operating System :: OS Independent",
"Programming Language :: Python",
"Programming Language :: Python :: 3.5",
"Programming Language :: Python :: 3.6",
"Programming Language :: Python :: 3.7",
"Programming Language :: Python :: Implementation :: PyPy",
"Topic :: Database",
"Topic :: Internet :: WWW/HTTP :: Indexing/Search",
"Topic :: Text Processing :: Indexing",
"Topic :: Text Processing :: Linguistic"
],
"description": "\nText to sentence splitter using heuristic algorithm by Philipp Koehn and Josh Schroeder.\n\nThis module allows splitting of text paragraphs into sentences. It is based on scripts developed by Philipp\nKoehn and Josh Schroeder for processing the `Europarl corpus `_.\n\nThe module is a port of `Lingua::Sentence Perl module `_ with\nsome extra additions (improved non-breaking prefix lists for some languages and added support for Danish,\nFinnish, Lithuanian, Norwegian (Bokm\u00e5l), Romanian, and Turkish).\n\n\n",
"description_content_type": "",
"docs_url": null,
"download_url": "",
"downloads": {
"last_day": -1,
"last_month": -1,
"last_week": -1
},
"home_page": "https://github.com/berkmancenter/mediacloud-sentence-splitter",
"keywords": "sentence splitter tokenization tokenizer tokenize",
"license": "LGPLv3",
"maintainer": "",
"maintainer_email": "",
"name": "sentence-splitter",
"package_url": "https://pypi.org/project/sentence-splitter/",
"platform": "any",
"project_url": "https://pypi.org/project/sentence-splitter/",
"project_urls": {
"Homepage": "https://github.com/berkmancenter/mediacloud-sentence-splitter"
},
"release_url": "https://pypi.org/project/sentence-splitter/1.4/",
"requires_dist": [
"regex (>=2017.12.12)"
],
"requires_python": ">=3.5",
"summary": "Text to sentence splitter using heuristic algorithm by Philipp Koehn and Josh Schroeder",
"version": "1.4"
},
"last_serial": 4695057,
"releases": {
"1.1": [
{
"comment_text": "",
"digests": {
"md5": "e18d81a7bf844eaa28713896ccaf72d6",
"sha256": "79c48aae8e7ddcc3c53f25c514051152a8fc2bc7a0f5049245baeac4d399933c"
},
"downloads": -1,
"filename": "sentence_splitter-1.1.tar.gz",
"has_sig": false,
"md5_digest": "e18d81a7bf844eaa28713896ccaf72d6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 30839,
"upload_time": "2017-12-22T18:47:36",
"url": "https://files.pythonhosted.org/packages/22/66/91135abdcdf401442858d290d0fed8b6057f4c947fdfa7103be56e3a2612/sentence_splitter-1.1.tar.gz"
}
],
"1.2": [
{
"comment_text": "",
"digests": {
"md5": "b19fecf3575c05dfa2826b5dc3f71e29",
"sha256": "7078cf4f30057f912e03f2bad65e54c1cee0a81f29e744632904c62bd7585b81"
},
"downloads": -1,
"filename": "sentence_splitter-1.2.tar.gz",
"has_sig": false,
"md5_digest": "b19fecf3575c05dfa2826b5dc3f71e29",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 30737,
"upload_time": "2017-12-22T19:13:01",
"url": "https://files.pythonhosted.org/packages/63/90/b65253e9df530d575f707ef50247a106b2bf4970f154766d8177a7836da2/sentence_splitter-1.2.tar.gz"
}
],
"1.3": [
{
"comment_text": "",
"digests": {
"md5": "fc3f9559d51cc6b1186b2674beff2a6d",
"sha256": "2c628fb88c8c1a5bc754d52c3b9ad5e116081bb7f8051f517e2fb86972a4ca87"
},
"downloads": -1,
"filename": "sentence_splitter-1.3-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "fc3f9559d51cc6b1186b2674beff2a6d",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.5",
"size": 44997,
"upload_time": "2019-01-14T16:15:07",
"url": "https://files.pythonhosted.org/packages/3a/c3/e33b77c8592f08269ef1d4ce943c05eedb365c067d8d36ffa305eed60dd7/sentence_splitter-1.3-py2.py3-none-any.whl"
},
{
"comment_text": "",
"digests": {
"md5": "3af9f635758ab466185b2558d5ce1dea",
"sha256": "338ff7daedcca02656e37e289f56feb242784c6379f42046445b6376b3775892"
},
"downloads": -1,
"filename": "sentence_splitter-1.3.tar.gz",
"has_sig": false,
"md5_digest": "3af9f635758ab466185b2558d5ce1dea",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.5",
"size": 30614,
"upload_time": "2019-01-14T16:15:09",
"url": "https://files.pythonhosted.org/packages/ad/57/ce2d0eaaf349c3cdd9177b8fafdd4ed183e21b1fa577c9a23252fa6f7bb2/sentence_splitter-1.3.tar.gz"
}
],
"1.4": [
{
"comment_text": "",
"digests": {
"md5": "2997a3de186228e9d434f92bceb751ec",
"sha256": "5645a3ad9c348e4287f4bc73bd573d92dccd4139042fddd51fff0591f1376763"
},
"downloads": -1,
"filename": "sentence_splitter-1.4-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "2997a3de186228e9d434f92bceb751ec",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.5",
"size": 44998,
"upload_time": "2019-01-14T17:11:23",
"url": "https://files.pythonhosted.org/packages/4a/ae/3bd609c760d57849d7ddf223762f1881f3c4df6467f4eadb3a33652b7e0d/sentence_splitter-1.4-py2.py3-none-any.whl"
},
{
"comment_text": "",
"digests": {
"md5": "a58c1f759d0b8ce0fe1e0c99b150ecb1",
"sha256": "3d1d773d07cc733ca2955aa87d0fa1c0a7274c6bdeec1daac5c5e92efb512f63"
},
"downloads": -1,
"filename": "sentence_splitter-1.4.tar.gz",
"has_sig": false,
"md5_digest": "a58c1f759d0b8ce0fe1e0c99b150ecb1",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.5",
"size": 30607,
"upload_time": "2019-01-14T17:11:25",
"url": "https://files.pythonhosted.org/packages/20/b3/86b431fe7002ba006c08b8559d2ad78e1153bfc515a453cc96d2f55a2c40/sentence_splitter-1.4.tar.gz"
}
]
},
"urls": [
{
"comment_text": "",
"digests": {
"md5": "2997a3de186228e9d434f92bceb751ec",
"sha256": "5645a3ad9c348e4287f4bc73bd573d92dccd4139042fddd51fff0591f1376763"
},
"downloads": -1,
"filename": "sentence_splitter-1.4-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "2997a3de186228e9d434f92bceb751ec",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.5",
"size": 44998,
"upload_time": "2019-01-14T17:11:23",
"url": "https://files.pythonhosted.org/packages/4a/ae/3bd609c760d57849d7ddf223762f1881f3c4df6467f4eadb3a33652b7e0d/sentence_splitter-1.4-py2.py3-none-any.whl"
},
{
"comment_text": "",
"digests": {
"md5": "a58c1f759d0b8ce0fe1e0c99b150ecb1",
"sha256": "3d1d773d07cc733ca2955aa87d0fa1c0a7274c6bdeec1daac5c5e92efb512f63"
},
"downloads": -1,
"filename": "sentence_splitter-1.4.tar.gz",
"has_sig": false,
"md5_digest": "a58c1f759d0b8ce0fe1e0c99b150ecb1",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.5",
"size": 30607,
"upload_time": "2019-01-14T17:11:25",
"url": "https://files.pythonhosted.org/packages/20/b3/86b431fe7002ba006c08b8559d2ad78e1153bfc515a453cc96d2f55a2c40/sentence_splitter-1.4.tar.gz"
}
]
}