kreuzberg 4.3.0

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 75+ formats with async/sync APIs.
Documentation 
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81

//! PDF document processing utilities.
//!
//! This module provides low-level PDF processing functions for text extraction,
//! metadata parsing, image extraction, and page rendering. Used internally by
//! the PDF extractor plugin.
//!
//! # Features
//!
//! - **Text extraction**: Extract text content from PDFs using `pdfium-render`
//! - **Metadata extraction**: Parse PDF metadata (title, author, creation date, etc.)
//! - **Image extraction**: Extract embedded images from PDF pages
//! - **Page rendering**: Render PDF pages to images for OCR processing
//! - **Error handling**: Comprehensive PDF-specific error types
//!
//! # Example
//!
//! ```rust
//! use kreuzberg::pdf::{extract_text_from_pdf, extract_metadata};
//!
//! # fn example() -> kreuzberg::Result<()> {
//! let pdf_bytes = std::fs::read("document.pdf")?;
//!
//! // Extract text
//! let text = extract_text_from_pdf(&pdf_bytes)?;
//! println!("Text: {}", text);
//!
//! // Extract metadata
//! let metadata = extract_metadata(&pdf_bytes)?;
//! println!("PDF version: {:?}", metadata.pdf_version);
//! # Ok(())
//! # }
//! ```
//!
//! # Note
//!
//! This module requires the `pdf` feature. The `ocr` feature enables additional
//! functionality in the PDF extractor for rendering pages to images.
#[cfg(feature = "pdf")]
pub(crate) mod bindings;
#[cfg(all(feature = "pdf", feature = "bundled-pdfium"))]
pub mod bundled;
#[cfg(feature = "pdf")]
pub mod error;
#[cfg(feature = "pdf")]
pub mod fonts;
#[cfg(feature = "pdf")]
pub mod hierarchy;
#[cfg(feature = "pdf")]
pub mod images;
#[cfg(feature = "pdf")]
pub mod metadata;
#[cfg(feature = "pdf")]
pub mod rendering;
#[cfg(feature = "pdf")]
pub mod table;
#[cfg(feature = "pdf")]
pub mod text;

#[cfg(feature = "pdf")]
pub use crate::core::config::HierarchyConfig;
#[cfg(all(feature = "pdf", feature = "bundled-pdfium"))]
pub use bundled::extract_bundled_pdfium;
#[cfg(feature = "pdf")]
pub use error::PdfError;
#[cfg(feature = "pdf")]
pub use fonts::{cached_font_count, get_font_descriptors, initialize_font_cache};
#[cfg(feature = "pdf")]
pub use hierarchy::{
    BoundingBox, CharData, FontSizeCluster, HierarchyLevel, TextBlock, assign_hierarchy_levels,
    assign_hierarchy_levels_from_clusters, cluster_font_sizes, extract_chars_with_fonts, should_trigger_ocr,
};
#[cfg(feature = "pdf")]
pub use images::{PdfImage, PdfImageExtractor, extract_images_from_pdf};
#[cfg(feature = "pdf")]
pub use metadata::extract_metadata;
#[cfg(feature = "pdf")]
pub use rendering::{PageRenderOptions, render_page_to_image};
#[cfg(feature = "pdf")]
pub use table::extract_words_from_page;
#[cfg(feature = "pdf")]
pub use text::extract_text_from_pdf;