summaryrefslogtreecommitdiffstats
path: root/doc/xml2wiki.py
blob: 2b7eb482745b16a5339819802517b39fb2164cae (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
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
import io
import re
import sys
import time
import xml.parsers.expat

from optparse import OptionParser

###############################################################################

writer = None

###############################################################################

class StreamEntry:
    def __init__( self, object, isElement ):
        self.object    = object
        self.isElement = isElement

###############################################################################

class Element:
    def __init__( self, parent, text=True, strip=True, delimBegin=None, delimEnd=None, newline=0 ):
        self._parent     = parent
        self._text       = text
        self._strip      = strip
        self._delimBegin = delimBegin
        self._delimEnd   = delimEnd
        self._newline    = newline
        self._stream     = []

    def _addElement( self, child ):
        self._stream.append( StreamEntry( child, True ))

    def _addText( self, text ):
        if self._text:
            self._stream.append( StreamEntry( text, False ))

    def _write( self, file ):
        if self._delimBegin:
            file.write( self._delimBegin )
        for entry in self._stream:
            if entry.isElement:
                entry.object.write( file )
            else:
                file.write( str(entry.object) )
        if self._delimEnd:
            file.write( self._delimEnd )

    def write( self, file ):
        if self._newline > writer.newlineCount:
            file.write( '\n' * (self._newline - writer.newlineCount))
        self._write( file )

###############################################################################

class Document( Element ):
    def __init__( self ):
        Element.__init__( self, None )
        self._stack        = [ self ]
        self._pending      = self
        self._summary      = None
        self._debugIndent  = ''
        self._chapterLevel = 0
        self._sectionLevel = 0
        self._dividerCount = 0
        self._majorHeading = Element( self, delimBegin='= ', delimEnd=' =\n\n' )

    def _pop( self ):
        self._stack.pop()
        self._pending = self._stack[-1]
        return self._pending

    def _pushChild( self, child, add=True ):
        if add:
            self._pending._addElement( child );
        self._stack.append( child )
        self._pending = child
        return self._pending

    def _chapterBegin( self ):
        self._chapterLevel = self._chapterLevel + 1

    def _chapterEnd( self ):
        self._chapterLevel = self._chapterLevel - 1

    def _sectionBegin( self ):
        self._sectionLevel = self._sectionLevel + 1

    def _sectionEnd( self ):
        self._sectionLevel = self._sectionLevel - 1

    def _write( self, file ):
        if options.date:
            file.write( "\n\n  ===== `[`generated by xml2wiki on %s`]` =====" % (time.strftime( '%c' ) ))
        Element._write( self, file )
        file.write( '\n' )

    def handleElementBegin( self, name, attrs ):
        self._debugIndent = '    ' * (len(self._stack) - 1)
        if options.verbose:
            print( '%sBEGIN %s %s' % (self._debugIndent, name, attrs))

        e = None
        shouldAdd = True

        if name == 'anchor':
            global anchor
            anchor = attrs['name']
        elif name == 'b':
            e = Element( self._pending, delimBegin="'''", delimEnd="'''" )
        elif name == 'chapter':
            self._chapterBegin()
        elif name == 'code':
            e = Element( self._pending, delimBegin='{{{{', delimEnd='}}}' )
        elif name == 'command':
            e = Element( self._pending, delimBegin='{{{', delimEnd='}}}' )
        elif name == 'enumerate':
            e = EnumerateElement( self._pending )
        elif name == 'example':
            e = CodeElement( self._pending )
        elif name == 'file':
            e = Element( self._pending, delimBegin='{{{', delimEnd='}}}' )
        elif name == 'i':
            e = Element( self._pending, delimBegin="''", delimEnd="''" )
        elif name == 'itemize':
            e = ItemizeElement( self._pending )
        elif name == 'item':
            e = ItemElement( self._pending )
        elif name == 'majorheading':
            e = self._majorHeading
            shouldAdd = False
        elif name == 'para':
            e = ParagraphElement( self._pending )
        elif name == 'quotation':
            e = IndentedElement( self._pending )
        elif name == 'samp':
            e = Element( self._pending, delimBegin='{{{', delimEnd='}}}' )
        elif name == 'section' or name == 'subsection':
            self._sectionBegin()
        #elif name == 'table':
        #    e = Element( self._pending, newline=1, delimBegin='<table border="1" cellpadding="4">', delimEnd='</table>', strip=True )
        elif name == 'tableitem':
            e = TableItemElement( self._pending )
        elif name == 'tableterm':
            e = Element( self._pending, delimBegin=' ', delimEnd='::\n' )
        elif name == 'title':
            e = HeadingElement( self._pending, self._chapterLevel + self._sectionLevel )
        elif name == 'unnumbered' or name == 'unnumberedsec':
            self._chapterBegin()
        elif name == 'uref':
            e = UrefInline( self._pending )
        elif name == 'urefdesc':
            e = UrefDescInline( self._pending )
        elif name == 'urefurl':
            e = UrefUrlInline( self._pending )
        elif name == 'xref':
            e = XrefInline( self._pending )
        elif name == 'xrefnodename':
            e = XrefNodenameInline( self._pending )

        if not e:
            self._pushChild( UnknownElement( self._pending ) )
            if options.verbose > 2:
                print( 'UNKNOWN:', name )
        else:
            self._pushChild( e, add=shouldAdd )

    def handleElementEnd( self, name ):
        if name == 'chapter':
            self._chapterEnd()
        elif name == 'section' or name == 'subsection':
            self._sectionEnd()
        elif name == 'unnumbered' or name == 'unnumberedsec':
            self._sectionEnd()

        self._pop()
        self._debugIndent = '    ' * (len(self._stack) - 1)
        if options.verbose:
            print( '%sEND %s' % (self._debugIndent, name))

    def handleCharacterData( self, data ):
        if options.verbose > 1:
            print( '%s[%s]' % (self._debugIndent, data.strip()))
        self._pending._addText( data )

###############################################################################

class UnknownElement( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, text=False )

###############################################################################

class PragmaElement( Element ):
    def __init__( self, parent, keyword ):
        Element.__init__( self, parent, delimBegin=('#' + keyword + ' ') )

###############################################################################

class BlockElement( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, newline=2, text=False )

###############################################################################

class CodeElement( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, newline=2, delimBegin='{{{\n', delimEnd='\n}}}\n' )

###############################################################################

class HeadingElement( Element ):
    def __init__( self, parent, level ):
        Element.__init__( self, parent, newline=2 )
        global anchor
        self._anchor = anchor

        self._level = level
        self._delimBegin = ('=' * level) + ' '
        self._delimEnd   =  ' %s #%s\n' % (('=' * level), self._anchor)
        #self._delimEnd   =  ' ' + ('=' * level) + ' #%s\n' % (self._anchor)

        # insert divider for level 1 headers
        if level == 1:
            if options.toc or doc._dividerCount:
                self._delimBegin = '----\n%s' % (self._delimBegin)
            doc._dividerCount = doc._dividerCount + 1

        toc.append( self )

###############################################################################

class IndentedElement( BlockElement ):
    def _write( self, file ):
        writer.increase()
        Element._write( self, file )
        writer.decrease()

###############################################################################

class EnumerateElement( IndentedElement ):
    pass

###############################################################################

class ItemizeElement( IndentedElement ):
    pass

###############################################################################

class ItemElement( BlockElement ):
    def __init__( self, parent ):
        BlockElement.__init__( self, parent )
        self._newline = 1
        if isinstance( parent, TableItemElement ):
            self._newline    = 0
            #self._delimBegin = '<td>'
            #self._delimEnd   = '</td>'
            self._delimBegin = '    '
            self._delimEnd   = '\n'

###############################################################################

class ParagraphElement( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, newline=2 )
        if isinstance( parent, ItemElement ):
            if isinstance( parent._parent, TableItemElement ):
                self._newline = 0
            elif isinstance( parent._parent, EnumerateElement ):
                self._newline    = 1
                self._delimBegin = '# '
            else:
                self._newline    = 1
                self._delimBegin = '* '

###############################################################################

class TableItemElement( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, newline=1, text=False )
        #self._delimBegin = '<tr>'
        #self._delimEnd   = '</tr>'

###############################################################################

class UrefInline( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, text=False, delimBegin='[', delimEnd=']' )

###############################################################################

class UrefDescInline( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, delimBegin=' ' )

###############################################################################

class UrefUrlInline( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent )

###############################################################################

class XrefInline( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent, text=False )

###############################################################################

class XrefNodenameInline( Element ):
    def __init__( self, parent ):
        Element.__init__( self, parent )

    def _write( self, file ):
        buffer = io.StringIO()
        Element._write( self, buffer )
        name = str( buffer.getvalue() )
        anchor = re.sub( ' ', '_', name )
        file.write( '[#%s %s]' % (anchor, name) )

###############################################################################

class IndentedWriter:
    def __init__( self, size, file ):
        self._chunk   = ' ' * size
        self._file    = file
        self._level   = 0
        self._indent  = ''
        self._pending = False

        self.newlineCount = 0

    def decrease( self ):
        self._level  = self._level - 1
        self._indent = self._chunk * self._level

    def increase( self ):
        self._level  = self._level + 1
        self._indent = self._chunk * self._level

    def write( self, data ):
        for b in data:
            if self._pending:
                self._pending = False
                self._file.write( self._indent )
            if b == '\n':
                self.newlineCount = self.newlineCount + 1
                self._pending = True
            else:
                self.newlineCount = 0
            self._file.write( b )

###############################################################################

parser = OptionParser( 'Usage: %prog [OPTIONS] xml' )
parser.add_option( '-d', '--date', action='store_true', default=False, help='generate date-stamp under title' )
parser.add_option( '-t', '--toc', action='store_true', default=False, help='generate table of contents' )
parser.add_option( '-v', '--verbose', action='count', default=False, help='increase verbosity' )

(options, args) = parser.parse_args()

if( len(args) != 1 ):
    parser.error( 'incorrect number of arguments' )

###############################################################################

doc = Document()
xml = xml.parsers.expat.ParserCreate()

xml.StartElementHandler  = doc.handleElementBegin
xml.EndElementHandler    = doc.handleElementEnd
xml.CharacterDataHandler = doc.handleCharacterData

anchor = None
toc = []
with open( args[0], 'rb' ) as fin:
    xml.ParseFile( fin )

writer = IndentedWriter( 4, sys.stdout )

doc._majorHeading.write( writer )
if options.toc:
    for e in toc:
        writer.write( '%s* [#%s %s]\n' % ('  ' * e._level,e._anchor,e._stream[0].object) )
doc.write( writer )