Struct LopdfBackend 

pub struct LopdfBackend;

The lopdf-based PDF backend.

Provides PDF parsing via lopdf::Document. This is the default backend used by pdfplumber-rs.

Example

use pdfplumber_parse::lopdf_backend::LopdfBackend;
use pdfplumber_parse::PdfBackend;

let doc = LopdfBackend::open(pdf_bytes)?;
let count = LopdfBackend::page_count(&doc);
let page = LopdfBackend::get_page(&doc, 0)?;

Trait Implementations

impl PdfBackend for LopdfBackend

type Document = LopdfDocument

The parsed PDF document type.

type Page = LopdfPage

A reference to a single page within a document.

type Error = BackendError

Backend-specific error type, convertible to PdfError.

fn open(bytes: &[u8]) -> Result<Self::Document, Self::Error>

Parse PDF bytes into a document.

fn open_with_password( bytes: &[u8], password: &[u8], ) -> Result<Self::Document, Self::Error>

Parse PDF bytes into a document, decrypting with the given password.

fn page_count(doc: &Self::Document) -> usize

Return the number of pages in the document.

fn get_page( doc: &Self::Document, index: usize, ) -> Result<Self::Page, Self::Error>

Access a page by 0-based index.

fn page_media_box( doc: &Self::Document, page: &Self::Page, ) -> Result<BBox, Self::Error>

Get the MediaBox for a page.

fn page_crop_box( doc: &Self::Document, page: &Self::Page, ) -> Result<Option<BBox>, Self::Error>

Get the CropBox for a page, if explicitly set.

fn page_trim_box( doc: &Self::Document, page: &Self::Page, ) -> Result<Option<BBox>, Self::Error>

Get the TrimBox for a page, if explicitly set.

fn page_bleed_box( doc: &Self::Document, page: &Self::Page, ) -> Result<Option<BBox>, Self::Error>

Get the BleedBox for a page, if explicitly set.

fn page_art_box( doc: &Self::Document, page: &Self::Page, ) -> Result<Option<BBox>, Self::Error>

Get the ArtBox for a page, if explicitly set.

fn page_rotate( doc: &Self::Document, page: &Self::Page, ) -> Result<i32, Self::Error>

Get the page rotation angle in degrees.

fn document_metadata( doc: &Self::Document, ) -> Result<DocumentMetadata, Self::Error>

Extract document-level metadata from the PDF /Info dictionary.

fn document_bookmarks( doc: &Self::Document, ) -> Result<Vec<Bookmark>, Self::Error>

Extract the document outline (bookmarks / table of contents).

fn document_form_fields( doc: &Self::Document, ) -> Result<Vec<FormField>, Self::Error>

Extract form fields from the document’s AcroForm dictionary.

fn document_signatures( doc: &Self::Document, ) -> Result<Vec<SignatureInfo>, Self::Error>

Extract digital signature information from the document.

fn document_structure_tree( doc: &Self::Document, ) -> Result<Vec<StructElement>, Self::Error>

Extract the document’s structure tree from /StructTreeRoot.

fn page_annotations( doc: &Self::Document, page: &Self::Page, ) -> Result<Vec<Annotation>, Self::Error>

Extract annotations from a page.

fn page_hyperlinks( doc: &Self::Document, page: &Self::Page, ) -> Result<Vec<Hyperlink>, Self::Error>

Extract hyperlinks from a page.

fn interpret_page( doc: &Self::Document, page: &Self::Page, handler: &mut dyn ContentHandler, options: &ExtractOptions, ) -> Result<(), Self::Error>

Interpret the page’s content stream, calling back into the handler.

fn extract_image_content( doc: &Self::Document, page: &Self::Page, image_name: &str, ) -> Result<ImageContent, Self::Error>

Extract image content (raw bytes) from a named image XObject on a page.

fn validate(doc: &Self::Document) -> Result<Vec<ValidationIssue>, Self::Error>

Validate the PDF document and report specification violations.

fn repair( bytes: &[u8], options: &RepairOptions, ) -> Result<(Vec<u8>, RepairResult), Self::Error>

Attempt to repair common PDF issues in the raw bytes.