xberg 1.1.3

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

//! Types for extraction result diffs.
//!
//! `DiffLine` and `CellChange` are canonical definitions live in
//! `crate::types::revisions` so that `RevisionDelta` can reference them
//! unconditionally without the `diff` feature gate. They are re-exported
//! here so the `crate::diff::DiffLine` path continues to work for callers
//! who import them through the `diff` feature.

use serde::{Deserialize, Serialize};

use crate::types::{extraction::ArchiveEntry, tables::Table};

pub use crate::types::revisions::{CellChange, DiffLine};

/// Options controlling how two `ExtractedDocument` values are compared.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct DiffOptions {
    /// Include metadata changes in the diff. Default: `true`.
    pub include_metadata: bool,
    /// Include embedded-children changes in the diff. Default: `true`.
    pub include_embedded: bool,
    /// Truncate content to this many characters before diffing.
    ///
    /// Useful for very large documents where only the first N characters matter.
    /// `None` means no truncation.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub max_content_chars: Option<usize>,
}

impl Default for DiffOptions {
    fn default() -> Self {
        Self {
            include_metadata: true,
            include_embedded: true,
            max_content_chars: None,
        }
    }
}

/// The complete diff between two `ExtractedDocument` values.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct ExtractionDiff {
    /// Unified-diff hunks for the `content` field.
    ///
    /// Empty when the content is identical.
    pub content_diff: Vec<DiffHunk>,

    /// Tables present in `b` but not in `a` (by index position, excess right-side tables).
    pub tables_added: Vec<Table>,

    /// Tables present in `a` but not in `b` (by index position, excess left-side tables).
    pub tables_removed: Vec<Table>,

    /// Cell-level changes for table pairs that share the same index and dimensions.
    pub tables_changed: Vec<TableDiff>,

    /// Metadata difference, encoded as a JSON object with three top-level keys:
    /// `added` (keys present in `b` but not `a`), `removed` (keys present in `a`
    /// but not `b`), and `changed` (keys whose values differ — each entry is
    /// `{ "from": <value-in-a>, "to": <value-in-b> }`).
    ///
    /// This is NOT RFC 6902 JSON Patch — we deliberately chose a flatter shape
    /// to avoid pulling in a json-patch crate. If you need RFC 6902 semantics
    /// (with JSON Pointer paths) feed `a.metadata` and `b.metadata` to your
    /// preferred json-patch impl directly.
    pub metadata_changed: serde_json::Value,

    /// Changes to embedded archive children.
    pub embedded_changes: EmbeddedChanges,
}

/// A single contiguous hunk in a unified diff.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct DiffHunk {
    /// Starting line number in the old content (0-indexed).
    pub from_line: usize,
    /// Number of lines from the old content in this hunk.
    pub from_count: usize,
    /// Starting line number in the new content (0-indexed).
    pub to_line: usize,
    /// Number of lines from the new content in this hunk.
    pub to_count: usize,
    /// Lines that make up this hunk.
    pub lines: Vec<DiffLine>,
}

/// Cell-level changes for a pair of tables that share the same index.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct TableDiff {
    /// Zero-based index of the table in both `a.tables` and `b.tables`.
    pub from_index: usize,
    /// Zero-based index in `b.tables` (equal to `from_index` for same-dimension tables).
    pub to_index: usize,
    /// Cell-level changes within the table.
    pub cell_changes: Vec<CellChange>,
}

/// Changes to embedded archive children between two results.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct EmbeddedChanges {
    /// Children present in `b` but not in `a` (matched by `path`).
    pub added: Vec<ArchiveEntry>,
    /// Children present in `a` but not in `b` (matched by `path`).
    pub removed: Vec<ArchiveEntry>,
    /// Children present in both but with differing content (matched by `path`).
    ///
    /// Each entry holds the diff of the nested `ExtractedDocument`.
    pub changed: Vec<EmbeddedDiff>,
}

/// Diff for a single embedded archive entry that appears in both results.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[cfg_attr(feature = "api", derive(utoipa::ToSchema))]
pub struct EmbeddedDiff {
    /// Archive-relative path identifying this entry.
    pub path: String,
    /// The recursive diff of the entry's extraction result.
    pub diff: Box<ExtractionDiff>,
}