rley 0.7.08 → 0.8.03
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +29 -5
- data/CHANGELOG.md +28 -4
- data/README.md +4 -5
- data/examples/NLP/nano_eng/nano_en_demo.rb +7 -11
- data/examples/NLP/nano_eng/nano_grammar.rb +18 -18
- data/examples/data_formats/JSON/json_ast_builder.rb +9 -18
- data/examples/data_formats/JSON/json_demo.rb +1 -2
- data/examples/data_formats/JSON/json_grammar.rb +11 -11
- data/examples/general/calc_iter1/calc_grammar.rb +5 -4
- data/examples/general/calc_iter2/calc_grammar.rb +9 -9
- data/examples/general/left.rb +1 -1
- data/examples/general/right.rb +1 -1
- data/lib/rley/base/dotted_item.rb +5 -0
- data/lib/rley/base/grm_items_builder.rb +6 -0
- data/lib/rley/constants.rb +1 -1
- data/lib/rley/engine.rb +2 -2
- data/lib/rley/interface.rb +16 -0
- data/lib/rley/notation/all_notation_nodes.rb +4 -0
- data/lib/rley/notation/ast_builder.rb +185 -0
- data/lib/rley/notation/ast_node.rb +44 -0
- data/lib/rley/notation/ast_visitor.rb +115 -0
- data/lib/rley/notation/grammar.rb +49 -0
- data/lib/rley/notation/grammar_builder.rb +505 -0
- data/lib/rley/notation/grouping_node.rb +23 -0
- data/lib/rley/notation/parser.rb +56 -0
- data/lib/rley/notation/sequence_node.rb +35 -0
- data/lib/rley/notation/symbol_node.rb +29 -0
- data/lib/rley/notation/tokenizer.rb +180 -0
- data/lib/rley/parse_rep/ast_base_builder.rb +44 -0
- data/lib/rley/parser/gfg_chart.rb +101 -6
- data/lib/rley/parser/gfg_earley_parser.rb +1 -1
- data/lib/rley/parser/gfg_parsing.rb +5 -3
- data/lib/rley/parser/parse_entry_set.rb +1 -1
- data/lib/rley/syntax/{grammar_builder.rb → base_grammar_builder.rb} +53 -15
- data/lib/rley/syntax/grm_symbol.rb +1 -1
- data/lib/rley/syntax/match_closest.rb +43 -0
- data/lib/rley/syntax/production.rb +6 -0
- data/lib/rley.rb +1 -1
- data/spec/rley/engine_spec.rb +6 -6
- data/spec/rley/gfg/grm_flow_graph_spec.rb +2 -2
- data/spec/rley/notation/grammar_builder_spec.rb +302 -0
- data/spec/rley/notation/parser_spec.rb +183 -0
- data/spec/rley/notation/tokenizer_spec.rb +364 -0
- data/spec/rley/parse_rep/ast_builder_spec.rb +0 -1
- data/spec/rley/parse_rep/groucho_spec.rb +1 -1
- data/spec/rley/parse_rep/parse_forest_builder_spec.rb +1 -1
- data/spec/rley/parse_rep/parse_forest_factory_spec.rb +2 -2
- data/spec/rley/parse_rep/parse_tree_factory_spec.rb +1 -1
- data/spec/rley/parser/dangling_else_spec.rb +447 -0
- data/spec/rley/parser/gfg_earley_parser_spec.rb +118 -10
- data/spec/rley/parser/gfg_parsing_spec.rb +2 -1
- data/spec/rley/parser/parse_walker_factory_spec.rb +2 -2
- data/spec/rley/support/ambiguous_grammar_helper.rb +2 -2
- data/spec/rley/support/grammar_abc_helper.rb +2 -2
- data/spec/rley/support/grammar_ambig01_helper.rb +2 -2
- data/spec/rley/support/grammar_arr_int_helper.rb +2 -2
- data/spec/rley/support/grammar_b_expr_helper.rb +2 -2
- data/spec/rley/support/grammar_int_seq_helper.rb +51 -0
- data/spec/rley/support/grammar_l0_helper.rb +2 -2
- data/spec/rley/support/grammar_pb_helper.rb +2 -2
- data/spec/rley/support/grammar_sppf_helper.rb +2 -2
- data/spec/rley/syntax/{grammar_builder_spec.rb → base_grammar_builder_spec.rb} +29 -11
- data/spec/rley/syntax/match_closest_spec.rb +46 -0
- data/spec/rley/syntax/production_spec.rb +4 -0
- metadata +29 -14
- data/lib/rley/parser/parse_state.rb +0 -78
- data/lib/rley/parser/parse_state_tracker.rb +0 -59
- data/lib/rley/parser/state_set.rb +0 -100
- data/spec/rley/parser/parse_state_spec.rb +0 -125
- data/spec/rley/parser/parse_tracer_spec.rb +0 -200
- data/spec/rley/parser/state_set_spec.rb +0 -130
@@ -0,0 +1,183 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative '../../spec_helper' # Use the RSpec framework
|
4
|
+
|
5
|
+
require_relative '../../../lib/rley/notation/ast_builder'
|
6
|
+
# Load the class under test
|
7
|
+
require_relative '../../../lib/rley/notation/parser'
|
8
|
+
|
9
|
+
module Rley
|
10
|
+
module Notation
|
11
|
+
describe Parser do
|
12
|
+
subject { Parser.new }
|
13
|
+
|
14
|
+
# Utility method to walk towards deeply nested node
|
15
|
+
# @param aNTNode [Rley::PTree::NonTerminalNode]
|
16
|
+
# @param subnodePath[Array<Integer>] An Array of subnode indices
|
17
|
+
def walk_subnodes(aNTNode, subnodePath)
|
18
|
+
curr_node = aNTNode
|
19
|
+
subnodePath.each do |index|
|
20
|
+
curr_node = curr_node.subnodes[index]
|
21
|
+
end
|
22
|
+
|
23
|
+
curr_node
|
24
|
+
end
|
25
|
+
|
26
|
+
context 'Initialization:' do
|
27
|
+
it 'should be initialized without argument' do
|
28
|
+
expect { Parser.new }.not_to raise_error
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'should have its parse engine initialized' do
|
32
|
+
expect(subject.engine).to be_kind_of(Rley::Engine)
|
33
|
+
end
|
34
|
+
end # context
|
35
|
+
|
36
|
+
context 'Parsing into CST:' do
|
37
|
+
subject do
|
38
|
+
instance = Parser.new
|
39
|
+
instance.engine.configuration.repr_builder = Rley::ParseRep::CSTBuilder
|
40
|
+
|
41
|
+
instance
|
42
|
+
end
|
43
|
+
|
44
|
+
it 'should parse single symbol names' do
|
45
|
+
samples = %w[IF ifCondition statement]
|
46
|
+
|
47
|
+
# One drawback od CSTs: they have a deeply nested structure
|
48
|
+
samples.each do |source|
|
49
|
+
ptree = subject.parse(source)
|
50
|
+
expect(ptree.root).to be_kind_of(Rley::PTree::NonTerminalNode)
|
51
|
+
expect(ptree.root.symbol.name).to eq('notation')
|
52
|
+
expect(ptree.root.subnodes[0]).to be_kind_of(Rley::PTree::NonTerminalNode)
|
53
|
+
expect(ptree.root.subnodes[0].symbol.name).to eq('rhs')
|
54
|
+
expect(ptree.root.subnodes[0].subnodes[0]).to be_kind_of(Rley::PTree::NonTerminalNode)
|
55
|
+
member_seq = ptree.root.subnodes[0].subnodes[0]
|
56
|
+
expect(member_seq.symbol.name).to eq('member_seq')
|
57
|
+
expect(member_seq.subnodes[0]).to be_kind_of(Rley::PTree::NonTerminalNode)
|
58
|
+
expect(member_seq.subnodes[0].symbol.name).to eq('member')
|
59
|
+
expect(member_seq.subnodes[0].subnodes[0]).to be_kind_of(Rley::PTree::NonTerminalNode)
|
60
|
+
expect(member_seq.subnodes[0].subnodes[0].symbol.name).to eq('strait_member')
|
61
|
+
strait_member = member_seq.subnodes[0].subnodes[0]
|
62
|
+
expect(strait_member.subnodes[0]).to be_kind_of(Rley::PTree::NonTerminalNode)
|
63
|
+
expect(strait_member.subnodes[0].symbol.name).to eq('base_member')
|
64
|
+
expect(strait_member.subnodes[0].subnodes[0]).to be_kind_of(Rley::PTree::TerminalNode)
|
65
|
+
expect(strait_member.subnodes[0].subnodes[0].token.lexeme).to eq(source)
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end # context
|
69
|
+
|
70
|
+
context 'Parsing into AST:' do
|
71
|
+
subject do
|
72
|
+
instance = Parser.new
|
73
|
+
instance.engine.configuration.repr_builder = ASTBuilder
|
74
|
+
|
75
|
+
instance
|
76
|
+
end
|
77
|
+
|
78
|
+
it 'should parse single symbol names' do
|
79
|
+
samples = %w[IF ifCondition statement]
|
80
|
+
|
81
|
+
samples.each do |source|
|
82
|
+
ptree = subject.parse(source)
|
83
|
+
expect(ptree.root).to be_kind_of(SymbolNode)
|
84
|
+
expect(ptree.root.name).to eq(source)
|
85
|
+
expect(ptree.root.repetition).to eq(:exactly_one)
|
86
|
+
end
|
87
|
+
end
|
88
|
+
|
89
|
+
it 'should parse a sequence of symbols' do
|
90
|
+
sequence = 'INT_LIT ELLIPSIS INT_LIT'
|
91
|
+
|
92
|
+
ptree = subject.parse(sequence)
|
93
|
+
expect(ptree.root).to be_kind_of(SequenceNode)
|
94
|
+
expect(ptree.root.subnodes[0]).to be_kind_of(SymbolNode)
|
95
|
+
expect(ptree.root.subnodes[0].name).to eq('INT_LIT')
|
96
|
+
expect(ptree.root.subnodes[1]).to be_kind_of(SymbolNode)
|
97
|
+
expect(ptree.root.subnodes[1].name).to eq('ELLIPSIS')
|
98
|
+
expect(ptree.root.subnodes[2]).to be_kind_of(SymbolNode)
|
99
|
+
expect(ptree.root.subnodes[2].name).to eq('INT_LIT')
|
100
|
+
end
|
101
|
+
|
102
|
+
it 'should parse an optional symbol' do
|
103
|
+
optional = 'member_seq?'
|
104
|
+
|
105
|
+
ptree = subject.parse(optional)
|
106
|
+
expect(ptree.root).to be_kind_of(SymbolNode)
|
107
|
+
expect(ptree.root.name).to eq('member_seq')
|
108
|
+
expect(ptree.root.repetition).to eq(:zero_or_one)
|
109
|
+
end
|
110
|
+
|
111
|
+
it 'should parse a symbol with a + modifier' do
|
112
|
+
one_or_more = 'member+'
|
113
|
+
|
114
|
+
ptree = subject.parse(one_or_more)
|
115
|
+
expect(ptree.root).to be_kind_of(SymbolNode)
|
116
|
+
expect(ptree.root.name).to eq('member')
|
117
|
+
expect(ptree.root.repetition).to eq(:one_or_more)
|
118
|
+
end
|
119
|
+
|
120
|
+
it 'should parse a symbol with a * modifier' do
|
121
|
+
zero_or_more = 'declaration* EOF'
|
122
|
+
|
123
|
+
ptree = subject.parse(zero_or_more)
|
124
|
+
expect(ptree.root).to be_kind_of(SequenceNode)
|
125
|
+
expect(ptree.root.subnodes[0]).to be_kind_of(SymbolNode)
|
126
|
+
expect(ptree.root.subnodes[0].name).to eq('declaration')
|
127
|
+
expect(ptree.root.subnodes[0].repetition).to eq(:zero_or_more)
|
128
|
+
expect(ptree.root.subnodes[1]).to be_kind_of(SymbolNode)
|
129
|
+
expect(ptree.root.subnodes[1].name).to eq('EOF')
|
130
|
+
expect(ptree.root.subnodes[1].repetition).to eq(:exactly_one)
|
131
|
+
end
|
132
|
+
|
133
|
+
it 'should parse a grouping with a modifier' do
|
134
|
+
input = 'IF ifCondition statement (ELSE statement)?'
|
135
|
+
|
136
|
+
ptree = subject.parse(input)
|
137
|
+
expect(ptree.root).to be_kind_of(SequenceNode)
|
138
|
+
expect(ptree.root.subnodes[0]).to be_kind_of(SymbolNode)
|
139
|
+
expect(ptree.root.subnodes[0].name).to eq('IF')
|
140
|
+
expect(ptree.root.subnodes[1]).to be_kind_of(SymbolNode)
|
141
|
+
expect(ptree.root.subnodes[1].name).to eq('ifCondition')
|
142
|
+
expect(ptree.root.subnodes[2]).to be_kind_of(SymbolNode)
|
143
|
+
expect(ptree.root.subnodes[2].name).to eq('statement')
|
144
|
+
expect(ptree.root.subnodes[3]).to be_kind_of(SequenceNode)
|
145
|
+
expect(ptree.root.subnodes[3].repetition).to eq(:zero_or_one)
|
146
|
+
expect(ptree.root.subnodes[3].subnodes[0]).to be_kind_of(SymbolNode)
|
147
|
+
expect(ptree.root.subnodes[3].subnodes[0].name).to eq('ELSE')
|
148
|
+
expect(ptree.root.subnodes[3].subnodes[1]).to be_kind_of(SymbolNode)
|
149
|
+
expect(ptree.root.subnodes[3].subnodes[1].name).to eq('statement')
|
150
|
+
end
|
151
|
+
|
152
|
+
it 'should parse an annotated symbol' do
|
153
|
+
optional = 'member_seq{repeat: 0..1}'
|
154
|
+
|
155
|
+
ptree = subject.parse(optional)
|
156
|
+
expect(ptree.root).to be_kind_of(SymbolNode)
|
157
|
+
expect(ptree.root.name).to eq('member_seq')
|
158
|
+
expect(ptree.root.repetition).to eq(:zero_or_one)
|
159
|
+
end
|
160
|
+
|
161
|
+
it 'should parse a grouping with embedded annotation' do
|
162
|
+
if_stmt = "IF ifCondition statement ( ELSE { match_closest: 'IF' } statement )?"
|
163
|
+
|
164
|
+
ptree = subject.parse(if_stmt)
|
165
|
+
expect(ptree.root).to be_kind_of(SequenceNode)
|
166
|
+
expect(ptree.root.subnodes[0]).to be_kind_of(SymbolNode)
|
167
|
+
expect(ptree.root.subnodes[0].name).to eq('IF')
|
168
|
+
expect(ptree.root.subnodes[1]).to be_kind_of(SymbolNode)
|
169
|
+
expect(ptree.root.subnodes[1].name).to eq('ifCondition')
|
170
|
+
expect(ptree.root.subnodes[2]).to be_kind_of(SymbolNode)
|
171
|
+
expect(ptree.root.subnodes[2].name).to eq('statement')
|
172
|
+
optional = ptree.root.subnodes[3]
|
173
|
+
expect(optional).to be_kind_of(SequenceNode)
|
174
|
+
expect(optional.repetition).to eq(:zero_or_one)
|
175
|
+
expect(optional.subnodes[0]).to be_kind_of(SymbolNode)
|
176
|
+
expect(optional.subnodes[0].name).to eq('ELSE')
|
177
|
+
expect(optional.subnodes[0].annotation).to eq({ 'match_closest' => 'IF' })
|
178
|
+
expect(optional.subnodes[1].name).to eq('statement')
|
179
|
+
end
|
180
|
+
end # context
|
181
|
+
end # describe
|
182
|
+
end # module
|
183
|
+
end # module
|
@@ -0,0 +1,364 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative '../../spec_helper'
|
4
|
+
|
5
|
+
# Load the class under test
|
6
|
+
require_relative '../../../lib/rley/notation/tokenizer'
|
7
|
+
|
8
|
+
module Rley # Open this namespace to avoid module qualifier prefixes
|
9
|
+
module Notation # Open this namespace to avoid module qualifier prefixes
|
10
|
+
describe Tokenizer do
|
11
|
+
# Utility method for comparing actual and expected token
|
12
|
+
# sequence. The final EOF is removed from the input sequence.
|
13
|
+
def match_expectations(aScanner, theExpectations)
|
14
|
+
tokens = aScanner.tokens
|
15
|
+
|
16
|
+
tokens.each_with_index do |token, i|
|
17
|
+
terminal, lexeme = theExpectations[i]
|
18
|
+
expect(token.terminal).to eq(terminal)
|
19
|
+
expect(token.lexeme).to eq(lexeme)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
context 'Initialization:' do
|
24
|
+
let(:sample_text) { 'begin-object member-list end-object' }
|
25
|
+
subject { Tokenizer.new }
|
26
|
+
|
27
|
+
it 'could be initialized with a text to tokenize or...' do
|
28
|
+
expect { Tokenizer.new(sample_text) }.not_to raise_error
|
29
|
+
end
|
30
|
+
|
31
|
+
it 'could be initialized without argument...' do
|
32
|
+
expect { Tokenizer.new }.not_to raise_error
|
33
|
+
end
|
34
|
+
|
35
|
+
it 'should have its scanner initialized' do
|
36
|
+
expect(subject.scanner).to be_kind_of(StringScanner)
|
37
|
+
end
|
38
|
+
end # context
|
39
|
+
|
40
|
+
context 'Input tokenization:' do
|
41
|
+
it 'should recognize single special character token' do
|
42
|
+
input = '(){}?*+,'
|
43
|
+
subject.start_with(input)
|
44
|
+
expectations = [
|
45
|
+
# [token lexeme]
|
46
|
+
%w[LEFT_PAREN (],
|
47
|
+
%w[RIGHT_PAREN )],
|
48
|
+
%w[LEFT_BRACE {],
|
49
|
+
%w[RIGHT_BRACE }],
|
50
|
+
%w[QUESTION_MARK ?],
|
51
|
+
%w[STAR *],
|
52
|
+
%w[PLUS +],
|
53
|
+
%w[COMMA ,]
|
54
|
+
]
|
55
|
+
match_expectations(subject, expectations)
|
56
|
+
end
|
57
|
+
|
58
|
+
it 'should recognize one or two special character tokens' do
|
59
|
+
input = '..'
|
60
|
+
subject.start_with(input)
|
61
|
+
expectations = [
|
62
|
+
# [token lexeme]
|
63
|
+
%w[ELLIPSIS ..]
|
64
|
+
]
|
65
|
+
match_expectations(subject, expectations)
|
66
|
+
end
|
67
|
+
|
68
|
+
it 'should treat ? * + as symbols if they occur as suffix' do
|
69
|
+
input = 'a+ + b* * 3 ?'
|
70
|
+
subject.start_with(input)
|
71
|
+
expectations = [
|
72
|
+
# [token lexeme]
|
73
|
+
%w[SYMBOL a],
|
74
|
+
%w[PLUS +],
|
75
|
+
%w[SYMBOL +],
|
76
|
+
%w[SYMBOL b],
|
77
|
+
%w[STAR *],
|
78
|
+
%w[SYMBOL *],
|
79
|
+
%w[INT_LIT 3],
|
80
|
+
%w[SYMBOL ?]
|
81
|
+
]
|
82
|
+
match_expectations(subject, expectations)
|
83
|
+
end
|
84
|
+
|
85
|
+
it 'should recognize annotation keywords' do
|
86
|
+
keywords = 'match_closest: repeat:'
|
87
|
+
subject.start_with(keywords)
|
88
|
+
expectations = [
|
89
|
+
# [token lexeme]
|
90
|
+
%w[KEY match_closest],
|
91
|
+
%w[KEY repeat]
|
92
|
+
]
|
93
|
+
match_expectations(subject, expectations)
|
94
|
+
end
|
95
|
+
|
96
|
+
it 'should recognize ordinal integer values' do
|
97
|
+
input = <<-RLEY_END
|
98
|
+
3 123
|
99
|
+
987654 0
|
100
|
+
RLEY_END
|
101
|
+
|
102
|
+
expectations = [
|
103
|
+
['3', 3],
|
104
|
+
['123', 123],
|
105
|
+
['987654', 987654],
|
106
|
+
['0', 0]
|
107
|
+
]
|
108
|
+
|
109
|
+
subject.start_with(input)
|
110
|
+
subject.tokens[0..-2].each_with_index do |tok, i|
|
111
|
+
expect(tok).to be_kind_of(Rley::Lexical::Token)
|
112
|
+
expect(tok.terminal).to eq('INT_LIT')
|
113
|
+
(lexeme,) = expectations[i]
|
114
|
+
expect(tok.lexeme).to eq(lexeme)
|
115
|
+
end
|
116
|
+
end
|
117
|
+
|
118
|
+
it 'should recognize string literals' do
|
119
|
+
input = <<-RLEY_END
|
120
|
+
""
|
121
|
+
"string"
|
122
|
+
"123"
|
123
|
+
''
|
124
|
+
'string'
|
125
|
+
'123'
|
126
|
+
RLEY_END
|
127
|
+
|
128
|
+
expectations = [
|
129
|
+
'',
|
130
|
+
'string',
|
131
|
+
'123'
|
132
|
+
] * 2
|
133
|
+
|
134
|
+
subject.start_with(input)
|
135
|
+
subject.tokens.each_with_index do |str, i|
|
136
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
137
|
+
expect(str.terminal).to eq('STR_LIT')
|
138
|
+
(lexeme,) = expectations[i]
|
139
|
+
expect(str.lexeme).to eq(lexeme)
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
it 'should recognize a sequence of symbols' do
|
144
|
+
input = 'IF ifCondition statement ELSE statement'
|
145
|
+
expectations = %w[IF ifCondition statement ELSE statement]
|
146
|
+
|
147
|
+
subject.start_with(input)
|
148
|
+
subject.tokens.each_with_index do |str, i|
|
149
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
150
|
+
expect(str.terminal).to eq('SYMBOL')
|
151
|
+
(lexeme,) = expectations[i]
|
152
|
+
expect(str.lexeme).to eq(lexeme)
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
it 'should recognize an optional symbol' do
|
157
|
+
input = 'RETURN expression? SEMICOLON'
|
158
|
+
expectations = [
|
159
|
+
%w[RETURN SYMBOL],
|
160
|
+
%w[expression SYMBOL],
|
161
|
+
%w[? QUESTION_MARK],
|
162
|
+
%w[SEMICOLON SYMBOL]
|
163
|
+
]
|
164
|
+
|
165
|
+
subject.start_with(input)
|
166
|
+
subject.tokens.each_with_index do |str, i|
|
167
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
168
|
+
(lexeme, token) = expectations[i]
|
169
|
+
expect(str.lexeme).to eq(lexeme)
|
170
|
+
expect(str.terminal).to eq(token)
|
171
|
+
end
|
172
|
+
end
|
173
|
+
|
174
|
+
it 'should recognize a symbol with a star quantifier' do
|
175
|
+
input = 'declaration* EOF'
|
176
|
+
expectations = [
|
177
|
+
%w[declaration SYMBOL],
|
178
|
+
%w[* STAR],
|
179
|
+
%w[EOF SYMBOL]
|
180
|
+
]
|
181
|
+
|
182
|
+
subject.start_with(input)
|
183
|
+
subject.tokens.each_with_index do |str, i|
|
184
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
185
|
+
(lexeme, token) = expectations[i]
|
186
|
+
expect(str.lexeme).to eq(lexeme)
|
187
|
+
expect(str.terminal).to eq(token)
|
188
|
+
end
|
189
|
+
end
|
190
|
+
|
191
|
+
it 'should recognize a symbol with a plus quantifier' do
|
192
|
+
input = 'declaration+ EOF'
|
193
|
+
expectations = [
|
194
|
+
%w[declaration SYMBOL],
|
195
|
+
%w[+ PLUS],
|
196
|
+
%w[EOF SYMBOL]
|
197
|
+
]
|
198
|
+
|
199
|
+
subject.start_with(input)
|
200
|
+
subject.tokens.each_with_index do |str, i|
|
201
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
202
|
+
(lexeme, token) = expectations[i]
|
203
|
+
expect(str.lexeme).to eq(lexeme)
|
204
|
+
expect(str.terminal).to eq(token)
|
205
|
+
end
|
206
|
+
end
|
207
|
+
|
208
|
+
it 'should recognize a grouping with a quantifier' do
|
209
|
+
input = 'IF ifCondition statement (ELSE statement)?'
|
210
|
+
expectations = [
|
211
|
+
%w[IF SYMBOL],
|
212
|
+
%w[ifCondition SYMBOL],
|
213
|
+
%w[statement SYMBOL],
|
214
|
+
%w[( LEFT_PAREN],
|
215
|
+
%w[ELSE SYMBOL],
|
216
|
+
%w[statement SYMBOL],
|
217
|
+
%w[) RIGHT_PAREN],
|
218
|
+
%w[? QUESTION_MARK]
|
219
|
+
]
|
220
|
+
|
221
|
+
subject.start_with(input)
|
222
|
+
subject.tokens.each_with_index do |str, i|
|
223
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
224
|
+
(lexeme, token) = expectations[i]
|
225
|
+
expect(str.lexeme).to eq(lexeme)
|
226
|
+
expect(str.terminal).to eq(token)
|
227
|
+
end
|
228
|
+
end
|
229
|
+
|
230
|
+
it 'should recognize a match closest constraint' do
|
231
|
+
input = "IF ifCondition statement ELSE { match_closest: 'IF' } statement"
|
232
|
+
expectations = [
|
233
|
+
%w[IF SYMBOL],
|
234
|
+
%w[ifCondition SYMBOL],
|
235
|
+
%w[statement SYMBOL],
|
236
|
+
%w[ELSE SYMBOL],
|
237
|
+
%w[{ LEFT_BRACE],
|
238
|
+
%w[match_closest KEY],
|
239
|
+
%w[IF STR_LIT],
|
240
|
+
%w[} RIGHT_BRACE],
|
241
|
+
%w[statement SYMBOL]
|
242
|
+
]
|
243
|
+
|
244
|
+
subject.start_with(input)
|
245
|
+
subject.tokens.each_with_index do |str, i|
|
246
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
247
|
+
(lexeme, token) = expectations[i]
|
248
|
+
expect(str.lexeme).to eq(lexeme)
|
249
|
+
expect(str.terminal).to eq(token)
|
250
|
+
end
|
251
|
+
end
|
252
|
+
|
253
|
+
it 'should recognize a repeat constraint' do
|
254
|
+
input = 'IF ifCondition statement { repeat: 1 } ELSE statement'
|
255
|
+
expectations = [
|
256
|
+
%w[IF SYMBOL],
|
257
|
+
%w[ifCondition SYMBOL],
|
258
|
+
%w[statement SYMBOL],
|
259
|
+
%w[{ LEFT_BRACE],
|
260
|
+
%w[repeat KEY],
|
261
|
+
%w[1 INT_LIT],
|
262
|
+
%w[} RIGHT_BRACE],
|
263
|
+
%w[ELSE SYMBOL],
|
264
|
+
%w[statement SYMBOL]
|
265
|
+
]
|
266
|
+
|
267
|
+
subject.start_with(input)
|
268
|
+
subject.tokens.each_with_index do |str, i|
|
269
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
270
|
+
(lexeme, token) = expectations[i]
|
271
|
+
expect(str.lexeme).to eq(lexeme)
|
272
|
+
expect(str.terminal).to eq(token)
|
273
|
+
end
|
274
|
+
end
|
275
|
+
|
276
|
+
it 'should recognize a grouping with a repeat constraint' do
|
277
|
+
input = 'IF ifCondition statement ( ELSE statement ){ repeat: 0..1 }'
|
278
|
+
expectations = [
|
279
|
+
%w[IF SYMBOL],
|
280
|
+
%w[ifCondition SYMBOL],
|
281
|
+
%w[statement SYMBOL],
|
282
|
+
%w[( LEFT_PAREN],
|
283
|
+
%w[ELSE SYMBOL],
|
284
|
+
%w[statement SYMBOL],
|
285
|
+
%w[) RIGHT_PAREN],
|
286
|
+
%w[{ LEFT_BRACE],
|
287
|
+
%w[repeat KEY],
|
288
|
+
%w[0 INT_LIT],
|
289
|
+
%w[.. ELLIPSIS],
|
290
|
+
%w[1 INT_LIT],
|
291
|
+
%w[} RIGHT_BRACE]
|
292
|
+
]
|
293
|
+
|
294
|
+
subject.start_with(input)
|
295
|
+
subject.tokens.each_with_index do |str, i|
|
296
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
297
|
+
(lexeme, token) = expectations[i]
|
298
|
+
expect(str.lexeme).to eq(lexeme)
|
299
|
+
expect(str.terminal).to eq(token)
|
300
|
+
end
|
301
|
+
end
|
302
|
+
|
303
|
+
it 'should recognize a combination of constraints' do
|
304
|
+
input = "IF ifCondition statement ELSE { repeat: 1, match_closest: 'IF' } statement"
|
305
|
+
expectations = [
|
306
|
+
%w[IF SYMBOL],
|
307
|
+
%w[ifCondition SYMBOL],
|
308
|
+
%w[statement SYMBOL],
|
309
|
+
%w[ELSE SYMBOL],
|
310
|
+
%w[{ LEFT_BRACE],
|
311
|
+
%w[repeat KEY],
|
312
|
+
%w[1 INT_LIT],
|
313
|
+
%w[, COMMA],
|
314
|
+
%w[match_closest KEY],
|
315
|
+
%w[IF STR_LIT],
|
316
|
+
%w[} RIGHT_BRACE],
|
317
|
+
%w[statement SYMBOL]
|
318
|
+
]
|
319
|
+
|
320
|
+
subject.start_with(input)
|
321
|
+
subject.tokens.each_with_index do |str, i|
|
322
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
323
|
+
(lexeme, token) = expectations[i]
|
324
|
+
expect(str.lexeme).to eq(lexeme)
|
325
|
+
expect(str.terminal).to eq(token)
|
326
|
+
end
|
327
|
+
end
|
328
|
+
|
329
|
+
it 'should recognize a grouping with a nested constraint' do
|
330
|
+
input = "IF ifCondition statement ( ELSE { match_closest: 'IF' } statement ){ repeat: 0..1 }"
|
331
|
+
expectations = [
|
332
|
+
%w[IF SYMBOL],
|
333
|
+
%w[ifCondition SYMBOL],
|
334
|
+
%w[statement SYMBOL],
|
335
|
+
%w[( LEFT_PAREN],
|
336
|
+
%w[ELSE SYMBOL],
|
337
|
+
%w[{ LEFT_BRACE],
|
338
|
+
%w[match_closest KEY],
|
339
|
+
%w[IF STR_LIT],
|
340
|
+
%w[} RIGHT_BRACE],
|
341
|
+
%w[statement SYMBOL],
|
342
|
+
%w[) RIGHT_PAREN],
|
343
|
+
%w[{ LEFT_BRACE],
|
344
|
+
%w[repeat KEY],
|
345
|
+
%w[0 INT_LIT],
|
346
|
+
%w[.. ELLIPSIS],
|
347
|
+
%w[1 INT_LIT],
|
348
|
+
%w[} RIGHT_BRACE]
|
349
|
+
]
|
350
|
+
|
351
|
+
subject.start_with(input)
|
352
|
+
subject.tokens.each_with_index do |str, i|
|
353
|
+
expect(str).to be_kind_of(Rley::Lexical::Token)
|
354
|
+
(lexeme, token) = expectations[i]
|
355
|
+
expect(str.lexeme).to eq(lexeme)
|
356
|
+
expect(str.terminal).to eq(token)
|
357
|
+
end
|
358
|
+
end
|
359
|
+
end # context
|
360
|
+
end # describe
|
361
|
+
end # module
|
362
|
+
end # module
|
363
|
+
|
364
|
+
# End of file
|