kreuzberg 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 +7 -0
- data/.gitignore +8 -0
- data/.rspec +3 -0
- data/.rubocop.yaml +534 -0
- data/Gemfile +9 -0
- data/Gemfile.lock +157 -0
- data/README.md +421 -0
- data/Rakefile +25 -0
- data/Steepfile +47 -0
- data/examples/async_patterns.rb +340 -0
- data/ext/kreuzberg_rb/extconf.rb +35 -0
- data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
- data/ext/kreuzberg_rb/native/README.md +425 -0
- data/ext/kreuzberg_rb/native/build.rs +17 -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 +2939 -0
- data/extconf.rb +28 -0
- data/kreuzberg.gemspec +105 -0
- data/lib/kreuzberg/api_proxy.rb +142 -0
- data/lib/kreuzberg/cache_api.rb +45 -0
- data/lib/kreuzberg/cli.rb +55 -0
- data/lib/kreuzberg/cli_proxy.rb +127 -0
- data/lib/kreuzberg/config.rb +684 -0
- data/lib/kreuzberg/errors.rb +50 -0
- data/lib/kreuzberg/extraction_api.rb +84 -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 +79 -0
- data/lib/kreuzberg/validator_protocol.rb +89 -0
- data/lib/kreuzberg/version.rb +5 -0
- data/lib/kreuzberg.rb +82 -0
- data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
- data/sig/kreuzberg/internal.rbs +184 -0
- data/sig/kreuzberg.rbs +468 -0
- data/spec/binding/cache_spec.rb +227 -0
- data/spec/binding/cli_proxy_spec.rb +87 -0
- data/spec/binding/cli_spec.rb +54 -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/examples.txt +104 -0
- data/spec/fixtures/config.toml +39 -0
- data/spec/fixtures/config.yaml +42 -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 +134 -0
- data/vendor/kreuzberg/README.md +175 -0
- data/vendor/kreuzberg/build.rs +460 -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/bin/profile_extract.rs +455 -0
- data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
- data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
- data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
- data/vendor/kreuzberg/src/core/config.rs +1032 -0
- data/vendor/kreuzberg/src/core/extractor.rs +903 -0
- data/vendor/kreuzberg/src/core/io.rs +327 -0
- data/vendor/kreuzberg/src/core/mime.rs +615 -0
- data/vendor/kreuzberg/src/core/mod.rs +42 -0
- data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
- data/vendor/kreuzberg/src/embeddings.rs +323 -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 +564 -0
- data/vendor/kreuzberg/src/extraction/mod.rs +77 -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 +128 -0
- 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/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 +425 -0
- data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
- data/vendor/kreuzberg/src/extractors/email.rs +129 -0
- data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
- data/vendor/kreuzberg/src/extractors/html.rs +410 -0
- data/vendor/kreuzberg/src/extractors/image.rs +195 -0
- data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
- data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
- data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
- data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
- data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
- data/vendor/kreuzberg/src/extractors/text.rs +242 -0
- data/vendor/kreuzberg/src/extractors/xml.rs +128 -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 +294 -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 +102 -0
- data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
- data/vendor/kreuzberg/src/mcp/server.rs +1966 -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 +847 -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/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 +420 -0
- data/vendor/kreuzberg/src/pdf/text.rs +161 -0
- data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
- data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
- data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
- data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
- data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
- data/vendor/kreuzberg/src/plugins/validator.rs +955 -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 +873 -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_tests.rs +966 -0
- data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
- data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
- data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
- data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
- data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
- data/vendor/kreuzberg/tests/config_features.rs +580 -0
- data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
- data/vendor/kreuzberg/tests/core_integration.rs +493 -0
- data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
- data/vendor/kreuzberg/tests/email_integration.rs +325 -0
- data/vendor/kreuzberg/tests/error_handling.rs +393 -0
- data/vendor/kreuzberg/tests/format_integration.rs +159 -0
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
- data/vendor/kreuzberg/tests/image_integration.rs +253 -0
- data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
- data/vendor/kreuzberg/tests/keywords_quality.rs +509 -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/pandoc_integration.rs +503 -0
- data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -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 +607 -0
- data/vendor/kreuzberg/tests/security_validation.rs +404 -0
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
- data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
- metadata +471 -0
|
@@ -0,0 +1,634 @@
|
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"abbastanza",
|
|
4
|
+
"abbia",
|
|
5
|
+
"abbiamo",
|
|
6
|
+
"abbiano",
|
|
7
|
+
"abbiate",
|
|
8
|
+
"accidenti",
|
|
9
|
+
"ad",
|
|
10
|
+
"adesso",
|
|
11
|
+
"affinché",
|
|
12
|
+
"agl",
|
|
13
|
+
"agli",
|
|
14
|
+
"ahime",
|
|
15
|
+
"ahimè",
|
|
16
|
+
"ai",
|
|
17
|
+
"al",
|
|
18
|
+
"alcuna",
|
|
19
|
+
"alcuni",
|
|
20
|
+
"alcuno",
|
|
21
|
+
"all",
|
|
22
|
+
"alla",
|
|
23
|
+
"alle",
|
|
24
|
+
"allo",
|
|
25
|
+
"allora",
|
|
26
|
+
"altre",
|
|
27
|
+
"altri",
|
|
28
|
+
"altrimenti",
|
|
29
|
+
"altro",
|
|
30
|
+
"altrove",
|
|
31
|
+
"altrui",
|
|
32
|
+
"anche",
|
|
33
|
+
"ancora",
|
|
34
|
+
"anni",
|
|
35
|
+
"anno",
|
|
36
|
+
"ansa",
|
|
37
|
+
"anticipo",
|
|
38
|
+
"assai",
|
|
39
|
+
"attesa",
|
|
40
|
+
"attraverso",
|
|
41
|
+
"avanti",
|
|
42
|
+
"avemmo",
|
|
43
|
+
"avendo",
|
|
44
|
+
"avente",
|
|
45
|
+
"aver",
|
|
46
|
+
"avere",
|
|
47
|
+
"averlo",
|
|
48
|
+
"avesse",
|
|
49
|
+
"avessero",
|
|
50
|
+
"avessi",
|
|
51
|
+
"avessimo",
|
|
52
|
+
"aveste",
|
|
53
|
+
"avesti",
|
|
54
|
+
"avete",
|
|
55
|
+
"aveva",
|
|
56
|
+
"avevamo",
|
|
57
|
+
"avevano",
|
|
58
|
+
"avevate",
|
|
59
|
+
"avevi",
|
|
60
|
+
"avevo",
|
|
61
|
+
"avrai",
|
|
62
|
+
"avranno",
|
|
63
|
+
"avrebbe",
|
|
64
|
+
"avrebbero",
|
|
65
|
+
"avrei",
|
|
66
|
+
"avremmo",
|
|
67
|
+
"avremo",
|
|
68
|
+
"avreste",
|
|
69
|
+
"avresti",
|
|
70
|
+
"avrete",
|
|
71
|
+
"avrà",
|
|
72
|
+
"avrò",
|
|
73
|
+
"avuta",
|
|
74
|
+
"avute",
|
|
75
|
+
"avuti",
|
|
76
|
+
"avuto",
|
|
77
|
+
"basta",
|
|
78
|
+
"ben",
|
|
79
|
+
"bene",
|
|
80
|
+
"benissimo",
|
|
81
|
+
"brava",
|
|
82
|
+
"bravo",
|
|
83
|
+
"buono",
|
|
84
|
+
"c",
|
|
85
|
+
"caso",
|
|
86
|
+
"cento",
|
|
87
|
+
"certa",
|
|
88
|
+
"certe",
|
|
89
|
+
"certi",
|
|
90
|
+
"certo",
|
|
91
|
+
"che",
|
|
92
|
+
"chi",
|
|
93
|
+
"chicchessia",
|
|
94
|
+
"chiunque",
|
|
95
|
+
"ci",
|
|
96
|
+
"ciascuna",
|
|
97
|
+
"ciascuno",
|
|
98
|
+
"cima",
|
|
99
|
+
"cinque",
|
|
100
|
+
"cio",
|
|
101
|
+
"cioe",
|
|
102
|
+
"cioè",
|
|
103
|
+
"circa",
|
|
104
|
+
"citta",
|
|
105
|
+
"città",
|
|
106
|
+
"ciò",
|
|
107
|
+
"co",
|
|
108
|
+
"codesta",
|
|
109
|
+
"codesti",
|
|
110
|
+
"codesto",
|
|
111
|
+
"cogli",
|
|
112
|
+
"coi",
|
|
113
|
+
"col",
|
|
114
|
+
"colei",
|
|
115
|
+
"coll",
|
|
116
|
+
"coloro",
|
|
117
|
+
"colui",
|
|
118
|
+
"come",
|
|
119
|
+
"cominci",
|
|
120
|
+
"comprare",
|
|
121
|
+
"comunque",
|
|
122
|
+
"con",
|
|
123
|
+
"concernente",
|
|
124
|
+
"conclusione",
|
|
125
|
+
"consecutivi",
|
|
126
|
+
"consecutivo",
|
|
127
|
+
"consiglio",
|
|
128
|
+
"contro",
|
|
129
|
+
"cortesia",
|
|
130
|
+
"cos",
|
|
131
|
+
"cosa",
|
|
132
|
+
"cosi",
|
|
133
|
+
"così",
|
|
134
|
+
"cui",
|
|
135
|
+
"d",
|
|
136
|
+
"da",
|
|
137
|
+
"dagl",
|
|
138
|
+
"dagli",
|
|
139
|
+
"dai",
|
|
140
|
+
"dal",
|
|
141
|
+
"dall",
|
|
142
|
+
"dalla",
|
|
143
|
+
"dalle",
|
|
144
|
+
"dallo",
|
|
145
|
+
"dappertutto",
|
|
146
|
+
"davanti",
|
|
147
|
+
"degl",
|
|
148
|
+
"degli",
|
|
149
|
+
"dei",
|
|
150
|
+
"del",
|
|
151
|
+
"dell",
|
|
152
|
+
"della",
|
|
153
|
+
"delle",
|
|
154
|
+
"dello",
|
|
155
|
+
"dentro",
|
|
156
|
+
"detto",
|
|
157
|
+
"deve",
|
|
158
|
+
"devo",
|
|
159
|
+
"di",
|
|
160
|
+
"dice",
|
|
161
|
+
"dietro",
|
|
162
|
+
"dire",
|
|
163
|
+
"dirimpetto",
|
|
164
|
+
"diventa",
|
|
165
|
+
"diventare",
|
|
166
|
+
"diventato",
|
|
167
|
+
"dopo",
|
|
168
|
+
"doppio",
|
|
169
|
+
"dov",
|
|
170
|
+
"dove",
|
|
171
|
+
"dovra",
|
|
172
|
+
"dovrà",
|
|
173
|
+
"dovunque",
|
|
174
|
+
"due",
|
|
175
|
+
"dunque",
|
|
176
|
+
"durante",
|
|
177
|
+
"e",
|
|
178
|
+
"ebbe",
|
|
179
|
+
"ebbero",
|
|
180
|
+
"ebbi",
|
|
181
|
+
"ecc",
|
|
182
|
+
"ecco",
|
|
183
|
+
"ed",
|
|
184
|
+
"effettivamente",
|
|
185
|
+
"egli",
|
|
186
|
+
"ella",
|
|
187
|
+
"entrambi",
|
|
188
|
+
"eppure",
|
|
189
|
+
"era",
|
|
190
|
+
"erano",
|
|
191
|
+
"eravamo",
|
|
192
|
+
"eravate",
|
|
193
|
+
"eri",
|
|
194
|
+
"ero",
|
|
195
|
+
"esempio",
|
|
196
|
+
"esse",
|
|
197
|
+
"essendo",
|
|
198
|
+
"esser",
|
|
199
|
+
"essere",
|
|
200
|
+
"essi",
|
|
201
|
+
"ex",
|
|
202
|
+
"fa",
|
|
203
|
+
"faccia",
|
|
204
|
+
"facciamo",
|
|
205
|
+
"facciano",
|
|
206
|
+
"facciate",
|
|
207
|
+
"faccio",
|
|
208
|
+
"facemmo",
|
|
209
|
+
"facendo",
|
|
210
|
+
"facesse",
|
|
211
|
+
"facessero",
|
|
212
|
+
"facessi",
|
|
213
|
+
"facessimo",
|
|
214
|
+
"faceste",
|
|
215
|
+
"facesti",
|
|
216
|
+
"faceva",
|
|
217
|
+
"facevamo",
|
|
218
|
+
"facevano",
|
|
219
|
+
"facevate",
|
|
220
|
+
"facevi",
|
|
221
|
+
"facevo",
|
|
222
|
+
"fai",
|
|
223
|
+
"fanno",
|
|
224
|
+
"farai",
|
|
225
|
+
"faranno",
|
|
226
|
+
"fare",
|
|
227
|
+
"farebbe",
|
|
228
|
+
"farebbero",
|
|
229
|
+
"farei",
|
|
230
|
+
"faremmo",
|
|
231
|
+
"faremo",
|
|
232
|
+
"fareste",
|
|
233
|
+
"faresti",
|
|
234
|
+
"farete",
|
|
235
|
+
"farà",
|
|
236
|
+
"farò",
|
|
237
|
+
"fatto",
|
|
238
|
+
"favore",
|
|
239
|
+
"fece",
|
|
240
|
+
"fecero",
|
|
241
|
+
"feci",
|
|
242
|
+
"fin",
|
|
243
|
+
"finalmente",
|
|
244
|
+
"finche",
|
|
245
|
+
"fine",
|
|
246
|
+
"fino",
|
|
247
|
+
"forse",
|
|
248
|
+
"forza",
|
|
249
|
+
"fosse",
|
|
250
|
+
"fossero",
|
|
251
|
+
"fossi",
|
|
252
|
+
"fossimo",
|
|
253
|
+
"foste",
|
|
254
|
+
"fosti",
|
|
255
|
+
"fra",
|
|
256
|
+
"frattempo",
|
|
257
|
+
"fu",
|
|
258
|
+
"fui",
|
|
259
|
+
"fummo",
|
|
260
|
+
"fuori",
|
|
261
|
+
"furono",
|
|
262
|
+
"futuro",
|
|
263
|
+
"generale",
|
|
264
|
+
"gente",
|
|
265
|
+
"gia",
|
|
266
|
+
"giacche",
|
|
267
|
+
"giorni",
|
|
268
|
+
"giorno",
|
|
269
|
+
"giu",
|
|
270
|
+
"già",
|
|
271
|
+
"gli",
|
|
272
|
+
"gliela",
|
|
273
|
+
"gliele",
|
|
274
|
+
"glieli",
|
|
275
|
+
"glielo",
|
|
276
|
+
"gliene",
|
|
277
|
+
"grande",
|
|
278
|
+
"grazie",
|
|
279
|
+
"gruppo",
|
|
280
|
+
"ha",
|
|
281
|
+
"haha",
|
|
282
|
+
"hai",
|
|
283
|
+
"hanno",
|
|
284
|
+
"ho",
|
|
285
|
+
"i",
|
|
286
|
+
"ie",
|
|
287
|
+
"ieri",
|
|
288
|
+
"il",
|
|
289
|
+
"improvviso",
|
|
290
|
+
"in",
|
|
291
|
+
"inc",
|
|
292
|
+
"indietro",
|
|
293
|
+
"infatti",
|
|
294
|
+
"inoltre",
|
|
295
|
+
"insieme",
|
|
296
|
+
"intanto",
|
|
297
|
+
"intorno",
|
|
298
|
+
"invece",
|
|
299
|
+
"io",
|
|
300
|
+
"l",
|
|
301
|
+
"la",
|
|
302
|
+
"lasciato",
|
|
303
|
+
"lato",
|
|
304
|
+
"le",
|
|
305
|
+
"lei",
|
|
306
|
+
"li",
|
|
307
|
+
"lo",
|
|
308
|
+
"lontano",
|
|
309
|
+
"loro",
|
|
310
|
+
"lui",
|
|
311
|
+
"lungo",
|
|
312
|
+
"luogo",
|
|
313
|
+
"là",
|
|
314
|
+
"ma",
|
|
315
|
+
"macche",
|
|
316
|
+
"magari",
|
|
317
|
+
"maggior",
|
|
318
|
+
"mai",
|
|
319
|
+
"male",
|
|
320
|
+
"malgrado",
|
|
321
|
+
"malissimo",
|
|
322
|
+
"me",
|
|
323
|
+
"medesimo",
|
|
324
|
+
"mediante",
|
|
325
|
+
"meglio",
|
|
326
|
+
"meno",
|
|
327
|
+
"mentre",
|
|
328
|
+
"mesi",
|
|
329
|
+
"mezzo",
|
|
330
|
+
"mi",
|
|
331
|
+
"mia",
|
|
332
|
+
"mie",
|
|
333
|
+
"miei",
|
|
334
|
+
"mila",
|
|
335
|
+
"miliardi",
|
|
336
|
+
"milioni",
|
|
337
|
+
"minimi",
|
|
338
|
+
"mio",
|
|
339
|
+
"modo",
|
|
340
|
+
"molta",
|
|
341
|
+
"molti",
|
|
342
|
+
"moltissimo",
|
|
343
|
+
"molto",
|
|
344
|
+
"momento",
|
|
345
|
+
"mondo",
|
|
346
|
+
"ne",
|
|
347
|
+
"negl",
|
|
348
|
+
"negli",
|
|
349
|
+
"nei",
|
|
350
|
+
"nel",
|
|
351
|
+
"nell",
|
|
352
|
+
"nella",
|
|
353
|
+
"nelle",
|
|
354
|
+
"nello",
|
|
355
|
+
"nemmeno",
|
|
356
|
+
"neppure",
|
|
357
|
+
"nessun",
|
|
358
|
+
"nessuna",
|
|
359
|
+
"nessuno",
|
|
360
|
+
"niente",
|
|
361
|
+
"no",
|
|
362
|
+
"noi",
|
|
363
|
+
"nome",
|
|
364
|
+
"non",
|
|
365
|
+
"nondimeno",
|
|
366
|
+
"nonostante",
|
|
367
|
+
"nonsia",
|
|
368
|
+
"nostra",
|
|
369
|
+
"nostre",
|
|
370
|
+
"nostri",
|
|
371
|
+
"nostro",
|
|
372
|
+
"novanta",
|
|
373
|
+
"nove",
|
|
374
|
+
"nulla",
|
|
375
|
+
"nuovi",
|
|
376
|
+
"nuovo",
|
|
377
|
+
"o",
|
|
378
|
+
"od",
|
|
379
|
+
"oggi",
|
|
380
|
+
"ogni",
|
|
381
|
+
"ognuna",
|
|
382
|
+
"ognuno",
|
|
383
|
+
"oltre",
|
|
384
|
+
"oppure",
|
|
385
|
+
"ora",
|
|
386
|
+
"ore",
|
|
387
|
+
"osi",
|
|
388
|
+
"ossia",
|
|
389
|
+
"ottanta",
|
|
390
|
+
"otto",
|
|
391
|
+
"paese",
|
|
392
|
+
"parecchi",
|
|
393
|
+
"parecchie",
|
|
394
|
+
"parecchio",
|
|
395
|
+
"parte",
|
|
396
|
+
"partendo",
|
|
397
|
+
"peccato",
|
|
398
|
+
"peggio",
|
|
399
|
+
"per",
|
|
400
|
+
"perche",
|
|
401
|
+
"perchè",
|
|
402
|
+
"perché",
|
|
403
|
+
"percio",
|
|
404
|
+
"perciò",
|
|
405
|
+
"perfino",
|
|
406
|
+
"pero",
|
|
407
|
+
"persino",
|
|
408
|
+
"persone",
|
|
409
|
+
"però",
|
|
410
|
+
"piedi",
|
|
411
|
+
"pieno",
|
|
412
|
+
"piglia",
|
|
413
|
+
"piu",
|
|
414
|
+
"piuttosto",
|
|
415
|
+
"più",
|
|
416
|
+
"po",
|
|
417
|
+
"pochissimo",
|
|
418
|
+
"poco",
|
|
419
|
+
"poi",
|
|
420
|
+
"poiche",
|
|
421
|
+
"possa",
|
|
422
|
+
"possedere",
|
|
423
|
+
"posteriore",
|
|
424
|
+
"posto",
|
|
425
|
+
"potrebbe",
|
|
426
|
+
"preferibilmente",
|
|
427
|
+
"presa",
|
|
428
|
+
"press",
|
|
429
|
+
"prima",
|
|
430
|
+
"primo",
|
|
431
|
+
"principalmente",
|
|
432
|
+
"probabilmente",
|
|
433
|
+
"promesso",
|
|
434
|
+
"proprio",
|
|
435
|
+
"puo",
|
|
436
|
+
"pure",
|
|
437
|
+
"purtroppo",
|
|
438
|
+
"può",
|
|
439
|
+
"qua",
|
|
440
|
+
"qualche",
|
|
441
|
+
"qualcosa",
|
|
442
|
+
"qualcuna",
|
|
443
|
+
"qualcuno",
|
|
444
|
+
"quale",
|
|
445
|
+
"quali",
|
|
446
|
+
"qualunque",
|
|
447
|
+
"quando",
|
|
448
|
+
"quanta",
|
|
449
|
+
"quante",
|
|
450
|
+
"quanti",
|
|
451
|
+
"quanto",
|
|
452
|
+
"quantunque",
|
|
453
|
+
"quarto",
|
|
454
|
+
"quasi",
|
|
455
|
+
"quattro",
|
|
456
|
+
"quel",
|
|
457
|
+
"quella",
|
|
458
|
+
"quelle",
|
|
459
|
+
"quelli",
|
|
460
|
+
"quello",
|
|
461
|
+
"quest",
|
|
462
|
+
"questa",
|
|
463
|
+
"queste",
|
|
464
|
+
"questi",
|
|
465
|
+
"questo",
|
|
466
|
+
"qui",
|
|
467
|
+
"quindi",
|
|
468
|
+
"quinto",
|
|
469
|
+
"realmente",
|
|
470
|
+
"recente",
|
|
471
|
+
"recentemente",
|
|
472
|
+
"registrazione",
|
|
473
|
+
"relativo",
|
|
474
|
+
"riecco",
|
|
475
|
+
"rispetto",
|
|
476
|
+
"salvo",
|
|
477
|
+
"sara",
|
|
478
|
+
"sarai",
|
|
479
|
+
"saranno",
|
|
480
|
+
"sarebbe",
|
|
481
|
+
"sarebbero",
|
|
482
|
+
"sarei",
|
|
483
|
+
"saremmo",
|
|
484
|
+
"saremo",
|
|
485
|
+
"sareste",
|
|
486
|
+
"saresti",
|
|
487
|
+
"sarete",
|
|
488
|
+
"sarà",
|
|
489
|
+
"sarò",
|
|
490
|
+
"scola",
|
|
491
|
+
"scopo",
|
|
492
|
+
"scorso",
|
|
493
|
+
"se",
|
|
494
|
+
"secondo",
|
|
495
|
+
"seguente",
|
|
496
|
+
"seguito",
|
|
497
|
+
"sei",
|
|
498
|
+
"sembra",
|
|
499
|
+
"sembrare",
|
|
500
|
+
"sembrato",
|
|
501
|
+
"sembrava",
|
|
502
|
+
"sembri",
|
|
503
|
+
"sempre",
|
|
504
|
+
"senza",
|
|
505
|
+
"sette",
|
|
506
|
+
"si",
|
|
507
|
+
"sia",
|
|
508
|
+
"siamo",
|
|
509
|
+
"siano",
|
|
510
|
+
"siate",
|
|
511
|
+
"siete",
|
|
512
|
+
"sig",
|
|
513
|
+
"solito",
|
|
514
|
+
"solo",
|
|
515
|
+
"soltanto",
|
|
516
|
+
"sono",
|
|
517
|
+
"sopra",
|
|
518
|
+
"soprattutto",
|
|
519
|
+
"sotto",
|
|
520
|
+
"spesso",
|
|
521
|
+
"sta",
|
|
522
|
+
"stai",
|
|
523
|
+
"stando",
|
|
524
|
+
"stanno",
|
|
525
|
+
"starai",
|
|
526
|
+
"staranno",
|
|
527
|
+
"starebbe",
|
|
528
|
+
"starebbero",
|
|
529
|
+
"starei",
|
|
530
|
+
"staremmo",
|
|
531
|
+
"staremo",
|
|
532
|
+
"stareste",
|
|
533
|
+
"staresti",
|
|
534
|
+
"starete",
|
|
535
|
+
"starà",
|
|
536
|
+
"starò",
|
|
537
|
+
"stata",
|
|
538
|
+
"state",
|
|
539
|
+
"stati",
|
|
540
|
+
"stato",
|
|
541
|
+
"stava",
|
|
542
|
+
"stavamo",
|
|
543
|
+
"stavano",
|
|
544
|
+
"stavate",
|
|
545
|
+
"stavi",
|
|
546
|
+
"stavo",
|
|
547
|
+
"stemmo",
|
|
548
|
+
"stessa",
|
|
549
|
+
"stesse",
|
|
550
|
+
"stessero",
|
|
551
|
+
"stessi",
|
|
552
|
+
"stessimo",
|
|
553
|
+
"stesso",
|
|
554
|
+
"steste",
|
|
555
|
+
"stesti",
|
|
556
|
+
"stette",
|
|
557
|
+
"stettero",
|
|
558
|
+
"stetti",
|
|
559
|
+
"stia",
|
|
560
|
+
"stiamo",
|
|
561
|
+
"stiano",
|
|
562
|
+
"stiate",
|
|
563
|
+
"sto",
|
|
564
|
+
"su",
|
|
565
|
+
"sua",
|
|
566
|
+
"subito",
|
|
567
|
+
"successivamente",
|
|
568
|
+
"successivo",
|
|
569
|
+
"sue",
|
|
570
|
+
"sugl",
|
|
571
|
+
"sugli",
|
|
572
|
+
"sui",
|
|
573
|
+
"sul",
|
|
574
|
+
"sull",
|
|
575
|
+
"sulla",
|
|
576
|
+
"sulle",
|
|
577
|
+
"sullo",
|
|
578
|
+
"suo",
|
|
579
|
+
"suoi",
|
|
580
|
+
"tale",
|
|
581
|
+
"tali",
|
|
582
|
+
"talvolta",
|
|
583
|
+
"tanto",
|
|
584
|
+
"te",
|
|
585
|
+
"tempo",
|
|
586
|
+
"terzo",
|
|
587
|
+
"th",
|
|
588
|
+
"ti",
|
|
589
|
+
"titolo",
|
|
590
|
+
"tra",
|
|
591
|
+
"tranne",
|
|
592
|
+
"tre",
|
|
593
|
+
"trenta",
|
|
594
|
+
"triplo",
|
|
595
|
+
"troppo",
|
|
596
|
+
"trovato",
|
|
597
|
+
"tu",
|
|
598
|
+
"tua",
|
|
599
|
+
"tue",
|
|
600
|
+
"tuo",
|
|
601
|
+
"tuoi",
|
|
602
|
+
"tutta",
|
|
603
|
+
"tuttavia",
|
|
604
|
+
"tutte",
|
|
605
|
+
"tutti",
|
|
606
|
+
"tutto",
|
|
607
|
+
"uguali",
|
|
608
|
+
"ulteriore",
|
|
609
|
+
"ultimo",
|
|
610
|
+
"un",
|
|
611
|
+
"una",
|
|
612
|
+
"uno",
|
|
613
|
+
"uomo",
|
|
614
|
+
"va",
|
|
615
|
+
"vai",
|
|
616
|
+
"vale",
|
|
617
|
+
"vari",
|
|
618
|
+
"varia",
|
|
619
|
+
"varie",
|
|
620
|
+
"vario",
|
|
621
|
+
"verso",
|
|
622
|
+
"vi",
|
|
623
|
+
"vicino",
|
|
624
|
+
"visto",
|
|
625
|
+
"vita",
|
|
626
|
+
"voi",
|
|
627
|
+
"volta",
|
|
628
|
+
"volte",
|
|
629
|
+
"vostra",
|
|
630
|
+
"vostre",
|
|
631
|
+
"vostri",
|
|
632
|
+
"vostro",
|
|
633
|
+
"è"
|
|
634
|
+
]
|