Struct PdfDocument 

pub struct PdfDocument { /* private fields */ }

High-level PDF document handle.

Implementations

impl PdfDocument

pub fn open(data: impl Into<PdfData>) -> Result<Self>

Open a PDF from bytes.

pub fn open_with_processing_limits( data: impl Into<PdfData>, limits: ProcessingLimits, ) -> Result<Self>

Open a PDF from bytes with processing limits.

pub fn open_with_password( data: impl Into<PdfData>, password: &str, ) -> Result<Self>

Open a password-protected PDF.

pub fn open_with_password_and_processing_limits( data: impl Into<PdfData>, password: &str, limits: ProcessingLimits, ) -> Result<Self>

Open a password-protected PDF with processing limits.

pub fn pdf(&self) -> &Pdf

Access the underlying parsed PDF.

pub fn set_settings(&mut self, settings: InterpreterSettings)

Set interpreter settings (font resolver, cmap resolver, etc.).

pub fn page_count(&self) -> usize

Number of pages.

pub fn page_geometry(&self, index: usize) -> Result<PageGeometry>

Get the geometry of a page.

pub fn render_page( &self, index: usize, options: &RenderOptions, ) -> Result<RenderedPage>

Render a single page.

If the document contains an XFA template, it is automatically flattened to static PDF content before rendering. This prevents the “Please wait” placeholder page that Adobe Reader would show when rendering an XFA PDF with a conventional renderer. If flattening fails, rendering falls back to the original document as a best-effort path.

pub fn render_page_with_config( &self, index: usize, config: &RenderConfig, ) -> Result<RenderedPage>

Render a single page using the high-level render config.

XFA documents are auto-flattened before rendering (same as render_page). If flattening fails, rendering falls back to the original document.

pub fn render_page_cmyk(&self, index: usize, dpi: u32) -> Result<RenderedPage>

Render a single page to a CMYK buffer.

pub fn render_all(&self, options: &RenderOptions) -> Vec<RenderedPage>

Render all pages, in parallel when the parallel feature is enabled.

pub fn render_all_with_config(&self, config: &RenderConfig) -> Vec<RenderedPage>

Render all pages using the high-level render config.

pub fn thumbnail( &self, index: usize, options: &ThumbnailOptions, ) -> Result<RenderedPage>

Generate a thumbnail for a single page.

pub fn thumbnails_all(&self, options: &ThumbnailOptions) -> Vec<RenderedPage>

Generate thumbnails for all pages, in parallel when the parallel feature is enabled.

pub fn extract_text(&self, index: usize) -> Result<String>

Extract text from a page as a single string.

pub fn extract_text_blocks(&self, index: usize) -> Result<Vec<TextBlock>>

Extract structured text blocks from a page.

pub fn extract_all_text_blocks(&self) -> Vec<Vec<TextBlock>>

Extract structured text blocks from all pages, reusing interpreter settings.

pub fn extract_acroform_text(&self) -> String

Extract text values from AcroForm fields, including push-button captions.

Returns a single string concatenating all non-empty field values separated by newlines. Useful when the document stores its readable content in form field values rather than (or in addition to) page content streams.

pub fn extract_all_text(&self) -> String

Extract all text from the document: page content streams plus AcroForm field values. Mirrors pdftotext behaviour.

pub fn search_text(&self, query: &str) -> Vec<usize>

Simple text search: returns page indices containing the query string.

pub fn info(&self) -> DocumentInfo

Extract document metadata.

pub fn bookmarks(&self) -> Vec<BookmarkItem>

Extract document outline / bookmarks.

pub fn ocr_page( &self, index: usize, backend: &dyn OcrBackend, dpi: f64, ) -> Result<OcrResult>

Run OCR on a page and return the recognized text and word positions.

The page is rendered at dpi (default 150) before recognition. Pass any [OcrBackend] implementation; use [OcrsBackend::try_default] to load the pure-Rust ocrs engine from the standard model paths.

Example

use pdf_engine::{PdfDocument, OcrsBackend, RenderOptions};

let doc = PdfDocument::open(std::fs::read("scan.pdf").unwrap()).unwrap();
let backend = OcrsBackend::try_default().unwrap();
let result = doc.ocr_page(0, &backend, 150.0_f64).unwrap();
println!("{}", result.text);