kreuzberg 4.3.8

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

//! Type definitions for HTML extraction.

use bytes::Bytes;
use serde::{Deserialize, Serialize};

pub use html_to_markdown_rs::{
    CodeBlockStyle, HeadingStyle, HighlightStyle, ListIndentType, NewlineStyle, PreprocessingOptions,
    PreprocessingPreset, WhitespaceMode,
};

/// Result of HTML extraction with optional images and warnings.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HtmlExtractionResult {
    pub markdown: String,
    pub images: Vec<ExtractedInlineImage>,
    pub warnings: Vec<String>,
}

/// Extracted inline image with metadata.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ExtractedInlineImage {
    /// Uses `bytes::Bytes` for cheap cloning of large buffers.
    pub data: Bytes,
    pub format: String,
    pub filename: Option<String>,
    pub description: Option<String>,
    pub dimensions: Option<(u32, u32)>,
    pub attributes: Vec<(String, String)>,
}