Rust API

Crate: edgeparse-core

convert(path, config) -> Result<Document>

Parse a PDF file and return a structured Document.

use std::path::Path;
use edgeparse_core::api::config::ProcessingConfig;
use edgeparse_core::convert;

let config = ProcessingConfig::default();
let doc = convert(Path::new("document.pdf"), &config)?;

println!("Pages: {}", doc.number_of_pages);
println!("Elements: {}", doc.kids.len());

Document struct

Field	Type	Description
file_name	String	Source file name
number_of_pages	usize	Total pages
author	Option<String>	PDF author metadata
title	Option<String>	PDF title metadata
kids	Vec<ContentElement>	Extracted elements in reading order

Output Renderers

use edgeparse_core::output;

// Markdown
let md = output::markdown::to_markdown(&doc)?;

// HTML
let html = output::html::to_html(&doc)?;

// JSON (legacy-compatible)
let json = output::legacy_json::to_legacy_json_string(&doc, "document")?;

Crate: pdf-cos

Low-level PDF COS object parser. Used internally by edgeparse-core.

[dependencies]
edgeparse-core = "0.1"