Struct Extractor 

pub struct Extractor { /* private fields */ }

PDF text extractor with configurable behavior.

Use the builder pattern to configure extraction, then call extract, extract_document, or pages.

Example

use pdfvec::{Extractor, Result};

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

    let text = Extractor::new()
        .parallel(false)
        .normalize_whitespace(true)
        .extract(&data)?;

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

Implementations

impl Extractor

pub fn new() -> Self

Creates a new extractor with default configuration.

Example

use pdfvec::Extractor;

let extractor = Extractor::new();

pub fn with_config(config: Config) -> Self

Creates a new extractor with the given configuration.

Example

use pdfvec::{Extractor, Config};

let config = Config::default().with_parallel(false);
let extractor = Extractor::with_config(config);

pub fn parallel(self, enabled: bool) -> Self

Enables or disables parallel page processing.

Default: true

Example

use pdfvec::Extractor;

let extractor = Extractor::new().parallel(false);

pub fn page_separator(self, separator: impl Into<String>) -> Self

Sets the string inserted between pages.

Default: "\n\n"

Example

use pdfvec::Extractor;

let extractor = Extractor::new().page_separator("\n---\n");

pub fn normalize_whitespace(self, enabled: bool) -> Self

Enables or disables whitespace normalization.

When enabled, consecutive whitespace is collapsed to single spaces.

Default: true

Example

use pdfvec::Extractor;

let extractor = Extractor::new().normalize_whitespace(false);

pub fn config(&self) -> &Config

Returns a reference to the extractor’s configuration.

Example

use pdfvec::Extractor;

let extractor = Extractor::new();
assert!(extractor.config().parallel());

pub fn extract(&self, data: &[u8]) -> Result<String>

Extracts all text from PDF data as a single string.

Pages are joined with the configured separator.

Errors

Returns an error if:

• The data is empty (Error::EmptyDocument)
• The PDF structure is invalid (Error::InvalidStructure)
• The PDF is encrypted (Error::EncryptedDocument)
• Page extraction fails (Error::PageExtractionFailed)

Example

use pdfvec::{Extractor, Result};

fn main() -> Result<()> {
    let data = std::fs::read("document.pdf")?;
    let text = Extractor::new().extract(&data)?;
    println!("Extracted {} characters", text.len());
    Ok(())
}

pub fn extract_document(&self, data: &[u8]) -> Result<Document>

Extracts a structured Document from PDF data.

Returns a document with individual page access.

Errors

Same as extract.

Example

use pdfvec::{Extractor, Result};

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

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

pub fn pages<'a>(&'a self, data: &'a [u8]) -> PageIterator<'a>

Returns a streaming iterator over pages.

Pages are extracted on-demand, maintaining constant memory usage regardless of PDF size. This is ideal for processing large documents.

Note: Streaming extraction is always sequential (not parallel).

Example

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?;
        if page.char_count() > 100 {
            println!("Page {} has content", page.number());
        }
    }
    Ok(())
}

pub fn extract_metadata(&self, data: &[u8]) -> Result<Metadata>

Extracts document metadata without processing page content.

This is faster than full extraction when you only need metadata like title, author, or creation date.

Errors

Returns an error if:

• The data is empty (Error::EmptyDocument)
• The PDF structure is invalid (Error::PdfLibrary)

Example

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());
    Ok(())
}

Trait Implementations

impl Clone for Extractor

fn clone(&self) -> Extractor

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Extractor

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Extractor

fn default() -> Self

Returns the “default value” for a type.