kreuzberg 4.0.0.rc1 → 4.0.0.rc2
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 +14 -8
- data/.rspec +3 -3
- data/.rubocop.yaml +1 -534
- data/.rubocop.yml +538 -0
- data/Gemfile +8 -9
- data/Gemfile.lock +9 -109
- data/README.md +426 -421
- data/Rakefile +25 -25
- data/Steepfile +47 -47
- data/examples/async_patterns.rb +341 -340
- data/ext/kreuzberg_rb/extconf.rb +45 -35
- data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +44 -36
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +15 -17
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
- data/ext/kreuzberg_rb/native/include/strings.h +20 -20
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
- data/ext/kreuzberg_rb/native/src/lib.rs +2998 -2939
- data/extconf.rb +28 -28
- data/kreuzberg.gemspec +148 -105
- data/lib/kreuzberg/api_proxy.rb +142 -142
- data/lib/kreuzberg/cache_api.rb +46 -45
- data/lib/kreuzberg/cli.rb +55 -55
- data/lib/kreuzberg/cli_proxy.rb +127 -127
- data/lib/kreuzberg/config.rb +691 -684
- data/lib/kreuzberg/error_context.rb +32 -0
- data/lib/kreuzberg/errors.rb +118 -50
- data/lib/kreuzberg/extraction_api.rb +85 -84
- data/lib/kreuzberg/mcp_proxy.rb +186 -186
- data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
- data/lib/kreuzberg/post_processor_protocol.rb +86 -86
- data/lib/kreuzberg/result.rb +216 -216
- data/lib/kreuzberg/setup_lib_path.rb +80 -79
- data/lib/kreuzberg/validator_protocol.rb +89 -89
- data/lib/kreuzberg/version.rb +5 -5
- data/lib/kreuzberg.rb +103 -82
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +520 -468
- data/spec/binding/cache_spec.rb +227 -227
- data/spec/binding/cli_proxy_spec.rb +85 -87
- data/spec/binding/cli_spec.rb +55 -54
- data/spec/binding/config_spec.rb +345 -345
- data/spec/binding/config_validation_spec.rb +283 -283
- data/spec/binding/error_handling_spec.rb +213 -213
- data/spec/binding/errors_spec.rb +66 -66
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
- data/spec/binding/plugins/postprocessor_spec.rb +269 -269
- data/spec/binding/plugins/validator_spec.rb +274 -274
- data/spec/fixtures/config.toml +39 -39
- data/spec/fixtures/config.yaml +41 -42
- data/spec/fixtures/invalid_config.toml +4 -4
- data/spec/smoke/package_spec.rb +178 -178
- data/spec/spec_helper.rb +42 -42
- data/vendor/kreuzberg/Cargo.toml +204 -134
- data/vendor/kreuzberg/README.md +175 -175
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
- data/vendor/kreuzberg/build.rs +474 -460
- data/vendor/kreuzberg/src/api/error.rs +81 -81
- data/vendor/kreuzberg/src/api/handlers.rs +199 -199
- data/vendor/kreuzberg/src/api/mod.rs +79 -79
- data/vendor/kreuzberg/src/api/server.rs +353 -353
- data/vendor/kreuzberg/src/api/types.rs +170 -170
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -1143
- data/vendor/kreuzberg/src/chunking/mod.rs +677 -677
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -35
- data/vendor/kreuzberg/src/core/config.rs +1032 -1032
- data/vendor/kreuzberg/src/core/extractor.rs +1024 -903
- data/vendor/kreuzberg/src/core/io.rs +329 -327
- data/vendor/kreuzberg/src/core/mime.rs +605 -615
- data/vendor/kreuzberg/src/core/mod.rs +45 -42
- data/vendor/kreuzberg/src/core/pipeline.rs +984 -906
- data/vendor/kreuzberg/src/embeddings.rs +432 -323
- data/vendor/kreuzberg/src/error.rs +431 -431
- data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
- data/vendor/kreuzberg/src/extraction/docx.rs +40 -40
- data/vendor/kreuzberg/src/extraction/email.rs +854 -854
- data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
- data/vendor/kreuzberg/src/extraction/html.rs +553 -553
- data/vendor/kreuzberg/src/extraction/image.rs +368 -368
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -564
- data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +81 -77
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -128
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -3000
- data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
- data/vendor/kreuzberg/src/extraction/table.rs +328 -328
- data/vendor/kreuzberg/src/extraction/text.rs +269 -269
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
- data/vendor/kreuzberg/src/extractors/archive.rs +446 -425
- data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
- data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
- data/vendor/kreuzberg/src/extractors/docx.rs +367 -479
- data/vendor/kreuzberg/src/extractors/email.rs +143 -129
- data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +343 -344
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
- data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
- data/vendor/kreuzberg/src/extractors/html.rs +393 -410
- data/vendor/kreuzberg/src/extractors/image.rs +198 -195
- data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
- data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
- data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
- data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
- data/vendor/kreuzberg/src/extractors/mod.rs +365 -268
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
- data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
- data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +493 -496
- data/vendor/kreuzberg/src/extractors/pptx.rs +248 -234
- data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
- data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
- data/vendor/kreuzberg/src/extractors/security.rs +484 -0
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
- data/vendor/kreuzberg/src/extractors/structured.rs +140 -126
- data/vendor/kreuzberg/src/extractors/text.rs +260 -242
- data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +135 -128
- data/vendor/kreuzberg/src/image/dpi.rs +164 -164
- data/vendor/kreuzberg/src/image/mod.rs +6 -6
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
- data/vendor/kreuzberg/src/image/resize.rs +89 -89
- data/vendor/kreuzberg/src/keywords/config.rs +154 -154
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
- data/vendor/kreuzberg/src/keywords/processor.rs +267 -267
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -294
- data/vendor/kreuzberg/src/keywords/types.rs +68 -68
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
- data/vendor/kreuzberg/src/language_detection/mod.rs +942 -942
- data/vendor/kreuzberg/src/lib.rs +105 -102
- data/vendor/kreuzberg/src/mcp/mod.rs +32 -32
- data/vendor/kreuzberg/src/mcp/server.rs +1968 -1966
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
- data/vendor/kreuzberg/src/ocr/error.rs +37 -37
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
- data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
- data/vendor/kreuzberg/src/ocr/processor.rs +863 -847
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -450
- data/vendor/kreuzberg/src/ocr/types.rs +393 -393
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
- data/vendor/kreuzberg/src/panic_context.rs +154 -0
- data/vendor/kreuzberg/src/pdf/error.rs +122 -122
- data/vendor/kreuzberg/src/pdf/images.rs +139 -139
- data/vendor/kreuzberg/src/pdf/metadata.rs +346 -346
- data/vendor/kreuzberg/src/pdf/mod.rs +50 -50
- data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
- data/vendor/kreuzberg/src/pdf/table.rs +393 -420
- data/vendor/kreuzberg/src/pdf/text.rs +158 -161
- data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -1010
- data/vendor/kreuzberg/src/plugins/mod.rs +209 -209
- data/vendor/kreuzberg/src/plugins/ocr.rs +620 -629
- data/vendor/kreuzberg/src/plugins/processor.rs +642 -641
- data/vendor/kreuzberg/src/plugins/registry.rs +1337 -1324
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
- data/vendor/kreuzberg/src/plugins/validator.rs +956 -955
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
- data/vendor/kreuzberg/src/text/mod.rs +19 -19
- data/vendor/kreuzberg/src/text/quality.rs +697 -697
- data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
- data/vendor/kreuzberg/src/types.rs +903 -873
- data/vendor/kreuzberg/src/utils/mod.rs +17 -17
- data/vendor/kreuzberg/src/utils/quality.rs +959 -959
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
- data/vendor/kreuzberg/tests/api_tests.rs +966 -966
- data/vendor/kreuzberg/tests/archive_integration.rs +543 -543
- data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -542
- data/vendor/kreuzberg/tests/batch_processing.rs +316 -304
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -509
- data/vendor/kreuzberg/tests/config_features.rs +598 -580
- data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -439
- data/vendor/kreuzberg/tests/core_integration.rs +510 -493
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -424
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -124
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
- data/vendor/kreuzberg/tests/email_integration.rs +325 -325
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
- data/vendor/kreuzberg/tests/error_handling.rs +393 -393
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
- data/vendor/kreuzberg/tests/format_integration.rs +159 -159
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
- data/vendor/kreuzberg/tests/image_integration.rs +253 -253
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
- data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
- data/vendor/kreuzberg/tests/mime_detection.rs +428 -428
- data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -510
- data/vendor/kreuzberg/tests/ocr_errors.rs +676 -676
- data/vendor/kreuzberg/tests/ocr_quality.rs +627 -627
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +43 -43
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -1412
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -771
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -561
- data/vendor/kreuzberg/tests/plugin_system.rs +921 -921
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -607
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
- data/vendor/kreuzberg/tests/security_validation.rs +415 -404
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
- data/vendor/kreuzberg/tests/test_fastembed.rs +609 -609
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
- data/vendor/rb-sys/.cargo-ok +1 -0
- data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
- data/vendor/rb-sys/Cargo.lock +393 -0
- data/vendor/rb-sys/Cargo.toml +70 -0
- data/vendor/rb-sys/Cargo.toml.orig +57 -0
- data/vendor/rb-sys/LICENSE-APACHE +190 -0
- data/vendor/rb-sys/LICENSE-MIT +21 -0
- data/vendor/rb-sys/bin/release.sh +21 -0
- data/vendor/rb-sys/build/features.rs +108 -0
- data/vendor/rb-sys/build/main.rs +246 -0
- data/vendor/rb-sys/build/stable_api_config.rs +153 -0
- data/vendor/rb-sys/build/version.rs +48 -0
- data/vendor/rb-sys/readme.md +36 -0
- data/vendor/rb-sys/src/bindings.rs +21 -0
- data/vendor/rb-sys/src/hidden.rs +11 -0
- data/vendor/rb-sys/src/lib.rs +34 -0
- data/vendor/rb-sys/src/macros.rs +371 -0
- data/vendor/rb-sys/src/memory.rs +53 -0
- data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
- data/vendor/rb-sys/src/special_consts.rs +31 -0
- data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
- data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
- data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
- data/vendor/rb-sys/src/stable_api.rs +261 -0
- data/vendor/rb-sys/src/symbol.rs +31 -0
- data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
- data/vendor/rb-sys/src/utils.rs +89 -0
- data/vendor/rb-sys/src/value_type.rs +7 -0
- metadata +90 -95
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/spec/examples.txt +0 -104
- data/vendor/kreuzberg/src/bin/profile_extract.rs +0 -455
- data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +0 -275
- data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +0 -178
- data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +0 -491
- data/vendor/kreuzberg/src/extraction/pandoc/server.rs +0 -496
- data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +0 -1188
- data/vendor/kreuzberg/src/extraction/pandoc/version.rs +0 -162
- data/vendor/kreuzberg/src/extractors/pandoc.rs +0 -201
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +0 -92
- data/vendor/kreuzberg/tests/pandoc_integration.rs +0 -503
|
@@ -1,622 +1,622 @@
|
|
|
1
|
-
[
|
|
2
|
-
"a",
|
|
3
|
-
"ab",
|
|
4
|
-
"aber",
|
|
5
|
-
"ach",
|
|
6
|
-
"acht",
|
|
7
|
-
"achte",
|
|
8
|
-
"achten",
|
|
9
|
-
"achter",
|
|
10
|
-
"achtes",
|
|
11
|
-
"ag",
|
|
12
|
-
"alle",
|
|
13
|
-
"allein",
|
|
14
|
-
"allem",
|
|
15
|
-
"allen",
|
|
16
|
-
"aller",
|
|
17
|
-
"allerdings",
|
|
18
|
-
"alles",
|
|
19
|
-
"allgemeinen",
|
|
20
|
-
"als",
|
|
21
|
-
"also",
|
|
22
|
-
"am",
|
|
23
|
-
"an",
|
|
24
|
-
"ander",
|
|
25
|
-
"andere",
|
|
26
|
-
"anderem",
|
|
27
|
-
"anderen",
|
|
28
|
-
"anderer",
|
|
29
|
-
"anderes",
|
|
30
|
-
"anderm",
|
|
31
|
-
"andern",
|
|
32
|
-
"anderr",
|
|
33
|
-
"anders",
|
|
34
|
-
"au",
|
|
35
|
-
"auch",
|
|
36
|
-
"auf",
|
|
37
|
-
"aus",
|
|
38
|
-
"ausser",
|
|
39
|
-
"ausserdem",
|
|
40
|
-
"außer",
|
|
41
|
-
"außerdem",
|
|
42
|
-
"b",
|
|
43
|
-
"bald",
|
|
44
|
-
"bei",
|
|
45
|
-
"beide",
|
|
46
|
-
"beiden",
|
|
47
|
-
"beim",
|
|
48
|
-
"beispiel",
|
|
49
|
-
"bekannt",
|
|
50
|
-
"bereits",
|
|
51
|
-
"besonders",
|
|
52
|
-
"besser",
|
|
53
|
-
"besten",
|
|
54
|
-
"bin",
|
|
55
|
-
"bis",
|
|
56
|
-
"bisher",
|
|
57
|
-
"bist",
|
|
58
|
-
"c",
|
|
59
|
-
"d",
|
|
60
|
-
"d.h",
|
|
61
|
-
"da",
|
|
62
|
-
"dabei",
|
|
63
|
-
"dadurch",
|
|
64
|
-
"dafür",
|
|
65
|
-
"dagegen",
|
|
66
|
-
"daher",
|
|
67
|
-
"dahin",
|
|
68
|
-
"dahinter",
|
|
69
|
-
"damals",
|
|
70
|
-
"damit",
|
|
71
|
-
"danach",
|
|
72
|
-
"daneben",
|
|
73
|
-
"dank",
|
|
74
|
-
"dann",
|
|
75
|
-
"daran",
|
|
76
|
-
"darauf",
|
|
77
|
-
"daraus",
|
|
78
|
-
"darf",
|
|
79
|
-
"darfst",
|
|
80
|
-
"darin",
|
|
81
|
-
"darum",
|
|
82
|
-
"darunter",
|
|
83
|
-
"darüber",
|
|
84
|
-
"das",
|
|
85
|
-
"dasein",
|
|
86
|
-
"daselbst",
|
|
87
|
-
"dass",
|
|
88
|
-
"dasselbe",
|
|
89
|
-
"davon",
|
|
90
|
-
"davor",
|
|
91
|
-
"dazu",
|
|
92
|
-
"dazwischen",
|
|
93
|
-
"daß",
|
|
94
|
-
"dein",
|
|
95
|
-
"deine",
|
|
96
|
-
"deinem",
|
|
97
|
-
"deinen",
|
|
98
|
-
"deiner",
|
|
99
|
-
"deines",
|
|
100
|
-
"dem",
|
|
101
|
-
"dementsprechend",
|
|
102
|
-
"demgegenüber",
|
|
103
|
-
"demgemäss",
|
|
104
|
-
"demgemäß",
|
|
105
|
-
"demselben",
|
|
106
|
-
"demzufolge",
|
|
107
|
-
"den",
|
|
108
|
-
"denen",
|
|
109
|
-
"denn",
|
|
110
|
-
"denselben",
|
|
111
|
-
"der",
|
|
112
|
-
"deren",
|
|
113
|
-
"derer",
|
|
114
|
-
"derjenige",
|
|
115
|
-
"derjenigen",
|
|
116
|
-
"dermassen",
|
|
117
|
-
"dermaßen",
|
|
118
|
-
"derselbe",
|
|
119
|
-
"derselben",
|
|
120
|
-
"des",
|
|
121
|
-
"deshalb",
|
|
122
|
-
"desselben",
|
|
123
|
-
"dessen",
|
|
124
|
-
"deswegen",
|
|
125
|
-
"dich",
|
|
126
|
-
"die",
|
|
127
|
-
"diejenige",
|
|
128
|
-
"diejenigen",
|
|
129
|
-
"dies",
|
|
130
|
-
"diese",
|
|
131
|
-
"dieselbe",
|
|
132
|
-
"dieselben",
|
|
133
|
-
"diesem",
|
|
134
|
-
"diesen",
|
|
135
|
-
"dieser",
|
|
136
|
-
"dieses",
|
|
137
|
-
"dir",
|
|
138
|
-
"doch",
|
|
139
|
-
"dort",
|
|
140
|
-
"drei",
|
|
141
|
-
"drin",
|
|
142
|
-
"dritte",
|
|
143
|
-
"dritten",
|
|
144
|
-
"dritter",
|
|
145
|
-
"drittes",
|
|
146
|
-
"du",
|
|
147
|
-
"durch",
|
|
148
|
-
"durchaus",
|
|
149
|
-
"durfte",
|
|
150
|
-
"durften",
|
|
151
|
-
"dürfen",
|
|
152
|
-
"dürft",
|
|
153
|
-
"e",
|
|
154
|
-
"eben",
|
|
155
|
-
"ebenso",
|
|
156
|
-
"ehrlich",
|
|
157
|
-
"ei",
|
|
158
|
-
"ei,",
|
|
159
|
-
"eigen",
|
|
160
|
-
"eigene",
|
|
161
|
-
"eigenen",
|
|
162
|
-
"eigener",
|
|
163
|
-
"eigenes",
|
|
164
|
-
"ein",
|
|
165
|
-
"einander",
|
|
166
|
-
"eine",
|
|
167
|
-
"einem",
|
|
168
|
-
"einen",
|
|
169
|
-
"einer",
|
|
170
|
-
"eines",
|
|
171
|
-
"einig",
|
|
172
|
-
"einige",
|
|
173
|
-
"einigem",
|
|
174
|
-
"einigen",
|
|
175
|
-
"einiger",
|
|
176
|
-
"einiges",
|
|
177
|
-
"einmal",
|
|
178
|
-
"eins",
|
|
179
|
-
"elf",
|
|
180
|
-
"en",
|
|
181
|
-
"ende",
|
|
182
|
-
"endlich",
|
|
183
|
-
"entweder",
|
|
184
|
-
"er",
|
|
185
|
-
"ernst",
|
|
186
|
-
"erst",
|
|
187
|
-
"erste",
|
|
188
|
-
"ersten",
|
|
189
|
-
"erster",
|
|
190
|
-
"erstes",
|
|
191
|
-
"es",
|
|
192
|
-
"etwa",
|
|
193
|
-
"etwas",
|
|
194
|
-
"euch",
|
|
195
|
-
"euer",
|
|
196
|
-
"eure",
|
|
197
|
-
"eurem",
|
|
198
|
-
"euren",
|
|
199
|
-
"eurer",
|
|
200
|
-
"eures",
|
|
201
|
-
"f",
|
|
202
|
-
"folgende",
|
|
203
|
-
"früher",
|
|
204
|
-
"fünf",
|
|
205
|
-
"fünfte",
|
|
206
|
-
"fünften",
|
|
207
|
-
"fünfter",
|
|
208
|
-
"fünftes",
|
|
209
|
-
"für",
|
|
210
|
-
"g",
|
|
211
|
-
"gab",
|
|
212
|
-
"ganz",
|
|
213
|
-
"ganze",
|
|
214
|
-
"ganzen",
|
|
215
|
-
"ganzer",
|
|
216
|
-
"ganzes",
|
|
217
|
-
"gar",
|
|
218
|
-
"gedurft",
|
|
219
|
-
"gegen",
|
|
220
|
-
"gegenüber",
|
|
221
|
-
"gehabt",
|
|
222
|
-
"gehen",
|
|
223
|
-
"geht",
|
|
224
|
-
"gekannt",
|
|
225
|
-
"gekonnt",
|
|
226
|
-
"gemacht",
|
|
227
|
-
"gemocht",
|
|
228
|
-
"gemusst",
|
|
229
|
-
"genug",
|
|
230
|
-
"gerade",
|
|
231
|
-
"gern",
|
|
232
|
-
"gesagt",
|
|
233
|
-
"geschweige",
|
|
234
|
-
"gewesen",
|
|
235
|
-
"gewollt",
|
|
236
|
-
"geworden",
|
|
237
|
-
"gibt",
|
|
238
|
-
"ging",
|
|
239
|
-
"gleich",
|
|
240
|
-
"gott",
|
|
241
|
-
"gross",
|
|
242
|
-
"grosse",
|
|
243
|
-
"grossen",
|
|
244
|
-
"grosser",
|
|
245
|
-
"grosses",
|
|
246
|
-
"groß",
|
|
247
|
-
"große",
|
|
248
|
-
"großen",
|
|
249
|
-
"großer",
|
|
250
|
-
"großes",
|
|
251
|
-
"gut",
|
|
252
|
-
"gute",
|
|
253
|
-
"guter",
|
|
254
|
-
"gutes",
|
|
255
|
-
"h",
|
|
256
|
-
"hab",
|
|
257
|
-
"habe",
|
|
258
|
-
"haben",
|
|
259
|
-
"habt",
|
|
260
|
-
"hast",
|
|
261
|
-
"hat",
|
|
262
|
-
"hatte",
|
|
263
|
-
"hatten",
|
|
264
|
-
"hattest",
|
|
265
|
-
"hattet",
|
|
266
|
-
"heisst",
|
|
267
|
-
"her",
|
|
268
|
-
"heute",
|
|
269
|
-
"hier",
|
|
270
|
-
"hin",
|
|
271
|
-
"hinter",
|
|
272
|
-
"hoch",
|
|
273
|
-
"hätte",
|
|
274
|
-
"hätten",
|
|
275
|
-
"i",
|
|
276
|
-
"ich",
|
|
277
|
-
"ihm",
|
|
278
|
-
"ihn",
|
|
279
|
-
"ihnen",
|
|
280
|
-
"ihr",
|
|
281
|
-
"ihre",
|
|
282
|
-
"ihrem",
|
|
283
|
-
"ihren",
|
|
284
|
-
"ihrer",
|
|
285
|
-
"ihres",
|
|
286
|
-
"im",
|
|
287
|
-
"immer",
|
|
288
|
-
"in",
|
|
289
|
-
"indem",
|
|
290
|
-
"infolgedessen",
|
|
291
|
-
"ins",
|
|
292
|
-
"irgend",
|
|
293
|
-
"ist",
|
|
294
|
-
"j",
|
|
295
|
-
"ja",
|
|
296
|
-
"jahr",
|
|
297
|
-
"jahre",
|
|
298
|
-
"jahren",
|
|
299
|
-
"je",
|
|
300
|
-
"jede",
|
|
301
|
-
"jedem",
|
|
302
|
-
"jeden",
|
|
303
|
-
"jeder",
|
|
304
|
-
"jedermann",
|
|
305
|
-
"jedermanns",
|
|
306
|
-
"jedes",
|
|
307
|
-
"jedoch",
|
|
308
|
-
"jemand",
|
|
309
|
-
"jemandem",
|
|
310
|
-
"jemanden",
|
|
311
|
-
"jene",
|
|
312
|
-
"jenem",
|
|
313
|
-
"jenen",
|
|
314
|
-
"jener",
|
|
315
|
-
"jenes",
|
|
316
|
-
"jetzt",
|
|
317
|
-
"k",
|
|
318
|
-
"kam",
|
|
319
|
-
"kann",
|
|
320
|
-
"kannst",
|
|
321
|
-
"kaum",
|
|
322
|
-
"kein",
|
|
323
|
-
"keine",
|
|
324
|
-
"keinem",
|
|
325
|
-
"keinen",
|
|
326
|
-
"keiner",
|
|
327
|
-
"keines",
|
|
328
|
-
"kleine",
|
|
329
|
-
"kleinen",
|
|
330
|
-
"kleiner",
|
|
331
|
-
"kleines",
|
|
332
|
-
"kommen",
|
|
333
|
-
"kommt",
|
|
334
|
-
"konnte",
|
|
335
|
-
"konnten",
|
|
336
|
-
"kurz",
|
|
337
|
-
"können",
|
|
338
|
-
"könnt",
|
|
339
|
-
"könnte",
|
|
340
|
-
"l",
|
|
341
|
-
"lang",
|
|
342
|
-
"lange",
|
|
343
|
-
"leicht",
|
|
344
|
-
"leide",
|
|
345
|
-
"lieber",
|
|
346
|
-
"los",
|
|
347
|
-
"m",
|
|
348
|
-
"machen",
|
|
349
|
-
"macht",
|
|
350
|
-
"machte",
|
|
351
|
-
"mag",
|
|
352
|
-
"magst",
|
|
353
|
-
"mahn",
|
|
354
|
-
"mal",
|
|
355
|
-
"man",
|
|
356
|
-
"manche",
|
|
357
|
-
"manchem",
|
|
358
|
-
"manchen",
|
|
359
|
-
"mancher",
|
|
360
|
-
"manches",
|
|
361
|
-
"mann",
|
|
362
|
-
"mehr",
|
|
363
|
-
"mein",
|
|
364
|
-
"meine",
|
|
365
|
-
"meinem",
|
|
366
|
-
"meinen",
|
|
367
|
-
"meiner",
|
|
368
|
-
"meines",
|
|
369
|
-
"mensch",
|
|
370
|
-
"menschen",
|
|
371
|
-
"mich",
|
|
372
|
-
"mir",
|
|
373
|
-
"mit",
|
|
374
|
-
"mittel",
|
|
375
|
-
"mochte",
|
|
376
|
-
"mochten",
|
|
377
|
-
"morgen",
|
|
378
|
-
"muss",
|
|
379
|
-
"musst",
|
|
380
|
-
"musste",
|
|
381
|
-
"mussten",
|
|
382
|
-
"muß",
|
|
383
|
-
"mußt",
|
|
384
|
-
"möchte",
|
|
385
|
-
"mögen",
|
|
386
|
-
"möglich",
|
|
387
|
-
"mögt",
|
|
388
|
-
"müssen",
|
|
389
|
-
"müsst",
|
|
390
|
-
"müßt",
|
|
391
|
-
"n",
|
|
392
|
-
"na",
|
|
393
|
-
"nach",
|
|
394
|
-
"nachdem",
|
|
395
|
-
"nahm",
|
|
396
|
-
"natürlich",
|
|
397
|
-
"neben",
|
|
398
|
-
"nein",
|
|
399
|
-
"neue",
|
|
400
|
-
"neuen",
|
|
401
|
-
"neun",
|
|
402
|
-
"neunte",
|
|
403
|
-
"neunten",
|
|
404
|
-
"neunter",
|
|
405
|
-
"neuntes",
|
|
406
|
-
"nicht",
|
|
407
|
-
"nichts",
|
|
408
|
-
"nie",
|
|
409
|
-
"niemand",
|
|
410
|
-
"niemandem",
|
|
411
|
-
"niemanden",
|
|
412
|
-
"noch",
|
|
413
|
-
"nun",
|
|
414
|
-
"nur",
|
|
415
|
-
"o",
|
|
416
|
-
"ob",
|
|
417
|
-
"oben",
|
|
418
|
-
"oder",
|
|
419
|
-
"offen",
|
|
420
|
-
"oft",
|
|
421
|
-
"ohne",
|
|
422
|
-
"ordnung",
|
|
423
|
-
"p",
|
|
424
|
-
"q",
|
|
425
|
-
"r",
|
|
426
|
-
"recht",
|
|
427
|
-
"rechte",
|
|
428
|
-
"rechten",
|
|
429
|
-
"rechter",
|
|
430
|
-
"rechtes",
|
|
431
|
-
"richtig",
|
|
432
|
-
"rund",
|
|
433
|
-
"s",
|
|
434
|
-
"sa",
|
|
435
|
-
"sache",
|
|
436
|
-
"sagt",
|
|
437
|
-
"sagte",
|
|
438
|
-
"sah",
|
|
439
|
-
"satt",
|
|
440
|
-
"schlecht",
|
|
441
|
-
"schluss",
|
|
442
|
-
"schon",
|
|
443
|
-
"sechs",
|
|
444
|
-
"sechste",
|
|
445
|
-
"sechsten",
|
|
446
|
-
"sechster",
|
|
447
|
-
"sechstes",
|
|
448
|
-
"sehr",
|
|
449
|
-
"sei",
|
|
450
|
-
"seid",
|
|
451
|
-
"seien",
|
|
452
|
-
"sein",
|
|
453
|
-
"seine",
|
|
454
|
-
"seinem",
|
|
455
|
-
"seinen",
|
|
456
|
-
"seiner",
|
|
457
|
-
"seines",
|
|
458
|
-
"seit",
|
|
459
|
-
"seitdem",
|
|
460
|
-
"selbst",
|
|
461
|
-
"sich",
|
|
462
|
-
"sie",
|
|
463
|
-
"sieben",
|
|
464
|
-
"siebente",
|
|
465
|
-
"siebenten",
|
|
466
|
-
"siebenter",
|
|
467
|
-
"siebentes",
|
|
468
|
-
"sind",
|
|
469
|
-
"so",
|
|
470
|
-
"solang",
|
|
471
|
-
"solche",
|
|
472
|
-
"solchem",
|
|
473
|
-
"solchen",
|
|
474
|
-
"solcher",
|
|
475
|
-
"solches",
|
|
476
|
-
"soll",
|
|
477
|
-
"sollen",
|
|
478
|
-
"sollst",
|
|
479
|
-
"sollt",
|
|
480
|
-
"sollte",
|
|
481
|
-
"sollten",
|
|
482
|
-
"sondern",
|
|
483
|
-
"sonst",
|
|
484
|
-
"soweit",
|
|
485
|
-
"sowie",
|
|
486
|
-
"später",
|
|
487
|
-
"startseite",
|
|
488
|
-
"statt",
|
|
489
|
-
"steht",
|
|
490
|
-
"suche",
|
|
491
|
-
"t",
|
|
492
|
-
"tag",
|
|
493
|
-
"tage",
|
|
494
|
-
"tagen",
|
|
495
|
-
"tat",
|
|
496
|
-
"teil",
|
|
497
|
-
"tel",
|
|
498
|
-
"tritt",
|
|
499
|
-
"trotzdem",
|
|
500
|
-
"tun",
|
|
501
|
-
"u",
|
|
502
|
-
"uhr",
|
|
503
|
-
"um",
|
|
504
|
-
"und",
|
|
505
|
-
"uns",
|
|
506
|
-
"unse",
|
|
507
|
-
"unsem",
|
|
508
|
-
"unsen",
|
|
509
|
-
"unser",
|
|
510
|
-
"unsere",
|
|
511
|
-
"unserer",
|
|
512
|
-
"unses",
|
|
513
|
-
"unter",
|
|
514
|
-
"v",
|
|
515
|
-
"vergangenen",
|
|
516
|
-
"viel",
|
|
517
|
-
"viele",
|
|
518
|
-
"vielem",
|
|
519
|
-
"vielen",
|
|
520
|
-
"vielleicht",
|
|
521
|
-
"vier",
|
|
522
|
-
"vierte",
|
|
523
|
-
"vierten",
|
|
524
|
-
"vierter",
|
|
525
|
-
"viertes",
|
|
526
|
-
"vom",
|
|
527
|
-
"von",
|
|
528
|
-
"vor",
|
|
529
|
-
"w",
|
|
530
|
-
"wahr",
|
|
531
|
-
"wann",
|
|
532
|
-
"war",
|
|
533
|
-
"waren",
|
|
534
|
-
"warst",
|
|
535
|
-
"wart",
|
|
536
|
-
"warum",
|
|
537
|
-
"was",
|
|
538
|
-
"weg",
|
|
539
|
-
"wegen",
|
|
540
|
-
"weil",
|
|
541
|
-
"weit",
|
|
542
|
-
"weiter",
|
|
543
|
-
"weitere",
|
|
544
|
-
"weiteren",
|
|
545
|
-
"weiteres",
|
|
546
|
-
"welche",
|
|
547
|
-
"welchem",
|
|
548
|
-
"welchen",
|
|
549
|
-
"welcher",
|
|
550
|
-
"welches",
|
|
551
|
-
"wem",
|
|
552
|
-
"wen",
|
|
553
|
-
"wenig",
|
|
554
|
-
"wenige",
|
|
555
|
-
"weniger",
|
|
556
|
-
"weniges",
|
|
557
|
-
"wenigstens",
|
|
558
|
-
"wenn",
|
|
559
|
-
"wer",
|
|
560
|
-
"werde",
|
|
561
|
-
"werden",
|
|
562
|
-
"werdet",
|
|
563
|
-
"weshalb",
|
|
564
|
-
"wessen",
|
|
565
|
-
"wie",
|
|
566
|
-
"wieder",
|
|
567
|
-
"wieso",
|
|
568
|
-
"will",
|
|
569
|
-
"willst",
|
|
570
|
-
"wir",
|
|
571
|
-
"wird",
|
|
572
|
-
"wirklich",
|
|
573
|
-
"wirst",
|
|
574
|
-
"wissen",
|
|
575
|
-
"wo",
|
|
576
|
-
"woher",
|
|
577
|
-
"wohin",
|
|
578
|
-
"wohl",
|
|
579
|
-
"wollen",
|
|
580
|
-
"wollt",
|
|
581
|
-
"wollte",
|
|
582
|
-
"wollten",
|
|
583
|
-
"worden",
|
|
584
|
-
"wurde",
|
|
585
|
-
"wurden",
|
|
586
|
-
"während",
|
|
587
|
-
"währenddem",
|
|
588
|
-
"währenddessen",
|
|
589
|
-
"wäre",
|
|
590
|
-
"würde",
|
|
591
|
-
"würden",
|
|
592
|
-
"x",
|
|
593
|
-
"y",
|
|
594
|
-
"z",
|
|
595
|
-
"z.b",
|
|
596
|
-
"zehn",
|
|
597
|
-
"zehnte",
|
|
598
|
-
"zehnten",
|
|
599
|
-
"zehnter",
|
|
600
|
-
"zehntes",
|
|
601
|
-
"zeit",
|
|
602
|
-
"zu",
|
|
603
|
-
"zuerst",
|
|
604
|
-
"zugleich",
|
|
605
|
-
"zum",
|
|
606
|
-
"zunächst",
|
|
607
|
-
"zur",
|
|
608
|
-
"zurück",
|
|
609
|
-
"zusammen",
|
|
610
|
-
"zwanzig",
|
|
611
|
-
"zwar",
|
|
612
|
-
"zwei",
|
|
613
|
-
"zweite",
|
|
614
|
-
"zweiten",
|
|
615
|
-
"zweiter",
|
|
616
|
-
"zweites",
|
|
617
|
-
"zwischen",
|
|
618
|
-
"zwölf",
|
|
619
|
-
"über",
|
|
620
|
-
"überhaupt",
|
|
621
|
-
"übrigens"
|
|
622
|
-
]
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"ab",
|
|
4
|
+
"aber",
|
|
5
|
+
"ach",
|
|
6
|
+
"acht",
|
|
7
|
+
"achte",
|
|
8
|
+
"achten",
|
|
9
|
+
"achter",
|
|
10
|
+
"achtes",
|
|
11
|
+
"ag",
|
|
12
|
+
"alle",
|
|
13
|
+
"allein",
|
|
14
|
+
"allem",
|
|
15
|
+
"allen",
|
|
16
|
+
"aller",
|
|
17
|
+
"allerdings",
|
|
18
|
+
"alles",
|
|
19
|
+
"allgemeinen",
|
|
20
|
+
"als",
|
|
21
|
+
"also",
|
|
22
|
+
"am",
|
|
23
|
+
"an",
|
|
24
|
+
"ander",
|
|
25
|
+
"andere",
|
|
26
|
+
"anderem",
|
|
27
|
+
"anderen",
|
|
28
|
+
"anderer",
|
|
29
|
+
"anderes",
|
|
30
|
+
"anderm",
|
|
31
|
+
"andern",
|
|
32
|
+
"anderr",
|
|
33
|
+
"anders",
|
|
34
|
+
"au",
|
|
35
|
+
"auch",
|
|
36
|
+
"auf",
|
|
37
|
+
"aus",
|
|
38
|
+
"ausser",
|
|
39
|
+
"ausserdem",
|
|
40
|
+
"außer",
|
|
41
|
+
"außerdem",
|
|
42
|
+
"b",
|
|
43
|
+
"bald",
|
|
44
|
+
"bei",
|
|
45
|
+
"beide",
|
|
46
|
+
"beiden",
|
|
47
|
+
"beim",
|
|
48
|
+
"beispiel",
|
|
49
|
+
"bekannt",
|
|
50
|
+
"bereits",
|
|
51
|
+
"besonders",
|
|
52
|
+
"besser",
|
|
53
|
+
"besten",
|
|
54
|
+
"bin",
|
|
55
|
+
"bis",
|
|
56
|
+
"bisher",
|
|
57
|
+
"bist",
|
|
58
|
+
"c",
|
|
59
|
+
"d",
|
|
60
|
+
"d.h",
|
|
61
|
+
"da",
|
|
62
|
+
"dabei",
|
|
63
|
+
"dadurch",
|
|
64
|
+
"dafür",
|
|
65
|
+
"dagegen",
|
|
66
|
+
"daher",
|
|
67
|
+
"dahin",
|
|
68
|
+
"dahinter",
|
|
69
|
+
"damals",
|
|
70
|
+
"damit",
|
|
71
|
+
"danach",
|
|
72
|
+
"daneben",
|
|
73
|
+
"dank",
|
|
74
|
+
"dann",
|
|
75
|
+
"daran",
|
|
76
|
+
"darauf",
|
|
77
|
+
"daraus",
|
|
78
|
+
"darf",
|
|
79
|
+
"darfst",
|
|
80
|
+
"darin",
|
|
81
|
+
"darum",
|
|
82
|
+
"darunter",
|
|
83
|
+
"darüber",
|
|
84
|
+
"das",
|
|
85
|
+
"dasein",
|
|
86
|
+
"daselbst",
|
|
87
|
+
"dass",
|
|
88
|
+
"dasselbe",
|
|
89
|
+
"davon",
|
|
90
|
+
"davor",
|
|
91
|
+
"dazu",
|
|
92
|
+
"dazwischen",
|
|
93
|
+
"daß",
|
|
94
|
+
"dein",
|
|
95
|
+
"deine",
|
|
96
|
+
"deinem",
|
|
97
|
+
"deinen",
|
|
98
|
+
"deiner",
|
|
99
|
+
"deines",
|
|
100
|
+
"dem",
|
|
101
|
+
"dementsprechend",
|
|
102
|
+
"demgegenüber",
|
|
103
|
+
"demgemäss",
|
|
104
|
+
"demgemäß",
|
|
105
|
+
"demselben",
|
|
106
|
+
"demzufolge",
|
|
107
|
+
"den",
|
|
108
|
+
"denen",
|
|
109
|
+
"denn",
|
|
110
|
+
"denselben",
|
|
111
|
+
"der",
|
|
112
|
+
"deren",
|
|
113
|
+
"derer",
|
|
114
|
+
"derjenige",
|
|
115
|
+
"derjenigen",
|
|
116
|
+
"dermassen",
|
|
117
|
+
"dermaßen",
|
|
118
|
+
"derselbe",
|
|
119
|
+
"derselben",
|
|
120
|
+
"des",
|
|
121
|
+
"deshalb",
|
|
122
|
+
"desselben",
|
|
123
|
+
"dessen",
|
|
124
|
+
"deswegen",
|
|
125
|
+
"dich",
|
|
126
|
+
"die",
|
|
127
|
+
"diejenige",
|
|
128
|
+
"diejenigen",
|
|
129
|
+
"dies",
|
|
130
|
+
"diese",
|
|
131
|
+
"dieselbe",
|
|
132
|
+
"dieselben",
|
|
133
|
+
"diesem",
|
|
134
|
+
"diesen",
|
|
135
|
+
"dieser",
|
|
136
|
+
"dieses",
|
|
137
|
+
"dir",
|
|
138
|
+
"doch",
|
|
139
|
+
"dort",
|
|
140
|
+
"drei",
|
|
141
|
+
"drin",
|
|
142
|
+
"dritte",
|
|
143
|
+
"dritten",
|
|
144
|
+
"dritter",
|
|
145
|
+
"drittes",
|
|
146
|
+
"du",
|
|
147
|
+
"durch",
|
|
148
|
+
"durchaus",
|
|
149
|
+
"durfte",
|
|
150
|
+
"durften",
|
|
151
|
+
"dürfen",
|
|
152
|
+
"dürft",
|
|
153
|
+
"e",
|
|
154
|
+
"eben",
|
|
155
|
+
"ebenso",
|
|
156
|
+
"ehrlich",
|
|
157
|
+
"ei",
|
|
158
|
+
"ei,",
|
|
159
|
+
"eigen",
|
|
160
|
+
"eigene",
|
|
161
|
+
"eigenen",
|
|
162
|
+
"eigener",
|
|
163
|
+
"eigenes",
|
|
164
|
+
"ein",
|
|
165
|
+
"einander",
|
|
166
|
+
"eine",
|
|
167
|
+
"einem",
|
|
168
|
+
"einen",
|
|
169
|
+
"einer",
|
|
170
|
+
"eines",
|
|
171
|
+
"einig",
|
|
172
|
+
"einige",
|
|
173
|
+
"einigem",
|
|
174
|
+
"einigen",
|
|
175
|
+
"einiger",
|
|
176
|
+
"einiges",
|
|
177
|
+
"einmal",
|
|
178
|
+
"eins",
|
|
179
|
+
"elf",
|
|
180
|
+
"en",
|
|
181
|
+
"ende",
|
|
182
|
+
"endlich",
|
|
183
|
+
"entweder",
|
|
184
|
+
"er",
|
|
185
|
+
"ernst",
|
|
186
|
+
"erst",
|
|
187
|
+
"erste",
|
|
188
|
+
"ersten",
|
|
189
|
+
"erster",
|
|
190
|
+
"erstes",
|
|
191
|
+
"es",
|
|
192
|
+
"etwa",
|
|
193
|
+
"etwas",
|
|
194
|
+
"euch",
|
|
195
|
+
"euer",
|
|
196
|
+
"eure",
|
|
197
|
+
"eurem",
|
|
198
|
+
"euren",
|
|
199
|
+
"eurer",
|
|
200
|
+
"eures",
|
|
201
|
+
"f",
|
|
202
|
+
"folgende",
|
|
203
|
+
"früher",
|
|
204
|
+
"fünf",
|
|
205
|
+
"fünfte",
|
|
206
|
+
"fünften",
|
|
207
|
+
"fünfter",
|
|
208
|
+
"fünftes",
|
|
209
|
+
"für",
|
|
210
|
+
"g",
|
|
211
|
+
"gab",
|
|
212
|
+
"ganz",
|
|
213
|
+
"ganze",
|
|
214
|
+
"ganzen",
|
|
215
|
+
"ganzer",
|
|
216
|
+
"ganzes",
|
|
217
|
+
"gar",
|
|
218
|
+
"gedurft",
|
|
219
|
+
"gegen",
|
|
220
|
+
"gegenüber",
|
|
221
|
+
"gehabt",
|
|
222
|
+
"gehen",
|
|
223
|
+
"geht",
|
|
224
|
+
"gekannt",
|
|
225
|
+
"gekonnt",
|
|
226
|
+
"gemacht",
|
|
227
|
+
"gemocht",
|
|
228
|
+
"gemusst",
|
|
229
|
+
"genug",
|
|
230
|
+
"gerade",
|
|
231
|
+
"gern",
|
|
232
|
+
"gesagt",
|
|
233
|
+
"geschweige",
|
|
234
|
+
"gewesen",
|
|
235
|
+
"gewollt",
|
|
236
|
+
"geworden",
|
|
237
|
+
"gibt",
|
|
238
|
+
"ging",
|
|
239
|
+
"gleich",
|
|
240
|
+
"gott",
|
|
241
|
+
"gross",
|
|
242
|
+
"grosse",
|
|
243
|
+
"grossen",
|
|
244
|
+
"grosser",
|
|
245
|
+
"grosses",
|
|
246
|
+
"groß",
|
|
247
|
+
"große",
|
|
248
|
+
"großen",
|
|
249
|
+
"großer",
|
|
250
|
+
"großes",
|
|
251
|
+
"gut",
|
|
252
|
+
"gute",
|
|
253
|
+
"guter",
|
|
254
|
+
"gutes",
|
|
255
|
+
"h",
|
|
256
|
+
"hab",
|
|
257
|
+
"habe",
|
|
258
|
+
"haben",
|
|
259
|
+
"habt",
|
|
260
|
+
"hast",
|
|
261
|
+
"hat",
|
|
262
|
+
"hatte",
|
|
263
|
+
"hatten",
|
|
264
|
+
"hattest",
|
|
265
|
+
"hattet",
|
|
266
|
+
"heisst",
|
|
267
|
+
"her",
|
|
268
|
+
"heute",
|
|
269
|
+
"hier",
|
|
270
|
+
"hin",
|
|
271
|
+
"hinter",
|
|
272
|
+
"hoch",
|
|
273
|
+
"hätte",
|
|
274
|
+
"hätten",
|
|
275
|
+
"i",
|
|
276
|
+
"ich",
|
|
277
|
+
"ihm",
|
|
278
|
+
"ihn",
|
|
279
|
+
"ihnen",
|
|
280
|
+
"ihr",
|
|
281
|
+
"ihre",
|
|
282
|
+
"ihrem",
|
|
283
|
+
"ihren",
|
|
284
|
+
"ihrer",
|
|
285
|
+
"ihres",
|
|
286
|
+
"im",
|
|
287
|
+
"immer",
|
|
288
|
+
"in",
|
|
289
|
+
"indem",
|
|
290
|
+
"infolgedessen",
|
|
291
|
+
"ins",
|
|
292
|
+
"irgend",
|
|
293
|
+
"ist",
|
|
294
|
+
"j",
|
|
295
|
+
"ja",
|
|
296
|
+
"jahr",
|
|
297
|
+
"jahre",
|
|
298
|
+
"jahren",
|
|
299
|
+
"je",
|
|
300
|
+
"jede",
|
|
301
|
+
"jedem",
|
|
302
|
+
"jeden",
|
|
303
|
+
"jeder",
|
|
304
|
+
"jedermann",
|
|
305
|
+
"jedermanns",
|
|
306
|
+
"jedes",
|
|
307
|
+
"jedoch",
|
|
308
|
+
"jemand",
|
|
309
|
+
"jemandem",
|
|
310
|
+
"jemanden",
|
|
311
|
+
"jene",
|
|
312
|
+
"jenem",
|
|
313
|
+
"jenen",
|
|
314
|
+
"jener",
|
|
315
|
+
"jenes",
|
|
316
|
+
"jetzt",
|
|
317
|
+
"k",
|
|
318
|
+
"kam",
|
|
319
|
+
"kann",
|
|
320
|
+
"kannst",
|
|
321
|
+
"kaum",
|
|
322
|
+
"kein",
|
|
323
|
+
"keine",
|
|
324
|
+
"keinem",
|
|
325
|
+
"keinen",
|
|
326
|
+
"keiner",
|
|
327
|
+
"keines",
|
|
328
|
+
"kleine",
|
|
329
|
+
"kleinen",
|
|
330
|
+
"kleiner",
|
|
331
|
+
"kleines",
|
|
332
|
+
"kommen",
|
|
333
|
+
"kommt",
|
|
334
|
+
"konnte",
|
|
335
|
+
"konnten",
|
|
336
|
+
"kurz",
|
|
337
|
+
"können",
|
|
338
|
+
"könnt",
|
|
339
|
+
"könnte",
|
|
340
|
+
"l",
|
|
341
|
+
"lang",
|
|
342
|
+
"lange",
|
|
343
|
+
"leicht",
|
|
344
|
+
"leide",
|
|
345
|
+
"lieber",
|
|
346
|
+
"los",
|
|
347
|
+
"m",
|
|
348
|
+
"machen",
|
|
349
|
+
"macht",
|
|
350
|
+
"machte",
|
|
351
|
+
"mag",
|
|
352
|
+
"magst",
|
|
353
|
+
"mahn",
|
|
354
|
+
"mal",
|
|
355
|
+
"man",
|
|
356
|
+
"manche",
|
|
357
|
+
"manchem",
|
|
358
|
+
"manchen",
|
|
359
|
+
"mancher",
|
|
360
|
+
"manches",
|
|
361
|
+
"mann",
|
|
362
|
+
"mehr",
|
|
363
|
+
"mein",
|
|
364
|
+
"meine",
|
|
365
|
+
"meinem",
|
|
366
|
+
"meinen",
|
|
367
|
+
"meiner",
|
|
368
|
+
"meines",
|
|
369
|
+
"mensch",
|
|
370
|
+
"menschen",
|
|
371
|
+
"mich",
|
|
372
|
+
"mir",
|
|
373
|
+
"mit",
|
|
374
|
+
"mittel",
|
|
375
|
+
"mochte",
|
|
376
|
+
"mochten",
|
|
377
|
+
"morgen",
|
|
378
|
+
"muss",
|
|
379
|
+
"musst",
|
|
380
|
+
"musste",
|
|
381
|
+
"mussten",
|
|
382
|
+
"muß",
|
|
383
|
+
"mußt",
|
|
384
|
+
"möchte",
|
|
385
|
+
"mögen",
|
|
386
|
+
"möglich",
|
|
387
|
+
"mögt",
|
|
388
|
+
"müssen",
|
|
389
|
+
"müsst",
|
|
390
|
+
"müßt",
|
|
391
|
+
"n",
|
|
392
|
+
"na",
|
|
393
|
+
"nach",
|
|
394
|
+
"nachdem",
|
|
395
|
+
"nahm",
|
|
396
|
+
"natürlich",
|
|
397
|
+
"neben",
|
|
398
|
+
"nein",
|
|
399
|
+
"neue",
|
|
400
|
+
"neuen",
|
|
401
|
+
"neun",
|
|
402
|
+
"neunte",
|
|
403
|
+
"neunten",
|
|
404
|
+
"neunter",
|
|
405
|
+
"neuntes",
|
|
406
|
+
"nicht",
|
|
407
|
+
"nichts",
|
|
408
|
+
"nie",
|
|
409
|
+
"niemand",
|
|
410
|
+
"niemandem",
|
|
411
|
+
"niemanden",
|
|
412
|
+
"noch",
|
|
413
|
+
"nun",
|
|
414
|
+
"nur",
|
|
415
|
+
"o",
|
|
416
|
+
"ob",
|
|
417
|
+
"oben",
|
|
418
|
+
"oder",
|
|
419
|
+
"offen",
|
|
420
|
+
"oft",
|
|
421
|
+
"ohne",
|
|
422
|
+
"ordnung",
|
|
423
|
+
"p",
|
|
424
|
+
"q",
|
|
425
|
+
"r",
|
|
426
|
+
"recht",
|
|
427
|
+
"rechte",
|
|
428
|
+
"rechten",
|
|
429
|
+
"rechter",
|
|
430
|
+
"rechtes",
|
|
431
|
+
"richtig",
|
|
432
|
+
"rund",
|
|
433
|
+
"s",
|
|
434
|
+
"sa",
|
|
435
|
+
"sache",
|
|
436
|
+
"sagt",
|
|
437
|
+
"sagte",
|
|
438
|
+
"sah",
|
|
439
|
+
"satt",
|
|
440
|
+
"schlecht",
|
|
441
|
+
"schluss",
|
|
442
|
+
"schon",
|
|
443
|
+
"sechs",
|
|
444
|
+
"sechste",
|
|
445
|
+
"sechsten",
|
|
446
|
+
"sechster",
|
|
447
|
+
"sechstes",
|
|
448
|
+
"sehr",
|
|
449
|
+
"sei",
|
|
450
|
+
"seid",
|
|
451
|
+
"seien",
|
|
452
|
+
"sein",
|
|
453
|
+
"seine",
|
|
454
|
+
"seinem",
|
|
455
|
+
"seinen",
|
|
456
|
+
"seiner",
|
|
457
|
+
"seines",
|
|
458
|
+
"seit",
|
|
459
|
+
"seitdem",
|
|
460
|
+
"selbst",
|
|
461
|
+
"sich",
|
|
462
|
+
"sie",
|
|
463
|
+
"sieben",
|
|
464
|
+
"siebente",
|
|
465
|
+
"siebenten",
|
|
466
|
+
"siebenter",
|
|
467
|
+
"siebentes",
|
|
468
|
+
"sind",
|
|
469
|
+
"so",
|
|
470
|
+
"solang",
|
|
471
|
+
"solche",
|
|
472
|
+
"solchem",
|
|
473
|
+
"solchen",
|
|
474
|
+
"solcher",
|
|
475
|
+
"solches",
|
|
476
|
+
"soll",
|
|
477
|
+
"sollen",
|
|
478
|
+
"sollst",
|
|
479
|
+
"sollt",
|
|
480
|
+
"sollte",
|
|
481
|
+
"sollten",
|
|
482
|
+
"sondern",
|
|
483
|
+
"sonst",
|
|
484
|
+
"soweit",
|
|
485
|
+
"sowie",
|
|
486
|
+
"später",
|
|
487
|
+
"startseite",
|
|
488
|
+
"statt",
|
|
489
|
+
"steht",
|
|
490
|
+
"suche",
|
|
491
|
+
"t",
|
|
492
|
+
"tag",
|
|
493
|
+
"tage",
|
|
494
|
+
"tagen",
|
|
495
|
+
"tat",
|
|
496
|
+
"teil",
|
|
497
|
+
"tel",
|
|
498
|
+
"tritt",
|
|
499
|
+
"trotzdem",
|
|
500
|
+
"tun",
|
|
501
|
+
"u",
|
|
502
|
+
"uhr",
|
|
503
|
+
"um",
|
|
504
|
+
"und",
|
|
505
|
+
"uns",
|
|
506
|
+
"unse",
|
|
507
|
+
"unsem",
|
|
508
|
+
"unsen",
|
|
509
|
+
"unser",
|
|
510
|
+
"unsere",
|
|
511
|
+
"unserer",
|
|
512
|
+
"unses",
|
|
513
|
+
"unter",
|
|
514
|
+
"v",
|
|
515
|
+
"vergangenen",
|
|
516
|
+
"viel",
|
|
517
|
+
"viele",
|
|
518
|
+
"vielem",
|
|
519
|
+
"vielen",
|
|
520
|
+
"vielleicht",
|
|
521
|
+
"vier",
|
|
522
|
+
"vierte",
|
|
523
|
+
"vierten",
|
|
524
|
+
"vierter",
|
|
525
|
+
"viertes",
|
|
526
|
+
"vom",
|
|
527
|
+
"von",
|
|
528
|
+
"vor",
|
|
529
|
+
"w",
|
|
530
|
+
"wahr",
|
|
531
|
+
"wann",
|
|
532
|
+
"war",
|
|
533
|
+
"waren",
|
|
534
|
+
"warst",
|
|
535
|
+
"wart",
|
|
536
|
+
"warum",
|
|
537
|
+
"was",
|
|
538
|
+
"weg",
|
|
539
|
+
"wegen",
|
|
540
|
+
"weil",
|
|
541
|
+
"weit",
|
|
542
|
+
"weiter",
|
|
543
|
+
"weitere",
|
|
544
|
+
"weiteren",
|
|
545
|
+
"weiteres",
|
|
546
|
+
"welche",
|
|
547
|
+
"welchem",
|
|
548
|
+
"welchen",
|
|
549
|
+
"welcher",
|
|
550
|
+
"welches",
|
|
551
|
+
"wem",
|
|
552
|
+
"wen",
|
|
553
|
+
"wenig",
|
|
554
|
+
"wenige",
|
|
555
|
+
"weniger",
|
|
556
|
+
"weniges",
|
|
557
|
+
"wenigstens",
|
|
558
|
+
"wenn",
|
|
559
|
+
"wer",
|
|
560
|
+
"werde",
|
|
561
|
+
"werden",
|
|
562
|
+
"werdet",
|
|
563
|
+
"weshalb",
|
|
564
|
+
"wessen",
|
|
565
|
+
"wie",
|
|
566
|
+
"wieder",
|
|
567
|
+
"wieso",
|
|
568
|
+
"will",
|
|
569
|
+
"willst",
|
|
570
|
+
"wir",
|
|
571
|
+
"wird",
|
|
572
|
+
"wirklich",
|
|
573
|
+
"wirst",
|
|
574
|
+
"wissen",
|
|
575
|
+
"wo",
|
|
576
|
+
"woher",
|
|
577
|
+
"wohin",
|
|
578
|
+
"wohl",
|
|
579
|
+
"wollen",
|
|
580
|
+
"wollt",
|
|
581
|
+
"wollte",
|
|
582
|
+
"wollten",
|
|
583
|
+
"worden",
|
|
584
|
+
"wurde",
|
|
585
|
+
"wurden",
|
|
586
|
+
"während",
|
|
587
|
+
"währenddem",
|
|
588
|
+
"währenddessen",
|
|
589
|
+
"wäre",
|
|
590
|
+
"würde",
|
|
591
|
+
"würden",
|
|
592
|
+
"x",
|
|
593
|
+
"y",
|
|
594
|
+
"z",
|
|
595
|
+
"z.b",
|
|
596
|
+
"zehn",
|
|
597
|
+
"zehnte",
|
|
598
|
+
"zehnten",
|
|
599
|
+
"zehnter",
|
|
600
|
+
"zehntes",
|
|
601
|
+
"zeit",
|
|
602
|
+
"zu",
|
|
603
|
+
"zuerst",
|
|
604
|
+
"zugleich",
|
|
605
|
+
"zum",
|
|
606
|
+
"zunächst",
|
|
607
|
+
"zur",
|
|
608
|
+
"zurück",
|
|
609
|
+
"zusammen",
|
|
610
|
+
"zwanzig",
|
|
611
|
+
"zwar",
|
|
612
|
+
"zwei",
|
|
613
|
+
"zweite",
|
|
614
|
+
"zweiten",
|
|
615
|
+
"zweiter",
|
|
616
|
+
"zweites",
|
|
617
|
+
"zwischen",
|
|
618
|
+
"zwölf",
|
|
619
|
+
"über",
|
|
620
|
+
"überhaupt",
|
|
621
|
+
"übrigens"
|
|
622
|
+
]
|