foreverman-dhaka 2.2.1
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +64 -0
- data/lib/dhaka.rb +62 -0
- data/lib/dhaka/dot/dot.rb +29 -0
- data/lib/dhaka/evaluator/evaluator.rb +133 -0
- data/lib/dhaka/grammar/closure_hash.rb +15 -0
- data/lib/dhaka/grammar/grammar.rb +236 -0
- data/lib/dhaka/grammar/grammar_symbol.rb +27 -0
- data/lib/dhaka/grammar/precedence.rb +19 -0
- data/lib/dhaka/grammar/production.rb +36 -0
- data/lib/dhaka/lexer/accept_actions.rb +36 -0
- data/lib/dhaka/lexer/alphabet.rb +21 -0
- data/lib/dhaka/lexer/compiled_lexer.rb +46 -0
- data/lib/dhaka/lexer/dfa.rb +121 -0
- data/lib/dhaka/lexer/lexeme.rb +32 -0
- data/lib/dhaka/lexer/lexer.rb +70 -0
- data/lib/dhaka/lexer/lexer_run.rb +78 -0
- data/lib/dhaka/lexer/regex_grammar.rb +393 -0
- data/lib/dhaka/lexer/regex_parser.rb +2010 -0
- data/lib/dhaka/lexer/regex_tokenizer.rb +14 -0
- data/lib/dhaka/lexer/specification.rb +96 -0
- data/lib/dhaka/lexer/state.rb +68 -0
- data/lib/dhaka/lexer/state_machine.rb +37 -0
- data/lib/dhaka/parser/action.rb +55 -0
- data/lib/dhaka/parser/channel.rb +58 -0
- data/lib/dhaka/parser/compiled_parser.rb +51 -0
- data/lib/dhaka/parser/conflict.rb +54 -0
- data/lib/dhaka/parser/item.rb +43 -0
- data/lib/dhaka/parser/parse_result.rb +50 -0
- data/lib/dhaka/parser/parse_tree.rb +66 -0
- data/lib/dhaka/parser/parser.rb +165 -0
- data/lib/dhaka/parser/parser_methods.rb +11 -0
- data/lib/dhaka/parser/parser_run.rb +39 -0
- data/lib/dhaka/parser/parser_state.rb +74 -0
- data/lib/dhaka/parser/token.rb +22 -0
- data/lib/dhaka/runtime.rb +51 -0
- data/lib/dhaka/tokenizer/tokenizer.rb +190 -0
- data/test/all_tests.rb +5 -0
- data/test/arithmetic/arithmetic_evaluator.rb +64 -0
- data/test/arithmetic/arithmetic_evaluator_test.rb +43 -0
- data/test/arithmetic/arithmetic_grammar.rb +41 -0
- data/test/arithmetic/arithmetic_grammar_test.rb +9 -0
- data/test/arithmetic/arithmetic_test_methods.rb +9 -0
- data/test/arithmetic/arithmetic_tokenizer.rb +39 -0
- data/test/arithmetic/arithmetic_tokenizer_test.rb +38 -0
- data/test/arithmetic_precedence/arithmetic_precedence_evaluator.rb +43 -0
- data/test/arithmetic_precedence/arithmetic_precedence_grammar.rb +24 -0
- data/test/arithmetic_precedence/arithmetic_precedence_grammar_test.rb +30 -0
- data/test/arithmetic_precedence/arithmetic_precedence_lexer_specification.rb +23 -0
- data/test/arithmetic_precedence/arithmetic_precedence_parser_test.rb +33 -0
- data/test/brackets/bracket_grammar.rb +23 -0
- data/test/brackets/bracket_tokenizer.rb +22 -0
- data/test/brackets/brackets_test.rb +28 -0
- data/test/chittagong/chittagong_driver.rb +46 -0
- data/test/chittagong/chittagong_driver_test.rb +276 -0
- data/test/chittagong/chittagong_evaluator.rb +284 -0
- data/test/chittagong/chittagong_evaluator_test.rb +38 -0
- data/test/chittagong/chittagong_grammar.rb +104 -0
- data/test/chittagong/chittagong_lexer.rb +109 -0
- data/test/chittagong/chittagong_lexer_specification.rb +37 -0
- data/test/chittagong/chittagong_lexer_test.rb +58 -0
- data/test/chittagong/chittagong_parser.rb +879 -0
- data/test/chittagong/chittagong_parser_test.rb +55 -0
- data/test/chittagong/chittagong_test.rb +170 -0
- data/test/core/another_lalr_but_not_slr_grammar.rb +20 -0
- data/test/core/compiled_parser_test.rb +44 -0
- data/test/core/dfa_test.rb +170 -0
- data/test/core/evaluator_test.rb +22 -0
- data/test/core/grammar_test.rb +83 -0
- data/test/core/lalr_but_not_slr_grammar.rb +19 -0
- data/test/core/lexer_test.rb +139 -0
- data/test/core/malformed_grammar.rb +7 -0
- data/test/core/malformed_grammar_test.rb +8 -0
- data/test/core/nullable_grammar.rb +21 -0
- data/test/core/parse_result_test.rb +44 -0
- data/test/core/parser_state_test.rb +24 -0
- data/test/core/parser_test.rb +131 -0
- data/test/core/precedence_grammar.rb +17 -0
- data/test/core/precedence_grammar_test.rb +9 -0
- data/test/core/rr_conflict_grammar.rb +21 -0
- data/test/core/simple_grammar.rb +22 -0
- data/test/core/sr_conflict_grammar.rb +16 -0
- data/test/dhaka_test_helper.rb +18 -0
- data/test/fake_logger.rb +17 -0
- metadata +137 -0
@@ -0,0 +1,55 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../dhaka_test_helper'
|
2
|
+
require File.dirname(__FILE__) + '/chittagong_grammar'
|
3
|
+
begin
|
4
|
+
require File.dirname(__FILE__) + "/chittagong_parser"
|
5
|
+
rescue LoadError
|
6
|
+
puts "Please run the rake command in the root folder to generate the lexer and parser required for this test."
|
7
|
+
exit
|
8
|
+
end
|
9
|
+
|
10
|
+
class TestChittagongParser < Test::Unit::TestCase
|
11
|
+
|
12
|
+
def test_parses_a_series_of_statements
|
13
|
+
token_stream = build_tokens(
|
14
|
+
'newline',
|
15
|
+
'word_literal', '=', 'numeric_literal', 'newline',
|
16
|
+
'print', 'word_literal', 'newline',
|
17
|
+
'newline',
|
18
|
+
'word_literal', '=', 'word_literal', 'newline',
|
19
|
+
'newline', Dhaka::END_SYMBOL_NAME
|
20
|
+
)
|
21
|
+
|
22
|
+
result = ChittagongParser.parse(token_stream)
|
23
|
+
|
24
|
+
assert_equal(["single_term",
|
25
|
+
"some_terms",
|
26
|
+
"variable_name",
|
27
|
+
"literal",
|
28
|
+
"assignment_statement",
|
29
|
+
"main_body_simple_statement",
|
30
|
+
"single_main_body_statement",
|
31
|
+
"single_term",
|
32
|
+
"variable_name",
|
33
|
+
"variable_reference",
|
34
|
+
"print_statement",
|
35
|
+
"main_body_simple_statement",
|
36
|
+
"multiple_main_body_statements",
|
37
|
+
"single_term",
|
38
|
+
"multiple_terms",
|
39
|
+
"variable_name",
|
40
|
+
"variable_name",
|
41
|
+
"variable_reference",
|
42
|
+
"assignment_statement",
|
43
|
+
"main_body_simple_statement",
|
44
|
+
"multiple_main_body_statements",
|
45
|
+
"single_term",
|
46
|
+
"multiple_terms",
|
47
|
+
"some_terms",
|
48
|
+
"program"], result.linearize.collect {|node| node.production.name})
|
49
|
+
|
50
|
+
end
|
51
|
+
|
52
|
+
def build_tokens *symbol_names
|
53
|
+
symbol_names.collect {|symbol_name| Dhaka::Token.new(symbol_name, nil, nil)}
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,170 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../dhaka_test_helper'
|
2
|
+
require File.dirname(__FILE__) + "/chittagong_grammar"
|
3
|
+
require File.dirname(__FILE__) + "/chittagong_lexer_specification"
|
4
|
+
begin
|
5
|
+
require File.dirname(__FILE__) + "/chittagong_parser"
|
6
|
+
require File.dirname(__FILE__) + "/chittagong_lexer"
|
7
|
+
rescue LoadError
|
8
|
+
puts "Please run the rake command in the root folder to generate the lexer and parser required for this test."
|
9
|
+
exit
|
10
|
+
end
|
11
|
+
require File.dirname(__FILE__) + "/chittagong_evaluator"
|
12
|
+
|
13
|
+
class TestChittagong < Test::Unit::TestCase
|
14
|
+
|
15
|
+
def fact(n)
|
16
|
+
return 1 if n==1
|
17
|
+
n * fact(n-1)
|
18
|
+
end
|
19
|
+
|
20
|
+
def program_output program
|
21
|
+
output_stream = []
|
22
|
+
parse_result = ChittagongParser.parse(ChittagongLexer.lex(program))
|
23
|
+
result = ChittagongEvaluator.new([{}], output_stream).evaluate(parse_result)
|
24
|
+
return result, output_stream
|
25
|
+
end
|
26
|
+
|
27
|
+
def test_iterative_fibonacci_without_functions
|
28
|
+
program = "
|
29
|
+
|
30
|
+
n = 1
|
31
|
+
a = 0
|
32
|
+
b = 1
|
33
|
+
while n < 10
|
34
|
+
print b
|
35
|
+
c = a
|
36
|
+
a = b
|
37
|
+
b = c + b
|
38
|
+
n = n + 1
|
39
|
+
end
|
40
|
+
|
41
|
+
"
|
42
|
+
|
43
|
+
result, output_stream = program_output(program)
|
44
|
+
assert_equal(["1.0", "1.0", "2.0", "3.0", "5.0", "8.0", "13.0", "21.0", "34.0"], output_stream)
|
45
|
+
end
|
46
|
+
|
47
|
+
def test_iterative_fibonacci_with_functions
|
48
|
+
program = "
|
49
|
+
|
50
|
+
def fib(n)
|
51
|
+
i = 0
|
52
|
+
a = 0
|
53
|
+
b = 1
|
54
|
+
while i < n
|
55
|
+
c = a
|
56
|
+
a = b
|
57
|
+
b = c + b
|
58
|
+
i = i + 1
|
59
|
+
end
|
60
|
+
return b
|
61
|
+
end
|
62
|
+
|
63
|
+
x = 0
|
64
|
+
while x < 9
|
65
|
+
print fib(x)
|
66
|
+
x = x + 1
|
67
|
+
end
|
68
|
+
|
69
|
+
"
|
70
|
+
result, output_stream = program_output(program)
|
71
|
+
assert_equal(["1.0", "1.0", "2.0", "3.0", "5.0", "8.0", "13.0", "21.0", "34.0"], output_stream)
|
72
|
+
end
|
73
|
+
|
74
|
+
def test_recursive_factorial
|
75
|
+
program = "
|
76
|
+
def fact(n)
|
77
|
+
if n == 1
|
78
|
+
return 1
|
79
|
+
end
|
80
|
+
return n * fact(n-1)
|
81
|
+
end
|
82
|
+
|
83
|
+
n = 1
|
84
|
+
while n < 11
|
85
|
+
print fact(n)
|
86
|
+
n = n+1
|
87
|
+
end"
|
88
|
+
|
89
|
+
result, output_stream = program_output(program)
|
90
|
+
assert_equal((1..10).collect {|i| fact(i).to_f.to_s}, output_stream)
|
91
|
+
end
|
92
|
+
|
93
|
+
def test_various_things
|
94
|
+
program = "
|
95
|
+
|
96
|
+
a = 1
|
97
|
+
b = 2
|
98
|
+
c = 3
|
99
|
+
|
100
|
+
def foo(a, b, c)
|
101
|
+
print a
|
102
|
+
print b
|
103
|
+
print c
|
104
|
+
return c
|
105
|
+
print 999
|
106
|
+
end
|
107
|
+
|
108
|
+
foo(4, a, 6)
|
109
|
+
|
110
|
+
"
|
111
|
+
|
112
|
+
result, output_stream = program_output(program)
|
113
|
+
assert_equal(["4.0", "1.0", "6.0"], output_stream)
|
114
|
+
end
|
115
|
+
|
116
|
+
def test_if_else_block
|
117
|
+
program = "
|
118
|
+
|
119
|
+
def foo(a, b)
|
120
|
+
if a < b
|
121
|
+
print 1
|
122
|
+
else
|
123
|
+
print 2
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
foo(1, 2)
|
128
|
+
foo(2, 1)
|
129
|
+
|
130
|
+
"
|
131
|
+
|
132
|
+
result, output_stream = program_output(program)
|
133
|
+
assert_equal(["1.0", "2.0"], output_stream)
|
134
|
+
end
|
135
|
+
|
136
|
+
def test_no_arg_functions
|
137
|
+
program = "
|
138
|
+
|
139
|
+
def foo()
|
140
|
+
print 1
|
141
|
+
print 2
|
142
|
+
end
|
143
|
+
foo()
|
144
|
+
|
145
|
+
"
|
146
|
+
|
147
|
+
result, output_stream = program_output(program)
|
148
|
+
assert_equal(["1.0", "2.0"], output_stream)
|
149
|
+
end
|
150
|
+
|
151
|
+
def test_decimal_numbers
|
152
|
+
program = "
|
153
|
+
print 0.2347 * 23.34
|
154
|
+
a = 1.012
|
155
|
+
b = 345.44
|
156
|
+
c = 0.234
|
157
|
+
print (a^b)/c
|
158
|
+
def foo(a)
|
159
|
+
print a
|
160
|
+
end
|
161
|
+
foo(3.4)
|
162
|
+
"
|
163
|
+
|
164
|
+
result, output_stream = program_output(program)
|
165
|
+
assert_equal(["5.477898", "263.233029427781", "3.4"], output_stream)
|
166
|
+
end
|
167
|
+
|
168
|
+
|
169
|
+
|
170
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require File.dirname(__FILE__)+'/../dhaka_test_helper'
|
2
|
+
|
3
|
+
class AnotherLALRButNotSLRGrammar < Dhaka::Grammar
|
4
|
+
|
5
|
+
for_symbol(Dhaka::START_SYMBOL_NAME) do
|
6
|
+
assignment %w| L = R |
|
7
|
+
rhs %w| R |
|
8
|
+
end
|
9
|
+
|
10
|
+
for_symbol('L') do
|
11
|
+
contents %w| * R |
|
12
|
+
identifier %w| id |
|
13
|
+
end
|
14
|
+
|
15
|
+
for_symbol('R') do
|
16
|
+
l_value %w| L |
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
20
|
+
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../dhaka_test_helper'
|
2
|
+
require File.dirname(__FILE__) + "/simple_grammar"
|
3
|
+
eval(Dhaka::Parser.new(SimpleGrammar).compile_to_ruby_source_as(:SimpleParser))
|
4
|
+
|
5
|
+
class TestCompiledParser < Test::Unit::TestCase
|
6
|
+
def test_compiled_parser_generates_parse_tree_for_simple_grammar
|
7
|
+
parse_tree = SimpleParser.parse(build_tokens(%w| ( n - ( n - n ) ) - n # | +[Dhaka::END_SYMBOL_NAME]))
|
8
|
+
assert_equal \
|
9
|
+
["literal",
|
10
|
+
"term",
|
11
|
+
"literal",
|
12
|
+
"term",
|
13
|
+
"literal",
|
14
|
+
"subtraction",
|
15
|
+
"parenthetized_expression",
|
16
|
+
"subtraction",
|
17
|
+
"parenthetized_expression",
|
18
|
+
"term",
|
19
|
+
"literal",
|
20
|
+
"subtraction",
|
21
|
+
"expression",
|
22
|
+
"start"], parse_tree.linearize.collect {|node| node.production.name}
|
23
|
+
end
|
24
|
+
|
25
|
+
def test_parse_result_has_error_result_if_only_end_token_passed
|
26
|
+
parse_result = SimpleParser.parse(build_tokens([Dhaka::END_SYMBOL_NAME]))
|
27
|
+
assert parse_result.has_error?
|
28
|
+
end
|
29
|
+
|
30
|
+
def test_parse_result_is_nil_if_no_end_token
|
31
|
+
parse_result = SimpleParser.parse(build_tokens(%w| n - n |))
|
32
|
+
assert_nil(parse_result)
|
33
|
+
end
|
34
|
+
|
35
|
+
def test_parser_returns_error_result_with_index_of_bad_token_if_parse_error
|
36
|
+
parse_result = SimpleParser.parse(build_tokens(['(', '-', ')', Dhaka::END_SYMBOL_NAME]))
|
37
|
+
assert parse_result.has_error?
|
38
|
+
assert_equal '-', parse_result.unexpected_token.symbol_name
|
39
|
+
end
|
40
|
+
|
41
|
+
def build_tokens(token_symbol_names)
|
42
|
+
token_symbol_names.collect {|symbol_name| Dhaka::Token.new(symbol_name, nil, nil)}
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,170 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../dhaka_test_helper'
|
2
|
+
|
3
|
+
class TestDFA < 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_full_match(machine, "abababb")
|
49
|
+
assert_full_match(machine, "ababaabb")
|
50
|
+
assert_empty(machine.match("abababab"))
|
51
|
+
assert_equal("abababb", machine.match("abababbc"))
|
52
|
+
assert_equal("abababb", machine.match("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_full_match(machine, "badccddabab")
|
58
|
+
assert_full_match(machine, "baddcc")
|
59
|
+
assert_empty(machine.match("badab"))
|
60
|
+
assert_empty(machine.match("bacdab"))
|
61
|
+
end
|
62
|
+
|
63
|
+
def test_match_a_nullable_regex
|
64
|
+
machine = Dhaka::LexerSupport::DFA.new("(ab)*")
|
65
|
+
assert_full_match(machine, "abab")
|
66
|
+
assert_full_match(machine, "ab")
|
67
|
+
assert_full_match(machine, "")
|
68
|
+
assert_equal("", machine.match("b"))
|
69
|
+
end
|
70
|
+
|
71
|
+
def test_match_a_regex_with_the_dot_character
|
72
|
+
machine = Dhaka::LexerSupport::DFA.new("ab.*cd")
|
73
|
+
assert_full_match(machine, "abacd")
|
74
|
+
assert_full_match(machine, "abcd")
|
75
|
+
assert_full_match(machine, "abAcd")
|
76
|
+
assert_empty(machine.match("ab999c"))
|
77
|
+
end
|
78
|
+
|
79
|
+
def test_match_a_regex_with_sets
|
80
|
+
machine = Dhaka::LexerSupport::DFA.new("ab[j-lu]*cd")
|
81
|
+
assert_empty(machine.match("abacd"))
|
82
|
+
assert_full_match(machine, "abcd")
|
83
|
+
assert_full_match(machine, "abjklucd")
|
84
|
+
assert_empty(machine.match("abijklucd"))
|
85
|
+
assert_empty(machine.match("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_full_match(machine, "abcd")
|
91
|
+
assert_empty(machine.match("abjcd"))
|
92
|
+
assert_empty(machine.match("abrcd"))
|
93
|
+
assert_empty(machine.match("abijklucd"))
|
94
|
+
assert_full_match(machine, "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_full_match(machine, "abcd")
|
100
|
+
assert_empty(machine.match("abjcd"))
|
101
|
+
assert_full_match(machine, "ab^-.cd")
|
102
|
+
assert_empty(machine.match("abijklucd"))
|
103
|
+
assert_empty(machine.match("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_full_match(machine, "^-")
|
109
|
+
assert_full_match(machine, "^-^-")
|
110
|
+
assert_empty(machine.match("?cd"))
|
111
|
+
end
|
112
|
+
|
113
|
+
def test_match_a_regex_using_escape_characters
|
114
|
+
machine = Dhaka::LexerSupport::DFA.new(%q/(-\?\(\)\\\\)*/)
|
115
|
+
assert_full_match(machine, "-?()\\")
|
116
|
+
end
|
117
|
+
|
118
|
+
def test_match_a_regex_using_lt_and_gt
|
119
|
+
machine = Dhaka::LexerSupport::DFA.new('<.+>')
|
120
|
+
assert_full_match(machine, "<ab>")
|
121
|
+
assert_full_match(machine, "<absdf><sdg><sse>")
|
122
|
+
assert_empty(machine.match("ab>"))
|
123
|
+
end
|
124
|
+
|
125
|
+
def test_simulating_curly_brace_quantifiers
|
126
|
+
machine = Dhaka::LexerSupport::DFA.new('aaa?a?a?')
|
127
|
+
assert_full_match(machine, "aa")
|
128
|
+
assert_full_match(machine, "aaa")
|
129
|
+
assert_full_match(machine, "aaaa")
|
130
|
+
assert_full_match(machine, "aaaaa")
|
131
|
+
assert_equal("aaaaa", machine.match("aaaaaa"))
|
132
|
+
assert_empty(machine.match("a"))
|
133
|
+
end
|
134
|
+
|
135
|
+
def test_matching_a_regex_with_lookahead
|
136
|
+
machine = Dhaka::LexerSupport::DFA.new('ab/cd')
|
137
|
+
assert_equal("ab", machine.match("abcd"))
|
138
|
+
assert_empty(machine.match("ab"))
|
139
|
+
assert_empty(machine.match("abef"))
|
140
|
+
end
|
141
|
+
|
142
|
+
def test_matching_a_regex_with_nullable_pre_lookahead_regex
|
143
|
+
machine = Dhaka::LexerSupport::DFA.new('(ab)*/cd')
|
144
|
+
assert_equal("ab", machine.match("abcd"))
|
145
|
+
assert_equal("ababab", machine.match("abababcd"))
|
146
|
+
assert_empty(machine.match("ababc"))
|
147
|
+
assert_empty(machine.match("abef"))
|
148
|
+
end
|
149
|
+
|
150
|
+
def test_matching_a_regex_with_post_lookahead_characters_in_common_with_pre_lookahead_characters
|
151
|
+
machine = Dhaka::LexerSupport::DFA.new('(ab)+/abcd')
|
152
|
+
assert_equal("ababab", machine.match("abababcd"))
|
153
|
+
assert_empty(machine.match("ab"))
|
154
|
+
assert_empty(machine.match("abef"))
|
155
|
+
end
|
156
|
+
|
157
|
+
def test_machine_with_nullable_lookahead
|
158
|
+
machine = Dhaka::LexerSupport::DFA.new(":/[aA\n\r\t]*")
|
159
|
+
assert_equal(":", machine.match(":"))
|
160
|
+
end
|
161
|
+
|
162
|
+
private
|
163
|
+
def assert_full_match(machine, input)
|
164
|
+
assert_equal(input, machine.match(input))
|
165
|
+
end
|
166
|
+
|
167
|
+
def assert_empty(input)
|
168
|
+
assert(input.empty?)
|
169
|
+
end
|
170
|
+
end
|