Module: Tina4::Metrics

Defined in:
lib/tina4/metrics.rb

Constant Summary collapse

CACHE_TTL = 
60
SEVERITY_RANK =

Severity ranking for sorting (higher = more severe).

{ "error" => 2, "warn" => 1, "info" => 0 }.freeze
OPERATOR_TYPES = 
%i[
  on_op
].freeze
OPERAND_TYPES = 
%i[
  on_ident on_int on_float on_tstring_content
  on_const on_symbeg on_rational on_imaginary
].freeze

Class Method Summary collapse

Class Method Details

._count_halstead(tokens) ⇒ Object 



869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
 
# File 'lib/tina4/metrics.rb', line 869

def self._count_halstead(tokens)
  stats = {
    operators: 0,
    operands: 0,
    unique_operators: Set.new,
    unique_operands: Set.new
  }

  # Need Set
  require 'set' unless defined?(Set)

  stats[:unique_operators] = Set.new
  stats[:unique_operands] = Set.new

  tokens.each do |(_pos, type, token)|
    case type
    when :on_op
      stats[:operators] += 1
      stats[:unique_operators].add(token)
    when :on_kw
      # Keywords that act as operators
      if %w[and or not defined? return yield raise].include?(token)
        stats[:operators] += 1
        stats[:unique_operators].add(token)
      end
    when :on_ident, :on_const
      stats[:operands] += 1
      stats[:unique_operands].add(token)
    when :on_int, :on_float, :on_rational, :on_imaginary
      stats[:operands] += 1
      stats[:unique_operands].add(token)
    when :on_tstring_content
      stats[:operands] += 1
      stats[:unique_operands].add(token[0, 50])
    end
  end

  stats
end

._cyclomatic_complexity_from_source(source) ⇒ Object 



819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
 
# File 'lib/tina4/metrics.rb', line 819

def self._cyclomatic_complexity_from_source(source)
  cc = 1

  # Use Ripper tokens for accurate counting
  tokens = begin
    Ripper.lex(source)
  rescue StandardError
    return cc
  end

  tokens.each do |(_pos, type, token)|
    case type
    when :on_kw
      case token
      when 'if', 'elsif', 'unless', 'when', 'while', 'until', 'for', 'rescue'
        # Skip modifier forms by checking if it's the first keyword on the line
        # For simplicity, count all — modifiers still add a decision path
        cc += 1
      end
    when :on_op
      case token
      when '&&', '||'
        cc += 1
      when '?'
        # Ternary operator
        cc += 1
      end
    when :on_ident
      # 'and' and 'or' are parsed as identifiers in some contexts
      # but usually as keywords
    end

    # Check for 'and'/'or' as keywords
    if type == :on_kw && (token == 'and' || token == 'or')
      cc += 1
    end
  end

  cc
end

._defined_constants(rel_path) ⇒ Object

Top-level class/module names defined in the file at rel_path (resolved against the last scan root when present). Distinctive names only: leading-uppercase, longer than 3 chars.



653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
 
# File 'lib/tina4/metrics.rb', line 653

def self._defined_constants(rel_path)
  src_file = if @last_scan_root && !@last_scan_root.empty? && !File.exist?(rel_path)
               File.join(@last_scan_root, rel_path)
             else
               rel_path
             end
  symbols = Set.new
  content = begin
    File.read(src_file, encoding: 'utf-8')
  rescue StandardError
    return symbols
  end
  content.each_line do |line|
    stripped = line.strip
    m = stripped.match(/\A(?:class|module)\s+([A-Z][A-Za-z0-9_]*)/)
    next unless m
    const = m[1]
    symbols.add(const) if const.length > 3
  end
  symbols
end

._detect_violations(functions, file_metrics) ⇒ Object 



917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
 
# File 'lib/tina4/metrics.rb', line 917

def self._detect_violations(functions, file_metrics)
  violations = []

  functions.each do |f|
    if f["complexity"] > 20
      violations << {
        "type" => "error",
        "rule" => "high_complexity",
        "message" => "#{f['name']} has cyclomatic complexity #{f['complexity']} (max 20)",
        "file" => f["file"],
        "line" => f["line"]
      }
    elsif f["complexity"] > 10
      violations << {
        "type" => "warning",
        "rule" => "moderate_complexity",
        "message" => "#{f['name']} has cyclomatic complexity #{f['complexity']} (recommended max 10)",
        "file" => f["file"],
        "line" => f["line"]
      }
    end
  end

  file_metrics.each do |fm|
    if fm["loc"] > 500
      violations << {
        "type" => "warning",
        "rule" => "large_file",
        "message" => "#{fm['path']} has #{fm['loc']} LOC (recommended max 500)",
        "file" => fm["path"],
        "line" => 1
      }
    end

    if fm["functions"] > 20
      violations << {
        "type" => "warning",
        "rule" => "too_many_functions",
        "message" => "#{fm['path']} has #{fm['functions']} functions (recommended max 20)",
        "file" => fm["path"],
        "line" => 1
      }
    end

    if fm["maintainability"] < 20
      violations << {
        "type" => "error",
        "rule" => "low_maintainability",
        "message" => "#{fm['path']} has maintainability index #{fm['maintainability']} (min 20)",
        "file" => fm["path"],
        "line" => 1
      }
    elsif fm["maintainability"] < 40
      violations << {
        "type" => "warning",
        "rule" => "moderate_maintainability",
        "message" => "#{fm['path']} has maintainability index #{fm['maintainability']} (recommended min 40)",
        "file" => fm["path"],
        "line" => 1
      }
    end
  end

  violations.sort_by! { |v| [v["type"] == "error" ? 0 : 1, v["file"]] }
  violations
end

._extract_functions(source, tokens, lines) ⇒ Object 



705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
 
# File 'lib/tina4/metrics.rb', line 705

def self._extract_functions(source, tokens, lines)
  functions = []
  # Track class/module nesting for method names
  context_stack = []
  i = 0

  while i < lines.length
    stripped = lines[i].strip

    # Track class/module context
    if stripped.match?(/\A(class|module)\s+(\S+)/)
      m = stripped.match(/\A(class|module)\s+(\S+)/)
      class_name = m[2].to_s.split('<').first.to_s.strip
      context_stack.push(class_name) unless class_name.empty?
    end

    # Detect method definitions
    if stripped.match?(/\Adef\s+/)
      method_match = stripped.match(/\Adef\s+(self\.)?(\S+?)(\(.*\))?\s*$/)
      if method_match
        prefix = method_match[1] ? 'self.' : ''
        method_name = prefix + method_match[2]

        # Build full name with class context
        full_name = if context_stack.any?
                      "#{context_stack.last}.#{method_name}"
                    else
                      method_name
                    end

        # Extract arguments
        args = []
        if method_match[3]
          arg_str = method_match[3].gsub(/[()]/, '')
          arg_str.split(',').each do |arg|
            arg = arg.strip.split('=').first.strip.gsub(/^[*&]+/, '')
            args << arg unless arg == 'self' || arg.empty?
          end
        end

        # Find method end and calculate LOC
        method_start = i
        method_end = _find_method_end(lines, i)
        method_loc = method_end - method_start + 1

        # Calculate complexity for this method's body
        method_lines = lines[method_start..method_end]
        method_source = method_lines.join("\n")
        cc = _cyclomatic_complexity_from_source(method_source)

        functions << {
          "name" => full_name,
          "line" => i + 1,
          "complexity" => cc,
          "loc" => method_loc,
          "args" => args
        }
      end
    end

    # Track end keywords for context popping
    if stripped == 'end'
      # Check if this closes a class/module
      # Simple heuristic: count def/class/module opens vs end closes
      # We only pop context when we're back at the class/module level
      indent = lines[i].length - lines[i].lstrip.length
      if indent == 0 && context_stack.any?
        context_stack.pop
      end
    end

    i += 1
  end

  functions
end

._extract_imports(lines) ⇒ Object 



690
691
692
693
694
695
696
697
698
699
700
701
702
703
 
# File 'lib/tina4/metrics.rb', line 690

def self._extract_imports(lines)
  imports = []
  lines.each do |line|
    stripped = line.strip
    if stripped.match?(/\Arequire\s+/)
      m = stripped.match(/\Arequire\s+['"]([^'"]+)['"]/)
      imports << m[1] if m
    elsif stripped.match?(/\Arequire_relative\s+/)
      m = stripped.match(/\Arequire_relative\s+['"]([^'"]+)['"]/)
      imports << m[1] if m
    end
  end
  imports
end

._files_hash(root) ⇒ Object 



675
676
677
678
679
680
681
682
683
684
685
686
687
688
 
# File 'lib/tina4/metrics.rb', line 675

def self._files_hash(root)
  md5 = Digest::MD5.new
  root_path = Pathname.new(root)
  if root_path.directory?
    Dir.glob(root_path.join('**', '*.rb')).sort.each do |f|
      begin
        md5.update("#{f}:#{File.mtime(f).to_f}")
      rescue StandardError
        # ignore
      end
    end
  end
  md5.hexdigest
end

._find_method_end(lines, start_index) ⇒ Object 



782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
 
# File 'lib/tina4/metrics.rb', line 782

def self._find_method_end(lines, start_index)
  depth = 0
  i = start_index
  base_indent = lines[i].length - lines[i].lstrip.length

  while i < lines.length
    stripped = lines[i].strip

    unless stripped.empty? || stripped.start_with?('#')
      # Count block openers
      if stripped.match?(/\b(def|class|module|if|unless|case|while|until|for|begin|do)\b/) &&
         !stripped.match?(/\bend\b/) &&
         !stripped.end_with?(' if ', ' unless ', ' while ', ' until ') &&
         !(stripped.match?(/\bif\b|\bunless\b|\bwhile\b|\buntil\b/) && i != start_index && _is_modifier?(stripped))
        depth += 1
      end

      if stripped == 'end' || stripped.start_with?('end ') || stripped.start_with?('end;')
        depth -= 1
        return i if depth <= 0
      end
    end

    i += 1
  end

  # If we never found the end, return last line
  lines.length - 1
end

._has_matching_test(rel_path) ⇒ Object

Check whether a source file has a test that actually exercises it.

PRECISE detection (a bare word-mention is NOT enough — that over-reported badly: ‘sqlite3_adapter.rb` looked “tested” because some spec merely said “sqlite3_adapter”):

1. Filename — a dedicated `<module>_spec.rb` / `<module>_test.rb` /
   `test_<module>.rb` for THIS exact module (NOT the parent directory —
   one `database_spec.rb` must not mark every file under `database/`
   tested).
2. Require — a spec that actually requires this file: its require path
   (`require "tina4/database/sqlite"` / `require_relative ".../sqlite"`)
   matched by the basename of a require target. A constant/class that is
   genuinely DEFINED in this file (top-level class/module) referenced by
   a spec also counts.

Returns true only on a real, file-specific signal — so the “untested” offenders surfaced by ‘tina4 metrics` and the dashboard “T” badge are trustworthy. (If you wire real coverage data later, prefer it over this.)



563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
 
# File 'lib/tina4/metrics.rb', line 563

def self._has_matching_test(rel_path)
  require 'set'

  name = File.basename(rel_path, '.rb')

  # Require path WITHOUT extension, leading lib/ stripped:
  # "lib/tina4/database/sqlite.rb" -> "tina4/database/sqlite"
  require_path = rel_path.sub(/\.rb$/, '').sub(%r{^lib/}, '')

  # Constants (classes/modules) DEFINED at the top level of this file — a
  # spec referencing one of them genuinely exercises this file. Names only,
  # distinctive (>3 chars, leading uppercase); bare module-name words and
  # guessed CamelCase are too loose to trust.
  defined_symbols = _defined_constants(rel_path)

  # Search roots: CWD plus (in framework-fallback mode) the repo root that
  # owns spec/ — walk up from the scan root to find it.
  search_roots = ['.']
  if @last_scan_root && !@last_scan_root.empty?
    scan_root = @last_scan_root
    5.times do
      if %w[spec test tests].any? { |d| Dir.exist?(File.join(scan_root, d)) }
        search_roots << scan_root
        break
      end
      parent = File.dirname(scan_root)
      break if parent == scan_root
      scan_root = parent
    end
  end
  search_roots.uniq!

  test_dirs = %w[spec test tests]

  # Stage 1: a dedicated spec/test FILE named for THIS module (no parent-dir
  # blanket match).
  filename_patterns = [
    "#{name}_spec.rb",
    "#{name}s_spec.rb",
    "#{name}_test.rb",
    "test_#{name}.rb",
  ]
  search_roots.each do |root|
    test_dirs.each do |td|
      filename_patterns.each do |fn|
        return true if File.exist?(File.join(root, td, fn))
      end
    end
  end

  # Stage 2: a spec that actually REQUIRES this module (precise — matched by
  # the require target's basename / tail of the require path), or references
  # a constant defined in it. NO bare word-of-the-module-name match.
  require_regexps = []
  unless require_path.empty?
    # require "…/<module>" or require_relative "…/<module>" — match the
    # require string ending in this file's require path or basename.
    rp = Regexp.escape(require_path)
    nm = Regexp.escape(name)
    require_regexps << /(?:require|require_relative)\s+['"][^'"]*#{rp}['"]/
    require_regexps << %r{(?:require|require_relative)\s+['"][^'"]*/#{nm}['"]}
  end
  unless defined_symbols.empty?
    sym_alt = defined_symbols.map { |s| Regexp.escape(s) }.join('|')
    require_regexps << /\b(?:#{sym_alt})\b/
  end

  return false if require_regexps.empty?

  search_roots.each do |root|
    test_dirs.each do |td|
      dir = File.join(root, td)
      next unless Dir.exist?(dir)
      Dir.glob(File.join(dir, '**', '*.rb')).each do |test_file|
        content = begin
          File.read(test_file, encoding: 'utf-8')
        rescue StandardError
          next
        end
        return true if require_regexps.any? { |re| content.match?(re) }
      end
    end
  end

  false
end

._is_modifier?(line) ⇒ Boolean

Returns:

  • (Boolean) 


812
813
814
815
816
817
 
# File 'lib/tina4/metrics.rb', line 812

def self._is_modifier?(line)
  # A rough check: if the keyword is not at the start of the meaningful content,
  # it's likely a modifier (e.g., "return x if condition")
  stripped = line.strip
  !stripped.match?(/\A(if|unless|while|until)\b/)
end

._maintainability_index(halstead_volume, avg_cc, loc) ⇒ Object 



909
910
911
912
913
914
915
 
# File 'lib/tina4/metrics.rb', line 909

def self._maintainability_index(halstead_volume, avg_cc, loc)
  return 100.0 if loc <= 0

  v = [halstead_volume, 1].max
  mi = 171 - 5.2 * Math.log(v) - 0.23 * avg_cc - 16.2 * Math.log(loc)
  [[0.0, mi * 100.0 / 171].max, 100.0].min
end

._resolve_root(root = 'src') ⇒ Object

Pick the right directory to scan.

If the root dir has Ruby files, scan the user’s project code. Otherwise, scan the framework itself — so the bubble chart is never empty.



33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/tina4/metrics.rb', line 33

def self._resolve_root(root = 'src')
  root_path = Pathname.new(root)
  if root_path.directory? && !Dir.glob(root_path.join('**', '*.rb')).empty?
    @last_scan_root = File.expand_path(root)
    return root
  end
  # Fallback: scan the framework package itself
  fw_dir = File.dirname(__FILE__)
  @last_scan_root = fw_dir
  fw_dir
end

.file_detail(file_path) ⇒ Object

── File Detail ─────────────────────────────────────────────



476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
 
# File 'lib/tina4/metrics.rb', line 476

def self.file_detail(file_path)
  unless File.exist?(file_path)
    # Try resolving relative to the last scan root (framework mode)
    if @last_scan_root && !@last_scan_root.empty?
      candidate = File.join(@last_scan_root, file_path)
      if File.exist?(candidate)
        file_path = candidate
      end
    end
  end
  unless File.exist?(file_path)
    return { "error" => "File not found: #{file_path}" }
  end

  source = begin
    File.read(file_path, encoding: 'utf-8')
  rescue StandardError => e
    return { "error" => "Read error: #{e.message}" }
  end

  tokens = begin
    Ripper.lex(source)
  rescue StandardError => e
    return { "error" => "Syntax error: #{e.message}" }
  end

  lines = source.lines.map(&:chomp)
  loc = lines.count { |l| !l.strip.empty? && !l.strip.start_with?('#') }

  functions = _extract_functions(source, tokens, lines)
  functions.sort_by! { |f| -f["complexity"] }

  classes = lines.count { |l| l.strip.match?(/\A(class|module)\s+/) }
  imports = _extract_imports(lines)

  warnings = []
  functions.each do |f|
    if f["loc"] <= 1
      warnings << { "type" => "empty_method", "message" => "Method '#{f["name"]}' appears to be empty", "line" => f["line"] }
    end
  end
  if classes > 0 && functions.empty? && loc <= 1
    warnings << { "type" => "empty_class", "message" => "Class/module appears to be empty", "line" => 1 }
  end

  {
    "path" => file_path,
    "loc" => loc,
    "total_lines" => lines.length,
    "classes" => classes,
    "functions" => functions.map { |f|
      {
        "name" => f["name"],
        "line" => f["line"],
        "complexity" => f["complexity"],
        "loc" => f["loc"],
        "args" => f["args"]
      }
    },
    "imports" => imports,
    "warnings" => warnings
  }
end

.full_analysis(root = 'src') ⇒ Object

── Full Analysis (Ripper-based) ────────────────────────────



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
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
 
# File 'lib/tina4/metrics.rb', line 215

def self.full_analysis(root = 'src')
  # Check if the requested directory exists before falling back
  root_path = Pathname.new(root)
  return { "error" => "Directory not found: #{root}" } unless root_path.directory?

  root = _resolve_root(root)
  root_path = Pathname.new(root)

  current_hash = _files_hash(root)
  now = Time.now.to_f

  if @full_cache_hash == current_hash && !@full_cache_data.nil? && (now - @full_cache_time) < CACHE_TTL
    return @full_cache_data
  end

  rb_files = Dir.glob(root_path.join('**', '*.rb'))

  all_functions = []
  file_metrics = []
  import_graph = {}
  reverse_graph = {}

  rb_files.each do |f|
    source = begin
      File.read(f, encoding: 'utf-8')
    rescue StandardError
      next
    end

    tokens = begin
      Ripper.lex(source)
    rescue StandardError
      next
    end

    rel_path = begin
      Pathname.new(f).relative_path_from(root_path).to_s
    rescue ArgumentError
      f
    end

    lines = source.lines.map(&:chomp)
    loc = lines.count { |l| !l.strip.empty? && !l.strip.start_with?('#') }

    # Extract imports (require/require_relative)
    imports = _extract_imports(lines)
    import_graph[rel_path] = imports

    imports.each do |imp|
      reverse_graph[imp] ||= []
      reverse_graph[imp] << rel_path
    end

    # Parse functions/methods and their complexity
    file_functions = _extract_functions(source, tokens, lines)
    file_complexity = 0

    file_functions.each do |func_info|
      func_info["file"] = rel_path
      all_functions << func_info
      file_complexity += func_info["complexity"]
    end

    # Halstead metrics from tokens
    halstead = _count_halstead(tokens)
    n1 = halstead[:unique_operators].length
    n2 = halstead[:unique_operands].length
    n_total_1 = halstead[:operators]
    n_total_2 = halstead[:operands]
    vocabulary = n1 + n2
    length = n_total_1 + n_total_2
    volume = vocabulary > 0 ? length * Math.log2(vocabulary) : 0.0

    # Maintainability index
    avg_cc = file_functions.empty? ? 0 : file_complexity.to_f / file_functions.length
    mi = _maintainability_index(volume, avg_cc, loc)

    # Coupling
    ce = imports.length
    ca = (reverse_graph[rel_path] || []).length
    instability = (ca + ce) > 0 ? ce.to_f / (ca + ce) : 0.0

    file_metrics << {
      "path" => rel_path,
      "loc" => loc,
      "complexity" => file_complexity,
      "avg_complexity" => avg_cc.round(2),
      "functions" => file_functions.length,
      "maintainability" => mi.round(1),
      "halstead_volume" => volume.round(1),
      "coupling_afferent" => ca,
      "coupling_efferent" => ce,
      "instability" => instability.round(3),
      "has_tests" => _has_matching_test(rel_path),
      "dep_count" => imports.length
    }
  end

  # Update afferent coupling now that all files are processed
  file_metrics.each do |fm|
    fm["coupling_afferent"] = (reverse_graph[fm["path"]] || []).length
    ca = fm["coupling_afferent"]
    ce = fm["coupling_efferent"]
    fm["instability"] = (ca + ce) > 0 ? (ce.to_f / (ca + ce)).round(3) : 0.0
  end

  all_functions.sort_by! { |f| -f["complexity"] }
  file_metrics.sort_by! { |f| f["maintainability"] }

  violations = _detect_violations(all_functions, file_metrics)

  total_cc = all_functions.sum { |f| f["complexity"] }
  avg_cc = all_functions.empty? ? 0 : total_cc.to_f / all_functions.length
  total_mi = file_metrics.sum { |f| f["maintainability"] }
  avg_mi = file_metrics.empty? ? 0 : total_mi.to_f / file_metrics.length

  # Detect if we're scanning framework or project
  framework_dir = File.expand_path(File.dirname(__FILE__))
  resolved_root = File.expand_path(root_path.to_s)
  scanning_framework = resolved_root == framework_dir || resolved_root.start_with?(framework_dir + '/')

  result = {
    "files_analyzed" => file_metrics.length,
    "total_functions" => all_functions.length,
    "avg_complexity" => avg_cc.round(2),
    "avg_maintainability" => avg_mi.round(1),
    "most_complex_functions" => all_functions.first(15),
    "file_metrics" => file_metrics,
    "violations" => violations,
    "dependency_graph" => import_graph,
    "scan_mode" => scanning_framework ? "framework" : "project",
    "scan_root" => resolved_root
  }

  @full_cache_hash = current_hash
  @full_cache_data = result
  @full_cache_time = now

  result
end

.last_scan_root ⇒ Object 



45
46
47
 
# File 'lib/tina4/metrics.rb', line 45

def self.last_scan_root
  @last_scan_root
end

.offenders(root = 'src', top = 20) ⇒ Object

Rank the worst code-quality issues into a single “top offenders” list.

Reuses full_analysis (does NOT re-analyze). Each offender is a hash:

{"file", "line", "kind", "severity", "score", "detail"}

Rules (one offender per matching condition):

- function complexity > 10  → kind "complexity"
      severity "error" if >20 else "warn"; score = complexity
- file loc > 500            → kind "large_file" (warn); score = loc/100
- file functions > 20       → kind "too_many_functions" (warn); score = functions/4
- file maintainability < 40 → kind "low_maintainability"
      severity "error" if <20 else "warn"; score = (50 - mi)
- file has_tests false      → kind "untested" (info); score = loc/100

Sorted by (severity rank, score) DESCENDING and truncated to ‘top`.

Returns => […], “summary” => {…} where summary carries the headline numbers the CLI prints (files_analyzed, total_functions, avg_complexity, avg_maintainability, scan_mode, scan_root, and the total offender count before truncation).



381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
 
# File 'lib/tina4/metrics.rb', line 381

def self.offenders(root = 'src', top = 20)
  analysis = full_analysis(root)
  if analysis.key?("error")
    return { "offenders" => [], "summary" => { "error" => analysis["error"] } }
  end

  items = []

  # Function-level: cyclomatic complexity.
  (analysis["most_complex_functions"] || []).each do |fn|
    cc = fn["complexity"]
    next unless cc > 10
    items << {
      "file" => fn["file"],
      "line" => fn["line"],
      "kind" => "complexity",
      "severity" => cc > 20 ? "error" : "warn",
      "score" => cc.to_f,
      "detail" => "#{fn['name']} — cyclomatic complexity #{cc}"
    }
  end

  # File-level rules.
  (analysis["file_metrics"] || []).each do |fm|
    path = fm["path"]
    loc = fm["loc"]
    funcs = fm["functions"]
    mi = fm["maintainability"]

    if loc > 500
      items << {
        "file" => path,
        "line" => 1,
        "kind" => "large_file",
        "severity" => "warn",
        "score" => loc / 100.0,
        "detail" => "#{loc} LOC (max 500)"
      }
    end

    if funcs > 20
      items << {
        "file" => path,
        "line" => 1,
        "kind" => "too_many_functions",
        "severity" => "warn",
        "score" => funcs / 4.0,
        "detail" => "#{funcs} functions (max 20)"
      }
    end

    if mi < 40
      items << {
        "file" => path,
        "line" => 1,
        "kind" => "low_maintainability",
        "severity" => mi < 20 ? "error" : "warn",
        "score" => 50 - mi,
        "detail" => "maintainability index #{mi} (min 40)"
      }
    end

    if fm["has_tests"] == false
      items << {
        "file" => path,
        "line" => 1,
        "kind" => "untested",
        "severity" => "info",
        "score" => loc / 100.0,
        "detail" => "no referencing test"
      }
    end
  end

  # Sort by (severity rank, score) DESCENDING — stable so insertion order
  # breaks ties deterministically.
  items = items.each_with_index.sort_by do |o, idx|
    [-SEVERITY_RANK[o["severity"]], -o["score"], idx]
  end.map(&:first)

  summary = {
    "files_analyzed" => analysis["files_analyzed"],
    "total_functions" => analysis["total_functions"],
    "avg_complexity" => analysis["avg_complexity"],
    "avg_maintainability" => analysis["avg_maintainability"],
    "scan_mode" => analysis["scan_mode"],
    "scan_root" => analysis["scan_root"],
    "total_offenders" => items.length
  }

  { "offenders" => items.first(top), "summary" => summary }
end

.quick_metrics(root = 'src') ⇒ Object

── Quick Metrics ───────────────────────────────────────────



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
 
# File 'lib/tina4/metrics.rb', line 51

def self.quick_metrics(root = 'src')
  # Check if the requested directory exists before falling back
  root_path = Pathname.new(root)
  return { "error" => "Directory not found: #{root}" } unless root_path.directory?

  root = _resolve_root(root)
  root_path = Pathname.new(root)

  rb_files = Dir.glob(root_path.join('**', '*.rb'))
  twig_files = Dir.glob(root_path.join('**', '*.twig')) + Dir.glob(root_path.join('**', '*.erb'))

  migrations_path = Pathname.new('migrations')
  sql_files = if migrations_path.directory?
                Dir.glob(migrations_path.join('**', '*.sql')) + Dir.glob(migrations_path.join('**', '*.rb'))
              else
                []
              end

  scss_files = Dir.glob(root_path.join('**', '*.scss')) + Dir.glob(root_path.join('**', '*.css'))

  total_loc = 0
  total_blank = 0
  total_comment = 0
  total_classes = 0
  total_functions = 0
  file_details = []

  rb_files.each do |f|
    source = begin
      File.read(f, encoding: 'utf-8')
    rescue StandardError
      next
    end

    lines = source.lines.map(&:chomp)
    loc = 0
    blank = 0
    comment = 0
    in_heredoc = false
    heredoc_id = nil
    in_block_comment = false

    lines.each do |line|
      stripped = line.strip

      if stripped.empty?
        blank += 1
        next
      end

      # =begin/=end block comments
      if in_block_comment
        comment += 1
        in_block_comment = false if stripped.start_with?('=end')
        next
      end

      if stripped.start_with?('=begin')
        comment += 1
        in_block_comment = true
        next
      end

      # Heredoc tracking (simplified)
      if in_heredoc
        if stripped == heredoc_id
          in_heredoc = false
        end
        loc += 1
        next
      end

      if stripped.match?(/<<[~-]?['"]?(\w+)['"]?/)
        m = stripped.match(/<<[~-]?['"]?(\w+)['"]?/)
        heredoc_id = m[1]
        in_heredoc = true unless stripped.include?(heredoc_id + stripped[-1].to_s)
        loc += 1
        next
      end

      if stripped.start_with?('#')
        comment += 1
        next
      end

      loc += 1
    end

    # Count classes and methods via simple pattern matching
    classes = lines.count { |l| l.strip.match?(/\A(class|module)\s+/) }
    functions = lines.count { |l| l.strip.match?(/\Adef\s+/) }

    total_loc += loc
    total_blank += blank
    total_comment += comment
    total_classes += classes
    total_functions += functions

    rel_path = begin
      Pathname.new(f).relative_path_from(root_path).to_s
    rescue ArgumentError
      f
    end

    file_details << {
      "path" => rel_path,
      "loc" => loc,
      "blank" => blank,
      "comment" => comment,
      "classes" => classes,
      "functions" => functions
    }
  end

  file_details.sort_by! { |d| -d["loc"] }

  # Route and ORM counts
  route_count = 0
  orm_count = 0
  begin
    if defined?(Tina4::Router) && Tina4::Router.respond_to?(:routes)
      route_count = Tina4::Router.routes.length
    elsif defined?(Tina4::Router) && Tina4::Router.instance_variable_defined?(:@routes)
      route_count = Tina4::Router.instance_variable_get(:@routes).length
    end
  rescue StandardError
    # ignore
  end

  begin
    if defined?(Tina4::ORM)
      orm_count = ObjectSpace.each_object(Class).count { |c| c < Tina4::ORM }
    end
  rescue StandardError
    # ignore
  end

  breakdown = {
    "ruby" => rb_files.length,
    "templates" => twig_files.length,
    "migrations" => sql_files.length,
    "stylesheets" => scss_files.length
  }

  {
    "file_count" => rb_files.length,
    "total_loc" => total_loc,
    "total_blank" => total_blank,
    "total_comment" => total_comment,
    "lloc" => total_loc,
    "classes" => total_classes,
    "functions" => total_functions,
    "route_count" => route_count,
    "orm_count" => orm_count,
    "template_count" => twig_files.length,
    "migration_count" => sql_files.length,
    "avg_file_size" => rb_files.empty? ? 0 : (total_loc.to_f / rb_files.length).round(1),
    "largest_files" => file_details.first(10),
    "breakdown" => breakdown
  }
end