paco 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/CHANGELOG.md +22 -0
- data/LICENSE.txt +21 -0
- data/README.md +42 -0
- data/bin/console +15 -0
- data/bin/setup +8 -0
- data/lib/paco/combinators/char.rb +206 -0
- data/lib/paco/combinators.rb +183 -0
- data/lib/paco/context.rb +40 -0
- data/lib/paco/parse_error.rb +29 -0
- data/lib/paco/parser.rb +168 -0
- data/lib/paco/version.rb +5 -0
- data/lib/paco.rb +17 -0
- metadata +60 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 874b690b05bae4b9627aab0da0d248b020de705fbbbc88be1dc6e08afdeb8bc5
|
4
|
+
data.tar.gz: 4d69df9a10c651470acc62b297c0c628ab80afa2f508c3f0588c24e811b14000
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6c5ed079f9a70a4eb11dc754ed24b59d1b50ee9e5a29baf36ab9f61cb040c6609284f8d4b9d6f3044d1ab26e8617a349b4b3811026c97b87c731d423422576d5
|
7
|
+
data.tar.gz: b1afa018f1646c3421e21d01be36cd052468cb824843dc66dd38cabd92a92aee734470a08fd5b169c5bbdadab196440543e1e14419322079e50cb0b31b82fd49
|
data/CHANGELOG.md
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# Changelog
|
2
|
+
|
3
|
+
All notable changes to this project will be documented in this file.
|
4
|
+
|
5
|
+
The format is based on [Keep a Changelog],
|
6
|
+
and this project adheres to [Semantic Versioning].
|
7
|
+
|
8
|
+
## [Unreleased]
|
9
|
+
|
10
|
+
## [0.1.0]
|
11
|
+
|
12
|
+
### Added
|
13
|
+
|
14
|
+
- Initial implementation. ([@skryukov])
|
15
|
+
|
16
|
+
[@skryukov]: https://github.com/skryukov
|
17
|
+
|
18
|
+
[Unreleased]: https://github.com/skryukov/paco/compare/v0.1.0...HEAD
|
19
|
+
[0.1.0]: https://github.com/skryukov/paco/commits/v0.1.0
|
20
|
+
|
21
|
+
[Keep a Changelog]: https://keepachangelog.com/en/1.0.0/
|
22
|
+
[Semantic Versioning]: https://semver.org/spec/v2.0.0.html
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2021 Svyatoslav Kryukov
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
# Paco
|
2
|
+
|
3
|
+
Paco is a parser combinator library inspired by Haskell's [Parsec] and [Parsimmon].
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem "paco"
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle install
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install paco
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
See [API documentation](docs/paco.md), [examples](examples) and [specs](spec).
|
24
|
+
|
25
|
+
## Development
|
26
|
+
|
27
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `bundle exec rspec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
28
|
+
|
29
|
+
To install this gem onto your local machine, run `bundle exec rake install`.
|
30
|
+
|
31
|
+
## Contributing
|
32
|
+
|
33
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/skryukov/paco.
|
34
|
+
|
35
|
+
## License
|
36
|
+
|
37
|
+
The gem is available as open source under the terms of the [MIT License].
|
38
|
+
|
39
|
+
[MIT License]: https://opensource.org/licenses/MIT
|
40
|
+
[Parsec]: https://github.com/haskell/parsec
|
41
|
+
[Parsimmon]: https://github.com/jneen/parsimmon
|
42
|
+
[parsby]: https://github.com/jolmg/parsby
|
data/bin/console
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require "bundler/setup"
|
5
|
+
require "paco"
|
6
|
+
|
7
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
8
|
+
# with your gem easier. You can also use a different console, if you like.
|
9
|
+
|
10
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
11
|
+
# require "pry"
|
12
|
+
# Pry.start
|
13
|
+
|
14
|
+
require "irb"
|
15
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
@@ -0,0 +1,206 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Paco
|
4
|
+
module Combinators
|
5
|
+
module Char
|
6
|
+
# Returns a parser that returns a single character if passed block result is truthy:
|
7
|
+
#
|
8
|
+
# @example
|
9
|
+
# lower = Combinators.satisfy do |char|
|
10
|
+
# char == char.downcase
|
11
|
+
# end
|
12
|
+
#
|
13
|
+
# lower.parse("a") #=> "a"
|
14
|
+
# lower.parse("P") #=> ParseError
|
15
|
+
#
|
16
|
+
# @param [String] desc optional description for the parser
|
17
|
+
# @param [Proc] block proc with one argument – a next char of the input
|
18
|
+
# @return [Paco::Parser]
|
19
|
+
def satisfy(desc = "", &block)
|
20
|
+
Parser.new(desc) do |ctx, parser|
|
21
|
+
parser.failure(ctx) if ctx.eof?
|
22
|
+
|
23
|
+
char = ctx.read(1)
|
24
|
+
parser.failure(ctx) unless block.call(char)
|
25
|
+
|
26
|
+
ctx.pos += 1
|
27
|
+
char
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
# Returns a parser that looks for a passed `matcher` string and returns its value on success.
|
32
|
+
# @param [String] matcher
|
33
|
+
# @return [Paco::Parser]
|
34
|
+
def string(matcher)
|
35
|
+
Parser.new(matcher) do |ctx, parser|
|
36
|
+
src = ctx.read(matcher.length)
|
37
|
+
parser.failure(ctx) if src != matcher
|
38
|
+
|
39
|
+
ctx.pos += matcher.length
|
40
|
+
src
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
# Returns a parser that looks for a match to the regexp and returns the entire text matched.
|
45
|
+
# The regexp will always match starting at the current parse location.
|
46
|
+
# When `group` is specified, it returns only the text in the specific regexp match group.
|
47
|
+
# @param [Regexp] regexp
|
48
|
+
# @return [Paco::Parser]
|
49
|
+
def regexp(regexp, group: 0)
|
50
|
+
anchored_regexp = Regexp.new("^(?:#{regexp.source})", regexp.options)
|
51
|
+
Parser.new(regexp.inspect) do |ctx, parser|
|
52
|
+
match = anchored_regexp.match(ctx.read_all)
|
53
|
+
parser.failure(ctx) if match.nil?
|
54
|
+
|
55
|
+
ctx.pos += match[0].length
|
56
|
+
match[group]
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
60
|
+
# Returns a parser that checks current character against the passed `regexp`
|
61
|
+
# @param [Regexp] regexp
|
62
|
+
# @return [Paco::Parser]
|
63
|
+
def regexp_char(regexp)
|
64
|
+
satisfy(regexp.inspect) { |char| regexp.match?(char) }
|
65
|
+
end
|
66
|
+
|
67
|
+
# Returns a parser that looks for exactly one character from passed
|
68
|
+
# `matcher`, and returns its value on success.
|
69
|
+
# @param [String, Array<String>] matcher
|
70
|
+
# @return [Paco::Parser]
|
71
|
+
def one_of(matcher)
|
72
|
+
satisfy(matcher.to_s) { |char| matcher.include?(char) }
|
73
|
+
end
|
74
|
+
|
75
|
+
# Returns a parser that looks for exactly one character _NOT_ from passed
|
76
|
+
# `matcher`, and returns its value on success.
|
77
|
+
# @param [String, Array<String>] matcher
|
78
|
+
# @return [Paco::Parser]
|
79
|
+
def none_of(matcher)
|
80
|
+
satisfy("not #{matcher}") { |char| !matcher.include?(char) }
|
81
|
+
end
|
82
|
+
|
83
|
+
# Returns a parser that consumes and returns the next character of the input.
|
84
|
+
# @return [Paco::Parser]
|
85
|
+
def any_char
|
86
|
+
memoize { satisfy("any_char") { |ch| ch.length > 0 } }
|
87
|
+
end
|
88
|
+
|
89
|
+
# Returns a parser that consumes and returns the entire remainder of the input.
|
90
|
+
# @return [Paco::Parser]
|
91
|
+
def remainder
|
92
|
+
memoize do
|
93
|
+
Parser.new("remainder of the input") do |ctx, parser|
|
94
|
+
result = ctx.read_all
|
95
|
+
ctx.pos += result.length
|
96
|
+
result
|
97
|
+
end
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
# Returns a parser that returns a string containing all the next
|
102
|
+
# characters that are truthy for the passed block.
|
103
|
+
# @param [Proc] block proc with one argument – a next char of the input
|
104
|
+
# @return [Paco::Parser]
|
105
|
+
def take_while(&block)
|
106
|
+
satisfy(&block).many.join
|
107
|
+
end
|
108
|
+
|
109
|
+
# Returns a parser that matches end of file and returns nil.
|
110
|
+
# @return [Paco::Parser]
|
111
|
+
def eof
|
112
|
+
memoize do
|
113
|
+
Parser.new("end of file") do |ctx, parser|
|
114
|
+
parser.failure(ctx) unless ctx.eof?
|
115
|
+
nil
|
116
|
+
end
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
# Returns a parser that checks for the "carriage return" (`\r`) character.
|
121
|
+
# @return [Paco::Parser]
|
122
|
+
def cr
|
123
|
+
memoize { string("\r") }
|
124
|
+
end
|
125
|
+
|
126
|
+
# Returns a parser that checks for the "line feed" (`\n`) character.
|
127
|
+
# @return [Paco::Parser]
|
128
|
+
def lf
|
129
|
+
memoize { string("\n") }
|
130
|
+
end
|
131
|
+
|
132
|
+
# Returns a parser that checks for the "carriage return" character followed by the "line feed" character (`\r\n`).
|
133
|
+
# @return [Paco::Parser]
|
134
|
+
def crlf
|
135
|
+
memoize { string("\r\n") }
|
136
|
+
end
|
137
|
+
|
138
|
+
# Returns a parser that will match any kind of line ending.
|
139
|
+
# @return [Paco::Parser]
|
140
|
+
def newline
|
141
|
+
memoize { alt(crlf, lf, cr) }
|
142
|
+
end
|
143
|
+
|
144
|
+
# Returns a parser that will match any kind of line ending *including* end of file.
|
145
|
+
# @return [Paco::Parser]
|
146
|
+
def end_of_line
|
147
|
+
memoize { alt(newline, eof) }
|
148
|
+
end
|
149
|
+
|
150
|
+
# Alias for `Paco::Combinators.regexp(/[a-z]/i)`.
|
151
|
+
# @return [Paco::Parser]
|
152
|
+
def letter
|
153
|
+
memoize { regexp_char(/[a-z]/i) }
|
154
|
+
end
|
155
|
+
|
156
|
+
# Alias for `Paco::Combinators.regexp(/[a-z]+/i)`.
|
157
|
+
# @return [Paco::Parser]
|
158
|
+
def letters
|
159
|
+
memoize { seq(letter, letter.many).fmap { |x| x.flatten.join } }
|
160
|
+
end
|
161
|
+
|
162
|
+
# Alias for `Paco::Combinators.regexp(/[a-z]*/i)`.
|
163
|
+
# @return [Paco::Parser]
|
164
|
+
def opt_letters
|
165
|
+
memoize { letters | succeed("") }
|
166
|
+
end
|
167
|
+
|
168
|
+
# Alias for `Paco::Combinators.regexp(/[0-9]/)`.
|
169
|
+
# @return [Paco::Parser]
|
170
|
+
def digit
|
171
|
+
memoize { regexp_char(/[0-9]/) }
|
172
|
+
end
|
173
|
+
|
174
|
+
# Alias for `Paco::Combinators.regexp(/[0-9]+/)`.
|
175
|
+
# @return [Paco::Parser]
|
176
|
+
def digits
|
177
|
+
memoize { seq(digit, digit.many).fmap { |x| x.flatten.join } }
|
178
|
+
end
|
179
|
+
|
180
|
+
# Alias for `Paco::Combinators.regexp(/[0-9]*/)`.
|
181
|
+
# @return [Paco::Parser]
|
182
|
+
def opt_digits
|
183
|
+
memoize { digits | succeed("") }
|
184
|
+
end
|
185
|
+
|
186
|
+
# Alias for `Paco::Combinators.regexp(/\s+/)`.
|
187
|
+
# @return [Paco::Parser]
|
188
|
+
def ws
|
189
|
+
memoize { regexp(/\s+/) }
|
190
|
+
end
|
191
|
+
|
192
|
+
# Alias for `Paco::Combinators.regexp(/\s*/)`.
|
193
|
+
# @return [Paco::Parser]
|
194
|
+
def opt_ws
|
195
|
+
memoize { regexp(/\s*/) }
|
196
|
+
end
|
197
|
+
|
198
|
+
# Alias for `parser.trim(Paco::Combinators.opt_ws)`.
|
199
|
+
# @param [Paco::Parser] parser
|
200
|
+
# @return [Paco::Parser]
|
201
|
+
def spaced(parser)
|
202
|
+
parser.trim(opt_ws)
|
203
|
+
end
|
204
|
+
end
|
205
|
+
end
|
206
|
+
end
|
@@ -0,0 +1,183 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "monitor"
|
4
|
+
|
5
|
+
require "paco/combinators/char"
|
6
|
+
|
7
|
+
module Paco
|
8
|
+
module Combinators
|
9
|
+
def self.extended(base)
|
10
|
+
base.extend MonitorMixin
|
11
|
+
base.extend Char
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.included(base)
|
15
|
+
base.include MonitorMixin
|
16
|
+
base.include Char
|
17
|
+
end
|
18
|
+
|
19
|
+
extend self
|
20
|
+
|
21
|
+
# Returns a parser that runs the passed `parser` without consuming the input, and
|
22
|
+
# returns `null` if the passed `parser` _does not match_ the input. Fails otherwise.
|
23
|
+
# @param [Paco::Parser] parser
|
24
|
+
# @return [Paco::Parser]
|
25
|
+
def not_followed_by(parser)
|
26
|
+
Parser.new("not #{parser.desc}") do |ctx, pars|
|
27
|
+
start_pos = ctx.pos
|
28
|
+
begin
|
29
|
+
parser._parse(ctx)
|
30
|
+
rescue ParseError
|
31
|
+
ctx.pos = start_pos
|
32
|
+
nil
|
33
|
+
else
|
34
|
+
pars.failure(ctx)
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
# Returns a parser that doesn't consume any input and always returns `result`.
|
40
|
+
# @return [Paco::Parser]
|
41
|
+
def succeed(result)
|
42
|
+
Parser.new { result }
|
43
|
+
end
|
44
|
+
|
45
|
+
# Returns a parser that doesn't consume any input and always fails with passed `message`.
|
46
|
+
# @param [String] message
|
47
|
+
# @return [Paco::Parser]
|
48
|
+
def failed(message)
|
49
|
+
Parser.new(message) { |ctx, parser| parser.failure(ctx) }
|
50
|
+
end
|
51
|
+
|
52
|
+
# Returns a parser that runs the passed `parser` without consuming the input,
|
53
|
+
# and returns empty string.
|
54
|
+
# @param [Paco::Parser] parser
|
55
|
+
# @return [Paco::Parser]
|
56
|
+
def lookahead(parser)
|
57
|
+
Parser.new do |ctx|
|
58
|
+
start_pos = ctx.pos
|
59
|
+
parser._parse(ctx)
|
60
|
+
ctx.pos = start_pos
|
61
|
+
""
|
62
|
+
end
|
63
|
+
end
|
64
|
+
|
65
|
+
# Accepts any number of parsers, and returns a parser that returns the value of the first parser that succeeds, backtracking in between.
|
66
|
+
# @param [Array<Paco::Parser>] parsers
|
67
|
+
# @return [Paco::Parser]
|
68
|
+
def alt(*parsers)
|
69
|
+
raise ArgumentError, "no parsers specified" if parsers.empty?
|
70
|
+
|
71
|
+
Parser.new do |ctx|
|
72
|
+
result = nil
|
73
|
+
last_error = nil
|
74
|
+
start_pos = ctx.pos
|
75
|
+
parsers.each do |pars|
|
76
|
+
break result = {value: pars._parse(ctx)}
|
77
|
+
rescue ParseError => e
|
78
|
+
last_error = e
|
79
|
+
ctx.pos = start_pos
|
80
|
+
next
|
81
|
+
end
|
82
|
+
raise last_error unless result
|
83
|
+
result[:value]
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
# Accepts one or more parsers, and returns a parser that expects them
|
88
|
+
# to match in order, returns an array of all their results.
|
89
|
+
# @param [Array<Paco::Parser>] parsers
|
90
|
+
# @return [Paco::Parser]
|
91
|
+
def seq(*parsers)
|
92
|
+
raise ArgumentError, "no parsers specified" if parsers.empty?
|
93
|
+
|
94
|
+
Parser.new do |ctx|
|
95
|
+
parsers.map { |parser| parser._parse(ctx) }
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
# Returns a parser that matches all `parsers` sequentially, and passes
|
100
|
+
# their results as an arguments to a `block`, and at the end returns its result.
|
101
|
+
# @param [Array<Paco::Parser>] parsers
|
102
|
+
# @return [Paco::Parser]
|
103
|
+
def seq_map(*parsers, &block)
|
104
|
+
raise ArgumentError, "no parsers specified" if parsers.empty?
|
105
|
+
|
106
|
+
seq(*parsers).fmap do |results|
|
107
|
+
block.call(*results)
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
# Accepts a block that returns a parser, which is evaluated the first time the parser is used.
|
112
|
+
# This is useful for referencing parsers that haven't yet been defined, and for implementing recursive parsers.
|
113
|
+
# @return [Paco::Parser]
|
114
|
+
def lazy(desc = "", &block)
|
115
|
+
Parser.new(desc) { |ctx| block.call._parse(ctx) }
|
116
|
+
end
|
117
|
+
|
118
|
+
# Returns a parser that expects zero or more matches for `parser`,
|
119
|
+
# separated by the parser `separator`. Returns an array of `parser` results.
|
120
|
+
# @param [Paco::Parser] parser
|
121
|
+
# @param [Paco::Parser] separator
|
122
|
+
# @return [Paco::Parser]
|
123
|
+
def sep_by(parser, separator)
|
124
|
+
alt(sep_by_1(parser, separator), succeed([]))
|
125
|
+
end
|
126
|
+
|
127
|
+
# Returns a parser that expects one or more matches for `parser`,
|
128
|
+
# separated by the parser `separator`. Returns an array of `parser` results.
|
129
|
+
# @param [Paco::Parser] parser
|
130
|
+
# @param [Paco::Parser] separator
|
131
|
+
# @return [Paco::Parser]
|
132
|
+
def sep_by_1(parser, separator)
|
133
|
+
seq_map(parser, many(separator.next(parser))) do |first, arr|
|
134
|
+
[first] + arr
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
138
|
+
# Expects the parser `before` before `parser` and `after` after `parser. Returns the result of the parser.
|
139
|
+
# @param [Paco::Parser] before
|
140
|
+
# @param [Paco::Parser] after
|
141
|
+
# @param [Paco::Parser] parser
|
142
|
+
# @return [Paco::Parser]
|
143
|
+
def wrap(before, after, parser)
|
144
|
+
before.next(parser).skip(after)
|
145
|
+
end
|
146
|
+
|
147
|
+
# Expects `parser` zero or more times, and returns an array of the results.
|
148
|
+
# @param [Paco::Parser] parser
|
149
|
+
# @return [Paco::Parser]
|
150
|
+
def many(parser)
|
151
|
+
Parser.new do |ctx|
|
152
|
+
results = []
|
153
|
+
# last_pos = ctx.pos
|
154
|
+
loop do
|
155
|
+
results << parser._parse(ctx)
|
156
|
+
# raise ArgumentError, "smth wrong" if last_pos == ctx.pos
|
157
|
+
# last_pos = ctx.pos
|
158
|
+
rescue ParseError
|
159
|
+
break
|
160
|
+
end
|
161
|
+
results
|
162
|
+
end
|
163
|
+
end
|
164
|
+
|
165
|
+
# Returns parser that returns result of the passed `parser` or nil if `parser` fails.
|
166
|
+
# @param [Paco::Parser] parser
|
167
|
+
# @return [Paco::Parser]
|
168
|
+
def optional(parser)
|
169
|
+
alt(parser, succeed(nil))
|
170
|
+
end
|
171
|
+
|
172
|
+
# Helper used for memoization
|
173
|
+
def memoize(&block)
|
174
|
+
key = block.source_location
|
175
|
+
synchronize do
|
176
|
+
@_paco_memoized ||= {}
|
177
|
+
return @_paco_memoized[key] if @_paco_memoized.key?(key)
|
178
|
+
|
179
|
+
@_paco_memoized[key] = block.call
|
180
|
+
end
|
181
|
+
end
|
182
|
+
end
|
183
|
+
end
|
data/lib/paco/context.rb
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
module Paco
|
3
|
+
class Context
|
4
|
+
attr_reader :input, :last_pos, :pos
|
5
|
+
|
6
|
+
def pos=(np)
|
7
|
+
# TODO: is that needed?
|
8
|
+
@last_pos = @pos
|
9
|
+
@pos = np
|
10
|
+
end
|
11
|
+
|
12
|
+
def initialize(input, pos = 0)
|
13
|
+
@input = input
|
14
|
+
@pos = pos
|
15
|
+
end
|
16
|
+
|
17
|
+
def read(n)
|
18
|
+
input[pos, n]
|
19
|
+
end
|
20
|
+
|
21
|
+
def read_all
|
22
|
+
input[pos..-1]
|
23
|
+
end
|
24
|
+
|
25
|
+
def eof?
|
26
|
+
pos >= input.length
|
27
|
+
end
|
28
|
+
|
29
|
+
def index(from = nil)
|
30
|
+
from ||= pos
|
31
|
+
lines = input[0..from].lines
|
32
|
+
|
33
|
+
{
|
34
|
+
line: lines.length,
|
35
|
+
column: lines[-1]&.length || 0,
|
36
|
+
pos: from
|
37
|
+
}
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
module Paco
|
3
|
+
class Error < StandardError; end
|
4
|
+
|
5
|
+
class ParseError < Error
|
6
|
+
# @param [Paco::Context] ctx
|
7
|
+
def initialize(ctx, expected)
|
8
|
+
@ctx = ctx
|
9
|
+
@pos = ctx.pos
|
10
|
+
@expected = expected
|
11
|
+
|
12
|
+
# TODO: make this possible to show every parsing message? or last n?
|
13
|
+
# puts ""
|
14
|
+
# puts "#{ctx.pos}/#{ctx.input.length}: #{ctx.input[ctx.last_pos..ctx.pos]}"
|
15
|
+
# puts "expected: #{expected}"
|
16
|
+
# puts ""
|
17
|
+
end
|
18
|
+
|
19
|
+
def message
|
20
|
+
index = @ctx.index(@pos)
|
21
|
+
<<~MSG
|
22
|
+
Parsing error
|
23
|
+
line #{index[:line]}, column #{index[:column]}:
|
24
|
+
unexpected #{@ctx.input[@pos] || "end of file"}
|
25
|
+
expecting #{@expected}
|
26
|
+
MSG
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
data/lib/paco/parser.rb
ADDED
@@ -0,0 +1,168 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "paco/combinators"
|
4
|
+
|
5
|
+
module Paco
|
6
|
+
class Parser
|
7
|
+
attr_reader :desc
|
8
|
+
|
9
|
+
def initialize(desc = "", &block)
|
10
|
+
@desc = desc
|
11
|
+
@block = block
|
12
|
+
end
|
13
|
+
|
14
|
+
def parse(input)
|
15
|
+
ctx = input.is_a?(Context) ? input : Context.new(input)
|
16
|
+
skip(Paco::Combinators.eof)._parse(ctx)
|
17
|
+
end
|
18
|
+
|
19
|
+
def _parse(ctx)
|
20
|
+
@block.call(ctx, self)
|
21
|
+
# TODO: add ability for debugging
|
22
|
+
# puts ""
|
23
|
+
# puts "#{@block.source_location} succeed."
|
24
|
+
# puts "#{ctx.input.length}/#{ctx.pos}: " + ctx.input[ctx.last_pos..ctx.pos].inspect
|
25
|
+
# puts ""
|
26
|
+
# res
|
27
|
+
end
|
28
|
+
|
29
|
+
# Raises ParseError
|
30
|
+
# @param [Paco::Context] ctx
|
31
|
+
# @raise [Paco::ParseError]
|
32
|
+
def failure(ctx)
|
33
|
+
raise ParseError.new(ctx, desc), "", []
|
34
|
+
end
|
35
|
+
|
36
|
+
# Returns a new parser which tries `parser`, and if it fails uses `other`.
|
37
|
+
def or(other)
|
38
|
+
Parser.new do |ctx|
|
39
|
+
_parse(ctx)
|
40
|
+
rescue ParseError
|
41
|
+
other._parse(ctx)
|
42
|
+
end
|
43
|
+
end
|
44
|
+
alias_method :|, :or
|
45
|
+
|
46
|
+
# Expects `other` parser to follow `parser`, but returns only the value of `parser`.
|
47
|
+
# @param [Poco::Parser] other
|
48
|
+
# @return [Paco::Parser]
|
49
|
+
def skip(other)
|
50
|
+
Paco::Combinators.seq(self, other).fmap { |results| results[0] }
|
51
|
+
end
|
52
|
+
alias_method :<, :skip
|
53
|
+
|
54
|
+
# Expects `other` parser to follow `parser`, but returns only the value of `other` parser.
|
55
|
+
# @param [Poco::Parser] other
|
56
|
+
# @return [Paco::Parser]
|
57
|
+
def next(other)
|
58
|
+
bind { other }
|
59
|
+
end
|
60
|
+
alias_method :>, :next
|
61
|
+
|
62
|
+
# Transforms the output of `parser` with the given block.
|
63
|
+
# @return [Paco::Parser]
|
64
|
+
def fmap(&block)
|
65
|
+
Parser.new do |ctx|
|
66
|
+
block.call(_parse(ctx))
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
# Returns a new parser which tries `parser`, and on success
|
71
|
+
# calls the `block` with the result of the parse, which is expected
|
72
|
+
# to return another parser, which will be tried next. This allows you
|
73
|
+
# to dynamically decide how to continue the parse, which is impossible
|
74
|
+
# with the other Paco::Combinators.
|
75
|
+
# @return [Paco::Parser]
|
76
|
+
def bind(&block)
|
77
|
+
Parser.new do |ctx|
|
78
|
+
block.call(_parse(ctx))._parse(ctx)
|
79
|
+
end
|
80
|
+
end
|
81
|
+
alias_method :chain, :bind
|
82
|
+
|
83
|
+
# Expects `parser` zero or more times, and returns an array of the results.
|
84
|
+
# @return [Paco::Parser]
|
85
|
+
def many
|
86
|
+
Paco::Combinators.many(self)
|
87
|
+
end
|
88
|
+
|
89
|
+
# Returns a new parser with the same behavior, but which returns passed `value`.
|
90
|
+
# @return [Paco::Parser]
|
91
|
+
def result(value)
|
92
|
+
fmap { value }
|
93
|
+
end
|
94
|
+
|
95
|
+
# Returns a new parser which tries `parser` and, if it fails, returns `value` without consuming any input.
|
96
|
+
# @return [Paco::Parser]
|
97
|
+
def fallback(value)
|
98
|
+
self.or(Paco::Combinators.succeed(value))
|
99
|
+
end
|
100
|
+
|
101
|
+
# Expects `other` parser before and after `parser`, and returns the result of the parser.
|
102
|
+
# @param [Paco::Parser] other
|
103
|
+
# @return [Paco::Parser]
|
104
|
+
def trim(other)
|
105
|
+
other.next(self).skip(other)
|
106
|
+
end
|
107
|
+
|
108
|
+
# Expects the parser `before` before `parser` and `after` after `parser. Returns the result of the parser.
|
109
|
+
# @param [Paco::Parser] before
|
110
|
+
# @param [Paco::Parser] after
|
111
|
+
# @return [Paco::Parser]
|
112
|
+
def wrap(before, after)
|
113
|
+
Paco::Combinators.wrap(before, after, self)
|
114
|
+
end
|
115
|
+
|
116
|
+
# Returns a parser that runs passed `other` parser without consuming the input, and
|
117
|
+
# returns result of the `parser` if the passed one _does not match_ the input. Fails otherwise.
|
118
|
+
# @param [Paco::Parser] other
|
119
|
+
# @return [Paco::Parser]
|
120
|
+
def not_followed_by(other)
|
121
|
+
skip(Paco::Combinators.not_followed_by(other))
|
122
|
+
end
|
123
|
+
|
124
|
+
# Returns a parser that runs `parser` and concatenate it results with the `separator`.
|
125
|
+
# @param [String] separator
|
126
|
+
# @return [Paco::Parser]
|
127
|
+
def join(separator = "")
|
128
|
+
fmap { |result| result.join(separator) }
|
129
|
+
end
|
130
|
+
|
131
|
+
# Returns a parser that runs `parser` between `min` and `max` times,
|
132
|
+
# and returns an array of the results. When `max` is not specified, `max` = `min`.
|
133
|
+
# @param [Integer] min
|
134
|
+
# @param [Integer] max
|
135
|
+
# @return [Paco::Parser]
|
136
|
+
def times(min, max = nil)
|
137
|
+
max ||= min
|
138
|
+
if min < 0 || max < min
|
139
|
+
raise ArgumentError, "invalid attributes: min `#{min}`, max `#{max}`"
|
140
|
+
end
|
141
|
+
|
142
|
+
Parser.new do |ctx|
|
143
|
+
results = min.times.map { _parse(ctx) }
|
144
|
+
(max - min).times.each do
|
145
|
+
results << _parse(ctx)
|
146
|
+
rescue ParseError
|
147
|
+
break
|
148
|
+
end
|
149
|
+
|
150
|
+
results
|
151
|
+
end
|
152
|
+
end
|
153
|
+
|
154
|
+
# Returns a parser that runs `parser` at least `num` times,
|
155
|
+
# and returns an array of the results.
|
156
|
+
def at_least(num)
|
157
|
+
Paco::Combinators.seq_map(times(num), many) do |head, rest|
|
158
|
+
head + rest
|
159
|
+
end
|
160
|
+
end
|
161
|
+
|
162
|
+
# Returns a parser that runs `parser` at most `num` times,
|
163
|
+
# and returns an array of the results.
|
164
|
+
def at_most(num)
|
165
|
+
times(0, num)
|
166
|
+
end
|
167
|
+
end
|
168
|
+
end
|
data/lib/paco/version.rb
ADDED
data/lib/paco.rb
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "paco/version"
|
4
|
+
require "paco/parse_error"
|
5
|
+
require "paco/context"
|
6
|
+
require "paco/parser"
|
7
|
+
require "paco/combinators"
|
8
|
+
|
9
|
+
module Paco
|
10
|
+
def self.extended(base)
|
11
|
+
base.extend Combinators
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.included(base)
|
15
|
+
base.include Combinators
|
16
|
+
end
|
17
|
+
end
|
metadata
ADDED
@@ -0,0 +1,60 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: paco
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Svyatoslav Kryukov
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2021-12-12 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Paco is a parser combinator library.
|
14
|
+
email:
|
15
|
+
- s.g.kryukov@yandex.ru
|
16
|
+
executables: []
|
17
|
+
extensions: []
|
18
|
+
extra_rdoc_files: []
|
19
|
+
files:
|
20
|
+
- CHANGELOG.md
|
21
|
+
- LICENSE.txt
|
22
|
+
- README.md
|
23
|
+
- bin/console
|
24
|
+
- bin/setup
|
25
|
+
- lib/paco.rb
|
26
|
+
- lib/paco/combinators.rb
|
27
|
+
- lib/paco/combinators/char.rb
|
28
|
+
- lib/paco/context.rb
|
29
|
+
- lib/paco/parse_error.rb
|
30
|
+
- lib/paco/parser.rb
|
31
|
+
- lib/paco/version.rb
|
32
|
+
homepage: https://github.com/skryukov/paco
|
33
|
+
licenses:
|
34
|
+
- MIT
|
35
|
+
metadata:
|
36
|
+
bug_tracker_uri: https://github.com/skryukov/paco/issues
|
37
|
+
changelog_uri: https://github.com/skryukov/paco/blob/master/CHANGELOG.md
|
38
|
+
documentation_uri: https://github.com/skryukov/paco/blob/master/README.md
|
39
|
+
homepage_uri: https://github.com/skryukov/paco
|
40
|
+
source_code_uri: https://github.com/skryukov/paco
|
41
|
+
post_install_message:
|
42
|
+
rdoc_options: []
|
43
|
+
require_paths:
|
44
|
+
- lib
|
45
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
46
|
+
requirements:
|
47
|
+
- - ">="
|
48
|
+
- !ruby/object:Gem::Version
|
49
|
+
version: 2.6.0
|
50
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
requirements: []
|
56
|
+
rubygems_version: 3.2.15
|
57
|
+
signing_key:
|
58
|
+
specification_version: 4
|
59
|
+
summary: Parser combinator library
|
60
|
+
test_files: []
|