1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
//! # pdfraw
//!
//! Layout-preserving PDF text extraction in pure Rust, inspired by
//! [pdfplumber](https://github.com/jsvine/pdfplumber).
//!
//! The core goal is to extract text from PDFs while preserving the original
//! spatial layout: column alignment, line breaks, right-aligned numbers in
//! invoices and credit notes, multi-page documents, etc.
//!
//! ## Quick start
//!
//! ```no_run
//! use pdfraw::prelude::*;
//!
//! # fn main() -> Result<()> {
//! let doc = Document::open("invoice.pdf")?;
//! for page in doc.pages() {
//! let page = page?;
//! let text = page.extract_text_layout(&TextOptions::pdfplumber_defaults())?;
//! println!("--- page {} ---\n{}", page.index(), text);
//! }
//! # Ok(()) }
//! ```
//!
//! ## Modules
//!
//! - [`document`]: top-level [`Document`] and metadata.
//! - [`page`]: per-page [`Page`] handle with text extraction methods.
//! - [`mod@char`]: positioned glyph [`Char`] (post-decoding).
//! - [`word`]: clustered [`Word`] with options.
//! - [`text`]: clustering, word extraction, layout reconstruction.
//! - [`error`]: error type and result alias.
//! - [`prelude`]: convenient re-exports.
// Internal parsing layer — implementation detail, not part of the stable API.
pub
pub use crateChar;
pub use crateDocument;
pub use crate;
pub use cratePage;
pub use crate;
pub use crate;