@delali/narsil-react-native 0.3.1-next.155 → 0.3.1-next.157
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.
- package/NOTICE +144 -0
- package/NarsilReactNative.podspec +2 -2
- package/android/CMakeLists.txt +1 -1
- package/cpp/HybridNarsilCoreAnalysis.cpp +277 -0
- package/cpp/HybridNarsilCoreImpl.hpp +43 -0
- package/cpp/HybridNarsilCoreKeyword.cpp +253 -0
- package/cpp/HybridNarsilCoreMath.cpp +47 -0
- package/cpp/core/include/narsil_analysis.h +86 -0
- package/cpp/core/include/narsil_core.h +1 -1
- package/cpp/core/include/narsil_keyword.h +110 -0
- package/cpp/core/include/narsil_math.h +36 -0
- package/cpp/core/src/analysis/analyse.c +281 -0
- package/cpp/core/src/analysis/analyser.h +49 -0
- package/cpp/core/src/analysis/languages.c +79 -0
- package/cpp/core/src/analysis/languages.h +42 -0
- package/cpp/core/src/analysis/normalise.c +242 -0
- package/cpp/core/src/analysis/normalise.h +28 -0
- package/cpp/core/src/analysis/split.c +183 -0
- package/cpp/core/src/analysis/split.h +27 -0
- package/cpp/core/src/analysis/stop_words.c +82 -0
- package/cpp/core/src/analysis/stop_words.h +19 -0
- package/cpp/core/src/analysis/term_cache.c +88 -0
- package/cpp/core/src/analysis/term_cache.h +36 -0
- package/cpp/core/src/analysis/text.c +161 -0
- package/cpp/core/src/analysis/text.h +45 -0
- package/cpp/core/src/analysis/transform.c +103 -0
- package/cpp/core/src/analysis/unicode.c +252 -0
- package/cpp/core/src/analysis/unicode.h +54 -0
- package/cpp/core/src/internal.h +4 -0
- package/cpp/core/src/keyword/pass.h +117 -0
- package/cpp/core/src/keyword/prune.c +324 -0
- package/cpp/core/src/keyword/request.c +179 -0
- package/cpp/core/src/keyword/rows.c +83 -0
- package/cpp/core/src/keyword/rows.h +18 -0
- package/cpp/core/src/keyword/score.c +257 -0
- package/cpp/core/src/keyword/score.h +17 -0
- package/cpp/core/src/keyword/scratch.c +226 -0
- package/cpp/core/src/keyword/scratch.h +55 -0
- package/cpp/core/src/keyword/select.c +155 -0
- package/cpp/core/src/keyword/select.h +17 -0
- package/cpp/core/src/languages/bulgarian_stemmer.c +114 -0
- package/cpp/core/src/languages/data/albanian.c +54 -0
- package/cpp/core/src/languages/data/amharic.c +93 -0
- package/cpp/core/src/languages/data/arabic.c +146 -0
- package/cpp/core/src/languages/data/armenian.c +46 -0
- package/cpp/core/src/languages/data/azerbaijani.c +68 -0
- package/cpp/core/src/languages/data/bambara.c +48 -0
- package/cpp/core/src/languages/data/basque.c +62 -0
- package/cpp/core/src/languages/data/belarusian.c +56 -0
- package/cpp/core/src/languages/data/bengali.c +63 -0
- package/cpp/core/src/languages/data/bosnian.c +73 -0
- package/cpp/core/src/languages/data/breton.c +52 -0
- package/cpp/core/src/languages/data/bulgarian.c +144 -0
- package/cpp/core/src/languages/data/burmese.c +48 -0
- package/cpp/core/src/languages/data/catalan.c +84 -0
- package/cpp/core/src/languages/data/chinese.c +70 -0
- package/cpp/core/src/languages/data/croatian.c +72 -0
- package/cpp/core/src/languages/data/czech.c +72 -0
- package/cpp/core/src/languages/data/dagbani.c +88 -0
- package/cpp/core/src/languages/data/danish.c +56 -0
- package/cpp/core/src/languages/data/declarations.h +114 -0
- package/cpp/core/src/languages/data/dutch.c +58 -0
- package/cpp/core/src/languages/data/english.c +172 -0
- package/cpp/core/src/languages/data/esperanto.c +71 -0
- package/cpp/core/src/languages/data/estonian.c +417 -0
- package/cpp/core/src/languages/data/ewe.c +89 -0
- package/cpp/core/src/languages/data/faroese.c +54 -0
- package/cpp/core/src/languages/data/fijian.c +44 -0
- package/cpp/core/src/languages/data/finnish.c +100 -0
- package/cpp/core/src/languages/data/french.c +74 -0
- package/cpp/core/src/languages/data/ga.c +83 -0
- package/cpp/core/src/languages/data/galician.c +70 -0
- package/cpp/core/src/languages/data/georgian.c +57 -0
- package/cpp/core/src/languages/data/german.c +96 -0
- package/cpp/core/src/languages/data/greek.c +202 -0
- package/cpp/core/src/languages/data/guarani.c +110 -0
- package/cpp/core/src/languages/data/gujarati.c +90 -0
- package/cpp/core/src/languages/data/haitian-creole.c +54 -0
- package/cpp/core/src/languages/data/hausa.c +85 -0
- package/cpp/core/src/languages/data/hawaiian.c +50 -0
- package/cpp/core/src/languages/data/hebrew.c +85 -0
- package/cpp/core/src/languages/data/hindi.c +91 -0
- package/cpp/core/src/languages/data/hungarian.c +98 -0
- package/cpp/core/src/languages/data/icelandic.c +73 -0
- package/cpp/core/src/languages/data/igbo.c +90 -0
- package/cpp/core/src/languages/data/indonesian.c +296 -0
- package/cpp/core/src/languages/data/irish.c +60 -0
- package/cpp/core/src/languages/data/italian.c +107 -0
- package/cpp/core/src/languages/data/japanese.c +52 -0
- package/cpp/core/src/languages/data/kannada.c +60 -0
- package/cpp/core/src/languages/data/kazakh.c +57 -0
- package/cpp/core/src/languages/data/khmer.c +71 -0
- package/cpp/core/src/languages/data/kinyarwanda.c +54 -0
- package/cpp/core/src/languages/data/kirundi.c +53 -0
- package/cpp/core/src/languages/data/korean.c +74 -0
- package/cpp/core/src/languages/data/kurmanji.c +43 -0
- package/cpp/core/src/languages/data/kyrgyz.c +65 -0
- package/cpp/core/src/languages/data/lao.c +46 -0
- package/cpp/core/src/languages/data/latin.c +46 -0
- package/cpp/core/src/languages/data/latvian.c +75 -0
- package/cpp/core/src/languages/data/lingala.c +88 -0
- package/cpp/core/src/languages/data/lithuanian.c +65 -0
- package/cpp/core/src/languages/data/luxembourgish.c +80 -0
- package/cpp/core/src/languages/data/macedonian.c +286 -0
- package/cpp/core/src/languages/data/malagasy.c +51 -0
- package/cpp/core/src/languages/data/malay.c +184 -0
- package/cpp/core/src/languages/data/malayalam.c +64 -0
- package/cpp/core/src/languages/data/maltese.c +102 -0
- package/cpp/core/src/languages/data/maori.c +52 -0
- package/cpp/core/src/languages/data/marathi.c +62 -0
- package/cpp/core/src/languages/data/nepali.c +72 -0
- package/cpp/core/src/languages/data/norwegian.c +74 -0
- package/cpp/core/src/languages/data/oromo.c +51 -0
- package/cpp/core/src/languages/data/persian.c +150 -0
- package/cpp/core/src/languages/data/polish.c +111 -0
- package/cpp/core/src/languages/data/portuguese.c +91 -0
- package/cpp/core/src/languages/data/punjabi.c +80 -0
- package/cpp/core/src/languages/data/registry.c +116 -0
- package/cpp/core/src/languages/data/romanian.c +93 -0
- package/cpp/core/src/languages/data/russian.c +76 -0
- package/cpp/core/src/languages/data/samoan.c +47 -0
- package/cpp/core/src/languages/data/sanskrit.c +53 -0
- package/cpp/core/src/languages/data/scottish-gaelic.c +119 -0
- package/cpp/core/src/languages/data/serbian.c +84 -0
- package/cpp/core/src/languages/data/shona.c +55 -0
- package/cpp/core/src/languages/data/sinhala.c +78 -0
- package/cpp/core/src/languages/data/slovak.c +135 -0
- package/cpp/core/src/languages/data/slovenian.c +139 -0
- package/cpp/core/src/languages/data/sorani.c +55 -0
- package/cpp/core/src/languages/data/spanish.c +84 -0
- package/cpp/core/src/languages/data/swahili.c +59 -0
- package/cpp/core/src/languages/data/swedish.c +60 -0
- package/cpp/core/src/languages/data/tagalog.c +75 -0
- package/cpp/core/src/languages/data/tamil.c +69 -0
- package/cpp/core/src/languages/data/tatar.c +548 -0
- package/cpp/core/src/languages/data/telugu.c +54 -0
- package/cpp/core/src/languages/data/thai.c +46 -0
- package/cpp/core/src/languages/data/tibetan.c +55 -0
- package/cpp/core/src/languages/data/tigrinya.c +73 -0
- package/cpp/core/src/languages/data/tongan.c +47 -0
- package/cpp/core/src/languages/data/turkish.c +100 -0
- package/cpp/core/src/languages/data/twi.c +88 -0
- package/cpp/core/src/languages/data/ukrainian.c +99 -0
- package/cpp/core/src/languages/data/urdu.c +174 -0
- package/cpp/core/src/languages/data/vietnamese.c +88 -0
- package/cpp/core/src/languages/data/welsh.c +143 -0
- package/cpp/core/src/languages/data/wolof.c +51 -0
- package/cpp/core/src/languages/data/xhosa.c +56 -0
- package/cpp/core/src/languages/data/yoruba.c +93 -0
- package/cpp/core/src/languages/data/zulu.c +58 -0
- package/cpp/core/src/languages/marks.c +64 -0
- package/cpp/core/src/languages/rules.c +63 -0
- package/cpp/core/src/languages/rules.h +68 -0
- package/cpp/core/src/languages/sanskrit_stemmer.c +50 -0
- package/cpp/core/src/languages/scripts.c +143 -0
- package/cpp/core/src/languages/slovenian_stemmer.c +46 -0
- package/cpp/core/src/languages/snowball/api.c +52 -0
- package/cpp/core/src/languages/snowball/api.h +43 -0
- package/cpp/core/src/languages/snowball/arabic_stemmer.c +1506 -0
- package/cpp/core/src/languages/snowball/arabic_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/armenian_stemmer.c +523 -0
- package/cpp/core/src/languages/snowball/armenian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/basque_stemmer.c +1089 -0
- package/cpp/core/src/languages/snowball/basque_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/catalan_stemmer.c +1380 -0
- package/cpp/core/src/languages/snowball/catalan_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/czech_stemmer.c +582 -0
- package/cpp/core/src/languages/snowball/czech_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/danish_stemmer.c +352 -0
- package/cpp/core/src/languages/snowball/danish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/dutch_stemmer.c +1657 -0
- package/cpp/core/src/languages/snowball/dutch_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/english_stemmer.c +1019 -0
- package/cpp/core/src/languages/snowball/english_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/esperanto_stemmer.c +716 -0
- package/cpp/core/src/languages/snowball/esperanto_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/estonian_stemmer.c +1361 -0
- package/cpp/core/src/languages/snowball/estonian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/finnish_stemmer.c +800 -0
- package/cpp/core/src/languages/snowball/finnish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/french_stemmer.c +1217 -0
- package/cpp/core/src/languages/snowball/french_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/german_stemmer.c +567 -0
- package/cpp/core/src/languages/snowball/german_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/greek_stemmer.c +3450 -0
- package/cpp/core/src/languages/snowball/greek_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/hindi_stemmer.c +325 -0
- package/cpp/core/src/languages/snowball/hindi_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/hungarian_stemmer.c +742 -0
- package/cpp/core/src/languages/snowball/hungarian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/indonesian_stemmer.c +443 -0
- package/cpp/core/src/languages/snowball/indonesian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/irish_stemmer.c +428 -0
- package/cpp/core/src/languages/snowball/irish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/italian_stemmer.c +983 -0
- package/cpp/core/src/languages/snowball/italian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/lithuanian_stemmer.c +794 -0
- package/cpp/core/src/languages/snowball/lithuanian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/nepali_stemmer.c +361 -0
- package/cpp/core/src/languages/snowball/nepali_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/norwegian_stemmer.c +332 -0
- package/cpp/core/src/languages/snowball/norwegian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/persian_stemmer.c +538 -0
- package/cpp/core/src/languages/snowball/persian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/polish_stemmer.c +501 -0
- package/cpp/core/src/languages/snowball/polish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/portuguese_stemmer.c +866 -0
- package/cpp/core/src/languages/snowball/portuguese_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/romanian_stemmer.c +940 -0
- package/cpp/core/src/languages/snowball/romanian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/russian_stemmer.c +598 -0
- package/cpp/core/src/languages/snowball/russian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/serbian_stemmer.c +6765 -0
- package/cpp/core/src/languages/snowball/serbian_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/snowball_runtime.h +122 -0
- package/cpp/core/src/languages/snowball/spanish_stemmer.c +955 -0
- package/cpp/core/src/languages/snowball/spanish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/swedish_stemmer.c +364 -0
- package/cpp/core/src/languages/snowball/swedish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/tamil_stemmer.c +1305 -0
- package/cpp/core/src/languages/snowball/tamil_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/turkish_stemmer.c +1700 -0
- package/cpp/core/src/languages/snowball/turkish_stemmer.h +24 -0
- package/cpp/core/src/languages/snowball/utilities.c +716 -0
- package/cpp/core/src/languages/substitutions.c +131 -0
- package/cpp/core/src/languages/swahili_stemmer.c +85 -0
- package/cpp/core/src/languages/ukrainian_stemmer.c +168 -0
- package/cpp/core/src/locks.c +2 -15
- package/cpp/core/src/math/apply.c +44 -0
- package/cpp/core/src/math/fdlibm.h +16 -0
- package/cpp/core/src/math/inverse.c +242 -0
- package/cpp/core/src/math/log.c +90 -0
- package/cpp/core/src/math/reduce.c +325 -0
- package/cpp/core/src/math/trig.c +188 -0
- package/cpp/core/src/math/words.h +45 -0
- package/cpp/core/src/thread_yield.h +18 -0
- package/cpp/core/src/unicode/decompositions.c +310 -0
- package/cpp/core/src/unicode/lowercase.c +172 -0
- package/cpp/core/src/unicode/properties.c +214 -0
- package/cpp/core/src/workspace.c +5 -1
- package/lib/engine/analysis.d.ts +3 -0
- package/lib/engine/analysis.js +76 -0
- package/lib/engine/core.js +5 -0
- package/lib/engine/keyword.d.ts +3 -0
- package/lib/engine/keyword.js +25 -0
- package/lib/specs/core.nitro.d.ts +1 -0
- package/nitrogen/generated/shared/c++/HybridNarsilCoreSpec.cpp +1 -0
- package/nitrogen/generated/shared/c++/HybridNarsilCoreSpec.hpp +1 -0
- package/package.json +4 -3
- package/src/engine/analysis.ts +87 -0
- package/src/engine/core.ts +6 -0
- package/src/engine/keyword.ts +26 -0
- package/src/specs/core.nitro.ts +1 -0
|
@@ -0,0 +1,135 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
|
|
4
|
+
#include <stddef.h>
|
|
5
|
+
#include <stdint.h>
|
|
6
|
+
|
|
7
|
+
static const uint16_t stop_word_units[1834] = {
|
|
8
|
+
97, 97, 98, 121, 97, 106, 97, 107, 97, 107, 101, 106, 97, 107, 101, 106, 382, 101, 97, 107, 111, 97, 107, 111, 109,
|
|
9
|
+
97, 107, 111, 109, 382, 101, 97, 107, 111, 117, 97, 107, 111, 117, 382, 101, 97, 107, 111, 382, 101, 97, 107, 225, 97,
|
|
10
|
+
107, 225, 382, 101, 97, 107, 233, 97, 107, 233, 104, 111, 97, 107, 233, 104, 111, 382, 101, 97, 107, 233, 109, 117,
|
|
11
|
+
97, 107, 233, 109, 117, 382, 101, 97, 107, 233, 382, 101, 97, 107, 250, 97, 107, 250, 382, 101, 97, 107, 253, 97, 107,
|
|
12
|
+
253, 99, 104, 97, 107, 253, 99, 104, 382, 101, 97, 107, 253, 109, 97, 107, 253, 109, 105, 97, 107, 253, 109, 105, 382,
|
|
13
|
+
101, 97, 107, 253, 109, 382, 101, 97, 107, 253, 382, 101, 97, 108, 101, 97, 108, 101, 98, 111, 97, 110, 105, 97, 115,
|
|
14
|
+
105, 97, 118, 353, 97, 107, 97, 382, 98, 97, 98, 101, 122, 98, 101, 122, 111, 98, 111, 108, 98, 111, 108, 97, 98, 111,
|
|
15
|
+
108, 105, 98, 111, 108, 111, 98, 117, 100, 101, 98, 117, 100, 101, 109, 98, 117, 100, 101, 109, 101, 98, 117, 100,
|
|
16
|
+
101, 116, 101, 98, 117, 100, 101, 353, 98, 117, 100, 250, 98, 117, 271, 98, 121, 98, 121, 357, 99, 101, 122, 99, 101,
|
|
17
|
+
122, 111, 100, 110, 101, 115, 100, 111, 101, 353, 116, 101, 104, 111, 104, 111, 99, 105, 105, 105, 98, 97, 105, 99,
|
|
18
|
+
104, 105, 109, 105, 110, 101, 106, 105, 110, 111, 109, 105, 110, 225, 105, 110, 233, 105, 110, 233, 104, 111, 105,
|
|
19
|
+
110, 233, 109, 117, 105, 110, 237, 105, 110, 250, 105, 110, 253, 105, 110, 253, 99, 104, 105, 110, 253, 109, 105, 110,
|
|
20
|
+
253, 109, 105, 106, 97, 106, 101, 106, 101, 104, 111, 106, 101, 106, 106, 101, 109, 117, 106, 117, 107, 107, 97, 109,
|
|
21
|
+
107, 97, 109, 382, 101, 107, 97, 382, 100, 111, 117, 107, 97, 382, 100, 225, 107, 97, 382, 100, 233, 107, 97, 382,
|
|
22
|
+
100, 233, 104, 111, 107, 97, 382, 100, 233, 109, 117, 107, 97, 382, 100, 237, 107, 97, 382, 100, 250, 107, 97, 382,
|
|
23
|
+
100, 253, 107, 97, 382, 100, 253, 99, 104, 107, 97, 382, 100, 253, 109, 107, 97, 382, 100, 253, 109, 105, 107, 100,
|
|
24
|
+
101, 107, 101, 106, 107, 101, 106, 382, 101, 107, 101, 271, 107, 101, 271, 382, 101, 107, 105, 101, 107, 105, 101,
|
|
25
|
+
104, 111, 107, 105, 101, 104, 111, 382, 101, 107, 105, 101, 109, 117, 107, 105, 101, 109, 117, 382, 101, 107, 105,
|
|
26
|
+
101, 382, 101, 107, 111, 104, 111, 107, 111, 109, 107, 111, 109, 117, 107, 111, 117, 107, 111, 117, 382, 101, 107,
|
|
27
|
+
116, 111, 107, 116, 111, 114, 101, 106, 107, 116, 111, 114, 111, 117, 107, 116, 111, 114, 225, 107, 116, 111, 114,
|
|
28
|
+
233, 107, 116, 111, 114, 237, 107, 116, 111, 114, 250, 107, 116, 111, 114, 253, 107, 116, 111, 114, 253, 99, 104, 107,
|
|
29
|
+
116, 111, 114, 253, 109, 107, 116, 111, 114, 253, 109, 105, 107, 117, 107, 225, 107, 225, 382, 101, 107, 233, 107,
|
|
30
|
+
233, 382, 101, 107, 250, 107, 250, 382, 101, 107, 253, 107, 253, 104, 111, 107, 253, 104, 111, 382, 101, 107, 253,
|
|
31
|
+
109, 107, 253, 109, 117, 107, 253, 109, 117, 382, 101, 107, 253, 382, 101, 108, 101, 98, 111, 108, 101, 100, 97, 108,
|
|
32
|
+
101, 100, 97, 382, 101, 108, 101, 110, 109, 97, 109, 97, 106, 250, 109, 97, 108, 109, 97, 108, 97, 109, 97, 108, 105,
|
|
33
|
+
109, 97, 357, 109, 101, 100, 122, 105, 109, 105, 109, 110, 101, 109, 110, 111, 117, 109, 111, 106, 97, 109, 111, 106,
|
|
34
|
+
101, 109, 111, 106, 101, 106, 109, 111, 106, 105, 99, 104, 109, 111, 106, 105, 109, 109, 111, 106, 105, 109, 105, 109,
|
|
35
|
+
111, 106, 111, 117, 109, 111, 106, 117, 109, 111, 382, 110, 111, 109, 117, 109, 117, 115, 105, 97, 109, 117, 115, 105,
|
|
36
|
+
101, 357, 109, 117, 115, 237, 109, 117, 115, 237, 109, 109, 117, 115, 237, 109, 101, 109, 117, 115, 237, 116, 101,
|
|
37
|
+
109, 117, 115, 237, 353, 109, 121, 109, 225, 109, 225, 109, 109, 225, 109, 101, 109, 225, 116, 101, 109, 225, 353,
|
|
38
|
+
109, 244, 99, 357, 109, 244, 106, 109, 244, 106, 104, 111, 109, 244, 382, 101, 109, 244, 382, 101, 109, 109, 244, 382,
|
|
39
|
+
101, 109, 101, 109, 244, 382, 101, 116, 101, 109, 244, 382, 101, 353, 109, 244, 382, 117, 109, 328, 97, 110, 97, 110,
|
|
40
|
+
97, 100, 110, 97, 100, 111, 110, 97, 106, 109, 228, 110, 97, 109, 105, 110, 97, 353, 97, 110, 97, 353, 101, 110, 97,
|
|
41
|
+
353, 101, 106, 110, 97, 353, 105, 110, 97, 353, 105, 99, 104, 110, 97, 353, 105, 109, 110, 97, 353, 105, 109, 105,
|
|
42
|
+
110, 97, 353, 111, 117, 110, 101, 110, 101, 99, 104, 110, 101, 104, 111, 110, 101, 106, 110, 101, 106, 97, 107, 101,
|
|
43
|
+
106, 110, 101, 106, 97, 107, 111, 109, 110, 101, 106, 97, 107, 111, 117, 110, 101, 106, 97, 107, 225, 110, 101, 106,
|
|
44
|
+
97, 107, 233, 110, 101, 106, 97, 107, 233, 104, 111, 110, 101, 106, 97, 107, 233, 109, 117, 110, 101, 106, 97, 107,
|
|
45
|
+
250, 110, 101, 106, 97, 107, 253, 110, 101, 106, 97, 107, 253, 99, 104, 110, 101, 106, 97, 107, 253, 109, 110, 101,
|
|
46
|
+
106, 97, 107, 253, 109, 105, 110, 101, 109, 117, 110, 101, 382, 110, 105, 99, 104, 110, 105, 101, 110, 105, 101, 107,
|
|
47
|
+
116, 111, 114, 101, 106, 110, 105, 101, 107, 116, 111, 114, 111, 109, 110, 105, 101, 107, 116, 111, 114, 111, 117,
|
|
48
|
+
110, 105, 101, 107, 116, 111, 114, 225, 110, 105, 101, 107, 116, 111, 114, 233, 110, 105, 101, 107, 116, 111, 114,
|
|
49
|
+
233, 104, 111, 110, 105, 101, 107, 116, 111, 114, 233, 109, 117, 110, 105, 101, 107, 116, 111, 114, 250, 110, 105,
|
|
50
|
+
101, 107, 116, 111, 114, 253, 110, 105, 101, 107, 116, 111, 114, 253, 99, 104, 110, 105, 101, 107, 116, 111, 114, 253,
|
|
51
|
+
109, 110, 105, 101, 107, 116, 111, 114, 253, 109, 105, 110, 105, 101, 108, 101, 110, 110, 105, 101, 269, 111, 110,
|
|
52
|
+
105, 109, 110, 105, 109, 105, 110, 105, 269, 110, 105, 269, 111, 104, 111, 110, 105, 269, 111, 109, 110, 105, 269,
|
|
53
|
+
111, 109, 117, 110, 105, 269, 237, 109, 110, 111, 110, 225, 109, 110, 225, 115, 110, 225, 353, 110, 225, 353, 104,
|
|
54
|
+
111, 110, 237, 109, 111, 111, 100, 111, 100, 111, 111, 110, 111, 110, 97, 111, 110, 105, 111, 110, 111, 111, 110, 121,
|
|
55
|
+
111, 328, 111, 328, 104, 111, 112, 111, 112, 111, 100, 112, 111, 100, 111, 112, 111, 100, 318, 97, 112, 111, 107, 105,
|
|
56
|
+
97, 318, 112, 111, 112, 111, 100, 112, 111, 112, 114, 105, 112, 111, 116, 111, 109, 112, 111, 122, 97, 112, 114, 101,
|
|
57
|
+
112, 114, 101, 100, 112, 114, 101, 100, 111, 112, 114, 101, 116, 111, 112, 114, 101, 116, 111, 382, 101, 112, 114,
|
|
58
|
+
101, 269, 111, 112, 114, 105, 112, 114, 225, 118, 101, 115, 115, 97, 115, 101, 98, 97, 115, 101, 98, 101, 115, 101,
|
|
59
|
+
98, 111, 117, 115, 101, 109, 115, 105, 115, 109, 101, 115, 111, 115, 111, 109, 115, 116, 101, 115, 118, 111, 106, 115,
|
|
60
|
+
118, 111, 106, 97, 115, 118, 111, 106, 101, 115, 118, 111, 106, 104, 111, 115, 118, 111, 106, 105, 99, 104, 115, 118,
|
|
61
|
+
111, 106, 105, 109, 115, 118, 111, 106, 105, 109, 105, 115, 118, 111, 106, 111, 117, 115, 118, 111, 106, 117, 115,
|
|
62
|
+
118, 111, 106, 237, 109, 115, 250, 116, 97, 116, 97, 107, 116, 97, 107, 101, 106, 116, 97, 107, 101, 106, 116, 111,
|
|
63
|
+
116, 97, 107, 225, 116, 97, 107, 225, 116, 111, 116, 97, 107, 233, 116, 97, 107, 233, 104, 111, 116, 97, 107, 233,
|
|
64
|
+
104, 111, 116, 111, 116, 97, 107, 233, 109, 117, 116, 97, 107, 233, 109, 117, 116, 111, 116, 97, 107, 233, 116, 111,
|
|
65
|
+
116, 97, 107, 237, 116, 97, 107, 250, 116, 97, 107, 250, 116, 111, 116, 97, 107, 253, 116, 97, 107, 253, 116, 111,
|
|
66
|
+
116, 97, 107, 382, 101, 116, 97, 109, 116, 101, 98, 97, 116, 101, 98, 101, 116, 101, 98, 111, 117, 116, 101, 100, 97,
|
|
67
|
+
116, 101, 106, 116, 101, 106, 116, 111, 116, 101, 110, 116, 101, 110, 116, 111, 116, 105, 116, 105, 101, 116, 105,
|
|
68
|
+
101, 116, 111, 116, 105, 101, 382, 116, 111, 116, 111, 104, 111, 116, 111, 104, 111, 116, 111, 116, 111, 104, 116,
|
|
69
|
+
111, 116, 111, 109, 116, 111, 109, 116, 111, 116, 111, 109, 117, 116, 111, 109, 117, 116, 111, 116, 111, 116, 111,
|
|
70
|
+
116, 111, 117, 116, 111, 117, 116, 111, 116, 117, 116, 118, 111, 106, 116, 118, 111, 106, 97, 116, 118, 111, 106, 101,
|
|
71
|
+
116, 118, 111, 106, 101, 106, 116, 118, 111, 106, 104, 111, 116, 118, 111, 106, 105, 116, 118, 111, 106, 105, 99, 104,
|
|
72
|
+
116, 118, 111, 106, 105, 109, 116, 118, 111, 106, 105, 109, 105, 116, 118, 111, 106, 237, 109, 116, 121, 116, 225,
|
|
73
|
+
116, 225, 116, 111, 116, 237, 116, 237, 116, 111, 116, 250, 116, 250, 116, 111, 116, 253, 99, 104, 116, 253, 109, 116,
|
|
74
|
+
253, 109, 105, 116, 253, 109, 116, 111, 117, 117, 382, 118, 118, 97, 109, 105, 118, 97, 353, 97, 118, 97, 353, 101,
|
|
75
|
+
118, 97, 353, 101, 106, 118, 97, 353, 105, 118, 97, 353, 105, 99, 104, 118, 97, 353, 105, 109, 118, 97, 353, 237, 109,
|
|
76
|
+
118, 101, 271, 118, 105, 97, 99, 118, 111, 118, 121, 118, 225, 109, 118, 225, 115, 118, 225, 353, 118, 225, 353, 104,
|
|
77
|
+
111, 118, 353, 97, 107, 118, 353, 101, 116, 99, 105, 118, 353, 101, 116, 107, 97, 118, 353, 101, 116, 107, 111, 118,
|
|
78
|
+
353, 101, 116, 107, 121, 118, 353, 101, 116, 111, 107, 122, 122, 97, 122, 97, 269, 111, 122, 97, 269, 111, 382, 101,
|
|
79
|
+
122, 111, 225, 110, 111, 269, 101, 106, 269, 105, 269, 105, 97, 269, 105, 101, 269, 105, 101, 104, 111, 269, 105, 101,
|
|
80
|
+
109, 117, 269, 105, 117, 269, 111, 269, 111, 104, 111, 269, 111, 109, 269, 111, 109, 117, 269, 111, 117, 269, 111,
|
|
81
|
+
382, 101, 269, 237, 269, 237, 109, 269, 237, 109, 105, 271, 97, 108, 353, 105, 97, 271, 97, 108, 353, 105, 101, 271,
|
|
82
|
+
97, 108, 353, 105, 101, 104, 111, 271, 97, 108, 353, 105, 101, 109, 117, 271, 97, 108, 353, 105, 117, 271, 97, 108,
|
|
83
|
+
353, 111, 109, 271, 97, 108, 353, 111, 117, 271, 97, 108, 353, 237, 271, 97, 108, 353, 237, 99, 104, 271, 97, 108,
|
|
84
|
+
353, 237, 109, 271, 97, 108, 353, 237, 109, 105, 328, 111, 109, 328, 111, 117, 328, 117, 382, 101,
|
|
85
|
+
};
|
|
86
|
+
|
|
87
|
+
static const uint32_t stop_word_offsets[419] = {
|
|
88
|
+
0, 1, 4, 6, 8, 12, 18, 21, 25, 31, 35, 41, 46, 49, 54, 57, 62, 69, 74, 81, 86, 89, 94, 97, 102, 109, 113, 118, 125,
|
|
89
|
+
131, 136, 139, 144, 147, 150, 155, 157, 159, 162, 166, 169, 173, 177, 181, 185, 190, 196, 202, 207, 211, 214, 216,
|
|
90
|
+
219, 222, 226, 230, 232, 236, 238, 242, 243, 246, 249, 251, 255, 259, 262, 265, 270, 275, 278, 281, 284, 289, 293,
|
|
91
|
+
298, 300, 302, 306, 309, 313, 315, 316, 319, 324, 330, 335, 340, 347, 354, 359, 364, 369, 376, 382, 389, 392, 395,
|
|
92
|
+
400, 403, 408, 411, 416, 423, 428, 435, 440, 444, 447, 451, 454, 459, 462, 468, 474, 479, 484, 489, 494, 499, 506,
|
|
93
|
+
512, 519, 521, 523, 527, 529, 533, 535, 539, 541, 545, 551, 554, 558, 564, 568, 572, 576, 582, 585, 587, 591, 594,
|
|
94
|
+
598, 602, 605, 610, 612, 615, 619, 623, 627, 632, 638, 643, 649, 654, 658, 663, 665, 670, 676, 680, 685, 691, 697,
|
|
95
|
+
702, 704, 706, 709, 713, 717, 720, 724, 727, 732, 736, 741, 747, 753, 758, 762, 765, 767, 770, 774, 779, 783, 787,
|
|
96
|
+
791, 796, 800, 806, 811, 817, 822, 824, 828, 832, 835, 842, 849, 856, 862, 868, 876, 884, 890, 896, 904, 911, 919,
|
|
97
|
+
923, 926, 930, 933, 942, 951, 960, 968, 976, 986, 996, 1004, 1012, 1022, 1031, 1041, 1047, 1052, 1055, 1059, 1062,
|
|
98
|
+
1068, 1073, 1079, 1084, 1086, 1089, 1092, 1095, 1100, 1103, 1104, 1106, 1109, 1111, 1114, 1117, 1120, 1123, 1125,
|
|
99
|
+
1129, 1131, 1134, 1138, 1143, 1149, 1154, 1159, 1164, 1168, 1171, 1175, 1180, 1185, 1192, 1197, 1200, 1205, 1206,
|
|
100
|
+
1208, 1212, 1216, 1221, 1224, 1226, 1229, 1231, 1234, 1237, 1241, 1246, 1251, 1257, 1264, 1270, 1277, 1283, 1288,
|
|
101
|
+
1294, 1296, 1298, 1301, 1306, 1313, 1317, 1323, 1327, 1333, 1341, 1347, 1355, 1361, 1365, 1369, 1375, 1379, 1385,
|
|
102
|
+
1390, 1393, 1397, 1401, 1406, 1410, 1413, 1418, 1421, 1426, 1428, 1431, 1436, 1440, 1442, 1446, 1452, 1457, 1460,
|
|
103
|
+
1465, 1469, 1475, 1479, 1482, 1487, 1489, 1493, 1498, 1503, 1509, 1515, 1520, 1527, 1533, 1540, 1546, 1548, 1550,
|
|
104
|
+
1554, 1556, 1560, 1562, 1566, 1570, 1573, 1577, 1582, 1583, 1585, 1586, 1590, 1594, 1598, 1603, 1607, 1613, 1618,
|
|
105
|
+
1623, 1626, 1630, 1632, 1634, 1637, 1640, 1643, 1648, 1652, 1658, 1664, 1670, 1676, 1682, 1683, 1685, 1689, 1695,
|
|
106
|
+
1697, 1700, 1703, 1705, 1708, 1711, 1716, 1721, 1724, 1726, 1730, 1733, 1737, 1740, 1744, 1746, 1749, 1753, 1759,
|
|
107
|
+
1765, 1773, 1781, 1787, 1793, 1799, 1804, 1811, 1817, 1824, 1827, 1830, 1832, 1834,
|
|
108
|
+
};
|
|
109
|
+
|
|
110
|
+
static const uint32_t keep_ranges[50] = {
|
|
111
|
+
48, 57, 65, 90, 97, 122, 193, 193, 196, 196, 201, 201, 205, 205, 211, 212, 218, 218, 221, 221, 225, 225, 228, 228,
|
|
112
|
+
233, 233, 237, 237, 243, 244, 250, 250, 253, 253, 268, 271, 313, 314, 317, 318, 327, 328, 340, 341, 352, 353, 356,
|
|
113
|
+
357, 381, 382,
|
|
114
|
+
};
|
|
115
|
+
|
|
116
|
+
const narsil_language narsil_language_slovak = {
|
|
117
|
+
.name = "slovak",
|
|
118
|
+
.revision = "1",
|
|
119
|
+
.stop_word_units = stop_word_units,
|
|
120
|
+
.stop_word_offsets = stop_word_offsets,
|
|
121
|
+
.stop_word_count = 418,
|
|
122
|
+
.ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
123
|
+
.keep_ranges = keep_ranges,
|
|
124
|
+
.keep_range_count = 25,
|
|
125
|
+
.splits_code_points = 0,
|
|
126
|
+
.strips_possessive = 0,
|
|
127
|
+
.normalises_diacritics = 0,
|
|
128
|
+
.min_token_length = 1,
|
|
129
|
+
.ngram_size = 0,
|
|
130
|
+
.normalise = NULL,
|
|
131
|
+
.stem_by_rules = NULL,
|
|
132
|
+
.create_snowball = NULL,
|
|
133
|
+
.snowball_stem = NULL,
|
|
134
|
+
.close_snowball = NULL,
|
|
135
|
+
};
|
|
@@ -0,0 +1,139 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
#include "../rules.h"
|
|
4
|
+
|
|
5
|
+
#include <stddef.h>
|
|
6
|
+
#include <stdint.h>
|
|
7
|
+
|
|
8
|
+
static const uint16_t stop_word_units[1915] = {
|
|
9
|
+
97, 97, 108, 105, 98, 105, 98, 105, 108, 98, 105, 108, 97, 98, 105, 108, 101, 98, 105, 108, 105, 98, 105, 108, 111,
|
|
10
|
+
98, 105, 116, 105, 98, 108, 105, 122, 117, 98, 111, 98, 111, 100, 111, 98, 111, 106, 111, 98, 111, 108, 106, 98, 111,
|
|
11
|
+
109, 98, 111, 109, 111, 98, 111, 115, 116, 101, 98, 111, 118, 97, 98, 111, 353, 98, 114, 101, 122, 99, 101, 108, 99,
|
|
12
|
+
101, 108, 97, 99, 101, 108, 105, 99, 101, 108, 111, 100, 97, 100, 97, 108, 101, 269, 100, 97, 110, 100, 97, 110, 101,
|
|
13
|
+
115, 100, 97, 116, 117, 109, 100, 101, 115, 101, 116, 100, 101, 115, 101, 116, 97, 100, 101, 115, 101, 116, 105, 100,
|
|
14
|
+
101, 115, 101, 116, 111, 100, 101, 118, 101, 116, 100, 101, 118, 101, 116, 97, 100, 101, 118, 101, 116, 105, 100, 101,
|
|
15
|
+
118, 101, 116, 111, 100, 111, 100, 111, 98, 101, 114, 100, 111, 98, 114, 97, 100, 111, 98, 114, 105, 100, 111, 98,
|
|
16
|
+
114, 111, 100, 111, 107, 108, 101, 114, 100, 111, 108, 100, 111, 108, 103, 100, 111, 108, 103, 97, 100, 111, 108, 103,
|
|
17
|
+
105, 100, 111, 118, 111, 108, 106, 100, 114, 117, 103, 100, 114, 117, 103, 97, 100, 114, 117, 103, 105, 100, 114, 117,
|
|
18
|
+
103, 111, 100, 118, 97, 100, 118, 101, 101, 100, 101, 110, 101, 110, 101, 110, 97, 101, 110, 101, 101, 110, 105, 101,
|
|
19
|
+
110, 107, 114, 97, 116, 101, 110, 111, 103, 97, 103, 111, 114, 103, 111, 115, 112, 97, 103, 111, 115, 112, 111, 100,
|
|
20
|
+
103, 111, 116, 111, 118, 111, 104, 104, 97, 108, 111, 104, 105, 116, 114, 111, 105, 105, 100, 114, 105, 105, 105, 105,
|
|
21
|
+
105, 105, 110, 105, 118, 105, 120, 105, 122, 106, 97, 106, 97, 122, 106, 101, 106, 105, 106, 105, 104, 106, 105, 109,
|
|
22
|
+
106, 111, 106, 117, 116, 114, 105, 107, 107, 97, 100, 97, 114, 107, 97, 100, 97, 114, 107, 111, 108, 105, 107, 97,
|
|
23
|
+
106, 107, 97, 106, 116, 105, 107, 97, 107, 111, 107, 97, 107, 111, 114, 107, 97, 109, 107, 97, 109, 111, 114, 107, 97,
|
|
24
|
+
109, 111, 114, 107, 111, 108, 105, 107, 97, 114, 107, 97, 114, 107, 111, 108, 105, 107, 97, 116, 101, 114, 105, 107,
|
|
25
|
+
111, 108, 105, 107, 100, 97, 106, 107, 100, 111, 107, 100, 111, 114, 107, 100, 111, 114, 107, 111, 108, 105, 107, 101,
|
|
26
|
+
114, 107, 105, 107, 106, 101, 107, 106, 101, 114, 107, 106, 101, 114, 107, 111, 108, 105, 107, 108, 106, 117, 98, 107,
|
|
27
|
+
111, 107, 111, 100, 101, 114, 107, 111, 100, 101, 114, 107, 111, 108, 105, 107, 111, 103, 97, 107, 111, 108, 105, 107,
|
|
28
|
+
111, 107, 111, 109, 117, 107, 111, 116, 107, 114, 97, 116, 101, 107, 107, 114, 97, 116, 107, 97, 107, 114, 97, 116,
|
|
29
|
+
107, 101, 107, 114, 97, 116, 107, 105, 108, 97, 104, 107, 97, 108, 97, 104, 107, 101, 108, 97, 104, 107, 105, 108, 97,
|
|
30
|
+
104, 107, 111, 108, 101, 108, 101, 112, 108, 101, 112, 97, 108, 101, 112, 101, 108, 101, 112, 105, 108, 101, 112, 111,
|
|
31
|
+
108, 101, 116, 111, 109, 97, 106, 104, 101, 110, 109, 97, 106, 104, 110, 97, 109, 97, 106, 104, 110, 105, 109, 97,
|
|
32
|
+
108, 99, 101, 109, 97, 108, 111, 109, 97, 110, 106, 109, 101, 109, 101, 100, 109, 101, 100, 116, 101, 109, 109, 101,
|
|
33
|
+
110, 101, 109, 101, 115, 101, 99, 109, 105, 109, 105, 100, 118, 97, 109, 105, 100, 118, 101, 109, 110, 111, 103, 111,
|
|
34
|
+
109, 111, 106, 109, 111, 106, 97, 109, 111, 106, 101, 109, 111, 114, 97, 109, 111, 114, 97, 106, 111, 109, 111, 114,
|
|
35
|
+
97, 109, 109, 111, 114, 97, 109, 111, 109, 111, 114, 97, 116, 101, 109, 111, 114, 97, 353, 109, 111, 114, 101, 109,
|
|
36
|
+
109, 117, 110, 97, 110, 97, 100, 110, 97, 106, 110, 97, 106, 105, 110, 97, 110, 97, 106, 105, 110, 111, 110, 97, 106,
|
|
37
|
+
109, 97, 110, 106, 110, 97, 106, 117, 110, 97, 106, 118, 101, 269, 110, 97, 109, 110, 97, 109, 114, 101, 269, 110, 97,
|
|
38
|
+
114, 111, 98, 101, 110, 97, 115, 110, 97, 116, 111, 110, 97, 122, 97, 106, 110, 97, 353, 110, 97, 353, 97, 110, 97,
|
|
39
|
+
353, 101, 110, 101, 110, 101, 100, 97, 118, 110, 111, 110, 101, 100, 101, 108, 106, 97, 110, 101, 107, 110, 101, 107,
|
|
40
|
+
97, 110, 101, 107, 97, 106, 110, 101, 107, 97, 116, 101, 114, 101, 110, 101, 107, 97, 116, 101, 114, 105, 110, 101,
|
|
41
|
+
107, 97, 116, 101, 114, 111, 110, 101, 107, 100, 111, 110, 101, 107, 101, 110, 101, 107, 101, 103, 97, 110, 101, 107,
|
|
42
|
+
105, 110, 101, 107, 106, 101, 110, 101, 107, 111, 110, 101, 107, 111, 103, 97, 110, 101, 107, 111, 269, 110, 105, 110,
|
|
43
|
+
105, 104, 269, 101, 110, 105, 107, 97, 109, 111, 114, 110, 105, 107, 100, 97, 114, 110, 105, 107, 106, 101, 114, 110,
|
|
44
|
+
105, 107, 111, 108, 105, 110, 105, 269, 110, 106, 101, 110, 106, 101, 103, 97, 110, 106, 101, 103, 111, 118, 110, 106,
|
|
45
|
+
101, 103, 111, 118, 97, 110, 106, 101, 103, 111, 118, 111, 110, 106, 101, 106, 110, 106, 101, 109, 117, 110, 106, 101,
|
|
46
|
+
110, 110, 106, 101, 110, 97, 110, 106, 101, 110, 111, 110, 106, 105, 110, 106, 105, 104, 110, 106, 105, 104, 111, 118,
|
|
47
|
+
110, 106, 105, 104, 111, 118, 97, 110, 106, 105, 104, 111, 118, 111, 110, 106, 105, 106, 117, 110, 106, 105, 109, 110,
|
|
48
|
+
106, 111, 110, 106, 117, 110, 110, 106, 117, 110, 97, 110, 106, 117, 110, 111, 110, 111, 110, 111, 99, 111, 106, 111,
|
|
49
|
+
111, 98, 111, 98, 97, 111, 98, 101, 111, 98, 111, 106, 101, 111, 100, 111, 100, 112, 114, 116, 111, 100, 112, 114,
|
|
50
|
+
116, 97, 111, 100, 112, 114, 116, 105, 111, 107, 111, 108, 105, 111, 107, 114, 111, 103, 111, 110, 111, 110, 97, 100,
|
|
51
|
+
118, 97, 111, 110, 101, 111, 110, 105, 111, 110, 105, 100, 118, 101, 111, 115, 101, 109, 111, 115, 109, 97, 111, 115,
|
|
52
|
+
109, 105, 111, 115, 109, 111, 112, 97, 112, 101, 116, 112, 101, 116, 97, 112, 101, 116, 101, 107, 112, 101, 116, 105,
|
|
53
|
+
112, 101, 116, 111, 112, 111, 112, 111, 100, 112, 111, 103, 111, 115, 116, 111, 112, 111, 108, 101, 103, 112, 111,
|
|
54
|
+
108, 110, 112, 111, 108, 110, 97, 112, 111, 108, 110, 105, 112, 111, 108, 110, 111, 112, 111, 110, 97, 118, 97, 100,
|
|
55
|
+
105, 112, 111, 110, 101, 100, 101, 108, 106, 101, 107, 112, 111, 110, 111, 118, 110, 111, 112, 111, 116, 101, 109,
|
|
56
|
+
112, 111, 118, 115, 111, 100, 112, 111, 122, 100, 114, 97, 118, 108, 106, 101, 110, 112, 111, 122, 100, 114, 97, 118,
|
|
57
|
+
108, 106, 101, 110, 105, 112, 114, 97, 118, 112, 114, 97, 118, 97, 112, 114, 97, 118, 101, 112, 114, 97, 118, 105,
|
|
58
|
+
112, 114, 97, 118, 111, 112, 114, 97, 122, 101, 110, 112, 114, 97, 122, 110, 97, 112, 114, 97, 122, 110, 111, 112,
|
|
59
|
+
114, 101, 99, 101, 106, 112, 114, 101, 100, 112, 114, 101, 106, 112, 114, 101, 107, 111, 112, 114, 105, 112, 114, 105,
|
|
60
|
+
98, 108, 105, 382, 110, 111, 112, 114, 105, 109, 101, 114, 112, 114, 105, 112, 114, 97, 118, 108, 106, 101, 110, 112,
|
|
61
|
+
114, 105, 112, 114, 97, 118, 108, 106, 101, 110, 97, 112, 114, 105, 112, 114, 97, 118, 108, 106, 101, 110, 105, 112,
|
|
62
|
+
114, 111, 116, 105, 112, 114, 118, 97, 112, 114, 118, 105, 112, 114, 118, 111, 112, 117, 114, 97, 118, 110, 111, 114,
|
|
63
|
+
101, 100, 107, 111, 114, 101, 115, 114, 101, 269, 115, 115, 97, 106, 115, 97, 109, 115, 97, 109, 97, 115, 97, 109,
|
|
64
|
+
101, 115, 97, 109, 105, 115, 97, 109, 111, 115, 101, 115, 101, 98, 101, 115, 101, 98, 105, 115, 101, 100, 97, 106,
|
|
65
|
+
115, 101, 100, 101, 109, 115, 101, 100, 109, 97, 115, 101, 100, 109, 105, 115, 101, 100, 109, 111, 115, 101, 109, 115,
|
|
66
|
+
101, 118, 101, 100, 97, 115, 105, 115, 105, 99, 101, 114, 115, 107, 111, 114, 97, 106, 115, 107, 111, 122, 105, 115,
|
|
67
|
+
108, 97, 98, 115, 109, 111, 115, 111, 115, 111, 98, 111, 116, 97, 115, 112, 101, 116, 115, 114, 101, 100, 97, 115,
|
|
68
|
+
114, 101, 100, 110, 106, 97, 115, 114, 101, 100, 110, 106, 105, 115, 116, 97, 115, 116, 101, 115, 116, 114, 97, 110,
|
|
69
|
+
115, 116, 118, 97, 114, 115, 118, 97, 116, 97, 116, 97, 107, 116, 97, 107, 97, 116, 97, 107, 101, 116, 97, 107, 105,
|
|
70
|
+
116, 97, 107, 111, 116, 97, 107, 111, 106, 116, 97, 109, 116, 101, 116, 101, 98, 101, 116, 101, 98, 105, 116, 101,
|
|
71
|
+
103, 97, 116, 101, 104, 116, 101, 109, 116, 101, 382, 97, 107, 116, 101, 382, 107, 97, 116, 101, 382, 107, 105, 116,
|
|
72
|
+
101, 382, 107, 111, 116, 105, 116, 105, 115, 116, 97, 116, 105, 115, 116, 101, 116, 105, 115, 116, 105, 116, 105, 115,
|
|
73
|
+
116, 111, 116, 106, 97, 116, 111, 116, 111, 100, 97, 116, 111, 107, 114, 97, 116, 116, 111, 108, 105, 107, 111, 116,
|
|
74
|
+
111, 114, 101, 107, 116, 114, 101, 116, 106, 97, 116, 114, 101, 116, 106, 101, 116, 114, 101, 116, 106, 105, 116, 114,
|
|
75
|
+
105, 116, 117, 116, 117, 100, 105, 116, 117, 107, 97, 106, 116, 118, 111, 106, 116, 118, 111, 106, 97, 116, 118, 111,
|
|
76
|
+
106, 101, 118, 118, 97, 106, 117, 118, 97, 109, 118, 97, 115, 118, 97, 353, 118, 97, 353, 97, 118, 97, 353, 101, 118,
|
|
77
|
+
101, 118, 101, 100, 110, 111, 118, 101, 108, 105, 107, 118, 101, 108, 105, 107, 97, 118, 101, 108, 105, 107, 105, 118,
|
|
78
|
+
101, 108, 105, 107, 111, 118, 101, 110, 100, 97, 114, 118, 101, 115, 118, 101, 269, 118, 105, 118, 105, 100, 118, 97,
|
|
79
|
+
118, 105, 105, 118, 105, 105, 105, 118, 105, 115, 111, 107, 118, 105, 115, 111, 107, 97, 118, 105, 115, 111, 107, 101,
|
|
80
|
+
118, 105, 115, 111, 107, 105, 118, 115, 97, 118, 115, 97, 106, 118, 115, 97, 107, 118, 115, 97, 107, 97, 118, 115, 97,
|
|
81
|
+
107, 100, 111, 118, 115, 97, 107, 101, 118, 115, 97, 107, 105, 118, 115, 97, 107, 111, 109, 117, 114, 118, 115, 101,
|
|
82
|
+
118, 115, 101, 103, 97, 118, 115, 105, 118, 115, 111, 118, 269, 97, 115, 105, 104, 118, 269, 101, 114, 97, 106, 122,
|
|
83
|
+
122, 97, 122, 97, 100, 97, 106, 122, 97, 100, 110, 106, 105, 122, 97, 107, 97, 106, 122, 97, 112, 114, 116, 97, 122,
|
|
84
|
+
97, 112, 114, 116, 105, 122, 97, 112, 114, 116, 111, 122, 97, 116, 111, 122, 100, 97, 106, 122, 101, 108, 111, 122,
|
|
85
|
+
103, 111, 114, 97, 106, 122, 117, 110, 97, 106, 269, 101, 269, 101, 115, 116, 111, 269, 101, 116, 114, 116, 97, 269,
|
|
86
|
+
101, 116, 114, 116, 101, 107, 269, 101, 116, 114, 116, 105, 269, 101, 116, 114, 116, 111, 269, 101, 122, 269, 105,
|
|
87
|
+
103, 97, 118, 353, 101, 108, 101, 353, 101, 115, 116, 353, 101, 115, 116, 97, 353, 101, 115, 116, 105, 353, 101, 115,
|
|
88
|
+
116, 111, 353, 116, 105, 114, 105, 382, 101,
|
|
89
|
+
};
|
|
90
|
+
|
|
91
|
+
static const uint32_t stop_word_offsets[428] = {
|
|
92
|
+
0, 1, 4, 6, 9, 13, 17, 21, 25, 29, 34, 36, 40, 44, 48, 51, 55, 60, 64, 67, 71, 74, 78, 82, 86, 88, 93, 96, 101, 106,
|
|
93
|
+
111, 117, 123, 129, 134, 140, 146, 152, 154, 159, 164, 169, 174, 180, 183, 187, 192, 197, 203, 207, 212, 217, 222,
|
|
94
|
+
225, 228, 232, 234, 237, 240, 243, 249, 252, 254, 257, 262, 268, 274, 275, 279, 284, 285, 288, 290, 293, 295, 297,
|
|
95
|
+
299, 301, 303, 306, 308, 310, 313, 316, 318, 323, 324, 329, 338, 341, 346, 350, 355, 358, 363, 372, 375, 382, 392,
|
|
96
|
+
396, 399, 403, 411, 414, 416, 419, 423, 431, 436, 438, 443, 452, 456, 462, 466, 469, 475, 481, 487, 493, 498, 503,
|
|
97
|
+
508, 513, 515, 518, 522, 526, 530, 534, 538, 544, 550, 556, 561, 565, 569, 571, 574, 580, 584, 589, 591, 596, 601,
|
|
98
|
+
606, 609, 613, 617, 621, 627, 632, 638, 644, 649, 654, 656, 658, 661, 664, 670, 676, 683, 687, 693, 696, 702, 708,
|
|
99
|
+
711, 715, 720, 723, 727, 731, 733, 740, 747, 750, 754, 759, 767, 775, 783, 788, 792, 798, 802, 807, 811, 817, 822,
|
|
100
|
+
824, 829, 836, 842, 848, 854, 857, 860, 865, 871, 878, 885, 889, 894, 898, 903, 908, 911, 915, 921, 928, 935, 940,
|
|
101
|
+
944, 947, 951, 956, 961, 963, 968, 969, 971, 974, 977, 982, 984, 989, 995, 1001, 1006, 1011, 1013, 1019, 1022, 1025,
|
|
102
|
+
1031, 1035, 1039, 1043, 1047, 1049, 1052, 1056, 1061, 1065, 1069, 1071, 1074, 1081, 1086, 1090, 1095, 1100, 1105,
|
|
103
|
+
1113, 1123, 1130, 1135, 1141, 1152, 1164, 1168, 1173, 1178, 1183, 1188, 1194, 1200, 1206, 1212, 1216, 1220, 1225,
|
|
104
|
+
1228, 1237, 1243, 1254, 1266, 1278, 1283, 1287, 1291, 1295, 1297, 1302, 1307, 1310, 1313, 1314, 1317, 1320, 1324,
|
|
105
|
+
1328, 1332, 1336, 1338, 1342, 1346, 1351, 1356, 1361, 1366, 1371, 1374, 1380, 1382, 1387, 1393, 1398, 1402, 1405,
|
|
106
|
+
1407, 1413, 1417, 1422, 1429, 1436, 1439, 1442, 1447, 1452, 1455, 1457, 1460, 1464, 1468, 1472, 1476, 1481, 1484,
|
|
107
|
+
1486, 1490, 1494, 1498, 1501, 1504, 1509, 1514, 1519, 1524, 1526, 1531, 1536, 1541, 1546, 1549, 1551, 1555, 1561,
|
|
108
|
+
1567, 1572, 1578, 1584, 1590, 1593, 1595, 1599, 1604, 1608, 1613, 1618, 1619, 1623, 1626, 1629, 1632, 1636, 1640,
|
|
109
|
+
1642, 1647, 1652, 1658, 1664, 1670, 1676, 1679, 1682, 1684, 1689, 1692, 1696, 1701, 1707, 1713, 1719, 1722, 1726,
|
|
110
|
+
1730, 1735, 1741, 1746, 1751, 1759, 1762, 1767, 1770, 1773, 1779, 1785, 1786, 1788, 1793, 1799, 1804, 1810, 1816,
|
|
111
|
+
1822, 1826, 1830, 1834, 1840, 1845, 1847, 1852, 1858, 1865, 1871, 1877, 1880, 1885, 1889, 1893, 1898, 1903, 1908,
|
|
112
|
+
1913, 1915,
|
|
113
|
+
};
|
|
114
|
+
|
|
115
|
+
static const uint32_t keep_ranges[28] = {
|
|
116
|
+
48, 57, 65, 90, 97, 122, 193, 193, 201, 201, 211, 211, 218, 218, 225, 225, 233, 233, 243, 243, 250, 250, 268, 269,
|
|
117
|
+
352, 353, 381, 382,
|
|
118
|
+
};
|
|
119
|
+
|
|
120
|
+
const narsil_language narsil_language_slovenian = {
|
|
121
|
+
.name = "slovenian",
|
|
122
|
+
.revision = "1",
|
|
123
|
+
.stop_word_units = stop_word_units,
|
|
124
|
+
.stop_word_offsets = stop_word_offsets,
|
|
125
|
+
.stop_word_count = 427,
|
|
126
|
+
.ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
127
|
+
.keep_ranges = keep_ranges,
|
|
128
|
+
.keep_range_count = 14,
|
|
129
|
+
.splits_code_points = 0,
|
|
130
|
+
.strips_possessive = 0,
|
|
131
|
+
.normalises_diacritics = 0,
|
|
132
|
+
.min_token_length = 1,
|
|
133
|
+
.ngram_size = 0,
|
|
134
|
+
.normalise = narsil_slovenian_normalise,
|
|
135
|
+
.stem_by_rules = narsil_slovenian_stem,
|
|
136
|
+
.create_snowball = NULL,
|
|
137
|
+
.snowball_stem = NULL,
|
|
138
|
+
.close_snowball = NULL,
|
|
139
|
+
};
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
#include "../rules.h"
|
|
4
|
+
|
|
5
|
+
#include <stddef.h>
|
|
6
|
+
#include <stdint.h>
|
|
7
|
+
|
|
8
|
+
static const uint16_t stop_word_units[269] = {
|
|
9
|
+
1574, 1742, 1605, 1749, 1574, 1742, 1608, 1749, 1574, 1749, 1605, 1574, 1749, 1608, 1574, 1749, 1608, 1575, 1606,
|
|
10
|
+
1574, 1749, 1608, 1749, 1740, 1576, 1734, 1576, 1742, 1576, 1742, 1580, 1711, 1749, 1576, 1749, 1576, 1749, 1576,
|
|
11
|
+
1742, 1576, 1749, 1583, 1749, 1605, 1576, 1749, 1585, 1583, 1749, 1605, 1576, 1749, 1585, 1604, 1749, 1576, 1749,
|
|
12
|
+
1585, 1749, 1608, 1740, 1576, 1749, 1585, 1749, 1608, 1749, 1576, 1749, 1604, 1575, 1740, 1576, 1749, 1662, 1742,
|
|
13
|
+
1740, 1578, 1734, 1578, 1742, 1580, 1711, 1749, 1583, 1608, 1575, 1740, 1583, 1608, 1608, 1583, 1749, 1583, 1749,
|
|
14
|
+
1705, 1575, 1578, 1583, 1749, 1711, 1749, 1717, 1587, 1749, 1585, 1604, 1742, 1604, 1749, 1604, 1749, 1576, 1575,
|
|
15
|
+
1576, 1749, 1578, 1604, 1749, 1576, 1575, 1578, 1740, 1604, 1749, 1576, 1575, 1585, 1749, 1740, 1604, 1749, 1576,
|
|
16
|
+
1585, 1742, 1578, 1740, 1604, 1749, 1576, 1606, 1604, 1749, 1576, 1749, 1585, 1604, 1749, 1576, 1749, 1740, 1606,
|
|
17
|
+
1740, 1604, 1749, 1583, 1749, 1605, 1604, 1749, 1585, 1742, 1604, 1749, 1585, 1742, 1711, 1575, 1604, 1749, 1585,
|
|
18
|
+
1749, 1608, 1740, 1604, 1749, 1587, 1749, 1585, 1604, 1749, 1604, 1575, 1740, 1749, 1606, 1604, 1749, 1606, 1575,
|
|
19
|
+
1608, 1604, 1749, 1606, 1742, 1608, 1604, 1749, 1608, 1604, 1749, 1662, 1742, 1606, 1575, 1608, 1740, 1604, 1749,
|
|
20
|
+
1688, 1742, 1585, 1604, 1749, 1711, 1749, 1717, 1605, 1606, 1606, 1575, 1608, 1606, 1742, 1608, 1575, 1606, 1607,
|
|
21
|
+
1749, 1585, 1607, 1749, 1585, 1608, 1749, 1607, 1575, 1608, 1608, 1749, 1705, 1662, 1575, 1588, 1662, 1742, 1662,
|
|
22
|
+
1742, 1588, 1670, 1749, 1606, 1583, 1705, 1585, 1583, 1705, 1749, 1726, 1749, 1585, 1726, 1749, 1585, 1608, 1749,
|
|
23
|
+
1726, 1575, 1740,
|
|
24
|
+
};
|
|
25
|
+
|
|
26
|
+
static const uint32_t stop_word_offsets[65] = {
|
|
27
|
+
0, 4, 8, 11, 14, 19, 24, 26, 28, 33, 35, 39, 44, 50, 55, 61, 67, 72, 77, 79, 81, 84, 88, 91, 93, 98, 103, 106, 108,
|
|
28
|
+
110, 117, 123, 130, 137, 141, 146, 153, 158, 162, 168, 174, 179, 186, 191, 196, 199, 207, 212, 217, 219, 222, 227,
|
|
29
|
+
230, 237, 238, 241, 244, 246, 249, 253, 256, 258, 261, 268, 269,
|
|
30
|
+
};
|
|
31
|
+
|
|
32
|
+
static const uint32_t keep_ranges[14] = {
|
|
33
|
+
48, 57, 65, 90, 97, 122, 1569, 1641, 1646, 1749, 1776, 1785, 8204, 8204,
|
|
34
|
+
};
|
|
35
|
+
|
|
36
|
+
const narsil_language narsil_language_sorani = {
|
|
37
|
+
.name = "sorani",
|
|
38
|
+
.revision = "1",
|
|
39
|
+
.stop_word_units = stop_word_units,
|
|
40
|
+
.stop_word_offsets = stop_word_offsets,
|
|
41
|
+
.stop_word_count = 64,
|
|
42
|
+
.ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
43
|
+
.keep_ranges = keep_ranges,
|
|
44
|
+
.keep_range_count = 7,
|
|
45
|
+
.splits_code_points = 0,
|
|
46
|
+
.strips_possessive = 0,
|
|
47
|
+
.normalises_diacritics = 0,
|
|
48
|
+
.min_token_length = 1,
|
|
49
|
+
.ngram_size = 0,
|
|
50
|
+
.normalise = narsil_sorani_normalise,
|
|
51
|
+
.stem_by_rules = NULL,
|
|
52
|
+
.create_snowball = NULL,
|
|
53
|
+
.snowball_stem = NULL,
|
|
54
|
+
.close_snowball = NULL,
|
|
55
|
+
};
|
|
@@ -0,0 +1,84 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
#include "../snowball/spanish_stemmer.h"
|
|
4
|
+
|
|
5
|
+
#include <stddef.h>
|
|
6
|
+
#include <stdint.h>
|
|
7
|
+
|
|
8
|
+
static const uint16_t stop_word_units[899] = {
|
|
9
|
+
97, 97, 108, 97, 108, 103, 111, 97, 108, 103, 117, 110, 97, 97, 108, 103, 117, 110, 97, 115, 97, 108, 103, 117, 110,
|
|
10
|
+
111, 97, 108, 103, 117, 110, 111, 115, 97, 108, 103, 250, 110, 97, 109, 98, 111, 115, 97, 110, 116, 101, 97, 110, 116,
|
|
11
|
+
101, 115, 97, 113, 117, 101, 108, 97, 113, 117, 101, 108, 108, 97, 97, 113, 117, 101, 108, 108, 97, 115, 97, 113, 117,
|
|
12
|
+
101, 108, 108, 111, 97, 113, 117, 101, 108, 108, 111, 115, 97, 113, 117, 237, 97, 114, 114, 105, 98, 97, 97, 115, 237,
|
|
13
|
+
97, 117, 110, 113, 117, 101, 97, 250, 110, 98, 97, 106, 111, 98, 97, 115, 116, 97, 110, 116, 101, 98, 105, 101, 110,
|
|
14
|
+
99, 97, 100, 97, 99, 97, 115, 105, 99, 111, 109, 111, 99, 111, 110, 99, 111, 110, 116, 114, 97, 99, 117, 97, 108, 99,
|
|
15
|
+
117, 97, 108, 101, 115, 99, 117, 97, 110, 100, 111, 99, 117, 225, 110, 100, 111, 99, 117, 225, 110, 116, 111, 99, 117,
|
|
16
|
+
225, 110, 116, 111, 115, 100, 101, 100, 101, 108, 100, 101, 109, 225, 115, 100, 101, 110, 116, 114, 111, 100, 101,
|
|
17
|
+
115, 100, 101, 100, 111, 110, 100, 101, 100, 111, 115, 100, 117, 114, 97, 110, 116, 101, 100, 243, 110, 100, 101, 101,
|
|
18
|
+
108, 101, 108, 108, 97, 101, 108, 108, 97, 115, 101, 108, 108, 111, 101, 108, 108, 111, 115, 101, 110, 101, 110, 99,
|
|
19
|
+
105, 109, 97, 101, 110, 116, 111, 110, 99, 101, 115, 101, 110, 116, 114, 101, 101, 114, 97, 101, 115, 97, 101, 115,
|
|
20
|
+
97, 115, 101, 115, 101, 101, 115, 111, 101, 115, 111, 115, 101, 115, 116, 97, 101, 115, 116, 97, 98, 97, 101, 115,
|
|
21
|
+
116, 97, 100, 111, 101, 115, 116, 97, 115, 101, 115, 116, 101, 101, 115, 116, 111, 101, 115, 116, 111, 115, 101, 115,
|
|
22
|
+
116, 225, 101, 115, 116, 225, 110, 102, 117, 101, 102, 117, 101, 114, 97, 102, 117, 101, 114, 111, 110, 104, 97, 104,
|
|
23
|
+
97, 99, 101, 104, 97, 99, 101, 110, 104, 97, 99, 101, 114, 104, 97, 99, 105, 97, 104, 97, 110, 104, 97, 115, 116, 97,
|
|
24
|
+
104, 97, 121, 108, 97, 108, 97, 115, 108, 101, 108, 101, 115, 108, 111, 108, 111, 115, 108, 117, 101, 103, 111, 109,
|
|
25
|
+
97, 115, 109, 101, 109, 101, 106, 111, 114, 109, 101, 110, 111, 115, 109, 105, 109, 105, 101, 110, 116, 114, 97, 115,
|
|
26
|
+
109, 105, 115, 109, 105, 115, 109, 97, 109, 105, 115, 109, 111, 109, 117, 99, 104, 97, 109, 117, 99, 104, 97, 115,
|
|
27
|
+
109, 117, 99, 104, 111, 109, 117, 99, 104, 111, 115, 109, 117, 121, 109, 225, 115, 109, 237, 109, 237, 97, 109, 237,
|
|
28
|
+
111, 110, 97, 100, 97, 110, 105, 110, 105, 110, 103, 117, 110, 97, 110, 105, 110, 103, 117, 110, 111, 110, 105, 110,
|
|
29
|
+
103, 250, 110, 110, 111, 110, 111, 115, 110, 111, 115, 111, 116, 114, 97, 115, 110, 111, 115, 111, 116, 114, 111, 115,
|
|
30
|
+
110, 117, 101, 115, 116, 114, 97, 110, 117, 101, 115, 116, 114, 97, 115, 110, 117, 101, 115, 116, 114, 111, 110, 117,
|
|
31
|
+
101, 115, 116, 114, 111, 115, 110, 117, 110, 99, 97, 111, 111, 115, 111, 116, 114, 97, 111, 116, 114, 97, 115, 111,
|
|
32
|
+
116, 114, 111, 111, 116, 114, 111, 115, 112, 97, 114, 97, 112, 101, 114, 111, 112, 111, 99, 97, 112, 111, 99, 97, 115,
|
|
33
|
+
112, 111, 99, 111, 112, 111, 99, 111, 115, 112, 111, 114, 112, 111, 114, 113, 117, 101, 113, 117, 101, 113, 117, 105,
|
|
34
|
+
101, 110, 113, 117, 105, 233, 110, 113, 117, 233, 115, 101, 115, 101, 97, 115, 101, 103, 250, 110, 115, 101, 114, 115,
|
|
35
|
+
101, 114, 225, 115, 105, 115, 105, 100, 111, 115, 105, 110, 115, 105, 110, 111, 115, 111, 98, 114, 101, 115, 111, 109,
|
|
36
|
+
111, 115, 115, 111, 110, 115, 111, 121, 115, 117, 115, 117, 115, 115, 117, 121, 97, 115, 117, 121, 97, 115, 115, 117,
|
|
37
|
+
121, 111, 115, 237, 116, 97, 109, 98, 105, 233, 110, 116, 97, 110, 116, 97, 110, 116, 111, 116, 101, 116, 101, 110,
|
|
38
|
+
103, 111, 116, 105, 116, 105, 101, 110, 101, 116, 105, 101, 110, 101, 110, 116, 111, 100, 97, 116, 111, 100, 97, 115,
|
|
39
|
+
116, 111, 100, 97, 118, 237, 97, 116, 111, 100, 111, 116, 111, 100, 111, 115, 116, 117, 116, 117, 115, 116, 117, 121,
|
|
40
|
+
97, 116, 117, 121, 111, 116, 250, 117, 110, 117, 110, 97, 117, 110, 97, 115, 117, 110, 111, 117, 110, 111, 115, 117,
|
|
41
|
+
115, 116, 101, 100, 117, 115, 116, 101, 100, 101, 115, 118, 97, 118, 97, 109, 111, 115, 118, 101, 114, 118, 101, 122,
|
|
42
|
+
118, 111, 115, 111, 116, 114, 97, 115, 118, 111, 115, 111, 116, 114, 111, 115, 118, 117, 101, 115, 116, 114, 97, 118,
|
|
43
|
+
117, 101, 115, 116, 114, 97, 115, 118, 117, 101, 115, 116, 114, 111, 118, 117, 101, 115, 116, 114, 111, 115, 121, 121,
|
|
44
|
+
97, 121, 111, 233, 108, 233, 115, 116, 97, 233, 115, 116, 97, 115, 233, 115, 116, 101, 233, 115, 116, 111, 115, 250,
|
|
45
|
+
108, 116, 105, 109, 97, 250, 108, 116, 105, 109, 97, 115, 250, 108, 116, 105, 109, 111, 250, 108, 116, 105, 109, 111,
|
|
46
|
+
115,
|
|
47
|
+
};
|
|
48
|
+
|
|
49
|
+
static const uint32_t stop_word_offsets[203] = {
|
|
50
|
+
0, 1, 3, 7, 13, 20, 26, 33, 38, 43, 47, 52, 57, 64, 72, 79, 87, 91, 97, 100, 106, 109, 113, 121, 125, 129, 133, 137,
|
|
51
|
+
140, 146, 150, 156, 162, 168, 174, 181, 183, 186, 191, 197, 202, 207, 210, 217, 222, 224, 228, 233, 237, 242, 244,
|
|
52
|
+
250, 258, 263, 266, 269, 273, 276, 279, 283, 287, 293, 299, 304, 308, 312, 317, 321, 326, 329, 334, 340, 342, 346,
|
|
53
|
+
351, 356, 361, 364, 369, 372, 374, 377, 379, 382, 384, 387, 392, 395, 397, 402, 407, 409, 417, 420, 425, 430, 435,
|
|
54
|
+
441, 446, 452, 455, 458, 460, 463, 466, 470, 472, 479, 486, 492, 494, 497, 505, 513, 520, 528, 535, 543, 548, 549,
|
|
55
|
+
551, 555, 560, 564, 569, 573, 577, 581, 586, 590, 595, 598, 604, 607, 612, 617, 620, 622, 625, 630, 633, 637, 639,
|
|
56
|
+
643, 646, 650, 655, 660, 663, 666, 668, 671, 675, 680, 684, 686, 693, 696, 701, 703, 708, 710, 715, 721, 725, 730,
|
|
57
|
+
737, 741, 746, 748, 751, 755, 759, 761, 763, 766, 770, 773, 777, 782, 789, 791, 796, 799, 802, 810, 818, 825, 833,
|
|
58
|
+
840, 848, 849, 851, 853, 855, 859, 864, 868, 873, 879, 886, 892, 899,
|
|
59
|
+
};
|
|
60
|
+
|
|
61
|
+
static const uint32_t keep_ranges[16] = {
|
|
62
|
+
48, 57, 65, 90, 97, 122, 193, 214, 216, 218, 220, 220, 225, 250, 252, 252,
|
|
63
|
+
};
|
|
64
|
+
|
|
65
|
+
const narsil_language narsil_language_spanish = {
|
|
66
|
+
.name = "spanish",
|
|
67
|
+
.revision = "8dc152fd2fcce882",
|
|
68
|
+
.stop_word_units = stop_word_units,
|
|
69
|
+
.stop_word_offsets = stop_word_offsets,
|
|
70
|
+
.stop_word_count = 202,
|
|
71
|
+
.ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
72
|
+
.keep_ranges = keep_ranges,
|
|
73
|
+
.keep_range_count = 8,
|
|
74
|
+
.splits_code_points = 0,
|
|
75
|
+
.strips_possessive = 0,
|
|
76
|
+
.normalises_diacritics = 0,
|
|
77
|
+
.min_token_length = 1,
|
|
78
|
+
.ngram_size = 0,
|
|
79
|
+
.normalise = NULL,
|
|
80
|
+
.stem_by_rules = NULL,
|
|
81
|
+
.create_snowball = spanish_create_env,
|
|
82
|
+
.snowball_stem = spanish_stem,
|
|
83
|
+
.close_snowball = spanish_close_env,
|
|
84
|
+
};
|
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
#include "../rules.h"
|
|
4
|
+
|
|
5
|
+
#include <stddef.h>
|
|
6
|
+
#include <stdint.h>
|
|
7
|
+
|
|
8
|
+
static const uint16_t stop_word_units[426] = {
|
|
9
|
+
97, 109, 97, 97, 117, 98, 97, 97, 100, 97, 98, 97, 100, 111, 98, 97, 108, 105, 98, 97, 115, 105, 98, 105, 108, 97, 99,
|
|
10
|
+
104, 97, 99, 104, 101, 99, 104, 105, 110, 105, 100, 97, 105, 109, 97, 101, 110, 100, 97, 112, 111, 103, 97, 110, 105,
|
|
11
|
+
104, 97, 100, 105, 104, 97, 107, 117, 110, 97, 104, 97, 108, 97, 102, 117, 104, 97, 112, 97, 104, 97, 112, 97, 110,
|
|
12
|
+
97, 104, 97, 115, 97, 104, 97, 116, 97, 104, 105, 105, 104, 105, 118, 105, 104, 105, 118, 121, 111, 104, 105, 121,
|
|
13
|
+
111, 104, 105, 122, 111, 104, 117, 107, 117, 105, 106, 97, 112, 111, 107, 117, 119, 97, 105, 107, 105, 119, 97, 105,
|
|
14
|
+
108, 101, 105, 108, 105, 105, 110, 103, 97, 119, 97, 105, 119, 97, 112, 111, 106, 117, 117, 107, 97, 98, 105, 115, 97,
|
|
15
|
+
107, 97, 98, 108, 97, 107, 97, 109, 97, 107, 97, 109, 119, 101, 107, 97, 114, 105, 98, 117, 107, 97, 116, 105, 107,
|
|
16
|
+
97, 107, 105, 100, 111, 103, 111, 107, 105, 108, 97, 107, 105, 115, 104, 97, 107, 111, 116, 101, 107, 117, 104, 117,
|
|
17
|
+
115, 117, 107, 117, 116, 111, 107, 97, 107, 117, 119, 97, 107, 119, 97, 107, 119, 97, 109, 98, 97, 107, 119, 97, 110,
|
|
18
|
+
105, 107, 119, 101, 108, 105, 108, 97, 108, 97, 98, 100, 97, 108, 97, 107, 105, 110, 105, 108, 105, 110, 105, 109, 97,
|
|
19
|
+
114, 97, 109, 98, 97, 108, 105, 109, 98, 101, 108, 101, 109, 101, 110, 103, 105, 109, 112, 97, 107, 97, 110, 97, 110,
|
|
20
|
+
97, 110, 105, 110, 100, 97, 110, 105, 110, 100, 105, 111, 110, 100, 105, 121, 111, 110, 105, 110, 105, 110, 105, 110,
|
|
21
|
+
106, 101, 110, 121, 105, 110, 103, 105, 110, 121, 117, 109, 97, 112, 97, 108, 101, 112, 101, 110, 103, 105, 110, 101,
|
|
22
|
+
112, 105, 97, 115, 97, 110, 97, 115, 97, 115, 97, 115, 97, 119, 97, 115, 105, 115, 105, 121, 111, 116, 97, 110, 103,
|
|
23
|
+
117, 116, 97, 121, 97, 114, 105, 116, 101, 110, 97, 116, 117, 118, 105, 112, 105, 119, 97, 119, 97, 107, 97, 116, 105,
|
|
24
|
+
119, 97, 107, 101, 119, 97, 108, 97, 119, 97, 112, 105, 119, 101, 110, 103, 105, 119, 111, 116, 101, 121, 97, 121, 97,
|
|
25
|
+
107, 101, 121, 97, 110, 103, 117, 121, 97, 111, 121, 101, 116, 117, 121, 111, 116, 101, 122, 97, 122, 97, 105, 100,
|
|
26
|
+
105, 122, 111, 116, 101,
|
|
27
|
+
};
|
|
28
|
+
|
|
29
|
+
static const uint32_t stop_word_offsets[98] = {
|
|
30
|
+
0, 3, 5, 10, 14, 18, 22, 26, 32, 37, 42, 48, 52, 56, 62, 68, 72, 78, 82, 86, 89, 93, 98, 102, 106, 110, 119, 124, 127,
|
|
31
|
+
130, 136, 141, 144, 150, 155, 159, 164, 170, 176, 182, 186, 191, 195, 201, 207, 211, 214, 220, 225, 230, 232, 237,
|
|
32
|
+
243, 247, 251, 256, 261, 266, 271, 273, 277, 282, 286, 291, 293, 297, 300, 306, 311, 315, 322, 325, 329, 333, 337,
|
|
33
|
+
339, 343, 348, 354, 358, 360, 364, 366, 372, 376, 380, 384, 389, 393, 395, 399, 404, 407, 411, 415, 417, 422, 426,
|
|
34
|
+
};
|
|
35
|
+
|
|
36
|
+
static const uint32_t keep_ranges[8] = {
|
|
37
|
+
39, 39, 48, 57, 65, 90, 97, 122,
|
|
38
|
+
};
|
|
39
|
+
|
|
40
|
+
const narsil_language narsil_language_swahili = {
|
|
41
|
+
.name = "swahili",
|
|
42
|
+
.revision = "1",
|
|
43
|
+
.stop_word_units = stop_word_units,
|
|
44
|
+
.stop_word_offsets = stop_word_offsets,
|
|
45
|
+
.stop_word_count = 97,
|
|
46
|
+
.ascii_keep = {0x03FF008000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
47
|
+
.keep_ranges = keep_ranges,
|
|
48
|
+
.keep_range_count = 4,
|
|
49
|
+
.splits_code_points = 0,
|
|
50
|
+
.strips_possessive = 0,
|
|
51
|
+
.normalises_diacritics = 0,
|
|
52
|
+
.min_token_length = 1,
|
|
53
|
+
.ngram_size = 0,
|
|
54
|
+
.normalise = NULL,
|
|
55
|
+
.stem_by_rules = narsil_swahili_stem,
|
|
56
|
+
.create_snowball = NULL,
|
|
57
|
+
.snowball_stem = NULL,
|
|
58
|
+
.close_snowball = NULL,
|
|
59
|
+
};
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
#include "../snowball/swedish_stemmer.h"
|
|
4
|
+
|
|
5
|
+
#include <stddef.h>
|
|
6
|
+
#include <stdint.h>
|
|
7
|
+
|
|
8
|
+
static const uint16_t stop_word_units[421] = {
|
|
9
|
+
97, 108, 108, 97, 97, 108, 108, 116, 97, 116, 116, 97, 118, 98, 108, 101, 118, 98, 108, 105, 98, 108, 105, 114, 98,
|
|
10
|
+
108, 105, 118, 105, 116, 100, 101, 100, 101, 109, 100, 101, 110, 100, 101, 110, 110, 97, 100, 101, 114, 97, 115, 100,
|
|
11
|
+
101, 115, 115, 100, 101, 115, 115, 97, 100, 101, 116, 100, 101, 116, 116, 97, 100, 105, 103, 100, 105, 110, 100, 105,
|
|
12
|
+
110, 97, 100, 105, 116, 116, 100, 117, 100, 228, 114, 100, 229, 101, 102, 116, 101, 114, 101, 106, 101, 108, 108, 101,
|
|
13
|
+
114, 101, 110, 101, 114, 101, 114, 97, 101, 114, 116, 101, 116, 116, 102, 114, 229, 110, 102, 246, 114, 104, 97, 104,
|
|
14
|
+
97, 100, 101, 104, 97, 110, 104, 97, 110, 115, 104, 97, 114, 104, 101, 110, 110, 101, 104, 101, 110, 110, 101, 115,
|
|
15
|
+
104, 111, 110, 104, 111, 110, 111, 109, 104, 117, 114, 104, 228, 114, 105, 105, 99, 107, 101, 105, 110, 103, 101, 110,
|
|
16
|
+
105, 110, 111, 109, 105, 110, 116, 101, 106, 97, 103, 106, 117, 107, 97, 110, 107, 117, 110, 100, 101, 109, 97, 110,
|
|
17
|
+
109, 101, 100, 109, 101, 108, 108, 97, 110, 109, 101, 110, 109, 105, 103, 109, 105, 110, 109, 105, 110, 97, 109, 105,
|
|
18
|
+
116, 116, 109, 111, 116, 109, 121, 99, 107, 101, 116, 110, 105, 110, 117, 110, 228, 114, 110, 229, 103, 111, 110, 110,
|
|
19
|
+
229, 103, 111, 116, 110, 229, 103, 114, 97, 111, 99, 104, 111, 109, 111, 115, 115, 112, 229, 115, 97, 109, 109, 97,
|
|
20
|
+
115, 101, 100, 97, 110, 115, 105, 103, 115, 105, 110, 115, 105, 110, 97, 115, 105, 116, 116, 115, 106, 228, 108, 118,
|
|
21
|
+
115, 107, 117, 108, 108, 101, 115, 111, 109, 115, 229, 115, 229, 100, 97, 110, 115, 229, 100, 97, 110, 97, 115, 229,
|
|
22
|
+
100, 97, 110, 116, 116, 105, 108, 108, 117, 110, 100, 101, 114, 117, 112, 112, 117, 116, 117, 116, 97, 110, 118, 97,
|
|
23
|
+
100, 118, 97, 114, 118, 97, 114, 97, 118, 97, 114, 102, 246, 114, 118, 97, 114, 105, 116, 118, 97, 114, 106, 101, 118,
|
|
24
|
+
97, 114, 115, 118, 97, 114, 116, 118, 101, 109, 118, 105, 118, 105, 100, 118, 105, 108, 107, 97, 118, 105, 108, 107,
|
|
25
|
+
97, 115, 118, 105, 108, 107, 101, 110, 118, 105, 108, 107, 101, 116, 118, 229, 114, 118, 229, 114, 97, 118, 229, 114,
|
|
26
|
+
116, 228, 110, 228, 114, 229, 116, 246, 118, 101, 114,
|
|
27
|
+
};
|
|
28
|
+
|
|
29
|
+
static const uint32_t stop_word_offsets[115] = {
|
|
30
|
+
0, 4, 8, 11, 13, 17, 20, 24, 30, 32, 35, 38, 43, 48, 52, 57, 60, 65, 68, 71, 75, 79, 81, 84, 86, 91, 93, 98, 100, 102,
|
|
31
|
+
105, 108, 111, 115, 118, 120, 124, 127, 131, 134, 139, 145, 148, 153, 156, 159, 160, 164, 169, 173, 177, 180, 182,
|
|
32
|
+
185, 190, 193, 196, 202, 205, 208, 211, 215, 219, 222, 228, 230, 232, 235, 240, 245, 250, 253, 255, 258, 260, 265,
|
|
33
|
+
270, 273, 276, 280, 284, 289, 295, 298, 300, 305, 311, 317, 321, 326, 329, 331, 335, 338, 341, 345, 351, 356, 361,
|
|
34
|
+
365, 369, 372, 374, 377, 382, 388, 394, 400, 403, 407, 411, 413, 415, 417, 421,
|
|
35
|
+
};
|
|
36
|
+
|
|
37
|
+
static const uint32_t keep_ranges[24] = {
|
|
38
|
+
45, 45, 48, 57, 65, 90, 97, 122, 196, 197, 201, 201, 214, 214, 220, 220, 228, 229, 233, 233, 246, 246, 252, 252,
|
|
39
|
+
};
|
|
40
|
+
|
|
41
|
+
const narsil_language narsil_language_swedish = {
|
|
42
|
+
.name = "swedish",
|
|
43
|
+
.revision = "5ff576fe6e2b2a68",
|
|
44
|
+
.stop_word_units = stop_word_units,
|
|
45
|
+
.stop_word_offsets = stop_word_offsets,
|
|
46
|
+
.stop_word_count = 114,
|
|
47
|
+
.ascii_keep = {0x03FF200000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
48
|
+
.keep_ranges = keep_ranges,
|
|
49
|
+
.keep_range_count = 12,
|
|
50
|
+
.splits_code_points = 0,
|
|
51
|
+
.strips_possessive = 0,
|
|
52
|
+
.normalises_diacritics = 0,
|
|
53
|
+
.min_token_length = 1,
|
|
54
|
+
.ngram_size = 0,
|
|
55
|
+
.normalise = NULL,
|
|
56
|
+
.stem_by_rules = NULL,
|
|
57
|
+
.create_snowball = swedish_create_env,
|
|
58
|
+
.snowball_stem = swedish_stem,
|
|
59
|
+
.close_snowball = swedish_close_env,
|
|
60
|
+
};
|
|
@@ -0,0 +1,75 @@
|
|
|
1
|
+
#include "../../analysis/languages.h"
|
|
2
|
+
#include "declarations.h"
|
|
3
|
+
|
|
4
|
+
#include <stddef.h>
|
|
5
|
+
#include <stdint.h>
|
|
6
|
+
|
|
7
|
+
static const uint16_t stop_word_units[778] = {
|
|
8
|
+
97, 107, 105, 110, 97, 107, 105, 110, 103, 97, 107, 111, 97, 108, 105, 110, 97, 109, 97, 109, 105, 110, 97, 109, 105,
|
|
9
|
+
110, 103, 97, 110, 103, 97, 110, 111, 97, 110, 117, 109, 97, 110, 103, 97, 112, 97, 116, 97, 116, 97, 116, 105, 110,
|
|
10
|
+
97, 116, 105, 110, 103, 97, 121, 98, 97, 98, 97, 98, 97, 98, 97, 103, 111, 98, 97, 107, 105, 116, 98, 97, 119, 97,
|
|
11
|
+
116, 98, 105, 108, 97, 110, 103, 100, 97, 104, 105, 108, 100, 97, 108, 97, 119, 97, 100, 97, 112, 97, 116, 100, 105,
|
|
12
|
+
110, 100, 105, 116, 111, 100, 111, 111, 110, 103, 97, 103, 97, 119, 105, 110, 103, 97, 121, 117, 110, 109, 97, 110,
|
|
13
|
+
103, 105, 110, 97, 103, 97, 119, 97, 103, 105, 110, 97, 119, 97, 103, 105, 110, 97, 119, 97, 110, 103, 103, 117, 109,
|
|
14
|
+
97, 119, 97, 103, 117, 115, 116, 111, 104, 97, 98, 97, 110, 103, 104, 97, 110, 103, 103, 97, 110, 103, 104, 105, 110,
|
|
15
|
+
100, 105, 104, 117, 119, 97, 103, 105, 98, 97, 105, 98, 97, 98, 97, 105, 98, 97, 98, 97, 119, 105, 98, 105, 103, 105,
|
|
16
|
+
107, 97, 119, 105, 108, 97, 103, 97, 121, 105, 108, 97, 108, 105, 109, 105, 108, 97, 110, 105, 110, 121, 111, 110,
|
|
17
|
+
103, 105, 115, 97, 105, 115, 97, 110, 103, 105, 116, 97, 97, 115, 105, 116, 111, 105, 121, 111, 105, 121, 111, 110,
|
|
18
|
+
105, 121, 111, 110, 103, 107, 97, 107, 97, 104, 105, 116, 107, 97, 105, 108, 97, 110, 103, 97, 110, 107, 97, 105, 108,
|
|
19
|
+
97, 110, 109, 97, 110, 107, 97, 109, 105, 107, 97, 110, 105, 108, 97, 107, 97, 110, 105, 108, 97, 110, 103, 107, 97,
|
|
20
|
+
110, 105, 110, 111, 107, 97, 110, 121, 97, 107, 97, 110, 121, 97, 110, 103, 107, 97, 112, 97, 103, 107, 97, 112, 119,
|
|
21
|
+
97, 107, 97, 114, 97, 109, 105, 104, 97, 110, 107, 97, 116, 105, 121, 97, 107, 97, 110, 107, 97, 116, 117, 108, 97,
|
|
22
|
+
100, 107, 97, 121, 97, 107, 97, 121, 115, 97, 107, 111, 107, 111, 110, 103, 107, 117, 108, 97, 110, 103, 107, 117,
|
|
23
|
+
109, 117, 104, 97, 107, 117, 110, 103, 108, 97, 98, 97, 110, 108, 97, 104, 97, 116, 108, 97, 109, 97, 110, 103, 108,
|
|
24
|
+
105, 107, 111, 100, 108, 105, 109, 97, 109, 97, 97, 97, 114, 105, 109, 97, 97, 97, 114, 105, 110, 103, 109, 97, 103,
|
|
25
|
+
105, 110, 103, 109, 97, 104, 117, 115, 97, 121, 109, 97, 107, 105, 116, 97, 109, 97, 114, 97, 109, 105, 109, 97, 114,
|
|
26
|
+
97, 112, 97, 116, 109, 97, 115, 121, 97, 100, 111, 109, 97, 121, 109, 97, 121, 114, 111, 111, 110, 109, 103, 97, 109,
|
|
27
|
+
105, 110, 115, 97, 110, 109, 105, 115, 109, 111, 109, 117, 108, 97, 109, 117, 108, 105, 110, 97, 110, 97, 98, 97, 110,
|
|
28
|
+
103, 103, 105, 116, 110, 97, 103, 105, 110, 103, 110, 97, 103, 107, 97, 114, 111, 111, 110, 110, 97, 105, 115, 110,
|
|
29
|
+
97, 107, 105, 116, 97, 110, 97, 109, 105, 110, 110, 97, 112, 97, 107, 97, 110, 97, 114, 105, 116, 111, 110, 97, 115,
|
|
30
|
+
97, 97, 110, 110, 103, 110, 103, 97, 121, 111, 110, 110, 105, 110, 105, 108, 97, 110, 105, 108, 97, 110, 103, 110,
|
|
31
|
+
105, 116, 111, 110, 105, 121, 97, 110, 105, 121, 97, 110, 103, 110, 111, 111, 110, 111, 112, 97, 112, 97, 97, 110,
|
|
32
|
+
111, 112, 97, 98, 97, 98, 97, 112, 97, 103, 103, 97, 119, 97, 112, 97, 103, 105, 116, 97, 110, 112, 97, 103, 107, 97,
|
|
33
|
+
107, 97, 114, 111, 111, 110, 112, 97, 103, 107, 97, 116, 97, 112, 111, 115, 112, 97, 108, 97, 98, 97, 115, 112, 97,
|
|
34
|
+
109, 97, 109, 97, 103, 105, 116, 97, 110, 112, 97, 110, 97, 104, 111, 110, 112, 97, 110, 103, 97, 108, 97, 119, 97,
|
|
35
|
+
112, 97, 114, 97, 112, 97, 114, 97, 97, 110, 112, 97, 114, 101, 104, 111, 112, 97, 116, 97, 97, 115, 112, 101, 114,
|
|
36
|
+
111, 112, 117, 109, 117, 110, 116, 97, 112, 117, 109, 117, 112, 117, 110, 116, 97, 115, 97, 115, 97, 97, 110, 115, 97,
|
|
37
|
+
98, 105, 115, 97, 98, 105, 104, 105, 110, 115, 97, 114, 105, 108, 105, 115, 105, 108, 97, 115, 105, 110, 111, 115,
|
|
38
|
+
105, 121, 97, 116, 97, 116, 108, 111, 116, 97, 121, 111, 116, 117, 108, 97, 100, 116, 117, 110, 103, 107, 111, 108,
|
|
39
|
+
117, 110, 97, 119, 97, 108, 97, 110, 103,
|
|
40
|
+
};
|
|
41
|
+
|
|
42
|
+
static const uint32_t stop_word_offsets[148] = {
|
|
43
|
+
0, 4, 9, 12, 16, 18, 22, 27, 30, 33, 40, 44, 46, 50, 55, 57, 63, 67, 72, 77, 83, 88, 94, 99, 102, 106, 110, 117, 125,
|
|
44
|
+
133, 139, 147, 153, 158, 164, 172, 177, 182, 185, 190, 196, 200, 204, 210, 216, 220, 226, 229, 234, 239, 242, 245,
|
|
45
|
+
249, 254, 256, 261, 270, 279, 283, 289, 297, 303, 308, 315, 320, 325, 334, 343, 350, 354, 359, 361, 365, 371, 377,
|
|
46
|
+
381, 386, 391, 397, 402, 406, 412, 420, 426, 433, 439, 445, 452, 459, 462, 469, 472, 478, 483, 487, 491, 493, 502,
|
|
47
|
+
508, 517, 521, 527, 532, 538, 544, 550, 552, 558, 560, 564, 570, 574, 578, 584, 588, 589, 591, 596, 602, 609, 616,
|
|
48
|
+
627, 637, 644, 655, 662, 671, 675, 681, 687, 693, 697, 704, 713, 715, 719, 723, 730, 736, 740, 744, 748, 753, 757,
|
|
49
|
+
762, 769, 772, 778,
|
|
50
|
+
};
|
|
51
|
+
|
|
52
|
+
static const uint32_t keep_ranges[6] = {
|
|
53
|
+
48, 57, 65, 90, 97, 122,
|
|
54
|
+
};
|
|
55
|
+
|
|
56
|
+
const narsil_language narsil_language_tagalog = {
|
|
57
|
+
.name = "tagalog",
|
|
58
|
+
.revision = "1",
|
|
59
|
+
.stop_word_units = stop_word_units,
|
|
60
|
+
.stop_word_offsets = stop_word_offsets,
|
|
61
|
+
.stop_word_count = 147,
|
|
62
|
+
.ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
|
|
63
|
+
.keep_ranges = keep_ranges,
|
|
64
|
+
.keep_range_count = 3,
|
|
65
|
+
.splits_code_points = 0,
|
|
66
|
+
.strips_possessive = 0,
|
|
67
|
+
.normalises_diacritics = 0,
|
|
68
|
+
.min_token_length = 1,
|
|
69
|
+
.ngram_size = 0,
|
|
70
|
+
.normalise = NULL,
|
|
71
|
+
.stem_by_rules = NULL,
|
|
72
|
+
.create_snowball = NULL,
|
|
73
|
+
.snowball_stem = NULL,
|
|
74
|
+
.close_snowball = NULL,
|
|
75
|
+
};
|