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
|
# rubocop:disable Style/Documentation
module PuppetX; end
module PuppetX::Augeas; end
module PuppetX::Augeas::Util; end
# rubocop:enable Style/Documentation
# Container for helpers to parse user provided data contained in manifests.
module PuppetX::Augeas::Util::Parser
TOKEN_ARRAY_CLOSE = %r{\s*\]\s*}.freeze
TOKEN_ARRAY_OPEN = %r{\s*\[\s*}.freeze
TOKEN_ARRAY_SEPARATOR = %r{\s*,\s*}.freeze
TOKEN_CLOSE_CURLY = %r|}|.freeze
TOKEN_DOUBLE_QUOTE = %r{"}.freeze
TOKEN_DOUBLE_QUOTE_ESCAPED_CHAR = %r{\\(["\\abtnvfres0-7xu])}.freeze
TOKEN_DOUBLE_QUOTE_UNESCAPED_CHAR = %r{[^"\\]}.freeze
TOKEN_HEX_CHAR = %r{[0-9a-fA-F]{1,2}}.freeze
TOKEN_OCTAL_CHAR = %r{[0-7]{1,3}}.freeze
TOKEN_OPEN_CURLY = %r|{|.freeze
TOKEN_SINGLE_QUOTE = %r{'}.freeze
TOKEN_SINGLE_QUOTE_ESCAPED_CHAR = %r{\\(['\\])}.freeze
TOKEN_SINGLE_QUOTE_UNESCAPED_CHAR = %r{[^'\\]}.freeze
TOKEN_SPACE = %r{\s}.freeze
TOKEN_UNICODE_LONG_HEX_CHAR = %r{[0-9a-fA-F]{1,6}}.freeze
TOKEN_UNICODE_SHORT_HEX_CHAR = %r{[0-9a-fA-F]{4}}.freeze
# Parse a string into the (nearly) equivalent Ruby array. This only handles
# arrays with string members (double-, or single-quoted), and does not
# support the full quite of escape sequences that Ruby allows in
# double-quoted strings.
#
# @param [String] The string to be parsed.
# @return [Array<String>] The parsed array elements, including handling any
# escape sequences.
def parse_to_array(string)
s = StringScanner.new(string)
match = array_open(s)
raise "Unexpected character in array at: #{s.rest}" if match.nil?
array_content = array_values(s)
match = array_close(s)
raise "Unexpected character in array at: #{s.rest}" if match.nil? || !s.empty?
array_content
end
def array_open(scanner)
scanner.scan(TOKEN_ARRAY_OPEN)
end
private :array_open
def array_close(scanner)
scanner.scan(TOKEN_ARRAY_CLOSE)
end
private :array_close
def array_separator(scanner)
scanner.scan(TOKEN_ARRAY_SEPARATOR)
end
private :array_separator
def single_quote_unescaped_char(scanner)
scanner.scan(TOKEN_SINGLE_QUOTE_UNESCAPED_CHAR)
end
private :single_quote_unescaped_char
def single_quote_escaped_char(scanner)
scanner.scan(TOKEN_SINGLE_QUOTE_ESCAPED_CHAR) && scanner[1]
end
private :single_quote_escaped_char
def single_quote_char(scanner)
single_quote_escaped_char(scanner) || single_quote_unescaped_char(scanner)
end
private :single_quote_char
def double_quote_unescaped_char(scanner)
scanner.scan(TOKEN_DOUBLE_QUOTE_UNESCAPED_CHAR)
end
private :double_quote_unescaped_char
# This handles the possible Ruby escape sequences in double-quoted strings,
# except for \M-x, \M-\C-x, \M-\cx, \c\M-x, \c?, and \C-?. The full list of
# escape sequences, and their meanings is taken from:
# https://github.com/ruby/ruby/blob/90fdfec11a4a42653722e2ce2a672d6e87a57b8e/doc/syntax/literals.rdoc#strings
def double_quote_escaped_char(scanner)
match = scanner.scan(TOKEN_DOUBLE_QUOTE_ESCAPED_CHAR)
return nil if match.nil?
case scanner[1]
when '\\' then '\\'
when '"' then '"'
when 'a' then "\a"
when 'b' then "\b"
when 't' then "\t"
when 'n' then "\n"
when 'v' then "\v"
when 'f' then "\f"
when 'r' then "\r"
when 'e' then "\e"
when 's' then "\s"
when %r{[0-7]}
# Back the scanner up by one byte so we can grab all of the potential
# octal digits at the same time.
scanner.pos = scanner.pos - 1
octal_character = scanner.scan(TOKEN_OCTAL_CHAR)
octal_character.to_i(8).chr
when 'x'
hex_character = scanner.scan(TOKEN_HEX_CHAR)
return nil if hex_character.nil?
hex_character.to_i(16).chr
when 'u'
unicode_short_hex_character(scanner) || unicode_long_hex_characters(scanner)
else
# Not a valid escape sequence as far as we're concerned.
nil
end
end
private :double_quote_escaped_char
def unicode_short_hex_character(scanner)
unicode_character = scanner.scan(TOKEN_UNICODE_SHORT_HEX_CHAR)
return nil if unicode_character.nil?
[unicode_character.hex].pack 'U'
end
private :unicode_short_hex_character
def unicode_long_hex_characters(scanner)
unicode_string = ''
return nil unless scanner.scan(TOKEN_OPEN_CURLY)
loop do
char = scanner.scan(TOKEN_UNICODE_LONG_HEX_CHAR)
break if char.nil?
unicode_string << [char.hex].pack('U')
separator = scanner.scan(TOKEN_SPACE)
break if separator.nil?
end
return nil if scanner.scan(TOKEN_CLOSE_CURLY).nil? || unicode_string.empty?
unicode_string
end
private :unicode_long_hex_characters
def single_quoted_string(scanner)
quoted_string = ''
match = scanner.scan(TOKEN_SINGLE_QUOTE)
return nil if match.nil?
loop do
match = single_quote_char(scanner)
break if match.nil?
quoted_string << match
end
match = scanner.scan(TOKEN_SINGLE_QUOTE)
return quoted_string if match
nil
end
private :single_quoted_string
def double_quote_char(scanner)
double_quote_escaped_char(scanner) || double_quote_unescaped_char(scanner)
end
private :double_quote_char
def double_quoted_string(scanner)
quoted_string = ''
match = scanner.scan(TOKEN_DOUBLE_QUOTE)
return nil if match.nil?
loop do
match = double_quote_char(scanner)
break if match.nil?
quoted_string << match
end
match = scanner.scan(TOKEN_DOUBLE_QUOTE)
return quoted_string if match
nil
end
private :double_quoted_string
def quoted_string(scanner)
single_quoted_string(scanner) || double_quoted_string(scanner)
end
private :quoted_string
def array_values(scanner)
values = []
loop do
match = quoted_string(scanner)
break if match.nil?
values << match
match = array_separator(scanner)
break if match.nil?
end
values
end
private :array_values
end
|
