treetop 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/treetop.rb +6 -0
- data/lib/treetop/api.rb +3 -0
- data/lib/treetop/api/load_grammar.rb +16 -0
- data/lib/treetop/api/malformed_grammar_exception.rb +9 -0
- data/lib/treetop/grammar.rb +7 -0
- data/lib/treetop/grammar/grammar.rb +48 -0
- data/lib/treetop/grammar/grammar_builder.rb +35 -0
- data/lib/treetop/grammar/parsing_expression_builder.rb +5 -0
- data/lib/treetop/grammar/parsing_expression_builder_helper.rb +121 -0
- data/lib/treetop/grammar/parsing_expressions.rb +18 -0
- data/lib/treetop/grammar/parsing_expressions/and_predicate.rb +17 -0
- data/lib/treetop/grammar/parsing_expressions/anything_symbol.rb +20 -0
- data/lib/treetop/grammar/parsing_expressions/character_class.rb +24 -0
- data/lib/treetop/grammar/parsing_expressions/node_instantiating_parsing_expression.rb +14 -0
- data/lib/treetop/grammar/parsing_expressions/node_propagating_parsing_expression.rb +4 -0
- data/lib/treetop/grammar/parsing_expressions/nonterminal_symbol.rb +42 -0
- data/lib/treetop/grammar/parsing_expressions/not_predicate.rb +18 -0
- data/lib/treetop/grammar/parsing_expressions/one_or_more.rb +12 -0
- data/lib/treetop/grammar/parsing_expressions/optional.rb +14 -0
- data/lib/treetop/grammar/parsing_expressions/ordered_choice.rb +27 -0
- data/lib/treetop/grammar/parsing_expressions/parsing_expression.rb +36 -0
- data/lib/treetop/grammar/parsing_expressions/predicate.rb +25 -0
- data/lib/treetop/grammar/parsing_expressions/repeating_parsing_expression.rb +29 -0
- data/lib/treetop/grammar/parsing_expressions/sequence.rb +41 -0
- data/lib/treetop/grammar/parsing_expressions/terminal_parsing_expression.rb +11 -0
- data/lib/treetop/grammar/parsing_expressions/terminal_symbol.rb +31 -0
- data/lib/treetop/grammar/parsing_expressions/zero_or_more.rb +11 -0
- data/lib/treetop/grammar/parsing_rule.rb +10 -0
- data/lib/treetop/metagrammar.rb +2 -0
- data/lib/treetop/metagrammar/metagrammar.rb +14 -0
- data/lib/treetop/metagrammar/metagrammar.treetop +320 -0
- data/lib/treetop/parser.rb +11 -0
- data/lib/treetop/parser/node_cache.rb +25 -0
- data/lib/treetop/parser/parse_cache.rb +17 -0
- data/lib/treetop/parser/parse_failure.rb +22 -0
- data/lib/treetop/parser/parse_result.rb +26 -0
- data/lib/treetop/parser/parser.rb +24 -0
- data/lib/treetop/parser/sequence_syntax_node.rb +14 -0
- data/lib/treetop/parser/syntax_node.rb +31 -0
- data/lib/treetop/parser/terminal_parse_failure.rb +18 -0
- data/lib/treetop/parser/terminal_syntax_node.rb +7 -0
- data/lib/treetop/protometagrammar.rb +16 -0
- data/lib/treetop/protometagrammar/anything_symbol_expression_builder.rb +13 -0
- data/lib/treetop/protometagrammar/block_expression_builder.rb +17 -0
- data/lib/treetop/protometagrammar/character_class_expression_builder.rb +25 -0
- data/lib/treetop/protometagrammar/grammar_expression_builder.rb +38 -0
- data/lib/treetop/protometagrammar/nonterminal_symbol_expression_builder.rb +45 -0
- data/lib/treetop/protometagrammar/ordered_choice_expression_builder.rb +21 -0
- data/lib/treetop/protometagrammar/parsing_rule_expression_builder.rb +23 -0
- data/lib/treetop/protometagrammar/parsing_rule_sequence_expression_builder.rb +14 -0
- data/lib/treetop/protometagrammar/prefix_expression_builder.rb +25 -0
- data/lib/treetop/protometagrammar/primary_expression_builder.rb +71 -0
- data/lib/treetop/protometagrammar/protometagrammar.rb +25 -0
- data/lib/treetop/protometagrammar/sequence_expression_builder.rb +37 -0
- data/lib/treetop/protometagrammar/suffix_expression_builder.rb +33 -0
- data/lib/treetop/protometagrammar/terminal_symbol_expression_builder.rb +52 -0
- data/lib/treetop/protometagrammar/trailing_block_expression_builder.rb +30 -0
- data/lib/treetop/ruby_extension.rb +11 -0
- metadata +110 -0
@@ -0,0 +1,14 @@
|
|
1
|
+
module Treetop
|
2
|
+
class Optional < OrderedChoice
|
3
|
+
attr_reader :expression
|
4
|
+
|
5
|
+
def initialize(optional_expression)
|
6
|
+
super([optional_expression, TerminalSymbol.epsilon])
|
7
|
+
@expression = optional_expression
|
8
|
+
end
|
9
|
+
|
10
|
+
def to_s
|
11
|
+
"(#{expression.to_s})?"
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
module Treetop
|
2
|
+
class OrderedChoice < NodePropagatingParsingExpression
|
3
|
+
attr_reader :alternatives
|
4
|
+
|
5
|
+
def initialize(alternatives)
|
6
|
+
@alternatives = alternatives
|
7
|
+
end
|
8
|
+
|
9
|
+
def to_s
|
10
|
+
parenthesize((alternatives.collect {|alt| alt.to_s}).join(" / "))
|
11
|
+
end
|
12
|
+
|
13
|
+
def parse_at(input, start_index, parser)
|
14
|
+
failures = []
|
15
|
+
for alt in alternatives
|
16
|
+
result = alt.parse_at(input, start_index, parser)
|
17
|
+
if result.success?
|
18
|
+
result.update_nested_failures(collect_nested_failures(failures))
|
19
|
+
return result
|
20
|
+
else
|
21
|
+
failures << result
|
22
|
+
end
|
23
|
+
end
|
24
|
+
return failure_at(start_index, failures)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
module Treetop
|
2
|
+
class ParsingExpression
|
3
|
+
def zero_or_more
|
4
|
+
ZeroOrMore.new(self)
|
5
|
+
end
|
6
|
+
|
7
|
+
def one_or_more
|
8
|
+
OneOrMore.new(self)
|
9
|
+
end
|
10
|
+
|
11
|
+
def optional
|
12
|
+
Optional.new(self)
|
13
|
+
end
|
14
|
+
|
15
|
+
def and_predicate
|
16
|
+
AndPredicate.new(self)
|
17
|
+
end
|
18
|
+
|
19
|
+
def not_predicate
|
20
|
+
NotPredicate.new(self)
|
21
|
+
end
|
22
|
+
|
23
|
+
def parenthesize(string)
|
24
|
+
"(#{string})"
|
25
|
+
end
|
26
|
+
|
27
|
+
protected
|
28
|
+
def failure_at(index, nested_results = [])
|
29
|
+
ParseFailure.new(index, collect_nested_failures(nested_results))
|
30
|
+
end
|
31
|
+
|
32
|
+
def collect_nested_failures(results)
|
33
|
+
(results.collect {|result| result.nested_failures}).flatten
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module Treetop
|
2
|
+
class Predicate < NodePropagatingParsingExpression
|
3
|
+
attr_reader :expression
|
4
|
+
|
5
|
+
def initialize(expression)
|
6
|
+
@expression = expression
|
7
|
+
end
|
8
|
+
|
9
|
+
def parse_at(input, start_index, parser)
|
10
|
+
result = expression.parse_at(input, start_index, parser)
|
11
|
+
|
12
|
+
if result.success?
|
13
|
+
return child_expression_success(start_index, input, result)
|
14
|
+
else
|
15
|
+
return child_expression_failure(start_index, input, result)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
protected
|
20
|
+
|
21
|
+
def success_at(index, input, nested_results)
|
22
|
+
SyntaxNode.new(input, index...index, collect_nested_failures(nested_results))
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
module Treetop
|
2
|
+
class RepeatingParsingExpression < Sequence
|
3
|
+
attr_reader :repeated_expression
|
4
|
+
|
5
|
+
def initialize(repeated_expression)
|
6
|
+
super
|
7
|
+
@repeated_expression = repeated_expression
|
8
|
+
end
|
9
|
+
|
10
|
+
def parse_at(input, start_index, parser)
|
11
|
+
results = []
|
12
|
+
next_index = start_index
|
13
|
+
|
14
|
+
while true
|
15
|
+
result = repeated_expression.parse_at(input, next_index, parser)
|
16
|
+
break if result.failure?
|
17
|
+
results << result
|
18
|
+
next_index = result.interval.end
|
19
|
+
end
|
20
|
+
|
21
|
+
if enough? results
|
22
|
+
interval = start_index...next_index
|
23
|
+
return success(input, interval, results, results + [result])
|
24
|
+
else
|
25
|
+
return failure_at(start_index, results + [result])
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
module Treetop
|
2
|
+
class Sequence < NodeInstantiatingParsingExpression
|
3
|
+
attr_reader :elements, :node_class
|
4
|
+
|
5
|
+
def initialize(elements)
|
6
|
+
super()
|
7
|
+
@elements = elements
|
8
|
+
end
|
9
|
+
|
10
|
+
def node_superclass
|
11
|
+
SequenceSyntaxNode
|
12
|
+
end
|
13
|
+
|
14
|
+
def to_s
|
15
|
+
parenthesize((@elements.collect {|elt| elt.to_s}).join(" "))
|
16
|
+
end
|
17
|
+
|
18
|
+
def parse_at(input, start_index, parser)
|
19
|
+
results = []
|
20
|
+
next_index = start_index
|
21
|
+
|
22
|
+
for elt in elements
|
23
|
+
result = elt.parse_at(input, next_index, parser)
|
24
|
+
results << result
|
25
|
+
return failure_at(start_index, results) if result.failure?
|
26
|
+
next_index = result.interval.end
|
27
|
+
end
|
28
|
+
|
29
|
+
success(input, start_index...next_index, results, results)
|
30
|
+
end
|
31
|
+
|
32
|
+
protected
|
33
|
+
|
34
|
+
def success(input, interval, results, encountered_child_results)
|
35
|
+
return node_class.new(input,
|
36
|
+
interval,
|
37
|
+
results,
|
38
|
+
collect_nested_failures(encountered_child_results))
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
@@ -0,0 +1,31 @@
|
|
1
|
+
module Treetop
|
2
|
+
class TerminalSymbol < TerminalParsingExpression
|
3
|
+
attr_accessor :prefix
|
4
|
+
|
5
|
+
def self.epsilon
|
6
|
+
@epsilon ||= self.new("")
|
7
|
+
end
|
8
|
+
|
9
|
+
def initialize(prefix)
|
10
|
+
super()
|
11
|
+
self.prefix = prefix
|
12
|
+
end
|
13
|
+
|
14
|
+
def epsilon?
|
15
|
+
prefix.blank?
|
16
|
+
end
|
17
|
+
|
18
|
+
def to_s
|
19
|
+
"\"#{prefix}\""
|
20
|
+
end
|
21
|
+
|
22
|
+
def parse_at(input, start_index, parser)
|
23
|
+
|
24
|
+
if input.index(prefix, start_index) == start_index
|
25
|
+
return node_class.new(input, start_index...(prefix.length + start_index))
|
26
|
+
else
|
27
|
+
TerminalParseFailure.new(start_index, self)
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
end
|
@@ -0,0 +1,14 @@
|
|
1
|
+
module Treetop
|
2
|
+
metagrammar_parser = Protometagrammar.new.new_parser
|
3
|
+
|
4
|
+
File.open(File.expand_path('metagrammar.treetop', File.dirname(__FILE__)), 'r') do |file|
|
5
|
+
metagrammar_text = file.read
|
6
|
+
result = metagrammar_parser.parse(metagrammar_text)
|
7
|
+
|
8
|
+
unless result.success?
|
9
|
+
raise 'unable to parse metagrammar'
|
10
|
+
end
|
11
|
+
|
12
|
+
Metagrammar = result.value
|
13
|
+
end
|
14
|
+
end
|
@@ -0,0 +1,320 @@
|
|
1
|
+
grammar Metagrammar
|
2
|
+
rule grammar
|
3
|
+
('grammar' space grammar_name? parsing_rule_sequence space? 'end') {
|
4
|
+
def value
|
5
|
+
grammar = Grammar.new(grammar_name)
|
6
|
+
parsing_rules(grammar).each do |parsing_rule|
|
7
|
+
grammar.add_parsing_rule(parsing_rule)
|
8
|
+
end
|
9
|
+
return grammar
|
10
|
+
end
|
11
|
+
|
12
|
+
def grammar_name
|
13
|
+
if elements[2].epsilon?
|
14
|
+
nil
|
15
|
+
else
|
16
|
+
elements[2].value
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def parsing_rules(grammar)
|
21
|
+
elements[3].value(grammar)
|
22
|
+
end
|
23
|
+
}
|
24
|
+
end
|
25
|
+
|
26
|
+
rule grammar_name
|
27
|
+
([A-Z] alphanumeric_char*) space {
|
28
|
+
def value
|
29
|
+
elements[0].text_value.to_sym
|
30
|
+
end
|
31
|
+
}
|
32
|
+
end
|
33
|
+
|
34
|
+
rule parsing_rule_sequence
|
35
|
+
(parsing_rule (space parsing_rule)*) {
|
36
|
+
def value(grammar)
|
37
|
+
[head.value(grammar)] + tail_values(grammar)
|
38
|
+
end
|
39
|
+
|
40
|
+
def head
|
41
|
+
elements[0]
|
42
|
+
end
|
43
|
+
|
44
|
+
def tail_elements
|
45
|
+
elements[1].elements
|
46
|
+
end
|
47
|
+
|
48
|
+
def tail_values(grammar)
|
49
|
+
tail_elements.collect {|tail_element| tail_element.elements[1].value(grammar)}
|
50
|
+
end
|
51
|
+
}
|
52
|
+
/
|
53
|
+
'' {
|
54
|
+
def value(grammar)
|
55
|
+
[]
|
56
|
+
end
|
57
|
+
}
|
58
|
+
end
|
59
|
+
|
60
|
+
rule parsing_rule
|
61
|
+
('rule' space nonterminal_symbol space ordered_choice space 'end') {
|
62
|
+
def value(grammar)
|
63
|
+
ParsingRule.new(nonterminal_symbol.value(grammar),
|
64
|
+
parsing_expression.value(grammar))
|
65
|
+
end
|
66
|
+
|
67
|
+
def nonterminal_symbol
|
68
|
+
elements[2]
|
69
|
+
end
|
70
|
+
|
71
|
+
def parsing_expression
|
72
|
+
elements[4]
|
73
|
+
end
|
74
|
+
}
|
75
|
+
end
|
76
|
+
|
77
|
+
rule ordered_choice
|
78
|
+
(sequence (space? '/' space? sequence)+) {
|
79
|
+
def value(grammar)
|
80
|
+
OrderedChoice.new(alternatives(grammar))
|
81
|
+
end
|
82
|
+
|
83
|
+
def alternatives(grammar)
|
84
|
+
[head.value(grammar)] + tail_values(grammar)
|
85
|
+
end
|
86
|
+
|
87
|
+
def head
|
88
|
+
elements[0]
|
89
|
+
end
|
90
|
+
|
91
|
+
def tail_elements
|
92
|
+
elements[1].elements
|
93
|
+
end
|
94
|
+
|
95
|
+
def tail_values(grammar)
|
96
|
+
tail_elements.map {|tail_element| tail_element.elements[3].value(grammar)}
|
97
|
+
end
|
98
|
+
}
|
99
|
+
/
|
100
|
+
sequence
|
101
|
+
end
|
102
|
+
|
103
|
+
rule sequence
|
104
|
+
(primary (space primary)+ trailing_block) {
|
105
|
+
def value(grammar)
|
106
|
+
trailing_block.value(Sequence.new(sequence_elements(grammar)))
|
107
|
+
end
|
108
|
+
|
109
|
+
def trailing_block
|
110
|
+
elements[2]
|
111
|
+
end
|
112
|
+
|
113
|
+
def sequence_elements(grammar)
|
114
|
+
[head.value(grammar)] + tail_values(grammar)
|
115
|
+
end
|
116
|
+
|
117
|
+
def head
|
118
|
+
elements[0]
|
119
|
+
end
|
120
|
+
|
121
|
+
def tail_elements
|
122
|
+
elements[1].elements
|
123
|
+
end
|
124
|
+
|
125
|
+
def tail_values(grammar)
|
126
|
+
tail_elements.map {|tail_element| tail_element.elements[1].value(grammar)}
|
127
|
+
end
|
128
|
+
}
|
129
|
+
/
|
130
|
+
primary
|
131
|
+
end
|
132
|
+
|
133
|
+
rule parenthesized_ordered_choice
|
134
|
+
'(' space? ordered_choice space? ')' trailing_block {
|
135
|
+
def value(grammar)
|
136
|
+
nested_value = nested_expression.value(grammar)
|
137
|
+
unless trailing_block.epsilon? || nested_value.kind_of?(NodeInstantiatingParsingExpression)
|
138
|
+
raise "Blocks can only follow node-instantiating parsing expressions such as sequences and terminal symbols."
|
139
|
+
end
|
140
|
+
return trailing_block.value(nested_expression.value(grammar))
|
141
|
+
end
|
142
|
+
|
143
|
+
def nested_expression
|
144
|
+
elements[2]
|
145
|
+
end
|
146
|
+
|
147
|
+
def trailing_block
|
148
|
+
elements[5]
|
149
|
+
end
|
150
|
+
}
|
151
|
+
end
|
152
|
+
|
153
|
+
rule primary
|
154
|
+
(prefix? ((parenthesized_ordered_choice / terminal_symbol / nonterminal_symbol) suffix?)) {
|
155
|
+
def value(grammar)
|
156
|
+
value = primary_expression.value(grammar)
|
157
|
+
value = suffix.value(value) unless suffix.epsilon?
|
158
|
+
value = prefix.value(value) unless prefix.epsilon?
|
159
|
+
value
|
160
|
+
end
|
161
|
+
|
162
|
+
def prefix
|
163
|
+
elements[0]
|
164
|
+
end
|
165
|
+
|
166
|
+
def primary_expression
|
167
|
+
elements[1].elements[0]
|
168
|
+
end
|
169
|
+
|
170
|
+
def suffix
|
171
|
+
elements[1].elements[1]
|
172
|
+
end
|
173
|
+
}
|
174
|
+
end
|
175
|
+
|
176
|
+
rule prefix
|
177
|
+
'&' {
|
178
|
+
def value(parsing_expression)
|
179
|
+
parsing_expression.and_predicate
|
180
|
+
end
|
181
|
+
}
|
182
|
+
/
|
183
|
+
'!' {
|
184
|
+
def value(parsing_expression)
|
185
|
+
parsing_expression.not_predicate
|
186
|
+
end
|
187
|
+
}
|
188
|
+
end
|
189
|
+
|
190
|
+
rule suffix
|
191
|
+
'*' {
|
192
|
+
def value(parsing_expression)
|
193
|
+
parsing_expression.zero_or_more
|
194
|
+
end
|
195
|
+
}
|
196
|
+
/
|
197
|
+
'+' {
|
198
|
+
def value(parsing_expression)
|
199
|
+
parsing_expression.one_or_more
|
200
|
+
end
|
201
|
+
}
|
202
|
+
/
|
203
|
+
'?' {
|
204
|
+
def value(parsing_expression)
|
205
|
+
parsing_expression.optional
|
206
|
+
end
|
207
|
+
}
|
208
|
+
end
|
209
|
+
|
210
|
+
rule nonterminal_symbol
|
211
|
+
(!(keyword !alphanumeric_char) (alpha_char alphanumeric_char*)) {
|
212
|
+
def value(grammar)
|
213
|
+
grammar.nonterminal_symbol(name)
|
214
|
+
end
|
215
|
+
|
216
|
+
def name
|
217
|
+
elements[1].text_value.to_sym
|
218
|
+
end
|
219
|
+
}
|
220
|
+
end
|
221
|
+
|
222
|
+
rule alpha_char
|
223
|
+
[A-Za-z_]
|
224
|
+
end
|
225
|
+
|
226
|
+
rule alphanumeric_char
|
227
|
+
alpha_char / [0-9]
|
228
|
+
end
|
229
|
+
|
230
|
+
rule terminal_symbol
|
231
|
+
terminal_symbol_prefix trailing_block {
|
232
|
+
def value(grammar = nil)
|
233
|
+
trailing_block.value(terminal_symbol.value)
|
234
|
+
end
|
235
|
+
|
236
|
+
def terminal_symbol
|
237
|
+
elements[0]
|
238
|
+
end
|
239
|
+
|
240
|
+
def trailing_block
|
241
|
+
elements[1]
|
242
|
+
end
|
243
|
+
}
|
244
|
+
end
|
245
|
+
|
246
|
+
rule terminal_symbol_prefix
|
247
|
+
single_quoted_string / double_quoted_string / character_class / anything_symbol
|
248
|
+
end
|
249
|
+
|
250
|
+
rule double_quoted_string
|
251
|
+
('"' (!'"' ('\"' / .))* '"') {
|
252
|
+
def value
|
253
|
+
TerminalSymbol.new(elements[1].text_value)
|
254
|
+
end
|
255
|
+
}
|
256
|
+
end
|
257
|
+
|
258
|
+
rule single_quoted_string
|
259
|
+
("'" (!"'" ("\'" / .))* "'") {
|
260
|
+
def value
|
261
|
+
TerminalSymbol.new(elements[1].text_value)
|
262
|
+
end
|
263
|
+
}
|
264
|
+
end
|
265
|
+
|
266
|
+
rule trailing_block
|
267
|
+
space block {
|
268
|
+
def value(parsing_expression)
|
269
|
+
parsing_expression.node_class_eval(block.value)
|
270
|
+
return parsing_expression
|
271
|
+
end
|
272
|
+
|
273
|
+
def block
|
274
|
+
elements[1]
|
275
|
+
end
|
276
|
+
}
|
277
|
+
/
|
278
|
+
'' {
|
279
|
+
def value(parsing_expression)
|
280
|
+
parsing_expression
|
281
|
+
end
|
282
|
+
}
|
283
|
+
end
|
284
|
+
|
285
|
+
rule block
|
286
|
+
('{' (block / ![{}] .)* '}') {
|
287
|
+
def value
|
288
|
+
elements[1].text_value
|
289
|
+
end
|
290
|
+
}
|
291
|
+
end
|
292
|
+
|
293
|
+
rule character_class
|
294
|
+
('[' (!']' ('\]'/.))+ ']') {
|
295
|
+
def value(grammar = nil)
|
296
|
+
CharacterClass.new(characters)
|
297
|
+
end
|
298
|
+
|
299
|
+
def characters
|
300
|
+
elements[1].text_value
|
301
|
+
end
|
302
|
+
}
|
303
|
+
end
|
304
|
+
|
305
|
+
rule keyword
|
306
|
+
'rule' / 'end'
|
307
|
+
end
|
308
|
+
|
309
|
+
rule anything_symbol
|
310
|
+
'.' {
|
311
|
+
def value(grammar = nil)
|
312
|
+
AnythingSymbol.new
|
313
|
+
end
|
314
|
+
}
|
315
|
+
end
|
316
|
+
|
317
|
+
rule space
|
318
|
+
[ \t\n\r]+
|
319
|
+
end
|
320
|
+
end
|