xberg 1.0.0.pre.rc.4 → 1.0.0.pre.rc.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 +25 -45
- data/ext/xberg_rb/native/Cargo.toml +6 -82
- data/ext/xberg_rb/src/lib.rs +1546 -2
- data/lib/xberg/native.rb +6 -4
- data/lib/xberg/version.rb +2 -2
- data/lib/xberg.rb +1 -1
- data/lib/xberg_rb.so +0 -0
- data/sig/types.rbs +44 -16
- 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: 8dd187e353e4926f840bca1b2fd8ac9aa099ff3b844580d4e325f78f1f20a547
|
|
4
|
+
data.tar.gz: 3d421a8ab9b4beb0539e4ba899af07c1ffea3b235c40d6ffc9633f6a80a6b69b
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8c640729c97cf6cc2a290b30823908cb46a3c74d2a032f03c222d8c6666e7a1c8451f0d957e0aa8b3a38fc47a4cc89eebfeb46361ede09323e5218e66af617cb
|
|
7
|
+
data.tar.gz: 8f6a497814c9215b7aeef1c326477e0b17ccfa2b0f30f10023f9488c99453ff51e7412299a957c8c7f99368e29773723e27ce9a01683f653792fdc9cc5495d35
|
|
@@ -1230,9 +1230,9 @@ dependencies = [
|
|
|
1230
1230
|
|
|
1231
1231
|
[[package]]
|
|
1232
1232
|
name = "crawlberg"
|
|
1233
|
-
version = "1.0.
|
|
1233
|
+
version = "1.0.3"
|
|
1234
1234
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1235
|
-
checksum = "
|
|
1235
|
+
checksum = "46b3f6dfec53e26f1f989b4685943153a54e1d2101f8bd3ae5afd810b7957423"
|
|
1236
1236
|
dependencies = [
|
|
1237
1237
|
"ahash 0.8.12",
|
|
1238
1238
|
"aho-corasick",
|
|
@@ -2534,9 +2534,9 @@ dependencies = [
|
|
|
2534
2534
|
|
|
2535
2535
|
[[package]]
|
|
2536
2536
|
name = "html-to-markdown-rs"
|
|
2537
|
-
version = "3.8.
|
|
2537
|
+
version = "3.8.2"
|
|
2538
2538
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
2539
|
-
checksum = "
|
|
2539
|
+
checksum = "bfb98086035f41cf7bcdb6bd1dab14b118e53b035e003e268698a6003c413fa0"
|
|
2540
2540
|
dependencies = [
|
|
2541
2541
|
"ahash 0.8.12",
|
|
2542
2542
|
"astral-tl",
|
|
@@ -3141,12 +3141,10 @@ checksum = "ccfe6121cbe750cf81efa362d85c0bde7ea298ec43092d3a193baca59cdbd634"
|
|
|
3141
3141
|
dependencies = [
|
|
3142
3142
|
"defmt",
|
|
3143
3143
|
"jiff-static",
|
|
3144
|
-
"jiff-tzdb-platform",
|
|
3145
3144
|
"log",
|
|
3146
3145
|
"portable-atomic",
|
|
3147
3146
|
"portable-atomic-util",
|
|
3148
3147
|
"serde_core",
|
|
3149
|
-
"windows-link",
|
|
3150
3148
|
]
|
|
3151
3149
|
|
|
3152
3150
|
[[package]]
|
|
@@ -3160,21 +3158,6 @@ dependencies = [
|
|
|
3160
3158
|
"syn 2.0.118",
|
|
3161
3159
|
]
|
|
3162
3160
|
|
|
3163
|
-
[[package]]
|
|
3164
|
-
name = "jiff-tzdb"
|
|
3165
|
-
version = "0.1.6"
|
|
3166
|
-
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3167
|
-
checksum = "c900ef84826f1338a557697dc8fc601df9ca9af4ac137c7fb61d4c6f2dfd3076"
|
|
3168
|
-
|
|
3169
|
-
[[package]]
|
|
3170
|
-
name = "jiff-tzdb-platform"
|
|
3171
|
-
version = "0.1.3"
|
|
3172
|
-
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3173
|
-
checksum = "875a5a69ac2bab1a891711cf5eccbec1ce0341ea805560dcd90b7a2e925132e8"
|
|
3174
|
-
dependencies = [
|
|
3175
|
-
"jiff-tzdb",
|
|
3176
|
-
]
|
|
3177
|
-
|
|
3178
3161
|
[[package]]
|
|
3179
3162
|
name = "jni"
|
|
3180
3163
|
version = "0.21.1"
|
|
@@ -3410,9 +3393,9 @@ checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
|
|
|
3410
3393
|
|
|
3411
3394
|
[[package]]
|
|
3412
3395
|
name = "liter-llm"
|
|
3413
|
-
version = "1.9.
|
|
3396
|
+
version = "1.9.3"
|
|
3414
3397
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3415
|
-
checksum = "
|
|
3398
|
+
checksum = "b2262222bbb692fb6c788b90bc24c1f8358d75f845374e4a0df6c70630541017"
|
|
3416
3399
|
dependencies = [
|
|
3417
3400
|
"ahash 0.8.12",
|
|
3418
3401
|
"async-trait",
|
|
@@ -3505,24 +3488,20 @@ dependencies = [
|
|
|
3505
3488
|
"aes 0.9.1",
|
|
3506
3489
|
"bitflags 2.13.0",
|
|
3507
3490
|
"cbc 0.2.1",
|
|
3508
|
-
"chrono",
|
|
3509
3491
|
"ecb",
|
|
3510
3492
|
"encoding_rs",
|
|
3511
3493
|
"flate2",
|
|
3512
3494
|
"getrandom 0.4.3",
|
|
3513
3495
|
"indexmap",
|
|
3514
3496
|
"itoa",
|
|
3515
|
-
"jiff",
|
|
3516
3497
|
"log",
|
|
3517
3498
|
"md-5",
|
|
3518
3499
|
"nom 8.0.0",
|
|
3519
3500
|
"rand 0.10.2",
|
|
3520
3501
|
"rangemap",
|
|
3521
|
-
"rayon",
|
|
3522
3502
|
"sha2 0.11.0",
|
|
3523
3503
|
"stringprep",
|
|
3524
3504
|
"thiserror 2.0.18",
|
|
3525
|
-
"time",
|
|
3526
3505
|
"ttf-parser",
|
|
3527
3506
|
"weezl 0.2.1",
|
|
3528
3507
|
]
|
|
@@ -5510,9 +5489,9 @@ dependencies = [
|
|
|
5510
5489
|
|
|
5511
5490
|
[[package]]
|
|
5512
5491
|
name = "rustc-hash"
|
|
5513
|
-
version = "2.1.
|
|
5492
|
+
version = "2.1.3"
|
|
5514
5493
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
5515
|
-
checksum = "
|
|
5494
|
+
checksum = "6b1e7f9a428571be2dc5bc0505c13fb6bf936822b894ec87abf8a08a4e51742d"
|
|
5516
5495
|
|
|
5517
5496
|
[[package]]
|
|
5518
5497
|
name = "rustfft"
|
|
@@ -7023,9 +7002,9 @@ dependencies = [
|
|
|
7023
7002
|
|
|
7024
7003
|
[[package]]
|
|
7025
7004
|
name = "tree-sitter"
|
|
7026
|
-
version = "0.26.
|
|
7005
|
+
version = "0.26.10"
|
|
7027
7006
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7028
|
-
checksum = "
|
|
7007
|
+
checksum = "3c343ed63e3f5c64d1acdecb5d2c13d4e169cb5fde0052106ebaa6c6f27f9e55"
|
|
7029
7008
|
dependencies = [
|
|
7030
7009
|
"cc",
|
|
7031
7010
|
"regex",
|
|
@@ -7043,15 +7022,15 @@ checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
|
|
|
7043
7022
|
|
|
7044
7023
|
[[package]]
|
|
7045
7024
|
name = "tree-sitter-language-pack"
|
|
7046
|
-
version = "1.12.
|
|
7025
|
+
version = "1.12.3"
|
|
7047
7026
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7048
|
-
checksum = "
|
|
7027
|
+
checksum = "32def7d253a2662db9a32196440b07bb0e9731a2133dbad0ed42239f94d548ea"
|
|
7049
7028
|
dependencies = [
|
|
7050
7029
|
"ahash 0.8.12",
|
|
7051
7030
|
"cc",
|
|
7052
7031
|
"dirs",
|
|
7053
7032
|
"fd-lock",
|
|
7054
|
-
"getrandom 0.
|
|
7033
|
+
"getrandom 0.4.3",
|
|
7055
7034
|
"libloading 0.9.0",
|
|
7056
7035
|
"memchr",
|
|
7057
7036
|
"serde",
|
|
@@ -8041,9 +8020,9 @@ dependencies = [
|
|
|
8041
8020
|
|
|
8042
8021
|
[[package]]
|
|
8043
8022
|
name = "xberg"
|
|
8044
|
-
version = "1.0.0-rc.
|
|
8023
|
+
version = "1.0.0-rc.7"
|
|
8045
8024
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8046
|
-
checksum = "
|
|
8025
|
+
checksum = "ae067a49ec38ff99d501d0e4bc745f5a1332dd22a86b3085083e219531249191"
|
|
8047
8026
|
dependencies = [
|
|
8048
8027
|
"ahash 0.8.12",
|
|
8049
8028
|
"async-trait",
|
|
@@ -8159,9 +8138,9 @@ dependencies = [
|
|
|
8159
8138
|
|
|
8160
8139
|
[[package]]
|
|
8161
8140
|
name = "xberg-gliner"
|
|
8162
|
-
version = "1.0.0-rc.
|
|
8141
|
+
version = "1.0.0-rc.7"
|
|
8163
8142
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8164
|
-
checksum = "
|
|
8143
|
+
checksum = "c2d29a5fcf85c2cc09f22be902f04c7e57e80d8902b044750293c7974c54c8cc"
|
|
8165
8144
|
dependencies = [
|
|
8166
8145
|
"ndarray 0.17.2",
|
|
8167
8146
|
"ort",
|
|
@@ -8173,9 +8152,9 @@ dependencies = [
|
|
|
8173
8152
|
|
|
8174
8153
|
[[package]]
|
|
8175
8154
|
name = "xberg-libheif"
|
|
8176
|
-
version = "1.0.0-rc.
|
|
8155
|
+
version = "1.0.0-rc.7"
|
|
8177
8156
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8178
|
-
checksum = "
|
|
8157
|
+
checksum = "2913e23c08a64d6ecb3a3318fbc615f1f046a8b33f40a849a42a484862c594b8"
|
|
8179
8158
|
dependencies = [
|
|
8180
8159
|
"cfg-if",
|
|
8181
8160
|
"enumn",
|
|
@@ -8186,9 +8165,9 @@ dependencies = [
|
|
|
8186
8165
|
|
|
8187
8166
|
[[package]]
|
|
8188
8167
|
name = "xberg-paddle-ocr"
|
|
8189
|
-
version = "1.0.0-rc.
|
|
8168
|
+
version = "1.0.0-rc.7"
|
|
8190
8169
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8191
|
-
checksum = "
|
|
8170
|
+
checksum = "797b2d23626c27d87aaa2831d23066f3260940c2ec740d540014299d07537c1c"
|
|
8192
8171
|
dependencies = [
|
|
8193
8172
|
"geo-clipper",
|
|
8194
8173
|
"geo-types",
|
|
@@ -8198,11 +8177,12 @@ dependencies = [
|
|
|
8198
8177
|
"ort",
|
|
8199
8178
|
"serde",
|
|
8200
8179
|
"thiserror 2.0.18",
|
|
8180
|
+
"tracing",
|
|
8201
8181
|
]
|
|
8202
8182
|
|
|
8203
8183
|
[[package]]
|
|
8204
8184
|
name = "xberg-rb"
|
|
8205
|
-
version = "1.0.0-rc.
|
|
8185
|
+
version = "1.0.0-rc.7"
|
|
8206
8186
|
dependencies = [
|
|
8207
8187
|
"async-trait",
|
|
8208
8188
|
"crawlberg",
|
|
@@ -8216,9 +8196,9 @@ dependencies = [
|
|
|
8216
8196
|
|
|
8217
8197
|
[[package]]
|
|
8218
8198
|
name = "xberg-tesseract"
|
|
8219
|
-
version = "1.0.0-rc.
|
|
8199
|
+
version = "1.0.0-rc.7"
|
|
8220
8200
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8221
|
-
checksum = "
|
|
8201
|
+
checksum = "9e290213d7492421f7e0e83bb43e747aeb13c05df3a113328e0496cb3c248607"
|
|
8222
8202
|
dependencies = [
|
|
8223
8203
|
"cc",
|
|
8224
8204
|
"cmake",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[package]
|
|
2
2
|
name = "xberg-rb"
|
|
3
|
-
version = "1.0.0-rc.
|
|
3
|
+
version = "1.0.0-rc.7"
|
|
4
4
|
edition = "2024"
|
|
5
5
|
license = "MIT"
|
|
6
6
|
description = "High-performance document intelligence library"
|
|
@@ -17,43 +17,12 @@ path = "../src/lib.rs"
|
|
|
17
17
|
crate-type = ["cdylib"]
|
|
18
18
|
|
|
19
19
|
[features]
|
|
20
|
-
default = [
|
|
21
|
-
"api",
|
|
22
|
-
"api-types",
|
|
23
|
-
"auto-rotate-types",
|
|
24
|
-
"chunking-tokenizers",
|
|
25
|
-
"diff",
|
|
26
|
-
"heic",
|
|
27
|
-
"heuristics",
|
|
28
|
-
"html",
|
|
29
|
-
"keywords-rake",
|
|
30
|
-
"keywords-yake",
|
|
31
|
-
"layout-types",
|
|
32
|
-
"liter-llm",
|
|
33
|
-
"markdown-footnotes",
|
|
34
|
-
"ocr",
|
|
35
|
-
"ocr-wasm",
|
|
36
|
-
"office",
|
|
37
|
-
"paddle-ocr-types",
|
|
38
|
-
"pdf",
|
|
39
|
-
"presets",
|
|
40
|
-
"quality",
|
|
41
|
-
"redaction",
|
|
42
|
-
"reranker",
|
|
43
|
-
"reranker-presets",
|
|
44
|
-
"svg",
|
|
45
|
-
"transcription-types",
|
|
46
|
-
"tree-sitter",
|
|
47
|
-
"url-config-types",
|
|
48
|
-
"url-ingestion",
|
|
49
|
-
"xml",
|
|
50
|
-
]
|
|
20
|
+
default = ["api", "api-types", "auto-rotate-types", "chunking-tokenizers", "diff", "heuristics", "html", "keywords-rake", "keywords-yake", "layout-types", "liter-llm", "markdown-footnotes", "ocr", "ocr-wasm", "office", "paddle-ocr-types", "pdf", "presets", "quality", "redaction", "reranker", "reranker-presets", "svg", "transcription-types", "tree-sitter", "url-config-types", "url-ingestion", "xml"]
|
|
51
21
|
api = ["xberg/api"]
|
|
52
22
|
api-types = ["xberg/api-types"]
|
|
53
23
|
auto-rotate-types = ["xberg/auto-rotate-types"]
|
|
54
24
|
chunking-tokenizers = ["xberg/chunking-tokenizers"]
|
|
55
25
|
diff = ["xberg/diff"]
|
|
56
|
-
heic = ["xberg/heic"]
|
|
57
26
|
heuristics = ["xberg/heuristics"]
|
|
58
27
|
html = ["xberg/html"]
|
|
59
28
|
keywords-rake = ["xberg/keywords-rake"]
|
|
@@ -80,62 +49,17 @@ xml = ["xberg/xml"]
|
|
|
80
49
|
|
|
81
50
|
[dependencies]
|
|
82
51
|
async-trait = "0.1"
|
|
83
|
-
crawlberg = { default-features = false, version = "1.0.
|
|
52
|
+
crawlberg = { default-features = false, version = "1.0.2" }
|
|
84
53
|
magnus = "0.8"
|
|
85
54
|
rb-sys = ">=0.9, <0.9.128"
|
|
86
55
|
serde = { version = "1", features = ["derive"] }
|
|
87
56
|
serde_json = "1"
|
|
88
57
|
tokio = { version = "1", features = ["rt-multi-thread"] }
|
|
89
58
|
[target.'cfg(not(any(target_os = "windows", all(target_os = "macos", target_arch = "x86_64"))))'.dependencies]
|
|
90
|
-
xberg = { version = "1.0.0-rc.
|
|
91
|
-
"full",
|
|
92
|
-
"pdf",
|
|
93
|
-
"ocr",
|
|
94
|
-
"paddle-ocr",
|
|
95
|
-
"paddle-ocr-types",
|
|
96
|
-
"layout-detection",
|
|
97
|
-
"layout-types",
|
|
98
|
-
"embeddings",
|
|
99
|
-
"embedding-presets",
|
|
100
|
-
"reranker",
|
|
101
|
-
"reranker-presets",
|
|
102
|
-
"chunking",
|
|
103
|
-
"keywords-yake",
|
|
104
|
-
"keywords-rake",
|
|
105
|
-
"language-detection",
|
|
106
|
-
"html",
|
|
107
|
-
"tree-sitter",
|
|
108
|
-
"office",
|
|
109
|
-
"email",
|
|
110
|
-
"archives",
|
|
111
|
-
"stopwords",
|
|
112
|
-
"auto-rotate",
|
|
113
|
-
"auto-rotate-types",
|
|
114
|
-
"tokio-runtime",
|
|
115
|
-
"api",
|
|
116
|
-
"api-types",
|
|
117
|
-
"mcp",
|
|
118
|
-
"liter-llm",
|
|
119
|
-
"quality",
|
|
120
|
-
"svg",
|
|
121
|
-
"transcription",
|
|
122
|
-
"transcription-types",
|
|
123
|
-
"classification",
|
|
124
|
-
"captioning",
|
|
125
|
-
"ner-onnx",
|
|
126
|
-
"ner-llm",
|
|
127
|
-
"diff",
|
|
128
|
-
"markdown-footnotes",
|
|
129
|
-
"redaction",
|
|
130
|
-
"enrichment",
|
|
131
|
-
"heuristics",
|
|
132
|
-
"presets",
|
|
133
|
-
"structured",
|
|
134
|
-
"url-ingestion",
|
|
135
|
-
] }
|
|
59
|
+
xberg = { version = "1.0.0-rc.7", features = ["full", "pdf", "ocr", "paddle-ocr", "paddle-ocr-types", "layout-detection", "layout-types", "embeddings", "embedding-presets", "reranker", "reranker-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"] }
|
|
136
60
|
|
|
137
61
|
[target.'cfg(target_os = "windows")'.dependencies]
|
|
138
|
-
xberg = { version = "1.0.0-rc.
|
|
62
|
+
xberg = { version = "1.0.0-rc.7", features = ["windows-target"] }
|
|
139
63
|
|
|
140
64
|
[target.'cfg(all(target_os = "macos", target_arch = "x86_64"))'.dependencies]
|
|
141
|
-
xberg = { version = "1.0.0-rc.
|
|
65
|
+
xberg = { version = "1.0.0-rc.7", features = ["macos-intel-target"] }
|