Struct Config 

pub struct Config { /* private fields */ }

Configuration for PDF text extraction.

Use the builder pattern to customize extraction behavior.

Example

use pdfvec::Config;

// Default configuration
let config = Config::default();

// Custom configuration
let config = Config::default()
    .with_page_separator("\n\n---\n\n")
    .with_parallel(true);

Implementations

impl Config

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

Sets the string inserted between pages in extracted text.

Example

use pdfvec::Config;

let config = Config::default().with_page_separator("\n---\n");

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

Enables or disables parallel page processing.

When enabled, pages are extracted concurrently using rayon. Disable for deterministic output order or when running in environments with limited threading support.

Default: true

Example

use pdfvec::Config;

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

pub fn with_normalize_whitespace(self, normalize: bool) -> Self

Enables or disables whitespace normalization.

When enabled, consecutive whitespace characters are collapsed to a single space and leading/trailing whitespace is trimmed.

Default: true

Example

use pdfvec::Config;

let config = Config::default().with_normalize_whitespace(false);

pub fn page_separator(&self) -> &str

Returns the page separator string.

pub fn parallel(&self) -> bool

Returns whether parallel processing is enabled.

pub fn normalize_whitespace(&self) -> bool

Returns whether whitespace normalization is enabled.

Trait Implementations

impl Clone for Config

fn clone(&self) -> Config

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Config

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

Formats the value using the given formatter.

impl Default for Config

fn default() -> Self

Returns the “default value” for a type.