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 +1,482 @@
|
|
|
1
|
+
[
|
|
2
|
+
"،",
|
|
3
|
+
"آض",
|
|
4
|
+
"آمينَ",
|
|
5
|
+
"آه",
|
|
6
|
+
"آهاً",
|
|
7
|
+
"آي",
|
|
8
|
+
"أ",
|
|
9
|
+
"أب",
|
|
10
|
+
"أجل",
|
|
11
|
+
"أجمع",
|
|
12
|
+
"أخ",
|
|
13
|
+
"أخذ",
|
|
14
|
+
"أصبح",
|
|
15
|
+
"أضحى",
|
|
16
|
+
"أقبل",
|
|
17
|
+
"أقل",
|
|
18
|
+
"أكثر",
|
|
19
|
+
"ألا",
|
|
20
|
+
"أم",
|
|
21
|
+
"أما",
|
|
22
|
+
"أمامك",
|
|
23
|
+
"أمامكَ",
|
|
24
|
+
"أمسى",
|
|
25
|
+
"أمّا",
|
|
26
|
+
"أن",
|
|
27
|
+
"أنا",
|
|
28
|
+
"أنت",
|
|
29
|
+
"أنتم",
|
|
30
|
+
"أنتما",
|
|
31
|
+
"أنتن",
|
|
32
|
+
"أنتِ",
|
|
33
|
+
"أنشأ",
|
|
34
|
+
"أنّى",
|
|
35
|
+
"أو",
|
|
36
|
+
"أوشك",
|
|
37
|
+
"أولئك",
|
|
38
|
+
"أولئكم",
|
|
39
|
+
"أولاء",
|
|
40
|
+
"أولالك",
|
|
41
|
+
"أوّهْ",
|
|
42
|
+
"أي",
|
|
43
|
+
"أيا",
|
|
44
|
+
"أين",
|
|
45
|
+
"أينما",
|
|
46
|
+
"أيّ",
|
|
47
|
+
"أَنَّ",
|
|
48
|
+
"أََيُّ",
|
|
49
|
+
"أُفٍّ",
|
|
50
|
+
"إذ",
|
|
51
|
+
"إذا",
|
|
52
|
+
"إذاً",
|
|
53
|
+
"إذما",
|
|
54
|
+
"إذن",
|
|
55
|
+
"إلى",
|
|
56
|
+
"إليكم",
|
|
57
|
+
"إليكما",
|
|
58
|
+
"إليكنّ",
|
|
59
|
+
"إليكَ",
|
|
60
|
+
"إلَيْكَ",
|
|
61
|
+
"إلّا",
|
|
62
|
+
"إمّا",
|
|
63
|
+
"إن",
|
|
64
|
+
"إنّما",
|
|
65
|
+
"إي",
|
|
66
|
+
"إياك",
|
|
67
|
+
"إياكم",
|
|
68
|
+
"إياكما",
|
|
69
|
+
"إياكن",
|
|
70
|
+
"إيانا",
|
|
71
|
+
"إياه",
|
|
72
|
+
"إياها",
|
|
73
|
+
"إياهم",
|
|
74
|
+
"إياهما",
|
|
75
|
+
"إياهن",
|
|
76
|
+
"إياي",
|
|
77
|
+
"إيهٍ",
|
|
78
|
+
"إِنَّ",
|
|
79
|
+
"ا",
|
|
80
|
+
"ابتدأ",
|
|
81
|
+
"اثر",
|
|
82
|
+
"اجل",
|
|
83
|
+
"احد",
|
|
84
|
+
"اخرى",
|
|
85
|
+
"اخلولق",
|
|
86
|
+
"اذا",
|
|
87
|
+
"اربعة",
|
|
88
|
+
"ارتدّ",
|
|
89
|
+
"استحال",
|
|
90
|
+
"اطار",
|
|
91
|
+
"اعادة",
|
|
92
|
+
"اعلنت",
|
|
93
|
+
"اف",
|
|
94
|
+
"اكثر",
|
|
95
|
+
"اكد",
|
|
96
|
+
"الألاء",
|
|
97
|
+
"الألى",
|
|
98
|
+
"الا",
|
|
99
|
+
"الاخيرة",
|
|
100
|
+
"الان",
|
|
101
|
+
"الاول",
|
|
102
|
+
"الاولى",
|
|
103
|
+
"التى",
|
|
104
|
+
"التي",
|
|
105
|
+
"الثاني",
|
|
106
|
+
"الثانية",
|
|
107
|
+
"الذاتي",
|
|
108
|
+
"الذى",
|
|
109
|
+
"الذي",
|
|
110
|
+
"الذين",
|
|
111
|
+
"السابق",
|
|
112
|
+
"الف",
|
|
113
|
+
"اللائي",
|
|
114
|
+
"اللاتي",
|
|
115
|
+
"اللتان",
|
|
116
|
+
"اللتيا",
|
|
117
|
+
"اللتين",
|
|
118
|
+
"اللذان",
|
|
119
|
+
"اللذين",
|
|
120
|
+
"اللواتي",
|
|
121
|
+
"الماضي",
|
|
122
|
+
"المقبل",
|
|
123
|
+
"الوقت",
|
|
124
|
+
"الى",
|
|
125
|
+
"اليوم",
|
|
126
|
+
"اما",
|
|
127
|
+
"امام",
|
|
128
|
+
"امس",
|
|
129
|
+
"ان",
|
|
130
|
+
"انبرى",
|
|
131
|
+
"انقلب",
|
|
132
|
+
"انه",
|
|
133
|
+
"انها",
|
|
134
|
+
"او",
|
|
135
|
+
"اول",
|
|
136
|
+
"اي",
|
|
137
|
+
"ايار",
|
|
138
|
+
"ايام",
|
|
139
|
+
"ايضا",
|
|
140
|
+
"ب",
|
|
141
|
+
"بات",
|
|
142
|
+
"باسم",
|
|
143
|
+
"بان",
|
|
144
|
+
"بخٍ",
|
|
145
|
+
"برس",
|
|
146
|
+
"بسبب",
|
|
147
|
+
"بسّ",
|
|
148
|
+
"بشكل",
|
|
149
|
+
"بضع",
|
|
150
|
+
"بطآن",
|
|
151
|
+
"بعد",
|
|
152
|
+
"بعض",
|
|
153
|
+
"بك",
|
|
154
|
+
"بكم",
|
|
155
|
+
"بكما",
|
|
156
|
+
"بكن",
|
|
157
|
+
"بل",
|
|
158
|
+
"بلى",
|
|
159
|
+
"بما",
|
|
160
|
+
"بماذا",
|
|
161
|
+
"بمن",
|
|
162
|
+
"بن",
|
|
163
|
+
"بنا",
|
|
164
|
+
"به",
|
|
165
|
+
"بها",
|
|
166
|
+
"بي",
|
|
167
|
+
"بيد",
|
|
168
|
+
"بين",
|
|
169
|
+
"بَسْ",
|
|
170
|
+
"بَلْهَ",
|
|
171
|
+
"بِئْسَ",
|
|
172
|
+
"تانِ",
|
|
173
|
+
"تانِك",
|
|
174
|
+
"تبدّل",
|
|
175
|
+
"تجاه",
|
|
176
|
+
"تحوّل",
|
|
177
|
+
"تلقاء",
|
|
178
|
+
"تلك",
|
|
179
|
+
"تلكم",
|
|
180
|
+
"تلكما",
|
|
181
|
+
"تم",
|
|
182
|
+
"تينك",
|
|
183
|
+
"تَيْنِ",
|
|
184
|
+
"تِه",
|
|
185
|
+
"تِي",
|
|
186
|
+
"ثلاثة",
|
|
187
|
+
"ثم",
|
|
188
|
+
"ثمّ",
|
|
189
|
+
"ثمّة",
|
|
190
|
+
"ثُمَّ",
|
|
191
|
+
"جعل",
|
|
192
|
+
"جلل",
|
|
193
|
+
"جميع",
|
|
194
|
+
"جير",
|
|
195
|
+
"حار",
|
|
196
|
+
"حاشا",
|
|
197
|
+
"حاليا",
|
|
198
|
+
"حاي",
|
|
199
|
+
"حتى",
|
|
200
|
+
"حرى",
|
|
201
|
+
"حسب",
|
|
202
|
+
"حم",
|
|
203
|
+
"حوالى",
|
|
204
|
+
"حول",
|
|
205
|
+
"حيث",
|
|
206
|
+
"حيثما",
|
|
207
|
+
"حين",
|
|
208
|
+
"حيَّ",
|
|
209
|
+
"حَبَّذَا",
|
|
210
|
+
"حَتَّى",
|
|
211
|
+
"حَذارِ",
|
|
212
|
+
"خلا",
|
|
213
|
+
"خلال",
|
|
214
|
+
"دون",
|
|
215
|
+
"دونك",
|
|
216
|
+
"ذا",
|
|
217
|
+
"ذات",
|
|
218
|
+
"ذاك",
|
|
219
|
+
"ذانك",
|
|
220
|
+
"ذانِ",
|
|
221
|
+
"ذلك",
|
|
222
|
+
"ذلكم",
|
|
223
|
+
"ذلكما",
|
|
224
|
+
"ذلكن",
|
|
225
|
+
"ذو",
|
|
226
|
+
"ذوا",
|
|
227
|
+
"ذواتا",
|
|
228
|
+
"ذواتي",
|
|
229
|
+
"ذيت",
|
|
230
|
+
"ذينك",
|
|
231
|
+
"ذَيْنِ",
|
|
232
|
+
"ذِه",
|
|
233
|
+
"ذِي",
|
|
234
|
+
"راح",
|
|
235
|
+
"رجع",
|
|
236
|
+
"رويدك",
|
|
237
|
+
"ريث",
|
|
238
|
+
"رُبَّ",
|
|
239
|
+
"زيارة",
|
|
240
|
+
"سبحان",
|
|
241
|
+
"سرعان",
|
|
242
|
+
"سنة",
|
|
243
|
+
"سنوات",
|
|
244
|
+
"سوف",
|
|
245
|
+
"سوى",
|
|
246
|
+
"سَاءَ",
|
|
247
|
+
"سَاءَمَا",
|
|
248
|
+
"شبه",
|
|
249
|
+
"شخصا",
|
|
250
|
+
"شرع",
|
|
251
|
+
"شَتَّانَ",
|
|
252
|
+
"صار",
|
|
253
|
+
"صباح",
|
|
254
|
+
"صفر",
|
|
255
|
+
"صهٍ",
|
|
256
|
+
"صهْ",
|
|
257
|
+
"ضد",
|
|
258
|
+
"ضمن",
|
|
259
|
+
"طاق",
|
|
260
|
+
"طالما",
|
|
261
|
+
"طفق",
|
|
262
|
+
"طَق",
|
|
263
|
+
"ظلّ",
|
|
264
|
+
"عاد",
|
|
265
|
+
"عام",
|
|
266
|
+
"عاما",
|
|
267
|
+
"عامة",
|
|
268
|
+
"عدا",
|
|
269
|
+
"عدة",
|
|
270
|
+
"عدد",
|
|
271
|
+
"عدم",
|
|
272
|
+
"عسى",
|
|
273
|
+
"عشر",
|
|
274
|
+
"عشرة",
|
|
275
|
+
"علق",
|
|
276
|
+
"على",
|
|
277
|
+
"عليك",
|
|
278
|
+
"عليه",
|
|
279
|
+
"عليها",
|
|
280
|
+
"علًّ",
|
|
281
|
+
"عن",
|
|
282
|
+
"عند",
|
|
283
|
+
"عندما",
|
|
284
|
+
"عوض",
|
|
285
|
+
"عين",
|
|
286
|
+
"عَدَسْ",
|
|
287
|
+
"عَمَّا",
|
|
288
|
+
"غدا",
|
|
289
|
+
"غير",
|
|
290
|
+
"ـ",
|
|
291
|
+
"ف",
|
|
292
|
+
"فان",
|
|
293
|
+
"فلان",
|
|
294
|
+
"فو",
|
|
295
|
+
"فى",
|
|
296
|
+
"في",
|
|
297
|
+
"فيم",
|
|
298
|
+
"فيما",
|
|
299
|
+
"فيه",
|
|
300
|
+
"فيها",
|
|
301
|
+
"قال",
|
|
302
|
+
"قام",
|
|
303
|
+
"قبل",
|
|
304
|
+
"قد",
|
|
305
|
+
"قطّ",
|
|
306
|
+
"قلما",
|
|
307
|
+
"قوة",
|
|
308
|
+
"كأنّما",
|
|
309
|
+
"كأين",
|
|
310
|
+
"كأيّ",
|
|
311
|
+
"كأيّن",
|
|
312
|
+
"كاد",
|
|
313
|
+
"كان",
|
|
314
|
+
"كانت",
|
|
315
|
+
"كذا",
|
|
316
|
+
"كذلك",
|
|
317
|
+
"كرب",
|
|
318
|
+
"كل",
|
|
319
|
+
"كلا",
|
|
320
|
+
"كلاهما",
|
|
321
|
+
"كلتا",
|
|
322
|
+
"كلم",
|
|
323
|
+
"كليكما",
|
|
324
|
+
"كليهما",
|
|
325
|
+
"كلّما",
|
|
326
|
+
"كلَّا",
|
|
327
|
+
"كم",
|
|
328
|
+
"كما",
|
|
329
|
+
"كي",
|
|
330
|
+
"كيت",
|
|
331
|
+
"كيف",
|
|
332
|
+
"كيفما",
|
|
333
|
+
"كَأَنَّ",
|
|
334
|
+
"كِخ",
|
|
335
|
+
"لئن",
|
|
336
|
+
"لا",
|
|
337
|
+
"لات",
|
|
338
|
+
"لاسيما",
|
|
339
|
+
"لدن",
|
|
340
|
+
"لدى",
|
|
341
|
+
"لعمر",
|
|
342
|
+
"لقاء",
|
|
343
|
+
"لك",
|
|
344
|
+
"لكم",
|
|
345
|
+
"لكما",
|
|
346
|
+
"لكن",
|
|
347
|
+
"لكنَّما",
|
|
348
|
+
"لكي",
|
|
349
|
+
"لكيلا",
|
|
350
|
+
"للامم",
|
|
351
|
+
"لم",
|
|
352
|
+
"لما",
|
|
353
|
+
"لمّا",
|
|
354
|
+
"لن",
|
|
355
|
+
"لنا",
|
|
356
|
+
"له",
|
|
357
|
+
"لها",
|
|
358
|
+
"لو",
|
|
359
|
+
"لوكالة",
|
|
360
|
+
"لولا",
|
|
361
|
+
"لوما",
|
|
362
|
+
"لي",
|
|
363
|
+
"لَسْتَ",
|
|
364
|
+
"لَسْتُ",
|
|
365
|
+
"لَسْتُم",
|
|
366
|
+
"لَسْتُمَا",
|
|
367
|
+
"لَسْتُنَّ",
|
|
368
|
+
"لَسْتِ",
|
|
369
|
+
"لَسْنَ",
|
|
370
|
+
"لَعَلَّ",
|
|
371
|
+
"لَكِنَّ",
|
|
372
|
+
"لَيْتَ",
|
|
373
|
+
"لَيْسَ",
|
|
374
|
+
"لَيْسَا",
|
|
375
|
+
"لَيْسَتَا",
|
|
376
|
+
"لَيْسَتْ",
|
|
377
|
+
"لَيْسُوا",
|
|
378
|
+
"لَِسْنَا",
|
|
379
|
+
"ما",
|
|
380
|
+
"ماانفك",
|
|
381
|
+
"مابرح",
|
|
382
|
+
"مادام",
|
|
383
|
+
"ماذا",
|
|
384
|
+
"مازال",
|
|
385
|
+
"مافتئ",
|
|
386
|
+
"مايو",
|
|
387
|
+
"متى",
|
|
388
|
+
"مثل",
|
|
389
|
+
"مذ",
|
|
390
|
+
"مساء",
|
|
391
|
+
"مع",
|
|
392
|
+
"معاذ",
|
|
393
|
+
"مقابل",
|
|
394
|
+
"مكانكم",
|
|
395
|
+
"مكانكما",
|
|
396
|
+
"مكانكنّ",
|
|
397
|
+
"مكانَك",
|
|
398
|
+
"مليار",
|
|
399
|
+
"مليون",
|
|
400
|
+
"مما",
|
|
401
|
+
"ممن",
|
|
402
|
+
"من",
|
|
403
|
+
"منذ",
|
|
404
|
+
"منها",
|
|
405
|
+
"مه",
|
|
406
|
+
"مهما",
|
|
407
|
+
"مَنْ",
|
|
408
|
+
"مِن",
|
|
409
|
+
"نحن",
|
|
410
|
+
"نحو",
|
|
411
|
+
"نعم",
|
|
412
|
+
"نفس",
|
|
413
|
+
"نفسه",
|
|
414
|
+
"نهاية",
|
|
415
|
+
"نَخْ",
|
|
416
|
+
"نِعِمّا",
|
|
417
|
+
"نِعْمَ",
|
|
418
|
+
"ها",
|
|
419
|
+
"هاؤم",
|
|
420
|
+
"هاكَ",
|
|
421
|
+
"هاهنا",
|
|
422
|
+
"هبّ",
|
|
423
|
+
"هذا",
|
|
424
|
+
"هذه",
|
|
425
|
+
"هكذا",
|
|
426
|
+
"هل",
|
|
427
|
+
"هلمَّ",
|
|
428
|
+
"هلّا",
|
|
429
|
+
"هم",
|
|
430
|
+
"هما",
|
|
431
|
+
"هن",
|
|
432
|
+
"هنا",
|
|
433
|
+
"هناك",
|
|
434
|
+
"هنالك",
|
|
435
|
+
"هو",
|
|
436
|
+
"هي",
|
|
437
|
+
"هيا",
|
|
438
|
+
"هيت",
|
|
439
|
+
"هيّا",
|
|
440
|
+
"هَؤلاء",
|
|
441
|
+
"هَاتانِ",
|
|
442
|
+
"هَاتَيْنِ",
|
|
443
|
+
"هَاتِه",
|
|
444
|
+
"هَاتِي",
|
|
445
|
+
"هَجْ",
|
|
446
|
+
"هَذا",
|
|
447
|
+
"هَذانِ",
|
|
448
|
+
"هَذَيْنِ",
|
|
449
|
+
"هَذِه",
|
|
450
|
+
"هَذِي",
|
|
451
|
+
"هَيْهَاتَ",
|
|
452
|
+
"و",
|
|
453
|
+
"و6",
|
|
454
|
+
"وا",
|
|
455
|
+
"واحد",
|
|
456
|
+
"واضاف",
|
|
457
|
+
"واضافت",
|
|
458
|
+
"واكد",
|
|
459
|
+
"وان",
|
|
460
|
+
"واهاً",
|
|
461
|
+
"واوضح",
|
|
462
|
+
"وراءَك",
|
|
463
|
+
"وفي",
|
|
464
|
+
"وقال",
|
|
465
|
+
"وقالت",
|
|
466
|
+
"وقد",
|
|
467
|
+
"وقف",
|
|
468
|
+
"وكان",
|
|
469
|
+
"وكانت",
|
|
470
|
+
"ولا",
|
|
471
|
+
"ولم",
|
|
472
|
+
"ومن",
|
|
473
|
+
"وهو",
|
|
474
|
+
"وهي",
|
|
475
|
+
"ويكأنّ",
|
|
476
|
+
"وَيْ",
|
|
477
|
+
"وُشْكَانََ",
|
|
478
|
+
"يكون",
|
|
479
|
+
"يمكن",
|
|
480
|
+
"يوم",
|
|
481
|
+
"ّأيّان"
|
|
482
|
+
]
|