stride-align 0.6.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/LICENSE +201 -0
- data/NOTICE +255 -0
- data/README.md +107 -0
- data/data/bmpm_data/gen_approx_any.txt +131 -0
- data/data/bmpm_data/gen_approx_arabic.txt +26 -0
- data/data/bmpm_data/gen_approx_common.txt +233 -0
- data/data/bmpm_data/gen_approx_cyrillic.txt +18 -0
- data/data/bmpm_data/gen_approx_czech.txt +18 -0
- data/data/bmpm_data/gen_approx_dutch.txt +18 -0
- data/data/bmpm_data/gen_approx_english.txt +47 -0
- data/data/bmpm_data/gen_approx_french.txt +25 -0
- data/data/bmpm_data/gen_approx_german.txt +73 -0
- data/data/bmpm_data/gen_approx_greek.txt +18 -0
- data/data/bmpm_data/gen_approx_greeklatin.txt +20 -0
- data/data/bmpm_data/gen_approx_hebrew.txt +18 -0
- data/data/bmpm_data/gen_approx_hungarian.txt +18 -0
- data/data/bmpm_data/gen_approx_italian.txt +18 -0
- data/data/bmpm_data/gen_approx_polish.txt +84 -0
- data/data/bmpm_data/gen_approx_portuguese.txt +18 -0
- data/data/bmpm_data/gen_approx_romanian.txt +18 -0
- data/data/bmpm_data/gen_approx_russian.txt +48 -0
- data/data/bmpm_data/gen_approx_spanish.txt +21 -0
- data/data/bmpm_data/gen_approx_turkish.txt +18 -0
- data/data/bmpm_data/gen_exact_any.txt +40 -0
- data/data/bmpm_data/gen_exact_approx_common.txt +79 -0
- data/data/bmpm_data/gen_exact_arabic.txt +18 -0
- data/data/bmpm_data/gen_exact_common.txt +32 -0
- data/data/bmpm_data/gen_exact_cyrillic.txt +18 -0
- data/data/bmpm_data/gen_exact_czech.txt +18 -0
- data/data/bmpm_data/gen_exact_dutch.txt +18 -0
- data/data/bmpm_data/gen_exact_english.txt +18 -0
- data/data/bmpm_data/gen_exact_french.txt +18 -0
- data/data/bmpm_data/gen_exact_german.txt +18 -0
- data/data/bmpm_data/gen_exact_greek.txt +18 -0
- data/data/bmpm_data/gen_exact_greeklatin.txt +18 -0
- data/data/bmpm_data/gen_exact_hebrew.txt +18 -0
- data/data/bmpm_data/gen_exact_hungarian.txt +18 -0
- data/data/bmpm_data/gen_exact_italian.txt +18 -0
- data/data/bmpm_data/gen_exact_polish.txt +23 -0
- data/data/bmpm_data/gen_exact_portuguese.txt +18 -0
- data/data/bmpm_data/gen_exact_romanian.txt +18 -0
- data/data/bmpm_data/gen_exact_russian.txt +19 -0
- data/data/bmpm_data/gen_exact_spanish.txt +19 -0
- data/data/bmpm_data/gen_exact_turkish.txt +18 -0
- data/data/bmpm_data/gen_hebrew_common.txt +113 -0
- data/data/bmpm_data/gen_lang.txt +295 -0
- data/data/bmpm_data/gen_languages.txt +36 -0
- data/data/bmpm_data/gen_rules_any.txt +367 -0
- data/data/bmpm_data/gen_rules_arabic.txt +76 -0
- data/data/bmpm_data/gen_rules_cyrillic.txt +99 -0
- data/data/bmpm_data/gen_rules_czech.txt +67 -0
- data/data/bmpm_data/gen_rules_dutch.txt +78 -0
- data/data/bmpm_data/gen_rules_english.txt +113 -0
- data/data/bmpm_data/gen_rules_french.txt +114 -0
- data/data/bmpm_data/gen_rules_german.txt +129 -0
- data/data/bmpm_data/gen_rules_greek.txt +97 -0
- data/data/bmpm_data/gen_rules_greeklatin.txt +118 -0
- data/data/bmpm_data/gen_rules_hebrew.txt +62 -0
- data/data/bmpm_data/gen_rules_hungarian.txt +83 -0
- data/data/bmpm_data/gen_rules_italian.txt +77 -0
- data/data/bmpm_data/gen_rules_polish.txt +185 -0
- data/data/bmpm_data/gen_rules_portuguese.txt +105 -0
- data/data/bmpm_data/gen_rules_romanian.txt +64 -0
- data/data/bmpm_data/gen_rules_russian.txt +142 -0
- data/data/bmpm_data/gen_rules_spanish.txt +85 -0
- data/data/bmpm_data/gen_rules_turkish.txt +50 -0
- data/data/keyboard_data/qwerty.npy +0 -0
- data/data/matrix_data/BLOSUM100 +31 -0
- data/data/matrix_data/BLOSUM30 +31 -0
- data/data/matrix_data/BLOSUM35 +31 -0
- data/data/matrix_data/BLOSUM40 +31 -0
- data/data/matrix_data/BLOSUM45 +25 -0
- data/data/matrix_data/BLOSUM50 +25 -0
- data/data/matrix_data/BLOSUM55 +31 -0
- data/data/matrix_data/BLOSUM60 +31 -0
- data/data/matrix_data/BLOSUM62 +25 -0
- data/data/matrix_data/BLOSUM65 +31 -0
- data/data/matrix_data/BLOSUM70 +31 -0
- data/data/matrix_data/BLOSUM75 +31 -0
- data/data/matrix_data/BLOSUM80 +25 -0
- data/data/matrix_data/BLOSUM85 +31 -0
- data/data/matrix_data/BLOSUM90 +25 -0
- data/data/matrix_data/NUC.4.4 +25 -0
- data/data/matrix_data/PAM10 +34 -0
- data/data/matrix_data/PAM100 +34 -0
- data/data/matrix_data/PAM110 +34 -0
- data/data/matrix_data/PAM120 +34 -0
- data/data/matrix_data/PAM130 +34 -0
- data/data/matrix_data/PAM140 +34 -0
- data/data/matrix_data/PAM150 +34 -0
- data/data/matrix_data/PAM160 +34 -0
- data/data/matrix_data/PAM170 +34 -0
- data/data/matrix_data/PAM180 +34 -0
- data/data/matrix_data/PAM190 +34 -0
- data/data/matrix_data/PAM20 +34 -0
- data/data/matrix_data/PAM200 +34 -0
- data/data/matrix_data/PAM210 +34 -0
- data/data/matrix_data/PAM220 +34 -0
- data/data/matrix_data/PAM230 +34 -0
- data/data/matrix_data/PAM240 +34 -0
- data/data/matrix_data/PAM250 +25 -0
- data/data/matrix_data/PAM260 +34 -0
- data/data/matrix_data/PAM270 +34 -0
- data/data/matrix_data/PAM280 +34 -0
- data/data/matrix_data/PAM290 +34 -0
- data/data/matrix_data/PAM30 +25 -0
- data/data/matrix_data/PAM300 +34 -0
- data/data/matrix_data/PAM310 +34 -0
- data/data/matrix_data/PAM320 +34 -0
- data/data/matrix_data/PAM330 +34 -0
- data/data/matrix_data/PAM340 +34 -0
- data/data/matrix_data/PAM350 +34 -0
- data/data/matrix_data/PAM360 +34 -0
- data/data/matrix_data/PAM370 +34 -0
- data/data/matrix_data/PAM380 +34 -0
- data/data/matrix_data/PAM390 +34 -0
- data/data/matrix_data/PAM40 +34 -0
- data/data/matrix_data/PAM400 +34 -0
- data/data/matrix_data/PAM410 +34 -0
- data/data/matrix_data/PAM420 +34 -0
- data/data/matrix_data/PAM430 +34 -0
- data/data/matrix_data/PAM440 +34 -0
- data/data/matrix_data/PAM450 +34 -0
- data/data/matrix_data/PAM460 +34 -0
- data/data/matrix_data/PAM470 +34 -0
- data/data/matrix_data/PAM480 +34 -0
- data/data/matrix_data/PAM490 +34 -0
- data/data/matrix_data/PAM50 +34 -0
- data/data/matrix_data/PAM500 +34 -0
- data/data/matrix_data/PAM60 +34 -0
- data/data/matrix_data/PAM70 +25 -0
- data/data/matrix_data/PAM80 +34 -0
- data/data/matrix_data/PAM90 +34 -0
- data/ext/stride_align/backend_avx2.cpp +2 -0
- data/ext/stride_align/backend_avx512bwvl.cpp +2 -0
- data/ext/stride_align/backend_generic.cpp +3 -0
- data/ext/stride_align/backend_impl.hpp +983 -0
- data/ext/stride_align/backend_lasx.cpp +2 -0
- data/ext/stride_align/backend_lsx.cpp +2 -0
- data/ext/stride_align/backend_neon.cpp +2 -0
- data/ext/stride_align/backend_rvv.cpp +2 -0
- data/ext/stride_align/backend_sse41.cpp +2 -0
- data/ext/stride_align/backend_sve.cpp +2 -0
- data/ext/stride_align/backend_sve2.cpp +2 -0
- data/ext/stride_align/backend_vsx.cpp +2 -0
- data/ext/stride_align/beider_morse_impl.cpp +5 -0
- data/ext/stride_align/cpu_detect.cpp +172 -0
- data/ext/stride_align/cpu_detect.hpp +6 -0
- data/ext/stride_align/extconf.rb +114 -0
- data/ext/stride_align/target_profile.hpp +82 -0
- data/ext/stride_align/vendor/beider_morse_impl.cpp +1467 -0
- data/ext/stride_align/vendor/stride_align/alignment.hpp +199 -0
- data/ext/stride_align/vendor/stride_align/batch.hpp +812 -0
- data/ext/stride_align/vendor/stride_align/beider_morse.hpp +121 -0
- data/ext/stride_align/vendor/stride_align/caverphone.hpp +222 -0
- data/ext/stride_align/vendor/stride_align/cologne_phonetic.hpp +202 -0
- data/ext/stride_align/vendor/stride_align/core.hpp +731 -0
- data/ext/stride_align/vendor/stride_align/daitch_mokotoff.hpp +631 -0
- data/ext/stride_align/vendor/stride_align/double_metaphone.hpp +796 -0
- data/ext/stride_align/vendor/stride_align/dtw.hpp +300 -0
- data/ext/stride_align/vendor/stride_align/encoded.hpp +235 -0
- data/ext/stride_align/vendor/stride_align/hamming.hpp +55 -0
- data/ext/stride_align/vendor/stride_align/indel.hpp +1200 -0
- data/ext/stride_align/vendor/stride_align/jaro.hpp +517 -0
- data/ext/stride_align/vendor/stride_align/lcs.hpp +159 -0
- data/ext/stride_align/vendor/stride_align/levenshtein.hpp +1247 -0
- data/ext/stride_align/vendor/stride_align/levenshtein_prepared.hpp +193 -0
- data/ext/stride_align/vendor/stride_align/match_rating.hpp +168 -0
- data/ext/stride_align/vendor/stride_align/metaphone.hpp +291 -0
- data/ext/stride_align/vendor/stride_align/ngram.hpp +176 -0
- data/ext/stride_align/vendor/stride_align/nysiis.hpp +199 -0
- data/ext/stride_align/vendor/stride_align/pairwise_alignment.hpp +465 -0
- data/ext/stride_align/vendor/stride_align/partial_ratio.hpp +486 -0
- data/ext/stride_align/vendor/stride_align/ratcliff_obershelp.hpp +101 -0
- data/ext/stride_align/vendor/stride_align/soundex.hpp +108 -0
- data/ext/stride_align/vendor/stride_align/token_ratios.hpp +445 -0
- data/ext/stride_align/vendor/stride_align/types.hpp +16 -0
- data/ext/stride_align/vendor/stride_align/utf8.hpp +512 -0
- data/ext/stride_align/vendor/stride_align/wratio.hpp +363 -0
- data/lib/stride_align/algorithms.rb +296 -0
- data/lib/stride_align/alignment_path.rb +217 -0
- data/lib/stride_align/backend.rb +47 -0
- data/lib/stride_align/batch.rb +705 -0
- data/lib/stride_align/core.rb +180 -0
- data/lib/stride_align/keyboard.rb +200 -0
- data/lib/stride_align/matrices.rb +403 -0
- data/lib/stride_align/version.rb +5 -0
- data/lib/stride_align.rb +87 -0
- metadata +231 -0
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
// General = Ashkenazic
|
|
19
|
+
|
|
20
|
+
"אי" "" "" "i"
|
|
21
|
+
"עי" "" "" "i"
|
|
22
|
+
"עו" "" "" "VV"
|
|
23
|
+
"או" "" "" "VV"
|
|
24
|
+
|
|
25
|
+
"ג׳" "" "" "Z"
|
|
26
|
+
"ד׳" "" "" "dZ"
|
|
27
|
+
|
|
28
|
+
"א" "" "" "L"
|
|
29
|
+
"ב" "" "" "b"
|
|
30
|
+
"ג" "" "" "g"
|
|
31
|
+
"ד" "" "" "d"
|
|
32
|
+
|
|
33
|
+
"ה" "^" "" "1"
|
|
34
|
+
"ה" "" "$" "1"
|
|
35
|
+
"ה" "" "" ""
|
|
36
|
+
|
|
37
|
+
"וו" "" "" "V"
|
|
38
|
+
"וי" "" "" "WW"
|
|
39
|
+
"ו" "" "" "W"
|
|
40
|
+
"ז" "" "" "z"
|
|
41
|
+
"ח" "" "" "X"
|
|
42
|
+
"ט" "" "" "T"
|
|
43
|
+
"יי" "" "" "i"
|
|
44
|
+
"י" "" "" "i"
|
|
45
|
+
"ך" "" "" "X"
|
|
46
|
+
"כ" "^" "" "K"
|
|
47
|
+
"כ" "" "" "k"
|
|
48
|
+
"ל" "" "" "l"
|
|
49
|
+
"ם" "" "" "m"
|
|
50
|
+
"מ" "" "" "m"
|
|
51
|
+
"ן" "" "" "n"
|
|
52
|
+
"נ" "" "" "n"
|
|
53
|
+
"ס" "" "" "s"
|
|
54
|
+
"ע" "" "" "L"
|
|
55
|
+
"ף" "" "" "f"
|
|
56
|
+
"פ" "" "" "f"
|
|
57
|
+
"ץ" "" "" "C"
|
|
58
|
+
"צ" "" "" "C"
|
|
59
|
+
"ק" "" "" "K"
|
|
60
|
+
"ר" "" "" "r"
|
|
61
|
+
"ש" "" "" "s"
|
|
62
|
+
"ת" "" "" "TB" // only Ashkenazic
|
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
// GENERAL
|
|
19
|
+
|
|
20
|
+
// CONSONANTS
|
|
21
|
+
"sz" "" "" "s"
|
|
22
|
+
"zs" "" "" "Z"
|
|
23
|
+
"cs" "" "" "tS"
|
|
24
|
+
|
|
25
|
+
"ay" "" "" "(oj|aj)"
|
|
26
|
+
"ai" "" "" "(oj|aj)"
|
|
27
|
+
"aj" "" "" "(oj|aj)"
|
|
28
|
+
|
|
29
|
+
"ei" "" "" "(aj|ej)" // German element
|
|
30
|
+
"ey" "" "" "(aj|ej)" // German element
|
|
31
|
+
|
|
32
|
+
"y" "[áo]" "" "j"
|
|
33
|
+
"i" "[áo]" "" "j"
|
|
34
|
+
"ee" "" "" "(ej|e)"
|
|
35
|
+
"ely" "" "" "(ej|eli)"
|
|
36
|
+
"ly" "" "" "(j|li)"
|
|
37
|
+
"gy" "" "[aeouáéóúüöőű]" "dj"
|
|
38
|
+
"gy" "" "" "(d|gi)"
|
|
39
|
+
"ny" "" "[aeouáéóúüöőű]" "nj"
|
|
40
|
+
"ny" "" "" "(n|ni)"
|
|
41
|
+
"ty" "" "[aeouáéóúüöőű]" "tj"
|
|
42
|
+
"ty" "" "" "(t|ti)"
|
|
43
|
+
"qu" "" "" "(ku|kv)"
|
|
44
|
+
"h" "" "$" ""
|
|
45
|
+
|
|
46
|
+
// SPECIAL VOWELS
|
|
47
|
+
"á" "" "" "a"
|
|
48
|
+
"é" "" "" "e"
|
|
49
|
+
"í" "" "" "i"
|
|
50
|
+
"ó" "" "" "o"
|
|
51
|
+
"ú" "" "" "u"
|
|
52
|
+
"ö" "" "" "Y"
|
|
53
|
+
"ő" "" "" "Y"
|
|
54
|
+
"ü" "" "" "Q"
|
|
55
|
+
"ű" "" "" "Q"
|
|
56
|
+
|
|
57
|
+
// LATIN ALPHABET
|
|
58
|
+
"a" "" "" "a"
|
|
59
|
+
"b" "" "" "b"
|
|
60
|
+
"c" "" "" "ts"
|
|
61
|
+
"d" "" "" "d"
|
|
62
|
+
"e" "" "" "E"
|
|
63
|
+
"f" "" "" "f"
|
|
64
|
+
"g" "" "" "g"
|
|
65
|
+
"h" "" "" "h"
|
|
66
|
+
"i" "" "" "I"
|
|
67
|
+
"j" "" "" "j"
|
|
68
|
+
"k" "" "" "k"
|
|
69
|
+
"l" "" "" "l"
|
|
70
|
+
"m" "" "" "m"
|
|
71
|
+
"n" "" "" "n"
|
|
72
|
+
"o" "" "" "o"
|
|
73
|
+
"p" "" "" "p"
|
|
74
|
+
"q" "" "" "k"
|
|
75
|
+
"r" "" "" "r"
|
|
76
|
+
"s" "" "" "(S|s)"
|
|
77
|
+
"t" "" "" "t"
|
|
78
|
+
"u" "" "" "u"
|
|
79
|
+
"v" "" "" "v"
|
|
80
|
+
"w" "" "" "v"
|
|
81
|
+
"x" "" "" "ks"
|
|
82
|
+
"y" "" "" "i"
|
|
83
|
+
"z" "" "" "z"
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
"kh" "" "" "x" // foreign
|
|
19
|
+
|
|
20
|
+
"gli" "" "" "(l|gli)"
|
|
21
|
+
"gn" "" "[aeou]" "(n|nj|gn)"
|
|
22
|
+
"gni" "" "" "(ni|gni)"
|
|
23
|
+
|
|
24
|
+
"gi" "" "[aeou]" "dZ"
|
|
25
|
+
"gg" "" "[ei]" "dZ"
|
|
26
|
+
"g" "" "[ei]" "dZ"
|
|
27
|
+
"h" "[bdgt]" "" "g" // gh is It; others from Arabic translit
|
|
28
|
+
"h" "" "$" "" // foreign
|
|
29
|
+
|
|
30
|
+
"ci" "" "[aeou]" "tS"
|
|
31
|
+
"ch" "" "[ei]" "k"
|
|
32
|
+
"sc" "" "[ei]" "S"
|
|
33
|
+
"cc" "" "[ei]" "tS"
|
|
34
|
+
"c" "" "[ei]" "tS"
|
|
35
|
+
"s" "[aeiou]" "[aeiou]" "z"
|
|
36
|
+
|
|
37
|
+
"i" "[aeou]" "" "j"
|
|
38
|
+
"i" "" "[aeou]" "j"
|
|
39
|
+
"y" "[aeou]" "" "j" // foreign
|
|
40
|
+
"y" "" "[aeou]" "j" // foreign
|
|
41
|
+
|
|
42
|
+
"qu" "" "" "k"
|
|
43
|
+
"uo" "" "" "(vo|o)"
|
|
44
|
+
"u" "" "[aei]" "v"
|
|
45
|
+
|
|
46
|
+
"�" "" "" "e"
|
|
47
|
+
"�" "" "" "e"
|
|
48
|
+
"�" "" "" "o"
|
|
49
|
+
"�" "" "" "o"
|
|
50
|
+
|
|
51
|
+
// LATIN ALPHABET
|
|
52
|
+
"a" "" "" "a"
|
|
53
|
+
"b" "" "" "b"
|
|
54
|
+
"c" "" "" "k"
|
|
55
|
+
"d" "" "" "d"
|
|
56
|
+
"e" "" "" "e"
|
|
57
|
+
"f" "" "" "f"
|
|
58
|
+
"g" "" "" "g"
|
|
59
|
+
"h" "" "" "h"
|
|
60
|
+
"i" "" "" "i"
|
|
61
|
+
"j" "" "" "(Z|dZ|j)" // foreign
|
|
62
|
+
"k" "" "" "k"
|
|
63
|
+
"l" "" "" "l"
|
|
64
|
+
"m" "" "" "m"
|
|
65
|
+
"n" "" "" "n"
|
|
66
|
+
"o" "" "" "o"
|
|
67
|
+
"p" "" "" "p"
|
|
68
|
+
"q" "" "" "k"
|
|
69
|
+
"r" "" "" "r"
|
|
70
|
+
"s" "" "" "s"
|
|
71
|
+
"t" "" "" "t"
|
|
72
|
+
"u" "" "" "u"
|
|
73
|
+
"v" "" "" "v"
|
|
74
|
+
"w" "" "" "v" // foreign
|
|
75
|
+
"x" "" "" "ks" // foreign
|
|
76
|
+
"y" "" "" "i" // foreign
|
|
77
|
+
"z" "" "" "(ts|dz)"
|
|
@@ -0,0 +1,185 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
// GENERIC
|
|
19
|
+
|
|
20
|
+
// CONVERTING FEMININE TO MASCULINE
|
|
21
|
+
"ska" "" "$" "ski"
|
|
22
|
+
"cka" "" "$" "tski"
|
|
23
|
+
"lowa" "" "$" "(lova|lof|l|el)"
|
|
24
|
+
"kowa" "" "$" "(kova|kof|k|ek)"
|
|
25
|
+
"owa" "" "$" "(ova|of|)"
|
|
26
|
+
"lowna" "" "$" "(lovna|levna|l|el)"
|
|
27
|
+
"kowna" "" "$" "(kovna|k|ek)"
|
|
28
|
+
"owna" "" "$" "(ovna|)"
|
|
29
|
+
"lówna" "" "$" "(l|el)"
|
|
30
|
+
"kówna" "" "$" "(k|ek)"
|
|
31
|
+
"ówna" "" "$" ""
|
|
32
|
+
"a" "" "$" "(a|i)"
|
|
33
|
+
|
|
34
|
+
// CONSONANTS
|
|
35
|
+
"czy" "" "" "tSi"
|
|
36
|
+
"cze" "" "[bcdgkpstwzż]" "(tSe|tSF)"
|
|
37
|
+
"ciewicz" "" "" "(tsevitS|tSevitS)"
|
|
38
|
+
"siewicz" "" "" "(sevitS|SevitS)"
|
|
39
|
+
"ziewicz" "" "" "(zevitS|ZevitS)"
|
|
40
|
+
"riewicz" "" "" "rjevitS"
|
|
41
|
+
"diewicz" "" "" "djevitS"
|
|
42
|
+
"tiewicz" "" "" "tjevitS"
|
|
43
|
+
"iewicz" "" "" "evitS"
|
|
44
|
+
"ewicz" "" "" "evitS"
|
|
45
|
+
"owicz" "" "" "ovitS"
|
|
46
|
+
"icz" "" "" "itS"
|
|
47
|
+
"cz" "" "" "tS"
|
|
48
|
+
"ch" "" "" "x"
|
|
49
|
+
|
|
50
|
+
"cia" "" "[bcdgkpstwzż]" "(tSB|tsB)"
|
|
51
|
+
"cia" "" "" "(tSa|tsa)"
|
|
52
|
+
"cią" "" "[bp]" "(tSom|tsom)"
|
|
53
|
+
"cią" "" "" "(tSon|tson)"
|
|
54
|
+
"cię" "" "[bp]" "(tSem|tsem)"
|
|
55
|
+
"cię" "" "" "(tSen|tsen)"
|
|
56
|
+
"cie" "" "[bcdgkpstwzż]" "(tSF|tsF)"
|
|
57
|
+
"cie" "" "" "(tSe|tse)"
|
|
58
|
+
"cio" "" "" "(tSo|tso)"
|
|
59
|
+
"ciu" "" "" "(tSu|tsu)"
|
|
60
|
+
"ci" "" "" "(tSi|tsI)"
|
|
61
|
+
"ć" "" "" "(tS|ts)"
|
|
62
|
+
|
|
63
|
+
"ssz" "" "" "S"
|
|
64
|
+
"sz" "" "" "S"
|
|
65
|
+
"sia" "" "[bcdgkpstwzż]" "(SB|sB|sja)"
|
|
66
|
+
"sia" "" "" "(Sa|sja)"
|
|
67
|
+
"sią" "" "[bp]" "(Som|som)"
|
|
68
|
+
"sią" "" "" "(Son|son)"
|
|
69
|
+
"się" "" "[bp]" "(Sem|sem)"
|
|
70
|
+
"się" "" "" "(Sen|sen)"
|
|
71
|
+
"sie" "" "[bcdgkpstwzż]" "(SF|sF|se)"
|
|
72
|
+
"sie" "" "" "(Se|se)"
|
|
73
|
+
"sio" "" "" "(So|so)"
|
|
74
|
+
"siu" "" "" "(Su|sju)"
|
|
75
|
+
"si" "" "" "(Si|sI)"
|
|
76
|
+
"ś" "" "" "(S|s)"
|
|
77
|
+
|
|
78
|
+
"zia" "" "[bcdgkpstwzż]" "(ZB|zB|zja)"
|
|
79
|
+
"zia" "" "" "(Za|zja)"
|
|
80
|
+
"zią" "" "[bp]" "(Zom|zom)"
|
|
81
|
+
"zią" "" "" "(Zon|zon)"
|
|
82
|
+
"zię" "" "[bp]" "(Zem|zem)"
|
|
83
|
+
"zię" "" "" "(Zen|zen)"
|
|
84
|
+
"zie" "" "[bcdgkpstwzż]" "(ZF|zF)"
|
|
85
|
+
"zie" "" "" "(Ze|ze)"
|
|
86
|
+
"zio" "" "" "(Zo|zo)"
|
|
87
|
+
"ziu" "" "" "(Zu|zju)"
|
|
88
|
+
"zi" "" "" "(Zi|zI)"
|
|
89
|
+
|
|
90
|
+
"że" "" "[bcdgkpstwzż]" "(Ze|ZF)"
|
|
91
|
+
"że" "" "[bcdgkpstwzż]" "(Ze|ZF|ze|zF)"
|
|
92
|
+
"że" "" "" "Ze"
|
|
93
|
+
"źe" "" "" "(Ze|ze)"
|
|
94
|
+
"ży" "" "" "Zi"
|
|
95
|
+
"źi" "" "" "(Zi|zi)"
|
|
96
|
+
"ż" "" "" "Z"
|
|
97
|
+
"ź" "" "" "(Z|z)"
|
|
98
|
+
|
|
99
|
+
"rze" "t" "" "(Se|re)"
|
|
100
|
+
"rze" "" "" "(Ze|re|rZe)"
|
|
101
|
+
"rzy" "t" "" "(Si|ri)"
|
|
102
|
+
"rzy" "" "" "(Zi|ri|rZi)"
|
|
103
|
+
"rz" "t" "" "(S|r)"
|
|
104
|
+
"rz" "" "" "(Z|r|rZ)"
|
|
105
|
+
|
|
106
|
+
"lio" "" "" "(lo|le)"
|
|
107
|
+
"ł" "" "" "l"
|
|
108
|
+
"ń" "" "" "n"
|
|
109
|
+
"qu" "" "" "k"
|
|
110
|
+
"s" "" "s" ""
|
|
111
|
+
|
|
112
|
+
// VOWELS
|
|
113
|
+
"ó" "" "" "(u|o)"
|
|
114
|
+
"ą" "" "[bp]" "om"
|
|
115
|
+
"ę" "" "[bp]" "em"
|
|
116
|
+
"ą" "" "" "on"
|
|
117
|
+
"ę" "" "" "en"
|
|
118
|
+
|
|
119
|
+
"ije" "" "" "je"
|
|
120
|
+
"yje" "" "" "je"
|
|
121
|
+
"iie" "" "" "je"
|
|
122
|
+
"yie" "" "" "je"
|
|
123
|
+
"iye" "" "" "je"
|
|
124
|
+
"yye" "" "" "je"
|
|
125
|
+
|
|
126
|
+
"ij" "" "[aou]" "j"
|
|
127
|
+
"yj" "" "[aou]" "j"
|
|
128
|
+
"ii" "" "[aou]" "j"
|
|
129
|
+
"yi" "" "[aou]" "j"
|
|
130
|
+
"iy" "" "[aou]" "j"
|
|
131
|
+
"yy" "" "[aou]" "j"
|
|
132
|
+
|
|
133
|
+
"rie" "" "" "rje"
|
|
134
|
+
"die" "" "" "dje"
|
|
135
|
+
"tie" "" "" "tje"
|
|
136
|
+
"ie" "" "[bcdgkpstwzż]" "F"
|
|
137
|
+
"ie" "" "" "e"
|
|
138
|
+
|
|
139
|
+
"aue" "" "" "aue"
|
|
140
|
+
"au" "" "" "au"
|
|
141
|
+
|
|
142
|
+
"ei" "" "" "aj"
|
|
143
|
+
"ey" "" "" "aj"
|
|
144
|
+
"ej" "" "" "aj"
|
|
145
|
+
|
|
146
|
+
"ai" "" "" "aj"
|
|
147
|
+
"ay" "" "" "aj"
|
|
148
|
+
"aj" "" "" "aj"
|
|
149
|
+
|
|
150
|
+
"i" "[aeou]" "" "j"
|
|
151
|
+
"y" "[aeou]" "" "j"
|
|
152
|
+
"i" "" "[aou]" "j"
|
|
153
|
+
"y" "" "[aeou]" "j"
|
|
154
|
+
|
|
155
|
+
"a" "" "[bcdgkpstwzż]" "B"
|
|
156
|
+
"e" "" "[bcdgkpstwzż]" "(E|F)"
|
|
157
|
+
"o" "" "[bcćdgklłmnńrsśtwzźż]" "P"
|
|
158
|
+
|
|
159
|
+
// LATIN ALPHABET
|
|
160
|
+
"a" "" "" "a"
|
|
161
|
+
"b" "" "" "b"
|
|
162
|
+
"c" "" "" "ts"
|
|
163
|
+
"d" "" "" "d"
|
|
164
|
+
"e" "" "" "E"
|
|
165
|
+
"f" "" "" "f"
|
|
166
|
+
"g" "" "" "g"
|
|
167
|
+
"h" "" "" "(h|x)"
|
|
168
|
+
"i" "" "" "I"
|
|
169
|
+
"j" "" "" "j"
|
|
170
|
+
"k" "" "" "k"
|
|
171
|
+
"l" "" "" "l"
|
|
172
|
+
"m" "" "" "m"
|
|
173
|
+
"n" "" "" "n"
|
|
174
|
+
"o" "" "" "o"
|
|
175
|
+
"p" "" "" "p"
|
|
176
|
+
"q" "" "" "k"
|
|
177
|
+
"r" "" "" "r"
|
|
178
|
+
"s" "" "" "s"
|
|
179
|
+
"t" "" "" "t"
|
|
180
|
+
"u" "" "" "u"
|
|
181
|
+
"v" "" "" "v"
|
|
182
|
+
"w" "" "" "v"
|
|
183
|
+
"x" "" "" "ks"
|
|
184
|
+
"y" "" "" "I"
|
|
185
|
+
"z" "" "" "z"
|
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
"kh" "" "" "x" // foreign
|
|
19
|
+
"ch" "" "" "S"
|
|
20
|
+
"ss" "" "" "s"
|
|
21
|
+
"sc" "" "[ei]" "s"
|
|
22
|
+
"sç" "" "[aou]" "s"
|
|
23
|
+
"ç" "" "" "s"
|
|
24
|
+
"c" "" "[ei]" "s"
|
|
25
|
+
// "c" "" "[aou]" "(k|C)"
|
|
26
|
+
|
|
27
|
+
"s" "^" "" "s"
|
|
28
|
+
"s" "[aáuiíoóeéêy]" "[aáuiíoóeéêy]" "z"
|
|
29
|
+
"s" "" "[dglmnrv]" "(Z|S)" // Z is Brazil
|
|
30
|
+
|
|
31
|
+
"z" "" "$" "(Z|s|S)" // s and S in Brazil
|
|
32
|
+
"z" "" "[bdgv]" "(Z|z)" // Z in Brazil
|
|
33
|
+
"z" "" "[ptckf]" "(s|S|z)" // s and S in Brazil
|
|
34
|
+
|
|
35
|
+
"gu" "" "[eiu]" "g"
|
|
36
|
+
"gu" "" "[ao]" "gv"
|
|
37
|
+
"g" "" "[ei]" "Z"
|
|
38
|
+
"qu" "" "[eiu]" "k"
|
|
39
|
+
"qu" "" "[ao]" "kv"
|
|
40
|
+
|
|
41
|
+
"uo" "" "" "(vo|o|u)"
|
|
42
|
+
"u" "" "[aei]" "v"
|
|
43
|
+
|
|
44
|
+
"lh" "" "" "l"
|
|
45
|
+
"nh" "" "" "nj"
|
|
46
|
+
"h" "[bdgt]" "" "" // translit. from Arabic
|
|
47
|
+
"h" "" "$" "" // foreign
|
|
48
|
+
|
|
49
|
+
"ex" "" "[aáuiíoóeéêy]" "(ez|eS|eks)" // ez in Brazil
|
|
50
|
+
"ex" "" "[cs]" "e"
|
|
51
|
+
|
|
52
|
+
"y" "[aáuiíoóeéê]" "" "j"
|
|
53
|
+
"y" "" "[aeiíou]" "j"
|
|
54
|
+
"m" "" "[bcdfglnprstv]" "(m|n)" // maybe to add a rule for m/n before a consonant that disappears [preceding vowel becomes nasalized]
|
|
55
|
+
"m" "" "$" "(m|n)" // maybe to add a rule for final m/n that disappears [preceding vowel becomes nasalized]
|
|
56
|
+
|
|
57
|
+
"ão" "" "" "(au|an|on)"
|
|
58
|
+
"ãe" "" "" "(aj|an)"
|
|
59
|
+
"ãi" "" "" "(aj|an)"
|
|
60
|
+
"õe" "" "" "(oj|on)"
|
|
61
|
+
"i" "[aáuoóeéê]" "" "j"
|
|
62
|
+
"i" "" "[aeou]" "j"
|
|
63
|
+
|
|
64
|
+
"â" "" "" "a"
|
|
65
|
+
"à" "" "" "a"
|
|
66
|
+
"á" "" "" "a"
|
|
67
|
+
"ã" "" "" "(a|an|on)"
|
|
68
|
+
"é" "" "" "e"
|
|
69
|
+
"ê" "" "" "e"
|
|
70
|
+
"í" "" "" "i"
|
|
71
|
+
"ô" "" "" "o"
|
|
72
|
+
"ó" "" "" "o"
|
|
73
|
+
"õ" "" "" "(o|on)"
|
|
74
|
+
"ú" "" "" "u"
|
|
75
|
+
"ü" "" "" "u"
|
|
76
|
+
|
|
77
|
+
"aue" "" "" "aue"
|
|
78
|
+
|
|
79
|
+
// LATIN ALPHABET
|
|
80
|
+
"a" "" "" "a"
|
|
81
|
+
"b" "" "" "b"
|
|
82
|
+
"c" "" "" "k"
|
|
83
|
+
"d" "" "" "d"
|
|
84
|
+
"e" "" "" "(e|i)"
|
|
85
|
+
"f" "" "" "f"
|
|
86
|
+
"g" "" "" "g"
|
|
87
|
+
"h" "" "" "h"
|
|
88
|
+
"i" "" "" "i"
|
|
89
|
+
"j" "" "" "Z"
|
|
90
|
+
"k" "" "" "k"
|
|
91
|
+
"l" "" "" "l"
|
|
92
|
+
"m" "" "" "m"
|
|
93
|
+
"n" "" "" "n"
|
|
94
|
+
"o" "" "" "(o|u)"
|
|
95
|
+
"p" "" "" "p"
|
|
96
|
+
"q" "" "" "k"
|
|
97
|
+
"r" "" "" "r"
|
|
98
|
+
"s" "" "" "S"
|
|
99
|
+
"t" "" "" "t"
|
|
100
|
+
"u" "" "" "u"
|
|
101
|
+
"v" "" "" "v"
|
|
102
|
+
"w" "" "" "v"
|
|
103
|
+
"x" "" "" "(S|ks)"
|
|
104
|
+
"y" "" "" "i"
|
|
105
|
+
"z" "" "" "z"
|
|
@@ -0,0 +1,64 @@
|
|
|
1
|
+
/*
|
|
2
|
+
* Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
* contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
* this work for additional information regarding copyright ownership.
|
|
5
|
+
* The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
* (the "License"); you may not use this file except in compliance with
|
|
7
|
+
* the License. You may obtain a copy of the License at
|
|
8
|
+
*
|
|
9
|
+
* https://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
*
|
|
11
|
+
* Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
* See the License for the specific language governing permissions and
|
|
15
|
+
* limitations under the License.
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
"ce" "" "" "tSe"
|
|
19
|
+
"ci" "" "" "(tSi|tS)"
|
|
20
|
+
"ch" "" "[ei]" "k"
|
|
21
|
+
"ch" "" "" "x" // foreign
|
|
22
|
+
|
|
23
|
+
"gi" "" "" "(dZi|dZ)"
|
|
24
|
+
"g" "" "[ei]" "dZ"
|
|
25
|
+
"gh" "" "" "g"
|
|
26
|
+
|
|
27
|
+
"i" "[aeou]" "" "j"
|
|
28
|
+
"i" "" "[aeou]" "j"
|
|
29
|
+
"ţ" "" "" "ts"
|
|
30
|
+
"ş" "" "" "S"
|
|
31
|
+
"qu" "" "" "k"
|
|
32
|
+
|
|
33
|
+
"î" "" "" "i"
|
|
34
|
+
"ea" "" "" "ja"
|
|
35
|
+
"ă" "" "" "(e|a)"
|
|
36
|
+
"aue" "" "" "aue"
|
|
37
|
+
|
|
38
|
+
// LATIN ALPHABET
|
|
39
|
+
"a" "" "" "a"
|
|
40
|
+
"b" "" "" "b"
|
|
41
|
+
"c" "" "" "k"
|
|
42
|
+
"d" "" "" "d"
|
|
43
|
+
"e" "" "" "E"
|
|
44
|
+
"f" "" "" "f"
|
|
45
|
+
"g" "" "" "g"
|
|
46
|
+
"h" "" "" "(x|h)"
|
|
47
|
+
"i" "" "" "I"
|
|
48
|
+
"j" "" "" "Z"
|
|
49
|
+
"k" "" "" "k"
|
|
50
|
+
"l" "" "" "l"
|
|
51
|
+
"m" "" "" "m"
|
|
52
|
+
"n" "" "" "n"
|
|
53
|
+
"o" "" "" "o"
|
|
54
|
+
"p" "" "" "p"
|
|
55
|
+
"q" "" "" "k"
|
|
56
|
+
"r" "" "" "r"
|
|
57
|
+
"s" "" "" "s"
|
|
58
|
+
"t" "" "" "t"
|
|
59
|
+
"u" "" "" "u"
|
|
60
|
+
"v" "" "" "v"
|
|
61
|
+
"w" "" "" "v"
|
|
62
|
+
"x" "" "" "ks"
|
|
63
|
+
"y" "" "" "i"
|
|
64
|
+
"z" "" "" "z"
|