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
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
|
# the scanner/lexer
require 'strscan'
require 'puppet'
module Puppet
class LexError < RuntimeError; end
module Parser
#---------------------------------------------------------------
class Lexer
attr_reader :line, :last, :file
attr_accessor :indefine
#%r{\w+} => :WORD,
@@tokens = {
%r{#.*} => :COMMENT,
%r{\[} => :LBRACK,
%r{\]} => :RBRACK,
%r{\{} => :LBRACE,
%r{\}} => :RBRACE,
%r{\(} => :LPAREN,
%r{\)} => :RPAREN,
%r{\"} => :DQUOTE,
%r{\n} => :RETURN,
%r{\'} => :SQUOTE,
%r{=} => :EQUALS,
%r{==} => :ISEQUAL,
%r{>=} => :GREATEREQUAL,
%r{>} => :GREATERTHAN,
%r{<} => :LESSTHAN,
%r{<=} => :LESSEQUAL,
%r{!=} => :NOTEQUAL,
%r{!} => :NOT,
%r{,} => :COMMA,
%r{\.} => :DOT,
%r{:} => :COLON,
%r{@} => :AT,
%r{<<\|} => :LLCOLLECT,
%r{\|>>} => :RRCOLLECT,
%r{<\|} => :LCOLLECT,
%r{\|>} => :RCOLLECT,
%r{;} => :SEMIC,
%r{\?} => :QMARK,
%r{\\} => :BACKSLASH,
%r{=>} => :FARROW,
%r{[a-z][-\w]*} => :NAME,
%r{([a-z][-\w]*::)+[a-z][-\w]*} => :CLASSNAME,
%r{([A-Z][-\w]*::)+[A-Z][-\w]*} => :CLASSREF,
%r{[A-Z][-\w]*} => :TYPE,
%r{[0-9]+} => :NUMBER,
%r{\$(\w*::)*\w+} => :VARIABLE
}
@@pairs = {
"{" => "}",
"(" => ")",
"[" => "]",
"<|" => "|>",
"<<|" => "|>>"
}
@@reverse_pairs = @@pairs.inject({}) { |hash, pair| hash[pair[1]] = pair[0]; hash }
@@keywords = {
"case" => :CASE,
"class" => :CLASS,
"default" => :DEFAULT,
"define" => :DEFINE,
"false" => :BOOLEAN,
"import" => :IMPORT,
"if" => :IF,
"elsif" => :ELSIF,
"else" => :ELSE,
"inherits" => :INHERITS,
"node" => :NODE,
"true" => :BOOLEAN,
"and" => :AND,
"or" => :OR,
"undef" => :UNDEF
}
def clear
initvars
end
def expected
if @expected.empty?
nil
else
token = @expected[-1]
@@tokens.each do |value, name|
if token == name
return value
end
end
return token
end
end
# scan the whole file
# basically just used for testing
def fullscan
array = []
self.scan { |token,str|
# Ignore any definition nesting problems
@indefine = false
#Puppet.debug("got token '%s' => '%s'" % [token,str])
if token.nil?
return array
else
array.push([token,str])
end
}
return array
end
# this is probably pretty damned inefficient...
# it'd be nice not to have to load the whole file first...
def file=(file)
@file = file
@line = 1
File.open(file) { |of|
str = ""
of.each { |line| str += line }
@scanner = StringScanner.new(str)
}
end
def indefine?
if defined? @indefine
@indefine
else
false
end
end
def initialize
initvars()
end
def initvars
@line = 1
@last = ""
@lasttoken = nil
@scanner = nil
@file = nil
# AAARRGGGG! okay, regexes in ruby are bloody annoying
# no one else has "\n" =~ /\s/
@skip = %r{[ \t]+}
@namestack = []
@indefine = false
@expected = []
end
# Go up one in the namespace.
def namepop
@namestack.pop
end
# Collect the current namespace.
def namespace
@namestack.join("::")
end
# This value might have :: in it, but we don't care -- it'll be
# handled normally when joining, and when popping we want to pop
# this full value, however long the namespace is.
def namestack(value)
@namestack << value
end
def rest
@scanner.rest
end
# this is the heart of the lexer
def scan
#Puppet.debug("entering scan")
if @scanner.nil?
raise TypeError.new("Invalid or empty string")
end
@scanner.skip(@skip)
until @scanner.eos? do
yielded = false
sendbreak = false # gah, this is a nasty hack
stoken = nil
sregex = nil
value = ""
# first find out which type of token we've got
@@tokens.each { |regex,token|
# we're just checking, which doesn't advance the scan
# pointer
tmp = @scanner.check(regex)
if tmp.nil?
#puppet.debug("did not match %s to '%s'" %
# [regex,@scanner.rest])
next
end
# find the longest match
if tmp.length > value.length
value = tmp
stoken = token
sregex = regex
else
# we've already got a longer match
next
end
}
# error out if we didn't match anything at all
if stoken.nil?
nword = nil
if @scanner.rest =~ /^(\S+)/
nword = $1
elsif@scanner.rest =~ /^(\s+)/
nword = $1
else
nword = @scanner.rest
end
raise "Could not match '%s'" % nword
end
value = @scanner.scan(sregex)
if value == ""
raise "Didn't match regex on token %s" % stoken
end
# token-specific operations
# if this gets much more complicated, it should
# be moved up to where the tokens themselves are defined
# which will get me about 75% of the way to a lexer generator
ptoken = stoken
case stoken
when :NAME then
wtoken = stoken
# we're looking for keywords here
if @@keywords.include?(value)
wtoken = @@keywords[value]
#Puppet.debug("token '%s'" % wtoken)
if wtoken == :BOOLEAN
value = eval(value)
end
end
ptoken = wtoken
when :NUMBER then
ptoken = :NAME
when :COMMENT then
# just throw comments away
next
when :RETURN then
@line += 1
@scanner.skip(@skip)
next
when :SQUOTE then
#Puppet.debug("searching '%s' after '%s'" % [self.rest,value])
value = self.slurpstring(value)
ptoken = :SQTEXT
#Puppet.debug("got string '%s' => '%s'" % [:DQTEXT,value])
when :DQUOTE then
value = self.slurpstring(value)
ptoken = :DQTEXT
when :VARIABLE then
value = value.sub(/^\$/, '')
end
if match = @@pairs[value] and ptoken != :DQUOTE and ptoken != :SQUOTE
@expected << match
elsif exp = @expected[-1] and exp == value and ptoken != :DQUOTE and ptoken != :SQUOTE
@expected.pop
end
yield [ptoken, value]
if @lasttoken == :CLASS
namestack(value)
end
if @lasttoken == :DEFINE
if indefine?
msg = "Cannot nest definition %s inside %s" % [value, @indefine]
self.indefine = false
raise Puppet::ParseError, msg
end
@indefine = value
end
@last = value
@lasttoken = ptoken
@scanner.skip(@skip)
end
@scanner = nil
yield [false,false]
end
# we've encountered an opening quote...
# slurp in the rest of the string and return it
def slurpstring(quote)
# we search for the next quote that isn't preceded by a
# backslash; the caret is there to match empty strings
str = @scanner.scan_until(/([^\\]|^)#{quote}/)
if str.nil?
raise Puppet::LexError.new("Unclosed quote after '%s' in '%s'" %
[self.last,self.rest])
else
str.sub!(/#{quote}\Z/,"")
str.gsub!(/\\#{quote}/,quote)
end
return str
end
# just parse a string, not a whole file
def string=(string)
@scanner = StringScanner.new(string)
end
end
#---------------------------------------------------------------
end
end
# $Id$
|