Trait DocumentParser

Source

pub trait DocumentParser: Send + Sync {
    // Required methods
    fn format(&self) -> DocumentFormat;
    fn parse<'life0, 'life1, 'async_trait>(
        &'life0 self,
        content: &'life1 str,
    ) -> Pin<Box<dyn Future<Output = Result<ParseResult>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;

    // Provided method
    fn parse_file<'life0, 'life1, 'async_trait>(
        &'life0 self,
        path: &'life1 Path,
    ) -> Pin<Box<dyn Future<Output = Result<ParseResult>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait { ... }
}

Expand description

A parser for extracting content from documents.

Implementations parse different document formats and produce a sequence of raw nodes that can be organized into a tree.

§Example

use vectorless::parser::{DocumentParser, MarkdownParser};

let parser = MarkdownParser::new();
let content = "# Title\n\nContent here.";
let result = parser.parse(content).await?;
println!("Found {} nodes", result.node_count());