[dependencies]
pdfvec = "0.1"

// One-liner extraction
let text = pdfvec::extract(&std::fs::read("document.pdf")?)?;

use pdfvec::{Extractor, Result};

fn main() -> Result<()> {
    let data = std::fs::read("document.pdf")?;

    // Simple extraction
    let text = Extractor::new().extract(&data)?;

    // With configuration
    let text = Extractor::new()
        .parallel(true)
        .page_separator("\n---\n")
        .normalize_whitespace(true)
        .extract(&data)?;

    println!("{text}");
    Ok(())
}

use pdfvec::{Extractor, Result};

fn main() -> Result<()> {
    let data = std::fs::read("document.pdf")?;
    let doc = Extractor::new().extract_document(&data)?;

    println!("Pages: {}", doc.page_count());
    println!("Total chars: {}", doc.total_chars());

    for page in doc.pages() {
        println!("Page {}: {} chars", page.number(), page.char_count());
    }
    Ok(())
}

use pdfvec::{Extractor, Result};

fn main() -> Result<()> {
    let data = std::fs::read("large.pdf")?;

    for page_result in Extractor::new().pages(&data) {
        let page = page_result?;
        // Process page immediately, memory freed after each iteration
        println!("Page {}: {} chars", page.number(), page.char_count());
    }
    Ok(())
}

use pdfvec::{Chunker, ChunkStrategy};

let text = "First sentence. Second sentence.\n\nNew paragraph here.";

// Fixed-size chunks with overlap
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Fixed)
    .chunk_size(100)
    .overlap(20)
    .chunks(text)
    .collect();

// Paragraph-based chunking
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Paragraph)
    .chunks(text)
    .collect();

// Sentence-based chunking
let chunks: Vec<_> = Chunker::new(ChunkStrategy::Sentence)
    .chunks(text)
    .collect();

for chunk in chunks {
    println!("[{}] {}", chunk.index(), chunk.text());
}

use pdfvec::{Extractor, Result};

fn main() -> Result<()> {
    let data = std::fs::read("document.pdf")?;
    let meta = Extractor::new().extract_metadata(&data)?;

    println!("Title: {:?}", meta.title());
    println!("Author: {:?}", meta.author());
    println!("Pages: {}", meta.page_count());

    if let Some(date) = meta.creation_date() {
        println!("Created: {}", date.format("%Y-%m-%d"));
    }
    Ok(())
}

# Install
cargo install pdfvec

# Extract text
pdfvec extract document.pdf

# Extract to file
pdfvec extract document.pdf -o output.txt

# Show metadata
pdfvec metadata document.pdf

# Process directory
pdfvec extract ./papers/ -o ./output/