aboutsummaryrefslogtreecommitdiff
path: root/app/python/mediawiki.py
blob: ea70ed805c4d3f698b1cb49bf860d1daf9b91cd3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
# -*- coding: utf-8 -*-
# Mediawiki module for Python 
# This file is part of GNU Dico.
# Copyright (C) 2008-2010, 2012 Wojciech Polak
#               2018 Sergey Poznyakoff
#
# GNU Dico is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3, or (at your option)
# any later version.
#
# GNU Dico is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with GNU Dico.  If not, see <http://www.gnu.org/licenses/>.

from __future__ import print_function
import sys
import re
import socket
from xml.dom import minidom
from wikitrans.wiki2text import TextWiktionaryMarkup

if sys.version_info[0] > 2:
    from urllib.request import urlopen, Request
    from urllib.error import URLError
    from urllib.parse import quote as url_quote
    from html.entities import name2codepoint
else:
    from urllib2 import urlopen, Request, quote as url_quote, URLError
    from htmlentitydefs import name2codepoint
    # Set utf-8 as the default encoding. 
    # Trying to do so using encode('utf_8')/unicode, which is 
    # supposed to be the right way, does not work.
    # Simply calling sys.setdefaultencoding is not possible,
    # because, for some obscure reason, Python chooses to delete 
    # this symbol from the namespace after setting its default 
    # encoding in site.py. That's why reload is needed. 
    reload(sys)
    sys.setdefaultencoding('utf-8')

try:
    import json
except ImportError:
    import simplejson as json

import dico

__version__ = '1.03'

class DicoModule:
    user_agent = 'Mozilla/1.0'
    endpoint_match  = '/w/api.php?action=opensearch&format=json&search='
    endpoint_define = '/wiki/Special:Export/'

    def __init__ (self, *argv):
        self.wikihost = argv[0]
        socket.setdefaulttimeout (4)
        dico.register_markup ('wiki')

    def open (self, dbname):
        self.dbname = dbname
        return True

    def close (self):
        return True

    def descr (self):
        return self.wikihost

    def info (self):
        return False

    def define_word (self, word):
        url = 'http://%s%s%s' % (self.wikihost, self.endpoint_define,
                                 url_quote (word))
        req = Request (url)
        req.add_header ('User-Agent', self.user_agent)
        try:
            xml = urlopen (req).read ()
        except URLError:
            return False
        dom = minidom.parseString (xml)
        el = dom.getElementsByTagName ('text')
        if len (el):
            data = el[0].firstChild.data
            if dico.current_markup () != 'wiki':
                data = self.__htmlentitydecode (data)
                if sys.version_info[0] == 2:
                    data = data.encode ('utf-8')
                wikiparser = TextWiktionaryMarkup (text=data)
                wikiparser.parse ()
                data = str (wikiparser)
            return ['define', data]
        else:
            return False

    def match_word (self, strat, key):
        url = 'http://%s%s%s' % (self.wikihost, self.endpoint_match,
                                 url_quote (key.word))
        req = Request (url)
        req.add_header ('User-Agent', self.user_agent)
        try:
            result = json.load (urlopen (req))
            if result:
                if strat.has_selector:
                    fltres = []
                    for k in result[1]:
                        if strat.select (k, key):
                            fltres.append (k)
                    if len(fltres) > 0:
                        return ['match', sorted(fltres, key=unicode.lower)]
                else:
                    result[1].sort ()
                    return ['match', sorted(result[1], key=unicode.lower)]
            return False
        except URLError:
            return False

    def output (self, rh, n):
        if rh[0] == 'define':
            print(rh[1], end='')
        else:
            list = rh[1]
            sys.stdout.softspace = 0
            print(list[n], end='')
        return True

    def result_count (self, rh):
        if rh[0] == 'define':
            return 1
        else:
            return len (rh[1])

    def compare_count (self, rh):
        return 1

    def result_headers (self, rh, hdr):
        if dico.current_markup () != 'wiki':
            hdr['Content-Type'] = 'text/plain';
        elif '.wikipedia.org' in self.wikihost:
            hdr['Content-Type'] = 'text/x-wiki-wikipedia';
        elif '.wiktionary.org' in self.wikihost:
            hdr['Content-Type'] = 'text/x-wiki-wiktionary';
        else:
            hdr['Content-Type'] = 'text/x-wiki';
        return hdr

    def free_result (self, rh):
        pass

    def __htmlentitydecode (self, s):
        return re.sub ('&(%s);' % '|'.join (name2codepoint),
                       lambda m: unichr (name2codepoint[m.group (1)]), s)

Return to:

Send suggestions and report system problems to the System administrator.