Module toc 

Table of Contents (TOC) processing module.

This module provides functionality to extract and verify document structure from PDF Table of Contents:

• Detection — Find TOC in document (regex + LLM fallback)
• Parsing — Convert TOC text to structured entries (LLM)
• Assignment — Map TOC pages to physical pages
• Verification — Sample verification of page assignments
• Repair — Fix incorrect assignments

Architecture

PDF Pages
    │
    ▼
┌─────────────────────────────────────────────────┐
│              TocProcessor                        │
│                                                  │
│  ┌─────────┐  ┌─────────┐  ┌─────────┐         │
│  │Detector │─▶│ Parser  │─▶│Assigner │         │
│  └─────────┘  └─────────┘  └────┬────┘         │
│                                │                │
│                                ▼                │
│                         ┌─────────────┐         │
│                         │  Verifier   │         │
│                         └──────┬──────┘         │
│                                │                │
│                                ▼                │
│                         ┌─────────────┐         │
│                         │  Repairer   │         │
│                         └─────────────┘         │
└─────────────────────────────────────────────────┘
    │
    ▼
Vec<TocEntry>

Example

use vectorless::parser::toc::TocProcessor;
use vectorless::parser::pdf::{PdfParser, PdfPage};

// Parse PDF
let pdf_parser = PdfParser::new();
let result = pdf_parser.parse_file("document.pdf".as_ref())?;

// Extract TOC
let processor = TocProcessor::new();
let entries = processor.process(&result.pages).await?;

// Use entries
for entry in &entries {
    println!("{} - Page {:?}", entry.title, entry.physical_page);
}

Structs

IndexRepairer

Index repairer - fixes incorrect page assignments.

IndexVerifier

Index verifier - verifies that TOC entries point to correct pages.

PageAssigner

Page assigner - assigns physical page numbers to TOC entries.

PageAssignerConfig

Page assigner configuration.

PageOffset

Page offset calculation result.

RepairerConfig

Repairer configuration.

TocDetection

Result of TOC detection.

TocDetector

TOC detector - finds table of contents in PDF documents.

TocDetectorConfig

TOC detector configuration.

TocEntry

A single TOC entry.

TocParser

TOC parser - converts raw TOC text to structured entries.

TocParserConfig

TOC parser configuration.

TocProcessor

TOC processor - orchestrates the complete TOC extraction pipeline.

TocProcessorConfig

TOC processor configuration.

VerificationError

Verification error for a single entry.

VerificationReport

Result of TOC verification.

VerifierConfig

Verifier configuration.

Enums

ErrorType

Type of verification error.