kreuzberg 4.0.0.pre.rc.18 → 4.0.0.pre.rc.20
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile.lock +3 -3
- data/ext/kreuzberg_rb/native/Cargo.lock +274 -13
- data/ext/kreuzberg_rb/native/Cargo.toml +2 -5
- data/ext/kreuzberg_rb/native/build.rs +3 -66
- data/ext/kreuzberg_rb/native/src/lib.rs +2 -0
- data/lib/kreuzberg/config.rb +41 -6
- data/lib/kreuzberg/version.rb +1 -1
- data/sig/kreuzberg.rbs +10 -3
- data/spec/binding/config_spec.rb +74 -0
- data/spec/binding/font_config_spec.rb +220 -0
- data/vendor/Cargo.toml +2 -1
- data/vendor/kreuzberg/Cargo.toml +13 -9
- data/vendor/kreuzberg/examples/bench_fixes.rs +74 -0
- data/vendor/kreuzberg/examples/test_pdfium_fork.rs +65 -0
- data/vendor/kreuzberg/src/api/handlers.rs +3 -2
- data/vendor/kreuzberg/src/api/server.rs +211 -36
- data/vendor/kreuzberg/src/api/types.rs +20 -7
- data/vendor/kreuzberg/src/core/batch_optimizations.rs +106 -26
- data/vendor/kreuzberg/src/core/config.rs +253 -22
- data/vendor/kreuzberg/src/core/extractor.rs +41 -3
- data/vendor/kreuzberg/src/core/pipeline.rs +15 -59
- data/vendor/kreuzberg/src/extraction/capacity.rs +270 -0
- data/vendor/kreuzberg/src/extraction/docx.rs +26 -17
- data/vendor/kreuzberg/src/extraction/excel.rs +132 -128
- data/vendor/kreuzberg/src/extraction/html.rs +13 -14
- data/vendor/kreuzberg/src/extraction/markdown.rs +4 -3
- data/vendor/kreuzberg/src/extraction/mod.rs +12 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +4 -1
- data/vendor/kreuzberg/src/extractors/docbook.rs +1 -1
- data/vendor/kreuzberg/src/extractors/email.rs +1 -1
- data/vendor/kreuzberg/src/extractors/excel.rs +62 -21
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +1 -1
- data/vendor/kreuzberg/src/extractors/html.rs +30 -18
- data/vendor/kreuzberg/src/extractors/jats.rs +1 -1
- data/vendor/kreuzberg/src/extractors/markdown.rs +3 -3
- data/vendor/kreuzberg/src/extractors/orgmode.rs +2 -2
- data/vendor/kreuzberg/src/extractors/pdf.rs +55 -50
- data/vendor/kreuzberg/src/extractors/typst.rs +2 -2
- data/vendor/kreuzberg/src/pdf/bindings.rs +6 -73
- data/vendor/kreuzberg/src/pdf/error.rs +8 -0
- data/vendor/kreuzberg/src/pdf/fonts.rs +384 -0
- data/vendor/kreuzberg/src/pdf/metadata.rs +40 -30
- data/vendor/kreuzberg/src/pdf/mod.rs +4 -0
- data/vendor/kreuzberg/src/pdf/rendering.rs +3 -3
- data/vendor/kreuzberg/src/pdf/table.rs +20 -20
- data/vendor/kreuzberg/src/pdf/text.rs +52 -2
- data/vendor/kreuzberg/src/text/quality.rs +30 -15
- data/vendor/kreuzberg/src/text/quality_processor.rs +3 -11
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +75 -60
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +20 -8
- data/vendor/kreuzberg/src/types.rs +5 -4
- data/vendor/kreuzberg/src/utils/mod.rs +3 -0
- data/vendor/kreuzberg/src/utils/pool.rs +172 -15
- data/vendor/kreuzberg/src/utils/pool_sizing.rs +393 -0
- data/vendor/kreuzberg/src/utils/string_pool.rs +373 -10
- data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +504 -0
- data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +302 -0
- data/vendor/kreuzberg/tests/api_tests.rs +514 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +4 -0
- data/vendor/kreuzberg/tests/email_integration.rs +1 -1
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +1 -1
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +2 -2
- data/vendor/kreuzberg/tests/ocr_language_registry.rs +1 -0
- data/vendor/kreuzberg/tests/pdfium_linking.rs +4 -4
- data/vendor/kreuzberg/tests/pipeline_integration.rs +8 -0
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1 -1
- data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +1 -1
- data/vendor/kreuzberg-ffi/src/batch_streaming.rs +1 -3
- data/vendor/kreuzberg-ffi/src/lib.rs +6 -4
- data/vendor/kreuzberg-ffi/src/result_pool.rs +1 -1
- data/vendor/kreuzberg-ffi/src/result_view.rs +9 -9
- data/vendor/kreuzberg-tesseract/Cargo.toml +1 -1
- data/vendor/kreuzberg-tesseract/build.rs +0 -227
- metadata +10 -33
- data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
- data/vendor/rb-sys/Cargo.lock +0 -393
- data/vendor/rb-sys/Cargo.toml +0 -70
- data/vendor/rb-sys/Cargo.toml.orig +0 -57
- data/vendor/rb-sys/LICENSE-APACHE +0 -190
- data/vendor/rb-sys/LICENSE-MIT +0 -21
- data/vendor/rb-sys/build/features.rs +0 -111
- data/vendor/rb-sys/build/main.rs +0 -286
- data/vendor/rb-sys/build/stable_api_config.rs +0 -155
- data/vendor/rb-sys/build/version.rs +0 -50
- data/vendor/rb-sys/readme.md +0 -36
- data/vendor/rb-sys/src/bindings.rs +0 -21
- data/vendor/rb-sys/src/hidden.rs +0 -11
- data/vendor/rb-sys/src/lib.rs +0 -35
- data/vendor/rb-sys/src/macros.rs +0 -371
- data/vendor/rb-sys/src/memory.rs +0 -53
- data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
- data/vendor/rb-sys/src/special_consts.rs +0 -31
- data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
- data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -332
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -325
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -323
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -339
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -339
- data/vendor/rb-sys/src/stable_api.rs +0 -260
- data/vendor/rb-sys/src/symbol.rs +0 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +0 -330
- data/vendor/rb-sys/src/utils.rs +0 -89
- data/vendor/rb-sys/src/value_type.rs +0 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 8f4c578323928e218a33fd0941a5b98e598da2a67567ecf59e1f76ac02299ac1
|
|
4
|
+
data.tar.gz: dde6bdee61e7baf36f2028ca3d06a746fa254263ee597fa2e47e28879d4afa06
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: d1e0a132d36eb9f6ce3abe27ac258a37f08b3028dafe6cebff55145a2218ea324682c3273134fd4626f1f5bd9f326cdf6e18270d9db759a1caafd2447052c1b4
|
|
7
|
+
data.tar.gz: a62f75e8d66d289532a5943c472c30642f3215e3d46555618632c4bfaf8826ea077b2ecb585e46b180706df12808b5206ff8ce697ff4962e76ea674c7eeaf952
|
data/Gemfile.lock
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
PATH
|
|
2
2
|
remote: .
|
|
3
3
|
specs:
|
|
4
|
-
kreuzberg (4.0.0.pre.rc.
|
|
4
|
+
kreuzberg (4.0.0.pre.rc.20)
|
|
5
5
|
|
|
6
6
|
GEM
|
|
7
7
|
remote: https://rubygems.org/
|
|
@@ -68,7 +68,7 @@ GEM
|
|
|
68
68
|
ffi (~> 1.0)
|
|
69
69
|
rb_sys (0.9.123)
|
|
70
70
|
rake-compiler-dock (= 1.10.0)
|
|
71
|
-
rbs (3.
|
|
71
|
+
rbs (3.10.0)
|
|
72
72
|
logger
|
|
73
73
|
regexp_parser (2.11.3)
|
|
74
74
|
rspec (3.13.2)
|
|
@@ -84,7 +84,7 @@ GEM
|
|
|
84
84
|
diff-lcs (>= 1.2.0, < 2.0)
|
|
85
85
|
rspec-support (~> 3.13.0)
|
|
86
86
|
rspec-support (3.13.6)
|
|
87
|
-
rubocop (1.82.
|
|
87
|
+
rubocop (1.82.1)
|
|
88
88
|
json (~> 2.3)
|
|
89
89
|
language_server-protocol (~> 3.17.0.2)
|
|
90
90
|
lint_roller (~> 1.1.0)
|
|
@@ -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"
|
|
@@ -608,6 +658,25 @@ dependencies = [
|
|
|
608
658
|
"cipher",
|
|
609
659
|
]
|
|
610
660
|
|
|
661
|
+
[[package]]
|
|
662
|
+
name = "cbindgen"
|
|
663
|
+
version = "0.29.2"
|
|
664
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
665
|
+
checksum = "befbfd072a8e81c02f8c507aefce431fe5e7d051f83d48a23ffc9b9fe5a11799"
|
|
666
|
+
dependencies = [
|
|
667
|
+
"clap",
|
|
668
|
+
"heck",
|
|
669
|
+
"indexmap",
|
|
670
|
+
"log",
|
|
671
|
+
"proc-macro2",
|
|
672
|
+
"quote",
|
|
673
|
+
"serde",
|
|
674
|
+
"serde_json",
|
|
675
|
+
"syn",
|
|
676
|
+
"tempfile",
|
|
677
|
+
"toml 0.9.10+spec-1.1.0",
|
|
678
|
+
]
|
|
679
|
+
|
|
611
680
|
[[package]]
|
|
612
681
|
name = "cc"
|
|
613
682
|
version = "1.2.50"
|
|
@@ -708,6 +777,33 @@ dependencies = [
|
|
|
708
777
|
"libloading 0.8.9",
|
|
709
778
|
]
|
|
710
779
|
|
|
780
|
+
[[package]]
|
|
781
|
+
name = "clap"
|
|
782
|
+
version = "4.5.53"
|
|
783
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
784
|
+
checksum = "c9e340e012a1bf4935f5282ed1436d1489548e8f72308207ea5df0e23d2d03f8"
|
|
785
|
+
dependencies = [
|
|
786
|
+
"clap_builder",
|
|
787
|
+
]
|
|
788
|
+
|
|
789
|
+
[[package]]
|
|
790
|
+
name = "clap_builder"
|
|
791
|
+
version = "4.5.53"
|
|
792
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
793
|
+
checksum = "d76b5d13eaa18c901fd2f7fca939fefe3a0727a953561fefdf3b2922b8569d00"
|
|
794
|
+
dependencies = [
|
|
795
|
+
"anstream",
|
|
796
|
+
"anstyle",
|
|
797
|
+
"clap_lex",
|
|
798
|
+
"strsim",
|
|
799
|
+
]
|
|
800
|
+
|
|
801
|
+
[[package]]
|
|
802
|
+
name = "clap_lex"
|
|
803
|
+
version = "0.7.6"
|
|
804
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
805
|
+
checksum = "a1d728cc89cf3aee9ff92b05e62b19ee65a02b5702cff7d5a377e32c6ae29d8d"
|
|
806
|
+
|
|
711
807
|
[[package]]
|
|
712
808
|
name = "cmake"
|
|
713
809
|
version = "0.1.57"
|
|
@@ -732,6 +828,12 @@ version = "1.1.0"
|
|
|
732
828
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
733
829
|
checksum = "3d7b894f5411737b7867f4827955924d7c254fc9f4d91a6aad6b097804b1018b"
|
|
734
830
|
|
|
831
|
+
[[package]]
|
|
832
|
+
name = "colorchoice"
|
|
833
|
+
version = "1.0.4"
|
|
834
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
835
|
+
checksum = "b05b61dc5112cbb17e4b6cd61790d9845d13888356391624cbe7e41efeac1e75"
|
|
836
|
+
|
|
735
837
|
[[package]]
|
|
736
838
|
name = "compact_str"
|
|
737
839
|
version = "0.9.0"
|
|
@@ -1104,13 +1206,34 @@ dependencies = [
|
|
|
1104
1206
|
"subtle",
|
|
1105
1207
|
]
|
|
1106
1208
|
|
|
1209
|
+
[[package]]
|
|
1210
|
+
name = "dirs"
|
|
1211
|
+
version = "5.0.1"
|
|
1212
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1213
|
+
checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
|
|
1214
|
+
dependencies = [
|
|
1215
|
+
"dirs-sys 0.4.1",
|
|
1216
|
+
]
|
|
1217
|
+
|
|
1107
1218
|
[[package]]
|
|
1108
1219
|
name = "dirs"
|
|
1109
1220
|
version = "6.0.0"
|
|
1110
1221
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1111
1222
|
checksum = "c3e8aa94d75141228480295a7d0e7feb620b1a5ad9f12bc40be62411e38cce4e"
|
|
1112
1223
|
dependencies = [
|
|
1113
|
-
"dirs-sys",
|
|
1224
|
+
"dirs-sys 0.5.0",
|
|
1225
|
+
]
|
|
1226
|
+
|
|
1227
|
+
[[package]]
|
|
1228
|
+
name = "dirs-sys"
|
|
1229
|
+
version = "0.4.1"
|
|
1230
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1231
|
+
checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
|
|
1232
|
+
dependencies = [
|
|
1233
|
+
"libc",
|
|
1234
|
+
"option-ext",
|
|
1235
|
+
"redox_users 0.4.6",
|
|
1236
|
+
"windows-sys 0.48.0",
|
|
1114
1237
|
]
|
|
1115
1238
|
|
|
1116
1239
|
[[package]]
|
|
@@ -1121,7 +1244,7 @@ checksum = "e01a3366d27ee9890022452ee61b2b63a67e6f13f58900b651ff5665f0bb1fab"
|
|
|
1121
1244
|
dependencies = [
|
|
1122
1245
|
"libc",
|
|
1123
1246
|
"option-ext",
|
|
1124
|
-
"redox_users",
|
|
1247
|
+
"redox_users 0.5.2",
|
|
1125
1248
|
"windows-sys 0.61.2",
|
|
1126
1249
|
]
|
|
1127
1250
|
|
|
@@ -1739,7 +1862,7 @@ version = "0.4.3"
|
|
|
1739
1862
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1740
1863
|
checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
|
|
1741
1864
|
dependencies = [
|
|
1742
|
-
"dirs",
|
|
1865
|
+
"dirs 6.0.0",
|
|
1743
1866
|
"http",
|
|
1744
1867
|
"indicatif",
|
|
1745
1868
|
"libc",
|
|
@@ -1782,15 +1905,16 @@ dependencies = [
|
|
|
1782
1905
|
|
|
1783
1906
|
[[package]]
|
|
1784
1907
|
name = "html-to-markdown-rs"
|
|
1785
|
-
version = "2.
|
|
1908
|
+
version = "2.16.1"
|
|
1786
1909
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
1787
|
-
checksum = "
|
|
1910
|
+
checksum = "eda029e154a976514850a89a56a1f07f03fb0611e0e8fc2357fd4ec739d63acc"
|
|
1788
1911
|
dependencies = [
|
|
1789
1912
|
"astral-tl",
|
|
1790
1913
|
"base64 0.22.1",
|
|
1791
1914
|
"html-escape",
|
|
1792
1915
|
"html5ever",
|
|
1793
1916
|
"image",
|
|
1917
|
+
"lru",
|
|
1794
1918
|
"markup5ever_rcdom",
|
|
1795
1919
|
"once_cell",
|
|
1796
1920
|
"regex",
|
|
@@ -2222,6 +2346,12 @@ dependencies = [
|
|
|
2222
2346
|
"serde",
|
|
2223
2347
|
]
|
|
2224
2348
|
|
|
2349
|
+
[[package]]
|
|
2350
|
+
name = "is_terminal_polyfill"
|
|
2351
|
+
version = "1.70.2"
|
|
2352
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
2353
|
+
checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
|
|
2354
|
+
|
|
2225
2355
|
[[package]]
|
|
2226
2356
|
name = "itertools"
|
|
2227
2357
|
version = "0.12.1"
|
|
@@ -2318,7 +2448,7 @@ dependencies = [
|
|
|
2318
2448
|
|
|
2319
2449
|
[[package]]
|
|
2320
2450
|
name = "kreuzberg"
|
|
2321
|
-
version = "4.0.0-rc.
|
|
2451
|
+
version = "4.0.0-rc.18"
|
|
2322
2452
|
dependencies = [
|
|
2323
2453
|
"ahash",
|
|
2324
2454
|
"async-trait",
|
|
@@ -2330,6 +2460,7 @@ dependencies = [
|
|
|
2330
2460
|
"calamine",
|
|
2331
2461
|
"chardetng",
|
|
2332
2462
|
"dashmap",
|
|
2463
|
+
"dirs 5.0.1",
|
|
2333
2464
|
"docx-lite",
|
|
2334
2465
|
"encoding_rs",
|
|
2335
2466
|
"fast_image_resize",
|
|
@@ -2355,6 +2486,7 @@ dependencies = [
|
|
|
2355
2486
|
"opentelemetry",
|
|
2356
2487
|
"opentelemetry_sdk",
|
|
2357
2488
|
"org",
|
|
2489
|
+
"parking_lot",
|
|
2358
2490
|
"pastey 0.2.1",
|
|
2359
2491
|
"pdfium-render",
|
|
2360
2492
|
"pkg-config",
|
|
@@ -2393,13 +2525,27 @@ dependencies = [
|
|
|
2393
2525
|
"zip 7.0.0",
|
|
2394
2526
|
]
|
|
2395
2527
|
|
|
2528
|
+
[[package]]
|
|
2529
|
+
name = "kreuzberg-ffi"
|
|
2530
|
+
version = "4.0.0-rc.18"
|
|
2531
|
+
dependencies = [
|
|
2532
|
+
"async-trait",
|
|
2533
|
+
"cbindgen",
|
|
2534
|
+
"html-to-markdown-rs",
|
|
2535
|
+
"kreuzberg",
|
|
2536
|
+
"serde",
|
|
2537
|
+
"serde_json",
|
|
2538
|
+
"tokio",
|
|
2539
|
+
]
|
|
2540
|
+
|
|
2396
2541
|
[[package]]
|
|
2397
2542
|
name = "kreuzberg-rb"
|
|
2398
|
-
version = "4.0.0-rc.
|
|
2543
|
+
version = "4.0.0-rc.20"
|
|
2399
2544
|
dependencies = [
|
|
2400
2545
|
"async-trait",
|
|
2401
2546
|
"html-to-markdown-rs",
|
|
2402
2547
|
"kreuzberg",
|
|
2548
|
+
"kreuzberg-ffi",
|
|
2403
2549
|
"magnus",
|
|
2404
2550
|
"pretty_assertions",
|
|
2405
2551
|
"rb-sys",
|
|
@@ -2409,7 +2555,9 @@ dependencies = [
|
|
|
2409
2555
|
|
|
2410
2556
|
[[package]]
|
|
2411
2557
|
name = "kreuzberg-tesseract"
|
|
2412
|
-
version = "4.0.0-rc.
|
|
2558
|
+
version = "4.0.0-rc.18"
|
|
2559
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
2560
|
+
checksum = "477791cd4bba39222e187ae6e235643e034a87c96f2c6fb5796667020560adba"
|
|
2413
2561
|
dependencies = [
|
|
2414
2562
|
"cc",
|
|
2415
2563
|
"cmake",
|
|
@@ -2594,6 +2742,15 @@ dependencies = [
|
|
|
2594
2742
|
"weezl",
|
|
2595
2743
|
]
|
|
2596
2744
|
|
|
2745
|
+
[[package]]
|
|
2746
|
+
name = "lru"
|
|
2747
|
+
version = "0.16.2"
|
|
2748
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
2749
|
+
checksum = "96051b46fc183dc9cd4a223960ef37b9af631b55191852a8274bfef064cda20f"
|
|
2750
|
+
dependencies = [
|
|
2751
|
+
"hashbrown 0.16.1",
|
|
2752
|
+
]
|
|
2753
|
+
|
|
2597
2754
|
[[package]]
|
|
2598
2755
|
name = "lru-slab"
|
|
2599
2756
|
version = "0.1.2"
|
|
@@ -3092,6 +3249,12 @@ version = "1.21.3"
|
|
|
3092
3249
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3093
3250
|
checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d"
|
|
3094
3251
|
|
|
3252
|
+
[[package]]
|
|
3253
|
+
name = "once_cell_polyfill"
|
|
3254
|
+
version = "1.70.2"
|
|
3255
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
3256
|
+
checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
|
|
3257
|
+
|
|
3095
3258
|
[[package]]
|
|
3096
3259
|
name = "onig"
|
|
3097
3260
|
version = "6.5.1"
|
|
@@ -4325,16 +4488,18 @@ dependencies = [
|
|
|
4325
4488
|
|
|
4326
4489
|
[[package]]
|
|
4327
4490
|
name = "rb-sys"
|
|
4328
|
-
version = "0.9.
|
|
4491
|
+
version = "0.9.123"
|
|
4492
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4493
|
+
checksum = "45fb1a185af97ee456f1c9e56dbe6e2e662bec4fdeaf83c4c28e0e6adfb18816"
|
|
4329
4494
|
dependencies = [
|
|
4330
4495
|
"rb-sys-build",
|
|
4331
4496
|
]
|
|
4332
4497
|
|
|
4333
4498
|
[[package]]
|
|
4334
4499
|
name = "rb-sys-build"
|
|
4335
|
-
version = "0.9.
|
|
4500
|
+
version = "0.9.123"
|
|
4336
4501
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4337
|
-
checksum = "
|
|
4502
|
+
checksum = "a58ebd02d7a6033e6a5f6f8d150c1e9f16506039092b84a73e6bedce6d3adf41"
|
|
4338
4503
|
dependencies = [
|
|
4339
4504
|
"bindgen",
|
|
4340
4505
|
"lazy_static",
|
|
@@ -4380,6 +4545,17 @@ dependencies = [
|
|
|
4380
4545
|
"bitflags",
|
|
4381
4546
|
]
|
|
4382
4547
|
|
|
4548
|
+
[[package]]
|
|
4549
|
+
name = "redox_users"
|
|
4550
|
+
version = "0.4.6"
|
|
4551
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4552
|
+
checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
|
|
4553
|
+
dependencies = [
|
|
4554
|
+
"getrandom 0.2.16",
|
|
4555
|
+
"libredox",
|
|
4556
|
+
"thiserror 1.0.69",
|
|
4557
|
+
]
|
|
4558
|
+
|
|
4383
4559
|
[[package]]
|
|
4384
4560
|
name = "redox_users"
|
|
4385
4561
|
version = "0.5.2"
|
|
@@ -4442,9 +4618,9 @@ checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
|
|
|
4442
4618
|
|
|
4443
4619
|
[[package]]
|
|
4444
4620
|
name = "reqwest"
|
|
4445
|
-
version = "0.12.
|
|
4621
|
+
version = "0.12.28"
|
|
4446
4622
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
4447
|
-
checksum = "
|
|
4623
|
+
checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
|
|
4448
4624
|
dependencies = [
|
|
4449
4625
|
"base64 0.22.1",
|
|
4450
4626
|
"bytes",
|
|
@@ -5282,6 +5458,19 @@ dependencies = [
|
|
|
5282
5458
|
"xattr",
|
|
5283
5459
|
]
|
|
5284
5460
|
|
|
5461
|
+
[[package]]
|
|
5462
|
+
name = "tempfile"
|
|
5463
|
+
version = "3.23.0"
|
|
5464
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
5465
|
+
checksum = "2d31c77bdf42a745371d260a26ca7163f1e0924b64afa0b688e61b5a9fa02f16"
|
|
5466
|
+
dependencies = [
|
|
5467
|
+
"fastrand",
|
|
5468
|
+
"getrandom 0.3.4",
|
|
5469
|
+
"once_cell",
|
|
5470
|
+
"rustix",
|
|
5471
|
+
"windows-sys 0.61.2",
|
|
5472
|
+
]
|
|
5473
|
+
|
|
5285
5474
|
[[package]]
|
|
5286
5475
|
name = "tendril"
|
|
5287
5476
|
version = "0.4.3"
|
|
@@ -5990,6 +6179,12 @@ version = "1.0.4"
|
|
|
5990
6179
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
5991
6180
|
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
|
|
5992
6181
|
|
|
6182
|
+
[[package]]
|
|
6183
|
+
name = "utf8parse"
|
|
6184
|
+
version = "0.2.2"
|
|
6185
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6186
|
+
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
|
|
6187
|
+
|
|
5993
6188
|
[[package]]
|
|
5994
6189
|
name = "uuid"
|
|
5995
6190
|
version = "1.19.0"
|
|
@@ -6306,6 +6501,15 @@ dependencies = [
|
|
|
6306
6501
|
"windows-link",
|
|
6307
6502
|
]
|
|
6308
6503
|
|
|
6504
|
+
[[package]]
|
|
6505
|
+
name = "windows-sys"
|
|
6506
|
+
version = "0.48.0"
|
|
6507
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6508
|
+
checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
|
|
6509
|
+
dependencies = [
|
|
6510
|
+
"windows-targets 0.48.5",
|
|
6511
|
+
]
|
|
6512
|
+
|
|
6309
6513
|
[[package]]
|
|
6310
6514
|
name = "windows-sys"
|
|
6311
6515
|
version = "0.52.0"
|
|
@@ -6342,6 +6546,21 @@ dependencies = [
|
|
|
6342
6546
|
"windows-link",
|
|
6343
6547
|
]
|
|
6344
6548
|
|
|
6549
|
+
[[package]]
|
|
6550
|
+
name = "windows-targets"
|
|
6551
|
+
version = "0.48.5"
|
|
6552
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6553
|
+
checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
|
|
6554
|
+
dependencies = [
|
|
6555
|
+
"windows_aarch64_gnullvm 0.48.5",
|
|
6556
|
+
"windows_aarch64_msvc 0.48.5",
|
|
6557
|
+
"windows_i686_gnu 0.48.5",
|
|
6558
|
+
"windows_i686_msvc 0.48.5",
|
|
6559
|
+
"windows_x86_64_gnu 0.48.5",
|
|
6560
|
+
"windows_x86_64_gnullvm 0.48.5",
|
|
6561
|
+
"windows_x86_64_msvc 0.48.5",
|
|
6562
|
+
]
|
|
6563
|
+
|
|
6345
6564
|
[[package]]
|
|
6346
6565
|
name = "windows-targets"
|
|
6347
6566
|
version = "0.52.6"
|
|
@@ -6375,6 +6594,12 @@ dependencies = [
|
|
|
6375
6594
|
"windows_x86_64_msvc 0.53.1",
|
|
6376
6595
|
]
|
|
6377
6596
|
|
|
6597
|
+
[[package]]
|
|
6598
|
+
name = "windows_aarch64_gnullvm"
|
|
6599
|
+
version = "0.48.5"
|
|
6600
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6601
|
+
checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
|
|
6602
|
+
|
|
6378
6603
|
[[package]]
|
|
6379
6604
|
name = "windows_aarch64_gnullvm"
|
|
6380
6605
|
version = "0.52.6"
|
|
@@ -6387,6 +6612,12 @@ version = "0.53.1"
|
|
|
6387
6612
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6388
6613
|
checksum = "a9d8416fa8b42f5c947f8482c43e7d89e73a173cead56d044f6a56104a6d1b53"
|
|
6389
6614
|
|
|
6615
|
+
[[package]]
|
|
6616
|
+
name = "windows_aarch64_msvc"
|
|
6617
|
+
version = "0.48.5"
|
|
6618
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6619
|
+
checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
|
|
6620
|
+
|
|
6390
6621
|
[[package]]
|
|
6391
6622
|
name = "windows_aarch64_msvc"
|
|
6392
6623
|
version = "0.52.6"
|
|
@@ -6399,6 +6630,12 @@ version = "0.53.1"
|
|
|
6399
6630
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6400
6631
|
checksum = "b9d782e804c2f632e395708e99a94275910eb9100b2114651e04744e9b125006"
|
|
6401
6632
|
|
|
6633
|
+
[[package]]
|
|
6634
|
+
name = "windows_i686_gnu"
|
|
6635
|
+
version = "0.48.5"
|
|
6636
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6637
|
+
checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
|
|
6638
|
+
|
|
6402
6639
|
[[package]]
|
|
6403
6640
|
name = "windows_i686_gnu"
|
|
6404
6641
|
version = "0.52.6"
|
|
@@ -6423,6 +6660,12 @@ version = "0.53.1"
|
|
|
6423
6660
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6424
6661
|
checksum = "fa7359d10048f68ab8b09fa71c3daccfb0e9b559aed648a8f95469c27057180c"
|
|
6425
6662
|
|
|
6663
|
+
[[package]]
|
|
6664
|
+
name = "windows_i686_msvc"
|
|
6665
|
+
version = "0.48.5"
|
|
6666
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6667
|
+
checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
|
|
6668
|
+
|
|
6426
6669
|
[[package]]
|
|
6427
6670
|
name = "windows_i686_msvc"
|
|
6428
6671
|
version = "0.52.6"
|
|
@@ -6435,6 +6678,12 @@ version = "0.53.1"
|
|
|
6435
6678
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6436
6679
|
checksum = "1e7ac75179f18232fe9c285163565a57ef8d3c89254a30685b57d83a38d326c2"
|
|
6437
6680
|
|
|
6681
|
+
[[package]]
|
|
6682
|
+
name = "windows_x86_64_gnu"
|
|
6683
|
+
version = "0.48.5"
|
|
6684
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6685
|
+
checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
|
|
6686
|
+
|
|
6438
6687
|
[[package]]
|
|
6439
6688
|
name = "windows_x86_64_gnu"
|
|
6440
6689
|
version = "0.52.6"
|
|
@@ -6447,6 +6696,12 @@ version = "0.53.1"
|
|
|
6447
6696
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6448
6697
|
checksum = "9c3842cdd74a865a8066ab39c8a7a473c0778a3f29370b5fd6b4b9aa7df4a499"
|
|
6449
6698
|
|
|
6699
|
+
[[package]]
|
|
6700
|
+
name = "windows_x86_64_gnullvm"
|
|
6701
|
+
version = "0.48.5"
|
|
6702
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6703
|
+
checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
|
|
6704
|
+
|
|
6450
6705
|
[[package]]
|
|
6451
6706
|
name = "windows_x86_64_gnullvm"
|
|
6452
6707
|
version = "0.52.6"
|
|
@@ -6459,6 +6714,12 @@ version = "0.53.1"
|
|
|
6459
6714
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6460
6715
|
checksum = "0ffa179e2d07eee8ad8f57493436566c7cc30ac536a3379fdf008f47f6bb7ae1"
|
|
6461
6716
|
|
|
6717
|
+
[[package]]
|
|
6718
|
+
name = "windows_x86_64_msvc"
|
|
6719
|
+
version = "0.48.5"
|
|
6720
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
6721
|
+
checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
|
|
6722
|
+
|
|
6462
6723
|
[[package]]
|
|
6463
6724
|
name = "windows_x86_64_msvc"
|
|
6464
6725
|
version = "0.52.6"
|
|
@@ -1,13 +1,9 @@
|
|
|
1
1
|
# This crate is excluded from the workspace to use a vendored kreuzberg crate for gem packaging
|
|
2
2
|
[workspace]
|
|
3
3
|
|
|
4
|
-
[patch.crates-io]
|
|
5
|
-
# Patch rb-sys to fix Windows i32/i64 type mismatch in tracking_allocator.rs
|
|
6
|
-
rb-sys = { path = "../../../vendor/rb-sys" }
|
|
7
|
-
|
|
8
4
|
[package]
|
|
9
5
|
name = "kreuzberg-rb"
|
|
10
|
-
version = "4.0.0-rc.
|
|
6
|
+
version = "4.0.0-rc.20"
|
|
11
7
|
edition = "2024"
|
|
12
8
|
rust-version = "1.91"
|
|
13
9
|
authors = ["Na'aman Hirschfeld <nhirschfeld@gmail.com>"]
|
|
@@ -30,6 +26,7 @@ default = []
|
|
|
30
26
|
[dependencies]
|
|
31
27
|
async-trait = "0.1.89"
|
|
32
28
|
kreuzberg = { path = "../../../vendor/kreuzberg", features = ["full"] }
|
|
29
|
+
kreuzberg-ffi = { path = "../../../vendor/kreuzberg-ffi" }
|
|
33
30
|
magnus = { git = "https://github.com/matsadler/magnus", rev = "f6db11769efb517427bf7f121f9c32e18b059b38", features = [
|
|
34
31
|
"rb-sys",
|
|
35
32
|
] }
|
|
@@ -1,71 +1,7 @@
|
|
|
1
|
-
use std::env;
|
|
2
|
-
use std::path::PathBuf;
|
|
3
|
-
|
|
4
1
|
fn main() {
|
|
5
|
-
let target = env::var("TARGET").unwrap();
|
|
6
|
-
let profile = env::var("PROFILE").unwrap_or_else(|_| "release".to_string());
|
|
7
|
-
|
|
8
|
-
// Try to locate kreuzberg-ffi library built alongside this crate
|
|
9
|
-
let cargo_manifest_dir = env::var("CARGO_MANIFEST_DIR").unwrap();
|
|
10
|
-
let manifest_path = PathBuf::from(&cargo_manifest_dir);
|
|
11
|
-
|
|
12
|
-
// Prefer host target layout, but include target-triple layout for cross builds.
|
|
13
|
-
// IMPORTANT: Only search lib directories, NOT deps directories.
|
|
14
|
-
// The deps/ directories may contain dylibs with hardcoded install_name paths,
|
|
15
|
-
// which causes load errors on macOS when users install the gem.
|
|
16
|
-
if let Some(packages_root) = manifest_path
|
|
17
|
-
.parent()
|
|
18
|
-
.and_then(|p| p.parent())
|
|
19
|
-
.and_then(|p| p.parent())
|
|
20
|
-
.and_then(|p| p.parent())
|
|
21
|
-
.and_then(|p| p.parent())
|
|
22
|
-
{
|
|
23
|
-
let host_lib_dir = packages_root.join("target").join(&profile);
|
|
24
|
-
let target_lib_dir = packages_root.join("target").join(&target).join(&profile);
|
|
25
|
-
|
|
26
|
-
// Try to find the static library and link it directly on Unix-like systems
|
|
27
|
-
// to avoid the linker preferring dylib over static lib.
|
|
28
|
-
if !target.contains("windows") {
|
|
29
|
-
let static_lib_name = if target.contains("windows") {
|
|
30
|
-
"kreuzberg_ffi.lib"
|
|
31
|
-
} else {
|
|
32
|
-
"libkreuzberg_ffi.a"
|
|
33
|
-
};
|
|
34
|
-
|
|
35
|
-
// Check both host and target lib directories for the static library
|
|
36
|
-
for lib_dir in [&host_lib_dir, &target_lib_dir] {
|
|
37
|
-
let static_lib = lib_dir.join(static_lib_name);
|
|
38
|
-
if static_lib.exists() {
|
|
39
|
-
// Found static library, link it directly by passing the full path
|
|
40
|
-
println!("cargo:rustc-link-arg={}", static_lib.display());
|
|
41
|
-
// Don't add the library search path or -l flag
|
|
42
|
-
// Jump to platform-specific configuration
|
|
43
|
-
if target.contains("darwin") {
|
|
44
|
-
println!("cargo:rustc-link-arg=-Wl,-undefined,dynamic_lookup");
|
|
45
|
-
println!("cargo:rustc-link-arg=-Wl,-rpath,@loader_path");
|
|
46
|
-
} else if target.contains("linux") {
|
|
47
|
-
println!("cargo:rustc-link-arg=-Wl,-rpath,$ORIGIN");
|
|
48
|
-
}
|
|
49
|
-
println!("cargo:rerun-if-changed=build.rs");
|
|
50
|
-
return;
|
|
51
|
-
}
|
|
52
|
-
}
|
|
53
|
-
}
|
|
54
|
-
|
|
55
|
-
// Fallback: Add search paths and use standard linking
|
|
56
|
-
for dir in [host_lib_dir, target_lib_dir] {
|
|
57
|
-
println!("cargo:rustc-link-search=native={}", dir.display());
|
|
58
|
-
}
|
|
59
|
-
}
|
|
60
|
-
|
|
61
|
-
// Link the kreuzberg-ffi library
|
|
62
|
-
// When kreuzberg-ffi is built, its symbols become available for linking
|
|
63
|
-
if target.contains("windows") {
|
|
64
|
-
println!("cargo:rustc-link-lib=dylib=kreuzberg_ffi");
|
|
65
|
-
} else {
|
|
66
|
-
println!("cargo:rustc-link-lib=static=kreuzberg_ffi");
|
|
67
|
-
}
|
|
2
|
+
let target = std::env::var("TARGET").unwrap();
|
|
68
3
|
|
|
4
|
+
// Configure platform-specific linker settings
|
|
69
5
|
if target.contains("darwin") {
|
|
70
6
|
println!("cargo:rustc-link-arg=-Wl,-undefined,dynamic_lookup");
|
|
71
7
|
println!("cargo:rustc-link-arg=-Wl,-rpath,@loader_path");
|
|
@@ -73,5 +9,6 @@ fn main() {
|
|
|
73
9
|
println!("cargo:rustc-link-arg=-Wl,-rpath,$ORIGIN");
|
|
74
10
|
}
|
|
75
11
|
|
|
12
|
+
// kreuzberg-ffi is a cargo dependency that will be linked via Cargo's build system
|
|
76
13
|
println!("cargo:rerun-if-changed=build.rs");
|
|
77
14
|
}
|