summaryrefslogtreecommitdiff
path: root/wikitrans/wiki2text.py
blob: 88e761022eb122e59b9d50b7083ff0a0c9080404 (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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Copyright (C) 2008-2018 Sergey Poznyakoff
# 
# This program 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.
# 
# This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.

"""
Wiki markup to plain text translator.

Classes:

TextWikiMarkup       -- Converts Wiki material to plain text.
TextWiktionaryMarkup -- Reserved for future use. Currently does the same as
                        TextWikiMarkup.

"""

from wikitrans.wikitoken import *
from wikitrans.wikimarkup import *
from wikitrans.wikins import wiki_ns_re, wiki_ns
import re
try:
    from urllib import quote as url_quote
except ImportError:
    from urllib.parse import quote as url_quote

class TextSeqNode(WikiSeqNode):
    def format(self):
        string = ""
        for x in self.content:
            if len(string) > 1 and not string[-1].isspace():
                string += ' '
            string += x.format()
        return string
    
class TextTextNode(WikiTextNode):
    def format(self):
        if isinstance(self.content,list):
            string = ""
            for s in self.content:
                if string:
                    if string.endswith("."):
                        string += "  "
                    else:
                        string += " "
                string += s
        else:
            string = self.content
        return string

class TextPreNode(WikiSeqNode):
    def format(self):
        string = ""
        for x in self.content:
            string += x.format()
        string += '\n'
        return string

class TextParaNode(WikiSeqNode):
    def format(self):
        string = ""
        for x in self.content:
            string += x.format()
        string = self.parser.fmtpara(string) + '\n\n'
        return string

class TextItNode(WikiSeqNode):
    def format(self):
        string = ""
        for x in self.content:
            s = x.format()
            if s:
                string += " " + s
        return "_" + string.lstrip(" ") + "_"
        
class TextBoldNode(WikiSeqNode):
    def format(self):
        string = ""
        for x in self.content:
            if string.endswith("."):
                string += "  "
            else:
                string += " "
            string += x.format()
        return string.upper()

class TextLinkNode(WikiSeqNode):
    def format(self):
        arg = self.content[0].format()
        if len(self.content) > 1:
            s = [x for x in map(lambda x: x.format(), self.content)]
            text = s[1]
        else:
            s = None
            text = None

        if s:
            if s[0] == 'disambigR' or s[0] == 'wikiquote':
                return ""
            if len(s) > 1 and s[1] == 'thumb':
                return ""
        (qual,sep,tgt) = arg.partition(':')
        if tgt != '':
            ns = self.parser.wiki_ns_name(qual)
            if ns:
                if ns == 'NS_IMAGE':
                    if not self.parser.show_urls:
                        return ""
                    text = "[%s: %s]" % (qual, text if text else arg)
                    tgt = "%s/%s/250px-%s" % (self.image_base,
                                              url_quote(tgt),
                                              url_quote(tgt))
                elif ns == 'NS_MEDIA':
                    text = "[%s]" % (qual)
                else:
                    tgt = self.parser.mktgt(tgt)
            elif self.type == 'LINK' and qual in self.parser.langtab:
                text = self.parser.langtab[qual] + ": " + tgt
                tgt = self.parser.mktgt(tgt, qual)
            else:
                tgt = self.parser.mktgt(tgt)
        else:
            tgt = self.parser.mktgt(arg)
        if self.parser.show_urls:
            return "%s (see %s) " % (text, tgt)
        elif not text or text == '':
            return arg
        else:
            return text
        
class TextTmplNode(TextLinkNode):
    def format(self):
        return '[' + super(TextTmplNode, self).format() + ']'
        
class TextBarNode(WikiNode):
    def format(self):
        w = self.parser.width
        if w < 5:
            w = 5
        return "\n" + ("-" * (w - 5)).center(w - 1) + "\n"

class TextHdrNode(WikiHdrNode):
    def format(self):
        return ("\n"
                + ("*" * self.level)
                + " "
                + self.content.format().lstrip(" ")
                + "\n\n")
        
class TextRefNode(WikiRefNode):
    def format(self):
        text = self.content.format()
        if text:
            return "%s (see %s) " % (text, self.ref)
        else:
            return "see " + self.ref

class TextEnvNode(WikiEnvNode):
    def format(self):
        type = self.envtype
        lev = self.level
        if lev > self.parser.width - 4:
            lev = 1
        string = ""
        n = 1
        for s in self.content:
            if not string.endswith("\n"):
                string += "\n"
            x = s.content.format()
            if type == "unnumbered":
                string += self.parser.indent(lev, "- " + x.lstrip(" "))
            elif type == "numbered":
                string += self.parser.indent(lev, "%d. %s" % (n, x))
                n += 1
            elif type == "defn":
                if s.subtype == 0:
                    string += self.parser.indent(lev-1, x)
                else:
                    string += self.parser.indent(lev+3, x)

            if not string.endswith("\n"):
                string += "\n"

        return string

class TextIndNode(WikiIndNode):
    def format(self):
        return (" " * self.level) + self.content.format() + '\n'

class TextTagNode(WikiTagNode):
    def format(self):
        if self.tag == 'code':
            self.parser.nested += 1
            s = self.content.format()
            self.parser.nested -= 1
        elif self.tag == 'ref':
            s = '[%d]' % (self.idx+1)
        elif self.tag == 'references':
            s = '\nReferences:\n'
            for ref in self.parser.references:
                s += ('[%d]. ' % (ref.idx+1))  + ref.content.format() + '\n'
        else:
            s = '<' + self.tag
            if self.args:
                s += ' ' + str(self.args)
            s += '>' + self.content.format() + '</' + self.tag + '>'
        return s            
    

class TextWikiMarkup(WikiMarkup):
    """A Wiki markup to plain text translator.

    Usage:

      x = TextWikiMarkup(file="input.wiki")
      # Parse the input:
      x.parse()
      # Print it as plain text:
      print(str(x))
    
    """

    # Output width
    width = 78
    # Do not show references.
    show_urls = False
    # Provide a minimum markup
    markup = True

    # Number of current element in the environment
    num = 0

    # Array of footnote references
    references = []
    
    def __init__(self, *args, **keywords):
        """Create a TextWikiMarkup object.

        TextWikiMarkup([filename=FILE],[file=FD],[text=STRING],[lang=CODE],
                       [html_base=URL],[image_base=URL],[media_base=URL],
                       [width=N],[show_urls=False])

        Most arguments have the same meaning as in the WikiMarkup constructor.

        Class-specific arguments:
        
        width=N
          Limit output width to N columns. Default is 78.  
        show_urls=False
          By default, the link URLs are displayed in parentheses next to the
          link text. If this argument is given, only the link text will be
          displayed.
        """
        
        super(TextWikiMarkup,self).__init__(*args, **keywords)
        if 'width' in keywords:
            self.width = keywords['width']
        if 'show_urls' in keywords:
            self.show_urls = keywords['show_urls']
        self.token_class['SEQ'] = TextSeqNode
        self.token_class['TEXT'] = TextTextNode
        self.token_class['PRE'] = TextPreNode
        self.token_class['PARA'] = TextParaNode
        self.token_class['SEQ'] = TextSeqNode
        self.token_class['IT'] = TextItNode
        self.token_class['BOLD'] = TextBoldNode
        self.token_class['LINK'] = TextLinkNode
        self.token_class['TMPL'] = TextTmplNode
        self.token_class['BAR'] = TextBarNode
        self.token_class['HDR'] = TextHdrNode
        self.token_class['REF'] = TextRefNode
        self.token_class['ENV'] = TextEnvNode
        self.token_class['IND'] = TextIndNode
        self.token_class['TAG'] = TextTagNode
    
    def wiki_ns_name(self, str):
        if str in wiki_ns[self.lang]:
            return wiki_ns[self.lang][str]
        elif str in wiki_ns_re[self.lang]:
            for elt in wiki_ns_re[self.lang][str]:
                if str.beginswith(elt[0]) and str.endswith(elt[1]):
                    return elt[2]
        return None
    
    def mktgt(self, tgt, lang = None):
        if not lang:
            lang = self.lang
        return self.html_base % { 'lang' : lang } + url_quote(tgt)
    
    def indent(self, lev, text):
        if text.find('\n') == -1:
            s = (" " * lev) + text 
        else:
            s = ""
            for elt in text.split('\n'):
                if elt:
                    s += (" " * lev) + elt + '\n'
            if not text.endswith('\n'):
                s = s.rstrip('\n')
        return s
    
    def fmtpara(self, input):
        output = ""
        linebuf = ""
        length = 0
        for s in input.split():
            wlen = len(s)
            if len(linebuf) == 0:
                wsc = 0
            elif linebuf.endswith("."):
                wsc = 2
            else:
                wsc = 1
            if length + wsc + wlen > self.width:
                # FIXME: fill out linebuf
                output += linebuf + '\n'
                wsc = 0
                length = 0
                linebuf = ""
            linebuf += " " * wsc + s
            length += wsc + wlen
        return output + linebuf
        
    def __str__(self):
        str = ""
        for elt in self.tree:
            str += elt.format()
        return str

class TextWiktionaryMarkup(TextWikiMarkup):
    """A class for translating Wiktionary articles into plain text.

    Reserved for future use. Currently does the same as TextWikiMarkup.
    """

    html_base='http://%(lang)s.wiktionary.org/wiki/'

Return to:

Send suggestions and report system problems to the System administrator.