xberg 1.3.6 → 1.3.7
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 +50 -60
- data/ext/xberg_rb/native/Cargo.toml +6 -6
- data/ext/xberg_rb/src/lib.rs +144 -1
- data/lib/xberg/version.rb +2 -2
- data/sig/types.rbs +11 -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: 2f77e5d2925ccf8901431a3b6a158aa60383b336ec55df56e4ad18c155165903
|
|
4
|
+
data.tar.gz: e692c7fb23881c16ece726c9168615263a7aa6163e39120a302dfd5557718148
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ead85a3fe7860015ab6184cedcdbf9401fddcf59a332361d263b51e83a5325883034e5c23b0471a7482c7e0c5e0a9a47a32df8de92cc76efc04111333000f8cf
|
|
7
|
+
data.tar.gz: f679e028b8b550eee84e7f9a6ef06efe1730ed5cb3f525e04a252a08b1a04bc337a5753fd489c308e3cf0255780b0326ef0aa97fb23cecb1ded2c0cf5ed11127
|
|
@@ -1405,9 +1405,9 @@ dependencies = [
|
|
|
1405
1405
|
|
|
1406
1406
|
[[package]]
|
|
1407
1407
|
name = "crawlberg"
|
|
1408
|
-
version = "1.10.
|
|
1408
|
+
version = "1.10.3"
|
|
1409
1409
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1410
|
-
checksum = "
|
|
1410
|
+
checksum = "15043ca3b85e20585879e8d8933ea77c516cb6dfa8502c85c5f2e6c350e8226a"
|
|
1411
1411
|
dependencies = [
|
|
1412
1412
|
"ahash",
|
|
1413
1413
|
"aho-corasick",
|
|
@@ -1450,7 +1450,7 @@ dependencies = [
|
|
|
1450
1450
|
"thiserror 2.0.21",
|
|
1451
1451
|
"tokio",
|
|
1452
1452
|
"tokio-stream",
|
|
1453
|
-
"toml 1.1.
|
|
1453
|
+
"toml 1.1.8+spec-1.1.0",
|
|
1454
1454
|
"tower",
|
|
1455
1455
|
"tracing",
|
|
1456
1456
|
"url",
|
|
@@ -1459,9 +1459,9 @@ dependencies = [
|
|
|
1459
1459
|
|
|
1460
1460
|
[[package]]
|
|
1461
1461
|
name = "crawlberg-robots"
|
|
1462
|
-
version = "1.10.
|
|
1462
|
+
version = "1.10.3"
|
|
1463
1463
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1464
|
-
checksum = "
|
|
1464
|
+
checksum = "a0b2204ccbe52f63dc889618f08e3859411e5bd4e6c332cef4103c783e90caf5"
|
|
1465
1465
|
|
|
1466
1466
|
[[package]]
|
|
1467
1467
|
name = "crc32fast"
|
|
@@ -1862,9 +1862,9 @@ dependencies = [
|
|
|
1862
1862
|
|
|
1863
1863
|
[[package]]
|
|
1864
1864
|
name = "either"
|
|
1865
|
-
version = "1.
|
|
1865
|
+
version = "1.19.0"
|
|
1866
1866
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1867
|
-
checksum = "
|
|
1867
|
+
checksum = "0e9c71c2167ca323c882b99918929403426e2373ea17242ff5653e0d5e1058be"
|
|
1868
1868
|
|
|
1869
1869
|
[[package]]
|
|
1870
1870
|
name = "email_address"
|
|
@@ -3903,9 +3903,9 @@ checksum = "47d9d19d1d6efa0109d2f65ff4c85cddd50bd572e5a00127ab10987290bcefae"
|
|
|
3903
3903
|
|
|
3904
3904
|
[[package]]
|
|
3905
3905
|
name = "liter-llm"
|
|
3906
|
-
version = "2.
|
|
3906
|
+
version = "2.2.0"
|
|
3907
3907
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3908
|
-
checksum = "
|
|
3908
|
+
checksum = "8638e8a77817d0debb8944de890ad736f80e1a46c2c53b8d75a303f59307fa68"
|
|
3909
3909
|
dependencies = [
|
|
3910
3910
|
"ahash",
|
|
3911
3911
|
"arc-swap",
|
|
@@ -3934,7 +3934,7 @@ dependencies = [
|
|
|
3934
3934
|
"thiserror 2.0.21",
|
|
3935
3935
|
"tokio",
|
|
3936
3936
|
"tokio-util",
|
|
3937
|
-
"toml 1.1.
|
|
3937
|
+
"toml 1.1.8+spec-1.1.0",
|
|
3938
3938
|
"tower",
|
|
3939
3939
|
"tower-http 0.7.1",
|
|
3940
3940
|
"tracing",
|
|
@@ -4224,12 +4224,6 @@ dependencies = [
|
|
|
4224
4224
|
"stable_deref_trait",
|
|
4225
4225
|
]
|
|
4226
4226
|
|
|
4227
|
-
[[package]]
|
|
4228
|
-
name = "memo-map"
|
|
4229
|
-
version = "0.3.4"
|
|
4230
|
-
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4231
|
-
checksum = "5449c8c750f1a07ea702bbd212bd999fceece9b3d1508b17023b3e174583124b"
|
|
4232
|
-
|
|
4233
4227
|
[[package]]
|
|
4234
4228
|
name = "micromap"
|
|
4235
4229
|
version = "0.3.0"
|
|
@@ -4254,13 +4248,9 @@ dependencies = [
|
|
|
4254
4248
|
|
|
4255
4249
|
[[package]]
|
|
4256
4250
|
name = "minijinja"
|
|
4257
|
-
version = "
|
|
4251
|
+
version = "3.0.0"
|
|
4258
4252
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4259
|
-
checksum = "
|
|
4260
|
-
dependencies = [
|
|
4261
|
-
"memo-map",
|
|
4262
|
-
"serde",
|
|
4263
|
-
]
|
|
4253
|
+
checksum = "13345868cfa94eadafc067112ff29271380a820d5594d9ee6ba81a8d00ea5dc2"
|
|
4264
4254
|
|
|
4265
4255
|
[[package]]
|
|
4266
4256
|
name = "minimal-lexical"
|
|
@@ -6452,9 +6442,9 @@ dependencies = [
|
|
|
6452
6442
|
|
|
6453
6443
|
[[package]]
|
|
6454
6444
|
name = "serde_spanned"
|
|
6455
|
-
version = "1.1.
|
|
6445
|
+
version = "1.1.2"
|
|
6456
6446
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6457
|
-
checksum = "
|
|
6447
|
+
checksum = "4e7523beb55eece201a2356bee0bbca0d1ab466c14c07703b2e0ee6d42cb0c2c"
|
|
6458
6448
|
dependencies = [
|
|
6459
6449
|
"serde_core",
|
|
6460
6450
|
]
|
|
@@ -7158,7 +7148,7 @@ dependencies = [
|
|
|
7158
7148
|
"cfg-expr",
|
|
7159
7149
|
"heck",
|
|
7160
7150
|
"pkg-config",
|
|
7161
|
-
"toml 1.1.
|
|
7151
|
+
"toml 1.1.8+spec-1.1.0",
|
|
7162
7152
|
"version-compare",
|
|
7163
7153
|
]
|
|
7164
7154
|
|
|
@@ -7598,14 +7588,14 @@ dependencies = [
|
|
|
7598
7588
|
|
|
7599
7589
|
[[package]]
|
|
7600
7590
|
name = "toml"
|
|
7601
|
-
version = "1.1.
|
|
7591
|
+
version = "1.1.8+spec-1.1.0"
|
|
7602
7592
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7603
|
-
checksum = "
|
|
7593
|
+
checksum = "20489e00e4d8741d6be680764cc12e270655e375a20d1011e844a9c3379e678d"
|
|
7604
7594
|
dependencies = [
|
|
7605
7595
|
"indexmap",
|
|
7606
7596
|
"serde_core",
|
|
7607
|
-
"serde_spanned 1.1.
|
|
7608
|
-
"toml_datetime 1.1.
|
|
7597
|
+
"serde_spanned 1.1.2",
|
|
7598
|
+
"toml_datetime 1.1.2+spec-1.1.0",
|
|
7609
7599
|
"toml_parser",
|
|
7610
7600
|
"toml_writer",
|
|
7611
7601
|
"winnow 1.0.4",
|
|
@@ -7622,9 +7612,9 @@ dependencies = [
|
|
|
7622
7612
|
|
|
7623
7613
|
[[package]]
|
|
7624
7614
|
name = "toml_datetime"
|
|
7625
|
-
version = "1.1.
|
|
7615
|
+
version = "1.1.2+spec-1.1.0"
|
|
7626
7616
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7627
|
-
checksum = "
|
|
7617
|
+
checksum = "2b86d767906c6c42421dcba507eb9d203e779497710a47782a224bb871653053"
|
|
7628
7618
|
dependencies = [
|
|
7629
7619
|
"serde_core",
|
|
7630
7620
|
]
|
|
@@ -7650,16 +7640,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
|
7650
7640
|
checksum = "1340ea94a5856333492c9064b02c778b191dd2c853778d9609debdcdfea3a614"
|
|
7651
7641
|
dependencies = [
|
|
7652
7642
|
"indexmap",
|
|
7653
|
-
"toml_datetime 1.1.
|
|
7643
|
+
"toml_datetime 1.1.2+spec-1.1.0",
|
|
7654
7644
|
"toml_parser",
|
|
7655
7645
|
"winnow 1.0.4",
|
|
7656
7646
|
]
|
|
7657
7647
|
|
|
7658
7648
|
[[package]]
|
|
7659
7649
|
name = "toml_parser"
|
|
7660
|
-
version = "1.1.
|
|
7650
|
+
version = "1.1.5+spec-1.1.0"
|
|
7661
7651
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7662
|
-
checksum = "
|
|
7652
|
+
checksum = "baa693a8032d7e1cada7d0041e96126df243179ff061456783ac7f12bda4744c"
|
|
7663
7653
|
dependencies = [
|
|
7664
7654
|
"winnow 1.0.4",
|
|
7665
7655
|
]
|
|
@@ -7672,9 +7662,9 @@ checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
|
|
|
7672
7662
|
|
|
7673
7663
|
[[package]]
|
|
7674
7664
|
name = "toml_writer"
|
|
7675
|
-
version = "1.1.
|
|
7665
|
+
version = "1.1.3+spec-1.1.0"
|
|
7676
7666
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
7677
|
-
checksum = "
|
|
7667
|
+
checksum = "06bdbd8cfc056b8d2e2e85f29b56a3bdbecb527cef81eb39e3e7b98af4652770"
|
|
7678
7668
|
|
|
7679
7669
|
[[package]]
|
|
7680
7670
|
name = "tower"
|
|
@@ -8009,9 +7999,9 @@ dependencies = [
|
|
|
8009
7999
|
|
|
8010
8000
|
[[package]]
|
|
8011
8001
|
name = "unhwp"
|
|
8012
|
-
version = "0.
|
|
8002
|
+
version = "0.15.2"
|
|
8013
8003
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8014
|
-
checksum = "
|
|
8004
|
+
checksum = "c068ba83bed698f530437fe034d4c684bac7c375f09030737eaa3131d1590f62"
|
|
8015
8005
|
dependencies = [
|
|
8016
8006
|
"cfb 0.15.0",
|
|
8017
8007
|
"flate2",
|
|
@@ -8118,9 +8108,9 @@ dependencies = [
|
|
|
8118
8108
|
|
|
8119
8109
|
[[package]]
|
|
8120
8110
|
name = "unparser-shared"
|
|
8121
|
-
version = "0.
|
|
8111
|
+
version = "0.5.0"
|
|
8122
8112
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8123
|
-
checksum = "
|
|
8113
|
+
checksum = "eb70246b07259d4efe9d08a70dfe2fcdc0fa77424e642a71e2e713706a4deb4c"
|
|
8124
8114
|
dependencies = [
|
|
8125
8115
|
"pulldown-cmark",
|
|
8126
8116
|
"pulldown-cmark-to-cmark",
|
|
@@ -8932,9 +8922,9 @@ dependencies = [
|
|
|
8932
8922
|
|
|
8933
8923
|
[[package]]
|
|
8934
8924
|
name = "xberg"
|
|
8935
|
-
version = "1.3.
|
|
8925
|
+
version = "1.3.7"
|
|
8936
8926
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
8937
|
-
checksum = "
|
|
8927
|
+
checksum = "232e7d3dc9538b4ae608350a405e4c784d74b60e9d9416a7473a5acdf417001a"
|
|
8938
8928
|
dependencies = [
|
|
8939
8929
|
"aes-gcm",
|
|
8940
8930
|
"ahash",
|
|
@@ -9039,7 +9029,7 @@ dependencies = [
|
|
|
9039
9029
|
"tokenizers 0.21.4",
|
|
9040
9030
|
"tokenizers 0.23.2",
|
|
9041
9031
|
"tokio",
|
|
9042
|
-
"toml 1.1.
|
|
9032
|
+
"toml 1.1.8+spec-1.1.0",
|
|
9043
9033
|
"tower",
|
|
9044
9034
|
"tower-http 0.7.1",
|
|
9045
9035
|
"tracing",
|
|
@@ -9071,9 +9061,9 @@ dependencies = [
|
|
|
9071
9061
|
|
|
9072
9062
|
[[package]]
|
|
9073
9063
|
name = "xberg-candle-ocr"
|
|
9074
|
-
version = "1.3.
|
|
9064
|
+
version = "1.3.7"
|
|
9075
9065
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9076
|
-
checksum = "
|
|
9066
|
+
checksum = "ae1351a11104c3059bf8b4b9b7b8fe257621682f9c89982061df28b089848cf6"
|
|
9077
9067
|
dependencies = [
|
|
9078
9068
|
"base64 0.23.1",
|
|
9079
9069
|
"candle-core",
|
|
@@ -9093,9 +9083,9 @@ dependencies = [
|
|
|
9093
9083
|
|
|
9094
9084
|
[[package]]
|
|
9095
9085
|
name = "xberg-gliner"
|
|
9096
|
-
version = "1.3.
|
|
9086
|
+
version = "1.3.7"
|
|
9097
9087
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9098
|
-
checksum = "
|
|
9088
|
+
checksum = "b14f2b9d5d706f09bf1194bedd52c243e6c7a4d3100ab0da9bc871d48a4e6c84"
|
|
9099
9089
|
dependencies = [
|
|
9100
9090
|
"getrandom 0.2.17",
|
|
9101
9091
|
"getrandom 0.3.4",
|
|
@@ -9109,9 +9099,9 @@ dependencies = [
|
|
|
9109
9099
|
|
|
9110
9100
|
[[package]]
|
|
9111
9101
|
name = "xberg-libheif"
|
|
9112
|
-
version = "1.3.
|
|
9102
|
+
version = "1.3.7"
|
|
9113
9103
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9114
|
-
checksum = "
|
|
9104
|
+
checksum = "6e3b34dea39b568a057501b541005bf6680bec1f1ed6016afb642f45cd1ca9f6"
|
|
9115
9105
|
dependencies = [
|
|
9116
9106
|
"cfg-if",
|
|
9117
9107
|
"enumn",
|
|
@@ -9122,9 +9112,9 @@ dependencies = [
|
|
|
9122
9112
|
|
|
9123
9113
|
[[package]]
|
|
9124
9114
|
name = "xberg-libwpd"
|
|
9125
|
-
version = "1.3.
|
|
9115
|
+
version = "1.3.7"
|
|
9126
9116
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9127
|
-
checksum = "
|
|
9117
|
+
checksum = "96e3abd771d6746a23e948e034374ec600e77d0ab9c22a16a43cb5311389d3c9"
|
|
9128
9118
|
dependencies = [
|
|
9129
9119
|
"cc",
|
|
9130
9120
|
"flate2",
|
|
@@ -9137,9 +9127,9 @@ dependencies = [
|
|
|
9137
9127
|
|
|
9138
9128
|
[[package]]
|
|
9139
9129
|
name = "xberg-native-pdf"
|
|
9140
|
-
version = "1.3.
|
|
9130
|
+
version = "1.3.7"
|
|
9141
9131
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9142
|
-
checksum = "
|
|
9132
|
+
checksum = "3980162c1327d1d3aae9dff9f5be106b952b6c730b5b5c13592e6a0734d1bff9"
|
|
9143
9133
|
dependencies = [
|
|
9144
9134
|
"aes 0.9.3",
|
|
9145
9135
|
"base64 0.23.1",
|
|
@@ -9184,9 +9174,9 @@ dependencies = [
|
|
|
9184
9174
|
|
|
9185
9175
|
[[package]]
|
|
9186
9176
|
name = "xberg-paddle-ocr"
|
|
9187
|
-
version = "1.3.
|
|
9177
|
+
version = "1.3.7"
|
|
9188
9178
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9189
|
-
checksum = "
|
|
9179
|
+
checksum = "e86d8d15e5bc2b39e1284be3f2fc219e551af5cc094a979cb36c599162ed4d5e"
|
|
9190
9180
|
dependencies = [
|
|
9191
9181
|
"geo-clipper",
|
|
9192
9182
|
"geo-types",
|
|
@@ -9201,9 +9191,9 @@ dependencies = [
|
|
|
9201
9191
|
|
|
9202
9192
|
[[package]]
|
|
9203
9193
|
name = "xberg-pdfium-render"
|
|
9204
|
-
version = "1.3.
|
|
9194
|
+
version = "1.3.7"
|
|
9205
9195
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9206
|
-
checksum = "
|
|
9196
|
+
checksum = "a9a13d59452c14bfcb7d2228e0699bc7d492a4222742c1f11a3dec173033351e"
|
|
9207
9197
|
dependencies = [
|
|
9208
9198
|
"bitflags 2.13.2",
|
|
9209
9199
|
"bytemuck",
|
|
@@ -9220,7 +9210,7 @@ dependencies = [
|
|
|
9220
9210
|
|
|
9221
9211
|
[[package]]
|
|
9222
9212
|
name = "xberg-rb"
|
|
9223
|
-
version = "1.3.
|
|
9213
|
+
version = "1.3.7"
|
|
9224
9214
|
dependencies = [
|
|
9225
9215
|
"async-trait",
|
|
9226
9216
|
"crawlberg",
|
|
@@ -9236,9 +9226,9 @@ dependencies = [
|
|
|
9236
9226
|
|
|
9237
9227
|
[[package]]
|
|
9238
9228
|
name = "xberg-tesseract"
|
|
9239
|
-
version = "1.3.
|
|
9229
|
+
version = "1.3.7"
|
|
9240
9230
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9241
|
-
checksum = "
|
|
9231
|
+
checksum = "a90867724dfbd9b3c8e58027949727b78b734cf95f20cba3ce29e05204da391f"
|
|
9242
9232
|
dependencies = [
|
|
9243
9233
|
"cc",
|
|
9244
9234
|
"cmake",
|
|
@@ -1,11 +1,11 @@
|
|
|
1
1
|
# This file is auto-generated by alef — DO NOT EDIT.
|
|
2
|
-
# alef:hash:
|
|
2
|
+
# alef:hash:a35074a20ca717ee54f07b153b49a9c727f639435558b33d857255e60e309542
|
|
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 = "1.3.
|
|
8
|
+
version = "1.3.7"
|
|
9
9
|
edition = "2024"
|
|
10
10
|
license = "MIT"
|
|
11
11
|
description = "High-performance document intelligence library"
|
|
@@ -72,7 +72,7 @@ xml = ["xberg/xml"]
|
|
|
72
72
|
|
|
73
73
|
[dependencies]
|
|
74
74
|
async-trait = "0.1"
|
|
75
|
-
crawlberg = { default-features = false, version = "1.10.
|
|
75
|
+
crawlberg = { default-features = false, version = "1.10.3" }
|
|
76
76
|
html-to-markdown-rs = { default-features = false, version = "3.17.2" }
|
|
77
77
|
magnus = "0.9"
|
|
78
78
|
rb-sys = ">=0.9.130, <0.10"
|
|
@@ -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 = "1.3.
|
|
85
|
+
xberg = { version = "1.3.7", 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 = "1.3.
|
|
88
|
+
xberg = { version = "1.3.7", features = ["full", "pdf", "pdf-pdfium", "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", "formula-recognition", "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 = "1.3.
|
|
91
|
+
xberg = { version = "1.3.7", 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:d77ecc12b6f0752c5cec96b6f0b205562ea146737a08606f1b824d4cca7eff52
|
|
3
3
|
// Re-generate with: alef generate
|
|
4
4
|
#![allow(dead_code, unused_imports, unused_variables)]
|
|
5
5
|
#![allow(
|
|
@@ -11154,6 +11154,7 @@ pub struct ExtractedDocument {
|
|
|
11154
11154
|
redaction_report: Option<RedactionReport>,
|
|
11155
11155
|
formulas: Vec<Formula>,
|
|
11156
11156
|
form_fields: Vec<PdfFormField>,
|
|
11157
|
+
ocr_page_failures: Option<Vec<OcrPageFailure>>,
|
|
11157
11158
|
}
|
|
11158
11159
|
|
|
11159
11160
|
unsafe impl IntoValueFromNative for ExtractedDocument {}
|
|
@@ -11506,6 +11507,15 @@ impl ExtractedDocument {
|
|
|
11506
11507
|
})?,
|
|
11507
11508
|
None => Default::default(),
|
|
11508
11509
|
},
|
|
11510
|
+
ocr_page_failures: match kwargs.get(ruby.to_symbol("ocr_page_failures")).filter(|v| !v.is_nil()) {
|
|
11511
|
+
Some(v) => Some(<Vec<OcrPageFailure>>::try_convert(v).map_err(|e| {
|
|
11512
|
+
magnus::Error::new(
|
|
11513
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
11514
|
+
format!("invalid value for `ocr_page_failures`: {}", e),
|
|
11515
|
+
)
|
|
11516
|
+
})?),
|
|
11517
|
+
None => None,
|
|
11518
|
+
},
|
|
11509
11519
|
})
|
|
11510
11520
|
}
|
|
11511
11521
|
|
|
@@ -11644,6 +11654,10 @@ impl ExtractedDocument {
|
|
|
11644
11654
|
self.form_fields.clone()
|
|
11645
11655
|
}
|
|
11646
11656
|
|
|
11657
|
+
fn ocr_page_failures(&self) -> Option<Vec<OcrPageFailure>> {
|
|
11658
|
+
self.ocr_page_failures.clone()
|
|
11659
|
+
}
|
|
11660
|
+
|
|
11647
11661
|
#[allow(clippy::should_implement_trait)]
|
|
11648
11662
|
fn to_s(&self) -> String {
|
|
11649
11663
|
self.content.clone()
|
|
@@ -23264,6 +23278,99 @@ impl OcrMetadata {
|
|
|
23264
23278
|
}
|
|
23265
23279
|
}
|
|
23266
23280
|
|
|
23281
|
+
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize)]
|
|
23282
|
+
#[serde(default)]
|
|
23283
|
+
#[magnus::wrap(class = "Xberg::OcrPageFailure")]
|
|
23284
|
+
pub struct OcrPageFailure {
|
|
23285
|
+
page: u32,
|
|
23286
|
+
error: String,
|
|
23287
|
+
recovered: bool,
|
|
23288
|
+
}
|
|
23289
|
+
|
|
23290
|
+
unsafe impl IntoValueFromNative for OcrPageFailure {}
|
|
23291
|
+
|
|
23292
|
+
impl magnus::TryConvert for OcrPageFailure {
|
|
23293
|
+
fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
|
|
23294
|
+
if let Ok(r) = <&OcrPageFailure as magnus::TryConvert>::try_convert(val) {
|
|
23295
|
+
return Ok(r.clone());
|
|
23296
|
+
}
|
|
23297
|
+
let json_str: String = if let Ok(s) = <String as magnus::TryConvert>::try_convert(val) {
|
|
23298
|
+
s
|
|
23299
|
+
} else {
|
|
23300
|
+
val.funcall::<_, _, String>("to_json", ()).map_err(|e| {
|
|
23301
|
+
magnus::Error::new(
|
|
23302
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
23303
|
+
format!("no implicit conversion into OcrPageFailure: {}", e),
|
|
23304
|
+
)
|
|
23305
|
+
})?
|
|
23306
|
+
};
|
|
23307
|
+
serde_json::from_str::<OcrPageFailure>(&json_str).map_err(|e| {
|
|
23308
|
+
magnus::Error::new(
|
|
23309
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
23310
|
+
format!("failed to deserialize OcrPageFailure: {}", e),
|
|
23311
|
+
)
|
|
23312
|
+
})
|
|
23313
|
+
}
|
|
23314
|
+
}
|
|
23315
|
+
|
|
23316
|
+
unsafe impl TryConvertOwned for OcrPageFailure {}
|
|
23317
|
+
|
|
23318
|
+
impl Default for OcrPageFailure {
|
|
23319
|
+
fn default() -> Self {
|
|
23320
|
+
xberg::OcrPageFailure::default().into()
|
|
23321
|
+
}
|
|
23322
|
+
}
|
|
23323
|
+
|
|
23324
|
+
impl OcrPageFailure {
|
|
23325
|
+
fn new(args: &[magnus::Value]) -> Result<Self, magnus::Error> {
|
|
23326
|
+
let ruby = unsafe { magnus::Ruby::get_unchecked() };
|
|
23327
|
+
let args = magnus::scan_args::scan_args::<(), (Option<magnus::RHash>,), (), (), (), ()>(args)?;
|
|
23328
|
+
let (kwargs_opt,) = args.optional;
|
|
23329
|
+
let kwargs = kwargs_opt.unwrap_or_else(|| ruby.hash_new());
|
|
23330
|
+
Ok(Self {
|
|
23331
|
+
page: match kwargs.get(ruby.to_symbol("page")) {
|
|
23332
|
+
Some(v) => u32::try_convert(v).map_err(|e| {
|
|
23333
|
+
magnus::Error::new(
|
|
23334
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
23335
|
+
format!("invalid value for `page`: {}", e),
|
|
23336
|
+
)
|
|
23337
|
+
})?,
|
|
23338
|
+
None => Default::default(),
|
|
23339
|
+
},
|
|
23340
|
+
error: match kwargs.get(ruby.to_symbol("error")) {
|
|
23341
|
+
Some(v) => String::try_convert(v).map_err(|e| {
|
|
23342
|
+
magnus::Error::new(
|
|
23343
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
23344
|
+
format!("invalid value for `error`: {}", e),
|
|
23345
|
+
)
|
|
23346
|
+
})?,
|
|
23347
|
+
None => Default::default(),
|
|
23348
|
+
},
|
|
23349
|
+
recovered: match kwargs.get(ruby.to_symbol("recovered")) {
|
|
23350
|
+
Some(v) => bool::try_convert(v).map_err(|e| {
|
|
23351
|
+
magnus::Error::new(
|
|
23352
|
+
unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
|
|
23353
|
+
format!("invalid value for `recovered`: {}", e),
|
|
23354
|
+
)
|
|
23355
|
+
})?,
|
|
23356
|
+
None => Default::default(),
|
|
23357
|
+
},
|
|
23358
|
+
})
|
|
23359
|
+
}
|
|
23360
|
+
|
|
23361
|
+
fn page(&self) -> u32 {
|
|
23362
|
+
self.page
|
|
23363
|
+
}
|
|
23364
|
+
|
|
23365
|
+
fn error(&self) -> String {
|
|
23366
|
+
self.error.clone()
|
|
23367
|
+
}
|
|
23368
|
+
|
|
23369
|
+
fn recovered(&self) -> bool {
|
|
23370
|
+
self.recovered
|
|
23371
|
+
}
|
|
23372
|
+
}
|
|
23373
|
+
|
|
23267
23374
|
#[derive(Clone, Debug, serde::Serialize)]
|
|
23268
23375
|
#[magnus::wrap(class = "Xberg::OcrPipelineConfig")]
|
|
23269
23376
|
pub struct OcrPipelineConfig {
|
|
@@ -50369,6 +50476,7 @@ impl From<ExtractedDocument> for xberg::ExtractedDocument {
|
|
|
50369
50476
|
__result.redaction_report = val.redaction_report.map(Into::into);
|
|
50370
50477
|
__result.formulas = val.formulas.into_iter().map(Into::into).collect();
|
|
50371
50478
|
__result.form_fields = val.form_fields.into_iter().map(Into::into).collect();
|
|
50479
|
+
__result.ocr_page_failures = val.ocr_page_failures.map(|v| v.into_iter().map(Into::into).collect());
|
|
50372
50480
|
__result
|
|
50373
50481
|
}
|
|
50374
50482
|
}
|
|
@@ -50417,6 +50525,7 @@ impl From<xberg::ExtractedDocument> for ExtractedDocument {
|
|
|
50417
50525
|
redaction_report: val.redaction_report.map(Into::into),
|
|
50418
50526
|
formulas: val.formulas.into_iter().map(Into::into).collect(),
|
|
50419
50527
|
form_fields: val.form_fields.into_iter().map(Into::into).collect(),
|
|
50528
|
+
ocr_page_failures: val.ocr_page_failures.map(|v| v.into_iter().map(Into::into).collect()),
|
|
50420
50529
|
}
|
|
50421
50530
|
}
|
|
50422
50531
|
}
|
|
@@ -52590,6 +52699,28 @@ impl From<xberg::OcrMetadata> for OcrMetadata {
|
|
|
52590
52699
|
}
|
|
52591
52700
|
}
|
|
52592
52701
|
|
|
52702
|
+
#[allow(clippy::needless_update)]
|
|
52703
|
+
impl From<OcrPageFailure> for xberg::OcrPageFailure {
|
|
52704
|
+
fn from(val: OcrPageFailure) -> Self {
|
|
52705
|
+
Self {
|
|
52706
|
+
page: val.page,
|
|
52707
|
+
error: val.error,
|
|
52708
|
+
recovered: val.recovered,
|
|
52709
|
+
..Default::default()
|
|
52710
|
+
}
|
|
52711
|
+
}
|
|
52712
|
+
}
|
|
52713
|
+
|
|
52714
|
+
impl From<xberg::OcrPageFailure> for OcrPageFailure {
|
|
52715
|
+
fn from(val: xberg::OcrPageFailure) -> Self {
|
|
52716
|
+
Self {
|
|
52717
|
+
page: val.page,
|
|
52718
|
+
error: val.error.to_string(),
|
|
52719
|
+
recovered: val.recovered,
|
|
52720
|
+
}
|
|
52721
|
+
}
|
|
52722
|
+
}
|
|
52723
|
+
|
|
52593
52724
|
#[allow(clippy::useless_conversion)]
|
|
52594
52725
|
impl From<OcrPipelineConfig> for xberg::OcrPipelineConfig {
|
|
52595
52726
|
fn from(val: OcrPipelineConfig) -> Self {
|
|
@@ -59145,6 +59276,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
|
|
|
59145
59276
|
|
|
59146
59277
|
class.define_method("form_fields", method!(ExtractedDocument::form_fields, 0))?;
|
|
59147
59278
|
|
|
59279
|
+
class.define_method("ocr_page_failures", method!(ExtractedDocument::ocr_page_failures, 0))?;
|
|
59280
|
+
|
|
59148
59281
|
class.define_method("to_s", method!(ExtractedDocument::to_s, 0))?;
|
|
59149
59282
|
|
|
59150
59283
|
let class = module.define_class("ExtractedImage", ruby.class_object())?;
|
|
@@ -60725,6 +60858,16 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
|
|
|
60725
60858
|
|
|
60726
60859
|
class.define_method("table_cols", method!(OcrMetadata::table_cols, 0))?;
|
|
60727
60860
|
|
|
60861
|
+
let class = module.define_class("OcrPageFailure", ruby.class_object())?;
|
|
60862
|
+
|
|
60863
|
+
class.define_singleton_method("new", function!(OcrPageFailure::new, -1))?;
|
|
60864
|
+
|
|
60865
|
+
class.define_method("page", method!(OcrPageFailure::page, 0))?;
|
|
60866
|
+
|
|
60867
|
+
class.define_method("error", method!(OcrPageFailure::error, 0))?;
|
|
60868
|
+
|
|
60869
|
+
class.define_method("recovered", method!(OcrPageFailure::recovered, 0))?;
|
|
60870
|
+
|
|
60728
60871
|
let class = module.define_class("OcrPipelineConfig", ruby.class_object())?;
|
|
60729
60872
|
|
|
60730
60873
|
class.define_singleton_method("new", function!(OcrPipelineConfig::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:0687e037476da4ba7e18fe1957eb56d2d154c61c20f178f4c8ee9e1cc7d090c2
|
|
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 = "1.3.
|
|
9
|
+
VERSION = "1.3.7"
|
|
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:ebe306889747c0ee64b78fefcf465898aca7871336bda3ba3caa4406a424946d
|
|
3
3
|
# To regenerate: alef generate
|
|
4
4
|
# To verify freshness: alef verify
|
|
5
5
|
|
|
@@ -906,8 +906,9 @@ def initialize: (sheets: Array[ExcelSheet], metadata: Hash[String, String], ?rev
|
|
|
906
906
|
attr_reader redaction_report: RedactionReport?
|
|
907
907
|
attr_reader formulas: Array[Formula]
|
|
908
908
|
attr_reader form_fields: Array[PdfFormField]
|
|
909
|
+
attr_reader ocr_page_failures: Array[OcrPageFailure]?
|
|
909
910
|
|
|
910
|
-
def initialize: (?content: String, ?mime_type: String, ?metadata: Metadata, ?extraction_method: enum_ExtractionMethod, ?tables: Array[Table], ?counts: DocumentCounts, ?detected_languages: Array[String], ?detected_language_confidences: Array[LanguageConfidence], ?chunks: Array[Chunk], ?images: Array[ExtractedImage], ?pages: Array[PageContent], ?elements: Array[Element], ?djot_content: DjotContent, ?ocr_elements: Array[OcrElement], ?document: DocumentStructure, ?extracted_keywords: Array[Keyword], ?quality_score: Float, ?processing_warnings: Array[ProcessingWarning], ?annotations: Array[PdfAnnotation], ?children: Array[ArchiveEntry], ?uris: Array[ExtractedUri], ?revisions: Array[DocumentRevision], ?structured_output: String, ?code_intelligence: String, ?llm_usage: Array[LlmUsage], ?entities: Array[Entity], ?summary: DocumentSummary, ?extraction_confidence: ExtractionConfidence, ?translation: Translation, ?page_classifications: Array[PageClassification], ?redaction_report: RedactionReport, ?formulas: Array[Formula], ?form_fields: Array[PdfFormField]) -> void
|
|
911
|
+
def initialize: (?content: String, ?mime_type: String, ?metadata: Metadata, ?extraction_method: enum_ExtractionMethod, ?tables: Array[Table], ?counts: DocumentCounts, ?detected_languages: Array[String], ?detected_language_confidences: Array[LanguageConfidence], ?chunks: Array[Chunk], ?images: Array[ExtractedImage], ?pages: Array[PageContent], ?elements: Array[Element], ?djot_content: DjotContent, ?ocr_elements: Array[OcrElement], ?document: DocumentStructure, ?extracted_keywords: Array[Keyword], ?quality_score: Float, ?processing_warnings: Array[ProcessingWarning], ?annotations: Array[PdfAnnotation], ?children: Array[ArchiveEntry], ?uris: Array[ExtractedUri], ?revisions: Array[DocumentRevision], ?structured_output: String, ?code_intelligence: String, ?llm_usage: Array[LlmUsage], ?entities: Array[Entity], ?summary: DocumentSummary, ?extraction_confidence: ExtractionConfidence, ?translation: Translation, ?page_classifications: Array[PageClassification], ?redaction_report: RedactionReport, ?formulas: Array[Formula], ?form_fields: Array[PdfFormField], ?ocr_page_failures: Array[OcrPageFailure]) -> void
|
|
911
912
|
end
|
|
912
913
|
|
|
913
914
|
class ExtractedImage
|
|
@@ -1769,6 +1770,14 @@ def initialize: (?content: String, ?mime_type: String, ?metadata: Hash[String, S
|
|
|
1769
1770
|
def initialize: (?language: String, ?psm: Integer, ?output_format: String, ?table_count: Integer, ?table_rows: Integer, ?table_cols: Integer) -> void
|
|
1770
1771
|
end
|
|
1771
1772
|
|
|
1773
|
+
class OcrPageFailure
|
|
1774
|
+
attr_reader page: Integer
|
|
1775
|
+
attr_reader error: String
|
|
1776
|
+
attr_reader recovered: bool
|
|
1777
|
+
|
|
1778
|
+
def initialize: (?page: Integer, ?error: String, ?recovered: bool) -> void
|
|
1779
|
+
end
|
|
1780
|
+
|
|
1772
1781
|
class OcrPipelineConfig
|
|
1773
1782
|
attr_reader stages: Array[OcrPipelineStage]
|
|
1774
1783
|
attr_reader quality_thresholds: OcrQualityThresholds
|
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: 1.3.
|
|
4
|
+
version: 1.3.7
|
|
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: 2026-10-
|
|
11
|
+
date: 2026-10-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rb_sys
|