kreuzberg 4.0.0.pre.rc.17 → 4.0.0.pre.rc.18
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/Gemfile.lock +1 -1
- data/ext/kreuzberg_rb/native/Cargo.lock +64 -2
- data/ext/kreuzberg_rb/native/Cargo.toml +1 -1
- data/ext/kreuzberg_rb/native/build.rs +6 -4
- data/lib/kreuzberg/version.rb +1 -1
- data/vendor/Cargo.toml +2 -2
- data/vendor/kreuzberg/Cargo.toml +1 -1
- data/vendor/kreuzberg-ffi/Cargo.toml +74 -0
- data/vendor/kreuzberg-ffi/README.md +851 -0
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +230 -0
- data/vendor/kreuzberg-ffi/build.rs +176 -0
- data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +2959 -0
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +626 -0
- data/vendor/kreuzberg-ffi/src/config.rs +1050 -0
- data/vendor/kreuzberg-ffi/src/error.rs +950 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +4107 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
- data/vendor/kreuzberg-ffi/src/result.rs +517 -0
- data/vendor/kreuzberg-ffi/src/result_pool.rs +675 -0
- data/vendor/kreuzberg-ffi/src/result_view.rs +815 -0
- data/vendor/kreuzberg-ffi/src/string_intern.rs +596 -0
- data/vendor/kreuzberg-ffi/src/validation.rs +938 -0
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +1 -1
- metadata +24 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: a1c1d7ddcc45217bf5d9ea47a4d9d3ef9f41ed5a4bd87f4ff1f2ada7cfe0bca6
|
|
4
|
+
data.tar.gz: 167fb6c623c9e4368bcd2388e0ef4631d170d0e167cc0555c2dc7cd814bff9eb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 37661576ba03012b1549c2388e0aee4c24cdb0e05cb34164fc85ca654c20236b28829678531c50fe46260433c43907c3f03cf516753f12c78ee2026a0b14a446
|
|
7
|
+
data.tar.gz: 96e1b3b10589fa7f47fc9609158da556e7d889a61963953c72e5f92337897828d68934d8dc0a66d7b2e28774204b6b1bf2c95226d5c26c84a98a01ce797e24df
|
data/Gemfile.lock
CHANGED
|
@@ -455,6 +455,18 @@ dependencies = [
|
|
|
455
455
|
"core2",
|
|
456
456
|
]
|
|
457
457
|
|
|
458
|
+
[[package]]
|
|
459
|
+
name = "bitvec"
|
|
460
|
+
version = "1.0.1"
|
|
461
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
462
|
+
checksum = "1bc2832c24239b0141d5674bb9174f9d68a8b5b3f2753311927c172ca46f7e9c"
|
|
463
|
+
dependencies = [
|
|
464
|
+
"funty",
|
|
465
|
+
"radium",
|
|
466
|
+
"tap",
|
|
467
|
+
"wyz",
|
|
468
|
+
]
|
|
469
|
+
|
|
458
470
|
[[package]]
|
|
459
471
|
name = "blake3"
|
|
460
472
|
version = "1.8.2"
|
|
@@ -987,6 +999,20 @@ dependencies = [
|
|
|
987
999
|
"serde",
|
|
988
1000
|
]
|
|
989
1001
|
|
|
1002
|
+
[[package]]
|
|
1003
|
+
name = "dashmap"
|
|
1004
|
+
version = "6.1.0"
|
|
1005
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1006
|
+
checksum = "5041cc499144891f3790297212f32a74fb938e5136a14943f338ef9e0ae276cf"
|
|
1007
|
+
dependencies = [
|
|
1008
|
+
"cfg-if",
|
|
1009
|
+
"crossbeam-utils",
|
|
1010
|
+
"hashbrown 0.14.5",
|
|
1011
|
+
"lock_api",
|
|
1012
|
+
"once_cell",
|
|
1013
|
+
"parking_lot_core",
|
|
1014
|
+
]
|
|
1015
|
+
|
|
990
1016
|
[[package]]
|
|
991
1017
|
name = "debug_unsafe"
|
|
992
1018
|
version = "0.1.3"
|
|
@@ -1434,6 +1460,12 @@ dependencies = [
|
|
|
1434
1460
|
"windows-sys 0.59.0",
|
|
1435
1461
|
]
|
|
1436
1462
|
|
|
1463
|
+
[[package]]
|
|
1464
|
+
name = "funty"
|
|
1465
|
+
version = "2.0.0"
|
|
1466
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1467
|
+
checksum = "e6d5a32815ae3f33302d95fdcb2ce17862f8c65363dcfd29360480ba1001fc9c"
|
|
1468
|
+
|
|
1437
1469
|
[[package]]
|
|
1438
1470
|
name = "futf"
|
|
1439
1471
|
version = "0.1.5"
|
|
@@ -1638,6 +1670,12 @@ dependencies = [
|
|
|
1638
1670
|
"zerocopy",
|
|
1639
1671
|
]
|
|
1640
1672
|
|
|
1673
|
+
[[package]]
|
|
1674
|
+
name = "hashbrown"
|
|
1675
|
+
version = "0.14.5"
|
|
1676
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1677
|
+
checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1"
|
|
1678
|
+
|
|
1641
1679
|
[[package]]
|
|
1642
1680
|
name = "hashbrown"
|
|
1643
1681
|
version = "0.15.5"
|
|
@@ -2280,7 +2318,7 @@ dependencies = [
|
|
|
2280
2318
|
|
|
2281
2319
|
[[package]]
|
|
2282
2320
|
name = "kreuzberg"
|
|
2283
|
-
version = "4.0.0-rc.
|
|
2321
|
+
version = "4.0.0-rc.17"
|
|
2284
2322
|
dependencies = [
|
|
2285
2323
|
"ahash",
|
|
2286
2324
|
"async-trait",
|
|
@@ -2288,8 +2326,10 @@ dependencies = [
|
|
|
2288
2326
|
"base64 0.22.1",
|
|
2289
2327
|
"base64-simd",
|
|
2290
2328
|
"biblatex",
|
|
2329
|
+
"bitvec",
|
|
2291
2330
|
"calamine",
|
|
2292
2331
|
"chardetng",
|
|
2332
|
+
"dashmap",
|
|
2293
2333
|
"docx-lite",
|
|
2294
2334
|
"encoding_rs",
|
|
2295
2335
|
"fast_image_resize",
|
|
@@ -2334,6 +2374,7 @@ dependencies = [
|
|
|
2334
2374
|
"serde_json",
|
|
2335
2375
|
"serde_yaml_ng",
|
|
2336
2376
|
"sevenz-rust2",
|
|
2377
|
+
"simdutf8",
|
|
2337
2378
|
"tar",
|
|
2338
2379
|
"text-splitter",
|
|
2339
2380
|
"thiserror 2.0.17",
|
|
@@ -2368,7 +2409,7 @@ dependencies = [
|
|
|
2368
2409
|
|
|
2369
2410
|
[[package]]
|
|
2370
2411
|
name = "kreuzberg-tesseract"
|
|
2371
|
-
version = "4.0.0-rc.
|
|
2412
|
+
version = "4.0.0-rc.17"
|
|
2372
2413
|
dependencies = [
|
|
2373
2414
|
"cc",
|
|
2374
2415
|
"cmake",
|
|
@@ -4124,6 +4165,12 @@ version = "5.3.0"
|
|
|
4124
4165
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4125
4166
|
checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
|
|
4126
4167
|
|
|
4168
|
+
[[package]]
|
|
4169
|
+
name = "radium"
|
|
4170
|
+
version = "0.7.0"
|
|
4171
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4172
|
+
checksum = "dc33ff2d4973d518d823d61aa239014831e521c75da58e3df4840d3f47749d09"
|
|
4173
|
+
|
|
4127
4174
|
[[package]]
|
|
4128
4175
|
name = "rake"
|
|
4129
4176
|
version = "0.3.6"
|
|
@@ -5218,6 +5265,12 @@ dependencies = [
|
|
|
5218
5265
|
"syn",
|
|
5219
5266
|
]
|
|
5220
5267
|
|
|
5268
|
+
[[package]]
|
|
5269
|
+
name = "tap"
|
|
5270
|
+
version = "1.0.1"
|
|
5271
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
5272
|
+
checksum = "55937e1799185b12863d447f42597ed69d9928686b8d88a1df17376a097d8369"
|
|
5273
|
+
|
|
5221
5274
|
[[package]]
|
|
5222
5275
|
name = "tar"
|
|
5223
5276
|
version = "0.4.44"
|
|
@@ -6439,6 +6492,15 @@ version = "0.6.2"
|
|
|
6439
6492
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6440
6493
|
checksum = "9edde0db4769d2dc68579893f2306b26c6ecfbe0ef499b013d731b7b9247e0b9"
|
|
6441
6494
|
|
|
6495
|
+
[[package]]
|
|
6496
|
+
name = "wyz"
|
|
6497
|
+
version = "0.5.1"
|
|
6498
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6499
|
+
checksum = "05f360fc0b24296329c78fda852a1e9ae82de9cf7b27dae4b7f62f118f77b9ed"
|
|
6500
|
+
dependencies = [
|
|
6501
|
+
"tap",
|
|
6502
|
+
]
|
|
6503
|
+
|
|
6442
6504
|
[[package]]
|
|
6443
6505
|
name = "xattr"
|
|
6444
6506
|
version = "1.6.1"
|
|
@@ -54,15 +54,17 @@ fn main() {
|
|
|
54
54
|
|
|
55
55
|
// Fallback: Add search paths and use standard linking
|
|
56
56
|
for dir in [host_lib_dir, target_lib_dir] {
|
|
57
|
-
|
|
58
|
-
println!("cargo:rustc-link-search=native={}", dir.display());
|
|
59
|
-
}
|
|
57
|
+
println!("cargo:rustc-link-search=native={}", dir.display());
|
|
60
58
|
}
|
|
61
59
|
}
|
|
62
60
|
|
|
63
61
|
// Link the kreuzberg-ffi library
|
|
64
62
|
// When kreuzberg-ffi is built, its symbols become available for linking
|
|
65
|
-
|
|
63
|
+
if target.contains("windows") {
|
|
64
|
+
println!("cargo:rustc-link-lib=dylib=kreuzberg_ffi");
|
|
65
|
+
} else {
|
|
66
|
+
println!("cargo:rustc-link-lib=static=kreuzberg_ffi");
|
|
67
|
+
}
|
|
66
68
|
|
|
67
69
|
if target.contains("darwin") {
|
|
68
70
|
println!("cargo:rustc-link-arg=-Wl,-undefined,dynamic_lookup");
|
data/lib/kreuzberg/version.rb
CHANGED
data/vendor/Cargo.toml
CHANGED
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
[workspace]
|
|
2
|
-
members = ["kreuzberg", "kreuzberg-tesseract"]
|
|
2
|
+
members = ["kreuzberg", "kreuzberg-tesseract", "kreuzberg-ffi"]
|
|
3
3
|
|
|
4
4
|
[workspace.package]
|
|
5
|
-
version = "4.0.0-rc.
|
|
5
|
+
version = "4.0.0-rc.18"
|
|
6
6
|
edition = "2024"
|
|
7
7
|
rust-version = "1.91"
|
|
8
8
|
authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
|
data/vendor/kreuzberg/Cargo.toml
CHANGED
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
[package]
|
|
2
|
+
name = "kreuzberg-ffi"
|
|
3
|
+
version.workspace = true
|
|
4
|
+
edition.workspace = true
|
|
5
|
+
rust-version.workspace = true
|
|
6
|
+
authors.workspace = true
|
|
7
|
+
description = "C FFI bindings for Kreuzberg document intelligence library"
|
|
8
|
+
license.workspace = true
|
|
9
|
+
repository = "https://github.com/kreuzberg-dev/kreuzberg"
|
|
10
|
+
homepage = "https://kreuzberg.dev"
|
|
11
|
+
documentation = "https://docs.rs/kreuzberg-ffi"
|
|
12
|
+
readme = "README.md"
|
|
13
|
+
keywords = ["ffi", "bindings", "document", "extraction", "api"]
|
|
14
|
+
categories = ["development-tools::ffi", "text-processing"]
|
|
15
|
+
|
|
16
|
+
[lib]
|
|
17
|
+
# cdylib: Required by Java (FFM API) and Go (cgo dynamic linking)
|
|
18
|
+
# staticlib: Required by Python (PyO3 static linking) to avoid dylib install_name issues on macOS
|
|
19
|
+
# rlib: Standard Rust library format for workspace dependencies
|
|
20
|
+
crate-type = ["cdylib", "staticlib", "rlib"]
|
|
21
|
+
|
|
22
|
+
[features]
|
|
23
|
+
# Mirror embeddings feature availability from kreuzberg dependency
|
|
24
|
+
embeddings = []
|
|
25
|
+
# Optional rayon for parallel batch processing
|
|
26
|
+
rayon = ["dep:rayon"]
|
|
27
|
+
# Re-export kreuzberg features for downstream conditional compilation
|
|
28
|
+
pdf = []
|
|
29
|
+
keywords-yake = []
|
|
30
|
+
keywords-rake = []
|
|
31
|
+
|
|
32
|
+
[dependencies]
|
|
33
|
+
serde_json = { workspace = true }
|
|
34
|
+
serde = { workspace = true }
|
|
35
|
+
async-trait = { workspace = true }
|
|
36
|
+
tokio = { workspace = true }
|
|
37
|
+
html-to-markdown-rs = { version = "2.16.1", default-features = false }
|
|
38
|
+
rayon = { version = "1.11", optional = true }
|
|
39
|
+
|
|
40
|
+
# On Windows MinGW, disable embeddings/ort since ONNX Runtime is not available
|
|
41
|
+
# in MinGW-compatible form. Use all other features but exclude embeddings.
|
|
42
|
+
[target.'cfg(all(windows, target_env = "gnu"))'.dependencies]
|
|
43
|
+
kreuzberg = { path = "../kreuzberg", features = [
|
|
44
|
+
"pdf",
|
|
45
|
+
"excel",
|
|
46
|
+
"office",
|
|
47
|
+
"email",
|
|
48
|
+
"html",
|
|
49
|
+
"xml",
|
|
50
|
+
"archives",
|
|
51
|
+
"ocr",
|
|
52
|
+
"language-detection",
|
|
53
|
+
"chunking",
|
|
54
|
+
"quality",
|
|
55
|
+
"keywords",
|
|
56
|
+
"api",
|
|
57
|
+
"mcp",
|
|
58
|
+
"otel",
|
|
59
|
+
"bundled-pdfium",
|
|
60
|
+
] }
|
|
61
|
+
|
|
62
|
+
[target.'cfg(not(all(windows, target_env = "gnu")))'.dependencies]
|
|
63
|
+
kreuzberg = { path = "../kreuzberg", features = ["full", "bundled-pdfium"] }
|
|
64
|
+
|
|
65
|
+
[build-dependencies]
|
|
66
|
+
cbindgen = "0.29"
|
|
67
|
+
|
|
68
|
+
[dev-dependencies]
|
|
69
|
+
tempfile = { workspace = true }
|
|
70
|
+
criterion = { version = "0.8", features = ["html_reports"] }
|
|
71
|
+
|
|
72
|
+
[[bench]]
|
|
73
|
+
name = "result_view_benchmark"
|
|
74
|
+
harness = false
|