|
Revision 452, 1.0 kB
(checked in by athomas, 1 year ago)
|
pyndexter: All modules are now prefixed with _ to avoid import collisions. Updated unit tests.
|
- Property svn:eol-style set to
native
|
| Line | |
|---|
| 1 |
# -*- coding: utf-8 -*- |
|---|
| 2 |
# |
|---|
| 3 |
# Copyright (C) 2006 Alec Thomas <alec@swapoff.org> |
|---|
| 4 |
# |
|---|
| 5 |
# This software is licensed as described in the file COPYING, which |
|---|
| 6 |
# you should have received as part of this distribution. |
|---|
| 7 |
# |
|---|
| 8 |
|
|---|
| 9 |
""" |
|---|
| 10 |
Snowball |
|---|
| 11 |
-------- |
|---|
| 12 |
|
|---|
| 13 |
`Snowball <http://snowball.tartarus.org/>`_ is a multi-language stemming |
|---|
| 14 |
library with `Python bindings <http://snowball.tartarus.org/wrappers/PyStemmer-1.0.1.tar.gz>`_. |
|---|
| 15 |
|
|---|
| 16 |
Usage |
|---|
| 17 |
~~~~~ |
|---|
| 18 |
|
|---|
| 19 |
:: |
|---|
| 20 |
|
|---|
| 21 |
snowball://<language> |
|---|
| 22 |
|
|---|
| 23 |
``<language>`` |
|---|
| 24 |
Any of the languages supported by Snowball. |
|---|
| 25 |
|
|---|
| 26 |
|
|---|
| 27 |
Installation |
|---|
| 28 |
~~~~~~~~~~~~ |
|---|
| 29 |
|
|---|
| 30 |
The Python bindings ship with the Snowball source, so it's an easy (and |
|---|
| 31 |
recommended) install. |
|---|
| 32 |
|
|---|
| 33 |
:: |
|---|
| 34 |
|
|---|
| 35 |
easy_install http://snowball.tartarus.org/wrappers/PyStemmer-1.0.1.tar.gz |
|---|
| 36 |
|
|---|
| 37 |
""" |
|---|
| 38 |
|
|---|
| 39 |
import Stemmer |
|---|
| 40 |
from pyndexter import PluginFactory |
|---|
| 41 |
|
|---|
| 42 |
class SnowballStemmer(object): |
|---|
| 43 |
def __init__(self, language): |
|---|
| 44 |
self.stemmer = Stemmer.Stemmer(language) |
|---|
| 45 |
|
|---|
| 46 |
def __call__(self, word): |
|---|
| 47 |
return self.stemmer.stemWord(word) |
|---|
| 48 |
|
|---|
| 49 |
stemmer_factory = PluginFactory(SnowballStemmer, host="language") |
|---|
