kreuzberg 4.0.0.pre.rc.6 → 4.0.0.rc1
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/.gitignore +0 -6
- data/.rubocop.yaml +534 -1
- data/Gemfile +2 -1
- data/Gemfile.lock +11 -11
- data/README.md +5 -10
- data/examples/async_patterns.rb +0 -1
- data/ext/kreuzberg_rb/extconf.rb +0 -10
- data/ext/kreuzberg_rb/native/Cargo.toml +15 -23
- data/ext/kreuzberg_rb/native/build.rs +2 -0
- data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
- data/ext/kreuzberg_rb/native/include/strings.h +2 -2
- data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
- data/ext/kreuzberg_rb/native/src/lib.rs +16 -75
- data/kreuzberg.gemspec +14 -57
- data/lib/kreuzberg/cache_api.rb +0 -1
- data/lib/kreuzberg/cli.rb +2 -2
- data/lib/kreuzberg/config.rb +2 -9
- data/lib/kreuzberg/errors.rb +7 -75
- data/lib/kreuzberg/extraction_api.rb +0 -1
- data/lib/kreuzberg/setup_lib_path.rb +0 -1
- data/lib/kreuzberg/version.rb +1 -1
- data/lib/kreuzberg.rb +0 -21
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg.rbs +3 -55
- data/spec/binding/cli_proxy_spec.rb +4 -2
- data/spec/binding/cli_spec.rb +11 -12
- data/spec/examples.txt +104 -0
- data/spec/fixtures/config.yaml +1 -0
- data/spec/spec_helper.rb +1 -1
- data/vendor/kreuzberg/Cargo.toml +42 -112
- data/vendor/kreuzberg/README.md +2 -2
- data/vendor/kreuzberg/build.rs +4 -18
- data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +3 -27
- data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
- data/vendor/kreuzberg/src/core/extractor.rs +81 -202
- data/vendor/kreuzberg/src/core/io.rs +2 -4
- data/vendor/kreuzberg/src/core/mime.rs +12 -2
- data/vendor/kreuzberg/src/core/mod.rs +1 -4
- data/vendor/kreuzberg/src/core/pipeline.rs +33 -111
- data/vendor/kreuzberg/src/embeddings.rs +16 -125
- data/vendor/kreuzberg/src/error.rs +1 -1
- data/vendor/kreuzberg/src/extraction/docx.rs +1 -1
- data/vendor/kreuzberg/src/extraction/image.rs +13 -13
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +1 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +5 -9
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
- data/vendor/kreuzberg/src/extractors/archive.rs +0 -21
- data/vendor/kreuzberg/src/extractors/docx.rs +128 -16
- data/vendor/kreuzberg/src/extractors/email.rs +0 -14
- data/vendor/kreuzberg/src/extractors/excel.rs +20 -19
- data/vendor/kreuzberg/src/extractors/html.rs +154 -137
- data/vendor/kreuzberg/src/extractors/image.rs +4 -7
- data/vendor/kreuzberg/src/extractors/mod.rs +9 -106
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +15 -12
- data/vendor/kreuzberg/src/extractors/pptx.rs +3 -17
- data/vendor/kreuzberg/src/extractors/structured.rs +0 -14
- data/vendor/kreuzberg/src/extractors/text.rs +5 -23
- data/vendor/kreuzberg/src/extractors/xml.rs +0 -7
- data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
- data/vendor/kreuzberg/src/lib.rs +1 -4
- data/vendor/kreuzberg/src/mcp/mod.rs +1 -1
- data/vendor/kreuzberg/src/mcp/server.rs +3 -5
- data/vendor/kreuzberg/src/ocr/processor.rs +2 -18
- data/vendor/kreuzberg/src/pdf/error.rs +1 -1
- data/vendor/kreuzberg/src/pdf/table.rs +44 -17
- data/vendor/kreuzberg/src/pdf/text.rs +3 -0
- data/vendor/kreuzberg/src/plugins/extractor.rs +5 -8
- data/vendor/kreuzberg/src/plugins/ocr.rs +11 -2
- data/vendor/kreuzberg/src/plugins/processor.rs +1 -2
- data/vendor/kreuzberg/src/plugins/registry.rs +0 -13
- data/vendor/kreuzberg/src/plugins/validator.rs +8 -9
- data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
- data/vendor/kreuzberg/src/types.rs +12 -42
- data/vendor/kreuzberg/tests/batch_orchestration.rs +5 -19
- data/vendor/kreuzberg/tests/batch_processing.rs +3 -15
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +1 -17
- data/vendor/kreuzberg/tests/config_features.rs +0 -18
- data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -15
- data/vendor/kreuzberg/tests/core_integration.rs +7 -24
- data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
- data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1 -0
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -0
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -1
- data/vendor/kreuzberg/tests/security_validation.rs +1 -12
- metadata +25 -90
- data/.rubocop.yml +0 -538
- data/ext/kreuzberg_rb/native/Cargo.lock +0 -6535
- data/lib/kreuzberg/error_context.rb +0 -32
- data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
- data/vendor/kreuzberg/src/extraction/markdown.rs +0 -213
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -287
- data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -469
- data/vendor/kreuzberg/src/extractors/docbook.rs +0 -502
- data/vendor/kreuzberg/src/extractors/epub.rs +0 -707
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -491
- data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
- data/vendor/kreuzberg/src/extractors/jats.rs +0 -1051
- data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -367
- data/vendor/kreuzberg/src/extractors/latex.rs +0 -652
- data/vendor/kreuzberg/src/extractors/markdown.rs +0 -700
- data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +0 -634
- data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -528
- data/vendor/kreuzberg/src/extractors/rst.rs +0 -576
- data/vendor/kreuzberg/src/extractors/rtf.rs +0 -810
- data/vendor/kreuzberg/src/extractors/security.rs +0 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
- data/vendor/kreuzberg/src/extractors/typst.rs +0 -650
- data/vendor/kreuzberg/src/panic_context.rs +0 -154
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -498
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
- data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
- data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -695
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -692
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -776
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1259
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -647
- data/vendor/rb-sys/.cargo-ok +0 -1
- 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/bin/release.sh +0 -21
- data/vendor/rb-sys/build/features.rs +0 -108
- data/vendor/rb-sys/build/main.rs +0 -246
- data/vendor/rb-sys/build/stable_api_config.rs +0 -153
- data/vendor/rb-sys/build/version.rs +0 -48
- 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 -34
- 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_6.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
- data/vendor/rb-sys/src/stable_api.rs +0 -261
- data/vendor/rb-sys/src/symbol.rs +0 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
- 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: bfb7dc6c3685285b053af795140387ad8292c698cbba4cfda3411390dfe3cd48
|
|
4
|
+
data.tar.gz: 7688722b9a8d99564044a8bca31c6fadf107208aabaa336d450069b636a02726
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 3c5b66fc2c0457f670c39e53f038a5fa040760ac3f36b8731c35210d2ca98b1cf65ae41411bd6788411f18090ffd269878cf814d4b93b4201098f5e5950782e0
|
|
7
|
+
data.tar.gz: 1a02c5c0ffb830454e20e03e937aa4d80e73d9e6a6ae4913ed9d35d6cdb84ffbb2141711fa3b2ce5fcd821b109613f5ec01cbfdcface5615071727b26c772347
|
data/.gitignore
CHANGED
|
@@ -6,9 +6,3 @@ lib/*.dll
|
|
|
6
6
|
lib/*.dylib
|
|
7
7
|
lib/*.so
|
|
8
8
|
lib/*.dll
|
|
9
|
-
|
|
10
|
-
# Vendor directory for local development (symlink to ../../crates/kreuzberg)
|
|
11
|
-
# In CI, this is replaced by the actual vendored crate files
|
|
12
|
-
# Exception: vendor/rb-sys is patched and committed
|
|
13
|
-
!vendor/rb-sys/
|
|
14
|
-
vendor/
|
data/.rubocop.yaml
CHANGED
|
@@ -1 +1,534 @@
|
|
|
1
|
-
|
|
1
|
+
|
|
2
|
+
plugins:
|
|
3
|
+
- rubocop-performance
|
|
4
|
+
- rubocop-rspec
|
|
5
|
+
|
|
6
|
+
AllCops:
|
|
7
|
+
TargetRubyVersion: 3.2
|
|
8
|
+
NewCops: enable
|
|
9
|
+
SuggestExtensions: false
|
|
10
|
+
Exclude:
|
|
11
|
+
- 'vendor/**/*'
|
|
12
|
+
- 'tmp/**/*'
|
|
13
|
+
- 'lib/**/*.bundle'
|
|
14
|
+
- 'ext/**/*'
|
|
15
|
+
|
|
16
|
+
Style/StringLiterals:
|
|
17
|
+
Enabled: true
|
|
18
|
+
EnforcedStyle: single_quotes
|
|
19
|
+
|
|
20
|
+
Style/StringLiteralsInInterpolation:
|
|
21
|
+
Enabled: true
|
|
22
|
+
EnforcedStyle: single_quotes
|
|
23
|
+
|
|
24
|
+
Style/FrozenStringLiteralComment:
|
|
25
|
+
Enabled: true
|
|
26
|
+
EnforcedStyle: always
|
|
27
|
+
|
|
28
|
+
Style/Documentation:
|
|
29
|
+
Enabled: false
|
|
30
|
+
|
|
31
|
+
Layout/LineLength:
|
|
32
|
+
Max: 120
|
|
33
|
+
AllowedPatterns:
|
|
34
|
+
- '\A\s*#'
|
|
35
|
+
Exclude:
|
|
36
|
+
- 'spec/**/*'
|
|
37
|
+
|
|
38
|
+
Metrics/BlockLength:
|
|
39
|
+
Max: 350
|
|
40
|
+
Exclude:
|
|
41
|
+
- '*.gemspec'
|
|
42
|
+
- 'examples/**/*'
|
|
43
|
+
|
|
44
|
+
Metrics/MethodLength:
|
|
45
|
+
Max: 18
|
|
46
|
+
Exclude:
|
|
47
|
+
- 'spec/**/*'
|
|
48
|
+
- 'examples/**/*'
|
|
49
|
+
|
|
50
|
+
Metrics/AbcSize:
|
|
51
|
+
Max: 20
|
|
52
|
+
Exclude:
|
|
53
|
+
- 'spec/**/*'
|
|
54
|
+
- 'examples/**/*'
|
|
55
|
+
|
|
56
|
+
Naming/FileName:
|
|
57
|
+
Enabled: true
|
|
58
|
+
Exclude:
|
|
59
|
+
- 'Gemfile'
|
|
60
|
+
- 'Rakefile'
|
|
61
|
+
|
|
62
|
+
RSpec/SpecFilePathFormat:
|
|
63
|
+
Enabled: false
|
|
64
|
+
RSpec/SpecFilePathSuffix:
|
|
65
|
+
Enabled: false
|
|
66
|
+
|
|
67
|
+
RSpec/PendingWithoutReason:
|
|
68
|
+
Enabled: false
|
|
69
|
+
|
|
70
|
+
RSpec/LeakyConstantDeclaration:
|
|
71
|
+
Enabled: false
|
|
72
|
+
|
|
73
|
+
RSpec/UnspecifiedException:
|
|
74
|
+
Enabled: false
|
|
75
|
+
|
|
76
|
+
Lint/ConstantDefinitionInBlock:
|
|
77
|
+
Exclude:
|
|
78
|
+
- 'spec/**/*'
|
|
79
|
+
|
|
80
|
+
RSpec/InstanceVariable:
|
|
81
|
+
Enabled: false
|
|
82
|
+
|
|
83
|
+
Gemspec/DevelopmentDependencies:
|
|
84
|
+
Enabled: false
|
|
85
|
+
|
|
86
|
+
Metrics/ParameterLists:
|
|
87
|
+
Max: 7
|
|
88
|
+
Exclude:
|
|
89
|
+
- 'lib/kreuzberg/config.rb'
|
|
90
|
+
|
|
91
|
+
Metrics/CyclomaticComplexity:
|
|
92
|
+
Max: 7
|
|
93
|
+
Exclude:
|
|
94
|
+
- 'lib/kreuzberg/config.rb'
|
|
95
|
+
|
|
96
|
+
RSpec/RepeatedExampleGroupBody:
|
|
97
|
+
Enabled: false
|
|
98
|
+
|
|
99
|
+
RSpec/DescribeClass:
|
|
100
|
+
Enabled: false
|
|
101
|
+
|
|
102
|
+
RSpec/PredicateMatcher:
|
|
103
|
+
Enabled: false
|
|
104
|
+
|
|
105
|
+
# New cops from RuboCop 1.65+
|
|
106
|
+
Gemspec/AddRuntimeDependency:
|
|
107
|
+
Enabled: true
|
|
108
|
+
|
|
109
|
+
Gemspec/AttributeAssignment:
|
|
110
|
+
Enabled: true
|
|
111
|
+
|
|
112
|
+
Gemspec/DeprecatedAttributeAssignment:
|
|
113
|
+
Enabled: true
|
|
114
|
+
|
|
115
|
+
Gemspec/RequireMFA:
|
|
116
|
+
Enabled: false
|
|
117
|
+
|
|
118
|
+
Layout/EmptyLinesAfterModuleInclusion:
|
|
119
|
+
Enabled: true
|
|
120
|
+
|
|
121
|
+
Layout/LineContinuationLeadingSpace:
|
|
122
|
+
Enabled: true
|
|
123
|
+
|
|
124
|
+
Layout/LineContinuationSpacing:
|
|
125
|
+
Enabled: true
|
|
126
|
+
|
|
127
|
+
Layout/LineEndStringConcatenationIndentation:
|
|
128
|
+
Enabled: true
|
|
129
|
+
|
|
130
|
+
Layout/SpaceBeforeBrackets:
|
|
131
|
+
Enabled: true
|
|
132
|
+
|
|
133
|
+
Lint/AmbiguousAssignment:
|
|
134
|
+
Enabled: true
|
|
135
|
+
|
|
136
|
+
Lint/AmbiguousOperatorPrecedence:
|
|
137
|
+
Enabled: true
|
|
138
|
+
|
|
139
|
+
Lint/AmbiguousRange:
|
|
140
|
+
Enabled: true
|
|
141
|
+
|
|
142
|
+
Lint/ArrayLiteralInRegexp:
|
|
143
|
+
Enabled: true
|
|
144
|
+
|
|
145
|
+
Lint/ConstantOverwrittenInRescue:
|
|
146
|
+
Enabled: true
|
|
147
|
+
|
|
148
|
+
Lint/ConstantReassignment:
|
|
149
|
+
Enabled: true
|
|
150
|
+
|
|
151
|
+
Lint/CopDirectiveSyntax:
|
|
152
|
+
Enabled: true
|
|
153
|
+
|
|
154
|
+
Lint/DeprecatedConstants:
|
|
155
|
+
Enabled: true
|
|
156
|
+
|
|
157
|
+
Lint/DuplicateBranch:
|
|
158
|
+
Enabled: true
|
|
159
|
+
|
|
160
|
+
Lint/DuplicateMagicComment:
|
|
161
|
+
Enabled: true
|
|
162
|
+
|
|
163
|
+
Lint/DuplicateMatchPattern:
|
|
164
|
+
Enabled: true
|
|
165
|
+
|
|
166
|
+
Lint/DuplicateRegexpCharacterClassElement:
|
|
167
|
+
Enabled: true
|
|
168
|
+
|
|
169
|
+
Lint/DuplicateSetElement:
|
|
170
|
+
Enabled: true
|
|
171
|
+
|
|
172
|
+
Lint/EmptyBlock:
|
|
173
|
+
Enabled: true
|
|
174
|
+
|
|
175
|
+
Lint/EmptyClass:
|
|
176
|
+
Enabled: true
|
|
177
|
+
|
|
178
|
+
Lint/EmptyInPattern:
|
|
179
|
+
Enabled: true
|
|
180
|
+
|
|
181
|
+
Lint/HashNewWithKeywordArgumentsAsDefault:
|
|
182
|
+
Enabled: true
|
|
183
|
+
|
|
184
|
+
Lint/IncompatibleIoSelectWithFiberScheduler:
|
|
185
|
+
Enabled: true
|
|
186
|
+
|
|
187
|
+
Lint/ItWithoutArgumentsInBlock:
|
|
188
|
+
Enabled: true
|
|
189
|
+
|
|
190
|
+
Lint/LambdaWithoutLiteralBlock:
|
|
191
|
+
Enabled: true
|
|
192
|
+
|
|
193
|
+
Lint/LiteralAssignmentInCondition:
|
|
194
|
+
Enabled: true
|
|
195
|
+
|
|
196
|
+
Lint/MixedCaseRange:
|
|
197
|
+
Enabled: true
|
|
198
|
+
|
|
199
|
+
Lint/NoReturnInBeginEndBlocks:
|
|
200
|
+
Enabled: true
|
|
201
|
+
|
|
202
|
+
Lint/NonAtomicFileOperation:
|
|
203
|
+
Enabled: true
|
|
204
|
+
|
|
205
|
+
Lint/NumberedParameterAssignment:
|
|
206
|
+
Enabled: true
|
|
207
|
+
|
|
208
|
+
Lint/NumericOperationWithConstantResult:
|
|
209
|
+
Enabled: true
|
|
210
|
+
|
|
211
|
+
Lint/OrAssignmentToConstant:
|
|
212
|
+
Enabled: true
|
|
213
|
+
|
|
214
|
+
Lint/RedundantDirGlobSort:
|
|
215
|
+
Enabled: true
|
|
216
|
+
|
|
217
|
+
Lint/RedundantRegexpQuantifiers:
|
|
218
|
+
Enabled: true
|
|
219
|
+
|
|
220
|
+
Lint/RedundantTypeConversion:
|
|
221
|
+
Enabled: true
|
|
222
|
+
|
|
223
|
+
Lint/RefinementImportMethods:
|
|
224
|
+
Enabled: true
|
|
225
|
+
|
|
226
|
+
Lint/RequireRangeParentheses:
|
|
227
|
+
Enabled: true
|
|
228
|
+
|
|
229
|
+
Lint/RequireRelativeSelfPath:
|
|
230
|
+
Enabled: true
|
|
231
|
+
|
|
232
|
+
Lint/SharedMutableDefault:
|
|
233
|
+
Enabled: true
|
|
234
|
+
|
|
235
|
+
Lint/SuppressedExceptionInNumberConversion:
|
|
236
|
+
Enabled: true
|
|
237
|
+
|
|
238
|
+
Lint/SymbolConversion:
|
|
239
|
+
Enabled: true
|
|
240
|
+
|
|
241
|
+
Lint/ToEnumArguments:
|
|
242
|
+
Enabled: true
|
|
243
|
+
|
|
244
|
+
Lint/TripleQuotes:
|
|
245
|
+
Enabled: true
|
|
246
|
+
|
|
247
|
+
Lint/UnescapedBracketInRegexp:
|
|
248
|
+
Enabled: true
|
|
249
|
+
|
|
250
|
+
Lint/UnexpectedBlockArity:
|
|
251
|
+
Enabled: true
|
|
252
|
+
|
|
253
|
+
Lint/UnmodifiedReduceAccumulator:
|
|
254
|
+
Enabled: true
|
|
255
|
+
|
|
256
|
+
Lint/UselessConstantScoping:
|
|
257
|
+
Enabled: true
|
|
258
|
+
|
|
259
|
+
Lint/UselessDefaultValueArgument:
|
|
260
|
+
Enabled: true
|
|
261
|
+
|
|
262
|
+
Lint/UselessDefined:
|
|
263
|
+
Enabled: true
|
|
264
|
+
|
|
265
|
+
Lint/UselessNumericOperation:
|
|
266
|
+
Enabled: true
|
|
267
|
+
|
|
268
|
+
Lint/UselessOr:
|
|
269
|
+
Enabled: true
|
|
270
|
+
|
|
271
|
+
Lint/UselessRescue:
|
|
272
|
+
Enabled: true
|
|
273
|
+
|
|
274
|
+
Lint/UselessRuby2Keywords:
|
|
275
|
+
Enabled: true
|
|
276
|
+
|
|
277
|
+
Metrics/CollectionLiteralLength:
|
|
278
|
+
Enabled: true
|
|
279
|
+
|
|
280
|
+
Naming/BlockForwarding:
|
|
281
|
+
Enabled: true
|
|
282
|
+
|
|
283
|
+
Naming/PredicateMethod:
|
|
284
|
+
Enabled: true
|
|
285
|
+
|
|
286
|
+
Security/CompoundHash:
|
|
287
|
+
Enabled: true
|
|
288
|
+
|
|
289
|
+
Security/IoMethods:
|
|
290
|
+
Enabled: true
|
|
291
|
+
|
|
292
|
+
Style/AmbiguousEndlessMethodDefinition:
|
|
293
|
+
Enabled: true
|
|
294
|
+
|
|
295
|
+
Style/ArgumentsForwarding:
|
|
296
|
+
Enabled: true
|
|
297
|
+
|
|
298
|
+
Style/ArrayIntersect:
|
|
299
|
+
Enabled: true
|
|
300
|
+
|
|
301
|
+
Style/ArrayIntersectWithSingleElement:
|
|
302
|
+
Enabled: true
|
|
303
|
+
|
|
304
|
+
Style/BitwisePredicate:
|
|
305
|
+
Enabled: true
|
|
306
|
+
|
|
307
|
+
Style/CollectionCompact:
|
|
308
|
+
Enabled: true
|
|
309
|
+
|
|
310
|
+
Style/CollectionQuerying:
|
|
311
|
+
Enabled: true
|
|
312
|
+
|
|
313
|
+
Style/CombinableDefined:
|
|
314
|
+
Enabled: true
|
|
315
|
+
|
|
316
|
+
Style/ComparableBetween:
|
|
317
|
+
Enabled: true
|
|
318
|
+
|
|
319
|
+
Style/ComparableClamp:
|
|
320
|
+
Enabled: true
|
|
321
|
+
|
|
322
|
+
Style/ConcatArrayLiterals:
|
|
323
|
+
Enabled: true
|
|
324
|
+
|
|
325
|
+
Style/DataInheritance:
|
|
326
|
+
Enabled: true
|
|
327
|
+
|
|
328
|
+
Style/DigChain:
|
|
329
|
+
Enabled: true
|
|
330
|
+
|
|
331
|
+
Style/DirEmpty:
|
|
332
|
+
Enabled: true
|
|
333
|
+
|
|
334
|
+
Style/DocumentDynamicEvalDefinition:
|
|
335
|
+
Enabled: true
|
|
336
|
+
|
|
337
|
+
Style/EmptyHeredoc:
|
|
338
|
+
Enabled: true
|
|
339
|
+
|
|
340
|
+
Style/EmptyStringInsideInterpolation:
|
|
341
|
+
Enabled: true
|
|
342
|
+
|
|
343
|
+
Style/EndlessMethod:
|
|
344
|
+
Enabled: true
|
|
345
|
+
|
|
346
|
+
Style/EnvHome:
|
|
347
|
+
Enabled: true
|
|
348
|
+
|
|
349
|
+
Style/ExactRegexpMatch:
|
|
350
|
+
Enabled: true
|
|
351
|
+
|
|
352
|
+
Style/FetchEnvVar:
|
|
353
|
+
Enabled: true
|
|
354
|
+
|
|
355
|
+
Style/FileEmpty:
|
|
356
|
+
Enabled: true
|
|
357
|
+
|
|
358
|
+
Style/FileNull:
|
|
359
|
+
Enabled: true
|
|
360
|
+
|
|
361
|
+
Style/FileRead:
|
|
362
|
+
Enabled: true
|
|
363
|
+
|
|
364
|
+
Style/FileTouch:
|
|
365
|
+
Enabled: true
|
|
366
|
+
|
|
367
|
+
Style/FileWrite:
|
|
368
|
+
Enabled: true
|
|
369
|
+
|
|
370
|
+
Style/HashConversion:
|
|
371
|
+
Enabled: true
|
|
372
|
+
|
|
373
|
+
Style/HashExcept:
|
|
374
|
+
Enabled: true
|
|
375
|
+
|
|
376
|
+
Style/HashFetchChain:
|
|
377
|
+
Enabled: true
|
|
378
|
+
|
|
379
|
+
Style/HashSlice:
|
|
380
|
+
Enabled: true
|
|
381
|
+
|
|
382
|
+
Style/IfWithBooleanLiteralBranches:
|
|
383
|
+
Enabled: true
|
|
384
|
+
|
|
385
|
+
Style/InPatternThen:
|
|
386
|
+
Enabled: true
|
|
387
|
+
|
|
388
|
+
Style/ItAssignment:
|
|
389
|
+
Enabled: true
|
|
390
|
+
|
|
391
|
+
Style/ItBlockParameter:
|
|
392
|
+
Enabled: true
|
|
393
|
+
|
|
394
|
+
Style/KeywordArgumentsMerging:
|
|
395
|
+
Enabled: true
|
|
396
|
+
|
|
397
|
+
Style/MagicCommentFormat:
|
|
398
|
+
Enabled: true
|
|
399
|
+
|
|
400
|
+
Style/MapCompactWithConditionalBlock:
|
|
401
|
+
Enabled: true
|
|
402
|
+
|
|
403
|
+
Style/MapIntoArray:
|
|
404
|
+
Enabled: true
|
|
405
|
+
|
|
406
|
+
Style/MapToHash:
|
|
407
|
+
Enabled: true
|
|
408
|
+
|
|
409
|
+
Style/MapToSet:
|
|
410
|
+
Enabled: true
|
|
411
|
+
|
|
412
|
+
Style/MinMaxComparison:
|
|
413
|
+
Enabled: true
|
|
414
|
+
|
|
415
|
+
Style/MultilineInPatternThen:
|
|
416
|
+
Enabled: true
|
|
417
|
+
|
|
418
|
+
Style/NegatedIfElseCondition:
|
|
419
|
+
Enabled: true
|
|
420
|
+
|
|
421
|
+
Style/NestedFileDirname:
|
|
422
|
+
Enabled: true
|
|
423
|
+
|
|
424
|
+
Style/NilLambda:
|
|
425
|
+
Enabled: true
|
|
426
|
+
|
|
427
|
+
Style/NumberedParameters:
|
|
428
|
+
Enabled: true
|
|
429
|
+
|
|
430
|
+
Style/NumberedParametersLimit:
|
|
431
|
+
Enabled: true
|
|
432
|
+
|
|
433
|
+
Style/ObjectThen:
|
|
434
|
+
Enabled: true
|
|
435
|
+
|
|
436
|
+
Style/OpenStructUse:
|
|
437
|
+
Enabled: true
|
|
438
|
+
|
|
439
|
+
Style/OperatorMethodCall:
|
|
440
|
+
Enabled: true
|
|
441
|
+
|
|
442
|
+
Style/QuotedSymbols:
|
|
443
|
+
Enabled: true
|
|
444
|
+
|
|
445
|
+
Style/RedundantArgument:
|
|
446
|
+
Enabled: true
|
|
447
|
+
|
|
448
|
+
Style/RedundantArrayConstructor:
|
|
449
|
+
Enabled: true
|
|
450
|
+
|
|
451
|
+
Style/RedundantArrayFlatten:
|
|
452
|
+
Enabled: true
|
|
453
|
+
|
|
454
|
+
Style/RedundantConstantBase:
|
|
455
|
+
Enabled: true
|
|
456
|
+
|
|
457
|
+
Style/RedundantCurrentDirectoryInPath:
|
|
458
|
+
Enabled: true
|
|
459
|
+
|
|
460
|
+
Style/RedundantDoubleSplatHashBraces:
|
|
461
|
+
Enabled: true
|
|
462
|
+
|
|
463
|
+
Style/RedundantEach:
|
|
464
|
+
Enabled: true
|
|
465
|
+
|
|
466
|
+
Style/RedundantFilterChain:
|
|
467
|
+
Enabled: true
|
|
468
|
+
|
|
469
|
+
Style/RedundantFormat:
|
|
470
|
+
Enabled: true
|
|
471
|
+
|
|
472
|
+
Style/RedundantHeredocDelimiterQuotes:
|
|
473
|
+
Enabled: true
|
|
474
|
+
|
|
475
|
+
Style/RedundantInitialize:
|
|
476
|
+
Enabled: true
|
|
477
|
+
|
|
478
|
+
Style/RedundantInterpolationUnfreeze:
|
|
479
|
+
Enabled: true
|
|
480
|
+
|
|
481
|
+
Style/RedundantLineContinuation:
|
|
482
|
+
Enabled: true
|
|
483
|
+
|
|
484
|
+
Style/RedundantRegexpArgument:
|
|
485
|
+
Enabled: true
|
|
486
|
+
|
|
487
|
+
Style/RedundantRegexpConstructor:
|
|
488
|
+
Enabled: true
|
|
489
|
+
|
|
490
|
+
Style/RedundantSelfAssignmentBranch:
|
|
491
|
+
Enabled: true
|
|
492
|
+
|
|
493
|
+
Style/RedundantStringEscape:
|
|
494
|
+
Enabled: true
|
|
495
|
+
|
|
496
|
+
Style/ReturnNilInPredicateMethodDefinition:
|
|
497
|
+
Enabled: true
|
|
498
|
+
|
|
499
|
+
Style/SafeNavigationChainLength:
|
|
500
|
+
Enabled: true
|
|
501
|
+
|
|
502
|
+
Style/SelectByRegexp:
|
|
503
|
+
Enabled: true
|
|
504
|
+
|
|
505
|
+
Style/SendWithLiteralMethodName:
|
|
506
|
+
Enabled: true
|
|
507
|
+
|
|
508
|
+
Style/SingleLineDoEndBlock:
|
|
509
|
+
Enabled: true
|
|
510
|
+
|
|
511
|
+
Style/StringChars:
|
|
512
|
+
Enabled: true
|
|
513
|
+
|
|
514
|
+
Style/SuperArguments:
|
|
515
|
+
Enabled: true
|
|
516
|
+
|
|
517
|
+
Style/SuperWithArgsParentheses:
|
|
518
|
+
Enabled: true
|
|
519
|
+
|
|
520
|
+
Style/SwapValues:
|
|
521
|
+
Enabled: true
|
|
522
|
+
|
|
523
|
+
Style/YAMLFileRead:
|
|
524
|
+
Enabled: true
|
|
525
|
+
|
|
526
|
+
# Adjust RSpec metrics for test blocks
|
|
527
|
+
RSpec/ExampleLength:
|
|
528
|
+
Max: 35
|
|
529
|
+
|
|
530
|
+
RSpec/MultipleExpectations:
|
|
531
|
+
Max: 15
|
|
532
|
+
|
|
533
|
+
RSpec/NestedGroups:
|
|
534
|
+
Max: 6
|
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
PATH
|
|
2
2
|
remote: .
|
|
3
3
|
specs:
|
|
4
|
-
kreuzberg (4.0.0.
|
|
4
|
+
kreuzberg (4.0.0.rc1)
|
|
5
5
|
|
|
6
6
|
GEM
|
|
7
7
|
remote: https://rubygems.org/
|
|
@@ -25,7 +25,7 @@ GEM
|
|
|
25
25
|
byebug (12.0.0)
|
|
26
26
|
coderay (1.1.3)
|
|
27
27
|
concurrent-ruby (1.3.5)
|
|
28
|
-
connection_pool (
|
|
28
|
+
connection_pool (2.5.4)
|
|
29
29
|
csv (3.3.5)
|
|
30
30
|
diff-lcs (1.6.2)
|
|
31
31
|
drb (2.2.3)
|
|
@@ -34,7 +34,7 @@ GEM
|
|
|
34
34
|
fileutils (1.8.0)
|
|
35
35
|
i18n (1.14.7)
|
|
36
36
|
concurrent-ruby (~> 1.0)
|
|
37
|
-
json (2.
|
|
37
|
+
json (2.16.0)
|
|
38
38
|
language_server-protocol (3.17.0.5)
|
|
39
39
|
lint_roller (1.1.0)
|
|
40
40
|
listen (3.9.0)
|
|
@@ -60,12 +60,12 @@ GEM
|
|
|
60
60
|
rake (13.3.1)
|
|
61
61
|
rake-compiler (1.3.0)
|
|
62
62
|
rake
|
|
63
|
-
rake-compiler-dock (1.
|
|
63
|
+
rake-compiler-dock (1.9.1)
|
|
64
64
|
rb-fsevent (0.11.2)
|
|
65
65
|
rb-inotify (0.11.1)
|
|
66
66
|
ffi (~> 1.0)
|
|
67
|
-
rb_sys (0.9.
|
|
68
|
-
rake-compiler-dock (= 1.
|
|
67
|
+
rb_sys (0.9.117)
|
|
68
|
+
rake-compiler-dock (= 1.9.1)
|
|
69
69
|
rbs (3.9.5)
|
|
70
70
|
logger
|
|
71
71
|
regexp_parser (2.11.3)
|
|
@@ -131,20 +131,20 @@ GEM
|
|
|
131
131
|
unicode-emoji (~> 4.1)
|
|
132
132
|
unicode-emoji (4.1.0)
|
|
133
133
|
uri (1.1.1)
|
|
134
|
-
yard (0.9.
|
|
134
|
+
yard (0.9.37)
|
|
135
135
|
|
|
136
136
|
PLATFORMS
|
|
137
|
-
arm64-darwin-23
|
|
138
137
|
arm64-darwin-24
|
|
138
|
+
ruby
|
|
139
139
|
|
|
140
140
|
DEPENDENCIES
|
|
141
|
-
bundler (~>
|
|
141
|
+
bundler (~> 2.0)
|
|
142
142
|
kreuzberg!
|
|
143
143
|
pry (~> 0.14)
|
|
144
144
|
pry-byebug (~> 3.10)
|
|
145
145
|
rake (~> 13.0)
|
|
146
146
|
rake-compiler (~> 1.2)
|
|
147
|
-
rb_sys (~> 0.9
|
|
147
|
+
rb_sys (~> 0.9)
|
|
148
148
|
rbs (~> 3.0)
|
|
149
149
|
rspec (~> 3.12)
|
|
150
150
|
rubocop (~> 1.66)
|
|
@@ -154,4 +154,4 @@ DEPENDENCIES
|
|
|
154
154
|
yard (~> 0.9)
|
|
155
155
|
|
|
156
156
|
BUNDLED WITH
|
|
157
|
-
|
|
157
|
+
2.7.2
|
data/README.md
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
[](https://rubygems.org/gems/kreuzberg)
|
|
4
4
|
[](https://crates.io/crates/kreuzberg)
|
|
5
5
|
[](https://pypi.org/project/kreuzberg/)
|
|
6
|
-
[](https://www.npmjs.com/package/kreuzberg)
|
|
6
|
+
[](https://www.npmjs.com/package/@goldziher/kreuzberg)
|
|
7
7
|
[](https://opensource.org/licenses/MIT)
|
|
8
8
|
[](https://kreuzberg.dev)
|
|
9
9
|
|
|
@@ -12,7 +12,7 @@ High-performance document intelligence for Ruby, powered by Rust.
|
|
|
12
12
|
Extract text, tables, images, and metadata from 30+ file formats including PDF, DOCX, PPTX, XLSX, images, and more.
|
|
13
13
|
|
|
14
14
|
> **🚀 Version 4.0.0 Release Candidate**
|
|
15
|
-
> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/
|
|
15
|
+
> This is a pre-release version. We invite you to test the library and [report any issues](https://github.com/Goldziher/kreuzberg/issues) you encounter.
|
|
16
16
|
|
|
17
17
|
## Features
|
|
18
18
|
|
|
@@ -390,15 +390,12 @@ Kreuzberg's Rust core provides significant performance improvements:
|
|
|
390
390
|
|
|
391
391
|
```bash
|
|
392
392
|
# Clone the repository
|
|
393
|
-
git clone https://github.com/
|
|
393
|
+
git clone https://github.com/Goldziher/kreuzberg.git
|
|
394
394
|
cd kreuzberg/packages/ruby
|
|
395
395
|
|
|
396
396
|
# Install dependencies
|
|
397
397
|
bundle install
|
|
398
398
|
|
|
399
|
-
# Set up vendor symlink for local development (required for building)
|
|
400
|
-
ln -sfn ../../crates/kreuzberg vendor/kreuzberg
|
|
401
|
-
|
|
402
399
|
# Build the Rust extension
|
|
403
400
|
bundle exec rake compile
|
|
404
401
|
|
|
@@ -409,8 +406,6 @@ bundle exec rspec
|
|
|
409
406
|
bundle exec rubocop
|
|
410
407
|
```
|
|
411
408
|
|
|
412
|
-
**Note**: The Ruby bindings use a vendored copy of the core `kreuzberg` Rust crate. For local development, create a symlink at `vendor/kreuzberg` pointing to `../../crates/kreuzberg`. In CI and gem packaging, the actual vendored files are copied to this location.
|
|
413
|
-
|
|
414
409
|
## License
|
|
415
410
|
|
|
416
411
|
MIT License. See [LICENSE](../../LICENSE) for details.
|
|
@@ -422,5 +417,5 @@ Contributions are welcome! Please see [CONTRIBUTING.md](../../CONTRIBUTING.md) f
|
|
|
422
417
|
## Links
|
|
423
418
|
|
|
424
419
|
- **Documentation**: https://docs.kreuzberg.dev
|
|
425
|
-
- **GitHub**: https://github.com/
|
|
426
|
-
- **Issues**: https://github.com/
|
|
420
|
+
- **GitHub**: https://github.com/Goldziher/kreuzberg
|
|
421
|
+
- **Issues**: https://github.com/Goldziher/kreuzberg/issues
|
data/examples/async_patterns.rb
CHANGED
|
@@ -236,7 +236,6 @@ end
|
|
|
236
236
|
# Pattern 15: Custom Ruby OCR Backend Plugin
|
|
237
237
|
# ============================================================================
|
|
238
238
|
|
|
239
|
-
# Example OCR backend implementation for custom processing.
|
|
240
239
|
class CustomOcrBackend
|
|
241
240
|
def process_image(image_bytes, language)
|
|
242
241
|
# In a real implementation, you would:
|
data/ext/kreuzberg_rb/extconf.rb
CHANGED
|
@@ -4,15 +4,6 @@ require 'mkmf'
|
|
|
4
4
|
require 'rb_sys/mkmf'
|
|
5
5
|
require 'rbconfig'
|
|
6
6
|
|
|
7
|
-
# Set shorter build directory for Windows to avoid MAX_PATH issues
|
|
8
|
-
if Gem.win_platform?
|
|
9
|
-
# Use a much shorter path to avoid Windows MAX_PATH (260 char) limit
|
|
10
|
-
short_target_dir = 'D:/kz-build'
|
|
11
|
-
ENV['CARGO_TARGET_DIR'] = short_target_dir
|
|
12
|
-
ENV['OUT_DIR'] = short_target_dir
|
|
13
|
-
puts "Windows detected: Using short build path #{short_target_dir}"
|
|
14
|
-
end
|
|
15
|
-
|
|
16
7
|
if /mswin|mingw/.match?(RbConfig::CONFIG['host_os'])
|
|
17
8
|
devkit = ENV.fetch('RI_DEVKIT', nil)
|
|
18
9
|
prefix = ENV['MSYSTEM_PREFIX'] || '/ucrt64'
|
|
@@ -40,6 +31,5 @@ native_dir = 'native'
|
|
|
40
31
|
|
|
41
32
|
create_rust_makefile('kreuzberg_rb') do |config|
|
|
42
33
|
config.profile = default_profile.to_sym
|
|
43
|
-
# Build from the actual Rust crate location (native/) so Cargo.toml is resolvable in packaged gems
|
|
44
34
|
config.ext_dir = native_dir
|
|
45
35
|
end
|