xberg 1.2.6 → 1.2.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/ext/xberg_rb/native/Cargo.lock +17 -17
- data/ext/xberg_rb/native/Cargo.toml +5 -5
- data/ext/xberg_rb/src/lib.rs +19 -1
- data/lib/xberg/version.rb +2 -2
- data/sig/types.rbs +3 -2
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: a84235cf1e73cb2055bf5c3e942400d7b91f2c6a9476db88355af230fe2dc940
|
|
4
|
+
data.tar.gz: 1000c9b90f339649e9ab7a673a9a94ef520a998f1f0df7d211c3488697c94333
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 22418ebea226122fb520449e3abe72b69599c258817df7426915818e3601af8e3881b902ad5c1e11ce3f3379c4038f4a0efb11cc3cbbcf3363e890103699525f
|
|
7
|
+
data.tar.gz: 95fb2e4b9b00c01db6081c088666a229b12dec67bc992a6f67b2fbcb42b52df25c85720a5db26352a995d4fdd07ffefbb5bcd79eb72b7cc8dae6f14f042982e0
|
|
@@ -9024,9 +9024,9 @@ dependencies = [
|
|
|
9024
9024
|
|
|
9025
9025
|
[[package]]
|
|
9026
9026
|
name = "xberg"
|
|
9027
|
-
version = "1.2.
|
|
9027
|
+
version = "1.2.7"
|
|
9028
9028
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9029
|
-
checksum = "
|
|
9029
|
+
checksum = "346e6f854ea416087ebdb236f66e06579d29eb6510060e978691b398c49fbe33"
|
|
9030
9030
|
dependencies = [
|
|
9031
9031
|
"aes-gcm",
|
|
9032
9032
|
"ahash",
|
|
@@ -9162,9 +9162,9 @@ dependencies = [
|
|
|
9162
9162
|
|
|
9163
9163
|
[[package]]
|
|
9164
9164
|
name = "xberg-candle-ocr"
|
|
9165
|
-
version = "1.2.
|
|
9165
|
+
version = "1.2.7"
|
|
9166
9166
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9167
|
-
checksum = "
|
|
9167
|
+
checksum = "b72c64105ab2017c067906c6930da9d1e264b3dac9aaec2a7def549f7dae66a1"
|
|
9168
9168
|
dependencies = [
|
|
9169
9169
|
"base64 0.23.1",
|
|
9170
9170
|
"candle-core",
|
|
@@ -9184,9 +9184,9 @@ dependencies = [
|
|
|
9184
9184
|
|
|
9185
9185
|
[[package]]
|
|
9186
9186
|
name = "xberg-gliner"
|
|
9187
|
-
version = "1.2.
|
|
9187
|
+
version = "1.2.7"
|
|
9188
9188
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9189
|
-
checksum = "
|
|
9189
|
+
checksum = "68a308e628e1b1ed77c742f73933d30c5745d93c15c83e96124a10e8abea7ad5"
|
|
9190
9190
|
dependencies = [
|
|
9191
9191
|
"getrandom 0.2.17",
|
|
9192
9192
|
"getrandom 0.3.4",
|
|
@@ -9200,9 +9200,9 @@ dependencies = [
|
|
|
9200
9200
|
|
|
9201
9201
|
[[package]]
|
|
9202
9202
|
name = "xberg-libheif"
|
|
9203
|
-
version = "1.2.
|
|
9203
|
+
version = "1.2.7"
|
|
9204
9204
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9205
|
-
checksum = "
|
|
9205
|
+
checksum = "2a6cef1ee4af2779af1f0622e0a1e7e15b682e7b5fcaff5f018efcc0906ed3ab"
|
|
9206
9206
|
dependencies = [
|
|
9207
9207
|
"cfg-if",
|
|
9208
9208
|
"enumn",
|
|
@@ -9213,9 +9213,9 @@ dependencies = [
|
|
|
9213
9213
|
|
|
9214
9214
|
[[package]]
|
|
9215
9215
|
name = "xberg-libwpd"
|
|
9216
|
-
version = "1.2.
|
|
9216
|
+
version = "1.2.7"
|
|
9217
9217
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9218
|
-
checksum = "
|
|
9218
|
+
checksum = "940da444bd6ef032d147baf75c7655c814014a8c6fe3c69455c8590f52597d1a"
|
|
9219
9219
|
dependencies = [
|
|
9220
9220
|
"cc",
|
|
9221
9221
|
"flate2",
|
|
@@ -9228,9 +9228,9 @@ dependencies = [
|
|
|
9228
9228
|
|
|
9229
9229
|
[[package]]
|
|
9230
9230
|
name = "xberg-native-pdf"
|
|
9231
|
-
version = "1.2.
|
|
9231
|
+
version = "1.2.7"
|
|
9232
9232
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9233
|
-
checksum = "
|
|
9233
|
+
checksum = "d9e487f72f61cdae74c7f520f74273f8ef21902e10fb0cd2ceb30d0e3c75d47b"
|
|
9234
9234
|
dependencies = [
|
|
9235
9235
|
"aes 0.9.3",
|
|
9236
9236
|
"base64 0.23.1",
|
|
@@ -9275,9 +9275,9 @@ dependencies = [
|
|
|
9275
9275
|
|
|
9276
9276
|
[[package]]
|
|
9277
9277
|
name = "xberg-paddle-ocr"
|
|
9278
|
-
version = "1.2.
|
|
9278
|
+
version = "1.2.7"
|
|
9279
9279
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9280
|
-
checksum = "
|
|
9280
|
+
checksum = "3495b7c085ab01b4addf70847d2dc6b01b5380e74f4a1a63e39e3fc2f41e4f43"
|
|
9281
9281
|
dependencies = [
|
|
9282
9282
|
"geo-clipper",
|
|
9283
9283
|
"geo-types",
|
|
@@ -9292,7 +9292,7 @@ dependencies = [
|
|
|
9292
9292
|
|
|
9293
9293
|
[[package]]
|
|
9294
9294
|
name = "xberg-rb"
|
|
9295
|
-
version = "1.2.
|
|
9295
|
+
version = "1.2.7"
|
|
9296
9296
|
dependencies = [
|
|
9297
9297
|
"async-trait",
|
|
9298
9298
|
"crawlberg",
|
|
@@ -9308,9 +9308,9 @@ dependencies = [
|
|
|
9308
9308
|
|
|
9309
9309
|
[[package]]
|
|
9310
9310
|
name = "xberg-tesseract"
|
|
9311
|
-
version = "1.2.
|
|
9311
|
+
version = "1.2.7"
|
|
9312
9312
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9313
|
-
checksum = "
|
|
9313
|
+
checksum = "0af6504efd1e8a0bc51930803db3acd79182d638946ad0356619e2a349724140"
|
|
9314
9314
|
dependencies = [
|
|
9315
9315
|
"cc",
|
|
9316
9316
|
"cmake",
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:1f5936bf945fb3ed15e46660587964a7a20efc25883fd450c39f4fde5fddc5d1
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify
|
|
5
5
|
|
|
6
6
|
[package]
|
|
7
7
|
name = "xberg-rb"
|
|
8
|
-
version = "1.2.
|
|
8
|
+
version = "1.2.7"
|
|
9
9
|
edition = "2024"
|
|
10
10
|
license = "MIT"
|
|
11
11
|
description = "High-performance document intelligence library"
|
|
@@ -82,13 +82,13 @@ tokio = { version = "1", features = ["rt-multi-thread"] }
|
|
|
82
82
|
tracing = "0.1"
|
|
83
83
|
|
|
84
84
|
[target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
|
|
85
|
-
xberg = { version = "1.2.
|
|
85
|
+
xberg = { version = "1.2.7", default-features = false, features = ["macos-intel-target", "simd-utf8"] }
|
|
86
86
|
|
|
87
87
|
[target.'cfg(not(any(target_os = "windows", all(target_os = "macos", target_arch = "x86_64"))))'.dependencies]
|
|
88
|
-
xberg = { version = "1.2.
|
|
88
|
+
xberg = { version = "1.2.7", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-presets", "sparse-embeddings", "sparse-embedding-presets", "late-interaction", "late-interaction-presets", "chunking", "keywords-yake", "keywords-rake", "language-detection", "html", "tree-sitter", "office", "email", "archives", "stopwords", "auto-rotate", "auto-rotate-types", "tokio-runtime", "api", "api-types", "mcp", "liter-llm", "quality", "svg", "transcription", "transcription-types", "classification", "captioning", "ner-onnx", "ner-llm", "diff", "markdown-footnotes", "redaction", "enrichment", "heuristics", "presets", "structured", "url-ingestion"] }
|
|
89
89
|
|
|
90
90
|
[target.'cfg(target_os = "windows")'.dependencies]
|
|
91
|
-
xberg = { version = "1.2.
|
|
91
|
+
xberg = { version = "1.2.7", default-features = false, features = ["windows-gnu-target", "simd-utf8"] }
|
|
92
92
|
|
|
93
93
|
# This crate deliberately does not use `[lints]` / `workspace = true`: its C-ABI /
|
|
94
94
|
# PyO3 / napi / ext-php-rs / NIF boundary requires `unsafe` code, and the workspace's
|
data/ext/xberg_rb/src/lib.rs
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
// This file is auto-generated by alef. DO NOT EDIT.
|
|
2
|
-
// alef:hash:
|
|
2
|
+
// alef:hash:f1a359a24f246b68ebe2717a124008b9358925ba194cc8cb713eb90df7dc417d
|
|
3
3
|
// Re-generate with: alef generate
|
|
4
4
|
#![allow(dead_code, unused_imports, unused_variables)]
|
|
5
5
|
#![allow(
|
|
@@ -3484,6 +3484,7 @@ impl CodeMetadata {
|
|
|
3484
3484
|
#[magnus::wrap(class = "Xberg::ConcurrencyConfig")]
|
|
3485
3485
|
pub struct ConcurrencyConfig {
|
|
3486
3486
|
max_threads: Option<usize>,
|
|
3487
|
+
max_concurrent_ocr: Option<usize>,
|
|
3487
3488
|
}
|
|
3488
3489
|
|
|
3489
3490
|
unsafe impl IntoValueFromNative for ConcurrencyConfig {}
|
|
@@ -3544,12 +3545,25 @@ impl ConcurrencyConfig {
|
|
|
3544
3545
|
})?),
|
|
3545
3546
|
None => None,
|
|
3546
3547
|
},
|
|
3548
|
+
max_concurrent_ocr: match kwargs.get(ruby.to_symbol("max_concurrent_ocr")).filter(|v| !v.is_nil()) {
|
|
3549
|
+
Some(v) => Some(usize::try_convert(v).map_err(|e| {
|
|
3550
|
+
magnus::Error::new(
|
|
3551
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
3552
|
+
format!("invalid value for `max_concurrent_ocr`: {}", e),
|
|
3553
|
+
)
|
|
3554
|
+
})?),
|
|
3555
|
+
None => None,
|
|
3556
|
+
},
|
|
3547
3557
|
})
|
|
3548
3558
|
}
|
|
3549
3559
|
|
|
3550
3560
|
fn max_threads(&self) -> Option<usize> {
|
|
3551
3561
|
self.max_threads
|
|
3552
3562
|
}
|
|
3563
|
+
|
|
3564
|
+
fn max_concurrent_ocr(&self) -> Option<usize> {
|
|
3565
|
+
self.max_concurrent_ocr
|
|
3566
|
+
}
|
|
3553
3567
|
}
|
|
3554
3568
|
|
|
3555
3569
|
#[derive(Clone, Debug, serde::Serialize)]
|
|
@@ -47485,6 +47499,7 @@ impl From<ConcurrencyConfig> for xberg::ConcurrencyConfig {
|
|
|
47485
47499
|
fn from(val: ConcurrencyConfig) -> Self {
|
|
47486
47500
|
Self {
|
|
47487
47501
|
max_threads: val.max_threads,
|
|
47502
|
+
max_concurrent_ocr: val.max_concurrent_ocr,
|
|
47488
47503
|
..Default::default()
|
|
47489
47504
|
}
|
|
47490
47505
|
}
|
|
@@ -47494,6 +47509,7 @@ impl From<xberg::ConcurrencyConfig> for ConcurrencyConfig {
|
|
|
47494
47509
|
fn from(val: xberg::ConcurrencyConfig) -> Self {
|
|
47495
47510
|
Self {
|
|
47496
47511
|
max_threads: val.max_threads,
|
|
47512
|
+
max_concurrent_ocr: val.max_concurrent_ocr,
|
|
47497
47513
|
}
|
|
47498
47514
|
}
|
|
47499
47515
|
}
|
|
@@ -56455,6 +56471,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
|
|
|
56455
56471
|
|
|
56456
56472
|
class.define_method("max_threads", method!(ConcurrencyConfig::max_threads, 0))?;
|
|
56457
56473
|
|
|
56474
|
+
class.define_method("max_concurrent_ocr", method!(ConcurrencyConfig::max_concurrent_ocr, 0))?;
|
|
56475
|
+
|
|
56458
56476
|
let class = module.define_class("ContentConfig", ruby.class_object())?;
|
|
56459
56477
|
|
|
56460
56478
|
class.define_singleton_method("new", function!(ContentConfig::new, -1))?;
|
data/lib/xberg/version.rb
CHANGED
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:49ce69ad0d044e0b83320a5dd3eefaebf328bcf29ddcdcfa681b1f5cdcb2febb
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify
|
|
5
5
|
# frozen_string_literal: true
|
|
6
6
|
|
|
7
7
|
module Xberg
|
|
8
8
|
## The version string for this package.
|
|
9
|
-
VERSION = "1.2.
|
|
9
|
+
VERSION = "1.2.7"
|
|
10
10
|
end
|
data/sig/types.rbs
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:4cc11f4292def27becadc457989d24ea976f6ddcaaa87e60c01e9796d7722c80
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify
|
|
5
5
|
|
|
@@ -279,8 +279,9 @@ def initialize: (?chunks: Array[CodeChunkInfo], ?data: CodeDataNode) -> void
|
|
|
279
279
|
|
|
280
280
|
class ConcurrencyConfig
|
|
281
281
|
attr_reader max_threads: Integer?
|
|
282
|
+
attr_reader max_concurrent_ocr: Integer?
|
|
282
283
|
|
|
283
|
-
def initialize: (?max_threads: Integer) -> void
|
|
284
|
+
def initialize: (?max_threads: Integer, ?max_concurrent_ocr: Integer) -> void
|
|
284
285
|
end
|
|
285
286
|
|
|
286
287
|
class ContentConfig
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: xberg
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.2.
|
|
4
|
+
version: 1.2.7
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Na'aman Hirschfeld <naaman@xberg.io>
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2026-09-
|
|
11
|
+
date: 2026-09-22 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rb_sys
|