Class: Strling::IR::Compiler
- Inherits:
-
Object
- Object
- Strling::IR::Compiler
- Defined in:
- lib/strling/ir.rb
Overview
Add others as needed
Class Method Summary collapse
Class Method Details
.compile(ast_node) ⇒ Object
23 24 25 26 27 28 29 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 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 |
# File 'lib/strling/ir.rb', line 23 def self.compile(ast_node) return nil if ast_node.nil? case ast_node # Core Nodes when Strling::Core::Lit Lit.new(ir: 'Lit', value: ast_node.value) when Strling::Core::Quant Quant.new( ir: 'Quant', child: compile(ast_node.child), min: ast_node.min, max: ast_node.max, mode: ast_node.mode ) when Strling::Core::Group Group.new( ir: 'Group', capturing: ast_node.capturing, body: compile(ast_node.body), name: ast_node.name, atomic: ast_node.atomic ) when Strling::Core::Alt Alt.new( ir: 'Alt', branches: ast_node.branches.map { |b| compile(b) } ) when Strling::Core::Seq parts = ast_node.parts.map { |p| compile(p) } merged_parts = [] parts.each do |part| if part.is_a?(Lit) && merged_parts.last.is_a?(Lit) last = merged_parts.pop merged_parts << Lit.new(ir: 'Lit', value: last.value + part.value) else merged_parts << part end end if merged_parts.size == 1 merged_parts.first else Seq.new(ir: 'Seq', parts: merged_parts) end when Strling::Core::Esc Esc.new(ir: 'Esc', type: ast_node.type, property: ast_node.property) when Strling::Core::Anchor at = ast_node.at == 'NonWordBoundary' ? 'NotWordBoundary' : ast_node.at Anchor.new(ir: 'Anchor', at: at) when Strling::Core::Look Look.new( ir: 'Look', dir: ast_node.dir, neg: ast_node.neg, body: compile(ast_node.body) ) # Legacy Nodes when Strling::Nodes::Literal Lit.new(ir: 'Lit', value: ast_node.value) when Strling::Nodes::Quantifier mode = if ast_node.possessive 'Possessive' elsif ast_node.lazy 'Lazy' else 'Greedy' end # Handle max being null/nil -> "Inf" max_val = ast_node.max.nil? ? 'Inf' : ast_node.max Quant.new( ir: 'Quant', child: compile(ast_node.target), min: ast_node.min, max: max_val, mode: mode ) when Strling::Nodes::CharacterClass items = ast_node.members.map do |member| if member.is_a?(Strling::Nodes::Literal) Char.new(ir: 'Char', char: member.value) elsif member.is_a?(Strling::Nodes::UnicodeProperty) type = member.negated ? 'P' : 'p' Esc.new(ir: 'Esc', type: type, property: member.value) elsif member.is_a?(Strling::Nodes::Escape) compile(member) else # Fallback or recursive compile if members can be other things compile(member) end end CharClass.new(ir: 'CharClass', negated: ast_node.negated, items: items) when Strling::Nodes::Group Group.new( ir: 'Group', capturing: ast_node.capturing, body: compile(ast_node.body), name: ast_node.name, atomic: ast_node.atomic ? true : nil ) when Strling::Nodes::Alternation Alt.new( ir: 'Alt', branches: ast_node.alternatives.map { |a| compile(a) } ) when Strling::Nodes::UnicodeProperty # If it appears standalone (not in CharClass), it might still be Esc? # In unicode_property_short.json it was inside CharacterClass. # Let's assume it maps to Esc. type = ast_node.negated ? 'P' : 'p' Esc.new(ir: 'Esc', type: type, property: ast_node.value) when Strling::Nodes::Sequence parts = ast_node.parts.map { |p| compile(p) } # Merge adjacent Lit nodes merged_parts = [] parts.each do |part| if part.is_a?(Lit) && merged_parts.last.is_a?(Lit) last = merged_parts.pop merged_parts << Lit.new(ir: 'Lit', value: last.value + part.value) else merged_parts << part end end if merged_parts.size == 1 merged_parts.first else Seq.new(ir: 'Seq', parts: merged_parts) end when Strling::Nodes::Lookahead Look.new( ir: 'Look', dir: 'Ahead', neg: ast_node.negative || false, # AST might not have negative if it's a separate node type "NegativeLookahead" body: compile(ast_node.body) ) when Strling::Nodes::Lookbehind Look.new( ir: 'Look', dir: 'Behind', neg: ast_node.negative || false, body: compile(ast_node.body) ) when Strling::Nodes::Anchor at = ast_node.at == 'NonWordBoundary' ? 'NotWordBoundary' : ast_node.at Anchor.new(ir: 'Anchor', at: at) when Strling::Nodes::Escape type = case ast_node.kind when 'digit' then 'd' when 'not-digit' then 'D' when 'space' then 's' when 'not-space' then 'S' when 'word' then 'w' when 'not-word' then 'W' # Add others if needed else ast_node.kind # Fallback end Esc.new(ir: 'Esc', type: type, property: nil) when Strling::Nodes::BackReference BackRef.new( ir: 'Backref', byIndex: ast_node.index, byName: ast_node.name ) when Strling::Nodes::Range Range.new(ir: 'Range', from: ast_node.from, to: ast_node.to) when Strling::Nodes::Dot Dot.new(ir: 'Dot') else # Fallback # puts "Warning: Unknown AST node for compilation: #{ast_node.class}" nil end end |