xberg 1.1.2

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
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

//! PDF metadata types (backend-agnostic).
//!
//! These types are shared between the native extraction backend and any callers
//! that consume PDF metadata. No PDF-library-specific dependencies.

use serde::{Deserialize, Serialize};

use crate::types::PageStructure;

/// PDF-specific metadata.
///
/// Contains metadata fields specific to PDF documents that are not in the common
/// `Metadata` structure. Common fields like title, authors, keywords, and dates
/// are at the `Metadata` level.
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct PdfMetadata {
    /// PDF version (e.g., "1.7", "2.0")
    #[serde(skip_serializing_if = "Option::is_none")]
    pub pdf_version: Option<String>,

    /// PDF producer (application that created the PDF)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub producer: Option<String>,

    /// Whether the PDF is encrypted/password-protected
    #[serde(skip_serializing_if = "Option::is_none")]
    pub is_encrypted: Option<bool>,

    /// First page width in points (1/72 inch)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub width: Option<i64>,

    /// First page height in points (1/72 inch)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub height: Option<i64>,

    /// Total number of pages in the PDF document
    #[serde(skip_serializing_if = "Option::is_none")]
    pub page_count: Option<u32>,

    /// How strongly the document's most scan-like page resembles a scan, in `[0.0, 1.0]`.
    ///
    /// `None` when the document could not be inspected. A full-page raster with no
    /// visible text scores at least `0.85`; a born-digital slide with a full-bleed
    /// background image scores `0.50`.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub scanned_confidence: Option<f32>,

    /// Pages that look like scans (1-indexed), using the default confidence threshold.
    ///
    /// `None` when the document could not be inspected; empty when no page qualifies.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub scanned_pages: Option<Vec<u32>>,

    /// Pages the `auto` layout strategy skipped (1-indexed).
    ///
    /// `None` unless layout detection ran with `LayoutStrategy::Auto`; empty
    /// when the gate selected every page.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub layout_gated_pages: Option<Vec<u32>>,

    /// Why the `auto` layout gate selected or skipped each page.
    ///
    /// Index `i` is page `i + 1`. Snake_case values such as `multi_column`,
    /// `table_grid`, or `plain_text` (the skip reason). `None` unless layout
    /// detection ran with `LayoutStrategy::Auto`.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub layout_gate_reasons: Option<Vec<String>>,
}
/// Complete PDF extraction metadata including common and PDF-specific fields.
///
/// Combines common document fields (title, authors, dates) with PDF-specific
/// metadata and optional page structure information.
#[cfg_attr(alef, alef(skip))]
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct PdfExtractionMetadata {
    /// Document title
    #[serde(skip_serializing_if = "Option::is_none")]
    pub title: Option<String>,

    /// Document subject or description
    #[serde(skip_serializing_if = "Option::is_none")]
    pub subject: Option<String>,

    /// Document authors (parsed from PDF Author field)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub authors: Option<Vec<String>>,

    /// Document keywords (parsed from PDF Keywords field)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub keywords: Option<Vec<String>>,

    /// Creation timestamp (ISO 8601 format)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub created_at: Option<String>,

    /// Last modification timestamp (ISO 8601 format)
    #[serde(skip_serializing_if = "Option::is_none")]
    pub modified_at: Option<String>,

    /// Application or user that created the document
    #[serde(skip_serializing_if = "Option::is_none")]
    pub created_by: Option<String>,

    /// PDF-specific metadata
    pub pdf_specific: PdfMetadata,

    /// Page structure with boundaries and optional per-page metadata
    #[serde(skip_serializing_if = "Option::is_none")]
    pub page_structure: Option<PageStructure>,
}
#[cfg_attr(alef, alef(skip))]
/// Common PDF metadata fields extracted from the document info dictionary.
///
/// Used as an intermediate type during extraction before building `PdfExtractionMetadata`.
#[cfg_attr(alef, alef(skip))]
#[derive(Debug, Clone, Default)]
pub struct CommonPdfMetadata {
    /// Document title from the PDF Info dictionary.
    pub title: Option<String>,
    /// Document subject from the PDF Info dictionary.
    pub subject: Option<String>,
    /// Document authors parsed from the PDF Author field.
    pub authors: Option<Vec<String>>,
    /// Keywords parsed from the PDF Keywords field.
    pub keywords: Option<Vec<String>>,
    /// Creation timestamp in ISO 8601 format.
    pub created_at: Option<String>,
    /// Last modification timestamp in ISO 8601 format.
    pub modified_at: Option<String>,
    /// Creator application or author name.
    pub created_by: Option<String>,
}