Class: Ace::Support::Nav::Molecules::ProtocolScanner

Inherits:
Object
  • Object
show all
Defined in:
lib/ace/support/nav/molecules/protocol_scanner.rb

Overview

Scans for protocol resources using registered sources

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(gem_resolver: nil, path_normalizer: nil, config_loader: nil, extension_inferrer: nil) ⇒ ProtocolScanner

Returns a new instance of ProtocolScanner.



17
18
19
20
21
22
23
24
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 17

def initialize(gem_resolver: nil, path_normalizer: nil, config_loader: nil, extension_inferrer: nil)
  @gem_resolver = gem_resolver || Atoms::GemResolver.new
  @path_normalizer = path_normalizer || Atoms::PathNormalizer.new
  @config_loader = config_loader || ConfigLoader.new
  # extension_inferrer param kept for backwards compatibility but ignored
  # ExtensionInferrer now uses class methods
  @extension_inference_enabled = nil
end

Instance Attribute Details

#config_loader ⇒ Object (readonly)

Returns the value of attribute config_loader.



15
16
17
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 15

def config_loader
  @config_loader
end

Instance Method Details

#deduplicate_resources(resources) ⇒ Object 



279
280
281
282
283
284
285
286
287
288
289
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 279

def deduplicate_resources(resources)
  seen = Set.new

  resources.each_with_object([]) do |resource, unique_resources|
    key = dedupe_resource_key(resource)
    next if seen.include?(key)

    seen.add(key)
    unique_resources << resource
  end
end

#extension_inference_enabled? ⇒ Boolean

Check if extension inference is enabled in settings (cached)

Returns:

  • (Boolean) 


292
293
294
295
296
297
298
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 292

def extension_inference_enabled?
  return @extension_inference_enabled unless @extension_inference_enabled.nil?

  settings = @config_loader.load_settings
  inference_config = settings["extension_inference"] || {}
  @extension_inference_enabled = inference_config["enabled"] != false  # Default true
end

#find_resources(protocol, pattern = "*") ⇒ Object

Find resources in all sources for a protocol



32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 32

def find_resources(protocol, pattern = "*")
  sources = sources_for_protocol(protocol)
  protocol_config = @config_loader.load_protocol_config(protocol)

  resources = []

  sources.each do |source|
    next unless source.exists?

    resources.concat(find_resources_in_source_internal(source, protocol_config, pattern))
  end

  deduplicate_resources(resources)
end

#find_resources_in_source(source, protocol, pattern = "*") ⇒ Object

Legacy wrapper method for HandbookScanner compatibility



306
307
308
309
310
311
312
313
314
315
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 306

def find_resources_in_source(source, protocol, pattern = "*")
  # If second param is a string (protocol name), load its config
  if protocol.is_a?(String)
    protocol_config = @config_loader.load_protocol_config(protocol)
    find_resources_in_source_internal(source, protocol_config, pattern)
  else
    # Already a protocol config
    find_resources_in_source_internal(source, protocol, pattern)
  end
end

#find_resources_in_source_internal(source, protocol_config, pattern = "*") ⇒ Object

Find resources in a specific source (internal implementation)



48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 48

def find_resources_in_source_internal(source, protocol_config, pattern = "*")
  # Try exact match first
  resources = find_resources_with_extensions(source, protocol_config, pattern)

  # If no results and extension inference is enabled, try with inferred extensions
  if resources.empty? && extension_inference_enabled? && !pattern.include?("/") && pattern != "*"
    resources = find_resources_with_inference(source, protocol_config, pattern)
  end

  resources
end

#find_resources_with_extensions(source, protocol_config, pattern = "*") ⇒ Object

Find resources using pattern and extensions (original logic)



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
212
213
214
215
216
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 61

def find_resources_with_extensions(source, protocol_config, pattern = "*")
  # Handle both ProtocolSource and HandbookSource objects
  if source.respond_to?(:full_path)
    return [] unless source.exists?
    search_path = source.full_path
  else
    # Legacy HandbookSource
    return [] unless source.exists?
    search_path = source.handbook_path
  end

  # Get extensions from protocol config
  extensions = protocol_config["extensions"] || []

  resources = []

  # Check if pattern contains directory structure
  if pattern.include?("/")
    # Handle subdirectory patterns
    if pattern.end_with?("/")
      # Pattern like "base/" has two interpretations:
      # 1. Files in a subdirectory named "base"
      # 2. Files that start with "base" prefix
      prefix = pattern.chomp("/")

      # First, try as a subdirectory
      subdir_path = File.join(search_path, prefix)
      has_subdir = Dir.exist?(subdir_path)

      if has_subdir
        # Subdirectory exists, list files in it
        found_subdir_paths = Set.new  # Track paths to avoid duplicates

        if extensions.empty?
          # Match any file in the subdirectory
          glob_pattern = File.join(subdir_path, "*")
          glob_pattern_nested = File.join(subdir_path, "**", "*")

          [glob_pattern, glob_pattern_nested].each do |gp|
            Dir.glob(gp).each do |file_path|
              next unless File.file?(file_path)
              next if found_subdir_paths.include?(file_path)  # Skip duplicates
              found_subdir_paths.add(file_path)
              resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
            end
          end
        else
          # Match files with specified extensions in the subdirectory
          extensions.each do |ext|
            glob_pattern = File.join(subdir_path, "*#{ext}")
            glob_pattern_nested = File.join(subdir_path, "**", "*#{ext}")

            [glob_pattern, glob_pattern_nested].each do |gp|
              Dir.glob(gp).each do |file_path|
                next unless File.file?(file_path)
                next if found_subdir_paths.include?(file_path)  # Skip duplicates
                found_subdir_paths.add(file_path)
                resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
              end
            end
          end
        end
      end

      # Also try as a prefix pattern (files starting with prefix)
      found_paths = Set.new  # Track paths to avoid duplicates

      if extensions.empty?
        # Match files starting with prefix
        glob_patterns = [
          File.join(search_path, "#{prefix}*"),
          File.join(search_path, "**", "#{prefix}*")
        ]

        glob_patterns.each do |gp|
          Dir.glob(gp).each do |file_path|
            next unless File.file?(file_path)
            next if found_paths.include?(file_path)  # Skip duplicates
            found_paths.add(file_path)
            resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
          end
        end
      else
        # Match files with specified extensions starting with prefix
        extensions.each do |ext|
          glob_patterns = [
            File.join(search_path, "#{prefix}*#{ext}"),
            File.join(search_path, "**", "#{prefix}*#{ext}")
          ]

          glob_patterns.each do |gp|
            Dir.glob(gp).each do |file_path|
              next unless File.file?(file_path)
              next if found_paths.include?(file_path)  # Skip duplicates
              found_paths.add(file_path)
              resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
            end
          end
        end
      end
    elsif extensions.empty?
      # Pattern like "base/*" or "base/something" - use as-is but handle properly
      glob_pattern = File.join(search_path, pattern)
      glob_pattern += "*" unless pattern.end_with?("*") || pattern.include?("*")

      Dir.glob(glob_pattern).each do |file_path|
        next unless File.file?(file_path)
        resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
      end
    else
      extensions.each do |ext|
        glob_pattern = if pattern.end_with?(ext)
          File.join(search_path, pattern)
        else
          File.join(search_path, "#{pattern}#{ext}")
        end

        Dir.glob(glob_pattern).each do |file_path|
          next unless File.file?(file_path)
          resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
        end
      end
    end
  elsif extensions.empty?
    # Original behavior for patterns without directory structure
    glob_pattern = File.join(search_path, "**", pattern)
    glob_pattern += "*" unless pattern.end_with?("*")

    Dir.glob(glob_pattern).each do |file_path|
      next unless File.file?(file_path)

      resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
    end
  # If no extensions specified, match any file
  else
    # Match files with specified extensions
    extensions.each do |ext|
      # Check if pattern already ends with this extension
      glob_pattern = if pattern.end_with?(ext)
        # Pattern already has extension, search as-is
        File.join(search_path, "**", pattern)
      else
        # Append extension to pattern
        File.join(search_path, "**", "#{pattern}#{ext}")
      end

      Dir.glob(glob_pattern).each do |file_path|
        next unless File.file?(file_path)

        resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
      end
    end
  end

  resources
end

#find_resources_with_inference(source, protocol_config, pattern) ⇒ Object

Find resources using extension inference when exact match fails



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
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 219

def find_resources_with_inference(source, protocol_config, pattern)
  # Handle both ProtocolSource and HandbookSource objects
  if source.respond_to?(:full_path)
    return [] unless source.exists?
    search_path = source.full_path
  else
    return [] unless source.exists?
    search_path = source.handbook_path
  end

  # Get configuration for extension inference
  settings = @config_loader.load_settings
  inference_config = settings["extension_inference"] || {}
  enabled = inference_config["enabled"] != false  # Default true
  fallback_order = inference_config["fallback_order"]

  # Get protocol extensions
  protocol_extensions = protocol_config["extensions"] || []
  inferred_extensions = protocol_config["inferred_extensions"] || protocol_extensions

  # Generate candidate patterns using extension inferrer
  candidates = Atoms::ExtensionInferrer.infer_extensions(
    pattern,
    protocol_extensions: inferred_extensions,
    enabled: enabled,
    fallback_order: fallback_order
  )

  resources = []
  found_paths = Set.new  # Track paths to avoid duplicates

  # Try each candidate pattern in order
  candidates.each do |candidate|
    # For inference, we need to allow additional extensions after the inferred one
    # e.g., "mydoc.cst" should match "mydoc.cst.md"
    # Use brace expansion for tighter matching: exact match or with extension
    glob_pattern = File.join(search_path, "**", candidate + "{,.*}")

    Dir.glob(glob_pattern).each do |file_path|
      next unless File.file?(file_path)
      next if found_paths.include?(file_path)

      # Only match if basename equals candidate or has candidate as prefix with dot separator
      # This prevents "multi-ext.g" from matching "multi-ext.guide.md"
      basename = File.basename(file_path)
      basename_candidate = File.basename(candidate)
      next unless basename == basename_candidate ||
        basename.start_with?(basename_candidate + ".")

      found_paths.add(file_path)
      resources << create_resource_info(file_path, search_path, source, protocol_config["protocol"])
    end

    # Stop at first match (DWIM: return first successful inference)
    break if resources.any?
  end

  resources
end

#reset_extension_inference_cache! ⇒ Object

Reset extension inference cache (for testing)



301
302
303
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 301

def reset_extension_inference_cache!
  @extension_inference_enabled = nil
end

#scan_all_sources ⇒ Object

Legacy method for compatibility - get all sources across all protocols



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
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 318

def scan_all_sources
  sources = []
  protocols = @config_loader.valid_protocols

  protocols.each do |protocol|
    protocol_sources = sources_for_protocol(protocol)

    # Convert to legacy HandbookSource format for compatibility
    protocol_sources.each do |source|
      # The path already points to the handbook directory
      # HandbookSource will append /handbook if needed
      base_path = source.full_path

      # Remove /handbook from the path if present since HandbookSource adds it
      if base_path.end_with?("/handbook")
        base_path = File.dirname(base_path)
      end

      sources << Models::HandbookSource.new(
        name: source.name,
        path: base_path,
        alias_name: "@#{source.name}",
        type: source.type.to_sym,
        priority: source.priority
      )
    end
  end

  # Remove duplicates by alias_name
  sources.uniq { |s| s.alias_name }
end

#scan_source_by_alias(alias_name) ⇒ Object

Legacy method - scan source by alias



351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 351

def scan_source_by_alias(alias_name)
  # Remove @ prefix if present
  name = alias_name.start_with?("@") ? alias_name[1..] : alias_name

  # Handle special aliases
  case name
  when "project", "local"
    return scan_project_source
  when "user", "global"
    return scan_user_source
  end

  # Find in registered sources
  protocols = @config_loader.valid_protocols

  protocols.each do |protocol|
    source = sources_for_protocol(protocol).find { |s| s.name == name }
    if source
      return Models::HandbookSource.new(
        name: source.name,
        path: File.dirname(source.full_path),
        alias_name: "@#{source.name}",
        type: source.type.to_sym,
        priority: source.priority
      )
    end
  end

  nil
end

#sources_for_protocol(protocol) ⇒ Object

Get all sources for a protocol



27
28
29
 
# File 'lib/ace/support/nav/molecules/protocol_scanner.rb', line 27

def sources_for_protocol(protocol)
  @config_loader.sources_for_protocol(protocol)
end