kreuzberg 4.4.6

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 88+ 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

//! Core types for the PDF-to-Markdown pipeline.

use crate::pdf::hierarchy::SegmentData;

/// A line of text composed of segments sharing a common baseline.
#[derive(Debug, Clone)]
pub(super) struct PdfLine {
    pub segments: Vec<SegmentData>,
    pub baseline_y: f32,
    pub dominant_font_size: f32,
    pub is_bold: bool,
    pub is_monospace: bool,
}

/// A paragraph composed of lines, with optional heading classification.
#[derive(Debug, Clone)]
pub(super) struct PdfParagraph {
    pub lines: Vec<PdfLine>,
    pub dominant_font_size: f32,
    pub heading_level: Option<u8>,
    pub is_bold: bool,
    pub is_list_item: bool,
    pub is_code_block: bool,
}