vibe.review.parsing.structure.builder¶

Structure builder: Convert layout to logical structure.

Converts LayoutPage[] into DocumentStructure by: 1. Classifying blocks (heading, paragraph, list item, etc.) 2. Detecting heading levels from font size and numbering 3. Detecting lists and nesting 4. Establishing reading order 5. Applying structure rules for enhanced classification

StructureConfig ¶

Configuration for structure building.

StructureBuilder ¶

Build document structure from layout pages.

Converts LayoutPage[] into a single DocumentStructure with classified and ordered blocks.

init ¶

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

Initialize the structure builder.

Parameters:	`config` (`StructureConfig \| 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.

build ¶

build(layout_pages: list[LayoutPage], source_path: str | None = None, source_type: str = 'pdf') -> DocumentStructure