xberg 1.1.0

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 107 formats and 371 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
42
43

//! Helper functions and utilities for extraction operations.
//!
//! This module provides shared utilities used across extraction modules.

use crate::Result;
use crate::plugins::InternalDocumentExtractor;
use std::sync::Arc;

/// Get an extractor from the registry.
///
/// This function acquires the registry read lock and retrieves the appropriate
/// extractor for the given MIME type.
///
/// When the `otel` feature is enabled, the returned extractor is wrapped in an
/// [`InstrumentedExtractor`](crate::plugins::extractor::instrumented::InstrumentedExtractor)
/// that adds tracing spans and metrics automatically.
///
/// # Performance
///
/// RwLock read + HashMap lookup is ~100ns, fast enough without caching.
/// Removed thread-local cache to avoid Tokio work-stealing scheduler issues.
pub(in crate::core::extractor) fn get_extractor(mime_type: &str) -> Result<(Arc<dyn InternalDocumentExtractor>, bool)> {
    let registry = crate::plugins::registry::get_document_extractor_registry();
    let registry_read = registry.read();
    let extractor = registry_read.get_registered(mime_type)?;
    let is_builtin = extractor.is_builtin();
    let extractor: Arc<dyn InternalDocumentExtractor> = Arc::new(extractor);

    #[cfg(feature = "otel")]
    {
        Ok((
            Arc::new(crate::plugins::extractor::instrumented::InstrumentedExtractor::new(
                extractor,
            )),
            is_builtin,
        ))
    }

    #[cfg(not(feature = "otel"))]
    {
        Ok((extractor, is_builtin))
    }
}