kreuzberg 4.8.3

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 91+ formats and 248 programming languages via tree-sitter code intelligence 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

//! PDF annotation types.

use super::extraction::BoundingBox;
use serde::{Deserialize, Serialize};

/// Type of PDF annotation.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
#[serde(rename_all = "snake_case")]
pub enum PdfAnnotationType {
    /// Sticky note / text annotation
    Text,
    /// Highlighted text region
    Highlight,
    /// Hyperlink annotation
    Link,
    /// Rubber stamp annotation
    Stamp,
    /// Underline text markup
    Underline,
    /// Strikeout text markup
    StrikeOut,
    /// Any other annotation type
    Other,
}

/// A PDF annotation extracted from a document page.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct PdfAnnotation {
    /// The type of annotation.
    pub annotation_type: PdfAnnotationType,
    /// Text content of the annotation (e.g., comment text, link URL).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub content: Option<String>,
    /// Page number where the annotation appears (1-indexed).
    pub page_number: usize,
    /// Bounding box of the annotation on the page.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub bounding_box: Option<BoundingBox>,
}