Initial version

8 files changed, 289 insertions, 2 deletions

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..046cca1
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,5 @@
+*.pyc
+MANIFEST
+dist/
+build/
+*.egg-info/
diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 0000000..6990722
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,8 @@
+language: python
+python:
+  - "2.6"
+  - "2.7"
+install:
+  - pip install -q -r requirements.txt --use-mirrors
+script: python test.py
+
diff --git a/README.md b/README.md
index 53eabe1..f25ae6f 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,90 @@
-python-slugify
-==============
\ No newline at end of file
+Python Slugify
+====================
+
+**A Python slugify application that handles unicode**
+
+**Author:** Val Neekman [ info@neekware.com, @vneekman ]
+
+Overview
+========
+
+A Python slugify application that handles unicode.
+
+How to install
+==================
+
+    1. easy_install python-slugify
+    2. pip install python-slugify
+    3. git clone http://github.com/un33k/python-slugify
+        a. cd python-slugify
+        b. run python setup.py
+    4. wget https://github.com/un33k/python-slugify/zipball/master
+        a. unzip the downloaded file
+        b. cd into python-slugify-* directory
+        c. run python setup.py
+
+How to use
+=================
+    from slugify import slugify
+
+    s = "This is a test ---"
+    r = slugify(s)
+    self.assertEquals(r, "this-is-a-test")
+
+    s = 'C\'est déjà l\'été.'
+    r = slugify(s)
+    self.assertEquals(r, "c-est-deja-lete")
+
+    s = 'Nín hǎo. Wǒ shì zhōng guó rén'
+    r = slugify(s)
+    self.assertEquals(r, "nin-hao-wo-shi-zhong-guo-ren")
+
+    s = '影師嗎'
+    r = slugify(s)
+    self.assertEquals(r, "ying-shi-ma")
+
+
+Running the tests
+=================
+
+To run the tests against the current environment:
+
+    python test.py
+
+Changelog
+=========
+
+0.0.1
+-----
+
+* Initial release
+
+
+License
+=======
+
+Copyright © Neekware Inc.
+
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without 
+modification, are permitted provided that the following conditions are met:
+
+Redistributions of source code must retain the above copyright notice, this 
+list of conditions and the following disclaimer.
+Redistributions in binary form must reproduce the above copyright notice, this 
+list of conditions and the following disclaimer in the documentation and/or 
+other materials provided with the distribution.
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND 
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED 
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE 
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR 
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, 
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+
+
diff --git a/pep8.sh b/pep8.sh
new file mode 100755
index 0000000..276f602
--- /dev/null
+++ b/pep8.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+echo -e "\nRunning: (pep8 --show-source --show-pep8 --select=errors --testsuite=.)\n\n"
+pep8 --show-source --show-pep8 --select=errors --testsuite=./
+echo -e "\n\n"
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..000ccb7
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+Unidecode>=0.04.9
+
diff --git a/setup.py b/setup.py
new file mode 100755
index 0000000..e2df292
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,83 @@
+#!/usr/bin/env python
+
+# -*- coding: utf-8 -*-
+from setuptools import setup
+import re
+import os
+import sys
+
+
+name = 'python-slugify'
+package = 'slugify'
+description = 'A Python slugify application that handles unicode'
+url = 'https://github.com/un33k/python-slugify'
+author = 'Val Neekman'
+author_email = 'info@neekware.com'
+license = 'BSD'
+install_requires = ['Unidecode>=0.04.9']
+classifiers = [
+    'Development Status :: 3 - Alpha',
+    'Intended Audience :: Developers',
+    'License :: OSI Approved :: BSD License',
+    'Operating System :: POSIX',
+    'Programming Language :: Python',
+]
+
+
+def get_version(package):
+    """
+    Return package version as listed in `__version__` in `init.py`.
+    """
+    init_py = open(os.path.join(package, '__init__.py')).read()
+    return re.search("^__version__ = ['\"]([^'\"]+)['\"]", init_py, re.MULTILINE).group(1)
+
+
+def get_packages(package):
+    """
+    Return root package and all sub-packages.
+    """
+    return [dirpath
+            for dirpath, dirnames, filenames in os.walk(package)
+            if os.path.exists(os.path.join(dirpath, '__init__.py'))]
+
+
+def get_package_data(package):
+    """
+    Return all files under the root package, that are not in a
+    package themselves.
+    """
+    walk = [(dirpath.replace(package + os.sep, '', 1), filenames)
+            for dirpath, dirnames, filenames in os.walk(package)
+            if not os.path.exists(os.path.join(dirpath, '__init__.py'))]
+
+    filepaths = []
+    for base, filenames in walk:
+        filepaths.extend([os.path.join(base, filename)
+                          for filename in filenames])
+    return {package: filepaths}
+
+
+if sys.argv[-1] == 'publish':
+    os.system("python setup.py sdist upload")
+    args = {'version': get_version(package)}
+    print "You probably want to also tag the version now:"
+    print "  git tag -a %(version)s -m 'version %(version)s'" % args
+    print "  git push --tags"
+    sys.exit()
+
+
+setup(
+    name=name,
+    version=get_version(package),
+    url=url,
+    license=license,
+    description=description,
+    author=author,
+    author_email=author_email,
+    packages=get_packages(package),
+    package_data=get_package_data(package),
+    install_requires=install_requires,
+    classifiers=classifiers
+)
+
+
diff --git a/slugify/__init__.py b/slugify/__init__.py
new file mode 100644
index 0000000..94d0bc1
--- /dev/null
+++ b/slugify/__init__.py
@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+
+__version__ = '0.0.1'
+
+__all__ = ['slugify']
+
+import re
+import unicodedata
+from htmlentitydefs import name2codepoint
+from types import UnicodeType
+from unidecode import unidecode
+
+# character entity reference
+CHAR_ENTITY_REXP = re.compile('&(%s);' % '|'.join(name2codepoint))
+
+# decimal character reference
+DECIMAL_REXP = re.compile('&#(\d+);')
+
+# hexadecimal character reference
+HEX_REXP = re.compile('&#x([\da-fA-F]+);')
+
+REPLACE1_REXP = re.compile(r'[\']+')
+REPLACE2_REXP = re.compile(r'[^-a-z0-9]+')
+REMOVE_REXP = re.compile('-{2,}')
+
+def slugify(text, entities=True, decimal=True, hexadecimal=True):
+    """ Make a slug from the given text """
+
+    # text to unicode
+    if type(text) != UnicodeType:
+        text = unicode(text, 'utf-8', 'ignore')
+
+    # decode unicode ( 影師嗎 = Ying Shi Ma)
+    text = unidecode(text)
+
+    # text back to unicode
+    text = unicode(text, 'utf-8', 'ignore')
+
+    # character entity reference
+    if entities:
+        text = CHAR_ENTITY_REXP.sub(lambda m: unichr(name2codepoint[m.group(1)]), text)
+
+    # decimal character reference
+    if decimal:
+        try:
+            text = DECIMAL_REXP.sub(lambda m: unichr(int(m.group(1))), text)
+        except:
+            pass
+
+    # hexadecimal character reference
+    if hexadecimal:
+        try:
+            text = HEX_REXP.sub(lambda m: unichr(int(m.group(1), 16)), text)
+        except:
+            pass
+
+    # translate
+    text = unicodedata.normalize('NFKD', text).encode('ascii', 'ignore')
+
+    # replace unwanted characters
+    text = REPLACE1_REXP.sub('', text.lower()) # replace ' with nothing instead with -
+    text = REPLACE2_REXP.sub('-', text.lower())
+
+    # remove redundant -
+    text = REMOVE_REXP.sub('-', text).strip('-')
+
+    return text
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..d713ee3
--- /dev/null
+++ b/test.py
@@ -0,0 +1,29 @@
+# -*- coding: utf-8 -*-
+
+import unittest
+from slugify import slugify
+
+class TestSequenceFunctions(unittest.TestCase):
+
+    def test_space_dash(self):
+        txt = "This is a test ---"
+        r = slugify(txt)
+        self.assertEquals(r, "this-is-a-test")
+
+    def test_special_chars(self):
+        txt = 'C\'est déjà l\'été.'
+        r = slugify(txt)
+        self.assertEquals(r, "cest-deja-lete")
+
+        txt = 'Nín hǎo. Wǒ shì zhōng guó rén'
+        r = slugify(txt)
+        self.assertEquals(r, "nin-hao-wo-shi-zhong-guo-ren")
+
+        txt = '影師嗎'
+        r = slugify(txt)
+        self.assertEquals(r, "ying-shi-ma")
+
+if __name__ == '__main__':
+    unittest.main()
+
+