ebnf 2.1.2 → 2.3.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (18) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +3 -2
  3. data/VERSION +1 -1
  4. data/bin/ebnf +5 -6
  5. data/etc/doap.ttl +1 -4
  6. data/etc/ebnf.html +22 -117
  7. data/etc/ebnf.ll1.rb +1 -1
  8. data/etc/ebnf.peg.rb +1 -1
  9. data/lib/ebnf/base.rb +5 -3
  10. data/lib/ebnf/ll1/lexer.rb +4 -28
  11. data/lib/ebnf/native.rb +2 -2
  12. data/lib/ebnf/peg/parser.rb +19 -4
  13. data/lib/ebnf/peg/rule.rb +39 -12
  14. data/lib/ebnf/rule.rb +4 -2
  15. data/lib/ebnf/unescape.rb +62 -0
  16. data/lib/ebnf/writer.rb +39 -17
  17. data/lib/ebnf.rb +1 -0
  18. metadata +46 -17
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: f58817e075b6100c10ce82eb2da850a71aa9ff76c8d1c359d819720c89477564
4
- data.tar.gz: 67fb9fc3ae589ae8ab49fef81a5703958635e7b3f8169ccc8df2d17e57c62074
3
+ metadata.gz: c56b57d125d152b6bfcd4c77b3a2d160ba1e7e11fc538c182085868fe5b2d4a4
4
+ data.tar.gz: c7c3987ce05152cc1efa031f0ecc03f2bc111442fbcbbcb3d2cf82b85f59e4cf
5
5
  SHA512:
6
- metadata.gz: 13874b6745062e294d15176bba4c482ccdc32974a2733429cb1bc23eb87f608ae6e2deeba4e972bdf236629783c3443d7c8461c90e0db4fc6ef6b39d2564582c
7
- data.tar.gz: 172c8fa0efc03357f845cabff8d06fb11260cd271cb5a084350f8f432beef8d560cc285cef6ab87f4526d5331d8c4c433ae2b9536e108d2a4e0a7bd522a3292b
6
+ metadata.gz: 9692cedc65cfde26fd21781f01a3f44c52f69de178893b63ce94b74e9a9ef24218979a9693eec18c02469bf69ea9b15a9b248817958b5c6a6874ec078ac02091
7
+ data.tar.gz: dc8c937d4ba0f70e4b981cd4c91a40b2cd59c6803e1b5409f5bdc8f5dea6acc4af2c176f26e1cde805077c035aa93baf3d8e0b15858238380e2a1c25a6f1c32b
data/README.md CHANGED
@@ -3,8 +3,9 @@
3
3
  [EBNF][] parser and generic parser generator.
4
4
 
5
5
  [![Gem Version](https://badge.fury.io/rb/ebnf.png)](https://badge.fury.io/rb/ebnf)
6
- [![Build Status](https://secure.travis-ci.org/dryruby/ebnf.png?branch=master)](https://travis-ci.org/dryruby/ebnf)
7
- [![Coverage Status](https://coveralls.io/repos/dryruby/ebnf/badge.svg)](https://coveralls.io/r/dryruby/ebnf)
6
+ [![Build Status](https://github.com/dryruby/ebnf/workflows/CI/badge.svg?branch=develop)](https://github.com/dryruby/ebnf/actions?query=workflow%3ACI)
7
+ [![Coverage Status](https://coveralls.io/repos/dryruby/ebnf/badge.svg?branch=develop)](https://coveralls.io/r/dryruby/ebnf?branch=develop)
8
+ [![Gitter chat](https://badges.gitter.im/ruby-rdf/rdf.png)](https://gitter.im/ruby-rdf/rdf)
8
9
 
9
10
  ## Description
10
11
  This is a [Ruby][] implementation of an [EBNF][] and [BNF][] parser and parser generator.
data/VERSION CHANGED
@@ -1 +1 @@
1
- 2.1.2
1
+ 2.3.0
data/bin/ebnf CHANGED
@@ -6,7 +6,6 @@
6
6
  # * And with First/Follow rules
7
7
 
8
8
  $:.unshift(File.expand_path(File.join(File.dirname(__FILE__), "..", 'lib')))
9
- require "bundler/setup"
10
9
  require 'rubygems'
11
10
  require 'getoptlong'
12
11
  require 'ebnf'
@@ -34,7 +33,7 @@ OPT_ARGS = [
34
33
  ["--prefix", "-p", GetoptLong::REQUIRED_ARGUMENT,"Prefix to use when generating Turtle"],
35
34
  ["--progress", "-v", GetoptLong::NO_ARGUMENT, "Detail on execution"],
36
35
  ["--renumber", GetoptLong::NO_ARGUMENT, "Renumber parsed reules"],
37
- ["--validate", GetoptLong::NO_ARGUMENT, "Validate grammar"],
36
+ ["--validate", GetoptLong::NO_ARGUMENT, "Validate grammar and any generated HTML"],
38
37
  ["--help", "-?", GetoptLong::NO_ARGUMENT, "This message"]
39
38
  ]
40
39
  def usage
@@ -67,7 +66,7 @@ opts.each do |opt, arg|
67
66
  end
68
67
  options[:format] = arg.to_sym
69
68
  when '--format'
70
- unless %w(abnf abnfh ebnf html isoebnf isoebnfh rb sxp).include?(arg)
69
+ unless %w(abnf abnfh ebnf html isoebnf isoebnfh rb sxp ttl).include?(arg)
71
70
  STDERR.puts("unrecognized output format #{arg}")
72
71
  usage
73
72
  end
@@ -99,11 +98,11 @@ ebnf.renumber! if options[:renumber]
99
98
 
100
99
  res = case options[:output_format]
101
100
  when :abnf then ebnf.to_s(format: :abnf)
102
- when :abnfh then ebnf.to_html(format: :abnf)
101
+ when :abnfh then ebnf.to_html(format: :abnf, validate: options[:validate])
103
102
  when :ebnf then ebnf.to_s
104
- when :html then ebnf.to_html
103
+ when :html then ebnf.to_html(validate: options[:validate])
105
104
  when :isoebnf then ebnf.to_s(format: :isoebnf)
106
- when :isoebnfh then ebnf.to_html(format: :isoebnf)
105
+ when :isoebnfh then ebnf.to_html(format: :isoebnf, validate: options[:validate])
107
106
  when :sxp then ebnf.to_sxp
108
107
  when :ttl then ebnf.to_ttl(options[:prefix], options[:namespace])
109
108
  when :rb then ebnf.to_ruby(out, grammarFile: ARGV[0], **options)
data/etc/doap.ttl CHANGED
@@ -12,7 +12,7 @@
12
12
  doap:name "ebnf" ;
13
13
  doap:homepage <https://github.com/dryruby/ebnf> ;
14
14
  doap:license <https://unlicense.org/1.0/> ;
15
- doap:shortdesc "EBNF parser and parser generator"@en ;
15
+ doap:shortdesc "EBNF parser and parser generator in Ruby."@en ;
16
16
  doap:description "EBNF is a Ruby parser for W3C EBNF and a parser generator for PEG and LL(1). Also includes parsing modes for ISO EBNF and ABNF."@en ;
17
17
  doap:created "2011-08-29"^^xsd:date ;
18
18
  doap:programming-language "Ruby" ;
@@ -34,7 +34,4 @@
34
34
  doap:maintainer <https://greggkellogg.net/foaf#me> ;
35
35
  doap:documenter <https://greggkellogg.net/foaf#me> ;
36
36
  foaf:maker <https://greggkellogg.net/foaf#me> ;
37
- dc:title "ebnf" ;
38
- dc:description "EBNF is a Ruby parser for W3C EBNF and a parser generator for PEG and LL(1). Also includes parsing modes for ISO EBNF and ABNF."@en ;
39
- dc:date "2011-08-29"^^xsd:date ;
40
37
  dc:creator <https://greggkellogg.net/foaf#me> .
data/etc/ebnf.html CHANGED
@@ -11,7 +11,7 @@
11
11
  <td>[2]</td>
12
12
  <td><code>declaration</code></td>
13
13
  <td>::=</td>
14
- <td>"@terminals" <code>|</code> <a href="#grammar-production-pass">pass</a></td>
14
+ <td>&quot;@terminals&quot; <code>|</code> <a href="#grammar-production-pass">pass</a></td>
15
15
  </tr>
16
16
  <tr id="grammar-production-rule">
17
17
  <td>[3]</td>
@@ -53,61 +53,24 @@
53
53
  <td>[9]</td>
54
54
  <td><code>primary</code></td>
55
55
  <td>::=</td>
56
- <td><a href="#grammar-production-HEX">HEX</a></td>
57
- </tr>
58
- <tr>
59
- <td>[9]</td>
60
- <td><code></code></td>
61
- <td>|</td>
62
- <td><a href="#grammar-production-SYMBOL">SYMBOL</a></td>
63
- </tr>
64
- <tr>
65
- <td>[9]</td>
66
- <td><code></code></td>
67
- <td>|</td>
68
- <td><a href="#grammar-production-O_RANGE">O_RANGE</a></td>
69
- </tr>
70
- <tr>
71
- <td>[9]</td>
72
- <td><code></code></td>
73
- <td>|</td>
74
- <td><a href="#grammar-production-RANGE">RANGE</a></td>
75
- </tr>
76
- <tr>
77
- <td>[9]</td>
78
- <td><code></code></td>
79
- <td>|</td>
80
- <td><a href="#grammar-production-STRING1">STRING1</a></td>
81
- </tr>
82
- <tr>
83
- <td>[9]</td>
84
- <td><code></code></td>
85
- <td>|</td>
86
- <td><a href="#grammar-production-STRING2">STRING2</a></td>
87
- </tr>
88
- <tr>
89
- <td>[9]</td>
90
- <td><code></code></td>
91
- <td>|</td>
92
- <td><code>(</code> "<code class="grammar-literal">(</code>" <a href="#grammar-production-expression">expression</a> "<code class="grammar-literal">)</code>"<code>)</code> </td>
56
+ <td><a href="#grammar-production-HEX">HEX</a> <code>|</code> <a href="#grammar-production-SYMBOL">SYMBOL</a> <code>|</code> <a href="#grammar-production-O_RANGE">O_RANGE</a> <code>|</code> <a href="#grammar-production-RANGE">RANGE</a> <code>|</code> <a href="#grammar-production-STRING1">STRING1</a> <code>|</code> <a href="#grammar-production-STRING2">STRING2</a> <code>|</code> <code>(</code> "<code class="grammar-literal">(</code>" <a href="#grammar-production-expression">expression</a> "<code class="grammar-literal">)</code>"<code>)</code> </td>
93
57
  </tr>
94
58
  <tr id="grammar-production-pass">
95
59
  <td>[10]</td>
96
60
  <td><code>pass</code></td>
97
61
  <td>::=</td>
98
- <td>"@pass" <a href="#grammar-production-expression">expression</a></td>
62
+ <td>&quot;@pass&quot; <a href="#grammar-production-expression">expression</a></td>
99
63
  </tr>
100
- <tr id="grammar-production-">
101
- <td>@terminals</td>
102
- <td><code></code></td>
64
+ <tr>
65
+ <td colspan=2>@terminals</td>
103
66
  <td></td>
104
- <td><strong>Productions for terminals</strong></td>
67
+ <td><strong># Productions for terminals</strong></td>
105
68
  </tr>
106
69
  <tr id="grammar-production-LHS">
107
70
  <td>[11]</td>
108
71
  <td><code>LHS</code></td>
109
72
  <td>::=</td>
110
- <td><code>(</code> "<code class="grammar-literal">[</code>" <a href="#grammar-production-SYMBOL">SYMBOL</a> "<code class="grammar-literal">]</code>" <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code>+</code> <code>)</code> <code>?</code> <a href="#grammar-production-SYMBOL">SYMBOL</a> <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code>*</code> "::="</td>
73
+ <td><code>(</code> "<code class="grammar-literal">[</code>" <a href="#grammar-production-SYMBOL">SYMBOL</a> "<code class="grammar-literal">]</code>" <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code>+</code> <code>)</code> <code>?</code> <a href="#grammar-production-SYMBOL">SYMBOL</a> <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code>*</code> &quot;::=&quot;</td>
111
74
  </tr>
112
75
  <tr id="grammar-production-SYMBOL">
113
76
  <td>[12]</td>
@@ -119,91 +82,37 @@
119
82
  <td>[13]</td>
120
83
  <td><code>HEX</code></td>
121
84
  <td>::=</td>
122
- <td>"#x" <code>(</code> <code>[</code> <code class="grammar-literal">a-f</code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-literal">A-F</code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-literal">0-9</code><code>]</code> <code>)</code> <code>+</code> </td>
85
+ <td>&quot;#x&quot; <code>(</code> <code>[</code> <code class="grammar-literal">a-f</code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-literal">A-F</code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-literal">0-9</code><code>]</code> <code>)</code> <code>+</code> </td>
123
86
  </tr>
124
87
  <tr id="grammar-production-RANGE">
125
88
  <td>[14]</td>
126
89
  <td><code>RANGE</code></td>
127
90
  <td>::=</td>
128
- <td>"<code class="grammar-literal">[</code>"</td>
129
- </tr>
130
- <tr id="grammar-production-">
131
- <td>[14]</td>
132
- <td><code></code></td>
133
- <td></td>
134
- <td><code>(</code> <code>(</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-R_CHAR">R_CHAR</a><code>)</code><code>(</code> <a href="#grammar-production-HEX">HEX</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>|</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> <code>|</code> <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>+</code></td>
135
- </tr>
136
- <tr id="grammar-production-">
137
- <td>[14]</td>
138
- <td><code></code></td>
139
- <td></td>
140
- <td>"<code class="grammar-literal">-</code>"<code>?</code></td>
141
- </tr>
142
- <tr id="grammar-production-">
143
- <td>[14]</td>
144
- <td><code></code></td>
145
- <td></td>
146
- <td><code>(</code> "<code class="grammar-literal">]</code>" <code>-</code> <a href="#grammar-production-LHS">LHS</a><code>)</code> </td>
91
+ <td>"<code class="grammar-literal">[</code>" <code>(</code> <code>(</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-R_CHAR">R_CHAR</a><code>)</code> <code>|</code> <code>(</code> <a href="#grammar-production-HEX">HEX</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>|</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> <code>|</code> <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>+</code> "<code class="grammar-literal">-</code>"<code>?</code> <code>(</code> "<code class="grammar-literal">]</code>" <code>-</code> <a href="#grammar-production-LHS">LHS</a><code>)</code> </td>
147
92
  </tr>
148
93
  <tr id="grammar-production-O_RANGE">
149
94
  <td>[15]</td>
150
95
  <td><code>O_RANGE</code></td>
151
96
  <td>::=</td>
152
- <td>"[^"</td>
153
- </tr>
154
- <tr id="grammar-production-">
155
- <td>[15]</td>
156
- <td><code></code></td>
157
- <td></td>
158
- <td><code>(</code> <code>(</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-R_CHAR">R_CHAR</a><code>)</code><code>(</code> <a href="#grammar-production-HEX">HEX</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>|</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> <code>|</code> <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>+</code></td>
159
- </tr>
160
- <tr id="grammar-production-">
161
- <td>[15]</td>
162
- <td><code></code></td>
163
- <td></td>
164
- <td>"<code class="grammar-literal">-</code>"<code>?</code></td>
165
- </tr>
166
- <tr id="grammar-production-">
167
- <td>[15]</td>
168
- <td><code></code></td>
169
- <td></td>
170
- <td>"<code class="grammar-literal">]</code>"</td>
97
+ <td>&quot;[^&quot; <code>(</code> <code>(</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-R_CHAR">R_CHAR</a><code>)</code> <code>|</code> <code>(</code> <a href="#grammar-production-HEX">HEX</a> "<code class="grammar-literal">-</code>" <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>|</code> <a href="#grammar-production-R_CHAR">R_CHAR</a> <code>|</code> <a href="#grammar-production-HEX">HEX</a><code>)</code> <code>+</code> "<code class="grammar-literal">-</code>"<code>?</code> "<code class="grammar-literal">]</code>"</td>
171
98
  </tr>
172
99
  <tr id="grammar-production-STRING1">
173
100
  <td>[16]</td>
174
101
  <td><code>STRING1</code></td>
175
102
  <td>::=</td>
176
- <td>'<code class="grammar-literal">"</code>' <code>(</code> <a href="#grammar-production-CHAR">CHAR</a> <code>-</code> '<code class="grammar-literal">"</code>'<code>)</code> <code>*</code> '<code class="grammar-literal">"</code>'</td>
103
+ <td>'<code class="grammar-literal">&quot;</code>' <code>(</code> <a href="#grammar-production-CHAR">CHAR</a> <code>-</code> '<code class="grammar-literal">&quot;</code>'<code>)</code> <code>*</code> '<code class="grammar-literal">&quot;</code>'</td>
177
104
  </tr>
178
105
  <tr id="grammar-production-STRING2">
179
106
  <td>[17]</td>
180
107
  <td><code>STRING2</code></td>
181
108
  <td>::=</td>
182
- <td>"<code class="grammar-literal">'</code>" <code>(</code> <a href="#grammar-production-CHAR">CHAR</a> <code>-</code> "<code class="grammar-literal">'</code>"<code>)</code> <code>*</code> "<code class="grammar-literal">'</code>"</td>
109
+ <td>"<code class="grammar-literal">&apos;</code>" <code>(</code> <a href="#grammar-production-CHAR">CHAR</a> <code>-</code> "<code class="grammar-literal">&apos;</code>"<code>)</code> <code>*</code> "<code class="grammar-literal">&apos;</code>"</td>
183
110
  </tr>
184
111
  <tr id="grammar-production-CHAR">
185
112
  <td>[18]</td>
186
113
  <td><code>CHAR</code></td>
187
114
  <td>::=</td>
188
- <td><code>[</code> <code class="grammar-char-escape"><abbr title="horizontal tab">#x09</abbr></code><code class="grammar-char-escape"><abbr title="new line">#x0A</abbr></code><code class="grammar-char-escape"><abbr title="carriage return">#x0D</abbr></code><code>]</code></td>
189
- </tr>
190
- <tr>
191
- <td>[18]</td>
192
- <td><code></code></td>
193
- <td>|</td>
194
- <td><code>[</code> <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode '퟿'">#xD7FF</abbr></code><code>]</code></td>
195
- </tr>
196
- <tr>
197
- <td>[18]</td>
198
- <td><code></code></td>
199
- <td>|</td>
200
- <td><code>[</code> <code class="grammar-char-escape"><abbr title="unicode ''">#xE000</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode '�'">#xFFFD</abbr></code><code>]</code></td>
201
- </tr>
202
- <tr>
203
- <td>[18]</td>
204
- <td><code></code></td>
205
- <td>|</td>
206
- <td><code>[</code> <code class="grammar-char-escape"><abbr title="unicode '𐀀'">#x00010000</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode '􏿿'">#x0010FFFF</abbr></code><code>]</code> </td>
115
+ <td><code>[</code> <code class="grammar-char-escape"><abbr title="horizontal tab">#x09</abbr></code><code class="grammar-char-escape"><abbr title="new line">#x0A</abbr></code><code class="grammar-char-escape"><abbr title="carriage return">#x0D</abbr></code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode 'Reserved'">#xD7FF</abbr></code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-char-escape"><abbr title="unicode 'Private-use'">#xE000</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode 'Graphic'">#xFFFD</abbr></code><code>]</code> <code>|</code> <code>[</code> <code class="grammar-char-escape"><abbr title="unicode 'Graphic'">#x00010000</abbr></code><code class="grammar-literal">-</code><code class="grammar-char-escape"><abbr title="unicode 'Noncharacter'">#x0010FFFF</abbr></code><code>]</code> </td>
207
116
  </tr>
208
117
  <tr id="grammar-production-R_CHAR">
209
118
  <td>[19]</td>
@@ -224,28 +133,24 @@
224
133
  <td><code>[</code> <code class="grammar-char-escape"><abbr title="horizontal tab">#x09</abbr></code><code class="grammar-char-escape"><abbr title="new line">#x0A</abbr></code><code class="grammar-char-escape"><abbr title="carriage return">#x0D</abbr></code><code class="grammar-char-escape"><abbr title="space">#x20</abbr></code><code>]</code></td>
225
134
  </tr>
226
135
  <tr>
227
- <td>[21]</td>
228
- <td><code></code></td>
136
+ <td colspan=2></td>
229
137
  <td>|</td>
230
- <td><code>(</code> <code>(</code> <code>(</code> "<code class="grammar-literal">#</code>" <code>-</code> "#x"<code>)</code> <code>|</code> "//"<code>)</code> <code>[</code> <code class="grammar-literal">^</code><code class="grammar-char-escape"><abbr title="new line">#x0A</abbr></code><code class="grammar-char-escape"><abbr title="carriage return">#x0D</abbr></code><code>]</code> <code>*</code> <code>)</code></td>
138
+ <td><code>(</code> <code>(</code> <code>(</code> "<code class="grammar-literal">#</code>" <code>-</code> &quot;#x&quot;<code>)</code> <code>|</code> &quot;//&quot;<code>)</code> <code>[</code> <code class="grammar-literal">^</code><code class="grammar-char-escape"><abbr title="new line">#x0A</abbr></code><code class="grammar-char-escape"><abbr title="carriage return">#x0D</abbr></code><code>]</code> <code>*</code> <code>)</code></td>
231
139
  </tr>
232
140
  <tr>
233
- <td>[21]</td>
234
- <td><code></code></td>
141
+ <td colspan=2></td>
235
142
  <td>|</td>
236
- <td><code>(</code> "/*" <code>(</code> <code>(</code> "<code class="grammar-literal">*</code>" <code>[</code> <code class="grammar-literal">^/</code><code>]</code> <code>)</code> <code>?</code> <code>|</code> <code>[</code> <code class="grammar-literal">^*</code><code>]</code> <code>)</code> <code>*</code> "*/"<code>)</code></td>
143
+ <td><code>(</code> &quot;/*&quot; <code>(</code> <code>(</code> "<code class="grammar-literal">*</code>" <code>[</code> <code class="grammar-literal">^/</code><code>]</code> <code>)</code> <code>?</code> <code>|</code> <code>[</code> <code class="grammar-literal">^*</code><code>]</code> <code>)</code> <code>*</code> &quot;*/&quot;<code>)</code></td>
237
144
  </tr>
238
145
  <tr>
239
- <td>[21]</td>
240
- <td><code></code></td>
146
+ <td colspan=2></td>
241
147
  <td>|</td>
242
- <td><code>(</code> "(*" <code>(</code> <code>(</code> "<code class="grammar-literal">*</code>" <code>[</code> <code class="grammar-literal">^)</code><code>]</code> <code>)</code> <code>?</code> <code>|</code> <code>[</code> <code class="grammar-literal">^*</code><code>]</code> <code>)</code> <code>*</code> "*)"<code>)</code> </td>
148
+ <td><code>(</code> &quot;(*&quot; <code>(</code> <code>(</code> "<code class="grammar-literal">*</code>" <code>[</code> <code class="grammar-literal">^)</code><code>]</code> <code>)</code> <code>?</code> <code>|</code> <code>[</code> <code class="grammar-literal">^*</code><code>]</code> <code>)</code> <code>*</code> &quot;*)&quot;<code>)</code> </td>
243
149
  </tr>
244
- <tr id="grammar-production-">
245
- <td>@pass</td>
246
- <td><code></code></td>
247
- <td></td>
150
+ <tr>
151
+ <td colspan=2>@pass</td>
248
152
  <td></td>
153
+ <td><a href="#grammar-production-PASS">PASS</a></td>
249
154
  </tr>
250
155
  </tbody>
251
156
  </table>
data/etc/ebnf.ll1.rb CHANGED
@@ -1,4 +1,4 @@
1
- # This file is automatically generated by ebnf version 2.0.0
1
+ # This file is automatically generated by ebnf version 2.1.2
2
2
  # Derived from etc/ebnf.ebnf
3
3
  module Meta
4
4
  START = :ebnf
data/etc/ebnf.peg.rb CHANGED
@@ -1,4 +1,4 @@
1
- # This file is automatically generated by ebnf version 2.0.0
1
+ # This file is automatically generated by ebnf version 2.1.2
2
2
  # Derived from etc/ebnf.ebnf
3
3
  module EBNFMeta
4
4
  RULES = [
data/lib/ebnf/base.rb CHANGED
@@ -201,8 +201,9 @@ module EBNF
201
201
 
202
202
  ##
203
203
  # Write out parsed syntax string as an S-Expression
204
+ #
204
205
  # @return [String]
205
- def to_sxp
206
+ def to_sxp(**options)
206
207
  require 'sxp' unless defined?(SXP)
207
208
  SXP::Generator.string(ast.map(&:for_sxp))
208
209
  end
@@ -220,9 +221,10 @@ module EBNF
220
221
  # Output formatted EBNF as HTML
221
222
  #
222
223
  # @param [:abnf, :ebnf, :isoebnf] format (:ebnf)
224
+ # @param [Boolean] validate (false) validate generated HTML.
223
225
  # @return [String]
224
- def to_html(format: :ebnf)
225
- Writer.html(*ast, format: format)
226
+ def to_html(format: :ebnf, validate: false)
227
+ Writer.html(*ast, format: format, validate: validate)
226
228
  end
227
229
 
228
230
  ##
data/lib/ebnf/ll1/lexer.rb CHANGED
@@ -32,21 +32,7 @@ module EBNF::LL1
32
32
  # @see https://en.wikipedia.org/wiki/Lexical_analysis
33
33
  class Lexer
34
34
  include Enumerable
35
-
36
- ESCAPE_CHARS = {
37
- '\\t' => "\t", # \u0009 (tab)
38
- '\\n' => "\n", # \u000A (line feed)
39
- '\\r' => "\r", # \u000D (carriage return)
40
- '\\b' => "\b", # \u0008 (backspace)
41
- '\\f' => "\f", # \u000C (form feed)
42
- '\\"' => '"', # \u0022 (quotation mark, double quote mark)
43
- "\\'" => '\'', # \u0027 (apostrophe-quote, single quote mark)
44
- '\\\\' => '\\' # \u005C (backslash)
45
- }.freeze
46
- ESCAPE_CHAR4 = /\\u(?:[0-9A-Fa-f]{4,4})/u.freeze # \uXXXX
47
- ESCAPE_CHAR8 = /\\U(?:[0-9A-Fa-f]{8,8})/u.freeze # \UXXXXXXXX
48
- ECHAR = /\\./u.freeze # More liberal unescaping
49
- UCHAR = /#{ESCAPE_CHAR4}|#{ESCAPE_CHAR8}/n.freeze
35
+ include ::EBNF::Unescape
50
36
 
51
37
  ##
52
38
  # @return [Regexp] defines whitespace, including comments, otherwise whitespace must be explicit in terminals
@@ -61,17 +47,7 @@ module EBNF::LL1
61
47
  # @return [String]
62
48
  # @see https://www.w3.org/TR/rdf-sparql-query/#codepointEscape
63
49
  def self.unescape_codepoints(string)
64
- string = string.dup
65
- string.force_encoding(Encoding::ASCII_8BIT) if string.respond_to?(:force_encoding)
66
-
67
- # Decode \uXXXX and \UXXXXXXXX code points:
68
- string = string.gsub(UCHAR) do |c|
69
- s = [(c[2..-1]).hex].pack('U*')
70
- s.respond_to?(:force_encoding) ? s.force_encoding(Encoding::ASCII_8BIT) : s
71
- end
72
-
73
- string.force_encoding(Encoding::UTF_8) if string.respond_to?(:force_encoding)
74
- string
50
+ ::EBNF::Unescape.unescape_codepoints(string)
75
51
  end
76
52
 
77
53
  ##
@@ -83,7 +59,7 @@ module EBNF::LL1
83
59
  # @return [String]
84
60
  # @see https://www.w3.org/TR/rdf-sparql-query/#grammarEscapes
85
61
  def self.unescape_string(input)
86
- input.gsub(ECHAR) { |escaped| ESCAPE_CHARS[escaped] || escaped[1..-1]}
62
+ ::EBNF::Unescape.unescape_string(input)
87
63
  end
88
64
 
89
65
  ##
@@ -338,7 +314,7 @@ module EBNF::LL1
338
314
  # @return [String]
339
315
  def unescape(string)
340
316
  if @options[:unescape]
341
- Lexer.unescape_string(Lexer.unescape_codepoints(string))
317
+ EBNF::Unescape.unescape(string)
342
318
  else
343
319
  string
344
320
  end
data/lib/ebnf/native.rb CHANGED
@@ -287,10 +287,10 @@ module EBNF
287
287
  case m = s[0,1]
288
288
  when '"', "'" # STRING1 or STRING2
289
289
  l, s = s[1..-1].split(m.rstrip, 2)
290
- [LL1::Lexer.unescape_string(l), s]
290
+ [Unescape.unescape_string(l), s]
291
291
  when '[' # RANGE, O_RANGE
292
292
  l, s = s[1..-1].split(/(?<=[^\\])\]/, 2)
293
- [[:range, LL1::Lexer.unescape_string(l)], s]
293
+ [[:range, Unescape.unescape_string(l)], s]
294
294
  when '#' # HEX
295
295
  s.match(/(#x\h+)(.*)$/)
296
296
  l, s = $1, $2
data/lib/ebnf/peg/parser.rb CHANGED
@@ -55,6 +55,7 @@ module EBNF::PEG
55
55
  def production_handlers; (@production_handlers ||= {}); end
56
56
  def terminal_handlers; (@terminal_handlers ||= {}); end
57
57
  def terminal_regexps; (@terminal_regexps ||= {}); end
58
+ def terminal_options; (@terminal_options ||= {}); end
58
59
 
59
60
  ##
60
61
  # Defines the pattern for a terminal node and a block to be invoked
@@ -72,9 +73,8 @@ module EBNF::PEG
72
73
  # defaults to the expression defined in the associated rule.
73
74
  # If unset, the terminal rule is used for matching.
74
75
  # @param [Hash] options
75
- # @option options [Hash{String => String}] :map ({})
76
- # A mapping from terminals, in lower-case form, to
77
- # their canonical value
76
+ # @option options [Boolean] :unescape
77
+ # Cause strings and codepoints to be unescaped.
78
78
  # @yield [value, prod]
79
79
  # @yieldparam [String] value
80
80
  # The scanned terminal value.
@@ -86,6 +86,7 @@ module EBNF::PEG
86
86
  def terminal(term, regexp = nil, **options, &block)
87
87
  terminal_regexps[term] = regexp if regexp
88
88
  terminal_handlers[term] = block if block_given?
89
+ terminal_options[term] = options.freeze
89
90
  end
90
91
 
91
92
  ##
@@ -100,6 +101,8 @@ module EBNF::PEG
100
101
  # Options which are returned from {Parser#onStart}.
101
102
  # @option options [Boolean] :as_hash (false)
102
103
  # If the production is a `seq`, causes the value to be represented as a single hash, rather than an array of individual hashes for each sub-production. Note that this is not always advisable due to the possibility of repeated productions within the sequence.
104
+ # @option options[:upper, :lower] :insensitive_strings
105
+ # Perform case-insensitive match of strings not defined as terminals, and map to either upper or lower case.
103
106
  # @yield [data, block]
104
107
  # @yieldparam [Hash] data
105
108
  # A Hash defined for the current production, during :start
@@ -182,6 +185,8 @@ module EBNF::PEG
182
185
  # @option options[Integer] :high_water passed to lexer
183
186
  # @option options [Logger] :logger for errors/progress/debug.
184
187
  # @option options[Integer] :low_water passed to lexer
188
+ # @option options[Boolean] :seq_hash (false)
189
+ # If `true`, sets the default for the value sent to a production handler that is for a `seq` to a hash composed of the flattened consitutent hashes that are otherwise provided.
185
190
  # @option options [Symbol, Regexp] :whitespace
186
191
  # Symbol of whitespace rule (defaults to `@pass`), or a regular expression
187
192
  # for eating whitespace between non-terminal rules (strongly encouraged).
@@ -195,6 +200,7 @@ module EBNF::PEG
195
200
  # @raise [Exception] Raises exceptions for parsing errors
196
201
  # or errors raised during processing callbacks. Internal
197
202
  # errors are raised using {Error}.
203
+ # @todo FIXME implement seq_hash
198
204
  def parse(input = nil, start = nil, rules = nil, **options, &block)
199
205
  start ||= options[:start]
200
206
  rules ||= options[:rules] || []
@@ -467,10 +473,19 @@ module EBNF::PEG
467
473
  #
468
474
  # @param [Symbol] sym
469
475
  # @return [Regexp]
470
- def find_terminal_regexp(sym)
476
+ def terminal_regexp(sym)
471
477
  self.class.terminal_regexps[sym]
472
478
  end
473
479
 
480
+ ##
481
+ # Find a regular expression defined for a terminal
482
+ #
483
+ # @param [Symbol] sym
484
+ # @return [Regexp]
485
+ def terminal_options(sym)
486
+ self.class.terminal_options[sym]
487
+ end
488
+
474
489
  ##
475
490
  # Record furthest failure.
476
491
  #
data/lib/ebnf/peg/rule.rb CHANGED
@@ -1,6 +1,8 @@
1
1
  module EBNF::PEG
2
2
  # Behaviior for parsing a PEG rule
3
3
  module Rule
4
+ include ::EBNF::Unescape
5
+
4
6
  ##
5
7
  # Initialized by parser when loading rules.
6
8
  # Used for finding rules and invoking elements of the parse process.
@@ -45,9 +47,18 @@ module EBNF::PEG
45
47
  # If the terminal is defined with a regular expression,
46
48
  # use that to match the input,
47
49
  # otherwise,
48
- if regexp = parser.find_terminal_regexp(sym)
49
- matched = input.scan(regexp)
50
+ if regexp = parser.terminal_regexp(sym)
51
+ term_opts = parser.terminal_options(sym)
52
+ if matched = input.scan(regexp)
53
+ # Optionally map matched
54
+ matched = term_opts.fetch(:map, {}).fetch(matched.downcase, matched)
55
+
56
+ # Optionally unescape matched
57
+ matched = unescape(matched) if term_opts[:unescape]
58
+ end
59
+
50
60
  result = parser.onTerminal(sym, (matched ? matched : :unmatched))
61
+
51
62
  # Update furthest failure for strings and terminals
52
63
  parser.update_furthest_failure(input.pos, input.lineno, sym) if result == :unmatched
53
64
  parser.packrat[sym][pos] = {
@@ -61,6 +72,7 @@ module EBNF::PEG
61
72
  eat_whitespace(input)
62
73
  end
63
74
  start_options = parser.onStart(sym)
75
+ string_regexp_opts = start_options[:insensitive_strings] ? Regexp::IGNORECASE : 0
64
76
 
65
77
  result = case expr.first
66
78
  when :alt
@@ -74,7 +86,12 @@ module EBNF::PEG
74
86
  raise "No rule found for #{prod}" unless rule
75
87
  rule.parse(input)
76
88
  when String
77
- input.scan(Regexp.new(Regexp.quote(prod))) || :unmatched
89
+ s = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))
90
+ case start_options[:insensitive_strings]
91
+ when :lower then s && s.downcase
92
+ when :upper then s && s.upcase
93
+ else s
94
+ end || :unmatched
78
95
  end
79
96
  if alt == :unmatched
80
97
  # Update furthest failure for strings and terminals
@@ -112,7 +129,7 @@ module EBNF::PEG
112
129
  raise "No rule found for #{prod}" unless rule
113
130
  rule.parse(input)
114
131
  when String
115
- input.scan(Regexp.new(Regexp.quote(prod))) || :unmatched
132
+ input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts)) || :unmatched
116
133
  end
117
134
  if res != :unmatched
118
135
  # Update furthest failure for terminals
@@ -123,7 +140,7 @@ module EBNF::PEG
123
140
  end
124
141
  when :opt
125
142
  # Result is the matched value or nil
126
- opt = rept(input, 0, 1, expr[1])
143
+ opt = rept(input, 0, 1, expr[1], string_regexp_opts, **start_options)
127
144
 
128
145
  # Update furthest failure for strings and terminals
129
146
  parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
@@ -131,7 +148,7 @@ module EBNF::PEG
131
148
  when :plus
132
149
  # Result is an array of all expressions while they match,
133
150
  # at least one must match
134
- plus = rept(input, 1, '*', expr[1])
151
+ plus = rept(input, 1, '*', expr[1], string_regexp_opts)
135
152
 
136
153
  # Update furthest failure for strings and terminals
137
154
  parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
@@ -146,7 +163,7 @@ module EBNF::PEG
146
163
  when :rept
147
164
  # Result is an array of all expressions while they match,
148
165
  # an empty array of none match
149
- rept = rept(input, expr[1], expr[2], expr[3])
166
+ rept = rept(input, expr[1], expr[2], expr[3], string_regexp_opts)
150
167
 
151
168
  # # Update furthest failure for strings and terminals
152
169
  parser.update_furthest_failure(input.pos, input.lineno, expr[3]) if terminal?
@@ -161,7 +178,12 @@ module EBNF::PEG
161
178
  raise "No rule found for #{prod}" unless rule
162
179
  rule.parse(input)
163
180
  when String
164
- input.scan(Regexp.new(Regexp.quote(prod))) || :unmatched
181
+ s = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))
182
+ case start_options[:insensitive_strings]
183
+ when :lower then s && s.downcase
184
+ when :upper then s && s.upcase
185
+ else s
186
+ end || :unmatched
165
187
  end
166
188
  if res == :unmatched
167
189
  # Update furthest failure for strings and terminals
@@ -182,7 +204,7 @@ module EBNF::PEG
182
204
  when :star
183
205
  # Result is an array of all expressions while they match,
184
206
  # an empty array of none match
185
- star = rept(input, 0, '*', expr[1])
207
+ star = rept(input, 0, '*', expr[1], string_regexp_opts)
186
208
 
187
209
  # Update furthest failure for strings and terminals
188
210
  parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
@@ -214,8 +236,9 @@ module EBNF::PEG
214
236
  # @param [Integer] max
215
237
  # If it is an integer, it stops matching after max entries.
216
238
  # @param [Symbol, String] prod
239
+ # @param [Integer] string_regexp_opts
217
240
  # @return [:unmatched, Array]
218
- def rept(input, min, max, prod)
241
+ def rept(input, min, max, prod, string_regexp_opts, **options)
219
242
  result = []
220
243
 
221
244
  case prod
@@ -227,9 +250,13 @@ module EBNF::PEG
227
250
  result << res
228
251
  end
229
252
  when String
230
- while (res = input.scan(Regexp.new(Regexp.quote(prod)))) && (max == '*' || result.length < max)
253
+ while (res = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))) && (max == '*' || result.length < max)
231
254
  eat_whitespace(input) unless terminal?
232
- result << res
255
+ result << case options[:insensitive_strings]
256
+ when :lower then res.downcase
257
+ when :upper then res.upcase
258
+ else res
259
+ end
233
260
  end
234
261
  end
235
262
 
data/lib/ebnf/rule.rb CHANGED
@@ -206,10 +206,11 @@ module EBNF
206
206
  end
207
207
 
208
208
  # Return SXP representation of this rule
209
+ #
209
210
  # @return [String]
210
- def to_sxp
211
+ def to_sxp(**options)
211
212
  require 'sxp' unless defined?(SXP)
212
- for_sxp.to_sxp
213
+ for_sxp.to_sxp(**options)
213
214
  end
214
215
 
215
216
  alias_method :to_s, :to_sxp
@@ -416,6 +417,7 @@ module EBNF
416
417
  # @param [Rule] other
417
418
  # @return [Boolean]
418
419
  def ==(other)
420
+ other.is_a?(Rule) &&
419
421
  sym == other.sym &&
420
422
  kind == other.kind &&
421
423
  expr == other.expr
data/lib/ebnf/unescape.rb ADDED
@@ -0,0 +1,62 @@
1
+ # encoding: utf-8
2
+ # Unsecape strings
3
+ module EBNF::Unescape
4
+ ESCAPE_CHARS = {
5
+ '\\t' => "\t", # \u0009 (tab)
6
+ '\\n' => "\n", # \u000A (line feed)
7
+ '\\r' => "\r", # \u000D (carriage return)
8
+ '\\b' => "\b", # \u0008 (backspace)
9
+ '\\f' => "\f", # \u000C (form feed)
10
+ '\\"' => '"', # \u0022 (quotation mark, double quote mark)
11
+ "\\'" => '\'', # \u0027 (apostrophe-quote, single quote mark)
12
+ '\\\\' => '\\' # \u005C (backslash)
13
+ }.freeze
14
+ ESCAPE_CHAR4 = /\\u(?:[0-9A-Fa-f]{4,4})/u.freeze # \uXXXX
15
+ ESCAPE_CHAR8 = /\\U(?:[0-9A-Fa-f]{8,8})/u.freeze # \UXXXXXXXX
16
+ ECHAR = /\\./u.freeze # More liberal unescaping
17
+ UCHAR = /#{ESCAPE_CHAR4}|#{ESCAPE_CHAR8}/n.freeze
18
+
19
+ ##
20
+ # Returns a copy of the given `input` string with all `\uXXXX` and
21
+ # `\UXXXXXXXX` Unicode codepoint escape sequences replaced with their
22
+ # unescaped UTF-8 character counterparts.
23
+ #
24
+ # @param [String] string
25
+ # @return [String]
26
+ # @see https://www.w3.org/TR/rdf-sparql-query/#codepointEscape
27
+ def unescape_codepoints(string)
28
+ string = string.dup
29
+ string.force_encoding(Encoding::ASCII_8BIT) if string.respond_to?(:force_encoding)
30
+
31
+ # Decode \uXXXX and \UXXXXXXXX code points:
32
+ string = string.gsub(UCHAR) do |c|
33
+ s = [(c[2..-1]).hex].pack('U*')
34
+ s.respond_to?(:force_encoding) ? s.force_encoding(Encoding::ASCII_8BIT) : s
35
+ end
36
+
37
+ string.force_encoding(Encoding::UTF_8) if string.respond_to?(:force_encoding)
38
+ string
39
+ end
40
+ module_function :unescape_codepoints
41
+
42
+ ##
43
+ # Returns a copy of the given `input` string with all string escape
44
+ # sequences (e.g. `\n` and `\t`) replaced with their unescaped UTF-8
45
+ # character counterparts.
46
+ #
47
+ # @param [String] input
48
+ # @return [String]
49
+ # @see https://www.w3.org/TR/rdf-sparql-query/#grammarEscapes
50
+ def unescape_string(input)
51
+ input.gsub(ECHAR) { |escaped| ESCAPE_CHARS[escaped] || escaped[1..-1]}
52
+ end
53
+ module_function :unescape_string
54
+
55
+ # Perform string and codepoint unescaping if defined for this terminal
56
+ # @param [String] string
57
+ # @return [String]
58
+ def unescape(string)
59
+ unescape_string(unescape_codepoints(string))
60
+ end
61
+ module_function :unescape
62
+ end
data/lib/ebnf/writer.rb CHANGED
@@ -2,6 +2,7 @@
2
2
  require 'rdf'
3
3
  require 'strscan' unless defined?(StringScanner)
4
4
  require "ostruct"
5
+ require 'unicode/types'
5
6
 
6
7
  ##
7
8
  # Serialize ruleset back to EBNF
@@ -86,22 +87,23 @@ module EBNF
86
87
  #
87
88
  # @param [Array<Rule>] rules
88
89
  # @param [:abnf, :ebnf, :isoebnf] format (:ebnf)
90
+ # @param [Boolean] validate (false) validate generated HTML.
89
91
  # @return [Object]
90
- def self.html(*rules, format: :ebnf)
92
+ def self.html(*rules, format: :ebnf, validate: false)
91
93
  require 'stringio' unless defined?(StringIO)
92
94
  buf = StringIO.new
93
- Writer.new(rules, out: buf, html: true, format: format)
95
+ Writer.new(rules, out: buf, html: true, format: format, validate: validate)
94
96
  buf.string
95
97
  end
96
98
 
97
99
  ##
98
100
  # @param [Array<Rule>] rules
101
+ # @param [:abnf, :ebnf, :isoebnf] format (:ebnf)
102
+ # @param [Boolean] html (false) generate HTML output
103
+ # @param [Boolean] validate (false) validate generated HTML.
99
104
  # @param [Hash{Symbol => Object}] options
100
105
  # @param [#write] out ($stdout)
101
- # @param [:abnf, :ebnf, :isoebnf] format (:ebnf)
102
- # @option options [Symbol] format
103
- # @option options [Boolean] html (false)
104
- def initialize(rules, out: $stdout, html: false, format: :ebnf, **options)
106
+ def initialize(rules, out: $stdout, html: false, format: :ebnf, validate: false, **options)
105
107
  @options = options.merge(html: html)
106
108
  return if rules.empty?
107
109
 
@@ -174,7 +176,21 @@ module EBNF
174
176
  end
175
177
  end
176
178
  end.flatten
177
- out.write eruby.evaluate(format: format, rules: formatted_rules)
179
+
180
+ html_result = eruby.evaluate(format: format, rules: formatted_rules)
181
+
182
+ if validate
183
+ begin
184
+ # Validate the output HTML
185
+ doc = Nokogiri::HTML5("<!DOCTYPE html>" + html_result, max_errors: 10)
186
+ raise EncodingError, "Errors found in generated HTML:\n " +
187
+ doc.errors.map(&:to_s).join("\n ") unless doc.errors.empty?
188
+ rescue LoadError, NoMethodError
189
+ # Skip
190
+ end
191
+ end
192
+
193
+ out.write html_result
178
194
  return
179
195
  rescue LoadError
180
196
  $stderr.puts "Generating HTML requires erubis and htmlentities gems to be loaded"
@@ -347,16 +363,20 @@ module EBNF
347
363
  end
348
364
  char = fmt % u.ord
349
365
  if @options[:html]
350
- if u.ord <= 0x20
351
- char = %(<abbr title="#{ASCII_ESCAPE_NAMES[u.ord]}">#{@coder.encode char}</abbr>)
366
+ char = if u.ord <= 0x20
367
+ %(<abbr title="#{ASCII_ESCAPE_NAMES[u.ord]}">#{@coder.encode char}</abbr>)
368
+ elsif u.ord == 0x22
369
+ %(<abbr title="quot">>&quot;</abbr>)
352
370
  elsif u.ord < 0x7F
353
- char = %(<abbr title="ascii '#{@coder.encode u}'">#{@coder.encode char}</abbr>)
371
+ %(<abbr title="ascii '#{@coder.encode u}'">#{@coder.encode char}</abbr>)
354
372
  elsif u.ord == 0x7F
355
- char = %(<abbr title="delete">#{@coder.encode char}</abbr>)
373
+ %(<abbr title="delete">#{@coder.encode char}</abbr>)
356
374
  elsif u.ord <= 0xFF
357
- char = %(<abbr title="extended ascii '#{u}'">#{char}</abbr>)
375
+ %(<abbr title="extended ascii '#{@coder.encode char}'">#{char}</abbr>)
376
+ elsif (%w(Control Private-use Surrogate Noncharacter Reserved) - ::Unicode::Types.of(u)).empty?
377
+ %(<abbr title="unicode '#{u}'">#{char}</abbr>)
358
378
  else
359
- char = %(<abbr title="unicode '#{u}'">#{char}</abbr>)
379
+ %(<abbr title="unicode '#{::Unicode::Types.of(u).first}'">#{char}</abbr>)
360
380
  end
361
381
  %(<code class="grammar-char-escape">#{char}</code>)
362
382
  else
@@ -455,7 +475,7 @@ module EBNF
455
475
  # Format a single-character string, prefering hex for non-main ASCII
456
476
  def format_abnf_char(c)
457
477
  if /[\x20-\x21\x23-\x7E]/.match?(c)
458
- c.inspect
478
+ @options[:html] ? %("<code class="grammar-literal">#{@coder.encode c}</code>") : c.inspect
459
479
  else
460
480
  escape_abnf_hex(c)
461
481
  end
@@ -536,14 +556,16 @@ module EBNF
536
556
  if @options[:html]
537
557
  if u.ord <= 0x20
538
558
  char = %(<abbr title="#{ASCII_ESCAPE_NAMES[u.ord]}">#{@coder.encode char}</abbr>)
539
- elsif u.ord <= 0x7F
559
+ elsif u.ord == 0x22
560
+ %(<abbr title="quot">>&quot;</abbr>)
561
+ elsif u.ord < 0x7F
540
562
  char = %(<abbr title="ascii '#{u}'">#{@coder.encode char}</abbr>)
541
563
  elsif u.ord == 0x7F
542
564
  char = %(<abbr title="delete">#{@coder.encode char}</abbr>)
543
565
  elsif u.ord <= 0xFF
544
566
  char = %(<abbr title="extended ascii '#{u}'">#{char}</abbr>)
545
567
  else
546
- char = %(<abbr title="unicode '#{u}'">#{char}</abbr>)
568
+ char = %(<abbr title="unicode '#{u.unicode_normaliz}'">#{char}</abbr>)
547
569
  end
548
570
  %(<code class="grammar-char-escape">#{char}</code>)
549
571
  else
@@ -686,7 +708,7 @@ module EBNF
686
708
  <table class="grammar">
687
709
  <tbody id="grammar-productions" class="<%= @format %>">
688
710
  <% for rule in @rules %>
689
- <tr<%= %{ id="grammar-production-#{rule.sym}"} unless %w(=/ |).include?(rule.assign)%>>
711
+ <tr<%= %{ id="grammar-production-#{rule.sym}"} unless %w(=/ |).include?(rule.assign) || rule.sym.nil?%>>
690
712
  <% if rule.id %>
691
713
  <td<%= " colspan=2" unless rule.sym %>><%= rule.id %></td>
692
714
  <% end %>
data/lib/ebnf.rb CHANGED
@@ -9,6 +9,7 @@ module EBNF
9
9
  autoload :PEG, "ebnf/peg"
10
10
  autoload :Rule, "ebnf/rule"
11
11
  autoload :Terminals,"ebnf/terminals"
12
+ autoload :Unescape, "ebnf/unescape"
12
13
  autoload :Writer, "ebnf/writer"
13
14
  autoload :VERSION, "ebnf/version"
14
15
 
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: ebnf
3
3
  version: !ruby/object:Gem::Version
4
- version: 2.1.2
4
+ version: 2.3.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Gregg Kellogg
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2020-10-25 00:00:00.000000000 Z
11
+ date: 2021-12-08 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: sxp
@@ -16,14 +16,14 @@ dependencies:
16
16
  requirements:
17
17
  - - "~>"
18
18
  - !ruby/object:Gem::Version
19
- version: '1.1'
19
+ version: '1.2'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: '1.1'
26
+ version: '1.2'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: scanf
29
29
  requirement: !ruby/object:Gem::Requirement
@@ -44,14 +44,14 @@ dependencies:
44
44
  requirements:
45
45
  - - "~>"
46
46
  - !ruby/object:Gem::Version
47
- version: '3.1'
47
+ version: '3.2'
48
48
  type: :runtime
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
52
  - - "~>"
53
53
  - !ruby/object:Gem::Version
54
- version: '3.1'
54
+ version: '3.2'
55
55
  - !ruby/object:Gem::Dependency
56
56
  name: htmlentities
57
57
  requirement: !ruby/object:Gem::Requirement
@@ -66,48 +66,76 @@ dependencies:
66
66
  - - "~>"
67
67
  - !ruby/object:Gem::Version
68
68
  version: '4.3'
69
+ - !ruby/object:Gem::Dependency
70
+ name: unicode-types
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - "~>"
74
+ - !ruby/object:Gem::Version
75
+ version: '1.7'
76
+ type: :runtime
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '1.7'
83
+ - !ruby/object:Gem::Dependency
84
+ name: amazing_print
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - "~>"
88
+ - !ruby/object:Gem::Version
89
+ version: '1.4'
90
+ type: :runtime
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - "~>"
95
+ - !ruby/object:Gem::Version
96
+ version: '1.4'
69
97
  - !ruby/object:Gem::Dependency
70
98
  name: rdf-spec
71
99
  requirement: !ruby/object:Gem::Requirement
72
100
  requirements:
73
101
  - - "~>"
74
102
  - !ruby/object:Gem::Version
75
- version: '3.1'
103
+ version: '3.2'
76
104
  type: :development
77
105
  prerelease: false
78
106
  version_requirements: !ruby/object:Gem::Requirement
79
107
  requirements:
80
108
  - - "~>"
81
109
  - !ruby/object:Gem::Version
82
- version: '3.1'
110
+ version: '3.2'
83
111
  - !ruby/object:Gem::Dependency
84
112
  name: rdf-turtle
85
113
  requirement: !ruby/object:Gem::Requirement
86
114
  requirements:
87
115
  - - "~>"
88
116
  - !ruby/object:Gem::Version
89
- version: '3.1'
117
+ version: '3.2'
90
118
  type: :development
91
119
  prerelease: false
92
120
  version_requirements: !ruby/object:Gem::Requirement
93
121
  requirements:
94
122
  - - "~>"
95
123
  - !ruby/object:Gem::Version
96
- version: '3.1'
124
+ version: '3.2'
97
125
  - !ruby/object:Gem::Dependency
98
126
  name: nokogiri
99
127
  requirement: !ruby/object:Gem::Requirement
100
128
  requirements:
101
129
  - - "~>"
102
130
  - !ruby/object:Gem::Version
103
- version: '1.10'
131
+ version: '1.12'
104
132
  type: :development
105
133
  prerelease: false
106
134
  version_requirements: !ruby/object:Gem::Requirement
107
135
  requirements:
108
136
  - - "~>"
109
137
  - !ruby/object:Gem::Version
110
- version: '1.10'
138
+ version: '1.12'
111
139
  - !ruby/object:Gem::Dependency
112
140
  name: erubis
113
141
  requirement: !ruby/object:Gem::Requirement
@@ -128,14 +156,14 @@ dependencies:
128
156
  requirements:
129
157
  - - "~>"
130
158
  - !ruby/object:Gem::Version
131
- version: '3.9'
159
+ version: '3.10'
132
160
  type: :development
133
161
  prerelease: false
134
162
  version_requirements: !ruby/object:Gem::Requirement
135
163
  requirements:
136
164
  - - "~>"
137
165
  - !ruby/object:Gem::Version
138
- version: '3.9'
166
+ version: '3.10'
139
167
  - !ruby/object:Gem::Dependency
140
168
  name: rspec-its
141
169
  requirement: !ruby/object:Gem::Requirement
@@ -240,6 +268,7 @@ files:
240
268
  - lib/ebnf/peg/rule.rb
241
269
  - lib/ebnf/rule.rb
242
270
  - lib/ebnf/terminals.rb
271
+ - lib/ebnf/unescape.rb
243
272
  - lib/ebnf/version.rb
244
273
  - lib/ebnf/writer.rb
245
274
  homepage: https://github.com/dryruby/ebnf
@@ -254,15 +283,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
254
283
  requirements:
255
284
  - - ">="
256
285
  - !ruby/object:Gem::Version
257
- version: '2.4'
286
+ version: '2.6'
258
287
  required_rubygems_version: !ruby/object:Gem::Requirement
259
288
  requirements:
260
289
  - - ">="
261
290
  - !ruby/object:Gem::Version
262
291
  version: '0'
263
292
  requirements: []
264
- rubygems_version: 3.1.4
293
+ rubygems_version: 3.3.3
265
294
  signing_key:
266
295
  specification_version: 4
267
- summary: EBNF parser and parser generator.
296
+ summary: EBNF parser and parser generator in Ruby.
268
297
  test_files: []