Class: SorbetBaml::CommentExtractor

Inherits:
Object
  • Object
show all
Extended by:
T::Sig
Defined in:
lib/sorbet_baml/comment_extractor.rb

Overview

Extracts documentation comments from Sorbet struct and enum source files

Class Method Summary collapse

Class Method Details

.extract_comments_from_lines(lines, class_name, comments) ⇒ Object 



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
 
# File 'lib/sorbet_baml/comment_extractor.rb', line 74

def self.extract_comments_from_lines(lines, class_name, comments)
  in_target_class = T.let(false, T::Boolean)
  current_comment = T.let(nil, T.nilable(String))
  brace_depth = 0

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

    # Check if we're entering the target class
    if stripped.match(/^class\s+#{Regexp.escape(class_name)}\s*<\s*T::Struct/)
      in_target_class = true
      brace_depth = 0
      next
    end

    next unless in_target_class

    # Track brace depth to handle nested classes
    brace_depth += stripped.count('{')
    brace_depth -= stripped.count('}')

    # Exit when we reach the end of the class
    break if stripped == 'end' && brace_depth == 0

    # Extract comment
    if stripped.start_with?('#')
      comment_text = T.must(stripped[1..-1]).strip
      current_comment = current_comment ? "#{current_comment} #{comment_text}" : comment_text
    elsif stripped.match(/^const\s+:(\w+)/) && current_comment
      field_name = T.must(stripped.match(/^const\s+:(\w+)/))[1]
      comments[T.must(field_name)] = current_comment
      current_comment = nil
    elsif !stripped.empty? && !stripped.start_with?('#')
      # Reset comment if we hit non-comment, non-const line
      current_comment = nil
    end
  end
end

.extract_enum_comments(klass) ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/sorbet_baml/comment_extractor.rb', line 28

def self.extract_enum_comments(klass)
  comments = {}
  source_file = find_source_file(klass)

  return comments unless source_file && File.exist?(source_file)

  lines = File.readlines(source_file)
  extract_enum_comments_from_lines(lines, T.must(T.must(klass.name).split('::').last), comments)

  comments
end

.extract_enum_comments_from_lines(lines, class_name, comments) ⇒ Object 



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
 
# File 'lib/sorbet_baml/comment_extractor.rb', line 114

def self.extract_enum_comments_from_lines(lines, class_name, comments)
  in_target_class = T.let(false, T::Boolean)
  in_enums_block = T.let(false, T::Boolean)
  current_comment = T.let(nil, T.nilable(String))

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

    # Check if we're entering the target enum class
    if stripped.match(/^class\s+#{Regexp.escape(class_name)}\s*<\s*T::Enum/)
      in_target_class = true
      next
    end

    next unless in_target_class

    # Check if we're in the enums block
    if stripped == 'enums do'
      in_enums_block = true
      next
    end

    # Exit enums block
    if in_enums_block && stripped == 'end'
      in_enums_block = false
      next
    end

    # Exit class
    break if stripped == 'end' && !in_enums_block

    next unless in_enums_block

    # Extract comment
    if stripped.start_with?('#')
      comment_text = T.must(stripped[1..-1]).strip
      current_comment = current_comment ? "#{current_comment} #{comment_text}" : comment_text
    elsif stripped.match(/^(\w+)\s*=\s*new/) && current_comment
      enum_name = T.must(stripped.match(/^(\w+)\s*=\s*new/))[1]
      comments[T.must(enum_name)] = current_comment
      current_comment = nil
    elsif !stripped.empty? && !stripped.start_with?('#')
      # Reset comment if we hit non-comment, non-enum line
      current_comment = nil
    end
  end
end

.extract_field_comments(klass) ⇒ Object 



10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
 
# File 'lib/sorbet_baml/comment_extractor.rb', line 10

def self.extract_field_comments(klass)
  # First try to get descriptions from the description extractor (extra field)
  descriptions = DescriptionExtractor.extract_prop_descriptions(klass)

  # Then fall back to comment-based extraction for any missing descriptions
  comments = {}
  source_file = find_source_file(klass)

  if source_file && File.exist?(source_file)
    lines = File.readlines(source_file)
    extract_comments_from_lines(lines, T.must(T.must(klass.name).split('::').last), comments)
  end

  # Merge with priority: description parameters > comments
  descriptions.merge(comments) { |_key, desc_param, _comment| desc_param }
end

.find_source_file(klass) ⇒ Object 



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
 
# File 'lib/sorbet_baml/comment_extractor.rb', line 41

def self.find_source_file(klass)
  # Try to find where the class was defined
  # This is a heuristic approach since Ruby doesn't provide reliable source location for classes

  # Method 1: Check if any methods have source location
  begin
    if klass.respond_to?(:new) && klass.method(:new).respond_to?(:source_location)
      location = klass.method(:new).source_location
      return location[0] if location
    end
  rescue StandardError
    # Ignore errors
  end

  # Method 2: Look at the current call stack for files that might contain the class
  caller_locations.each do |location|
    file_path = location.absolute_path || location.path
    next unless file_path && File.exist?(file_path)

    # Read the file and check if it contains the class definition
    begin
      content = File.read(file_path)
      class_name = T.must(klass.name).split('::').last
      return file_path if content.match(/class\s+#{Regexp.escape(T.must(class_name))}\s*</)
    rescue StandardError
      # Ignore file read errors
    end
  end

  nil
end