skeem 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +9 -0
- data/README.md +11 -3
- data/lib/skeem.rb +7 -4
- data/lib/skeem/grammar.rb +42 -0
- data/lib/skeem/parser.rb +36 -0
- data/lib/skeem/tokenizer.rb +9 -1
- data/lib/skeem/version.rb +1 -1
- data/spec/skeem/parser_spec.rb +26 -0
- data/spec/skeem/tokenizer_spec.rb +50 -4
- metadata +6 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 670bb82d2fecac647938c03d92b8c910f9385a49
|
4
|
+
data.tar.gz: 3ac772b051b36ded30aefe62c6745239c9a1941f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6b8488389ba2a11fa1664bb6f3e2a40c752a16045061f516360cce2744e9e05e2746d823f8854fa40f23fe24183105384863f19156a7b425a86d95071d2ad9c4
|
7
|
+
data.tar.gz: 1c6029799408c83027072cdfca72f9d86dd6bbf5519af149fbb3736e4224f223f553c1463e56fd0461b0e977ae91a2be14ab2a8f4355e9a1ae5449094167a08b
|
data/CHANGELOG.md
CHANGED
@@ -1,3 +1,12 @@
|
|
1
|
+
## [0.0.3] - 2018-08-25
|
2
|
+
### Added
|
3
|
+
- File `grammar.rb` with minimalist grammar.
|
4
|
+
- Initial `Parser` class commit
|
5
|
+
|
6
|
+
### Changed
|
7
|
+
- Class`Tokenizer` recognizes `define` keyword
|
8
|
+
- Spec file `Tokenizer_spec.rb` expanded with more tests.
|
9
|
+
|
1
10
|
## [0.0.2] - 2018-08-25
|
2
11
|
### Changed
|
3
12
|
- Class`Tokenizer` improved, does recognize delimiters, booleans, integers, real numbers, strings, and identifiers.
|
data/README.md
CHANGED
@@ -1,4 +1,8 @@
|
|
1
1
|
# Skeem
|
2
|
+
[![Linux Build Status](https://travis-ci.org/famished-tiger/Skeem.svg?branch=master)](https://travis-ci.org/famished-tiger/Skeem)
|
3
|
+
[![Gem Version](https://badge.fury.io/rb/skeem.svg)](https://badge.fury.io/rb/skeem)
|
4
|
+
[![License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat)](https://github.com/famished-tiger/Skeem/blob/master/LICENSE.txt)
|
5
|
+
|
2
6
|
__Skeem__ will be an interpreter of a subset of the Scheme programming language.
|
3
7
|
|
4
8
|
|
@@ -20,8 +24,12 @@ Or install it yourself as:
|
|
20
24
|
|
21
25
|
## Usage
|
22
26
|
|
23
|
-
The __Skeem__ project has just started.
|
24
|
-
At this stage,
|
27
|
+
The __Skeem__ project has just started.
|
28
|
+
At this stage, the gem consists of a tokenizer.
|
29
|
+
At least these steps must be done in order to have a first interpreter:
|
30
|
+
- TODO: define subset of Scheme grammar
|
31
|
+
- TODO: buuild parser of Scheme subset
|
32
|
+
- TODO: Implement Skeem interpreter (and REPL)
|
25
33
|
|
26
34
|
Roadmap:
|
27
35
|
- Implement an equivalent of [lis.py](http://www.norvig.com/lispy.html)
|
@@ -33,7 +41,7 @@ Roadmap:
|
|
33
41
|
TODO: Write usage instructions here
|
34
42
|
|
35
43
|
Good to know:
|
36
|
-
Online book: [The Scheme Programming Language (4th Ed.)](https://www.scheme.com/tspl4/)
|
44
|
+
Online book: [The Scheme Programming Language (4th Ed.)](https://www.scheme.com/tspl4/). Remark: covers an older version of Scheme.
|
37
45
|
|
38
46
|
## Development
|
39
47
|
|
data/lib/skeem.rb
CHANGED
@@ -1,5 +1,8 @@
|
|
1
|
-
|
1
|
+
# File: skeem.rb
|
2
|
+
# This file acts as a jumping-off point for loading dependencies expected
|
3
|
+
# for a Skeem client.
|
2
4
|
|
3
|
-
|
4
|
-
|
5
|
-
|
5
|
+
require_relative './skeem/version'
|
6
|
+
require_relative './skeem/parser'
|
7
|
+
|
8
|
+
# End of file
|
@@ -0,0 +1,42 @@
|
|
1
|
+
# Grammar for Skeem (a subset of Scheme language)
|
2
|
+
require 'rley' # Load the gem
|
3
|
+
|
4
|
+
module Skeem
|
5
|
+
########################################
|
6
|
+
# Define a grammar for Skeem
|
7
|
+
# Official Small Scheme grammar is available at:
|
8
|
+
# https://bitbucket.org/cowan/r7rs/src/draft-10/rnrs/r7rs.pdf
|
9
|
+
# Names of grammar elements are based on the R7RS documentation
|
10
|
+
builder = Rley::Syntax::GrammarBuilder.new do
|
11
|
+
# Delimitersn, separators...
|
12
|
+
# add_terminals('APOSTROPHE', 'BACKQUOTE')
|
13
|
+
add_terminals('LPAREN', 'RPAREN')
|
14
|
+
# add_terminals('PERIOD')
|
15
|
+
|
16
|
+
# Literal values...
|
17
|
+
add_terminals('BOOLEAN', 'INTEGER', 'REAL')
|
18
|
+
add_terminals('STRING_LIT', 'IDENTIFIER')
|
19
|
+
|
20
|
+
# Keywords...
|
21
|
+
# add_terminals('BEGIN', 'DEFINE')
|
22
|
+
add_terminals('DEFINE')
|
23
|
+
|
24
|
+
rule 'program' => 'cmd_or_def_plus'
|
25
|
+
rule 'cmd_or_def_plus' => 'cmd_or_def_plus cmd_or_def'
|
26
|
+
rule 'cmd_or_def_plus' => 'cmd_or_def'
|
27
|
+
rule 'cmd_or_def' => 'definition'
|
28
|
+
rule 'definition' => 'LPAREN DEFINE IDENTIFIER expression RPAREN'
|
29
|
+
rule 'expression' => 'IDENTIFIER'
|
30
|
+
rule 'expression' => 'literal'
|
31
|
+
rule 'literal' => 'self-evaluating'
|
32
|
+
rule 'self-evaluating' => 'BOOLEAN'
|
33
|
+
rule 'self-evaluating' => 'number'
|
34
|
+
rule 'self-evaluating' => 'STRING_LIT'
|
35
|
+
rule 'number' => 'INTEGER'
|
36
|
+
rule 'number' => 'REAL'
|
37
|
+
end
|
38
|
+
|
39
|
+
# And now build the grammar and make it accessible via a global constant
|
40
|
+
# [Rley::Syntax::Grammar]
|
41
|
+
Grammar = builder.grammar
|
42
|
+
end # module
|
data/lib/skeem/parser.rb
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
require_relative 'tokenizer'
|
2
|
+
require_relative 'grammar'
|
3
|
+
|
4
|
+
module Skeem
|
5
|
+
class Parser
|
6
|
+
attr_reader(:engine)
|
7
|
+
|
8
|
+
def initialize()
|
9
|
+
# Create a Rley facade object
|
10
|
+
@engine = Rley::Engine.new { |cfg| cfg.diagnose = true }
|
11
|
+
|
12
|
+
# Step 1. Load Skeem grammar
|
13
|
+
@engine.use_grammar(Skeem::Grammar)
|
14
|
+
end
|
15
|
+
|
16
|
+
# Parse the given Skeem expression into a parse tree.
|
17
|
+
# @param source [String] Skeem expression to parse
|
18
|
+
# @return [ParseTree] A regexp object equivalent to the Skeem expression.
|
19
|
+
# @example Defining a function that computes the area of a circle
|
20
|
+
# source = "(define circle-area (lambda (r) (* pi (* r r))))"
|
21
|
+
# regex = Skeem::parse(source)
|
22
|
+
def parse(source)
|
23
|
+
lexer = Skeem::Tokenizer.new(source)
|
24
|
+
result = engine.parse(lexer.tokens)
|
25
|
+
|
26
|
+
unless result.success?
|
27
|
+
# Stop if the parse failed...
|
28
|
+
line1 = "Parsing failed\n"
|
29
|
+
line2 = "Reason: #{result.failure_reason.message}"
|
30
|
+
raise StandardError, line1 + line2
|
31
|
+
end
|
32
|
+
|
33
|
+
return result
|
34
|
+
end
|
35
|
+
end # class
|
36
|
+
end # module
|
data/lib/skeem/tokenizer.rb
CHANGED
@@ -24,6 +24,12 @@ module Skeem
|
|
24
24
|
'(' => 'LPAREN',
|
25
25
|
')' => 'RPAREN'
|
26
26
|
}.freeze
|
27
|
+
|
28
|
+
# Here are all the SRL keywords (in uppercase)
|
29
|
+
@@keywords = %w[
|
30
|
+
BEGIN
|
31
|
+
DEFINE
|
32
|
+
].map { |x| [x, x] } .to_h
|
27
33
|
|
28
34
|
class ScanError < StandardError; end
|
29
35
|
|
@@ -77,7 +83,9 @@ module Skeem
|
|
77
83
|
unquoted = lexeme.gsub(/(^")|("$)/, '')
|
78
84
|
token = build_token('STRING_LIT', unquoted)
|
79
85
|
elsif (lexeme = scanner.scan(/[a-zA-Z!$%&*\/:<=>?@^_~][a-zA-Z0-9!$%&*+-.\/:<=>?@^_~+-]*/))
|
80
|
-
|
86
|
+
keyw = @@keywords[lexeme.upcase]
|
87
|
+
tok_type = keyw ? keyw : 'IDENTIFIER'
|
88
|
+
token = build_token(tok_type, lexeme)
|
81
89
|
elsif (lexeme = scanner.scan(/\|(?:[^|])*\|/)) # Vertical bar delimited
|
82
90
|
token = build_token('IDENTIFIER', lexeme)
|
83
91
|
elsif (lexeme = scanner.scan(/([\+\-])((?=\s|[|()";])|$)/))
|
data/lib/skeem/version.rb
CHANGED
@@ -0,0 +1,26 @@
|
|
1
|
+
require_relative '../spec_helper' # Use the RSpec framework
|
2
|
+
require_relative '../../lib/skeem/tokenizer' # Load the class under test
|
3
|
+
|
4
|
+
module Skeem
|
5
|
+
describe Parser do
|
6
|
+
|
7
|
+
context 'Initialization:' do
|
8
|
+
it 'should be initialized without argument' do
|
9
|
+
expect { Parser.new() }.not_to raise_error
|
10
|
+
end
|
11
|
+
|
12
|
+
it 'should have its enginer initialized' do
|
13
|
+
expect(subject.engine).to be_kind_of(Rley::Engine)
|
14
|
+
end
|
15
|
+
end # context
|
16
|
+
|
17
|
+
context 'Parsing:' do
|
18
|
+
it 'should parse definitions' do
|
19
|
+
source = "(define r 10)"
|
20
|
+
expect { subject.parse(source) }.not_to raise_error
|
21
|
+
end
|
22
|
+
end # context
|
23
|
+
end # describe
|
24
|
+
end # module
|
25
|
+
|
26
|
+
# End of file
|
@@ -10,7 +10,7 @@ module Skeem
|
|
10
10
|
expect(token.lexeme).to eq(lexeme)
|
11
11
|
end
|
12
12
|
end
|
13
|
-
|
13
|
+
|
14
14
|
def unquoted(aString)
|
15
15
|
aString.gsub(/(^")|("$)/, '')
|
16
16
|
end
|
@@ -141,18 +141,64 @@ containing just one line"
|
|
141
141
|
end
|
142
142
|
end
|
143
143
|
end # context
|
144
|
-
|
144
|
+
|
145
145
|
context 'Scanning Scheme sample code' do
|
146
146
|
it 'should read examples from lis.py page' do
|
147
|
+
# Shallow tokenizer testing
|
147
148
|
source = <<-SCHEME
|
148
|
-
(if (> (val x) 0)
|
149
|
-
(fn (+ (aref A i) (* 3 i))
|
149
|
+
(if (> (val x) 0)
|
150
|
+
(fn (+ (aref A i) (* 3 i))
|
150
151
|
(quote (one two)))
|
151
152
|
end
|
152
153
|
end
|
153
154
|
SCHEME
|
154
155
|
subject.reinitialize(source)
|
155
156
|
expect { subject.tokens }.not_to raise_error
|
157
|
+
|
158
|
+
source = "(define circle-area (lambda (r) (* pi (* r r))))"
|
159
|
+
subject.reinitialize(source)
|
160
|
+
expect { subject.tokens }.not_to raise_error
|
161
|
+
|
162
|
+
source = "(define fact (lambda (n) (if (<= n 1) 1 (* n (fact (- n 1))))))"
|
163
|
+
subject.reinitialize(source)
|
164
|
+
expect { subject.tokens }.not_to raise_error
|
165
|
+
|
166
|
+
source = <<-SCHEME
|
167
|
+
define first car)
|
168
|
+
define rest cdr)
|
169
|
+
define count (lambda (item L) (if L (+ (equal? item (first L)) (count item (rest L))) 0)))
|
170
|
+
count 0 (list 0 1 2 3 0 0))
|
171
|
+
SCHEME
|
172
|
+
subject.reinitialize(source)
|
173
|
+
expect { subject.tokens }.not_to raise_error
|
174
|
+
end
|
175
|
+
|
176
|
+
it 'should produce a sequence of token objects' do
|
177
|
+
# Deeper tokenizer testing
|
178
|
+
source = "(define circle-area (lambda (r) (* pi (* r r))))"
|
179
|
+
subject.reinitialize(source)
|
180
|
+
predicted = [
|
181
|
+
['LPAREN', '('],
|
182
|
+
['DEFINE', 'define'],
|
183
|
+
['IDENTIFIER', 'circle-area'],
|
184
|
+
['LPAREN', '('],
|
185
|
+
['IDENTIFIER', 'lambda'],
|
186
|
+
['LPAREN', '('],
|
187
|
+
['IDENTIFIER', 'r'],
|
188
|
+
['RPAREN', ')'],
|
189
|
+
['LPAREN', '('],
|
190
|
+
['IDENTIFIER', '*'],
|
191
|
+
['IDENTIFIER', 'pi'],
|
192
|
+
['LPAREN', '('],
|
193
|
+
['IDENTIFIER', '*'],
|
194
|
+
['IDENTIFIER', 'r'],
|
195
|
+
['IDENTIFIER', 'r'],
|
196
|
+
['RPAREN', ')'],
|
197
|
+
['RPAREN', ')'],
|
198
|
+
['RPAREN', ')'],
|
199
|
+
['RPAREN', ')']
|
200
|
+
]
|
201
|
+
match_expectations(subject, predicted)
|
156
202
|
end
|
157
203
|
end # context
|
158
204
|
end # describe
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: skeem
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dimitri Geshef
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-08-
|
11
|
+
date: 2018-08-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rley
|
@@ -85,10 +85,13 @@ files:
|
|
85
85
|
- Rakefile
|
86
86
|
- appveyor.yml
|
87
87
|
- lib/skeem.rb
|
88
|
+
- lib/skeem/grammar.rb
|
89
|
+
- lib/skeem/parser.rb
|
88
90
|
- lib/skeem/stoken.rb
|
89
91
|
- lib/skeem/tokenizer.rb
|
90
92
|
- lib/skeem/version.rb
|
91
93
|
- skeem.gemspec
|
94
|
+
- spec/skeem/parser_spec.rb
|
92
95
|
- spec/skeem/tokenizer_spec.rb
|
93
96
|
- spec/skeem_spec.rb
|
94
97
|
- spec/spec_helper.rb
|
@@ -119,5 +122,6 @@ specification_version: 4
|
|
119
122
|
summary: Skeem is an interpreter of a subset of the Scheme programming language. Scheme
|
120
123
|
is a descendent of the Lisp language.
|
121
124
|
test_files:
|
125
|
+
- spec/skeem/parser_spec.rb
|
122
126
|
- spec/skeem/tokenizer_spec.rb
|
123
127
|
- spec/skeem_spec.rb
|