@delali/narsil-react-native 0.3.1-next.155 → 0.3.1-next.157

package/cpp/core/src/languages/data/lingala.c

@@ -0,0 +1,88 @@
+#include "../../analysis/languages.h"
+#include "declarations.h"
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const uint16_t stop_word_units[216] = {
+  97, 119, 97, 97, 122, 97, 108, 97, 107, 105, 97, 122, 97, 108, 105, 98, 97, 110, 103, 111, 98, 97, 115, 117, 115, 117,
+  98, 97, 122, 97, 108, 105, 98, 105, 110, 111, 98, 105, 115, 111, 98, 111, 110, 103, 111, 98, 111, 121, 101, 101, 112,
+  97, 105, 101, 122, 97, 108, 97, 107, 105, 101, 122, 97, 108, 105, 107, 97, 107, 97, 107, 97, 115, 105, 107, 97, 116,
+  105, 107, 117, 110, 97, 108, 105, 98, 111, 115, 111, 108, 105, 107, 111, 108, 111, 108, 105, 115, 117, 115, 117, 108,
+  111, 107, 111, 108, 97, 109, 105, 110, 103, 105, 109, 105, 115, 117, 115, 117, 109, 111, 107, 111, 109, 111, 115, 117,
+  115, 117, 109, 112, 101, 109, 112, 111, 110, 97, 110, 97, 105, 110, 111, 110, 97, 122, 97, 108, 105, 110, 103, 97,
+  105, 110, 115, 101, 110, 115, 105, 109, 97, 110, 121, 111, 110, 115, 111, 111, 121, 111, 111, 122, 97, 108, 105, 112,
+  101, 115, 105, 107, 97, 119, 97, 115, 105, 107, 111, 121, 111, 115, 105, 109, 97, 115, 111, 107, 105, 116, 101, 116,
+  105, 105, 116, 111, 116, 111, 122, 97, 108, 105, 119, 97, 110, 97, 121, 97, 121, 101, 121, 111,
+};
+
+static const uint32_t stop_word_offsets[50] = {
+  0, 3, 10, 15, 20, 26, 32, 36, 40, 45, 49, 53, 60, 65, 69, 73, 77, 81, 87, 93, 99, 105, 110, 116, 120, 126, 129, 132,
+  134, 139, 145, 149, 152, 157, 163, 166, 171, 173, 179, 185, 189, 193, 195, 198, 200, 206, 210, 212, 214, 216,
+};
+
+static const uint32_t keep_ranges[732] = {
+  48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 768, 879, 921, 921, 953, 953,
+  1155, 1161, 1425, 1469, 1471, 1471, 1473, 1474, 1476, 1477, 1479, 1479, 1552, 1562, 1611, 1631, 1648, 1648, 1750,
+  1756, 1759, 1764, 1767, 1768, 1770, 1773, 1809, 1809, 1840, 1866, 1958, 1968, 2027, 2035, 2045, 2045, 2070, 2073,
+  2075, 2083, 2085, 2087, 2089, 2093, 2137, 2139, 2199, 2207, 2250, 2273, 2275, 2307, 2362, 2364, 2366, 2383, 2385,
+  2391, 2402, 2403, 2433, 2435, 2492, 2492, 2494, 2500, 2503, 2504, 2507, 2509, 2519, 2519, 2530, 2531, 2558, 2558,
+  2561, 2563, 2620, 2620, 2622, 2626, 2631, 2632, 2635, 2637, 2641, 2641, 2672, 2673, 2677, 2677, 2689, 2691, 2748,
+  2748, 2750, 2757, 2759, 2761, 2763, 2765, 2786, 2787, 2810, 2815, 2817, 2819, 2876, 2876, 2878, 2884, 2887, 2888,
+  2891, 2893, 2901, 2903, 2914, 2915, 2946, 2946, 3006, 3010, 3014, 3016, 3018, 3021, 3031, 3031, 3072, 3076, 3132,
+  3132, 3134, 3140, 3142, 3144, 3146, 3149, 3157, 3158, 3170, 3171, 3201, 3203, 3260, 3260, 3262, 3268, 3270, 3272,
+  3274, 3277, 3285, 3286, 3298, 3299, 3315, 3315, 3328, 3331, 3387, 3388, 3390, 3396, 3398, 3400, 3402, 3405, 3415,
+  3415, 3426, 3427, 3457, 3459, 3530, 3530, 3535, 3540, 3542, 3542, 3544, 3551, 3570, 3571, 3633, 3633, 3636, 3642,
+  3655, 3662, 3761, 3761, 3764, 3772, 3784, 3790, 3864, 3865, 3893, 3893, 3895, 3895, 3897, 3897, 3902, 3903, 3953,
+  3972, 3974, 3975, 3981, 3991, 3993, 4028, 4038, 4038, 4139, 4158, 4182, 4185, 4190, 4192, 4194, 4196, 4199, 4205,
+  4209, 4212, 4226, 4237, 4239, 4239, 4250, 4253, 4957, 4959, 5906, 5909, 5938, 5940, 5970, 5971, 6002, 6003, 6068,
+  6099, 6109, 6109, 6155, 6157, 6159, 6159, 6277, 6278, 6313, 6313, 6432, 6443, 6448, 6459, 6679, 6683, 6741, 6750,
+  6752, 6780, 6783, 6783, 6832, 6877, 6880, 6891, 6912, 6916, 6964, 6980, 7019, 7027, 7040, 7042, 7073, 7085, 7142,
+  7155, 7204, 7223, 7376, 7378, 7380, 7400, 7405, 7405, 7412, 7412, 7415, 7417, 7424, 7461, 7468, 7516, 7522, 7525,
+  7531, 7543, 7545, 7614, 7616, 7935, 8126, 8126, 8305, 8305, 8319, 8319, 8336, 8348, 8400, 8432, 8490, 8491, 8498,
+  8498, 8526, 8526, 8544, 8584, 11360, 11391, 11503, 11505, 11647, 11647, 11744, 11775, 12330, 12335, 12441, 12442,
+  42607, 42610, 42612, 42621, 42654, 42655, 42736, 42737, 42786, 42887, 42891, 42972, 42993, 43007, 43010, 43010, 43014,
+  43014, 43019, 43019, 43043, 43047, 43052, 43052, 43136, 43137, 43188, 43205, 43232, 43249, 43263, 43263, 43302, 43309,
+  43335, 43347, 43392, 43395, 43443, 43456, 43493, 43493, 43561, 43574, 43587, 43587, 43596, 43597, 43643, 43645, 43696,
+  43696, 43698, 43700, 43703, 43704, 43710, 43711, 43713, 43713, 43755, 43759, 43765, 43766, 43824, 43866, 43868, 43876,
+  43878, 43881, 44003, 44010, 44012, 44013, 64256, 64262, 64286, 64286, 65024, 65039, 65056, 65071, 65313, 65338, 65345,
+  65370, 66045, 66045, 66272, 66272, 66422, 66426, 67456, 67461, 67463, 67504, 67506, 67514, 68097, 68099, 68101, 68102,
+  68108, 68111, 68152, 68154, 68159, 68159, 68325, 68326, 68900, 68903, 68969, 68973, 69291, 69292, 69370, 69375, 69446,
+  69456, 69506, 69509, 69632, 69634, 69688, 69702, 69744, 69744, 69747, 69748, 69759, 69762, 69808, 69818, 69826, 69826,
+  69888, 69890, 69927, 69940, 69957, 69958, 70003, 70003, 70016, 70018, 70067, 70080, 70089, 70092, 70094, 70095, 70188,
+  70199, 70206, 70206, 70209, 70209, 70367, 70378, 70400, 70403, 70459, 70460, 70462, 70468, 70471, 70472, 70475, 70477,
+  70487, 70487, 70498, 70499, 70502, 70508, 70512, 70516, 70584, 70592, 70594, 70594, 70597, 70597, 70599, 70602, 70604,
+  70608, 70610, 70610, 70625, 70626, 70709, 70726, 70750, 70750, 70832, 70851, 71087, 71093, 71096, 71104, 71132, 71133,
+  71216, 71232, 71339, 71351, 71453, 71467, 71724, 71738, 71984, 71989, 71991, 71992, 71995, 71998, 72000, 72000, 72002,
+  72003, 72145, 72151, 72154, 72160, 72164, 72164, 72193, 72202, 72243, 72249, 72251, 72254, 72263, 72263, 72273, 72283,
+  72330, 72345, 72544, 72551, 72751, 72758, 72760, 72767, 72850, 72871, 72873, 72886, 73009, 73014, 73018, 73018, 73020,
+  73021, 73023, 73029, 73031, 73031, 73098, 73102, 73104, 73105, 73107, 73111, 73459, 73462, 73472, 73473, 73475, 73475,
+  73524, 73530, 73534, 73538, 73562, 73562, 78912, 78912, 78919, 78933, 90398, 90415, 92912, 92916, 92976, 92982, 94031,
+  94031, 94033, 94087, 94095, 94098, 94180, 94180, 94192, 94193, 113821, 113822, 118528, 118573, 118576, 118598, 119141,
+  119145, 119149, 119154, 119163, 119170, 119173, 119179, 119210, 119213, 119362, 119364, 121344, 121398, 121403,
+  121452, 121461, 121461, 121476, 121476, 121499, 121503, 121505, 121519, 122624, 122654, 122661, 122666, 122880,
+  122886, 122888, 122904, 122907, 122913, 122915, 122916, 122918, 122922, 123023, 123023, 123184, 123190, 123566,
+  123566, 123628, 123631, 124140, 124143, 124398, 124399, 124643, 124643, 124646, 124646, 124654, 124655, 124661,
+  124661, 125136, 125142, 125252, 125258, 917760, 917999,
+};
+
+const narsil_language narsil_language_lingala = {
+  .name = "lingala",
+  .revision = "1",
+  .stop_word_units = stop_word_units,
+  .stop_word_offsets = stop_word_offsets,
+  .stop_word_count = 49,
+  .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
+  .keep_ranges = keep_ranges,
+  .keep_range_count = 366,
+  .splits_code_points = 1,
+  .strips_possessive = 0,
+  .normalises_diacritics = 0,
+  .min_token_length = 1,
+  .ngram_size = 0,
+  .normalise = NULL,
+  .stem_by_rules = NULL,
+  .create_snowball = NULL,
+  .snowball_stem = NULL,
+  .close_snowball = NULL,
+};

package/cpp/core/src/languages/data/lithuanian.c

@@ -0,0 +1,65 @@
+#include "../../analysis/languages.h"
+#include "declarations.h"
+#include "../snowball/lithuanian_stemmer.h"
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const uint16_t stop_word_units[501] = {
+  97, 110, 116, 97, 112, 105, 101, 97, 114, 97, 114, 98, 97, 97, 353, 98, 101, 98, 101, 105, 98, 101, 116, 98, 117, 115,
+  98, 117, 118, 111, 98, 363, 116, 105, 98, 363, 116, 371, 100, 279, 108, 103, 97, 108, 105, 105, 107, 105, 105, 114,
+  105, 353, 106, 97, 106, 97, 105, 106, 97, 105, 115, 106, 97, 109, 106, 97, 109, 101, 106, 97, 115, 106, 101, 105, 106,
+  105, 106, 105, 101, 106, 105, 101, 100, 117, 106, 105, 101, 100, 118, 105, 106, 105, 101, 100, 118, 105, 101, 109,
+  106, 105, 101, 100, 118, 105, 101, 115, 101, 106, 105, 101, 109, 115, 106, 105, 115, 106, 111, 106, 111, 100, 118,
+  105, 101, 109, 106, 111, 103, 106, 111, 106, 101, 106, 111, 109, 105, 115, 106, 111, 109, 115, 106, 111, 115, 106,
+  111, 115, 101, 106, 117, 100, 117, 106, 117, 100, 118, 105, 106, 117, 100, 118, 105, 101, 106, 371, 106, 117, 100,
+  118, 105, 101, 109, 106, 117, 100, 118, 105, 101, 115, 101, 106, 117, 109, 105, 115, 106, 117, 109, 115, 106, 117,
+  109, 121, 115, 101, 106, 117, 111, 106, 117, 111, 100, 117, 106, 117, 111, 100, 118, 105, 101, 115, 101, 106, 117,
+  111, 115, 106, 117, 111, 115, 101, 106, 117, 115, 106, 261, 106, 303, 106, 363, 115, 106, 363, 115, 371, 106, 371,
+  106, 371, 100, 118, 105, 101, 106, 371, 107, 97, 100, 107, 97, 105, 107, 97, 105, 112, 107, 97, 115, 107, 105, 101,
+  107, 107, 111, 108, 107, 117, 114, 107, 117, 114, 105, 101, 107, 117, 114, 105, 115, 107, 261, 109, 97, 110, 109, 97,
+  110, 101, 109, 97, 110, 105, 109, 105, 109, 97, 110, 111, 109, 97, 110, 121, 106, 101, 109, 97, 110, 281, 115, 109,
+  101, 115, 109, 101, 116, 117, 109, 117, 100, 117, 109, 117, 100, 118, 105, 109, 117, 100, 118, 105, 101, 106, 371,
+  109, 117, 100, 118, 105, 101, 109, 109, 117, 100, 118, 105, 101, 115, 101, 109, 117, 109, 105, 115, 109, 117, 109,
+  115, 109, 117, 109, 121, 115, 101, 109, 117, 115, 109, 363, 115, 371, 110, 101, 105, 110, 101, 115, 110, 101, 116,
+  110, 111, 114, 115, 110, 117, 111, 111, 112, 97, 116, 112, 101, 114, 112, 111, 112, 114, 105, 101, 112, 114, 105, 101,
+  353, 115, 97, 117, 115, 97, 118, 101, 115, 97, 118, 105, 109, 105, 115, 97, 118, 111, 115, 97, 118, 121, 106, 101,
+  115, 97, 118, 281, 115, 115, 117, 116, 97, 100, 97, 116, 97, 105, 116, 97, 105, 112, 116, 97, 115, 116, 97, 117, 116,
+  97, 118, 101, 116, 97, 118, 105, 109, 105, 116, 97, 118, 121, 106, 101, 116, 97, 118, 281, 115, 116, 97, 269, 105, 97,
+  117, 116, 101, 110, 116, 111, 116, 111, 100, 279, 108, 116, 117, 116, 117, 111, 117, 382, 118, 105, 115, 105, 121,
+  114, 97, 303,
+};
+
+static const uint32_t stop_word_offsets[126] = {
+  0, 3, 7, 9, 13, 15, 17, 20, 23, 26, 30, 34, 38, 41, 45, 48, 50, 52, 54, 57, 61, 64, 68, 71, 74, 76, 79, 84, 90, 98,
+  107, 112, 115, 117, 124, 127, 131, 136, 140, 143, 147, 151, 156, 164, 171, 179, 184, 188, 194, 197, 202, 211, 215,
+  220, 223, 225, 227, 230, 234, 236, 244, 247, 250, 254, 257, 261, 264, 267, 272, 277, 279, 282, 286, 292, 296, 302,
+  307, 310, 314, 318, 323, 331, 338, 346, 351, 355, 361, 364, 368, 371, 374, 377, 381, 384, 385, 388, 391, 393, 397,
+  402, 405, 409, 415, 419, 425, 430, 432, 436, 439, 443, 446, 449, 453, 459, 465, 470, 476, 479, 481, 486, 488, 491,
+  493, 497, 500, 501,
+};
+
+static const uint32_t keep_ranges[22] = {
+  48, 57, 65, 90, 97, 122, 260, 261, 268, 269, 278, 281, 302, 303, 352, 353, 362, 363, 370, 371, 381, 382,
+};
+
+const narsil_language narsil_language_lithuanian = {
+  .name = "lithuanian",
+  .revision = "6c40fb18cf07c9b6",
+  .stop_word_units = stop_word_units,
+  .stop_word_offsets = stop_word_offsets,
+  .stop_word_count = 125,
+  .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
+  .keep_ranges = keep_ranges,
+  .keep_range_count = 11,
+  .splits_code_points = 0,
+  .strips_possessive = 0,
+  .normalises_diacritics = 0,
+  .min_token_length = 1,
+  .ngram_size = 0,
+  .normalise = NULL,
+  .stem_by_rules = NULL,
+  .create_snowball = lithuanian_create_env,
+  .snowball_stem = lithuanian_stem,
+  .close_snowball = lithuanian_close_env,
+};

package/cpp/core/src/languages/data/luxembourgish.c

@@ -0,0 +1,80 @@
+#include "../../analysis/languages.h"
+#include "declarations.h"
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const uint16_t stop_word_units[828] = {
+  97, 97, 108, 108, 97, 108, 108, 101, 103, 117, 101, 114, 97, 108, 108, 101, 109, 97, 108, 108, 101, 115, 97, 108, 115,
+  97, 108, 115, 111, 97, 109, 97, 110, 97, 110, 101, 114, 101, 102, 97, 108, 108, 115, 97, 115, 115, 97, 117, 115, 97,
+  119, 101, 114, 98, 101, 105, 98, 101, 105, 109, 98, 105, 115, 100, 97, 100, 97, 99, 104, 100, 97, 110, 110, 100, 97,
+  116, 100, 97, 116, 116, 100, 101, 100, 101, 101, 100, 101, 101, 108, 100, 101, 101, 109, 100, 101, 101, 110, 100, 101,
+  101, 110, 101, 100, 101, 109, 100, 101, 110, 100, 101, 110, 103, 100, 101, 110, 103, 101, 114, 100, 101, 114, 100,
+  105, 100, 105, 114, 100, 111, 100, 111, 109, 97, 116, 100, 111, 122, 111, 117, 100, 114, 111, 112, 100, 117, 100, 117,
+  101, 114, 99, 104, 100, 117, 101, 114, 110, 111, 100, 228, 105, 110, 100, 228, 114, 100, 233, 105, 100, 235, 115, 101,
+  109, 101, 101, 99, 104, 101, 101, 101, 101, 110, 101, 101, 110, 116, 101, 105, 115, 101, 105, 115, 101, 101, 105, 115,
+  101, 110, 101, 105, 115, 101, 114, 101, 105, 115, 101, 114, 101, 101, 110, 101, 105, 115, 101, 115, 101, 109, 101,
+  110, 101, 110, 103, 101, 110, 103, 101, 109, 101, 110, 103, 101, 114, 101, 110, 116, 119, 101, 100, 101, 114, 101,
+  114, 233, 105, 115, 99, 104, 116, 101, 115, 111, 117, 101, 116, 102, 97, 108, 108, 115, 102, 105, 114, 103, 101, 101,
+  116, 103, 105, 103, 105, 110, 110, 103, 111, 117, 102, 103, 111, 117, 102, 102, 103, 111, 117, 110, 103, 103, 233,
+  105, 102, 103, 233, 105, 110, 116, 103, 235, 116, 103, 235, 116, 116, 104, 97, 116, 104, 97, 116, 101, 110, 104, 97,
+  116, 116, 104, 101, 105, 104, 105, 101, 110, 104, 105, 101, 114, 104, 105, 110, 104, 105, 114, 104, 105, 114, 101,
+  110, 104, 117, 104, 117, 101, 116, 104, 117, 110, 104, 117, 110, 110, 104, 228, 116, 116, 105, 101, 99, 104, 105, 110,
+  115, 105, 119, 119, 101, 114, 106, 105, 100, 100, 101, 114, 101, 101, 110, 106, 105, 100, 100, 101, 114, 101, 110,
+  106, 105, 100, 100, 101, 114, 101, 110, 103, 106, 105, 100, 100, 119, 101, 114, 101, 101, 110, 106, 105, 100, 100,
+  119, 101, 114, 101, 110, 103, 101, 110, 106, 111, 107, 97, 110, 110, 107, 101, 101, 107, 101, 101, 110, 107, 111, 117,
+  109, 107, 117, 99, 107, 116, 107, 233, 110, 103, 107, 233, 110, 103, 101, 109, 107, 233, 110, 103, 101, 110, 107, 235,
+  110, 110, 101, 107, 235, 110, 110, 116, 109, 97, 109, 97, 109, 109, 97, 116, 109, 101, 99, 104, 109, 101, 110, 103,
+  109, 101, 110, 103, 101, 114, 109, 101, 114, 109, 105, 114, 109, 117, 115, 115, 109, 228, 109, 233, 99, 104, 116, 109,
+  233, 105, 110, 97, 99, 104, 110, 97, 119, 101, 108, 108, 110, 101, 101, 110, 101, 101, 115, 110, 101, 116, 110, 111,
+  110, 111, 109, 110, 117, 110, 228, 105, 115, 99, 104, 116, 110, 228, 109, 109, 101, 108, 101, 99, 104, 110, 228, 109,
+  109, 108, 101, 99, 104, 110, 235, 109, 109, 101, 110, 235, 109, 109, 101, 110, 111, 99, 104, 111, 100, 101, 114, 111,
+  109, 111, 110, 115, 111, 110, 115, 101, 110, 111, 110, 115, 101, 114, 111, 110, 115, 101, 114, 101, 101, 110, 111,
+  110, 115, 116, 111, 112, 111, 117, 110, 105, 115, 99, 104, 111, 110, 110, 115, 99, 104, 111, 110, 110, 115, 115, 101,
+  115, 101, 99, 104, 115, 101, 108, 119, 101, 99, 104, 116, 115, 101, 108, 119, 101, 114, 115, 101, 110, 103, 115, 101,
+  110, 103, 101, 115, 101, 110, 103, 101, 109, 115, 101, 110, 103, 101, 114, 115, 105, 115, 105, 100, 115, 105, 101,
+  115, 105, 110, 110, 115, 111, 108, 108, 116, 101, 110, 115, 111, 115, 115, 115, 111, 116, 115, 111, 117, 115, 111,
+  117, 103, 117, 101, 114, 115, 228, 105, 115, 228, 105, 110, 116, 235, 115, 99, 104, 116, 117, 117, 109, 117, 110, 118,
+  105, 114, 100, 114, 117, 110, 118, 117, 118, 117, 109, 118, 117, 110, 119, 97, 110, 110, 119, 97, 114, 119, 97, 114,
+  101, 110, 119, 97, 115, 119, 97, 116, 119, 101, 105, 100, 101, 114, 119, 105, 119, 111, 108, 108, 116, 119, 111, 117,
+  119, 111, 117, 104, 105, 110, 119, 233, 105, 119, 233, 105, 110, 105, 119, 233, 105, 110, 115, 116, 119, 235, 108,
+  108, 116, 122, 97, 110, 116, 101, 114, 122, 101, 122, 117, 122, 117, 109, 122, 119, 97, 114, 224, 228, 101, 114, 116,
+  228, 105, 115, 228, 114, 228, 114, 101, 110, 228, 114, 116, 235, 235, 109, 235, 110, 110, 101, 114,
+};
+
+static const uint32_t stop_word_offsets[203] = {
+  0, 1, 4, 12, 17, 22, 25, 29, 31, 33, 43, 46, 49, 53, 56, 60, 63, 65, 69, 73, 76, 80, 82, 85, 89, 93, 97, 102, 105,
+  108, 112, 118, 121, 123, 126, 128, 133, 138, 142, 144, 150, 156, 160, 163, 166, 171, 172, 175, 177, 180, 184, 187,
+  191, 196, 201, 209, 214, 216, 218, 221, 226, 231, 239, 247, 251, 253, 258, 261, 265, 267, 271, 275, 280, 285, 289,
+  294, 297, 301, 304, 309, 313, 316, 320, 324, 327, 330, 335, 337, 341, 344, 348, 352, 356, 359, 364, 373, 381, 390,
+  400, 412, 414, 418, 421, 425, 429, 434, 438, 444, 450, 455, 460, 462, 465, 468, 472, 476, 482, 485, 488, 492, 494,
+  499, 502, 506, 512, 515, 519, 522, 524, 527, 529, 536, 545, 553, 558, 564, 567, 571, 573, 576, 581, 586, 594, 598,
+  600, 604, 610, 617, 619, 623, 631, 637, 641, 646, 652, 658, 660, 663, 666, 670, 677, 681, 684, 687, 694, 697, 701,
+  707, 708, 710, 712, 719, 721, 724, 727, 731, 734, 739, 742, 745, 751, 753, 758, 761, 767, 770, 775, 781, 786, 792,
+  794, 796, 799, 803, 804, 808, 811, 813, 817, 820, 821, 823, 828,
+};
+
+static const uint32_t keep_ranges[22] = {
+  48, 57, 65, 90, 97, 122, 192, 192, 196, 196, 201, 201, 203, 203, 224, 224, 228, 228, 233, 233, 235, 235,
+};
+
+const narsil_language narsil_language_luxembourgish = {
+  .name = "luxembourgish",
+  .revision = "1",
+  .stop_word_units = stop_word_units,
+  .stop_word_offsets = stop_word_offsets,
+  .stop_word_count = 202,
+  .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
+  .keep_ranges = keep_ranges,
+  .keep_range_count = 11,
+  .splits_code_points = 0,
+  .strips_possessive = 0,
+  .normalises_diacritics = 0,
+  .min_token_length = 1,
+  .ngram_size = 0,
+  .normalise = NULL,
+  .stem_by_rules = NULL,
+  .create_snowball = NULL,
+  .snowball_stem = NULL,
+  .close_snowball = NULL,
+};

package/cpp/core/src/languages/data/macedonian.c

@@ -0,0 +1,286 @@
+#include "../../analysis/languages.h"
+#include "declarations.h"
+#include "../rules.h"
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const uint16_t stop_word_units[3942] = {
+  97, 1074, 1072, 1072, 1073, 1088, 1077, 1072, 1080, 1072, 1082, 1086, 1072, 1083, 1072, 1083, 1086, 1072, 1084, 1072,
+  1084, 1072, 1072, 1084, 1072, 1085, 1072, 1084, 1080, 1072, 1084, 1080, 1085, 1072, 1091, 1072, 1091, 1093, 1072,
+  1091, 1095, 1072, 1093, 1072, 1093, 1072, 1072, 1096, 1072, 1096, 1082, 1086, 1083, 1089, 1091, 1084, 1072, 1096,
+  1082, 1086, 1083, 1089, 1091, 1085, 1072, 1112, 1072, 1112, 1076, 1077, 1072, 1112, 1089, 1072, 1119, 1072, 1073,
+  1072, 1073, 1072, 1074, 1085, 1086, 1073, 1072, 1084, 1073, 1072, 1087, 1073, 1072, 1088, 1073, 1072, 1088, 1077,
+  1073, 1072, 1088, 1077, 1084, 1073, 1072, 1091, 1073, 1072, 1096, 1073, 1072, 1112, 1073, 1077, 1073, 1077, 1072,
+  1073, 1077, 1074, 1073, 1077, 1074, 1084, 1077, 1073, 1077, 1074, 1090, 1077, 1073, 1077, 1079, 1073, 1077, 1079,
+  1073, 1077, 1083, 1080, 1073, 1077, 1079, 1076, 1088, 1091, 1075, 1086, 1073, 1077, 1083, 1082, 1080, 1073, 1077,
+  1096, 1077, 1073, 1080, 1073, 1080, 1076, 1077, 1112, 1116, 1080, 1073, 1080, 1084, 1073, 1080, 1089, 1073, 1083,
+  1072, 1073, 1083, 1072, 1079, 1077, 1073, 1086, 1075, 1072, 1084, 1080, 1073, 1086, 1078, 1077, 1084, 1073, 1086,
+  1094, 1073, 1088, 1072, 1074, 1086, 1073, 1088, 1072, 1074, 1086, 1089, 1073, 1088, 1077, 1073, 1088, 1077, 1112,
+  1073, 1088, 1079, 1086, 1073, 1088, 1080, 1096, 1082, 1072, 1073, 1088, 1088, 1088, 1073, 1091, 1073, 1091, 1084,
+  1073, 1091, 1092, 1073, 1091, 1094, 1073, 1091, 1112, 1088, 1091, 1084, 1074, 1072, 1072, 1074, 1072, 1084, 1074,
+  1072, 1088, 1072, 1112, 1074, 1072, 1088, 1076, 1072, 1074, 1072, 1089, 1074, 1072, 1112, 1074, 1077, 1074, 1077,
+  1083, 1072, 1090, 1074, 1077, 1083, 1080, 1074, 1077, 1088, 1089, 1091, 1089, 1074, 1077, 1116, 1077, 1074, 1080,
+  1074, 1080, 1072, 1074, 1080, 1076, 1080, 1074, 1080, 1077, 1074, 1080, 1089, 1090, 1080, 1085, 1072, 1074, 1080,
+  1090, 1086, 1089, 1074, 1085, 1072, 1090, 1088, 1077, 1074, 1086, 1074, 1086, 1079, 1074, 1086, 1085, 1074, 1087,
+  1088, 1086, 1095, 1077, 1084, 1074, 1088, 1074, 1074, 1088, 1077, 1076, 1074, 1088, 1077, 1084, 1077, 1074, 1088,
+  1079, 1074, 1089, 1091, 1096, 1085, 1086, 1089, 1090, 1074, 1090, 1086, 1088, 1075, 1072, 1083, 1080, 1073, 1072,
+  1075, 1080, 1075, 1080, 1090, 1083, 1072, 1075, 1086, 1075, 1086, 1076, 1077, 1075, 1086, 1076, 1080, 1096, 1085,
+  1080, 1082, 1075, 1086, 1088, 1077, 1075, 1088, 1072, 1075, 1091, 1094, 1075, 1113, 1091, 1076, 1072, 1076, 1072,
+  1072, 1085, 1076, 1072, 1074, 1072, 1076, 1072, 1083, 1076, 1072, 1083, 1080, 1076, 1072, 1085, 1076, 1074, 1072,
+  1076, 1074, 1072, 1077, 1089, 1077, 1090, 1076, 1074, 1072, 1085, 1072, 1077, 1089, 1077, 1090, 1076, 1074, 1072,
+  1112, 1094, 1072, 1076, 1074, 1077, 1076, 1074, 1077, 1089, 1090, 1077, 1076, 1074, 1080, 1078, 1072, 1084, 1076,
+  1074, 1080, 1078, 1072, 1090, 1076, 1074, 1080, 1078, 1080, 1076, 1074, 1080, 1078, 1080, 1084, 1077, 1076, 1074,
+  1080, 1078, 1080, 1090, 1077, 1076, 1074, 1080, 1078, 1080, 1096, 1076, 1077, 1076, 1077, 1074, 1077, 1076, 1077,
+  1089, 1077, 1090, 1076, 1077, 1074, 1077, 1090, 1076, 1077, 1074, 1077, 1090, 1085, 1072, 1077, 1089, 1077, 1090,
+  1076, 1077, 1074, 1077, 1090, 1089, 1090, 1086, 1090, 1080, 1085, 1080, 1076, 1077, 1074, 1077, 1090, 1090, 1080,
+  1076, 1077, 1082, 1072, 1076, 1077, 1083, 1076, 1077, 1083, 1084, 1080, 1076, 1077, 1084, 1077, 1082, 1076, 1077,
+  1089, 1077, 1090, 1076, 1077, 1089, 1077, 1090, 1080, 1085, 1072, 1076, 1077, 1089, 1077, 1090, 1090, 1080, 1076,
+  1077, 1089, 1080, 1090, 1080, 1094, 1080, 1076, 1077, 1112, 1075, 1080, 1076, 1080, 1076, 1077, 1112, 1076, 1080,
+  1076, 1080, 1076, 1080, 1083, 1084, 1080, 1076, 1080, 1085, 1076, 1080, 1087, 1076, 1085, 1086, 1076, 1086, 1076,
+  1086, 1074, 1086, 1083, 1085, 1086, 1076, 1086, 1076, 1077, 1082, 1072, 1076, 1086, 1076, 1091, 1096, 1072, 1076,
+  1086, 1082, 1072, 1112, 1076, 1086, 1082, 1086, 1083, 1082, 1091, 1076, 1086, 1087, 1088, 1072, 1074, 1077, 1085,
+  1086, 1076, 1086, 1087, 1088, 1072, 1074, 1080, 1076, 1086, 1089, 1072, 1084, 1086, 1090, 1080, 1076, 1086, 1089,
+  1090, 1072, 1076, 1088, 1078, 1080, 1076, 1088, 1085, 1076, 1088, 1091, 1075, 1076, 1088, 1091, 1075, 1072, 1076,
+  1088, 1091, 1075, 1072, 1090, 1072, 1076, 1088, 1091, 1075, 1080, 1076, 1088, 1091, 1075, 1080, 1086, 1090, 1076,
+  1088, 1091, 1075, 1080, 1090, 1077, 1076, 1088, 1091, 1075, 1086, 1076, 1088, 1091, 1075, 1086, 1090, 1086, 1076,
+  1091, 1084, 1076, 1091, 1088, 1076, 1091, 1088, 1080, 1077, 1077, 1074, 1072, 1083, 1072, 1077, 1074, 1077, 1077,
+  1074, 1077, 1090, 1077, 1075, 1072, 1077, 1075, 1080, 1076, 1080, 1077, 1076, 1077, 1085, 1077, 1076, 1080, 1082,
+  1086, 1112, 1089, 1080, 1077, 1076, 1080, 1085, 1072, 1077, 1089, 1077, 1090, 1077, 1076, 1080, 1085, 1089, 1090,
+  1074, 1077, 1085, 1086, 1077, 1076, 1085, 1072, 1096, 1077, 1076, 1085, 1086, 1077, 1082, 1089, 1080, 1082, 1077,
+  1083, 1072, 1077, 1083, 1073, 1077, 1090, 1077, 1077, 1083, 1077, 1084, 1077, 1083, 1080, 1077, 1084, 1077, 1084,
+  1080, 1077, 1085, 1077, 1077, 1090, 1077, 1077, 1091, 1088, 1077, 1082, 1072, 1077, 1093, 1077, 1112, 1078, 1080,
+  1084, 1080, 1078, 1080, 1090, 1080, 1079, 1072, 1079, 1072, 1074, 1072, 1083, 1079, 1072, 1074, 1088, 1096, 1080,
+  1079, 1072, 1076, 1079, 1072, 1076, 1077, 1082, 1072, 1079, 1072, 1076, 1086, 1074, 1086, 1083, 1085, 1072, 1079,
+  1072, 1076, 1088, 1078, 1080, 1079, 1072, 1077, 1076, 1085, 1086, 1079, 1072, 1088, 1079, 1072, 1088, 1072, 1076,
+  1079, 1072, 1088, 1072, 1076, 1080, 1079, 1072, 1088, 1077, 1079, 1072, 1088, 1077, 1084, 1079, 1072, 1090, 1086,
+  1072, 1079, 1072, 1096, 1090, 1086, 1079, 1075, 1086, 1088, 1072, 1079, 1077, 1084, 1072, 1079, 1077, 1084, 1077,
+  1079, 1077, 1084, 1091, 1074, 1072, 1079, 1077, 1088, 1079, 1085, 1072, 1095, 1080, 1079, 1086, 1096, 1090, 1086,
+  1079, 1091, 1112, 1080, 1080, 1072, 1082, 1086, 1080, 1079, 1080, 1079, 1074, 1077, 1079, 1077, 1085, 1080, 1079,
+  1075, 1083, 1077, 1076, 1072, 1080, 1079, 1084, 1077, 1107, 1091, 1080, 1079, 1085, 1086, 1089, 1080, 1083, 1080,
+  1080, 1083, 1112, 1072, 1076, 1072, 1080, 1083, 1112, 1072, 1076, 1080, 1080, 1084, 1080, 1084, 1072, 1080, 1084,
+  1072, 1072, 1080, 1084, 1072, 1072, 1090, 1080, 1084, 1072, 1074, 1084, 1077, 1080, 1084, 1072, 1074, 1090, 1077,
+  1080, 1084, 1072, 1084, 1080, 1084, 1072, 1084, 1077, 1080, 1084, 1072, 1090, 1077, 1080, 1084, 1072, 1096, 1080,
+  1084, 1072, 1096, 1077, 1080, 1084, 1077, 1080, 1084, 1077, 1085, 1086, 1080, 1084, 1077, 1085, 1091, 1074, 1072,
+  1080, 1084, 1087, 1083, 1080, 1094, 1080, 1088, 1072, 1080, 1084, 1087, 1083, 1080, 1094, 1080, 1088, 1072, 1072,
+  1090, 1080, 1084, 1087, 1083, 1080, 1094, 1080, 1088, 1072, 1084, 1080, 1084, 1087, 1083, 1080, 1094, 1080, 1088,
+  1072, 1084, 1077, 1080, 1084, 1087, 1083, 1080, 1094, 1080, 1088, 1072, 1090, 1077, 1080, 1084, 1087, 1083, 1080,
+  1094, 1080, 1088, 1072, 1096, 1080, 1085, 1072, 1082, 1091, 1080, 1085, 1076, 1080, 1094, 1080, 1088, 1072, 1080,
+  1089, 1077, 1095, 1086, 1082, 1080, 1089, 1082, 1083, 1091, 1095, 1077, 1085, 1080, 1089, 1082, 1083, 1091, 1095,
+  1077, 1085, 1072, 1080, 1089, 1082, 1083, 1091, 1095, 1077, 1085, 1080, 1080, 1089, 1082, 1083, 1091, 1095, 1077,
+  1085, 1086, 1080, 1089, 1082, 1086, 1088, 1080, 1089, 1090, 1077, 1085, 1080, 1089, 1082, 1086, 1088, 1080, 1089,
+  1090, 1077, 1085, 1072, 1080, 1089, 1082, 1086, 1088, 1080, 1089, 1090, 1077, 1085, 1080, 1080, 1089, 1082, 1086,
+  1088, 1080, 1089, 1090, 1077, 1085, 1086, 1080, 1089, 1082, 1086, 1088, 1080, 1089, 1090, 1080, 1080, 1089, 1082,
+  1088, 1072, 1112, 1080, 1089, 1090, 1080, 1080, 1089, 1090, 1086, 1080, 1090, 1072, 1082, 1072, 1080, 1090, 1085,
+  1080, 1093, 1080, 1093, 1072, 1080, 1093, 1091, 1091, 1080, 1096, 1080, 1096, 1072, 1083, 1072, 1080, 1112, 1082,
+  1072, 1082, 1072, 1076, 1077, 1082, 1072, 1078, 1091, 1074, 1072, 1082, 1072, 1082, 1086, 1082, 1072, 1082, 1086,
+  1074, 1082, 1072, 1084, 1086, 1083, 1080, 1082, 1072, 1112, 1082, 1074, 1072, 1082, 1080, 1082, 1080, 1090, 1082,
+  1083, 1086, 1082, 1083, 1091, 1084, 1082, 1086, 1075, 1072, 1082, 1086, 1075, 1086, 1082, 1086, 1077, 1082, 1086,
+  1080, 1082, 1086, 1083, 1080, 1095, 1077, 1089, 1090, 1074, 1086, 1082, 1086, 1083, 1080, 1095, 1080, 1085, 1072,
+  1082, 1086, 1083, 1082, 1091, 1082, 1086, 1084, 1091, 1082, 1086, 1085, 1082, 1086, 1088, 1080, 1089, 1090, 1077,
+  1085, 1072, 1082, 1086, 1088, 1080, 1089, 1090, 1077, 1085, 1080, 1082, 1086, 1088, 1080, 1089, 1090, 1077, 1085,
+  1086, 1082, 1086, 1088, 1080, 1089, 1090, 1080, 1082, 1086, 1090, 1082, 1086, 1090, 1088, 1088, 1082, 1086, 1112,
+  1082, 1086, 1112, 1072, 1082, 1086, 1112, 1079, 1085, 1072, 1077, 1082, 1086, 1112, 1096, 1090, 1086, 1082, 1088,
+  1072, 1112, 1082, 1088, 1077, 1082, 1082, 1088, 1079, 1082, 1088, 1082, 1082, 1088, 1094, 1082, 1091, 1082, 1091,
+  1082, 1091, 1082, 1091, 1088, 1080, 1075, 1091, 1082, 1091, 1096, 1083, 1077, 1083, 1077, 1073, 1072, 1084, 1080,
+  1083, 1077, 1083, 1077, 1083, 1077, 1083, 1080, 1083, 1080, 1083, 1080, 1076, 1091, 1083, 1091, 1087, 1084, 1072,
+  1084, 1072, 1082, 1072, 1088, 1084, 1072, 1083, 1082, 1091, 1084, 1072, 1088, 1096, 1084, 1072, 1090, 1084, 1072,
+  1094, 1084, 1072, 1096, 1072, 1083, 1072, 1084, 1077, 1084, 1077, 1085, 1077, 1084, 1077, 1089, 1090, 1086, 1084,
+  1077, 1107, 1091, 1084, 1077, 1107, 1091, 1074, 1088, 1077, 1084, 1077, 1084, 1077, 1107, 1091, 1090, 1086, 1072,
+  1084, 1080, 1084, 1086, 1077, 1084, 1086, 1078, 1077, 1084, 1086, 1078, 1077, 1073, 1080, 1084, 1086, 1083, 1072,
+  1084, 1084, 1086, 1083, 1080, 1084, 1086, 1088, 1084, 1086, 1088, 1072, 1084, 1086, 1088, 1077, 1084, 1086, 1088,
+  1080, 1084, 1088, 1072, 1079, 1077, 1094, 1084, 1091, 1084, 1091, 1082, 1083, 1077, 1094, 1084, 1091, 1090, 1083,
+  1072, 1082, 1084, 1091, 1094, 1084, 1112, 1072, 1091, 1085, 1072, 1085, 1072, 1074, 1080, 1076, 1091, 1084, 1085,
+  1072, 1074, 1080, 1089, 1090, 1080, 1085, 1072, 1085, 1072, 1076, 1085, 1072, 1076, 1074, 1086, 1088, 1085, 1072,
+  1079, 1072, 1076, 1085, 1072, 1082, 1072, 1112, 1085, 1072, 1082, 1088, 1072, 1112, 1085, 1072, 1083, 1080, 1085,
+  1072, 1084, 1085, 1072, 1084, 1077, 1089, 1090, 1086, 1085, 1072, 1086, 1082, 1086, 1083, 1091, 1085, 1072, 1087,
+  1088, 1072, 1074, 1077, 1085, 1086, 1085, 1072, 1087, 1088, 1072, 1074, 1080, 1085, 1072, 1087, 1088, 1077, 1076,
+  1085, 1072, 1089, 1085, 1072, 1089, 1087, 1086, 1088, 1077, 1076, 1085, 1072, 1089, 1087, 1088, 1077, 1084, 1072,
+  1085, 1072, 1089, 1087, 1088, 1086, 1090, 1080, 1085, 1072, 1089, 1088, 1077, 1076, 1085, 1072, 1090, 1072, 1084,
+  1091, 1085, 1072, 1090, 1077, 1084, 1072, 1085, 1072, 1095, 1080, 1085, 1085, 1072, 1096, 1085, 1072, 1096, 1072,
+  1085, 1072, 1096, 1077, 1085, 1072, 1096, 1080, 1085, 1072, 1112, 1085, 1072, 1112, 1076, 1086, 1094, 1085, 1072,
+  1085, 1072, 1112, 1084, 1072, 1083, 1082, 1091, 1085, 1072, 1112, 1084, 1085, 1086, 1075, 1091, 1085, 1077, 1085,
+  1077, 1072, 1085, 1077, 1075, 1086, 1085, 1077, 1075, 1086, 1074, 1085, 1077, 1075, 1086, 1074, 1072, 1085, 1077,
+  1075, 1086, 1074, 1080, 1085, 1077, 1075, 1086, 1074, 1086, 1085, 1077, 1079, 1077, 1085, 1077, 1082, 1072, 1085,
+  1077, 1082, 1072, 1076, 1077, 1085, 1077, 1082, 1072, 1082, 1086, 1085, 1077, 1082, 1072, 1082, 1086, 1074, 1085,
+  1077, 1082, 1086, 1075, 1086, 1085, 1077, 1082, 1086, 1077, 1085, 1077, 1082, 1086, 1080, 1085, 1077, 1082, 1086,
+  1083, 1082, 1091, 1085, 1077, 1082, 1086, 1084, 1091, 1085, 1077, 1082, 1086, 1112, 1085, 1077, 1082, 1086, 1112,
+  1089, 1080, 1085, 1077, 1083, 1080, 1085, 1077, 1084, 1086, 1112, 1085, 1077, 1084, 1091, 1085, 1077, 1086, 1090,
+  1080, 1085, 1077, 1095, 1080, 1112, 1085, 1077, 1096, 1090, 1086, 1085, 1077, 1112, 1079, 1077, 1085, 1077, 1112,
+  1079, 1080, 1085, 1085, 1077, 1112, 1079, 1080, 1085, 1080, 1085, 1077, 1112, 1079, 1080, 1085, 1086, 1085, 1077,
+  1112, 1089, 1077, 1085, 1080, 1085, 1080, 1074, 1085, 1080, 1074, 1077, 1085, 1085, 1080, 1074, 1085, 1072, 1085,
+  1080, 1074, 1085, 1080, 1085, 1080, 1074, 1085, 1086, 1085, 1080, 1077, 1085, 1080, 1079, 1085, 1080, 1082, 1072,
+  1076, 1077, 1085, 1080, 1082, 1072, 1082, 1086, 1085, 1080, 1082, 1086, 1075, 1072, 1096, 1085, 1080, 1082, 1086,
+  1075, 1086, 1085, 1080, 1082, 1086, 1084, 1091, 1085, 1080, 1082, 1086, 1112, 1085, 1080, 1084, 1085, 1080, 1090,
+  1080, 1085, 1080, 1090, 1086, 1085, 1080, 1090, 1091, 1085, 1080, 1095, 1080, 1112, 1085, 1080, 1096, 1090, 1086,
+  1085, 1086, 1085, 1104, 1086, 1086, 1073, 1088, 1086, 1074, 1072, 1086, 1074, 1072, 1072, 1086, 1074, 1072, 1112,
+  1086, 1074, 1076, 1077, 1086, 1074, 1077, 1075, 1072, 1086, 1074, 1080, 1077, 1086, 1074, 1086, 1112, 1086, 1076,
+  1086, 1076, 1072, 1074, 1076, 1077, 1086, 1076, 1080, 1086, 1076, 1085, 1077, 1089, 1091, 1074, 1072, 1086, 1076,
+  1085, 1086, 1089, 1085, 1086, 1086, 1076, 1086, 1096, 1090, 1086, 1086, 1082, 1086, 1083, 1091, 1086, 1083, 1077,
+  1083, 1077, 1086, 1083, 1082, 1072, 1094, 1086, 1082, 1086, 1085, 1086, 1085, 1072, 1086, 1085, 1072, 1072, 1086,
+  1085, 1072, 1082, 1072, 1086, 1085, 1072, 1082, 1086, 1074, 1086, 1085, 1076, 1077, 1086, 1085, 1080, 1086, 1085,
+  1080, 1077, 1086, 1085, 1086, 1086, 1085, 1086, 1112, 1086, 1087, 1086, 1089, 1074, 1077, 1084, 1086, 1089, 1074,
+  1077, 1085, 1086, 1089, 1077, 1084, 1086, 1089, 1084, 1080, 1086, 1089, 1091, 1084, 1086, 1089, 1091, 1084, 1076,
+  1077, 1089, 1077, 1090, 1086, 1089, 1091, 1084, 1085, 1072, 1077, 1089, 1077, 1090, 1086, 1089, 1091, 1084, 1089,
+  1090, 1086, 1090, 1080, 1090, 1085, 1080, 1086, 1090, 1072, 1076, 1077, 1086, 1090, 1080, 1086, 1090, 1082, 1072,
+  1082, 1086, 1086, 1090, 1082, 1072, 1112, 1086, 1090, 1082, 1086, 1075, 1072, 1086, 1090, 1082, 1086, 1083, 1082,
+  1091, 1086, 1090, 1090, 1072, 1084, 1091, 1086, 1090, 1090, 1091, 1082, 1072, 1086, 1092, 1086, 1093, 1086, 1112,
+  1087, 1072, 1087, 1072, 1082, 1087, 1072, 1087, 1072, 1087, 1072, 1088, 1076, 1086, 1085, 1087, 1072, 1090, 1080,
+  1087, 1072, 1091, 1087, 1072, 1095, 1077, 1087, 1077, 1077, 1089, 1077, 1090, 1087, 1077, 1082, 1080, 1087, 1077,
+  1090, 1087, 1077, 1090, 1085, 1072, 1077, 1089, 1077, 1090, 1087, 1077, 1090, 1089, 1090, 1086, 1090, 1080, 1085,
+  1080, 1087, 1077, 1090, 1090, 1080, 1087, 1080, 1087, 1080, 1089, 1087, 1083, 1072, 1089, 1087, 1083, 1091, 1089,
+  1087, 1086, 1087, 1086, 1073, 1072, 1074, 1085, 1086, 1087, 1086, 1073, 1083, 1080, 1089, 1082, 1091, 1087, 1086,
+  1073, 1088, 1079, 1086, 1087, 1086, 1073, 1091, 1085, 1080, 1087, 1086, 1074, 1077, 1116, 1077, 1087, 1086, 1074,
+  1090, 1086, 1088, 1085, 1086, 1087, 1086, 1076, 1087, 1086, 1076, 1072, 1083, 1077, 1082, 1091, 1087, 1086, 1076,
+  1086, 1083, 1091, 1087, 1086, 1076, 1086, 1094, 1085, 1072, 1087, 1086, 1076, 1088, 1091, 1075, 1086, 1087, 1086,
+  1079, 1072, 1076, 1080, 1087, 1086, 1080, 1085, 1072, 1082, 1074, 1072, 1087, 1086, 1080, 1085, 1072, 1082, 1074,
+  1080, 1087, 1086, 1080, 1085, 1072, 1082, 1074, 1086, 1087, 1086, 1080, 1085, 1072, 1082, 1086, 1074, 1087, 1086,
+  1080, 1085, 1072, 1082, 1091, 1087, 1086, 1082, 1072, 1078, 1077, 1087, 1086, 1082, 1072, 1078, 1091, 1074, 1072,
+  1087, 1086, 1082, 1088, 1072, 1112, 1087, 1086, 1083, 1085, 1086, 1087, 1086, 1084, 1072, 1083, 1082, 1091, 1087,
+  1086, 1084, 1077, 1107, 1091, 1087, 1086, 1085, 1072, 1090, 1072, 1084, 1091, 1087, 1086, 1085, 1077, 1082, 1086,
+  1075, 1072, 1096, 1087, 1086, 1085, 1077, 1082, 1086, 1112, 1087, 1086, 1088, 1072, 1076, 1080, 1087, 1086, 1088,
+  1072, 1079, 1083, 1080, 1095, 1077, 1085, 1087, 1086, 1088, 1072, 1079, 1083, 1080, 1095, 1085, 1072, 1087, 1086,
+  1088, 1072, 1079, 1083, 1080, 1095, 1085, 1080, 1087, 1086, 1088, 1072, 1079, 1083, 1080, 1095, 1085, 1086, 1087,
+  1086, 1089, 1077, 1076, 1091, 1074, 1072, 1087, 1086, 1089, 1083, 1077, 1087, 1086, 1089, 1083, 1077, 1076, 1077,
+  1085, 1087, 1086, 1089, 1083, 1077, 1076, 1085, 1072, 1087, 1086, 1089, 1083, 1077, 1076, 1085, 1080, 1087, 1086,
+  1089, 1083, 1077, 1076, 1085, 1086, 1087, 1086, 1089, 1087, 1086, 1088, 1086, 1087, 1086, 1090, 1077, 1075, 1087,
+  1086, 1090, 1086, 1072, 1087, 1086, 1096, 1080, 1088, 1086, 1082, 1086, 1087, 1088, 1072, 1074, 1080, 1087, 1088,
+  1072, 1079, 1085, 1086, 1087, 1088, 1074, 1087, 1088, 1077, 1076, 1087, 1088, 1077, 1079, 1087, 1088, 1077, 1082,
+  1091, 1087, 1088, 1077, 1090, 1077, 1078, 1085, 1086, 1087, 1088, 1077, 1090, 1093, 1086, 1076, 1077, 1085, 1087,
+  1088, 1077, 1090, 1093, 1086, 1076, 1085, 1072, 1087, 1088, 1077, 1090, 1093, 1086, 1076, 1085, 1080, 1087, 1088,
+  1077, 1090, 1093, 1086, 1076, 1085, 1080, 1082, 1087, 1088, 1077, 1090, 1093, 1086, 1076, 1085, 1086, 1087, 1088,
+  1080, 1087, 1088, 1080, 1089, 1074, 1086, 1080, 1087, 1088, 1080, 1090, 1086, 1072, 1087, 1088, 1080, 1095, 1080,
+  1085, 1091, 1074, 1072, 1087, 1088, 1080, 1112, 1072, 1090, 1085, 1086, 1087, 1088, 1086, 1089, 1090, 1086, 1087,
+  1088, 1086, 1090, 1080, 1074, 1087, 1088, 1088, 1087, 1089, 1090, 1087, 1091, 1082, 1087, 1091, 1089, 1090, 1086,
+  1087, 1091, 1092, 1087, 1091, 1112, 1087, 1092, 1091, 1112, 1087, 1096, 1090, 1088, 1072, 1076, 1080, 1088, 1072,
+  1079, 1083, 1080, 1095, 1077, 1085, 1088, 1072, 1079, 1083, 1080, 1095, 1085, 1072, 1088, 1072, 1079, 1083, 1080,
+  1095, 1085, 1080, 1088, 1072, 1079, 1083, 1080, 1095, 1085, 1086, 1088, 1072, 1079, 1085, 1080, 1088, 1072, 1079,
+  1086, 1088, 1091, 1078, 1077, 1085, 1088, 1072, 1079, 1088, 1077, 1076, 1083, 1080, 1074, 1088, 1072, 1084, 1082,
+  1080, 1090, 1077, 1088, 1072, 1084, 1085, 1086, 1086, 1073, 1088, 1072, 1079, 1085, 1086, 1088, 1072, 1089, 1090,
+  1088, 1077, 1074, 1086, 1078, 1077, 1085, 1086, 1088, 1072, 1089, 1090, 1088, 1077, 1087, 1077, 1088, 1077, 1085,
+  1086, 1088, 1072, 1089, 1095, 1091, 1074, 1089, 1090, 1074, 1091, 1074, 1072, 1085, 1086, 1088, 1072, 1090, 1086,
+  1073, 1086, 1088, 1085, 1086, 1088, 1077, 1095, 1077, 1088, 1086, 1076, 1077, 1085, 1089, 1089, 1072, 1082, 1072,
+  1085, 1089, 1072, 1084, 1089, 1072, 1084, 1072, 1089, 1072, 1084, 1080, 1089, 1072, 1084, 1080, 1090, 1077, 1089,
+  1072, 1084, 1086, 1089, 1072, 1084, 1086, 1090, 1080, 1089, 1074, 1086, 1077, 1089, 1074, 1086, 1080, 1089, 1074,
+  1086, 1112, 1089, 1074, 1086, 1112, 1072, 1089, 1077, 1089, 1077, 1073, 1077, 1089, 1077, 1073, 1077, 1089, 1080,
+  1089, 1077, 1075, 1072, 1089, 1077, 1076, 1084, 1080, 1089, 1077, 1076, 1091, 1084, 1089, 1077, 1076, 1091, 1084,
+  1076, 1077, 1089, 1077, 1090, 1089, 1077, 1076, 1091, 1084, 1085, 1072, 1077, 1089, 1077, 1090, 1089, 1077, 1076,
+  1091, 1084, 1089, 1090, 1086, 1090, 1080, 1085, 1080, 1089, 1077, 1082, 1072, 1076, 1077, 1089, 1077, 1082, 1072,
+  1082, 1086, 1074, 1089, 1077, 1082, 1080, 1089, 1077, 1082, 1086, 1075, 1072, 1096, 1089, 1077, 1082, 1086, 1075,
+  1086, 1089, 1077, 1082, 1086, 1084, 1091, 1089, 1077, 1082, 1086, 1112, 1089, 1077, 1082, 1086, 1112, 1076, 1085,
+  1077, 1074, 1085, 1086, 1089, 1077, 1084, 1089, 1077, 1085, 1077, 1096, 1090, 1086, 1089, 1077, 1087, 1072, 1082,
+  1089, 1077, 1088, 1080, 1086, 1079, 1077, 1085, 1089, 1077, 1088, 1080, 1086, 1079, 1085, 1072, 1089, 1077, 1088,
+  1080, 1086, 1079, 1085, 1080, 1089, 1077, 1088, 1080, 1086, 1079, 1085, 1086, 1089, 1077, 1090, 1089, 1077, 1095,
+  1080, 1112, 1089, 1077, 1096, 1090, 1086, 1089, 1080, 1089, 1080, 1082, 1090, 1077, 1088, 1089, 1080, 1086, 1090,
+  1089, 1080, 1087, 1089, 1080, 1088, 1077, 1095, 1089, 1080, 1090, 1077, 1089, 1080, 1095, 1082, 1086, 1089, 1082,
+  1086, 1082, 1089, 1082, 1086, 1088, 1086, 1089, 1082, 1088, 1094, 1089, 1083, 1077, 1076, 1073, 1077, 1085, 1080,
+  1082, 1089, 1083, 1077, 1076, 1073, 1077, 1085, 1080, 1095, 1082, 1072, 1089, 1083, 1077, 1076, 1077, 1085, 1089,
+  1083, 1077, 1076, 1086, 1074, 1072, 1090, 1077, 1083, 1085, 1086, 1089, 1083, 1077, 1076, 1089, 1090, 1074, 1077,
+  1085, 1086, 1089, 1084, 1077, 1089, 1086, 1089, 1086, 1085, 1077, 1089, 1086, 1087, 1089, 1090, 1074, 1077, 1085,
+  1089, 1086, 1087, 1089, 1090, 1074, 1077, 1085, 1072, 1089, 1086, 1087, 1089, 1090, 1074, 1077, 1085, 1080, 1089,
+  1086, 1087, 1089, 1090, 1074, 1077, 1085, 1086, 1089, 1086, 1089, 1077, 1089, 1086, 1089, 1077, 1084, 1089, 1087,
+  1086, 1083, 1072, 1112, 1089, 1087, 1086, 1088, 1077, 1076, 1089, 1087, 1086, 1088, 1086, 1089, 1087, 1088, 1077,
+  1084, 1072, 1089, 1087, 1088, 1086, 1090, 1080, 1089, 1087, 1088, 1086, 1090, 1080, 1074, 1089, 1088, 1077, 1076,
+  1089, 1088, 1077, 1076, 1077, 1089, 1088, 1077, 1116, 1085, 1086, 1089, 1088, 1086, 1095, 1077, 1085, 1089, 1089,
+  1090, 1089, 1090, 1072, 1074, 1072, 1089, 1090, 1072, 1074, 1072, 1072, 1090, 1089, 1090, 1072, 1074, 1072, 1084,
+  1089, 1090, 1072, 1074, 1072, 1084, 1077, 1089, 1090, 1072, 1074, 1072, 1090, 1077, 1089, 1090, 1072, 1074, 1072,
+  1096, 1089, 1090, 1072, 1074, 1080, 1089, 1090, 1077, 1089, 1090, 1086, 1089, 1090, 1086, 1087, 1089, 1090, 1088,
+  1072, 1085, 1072, 1089, 1091, 1084, 1089, 1091, 1084, 1072, 1089, 1091, 1087, 1077, 1088, 1089, 1091, 1089, 1089,
+  1104, 1090, 1072, 1090, 1072, 1072, 1090, 1072, 1082, 1072, 1090, 1072, 1082, 1074, 1072, 1090, 1072, 1082, 1074,
+  1080, 1090, 1072, 1082, 1086, 1074, 1090, 1072, 1084, 1072, 1084, 1090, 1072, 1084, 1091, 1090, 1072, 1087, 1090,
+  1074, 1086, 1077, 1090, 1077, 1090, 1077, 1073, 1077, 1090, 1077, 1073, 1077, 1082, 1072, 1090, 1077, 1082, 1090,
+  1077, 1082, 1086, 1090, 1090, 1080, 1090, 1080, 1077, 1090, 1080, 1079, 1077, 1090, 1080, 1082, 1080, 1090, 1086,
+  1072, 1090, 1086, 1075, 1072, 1096, 1090, 1086, 1112, 1090, 1088, 1072, 1082, 1090, 1088, 1072, 1089, 1090, 1088,
+  1077, 1073, 1072, 1090, 1088, 1077, 1090, 1090, 1088, 1080, 1090, 1088, 1080, 1077, 1089, 1077, 1090, 1090, 1088,
+  1080, 1085, 1072, 1077, 1089, 1090, 1090, 1088, 1080, 1089, 1090, 1072, 1090, 1088, 1091, 1087, 1090, 1088, 1091,
+  1087, 1072, 1090, 1088, 1091, 1089, 1090, 1091, 1090, 1091, 1082, 1072, 1090, 1091, 1082, 1091, 1090, 1091, 1082,
+  1091, 1096, 1090, 1086, 1090, 1091, 1092, 1091, 1091, 1072, 1091, 1073, 1072, 1074, 1086, 1091, 1074, 1080, 1091,
+  1078, 1072, 1089, 1085, 1086, 1091, 1079, 1091, 1088, 1072, 1091, 1091, 1091, 1092, 1091, 1093, 1072, 1091, 1096,
+  1091, 1096, 1090, 1077, 1092, 1072, 1079, 1077, 1085, 1092, 1072, 1083, 1072, 1092, 1080, 1083, 1092, 1080, 1083,
+  1072, 1085, 1092, 1080, 1089, 1092, 1080, 1091, 1092, 1080, 1113, 1072, 1085, 1092, 1086, 1073, 1092, 1086, 1085,
+  1093, 1072, 1093, 1077, 1093, 1077, 1112, 1093, 1080, 1093, 1084, 1093, 1086, 1094, 1072, 1082, 1094, 1072, 1087,
+  1094, 1077, 1083, 1080, 1085, 1072, 1094, 1077, 1083, 1086, 1094, 1080, 1094, 1095, 1077, 1082, 1072, 1112, 1095,
+  1077, 1089, 1090, 1086, 1095, 1077, 1090, 1074, 1088, 1090, 1095, 1077, 1090, 1080, 1088, 1080, 1095, 1077, 1090,
+  1080, 1088, 1080, 1077, 1089, 1077, 1090, 1095, 1077, 1090, 1080, 1088, 1080, 1085, 1072, 1077, 1089, 1077, 1090,
+  1095, 1077, 1090, 1080, 1088, 1089, 1090, 1086, 1090, 1080, 1085, 1080, 1095, 1080, 1077, 1095, 1080, 1080, 1095,
+  1080, 1082, 1095, 1080, 1085, 1080, 1095, 1080, 1096, 1095, 1080, 1112, 1095, 1080, 1112, 1072, 1095, 1080, 1112,
+  1096, 1090, 1086, 1095, 1082, 1088, 1072, 1087, 1095, 1086, 1084, 1091, 1095, 1091, 1082, 1095, 1091, 1082, 1096,
+  1095, 1091, 1084, 1091, 1095, 1091, 1085, 1082, 1080, 1096, 1077, 1077, 1089, 1077, 1090, 1096, 1077, 1089, 1085,
+  1072, 1077, 1089, 1077, 1090, 1096, 1077, 1089, 1090, 1096, 1077, 1089, 1090, 1080, 1096, 1077, 1089, 1090, 1086,
+  1090, 1080, 1085, 1080, 1096, 1080, 1088, 1091, 1084, 1096, 1083, 1072, 1082, 1096, 1083, 1072, 1087, 1096, 1083,
+  1091, 1087, 1096, 1084, 1088, 1082, 1096, 1090, 1086, 1096, 1090, 1086, 1075, 1086, 1076, 1077, 1096, 1090, 1086,
+  1084, 1096, 1090, 1086, 1090, 1091, 1082, 1091, 1096, 1090, 1088, 1072, 1082, 1096, 1090, 1088, 1072, 1087, 1096,
+  1091, 1116, 1091, 1088, 1107, 1080, 1076, 1080, 1107, 1086, 1072, 1107, 1086, 1072, 1084, 1080, 1090, 1080, 1109,
+  1072, 1085, 1109, 1077, 1109, 1080, 1085, 1112, 1072, 1112, 1072, 1076, 1077, 1094, 1112, 1072, 1079, 1077, 1112,
+  1072, 1083, 1080, 1112, 1072, 1089, 1112, 1072, 1089, 1082, 1072, 1112, 1086, 1082, 1116, 1077, 1116, 1077, 1096,
+  1082, 1080, 1117, 1119, 1072, 1085, 1072, 1084,
+};
+
+static const uint32_t stop_word_offsets[789] = {
+  0, 2, 3, 7, 9, 12, 17, 19, 22, 26, 29, 33, 35, 38, 41, 43, 46, 48, 56, 64, 66, 70, 73, 78, 83, 86, 89, 92, 96, 101,
+  104, 107, 110, 112, 115, 118, 123, 128, 131, 138, 146, 151, 155, 157, 164, 167, 170, 173, 178, 184, 189, 192, 197,
+  203, 206, 210, 214, 220, 224, 226, 229, 232, 235, 241, 244, 247, 252, 257, 260, 263, 265, 270, 274, 280, 284, 286,
+  289, 293, 296, 303, 308, 314, 316, 319, 322, 329, 332, 336, 341, 344, 352, 356, 362, 364, 369, 371, 375, 383, 387,
+  390, 393, 396, 398, 402, 406, 409, 413, 416, 419, 426, 435, 441, 444, 450, 456, 462, 467, 474, 481, 487, 489, 498,
+  503, 514, 526, 533, 537, 540, 545, 550, 555, 563, 570, 578, 585, 590, 592, 597, 600, 603, 606, 608, 615, 621, 627,
+  632, 639, 648, 655, 663, 668, 672, 675, 679, 684, 691, 696, 703, 710, 715, 722, 725, 728, 732, 733, 738, 741, 745,
+  748, 753, 757, 765, 774, 784, 789, 793, 798, 801, 807, 811, 814, 816, 819, 822, 825, 831, 833, 835, 839, 843, 845,
+  850, 856, 859, 865, 874, 880, 886, 889, 894, 900, 904, 909, 914, 919, 924, 928, 932, 938, 941, 946, 951, 954, 955,
+  959, 961, 968, 975, 981, 986, 989, 995, 1001, 1003, 1006, 1010, 1015, 1021, 1027, 1031, 1036, 1041, 1045, 1050, 1053,
+  1058, 1065, 1074, 1085, 1095, 1106, 1117, 1127, 1132, 1140, 1146, 1154, 1163, 1172, 1181, 1191, 1202, 1213, 1224,
+  1233, 1239, 1243, 1247, 1252, 1255, 1257, 1260, 1264, 1266, 1271, 1273, 1275, 1279, 1285, 1289, 1294, 1300, 1303,
+  1306, 1308, 1311, 1314, 1318, 1322, 1326, 1329, 1332, 1342, 1350, 1355, 1359, 1362, 1371, 1380, 1389, 1396, 1399,
+  1404, 1407, 1411, 1418, 1424, 1428, 1432, 1435, 1438, 1441, 1445, 1453, 1456, 1458, 1464, 1468, 1472, 1474, 1478,
+  1481, 1483, 1488, 1493, 1497, 1500, 1503, 1509, 1511, 1515, 1520, 1524, 1533, 1540, 1542, 1545, 1549, 1555, 1560,
+  1564, 1567, 1571, 1575, 1579, 1585, 1587, 1593, 1599, 1602, 1606, 1608, 1615, 1624, 1627, 1633, 1638, 1643, 1649,
+  1653, 1656, 1663, 1670, 1679, 1686, 1692, 1695, 1703, 1711, 1719, 1725, 1731, 1737, 1742, 1745, 1749, 1753, 1757,
+  1760, 1768, 1776, 1784, 1786, 1789, 1793, 1798, 1804, 1810, 1816, 1820, 1824, 1830, 1836, 1843, 1849, 1854, 1859,
+  1866, 1872, 1877, 1884, 1888, 1893, 1897, 1902, 1907, 1912, 1917, 1923, 1930, 1937, 1942, 1944, 1947, 1952, 1957,
+  1962, 1967, 1970, 1973, 1979, 1985, 1992, 1998, 2004, 2009, 2012, 2016, 2020, 2024, 2029, 2034, 2036, 2038, 2039,
+  2042, 2045, 2049, 2053, 2057, 2062, 2066, 2070, 2072, 2078, 2081, 2089, 2096, 2102, 2107, 2112, 2119, 2121, 2124,
+  2128, 2133, 2139, 2143, 2146, 2150, 2153, 2157, 2159, 2164, 2169, 2173, 2177, 2181, 2190, 2200, 2212, 2217, 2220,
+  2226, 2231, 2237, 2244, 2250, 2256, 2258, 2260, 2262, 2264, 2267, 2271, 2277, 2281, 2284, 2288, 2294, 2298, 2301,
+  2310, 2320, 2325, 2327, 2330, 2334, 2338, 2340, 2347, 2355, 2361, 2367, 2373, 2381, 2384, 2392, 2398, 2405, 2412,
+  2418, 2426, 2434, 2442, 2450, 2457, 2463, 2471, 2477, 2482, 2489, 2495, 2503, 2512, 2519, 2525, 2535, 2545, 2555,
+  2565, 2573, 2578, 2586, 2594, 2602, 2610, 2617, 2622, 2627, 2635, 2640, 2646, 2649, 2653, 2657, 2662, 2670, 2679,
+  2688, 2697, 2707, 2716, 2719, 2726, 2732, 2741, 2749, 2755, 2761, 2764, 2767, 2770, 2775, 2778, 2781, 2785, 2788,
+  2792, 2800, 2808, 2816, 2824, 2829, 2838, 2847, 2854, 2866, 2878, 2890, 2904, 2913, 2917, 2922, 2923, 2928, 2931,
+  2935, 2939, 2945, 2949, 2955, 2959, 2963, 2967, 2972, 2974, 2978, 2984, 2988, 2993, 2998, 3008, 3019, 3031, 3037,
+  3044, 3048, 3055, 3061, 3067, 3072, 3083, 3086, 3093, 3098, 3106, 3114, 3122, 3130, 3133, 3138, 3143, 3145, 3151,
+  3155, 3158, 3163, 3167, 3172, 3176, 3181, 3185, 3194, 3205, 3211, 3223, 3233, 3236, 3238, 3242, 3250, 3259, 3268,
+  3277, 3281, 3286, 3292, 3298, 3303, 3309, 3315, 3322, 3326, 3331, 3337, 3343, 3346, 3351, 3358, 3364, 3371, 3378,
+  3384, 3389, 3392, 3395, 3399, 3405, 3408, 3412, 3417, 3420, 3422, 3424, 3427, 3431, 3436, 3441, 3446, 3451, 3455,
+  3458, 3462, 3464, 3468, 3474, 3477, 3482, 3484, 3487, 3491, 3495, 3498, 3503, 3506, 3510, 3514, 3519, 3523, 3526,
+  3533, 3541, 3547, 3551, 3556, 3560, 3562, 3566, 3570, 3577, 3580, 3581, 3583, 3588, 3591, 3597, 3599, 3602, 3604,
+  3606, 3609, 3611, 3615, 3620, 3624, 3627, 3632, 3635, 3638, 3643, 3646, 3649, 3651, 3653, 3656, 3658, 3660, 3662,
+  3665, 3668, 3674, 3678, 3681, 3686, 3691, 3697, 3703, 3713, 3725, 3737, 3740, 3743, 3746, 3750, 3753, 3756, 3760,
+  3766, 3771, 3775, 3778, 3782, 3786, 3791, 3797, 3806, 3810, 3815, 3824, 3829, 3833, 3837, 3841, 3845, 3848, 3855,
+  3859, 3866, 3871, 3876, 3881, 3885, 3888, 3895, 3898, 3900, 3903, 3905, 3910, 3914, 3918, 3921, 3926, 3929, 3931,
+  3936, 3937, 3942,
+};
+
+static const uint32_t keep_ranges[30] = {
+  48, 57, 65, 90, 97, 122, 1024, 1024, 1027, 1027, 1029, 1029, 1032, 1034, 1036, 1037, 1039, 1104, 1107, 1107, 1109,
+  1109, 1112, 1114, 1116, 1117, 1119, 1119, 7296, 7302,
+};
+
+const narsil_language narsil_language_macedonian = {
+  .name = "macedonian",
+  .revision = "1",
+  .stop_word_units = stop_word_units,
+  .stop_word_offsets = stop_word_offsets,
+  .stop_word_count = 788,
+  .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
+  .keep_ranges = keep_ranges,
+  .keep_range_count = 15,
+  .splits_code_points = 0,
+  .strips_possessive = 0,
+  .normalises_diacritics = 0,
+  .min_token_length = 1,
+  .ngram_size = 0,
+  .normalise = narsil_macedonian_normalise,
+  .stem_by_rules = NULL,
+  .create_snowball = NULL,
+  .snowball_stem = NULL,
+  .close_snowball = NULL,
+};

package/cpp/core/src/languages/data/malagasy.c

@@ -0,0 +1,51 @@
+#include "../../analysis/languages.h"
+#include "declarations.h"
+
+#include <stddef.h>
+#include <stdint.h>
+
+static const uint16_t stop_word_units[215] = {
+  97, 104, 111, 97, 104, 121, 97, 109, 105, 110, 97, 110, 97, 111, 97, 110, 97, 121, 97, 110, 116, 115, 105, 107, 97,
+  97, 110, 121, 97, 111, 97, 114, 121, 97, 118, 111, 107, 111, 97, 97, 118, 121, 97, 122, 121, 100, 97, 104, 111, 108,
+  111, 100, 105, 97, 101, 102, 97, 101, 116, 111, 102, 97, 102, 111, 97, 110, 97, 104, 111, 104, 111, 101, 105, 97, 110,
+  97, 111, 105, 97, 110, 97, 114, 101, 111, 105, 104, 97, 110, 121, 105, 108, 97, 121, 105, 110, 100, 114, 105, 110,
+  100, 114, 97, 105, 110, 121, 105, 111, 105, 114, 101, 111, 105, 115, 97, 107, 121, 105, 115, 105, 107, 97, 105, 116,
+  121, 105, 122, 97, 104, 97, 121, 105, 122, 97, 110, 121, 105, 122, 97, 111, 105, 122, 97, 121, 105, 122, 121, 107, 97,
+  107, 111, 97, 109, 98, 97, 109, 98, 111, 108, 97, 109, 105, 115, 121, 110, 97, 110, 111, 110, 111, 104, 111, 110, 121,
+  114, 97, 104, 97, 114, 101, 104, 101, 102, 97, 115, 97, 109, 121, 115, 97, 116, 114, 105, 97, 115, 121, 116, 97, 104,
+  97, 107, 97, 116, 97, 109, 105, 110, 116, 111, 121, 116, 115, 121, 118, 97, 111,
+};
+
+static const uint32_t stop_word_offsets[56] = {
+  0, 3, 6, 10, 14, 18, 25, 28, 30, 33, 39, 42, 45, 51, 54, 57, 60, 62, 67, 69, 72, 77, 84, 89, 93, 102, 105, 107, 111,
+  116, 121, 124, 130, 135, 139, 143, 146, 148, 151, 154, 159, 163, 165, 167, 171, 173, 177, 183, 187, 193, 195, 201,
+  206, 209, 212, 215,
+};
+
+static const uint32_t keep_ranges[74] = {
+  48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 7424, 7461, 7468, 7516, 7522,
+  7525, 7531, 7543, 7545, 7614, 7680, 7935, 8305, 8305, 8319, 8319, 8336, 8348, 8490, 8491, 8498, 8498, 8526, 8526,
+  8544, 8584, 11360, 11391, 42786, 42887, 42891, 42972, 42993, 43007, 43824, 43866, 43868, 43876, 43878, 43881, 64256,
+  64262, 65313, 65338, 65345, 65370, 67456, 67461, 67463, 67504, 67506, 67514, 122624, 122654, 122661, 122666,
+};
+
+const narsil_language narsil_language_malagasy = {
+  .name = "malagasy",
+  .revision = "1",
+  .stop_word_units = stop_word_units,
+  .stop_word_offsets = stop_word_offsets,
+  .stop_word_count = 55,
+  .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
+  .keep_ranges = keep_ranges,
+  .keep_range_count = 37,
+  .splits_code_points = 1,
+  .strips_possessive = 0,
+  .normalises_diacritics = 0,
+  .min_token_length = 1,
+  .ngram_size = 0,
+  .normalise = NULL,
+  .stem_by_rules = NULL,
+  .create_snowball = NULL,
+  .snowball_stem = NULL,
+  .close_snowball = NULL,
+};