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
|
# Wiki "dump" format. -*- coding: utf-8 -*-
# Copyright (C) 2015-2018 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/>.
"""
Print Wiki parse tree as JSON.
Classes:
DumpWikiMarkup
"""
from __future__ import print_function
from wikitrans.wikitoken import *
import json
from wikitrans.wikimarkup import WikiMarkup
class DumpReferences(object):
idx = 0
def __len__(self):
return self.idx + 1
def append(self, obj):
self.idx += 1
class DumpWikiMarkup(WikiMarkup):
"""Produce a JSON dump of the Wiki markup parse tree.
Usage:
x = DumpWikiMarkup(file="input.wiki")
# Parse the input:
x.parse()
# Print a JSON dump of the parse tree
print(str(x))
"""
indent = None
references = DumpReferences()
def __init__(self, **kwarg):
"""Create a DumpWikiMarkup object.
Arguments:
filename=FILE
Read Wiki material from the file named FILE.
file=FD
Read Wiki material from file object FD.
text=STRING
Read Wiki material from STRING.
indent=N
Basic indent offset for JSON objects.
"""
n = kwarg.pop('indent', None)
if n != None:
self.indent = int(n)
super(DumpWikiMarkup, self).__init__(self, **kwarg)
def __str__(self):
return json.dumps(self.tree,
cls=WikiNodeEncoder,
indent=self.indent,
separators=(',', ': '),
sort_keys=True)
|