Class: Cataract::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/cataract/pure/parser.rb

Overview

Pure Ruby CSS parser - char-by-char, NO REGEXP

Constant Summary collapse

MAX_PARSE_DEPTH =

Maximum parse depth (prevent infinite recursion)

10
MAX_MEDIA_QUERIES =

Maximum media queries (prevent symbol table exhaustion)

1000
AT_RULE_TYPES =
%w[supports layer container scope].freeze

Instance Method Summary collapse

Constructor Details

#initialize(css_string, parser_options: {}, parent_media_sym: nil, parent_media_query_id: nil, depth: 0) ⇒ Parser

Returns a new instance of Parser.

Raises:

  • (TypeError)


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
# File 'lib/cataract/pure/parser.rb', line 62

def initialize(css_string, parser_options: {}, parent_media_sym: nil, parent_media_query_id: nil, depth: 0)
  # Type validation
  raise TypeError, "css_string must be a String, got #{css_string.class}" unless css_string.is_a?(String)

  # Private: Internal parsing state
  @_css = css_string.dup.freeze
  @_pos = 0
  @_len = @_css.bytesize
  @_parent_media_sym = parent_media_sym
  @_parent_media_query_id = parent_media_query_id
  @_depth = depth # Current recursion depth (passed from parent parser)

  # Private: Parser options with defaults
  @_parser_options = {
    selector_lists: true,
    base_uri: nil,
    absolute_paths: false,
    uri_resolver: nil,
    raise_parse_errors: false
  }.merge(parser_options)

  # Private: Extract options to ivars to avoid repeated hash lookups in hot path
  @_selector_lists_enabled = @_parser_options[:selector_lists]
  @_base_uri = @_parser_options[:base_uri]
  @_absolute_paths = @_parser_options[:absolute_paths]
  @_uri_resolver = @_parser_options[:uri_resolver] || Cataract::DEFAULT_URI_RESOLVER

  # Parse error handling options - extract to ivars for hot path performance
  @_raise_parse_errors = @_parser_options[:raise_parse_errors]
  if @_raise_parse_errors.is_a?(Hash)
    # Granular control - default all to false (opt-in)
    @_check_empty_values = @_raise_parse_errors[:empty_values] || false
    @_check_malformed_declarations = @_raise_parse_errors[:malformed_declarations] || false
    @_check_invalid_selectors = @_raise_parse_errors[:invalid_selectors] || false
    @_check_invalid_selector_syntax = @_raise_parse_errors[:invalid_selector_syntax] || false
    @_check_malformed_at_rules = @_raise_parse_errors[:malformed_at_rules] || false
    @_check_unclosed_blocks = @_raise_parse_errors[:unclosed_blocks] || false
  elsif @_raise_parse_errors == true
    # Enable all error checks
    @_check_empty_values = true
    @_check_malformed_declarations = true
    @_check_invalid_selectors = true
    @_check_invalid_selector_syntax = true
    @_check_malformed_at_rules = true
    @_check_unclosed_blocks = true
  else
    # Disabled
    @_check_empty_values = false
    @_check_malformed_declarations = false
    @_check_invalid_selectors = false
    @_check_invalid_selector_syntax = false
    @_check_malformed_at_rules = false
    @_check_unclosed_blocks = false
  end

  # Private: Internal counters
  @_media_query_id_counter = 0   # Next MediaQuery ID (0-indexed)
  @_next_selector_list_id = 0    # Counter for selector list IDs
  @_next_media_query_list_id = 0 # Counter for media query list IDs
  @_rule_id_counter = 0          # Next rule ID (0-indexed)
  @_media_query_count = 0        # Safety limit

  # Public: Parser results (returned in parse result hash)
  @rules = []                    # Flat array of Rule structs
  @media_queries = []            # Array of MediaQuery objects
  @media_index = {}              # Symbol => Array of rule IDs (for backwards compat/caching)
  @imports = []                  # Array of ImportStatement structs
  @charset = nil                 # @charset declaration

  # Semi-private: Internal state exposed with _ prefix in result
  @_selector_lists = {}          # Hash: list_id => Array of rule IDs
  @_media_query_lists = {}       # Hash: list_id => Array of MediaQuery IDs (for "screen, print")
  @_has_nesting = false          # Set to true if any nested rules found
end

Instance Method Details

#byteslice_encoded(start, length, encoding: 'UTF-8') ⇒ Object

Extract substring and force specified encoding Per CSS spec, charset detection happens at byte-stream level before parsing. All parsing operations treat content as UTF-8 (spec requires fallback to UTF-8). This prevents ArgumentError on broken/invalid encodings when calling string methods. Optional encoding parameter (default: 'UTF-8', use 'US-ASCII' for property names)



33
34
35
# File 'lib/cataract/pure/parser.rb', line 33

def byteslice_encoded(start, length, encoding: 'UTF-8')
  @_css.byteslice(start, length).force_encoding(encoding)
end

#match_ascii_ci?(str, pos, pattern) ⇒ Boolean

Helper: Case-insensitive ASCII byte comparison Compares bytes at given position with ASCII pattern (case-insensitive) Safe to use even if position is in middle of multi-byte UTF-8 characters Returns true if match, false otherwise

Returns:

  • (Boolean)


41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
# File 'lib/cataract/pure/parser.rb', line 41

def match_ascii_ci?(str, pos, pattern)
  pattern_len = pattern.bytesize
  return false if pos + pattern_len > str.bytesize

  i = 0
  while i < pattern_len
    str_byte = str.getbyte(pos + i)
    pat_byte = pattern.getbyte(i)

    # Convert both to lowercase for comparison (ASCII only: A-Z -> a-z)
    str_byte += BYTE_CASE_DIFF if str_byte >= BYTE_UPPER_A && str_byte <= BYTE_UPPER_Z
    pat_byte += BYTE_CASE_DIFF if pat_byte >= BYTE_UPPER_A && pat_byte <= BYTE_UPPER_Z

    return false if str_byte != pat_byte

    i += 1
  end

  true
end

#parseObject



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
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
# File 'lib/cataract/pure/parser.rb', line 137

def parse
  # @import statements are now handled in parse_at_rule
  # They must come before all rules (except @charset) per CSS spec

  # Main parsing loop - char-by-char, NO REGEXP
  until eof?
    skip_ws_and_comments
    break if eof?

    # Peek at next byte to determine what to parse
    byte = peek_byte

    # Check for at-rules (@media, @charset, etc)
    if byte == BYTE_AT
      parse_at_rule
      next
    end

    # Must be a selector-based rule
    selector = parse_selector

    if selector.nil? || selector.empty?
      next
    end

    # Find the block boundaries
    decl_start = @_pos # Should be right after the {
    decl_end = find_matching_brace(decl_start)

    # Check if block has nested selectors
    if has_nested_selectors?(decl_start, decl_end)
      # NESTED PATH: Parse mixed declarations + nested rules
      # Split comma-separated selectors and parse each one
      selectors = split_and_validate_selectors(selector, decl_start)

      selectors.each do |individual_selector|
        next if individual_selector.empty?

        # Get rule ID for this selector
        current_rule_id = @_rule_id_counter
        @_rule_id_counter += 1

        # Reserve parent's position in rules array (ensures parent comes before nested)
        parent_position = @rules.length
        @rules << nil # Placeholder

        # Parse mixed block (declarations + nested selectors)
        @_depth += 1
        parent_declarations = parse_mixed_block(decl_start, decl_end,
                                                individual_selector, current_rule_id, @_parent_media_sym, @_parent_media_query_id)
        @_depth -= 1

        # Create parent rule and replace placeholder
        rule = Rule.new(
          current_rule_id,
          individual_selector,
          parent_declarations,
          nil,  # specificity
          nil,  # parent_rule_id (top-level)
          nil   # nesting_style
        )

        @rules[parent_position] = rule
      end

      # Move position past the closing brace
      @_pos = decl_end
      @_pos += 1 if @_pos < @_len && @_css.getbyte(@_pos) == BYTE_RBRACE
    else
      # NON-NESTED PATH: Parse declarations only
      @_pos = decl_start # Reset to start of block
      declarations = parse_declarations

      # Split comma-separated selectors into individual rules
      selectors = split_and_validate_selectors(selector, decl_start)

      # Determine if we should track this as a selector list
      # Check boolean first to potentially avoid size() call via short-circuit evaluation
      list_id = nil
      if @_selector_lists_enabled && selectors.size > 1
        list_id = @_next_selector_list_id
        @_next_selector_list_id += 1
        @_selector_lists[list_id] = []
      end

      selectors.each do |individual_selector|
        next if individual_selector.empty?

        rule_id = @_rule_id_counter

        # Dup declarations for each rule in a selector list to avoid shared state
        # (principle of least surprise - modifying one rule shouldn't affect others)
        # Must deep dup: both the array and the Declaration objects inside
        rule_declarations = if list_id
                              declarations.map { |d| Declaration.new(d.property, d.value, d.important) }
                            else
                              declarations
                            end

        # Create Rule struct (with selector_list_id as 7th parameter)
        rule = Rule.new(
          rule_id,             # id
          individual_selector, # selector
          rule_declarations,   # declarations
          nil,                 # specificity (calculated lazily)
          nil,                 # parent_rule_id
          nil,                 # nesting_style
          list_id              # selector_list_id
        )

        @rules << rule
        @_rule_id_counter += 1

        # Track in selector list if applicable
        @_selector_lists[list_id] << rule_id if list_id
      end
    end
  end

  {
    rules: @rules,
    _media_index: @media_index,
    media_queries: @media_queries,
    _selector_lists: @_selector_lists,
    _media_query_lists: @_media_query_lists,
    imports: @imports,
    charset: @charset,
    _has_nesting: @_has_nesting
  }
end