spectre_parse 1.0.0

//! `spectre_parse` — a lazy, read-only PDF parser.
//!
//! # Design — what "lazy" means here
//!
//! [`Document::open`] does **only** these steps eagerly:
//!
//! 1. Locate `%PDF-x.y` header (≤ 1 KB scan).
//! 2. Locate `startxref` (≤ 4 KB scan from EOF).
//! 3. Parse the xref table (or xref stream) at the start offset, plus
//! every preceding `Prev` xref the trailer chain points at.
//! 4. Parse the trailer dictionary.
//!
//! Steps 1–4 don't materialize a single body object. The returned
//! [`Document`] holds a borrow of the source bytes plus an indexed
//! `BTreeMap<ObjectId, XrefEntry>`. Object bodies are parsed on the
//! first call to [`Document::get_object`] (or anything that reaches
//! `get_object` transitively — page tree walks, font lookups, etc.)
//! and cached in an interior-mutable cell so subsequent reads are a
//! plain map lookup.
//!
//! # Scope (read-only)
//!
//! `spectre_parse` reads PDFs and decrypts password-protected documents
//! (full PDF Standard Security Handler: RC4 40/128-bit, AES-128 CBC,
//! AES-256 R=5/R=6 with Algorithm 2.B — see [`crate::decrypt`]). It does
//! NOT write PDFs, edit objects, or run JavaScript in form widgets. It
//! exists to serve the read paths inside `spectre_pdf` (text extraction,
//! table detection, structural metadata) with the smallest possible
//! parse cost. The matching write/modify surface lives in
//! `lopdf-fork/` for development-time use.

#![deny(rust_2018_idioms)]
#![warn(missing_docs)]

mod cmap;
mod content;
mod decrypt;
mod document;
mod encoding;
mod error;
mod filter;
mod object;
mod parser;
mod xref;

pub use content::{Content, Operation};
pub use document::{
    Document, FormField, FormFieldType, ImageEncoding, PdfImageInfo, TocEntry,
};
pub use encoding::{resolve_page_encodings, Encoding};
pub use error::{Error, ParseError, Result};
pub use object::{Dictionary, Object, ObjectId, Stream};