dhaka 2.1.0 → 2.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/evaluator/evaluator.rb +18 -17
- data/lib/grammar/grammar.rb +4 -5
- data/lib/lexer/dfa.rb +63 -13
- data/lib/lexer/lexeme.rb +3 -4
- data/lib/lexer/lexer.rb +12 -3
- data/lib/lexer/lexer_run.rb +22 -10
- data/lib/lexer/regex_grammar.rb +88 -14
- data/lib/lexer/regex_parser.rb +1523 -1401
- data/lib/lexer/specification.rb +29 -3
- data/lib/lexer/state.rb +32 -9
- data/lib/lexer/state_machine.rb +2 -2
- data/lib/parser/channel.rb +4 -4
- data/lib/parser/parser.rb +17 -12
- data/lib/parser/parser_state.rb +3 -1
- data/test/chittagong/chittagong_lexer.rb +63 -63
- data/test/chittagong/chittagong_lexer.rb.rej +189 -0
- data/test/chittagong/chittagong_lexer_specification.rb +6 -8
- data/test/chittagong/chittagong_parser.rb +659 -659
- data/test/chittagong/chittagong_parser.rb.rej +1623 -0
- data/test/{another_lalr_but_not_slr_grammar.rb → core/another_lalr_but_not_slr_grammar.rb} +1 -1
- data/test/{compiled_parser_test.rb → core/compiled_parser_test.rb} +1 -1
- data/test/core/dfa_test.rb +170 -0
- data/test/{evaluator_test.rb → core/evaluator_test.rb} +3 -3
- data/test/{grammar_test.rb → core/grammar_test.rb} +3 -3
- data/test/{lalr_but_not_slr_grammar.rb → core/lalr_but_not_slr_grammar.rb} +0 -0
- data/test/core/lexer_test.rb +139 -0
- data/test/{malformed_grammar.rb → core/malformed_grammar.rb} +0 -0
- data/test/{malformed_grammar_test.rb → core/malformed_grammar_test.rb} +1 -1
- data/test/{nullable_grammar.rb → core/nullable_grammar.rb} +0 -0
- data/test/{parse_result_test.rb → core/parse_result_test.rb} +1 -1
- data/test/{parser_state_test.rb → core/parser_state_test.rb} +1 -1
- data/test/{parser_test.rb → core/parser_test.rb} +2 -2
- data/test/{precedence_grammar.rb → core/precedence_grammar.rb} +0 -0
- data/test/{precedence_grammar_test.rb → core/precedence_grammar_test.rb} +1 -1
- data/test/{rr_conflict_grammar.rb → core/rr_conflict_grammar.rb} +0 -0
- data/test/{simple_grammar.rb → core/simple_grammar.rb} +0 -0
- data/test/{sr_conflict_grammar.rb → core/sr_conflict_grammar.rb} +0 -0
- metadata +25 -22
- data/test/lexer_test.rb +0 -215
data/test/lexer_test.rb
DELETED
@@ -1,215 +0,0 @@
|
|
1
|
-
require File.dirname(__FILE__) + '/dhaka_test_helper'
|
2
|
-
|
3
|
-
class TestLexer < Test::Unit::TestCase
|
4
|
-
def test_build_AST_from_parse_tree_and_compute_follow_first_and_last
|
5
|
-
root = Dhaka::LexerSupport::RegexParser.parse(Dhaka::LexerSupport::RegexTokenizer.tokenize("(a|b)*abb"))
|
6
|
-
star_node = root.left.left.left.left
|
7
|
-
or_node = star_node.child
|
8
|
-
first_a = or_node.children[0]
|
9
|
-
first_b = or_node.children[1]
|
10
|
-
second_a = root.left.left.left.right
|
11
|
-
second_b = root.left.left.right
|
12
|
-
last_b = root.left.right
|
13
|
-
sentinel = root.right
|
14
|
-
|
15
|
-
assert(!root.nullable)
|
16
|
-
assert(!root.left.nullable)
|
17
|
-
assert(!root.left.left.nullable)
|
18
|
-
assert(star_node.nullable)
|
19
|
-
|
20
|
-
assert_equal(Set.new([first_a, first_b, second_a]), root.first)
|
21
|
-
assert_equal(Set.new([last_b]), root.left.last)
|
22
|
-
|
23
|
-
root.calculate_follow_sets
|
24
|
-
|
25
|
-
assert_equal(Set.new([first_a, first_b, second_a]), first_a.follow_set)
|
26
|
-
assert_equal(Set.new([first_a, first_b, second_a]), first_b.follow_set)
|
27
|
-
assert_equal(Set.new([second_b]), second_a.follow_set)
|
28
|
-
assert_equal(Set.new([last_b]), second_b.follow_set)
|
29
|
-
assert_equal(Set.new([sentinel]), last_b.follow_set)
|
30
|
-
end
|
31
|
-
|
32
|
-
def test_DFA_raises_exception_if_empty_regex
|
33
|
-
machine = Dhaka::LexerSupport::DFA.new("")
|
34
|
-
flunk "Should have thrown an unexpected end of regex exception"
|
35
|
-
rescue Dhaka::LexerSupport::InvalidRegexException => e
|
36
|
-
assert_equal("Unexpected end of regex.", e.message)
|
37
|
-
end
|
38
|
-
|
39
|
-
def test_DFA_raises_exception_if_error_parsing_regex
|
40
|
-
machine = Dhaka::LexerSupport::DFA.new("(a|b)*+abb")
|
41
|
-
flunk "Should have thrown an unexpected token exception"
|
42
|
-
rescue Dhaka::LexerSupport::InvalidRegexException => e
|
43
|
-
assert_equal("Unexpected token +: (a|b)*>>>+abb", e.message)
|
44
|
-
end
|
45
|
-
|
46
|
-
def test_match_a_regex
|
47
|
-
machine = Dhaka::LexerSupport::DFA.new("(a|b)*abb")
|
48
|
-
assert(machine.matches("abababb"))
|
49
|
-
assert(machine.matches("ababaabb"))
|
50
|
-
assert(!machine.matches("abababab"))
|
51
|
-
assert(!machine.matches("abababbc"))
|
52
|
-
assert(!machine.matches("abababbaa"))
|
53
|
-
end
|
54
|
-
|
55
|
-
def test_match_a_regex_with_optional_characters_at_the_end
|
56
|
-
machine = Dhaka::LexerSupport::DFA.new("bad(c|d)+(ab)*")
|
57
|
-
assert(machine.matches("badccddabab"))
|
58
|
-
assert(machine.matches("baddcc"))
|
59
|
-
assert(!machine.matches("badab"))
|
60
|
-
assert(!machine.matches("bacdab"))
|
61
|
-
end
|
62
|
-
|
63
|
-
def test_match_a_nullable_regex
|
64
|
-
machine = Dhaka::LexerSupport::DFA.new("(ab)*")
|
65
|
-
assert(machine.matches("abab"))
|
66
|
-
assert(machine.matches("ab"))
|
67
|
-
assert(machine.matches(""))
|
68
|
-
assert(!machine.matches("b"))
|
69
|
-
end
|
70
|
-
|
71
|
-
def test_match_a_regex_with_the_dot_character
|
72
|
-
machine = Dhaka::LexerSupport::DFA.new("ab.*cd")
|
73
|
-
assert(machine.matches("abacd"))
|
74
|
-
assert(machine.matches("abcd"))
|
75
|
-
assert(machine.matches("abAcd"))
|
76
|
-
assert(!machine.matches("ab999c"))
|
77
|
-
end
|
78
|
-
|
79
|
-
def test_match_a_regex_with_sets
|
80
|
-
machine = Dhaka::LexerSupport::DFA.new("ab[j-lu]*cd")
|
81
|
-
assert(!machine.matches("abacd"))
|
82
|
-
assert(machine.matches("abcd"))
|
83
|
-
assert(machine.matches("abjklucd"))
|
84
|
-
assert(!machine.matches("abijklucd"))
|
85
|
-
assert(!machine.matches("ab999c"))
|
86
|
-
end
|
87
|
-
|
88
|
-
def test_match_a_regex_with_negative_sets
|
89
|
-
machine = Dhaka::LexerSupport::DFA.new("ab[^j-lr]*cd")
|
90
|
-
assert(machine.matches("abcd"))
|
91
|
-
assert(!machine.matches("abjcd"))
|
92
|
-
assert(!machine.matches("abrcd"))
|
93
|
-
assert(!machine.matches("abijklucd"))
|
94
|
-
assert(machine.matches("abyqcd"))
|
95
|
-
end
|
96
|
-
|
97
|
-
def test_match_a_regex_with_sets_containing_escaped_characters
|
98
|
-
machine = Dhaka::LexerSupport::DFA.new("ab[\\^\\-.]*cd")
|
99
|
-
assert(machine.matches("abcd"))
|
100
|
-
assert(!machine.matches("abjcd"))
|
101
|
-
assert(machine.matches("ab^-.cd"))
|
102
|
-
assert(!machine.matches("abijklucd"))
|
103
|
-
assert(!machine.matches("ab\\cd"))
|
104
|
-
end
|
105
|
-
|
106
|
-
def test_match_a_regex_using_unescaped_caret_and_dash_characters
|
107
|
-
machine = Dhaka::LexerSupport::DFA.new("(\\^-)+")
|
108
|
-
assert(machine.matches("^-"))
|
109
|
-
assert(machine.matches("^-^-"))
|
110
|
-
assert(!machine.matches("?cd"))
|
111
|
-
end
|
112
|
-
|
113
|
-
def test_match_a_regex_using_escape_characters
|
114
|
-
machine = Dhaka::LexerSupport::DFA.new(%q/(-\?\(\)\\\\)*/)
|
115
|
-
assert(machine.matches("-?()\\"))
|
116
|
-
end
|
117
|
-
|
118
|
-
def test_match_a_regex_using_lt_and_gt
|
119
|
-
machine = Dhaka::LexerSupport::DFA.new('<.+>')
|
120
|
-
assert(machine.matches("<ab>"))
|
121
|
-
assert(machine.matches("<absdf><sdg><sse>"))
|
122
|
-
assert(!machine.matches("ab>"))
|
123
|
-
end
|
124
|
-
|
125
|
-
def test_simulating_curly_brace_quantifiers
|
126
|
-
machine = Dhaka::LexerSupport::DFA.new('aaa?a?a?')
|
127
|
-
assert(machine.matches("aa"))
|
128
|
-
assert(machine.matches("aaa"))
|
129
|
-
assert(machine.matches("aaaa"))
|
130
|
-
assert(machine.matches("aaaaa"))
|
131
|
-
assert(!machine.matches("aaaaaa"))
|
132
|
-
assert(!machine.matches("a"))
|
133
|
-
end
|
134
|
-
|
135
|
-
class LexerSpec < Dhaka::LexerSpecification
|
136
|
-
|
137
|
-
for_pattern 'zz' do
|
138
|
-
"recognized two zs"
|
139
|
-
end
|
140
|
-
|
141
|
-
for_pattern '\w(\w|\d)*' do
|
142
|
-
"recognized word token #{current_lexeme.value}"
|
143
|
-
end
|
144
|
-
|
145
|
-
for_pattern '(\d)*(\.\d+)?' do
|
146
|
-
"recognized number #{current_lexeme.value}"
|
147
|
-
end
|
148
|
-
|
149
|
-
for_pattern '<.*>' do
|
150
|
-
"recognized tag #{current_lexeme.value}"
|
151
|
-
end
|
152
|
-
|
153
|
-
for_pattern ' +' do
|
154
|
-
#ignores whitespace
|
155
|
-
end
|
156
|
-
|
157
|
-
for_pattern "\n+" do
|
158
|
-
"recognized newline"
|
159
|
-
end
|
160
|
-
end
|
161
|
-
|
162
|
-
def test_lexer_with_valid_input
|
163
|
-
lexer = Dhaka::Lexer.new(LexerSpec)
|
164
|
-
eval(lexer.compile_to_ruby_source_as(:SomeLexer))
|
165
|
-
input = "these are words a z zz caPITALIZED word
|
166
|
-
this is a float 12.00 an integer 134 a float without a leading digit .2335 another word1"
|
167
|
-
results = SomeLexer.lex(input).collect
|
168
|
-
assert_equal(
|
169
|
-
["recognized word token these",
|
170
|
-
"recognized word token are",
|
171
|
-
"recognized word token words",
|
172
|
-
"recognized word token a",
|
173
|
-
"recognized word token z",
|
174
|
-
"recognized two zs",
|
175
|
-
"recognized word token caPITALIZED",
|
176
|
-
"recognized word token word",
|
177
|
-
"recognized newline",
|
178
|
-
"recognized word token this",
|
179
|
-
"recognized word token is",
|
180
|
-
"recognized word token a",
|
181
|
-
"recognized word token float",
|
182
|
-
"recognized number 12.00",
|
183
|
-
"recognized word token an",
|
184
|
-
"recognized word token integer",
|
185
|
-
"recognized number 134",
|
186
|
-
"recognized word token a",
|
187
|
-
"recognized word token float",
|
188
|
-
"recognized word token without",
|
189
|
-
"recognized word token a",
|
190
|
-
"recognized word token leading",
|
191
|
-
"recognized word token digit",
|
192
|
-
"recognized number .2335",
|
193
|
-
"recognized word token another",
|
194
|
-
"recognized word token word1"], results[0..-2])
|
195
|
-
end
|
196
|
-
|
197
|
-
def test_lexer_with_invalid_input
|
198
|
-
lexer = Dhaka::Lexer.new(LexerSpec)
|
199
|
-
result = lexer.lex("this will cause an error here 123.").each do |result|
|
200
|
-
end
|
201
|
-
assert(result.has_error?)
|
202
|
-
assert_equal(34, result.unexpected_char_index)
|
203
|
-
end
|
204
|
-
|
205
|
-
def test_lexer_with_greedy_character_consumption
|
206
|
-
lexer = Dhaka::Lexer.new(LexerSpec)
|
207
|
-
results = lexer.lex("<html></html>this is a word").collect
|
208
|
-
assert_equal(["recognized tag <html></html>",
|
209
|
-
"recognized word token this",
|
210
|
-
"recognized word token is",
|
211
|
-
"recognized word token a",
|
212
|
-
"recognized word token word"], results[0..-2])
|
213
|
-
end
|
214
|
-
|
215
|
-
end
|