Struct Document 

pub struct Document { /* private fields */ }

A fully extracted PDF document.

Contains all pages and provides convenient access patterns.

Example

use pdfvec::{Extractor, Result};

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

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

Implementations

impl Document

pub fn page_count(&self) -> usize

Returns the number of pages in the document.

pub fn is_empty(&self) -> bool

Returns true if the document has no pages with text.

pub fn pages(&self) -> impl Iterator<Item = &Page>

Returns an iterator over the pages.

pub fn iter(&self) -> Iter<'_, Page>

Returns an iterator over the pages (same as pages).

pub fn page(&self, number: u32) -> Option<&Page>

Returns a specific page by 1-indexed number.

Returns None if the page number is out of range.

pub fn into_pages(self) -> Vec<Page>

Consumes the document and returns all pages.

pub fn text(&self, separator: &str) -> String

Returns all text concatenated with the given separator.

pub fn full_text(&self) -> String

Returns all text concatenated with default separator (double newline).

pub fn total_chars(&self) -> usize

Returns total character count across all pages.

Trait Implementations

impl Clone for Document

fn clone(&self) -> Document

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Document

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

Formats the value using the given formatter.

impl<'a> IntoIterator for &'a Document

type Item = &'a Page

The type of the elements being iterated over.

type IntoIter = Iter<'a, Page>

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.

impl IntoIterator for Document

type Item = Page

The type of the elements being iterated over.

type IntoIter = IntoIter<Page>

Which kind of iterator are we turning this into?

fn into_iter(self) -> Self::IntoIter

Creates an iterator from a value.