zenlish 0.2.05 → 0.2.06
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +455 -0
- data/CHANGELOG.md +11 -0
- data/Gemfile +5 -3
- data/Rakefile +5 -3
- data/lib/zenlish/feature/boolean_domain.rb +6 -4
- data/lib/zenlish/feature/boolean_value.rb +3 -2
- data/lib/zenlish/feature/enumeration_domain.rb +5 -2
- data/lib/zenlish/feature/feature.rb +9 -7
- data/lib/zenlish/feature/feature_def.rb +9 -6
- data/lib/zenlish/feature/feature_domain.rb +4 -2
- data/lib/zenlish/feature/feature_struct.rb +3 -1
- data/lib/zenlish/feature/feature_struct_def.rb +5 -1
- data/lib/zenlish/feature/feature_struct_def_bearer.rb +6 -4
- data/lib/zenlish/feature/feature_value.rb +4 -2
- data/lib/zenlish/feature/identifier_domain.rb +5 -3
- data/lib/zenlish/feature/identifier_value.rb +3 -2
- data/lib/zenlish/feature/symbol_value.rb +3 -1
- data/lib/zenlish/inflect/atomic_o_expression.rb +2 -1
- data/lib/zenlish/inflect/composite_o_expression.rb +3 -1
- data/lib/zenlish/inflect/concatenation.rb +3 -2
- data/lib/zenlish/inflect/equals_literal.rb +3 -1
- data/lib/zenlish/inflect/feature_heading.rb +2 -5
- data/lib/zenlish/inflect/formal_argument.rb +3 -1
- data/lib/zenlish/inflect/function_call.rb +4 -1
- data/lib/zenlish/inflect/heading.rb +2 -0
- data/lib/zenlish/inflect/inflection_rule.rb +2 -0
- data/lib/zenlish/inflect/inflection_table.rb +6 -4
- data/lib/zenlish/inflect/inflection_table_builder.rb +21 -18
- data/lib/zenlish/inflect/input_asis.rb +3 -0
- data/lib/zenlish/inflect/input_expression.rb +4 -2
- data/lib/zenlish/inflect/literal_asis.rb +4 -1
- data/lib/zenlish/inflect/matches_pattern.rb +2 -0
- data/lib/zenlish/inflect/membership.rb +2 -0
- data/lib/zenlish/inflect/method_heading.rb +3 -6
- data/lib/zenlish/inflect/not_equals_literal.rb +2 -0
- data/lib/zenlish/inflect/nullary_input_expression.rb +3 -1
- data/lib/zenlish/inflect/output_expression.rb +2 -0
- data/lib/zenlish/inflect/substitution.rb +3 -1
- data/lib/zenlish/inflect/unary_input_expression.rb +4 -1
- data/lib/zenlish/inflect/unconditionally_true.rb +4 -2
- data/lib/zenlish/lang/dictionary.rb +19 -16
- data/lib/zenlish/lang/lemmatizer.rb +40 -0
- data/lib/zenlish/lang/zenlish_grammar.rb +6 -4
- data/lib/zenlish/lex/empty_lexicon_factory.rb +3 -2
- data/lib/zenlish/lex/lexeme.rb +6 -4
- data/lib/zenlish/lex/lexical_entry.rb +6 -4
- data/lib/zenlish/lex/lexicon.rb +4 -3
- data/lib/zenlish/lex/literal.rb +3 -1
- data/lib/zenlish/lexer/lexer.rb +144 -0
- data/lib/zenlish/trie/base_trie_node.rb +27 -0
- data/lib/zenlish/trie/trie.rb +132 -0
- data/lib/zenlish/trie/trie_node.rb +21 -0
- data/lib/zenlish/trie/trie_root.rb +10 -0
- data/lib/zenlish/version.rb +3 -1
- data/lib/zenlish/wclasses/adjective.rb +4 -2
- data/lib/zenlish/wclasses/adverb.rb +3 -1
- data/lib/zenlish/wclasses/adverb_maybe.rb +3 -1
- data/lib/zenlish/wclasses/adverb_not.rb +2 -0
- data/lib/zenlish/wclasses/all_word_classes.rb +3 -1
- data/lib/zenlish/wclasses/article.rb +2 -0
- data/lib/zenlish/wclasses/auxiliary.rb +2 -0
- data/lib/zenlish/wclasses/auxiliary_be.rb +7 -6
- data/lib/zenlish/wclasses/auxiliary_do.rb +6 -5
- data/lib/zenlish/wclasses/cardinal.rb +3 -1
- data/lib/zenlish/wclasses/common_noun.rb +2 -0
- data/lib/zenlish/wclasses/comparative_particle.rb +5 -3
- data/lib/zenlish/wclasses/conjunction.rb +2 -0
- data/lib/zenlish/wclasses/conjunctive_pronoun.rb +2 -0
- data/lib/zenlish/wclasses/coordinator.rb +4 -2
- data/lib/zenlish/wclasses/definite_article.rb +2 -0
- data/lib/zenlish/wclasses/degree_adverb.rb +2 -0
- data/lib/zenlish/wclasses/demonstrative_determiner.rb +6 -4
- data/lib/zenlish/wclasses/demonstrative_pronoun.rb +2 -0
- data/lib/zenlish/wclasses/determiner.rb +3 -1
- data/lib/zenlish/wclasses/distributive_determiner.rb +2 -0
- data/lib/zenlish/wclasses/existential_there.rb +2 -0
- data/lib/zenlish/wclasses/fronting_quantifier.rb +3 -1
- data/lib/zenlish/wclasses/indefinite_article.rb +2 -0
- data/lib/zenlish/wclasses/indefinite_pronoun.rb +3 -1
- data/lib/zenlish/wclasses/irregular_linking_verb.rb +3 -1
- data/lib/zenlish/wclasses/irregular_verb.rb +13 -15
- data/lib/zenlish/wclasses/irregular_verb_be.rb +8 -7
- data/lib/zenlish/wclasses/irregular_verb_can.rb +8 -7
- data/lib/zenlish/wclasses/irregular_verb_do.rb +7 -6
- data/lib/zenlish/wclasses/irregular_verb_extension.rb +8 -6
- data/lib/zenlish/wclasses/irregular_verb_have.rb +12 -11
- data/lib/zenlish/wclasses/irregular_verb_know.rb +3 -1
- data/lib/zenlish/wclasses/irregular_verb_say.rb +3 -1
- data/lib/zenlish/wclasses/irregular_verb_think.rb +3 -1
- data/lib/zenlish/wclasses/lexical_verb.rb +3 -4
- data/lib/zenlish/wclasses/linking_adverb.rb +2 -0
- data/lib/zenlish/wclasses/modal_verb_can.rb +7 -5
- data/lib/zenlish/wclasses/noun.rb +4 -2
- data/lib/zenlish/wclasses/numeral.rb +2 -0
- data/lib/zenlish/wclasses/personal_pronoun.rb +8 -6
- data/lib/zenlish/wclasses/possessive_determiner.rb +13 -12
- data/lib/zenlish/wclasses/preposition.rb +3 -1
- data/lib/zenlish/wclasses/preposition_of.rb +2 -0
- data/lib/zenlish/wclasses/preposition_than.rb +2 -0
- data/lib/zenlish/wclasses/pronoun.rb +3 -1
- data/lib/zenlish/wclasses/proper_noun.rb +10 -8
- data/lib/zenlish/wclasses/quantifier.rb +3 -1
- data/lib/zenlish/wclasses/regular_verb.rb +9 -9
- data/lib/zenlish/wclasses/regular_verb_want.rb +4 -2
- data/lib/zenlish/wclasses/relative_pronoun.rb +4 -2
- data/lib/zenlish/wclasses/subordinating_conjunction.rb +7 -5
- data/lib/zenlish/wclasses/verb.rb +5 -3
- data/lib/zenlish/wclasses/word_class.rb +7 -5
- data/spec/spec_helper.rb +3 -1
- data/spec/zenlish/feature/boolean_domain_spec.rb +2 -2
- data/spec/zenlish/feature/boolean_value_spec.rb +1 -1
- data/spec/zenlish/feature/enumeration_domain_spec.rb +7 -7
- data/spec/zenlish/feature/feature_spec.rb +3 -3
- data/spec/zenlish/feature/feature_struct_def_bearer_spec.rb +10 -8
- data/spec/zenlish/feature/feature_struct_def_spec.rb +3 -2
- data/spec/zenlish/feature/identifier_domain_spec.rb +3 -3
- data/spec/zenlish/feature/identifier_value_spec.rb +4 -4
- data/spec/zenlish/feature/symbol_value_spec.rb +3 -3
- data/spec/zenlish/inflect/concatenation_spec.rb +7 -7
- data/spec/zenlish/inflect/feature_heading_spec.rb +9 -9
- data/spec/zenlish/inflect/formal_argument_spec.rb +2 -2
- data/spec/zenlish/inflect/function_call_spec.rb +4 -4
- data/spec/zenlish/inflect/inflection_rule_spec.rb +9 -5
- data/spec/zenlish/inflect/inflection_table_builder_spec.rb +26 -21
- data/spec/zenlish/inflect/inflection_table_spec.rb +18 -16
- data/spec/zenlish/inflect/input_asis_spec.rb +2 -6
- data/spec/zenlish/inflect/literal_asis_spec.rb +3 -3
- data/spec/zenlish/inflect/matches_pattern_spec.rb +1 -1
- data/spec/zenlish/inflect/membership_spec.rb +2 -2
- data/spec/zenlish/inflect/method_heading_spec.rb +3 -3
- data/spec/zenlish/inflect/substitution_spec.rb +1 -1
- data/spec/zenlish/inflect/unconditionally_true_spec.rb +2 -2
- data/spec/zenlish/lang/dictionary_spec.rb +11 -12
- data/spec/zenlish/lang/lemmatizer_spec.rb +43 -0
- data/spec/zenlish/lang/zenlish_grammar_spec.rb +2 -2
- data/spec/zenlish/lex/lexeme_spec.rb +11 -12
- data/spec/zenlish/lex/lexical_entry_spec.rb +1 -2
- data/spec/zenlish/lex/lexicon_spec.rb +9 -8
- data/spec/zenlish/lex/literal_spec.rb +2 -2
- data/spec/zenlish/lexer/lexer_spec.rb +52 -0
- data/spec/zenlish/parser/lesson1_spec.rb +2 -2
- data/spec/zenlish/parser/lesson2_spec.rb +31 -36
- data/spec/zenlish/parser/lesson3_spec.rb +98 -138
- data/spec/zenlish/parser/zparser_spec.rb +2 -1
- data/spec/zenlish/support/minimal_lexicon.rb +2 -0
- data/spec/zenlish/support/var2word.rb +18 -9
- data/spec/zenlish/trie/base_trie_node_spec.rb +33 -0
- data/spec/zenlish/trie/trie_spec.rb +108 -0
- data/spec/zenlish/wclasses/common_noun_spec.rb +6 -10
- data/spec/zenlish/wclasses/demonstrative_determiner_spec.rb +2 -2
- data/spec/zenlish/wclasses/irregular_verb_can_spec.rb +9 -9
- data/spec/zenlish/wclasses/irregular_verb_spec.rb +9 -9
- data/spec/zenlish/wclasses/lexical_verb_spec.rb +3 -3
- data/spec/zenlish/wclasses/modal_verb_can_spec.rb +4 -4
- data/spec/zenlish/wclasses/personal_pronoun_spec.rb +6 -9
- data/spec/zenlish/wclasses/possessive_determiner_spec.rb +19 -22
- data/spec/zenlish/wclasses/regular_verb_spec.rb +20 -20
- data/spec/zenlish/wclasses/regular_verb_want_spec.rb +30 -0
- data/spec/zenlish_spec.rb +3 -1
- data/zenlish.gemspec +17 -14
- metadata +26 -9
@@ -0,0 +1,21 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative 'base_trie_node'
|
4
|
+
|
5
|
+
module Zenlish
|
6
|
+
module Trie
|
7
|
+
class TrieNode < BaseTrieNode
|
8
|
+
# @return [String] the matching character
|
9
|
+
attr_reader :key
|
10
|
+
|
11
|
+
# @return [Object, NilClass] Result when this character matches end-of-word.
|
12
|
+
attr_accessor :value
|
13
|
+
|
14
|
+
def initialize(aChar)
|
15
|
+
super()
|
16
|
+
@key = aChar
|
17
|
+
@value = nil
|
18
|
+
end
|
19
|
+
end # class
|
20
|
+
end # module
|
21
|
+
end # module
|
data/lib/zenlish/version.rb
CHANGED
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'word_class'
|
2
4
|
|
3
5
|
module Zenlish
|
@@ -7,8 +9,8 @@ module Zenlish
|
|
7
9
|
# @return [FalseClass] Indicates that an adjective may inflect.
|
8
10
|
def invariable?
|
9
11
|
# TODO: set to false once we introduce the degrees (basic, comparative, superlative)
|
10
|
-
true
|
11
|
-
end
|
12
|
+
true
|
13
|
+
end
|
12
14
|
end # class
|
13
15
|
end # module
|
14
16
|
end # module
|
@@ -1,8 +1,10 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'adverb'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
|
-
# The adverb maybe expresses uncertainty and is often placed in front
|
7
|
+
# The adverb maybe expresses uncertainty and is often placed in front
|
6
8
|
# of clauses.
|
7
9
|
class AdverbMaybe < Adverb
|
8
10
|
end # class
|
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
# Load the WordClass class hierarchy
|
2
4
|
# Algorithm: load the leaf classes from hierarchy
|
3
5
|
|
@@ -43,4 +45,4 @@ require_relative 'fronting_quantifier'
|
|
43
45
|
require_relative 'regular_verb'
|
44
46
|
require_relative 'regular_verb_want'
|
45
47
|
require_relative 'relative_pronoun'
|
46
|
-
require_relative 'subordinating_conjunction'
|
48
|
+
require_relative 'subordinating_conjunction'
|
@@ -1,20 +1,20 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'auxiliary'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
7
|
class AuxiliaryBe < Auxiliary
|
6
|
-
|
7
|
-
super()
|
8
|
-
end
|
8
|
+
# rubocop: disable Layout/SpaceInsideArrayLiteralBrackets
|
9
9
|
|
10
10
|
private
|
11
11
|
|
12
12
|
def init_feature_defs
|
13
13
|
super
|
14
14
|
# Create standard feature definitions for modal verb can.
|
15
|
-
feature_def_dsl
|
15
|
+
feature_def_dsl do
|
16
16
|
feature_def 'PARADIGM' => [identifier, 'Verb_be_inflection'] # 2nd item is default value
|
17
|
-
|
17
|
+
end
|
18
18
|
end
|
19
19
|
|
20
20
|
def init_paradigms
|
@@ -35,7 +35,8 @@ module Zenlish
|
|
35
35
|
rule([dont_care, dont_care, equals(:past_participle)], literal('been'))
|
36
36
|
end
|
37
37
|
add_paradigm(table)
|
38
|
-
end
|
38
|
+
end
|
39
|
+
# rubocop: enable Layout/SpaceInsideArrayLiteralBrackets
|
39
40
|
end # class
|
40
41
|
end # module
|
41
42
|
end # module
|
@@ -1,21 +1,21 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'auxiliary'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
7
|
# TODO: document
|
6
8
|
class AuxiliaryDo < Auxiliary
|
7
|
-
|
8
|
-
super()
|
9
|
-
end
|
9
|
+
# rubocop: disable Layout/SpaceInsideArrayLiteralBrackets
|
10
10
|
|
11
11
|
private
|
12
12
|
|
13
13
|
def init_feature_defs
|
14
14
|
super
|
15
15
|
# Create standard feature definitions for modal verb can.
|
16
|
-
feature_def_dsl
|
16
|
+
feature_def_dsl do
|
17
17
|
feature_def 'PARADIGM' => [identifier, 'Verb_do_inflection'] # 2nd item is default value
|
18
|
-
|
18
|
+
end
|
19
19
|
end
|
20
20
|
|
21
21
|
def init_paradigms
|
@@ -34,6 +34,7 @@ module Zenlish
|
|
34
34
|
end
|
35
35
|
add_paradigm(table)
|
36
36
|
end
|
37
|
+
# rubocop: enable Layout/SpaceInsideArrayLiteralBrackets
|
37
38
|
end # class
|
38
39
|
end # module
|
39
40
|
end # module
|
@@ -1,10 +1,12 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'word_class'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
|
-
# TODO: document
|
7
|
+
# TODO: document
|
6
8
|
# Example: 'as' in 'same ... as'
|
7
|
-
class ComparativeParticle < WordClass
|
9
|
+
class ComparativeParticle < WordClass
|
8
10
|
end # class
|
9
11
|
end # module
|
10
|
-
end # module
|
12
|
+
end # module
|
@@ -1,12 +1,14 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'conjunction'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
|
-
# A coordinator (aka coordinating conjunction) is a word or phrase that
|
7
|
+
# A coordinator (aka coordinating conjunction) is a word or phrase that
|
6
8
|
# can join words, phrases, and clauses that share some logical relationhip
|
7
9
|
# Common coordinators are enumerated in the FANBOYS acronym:
|
8
10
|
# For, And, Nor, But, Or, Yet and So.
|
9
|
-
class Coordinator < WordClass
|
11
|
+
class Coordinator < WordClass
|
10
12
|
end # class
|
11
13
|
end # module
|
12
14
|
end # module
|
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'determiner'
|
2
4
|
require_relative '../inflect/inflection_table_builder'
|
3
5
|
|
@@ -10,7 +12,7 @@ module Zenlish
|
|
10
12
|
super()
|
11
13
|
init_feature_defs
|
12
14
|
init_paradigms
|
13
|
-
end
|
15
|
+
end
|
14
16
|
|
15
17
|
# @return [FalseClass] Indicates that demonstrative determiners inflects.
|
16
18
|
def invariable?
|
@@ -21,11 +23,11 @@ module Zenlish
|
|
21
23
|
|
22
24
|
def init_feature_defs
|
23
25
|
# Create standard feature definitions for irregular verbs.
|
24
|
-
feature_def_dsl
|
26
|
+
feature_def_dsl do
|
25
27
|
feature_def 'NUMBER' => enumeration(:singular, :plural)
|
26
28
|
feature_def 'DISTANCE' => enumeration(:near, :far)
|
27
29
|
feature_def 'PARADIGM' => [identifier, 'Demonstrative_det_paradigm'] # 2nd item is default value
|
28
|
-
|
30
|
+
end
|
29
31
|
end
|
30
32
|
|
31
33
|
def init_paradigms
|
@@ -37,7 +39,7 @@ module Zenlish
|
|
37
39
|
rule([equals(:singular), equals(:near)], func('base_form'))
|
38
40
|
rule([equals(:singular), equals(:far)], literal('that'))
|
39
41
|
rule([equals(:plural), equals(:near)], literal('these'))
|
40
|
-
rule([equals(:plural), equals(:far)
|
42
|
+
rule([equals(:plural), equals(:far)], literal('those'))
|
41
43
|
end
|
42
44
|
add_paradigm(table)
|
43
45
|
end
|
@@ -1,9 +1,11 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'quantifier'
|
2
4
|
|
3
5
|
module Zenlish
|
4
6
|
module WClasses
|
5
7
|
# Quantifiers that appear in front of determiners: all, both
|
6
|
-
class
|
8
|
+
class FrontingQuantifier < Quantifier
|
7
9
|
end # class
|
8
10
|
end # module
|
9
11
|
end # module
|
@@ -1,3 +1,5 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
1
3
|
require_relative 'lexical_verb'
|
2
4
|
require_relative 'irregular_verb_extension'
|
3
5
|
|
@@ -7,24 +9,20 @@ module Zenlish
|
|
7
9
|
# @return [Array<String>] [the past simple form, past participle form].
|
8
10
|
attr_writer :forms
|
9
11
|
|
10
|
-
def initialize
|
11
|
-
super()
|
12
|
-
end
|
13
|
-
|
14
12
|
# The mix-in module used to extend the lexeme
|
15
13
|
# @return [Module, NilClass]
|
16
14
|
def extension
|
17
15
|
IrregularVerbExtension
|
18
|
-
end
|
16
|
+
end
|
19
17
|
|
20
18
|
private
|
21
|
-
|
19
|
+
|
22
20
|
def init_feature_defs
|
23
21
|
super
|
24
22
|
# Create standard feature definitions for irregular verbs.
|
25
|
-
feature_def_dsl
|
23
|
+
feature_def_dsl do
|
26
24
|
feature_def 'PARADIGM' => [identifier, 'Irregular_inflection'] # 2nd item is default value
|
27
|
-
|
25
|
+
end
|
28
26
|
end
|
29
27
|
|
30
28
|
def init_paradigms
|
@@ -37,17 +35,17 @@ module Zenlish
|
|
37
35
|
# PERSON NUMBER TIME base_form
|
38
36
|
rule([not_equal(:third), equals(:singular), equals(:present), dont_care], col('base_form'))
|
39
37
|
rule([equals(:third), equals(:singular), equals(:present), matches(/[^aeiouy]y$/)], sub(col('base_form'), /y$/, 'ies'))
|
40
|
-
rule([equals(:third), equals(:singular), equals(:present), matches(/(?:[osxz]|ch|sh)$/)], concat(col('base_form'), 'es'))
|
38
|
+
rule([equals(:third), equals(:singular), equals(:present), matches(/(?:[osxz]|ch|sh)$/)], concat(col('base_form'), 'es'))
|
41
39
|
rule([equals(:third), equals(:singular), equals(:present), dont_care], concat(col('base_form'), 's'))
|
42
|
-
rule([dont_care, equals(:plural), equals(:present), dont_care], col('base_form'))
|
43
|
-
rule([dont_care, dont_care, equals(:progressive), matches(/ie$/)], sub(col('base_form'), /ie$/, 'ying'))
|
44
|
-
rule([dont_care, dont_care, equals(:progressive), matches(/[^eoy]e$/)], sub(col('base_form'), /e$/, 'ing'))
|
40
|
+
rule([dont_care, equals(:plural), equals(:present), dont_care], col('base_form'))
|
41
|
+
rule([dont_care, dont_care, equals(:progressive), matches(/ie$/)], sub(col('base_form'), /ie$/, 'ying'))
|
42
|
+
rule([dont_care, dont_care, equals(:progressive), matches(/[^eoy]e$/)], sub(col('base_form'), /e$/, 'ing'))
|
45
43
|
rule([dont_care, dont_care, equals(:progressive), dont_care], concat(col('base_form'), 'ing'))
|
46
|
-
rule([dont_care, dont_care, equals(:past_simple), dont_care], func('past_simple'))
|
44
|
+
rule([dont_care, dont_care, equals(:past_simple), dont_care], func('past_simple'))
|
47
45
|
rule([dont_care, dont_care, equals(:past_participle), dont_care], func('past_participle'))
|
48
46
|
end
|
49
47
|
add_paradigm(table)
|
50
|
-
end
|
48
|
+
end
|
51
49
|
end # class
|
52
50
|
end # module
|
53
|
-
end # module
|
51
|
+
end # module
|