kreuzberg 4.0.0.pre.rc.6
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 +7 -0
- data/.gitignore +14 -0
- data/.rspec +3 -0
- data/.rubocop.yaml +1 -0
- data/.rubocop.yml +538 -0
- data/Gemfile +8 -0
- data/Gemfile.lock +157 -0
- data/README.md +426 -0
- data/Rakefile +25 -0
- data/Steepfile +47 -0
- data/examples/async_patterns.rb +341 -0
- data/ext/kreuzberg_rb/extconf.rb +45 -0
- data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +44 -0
- data/ext/kreuzberg_rb/native/README.md +425 -0
- data/ext/kreuzberg_rb/native/build.rs +15 -0
- data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
- data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
- data/ext/kreuzberg_rb/native/include/strings.h +20 -0
- data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
- data/ext/kreuzberg_rb/native/src/lib.rs +2998 -0
- data/extconf.rb +28 -0
- data/kreuzberg.gemspec +148 -0
- data/lib/kreuzberg/api_proxy.rb +142 -0
- data/lib/kreuzberg/cache_api.rb +46 -0
- data/lib/kreuzberg/cli.rb +55 -0
- data/lib/kreuzberg/cli_proxy.rb +127 -0
- data/lib/kreuzberg/config.rb +691 -0
- data/lib/kreuzberg/error_context.rb +32 -0
- data/lib/kreuzberg/errors.rb +118 -0
- data/lib/kreuzberg/extraction_api.rb +85 -0
- data/lib/kreuzberg/mcp_proxy.rb +186 -0
- data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
- data/lib/kreuzberg/post_processor_protocol.rb +86 -0
- data/lib/kreuzberg/result.rb +216 -0
- data/lib/kreuzberg/setup_lib_path.rb +80 -0
- data/lib/kreuzberg/validator_protocol.rb +89 -0
- data/lib/kreuzberg/version.rb +5 -0
- data/lib/kreuzberg.rb +103 -0
- data/sig/kreuzberg/internal.rbs +184 -0
- data/sig/kreuzberg.rbs +520 -0
- data/spec/binding/cache_spec.rb +227 -0
- data/spec/binding/cli_proxy_spec.rb +85 -0
- data/spec/binding/cli_spec.rb +55 -0
- data/spec/binding/config_spec.rb +345 -0
- data/spec/binding/config_validation_spec.rb +283 -0
- data/spec/binding/error_handling_spec.rb +213 -0
- data/spec/binding/errors_spec.rb +66 -0
- data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
- data/spec/binding/plugins/postprocessor_spec.rb +269 -0
- data/spec/binding/plugins/validator_spec.rb +274 -0
- data/spec/fixtures/config.toml +39 -0
- data/spec/fixtures/config.yaml +41 -0
- data/spec/fixtures/invalid_config.toml +4 -0
- data/spec/smoke/package_spec.rb +178 -0
- data/spec/spec_helper.rb +42 -0
- data/vendor/kreuzberg/Cargo.toml +204 -0
- data/vendor/kreuzberg/README.md +175 -0
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
- data/vendor/kreuzberg/build.rs +474 -0
- data/vendor/kreuzberg/src/api/error.rs +81 -0
- data/vendor/kreuzberg/src/api/handlers.rs +199 -0
- data/vendor/kreuzberg/src/api/mod.rs +79 -0
- data/vendor/kreuzberg/src/api/server.rs +353 -0
- data/vendor/kreuzberg/src/api/types.rs +170 -0
- data/vendor/kreuzberg/src/cache/mod.rs +1167 -0
- data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -0
- data/vendor/kreuzberg/src/core/config.rs +1032 -0
- data/vendor/kreuzberg/src/core/extractor.rs +1024 -0
- data/vendor/kreuzberg/src/core/io.rs +329 -0
- data/vendor/kreuzberg/src/core/mime.rs +605 -0
- data/vendor/kreuzberg/src/core/mod.rs +45 -0
- data/vendor/kreuzberg/src/core/pipeline.rs +984 -0
- data/vendor/kreuzberg/src/embeddings.rs +432 -0
- data/vendor/kreuzberg/src/error.rs +431 -0
- data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
- data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
- data/vendor/kreuzberg/src/extraction/email.rs +854 -0
- data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
- data/vendor/kreuzberg/src/extraction/html.rs +553 -0
- data/vendor/kreuzberg/src/extraction/image.rs +368 -0
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -0
- data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +81 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -0
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
- data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
- data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
- data/vendor/kreuzberg/src/extraction/table.rs +328 -0
- data/vendor/kreuzberg/src/extraction/text.rs +269 -0
- data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
- data/vendor/kreuzberg/src/extractors/archive.rs +446 -0
- 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 -0
- data/vendor/kreuzberg/src/extractors/email.rs +143 -0
- data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +343 -0
- 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 -0
- data/vendor/kreuzberg/src/extractors/image.rs +198 -0
- 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 -0
- 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 -0
- data/vendor/kreuzberg/src/extractors/pptx.rs +248 -0
- 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 -0
- data/vendor/kreuzberg/src/extractors/text.rs +260 -0
- data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +135 -0
- data/vendor/kreuzberg/src/image/dpi.rs +164 -0
- data/vendor/kreuzberg/src/image/mod.rs +6 -0
- data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
- data/vendor/kreuzberg/src/image/resize.rs +89 -0
- data/vendor/kreuzberg/src/keywords/config.rs +154 -0
- data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
- data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -0
- data/vendor/kreuzberg/src/keywords/types.rs +68 -0
- data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
- data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
- data/vendor/kreuzberg/src/lib.rs +105 -0
- data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
- data/vendor/kreuzberg/src/mcp/server.rs +1968 -0
- data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
- data/vendor/kreuzberg/src/ocr/error.rs +37 -0
- data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
- data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
- data/vendor/kreuzberg/src/ocr/processor.rs +863 -0
- data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
- data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
- data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
- data/vendor/kreuzberg/src/ocr/types.rs +393 -0
- data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
- data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
- data/vendor/kreuzberg/src/panic_context.rs +154 -0
- data/vendor/kreuzberg/src/pdf/error.rs +122 -0
- data/vendor/kreuzberg/src/pdf/images.rs +139 -0
- data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
- data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
- data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
- data/vendor/kreuzberg/src/pdf/table.rs +393 -0
- data/vendor/kreuzberg/src/pdf/text.rs +158 -0
- data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -0
- data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
- data/vendor/kreuzberg/src/plugins/ocr.rs +620 -0
- data/vendor/kreuzberg/src/plugins/processor.rs +642 -0
- data/vendor/kreuzberg/src/plugins/registry.rs +1337 -0
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
- data/vendor/kreuzberg/src/plugins/validator.rs +956 -0
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
- data/vendor/kreuzberg/src/text/mod.rs +19 -0
- data/vendor/kreuzberg/src/text/quality.rs +697 -0
- data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
- data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
- data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
- data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
- data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
- data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
- data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
- data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
- data/vendor/kreuzberg/src/types.rs +903 -0
- data/vendor/kreuzberg/src/utils/mod.rs +17 -0
- data/vendor/kreuzberg/src/utils/quality.rs +959 -0
- data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
- data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
- data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
- data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
- data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
- data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
- data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
- data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
- data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
- data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
- data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
- data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
- data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
- data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
- data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
- data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
- data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
- data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
- data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
- data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
- data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
- data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
- data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
- data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
- data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
- data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
- data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
- data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
- data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
- data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
- data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
- data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
- data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
- data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
- data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
- data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
- data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
- data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
- data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
- data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
- data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
- data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
- data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
- data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
- data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
- data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
- data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
- data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
- data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
- data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
- data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
- data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
- data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
- data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
- data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
- data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
- data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
- data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
- data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
- data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
- data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
- data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
- data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
- data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
- data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
- data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
- data/vendor/kreuzberg/tests/api_tests.rs +966 -0
- data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
- data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +316 -0
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -0
- data/vendor/kreuzberg/tests/config_features.rs +598 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -0
- data/vendor/kreuzberg/tests/core_integration.rs +510 -0
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -0
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -0
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
- data/vendor/kreuzberg/tests/email_integration.rs +325 -0
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
- data/vendor/kreuzberg/tests/error_handling.rs +393 -0
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
- data/vendor/kreuzberg/tests/format_integration.rs +159 -0
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
- data/vendor/kreuzberg/tests/image_integration.rs +253 -0
- 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 -0
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
- 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 -0
- data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
- data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
- data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
- 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 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -0
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -0
- data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -0
- 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 -0
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
- data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
- 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 -0
- 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 +536 -0
|
@@ -0,0 +1,562 @@
|
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"acerca",
|
|
4
|
+
"adeus",
|
|
5
|
+
"agora",
|
|
6
|
+
"ainda",
|
|
7
|
+
"alem",
|
|
8
|
+
"algmas",
|
|
9
|
+
"algo",
|
|
10
|
+
"algumas",
|
|
11
|
+
"alguns",
|
|
12
|
+
"ali",
|
|
13
|
+
"além",
|
|
14
|
+
"ambas",
|
|
15
|
+
"ambos",
|
|
16
|
+
"ano",
|
|
17
|
+
"anos",
|
|
18
|
+
"antes",
|
|
19
|
+
"ao",
|
|
20
|
+
"aonde",
|
|
21
|
+
"aos",
|
|
22
|
+
"apenas",
|
|
23
|
+
"apoio",
|
|
24
|
+
"apontar",
|
|
25
|
+
"apos",
|
|
26
|
+
"após",
|
|
27
|
+
"aquela",
|
|
28
|
+
"aquelas",
|
|
29
|
+
"aquele",
|
|
30
|
+
"aqueles",
|
|
31
|
+
"aqui",
|
|
32
|
+
"aquilo",
|
|
33
|
+
"as",
|
|
34
|
+
"assim",
|
|
35
|
+
"através",
|
|
36
|
+
"atrás",
|
|
37
|
+
"até",
|
|
38
|
+
"aí",
|
|
39
|
+
"baixo",
|
|
40
|
+
"bastante",
|
|
41
|
+
"bem",
|
|
42
|
+
"boa",
|
|
43
|
+
"boas",
|
|
44
|
+
"bom",
|
|
45
|
+
"bons",
|
|
46
|
+
"breve",
|
|
47
|
+
"cada",
|
|
48
|
+
"caminho",
|
|
49
|
+
"catorze",
|
|
50
|
+
"cedo",
|
|
51
|
+
"cento",
|
|
52
|
+
"certamente",
|
|
53
|
+
"certeza",
|
|
54
|
+
"cima",
|
|
55
|
+
"cinco",
|
|
56
|
+
"coisa",
|
|
57
|
+
"com",
|
|
58
|
+
"como",
|
|
59
|
+
"comprido",
|
|
60
|
+
"conhecido",
|
|
61
|
+
"conselho",
|
|
62
|
+
"contra",
|
|
63
|
+
"contudo",
|
|
64
|
+
"corrente",
|
|
65
|
+
"cuja",
|
|
66
|
+
"cujas",
|
|
67
|
+
"cujo",
|
|
68
|
+
"cujos",
|
|
69
|
+
"custa",
|
|
70
|
+
"cá",
|
|
71
|
+
"da",
|
|
72
|
+
"daquela",
|
|
73
|
+
"daquelas",
|
|
74
|
+
"daquele",
|
|
75
|
+
"daqueles",
|
|
76
|
+
"dar",
|
|
77
|
+
"das",
|
|
78
|
+
"de",
|
|
79
|
+
"debaixo",
|
|
80
|
+
"dela",
|
|
81
|
+
"delas",
|
|
82
|
+
"dele",
|
|
83
|
+
"deles",
|
|
84
|
+
"demais",
|
|
85
|
+
"dentro",
|
|
86
|
+
"depois",
|
|
87
|
+
"desde",
|
|
88
|
+
"desligado",
|
|
89
|
+
"dessa",
|
|
90
|
+
"dessas",
|
|
91
|
+
"desse",
|
|
92
|
+
"desses",
|
|
93
|
+
"desta",
|
|
94
|
+
"destas",
|
|
95
|
+
"deste",
|
|
96
|
+
"destes",
|
|
97
|
+
"deve",
|
|
98
|
+
"devem",
|
|
99
|
+
"deverá",
|
|
100
|
+
"dez",
|
|
101
|
+
"dezanove",
|
|
102
|
+
"dezasseis",
|
|
103
|
+
"dezassete",
|
|
104
|
+
"dezoito",
|
|
105
|
+
"dia",
|
|
106
|
+
"diante",
|
|
107
|
+
"direita",
|
|
108
|
+
"dispoe",
|
|
109
|
+
"dispoem",
|
|
110
|
+
"diversa",
|
|
111
|
+
"diversas",
|
|
112
|
+
"diversos",
|
|
113
|
+
"diz",
|
|
114
|
+
"dizem",
|
|
115
|
+
"dizer",
|
|
116
|
+
"do",
|
|
117
|
+
"dois",
|
|
118
|
+
"dos",
|
|
119
|
+
"doze",
|
|
120
|
+
"duas",
|
|
121
|
+
"durante",
|
|
122
|
+
"dá",
|
|
123
|
+
"dão",
|
|
124
|
+
"dúvida",
|
|
125
|
+
"e",
|
|
126
|
+
"ela",
|
|
127
|
+
"elas",
|
|
128
|
+
"ele",
|
|
129
|
+
"eles",
|
|
130
|
+
"em",
|
|
131
|
+
"embora",
|
|
132
|
+
"enquanto",
|
|
133
|
+
"entao",
|
|
134
|
+
"entre",
|
|
135
|
+
"então",
|
|
136
|
+
"era",
|
|
137
|
+
"eram",
|
|
138
|
+
"essa",
|
|
139
|
+
"essas",
|
|
140
|
+
"esse",
|
|
141
|
+
"esses",
|
|
142
|
+
"esta",
|
|
143
|
+
"estado",
|
|
144
|
+
"estamos",
|
|
145
|
+
"estar",
|
|
146
|
+
"estará",
|
|
147
|
+
"estas",
|
|
148
|
+
"estava",
|
|
149
|
+
"estavam",
|
|
150
|
+
"este",
|
|
151
|
+
"esteja",
|
|
152
|
+
"estejam",
|
|
153
|
+
"estejamos",
|
|
154
|
+
"estes",
|
|
155
|
+
"esteve",
|
|
156
|
+
"estive",
|
|
157
|
+
"estivemos",
|
|
158
|
+
"estiver",
|
|
159
|
+
"estivera",
|
|
160
|
+
"estiveram",
|
|
161
|
+
"estiverem",
|
|
162
|
+
"estivermos",
|
|
163
|
+
"estivesse",
|
|
164
|
+
"estivessem",
|
|
165
|
+
"estiveste",
|
|
166
|
+
"estivestes",
|
|
167
|
+
"estivéramos",
|
|
168
|
+
"estivéssemos",
|
|
169
|
+
"estou",
|
|
170
|
+
"está",
|
|
171
|
+
"estás",
|
|
172
|
+
"estávamos",
|
|
173
|
+
"estão",
|
|
174
|
+
"eu",
|
|
175
|
+
"exemplo",
|
|
176
|
+
"falta",
|
|
177
|
+
"fará",
|
|
178
|
+
"favor",
|
|
179
|
+
"faz",
|
|
180
|
+
"fazeis",
|
|
181
|
+
"fazem",
|
|
182
|
+
"fazemos",
|
|
183
|
+
"fazer",
|
|
184
|
+
"fazes",
|
|
185
|
+
"fazia",
|
|
186
|
+
"faço",
|
|
187
|
+
"fez",
|
|
188
|
+
"fim",
|
|
189
|
+
"final",
|
|
190
|
+
"foi",
|
|
191
|
+
"fomos",
|
|
192
|
+
"for",
|
|
193
|
+
"fora",
|
|
194
|
+
"foram",
|
|
195
|
+
"forem",
|
|
196
|
+
"forma",
|
|
197
|
+
"formos",
|
|
198
|
+
"fosse",
|
|
199
|
+
"fossem",
|
|
200
|
+
"foste",
|
|
201
|
+
"fostes",
|
|
202
|
+
"fui",
|
|
203
|
+
"fôramos",
|
|
204
|
+
"fôssemos",
|
|
205
|
+
"geral",
|
|
206
|
+
"grande",
|
|
207
|
+
"grandes",
|
|
208
|
+
"grupo",
|
|
209
|
+
"ha",
|
|
210
|
+
"haja",
|
|
211
|
+
"hajam",
|
|
212
|
+
"hajamos",
|
|
213
|
+
"havemos",
|
|
214
|
+
"havia",
|
|
215
|
+
"hei",
|
|
216
|
+
"hoje",
|
|
217
|
+
"hora",
|
|
218
|
+
"horas",
|
|
219
|
+
"houve",
|
|
220
|
+
"houvemos",
|
|
221
|
+
"houver",
|
|
222
|
+
"houvera",
|
|
223
|
+
"houveram",
|
|
224
|
+
"houverei",
|
|
225
|
+
"houverem",
|
|
226
|
+
"houveremos",
|
|
227
|
+
"houveria",
|
|
228
|
+
"houveriam",
|
|
229
|
+
"houvermos",
|
|
230
|
+
"houverá",
|
|
231
|
+
"houverão",
|
|
232
|
+
"houveríamos",
|
|
233
|
+
"houvesse",
|
|
234
|
+
"houvessem",
|
|
235
|
+
"houvéramos",
|
|
236
|
+
"houvéssemos",
|
|
237
|
+
"há",
|
|
238
|
+
"hão",
|
|
239
|
+
"iniciar",
|
|
240
|
+
"inicio",
|
|
241
|
+
"ir",
|
|
242
|
+
"irá",
|
|
243
|
+
"isso",
|
|
244
|
+
"ista",
|
|
245
|
+
"iste",
|
|
246
|
+
"isto",
|
|
247
|
+
"já",
|
|
248
|
+
"lado",
|
|
249
|
+
"lhe",
|
|
250
|
+
"lhes",
|
|
251
|
+
"ligado",
|
|
252
|
+
"local",
|
|
253
|
+
"logo",
|
|
254
|
+
"longe",
|
|
255
|
+
"lugar",
|
|
256
|
+
"lá",
|
|
257
|
+
"maior",
|
|
258
|
+
"maioria",
|
|
259
|
+
"maiorias",
|
|
260
|
+
"mais",
|
|
261
|
+
"mal",
|
|
262
|
+
"mas",
|
|
263
|
+
"me",
|
|
264
|
+
"mediante",
|
|
265
|
+
"meio",
|
|
266
|
+
"menor",
|
|
267
|
+
"menos",
|
|
268
|
+
"meses",
|
|
269
|
+
"mesma",
|
|
270
|
+
"mesmas",
|
|
271
|
+
"mesmo",
|
|
272
|
+
"mesmos",
|
|
273
|
+
"meu",
|
|
274
|
+
"meus",
|
|
275
|
+
"mil",
|
|
276
|
+
"minha",
|
|
277
|
+
"minhas",
|
|
278
|
+
"momento",
|
|
279
|
+
"muito",
|
|
280
|
+
"muitos",
|
|
281
|
+
"máximo",
|
|
282
|
+
"mês",
|
|
283
|
+
"na",
|
|
284
|
+
"nada",
|
|
285
|
+
"nao",
|
|
286
|
+
"naquela",
|
|
287
|
+
"naquelas",
|
|
288
|
+
"naquele",
|
|
289
|
+
"naqueles",
|
|
290
|
+
"nas",
|
|
291
|
+
"nem",
|
|
292
|
+
"nenhuma",
|
|
293
|
+
"nessa",
|
|
294
|
+
"nessas",
|
|
295
|
+
"nesse",
|
|
296
|
+
"nesses",
|
|
297
|
+
"nesta",
|
|
298
|
+
"nestas",
|
|
299
|
+
"neste",
|
|
300
|
+
"nestes",
|
|
301
|
+
"no",
|
|
302
|
+
"noite",
|
|
303
|
+
"nome",
|
|
304
|
+
"nos",
|
|
305
|
+
"nossa",
|
|
306
|
+
"nossas",
|
|
307
|
+
"nosso",
|
|
308
|
+
"nossos",
|
|
309
|
+
"nova",
|
|
310
|
+
"novas",
|
|
311
|
+
"nove",
|
|
312
|
+
"novo",
|
|
313
|
+
"novos",
|
|
314
|
+
"num",
|
|
315
|
+
"numa",
|
|
316
|
+
"numas",
|
|
317
|
+
"nunca",
|
|
318
|
+
"nuns",
|
|
319
|
+
"não",
|
|
320
|
+
"nível",
|
|
321
|
+
"nós",
|
|
322
|
+
"número",
|
|
323
|
+
"o",
|
|
324
|
+
"obra",
|
|
325
|
+
"obrigada",
|
|
326
|
+
"obrigado",
|
|
327
|
+
"oitava",
|
|
328
|
+
"oitavo",
|
|
329
|
+
"oito",
|
|
330
|
+
"onde",
|
|
331
|
+
"ontem",
|
|
332
|
+
"onze",
|
|
333
|
+
"os",
|
|
334
|
+
"ou",
|
|
335
|
+
"outra",
|
|
336
|
+
"outras",
|
|
337
|
+
"outro",
|
|
338
|
+
"outros",
|
|
339
|
+
"para",
|
|
340
|
+
"parece",
|
|
341
|
+
"parte",
|
|
342
|
+
"partir",
|
|
343
|
+
"paucas",
|
|
344
|
+
"pegar",
|
|
345
|
+
"pela",
|
|
346
|
+
"pelas",
|
|
347
|
+
"pelo",
|
|
348
|
+
"pelos",
|
|
349
|
+
"perante",
|
|
350
|
+
"perto",
|
|
351
|
+
"pessoas",
|
|
352
|
+
"pode",
|
|
353
|
+
"podem",
|
|
354
|
+
"poder",
|
|
355
|
+
"poderá",
|
|
356
|
+
"podia",
|
|
357
|
+
"pois",
|
|
358
|
+
"ponto",
|
|
359
|
+
"pontos",
|
|
360
|
+
"por",
|
|
361
|
+
"porque",
|
|
362
|
+
"porquê",
|
|
363
|
+
"portanto",
|
|
364
|
+
"posição",
|
|
365
|
+
"possivelmente",
|
|
366
|
+
"posso",
|
|
367
|
+
"possível",
|
|
368
|
+
"pouca",
|
|
369
|
+
"pouco",
|
|
370
|
+
"poucos",
|
|
371
|
+
"povo",
|
|
372
|
+
"primeira",
|
|
373
|
+
"primeiras",
|
|
374
|
+
"primeiro",
|
|
375
|
+
"primeiros",
|
|
376
|
+
"promeiro",
|
|
377
|
+
"propios",
|
|
378
|
+
"proprio",
|
|
379
|
+
"própria",
|
|
380
|
+
"próprias",
|
|
381
|
+
"próprio",
|
|
382
|
+
"próprios",
|
|
383
|
+
"próxima",
|
|
384
|
+
"próximas",
|
|
385
|
+
"próximo",
|
|
386
|
+
"próximos",
|
|
387
|
+
"puderam",
|
|
388
|
+
"pôde",
|
|
389
|
+
"põe",
|
|
390
|
+
"põem",
|
|
391
|
+
"quais",
|
|
392
|
+
"qual",
|
|
393
|
+
"qualquer",
|
|
394
|
+
"quando",
|
|
395
|
+
"quanto",
|
|
396
|
+
"quarta",
|
|
397
|
+
"quarto",
|
|
398
|
+
"quatro",
|
|
399
|
+
"que",
|
|
400
|
+
"quem",
|
|
401
|
+
"quer",
|
|
402
|
+
"quereis",
|
|
403
|
+
"querem",
|
|
404
|
+
"queremas",
|
|
405
|
+
"queres",
|
|
406
|
+
"quero",
|
|
407
|
+
"questão",
|
|
408
|
+
"quieto",
|
|
409
|
+
"quinta",
|
|
410
|
+
"quinto",
|
|
411
|
+
"quinze",
|
|
412
|
+
"quáis",
|
|
413
|
+
"quê",
|
|
414
|
+
"relação",
|
|
415
|
+
"sabe",
|
|
416
|
+
"sabem",
|
|
417
|
+
"saber",
|
|
418
|
+
"se",
|
|
419
|
+
"segunda",
|
|
420
|
+
"segundo",
|
|
421
|
+
"sei",
|
|
422
|
+
"seis",
|
|
423
|
+
"seja",
|
|
424
|
+
"sejam",
|
|
425
|
+
"sejamos",
|
|
426
|
+
"sem",
|
|
427
|
+
"sempre",
|
|
428
|
+
"sendo",
|
|
429
|
+
"ser",
|
|
430
|
+
"serei",
|
|
431
|
+
"seremos",
|
|
432
|
+
"seria",
|
|
433
|
+
"seriam",
|
|
434
|
+
"será",
|
|
435
|
+
"serão",
|
|
436
|
+
"seríamos",
|
|
437
|
+
"sete",
|
|
438
|
+
"seu",
|
|
439
|
+
"seus",
|
|
440
|
+
"sexta",
|
|
441
|
+
"sexto",
|
|
442
|
+
"sim",
|
|
443
|
+
"sistema",
|
|
444
|
+
"sob",
|
|
445
|
+
"sobre",
|
|
446
|
+
"sois",
|
|
447
|
+
"somente",
|
|
448
|
+
"somos",
|
|
449
|
+
"sou",
|
|
450
|
+
"sua",
|
|
451
|
+
"suas",
|
|
452
|
+
"são",
|
|
453
|
+
"sétima",
|
|
454
|
+
"sétimo",
|
|
455
|
+
"só",
|
|
456
|
+
"tal",
|
|
457
|
+
"talvez",
|
|
458
|
+
"tambem",
|
|
459
|
+
"também",
|
|
460
|
+
"tanta",
|
|
461
|
+
"tantas",
|
|
462
|
+
"tanto",
|
|
463
|
+
"tarde",
|
|
464
|
+
"te",
|
|
465
|
+
"tem",
|
|
466
|
+
"temos",
|
|
467
|
+
"tempo",
|
|
468
|
+
"tendes",
|
|
469
|
+
"tenha",
|
|
470
|
+
"tenham",
|
|
471
|
+
"tenhamos",
|
|
472
|
+
"tenho",
|
|
473
|
+
"tens",
|
|
474
|
+
"tentar",
|
|
475
|
+
"tentaram",
|
|
476
|
+
"tente",
|
|
477
|
+
"tentei",
|
|
478
|
+
"ter",
|
|
479
|
+
"terceira",
|
|
480
|
+
"terceiro",
|
|
481
|
+
"terei",
|
|
482
|
+
"teremos",
|
|
483
|
+
"teria",
|
|
484
|
+
"teriam",
|
|
485
|
+
"terá",
|
|
486
|
+
"terão",
|
|
487
|
+
"teríamos",
|
|
488
|
+
"teu",
|
|
489
|
+
"teus",
|
|
490
|
+
"teve",
|
|
491
|
+
"tinha",
|
|
492
|
+
"tinham",
|
|
493
|
+
"tipo",
|
|
494
|
+
"tive",
|
|
495
|
+
"tivemos",
|
|
496
|
+
"tiver",
|
|
497
|
+
"tivera",
|
|
498
|
+
"tiveram",
|
|
499
|
+
"tiverem",
|
|
500
|
+
"tivermos",
|
|
501
|
+
"tivesse",
|
|
502
|
+
"tivessem",
|
|
503
|
+
"tiveste",
|
|
504
|
+
"tivestes",
|
|
505
|
+
"tivéramos",
|
|
506
|
+
"tivéssemos",
|
|
507
|
+
"toda",
|
|
508
|
+
"todas",
|
|
509
|
+
"todo",
|
|
510
|
+
"todos",
|
|
511
|
+
"trabalhar",
|
|
512
|
+
"trabalho",
|
|
513
|
+
"treze",
|
|
514
|
+
"três",
|
|
515
|
+
"tu",
|
|
516
|
+
"tua",
|
|
517
|
+
"tuas",
|
|
518
|
+
"tudo",
|
|
519
|
+
"tão",
|
|
520
|
+
"tém",
|
|
521
|
+
"têm",
|
|
522
|
+
"tínhamos",
|
|
523
|
+
"um",
|
|
524
|
+
"uma",
|
|
525
|
+
"umas",
|
|
526
|
+
"uns",
|
|
527
|
+
"usa",
|
|
528
|
+
"usar",
|
|
529
|
+
"vai",
|
|
530
|
+
"vais",
|
|
531
|
+
"valor",
|
|
532
|
+
"veja",
|
|
533
|
+
"vem",
|
|
534
|
+
"vens",
|
|
535
|
+
"ver",
|
|
536
|
+
"verdade",
|
|
537
|
+
"verdadeiro",
|
|
538
|
+
"vez",
|
|
539
|
+
"vezes",
|
|
540
|
+
"viagem",
|
|
541
|
+
"vindo",
|
|
542
|
+
"vinte",
|
|
543
|
+
"você",
|
|
544
|
+
"vocês",
|
|
545
|
+
"vos",
|
|
546
|
+
"vossa",
|
|
547
|
+
"vossas",
|
|
548
|
+
"vosso",
|
|
549
|
+
"vossos",
|
|
550
|
+
"vários",
|
|
551
|
+
"vão",
|
|
552
|
+
"vêm",
|
|
553
|
+
"vós",
|
|
554
|
+
"zero",
|
|
555
|
+
"à",
|
|
556
|
+
"às",
|
|
557
|
+
"área",
|
|
558
|
+
"é",
|
|
559
|
+
"éramos",
|
|
560
|
+
"és",
|
|
561
|
+
"último"
|
|
562
|
+
]
|