kreuzberg 4.0.0.pre.rc.6 → 4.0.0.pre.rc.8

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.
Files changed (127) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile.lock +5 -5
  3. data/README.md +15 -9
  4. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -0
  5. data/ext/kreuzberg_rb/native/Cargo.lock +511 -325
  6. data/ext/kreuzberg_rb/native/Cargo.toml +13 -3
  7. data/ext/kreuzberg_rb/native/src/lib.rs +139 -2
  8. data/kreuzberg.gemspec +38 -4
  9. data/lib/kreuzberg/config.rb +34 -1
  10. data/lib/kreuzberg/result.rb +77 -14
  11. data/lib/kreuzberg/version.rb +1 -1
  12. data/sig/kreuzberg.rbs +23 -6
  13. data/vendor/kreuzberg/Cargo.toml +32 -11
  14. data/vendor/kreuzberg/README.md +54 -8
  15. data/vendor/kreuzberg/build.rs +549 -132
  16. data/vendor/kreuzberg/src/chunking/mod.rs +1279 -79
  17. data/vendor/kreuzberg/src/chunking/processor.rs +220 -0
  18. data/vendor/kreuzberg/src/core/config.rs +49 -1
  19. data/vendor/kreuzberg/src/core/extractor.rs +134 -2
  20. data/vendor/kreuzberg/src/core/mod.rs +4 -2
  21. data/vendor/kreuzberg/src/core/pipeline.rs +188 -1
  22. data/vendor/kreuzberg/src/extraction/docx.rs +358 -0
  23. data/vendor/kreuzberg/src/extraction/html.rs +24 -8
  24. data/vendor/kreuzberg/src/extraction/image.rs +124 -1
  25. data/vendor/kreuzberg/src/extraction/libreoffice.rs +1 -2
  26. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -3
  27. data/vendor/kreuzberg/src/extraction/pptx.rs +187 -87
  28. data/vendor/kreuzberg/src/extractors/archive.rs +1 -0
  29. data/vendor/kreuzberg/src/extractors/bibtex.rs +1 -0
  30. data/vendor/kreuzberg/src/extractors/docbook.rs +2 -0
  31. data/vendor/kreuzberg/src/extractors/docx.rs +50 -17
  32. data/vendor/kreuzberg/src/extractors/email.rs +29 -15
  33. data/vendor/kreuzberg/src/extractors/epub.rs +1 -0
  34. data/vendor/kreuzberg/src/extractors/excel.rs +2 -0
  35. data/vendor/kreuzberg/src/extractors/fictionbook.rs +1 -0
  36. data/vendor/kreuzberg/src/extractors/html.rs +29 -15
  37. data/vendor/kreuzberg/src/extractors/image.rs +25 -4
  38. data/vendor/kreuzberg/src/extractors/jats.rs +3 -0
  39. data/vendor/kreuzberg/src/extractors/jupyter.rs +1 -0
  40. data/vendor/kreuzberg/src/extractors/latex.rs +1 -0
  41. data/vendor/kreuzberg/src/extractors/markdown.rs +1 -0
  42. data/vendor/kreuzberg/src/extractors/mod.rs +78 -14
  43. data/vendor/kreuzberg/src/extractors/odt.rs +3 -3
  44. data/vendor/kreuzberg/src/extractors/opml.rs +1 -0
  45. data/vendor/kreuzberg/src/extractors/orgmode.rs +1 -0
  46. data/vendor/kreuzberg/src/extractors/pdf.rs +197 -17
  47. data/vendor/kreuzberg/src/extractors/pptx.rs +32 -13
  48. data/vendor/kreuzberg/src/extractors/rst.rs +1 -0
  49. data/vendor/kreuzberg/src/extractors/rtf.rs +3 -4
  50. data/vendor/kreuzberg/src/extractors/structured.rs +2 -0
  51. data/vendor/kreuzberg/src/extractors/text.rs +7 -2
  52. data/vendor/kreuzberg/src/extractors/typst.rs +1 -0
  53. data/vendor/kreuzberg/src/extractors/xml.rs +27 -15
  54. data/vendor/kreuzberg/src/keywords/processor.rs +9 -1
  55. data/vendor/kreuzberg/src/language_detection/mod.rs +43 -0
  56. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -0
  57. data/vendor/kreuzberg/src/lib.rs +10 -2
  58. data/vendor/kreuzberg/src/mcp/mod.rs +3 -0
  59. data/vendor/kreuzberg/src/mcp/server.rs +120 -12
  60. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +2 -0
  61. data/vendor/kreuzberg/src/pdf/bundled.rs +328 -0
  62. data/vendor/kreuzberg/src/pdf/error.rs +8 -0
  63. data/vendor/kreuzberg/src/pdf/metadata.rs +238 -95
  64. data/vendor/kreuzberg/src/pdf/mod.rs +18 -2
  65. data/vendor/kreuzberg/src/pdf/rendering.rs +1 -2
  66. data/vendor/kreuzberg/src/pdf/table.rs +26 -2
  67. data/vendor/kreuzberg/src/pdf/text.rs +89 -7
  68. data/vendor/kreuzberg/src/plugins/extractor.rs +34 -3
  69. data/vendor/kreuzberg/src/plugins/mod.rs +3 -0
  70. data/vendor/kreuzberg/src/plugins/ocr.rs +22 -3
  71. data/vendor/kreuzberg/src/plugins/processor.rs +8 -0
  72. data/vendor/kreuzberg/src/plugins/registry.rs +2 -0
  73. data/vendor/kreuzberg/src/plugins/validator.rs +11 -0
  74. data/vendor/kreuzberg/src/text/mod.rs +6 -0
  75. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -0
  76. data/vendor/kreuzberg/src/types.rs +173 -21
  77. data/vendor/kreuzberg/tests/archive_integration.rs +2 -0
  78. data/vendor/kreuzberg/tests/batch_processing.rs +5 -3
  79. data/vendor/kreuzberg/tests/concurrency_stress.rs +14 -6
  80. data/vendor/kreuzberg/tests/config_features.rs +15 -1
  81. data/vendor/kreuzberg/tests/config_loading_tests.rs +1 -0
  82. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +2 -0
  83. data/vendor/kreuzberg/tests/email_integration.rs +2 -0
  84. data/vendor/kreuzberg/tests/error_handling.rs +43 -34
  85. data/vendor/kreuzberg/tests/format_integration.rs +2 -0
  86. data/vendor/kreuzberg/tests/image_integration.rs +2 -0
  87. data/vendor/kreuzberg/tests/mime_detection.rs +17 -16
  88. data/vendor/kreuzberg/tests/ocr_configuration.rs +4 -0
  89. data/vendor/kreuzberg/tests/ocr_errors.rs +22 -0
  90. data/vendor/kreuzberg/tests/ocr_quality.rs +2 -0
  91. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -21
  92. data/vendor/kreuzberg/tests/pdf_integration.rs +2 -0
  93. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -0
  94. data/vendor/kreuzberg/tests/pipeline_integration.rs +25 -0
  95. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +5 -0
  96. data/vendor/kreuzberg/tests/plugin_system.rs +6 -0
  97. data/vendor/kreuzberg/tests/registry_integration_tests.rs +1 -0
  98. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +2 -0
  99. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -1
  100. data/vendor/kreuzberg/tests/security_validation.rs +1 -0
  101. data/vendor/kreuzberg/tests/test_fastembed.rs +45 -23
  102. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1 -0
  103. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +3 -2
  104. data/vendor/rb-sys/.cargo_vcs_info.json +2 -2
  105. data/vendor/rb-sys/Cargo.lock +15 -15
  106. data/vendor/rb-sys/Cargo.toml +4 -4
  107. data/vendor/rb-sys/Cargo.toml.orig +4 -4
  108. data/vendor/rb-sys/build/features.rs +5 -2
  109. data/vendor/rb-sys/build/main.rs +55 -15
  110. data/vendor/rb-sys/build/stable_api_config.rs +4 -2
  111. data/vendor/rb-sys/build/version.rs +3 -1
  112. data/vendor/rb-sys/src/lib.rs +1 -0
  113. data/vendor/rb-sys/src/macros.rs +2 -2
  114. data/vendor/rb-sys/src/special_consts.rs +1 -1
  115. data/vendor/rb-sys/src/stable_api/compiled.rs +1 -1
  116. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +12 -4
  117. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +12 -4
  118. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +12 -4
  119. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +12 -4
  120. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +19 -6
  121. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +17 -5
  122. data/vendor/rb-sys/src/stable_api.rs +0 -1
  123. data/vendor/rb-sys/src/tracking_allocator.rs +1 -3
  124. metadata +13 -10
  125. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  126. data/vendor/rb-sys/.cargo-ok +0 -1
  127. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
@@ -75,6 +75,56 @@ dependencies = [
75
75
  "libc",
76
76
  ]
77
77
 
78
+ [[package]]
79
+ name = "anstream"
80
+ version = "0.6.21"
81
+ source = "registry+https://github.com/rust-lang/crates.io-index"
82
+ checksum = "43d5b281e737544384e969a5ccad3f1cdd24b48086a0fc1b2a5262a26b8f4f4a"
83
+ dependencies = [
84
+ "anstyle",
85
+ "anstyle-parse",
86
+ "anstyle-query",
87
+ "anstyle-wincon",
88
+ "colorchoice",
89
+ "is_terminal_polyfill",
90
+ "utf8parse",
91
+ ]
92
+
93
+ [[package]]
94
+ name = "anstyle"
95
+ version = "1.0.13"
96
+ source = "registry+https://github.com/rust-lang/crates.io-index"
97
+ checksum = "5192cca8006f1fd4f7237516f40fa183bb07f8fbdfedaa0036de5ea9b0b45e78"
98
+
99
+ [[package]]
100
+ name = "anstyle-parse"
101
+ version = "0.2.7"
102
+ source = "registry+https://github.com/rust-lang/crates.io-index"
103
+ checksum = "4e7644824f0aa2c7b9384579234ef10eb7efb6a0deb83f9630a49594dd9c15c2"
104
+ dependencies = [
105
+ "utf8parse",
106
+ ]
107
+
108
+ [[package]]
109
+ name = "anstyle-query"
110
+ version = "1.1.5"
111
+ source = "registry+https://github.com/rust-lang/crates.io-index"
112
+ checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
113
+ dependencies = [
114
+ "windows-sys 0.61.2",
115
+ ]
116
+
117
+ [[package]]
118
+ name = "anstyle-wincon"
119
+ version = "3.0.11"
120
+ source = "registry+https://github.com/rust-lang/crates.io-index"
121
+ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
122
+ dependencies = [
123
+ "anstyle",
124
+ "once_cell_polyfill",
125
+ "windows-sys 0.61.2",
126
+ ]
127
+
78
128
  [[package]]
79
129
  name = "anyhow"
80
130
  version = "1.0.100"
@@ -148,9 +198,9 @@ dependencies = [
148
198
 
149
199
  [[package]]
150
200
  name = "astral-tl"
151
- version = "0.7.10"
201
+ version = "0.7.11"
152
202
  source = "registry+https://github.com/rust-lang/crates.io-index"
153
- checksum = "b8dfa40da988ff8327db15678418b2394b0546514b7a5c9fac75e1eb3fa40550"
203
+ checksum = "d90933ffb0f97e2fc2e0de21da9d3f20597b804012d199843a6fe7c2810d28f3"
154
204
  dependencies = [
155
205
  "memchr",
156
206
  ]
@@ -304,6 +354,19 @@ version = "1.8.0"
304
354
  source = "registry+https://github.com/rust-lang/crates.io-index"
305
355
  checksum = "55248b47b0caf0546f7988906588779981c43bb1bc9d0c44087278f80cdb44ba"
306
356
 
357
+ [[package]]
358
+ name = "biblatex"
359
+ version = "0.11.0"
360
+ source = "registry+https://github.com/rust-lang/crates.io-index"
361
+ checksum = "53d0c374feba1b9a59042a7c1cf00ce7c34b977b9134fe7c42b08e5183729f66"
362
+ dependencies = [
363
+ "paste",
364
+ "roman-numerals-rs",
365
+ "strum",
366
+ "unicode-normalization",
367
+ "unscanny",
368
+ ]
369
+
307
370
  [[package]]
308
371
  name = "bincode"
309
372
  version = "2.0.1"
@@ -539,11 +602,30 @@ dependencies = [
539
602
  "cipher",
540
603
  ]
541
604
 
605
+ [[package]]
606
+ name = "cbindgen"
607
+ version = "0.29.2"
608
+ source = "registry+https://github.com/rust-lang/crates.io-index"
609
+ checksum = "befbfd072a8e81c02f8c507aefce431fe5e7d051f83d48a23ffc9b9fe5a11799"
610
+ dependencies = [
611
+ "clap",
612
+ "heck",
613
+ "indexmap",
614
+ "log",
615
+ "proc-macro2",
616
+ "quote",
617
+ "serde",
618
+ "serde_json",
619
+ "syn",
620
+ "tempfile",
621
+ "toml 0.9.8",
622
+ ]
623
+
542
624
  [[package]]
543
625
  name = "cc"
544
- version = "1.2.48"
626
+ version = "1.2.49"
545
627
  source = "registry+https://github.com/rust-lang/crates.io-index"
546
- checksum = "c481bdbf0ed3b892f6f806287d72acd515b352a4ec27a208489b8c1bc839633a"
628
+ checksum = "90583009037521a116abf44494efecd645ba48b6622457080f080b85544e2215"
547
629
  dependencies = [
548
630
  "find-msvc-tools",
549
631
  "jobserver",
@@ -639,6 +721,33 @@ dependencies = [
639
721
  "libloading 0.8.9",
640
722
  ]
641
723
 
724
+ [[package]]
725
+ name = "clap"
726
+ version = "4.5.53"
727
+ source = "registry+https://github.com/rust-lang/crates.io-index"
728
+ checksum = "c9e340e012a1bf4935f5282ed1436d1489548e8f72308207ea5df0e23d2d03f8"
729
+ dependencies = [
730
+ "clap_builder",
731
+ ]
732
+
733
+ [[package]]
734
+ name = "clap_builder"
735
+ version = "4.5.53"
736
+ source = "registry+https://github.com/rust-lang/crates.io-index"
737
+ checksum = "d76b5d13eaa18c901fd2f7fca939fefe3a0727a953561fefdf3b2922b8569d00"
738
+ dependencies = [
739
+ "anstream",
740
+ "anstyle",
741
+ "clap_lex",
742
+ "strsim",
743
+ ]
744
+
745
+ [[package]]
746
+ name = "clap_lex"
747
+ version = "0.7.6"
748
+ source = "registry+https://github.com/rust-lang/crates.io-index"
749
+ checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
750
+
642
751
  [[package]]
643
752
  name = "cmake"
644
753
  version = "0.1.54"
@@ -663,6 +772,12 @@ version = "1.1.0"
663
772
  source = "registry+https://github.com/rust-lang/crates.io-index"
664
773
  checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b"
665
774
 
775
+ [[package]]
776
+ name = "colorchoice"
777
+ version = "1.0.4"
778
+ source = "registry+https://github.com/rust-lang/crates.io-index"
779
+ checksum = "b05b61dc5112cbb17e4b6cd61790d9845d13888356391624cbe7e41efeac1e75"
780
+
666
781
  [[package]]
667
782
  name = "compact_str"
668
783
  version = "0.9.0"
@@ -862,29 +977,6 @@ dependencies = [
862
977
  "typenum",
863
978
  ]
864
979
 
865
- [[package]]
866
- name = "cssparser"
867
- version = "0.35.0"
868
- source = "registry+https://github.com/rust-lang/crates.io-index"
869
- checksum = "4e901edd733a1472f944a45116df3f846f54d37e67e68640ac8bb69689aca2aa"
870
- dependencies = [
871
- "cssparser-macros",
872
- "dtoa-short",
873
- "itoa",
874
- "phf 0.11.3",
875
- "smallvec 1.15.1",
876
- ]
877
-
878
- [[package]]
879
- name = "cssparser-macros"
880
- version = "0.6.1"
881
- source = "registry+https://github.com/rust-lang/crates.io-index"
882
- checksum = "13b588ba4ac1a99f7f2964d24b3d896ddc6bf847ee3855dbd4366f058cfcd331"
883
- dependencies = [
884
- "quote",
885
- "syn",
886
- ]
887
-
888
980
  [[package]]
889
981
  name = "darling"
890
982
  version = "0.20.11"
@@ -1002,27 +1094,6 @@ dependencies = [
1002
1094
  "syn",
1003
1095
  ]
1004
1096
 
1005
- [[package]]
1006
- name = "derive_more"
1007
- version = "2.1.0"
1008
- source = "registry+https://github.com/rust-lang/crates.io-index"
1009
- checksum = "10b768e943bed7bf2cab53df09f4bc34bfd217cdb57d971e769874c9a6710618"
1010
- dependencies = [
1011
- "derive_more-impl",
1012
- ]
1013
-
1014
- [[package]]
1015
- name = "derive_more-impl"
1016
- version = "2.1.0"
1017
- source = "registry+https://github.com/rust-lang/crates.io-index"
1018
- checksum = "6d286bfdaf75e988b4a78e013ecd79c581e06399ab53fbacd2d916c2f904f30b"
1019
- dependencies = [
1020
- "proc-macro2",
1021
- "quote",
1022
- "rustc_version",
1023
- "syn",
1024
- ]
1025
-
1026
1097
  [[package]]
1027
1098
  name = "derive_utils"
1028
1099
  version = "0.15.0"
@@ -1092,6 +1163,19 @@ dependencies = [
1092
1163
  "litrs",
1093
1164
  ]
1094
1165
 
1166
+ [[package]]
1167
+ name = "document_tree"
1168
+ version = "0.4.2"
1169
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1170
+ checksum = "6742722dd3e6cd908bc522283cb5502e25f696d1c9904fb251ec266b6b3f9cce"
1171
+ dependencies = [
1172
+ "anyhow",
1173
+ "regex",
1174
+ "serde",
1175
+ "serde_derive",
1176
+ "url",
1177
+ ]
1178
+
1095
1179
  [[package]]
1096
1180
  name = "docx-lite"
1097
1181
  version = "0.2.0"
@@ -1103,21 +1187,6 @@ dependencies = [
1103
1187
  "zip 0.6.6",
1104
1188
  ]
1105
1189
 
1106
- [[package]]
1107
- name = "dtoa"
1108
- version = "1.0.10"
1109
- source = "registry+https://github.com/rust-lang/crates.io-index"
1110
- checksum = "d6add3b8cff394282be81f3fc1a0605db594ed69890078ca6e2cab1c408bcf04"
1111
-
1112
- [[package]]
1113
- name = "dtoa-short"
1114
- version = "0.3.5"
1115
- source = "registry+https://github.com/rust-lang/crates.io-index"
1116
- checksum = "cd1511a7b6a56299bd043a9c167a6d2bfb37bf84a6dfceaba651168adfb43c87"
1117
- dependencies = [
1118
- "dtoa",
1119
- ]
1120
-
1121
1190
  [[package]]
1122
1191
  name = "dyn-clone"
1123
1192
  version = "1.0.20"
@@ -1134,10 +1203,13 @@ dependencies = [
1134
1203
  ]
1135
1204
 
1136
1205
  [[package]]
1137
- name = "ego-tree"
1138
- version = "0.10.0"
1206
+ name = "ecow"
1207
+ version = "0.2.6"
1139
1208
  source = "registry+https://github.com/rust-lang/crates.io-index"
1140
- checksum = "b2972feb8dffe7bc8c5463b1dacda1b0dfbed3710e50f977d965429692d74cd8"
1209
+ checksum = "78e4f79b296fbaab6ce2e22d52cb4c7f010fe0ebe7a32e34fa25885fd797bd02"
1210
+ dependencies = [
1211
+ "serde",
1212
+ ]
1141
1213
 
1142
1214
  [[package]]
1143
1215
  name = "either"
@@ -1281,13 +1353,12 @@ dependencies = [
1281
1353
 
1282
1354
  [[package]]
1283
1355
  name = "fastembed"
1284
- version = "5.3.1"
1356
+ version = "5.4.0"
1285
1357
  source = "registry+https://github.com/rust-lang/crates.io-index"
1286
- checksum = "d9c4e3e151df5140e4661795b7be82c6280b5c29157d9f0f330aaef2eef1ca4c"
1358
+ checksum = "b0d719825156b62586040fd0e5653a4f7bc0ad9caf6c7ec38cb18f1a08ee0384"
1287
1359
  dependencies = [
1288
1360
  "anyhow",
1289
1361
  "hf-hub",
1290
- "image",
1291
1362
  "ndarray 0.16.1",
1292
1363
  "ort",
1293
1364
  "serde_json",
@@ -1320,6 +1391,18 @@ dependencies = [
1320
1391
  "syn",
1321
1392
  ]
1322
1393
 
1394
+ [[package]]
1395
+ name = "fb2"
1396
+ version = "0.4.4"
1397
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1398
+ checksum = "f2d27bbfaf8178bef57815d3b6169100928316099922e419668ee50f61e87e7a"
1399
+ dependencies = [
1400
+ "chrono",
1401
+ "language-tags",
1402
+ "quick-xml 0.30.0",
1403
+ "serde",
1404
+ ]
1405
+
1323
1406
  [[package]]
1324
1407
  name = "fdeflate"
1325
1408
  version = "0.3.7"
@@ -1520,15 +1603,6 @@ dependencies = [
1520
1603
  "slab",
1521
1604
  ]
1522
1605
 
1523
- [[package]]
1524
- name = "fxhash"
1525
- version = "0.2.1"
1526
- source = "registry+https://github.com/rust-lang/crates.io-index"
1527
- checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
1528
- dependencies = [
1529
- "byteorder",
1530
- ]
1531
-
1532
1606
  [[package]]
1533
1607
  name = "generic-array"
1534
1608
  version = "0.14.7"
@@ -1591,6 +1665,19 @@ version = "0.3.3"
1591
1665
  source = "registry+https://github.com/rust-lang/crates.io-index"
1592
1666
  checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
1593
1667
 
1668
+ [[package]]
1669
+ name = "gloo-utils"
1670
+ version = "0.1.7"
1671
+ source = "registry+https://github.com/rust-lang/crates.io-index"
1672
+ checksum = "037fcb07216cb3a30f7292bd0176b050b7b9a052ba830ef7d5d65f6dc64ba58e"
1673
+ dependencies = [
1674
+ "js-sys",
1675
+ "serde",
1676
+ "serde_json",
1677
+ "wasm-bindgen",
1678
+ "web-sys",
1679
+ ]
1680
+
1594
1681
  [[package]]
1595
1682
  name = "h2"
1596
1683
  version = "0.4.12"
@@ -1689,7 +1776,7 @@ dependencies = [
1689
1776
  "indicatif",
1690
1777
  "libc",
1691
1778
  "log",
1692
- "rand 0.9.2",
1779
+ "rand",
1693
1780
  "reqwest",
1694
1781
  "serde",
1695
1782
  "serde_json",
@@ -1727,14 +1814,14 @@ dependencies = [
1727
1814
 
1728
1815
  [[package]]
1729
1816
  name = "html-to-markdown-rs"
1730
- version = "2.11.1"
1817
+ version = "2.14.1"
1731
1818
  source = "registry+https://github.com/rust-lang/crates.io-index"
1732
- checksum = "529efa8df8408c0dafd92d4a5162cb0b3f92c5207f21af8a82ded8484aca1824"
1819
+ checksum = "b4c5648cf0023eeccd94b7374bb998af20a976bffb863cca1d8cf1ec1b1b12ef"
1733
1820
  dependencies = [
1734
1821
  "astral-tl",
1735
1822
  "base64 0.22.1",
1736
1823
  "html-escape",
1737
- "html5ever 0.36.1",
1824
+ "html5ever",
1738
1825
  "image",
1739
1826
  "markup5ever_rcdom",
1740
1827
  "once_cell",
@@ -1742,17 +1829,6 @@ dependencies = [
1742
1829
  "thiserror 2.0.17",
1743
1830
  ]
1744
1831
 
1745
- [[package]]
1746
- name = "html5ever"
1747
- version = "0.35.0"
1748
- source = "registry+https://github.com/rust-lang/crates.io-index"
1749
- checksum = "55d958c2f74b664487a2035fe1dadb032c48718a03b63f3ab0b8537db8549ed4"
1750
- dependencies = [
1751
- "log",
1752
- "markup5ever 0.35.0",
1753
- "match_token",
1754
- ]
1755
-
1756
1832
  [[package]]
1757
1833
  name = "html5ever"
1758
1834
  version = "0.36.1"
@@ -1760,7 +1836,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
1760
1836
  checksum = "6452c4751a24e1b99c3260d505eaeee76a050573e61f30ac2c924ddc7236f01e"
1761
1837
  dependencies = [
1762
1838
  "log",
1763
- "markup5ever 0.36.1",
1839
+ "markup5ever",
1764
1840
  ]
1765
1841
 
1766
1842
  [[package]]
@@ -2077,10 +2153,8 @@ dependencies = [
2077
2153
  "moxcms",
2078
2154
  "num-traits",
2079
2155
  "png",
2080
- "qoi",
2081
2156
  "ravif",
2082
2157
  "rayon",
2083
- "rgb",
2084
2158
  "tiff",
2085
2159
  "zune-core 0.5.0",
2086
2160
  "zune-jpeg 0.5.5",
@@ -2173,6 +2247,12 @@ dependencies = [
2173
2247
  "serde",
2174
2248
  ]
2175
2249
 
2250
+ [[package]]
2251
+ name = "is_terminal_polyfill"
2252
+ version = "1.70.2"
2253
+ source = "registry+https://github.com/rust-lang/crates.io-index"
2254
+ checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
2255
+
2176
2256
  [[package]]
2177
2257
  name = "itertools"
2178
2258
  version = "0.12.1"
@@ -2269,20 +2349,21 @@ dependencies = [
2269
2349
 
2270
2350
  [[package]]
2271
2351
  name = "kreuzberg"
2272
- version = "4.0.0-rc.5"
2352
+ version = "4.0.0-rc.7"
2273
2353
  dependencies = [
2274
2354
  "ahash",
2275
2355
  "async-trait",
2276
2356
  "base64 0.22.1",
2277
2357
  "base64-simd",
2358
+ "biblatex",
2278
2359
  "calamine",
2279
2360
  "chardetng",
2280
2361
  "docx-lite",
2281
2362
  "encoding_rs",
2282
2363
  "fast_image_resize",
2283
2364
  "fastembed",
2365
+ "fb2",
2284
2366
  "hex",
2285
- "html-escape",
2286
2367
  "html-to-markdown-rs",
2287
2368
  "image",
2288
2369
  "indexmap",
@@ -2299,9 +2380,11 @@ dependencies = [
2299
2380
  "ndarray 0.17.1",
2300
2381
  "num_cpus",
2301
2382
  "once_cell",
2383
+ "org",
2302
2384
  "paste",
2303
2385
  "pdfium-render",
2304
2386
  "polars",
2387
+ "pulldown-cmark",
2305
2388
  "quick-xml 0.38.4",
2306
2389
  "rake",
2307
2390
  "rayon",
@@ -2309,7 +2392,8 @@ dependencies = [
2309
2392
  "reqwest",
2310
2393
  "rmp-serde",
2311
2394
  "roxmltree",
2312
- "scraper",
2395
+ "rst_parser",
2396
+ "rtf-parser",
2313
2397
  "serde",
2314
2398
  "serde_json",
2315
2399
  "serde_yaml_ng",
@@ -2317,9 +2401,11 @@ dependencies = [
2317
2401
  "tar",
2318
2402
  "text-splitter",
2319
2403
  "thiserror 2.0.17",
2404
+ "tiff",
2320
2405
  "tokio",
2321
- "toml",
2406
+ "toml 0.9.8",
2322
2407
  "tracing",
2408
+ "typst-syntax",
2323
2409
  "unicode-normalization",
2324
2410
  "uuid",
2325
2411
  "whatlang",
@@ -2327,13 +2413,27 @@ dependencies = [
2327
2413
  "zip 6.0.0",
2328
2414
  ]
2329
2415
 
2416
+ [[package]]
2417
+ name = "kreuzberg-ffi"
2418
+ version = "4.0.0-rc.7"
2419
+ dependencies = [
2420
+ "async-trait",
2421
+ "cbindgen",
2422
+ "html-to-markdown-rs",
2423
+ "kreuzberg",
2424
+ "serde",
2425
+ "serde_json",
2426
+ "tokio",
2427
+ ]
2428
+
2330
2429
  [[package]]
2331
2430
  name = "kreuzberg-rb"
2332
- version = "4.0.0-rc.5"
2431
+ version = "4.0.0-rc.7"
2333
2432
  dependencies = [
2334
2433
  "async-trait",
2335
2434
  "html-to-markdown-rs",
2336
2435
  "kreuzberg",
2436
+ "kreuzberg-ffi",
2337
2437
  "magnus",
2338
2438
  "pretty_assertions",
2339
2439
  "rb-sys",
@@ -2343,9 +2443,9 @@ dependencies = [
2343
2443
 
2344
2444
  [[package]]
2345
2445
  name = "kreuzberg-tesseract"
2346
- version = "1.0.0-rc.1"
2446
+ version = "4.0.0-rc.6"
2347
2447
  source = "registry+https://github.com/rust-lang/crates.io-index"
2348
- checksum = "b30f3556047862787280ab85a021a387ff6cb6b8bf4ba3b33e4a2ceb70da948e"
2448
+ checksum = "4977f0d2fdb7f1983bd55b76cc53e0fe4846b3e3dbfdcfd5bba7ef8aa895a97c"
2349
2449
  dependencies = [
2350
2450
  "cc",
2351
2451
  "cmake",
@@ -2355,6 +2455,15 @@ dependencies = [
2355
2455
  "zip 6.0.0",
2356
2456
  ]
2357
2457
 
2458
+ [[package]]
2459
+ name = "language-tags"
2460
+ version = "0.3.2"
2461
+ source = "registry+https://github.com/rust-lang/crates.io-index"
2462
+ checksum = "d4345964bb142484797b161f473a503a434de77149dd8c7427788c6e13379388"
2463
+ dependencies = [
2464
+ "serde",
2465
+ ]
2466
+
2358
2467
  [[package]]
2359
2468
  name = "lazy_static"
2360
2469
  version = "1.5.0"
@@ -2510,7 +2619,7 @@ dependencies = [
2510
2619
  "md-5",
2511
2620
  "nom 8.0.0",
2512
2621
  "nom_locate",
2513
- "rand 0.9.2",
2622
+ "rand",
2514
2623
  "rangemap",
2515
2624
  "rayon",
2516
2625
  "sha2",
@@ -2618,17 +2727,6 @@ dependencies = [
2618
2727
  "hashify",
2619
2728
  ]
2620
2729
 
2621
- [[package]]
2622
- name = "markup5ever"
2623
- version = "0.35.0"
2624
- source = "registry+https://github.com/rust-lang/crates.io-index"
2625
- checksum = "311fe69c934650f8f19652b3946075f0fc41ad8757dbb68f1ca14e7900ecc1c3"
2626
- dependencies = [
2627
- "log",
2628
- "tendril",
2629
- "web_atoms 0.1.3",
2630
- ]
2631
-
2632
2730
  [[package]]
2633
2731
  name = "markup5ever"
2634
2732
  version = "0.36.1"
@@ -2637,7 +2735,7 @@ checksum = "6c3294c4d74d0742910f8c7b466f44dda9eb2d5742c1e430138df290a1e8451c"
2637
2735
  dependencies = [
2638
2736
  "log",
2639
2737
  "tendril",
2640
- "web_atoms 0.2.0",
2738
+ "web_atoms",
2641
2739
  ]
2642
2740
 
2643
2741
  [[package]]
@@ -2646,23 +2744,12 @@ version = "0.36.0+unofficial"
2646
2744
  source = "registry+https://github.com/rust-lang/crates.io-index"
2647
2745
  checksum = "3e5fc8802e8797c0dfdd2ce5c21aa0aee21abbc7b3b18559100651b3352a7b63"
2648
2746
  dependencies = [
2649
- "html5ever 0.36.1",
2650
- "markup5ever 0.36.1",
2747
+ "html5ever",
2748
+ "markup5ever",
2651
2749
  "tendril",
2652
2750
  "xml5ever",
2653
2751
  ]
2654
2752
 
2655
- [[package]]
2656
- name = "match_token"
2657
- version = "0.35.0"
2658
- source = "registry+https://github.com/rust-lang/crates.io-index"
2659
- checksum = "ac84fd3f360fcc43dc5f5d186f02a94192761a080e8bc58621ad4d12296a58cf"
2660
- dependencies = [
2661
- "proc-macro2",
2662
- "quote",
2663
- "syn",
2664
- ]
2665
-
2666
2753
  [[package]]
2667
2754
  name = "matchgen"
2668
2755
  version = "0.3.1"
@@ -3033,7 +3120,7 @@ dependencies = [
3033
3120
  "parking_lot",
3034
3121
  "percent-encoding",
3035
3122
  "quick-xml 0.38.4",
3036
- "rand 0.9.2",
3123
+ "rand",
3037
3124
  "reqwest",
3038
3125
  "ring",
3039
3126
  "serde",
@@ -3054,6 +3141,12 @@ version = "1.21.3"
3054
3141
  source = "registry+https://github.com/rust-lang/crates.io-index"
3055
3142
  checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
3056
3143
 
3144
+ [[package]]
3145
+ name = "once_cell_polyfill"
3146
+ version = "1.70.2"
3147
+ source = "registry+https://github.com/rust-lang/crates.io-index"
3148
+ checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
3149
+
3057
3150
  [[package]]
3058
3151
  name = "onig"
3059
3152
  version = "6.5.1"
@@ -3126,6 +3219,12 @@ version = "0.2.0"
3126
3219
  source = "registry+https://github.com/rust-lang/crates.io-index"
3127
3220
  checksum = "04744f49eae99ab78e0d5c0b603ab218f515ea8cfe5a456d7629ad883a3b6e7d"
3128
3221
 
3222
+ [[package]]
3223
+ name = "org"
3224
+ version = "0.3.1"
3225
+ source = "registry+https://github.com/rust-lang/crates.io-index"
3226
+ checksum = "cfdf547b633735ad9d67353aba48b3e685ab5ffb3195aaa9a1b1d8613e11b98c"
3227
+
3129
3228
  [[package]]
3130
3229
  name = "ort"
3131
3230
  version = "2.0.0-rc.10"
@@ -3250,13 +3349,46 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
3250
3349
  checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
3251
3350
 
3252
3351
  [[package]]
3253
- name = "phf"
3254
- version = "0.11.3"
3352
+ name = "pest"
3353
+ version = "2.8.4"
3354
+ source = "registry+https://github.com/rust-lang/crates.io-index"
3355
+ checksum = "cbcfd20a6d4eeba40179f05735784ad32bdaef05ce8e8af05f180d45bb3e7e22"
3356
+ dependencies = [
3357
+ "memchr",
3358
+ "ucd-trie",
3359
+ ]
3360
+
3361
+ [[package]]
3362
+ name = "pest_derive"
3363
+ version = "2.8.4"
3364
+ source = "registry+https://github.com/rust-lang/crates.io-index"
3365
+ checksum = "51f72981ade67b1ca6adc26ec221be9f463f2b5839c7508998daa17c23d94d7f"
3366
+ dependencies = [
3367
+ "pest",
3368
+ "pest_generator",
3369
+ ]
3370
+
3371
+ [[package]]
3372
+ name = "pest_generator"
3373
+ version = "2.8.4"
3374
+ source = "registry+https://github.com/rust-lang/crates.io-index"
3375
+ checksum = "dee9efd8cdb50d719a80088b76f81aec7c41ed6d522ee750178f83883d271625"
3376
+ dependencies = [
3377
+ "pest",
3378
+ "pest_meta",
3379
+ "proc-macro2",
3380
+ "quote",
3381
+ "syn",
3382
+ ]
3383
+
3384
+ [[package]]
3385
+ name = "pest_meta"
3386
+ version = "2.8.4"
3255
3387
  source = "registry+https://github.com/rust-lang/crates.io-index"
3256
- checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
3388
+ checksum = "bf1d70880e76bdc13ba52eafa6239ce793d85c8e43896507e43dd8984ff05b82"
3257
3389
  dependencies = [
3258
- "phf_macros",
3259
- "phf_shared 0.11.3",
3390
+ "pest",
3391
+ "sha2",
3260
3392
  ]
3261
3393
 
3262
3394
  [[package]]
@@ -3278,36 +3410,16 @@ dependencies = [
3278
3410
  "serde",
3279
3411
  ]
3280
3412
 
3281
- [[package]]
3282
- name = "phf_codegen"
3283
- version = "0.11.3"
3284
- source = "registry+https://github.com/rust-lang/crates.io-index"
3285
- checksum = "aef8048c789fa5e851558d709946d6d79a8ff88c0440c587967f8e94bfb1216a"
3286
- dependencies = [
3287
- "phf_generator 0.11.3",
3288
- "phf_shared 0.11.3",
3289
- ]
3290
-
3291
3413
  [[package]]
3292
3414
  name = "phf_codegen"
3293
3415
  version = "0.13.1"
3294
3416
  source = "registry+https://github.com/rust-lang/crates.io-index"
3295
3417
  checksum = "49aa7f9d80421bca176ca8dbfebe668cc7a2684708594ec9f3c0db0805d5d6e1"
3296
3418
  dependencies = [
3297
- "phf_generator 0.13.1",
3419
+ "phf_generator",
3298
3420
  "phf_shared 0.13.1",
3299
3421
  ]
3300
3422
 
3301
- [[package]]
3302
- name = "phf_generator"
3303
- version = "0.11.3"
3304
- source = "registry+https://github.com/rust-lang/crates.io-index"
3305
- checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
3306
- dependencies = [
3307
- "phf_shared 0.11.3",
3308
- "rand 0.8.5",
3309
- ]
3310
-
3311
3423
  [[package]]
3312
3424
  name = "phf_generator"
3313
3425
  version = "0.13.1"
@@ -3318,28 +3430,6 @@ dependencies = [
3318
3430
  "phf_shared 0.13.1",
3319
3431
  ]
3320
3432
 
3321
- [[package]]
3322
- name = "phf_macros"
3323
- version = "0.11.3"
3324
- source = "registry+https://github.com/rust-lang/crates.io-index"
3325
- checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
3326
- dependencies = [
3327
- "phf_generator 0.11.3",
3328
- "phf_shared 0.11.3",
3329
- "proc-macro2",
3330
- "quote",
3331
- "syn",
3332
- ]
3333
-
3334
- [[package]]
3335
- name = "phf_shared"
3336
- version = "0.11.3"
3337
- source = "registry+https://github.com/rust-lang/crates.io-index"
3338
- checksum = "67eabc2ef2a60eb7faa00097bd1ffdb5bd28e62bf39990626a582201b7a754e5"
3339
- dependencies = [
3340
- "siphasher",
3341
- ]
3342
-
3343
3433
  [[package]]
3344
3434
  name = "phf_shared"
3345
3435
  version = "0.12.1"
@@ -3483,7 +3573,7 @@ dependencies = [
3483
3573
  "polars-arrow",
3484
3574
  "polars-error",
3485
3575
  "polars-utils",
3486
- "rand 0.9.2",
3576
+ "rand",
3487
3577
  "ryu",
3488
3578
  "serde",
3489
3579
  "strength_reduce",
@@ -3514,7 +3604,7 @@ dependencies = [
3514
3604
  "polars-row",
3515
3605
  "polars-schema",
3516
3606
  "polars-utils",
3517
- "rand 0.9.2",
3607
+ "rand",
3518
3608
  "rand_distr",
3519
3609
  "rayon",
3520
3610
  "regex",
@@ -3573,7 +3663,7 @@ dependencies = [
3573
3663
  "polars-row",
3574
3664
  "polars-time",
3575
3665
  "polars-utils",
3576
- "rand 0.9.2",
3666
+ "rand",
3577
3667
  "rayon",
3578
3668
  "recursive",
3579
3669
  "regex",
@@ -3806,7 +3896,7 @@ dependencies = [
3806
3896
  "polars-plan",
3807
3897
  "polars-time",
3808
3898
  "polars-utils",
3809
- "rand 0.9.2",
3899
+ "rand",
3810
3900
  "regex",
3811
3901
  "serde",
3812
3902
  "sqlparser",
@@ -3844,7 +3934,7 @@ dependencies = [
3844
3934
  "polars-plan",
3845
3935
  "polars-time",
3846
3936
  "polars-utils",
3847
- "rand 0.9.2",
3937
+ "rand",
3848
3938
  "rayon",
3849
3939
  "recursive",
3850
3940
  "slotmap",
@@ -3894,7 +3984,7 @@ dependencies = [
3894
3984
  "memmap2",
3895
3985
  "num-traits",
3896
3986
  "polars-error",
3897
- "rand 0.9.2",
3987
+ "rand",
3898
3988
  "raw-cpuid",
3899
3989
  "rayon",
3900
3990
  "regex",
@@ -4016,10 +4106,18 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
4016
4106
  checksum = "1e8bbe1a966bd2f362681a44f6edce3c2310ac21e4d5067a6e7ec396297a6ea0"
4017
4107
  dependencies = [
4018
4108
  "bitflags",
4109
+ "getopts",
4019
4110
  "memchr",
4111
+ "pulldown-cmark-escape",
4020
4112
  "unicase",
4021
4113
  ]
4022
4114
 
4115
+ [[package]]
4116
+ name = "pulldown-cmark-escape"
4117
+ version = "0.11.0"
4118
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4119
+ checksum = "007d8adb5ddab6f8e3f491ac63566a7d5002cc7ed73901f72057943fa71ae1ae"
4120
+
4023
4121
  [[package]]
4024
4122
  name = "pxfm"
4025
4123
  version = "0.1.26"
@@ -4029,21 +4127,22 @@ dependencies = [
4029
4127
  "num-traits",
4030
4128
  ]
4031
4129
 
4032
- [[package]]
4033
- name = "qoi"
4034
- version = "0.4.1"
4035
- source = "registry+https://github.com/rust-lang/crates.io-index"
4036
- checksum = "7f6d64c71eb498fe9eae14ce4ec935c555749aef511cca85b5568910d6e48001"
4037
- dependencies = [
4038
- "bytemuck",
4039
- ]
4040
-
4041
4130
  [[package]]
4042
4131
  name = "quick-error"
4043
4132
  version = "2.0.1"
4044
4133
  source = "registry+https://github.com/rust-lang/crates.io-index"
4045
4134
  checksum = "a993555f31e5a609f617c12db6250dedcac1b0a85076912c436e6fc9b2c8e6a3"
4046
4135
 
4136
+ [[package]]
4137
+ name = "quick-xml"
4138
+ version = "0.30.0"
4139
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4140
+ checksum = "eff6510e86862b57b210fd8cbe8ed3f0d7d600b9c2863cd4549a2e033c66e956"
4141
+ dependencies = [
4142
+ "memchr",
4143
+ "serde",
4144
+ ]
4145
+
4047
4146
  [[package]]
4048
4147
  name = "quick-xml"
4049
4148
  version = "0.36.2"
@@ -4093,7 +4192,7 @@ dependencies = [
4093
4192
  "bytes",
4094
4193
  "getrandom 0.3.4",
4095
4194
  "lru-slab",
4096
- "rand 0.9.2",
4195
+ "rand",
4097
4196
  "ring",
4098
4197
  "rustc-hash 2.1.1",
4099
4198
  "rustls",
@@ -4145,15 +4244,6 @@ dependencies = [
4145
4244
  "serde",
4146
4245
  ]
4147
4246
 
4148
- [[package]]
4149
- name = "rand"
4150
- version = "0.8.5"
4151
- source = "registry+https://github.com/rust-lang/crates.io-index"
4152
- checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
4153
- dependencies = [
4154
- "rand_core 0.6.4",
4155
- ]
4156
-
4157
4247
  [[package]]
4158
4248
  name = "rand"
4159
4249
  version = "0.9.2"
@@ -4161,7 +4251,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
4161
4251
  checksum = "6db2770f06117d490610c7488547d543617b21bfa07796d7a12f6f1bd53850d1"
4162
4252
  dependencies = [
4163
4253
  "rand_chacha",
4164
- "rand_core 0.9.3",
4254
+ "rand_core",
4165
4255
  ]
4166
4256
 
4167
4257
  [[package]]
@@ -4171,15 +4261,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
4171
4261
  checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb"
4172
4262
  dependencies = [
4173
4263
  "ppv-lite86",
4174
- "rand_core 0.9.3",
4264
+ "rand_core",
4175
4265
  ]
4176
4266
 
4177
- [[package]]
4178
- name = "rand_core"
4179
- version = "0.6.4"
4180
- source = "registry+https://github.com/rust-lang/crates.io-index"
4181
- checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
4182
-
4183
4267
  [[package]]
4184
4268
  name = "rand_core"
4185
4269
  version = "0.9.3"
@@ -4196,7 +4280,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
4196
4280
  checksum = "6a8615d50dcf34fa31f7ab52692afec947c4dd0ab803cc87cb3b0b4570ff7463"
4197
4281
  dependencies = [
4198
4282
  "num-traits",
4199
- "rand 0.9.2",
4283
+ "rand",
4200
4284
  ]
4201
4285
 
4202
4286
  [[package]]
@@ -4232,7 +4316,7 @@ dependencies = [
4232
4316
  "num-traits",
4233
4317
  "paste",
4234
4318
  "profiling",
4235
- "rand 0.9.2",
4319
+ "rand",
4236
4320
  "rand_chacha",
4237
4321
  "simd_helpers",
4238
4322
  "thiserror 2.0.17",
@@ -4303,18 +4387,16 @@ dependencies = [
4303
4387
 
4304
4388
  [[package]]
4305
4389
  name = "rb-sys"
4306
- version = "0.9.117"
4307
- source = "registry+https://github.com/rust-lang/crates.io-index"
4308
- checksum = "f900d1ce4629a2ebffaf5de74bd8f9c1188d4c5ed406df02f97e22f77a006f44"
4390
+ version = "0.9.119"
4309
4391
  dependencies = [
4310
4392
  "rb-sys-build",
4311
4393
  ]
4312
4394
 
4313
4395
  [[package]]
4314
4396
  name = "rb-sys-build"
4315
- version = "0.9.117"
4397
+ version = "0.9.119"
4316
4398
  source = "registry+https://github.com/rust-lang/crates.io-index"
4317
- checksum = "ef1e9c857028f631056bcd6d88cec390c751e343ce2223ddb26d23eb4a151d59"
4399
+ checksum = "2e0109499e06c85f56df4abad7d9c642ea8a2dd821d1d7132b4d1b69534677f3"
4318
4400
  dependencies = [
4319
4401
  "bindgen",
4320
4402
  "lazy_static",
@@ -4402,9 +4484,9 @@ checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
4402
4484
 
4403
4485
  [[package]]
4404
4486
  name = "reqwest"
4405
- version = "0.12.24"
4487
+ version = "0.12.25"
4406
4488
  source = "registry+https://github.com/rust-lang/crates.io-index"
4407
- checksum = "9d0946410b9f7b082a427e4ef5c8ff541a88b357bc6c637c40db3a68ac70a36f"
4489
+ checksum = "b6eff9328d40131d43bd911d42d79eb6a47312002a4daefc9e37f17e74a7701a"
4408
4490
  dependencies = [
4409
4491
  "base64 0.22.1",
4410
4492
  "bytes",
@@ -4486,6 +4568,12 @@ dependencies = [
4486
4568
  "serde",
4487
4569
  ]
4488
4570
 
4571
+ [[package]]
4572
+ name = "roman-numerals-rs"
4573
+ version = "3.1.0"
4574
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4575
+ checksum = "c85cd47a33a4510b1424fe796498e174c6a9cf94e606460ef022a19f3e4ff85e"
4576
+
4489
4577
  [[package]]
4490
4578
  name = "roxmltree"
4491
4579
  version = "0.21.1"
@@ -4495,6 +4583,29 @@ dependencies = [
4495
4583
  "memchr",
4496
4584
  ]
4497
4585
 
4586
+ [[package]]
4587
+ name = "rst_parser"
4588
+ version = "0.4.2"
4589
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4590
+ checksum = "6f3029872a42c0be67d86e3e88bf8c1e73d1da3d714da00b9c29f60a4605bfb1"
4591
+ dependencies = [
4592
+ "anyhow",
4593
+ "document_tree",
4594
+ "pest",
4595
+ "pest_derive",
4596
+ ]
4597
+
4598
+ [[package]]
4599
+ name = "rtf-parser"
4600
+ version = "0.4.2"
4601
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4602
+ checksum = "b37b8463a5beedce6c01d05e7f76da154c078fd713555fdeed11a62f297b1708"
4603
+ dependencies = [
4604
+ "serde",
4605
+ "tsify",
4606
+ "wasm-bindgen",
4607
+ ]
4608
+
4498
4609
  [[package]]
4499
4610
  name = "rustc-hash"
4500
4611
  version = "1.1.0"
@@ -4507,15 +4618,6 @@ version = "2.1.1"
4507
4618
  source = "registry+https://github.com/rust-lang/crates.io-index"
4508
4619
  checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d"
4509
4620
 
4510
- [[package]]
4511
- name = "rustc_version"
4512
- version = "0.4.1"
4513
- source = "registry+https://github.com/rust-lang/crates.io-index"
4514
- checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92"
4515
- dependencies = [
4516
- "semver",
4517
- ]
4518
-
4519
4621
  [[package]]
4520
4622
  name = "rustix"
4521
4623
  version = "1.1.2"
@@ -4613,21 +4715,6 @@ version = "1.2.0"
4613
4715
  source = "registry+https://github.com/rust-lang/crates.io-index"
4614
4716
  checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
4615
4717
 
4616
- [[package]]
4617
- name = "scraper"
4618
- version = "0.24.0"
4619
- source = "registry+https://github.com/rust-lang/crates.io-index"
4620
- checksum = "e5f3a24d916e78954af99281a455168d4a9515d65eca99a18da1b813689c4ad9"
4621
- dependencies = [
4622
- "cssparser",
4623
- "ego-tree",
4624
- "getopts",
4625
- "html5ever 0.35.0",
4626
- "precomputed-hash",
4627
- "selectors",
4628
- "tendril",
4629
- ]
4630
-
4631
4718
  [[package]]
4632
4719
  name = "security-framework"
4633
4720
  version = "2.11.1"
@@ -4676,31 +4763,6 @@ dependencies = [
4676
4763
  "itertools 0.14.0",
4677
4764
  ]
4678
4765
 
4679
- [[package]]
4680
- name = "selectors"
4681
- version = "0.31.0"
4682
- source = "registry+https://github.com/rust-lang/crates.io-index"
4683
- checksum = "5685b6ae43bfcf7d2e7dfcfb5d8e8f61b46442c902531e41a32a9a8bf0ee0fb6"
4684
- dependencies = [
4685
- "bitflags",
4686
- "cssparser",
4687
- "derive_more",
4688
- "fxhash",
4689
- "log",
4690
- "new_debug_unreachable",
4691
- "phf 0.11.3",
4692
- "phf_codegen 0.11.3",
4693
- "precomputed-hash",
4694
- "servo_arc",
4695
- "smallvec 1.15.1",
4696
- ]
4697
-
4698
- [[package]]
4699
- name = "semver"
4700
- version = "1.0.27"
4701
- source = "registry+https://github.com/rust-lang/crates.io-index"
4702
- checksum = "d767eb0aabc880b29956c35734170f26ed551a859dbd361d140cdbeca61ab1e2"
4703
-
4704
4766
  [[package]]
4705
4767
  name = "seq-macro"
4706
4768
  version = "0.3.6"
@@ -4737,6 +4799,17 @@ dependencies = [
4737
4799
  "syn",
4738
4800
  ]
4739
4801
 
4802
+ [[package]]
4803
+ name = "serde_derive_internals"
4804
+ version = "0.28.0"
4805
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4806
+ checksum = "e578a843d40b4189a4d66bba51d7684f57da5bd7c304c64e14bd63efbef49509"
4807
+ dependencies = [
4808
+ "proc-macro2",
4809
+ "quote",
4810
+ "syn",
4811
+ ]
4812
+
4740
4813
  [[package]]
4741
4814
  name = "serde_json"
4742
4815
  version = "1.0.145"
@@ -4750,6 +4823,15 @@ dependencies = [
4750
4823
  "serde_core",
4751
4824
  ]
4752
4825
 
4826
+ [[package]]
4827
+ name = "serde_spanned"
4828
+ version = "0.6.9"
4829
+ source = "registry+https://github.com/rust-lang/crates.io-index"
4830
+ checksum = "bf41e0cfaf7226dca15e8197172c295a782857fcb97fad1808a166870dee75a3"
4831
+ dependencies = [
4832
+ "serde",
4833
+ ]
4834
+
4753
4835
  [[package]]
4754
4836
  name = "serde_spanned"
4755
4837
  version = "1.0.3"
@@ -4795,15 +4877,6 @@ dependencies = [
4795
4877
  "unsafe-libyaml",
4796
4878
  ]
4797
4879
 
4798
- [[package]]
4799
- name = "servo_arc"
4800
- version = "0.4.3"
4801
- source = "registry+https://github.com/rust-lang/crates.io-index"
4802
- checksum = "170fb83ab34de17dc69aa7c67482b22218ddb85da56546f9bd6b929e32a05930"
4803
- dependencies = [
4804
- "stable_deref_trait",
4805
- ]
4806
-
4807
4880
  [[package]]
4808
4881
  name = "sevenz-rust"
4809
4882
  version = "0.6.1"
@@ -5025,19 +5098,6 @@ version = "0.2.4"
5025
5098
  source = "registry+https://github.com/rust-lang/crates.io-index"
5026
5099
  checksum = "fe895eb47f22e2ddd4dabc02bce419d2e643c8e3b585c78158b349195bc24d82"
5027
5100
 
5028
- [[package]]
5029
- name = "string_cache"
5030
- version = "0.8.9"
5031
- source = "registry+https://github.com/rust-lang/crates.io-index"
5032
- checksum = "bf776ba3fa74f83bf4b63c3dcbbf82173db2632ed8452cb2d891d33f459de70f"
5033
- dependencies = [
5034
- "new_debug_unreachable",
5035
- "parking_lot",
5036
- "phf_shared 0.11.3",
5037
- "precomputed-hash",
5038
- "serde",
5039
- ]
5040
-
5041
5101
  [[package]]
5042
5102
  name = "string_cache"
5043
5103
  version = "0.9.0"
@@ -5051,25 +5111,13 @@ dependencies = [
5051
5111
  "serde",
5052
5112
  ]
5053
5113
 
5054
- [[package]]
5055
- name = "string_cache_codegen"
5056
- version = "0.5.4"
5057
- source = "registry+https://github.com/rust-lang/crates.io-index"
5058
- checksum = "c711928715f1fe0fe509c53b43e993a9a557babc2d0a3567d0a3006f1ac931a0"
5059
- dependencies = [
5060
- "phf_generator 0.11.3",
5061
- "phf_shared 0.11.3",
5062
- "proc-macro2",
5063
- "quote",
5064
- ]
5065
-
5066
5114
  [[package]]
5067
5115
  name = "string_cache_codegen"
5068
5116
  version = "0.6.1"
5069
5117
  source = "registry+https://github.com/rust-lang/crates.io-index"
5070
5118
  checksum = "585635e46db231059f76c5849798146164652513eb9e8ab2685939dd90f29b69"
5071
5119
  dependencies = [
5072
- "phf_generator 0.13.1",
5120
+ "phf_generator",
5073
5121
  "phf_shared 0.13.1",
5074
5122
  "proc-macro2",
5075
5123
  "quote",
@@ -5203,6 +5251,12 @@ dependencies = [
5203
5251
  "thiserror 2.0.17",
5204
5252
  ]
5205
5253
 
5254
+ [[package]]
5255
+ name = "thin-vec"
5256
+ version = "0.2.14"
5257
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5258
+ checksum = "144f754d318415ac792f9d69fc87abbbfc043ce2ef041c60f16ad828f638717d"
5259
+
5206
5260
  [[package]]
5207
5261
  name = "thiserror"
5208
5262
  version = "1.0.69"
@@ -5333,7 +5387,7 @@ dependencies = [
5333
5387
  "monostate",
5334
5388
  "onig",
5335
5389
  "paste",
5336
- "rand 0.9.2",
5390
+ "rand",
5337
5391
  "rayon",
5338
5392
  "rayon-cond",
5339
5393
  "regex",
@@ -5397,6 +5451,18 @@ dependencies = [
5397
5451
  "tokio",
5398
5452
  ]
5399
5453
 
5454
+ [[package]]
5455
+ name = "toml"
5456
+ version = "0.8.23"
5457
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5458
+ checksum = "dc1beb996b9d83529a9e75c17a1686767d148d70663143c7854d8b4a09ced362"
5459
+ dependencies = [
5460
+ "serde",
5461
+ "serde_spanned 0.6.9",
5462
+ "toml_datetime 0.6.11",
5463
+ "toml_edit",
5464
+ ]
5465
+
5400
5466
  [[package]]
5401
5467
  name = "toml"
5402
5468
  version = "0.9.8"
@@ -5405,13 +5471,22 @@ checksum = "f0dc8b1fb61449e27716ec0e1bdf0f6b8f3e8f6b05391e8497b8b6d7804ea6d8"
5405
5471
  dependencies = [
5406
5472
  "indexmap",
5407
5473
  "serde_core",
5408
- "serde_spanned",
5409
- "toml_datetime",
5474
+ "serde_spanned 1.0.3",
5475
+ "toml_datetime 0.7.3",
5410
5476
  "toml_parser",
5411
5477
  "toml_writer",
5412
5478
  "winnow",
5413
5479
  ]
5414
5480
 
5481
+ [[package]]
5482
+ name = "toml_datetime"
5483
+ version = "0.6.11"
5484
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5485
+ checksum = "22cddaf88f4fbc13c51aebbf5f8eceb5c7c5a9da2ac40a13519eb5b0a0e8f11c"
5486
+ dependencies = [
5487
+ "serde",
5488
+ ]
5489
+
5415
5490
  [[package]]
5416
5491
  name = "toml_datetime"
5417
5492
  version = "0.7.3"
@@ -5421,6 +5496,20 @@ dependencies = [
5421
5496
  "serde_core",
5422
5497
  ]
5423
5498
 
5499
+ [[package]]
5500
+ name = "toml_edit"
5501
+ version = "0.22.27"
5502
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5503
+ checksum = "41fe8c660ae4257887cf66394862d21dbca4a6ddd26f04a3560410406a2f819a"
5504
+ dependencies = [
5505
+ "indexmap",
5506
+ "serde",
5507
+ "serde_spanned 0.6.9",
5508
+ "toml_datetime 0.6.11",
5509
+ "toml_write",
5510
+ "winnow",
5511
+ ]
5512
+
5424
5513
  [[package]]
5425
5514
  name = "toml_parser"
5426
5515
  version = "1.0.4"
@@ -5430,6 +5519,12 @@ dependencies = [
5430
5519
  "winnow",
5431
5520
  ]
5432
5521
 
5522
+ [[package]]
5523
+ name = "toml_write"
5524
+ version = "0.1.2"
5525
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5526
+ checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
5527
+
5433
5528
  [[package]]
5434
5529
  name = "toml_writer"
5435
5530
  version = "1.0.4"
@@ -5453,9 +5548,9 @@ dependencies = [
5453
5548
 
5454
5549
  [[package]]
5455
5550
  name = "tower-http"
5456
- version = "0.6.7"
5551
+ version = "0.6.8"
5457
5552
  source = "registry+https://github.com/rust-lang/crates.io-index"
5458
- checksum = "9cf146f99d442e8e68e585f5d798ccd3cad9a7835b917e09728880a862706456"
5553
+ checksum = "d4e6559d53cc268e5031cd8429d05415bc4cb4aefc4aa5d6cc35fbf5b924a1f8"
5459
5554
  dependencies = [
5460
5555
  "bitflags",
5461
5556
  "bytes",
@@ -5518,6 +5613,31 @@ version = "0.2.5"
5518
5613
  source = "registry+https://github.com/rust-lang/crates.io-index"
5519
5614
  checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
5520
5615
 
5616
+ [[package]]
5617
+ name = "tsify"
5618
+ version = "0.4.5"
5619
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5620
+ checksum = "d6b26cf145f2f3b9ff84e182c448eaf05468e247f148cf3d2a7d67d78ff023a0"
5621
+ dependencies = [
5622
+ "gloo-utils",
5623
+ "serde",
5624
+ "serde_json",
5625
+ "tsify-macros",
5626
+ "wasm-bindgen",
5627
+ ]
5628
+
5629
+ [[package]]
5630
+ name = "tsify-macros"
5631
+ version = "0.4.5"
5632
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5633
+ checksum = "7a94b0f0954b3e59bfc2c246b4c8574390d94a4ad4ad246aaf2fb07d7dfd3b47"
5634
+ dependencies = [
5635
+ "proc-macro2",
5636
+ "quote",
5637
+ "serde_derive_internals",
5638
+ "syn",
5639
+ ]
5640
+
5521
5641
  [[package]]
5522
5642
  name = "ttf-parser"
5523
5643
  version = "0.25.1"
@@ -5530,6 +5650,57 @@ version = "1.19.0"
5530
5650
  source = "registry+https://github.com/rust-lang/crates.io-index"
5531
5651
  checksum = "562d481066bde0658276a35467c4af00bdc6ee726305698a55b86e61d7ad82bb"
5532
5652
 
5653
+ [[package]]
5654
+ name = "typst-syntax"
5655
+ version = "0.14.1"
5656
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5657
+ checksum = "19e223636668a2930e0a46b18e3786d4ae02f69ac5d9dda58e34ca431403d05c"
5658
+ dependencies = [
5659
+ "ecow",
5660
+ "rustc-hash 2.1.1",
5661
+ "serde",
5662
+ "toml 0.8.23",
5663
+ "typst-timing",
5664
+ "typst-utils",
5665
+ "unicode-ident",
5666
+ "unicode-math-class",
5667
+ "unicode-script",
5668
+ "unicode-segmentation",
5669
+ "unscanny",
5670
+ ]
5671
+
5672
+ [[package]]
5673
+ name = "typst-timing"
5674
+ version = "0.14.1"
5675
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5676
+ checksum = "3347a043b8659b104f198abe825a6c419d0675da276489c310a5620aea799816"
5677
+ dependencies = [
5678
+ "parking_lot",
5679
+ "serde",
5680
+ "serde_json",
5681
+ ]
5682
+
5683
+ [[package]]
5684
+ name = "typst-utils"
5685
+ version = "0.14.1"
5686
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5687
+ checksum = "737d445f5c0cb75b382a6841953a9e22daadad2c264402b41ebf5388356369fd"
5688
+ dependencies = [
5689
+ "once_cell",
5690
+ "portable-atomic",
5691
+ "rayon",
5692
+ "rustc-hash 2.1.1",
5693
+ "siphasher",
5694
+ "thin-vec",
5695
+ "unicode-math-class",
5696
+ ]
5697
+
5698
+ [[package]]
5699
+ name = "ucd-trie"
5700
+ version = "0.1.7"
5701
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5702
+ checksum = "2896d95c02a80c6d6a5d6e953d479f5ddf2dfdb6a244441010e373ac0fb88971"
5703
+
5533
5704
  [[package]]
5534
5705
  name = "unicase"
5535
5706
  version = "2.8.1"
@@ -5548,6 +5719,12 @@ version = "1.0.22"
5548
5719
  source = "registry+https://github.com/rust-lang/crates.io-index"
5549
5720
  checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
5550
5721
 
5722
+ [[package]]
5723
+ name = "unicode-math-class"
5724
+ version = "0.1.0"
5725
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5726
+ checksum = "7d246cf599d5fae3c8d56e04b20eb519adb89a8af8d0b0fbcded369aa3647d65"
5727
+
5551
5728
  [[package]]
5552
5729
  name = "unicode-normalization"
5553
5730
  version = "0.1.25"
@@ -5581,6 +5758,12 @@ dependencies = [
5581
5758
  "unicode-segmentation",
5582
5759
  ]
5583
5760
 
5761
+ [[package]]
5762
+ name = "unicode-script"
5763
+ version = "0.5.8"
5764
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5765
+ checksum = "383ad40bb927465ec0ce7720e033cb4ca06912855fc35db31b5755d0de75b1ee"
5766
+
5584
5767
  [[package]]
5585
5768
  name = "unicode-segmentation"
5586
5769
  version = "1.12.0"
@@ -5605,6 +5788,12 @@ version = "0.2.11"
5605
5788
  source = "registry+https://github.com/rust-lang/crates.io-index"
5606
5789
  checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861"
5607
5790
 
5791
+ [[package]]
5792
+ name = "unscanny"
5793
+ version = "0.1.0"
5794
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5795
+ checksum = "e9df2af067a7953e9c3831320f35c1cc0600c30d44d9f7a12b01db1cd88d6b47"
5796
+
5608
5797
  [[package]]
5609
5798
  name = "untrusted"
5610
5799
  version = "0.9.0"
@@ -5705,6 +5894,12 @@ version = "1.0.4"
5705
5894
  source = "registry+https://github.com/rust-lang/crates.io-index"
5706
5895
  checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
5707
5896
 
5897
+ [[package]]
5898
+ name = "utf8parse"
5899
+ version = "0.2.2"
5900
+ source = "registry+https://github.com/rust-lang/crates.io-index"
5901
+ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
5902
+
5708
5903
  [[package]]
5709
5904
  name = "uuid"
5710
5905
  version = "1.19.0"
@@ -5886,18 +6081,6 @@ dependencies = [
5886
6081
  "wasm-bindgen",
5887
6082
  ]
5888
6083
 
5889
- [[package]]
5890
- name = "web_atoms"
5891
- version = "0.1.3"
5892
- source = "registry+https://github.com/rust-lang/crates.io-index"
5893
- checksum = "57ffde1dc01240bdf9992e3205668b235e59421fd085e8a317ed98da0178d414"
5894
- dependencies = [
5895
- "phf 0.11.3",
5896
- "phf_codegen 0.11.3",
5897
- "string_cache 0.8.9",
5898
- "string_cache_codegen 0.5.4",
5899
- ]
5900
-
5901
6084
  [[package]]
5902
6085
  name = "web_atoms"
5903
6086
  version = "0.2.0"
@@ -5905,9 +6088,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
5905
6088
  checksum = "acd0c322f146d0f8aad130ce6c187953889359584497dac6561204c8e17bb43d"
5906
6089
  dependencies = [
5907
6090
  "phf 0.13.1",
5908
- "phf_codegen 0.13.1",
5909
- "string_cache 0.9.0",
5910
- "string_cache_codegen 0.6.1",
6091
+ "phf_codegen",
6092
+ "string_cache",
6093
+ "string_cache_codegen",
5911
6094
  ]
5912
6095
 
5913
6096
  [[package]]
@@ -6212,6 +6395,9 @@ name = "winnow"
6212
6395
  version = "0.7.14"
6213
6396
  source = "registry+https://github.com/rust-lang/crates.io-index"
6214
6397
  checksum = "5a5364e9d77fcdeeaa6062ced926ee3381faa2ee02d3eb83a5c27a8825540829"
6398
+ dependencies = [
6399
+ "memchr",
6400
+ ]
6215
6401
 
6216
6402
  [[package]]
6217
6403
  name = "wit-bindgen"
@@ -6242,7 +6428,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
6242
6428
  checksum = "f57dd51b88a4b9f99f9b55b136abb86210629d61c48117ddb87f567e51e66be7"
6243
6429
  dependencies = [
6244
6430
  "log",
6245
- "markup5ever 0.36.1",
6431
+ "markup5ever",
6246
6432
  ]
6247
6433
 
6248
6434
  [[package]]