{ "info": { "author": "Tatsuro Yasukawa", "author_email": "t.yasukawa01@gmail.com", "bugtrack_url": null, "classifiers": [ "Environment :: MacOS X", "Intended Audience :: Developers", "Intended Audience :: Science/Research", "License :: OSI Approved :: BSD License", "Programming Language :: Python", "Programming Language :: Python :: 3", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Text Processing :: Linguistic" ], "description": "TinySegmenter\n----------\n\nTinySegmenter -- Super compact Japanese tokenizer was originally created by\n(c) 2008 Taku Kudo for javascript under the terms of a new BSD licence.\nFor details, see [here](http://lilyx.net/pages/tinysegmenter_licence.txt)\n\ntinysegmenter for python2.x was written by Masato Hagiwara.\nfor his information see [here](http://lilyx.net/pages/tinysegmenterp.html)\n\nThis tinysegmenter is modified for python3.x and python2.x for distribution by Tatsuro Yasukawa.\nAdditionaly, this tinysegmenter is modified for being more faster - thanks to\n@chezou, @cocoatomo and @methane.\n\nSee info about [tinysegmenter](https://github.com/SamuraiT/tinysegmenter)\n\nInstallation\n------------\n\n```\npip install tinysegmenter3\n```\n\nUsage\n----------\n\n```py\nimport tinysegmenter\nstatement = '\u79c1\u306fpython\u5927\u597d\u304dStanding Engineer\u3067\u3059\uff0e'\ntokenized_statement = tinysegmenter.tokenize(statement)\nprint(tokenized_statement)\n# ['\u79c1', '\u306f', 'python', '\u5927\u597d\u304d', 'Standing', ' Engineer', '\u3067\u3059', '\uff0e']\n```\n\n\nTest Text\n----------\n\nThe [test text](http://www.genpaku.org/timemachine/timemachineu8j.txt) (in the `tests` directory) was [The Time Machine](https://en.wikipedia.org/wiki/The_Time_Machine) by H.G. Wells, translated to Japanese by Hiroo Yamagata under the CC BY-SA 2.0 License.\n\nHow to run Test\n-----------\n\nInstall requirements from `requirements.txt` by\n```py\npip install -r requirements.txt\n```\n\nthen run this:\n```py\n./runtests.sh\n```", "description_content_type": null, "docs_url": null, "download_url": "UNKNOWN", "downloads": { "last_day": -1, "last_month": -1, "last_week": -1 }, "home_page": "https://github.com/SamuraiT/tinysegmenter", "keywords": null, "license": "New BSD", "maintainer": null, "maintainer_email": null, "name": "tinysegmenter3", "package_url": "https://pypi.org/project/tinysegmenter3/", "platform": "UNKNOWN", "project_url": "https://pypi.org/project/tinysegmenter3/", "project_urls": { "Download": "UNKNOWN", "Homepage": "https://github.com/SamuraiT/tinysegmenter" }, "release_url": "https://pypi.org/project/tinysegmenter3/0.1.0/", "requires_dist": null, "requires_python": null, "summary": "Super compact Japanese tokenizer", "version": "0.1.0" }, "last_serial": 1798995, "releases": { "0.0.2": [ { "comment_text": "", "digests": { "md5": "950ffbe2bae439806302bdca13eef9d6", "sha256": "d2dc53ecc982f9d5c07c34eafafba6c284179bd3b7d6c2d830063e86c176f98c" }, "downloads": -1, "filename": "tinysegmenter3-0.0.2.tar.gz", "has_sig": false, "md5_digest": "950ffbe2bae439806302bdca13eef9d6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 9920, "upload_time": "2014-07-14T03:48:47", "url": "https://files.pythonhosted.org/packages/78/cb/8fc3479aa9b6845e9ed6c268ee0f4d18c1cb541d2af213a36426c443c530/tinysegmenter3-0.0.2.tar.gz" } ], "0.0.3": [ { "comment_text": "", "digests": { "md5": "8641389cc876b556edaabb336dfc87b6", "sha256": "f1c559cd22968233d436e37f535b5de2a2b3fbfd46227d94084d3c2c0e2607b1" }, "downloads": -1, "filename": "tinysegmenter3-0.0.3.tar.gz", "has_sig": false, "md5_digest": "8641389cc876b556edaabb336dfc87b6", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 10413, "upload_time": "2014-07-14T06:48:30", "url": "https://files.pythonhosted.org/packages/32/ab/99faa83ad4c15527f8940629a2a4182febcd6bc0eb4f8fa5090ebfa5d9ce/tinysegmenter3-0.0.3.tar.gz" } ], "0.1.0": [ { "comment_text": "", "digests": { "md5": "ce8f4eac7b2ca498c4655b88e4f0efa9", "sha256": "704703302fbf95d270791506d0d37d3088e09f58c822aff69497d5415bce6e62" }, "downloads": -1, "filename": "tinysegmenter3-0.1.0.tar.gz", "has_sig": false, "md5_digest": "ce8f4eac7b2ca498c4655b88e4f0efa9", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11176, "upload_time": "2015-11-03T13:06:27", "url": "https://files.pythonhosted.org/packages/fa/02/fcfeebe21e1e030da593f2151538c273e1eeccd8fb62d18811dbffc5cd6d/tinysegmenter3-0.1.0.tar.gz" } ] }, "urls": [ { "comment_text": "", "digests": { "md5": "ce8f4eac7b2ca498c4655b88e4f0efa9", "sha256": "704703302fbf95d270791506d0d37d3088e09f58c822aff69497d5415bce6e62" }, "downloads": -1, "filename": "tinysegmenter3-0.1.0.tar.gz", "has_sig": false, "md5_digest": "ce8f4eac7b2ca498c4655b88e4f0efa9", "packagetype": "sdist", "python_version": "source", "requires_python": null, "size": 11176, "upload_time": "2015-11-03T13:06:27", "url": "https://files.pythonhosted.org/packages/fa/02/fcfeebe21e1e030da593f2151538c273e1eeccd8fb62d18811dbffc5cd6d/tinysegmenter3-0.1.0.tar.gz" } ] }