rlex 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +74 -0
- data/Rakefile +2 -0
- data/lib/rlex.rb +8 -0
- data/lib/rlex/lexer.rb +172 -0
- data/lib/rlex/token.rb +16 -0
- data/lib/rlex/version.rb +4 -0
- data/rlex.gemspec +20 -0
- data/spec/rlex/lexer_spec.rb +69 -0
- data/spec/spec_helper.rb +11 -0
- metadata +69 -0
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Rasmus Borgsmidt
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Rlex
|
2
|
+
|
3
|
+
Provides a simple lexer based on the <tt>StringScanner</tt> class.
|
4
|
+
|
5
|
+
The lexer was written for use with Racc, a Ruby variant of
|
6
|
+
Yacc. But there is no code dependency on that project so the
|
7
|
+
lexer may also be used on its own or with other packages.
|
8
|
+
|
9
|
+
* Ignored input takes precedence over rules and keywords, so if
|
10
|
+
a prefix is matched by an ignore pattern, it's ignored even if
|
11
|
+
it's also a keyword or matched by a rule
|
12
|
+
* The lexer is greedy, so if a prefix is matched by multiple
|
13
|
+
rules or keywords, the lexer chooses the option consuming the
|
14
|
+
most input
|
15
|
+
|
16
|
+
## Documentation
|
17
|
+
|
18
|
+
Find out more about this project on [GitHub][gh_rlex],
|
19
|
+
[RubyGems][rg_rlex] and [RubyDoc][rd_rlex].
|
20
|
+
|
21
|
+
[gh_rlex]: https://github.com/borgsmidt/rlex
|
22
|
+
[rg_rlex]: http://rubygems.org/gems/rlex
|
23
|
+
[rd_rlex]: http://rubydoc.info/gems/rlex
|
24
|
+
|
25
|
+
## Installation
|
26
|
+
|
27
|
+
Install the gem using:
|
28
|
+
|
29
|
+
$ gem install rlex
|
30
|
+
|
31
|
+
Alternatively, add this line to your application's Gemfile:
|
32
|
+
|
33
|
+
gem 'rlex'
|
34
|
+
|
35
|
+
Then execute:
|
36
|
+
|
37
|
+
$ bundle
|
38
|
+
|
39
|
+
## Usage
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
# Define behavior
|
43
|
+
lexer = Lexer.new
|
44
|
+
lexer.ignore /\s+/ # ignore whitespace
|
45
|
+
lexer.rule :word, /\w+/ # consider any text a 'word'
|
46
|
+
lexer.keyword :if # treat 'if' as a special keyword
|
47
|
+
lexer.keyword :lparen, "(" # any fixed input such as parentheses
|
48
|
+
lexer.keyword :rparen, ")" # may be defined as keywords
|
49
|
+
|
50
|
+
# Initialize with input
|
51
|
+
lexer.start "if ( foo ) bar" # initialize the lexer with a string
|
52
|
+
|
53
|
+
# Iterate through tokens
|
54
|
+
lexer.next_token # => Token (type = :if, value = 'if' )
|
55
|
+
lexer.next_token # => Token (type = :lparen, value = '(' )
|
56
|
+
lexer.next_token # => Token (type = :word, value = 'foo')
|
57
|
+
lexer.next_token # => Token (type = :rparen, value = ')' )
|
58
|
+
lexer.next_token # => Token (type = :word, value = 'bar')
|
59
|
+
lexer.next_token # => EOF_TOKEN
|
60
|
+
```
|
61
|
+
|
62
|
+
## Contributing
|
63
|
+
|
64
|
+
1. Fork it on [GitHub][gh_rlex]
|
65
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
66
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
67
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
68
|
+
5. Create new Pull Request
|
69
|
+
|
70
|
+
## License
|
71
|
+
|
72
|
+
Written by Rasmus Borgsmidt <<rasmus@borgsmidt.dk>>
|
73
|
+
|
74
|
+
Released under the MIT license: www.opensource.org/licenses/MIT
|
data/Rakefile
ADDED
data/lib/rlex.rb
ADDED
data/lib/rlex/lexer.rb
ADDED
@@ -0,0 +1,172 @@
|
|
1
|
+
require 'strscan'
|
2
|
+
require 'rlex/token'
|
3
|
+
|
4
|
+
module Rlex
|
5
|
+
# Implements a simple lexer using a <tt>StringScanner</tt>.
|
6
|
+
#
|
7
|
+
# The lexer was written for use with Racc, a Ruby variant of
|
8
|
+
# Yacc. But there is no code dependency on that project so the
|
9
|
+
# lexer may also be used on its own or with other packages.
|
10
|
+
#
|
11
|
+
# * Ignored input takes precedence over rules and keywords, so if
|
12
|
+
# a prefix is matched by an ignore pattern, it's ignored even if
|
13
|
+
# it's also a keyword or matched by a rule
|
14
|
+
# * The lexer is greedy, so if a prefix is matched by multiple
|
15
|
+
# rules or keywords, the lexer chooses the option consuming the
|
16
|
+
# most input
|
17
|
+
#
|
18
|
+
# @author Rasmus Borgsmidt <rasmus@borgsmidt.dk>
|
19
|
+
#
|
20
|
+
# @example Basic usage
|
21
|
+
# # Define behavior
|
22
|
+
# lexer = Lexer.new
|
23
|
+
# lexer.ignore /\s+/ # ignore whitespace
|
24
|
+
# lexer.rule :word, /\w+/ # consider any text a 'word'
|
25
|
+
# lexer.keyword :if # treat 'if' as a special keyword
|
26
|
+
# lexer.keyword :lparen, "(" # any fixed input such as parentheses
|
27
|
+
# lexer.keyword :rparen, ")" # may be defined as keywords
|
28
|
+
#
|
29
|
+
# # Initialize with input
|
30
|
+
# lexer.start "if ( foo ) bar" # initialize the lexer with a string
|
31
|
+
#
|
32
|
+
# # Iterate through tokens
|
33
|
+
# lexer.next_token # => Token (type = :if, value = 'if')
|
34
|
+
# lexer.next_token # => Token (type = :lparen, value = '(')
|
35
|
+
# lexer.next_token # => Token (type = :word, value = 'foo')
|
36
|
+
# lexer.next_token # => Token (type = :rparen, value = ')')
|
37
|
+
# lexer.next_token # => Token (type = :word, value = 'bar')
|
38
|
+
# lexer.next_token # => EOF_TOKEN
|
39
|
+
#
|
40
|
+
class Lexer
|
41
|
+
# Initializes an empty Lexer.
|
42
|
+
#
|
43
|
+
def initialize
|
44
|
+
@ignored = []
|
45
|
+
@rules = []
|
46
|
+
@keywords = {}
|
47
|
+
end
|
48
|
+
|
49
|
+
# Instructs the lexer to ignore input matched by the specified
|
50
|
+
# pattern. If appropriate, call this multiple times to ignore
|
51
|
+
# several patterns.
|
52
|
+
#
|
53
|
+
# @note Ignored input takes precedence over rules and keywords,
|
54
|
+
# so if a prefix is matched by an ignore pattern, it's ignored
|
55
|
+
# even if it's also a keyword or matched by a rule
|
56
|
+
#
|
57
|
+
# @param [Regexp] pattern Pattern of input to ignore
|
58
|
+
#
|
59
|
+
# @return [Regexp] The specified pattern
|
60
|
+
#
|
61
|
+
def ignore(pattern)
|
62
|
+
@ignored << pattern
|
63
|
+
return pattern
|
64
|
+
end
|
65
|
+
|
66
|
+
# Defines a rule to match the specified pattern.
|
67
|
+
#
|
68
|
+
# @note Use keywords for efficiency instead of rules whenever
|
69
|
+
# the matched input is static
|
70
|
+
#
|
71
|
+
# @param [Symbol, #to_sym] name Unique name of rule
|
72
|
+
# @param [Regexp] pattern Pattern of input to match
|
73
|
+
#
|
74
|
+
# @raise [ArgumentError] If the specified name is already
|
75
|
+
# used by other rules or keywords
|
76
|
+
#
|
77
|
+
# @return [Symbol] The name of the rule
|
78
|
+
#
|
79
|
+
def rule(name, pattern)
|
80
|
+
# @todo Validate the rule name
|
81
|
+
@rules << (Rule.new name.to_sym, pattern)
|
82
|
+
return name.to_sym
|
83
|
+
end
|
84
|
+
|
85
|
+
# Defines a static sequence of input as a keyword.
|
86
|
+
#
|
87
|
+
# @note Use keywords for efficiency instead of rules whenever
|
88
|
+
# the matched input is static
|
89
|
+
#
|
90
|
+
# @param [optional, Symbol, #to_sym] name Unique name of the
|
91
|
+
# keyword. If this argument is not given, the keyword is used
|
92
|
+
# to name itself
|
93
|
+
# @param [String, #to_s] kword Sequence of input to match as a
|
94
|
+
# keyword
|
95
|
+
#
|
96
|
+
# @raise [ArgumentError] If the specified name is already
|
97
|
+
# used by other rules or keywords
|
98
|
+
#
|
99
|
+
# @return [Symbol] The name of the keyword
|
100
|
+
#
|
101
|
+
def keyword(name = nil, kword)
|
102
|
+
# @todo Validate the keyword name
|
103
|
+
name = kword if name == nil
|
104
|
+
pattern = Regexp.new(Regexp.escape kword.to_s)
|
105
|
+
rule name, pattern
|
106
|
+
@keywords[kword.to_s] = Token.new name.to_sym, kword.to_s
|
107
|
+
return name.to_sym
|
108
|
+
end
|
109
|
+
|
110
|
+
# Initializes the lexer with new input.
|
111
|
+
#
|
112
|
+
# @note This resets the lexer with a new StringScanner so any
|
113
|
+
# state information related to previous input is lost
|
114
|
+
#
|
115
|
+
# @param [String] input Input to scan for tokens
|
116
|
+
#
|
117
|
+
# @return [String] The specified input
|
118
|
+
#
|
119
|
+
def start(input)
|
120
|
+
@scanner = StringScanner.new input
|
121
|
+
return input
|
122
|
+
end
|
123
|
+
|
124
|
+
# Returns the next token matched from the remaining input. If no
|
125
|
+
# input is left, or the lexer has not been initialized,
|
126
|
+
# <tt>EOF_TOKEN</tt> is returned.
|
127
|
+
#
|
128
|
+
# @raise [RuntimeError] If there is any unmatched input
|
129
|
+
#
|
130
|
+
# @return [Token] Next token or <tt>EOF_TOKEN</tt>
|
131
|
+
#
|
132
|
+
def next_token
|
133
|
+
return EOF_TOKEN if @scanner.nil? or @scanner.empty?
|
134
|
+
return next_token if ignore_prefix?
|
135
|
+
rule = greediest_rule
|
136
|
+
if rule
|
137
|
+
prefix = @scanner.scan(rule.pattern)
|
138
|
+
keyword = @keywords[prefix]
|
139
|
+
return keyword ? keyword : Token.new(rule.name, prefix)
|
140
|
+
end
|
141
|
+
raise "unexpected input <#{@scanner.peek(5)}>"
|
142
|
+
end
|
143
|
+
|
144
|
+
private
|
145
|
+
|
146
|
+
# @private
|
147
|
+
Rule = Struct.new :name, :pattern
|
148
|
+
|
149
|
+
# @private
|
150
|
+
def ignore_prefix?
|
151
|
+
@ignored.each do |pattern|
|
152
|
+
prefix = @scanner.scan(pattern)
|
153
|
+
return true if prefix
|
154
|
+
end
|
155
|
+
return false
|
156
|
+
end
|
157
|
+
|
158
|
+
# @private
|
159
|
+
def greediest_rule
|
160
|
+
r = nil
|
161
|
+
len = 0
|
162
|
+
@rules.each do |rule|
|
163
|
+
prefix = @scanner.check(rule.pattern)
|
164
|
+
if prefix and prefix.length > len
|
165
|
+
r = rule
|
166
|
+
len = prefix.length
|
167
|
+
end
|
168
|
+
end
|
169
|
+
return r
|
170
|
+
end
|
171
|
+
end
|
172
|
+
end
|
data/lib/rlex/token.rb
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
module Rlex
|
2
|
+
# Simple class to represent tokens matched from the input.
|
3
|
+
#
|
4
|
+
# @author Rasmus Borgsmidt <rasmus@borgsmidt.dk>
|
5
|
+
#
|
6
|
+
# @attr_reader [Symbol] type Type of the token, such as the name of
|
7
|
+
# the rule used to match it
|
8
|
+
# @attr_reader [String] value Text matched from the input
|
9
|
+
#
|
10
|
+
Token = Struct.new :type, :value
|
11
|
+
|
12
|
+
# Special token used when the lexer has reached the end of the
|
13
|
+
# specified input.
|
14
|
+
#
|
15
|
+
EOF_TOKEN = Token.new :eof, ""
|
16
|
+
end
|
data/lib/rlex/version.rb
ADDED
data/rlex.gemspec
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/rlex/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Rasmus Borgsmidt"]
|
6
|
+
gem.email = ["rasmus@borgsmidt.dk"]
|
7
|
+
gem.description = %q{Implements a simple lexer using a StringScanner}
|
8
|
+
gem.summary = %q{The lexer was written for use with Racc, a
|
9
|
+
Ruby variant of Yacc. But there is no code
|
10
|
+
dependency on that project so the lexer may
|
11
|
+
also be used on its own or with other packages.}
|
12
|
+
gem.homepage = "https://github.com/borgsmidt/rlex"
|
13
|
+
|
14
|
+
gem.files = `git ls-files`.split($\)
|
15
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
16
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
17
|
+
gem.name = "rlex"
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.version = Rlex::VERSION
|
20
|
+
end
|
@@ -0,0 +1,69 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
require 'rlex/token'
|
3
|
+
require 'rlex/lexer'
|
4
|
+
include Rlex
|
5
|
+
|
6
|
+
describe Lexer do
|
7
|
+
before :each do
|
8
|
+
@lexer = Lexer.new
|
9
|
+
end
|
10
|
+
|
11
|
+
describe "next_token" do
|
12
|
+
it "should return EOF_TOKEN when the lexer has been assigned no input" do
|
13
|
+
@lexer.next_token.should eq EOF_TOKEN
|
14
|
+
end
|
15
|
+
|
16
|
+
it "should return EOF_TOKEN when there is no more input" do
|
17
|
+
@lexer.start ""
|
18
|
+
@lexer.next_token.should eq EOF_TOKEN
|
19
|
+
end
|
20
|
+
|
21
|
+
it "should raise an error when remaining input is not matched by any rules" do
|
22
|
+
@lexer.start "unmatched input"
|
23
|
+
lambda {@lexer.next_token}.should raise_error RuntimeError
|
24
|
+
end
|
25
|
+
|
26
|
+
it "should return EOF_TOKEN when instructed to ignore everything" do
|
27
|
+
@lexer.ignore /.*/
|
28
|
+
@lexer.start "input to be ignored"
|
29
|
+
@lexer.next_token.should eq EOF_TOKEN
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should return recognized keywords and finish with EOF_TOKEN" do
|
33
|
+
@lexer.ignore /\s+/
|
34
|
+
@lexer.keyword :special
|
35
|
+
@lexer.start " \t\nspecialspecial special "
|
36
|
+
special = Token.new :special, "special"
|
37
|
+
@lexer.next_token.should eq special
|
38
|
+
@lexer.next_token.should eq special
|
39
|
+
@lexer.next_token.should eq special
|
40
|
+
@lexer.next_token.should eq EOF_TOKEN
|
41
|
+
end
|
42
|
+
|
43
|
+
it "should return tokens matched by regular rules and finish with EOF_TOKEN" do
|
44
|
+
@lexer.ignore /\s+/
|
45
|
+
@lexer.rule :word, /\w+/
|
46
|
+
@lexer.start "sentence with four tokens"
|
47
|
+
@lexer.next_token.should eq Token.new :word, "sentence"
|
48
|
+
@lexer.next_token.should eq Token.new :word, "with"
|
49
|
+
@lexer.next_token.should eq Token.new :word, "four"
|
50
|
+
@lexer.next_token.should eq Token.new :word, "tokens"
|
51
|
+
@lexer.next_token.should eq EOF_TOKEN
|
52
|
+
end
|
53
|
+
|
54
|
+
it "should return all types of tokens and finish with EOF_TOKEN" do
|
55
|
+
@lexer.ignore /\s+/
|
56
|
+
@lexer.keyword :if
|
57
|
+
@lexer.keyword :lparen, "("
|
58
|
+
@lexer.keyword :rparen, ")"
|
59
|
+
@lexer.rule :word, /\w+/
|
60
|
+
@lexer.start "ifu ( if ) ifu"
|
61
|
+
@lexer.next_token.should eq Token.new :word, "ifu"
|
62
|
+
@lexer.next_token.should eq Token.new :lparen, "("
|
63
|
+
@lexer.next_token.should eq Token.new :if, "if"
|
64
|
+
@lexer.next_token.should eq Token.new :rparen, ")"
|
65
|
+
@lexer.next_token.should eq Token.new :word, "ifu"
|
66
|
+
@lexer.next_token.should eq EOF_TOKEN
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
2
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
3
|
+
# Require this file using `require "spec_helper.rb"` to ensure that it is only
|
4
|
+
# loaded once.
|
5
|
+
#
|
6
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
7
|
+
RSpec.configure do |config|
|
8
|
+
config.treat_symbols_as_metadata_keys_with_true_values = true
|
9
|
+
config.run_all_when_everything_filtered = true
|
10
|
+
config.filter_run :focus
|
11
|
+
end
|
metadata
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rlex
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease:
|
5
|
+
version: 0.5.0
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Rasmus Borgsmidt
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
|
13
|
+
date: 2012-04-24 00:00:00 Z
|
14
|
+
dependencies: []
|
15
|
+
|
16
|
+
description: Implements a simple lexer using a StringScanner
|
17
|
+
email:
|
18
|
+
- rasmus@borgsmidt.dk
|
19
|
+
executables: []
|
20
|
+
|
21
|
+
extensions: []
|
22
|
+
|
23
|
+
extra_rdoc_files: []
|
24
|
+
|
25
|
+
files:
|
26
|
+
- .gitignore
|
27
|
+
- .rspec
|
28
|
+
- Gemfile
|
29
|
+
- LICENSE
|
30
|
+
- README.md
|
31
|
+
- Rakefile
|
32
|
+
- lib/rlex.rb
|
33
|
+
- lib/rlex/lexer.rb
|
34
|
+
- lib/rlex/token.rb
|
35
|
+
- lib/rlex/version.rb
|
36
|
+
- rlex.gemspec
|
37
|
+
- spec/rlex/lexer_spec.rb
|
38
|
+
- spec/spec_helper.rb
|
39
|
+
homepage: https://github.com/borgsmidt/rlex
|
40
|
+
licenses: []
|
41
|
+
|
42
|
+
post_install_message:
|
43
|
+
rdoc_options: []
|
44
|
+
|
45
|
+
require_paths:
|
46
|
+
- lib
|
47
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
48
|
+
none: false
|
49
|
+
requirements:
|
50
|
+
- - ">="
|
51
|
+
- !ruby/object:Gem::Version
|
52
|
+
version: "0"
|
53
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
54
|
+
none: false
|
55
|
+
requirements:
|
56
|
+
- - ">="
|
57
|
+
- !ruby/object:Gem::Version
|
58
|
+
version: "0"
|
59
|
+
requirements: []
|
60
|
+
|
61
|
+
rubyforge_project:
|
62
|
+
rubygems_version: 1.8.11
|
63
|
+
signing_key:
|
64
|
+
specification_version: 3
|
65
|
+
summary: The lexer was written for use with Racc, a Ruby variant of Yacc. But there is no code dependency on that project so the lexer may also be used on its own or with other packages.
|
66
|
+
test_files:
|
67
|
+
- spec/rlex/lexer_spec.rb
|
68
|
+
- spec/spec_helper.rb
|
69
|
+
has_rdoc:
|