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
|
# frozen_string_literal: true
module IpynbDiff
class InvalidTokenError < StandardError
end
# Creates a symbol map for a ipynb file (JSON format)
class IpynbSymbolMap
class << self
def parse(notebook, objects_to_ignore = [])
IpynbSymbolMap.new(notebook, objects_to_ignore).parse('')
end
end
attr_reader :current_line, :char_idx, :results
WHITESPACE_CHARS = ["\t", "\r", ' ', "\n"].freeze
VALUE_STOPPERS = [',', '[', ']', '{', '}', *WHITESPACE_CHARS].freeze
def initialize(notebook, objects_to_ignore = [])
@chars = notebook.chars
@current_line = 0
@char_idx = 0
@results = {}
@objects_to_ignore = objects_to_ignore
end
def parse(prefix = '.')
raise_if_file_ended
skip_whitespaces
if (c = current_char) == '"'
parse_string
elsif c == '['
parse_array(prefix)
elsif c == '{'
parse_object(prefix)
else
parse_value
end
results
end
def parse_array(prefix)
# [1, 2, {"some": "object"}, [1]]
i = 0
current_should_be '['
loop do
raise_if_file_ended
break if skip_beginning(']')
new_prefix = "#{prefix}.#{i}"
add_result(new_prefix, current_line)
parse(new_prefix)
i += 1
end
end
def parse_object(prefix)
# {"name":"value", "another_name": [1, 2, 3]}
current_should_be '{'
loop do
raise_if_file_ended
break if skip_beginning('}')
prop_name = parse_string(return_value: true)
next_and_skip_whitespaces
current_should_be ':'
next_and_skip_whitespaces
if @objects_to_ignore.include? prop_name
skip
else
new_prefix = "#{prefix}.#{prop_name}"
add_result(new_prefix, current_line)
parse(new_prefix)
end
end
end
def parse_string(return_value: false)
current_should_be '"'
init_idx = @char_idx
loop do
increment_char_index
raise_if_file_ended
if current_char == '"' && !prev_backslash?
init_idx += 1
break
end
end
@chars[init_idx...@char_idx].join if return_value
end
def add_result(key, line_number)
@results[key] = line_number
end
def parse_value
increment_char_index until raise_if_file_ended || VALUE_STOPPERS.include?(current_char)
end
def skip_whitespaces
while WHITESPACE_CHARS.include?(current_char)
raise_if_file_ended
check_for_new_line
increment_char_index
end
end
def increment_char_index
@char_idx += 1
end
def next_and_skip_whitespaces
increment_char_index
skip_whitespaces
end
def current_char
raise_if_file_ended
@chars[@char_idx]
end
def prev_backslash?
@chars[@char_idx - 1] == '\\' && @chars[@char_idx - 2] != '\\'
end
def current_should_be(another_char)
raise InvalidTokenError unless current_char == another_char
end
def check_for_new_line
@current_line += 1 if current_char == "\n"
end
def raise_if_file_ended
@char_idx >= @chars.size && raise(InvalidTokenError)
end
def skip
raise_if_file_ended
skip_whitespaces
if (c = current_char) == '"'
parse_string
elsif c == '['
skip_array
elsif c == '{'
skip_object
else
parse_value
end
end
def skip_array
loop do
raise_if_file_ended
break if skip_beginning(']')
skip
end
end
def skip_object
loop do
raise_if_file_ended
break if skip_beginning('}')
parse_string
next_and_skip_whitespaces
current_should_be ':'
next_and_skip_whitespaces
skip
end
end
def skip_beginning(closing_char)
check_for_new_line
next_and_skip_whitespaces
return true if current_char == closing_char
next_and_skip_whitespaces if current_char == ','
end
end
end
|
