Class: Flay

Inherits:
Object
  • Object
show all
Defined in:
lib/flay.rb,
lib/flay_erb.rb

Constant Summary collapse

VERSION = 
'1.2.1'

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(option = nil) ⇒ Flay

Returns a new instance of Flay.



93
94
95
96
97
98
99
100
101
102
103
 
# File 'lib/flay.rb', line 93

def initialize option = nil
  @option = option || Flay.default_options
  @hashes = Hash.new { |h,k| h[k] = [] }

  self.identical      = {}
  self.masses         = {}
  self.total          = 0
  self.mass_threshold = @option[:mass]

  require 'ruby2ruby' if @option[:verbose]
end

Instance Attribute Details

#hashes ⇒ Object (readonly)

Returns the value of attribute hashes.



91
92
93
 
# File 'lib/flay.rb', line 91

def hashes
  @hashes
end

#identical ⇒ Object

Returns the value of attribute identical.



90
91
92
 
# File 'lib/flay.rb', line 90

def identical
  @identical
end

#mass_threshold ⇒ Object

Returns the value of attribute mass_threshold.



90
91
92
 
# File 'lib/flay.rb', line 90

def mass_threshold
  @mass_threshold
end

#masses ⇒ Object

Returns the value of attribute masses.



90
91
92
 
# File 'lib/flay.rb', line 90

def masses
  @masses
end

#option ⇒ Object (readonly)

Returns the value of attribute option.



91
92
93
 
# File 'lib/flay.rb', line 91

def option
  @option
end

#total ⇒ Object

Returns the value of attribute total.



90
91
92
 
# File 'lib/flay.rb', line 90

def total
  @total
end

Class Method Details

.default_options ⇒ Object 



16
17
18
19
20
21
22
 
# File 'lib/flay.rb', line 16

def self.default_options
  {
    :fuzzy   => false,
    :verbose => false,
    :mass    => 16,
  }
end

.expand_dirs_to_files(*dirs) ⇒ Object 



61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/flay.rb', line 61

def self.expand_dirs_to_files *dirs
  extensions = ['rb'] + Flay.load_plugins

  dirs.flatten.map { |p|
    if File.directory? p then
      Dir[File.join(p, '**', "*.{#{extensions.join(',')}}")]
    else
      p
    end
  }.flatten
end

.load_plugins ⇒ Object 



73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
 
# File 'lib/flay.rb', line 73

def self.load_plugins
  unless defined? @@plugins then
    plugins = Gem.find_files("flay_*.rb").reject { |p| p =~ /flay_task/ }

    plugins.each do |plugin|
      begin
        load plugin
      rescue LoadError => e
        warn "error loading #{plugin.inspect}: #{e.message}. skipping..."
      end
    end

    @@plugins = plugins.map { |f| File.basename(f, '.rb').sub(/^flay_/, '') }
  end
  @@plugins
end

.parse_options ⇒ Object 



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
 
# File 'lib/flay.rb', line 24

def self.parse_options
  options = self.default_options

  OptionParser.new do |opts|
    opts.banner  = 'flay [options] files_or_dirs'
    opts.version = Flay::VERSION

    opts.separator ""
    opts.separator "Specific options:"
    opts.separator ""

    opts.on('-h', '--help', 'Display this help.') do
      puts opts
      exit
    end

    opts.on('-f', '--fuzzy', "Attempt to do fuzzy similarities. (SLOW)") do
      options[:fuzzy] = true
    end

    opts.on('-m', '--mass MASS', Integer, "Sets mass threshold") do |m|
      options[:mass] = m.to_i
    end

    opts.on('-v', '--verbose', "Verbose. Display N-Way diff for ruby.") do
      options[:verbose] = true
    end

    extensions = ['rb'] + Flay.load_plugins

    opts.separator ""
    opts.separator "Known extensions: #{extensions.join(', ')}"
  end.parse!

  options
end

Instance Method Details

#analyze ⇒ Object 



136
137
138
139
140
141
142
143
144
145
 
# File 'lib/flay.rb', line 136

def analyze
  self.prune

  self.hashes.each do |hash,nodes|
    identical[hash] = nodes[1..-1].all? { |n| n == nodes.first }
    masses[hash] = nodes.first.mass * nodes.size
    masses[hash] *= (nodes.size) if identical[hash]
    self.total += masses[hash]
  end
end

#n_way_diff(*data) ⇒ Object 



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
 
# File 'lib/flay.rb', line 214

def n_way_diff *data
  data.each_with_index do |s, i|
    c = (?A + i).chr
    s.group = c
  end

  max = data.map { |s| s.scan(/^.*/).size }.max

  data.map! { |s| # FIX: this is tarded, but I'm out of brain
    c = s.group
    s = s.scan(/^.*/)
    s.push(*([""] * (max - s.size))) # pad
    s.each do |o|
      o.group = c
    end
    s
  }

  groups = data[0].zip(*data[1..-1])
  groups.map! { |lines|
    collapsed = lines.uniq
    if collapsed.size == 1 then
      "   #{lines.first}"
    else
      # TODO: make r2r have a canonical mode (doesn't make 1-liners)
      lines.reject { |l| l.empty? }.map { |l| "#{l.group}: #{l}" }
    end
  }
  groups.flatten.join("\n")
end

#process(*files) ⇒ Object

TODO: rename from process - should act as SexpProcessor



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
 
# File 'lib/flay.rb', line 105

def process(*files) # TODO: rename from process - should act as SexpProcessor
  files.each do |file|
    warn "Processing #{file}"

    ext = File.extname(file).sub(/^\./, '')
    ext = "rb" if ext.nil? || ext.empty?
    msg = "process_#{ext}"

    unless respond_to? msg then
      warn "  Unknown file type: #{ext}, defaulting to ruby"
      msg = "process_rb"
    end

    sexp = begin
             send msg, file
           rescue => e
             warn "  #{e.message.strip}"
             warn "  skipping #{file}"
             nil
           end

    next unless sexp

    process_sexp sexp
  end

  process_fuzzy_similarities if option[:fuzzy]

  analyze
end

#process_erb(file) ⇒ Object 



8
9
10
11
12
13
 
# File 'lib/flay_erb.rb', line 8

def process_erb file
  erb = File.read file

  src = ERB.new(erb).src
  RubyParser.new.process(src, file)
end

#process_fuzzy_similarities ⇒ Object 



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
 
# File 'lib/flay.rb', line 160

def process_fuzzy_similarities
  all_hashes, detected = {}, {}

  self.hashes.values.each do |nodes|
    nodes.each do |node|
      next if node.mass > 4 * self.mass_threshold
      # TODO: try out with fuzzy_hash
      # all_hashes[node] = node.grep(Sexp).map { |s| [s.hash] * s.mass }.flatten
      all_hashes[node] = node.grep(Sexp).map { |s| [s.hash] }.flatten
    end
  end

  # warn "looking for copy/paste/edit code across #{all_hashes.size} nodes"

  all_hashes = all_hashes.to_a
  all_hashes.each_with_index do |(s1, h1), i|
    similar = [s1]
    all_hashes[i+1..-1].each do |(s2, h2)|
      next if detected[h2]
      intersection = h1.intersection h2
      max = [h1.size, h2.size].max
      if intersection.size >= max * 0.60 then
        similarity = s1.similarity(s2)
        if similarity > 0.60 then
          similar << s2
          detected[h2] = true
        else
          p [similarity, s1, s2]
        end
      end
    end

    self.hashes[similar.first.hash].push(*similar) if similar.size > 1
  end
end

#process_rb(file) ⇒ Object 



147
148
149
 
# File 'lib/flay.rb', line 147

def process_rb file
  RubyParser.new.process(File.read(file), file)
end

#process_sexp(pt) ⇒ Object 



151
152
153
154
155
156
157
158
 
# File 'lib/flay.rb', line 151

def process_sexp pt
  pt.deep_each do |node|
    next unless node.any? { |sub| Sexp === sub }
    next if node.mass < self.mass_threshold

    self.hashes[node.fuzzy_hash] << node
  end
end

#prune ⇒ Object 



196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
 
# File 'lib/flay.rb', line 196

def prune
  # prune trees that aren't duped at all, or are too small
  self.hashes.delete_if { |_,nodes| nodes.size == 1 }

  # extract all subtree hashes from all nodes
  all_hashes = {}
  self.hashes.values.each do |nodes|
    nodes.each do |node|
      node.all_subhashes.each do |h|
        all_hashes[h] = true
      end
    end
  end

  # nuke subtrees so we show the biggest matching tree possible
  self.hashes.delete_if { |h,_| all_hashes[h] }
end

#report(prune = nil) ⇒ Object 



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
 
# File 'lib/flay.rb', line 245

def report prune = nil
  puts "Total score (lower is better) = #{self.total}"
  puts

  count = 0
  masses.sort_by { |h,m| [-m, hashes[h].first.file] }.each do |hash, mass|
    nodes = hashes[hash]
    next unless nodes.first.first == prune if prune
    puts

    same = identical[hash]
    node = nodes.first
    n = nodes.size
    match, bonus = if same then
                     ["IDENTICAL", "*#{n}"]
                   else
                     ["Similar",   ""]
                   end

    count += 1
    puts "%d) %s code found in %p (mass%s = %d)" %
      [count, match, node.first, bonus, mass]

    nodes.each_with_index do |node, i|
      if option[:verbose] then
        c = (?A + i).chr
        puts "  #{c}: #{node.file}:#{node.line}"
      else
        puts "  #{node.file}:#{node.line}"
      end
    end

    if option[:verbose] then
      puts
      r2r = Ruby2Ruby.new
      puts n_way_diff(*nodes.map { |s| r2r.process(s.deep_clone) })
    end
  end
end