summaryrefslogtreecommitdiff
path: root/scripts/jsondiff.py
blob: 3b1f9110fbc25eccefb1ea987c580d6a346db9b7 (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
#!/usr/bin/env python
##########################################################################
#
# Copyright 2015 VMware, Inc.
# Copyright 2011 Jose Fonseca
# All Rights Reserved.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.
#
##########################################################################/


import json
import optparse
import re
import difflib
import sys


def strip_object_hook(obj):
    if '__class__' in obj:
        return None
    for name in obj.keys():
        if name.startswith('__') and name.endswith('__'):
            del obj[name]
    return obj


class Visitor:

    def visit(self, node, *args, **kwargs):
        if isinstance(node, dict):
            return self.visitObject(node, *args, **kwargs)
        elif isinstance(node, list):
            return self.visitArray(node, *args, **kwargs)
        else:
            return self.visitValue(node, *args, **kwargs)

    def visitObject(self, node, *args, **kwargs):
        pass

    def visitArray(self, node, *args, **kwargs):
        pass

    def visitValue(self, node, *args, **kwargs):
        pass


class Dumper(Visitor):

    def __init__(self, stream = sys.stdout):
        self.stream = stream
        self.level = 0

    def _write(self, s):
        self.stream.write(s)

    def _indent(self):
        self._write('  '*self.level)

    def _newline(self):
        self._write('\n')

    def visitObject(self, node):
        self.enter_object()

        members = node.keys()
        members.sort()
        for i in range(len(members)):
            name = members[i]
            value = node[name]
            self.enter_member(name)
            self.visit(value)
            self.leave_member(i == len(members) - 1)
        self.leave_object()

    def enter_object(self):
        self._write('{')
        self._newline()
        self.level += 1

    def enter_member(self, name):
        self._indent()
        self._write('%s: ' % name)

    def leave_member(self, last):
        if not last:
            self._write(',')
        self._newline()

    def leave_object(self):
        self.level -= 1
        self._indent()
        self._write('}')
        if self.level <= 0:
            self._newline()

    def visitArray(self, node):
        self.enter_array()
        for i in range(len(node)):
            value = node[i]
            self._indent()
            self.visit(value)
            if i != len(node) - 1:
                self._write(',')
            self._newline()
        self.leave_array()

    def enter_array(self):
        self._write('[')
        self._newline()
        self.level += 1

    def leave_array(self):
        self.level -= 1
        self._indent()
        self._write(']')

    def visitValue(self, node):
        self._write(json.dumps(node, allow_nan=True))



class Comparer(Visitor):

    def __init__(self, ignore_added = False, tolerance = 2.0 ** -24):
        self.ignore_added = ignore_added
        self.tolerance = tolerance

    def visitObject(self, a, b):
        if not isinstance(b, dict):
            return False
        if len(a) != len(b) and not self.ignore_added:
            return False
        ak = a.keys()
        bk = b.keys()
        ak.sort()
        bk.sort()
        if ak != bk and not self.ignore_added:
            return False
        for k in ak:
            ae = a[k]
            try:
                be = b[k]
            except KeyError:
                return False
            if not self.visit(ae, be):
                return False
        return True

    def visitArray(self, a, b):
        if not isinstance(b, list):
            return False
        if len(a) != len(b):
            return False
        for ae, be in zip(a, b):
            if not self.visit(ae, be):
                return False
        return True

    def visitValue(self, a, b):
        if isinstance(a, float) and isinstance(b, (int, long, float)) or \
           isinstance(b, float) and isinstance(a, (int, long, float)):
            if a is b:
                # NaNs take this path
                return True
            elif a == b:
                return True
            elif a == 0:
                return abs(b) < self.tolerance
            else:
                return abs((b - a)/a) < self.tolerance
        else:
            return a == b


class Differ(Visitor):

    def __init__(self, stream = sys.stdout, ignore_added = False):
        self.dumper = Dumper(stream)
        self.comparer = Comparer(ignore_added = ignore_added)

    def visit(self, a, b):
        if self.comparer.visit(a, b):
            return
        Visitor.visit(self, a, b)

    def visitObject(self, a, b):
        if not isinstance(b, dict):
            self.replace(a, b)
        else:
            self.dumper.enter_object()
            names = set(a.keys())
            if not self.comparer.ignore_added:
                names.update(b.keys())
            names = list(names)
            names.sort()

            for i in range(len(names)):
                name = names[i]
                ae = a.get(name, None)
                be = b.get(name, None)
                if not self.comparer.visit(ae, be):
                    self.dumper.enter_member(name)
                    self.visit(ae, be)
                    self.dumper.leave_member(i == len(names) - 1)

            self.dumper.leave_object()

    def visitArray(self, a, b):
        if not isinstance(b, list):
            self.replace(a, b)
        else:
            self.dumper.enter_array()
            max_len = max(len(a), len(b))
            for i in range(max_len):
                try:
                    ae = a[i]
                except IndexError:
                    ae = None
                try:
                    be = b[i]
                except IndexError:
                    be = None
                self.dumper._indent()
                if self.comparer.visit(ae, be):
                    self.dumper.visit(ae)
                else:
                    self.visit(ae, be)
                if i != max_len - 1:
                    self.dumper._write(',')
                self.dumper._newline()

            self.dumper.leave_array()

    def visitValue(self, a, b):
        if a != b:
            self.replace(a, b)

    def replace(self, a, b):
        if self.isMultilineString(a) or self.isMultilineString(b):
            a = str(a)
            b = str(b)
            a = a.splitlines()
            b = b.splitlines()
            differ = difflib.Differ()
            result = differ.compare(a, b)
            self.dumper.level += 1
            for entry in result:
                self.dumper._newline()
                self.dumper._indent()
                tag = entry[:2]
                text = entry[2:]
                if tag == '? ':
                    tag = '  '
                    prefix = ' '
                    text = text.rstrip()
                    suffix = ''
                else:
                    prefix = '"'
                    suffix = '\\n"'
                line = tag + prefix + text + suffix
                self.dumper._write(line)
            self.dumper.level -= 1
            return
        self.dumper.visit(a)
        self.dumper._write(' -> ')
        self.dumper.visit(b)

    def isMultilineString(self, value):
        return isinstance(value, basestring) and '\n' in value


#
# Unfortunately JSON standard does not include comments, but this is a quite
# useful feature to have on regressions tests
#

_token_res = [
    r'//[^\r\n]*', # comment
    r'"[^"\\]*(\\.[^"\\]*)*"', # string
]

_tokens_re = re.compile(r'|'.join(['(' + token_re + ')' for token_re in _token_res]), re.DOTALL)


def _strip_comment(mo):
    if mo.group(1):
        return ''
    else:
        return mo.group(0)


def _strip_comments(data):
    '''Strip (non-standard) JSON comments.'''
    return _tokens_re.sub(_strip_comment, data)


assert _strip_comments('''// a comment
"// a comment in a string
"''') == '''
"// a comment in a string
"'''


def load(stream, strip_images = True, strip_comments = True):
    if strip_images:
        object_hook = strip_object_hook
    else:
        object_hook = None
    if strip_comments:
        data = stream.read()
        data = _strip_comments(data)
        return json.loads(data, strict=False, object_hook = object_hook)
    else:
        return json.load(stream, strict=False, object_hook = object_hook)


def main():
    optparser = optparse.OptionParser(
        usage="\n\t%prog [options] <ref_json> <src_json>")
    optparser.add_option(
        '--ignore-added',
        action="store_true", dest="ignore_added", default=False,
        help="ignore added state")
    optparser.add_option(
        '--keep-images',
        action="store_false", dest="strip_images", default=True,
        help="compare images")

    (options, args) = optparser.parse_args(sys.argv[1:])

    if len(args) != 2:
        optparser.error('incorrect number of arguments')

    a = load(open(args[0], 'rt'), options.strip_images)
    b = load(open(args[1], 'rt'), options.strip_images)

    if False:
        dumper = Dumper()
        dumper.visit(a)

    differ = Differ(ignore_added = options.ignore_added)
    differ.visit(a, b)


if __name__ == '__main__':
    main()