UnicodeSplitter.py :  » Issue-Tracker » IssueTracker » IssueTrackerProduct » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Issue Tracker » IssueTracker 
IssueTracker » IssueTrackerProduct » UnicodeSplitter.py
## Copyright (c) 2002, Infrae. All rights reserved.

## Redistribution and use in source and binary forms, with or without
## modification, are permitted provided that the following conditions are
## met:

##   1. Redistributions of source code must retain the above copyright
##      notice, this list of conditions and the following disclaimer.

##   2. 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.

##   3. Neither the name of Infrae nor the names of its contributors may
##      be used to endorse or promote products derived from this software
##      without specific prior written permission.

## 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 INFRAE 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.

#from utils import classImplements # peter
from Products.ZCTextIndex.ISplitter import ISplitter
from Products.ZCTextIndex.PipelineFactory import element_factory

import re
enc = 'utf-8'

class Splitter:

    __implements__ = ISplitter

    rx_L = re.compile(r"\w+", re.LOCALE)
    rxGlob_L = re.compile(r"\w+[\w*?]*", re.LOCALE)

    rx_U = re.compile(r"\w+", re.UNICODE)
    rxGlob_U = re.compile(r"\w+[\w*?]*", re.UNICODE)

    def process(self, lst):
        result = []
        for s in lst:
            # This is a hack to get the word splitting working with
            # non-unicode text.
            try:
                if not isinstance(s, unicode):
                    s = unicode(s, enc)
            except (UnicodeDecodeError, TypeError):
                # Fall back to locale aware splitter
                result += self.rx_L.findall(s)
            else:
                words = self.rx_U.findall(s)
                result += [w.encode(enc) for w in words]
        return result

    def processGlob(self, lst):
        result = []
        for s in lst:
            # This is a hack to get the word splitting working with
            # non-unicode text.
            try:
                if not isinstance(s, unicode):
                    s = unicode(s, enc)
            except (UnicodeDecodeError, TypeError):
                # Fall back to locale aware splitter
                result += self.rxGlob_L.findall(s)
            else:
                words = self.rxGlob_U.findall(s)
                result += [w.encode(enc) for w in words]
        return result

#classImplements(Splitter, Splitter.__implements__) # peter

try:
    element_factory.registerFactory('Word Splitter',
        'Unicode Whitespace splitter', Splitter)
except ValueError:
    # In case the splitter is already registered, ValueError is raised
    pass

class CaseNormalizer:

    def process(self, lst):
        result = []
        for s in lst:
            # This is a hack to get the normalizer working with
            # non-unicode text.
            try:
                if not isinstance(s, unicode):
                    s = unicode(s, enc)
            except (UnicodeDecodeError, TypeError):
                result.append(s.lower())
            else:
                result.append(s.lower().encode(enc))
        return result

try:
    element_factory.registerFactory('Case Normalizer',
        'Unicode Case Normalizer', CaseNormalizer)
except ValueError:
    # In case the normalizer is already registered, ValueError is raised
    pass

www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.