Class: Flay

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

Constant Summary collapse

VERSION = 
'2.1.0'

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(option = nil) ⇒ Flay

Returns a new instance of Flay.



129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/flay.rb', line 129

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[:diff]
end

Instance Attribute Details

#hashes ⇒ Object (readonly)

Returns the value of attribute hashes.



127
128
129
 
# File 'lib/flay.rb', line 127

def hashes
  @hashes
end

#identical ⇒ Object

Returns the value of attribute identical.



126
127
128
 
# File 'lib/flay.rb', line 126

def identical
  @identical
end

#mass_threshold ⇒ Object

Returns the value of attribute mass_threshold.



126
127
128
 
# File 'lib/flay.rb', line 126

def mass_threshold
  @mass_threshold
end

#masses ⇒ Object

Returns the value of attribute masses.



126
127
128
 
# File 'lib/flay.rb', line 126

def masses
  @masses
end

#option ⇒ Object (readonly)

Returns the value of attribute option.



127
128
129
 
# File 'lib/flay.rb', line 127

def option
  @option
end

#total ⇒ Object

Returns the value of attribute total.



126
127
128
 
# File 'lib/flay.rb', line 126

def total
  @total
end

Class Method Details

.default_options ⇒ Object 



20
21
22
23
24
25
26
27
28
 
# File 'lib/flay.rb', line 20

def self.default_options
  {
    :diff    => false,
    :mass    => 16,
    :summary => false,
    :verbose => false,
    :timeout => 10,
  }
end

.expand_dirs_to_files(*dirs) ⇒ Object 



92
93
94
95
96
97
98
99
100
101
102
 
# File 'lib/flay.rb', line 92

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 



104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
 
# File 'lib/flay.rb', line 104

def self.load_plugins
  unless defined? @@plugins then
    @@plugins = []

    plugins = Gem.find_files("flay_*.rb").reject { |p| p =~ /flay_task/ }

    plugins.each do |plugin|
      plugin_name = File.basename(plugin, '.rb').sub(/^flay_/, '')
      next if @@plugins.include? plugin_name
      begin
        load plugin
        @@plugins << plugin_name
      rescue LoadError => e
        warn "error loading #{plugin.inspect}: #{e.message}. skipping..."
      end
    end
  end
  @@plugins
rescue
  # ignore
end

.parse_options(args = ARGV) ⇒ Object 



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
 
# File 'lib/flay.rb', line 30

def self.parse_options args = ARGV
  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', "DEAD: fuzzy similarities.") do
      abort "--fuzzy is no longer supported. Sorry. It sucked."
    end

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

    opts.on('-v', '--verbose', "Verbose. Show progress processing files.") do
      options[:verbose] = true
    end

    opts.on('-d', '--diff', "Diff Mode. Display N-Way diff for ruby.") do
      options[:diff] = true
    end

    opts.on('-s', '--summary', "Summarize. Show flay score per file only.") do
      options[:summary] = true
    end

    opts.on('-t', '--timeout TIME', Integer,
            "Set the timeout. (default = #{options[:timeout]})") do |t|
      options[:timeout] = t.to_i
    end

    extensions = ['rb'] + Flay.load_plugins

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

    extensions.each do |meth|
      msg = "options_#{meth}"
      send msg, opts, options if self.respond_to?(msg)
    end

    begin
      opts.parse! args
    rescue => e
      abort "#{e}\n\n#{opts}"
    end
  end

  options
end

Instance Method Details

#analyze ⇒ Object 



172
173
174
175
176
177
178
179
180
181
 
# File 'lib/flay.rb', line 172

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 



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
 
# File 'lib/flay.rb', line 218

def n_way_diff *data
  data.each_with_index do |s, i|
    c = (?A.ord + 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



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
 
# File 'lib/flay.rb', line 141

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

    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

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

      next unless sexp

      process_sexp sexp
    rescue SyntaxError => e
      warn "  skipping #{file}: #{e.message}"
    end
  end
end

#process_erb(file) ⇒ Object 



8
9
10
11
12
13
14
15
16
17
18
 
# File 'lib/flay_erb.rb', line 8

def process_erb file
  erb = File.read file

  ruby = ERB.new(erb).src
  begin
    RubyParser.new.process(ruby, file)
  rescue => e
    warn ruby if option[:verbose]
    raise e
  end
end

#process_rb(file) ⇒ Object 



183
184
185
186
187
188
189
 
# File 'lib/flay.rb', line 183

def process_rb file
  begin
    RubyParser.new.process(File.binread(file), file, option[:timeout])
  rescue Timeout::Error
    warn "TIMEOUT parsing #{file}. Skipping."
  end
end

#process_sexp(pt) ⇒ Object 



191
192
193
194
195
196
197
198
 
# File 'lib/flay.rb', line 191

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.structural_hash] << node
  end
end

#prune ⇒ Object 



200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
 
# File 'lib/flay.rb', line 200

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_structural_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 



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
 
# File 'lib/flay.rb', line 263

def report prune = nil
  analyze

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

  if option[:summary] then

    self.summary.sort_by { |_,v| -v }.each do |file, score|
      puts "%8.2f: %s" % [score, file]
    end

    return
  end

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

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

#summary ⇒ Object 



249
250
251
252
253
254
255
256
257
258
259
260
261
 
# File 'lib/flay.rb', line 249

def summary
  score = Hash.new 0

  masses.each do |hash, mass|
    sexps = hashes[hash]
    mass_per_file = mass.to_f / sexps.size
    sexps.each do |sexp|
      score[sexp.file] += mass_per_file
    end
  end

  score
end