vibe.review.parsing.semantic.extractor

Semantic extraction from document structure.

Extracts contract-specific semantics: - Clause numbering and hierarchy - Definitions - Cross-references - Parties - Rule-based tagging for enhanced classification

SemanticConfig

Configuration for semantic extraction.

SemanticExtractor

Extract semantic information from document structure.

Converts DocumentStructure into SemanticDocument with: - Hierarchical clause structure - Defined terms - Resolved cross-references - Identified parties - Rule-based semantic tagging

__init__

__init__(config: SemanticConfig | None = None, rules_dir: Path | None = None, rule_engine: RuleEngine | None = None) -> None

Initialize the semantic extractor.

Parameters:
  • config (SemanticConfig | None, default: None ) –

    Configuration options. Uses defaults if not provided.

  • rules_dir (Path | None, default: None ) –

    Directory containing rule YAML files. Defaults to built-in rules.

  • rule_engine (RuleEngine | None, default: None ) –

    Pre-configured rule engine. If provided, rules_dir is ignored.

extract

extract(structure: DocumentStructure) -> SemanticDocument

Extract semantic information from document structure.

Parameters:
Returns: