1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
|
#!/usr/bin/env ruby -w
good = false
rules = Hash.new { |h,k| h[k] = [] }
rule = nil
order = []
def munge s
renames = [
# unquote... wtf?
/`(.+?)'/, proc { $1 },
/"'(.+?)'"/, proc { "\"#{$1}\"" },
"'='", "tEQL",
"'!'", "tBANG",
"'%'", "tPERCENT",
"'&'", "tAMPER2",
"'('", "tLPAREN2",
"')'", "tRPAREN",
"'*'", "tSTAR2",
"'+'", "tPLUS",
"','", "tCOMMA",
"'-'", "tMINUS",
"'.'", "tDOT",
"'/'", "tDIVIDE",
"';'", "tSEMI",
"':'", "tCOLON",
"'<'", "tLT",
"'>'", "tGT",
"'?'", "tEH",
"'['", "tLBRACK",
"'\\n'", "tNL",
"']'", "tRBRACK",
"'^'", "tCARET",
"'`'", "tBACK_REF2",
"'{'", "tLCURLY",
"'|'", "tPIPE",
"'}'", "tRCURLY",
"'~'", "tTILDE",
'"["', "tLBRACK",
# 2.0 changes?
'"<=>"', "tCMP",
'"=="', "tEQ",
'"==="', "tEQQ",
'"!~"', "tNMATCH",
'"=~"', "tMATCH",
'">="', "tGEQ",
'"<="', "tLEQ",
'"!="', "tNEQ",
'"<<"', "tLSHFT",
'">>"', "tRSHFT",
'"*"', "tSTAR",
'".."', "tDOT2",
'"&"', "tAMPER",
'"&&"', "tANDOP",
'"&."', "tLONELY",
'"||"', "tOROP",
'"..."', "tDOT3",
'"**"', "tPOW",
'"unary+"', "tUPLUS",
'"unary-"', "tUMINUS",
'"[]"', "tAREF",
'"[]="', "tASET",
'"::"', "tCOLON2",
'"{ arg"', "tLBRACE_ARG",
'"( arg"', "tLPAREN_ARG",
'"("', "tLPAREN",
'rparen', "tRPAREN",
'"{"', "tLBRACE",
'"=>"', "tASSOC",
'"->"', "tLAMBDA",
'":: at EXPR_BEG"', "tCOLON3",
'"**arg"', "tDSTAR",
'","', "tCOMMA",
# other
'tLBRACK2', "tLBRACK", # HACK
"' '", "tSPACE", # needs to be later to avoid bad hits
"%empty", "none", # newer bison
"/* empty */", "none",
/^\s*$/, "none",
"keyword_BEGIN", "klBEGIN",
"keyword_END", "klEND",
/keyword_(\w+)/, proc { "k#{$1.upcase}" },
/\bk_([a-z_]+)/, proc { "k#{$1.upcase}" },
/modifier_(\w+)/, proc { "k#{$1.upcase}_MOD" },
"kVARIABLE", "keyword_variable", # ugh
# 2.6 collapses klBEGIN to kBEGIN
"klBEGIN", "kBEGIN",
"klEND", "kEND",
/keyword_(\w+)/, proc { "k#{$1.upcase}" },
/\bk_([^_][a-z_]+)/, proc { "k#{$1.upcase}" },
/modifier_(\w+)/, proc { "k#{$1.upcase}_MOD" },
"kVARIABLE", "keyword_variable", # ugh: this is a rule name
# 2.7 changes:
'"global variable"', "tGVAR",
'"operator-assignment"', "tOP_ASGN",
'"back reference"', "tBACK_REF",
'"numbered reference"', "tNTH_REF",
'"local variable or method"', "tIDENTIFIER",
'"constant"', "tCONSTANT",
'"(.."', "tBDOT2",
'"(..."', "tBDOT3",
'"char literal"', "tCHAR",
'"literal content"', "tSTRING_CONTENT",
'"string literal"', "tSTRING_BEG",
'"symbol literal"', "tSYMBEG",
'"backtick literal"', "tXSTRING_BEG",
'"regexp literal"', "tREGEXP_BEG",
'"word list"', "tWORDS_BEG",
'"verbatim word list"', "tQWORDS_BEG",
'"symbol list"', "tSYMBOLS_BEG",
'"verbatim symbol list"', "tQSYMBOLS_BEG",
'"float literal"', "tFLOAT",
'"imaginary literal"', "tIMAGINARY",
'"integer literal"', "tINTEGER",
'"rational literal"', "tRATIONAL",
'"instance variable"', "tIVAR",
'"class variable"', "tCVAR",
'"terminator"', "tSTRING_END", # TODO: switch this?
'"method"', "tFID",
'"}"', "tSTRING_DEND",
'"do for block"', "kDO_BLOCK",
'"do for condition"', "kDO_COND",
'"do for lambda"', "kDO_LAMBDA",
"tLABEL", "kLABEL",
# UGH
"k_LINE__", "k__LINE__",
"k_FILE__", "k__FILE__",
"k_ENCODING__", "k__ENCODING__",
'"defined?"', "kDEFINED",
'"do (for condition)"', "kDO_COND",
'"do (for lambda)"', "kDO_LAMBDA",
'"do (for block)"', "kDO_BLOCK",
/\"(\w+) \(?modifier\)?\"/, proc { |x| "k#{$1.upcase}_MOD" },
/\"(\w+)\"/, proc { |x| "k#{$1.upcase}" },
/\$?@(\d+)(\s+|$)/, "", # newer bison
# TODO: remove for 3.0 work:
"lex_ctxt ", "" # 3.0 production that's mostly noise right now
]
renames.each_slice(2) do |(a, b)|
if Proc === b then
s.gsub!(a, &b)
else
s.gsub!(a, b)
end
end
s.strip
end
ARGF.each_line do |line|
next unless good or line =~ /^-* ?Grammar|\$accept : /
case line.strip
when /^$/ then
when /^(\d+) (\$?[@\w]+): (.*)/ then # yacc
rule = $2
order << rule unless rules.has_key? rule
rules[rule] << munge($3)
when /^(\d+) \s+\| (.*)/ then # yacc
rules[rule] << munge($2)
when /^(\d+) (@\d+): (.*)/ then # yacc
rule = $2
order << rule unless rules.has_key? rule
rules[rule] << munge($3)
when /^rule (\d+) (@?\w+):(.*)/ then # racc
rule = $2
order << rule unless rules.has_key? rule
rules[rule] << munge($3)
when /\$accept/ then # byacc?
good = true
when /Grammar/ then # both
good = true
when /^-+ Symbols/ then # racc
break
when /^Terminals/ then # yacc
break
when /^\cL/ then # byacc
break
else
warn "unparsed: #{$.}: #{line.strip.inspect}"
end
end
require 'yaml'
order.each do |k|
next if k =~ /@/
puts
puts "#{k}:"
puts rules[k].map { |r| " #{r}" }.join "\n"
end
|
