xberg 1.3.2 → 1.3.4

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 03177551c298f9b95e0770c1d9cfd9498c0331720891b289c098153ce471f261
4
- data.tar.gz: 20bc21a7fdfdee8e55bfe0261e61e63b7be3ff79dd0a7884494b0da1af4efb51
3
+ metadata.gz: 776ad3d215ba3a5adf1325330a593b9b4853acc77504fdc8d11161dea9374d6d
4
+ data.tar.gz: d17b3122b02e8420d6b7d46e374278b6f1d9fde0889c9543f63cae2ef9a17f29
5
5
  SHA512:
6
- metadata.gz: b023f6eb38243bee3aefb4fc72a7639b4546fa48c68e22f94d58775a222f2c578e72ccd6f0b0981a3ad12d2bfc1ae83011d735e3f9181484dc294b3a485d30be
7
- data.tar.gz: 7e11cb61a4bb04c0492d8065481ca4de3060e9f360c2dab7dab71df8bfaf003603c19c71e37afb37696c18e3fee0beead2e8cf4ab812c5a38e0910bf6b586c1e
6
+ metadata.gz: fb7cdedf5123544de3abaa28010bb47127ce0fdb389b95d1ebeb6d2920c6c2dff92bd2d92081f2dad46659e6164cae092fc85dac955dca0c94de87bd3724cef9
7
+ data.tar.gz: e45ffd440c69abf6ed32e28d945e5a08bc772d4253d542284248210dc5c2ea70efd018386b4614d827fc889756381d50e72b2b32dc9f82e00b44d5f965534721
@@ -223,9 +223,9 @@ dependencies = [
223
223
 
224
224
  [[package]]
225
225
  name = "async-compression"
226
- version = "0.4.48"
226
+ version = "0.4.50"
227
227
  source = "registry+https://github.com/rust-lang/crates.io-index"
228
- checksum = "fb61aea1a7def73ee7c350a184f0e70b32c182344e2e75bf70c9b621b83417fd"
228
+ checksum = "ee19bd99b43e3691acbad4e840420a4881cea6c0b66a208125a824f8fd53f5a1"
229
229
  dependencies = [
230
230
  "compression-codecs",
231
231
  "compression-core",
@@ -411,9 +411,9 @@ dependencies = [
411
411
 
412
412
  [[package]]
413
413
  name = "aws-smithy-runtime-api"
414
- version = "1.18.0"
414
+ version = "1.19.0"
415
415
  source = "registry+https://github.com/rust-lang/crates.io-index"
416
- checksum = "9bb0deb40a69de59f7809251cfe1ab16de135f42c49d222d1202b4d0ce19720f"
416
+ checksum = "c0730c16f91124c6a2abb4932c77e299288b3dd9f967ea2e9ec48cc6731e87a4"
417
417
  dependencies = [
418
418
  "aws-smithy-async",
419
419
  "aws-smithy-runtime-api-macros",
@@ -758,17 +758,6 @@ dependencies = [
758
758
  "syn 3.0.6",
759
759
  ]
760
760
 
761
- [[package]]
762
- name = "brotli"
763
- version = "8.0.4"
764
- source = "registry+https://github.com/rust-lang/crates.io-index"
765
- checksum = "5cc91aac060a7a1e25823bdccbfb6af1875b88f17c6daac97894eed8207166b3"
766
- dependencies = [
767
- "alloc-no-stdlib 2.0.4",
768
- "alloc-stdlib 0.2.4",
769
- "brotli-decompressor 5.0.3",
770
- ]
771
-
772
761
  [[package]]
773
762
  name = "brotli"
774
763
  version = "9.0.0"
@@ -1055,9 +1044,9 @@ dependencies = [
1055
1044
 
1056
1045
  [[package]]
1057
1046
  name = "cfg-expr"
1058
- version = "0.20.9"
1047
+ version = "0.20.10"
1059
1048
  source = "registry+https://github.com/rust-lang/crates.io-index"
1060
- checksum = "fe4ece8474b5f766c63426647e7b4b316b67431ade1036a8313cee24a03ae917"
1049
+ checksum = "9ba9e9ec16c447027685b1f897b720e18e9a8afd00bd7332c483537e38086c9f"
1061
1050
  dependencies = [
1062
1051
  "smallvec",
1063
1052
  "target-lexicon",
@@ -1231,11 +1220,11 @@ dependencies = [
1231
1220
 
1232
1221
  [[package]]
1233
1222
  name = "compression-codecs"
1234
- version = "0.4.43"
1223
+ version = "0.4.45"
1235
1224
  source = "registry+https://github.com/rust-lang/crates.io-index"
1236
- checksum = "bef16c47ba2797aa6a909cc37d39911f3a6743811fe7408ac0b0cc0276b656e9"
1225
+ checksum = "98fc98460ba0ad5317075d3632b8dfc45d0be8c4a49347c2a38272019717614a"
1237
1226
  dependencies = [
1238
- "brotli 8.0.4",
1227
+ "brotli",
1239
1228
  "compression-core",
1240
1229
  "flate2",
1241
1230
  "memchr",
@@ -2708,9 +2697,9 @@ checksum = "f70749695b063ecbf6b62949ccccde2e733ec3ecbbd71d467dca4e5c6c97cca0"
2708
2697
 
2709
2698
  [[package]]
2710
2699
  name = "glam"
2711
- version = "0.33.11"
2700
+ version = "0.33.12"
2712
2701
  source = "registry+https://github.com/rust-lang/crates.io-index"
2713
- checksum = "35b4e837a1d133645d1dcf283e146a4b9901e390a1c13545f959cfed3a72f24f"
2702
+ checksum = "37bfe73dc8ec21f54d181e5a60554327ec3f1c600c455a75ccbfc65d2106a6c4"
2714
2703
 
2715
2704
  [[package]]
2716
2705
  name = "glob"
@@ -2968,9 +2957,9 @@ checksum = "c9356095b4b41197bba32173600e1582792cda618f65d12f68e2e77d273413c5"
2968
2957
 
2969
2958
  [[package]]
2970
2959
  name = "html-to-markdown-rs"
2971
- version = "3.15.1"
2960
+ version = "3.16.0"
2972
2961
  source = "registry+https://github.com/rust-lang/crates.io-index"
2973
- checksum = "1287459abcb674d1fb9a54b2860630346183c38aae85fc57b69e5fbeff4e0d46"
2962
+ checksum = "74c4d770081ede1c6ec100e61a57cac65bf41d28ab5516b1eae907b9f3415778"
2974
2963
  dependencies = [
2975
2964
  "ahash",
2976
2965
  "astral-tl",
@@ -3632,9 +3621,9 @@ dependencies = [
3632
3621
 
3633
3622
  [[package]]
3634
3623
  name = "jsonschema"
3635
- version = "0.58.1"
3624
+ version = "0.58.4"
3636
3625
  source = "registry+https://github.com/rust-lang/crates.io-index"
3637
- checksum = "0a083dc3204bad08c6654f3648b2e840668d843044605df8850b16d2b24d307f"
3626
+ checksum = "5761b0ca0a31464030d7c2a98087fde3124ebb5e09b5a112cdb815f03b8ee150"
3638
3627
  dependencies = [
3639
3628
  "ahash",
3640
3629
  "bytecount",
@@ -3660,18 +3649,18 @@ dependencies = [
3660
3649
 
3661
3650
  [[package]]
3662
3651
  name = "jsonschema-regex"
3663
- version = "0.58.1"
3652
+ version = "0.58.4"
3664
3653
  source = "registry+https://github.com/rust-lang/crates.io-index"
3665
- checksum = "655372e8fbbefa3e5bd9b7397b4937bf75b4a71f1f84d85122cbd7758b57c8b0"
3654
+ checksum = "f1ffba4378a3d6ee7f1ab65a8ed95c711ccfe4a3870932bdce89d8260abed38a"
3666
3655
  dependencies = [
3667
3656
  "regex-syntax",
3668
3657
  ]
3669
3658
 
3670
3659
  [[package]]
3671
3660
  name = "jsonschema-value"
3672
- version = "0.58.1"
3661
+ version = "0.58.4"
3673
3662
  source = "registry+https://github.com/rust-lang/crates.io-index"
3674
- checksum = "0a6ed45167e78187301842eab0510c7dd5d7e7d065d275ef0fe01ddd25f6607b"
3663
+ checksum = "386121f898b560ff6aaa7974952720e9d9276a201eca31296387c2ed8707855e"
3675
3664
  dependencies = [
3676
3665
  "ahash",
3677
3666
  "bytecount",
@@ -3757,9 +3746,9 @@ dependencies = [
3757
3746
 
3758
3747
  [[package]]
3759
3748
  name = "lazy_static"
3760
- version = "1.5.0"
3749
+ version = "1.5.1"
3761
3750
  source = "registry+https://github.com/rust-lang/crates.io-index"
3762
- checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
3751
+ checksum = "20870f649af7073d53e38067b2a84312175d56ea15217e1b15bc83506ec50afb"
3763
3752
 
3764
3753
  [[package]]
3765
3754
  name = "lebe"
@@ -3886,9 +3875,9 @@ checksum = "47d9d19d1d6efa0109d2f65ff4c85cddd50bd572e5a00127ab10987290bcefae"
3886
3875
 
3887
3876
  [[package]]
3888
3877
  name = "liter-llm"
3889
- version = "2.1.1"
3878
+ version = "2.1.2"
3890
3879
  source = "registry+https://github.com/rust-lang/crates.io-index"
3891
- checksum = "71e3d2ee6d906bd5bd018254d38737e0287f355d4e9706736128e63bc87009a1"
3880
+ checksum = "195beed58c0db82dd1159f4f5a5ba80847f9be9dc1d583faf02f98ac67233aba"
3892
3881
  dependencies = [
3893
3882
  "ahash",
3894
3883
  "arc-swap",
@@ -4066,9 +4055,9 @@ checksum = "fc04a4c58212d57930a24bf47d3fa87485264a3a054e9c10e042eb373573ad3c"
4066
4055
 
4067
4056
  [[package]]
4068
4057
  name = "magnus"
4069
- version = "0.9.1"
4058
+ version = "0.9.2"
4070
4059
  source = "registry+https://github.com/rust-lang/crates.io-index"
4071
- checksum = "4c01bef153b8d0f086991f0e166474a1d57b738221f9a9c11405d498ac95a44d"
4060
+ checksum = "b9068710e00d21be762edca59b9c4c8946dbdb29820d4f76ad559afea07982c9"
4072
4061
  dependencies = [
4073
4062
  "magnus-macros",
4074
4063
  "rb-sys",
@@ -4377,7 +4366,7 @@ dependencies = [
4377
4366
  "glam 0.30.10",
4378
4367
  "glam 0.31.1",
4379
4368
  "glam 0.32.1",
4380
- "glam 0.33.11",
4369
+ "glam 0.33.12",
4381
4370
  "matrixmultiply",
4382
4371
  "num-complex",
4383
4372
  "num-rational",
@@ -5142,9 +5131,9 @@ checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
5142
5131
 
5143
5132
  [[package]]
5144
5133
  name = "pin-utils"
5145
- version = "0.1.0"
5134
+ version = "0.1.1"
5146
5135
  source = "registry+https://github.com/rust-lang/crates.io-index"
5147
- checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184"
5136
+ checksum = "13bee6c73da26345c729282832b60b0363cf3dd9f4bfd81d8551b7a1c889a113"
5148
5137
 
5149
5138
  [[package]]
5150
5139
  name = "piston-float"
@@ -5350,9 +5339,9 @@ checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
5350
5339
 
5351
5340
  [[package]]
5352
5341
  name = "pulldown-cmark-to-cmark"
5353
- version = "22.0.1"
5342
+ version = "22.0.3"
5354
5343
  source = "registry+https://github.com/rust-lang/crates.io-index"
5355
- checksum = "ab1ad36992cead65f02aa399a373a42730922f1525d988172634fdefdecb8a60"
5344
+ checksum = "84bbb29c624230c4bd1047bbdb2aa47e41c860e9665ce62ba9504eebe91bf867"
5356
5345
  dependencies = [
5357
5346
  "pulldown-cmark",
5358
5347
  ]
@@ -5462,9 +5451,9 @@ dependencies = [
5462
5451
 
5463
5452
  [[package]]
5464
5453
  name = "quinn-proto"
5465
- version = "0.11.18"
5454
+ version = "0.11.19"
5466
5455
  source = "registry+https://github.com/rust-lang/crates.io-index"
5467
- checksum = "a9746dbde176634f4f2f1faf2404e30a31b2bc1e9cafb5329c95d8177a18c9fc"
5456
+ checksum = "0e750cca55fe4f0439a15d0bb529da9651e79993e8e72c61a899a36d462befbe"
5468
5457
  dependencies = [
5469
5458
  "aws-lc-rs",
5470
5459
  "bytes",
@@ -5485,9 +5474,9 @@ dependencies = [
5485
5474
 
5486
5475
  [[package]]
5487
5476
  name = "quinn-udp"
5488
- version = "0.5.15"
5477
+ version = "0.5.16"
5489
5478
  source = "registry+https://github.com/rust-lang/crates.io-index"
5490
- checksum = "35a133f956daabe89a61a685c2649f13d82d5aa4bd5d12d1277e1072a21c0694"
5479
+ checksum = "af66907df18639dcf4db56ca65490cabc4b27a97dbadd96f2926cca73298f016"
5491
5480
  dependencies = [
5492
5481
  "cfg_aliases",
5493
5482
  "libc",
@@ -5839,9 +5828,9 @@ dependencies = [
5839
5828
 
5840
5829
  [[package]]
5841
5830
  name = "referencing"
5842
- version = "0.58.1"
5831
+ version = "0.58.4"
5843
5832
  source = "registry+https://github.com/rust-lang/crates.io-index"
5844
- checksum = "c9bf6d3c834f2614907b0fd413854581ecb48f0a713ea5d6cdfbce36f24e700e"
5833
+ checksum = "5cfa1c91745dbca76a406b926918d7c63e15a4525ebab939fec3e015a1fb82b1"
5845
5834
  dependencies = [
5846
5835
  "ahash",
5847
5836
  "fluent-uri",
@@ -7598,9 +7587,9 @@ dependencies = [
7598
7587
 
7599
7588
  [[package]]
7600
7589
  name = "tokio-rustls"
7601
- version = "0.26.5"
7590
+ version = "0.26.6"
7602
7591
  source = "registry+https://github.com/rust-lang/crates.io-index"
7603
- checksum = "b0c85f2c3ef0b1cd58b36682f4b17aaa995f0e5db534d85692b4903abce21f67"
7592
+ checksum = "c9cc2678c2cdd569ef8215e2afd7954ada2ae20b4fdd2c5fe6139a3b02d105db"
7604
7593
  dependencies = [
7605
7594
  "rustls",
7606
7595
  "tokio",
@@ -9010,9 +8999,9 @@ dependencies = [
9010
8999
 
9011
9000
  [[package]]
9012
9001
  name = "xberg"
9013
- version = "1.3.2"
9002
+ version = "1.3.4"
9014
9003
  source = "registry+https://github.com/rust-lang/crates.io-index"
9015
- checksum = "5bf89e79d3973db1313163338cfc9e0fead041a27d83ace63f7cb94ff053da90"
9004
+ checksum = "ca1840b552a16d2d9a2dbb9dec557e822cc9c834b32c6740726413d508e463e2"
9016
9005
  dependencies = [
9017
9006
  "aes-gcm",
9018
9007
  "ahash",
@@ -9149,9 +9138,9 @@ dependencies = [
9149
9138
 
9150
9139
  [[package]]
9151
9140
  name = "xberg-candle-ocr"
9152
- version = "1.3.2"
9141
+ version = "1.3.4"
9153
9142
  source = "registry+https://github.com/rust-lang/crates.io-index"
9154
- checksum = "004ba13a26e1cf81ec760277dc82d3a73cd59f666276a2ce43e6a462ce5918e0"
9143
+ checksum = "c1fcf7160e4c88f64b30fef0cca75c849c41874fce7269066a152a45f008fe80"
9155
9144
  dependencies = [
9156
9145
  "base64 0.23.1",
9157
9146
  "candle-core",
@@ -9171,9 +9160,9 @@ dependencies = [
9171
9160
 
9172
9161
  [[package]]
9173
9162
  name = "xberg-gliner"
9174
- version = "1.3.2"
9163
+ version = "1.3.4"
9175
9164
  source = "registry+https://github.com/rust-lang/crates.io-index"
9176
- checksum = "078372b00903218a3148ad1ec0af632157c096127d24a778550abb84426c321d"
9165
+ checksum = "d1ecc238993ea3b1f38084c3fbe41a689ed8321145454078057c5991522d02e9"
9177
9166
  dependencies = [
9178
9167
  "getrandom 0.2.17",
9179
9168
  "getrandom 0.3.4",
@@ -9187,9 +9176,9 @@ dependencies = [
9187
9176
 
9188
9177
  [[package]]
9189
9178
  name = "xberg-libheif"
9190
- version = "1.3.2"
9179
+ version = "1.3.4"
9191
9180
  source = "registry+https://github.com/rust-lang/crates.io-index"
9192
- checksum = "9d91469af69a1dc90f4a04d1941d454717fb5824b377484f0891f4a88b9316db"
9181
+ checksum = "db2f00105c1a2eaa09437849281da3e917410cf3dd45fbc8782bbc96d2eacde6"
9193
9182
  dependencies = [
9194
9183
  "cfg-if",
9195
9184
  "enumn",
@@ -9200,9 +9189,9 @@ dependencies = [
9200
9189
 
9201
9190
  [[package]]
9202
9191
  name = "xberg-libwpd"
9203
- version = "1.3.2"
9192
+ version = "1.3.4"
9204
9193
  source = "registry+https://github.com/rust-lang/crates.io-index"
9205
- checksum = "21ee884fd7a51ed8d7871301ada76b53edc122ae1d13567765fcf829d86641a5"
9194
+ checksum = "2ee648b64ea792f80741925552acd13e69bf771d9b86039555e660593d6732c0"
9206
9195
  dependencies = [
9207
9196
  "cc",
9208
9197
  "flate2",
@@ -9215,13 +9204,13 @@ dependencies = [
9215
9204
 
9216
9205
  [[package]]
9217
9206
  name = "xberg-native-pdf"
9218
- version = "1.3.2"
9207
+ version = "1.3.4"
9219
9208
  source = "registry+https://github.com/rust-lang/crates.io-index"
9220
- checksum = "865394a14d05e6424eeb4b5b96bd098376e55db5a532f533d22479765ca23dd1"
9209
+ checksum = "4fe79b781a7212508ab39b2be14dcde450e006e2b288207ac6f3eb130804e6bc"
9221
9210
  dependencies = [
9222
9211
  "aes 0.9.3",
9223
9212
  "base64 0.23.1",
9224
- "brotli 9.0.0",
9213
+ "brotli",
9225
9214
  "byteorder",
9226
9215
  "bytes",
9227
9216
  "cbc 0.2.1",
@@ -9262,9 +9251,9 @@ dependencies = [
9262
9251
 
9263
9252
  [[package]]
9264
9253
  name = "xberg-paddle-ocr"
9265
- version = "1.3.2"
9254
+ version = "1.3.4"
9266
9255
  source = "registry+https://github.com/rust-lang/crates.io-index"
9267
- checksum = "0bda36565106c1a4209c2de4fd72d40b43e00a299c4232bebf6835edd058b9d5"
9256
+ checksum = "f5ff67ca24c1f2a22730c9e6dbcd5f5614b244fe8fb74c3e1e9b13073f8a4c9d"
9268
9257
  dependencies = [
9269
9258
  "geo-clipper",
9270
9259
  "geo-types",
@@ -9279,9 +9268,9 @@ dependencies = [
9279
9268
 
9280
9269
  [[package]]
9281
9270
  name = "xberg-pdfium-render"
9282
- version = "1.3.2"
9271
+ version = "1.3.4"
9283
9272
  source = "registry+https://github.com/rust-lang/crates.io-index"
9284
- checksum = "287b634afe53b563d09a9687125e651ce5139a0712f3f853a960f4f08c2576bf"
9273
+ checksum = "90013a4daf6eca014fd0e1fb9cea7cbac5ba93316338a4181feead9aea2b1f78"
9285
9274
  dependencies = [
9286
9275
  "bitflags 2.13.2",
9287
9276
  "bytemuck",
@@ -9298,7 +9287,7 @@ dependencies = [
9298
9287
 
9299
9288
  [[package]]
9300
9289
  name = "xberg-rb"
9301
- version = "1.3.2"
9290
+ version = "1.3.4"
9302
9291
  dependencies = [
9303
9292
  "async-trait",
9304
9293
  "crawlberg",
@@ -9314,9 +9303,9 @@ dependencies = [
9314
9303
 
9315
9304
  [[package]]
9316
9305
  name = "xberg-tesseract"
9317
- version = "1.3.2"
9306
+ version = "1.3.4"
9318
9307
  source = "registry+https://github.com/rust-lang/crates.io-index"
9319
- checksum = "8e5ace00cbd63f3f07634c0f7fa115ae96d8205859fd3bb34b2fd58532cf891c"
9308
+ checksum = "29967431e67fd43c971d9d348935ee1ca58223bb3110b470dca7fdda0fd67c30"
9320
9309
  dependencies = [
9321
9310
  "cc",
9322
9311
  "cmake",
@@ -9495,9 +9484,9 @@ dependencies = [
9495
9484
 
9496
9485
  [[package]]
9497
9486
  name = "yoke-derive"
9498
- version = "0.8.3"
9487
+ version = "0.8.4"
9499
9488
  source = "registry+https://github.com/rust-lang/crates.io-index"
9500
- checksum = "33811428bee40dbceb6d545e95754741d17a6aef9a4849f0fd62e2ba4f412a78"
9489
+ checksum = "ec8ebde2db3681e8c9980cc27822030e68752690ddfa9473e739aeb4dbde6d71"
9501
9490
  dependencies = [
9502
9491
  "proc-macro2",
9503
9492
  "quote",
@@ -1,11 +1,11 @@
1
1
  # This file is auto-generated by alef — DO NOT EDIT.
2
- # alef:hash:a9572669372f324e7feb3a67c8a684ef01cf27a2eb205fd5fd8c0ee418dbb7b4
2
+ # alef:hash:715ad8642ffff546e63c46773a283e4a03bcb5b87f1ccadddc688baa7e1c4d1d
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 = "1.3.2"
8
+ version = "1.3.4"
9
9
  edition = "2024"
10
10
  license = "MIT"
11
11
  description = "High-performance document intelligence library"
@@ -73,7 +73,7 @@ xml = ["xberg/xml"]
73
73
  [dependencies]
74
74
  async-trait = "0.1"
75
75
  crawlberg = { default-features = false, version = "1.8.0" }
76
- html-to-markdown-rs = { default-features = false, version = "3.15" }
76
+ html-to-markdown-rs = { default-features = false, version = "3.16" }
77
77
  magnus = "0.9"
78
78
  rb-sys = ">=0.9.130, <0.10"
79
79
  serde = { version = "1", features = ["derive"] }
@@ -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 = "1.3.2", default-features = false, features = ["macos-intel-target", "simd-utf8"] }
85
+ xberg = { version = "1.3.4", 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 = "1.3.2", 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"] }
88
+ xberg = { version = "1.3.4", 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 = "1.3.2", default-features = false, features = ["windows-gnu-target", "simd-utf8"] }
91
+ xberg = { version = "1.3.4", 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
@@ -1,5 +1,5 @@
1
1
  // This file is auto-generated by alef. DO NOT EDIT.
2
- // alef:hash:e004b1d953b206d06d83d0462afc0689784b447478a1e0085a43e79980b1fd22
2
+ // alef:hash:3e862eca7b1250c4aa8d40b5563353572b94bd205d31f9f57c9efc950fcd26cb
3
3
  // Re-generate with: alef generate
4
4
  #![allow(dead_code, unused_imports, unused_variables)]
5
5
  #![allow(
@@ -4083,6 +4083,7 @@ pub struct ConversionOptions {
4083
4083
  strip_tags: Vec<String>,
4084
4084
  preserve_tags: Vec<String>,
4085
4085
  skip_images: bool,
4086
+ inline_data_media: InlineDataMedia,
4086
4087
  url_escape_style: UrlEscapeStyle,
4087
4088
  link_style: LinkStyle,
4088
4089
  output_format: HtmlToMarkdownRsOutputFormat,
@@ -4426,6 +4427,15 @@ impl ConversionOptions {
4426
4427
  })?,
4427
4428
  None => false,
4428
4429
  },
4430
+ inline_data_media: match kwargs.get(ruby.to_symbol("inline_data_media")) {
4431
+ Some(v) => InlineDataMedia::try_convert(v).map_err(|e| {
4432
+ magnus::Error::new(
4433
+ unsafe { magnus::Ruby::get_unchecked() }.exception_type_error(),
4434
+ format!("invalid value for `inline_data_media`: {}", e),
4435
+ )
4436
+ })?,
4437
+ None => InlineDataMedia::Keep,
4438
+ },
4429
4439
  url_escape_style: match kwargs.get(ruby.to_symbol("url_escape_style")) {
4430
4440
  Some(v) => UrlEscapeStyle::try_convert(v).map_err(|e| {
4431
4441
  magnus::Error::new(
@@ -4665,6 +4675,10 @@ impl ConversionOptions {
4665
4675
  self.skip_images
4666
4676
  }
4667
4677
 
4678
+ fn inline_data_media(&self) -> InlineDataMedia {
4679
+ self.inline_data_media.clone()
4680
+ }
4681
+
4668
4682
  fn url_escape_style(&self) -> UrlEscapeStyle {
4669
4683
  self.url_escape_style.clone()
4670
4684
  }
@@ -39230,6 +39244,58 @@ impl magnus::TryConvert for ImageType {
39230
39244
  unsafe impl IntoValueFromNative for ImageType {}
39231
39245
  unsafe impl TryConvertOwned for ImageType {}
39232
39246
 
39247
+ #[derive(Clone, Copy, PartialEq, Eq, Hash, Debug, serde::Serialize, serde::Deserialize)]
39248
+ pub enum InlineDataMedia {
39249
+ Keep,
39250
+ AltTextOnly,
39251
+ DropElement,
39252
+ }
39253
+
39254
+ impl Default for InlineDataMedia {
39255
+ fn default() -> Self {
39256
+ Self::Keep
39257
+ }
39258
+ }
39259
+
39260
+ impl magnus::IntoValue for InlineDataMedia {
39261
+ fn into_value_with(self, handle: &Ruby) -> magnus::Value {
39262
+ let sym = match self {
39263
+ InlineDataMedia::Keep => "Keep",
39264
+ InlineDataMedia::AltTextOnly => "AltTextOnly",
39265
+ InlineDataMedia::DropElement => "DropElement",
39266
+ };
39267
+ handle.to_symbol(sym).into_value_with(handle)
39268
+ }
39269
+ }
39270
+
39271
+ impl magnus::TryConvert for InlineDataMedia {
39272
+ fn try_convert(val: magnus::Value) -> Result<Self, magnus::Error> {
39273
+ // IntoValue emits Symbols, including when this enum is a Hash key.
39274
+ // Accept that exact representation as well as String inputs; do not
39275
+ // coerce arbitrary objects through to_s.
39276
+ let s: String = if let Some(symbol) = magnus::Symbol::from_value(val) {
39277
+ symbol.name()?.into_owned()
39278
+ } else {
39279
+ magnus::TryConvert::try_convert(val)?
39280
+ };
39281
+ // Accept the real serde wire value, the legacy always-snake_case symbol Magnus used to
39282
+ // emit unconditionally, and the verbatim PascalCase Rust variant name, so fixtures and
39283
+ // existing consumer code written in any of those styles keep working.
39284
+ match s.as_str() {
39285
+ "Keep" | "keep" => Ok(InlineDataMedia::Keep),
39286
+ "AltTextOnly" | "alt_text_only" => Ok(InlineDataMedia::AltTextOnly),
39287
+ "DropElement" | "drop_element" => Ok(InlineDataMedia::DropElement),
39288
+ other => Err(magnus::Error::new(
39289
+ unsafe { Ruby::get_unchecked() }.exception_arg_error(),
39290
+ format!("invalid InlineDataMedia value: {other}"),
39291
+ )),
39292
+ }
39293
+ }
39294
+ }
39295
+
39296
+ unsafe impl IntoValueFromNative for InlineDataMedia {}
39297
+ unsafe impl TryConvertOwned for InlineDataMedia {}
39298
+
39233
39299
  #[derive(Clone, Copy, PartialEq, Eq, Hash, Debug, serde::Serialize, serde::Deserialize)]
39234
39300
  #[serde(rename_all = "snake_case")]
39235
39301
  pub enum InlineType {
@@ -48845,6 +48911,7 @@ impl From<ConversionOptions> for html_to_markdown_rs::ConversionOptions {
48845
48911
  strip_tags: val.strip_tags.into_iter().collect(),
48846
48912
  preserve_tags: val.preserve_tags.into_iter().collect(),
48847
48913
  skip_images: val.skip_images,
48914
+ inline_data_media: val.inline_data_media.into(),
48848
48915
  url_escape_style: val.url_escape_style.into(),
48849
48916
  link_style: val.link_style.into(),
48850
48917
  output_format: val.output_format.into(),
@@ -48898,6 +48965,7 @@ impl From<html_to_markdown_rs::ConversionOptions> for ConversionOptions {
48898
48965
  strip_tags: val.strip_tags.into_iter().collect(),
48899
48966
  preserve_tags: val.preserve_tags.into_iter().collect(),
48900
48967
  skip_images: val.skip_images,
48968
+ inline_data_media: val.inline_data_media.into(),
48901
48969
  url_escape_style: val.url_escape_style.into(),
48902
48970
  link_style: val.link_style.into(),
48903
48971
  output_format: val.output_format.into(),
@@ -55821,6 +55889,26 @@ impl From<xberg::ImageType> for ImageType {
55821
55889
  }
55822
55890
  }
55823
55891
 
55892
+ impl From<InlineDataMedia> for html_to_markdown_rs::InlineDataMedia {
55893
+ fn from(val: InlineDataMedia) -> Self {
55894
+ match val {
55895
+ InlineDataMedia::Keep => Self::Keep,
55896
+ InlineDataMedia::AltTextOnly => Self::AltTextOnly,
55897
+ InlineDataMedia::DropElement => Self::DropElement,
55898
+ }
55899
+ }
55900
+ }
55901
+
55902
+ impl From<html_to_markdown_rs::InlineDataMedia> for InlineDataMedia {
55903
+ fn from(val: html_to_markdown_rs::InlineDataMedia) -> Self {
55904
+ match val {
55905
+ html_to_markdown_rs::InlineDataMedia::Keep => Self::Keep,
55906
+ html_to_markdown_rs::InlineDataMedia::AltTextOnly => Self::AltTextOnly,
55907
+ html_to_markdown_rs::InlineDataMedia::DropElement => Self::DropElement,
55908
+ }
55909
+ }
55910
+ }
55911
+
55824
55912
  impl From<InlineType> for xberg::InlineType {
55825
55913
  fn from(val: InlineType) -> Self {
55826
55914
  match val {
@@ -57922,6 +58010,8 @@ fn ruby_init(ruby: &Ruby) -> Result<(), Error> {
57922
58010
 
57923
58011
  class.define_method("skip_images", method!(ConversionOptions::skip_images, 0))?;
57924
58012
 
58013
+ class.define_method("inline_data_media", method!(ConversionOptions::inline_data_media, 0))?;
58014
+
57925
58015
  class.define_method("url_escape_style", method!(ConversionOptions::url_escape_style, 0))?;
57926
58016
 
57927
58017
  class.define_method("link_style", method!(ConversionOptions::link_style, 0))?;
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:c7a2e4c0b7a9168d08ef7f09b8b967926ae2bdff61094ac93d54a86a9813924d
2
+ # alef:hash:a73b2b7b23be41b809d7a63c6e84f6b22dc213b4d2d018e2004ef2a2f0e9410e
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 = "1.3.2"
9
+ VERSION = "1.3.4"
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:714d17cb31a0dbcf05ffbfd2931268de7747a7876060ed07e56d20da729e9edf
2
+ # alef:hash:4d6e82c5b0834d91c2575ca21fe65ed7dc5bb424ab80623cb550f60e8cd268ad
3
3
  # To regenerate: alef generate
4
4
  # To verify freshness: alef verify
5
5
 
@@ -355,6 +355,7 @@ def initialize: (?output_format: String, ?preprocessing_preset: String, ?remove_
355
355
  attr_reader strip_tags: Array[String]
356
356
  attr_reader preserve_tags: Array[String]
357
357
  attr_reader skip_images: bool
358
+ attr_reader inline_data_media: enum_InlineDataMedia
358
359
  attr_reader url_escape_style: enum_UrlEscapeStyle
359
360
  attr_reader link_style: enum_LinkStyle
360
361
  attr_reader output_format: enum_HtmlToMarkdownRsOutputFormat
@@ -368,7 +369,7 @@ def initialize: (?output_format: String, ?preprocessing_preset: String, ?remove_
368
369
  attr_reader tier_strategy: enum_TierStrategy
369
370
  attr_reader base_url: String?
370
371
 
371
- def initialize: (?heading_style: enum_HeadingStyle, ?list_indent_type: enum_ListIndentType, ?list_indent_width: Integer, ?bullets: String, ?strong_em_symbol: String, ?escape_asterisks: bool, ?escape_underscores: bool, ?escape_misc: bool, ?escape_ascii: bool, ?code_language: String, ?autolinks: bool, ?default_title: bool, ?br_in_tables: bool, ?compact_tables: bool, ?highlight_style: enum_HighlightStyle, ?extract_metadata: bool, ?whitespace_mode: enum_WhitespaceMode, ?strip_newlines: bool, ?wrap: bool, ?wrap_width: Integer, ?convert_as_inline: bool, ?sub_symbol: String, ?sup_symbol: String, ?newline_style: enum_NewlineStyle, ?code_block_style: enum_CodeBlockStyle, ?keep_inline_images_in: Array[String], ?preprocessing: PreprocessingOptions, ?encoding: String, ?debug: bool, ?strip_tags: Array[String], ?preserve_tags: Array[String], ?skip_images: bool, ?url_escape_style: enum_UrlEscapeStyle, ?link_style: enum_LinkStyle, ?output_format: enum_HtmlToMarkdownRsOutputFormat, ?include_document_structure: bool, ?extract_images: bool, ?max_image_size: Integer, ?capture_svg: bool, ?infer_dimensions: bool, ?max_depth: Integer, ?exclude_selectors: Array[String], ?tier_strategy: enum_TierStrategy, ?base_url: String) -> void
372
+ def initialize: (?heading_style: enum_HeadingStyle, ?list_indent_type: enum_ListIndentType, ?list_indent_width: Integer, ?bullets: String, ?strong_em_symbol: String, ?escape_asterisks: bool, ?escape_underscores: bool, ?escape_misc: bool, ?escape_ascii: bool, ?code_language: String, ?autolinks: bool, ?default_title: bool, ?br_in_tables: bool, ?compact_tables: bool, ?highlight_style: enum_HighlightStyle, ?extract_metadata: bool, ?whitespace_mode: enum_WhitespaceMode, ?strip_newlines: bool, ?wrap: bool, ?wrap_width: Integer, ?convert_as_inline: bool, ?sub_symbol: String, ?sup_symbol: String, ?newline_style: enum_NewlineStyle, ?code_block_style: enum_CodeBlockStyle, ?keep_inline_images_in: Array[String], ?preprocessing: PreprocessingOptions, ?encoding: String, ?debug: bool, ?strip_tags: Array[String], ?preserve_tags: Array[String], ?skip_images: bool, ?inline_data_media: enum_InlineDataMedia, ?url_escape_style: enum_UrlEscapeStyle, ?link_style: enum_LinkStyle, ?output_format: enum_HtmlToMarkdownRsOutputFormat, ?include_document_structure: bool, ?extract_images: bool, ?max_image_size: Integer, ?capture_svg: bool, ?infer_dimensions: bool, ?max_depth: Integer, ?exclude_selectors: Array[String], ?tier_strategy: enum_TierStrategy, ?base_url: String) -> void
372
373
  end
373
374
 
374
375
  class CoreProperties
@@ -2870,6 +2871,8 @@ def initialize: (?min: Integer, ?max: Integer, years: Array[Integer]) -> void
2870
2871
 
2871
2872
  type enum_ImageType = :"data-uri" | :"inline-svg" | :external | :relative
2872
2873
 
2874
+ type enum_InlineDataMedia = :Keep | :AltTextOnly | :DropElement
2875
+
2873
2876
  type enum_InlineType = :text | :strong | :emphasis | :highlight | :subscript | :superscript | :insert | :delete | :code | :link | :image | :span | :math | :raw_inline | :footnote_ref | :symbol
2874
2877
 
2875
2878
  type enum_JupyterCellRendering = :source | :outputs | :both
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: 1.3.2
4
+ version: 1.3.4
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: 2026-10-02 00:00:00.000000000 Z
11
+ date: 2026-10-05 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: rb_sys