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
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
|
#!/usr/bin/env ruby -ws
$v ||= false
stack = []
last_token = nil
reduce_line = nil
def munge s
renames = [
"'='", "tEQL",
"'!'", "tBANG",
"'%'", "tPERCENT",
"'&'", "tAMPER2",
"'('", "tLPAREN2",
"')'", "tRPAREN",
"'*'", "tSTAR2",
"'+'", "tPLUS",
"','", "tCOMMA",
"'-'", "tMINUS",
"'.'", "tDOT",
"'/'", "tDIVIDE",
"';'", "tSEMI",
"':'", "tCOLON",
"'<'", "tLT",
"'>'", "tGT",
"'?'", "tEH",
"'['", "tLBRACK",
"'\\n'", "tNL",
"']'", "tRBRACK",
"'^'", "tCARET",
"'`'", "tBACK_REF2",
"'{'", "tLCURLY",
"'|'", "tPIPE",
"'}'", "tRCURLY",
"'~'", "tTILDE",
'"["', "tLBRACK",
# 2.0 changes?
'"<=>"', "tCMP",
'"=="', "tEQ",
'"==="', "tEQQ",
'"!~"', "tNMATCH",
'"=~"', "tMATCH",
'">="', "tGEQ",
'"<="', "tLEQ",
'"!="', "tNEQ",
'"<<"', "tLSHFT",
'">>"', "tRSHFT",
'"*"', "tSTAR",
'".."', "tDOT2",
'"&"', "tAMPER",
'"&&"', "tANDOP",
'"&."', "tLONELY",
'"||"', "tOROP",
'"..."', "tDOT3",
'"**"', "tPOW",
'"unary+"', "tUPLUS",
'"unary-"', "tUMINUS",
'"[]"', "tAREF",
'"[]="', "tASET",
'"::"', "tCOLON2",
'"{ arg"', "tLBRACE_ARG",
'"( arg"', "tLPAREN_ARG",
'"("', "tLPAREN",
'rparen', "tRPAREN",
'"{"', "tLBRACE",
'"=>"', "tASSOC",
'"->"', "tLAMBDA",
'":: at EXPR_BEG"', "tCOLON3",
'"**arg"', "tDSTAR",
'","', "tCOMMA",
# other
'kTERMINATOR', "tSTRING_END",
'"kTERMINATOR"', "tSTRING_END",
'kTRCURLY', "tSTRING_DEND",
'"symbol literal"', "tSYMBEG",
'"string literal"', "tSTRING_BEG",
'"backtick literal"', "tXSTRING_BEG",
'"regexp literal"', "tREGEXP_BEG",
'"word list"', "tWORDS_BEG",
'"verbatim word list"', "tQWORDS_BEG",
'"symbol list"', "tSYMBOLS_BEG",
'"verbatim symbol list"', "tQSYMBOLS_BEG",
'"terminator"', "tSTRING_END",
'"\'}\'"', "tSTRING_DEND",
'"string literal"',"tSTRING_BEG",
'"literal content"', "tSTRING_CONTENT",
/\$/, "", # try to remove these lumps?
'tLBRACK2', "tLBRACK", # HACK
"' '", "tSPACE", # needs to be later to avoid bad hits
"/* empty */", "none",
/^\s*$/, "",
"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
"tCONST", "kCONST",
# 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
# UGH
"k_LINE__", "k__LINE__",
"k_FILE__", "k__FILE__",
"k_ENCODING__", "k__ENCODING__",
'"defined?"', "kDEFINED",
"<none>", "none",
'"do (for condition)"', "kDO_COND",
'"do (for lambda)"', "kDO_LAMBDA",
'"do (for block)"', "kDO_BLOCK",
'"local variable or method"', "tIDENTIFIER",
/\"(\w+) \(modifier\)\"/, proc { |x| "k#{$1.upcase}_MOD" },
/\"(\w+)\"/, proc { |x| "k#{$1.upcase}" },
/\"`(\w+)'\"/, proc { |x| "k#{$1.upcase}" },
/@(\d+)(\s+|$)/, "",
/\$?@(\d+) */, "", # TODO: remove?
/_EXPR/, "",
]
renames.each_slice(2) do |(a, b)|
if Proc === b then
s.gsub!(a, &b)
else
s.gsub!(a, b)
end
end
if s.empty? then
nil
else
s.strip.squeeze " "
end
end
ARGF.each_line do |line|
case line
when /^(Stack now|Entering state|Shifting|Cleanup|Starting)/ then
# do nothing
when /^vtable_/ then
# do nothing
when /Gem::MissingSpecError/ then
# do nothing -- ruby 2.5 is being bitchy?
when /^Reading a token: Next token is token (.*?) \(\)/ then
token = munge $1
next if last_token == token
puts "next token is %p" % [token]
last_token = token
when /^Reading a token: / then
next # skip
when /^Reading a token$/ then # wtf?
next # skip
when /^(?:add_delayed_token|parser_dispatch)/ then # dunno what this is yet
next # skip
when /^read\s+:(\w+)/ then # read :tNL(tNL) nil
token = munge $1
next if last_token == token
puts "next token is %p" % [token]
last_token = token
when /^Next token is token ("[^"]+"|\S+)/ then
token = munge $1
next if last_token == token
puts "next token is %p" % [token]
last_token = token
when /^read\s+false/ then # read false($end) "$end"
puts "next token is EOF"
when /^Now at end of input./ then
# do nothing
when /^.:scan=>\["([^"]+)"/ then
puts "scan = %p" % [$1]
when /^.:getch=>\["([^"]+)/ then
puts "SCAN = %p" % [$1]
when /^Reducing stack by rule (\d+) \(line (\d+)\):/ then
reduce_line = $2.to_i
when /^ \$\d+ = (?:token|nterm) (.+) \(.*\)/ then
item = $1
stack << munge(item)
when /^-> \$\$ = (?:token|nterm) (.+) \(.*\)/ then
stack << "none" if stack.empty?
item = munge $1
x = stack.compact.map { |s| munge s.strip }.compact.join " "
if x != item then # prevent kdef -> kdef
if $v && reduce_line then
puts "reduce #{x} --> #{item} at #{reduce_line}".squeeze " "
else
puts "reduce #{x} --> #{item}".squeeze " "
end
puts
end
reduce_line = nil
stack.clear
when /^reduce/ then # ruby_parser side
s = munge line.chomp
next if s =~ /reduce\s+(\w+) --> \1/
puts s
puts
when /^(\w+_stack)\.(\w+)/ then
# TODO: make pretty, but still informative w/ line numbers etc
puts line.gsub("true", "1").gsub("false", "0")
# puts "#{$1}(#{$2})"
when /^(\w+_stack(\(\w+\))?: \S+)/ then
# _data = $v ? line.chomp : $1
# puts line
# TODO: make pretty, but still informative w/ line numbers etc
puts line.gsub("true", "1").gsub("false", "0")
when /^lex_state: :?([\w|()]+) -> :?([\w|]+)(?: (?:at|from) (.*))?/ then
a, b, c = $1.upcase, $2.upcase, $3
a.gsub!(/EXPR_/, "")
b.gsub!(/EXPR_/, "")
if c && $v then
puts "lex_state: #{a} -> #{b} at #{c}"
else
puts "lex_state: #{a} -> #{b}"
end
when /debug|FUCK/ then
puts line.chomp
when /^(#.*parse error|on )/ then
puts line.chomp
when /^(goto|shift| +\[|$)/ then # racc
# do nothing
# when /^Reading a token: Now at end of input./ then
# # puts "EOF"
# when /^Reading a token: Next token is token (.+)/ then
# puts "READ: #{$1.inspect}"
when /^accept/ then
puts "DONE"
else
puts "unparsed: #{line.chomp}"
end
end
|
