xberg 1.0.7

High-performance document intelligence library for Rust. Extract text, metadata, and structured data from PDFs, Office documents, images, and 101 formats and 306 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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198

//! Per-file extraction configuration overrides for batch processing.
//!
//! This module contains [`FileExtractionConfig`], a subset of [`super::ExtractionConfig`]
//! where every field is optional. When used with batch extraction functions, each file
//! can specify overrides that are merged with the batch-level default config.
//!
//! Fields that are batch-level concerns (concurrency, caching, acceleration, security)
//! are intentionally excluded and can only be set on the batch-level [`super::ExtractionConfig`].

use serde::{Deserialize, Serialize};

use super::super::formats::OutputFormat;
use super::super::ocr::{OcrConfig, OcrStrategy};
use super::super::page::PageConfig;
use super::super::processing::{ChunkingConfig, PostProcessorConfig};
use super::types::{ImageExtractionConfig, LanguageDetectionConfig, TokenReductionOptions, UrlExtractionConfig};

/// Per-file extraction configuration overrides for batch processing.
///
/// All fields are `Option<T>` — `None` means "use the batch-level default."
/// This type is used by [`crate::ExtractInput::config`] and [`crate::extract_batch`]
/// to allow heterogeneous extraction settings within a single batch.
///
/// # Excluded Fields
///
/// The following [`super::ExtractionConfig`] fields are batch-level only and
/// cannot be overridden per file:
/// - `max_concurrent_extractions` — controls batch parallelism
/// - `use_cache` — global caching policy
/// - `acceleration` — shared ONNX execution provider
/// - `security_limits` — global archive security policy
///
/// # Example
///
/// ```rust
/// use xberg::FileExtractionConfig;
///
/// // Override just OCR forcing for a specific file
/// let config = FileExtractionConfig {
///     force_ocr: Some(true),
///     ..Default::default()
/// };
/// ```
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
#[serde(default)]
pub struct FileExtractionConfig {
    /// Override quality post-processing for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub enable_quality_processing: Option<bool>,

    /// Override OCR configuration for this file (None in the Option = use batch default).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub ocr: Option<OcrConfig>,

    /// Override force OCR for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub force_ocr: Option<bool>,

    /// Override the OCR page-selection strategy for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub ocr_strategy: Option<OcrStrategy>,

    /// Override force OCR pages for this file (1-indexed page numbers).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub force_ocr_pages: Option<Vec<u32>>,

    /// Override disable OCR for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub disable_ocr: Option<bool>,

    /// Override chunking configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub chunking: Option<ChunkingConfig>,

    /// Override content filtering configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub content_filter: Option<super::super::content_filter::ContentFilterConfig>,

    /// Override image extraction configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub images: Option<ImageExtractionConfig>,

    /// Override PDF options for this file.
    #[cfg(feature = "pdf")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pdf_options: Option<super::super::pdf::PdfConfig>,

    /// Override token reduction for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub token_reduction: Option<TokenReductionOptions>,

    /// Override language detection for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub language_detection: Option<LanguageDetectionConfig>,

    /// Override page extraction for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pages: Option<PageConfig>,

    /// Override keyword extraction for this file.
    #[cfg(any(feature = "keywords-yake", feature = "keywords-rake"))]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub keywords: Option<crate::keywords::KeywordConfig>,

    /// Override post-processor for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub postprocessor: Option<PostProcessorConfig>,

    /// Override HTML conversion options for this file.
    #[cfg(feature = "html")]
    #[serde(skip_serializing_if = "Option::is_none")]
    #[cfg_attr(alef, alef(skip))]
    pub html_options: Option<html_to_markdown_rs::ConversionOptions>,

    /// Override styled HTML output configuration for this file.
    #[cfg(feature = "html")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub html_output: Option<super::super::html_output::HtmlOutputConfig>,

    /// Override result format for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub result_format: Option<crate::types::ResultFormat>,

    /// Override output content format for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub output_format: Option<OutputFormat>,

    /// Override document structure output for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub include_document_structure: Option<bool>,

    /// Override layout detection for this file.
    #[cfg(feature = "layout-types")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub layout: Option<super::super::layout::LayoutDetectionConfig>,

    /// Transcription configuration (see ExtractionConfig for docs).
    #[cfg(feature = "transcription-types")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub transcription: Option<super::super::transcription::TranscriptionConfig>,

    /// Override per-file extraction timeout in seconds.
    ///
    /// When set, the extraction for this file will be canceled after the
    /// specified duration. A timed-out file produces an error result without
    /// affecting other files in the batch.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub timeout_secs: Option<u64>,

    /// Override tree-sitter configuration for this file.
    #[cfg(feature = "tree-sitter")]
    #[serde(skip_serializing_if = "Option::is_none")]
    pub tree_sitter: Option<super::super::tree_sitter::TreeSitterConfig>,

    /// Override structured extraction configuration for this file.
    ///
    /// When set, enables LLM-based structured extraction with a JSON schema
    /// for this specific file. The extracted content is sent to a VLM/LLM
    /// and the response is parsed according to the provided schema.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub structured_extraction: Option<super::super::llm::StructuredExtractionConfig>,

    /// Override URL ingestion and crawl configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub url: Option<UrlExtractionConfig>,

    /// Override named-entity recognition configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub ner: Option<super::super::ner::NerConfig>,

    /// Override redaction configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub redaction: Option<super::super::redaction::RedactionConfig>,

    /// Override summarization configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub summarization: Option<super::super::summarization::SummarizationConfig>,

    /// Override translation configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub translation: Option<super::super::translation::TranslationConfig>,

    /// Override per-page classification configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub page_classification: Option<super::super::classification::PageClassificationConfig>,

    /// Override per-chunk classification configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub chunk_classification: Option<super::super::chunk_classification::ChunkClassificationConfig>,

    /// Override VLM captioning configuration for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub captioning: Option<super::super::captioning::CaptioningConfig>,

    /// Override QR-code detection for this file.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub qr_codes: Option<bool>,
}