| 1 |
#!/bin/python3 |
| 2 |
# -*- coding: utf-8 -*- |
| 3 |
|
| 4 |
# ##### BEGIN LICENSE BLOCK ##### |
| 5 |
# Version: MPL 1.1/GPL 2.0/LGPL 2.1 |
| 6 |
# |
| 7 |
# The contents of this file are subject to the Mozilla Public License Version |
| 8 |
# 1.1 (the "License"); you may not use this file except in compliance with |
| 9 |
# the License. You may obtain a copy of the License at |
| 10 |
# http://www.mozilla.org/MPL/ |
| 11 |
# |
| 12 |
# Software distributed under the License is distributed on an "AS IS" basis, |
| 13 |
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License |
| 14 |
# for the specific language governing rights and limitations under the |
| 15 |
# License. |
| 16 |
# |
| 17 |
# The Original Code is Mozilla Universal charset detector code. |
| 18 |
# |
| 19 |
# The Initial Developer of the Original Code is |
| 20 |
# Netscape Communications Corporation. |
| 21 |
# Portions created by the Initial Developer are Copyright (C) 2001 |
| 22 |
# the Initial Developer. All Rights Reserved. |
| 23 |
# |
| 24 |
# Contributor(s): |
| 25 |
# Jehan <[email protected]> |
| 26 |
# |
| 27 |
# Alternatively, the contents of this file may be used under the terms of |
| 28 |
# either the GNU General Public License Version 2 or later (the "GPL"), or |
| 29 |
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"), |
| 30 |
# in which case the provisions of the GPL or the LGPL are applicable instead |
| 31 |
# of those above. If you wish to allow use of your version of this file only |
| 32 |
# under the terms of either the GPL or the LGPL, and not to allow others to |
| 33 |
# use your version of this file under the terms of the MPL, indicate your |
| 34 |
# decision by deleting the provisions above and replace them with the notice |
| 35 |
# and other provisions required by the GPL or the LGPL. If you do not delete |
| 36 |
# the provisions above, a recipient may use your version of this file under |
| 37 |
# the terms of any one of the MPL, the GPL or the LGPL. |
| 38 |
# |
| 39 |
# ##### END LICENSE BLOCK ##### |
| 40 |
|
| 41 |
import re |
| 42 |
|
| 43 |
## Mandatory Properties ## |
| 44 |
|
| 45 |
# The human name for the language, in English. |
| 46 |
name = 'Czech' |
| 47 |
# Use 2-letter ISO 639-1 if possible, 3-letter ISO code otherwise, |
| 48 |
# or use another catalog as a last resort. |
| 49 |
code = 'cs' |
| 50 |
# ASCII characters are also used in French. |
| 51 |
use_ascii = True |
| 52 |
# The charsets we want to support and create data for. |
| 53 |
charsets = ['ISO-8859-2', 'Windows-1250', 'IBM852', 'MAC-CENTRALEUROPE'] |
| 54 |
|
| 55 |
## Optional Properties ## |
| 56 |
|
| 57 |
# Alphabet characters. |
| 58 |
# If use_ascii=True, there is no need to add any ASCII characters. |
| 59 |
# If case_mapping=True, there is no need to add several cases of a same |
| 60 |
# character (provided Python algorithms know the right cases). |
| 61 |
alphabet = 'áčďéěíňóřšťúůýž' |
| 62 |
# The starred page which was rewarded on the main page when I created |
| 63 |
# the data. |
| 64 |
start_pages = ['Sociální fobie'] |
| 65 |
# give possibility to select another code for the Wikipedia URL. |
| 66 |
wikipedia_code = code |
| 67 |
# 'a' and 'A' will be considered the same character, and so on. |
| 68 |
# This uses Python algorithm to determine upper/lower-case of a given |
| 69 |
# character. |
| 70 |
case_mapping = True |
| 71 |
|
| 72 |
# A function to clean content returned by the `wikipedia` python lib, |
| 73 |
# in case some unwanted data has been overlooked. |
| 74 |
# Note that we are already cleaning away the '=' from the title syntax |
| 75 |
# of Wikipedia, as well as double spaces. But sometimes, Wikipedia in |
| 76 |
# some language may return weird syntax or UI text which should be |
| 77 |
# discarded. If you encounter one of these cases, use this function. |
| 78 |
def clean_wikipedia_content(content): |
| 79 |
# Do your garbage text cleaning here. |
| 80 |
return content |