parser 0.9.alpha → 0.9.alpha1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +21 -0
- data/.travis.yml +9 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +25 -0
- data/README.md +29 -0
- data/Rakefile +15 -182
- data/lib/parser.rb +4 -0
- data/lib/parser/lexer.rl +1713 -0
- data/lib/parser/lexer_literal.rb +175 -0
- data/lib/parser/static_environment.rb +38 -0
- data/lib/parser/syntax_error.rb +3 -0
- data/parser.gemspec +25 -0
- data/test/{test_ruby_lexer.rb → test_lexer.rb} +77 -129
- data/test/test_static_environment.rb +46 -0
- metadata +39 -98
- data/.autotest +0 -50
- data/.gemtest +0 -0
- data/History.txt +0 -558
- data/Manifest.txt +0 -18
- data/README.txt +0 -87
- data/bin/ruby_parse +0 -96
- data/bin/ruby_parse_extract_error +0 -130
- data/lib/gauntlet_rubyparser.rb +0 -117
- data/lib/ruby18_parser.rb +0 -5706
- data/lib/ruby18_parser.y +0 -1846
- data/lib/ruby19_parser.rb +0 -6054
- data/lib/ruby19_parser.y +0 -2035
- data/lib/ruby_lexer.rb +0 -6789
- data/lib/ruby_parser.rb +0 -4
- data/lib/ruby_parser_extras.rb +0 -1148
- data/test/test_ruby_parser.rb +0 -1772
- data/test/test_ruby_parser_extras.rb +0 -228
data/Manifest.txt
DELETED
@@ -1,18 +0,0 @@
|
|
1
|
-
.autotest
|
2
|
-
History.txt
|
3
|
-
Manifest.txt
|
4
|
-
README.txt
|
5
|
-
Rakefile
|
6
|
-
bin/ruby_parse
|
7
|
-
bin/ruby_parse_extract_error
|
8
|
-
lib/gauntlet_rubyparser.rb
|
9
|
-
lib/ruby18_parser.rb
|
10
|
-
lib/ruby18_parser.y
|
11
|
-
lib/ruby19_parser.rb
|
12
|
-
lib/ruby19_parser.y
|
13
|
-
lib/ruby_lexer.rb
|
14
|
-
lib/ruby_parser.rb
|
15
|
-
lib/ruby_parser_extras.rb
|
16
|
-
test/test_ruby_lexer.rb
|
17
|
-
test/test_ruby_parser.rb
|
18
|
-
test/test_ruby_parser_extras.rb
|
data/README.txt
DELETED
@@ -1,87 +0,0 @@
|
|
1
|
-
= ruby_parser
|
2
|
-
|
3
|
-
home :: https://github.com/seattlerb/ruby_parser
|
4
|
-
bugs :: https://github.com/seattlerb/ruby_parser/issues
|
5
|
-
rdoc :: http://docs.seattlerb.org/ruby_parser
|
6
|
-
|
7
|
-
== DESCRIPTION:
|
8
|
-
|
9
|
-
ruby_parser (RP) is a ruby parser written in pure ruby (utilizing
|
10
|
-
racc--which does by default use a C extension). RP's output is
|
11
|
-
the same as ParseTree's output: s-expressions using ruby's arrays and
|
12
|
-
base types.
|
13
|
-
|
14
|
-
As an example:
|
15
|
-
|
16
|
-
def conditional1 arg1
|
17
|
-
return 1 if arg1 == 0
|
18
|
-
return 0
|
19
|
-
end
|
20
|
-
|
21
|
-
becomes:
|
22
|
-
|
23
|
-
s(:defn, :conditional1, s(:args, :arg1),
|
24
|
-
s(:if,
|
25
|
-
s(:call, s(:lvar, :arg1), :==, s(:lit, 0)),
|
26
|
-
s(:return, s(:lit, 1)),
|
27
|
-
nil),
|
28
|
-
s(:return, s(:lit, 0)))
|
29
|
-
|
30
|
-
== FEATURES/PROBLEMS:
|
31
|
-
|
32
|
-
* Pure ruby, no compiles.
|
33
|
-
* Includes preceding comment data for defn/defs/class/module nodes!
|
34
|
-
* Incredibly simple interface.
|
35
|
-
* Output is 100% equivalent to ParseTree.
|
36
|
-
* Can utilize PT's SexpProcessor and UnifiedRuby for language processing.
|
37
|
-
* Known Issue: Speed is now pretty good, but can always improve:
|
38
|
-
* RP parses a corpus of 3702 files in 125s (avg 108 Kb/s)
|
39
|
-
* MRI+PT parsed the same in 67.38s (avg 200.89 Kb/s)
|
40
|
-
* Known Issue: Code is much better, but still has a long way to go.
|
41
|
-
* Known Issue: Totally awesome.
|
42
|
-
* Known Issue: line number values can be slightly off. Parsing LR sucks.
|
43
|
-
|
44
|
-
== SYNOPSIS:
|
45
|
-
|
46
|
-
RubyParser.new.parse "1+1"
|
47
|
-
# => s(:call, s(:lit, 1), :+, s(:lit, 1))
|
48
|
-
|
49
|
-
You can also use Ruby19Parser, Ruby18Parser, or RubyParser.for_current_ruby:
|
50
|
-
|
51
|
-
RubyParser.for_current_ruby.parse "1+1"
|
52
|
-
# => s(:call, s(:lit, 1), :+, s(:lit, 1))
|
53
|
-
|
54
|
-
== REQUIREMENTS:
|
55
|
-
|
56
|
-
* ruby. woot.
|
57
|
-
* sexp_processor for Sexp and SexpProcessor classes, and testing.
|
58
|
-
* racc full package for parser development (compiling .y to .rb).
|
59
|
-
|
60
|
-
== INSTALL:
|
61
|
-
|
62
|
-
* sudo gem install ruby_parser
|
63
|
-
|
64
|
-
== LICENSE:
|
65
|
-
|
66
|
-
(The MIT License)
|
67
|
-
|
68
|
-
Copyright (c) Ryan Davis, seattle.rb
|
69
|
-
|
70
|
-
Permission is hereby granted, free of charge, to any person obtaining
|
71
|
-
a copy of this software and associated documentation files (the
|
72
|
-
'Software'), to deal in the Software without restriction, including
|
73
|
-
without limitation the rights to use, copy, modify, merge, publish,
|
74
|
-
distribute, sublicense, and/or sell copies of the Software, and to
|
75
|
-
permit persons to whom the Software is furnished to do so, subject to
|
76
|
-
the following conditions:
|
77
|
-
|
78
|
-
The above copyright notice and this permission notice shall be
|
79
|
-
included in all copies or substantial portions of the Software.
|
80
|
-
|
81
|
-
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
82
|
-
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
83
|
-
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
84
|
-
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
85
|
-
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
86
|
-
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
87
|
-
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/bin/ruby_parse
DELETED
@@ -1,96 +0,0 @@
|
|
1
|
-
#!/usr/bin/ruby -s
|
2
|
-
|
3
|
-
$q ||= false
|
4
|
-
$g ||= false
|
5
|
-
|
6
|
-
require 'rubygems'
|
7
|
-
require 'ruby_parser'
|
8
|
-
require 'pp'
|
9
|
-
|
10
|
-
good = bad = 0
|
11
|
-
|
12
|
-
multi = ARGV.size != 1
|
13
|
-
total_time = 0
|
14
|
-
total_loc = 0
|
15
|
-
total_kbytes = 0
|
16
|
-
times = {}
|
17
|
-
locs = {}
|
18
|
-
kbytes = {}
|
19
|
-
|
20
|
-
class File
|
21
|
-
RUBY19 = "<3".respond_to? :encoding
|
22
|
-
|
23
|
-
class << self
|
24
|
-
alias :binread :read unless RUBY19
|
25
|
-
end
|
26
|
-
end
|
27
|
-
|
28
|
-
begin
|
29
|
-
ARGV.each do |file|
|
30
|
-
rp = RubyParser.new
|
31
|
-
loc = `wc -l #{file}`.strip.to_i
|
32
|
-
size = `wc -c #{file}`.strip.to_i / 1024.0
|
33
|
-
locs[file] = loc
|
34
|
-
kbytes[file] = size
|
35
|
-
total_loc += loc
|
36
|
-
total_kbytes += size
|
37
|
-
if $q then
|
38
|
-
$stderr.print "."
|
39
|
-
else
|
40
|
-
warn "# file = #{file} loc = #{loc}"
|
41
|
-
end
|
42
|
-
GC.start if $g
|
43
|
-
|
44
|
-
t = Time.now
|
45
|
-
begin
|
46
|
-
begin
|
47
|
-
rp.reset
|
48
|
-
r = rp.parse(File.binread(file), file)
|
49
|
-
pp r unless $q
|
50
|
-
good += 1
|
51
|
-
rescue SyntaxError => e
|
52
|
-
warn "SyntaxError for #{file}: #{e.message}"
|
53
|
-
bad += 1
|
54
|
-
end
|
55
|
-
rescue => e
|
56
|
-
warn "#{e.backtrace.first} #{e.inspect.gsub(/\n/, ' ')} for #{file}"
|
57
|
-
warn " #{e.backtrace.join("\n ")}"
|
58
|
-
bad += 1
|
59
|
-
end
|
60
|
-
|
61
|
-
t = Time.now - t
|
62
|
-
times[file] = t
|
63
|
-
total_time += t
|
64
|
-
end
|
65
|
-
rescue Interrupt
|
66
|
-
# do nothing
|
67
|
-
end
|
68
|
-
|
69
|
-
warn "done"
|
70
|
-
|
71
|
-
total = 0
|
72
|
-
times.values.each do |t|
|
73
|
-
total += t
|
74
|
-
end
|
75
|
-
|
76
|
-
puts
|
77
|
-
puts "good = #{good} bad = #{bad}" if multi
|
78
|
-
puts
|
79
|
-
|
80
|
-
format = "%5.2fs:%9.2f l/s:%8.2f Kb/s:%5d Kb:%5d loc:%s"
|
81
|
-
|
82
|
-
times.sort_by { |f, t| -t }.each do |f, t|
|
83
|
-
next if t < 0.005
|
84
|
-
loc = locs[f]
|
85
|
-
size = kbytes[f]
|
86
|
-
puts format % [t, loc / t, size / t, size, loc, f]
|
87
|
-
end
|
88
|
-
|
89
|
-
puts
|
90
|
-
|
91
|
-
puts format % [total_time,
|
92
|
-
total_loc / total_time,
|
93
|
-
total_kbytes / total_time,
|
94
|
-
total_kbytes,
|
95
|
-
total_loc,
|
96
|
-
"TOTAL"] unless total_time == 0
|
@@ -1,130 +0,0 @@
|
|
1
|
-
#!/usr/bin/ruby -ws
|
2
|
-
|
3
|
-
$d ||= false
|
4
|
-
$d ||= ENV["DELETE"]
|
5
|
-
$t ||= false
|
6
|
-
$t ||= ENV["DELETE_TIMEOUT"]
|
7
|
-
$m ||= false
|
8
|
-
$m ||= ENV["MOVE_TIMEOUT"]
|
9
|
-
$q ||= false
|
10
|
-
$q ||= ENV["QUIET"]
|
11
|
-
|
12
|
-
require 'rubygems'
|
13
|
-
require 'ruby_parser'
|
14
|
-
require 'fileutils'
|
15
|
-
|
16
|
-
ARGV.push "-" if ARGV.empty?
|
17
|
-
|
18
|
-
class Racc::Parser
|
19
|
-
def extract_defs
|
20
|
-
ss = lexer.src
|
21
|
-
|
22
|
-
raise "can't access source. possible encoding issue" unless ss
|
23
|
-
|
24
|
-
src = ss.string
|
25
|
-
pre_error = src[0...ss.pos]
|
26
|
-
|
27
|
-
defs = pre_error.grep(/^ *(?:def|it)/)
|
28
|
-
|
29
|
-
raise "can't figure out where the bad code starts" unless defs.last
|
30
|
-
|
31
|
-
last_def_indent = defs.last[/^ */]
|
32
|
-
|
33
|
-
post_error = src[ss.pos..-1]
|
34
|
-
idx = post_error =~ /^#{last_def_indent}end.*/
|
35
|
-
|
36
|
-
raise "can't figure out where the bad code ends" unless idx
|
37
|
-
|
38
|
-
src = pre_error + post_error[0..idx+$&.length]
|
39
|
-
|
40
|
-
src.scan(/^(( *)(?:def|it) .*?^\2end)/m)
|
41
|
-
end
|
42
|
-
|
43
|
-
def retest_for_errors defs
|
44
|
-
parser = self.class.new
|
45
|
-
|
46
|
-
parser.process(defs.join("\n\n"))
|
47
|
-
rescue SyntaxError, StandardError
|
48
|
-
nil
|
49
|
-
end
|
50
|
-
end
|
51
|
-
|
52
|
-
def expand path
|
53
|
-
if File.directory? path then
|
54
|
-
require 'find'
|
55
|
-
|
56
|
-
files = []
|
57
|
-
|
58
|
-
Find.find(*Dir[path]) do |f|
|
59
|
-
files << f if File.file? f
|
60
|
-
end
|
61
|
-
|
62
|
-
files.sort
|
63
|
-
else
|
64
|
-
Dir.glob path
|
65
|
-
end
|
66
|
-
end
|
67
|
-
|
68
|
-
def process_error parser
|
69
|
-
defs = parser.extract_defs
|
70
|
-
|
71
|
-
if parser.retest_for_errors defs then
|
72
|
-
warn "Can't reproduce error with just methods, punting..."
|
73
|
-
return
|
74
|
-
end
|
75
|
-
|
76
|
-
catch :extract_done do
|
77
|
-
(1..defs.size).each do |perm_size|
|
78
|
-
defs.combination(perm_size).each do |trial|
|
79
|
-
unless parser.retest_for_errors trial then
|
80
|
-
puts trial.join "\n"
|
81
|
-
throw :extract_done
|
82
|
-
end
|
83
|
-
end
|
84
|
-
end
|
85
|
-
end
|
86
|
-
rescue RuntimeError, Racc::ParseError => e
|
87
|
-
warn "# process error: #{e.message.strip}"
|
88
|
-
end
|
89
|
-
|
90
|
-
def process file
|
91
|
-
ruby = file == "-" ? $stdin.read : File.read(file)
|
92
|
-
time = (ENV["RP_TIMEOUT"] || 10).to_i
|
93
|
-
|
94
|
-
$stderr.print "# Validating #{file}: "
|
95
|
-
parser = Ruby19Parser.new
|
96
|
-
parser.process(ruby, file, time)
|
97
|
-
warn "good"
|
98
|
-
File.unlink file if $d
|
99
|
-
rescue Timeout::Error
|
100
|
-
$exit = 1
|
101
|
-
warn "TIMEOUT parsing #{file}. Skipping."
|
102
|
-
|
103
|
-
if $m then
|
104
|
-
dir = File.join $m, File.dirname(file)
|
105
|
-
FileUtils.mkdir_p dir
|
106
|
-
FileUtils.move file, dir
|
107
|
-
elsif $t then
|
108
|
-
File.unlink file
|
109
|
-
end
|
110
|
-
rescue StandardError, SyntaxError, Racc::ParseError => e
|
111
|
-
$exit = 1
|
112
|
-
warn ""
|
113
|
-
warn "# error: #{e.message.strip}" unless $q
|
114
|
-
warn ""
|
115
|
-
return if $q
|
116
|
-
|
117
|
-
process_error parser
|
118
|
-
end
|
119
|
-
|
120
|
-
$exit = 0
|
121
|
-
$stdout.sync = true
|
122
|
-
|
123
|
-
ARGV.each do |path|
|
124
|
-
expand(path).each do |file|
|
125
|
-
next unless File.file? file # omg... why would you name a dir support.rb?
|
126
|
-
process file
|
127
|
-
end
|
128
|
-
end
|
129
|
-
|
130
|
-
exit $exit
|
data/lib/gauntlet_rubyparser.rb
DELETED
@@ -1,117 +0,0 @@
|
|
1
|
-
#!/usr/bin/ruby -ws
|
2
|
-
|
3
|
-
$f ||= false
|
4
|
-
|
5
|
-
$:.unshift "../../ruby_parser/dev/lib"
|
6
|
-
$:.unshift "../../ruby2ruby/dev/lib"
|
7
|
-
|
8
|
-
require 'rubygems'
|
9
|
-
require 'ruby2ruby'
|
10
|
-
require 'ruby_parser'
|
11
|
-
|
12
|
-
require 'gauntlet'
|
13
|
-
|
14
|
-
class RubyParserGauntlet < Gauntlet
|
15
|
-
def initialize
|
16
|
-
super
|
17
|
-
|
18
|
-
self.data = Hash.new { |h,k| h[k] = {} }
|
19
|
-
old_data = load_yaml data_file
|
20
|
-
self.data.merge! old_data
|
21
|
-
end
|
22
|
-
|
23
|
-
def should_skip? name
|
24
|
-
if $f then
|
25
|
-
if Hash === data[name] then
|
26
|
-
! data[name].empty?
|
27
|
-
else
|
28
|
-
data[name]
|
29
|
-
end
|
30
|
-
else
|
31
|
-
data[name] == true # yes, == true on purpose
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
def diff_pp o1, o2
|
36
|
-
require 'pp'
|
37
|
-
|
38
|
-
Tempfile.new('ruby_parser_a') do |file_a|
|
39
|
-
PP.pp o1, file_a
|
40
|
-
|
41
|
-
Tempfile.new('ruby_parser_b') do |file_b|
|
42
|
-
PP.pp o2, file_b
|
43
|
-
|
44
|
-
`diff -u #{file_a.path} #{file_b.path}`
|
45
|
-
end
|
46
|
-
end
|
47
|
-
end
|
48
|
-
|
49
|
-
def broke name, file, msg
|
50
|
-
warn "bad"
|
51
|
-
self.data[name][file] = msg
|
52
|
-
self.dirty = true
|
53
|
-
end
|
54
|
-
|
55
|
-
def process path, name
|
56
|
-
begin
|
57
|
-
$stderr.print " #{path}: "
|
58
|
-
rp = RubyParser.new
|
59
|
-
r2r = Ruby2Ruby.new
|
60
|
-
|
61
|
-
old_ruby = File.read(path)
|
62
|
-
|
63
|
-
begin
|
64
|
-
old_sexp = rp.process old_ruby
|
65
|
-
rescue Racc::ParseError => e
|
66
|
-
self.data[name][path] = :unparsable
|
67
|
-
self.dirty = true
|
68
|
-
return
|
69
|
-
end
|
70
|
-
|
71
|
-
new_ruby = r2r.process old_sexp.deep_clone
|
72
|
-
|
73
|
-
begin
|
74
|
-
new_sexp = rp.process new_ruby
|
75
|
-
rescue Racc::ParseError => e
|
76
|
-
broke name, path, "couldn't parse new_ruby: #{e.message.strip}"
|
77
|
-
return
|
78
|
-
end
|
79
|
-
|
80
|
-
if old_sexp != new_sexp then
|
81
|
-
broke name, path, diff_pp(old_sexp, new_sexp)
|
82
|
-
return
|
83
|
-
end
|
84
|
-
|
85
|
-
self.data[name][path] = true
|
86
|
-
self.dirty = true
|
87
|
-
|
88
|
-
warn "good"
|
89
|
-
rescue Interrupt
|
90
|
-
puts "User cancelled"
|
91
|
-
exit 1
|
92
|
-
rescue Exception => e
|
93
|
-
broke name, path, " UNKNOWN ERROR: #{e}: #{e.message.strip}"
|
94
|
-
end
|
95
|
-
end
|
96
|
-
|
97
|
-
def run name
|
98
|
-
warn name
|
99
|
-
Dir["**/*.rb"].sort.each do |path|
|
100
|
-
next if path =~ /gemspec.rb/ # HACK
|
101
|
-
next if data[name][path] == true
|
102
|
-
process path, name
|
103
|
-
end
|
104
|
-
|
105
|
-
if self.data[name].values.all? { |v| v == true } then
|
106
|
-
warn " ALL GOOD!"
|
107
|
-
self.data[name] = true
|
108
|
-
self.dirty = true
|
109
|
-
end
|
110
|
-
end
|
111
|
-
end
|
112
|
-
|
113
|
-
filter = ARGV.shift
|
114
|
-
filter = Regexp.new filter if filter
|
115
|
-
|
116
|
-
gauntlet = RubyParserGauntlet.new
|
117
|
-
gauntlet.run_the_gauntlet filter
|