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
|
#!/usr/bin/ruby
=begin
parser/ruby.rb - parser for ruby script
Copyright (C) 2003-2005 Masao Mutoh
Copyright (C) 2005 speakillof
Copyright (C) 2001,2002 Yasushi Shoji, Masao Mutoh
You may redistribute it and/or modify it under the same
license terms as Ruby.
$Id: ruby.rb,v 1.7 2006/06/11 15:36:20 mutoh Exp $
=end
require 'irb/ruby-lex.rb'
require 'stringio'
class RubyLexX < RubyLex # :nodoc: all
def initialize
super
@prompt = nil
@here_header = nil
@lex_state = nil
end
def read_escape
case ch = getc
when "\n", "\r", "\f"
when "\\", "n", "t", "r", "f", "v", "a", "e", "b" #"
return "\\".concat(ch)
when /[0-7]/
ungetc ch
3.times do
case ch = getc
when /[0-7]/
when nil
break
else
ungetc
break
end
end
when "x"
2.times do
case ch = getc
when /[0-9a-fA-F]/
when nil
break
else
ungetc
break
end
end
when "M"
if (ch = getc) != '-'
ungetc
else
if (ch = getc) == "\\" #"
read_escape
end
end
when "C", "c", "^"
if ch == "C" and (ch = getc) != "-"
ungetc
elsif (ch = getc) == "\\" #"
read_escape
end
when '#'
return ch
else
# other characters
end
end
# Parser#parse resemlbes RubyLex#lex
def parse
until ( (tk = token).kind_of?(RubyToken::TkEND_OF_SCRIPT) && !@continue or tk.nil? )
s = get_readed
if RubyToken::TkSTRING === tk
def tk.value
@value
end
def tk.value=(s)
@value = s
end
if @here_header
s = s.sub(/\A.*?\n/, '').sub(/^.*\n\Z/, '')
else
begin
s = eval(s)
rescue Exception
# Do nothing.
end
end
tk.value = s
end
if $DEBUG
if tk.is_a? TkSTRING
$stderr.puts("#{tk}: #{tk.value}")
elsif tk.is_a? TkIDENTIFIER
$stderr.puts("#{tk}: #{tk.name}")
else
$stderr.puts(tk)
end
end
yield tk
end
return nil
end
end
module GetText
module RubyParser
ID = ['gettext', '_', 'N_', 'sgettext', 's_']
PLURAL_ID = ['ngettext', 'n_', 'Nn_']
module_function
def parse(file, targets = []) # :nodoc:
lines = IO.readlines(file)
parse_lines(file, lines, targets)
end
def parse_lines(file_name, lines, targets) # :nodoc:
file = StringIO.new(lines.join + "\n")
rl = RubyLexX.new
rl.set_input(file)
rl.skip_space = true
#rl.readed_auto_clean_up = true
target = nil
msgid = nil
line_no = nil
rl.parse do |tk|
case tk
when RubyToken::TkIDENTIFIER, RubyToken::TkCONSTANT
if ID.include?(tk.name)
target = :normal
elsif PLURAL_ID.include?(tk.name)
target = :plural
else
target = nil
end
line_no = tk.line_no.to_s
when RubyToken::TkSTRING
if target
if msgid
msgid += tk.value
else
msgid = tk.value
end
end
when RubyToken::TkPLUS, RubyToken::TkNL
#do nothing
when RubyToken::TkCOMMA
if msgid and target == :plural
msgid += "\000"
target = :normal
end
else
if msgid
key_existed = targets.assoc(msgid.gsub(/\n/, '\n'))
if key_existed
targets[targets.index(key_existed)] = key_existed <<
file_name + ":" + line_no
else
targets << [msgid.gsub(/\n/, '\n'), file_name + ":" + line_no]
end
msgid = nil
target = nil
end
end
targets
end
targets
end
def target?(file) # :nodoc:
true # always true, as default parser.
end
end
end
if __FILE__ == $0
require 'pp'
ARGV.each do |file|
pp GetText::RubyParser.parse(file)
end
#rl = RubyLexX.new; rl.set_input(ARGF)
#rl.parse do |tk|
#p tk
#end
end
|
