racc 1.5.2-java → 1.6.0-java
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.ja.rdoc +0 -1
- data/README.rdoc +6 -7
- data/{rdoc → doc}/en/NEWS.en.rdoc +0 -0
- data/{rdoc → doc}/en/grammar.en.rdoc +27 -31
- data/doc/en/grammar2.en.rdoc +219 -0
- data/{rdoc → doc}/ja/NEWS.ja.rdoc +0 -0
- data/{rdoc → doc}/ja/command.ja.html +0 -0
- data/{rdoc → doc}/ja/debug.ja.rdoc +0 -0
- data/{rdoc → doc}/ja/grammar.ja.rdoc +0 -0
- data/{rdoc → doc}/ja/index.ja.html +0 -0
- data/{rdoc → doc}/ja/parser.ja.rdoc +0 -0
- data/{rdoc → doc}/ja/usage.ja.html +0 -0
- data/ext/racc/cparse/cparse.c +1 -1
- data/ext/racc/cparse/extconf.rb +1 -0
- data/lib/racc/cparse-jruby.jar +0 -0
- data/lib/racc/info.rb +1 -1
- data/lib/racc/parser-text.rb +1 -1
- data/lib/racc/parser.rb +1 -1
- data/lib/racc/parserfilegenerator.rb +0 -44
- data/lib/racc/statetransitiontable.rb +2 -8
- metadata +15 -121
- data/Rakefile +0 -79
- data/ext/racc/com/headius/racc/Cparse.java +0 -849
- data/lib/racc/pre-setup +0 -13
- data/sample/array.y +0 -67
- data/sample/array2.y +0 -59
- data/sample/calc-ja.y +0 -66
- data/sample/calc.y +0 -65
- data/sample/conflict.y +0 -15
- data/sample/hash.y +0 -60
- data/sample/lalr.y +0 -17
- data/sample/lists.y +0 -57
- data/sample/syntax.y +0 -46
- data/sample/yyerr.y +0 -46
- data/test/assets/cadenza.y +0 -170
- data/test/assets/cast.y +0 -926
- data/test/assets/chk.y +0 -126
- data/test/assets/conf.y +0 -16
- data/test/assets/csspool.y +0 -729
- data/test/assets/digraph.y +0 -29
- data/test/assets/echk.y +0 -118
- data/test/assets/edtf.y +0 -583
- data/test/assets/err.y +0 -60
- data/test/assets/error_recovery.y +0 -35
- data/test/assets/expect.y +0 -7
- data/test/assets/firstline.y +0 -4
- data/test/assets/huia.y +0 -318
- data/test/assets/ichk.y +0 -102
- data/test/assets/intp.y +0 -546
- data/test/assets/journey.y +0 -47
- data/test/assets/liquor.y +0 -313
- data/test/assets/machete.y +0 -423
- data/test/assets/macruby.y +0 -2197
- data/test/assets/mailp.y +0 -437
- data/test/assets/mediacloth.y +0 -599
- data/test/assets/mof.y +0 -649
- data/test/assets/namae.y +0 -302
- data/test/assets/nasl.y +0 -626
- data/test/assets/newsyn.y +0 -25
- data/test/assets/noend.y +0 -4
- data/test/assets/nokogiri-css.y +0 -255
- data/test/assets/nonass.y +0 -41
- data/test/assets/normal.y +0 -27
- data/test/assets/norule.y +0 -4
- data/test/assets/nullbug1.y +0 -25
- data/test/assets/nullbug2.y +0 -15
- data/test/assets/opal.y +0 -1807
- data/test/assets/opt.y +0 -123
- data/test/assets/percent.y +0 -35
- data/test/assets/php_serialization.y +0 -98
- data/test/assets/recv.y +0 -97
- data/test/assets/riml.y +0 -665
- data/test/assets/rrconf.y +0 -14
- data/test/assets/ruby18.y +0 -1943
- data/test/assets/ruby19.y +0 -2174
- data/test/assets/ruby20.y +0 -2350
- data/test/assets/ruby21.y +0 -2359
- data/test/assets/ruby22.y +0 -2381
- data/test/assets/scan.y +0 -72
- data/test/assets/syntax.y +0 -50
- data/test/assets/tp_plus.y +0 -622
- data/test/assets/twowaysql.y +0 -278
- data/test/assets/unterm.y +0 -5
- data/test/assets/useless.y +0 -12
- data/test/assets/yyerr.y +0 -46
- data/test/bench.y +0 -36
- data/test/helper.rb +0 -115
- data/test/infini.y +0 -8
- data/test/regress/cadenza +0 -796
- data/test/regress/cast +0 -3428
- data/test/regress/csspool +0 -2314
- data/test/regress/edtf +0 -1794
- data/test/regress/huia +0 -1392
- data/test/regress/journey +0 -222
- data/test/regress/liquor +0 -885
- data/test/regress/machete +0 -833
- data/test/regress/mediacloth +0 -1463
- data/test/regress/mof +0 -1368
- data/test/regress/namae +0 -634
- data/test/regress/nasl +0 -2058
- data/test/regress/nokogiri-css +0 -836
- data/test/regress/opal +0 -6431
- data/test/regress/php_serialization +0 -336
- data/test/regress/riml +0 -3283
- data/test/regress/ruby18 +0 -6344
- data/test/regress/ruby22 +0 -7460
- data/test/regress/tp_plus +0 -1933
- data/test/regress/twowaysql +0 -556
- data/test/scandata/brace +0 -7
- data/test/scandata/gvar +0 -1
- data/test/scandata/normal +0 -4
- data/test/scandata/percent +0 -18
- data/test/scandata/slash +0 -10
- data/test/src.intp +0 -34
- data/test/start.y +0 -20
- data/test/test_chk_y.rb +0 -52
- data/test/test_grammar_file_parser.rb +0 -15
- data/test/test_racc_command.rb +0 -339
- data/test/test_scan_y.rb +0 -52
- data/test/testscanner.rb +0 -51
- data/web/racc.en.rhtml +0 -42
- data/web/racc.ja.rhtml +0 -51
data/test/assets/namae.y
DELETED
@@ -1,302 +0,0 @@
|
|
1
|
-
# -*- ruby -*-
|
2
|
-
# vi: set ft=ruby :
|
3
|
-
|
4
|
-
# Copyright (C) 2012 President and Fellows of Harvard College
|
5
|
-
# Copyright (C) 2013-2014 Sylvester Keil
|
6
|
-
#
|
7
|
-
# Redistribution and use in source and binary forms, with or without
|
8
|
-
# modification, are permitted provided that the following conditions are met:
|
9
|
-
#
|
10
|
-
# 1. Redistributions of source code must retain the above copyright notice,
|
11
|
-
# this list of conditions and the following disclaimer.
|
12
|
-
#
|
13
|
-
# 2. Redistributions in binary form must reproduce the above copyright notice,
|
14
|
-
# this list of conditions and the following disclaimer in the documentation
|
15
|
-
# and/or other materials provided with the distribution.
|
16
|
-
#
|
17
|
-
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER ``AS IS'' AND ANY EXPRESS OR
|
18
|
-
# IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
19
|
-
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
20
|
-
# EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
|
21
|
-
# INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
|
22
|
-
# BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
23
|
-
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
|
24
|
-
# OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
|
25
|
-
# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
|
26
|
-
# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
27
|
-
#
|
28
|
-
# The views and conclusions contained in the software and documentation are
|
29
|
-
# those of the authors and should not be interpreted as representing official
|
30
|
-
# policies, either expressed or implied, of the copyright holder.
|
31
|
-
|
32
|
-
class Namae::Parser
|
33
|
-
|
34
|
-
token COMMA UWORD LWORD PWORD NICK AND APPELLATION TITLE SUFFIX
|
35
|
-
|
36
|
-
expect 0
|
37
|
-
|
38
|
-
rule
|
39
|
-
|
40
|
-
names : { result = [] }
|
41
|
-
| name { result = [val[0]] }
|
42
|
-
| names AND name { result = val[0] << val[2] }
|
43
|
-
|
44
|
-
name : word { result = Name.new(:given => val[0]) }
|
45
|
-
| display_order
|
46
|
-
| honorific word { result = val[0].merge(:family => val[1]) }
|
47
|
-
| honorific display_order { result = val[1].merge(val[0]) }
|
48
|
-
| sort_order
|
49
|
-
|
50
|
-
honorific : APPELLATION { result = Name.new(:appellation => val[0]) }
|
51
|
-
| TITLE { result = Name.new(:title => val[0]) }
|
52
|
-
|
53
|
-
display_order : u_words word opt_suffices opt_titles
|
54
|
-
{
|
55
|
-
result = Name.new(:given => val[0], :family => val[1],
|
56
|
-
:suffix => val[2], :title => val[3])
|
57
|
-
}
|
58
|
-
| u_words NICK last opt_suffices opt_titles
|
59
|
-
{
|
60
|
-
result = Name.new(:given => val[0], :nick => val[1],
|
61
|
-
:family => val[2], :suffix => val[3], :title => val[4])
|
62
|
-
}
|
63
|
-
| u_words NICK von last opt_suffices opt_titles
|
64
|
-
{
|
65
|
-
result = Name.new(:given => val[0], :nick => val[1],
|
66
|
-
:particle => val[2], :family => val[3],
|
67
|
-
:suffix => val[4], :title => val[5])
|
68
|
-
}
|
69
|
-
| u_words von last
|
70
|
-
{
|
71
|
-
result = Name.new(:given => val[0], :particle => val[1],
|
72
|
-
:family => val[2])
|
73
|
-
}
|
74
|
-
| von last
|
75
|
-
{
|
76
|
-
result = Name.new(:particle => val[0], :family => val[1])
|
77
|
-
}
|
78
|
-
|
79
|
-
sort_order : last COMMA first
|
80
|
-
{
|
81
|
-
result = Name.new({ :family => val[0], :suffix => val[2][0],
|
82
|
-
:given => val[2][1] }, !!val[2][0])
|
83
|
-
}
|
84
|
-
| von last COMMA first
|
85
|
-
{
|
86
|
-
result = Name.new({ :particle => val[0], :family => val[1],
|
87
|
-
:suffix => val[3][0], :given => val[3][1] }, !!val[3][0])
|
88
|
-
}
|
89
|
-
| u_words von last COMMA first
|
90
|
-
{
|
91
|
-
result = Name.new({ :particle => val[0,2].join(' '), :family => val[2],
|
92
|
-
:suffix => val[4][0], :given => val[4][1] }, !!val[4][0])
|
93
|
-
}
|
94
|
-
;
|
95
|
-
|
96
|
-
von : LWORD
|
97
|
-
| von LWORD { result = val.join(' ') }
|
98
|
-
| von u_words LWORD { result = val.join(' ') }
|
99
|
-
|
100
|
-
last : LWORD | u_words
|
101
|
-
|
102
|
-
first : opt_words { result = [nil,val[0]] }
|
103
|
-
| words opt_comma suffices { result = [val[2],val[0]] }
|
104
|
-
| suffices { result = [val[0],nil] }
|
105
|
-
| suffices COMMA words { result = [val[0],val[2]] }
|
106
|
-
|
107
|
-
u_words : u_word
|
108
|
-
| u_words u_word { result = val.join(' ') }
|
109
|
-
|
110
|
-
u_word : UWORD | PWORD
|
111
|
-
|
112
|
-
words : word
|
113
|
-
| words word { result = val.join(' ') }
|
114
|
-
|
115
|
-
opt_comma : /* empty */ | COMMA
|
116
|
-
opt_words : /* empty */ | words
|
117
|
-
|
118
|
-
word : LWORD | UWORD | PWORD
|
119
|
-
|
120
|
-
opt_suffices : /* empty */ | suffices
|
121
|
-
|
122
|
-
suffices : SUFFIX
|
123
|
-
| suffices SUFFIX { result = val.join(' ') }
|
124
|
-
|
125
|
-
opt_titles : /* empty */ | titles
|
126
|
-
|
127
|
-
titles : TITLE
|
128
|
-
| titles TITLE { result = val.join(' ') }
|
129
|
-
|
130
|
-
---- header
|
131
|
-
require 'singleton'
|
132
|
-
require 'strscan'
|
133
|
-
|
134
|
-
---- inner
|
135
|
-
|
136
|
-
include Singleton
|
137
|
-
|
138
|
-
attr_reader :options, :input
|
139
|
-
|
140
|
-
def initialize
|
141
|
-
@input, @options = StringScanner.new(''), {
|
142
|
-
:debug => false,
|
143
|
-
:prefer_comma_as_separator => false,
|
144
|
-
:comma => ',',
|
145
|
-
:stops => ',;',
|
146
|
-
:separator => /\s*(\band\b|\&|;)\s*/i,
|
147
|
-
:title => /\s*\b(sir|lord|count(ess)?|(gen|adm|col|maj|capt|cmdr|lt|sgt|cpl|pvt|prof|dr|md|ph\.?d)\.?)(\s+|$)/i,
|
148
|
-
:suffix => /\s*\b(JR|Jr|jr|SR|Sr|sr|[IVX]{2,})(\.|\b)/,
|
149
|
-
:appellation => /\s*\b((mrs?|ms|fr|hr)\.?|miss|herr|frau)(\s+|$)/i
|
150
|
-
}
|
151
|
-
end
|
152
|
-
|
153
|
-
def debug?
|
154
|
-
options[:debug] || ENV['DEBUG']
|
155
|
-
end
|
156
|
-
|
157
|
-
def separator
|
158
|
-
options[:separator]
|
159
|
-
end
|
160
|
-
|
161
|
-
def comma
|
162
|
-
options[:comma]
|
163
|
-
end
|
164
|
-
|
165
|
-
def stops
|
166
|
-
options[:stops]
|
167
|
-
end
|
168
|
-
|
169
|
-
def title
|
170
|
-
options[:title]
|
171
|
-
end
|
172
|
-
|
173
|
-
def suffix
|
174
|
-
options[:suffix]
|
175
|
-
end
|
176
|
-
|
177
|
-
def appellation
|
178
|
-
options[:appellation]
|
179
|
-
end
|
180
|
-
|
181
|
-
def prefer_comma_as_separator?
|
182
|
-
options[:prefer_comma_as_separator]
|
183
|
-
end
|
184
|
-
|
185
|
-
def parse(input)
|
186
|
-
parse!(input)
|
187
|
-
rescue => e
|
188
|
-
warn e.message if debug?
|
189
|
-
[]
|
190
|
-
end
|
191
|
-
|
192
|
-
def parse!(string)
|
193
|
-
input.string = normalize(string)
|
194
|
-
reset
|
195
|
-
do_parse
|
196
|
-
end
|
197
|
-
|
198
|
-
def normalize(string)
|
199
|
-
string = string.strip
|
200
|
-
string
|
201
|
-
end
|
202
|
-
|
203
|
-
def reset
|
204
|
-
@commas, @words, @initials, @suffices, @yydebug = 0, 0, 0, 0, debug?
|
205
|
-
self
|
206
|
-
end
|
207
|
-
|
208
|
-
private
|
209
|
-
|
210
|
-
def stack
|
211
|
-
@vstack || @racc_vstack || []
|
212
|
-
end
|
213
|
-
|
214
|
-
def last_token
|
215
|
-
stack[-1]
|
216
|
-
end
|
217
|
-
|
218
|
-
def consume_separator
|
219
|
-
return next_token if seen_separator?
|
220
|
-
@commas, @words, @initials, @suffices = 0, 0, 0, 0
|
221
|
-
[:AND, :AND]
|
222
|
-
end
|
223
|
-
|
224
|
-
def consume_comma
|
225
|
-
@commas += 1
|
226
|
-
[:COMMA, :COMMA]
|
227
|
-
end
|
228
|
-
|
229
|
-
def consume_word(type, word)
|
230
|
-
@words += 1
|
231
|
-
|
232
|
-
case type
|
233
|
-
when :UWORD
|
234
|
-
@initials += 1 if word =~ /^[[:upper:]]+\b/
|
235
|
-
when :SUFFIX
|
236
|
-
@suffices += 1
|
237
|
-
end
|
238
|
-
|
239
|
-
[type, word]
|
240
|
-
end
|
241
|
-
|
242
|
-
def seen_separator?
|
243
|
-
!stack.empty? && last_token == :AND
|
244
|
-
end
|
245
|
-
|
246
|
-
def suffix?
|
247
|
-
!@suffices.zero? || will_see_suffix?
|
248
|
-
end
|
249
|
-
|
250
|
-
def will_see_suffix?
|
251
|
-
input.peek(8).to_s.strip.split(/\s+/)[0] =~ suffix
|
252
|
-
end
|
253
|
-
|
254
|
-
def will_see_initial?
|
255
|
-
input.peek(6).to_s.strip.split(/\s+/)[0] =~ /^[[:upper:]]+\b/
|
256
|
-
end
|
257
|
-
|
258
|
-
def seen_full_name?
|
259
|
-
prefer_comma_as_separator? && @words > 1 &&
|
260
|
-
(@initials > 0 || !will_see_initial?) && !will_see_suffix?
|
261
|
-
end
|
262
|
-
|
263
|
-
def next_token
|
264
|
-
case
|
265
|
-
when input.nil?, input.eos?
|
266
|
-
nil
|
267
|
-
when input.scan(separator)
|
268
|
-
consume_separator
|
269
|
-
when input.scan(/\s*#{comma}\s*/)
|
270
|
-
if @commas.zero? && !seen_full_name? || @commas == 1 && suffix?
|
271
|
-
consume_comma
|
272
|
-
else
|
273
|
-
consume_separator
|
274
|
-
end
|
275
|
-
when input.scan(/\s+/)
|
276
|
-
next_token
|
277
|
-
when input.scan(title)
|
278
|
-
consume_word(:TITLE, input.matched.strip)
|
279
|
-
when input.scan(suffix)
|
280
|
-
consume_word(:SUFFIX, input.matched.strip)
|
281
|
-
when input.scan(appellation)
|
282
|
-
[:APPELLATION, input.matched.strip]
|
283
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:upper:]][^\s#{stops}]*/)
|
284
|
-
consume_word(:UWORD, input.matched)
|
285
|
-
when input.scan(/((\\\w+)?\{[^\}]*\})*[[:lower:]][^\s#{stops}]*/)
|
286
|
-
consume_word(:LWORD, input.matched)
|
287
|
-
when input.scan(/(\\\w+)?\{[^\}]*\}[^\s#{stops}]*/)
|
288
|
-
consume_word(:PWORD, input.matched)
|
289
|
-
when input.scan(/('[^'\n]+')|("[^"\n]+")/)
|
290
|
-
consume_word(:NICK, input.matched[1...-1])
|
291
|
-
else
|
292
|
-
raise ArgumentError,
|
293
|
-
"Failed to parse name #{input.string.inspect}: unmatched data at offset #{input.pos}"
|
294
|
-
end
|
295
|
-
end
|
296
|
-
|
297
|
-
def on_error(tid, value, stack)
|
298
|
-
raise ArgumentError,
|
299
|
-
"Failed to parse name: unexpected '#{value}' at #{stack.inspect}"
|
300
|
-
end
|
301
|
-
|
302
|
-
# -*- racc -*-
|