From e20caae048fe62a40ed355f7e81c11cff8bd8bfa Mon Sep 17 00:00:00 2001 From: PyYoshi Date: Mon, 17 Oct 2016 19:39:55 +0900 Subject: [PATCH] add rst documents --- CHANGES.rst | 9 ++++ README.rst | 133 ++++++++++++++++++++++++++++++++++++++++++++++++++++ setup.py | 11 +++-- 3 files changed, 150 insertions(+), 3 deletions(-) create mode 100644 CHANGES.rst create mode 100644 README.rst diff --git a/CHANGES.rst b/CHANGES.rst new file mode 100644 index 0000000..e8339cb --- /dev/null +++ b/CHANGES.rst @@ -0,0 +1,9 @@ +CHANGES +======= + +1.1.0 (2016-10-17) +------------------ + +- Add Detector class + +- Improve unit tests diff --git a/README.rst b/README.rst new file mode 100644 index 0000000..79fba94 --- /dev/null +++ b/README.rst @@ -0,0 +1,133 @@ +cChardet +======== + +cChardet is high speed universal character encoding detector. - binding to `charsetdetect`_. + +.. image:: https://badge.fury.io/py/cchardet.svg + :target: https://badge.fury.io/py/cchardet + :alt: PyPI version +.. image:: https://travis-ci.org/PyYoshi/cChardet.svg?branch=master + :target: https://travis-ci.org/PyYoshi/cChardet + :alt: Travis Ci build status +.. image:: https://ci.appveyor.com/api/projects/status/lwkc4rgf3gncb1ne/branch/master?svg=true + :target: https://ci.appveyor.com/project/PyYoshi/cchardet/branch/master + :alt: AppVeyor build status + +Support codecs +-------------- + +- Big5 +- EUC-JP +- EUC-KR +- GB18030 +- HZ-GB-2312 +- IBM855 +- IBM866 +- ISO-2022-CN +- ISO-2022-JP +- ISO-2022-KR +- ISO-8859-2 +- ISO-8859-5 +- ISO-8859-7 +- ISO-8859-8 +- KOI8-R +- Shift_JIS +- TIS-620 +- UTF-8 +- UTF-16BE +- UTF-16LE +- UTF-32BE +- UTF-32LE +- WINDOWS-1250 +- WINDOWS-1251 +- WINDOWS-1252 +- WINDOWS-1253 +- WINDOWS-1255 +- EUC-TW +- X-ISO-10646-UCS-4-2143 +- X-ISO-10646-UCS-4-3412 +- x-mac-cyrillic + +Requirements +------------ + +- `Cython`_ + +Example +------- + +.. code-block:: python + + # -*- coding: utf-8 -*- + import cchardet as chardet + with open(r"src/tests/testdata/wikipediaJa_One_Thousand_and_One_Nights_SJIS.txt", "rb") as f: + msg = f.read() + result = chardet.detect(msg) + print(result) + + +Benchmark +--------- + +.. code-block:: bash + + $ cd src/ + $ pip install chardet + $ python tests/bench.py + + +Results +~~~~~~~ + +CPU: Intel(R) Core(TM) i3-4170 CPU @ 3.70GHz + +RAM: DDR3 1600Mhz 16GB + +Platform: Ubuntu 16.04 amd64 + +Python 2.7.12 +^^^^^^^^^^^^^ + ++----------+------------------+ +| | Request (call/s) | ++==========+==================+ +| chardet | 0.26 | ++----------+------------------+ +| cchardet | 1408.73 | ++----------+------------------+ + +Python 3.5.2 +^^^^^^^^^^^^ + ++----------+------------------+ +| | Request (call/s) | ++==========+==================+ +| chardet | 0.28 | ++----------+------------------+ +| cchardet | 1380.40 | ++----------+------------------+ + +License +------- + +- The MIT License: `src/cchardet`_ +- Other Libraries License: Please, look at the `src/ext`_ directory. + +Thanks +------ + +- `uchardet-enhanced`_ +- `Cython`_ + +Contact +------- + +`Issues`_ + + +.. _charsetdetect: https://bitbucket.org/medoc/uchardet-enhanced/overview +.. _Cython: http://www.cython.org/ +.. _src/cchardet: https://github.com/PyYoshi/cChardet/tree/master/src/cchardet +.. _src/ext: https://github.com/PyYoshi/cChardet/tree/master/src/ext +.. _uchardet-enhanced: https://bitbucket.org/medoc/uchardet-enhanced/overview +.. _Issues: https://github.com/PyYoshi/cChardet/issues?page=1&state=open diff --git a/setup.py b/setup.py index 6e38dd8..ddbfa81 100644 --- a/setup.py +++ b/setup.py @@ -59,15 +59,17 @@ cchardet_module = Extension( define_macros=macros, ) + +def read(f): + return open(os.path.join(os.path.dirname(__file__), f)).read().strip() + setup( name='cchardet', author='PyYoshi', author_email='myoshi321go@gmail.com', url=r'https://github.com/PyYoshi/cChardet', description='Universal encoding detector. This library is faster than chardet.', - long_description='''cChardet is high speed universal character encoding detector. - binding to charsetdetect. -This library is faster than chardet. -''', + long_description='\n\n'.join((read('README.rst'), read('CHANGES.rst'))), version='1.1.0', license='MIT License', classifiers=[ @@ -76,7 +78,10 @@ This library is faster than chardet. 'Programming Language :: Python', 'Topic :: Software Development :: Libraries', 'Programming Language :: Python :: 2', + 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.4', + 'Programming Language :: Python :: 3.5', ], keywords=[ 'cython',