extra-english.web 0.0.0-stage → 1.2.0
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.
- package/LICENSE +21 -0
- package/README.md +75 -2
- package/deno.lock +39 -0
- package/index.d.ts +44 -0
- package/index.js +2 -0
- package/index.js.map +7 -0
- package/index.test.ts +63 -0
- package/package.json +13 -3
package/LICENSE
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
MIT License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2018-26 Subhajit Sahu
|
|
4
|
+
|
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
+
in the Software without restriction, including without limitation the rights
|
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
+
furnished to do so, subject to the following conditions:
|
|
11
|
+
|
|
12
|
+
The above copyright notice and this permission notice shall be included in all
|
|
13
|
+
copies or substantial portions of the Software.
|
|
14
|
+
|
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
21
|
+
SOFTWARE.
|
package/README.md
CHANGED
|
@@ -1,3 +1,76 @@
|
|
|
1
|
-
|
|
1
|
+
[English] is a West Germanic language, first spoken in early medieval England. This package is a collection of various English language utilities. It includes functions for converting text to phonetic representations and stemming words.
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[English]: https://en.wikipedia.org/wiki/English_language
|
|
4
|
+
|
|
5
|
+
▌
|
|
6
|
+
📦 [JSR](https://jsr.io/@nodef/extra-english),
|
|
7
|
+
📦 [NPM](https://www.npmjs.com/package/@nodef/extra-english),
|
|
8
|
+
🌐 [Web](https://cdn.jsdelivr.net/npm/@nodef/extra-english.web),
|
|
9
|
+
📰 [Docs](https://jsr.io/@nodef/extra-english/doc).
|
|
10
|
+
|
|
11
|
+
<br>
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
```typescript
|
|
15
|
+
import * as xenglish from "jsr:@nodef/extra-english";
|
|
16
|
+
|
|
17
|
+
//# Phonetic functions
|
|
18
|
+
xenglish.caverphonePhonetic('Thompson', true);
|
|
19
|
+
// → 'TMPSN1'
|
|
20
|
+
|
|
21
|
+
xenglish.colognePhonetic('Hari');
|
|
22
|
+
// → '7'
|
|
23
|
+
|
|
24
|
+
xenglish.metaphonePhonetic('Lightyear');
|
|
25
|
+
// → 'LHTYAR'
|
|
26
|
+
|
|
27
|
+
xenglish.mraPhonetic('Byrne');
|
|
28
|
+
// → 'BYRN'
|
|
29
|
+
|
|
30
|
+
xenglish.soundexPhonetic('Tymczak');
|
|
31
|
+
// → 'T522'
|
|
32
|
+
|
|
33
|
+
xenglish.soundexSqlPhonetic('Tymczak');
|
|
34
|
+
// → 'T520'
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
//# Stemming functions
|
|
38
|
+
xenglish.lancasterStem('running');
|
|
39
|
+
// → 'run'
|
|
40
|
+
|
|
41
|
+
xenglish.porterStem('running');
|
|
42
|
+
// → 'run'
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
### Index
|
|
47
|
+
|
|
48
|
+
| Name | Action
|
|
49
|
+
|------------------------------|-------
|
|
50
|
+
| [caverphonePhonetic] | Get Caverphone phonetic of English text.
|
|
51
|
+
| [colognePhonetic] | Get Cologne phonetic of English text.
|
|
52
|
+
| [metaphonePhonetic] | Get Metaphone phonetic of English text.
|
|
53
|
+
| [mraPhonetic] | Get Match Rating Approach phonetic of English text.
|
|
54
|
+
| [soundexPhonetic] | Get Soundex phonetic of English text.
|
|
55
|
+
| [soundexSqlPhonetic] | Get Soundex phonetic (SQL) of English text.
|
|
56
|
+
| [lancasterStem] | Stem a word to its base form using the Lancaster stemmer.
|
|
57
|
+
| [porterStem] | Stem a word to its base form using the Porter stemmer.
|
|
58
|
+
<!-- | [nysiisPhonetic] | Get NYSIIS phonetic of English text. -->
|
|
59
|
+
|
|
60
|
+
<br>
|
|
61
|
+
<br>
|
|
62
|
+
|
|
63
|
+
[](https://wolfram77.github.io)<br>
|
|
64
|
+
[](https://nodef.github.io)
|
|
65
|
+

|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
[caverphonePhonetic]: https://jsr.io/@nodef/extra-english/doc/~/caverphonePhonetic
|
|
69
|
+
[colognePhonetic]: https://jsr.io/@nodef/extra-english/doc/~/colognePhonetic
|
|
70
|
+
[metaphonePhonetic]: https://jsr.io/@nodef/extra-english/doc/~/metaphonePhonetic
|
|
71
|
+
[mraPhonetic]: https://jsr.io/@nodef/extra-english/doc/~/mraPhonetic
|
|
72
|
+
[nysiisPhonetic]: https://jsr.io/@nodef/extra-english/doc/~/nysiisPhonetic
|
|
73
|
+
[soundexPhonetic]: https://jsr.io/@nodef/extra-english/doc/~/soundexPhonetic
|
|
74
|
+
[soundexSqlPhonetic]: https://jsr.io/@nodef/extra-english/doc/~/soundexSqlPhonetic
|
|
75
|
+
[lancasterStem]: https://jsr.io/@nodef/extra-english/doc/~/lancasterStem
|
|
76
|
+
[porterStem]: https://jsr.io/@nodef/extra-english/doc/~/porterStem
|
package/deno.lock
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
{
|
|
2
|
+
"version": "5",
|
|
3
|
+
"specifiers": {
|
|
4
|
+
"jsr:@std/assert@*": "1.0.12",
|
|
5
|
+
"jsr:@std/assert@^1.0.19": "1.0.19",
|
|
6
|
+
"jsr:@std/cli@^1.0.32": "1.0.32",
|
|
7
|
+
"jsr:@std/internal@^1.0.12": "1.0.14",
|
|
8
|
+
"jsr:@std/internal@^1.0.6": "1.0.6"
|
|
9
|
+
},
|
|
10
|
+
"jsr": {
|
|
11
|
+
"@std/assert@1.0.12": {
|
|
12
|
+
"integrity": "08009f0926dda9cbd8bef3a35d3b6a4b964b0ab5c3e140a4e0351fbf34af5b9a",
|
|
13
|
+
"dependencies": [
|
|
14
|
+
"jsr:@std/internal@^1.0.6"
|
|
15
|
+
]
|
|
16
|
+
},
|
|
17
|
+
"@std/assert@1.0.19": {
|
|
18
|
+
"integrity": "eaada96ee120cb980bc47e040f82814d786fe8162ecc53c91d8df60b8755991e",
|
|
19
|
+
"dependencies": [
|
|
20
|
+
"jsr:@std/internal@^1.0.12"
|
|
21
|
+
]
|
|
22
|
+
},
|
|
23
|
+
"@std/cli@1.0.32": {
|
|
24
|
+
"integrity": "188b3a100d6202d64e3f5bd3d799c7fa4f6d77f92cc65eb7f641c1fa0aa92a66"
|
|
25
|
+
},
|
|
26
|
+
"@std/internal@1.0.6": {
|
|
27
|
+
"integrity": "9533b128f230f73bd209408bb07a4b12f8d4255ab2a4d22a1fd6d87304aca9a4"
|
|
28
|
+
},
|
|
29
|
+
"@std/internal@1.0.14": {
|
|
30
|
+
"integrity": "291516b3d4c35024d6ffbc0a9df5bf4c64116e05b50012cf846710152d2ffdf7"
|
|
31
|
+
}
|
|
32
|
+
},
|
|
33
|
+
"workspace": {
|
|
34
|
+
"dependencies": [
|
|
35
|
+
"jsr:@std/assert@^1.0.19",
|
|
36
|
+
"jsr:@std/cli@^1.0.32"
|
|
37
|
+
]
|
|
38
|
+
}
|
|
39
|
+
}
|
package/index.d.ts
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Get Caverphone phonetic of English text.
|
|
3
|
+
* @param txt english text
|
|
4
|
+
* @param ext extended caverphone? [false]
|
|
5
|
+
* @returns caverphone phonetic string
|
|
6
|
+
*/ export declare function caverphonePhonetic(txt: string, ext?: boolean): string;
|
|
7
|
+
/**
|
|
8
|
+
* Get Cologne phonetic of English text.
|
|
9
|
+
* @param txt english text
|
|
10
|
+
* @returns cologne phonetic string
|
|
11
|
+
*/ export declare function colognePhonetic(txt: string): string;
|
|
12
|
+
/**
|
|
13
|
+
* Get Metaphone phonetic of English text.
|
|
14
|
+
* @param txt english text
|
|
15
|
+
* @returns metaphone phonetic string
|
|
16
|
+
*/ export declare function metaphonePhonetic(txt: string): string;
|
|
17
|
+
/**
|
|
18
|
+
* Get Match Rating Approach (MRA) phonetic of English text.
|
|
19
|
+
* @param txt english text
|
|
20
|
+
* @param ext extended MRA? [false]
|
|
21
|
+
* @returns MRA phonetic string
|
|
22
|
+
*/ export declare function mraPhonetic(txt: string, ext?: boolean): string;
|
|
23
|
+
/**
|
|
24
|
+
* Get Soundex phonetic of English text.
|
|
25
|
+
* @param txt english text
|
|
26
|
+
* @param ext extended soundex? [false]
|
|
27
|
+
* @returns soundex phonetic string
|
|
28
|
+
*/ export declare function soundexPhonetic(txt: string, ext?: boolean): string;
|
|
29
|
+
/**
|
|
30
|
+
* Get Soundex phonetic (SQL) of English text.
|
|
31
|
+
* @param txt english text
|
|
32
|
+
* @param ext extended soundex? [false]
|
|
33
|
+
* @returns soundex phonetic (SQL) string
|
|
34
|
+
*/ export declare function soundexSqlPhonetic(txt: string, ext?: boolean): string;
|
|
35
|
+
/**
|
|
36
|
+
* Stem a word to its base form using the Lancaster stemmer.
|
|
37
|
+
* @param word word to be stemmed
|
|
38
|
+
* @returns stemmed word
|
|
39
|
+
*/ export declare function lancasterStem(word: string): string;
|
|
40
|
+
/**
|
|
41
|
+
* Stem a word to its base form using the Porter stemmer.
|
|
42
|
+
* @param word word to be stemmed
|
|
43
|
+
* @returns stemmed word
|
|
44
|
+
*/ export declare function porterStem(word: string): string;
|
package/index.js
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
1
|
+
var E=[{p:/^cough/g,v:"cou2f"},{p:/^rough/g,v:"rou2f"},{p:/^tough/g,v:"tou2f"},{p:/^enough/g,v:"enou2f"},{p:/^gn/g,v:"2n"},{p:/mb$/g,v:"m2"},{p:/cq/g,v:"2q"},{p:/ci/g,v:"si"},{p:/ce/g,v:"se"},{p:/cy/g,v:"sy"},{p:/tch/g,v:"2ch"},{p:/c/g,v:"k"},{p:/q/g,v:"k"},{p:/x/g,v:"k"},{p:/v/g,v:"f"},{p:/dg/g,v:"2g"},{p:/tio/g,v:"sio"},{p:/tia/g,v:"sia"},{p:/ph/g,v:"fh"},{p:/b/g,v:"p"},{p:/sh/g,v:"s2"},{p:/z/g,v:"s"},{p:/^[aeiou]/g,v:"A"},{p:/[aeiou]/g,v:"3"},{p:/3gh3/g,v:"3kh3"},{p:/gh/g,v:"22"},{p:/g/g,v:"k"},{p:/ss+/g,v:"S"},{p:/tt+/g,v:"T"},{p:/pp+/g,v:"P"},{p:/kk+/g,v:"K"},{p:/ff+/g,v:"F"},{p:/mm+/g,v:"M"},{p:/nn+/g,v:"N"},{p:/w3/g,v:"W3"},{p:/wy/g,v:"Wy"},{p:/wh3/g,v:"Wh3"},{p:/why/g,v:"Why"},{p:/^h/g,v:"A"},{p:/h/g,v:"2"},{p:/r3/g,v:"R3"},{p:/ry/g,v:"Ry"},{p:/r/g,v:"2"},{p:/l3/g,v:"L3"},{p:/ly/g,v:"Ly"},{p:/l/g,v:"2"},{p:/j/g,v:"y"},{p:/y3/g,v:"Y3"},{p:/y/g,v:"2"},{p:/2/g,v:""},{p:/3/g,v:""},{p:/z/g,v:"s"},{p:/z/g,v:"s"},{p:/z/g,v:"s"},{p:/z/g,v:"s"}];function w(n,e=!1){let s=n.replace(/[^A-Za-z]/g,"").toLowerCase();for(let t of E)s=s.replace(t.p,t.v);return s=e?s:(s+"111111").substring(0,6),s.toUpperCase()}var c=()=>"0",A=()=>"",m=()=>"1",x=n=>n!=="H"?"1":"3",v=n=>"CSZ".indexOf(n)<0?"2":"8",f=()=>"3",a=()=>"4",y=(n,e,s)=>s&&"AHKLOQRUX".indexOf(n)>=0||"AHKOQUX".indexOf(n)>=0&&"SZ".indexOf(e)<0?"4":"8",$=(n,e)=>"CKQ".indexOf(e)<0?"48":"8",F=()=>"5",h=()=>"6",I=()=>"7",d=()=>"8",S=new Map([["A",c],["B",m],["C",y],["D",v],["E",c],["F",f],["G",a],["H",A],["I",c],["J",c],["K",a],["L",F],["M",h],["N",h],["O",c],["P",x],["Q",a],["R",I],["S",d],["T",v],["U",c],["V",f],["W",f],["X",$],["Y",c],["Z",d]]);function Q(n){let e=n.replace(/[^A-Za-z]/g,"").toUpperCase().replace(/[ÄÖÜß]/g,"A"),s=S.get(e[0])(e[1]," ",!0);for(let t=1,r=e.length,l=s;t<r;t++){let i=S.get(e[t])(e[t+1],e[t-1],t===0);i!==l&&i!=="0"&&(s+=i),l=i}return s}var U=[{p:/([^C])\1/g,v:"$1"},{p:/^[KGP]N/g,v:"N"},{p:/^AE/g,v:"E"},{p:/^WR/g,v:"R"},{p:/MB$/g,v:"M"},{p:/SCH/g,v:"K"},{p:/C(IA|H)/g,v:"X$1"},{p:/C(I|E|Y)/g,v:"S$1"},{p:/C/g,v:"K"},{p:/D(GE|GY|GI)/g,v:"J$1"},{p:/D/g,v:"T"},{p:/G(H[^AEIOU])/g,v:"$1"},{p:/G(N|NED)$/g,v:"$1"},{p:/([^G])G(I|E|Y)/g,v:"$1J$2"},{p:/G/g,v:"K"},{p:/([AEIOU])H([^AEIOU])|([AEIOU])H$/g,v:"$1H$2"},{p:/CK/g,v:"K"},{p:/PH/g,v:"F"},{p:/Q/g,v:"K"},{p:/S(H|IO|IA)/g,v:"X$1"},{p:/T(IA|IO)/g,v:"X$1"},{p:/TH/g,v:"0"},{p:/TCH/g,v:"CH"},{p:/V/g,v:"F"},{p:/^WH/g,v:"W"},{p:/W([^AEIOU])|W$/g,v:"$1"},{p:/^X/g,v:"S"},{p:/X/g,v:"KS"},{p:/Y([^AEIOU])|Y$/g,v:"$1"},{p:/Z/g,v:"S"},{p:/(.)[AEIOU]/g,v:"$1"}];function J(n){let e=n.replace(/[^A-Za-z]/g,"").toUpperCase();for(let s of U)e=e.replace(s.p,s.v);return e}function j(n,e=!1){let s=n.replace(/[^A-Za-z]/g,"").toUpperCase();return s=(s[0]+s.substring(1).replace(/[AEIOU]/g,"")).replace(/(.)\1+/g,"$1"),e||s.length<=6?s:s.substring(0,3)+s.substring(s.length-3)}var H="aeiouy",P="aeiouyhw",X="bfpv",D="cgjkqsxz",b="dt",L="l",W="mn";function B(n,e=!1){n=n.replace(/[^A-Za-z]/g,"").toLowerCase();let s=0,t=0,r=!1,l="";for(let o of n)P.indexOf(o)>=0?t=0:X.indexOf(o)>=0?t=1:D.indexOf(o)>=0?t=2:b[0]===o||b[1]===o?t=3:L===o?t=4:W[0]===o||W[1]===o?t=5:t=6,l.length?t&&(t!==s||r)&&(l+=t):l+=o.toUpperCase(),r=t?!1:r||H.indexOf(o)>=0,s=t||s;let i=l.length;return e||!i?l:i<4?l+"000".substring(0,4-i):l.substring(0,4)}var R="aeiouyhw",K="bfpv",k="cgjkqsxz",z="dt",G="l",O="mn";function _(n,e=!1){n=n.replace(/[^A-Za-z]/g,"").toLowerCase();let s=0,t=0,r="";for(let i of n)R.indexOf(i)>=0?t=0:K.indexOf(i)>=0?t=1:k.indexOf(i)>=0?t=2:z[0]===i||z[1]===i?t=3:G===i?t=4:O[0]===i||O[1]===i?t=5:t=6,r.length?t&&t!==s&&(r+=t):r+=i.toUpperCase(),t&&(s=t);let l=r.length;return e||!l?r:l<4?r+"000".substring(0,4-l):r.substring(0,4)}var V=[{s:"ational",r:"ate"},{s:"tional",r:"tion"},{s:"fulness",r:"ful"},{s:"ousness",r:"ous"},{s:"iveness",r:"ive"},{s:"ization",r:"ize"},{s:"isation",r:"ize"},{s:"biliti",r:"ble"},{s:"lessli",r:"less"},{s:"entli",r:"ent"},{s:"ation",r:"ate"},{s:"ator",r:"ate"},{s:"alism",r:"al"},{s:"aliti",r:"al"},{s:"ousli",r:"ous"},{s:"iviti",r:"ive"},{s:"fulli",r:"ful"},{s:"enci",r:"ence"},{s:"anci",r:"ance"},{s:"abli",r:"able"},{s:"izer",r:"ize"},{s:"iser",r:"ise"},{s:"alli",r:"al"},{s:"ical",r:"ic"},{s:"ement",r:""},{s:"ance",r:""},{s:"ence",r:""},{s:"able",r:""},{s:"ible",r:""},{s:"ment",r:""},{s:"ness",r:""},{s:"ful",r:""},{s:"ous",r:""},{s:"ive",r:""},{s:"ize",r:""},{s:"ise",r:""},{s:"ing",r:"",l:4,v:!0},{s:"ed",r:"",l:3,v:!0},{s:"es",r:"e",l:3},{s:"es",r:"",l:3,v:!0},{s:"ly",r:"",l:3},{s:"li",r:"",l:3},{s:"ti",r:"t",l:3},{s:"ci",r:"c",l:3},{s:"gi",r:"g",l:3},{s:"si",r:"s",l:3},{s:"zi",r:"z",l:3},{s:"s",r:"",l:2},{s:"e",r:"",l:3},{s:"bb",r:"b",l:3,v:!0},{s:"dd",r:"d",l:3,v:!0},{s:"ff",r:"f",l:3,v:!0},{s:"gg",r:"g",l:3,v:!0},{s:"ll",r:"l",l:3,v:!0},{s:"mm",r:"m",l:3,v:!0},{s:"nn",r:"n",l:3,v:!0},{s:"pp",r:"p",l:3,v:!0},{s:"rr",r:"r",l:3,v:!0},{s:"ss",r:"s",l:3,v:!0},{s:"tt",r:"t",l:3,v:!0},{s:"zz",r:"z",l:3,v:!0},{s:"i",r:"",l:3,v:!0},{s:"ant",r:""},{s:"ent",r:""},{s:"ism",r:""},{s:"ist",r:""},{s:"er",r:"",l:3},{s:"or",r:"",l:3},{s:"al",r:"",l:3},{s:"ic",r:"",l:3},{s:"at",r:"",l:3},{s:"en",r:"",l:3},{s:"um",r:"",l:3},{s:"us",r:"",l:3},{s:"on",r:"",l:3},{s:"ar",r:"",l:3},{s:"el",r:"",l:3},{s:"em",r:"",l:3},{s:"in",r:"",l:3},{s:"it",r:"",l:3},{s:"ol",r:"",l:3},{s:"op",r:"",l:3},{s:"ot",r:"",l:3},{s:"un",r:"",l:3},{s:"up",r:"",l:3},{s:"ur",r:"",l:3},{s:"ut",r:"",l:3},{s:"ct",r:"c",l:3},{s:"lt",r:"l",l:3},{s:"nt",r:"n",l:3},{s:"pt",r:"p",l:3},{s:"rt",r:"r",l:3},{s:"st",r:"s",l:3},{s:"xt",r:"x",l:3},{s:"y",r:"",l:3,v:!0}];function Z(n){return/[aeiouy]/.test(n)}function N(n){if(!n)return"";let e=n.toLowerCase();for(let s of V){if(!e.endsWith(s.s))continue;let t=e.slice(0,-s.s.length)+s.r;if(!(s.l&&t.length<s.l)&&!(s.v&&!Z(t)))return N(t)}return e}var M=[["ational","ate"],["tional","tion"],["enci","ence"],["anci","ance"],["izer","ize"],["abli","able"],["alli","al"],["entli","ent"],["eli","e"],["ousli","ous"],["ization","ize"],["ation","ate"],["ator","ate"],["alism","al"],["iveness","ive"],["fulness","ful"],["ousness","ous"],["aliti","al"],["iviti","ive"],["biliti","ble"]],T=[["icate","ic"],["ative",""],["alize","al"],["iciti","ic"],["ical","ic"],["ful",""],["ness",""]],Y=["al","ance","ence","er","ic","able","ible","ant","ement","ment","ent","ion","ou","ism","ate","iti","ous","ive","ize"];function p(n,e){return"aeiou".includes(n[e])?!1:n[e]==="y"?e===0?!0:!p(n,e-1):!0}function u(n){for(let e=0;e<n.length;e++)if(!p(n,e))return!0;return!1}function q(n){let e=n.length;return e<2?!1:n[e-1]===n[e-2]&&p(n,e-1)}function g(n){let e=0,s=!1;for(let t=0;t<n.length;t++)p(n,t)?s&&(e++,s=!1):s=!0;return e}function C(n,e){return e<2||!p(n,e)||p(n,e-1)||!p(n,e-2)?!1:!"wxy".includes(n[e])}function ee(n){let e=n.toLowerCase().replace(/[^a-z]/g,"");if(e.length<3)return e;if(e.endsWith("sses")||e.endsWith("ies")?e=e.slice(0,-2):e.endsWith("ss")||e.endsWith("s")&&(e=e.slice(0,-1)),e.endsWith("eed")){let s=e.slice(0,-3);g(e)>0&&(e=s+"ee")}else(e.endsWith("ed")&&u(e.slice(0,-2))||e.endsWith("ing")&&u(e.slice(0,-3)))&&(e=e.endsWith("ed")?e.slice(0,e.length-2):e.slice(0,e.length-3),e.endsWith("at")||e.endsWith("bl")||e.endsWith("iz")?e+="e":q(e)&&!"lsz".includes(e[e.length-1])?e=e.slice(0,-1):g(e)===1&&C(e,e.length-1)&&(e+="e"));e.endsWith("y")&&u(e)&&(e=e.slice(0,-1)+"i");for(let[s,t]of M){if(!e.endsWith(s))continue;let r=e.slice(0,e.length-s.length);g(e)>0&&(e=r+t);break}for(let[s,t]of T){if(!e.endsWith(s))continue;let r=e.slice(0,e.length-s.length);g(e)>0&&(e=r+t);break}for(let s of Y){if(!e.endsWith(s))continue;let t=e.slice(0,e.length-s.length);g(e)>1&&(s!=="ion"||t.endsWith("s")||t.endsWith("t"))&&(e=t);break}if(e.endsWith("e")){let s=g(e);(s>1||s===1&&!C(e,e.length-2))&&(e=e.slice(0,-1))}return e.endsWith("ll")&&g(e)>1&&(e=e.slice(0,-1)),e}export{w as caverphonePhonetic,Q as colognePhonetic,N as lancasterStem,J as metaphonePhonetic,j as mraPhonetic,ee as porterStem,B as soundexPhonetic,_ as soundexSqlPhonetic};
|
|
2
|
+
//# sourceMappingURL=index.js.map
|
package/index.js.map
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
{
|
|
2
|
+
"version": 3,
|
|
3
|
+
"sources": ["../../index.ts"],
|
|
4
|
+
"sourcesContent": ["//#region CAVERPHONE PHONETIC\n/** Replace rules for Caverphone phonetic algorithm. */\nconst RCAVERPHONE = [\n {p: /^cough/g, v: 'cou2f'},\n {p: /^rough/g, v: 'rou2f'},\n {p: /^tough/g, v: 'tou2f'},\n {p: /^enough/g, v: 'enou2f'},\n {p: /^gn/g, v: '2n'},\n {p: /mb$/g, v: 'm2'},\n {p: /cq/g, v: '2q'},\n {p: /ci/g, v: 'si'},\n {p: /ce/g, v: 'se'},\n {p: /cy/g, v: 'sy'},\n {p: /tch/g, v: '2ch'},\n {p: /c/g, v: 'k'},\n {p: /q/g, v: 'k'},\n {p: /x/g, v: 'k'},\n {p: /v/g, v: 'f'},\n {p: /dg/g, v: '2g'},\n {p: /tio/g, v: 'sio'},\n {p: /tia/g, v: 'sia'},\n {p: /ph/g, v: 'fh'},\n {p: /b/g, v: 'p'},\n {p: /sh/g, v: 's2'},\n {p: /z/g, v: 's'},\n {p: /^[aeiou]/g, v: 'A'},\n {p: /[aeiou]/g, v: '3'},\n {p: /3gh3/g, v: '3kh3'},\n {p: /gh/g, v: '22'},\n {p: /g/g, v: 'k'},\n {p: /ss+/g, v: 'S'},\n {p: /tt+/g, v: 'T'},\n {p: /pp+/g, v: 'P'},\n {p: /kk+/g, v: 'K'},\n {p: /ff+/g, v: 'F'},\n {p: /mm+/g, v: 'M'},\n {p: /nn+/g, v: 'N'},\n {p: /w3/g, v: 'W3'},\n {p: /wy/g, v: 'Wy'},\n {p: /wh3/g, v: 'Wh3'},\n {p: /why/g, v: 'Why'},\n {p: /^h/g, v: 'A'},\n {p: /h/g, v: '2'},\n {p: /r3/g, v: 'R3'},\n {p: /ry/g, v: 'Ry'},\n {p: /r/g, v: '2'},\n {p: /l3/g, v: 'L3'},\n {p: /ly/g, v: 'Ly'},\n {p: /l/g, v: '2'},\n {p: /j/g, v: 'y'},\n {p: /y3/g, v: 'Y3'},\n {p: /y/g, v: '2'},\n {p: /2/g, v: ''},\n {p: /3/g, v: ''},\n {p: /z/g, v: 's'},\n {p: /z/g, v: 's'},\n {p: /z/g, v: 's'},\n {p: /z/g, v: 's'},\n];\n\n\n/**\n * Get Caverphone phonetic of English text.\n * @param txt english text\n * @param ext extended caverphone? [false]\n * @returns caverphone phonetic string\n */\nexport function caverphonePhonetic(txt: string, ext=false): string {\n let t = txt.replace(/[^A-Za-z]/g, '').toLowerCase();\n for (const r of RCAVERPHONE)\n t = t.replace(r.p, r.v);\n t = ext? t : (t + '111111').substring(0, 6);\n return t.toUpperCase();\n}\n//#endregion\n\n\n\n\n//#region COLOGNE PHONETIC\n/**\n * Represents a handler function for Cologne phonetic algorithm.\n * @param nextChar next character in the string\n * @param prevChar previous character in the string\n * @param isFirst is the current character the first character?\n * @returns the cologne phonetic code for the character\n */\ntype FCologne = (nextChar: string, prevChar: string, isFirst: boolean) => string;\n\n// Cologne phonetic algorithm handlers.\nconst FAEIJOUY: FCologne = () => '0';\nconst FH: FCologne = () => '';\nconst FB: FCologne = () => '1';\nconst FP: FCologne = (b) => b!=='H'? '1':'3';\nconst FDT: FCologne = (b) => 'CSZ'.indexOf(b)<0? '2':'8';\nconst FFVW: FCologne = () => '3';\nconst FGKQ: FCologne = () => '4';\nconst FC: FCologne = (b, a, i) => (i && 'AHKLOQRUX'.indexOf(b) >= 0) || ('AHKOQUX'.indexOf(b) >= 0 && 'SZ'.indexOf(a) < 0)? '4' : '8';\nconst FX: FCologne = (_b, a) => 'CKQ'.indexOf(a)<0? '48':'8';\nconst FL: FCologne = () => '5';\nconst FMN: FCologne = () => '6';\nconst FR: FCologne = () => '7';\nconst FSZ: FCologne = () => '8';\n\n/** Cologne phonetic algorithm table. */\nconst RCOLOGNE = new Map<string, FCologne>([\n ['A', FAEIJOUY],\n ['B', FB],\n ['C', FC],\n ['D', FDT],\n ['E', FAEIJOUY],\n ['F', FFVW],\n ['G', FGKQ],\n ['H', FH],\n ['I', FAEIJOUY],\n ['J', FAEIJOUY],\n ['K', FGKQ],\n ['L', FL],\n ['M', FMN],\n ['N', FMN],\n ['O', FAEIJOUY],\n ['P', FP],\n ['Q', FGKQ],\n ['R', FR],\n ['S', FSZ],\n ['T', FDT],\n ['U', FAEIJOUY],\n ['V', FFVW],\n ['W', FFVW],\n ['X', FX],\n ['Y', FAEIJOUY],\n ['Z', FSZ],\n]);\n\n\n/**\n * Get Cologne phonetic of English text.\n * @param txt english text\n * @returns cologne phonetic string\n */\nexport function colognePhonetic(txt: string): string {\n const t = txt.replace(/[^A-Za-z]/g, '').toUpperCase().replace(/[ÄÖÜß]/g, 'A');\n let a = (RCOLOGNE.get(t[0]) as FCologne)(t[1], ' ', true);\n for (let i=1, I=t.length, pc=a; i<I; i++) {\n const c = (RCOLOGNE.get(t[i]) as FCologne)(t[i+1], t[i-1], i===0);\n if (c!==pc && c!=='0') a += c;\n pc = c;\n }\n return a;\n}\n//#endregion\n\n\n\n\n//#region METAPHONE PHONETIC\n/** Replace rules for Metaphone phonetic algorithm. */\nconst RMETAPHONE = [\n {p: /([^C])\\1/g, v: '$1'},\n {p: /^[KGP]N/g, v: 'N'},\n {p: /^AE/g, v: 'E'},\n {p: /^WR/g, v: 'R'},\n {p: /MB$/g, v: 'M'},\n {p: /SCH/g, v: 'K'},\n {p: /C(IA|H)/g, v: 'X$1'},\n {p: /C(I|E|Y)/g, v: 'S$1'},\n {p: /C/g, v: 'K'},\n {p: /D(GE|GY|GI)/g, v: 'J$1'},\n {p: /D/g, v: 'T'},\n {p: /G(H[^AEIOU])/g, v: '$1'},\n {p: /G(N|NED)$/g, v: '$1'},\n {p: /([^G])G(I|E|Y)/g, v: '$1J$2'},\n {p: /G/g, v: 'K'},\n {p: /([AEIOU])H([^AEIOU])|([AEIOU])H$/g, v: '$1H$2'},\n {p: /CK/g, v: 'K'},\n {p: /PH/g, v: 'F'},\n {p: /Q/g, v: 'K'},\n {p: /S(H|IO|IA)/g, v: 'X$1'},\n {p: /T(IA|IO)/g, v: 'X$1'},\n {p: /TH/g, v: '0'},\n {p: /TCH/g, v: 'CH'},\n {p: /V/g, v: 'F'},\n {p: /^WH/g, v: 'W'},\n {p: /W([^AEIOU])|W$/g, v: '$1'},\n {p: /^X/g, v: 'S'},\n {p: /X/g, v: 'KS'},\n {p: /Y([^AEIOU])|Y$/g, v: '$1'},\n {p: /Z/g, v: 'S'},\n {p: /(.)[AEIOU]/g, v: '$1'}\n];\n\n\n/**\n * Get Metaphone phonetic of English text.\n * @param txt english text\n * @returns metaphone phonetic string\n */\nexport function metaphonePhonetic(txt: string): string {\n let a = txt.replace(/[^A-Za-z]/g, '').toUpperCase();\n for (const r of RMETAPHONE)\n a = a.replace(r.p, r.v);\n return a;\n}\n//#endregion\n\n\n\n\n//#region MRA PHONETIC\n/**\n * Get Match Rating Approach (MRA) phonetic of English text.\n * @param txt english text\n * @param ext extended MRA? [false]\n * @returns MRA phonetic string\n */\nexport function mraPhonetic(txt: string, ext=false): string {\n let t = txt.replace(/[^A-Za-z]/g, '').toUpperCase();\n t = (t[0] + t.substring(1).replace(/[AEIOU]/g, '')).replace(/(.)\\1+/g, '$1');\n return ext || t.length <= 6? t : t.substring(0, 3) + t.substring(t.length - 3);\n}\n//#endregion\n\n\n\n\n//#region NYSIIS PHONETIC\n//#endregion\n\n\n\n\n//#region SOUNDEX PHONETIC\n// Soundex phonetic algorithm constants.\nconst SXVOWEL = 'aeiouy';\nconst SXREMOVE = 'aeiouyhw';\nconst SXD1 = 'bfpv';\nconst SXD2 = 'cgjkqsxz';\nconst SXD3 = 'dt';\nconst SXD4 = 'l';\nconst SXD5 = 'mn';\n// const SXD6 = 'r';\n\n\n/**\n * Get Soundex phonetic of English text.\n * @param txt english text\n * @param ext extended soundex? [false]\n * @returns soundex phonetic string\n */\nexport function soundexPhonetic(txt: string, ext=false): string {\n // 1. Filter text, keep only alphabets.\n txt = txt.replace(/[^A-Za-z]/g, '').toLowerCase();\n let dp = 0, d = 0, v = false, a = '';\n // 2. Get soundex code.\n for (const c of txt) {\n // a. Get digit.\n if (SXREMOVE.indexOf(c) >= 0) d = 0;\n else if (SXD1.indexOf(c) >= 0) d = 1;\n else if (SXD2.indexOf(c) >= 0) d = 2;\n else if (SXD3[0]===c || SXD3[1]===c) d = 3;\n else if (SXD4===c) d = 4;\n else if (SXD5[0]===c || SXD5[1]===c) d = 5;\n else d = 6;\n // b. Update code.\n if (!a.length) a += c.toUpperCase();\n else if (d && (d!==dp || v)) a += d;\n // c. Track vowel, previous digit.\n v = d? false : (v || SXVOWEL.indexOf(c) >= 0);\n dp = d? d : dp;\n }\n // 3. Return normal/extended code.\n const l = a.length;\n if (ext || !l) return a;\n if (l < 4) return a+'000'.substring(0, 4-l);\n return a.substring(0, 4);\n}\n//#endregion\n\n\n\n\n//#region SOUNDEX SQL PHONETIC\n// Soundex SQL phonetic algorithm constants.\nconst SSREMOVE = 'aeiouyhw';\nconst SSD1 = 'bfpv';\nconst SSD2 = 'cgjkqsxz';\nconst SSD3 = 'dt';\nconst SSD4 = 'l';\nconst SSD5 = 'mn';\n// const SSD6 = 'r';\n\n\n/**\n * Get Soundex phonetic (SQL) of English text.\n * @param txt english text\n * @param ext extended soundex? [false]\n * @returns soundex phonetic (SQL) string\n */\nexport function soundexSqlPhonetic(txt: string, ext=false): string {\n // 1. Filter text, keep only alphabets.\n txt = txt.replace(/[^A-Za-z]/g, '').toLowerCase();\n let dp = 0, d = 0, a = '';\n // 2. Get soundex code.\n for (const c of txt) {\n // a. Get digit.\n if (SSREMOVE.indexOf(c) >= 0) d = 0;\n else if (SSD1.indexOf(c) >= 0) d = 1;\n else if (SSD2.indexOf(c) >= 0) d = 2;\n else if (SSD3[0]===c || SSD3[1]===c) d = 3;\n else if (SSD4===c) d = 4;\n else if (SSD5[0]===c || SSD5[1]===c) d = 5;\n else d = 6;\n // b. Update code.\n if (!a.length) a += c.toUpperCase();\n else if (d && d!==dp) a += d;\n if (d) dp = d;\n }\n // 3. Return normal/extended code.\n const l = a.length;\n if (ext || !l) return a;\n if (l < 4) return a + '000'.substring(0, 4-l);\n return a.substring(0, 4);\n}\n//#endregion\n\n\n\n\n//#region LANCASTER STEM\n/** Represents a replacement rule for the Lancaster stemmer. */\ninterface LSRule {\n /** Suffix to be replaced. */\n s: string;\n /** Replacement string. */\n r: string;\n /** Minimum length of the stemmed word. */\n l?: number;\n /** Check if the stemmed word contains a vowel. */\n v?: boolean;\n};\n\n\n/** Replace rules for the Lancaster stemmer. */\nconst LSRULES: LSRule[] = [\n { s: 'ational', r: 'ate' },\n { s: 'tional', r: 'tion' },\n { s: 'fulness', r: 'ful' },\n { s: 'ousness', r: 'ous' },\n { s: 'iveness', r: 'ive' },\n { s: 'ization', r: 'ize' },\n { s: 'isation', r: 'ize' },\n { s: 'biliti', r: 'ble' },\n { s: 'lessli', r: 'less' },\n { s: 'entli', r: 'ent' },\n { s: 'ation', r: 'ate' },\n { s: 'ator', r: 'ate' },\n { s: 'alism', r: 'al' },\n { s: 'aliti', r: 'al' },\n { s: 'ousli', r: 'ous' },\n { s: 'iviti', r: 'ive' },\n { s: 'fulli', r: 'ful' },\n { s: 'enci', r: 'ence' },\n { s: 'anci', r: 'ance' },\n { s: 'abli', r: 'able' },\n { s: 'izer', r: 'ize' },\n { s: 'iser', r: 'ise' },\n { s: 'alli', r: 'al' },\n { s: 'ical', r: 'ic' },\n { s: 'ement', r: '' },\n { s: 'ance', r: '' },\n { s: 'ence', r: '' },\n { s: 'able', r: '' },\n { s: 'ible', r: '' },\n { s: 'ment', r: '' },\n { s: 'ness', r: '' },\n { s: 'ful', r: '' },\n { s: 'ous', r: '' },\n { s: 'ive', r: '' },\n { s: 'ize', r: '' },\n { s: 'ise', r: '' },\n { s: 'ing', r: '', l: 4, v: true },\n { s: 'ed', r: '', l: 3, v: true },\n { s: 'es', r: 'e', l: 3 },\n { s: 'es', r: '', l: 3, v: true },\n { s: 'ly', r: '', l: 3 },\n { s: 'li', r: '', l: 3 },\n { s: 'ti', r: 't', l: 3 },\n { s: 'ci', r: 'c', l: 3 },\n { s: 'gi', r: 'g', l: 3 },\n { s: 'si', r: 's', l: 3 },\n { s: 'zi', r: 'z', l: 3 },\n { s: 's', r: '', l: 2 },\n { s: 'e', r: '', l: 3 },\n { s: 'bb', r: 'b', l: 3, v: true },\n { s: 'dd', r: 'd', l: 3, v: true },\n { s: 'ff', r: 'f', l: 3, v: true },\n { s: 'gg', r: 'g', l: 3, v: true },\n { s: 'll', r: 'l', l: 3, v: true },\n { s: 'mm', r: 'm', l: 3, v: true },\n { s: 'nn', r: 'n', l: 3, v: true },\n { s: 'pp', r: 'p', l: 3, v: true },\n { s: 'rr', r: 'r', l: 3, v: true },\n { s: 'ss', r: 's', l: 3, v: true },\n { s: 'tt', r: 't', l: 3, v: true },\n { s: 'zz', r: 'z', l: 3, v: true },\n { s: 'i', r: '', l: 3, v: true },\n { s: 'ant', r: '' },\n { s: 'ent', r: '' },\n { s: 'ism', r: '' },\n { s: 'ist', r: '' },\n { s: 'er', r: '', l: 3 },\n { s: 'or', r: '', l: 3 },\n { s: 'al', r: '', l: 3 },\n { s: 'ic', r: '', l: 3 },\n { s: 'at', r: '', l: 3 },\n { s: 'en', r: '', l: 3 },\n { s: 'um', r: '', l: 3 },\n { s: 'us', r: '', l: 3 },\n { s: 'on', r: '', l: 3 },\n { s: 'ar', r: '', l: 3 },\n { s: 'el', r: '', l: 3 },\n { s: 'em', r: '', l: 3 },\n { s: 'in', r: '', l: 3 },\n { s: 'it', r: '', l: 3 },\n { s: 'ol', r: '', l: 3 },\n { s: 'op', r: '', l: 3 },\n { s: 'ot', r: '', l: 3 },\n { s: 'un', r: '', l: 3 },\n { s: 'up', r: '', l: 3 },\n { s: 'ur', r: '', l: 3 },\n { s: 'ut', r: '', l: 3 },\n { s: 'ct', r: 'c', l: 3 },\n { s: 'lt', r: 'l', l: 3 },\n { s: 'nt', r: 'n', l: 3 },\n { s: 'pt', r: 'p', l: 3 },\n { s: 'rt', r: 'r', l: 3 },\n { s: 'st', r: 's', l: 3 },\n { s: 'xt', r: 'x', l: 3 },\n { s: 'y', r: '', l: 3, v: true }\n];\n\n\n/**\n * Check if a word contains at least one vowel.\n * @param word word to be checked\n * @returns true if the word contains a vowel, false otherwise\n */\nfunction hasVowel(word: string): boolean {\n return /[aeiouy]/.test(word);\n}\n\n\n/**\n * Stem a word to its base form using the Lancaster stemmer.\n * @param word word to be stemmed\n * @returns stemmed word\n */\nexport function lancasterStem(word: string): string {\n if (!word) return '';\n const w = word.toLowerCase();\n for (const r of LSRULES) {\n if (!w.endsWith(r.s)) continue;\n const base = w.slice(0, -r.s.length) + r.r;\n if (r.l && base.length < r.l) continue;\n if (r.v && !hasVowel(base)) continue;\n // Recursively stem again if further changes are possible.\n return lancasterStem(base);\n }\n return w;\n}\n//#endregion\n\n\n\n\n//#region PORTER STEM\n/** Step 2 replacements for the Porter stemmer. */\nconst PSREPLACE2: Array<[string, string]> = [\n ['ational', 'ate'],\n ['tional', 'tion'],\n ['enci', 'ence'],\n ['anci', 'ance'],\n ['izer', 'ize'],\n ['abli', 'able'],\n ['alli', 'al'],\n ['entli', 'ent'],\n ['eli', 'e'],\n ['ousli', 'ous'],\n ['ization', 'ize'],\n ['ation', 'ate'],\n ['ator', 'ate'],\n ['alism', 'al'],\n ['iveness', 'ive'],\n ['fulness', 'ful'],\n ['ousness', 'ous'],\n ['aliti', 'al'],\n ['iviti', 'ive'],\n ['biliti', 'ble'],\n];\n\n\n/** Step 3 replacements for the Porter stemmer. */\nconst PSREPLACE3: Array<[string, string]> = [\n ['icate', 'ic'],\n ['ative', ''],\n ['alize', 'al'],\n ['iciti', 'ic'],\n ['ical', 'ic'],\n ['ful', ''],\n ['ness', ''],\n];\n\n\n/** Step 4 suffixes for the Porter stemmer. */\nconst PSSUFFIXES4 = [\n 'al',\n 'ance',\n 'ence',\n 'er',\n 'ic',\n 'able',\n 'ible',\n 'ant',\n 'ement',\n 'ment',\n 'ent',\n 'ion',\n 'ou',\n 'ism',\n 'ate',\n 'iti',\n 'ous',\n 'ive',\n 'ize',\n];\n\n\n/**\n * Test whether the letter at position i is a consonant.\n * @param w word to be processed\n * @param i position of the letter in the word\n * @returns true if the letter is a consonant, false otherwise\n */\nfunction isConsonant(w: string, i: number): boolean {\n if (\"aeiou\".includes(w[i])) return false;\n // 'y' is a consonant unless preceded by a vowel.\n if (w[i]===\"y\") return i===0? true : !isConsonant(w, i-1);\n return true;\n}\n\n\n/**\n * Test whether the word contains a vowel.\n * @param w word to be processed\n * @returns true if the word contains a vowel, false otherwise\n */\nfunction containsVowel(w: string): boolean {\n for (let i=0; i<w.length; i++)\n if (!isConsonant(w, i)) return true;\n return false;\n}\n\n\n/**\n * Test whether the word ends with a double consonant.\n * @param w word to be processed\n * @returns true if the word ends with a double consonant, false otherwise\n */\nfunction endsWithDoubleConsonant(w: string): boolean {\n const W = w.length;\n if (W<2) return false;\n return w[W-1] === w[W-2] && isConsonant(w, W-1);\n}\n\n\n/**\n * Compute the VC measure of a word.\n * @param w word to be processed\n * @returns count of VC sequences in the word\n */\nfunction measureVC(w: string): number {\n let m = 0, f = false;\n for (let i=0; i<w.length; i++) {\n // We enter a vowel segment.\n if (!isConsonant(w, i)) f = true;\n // Transition from vowel to consonant increases the count.\n else if (f) { m++; f = false; }\n }\n return m;\n}\n\n\n/**\n * Check if the word ends with a consonant-vowel-consonant pattern.\n * @param w word to be processed\n * @param i position of the letter in the word\n * @returns true if the word ends with a CVC pattern, false otherwise\n */\nfunction endsWithCVC(w: string, i: number): boolean {\n if (i < 2) return false;\n if (!isConsonant(w, i) || isConsonant(w, i-1) || !isConsonant(w, i-2)) return false;\n return !\"wxy\".includes(w[i]);\n}\n\n\n/**\n * Stem a word to its base form using the Porter stemmer.\n * @param word word to be stemmed\n * @returns stemmed word\n */\nexport function porterStem(word: string): string {\n let w = word.toLowerCase().replace(/[^a-z]/g, '');\n if (w.length < 3) return w;\n // 1a. Deal with plurals and -ed, -ing endings.\n if (w.endsWith(\"sses\")) w = w.slice(0, -2);\n else if (w.endsWith(\"ies\")) w = w.slice(0, -2);\n else if (w.endsWith(\"ss\")) { /* Ignore */ }\n else if (w.endsWith(\"s\")) w = w.slice(0, -1);\n // 1b. Remove -ed and -ing where appropriate.\n if (w.endsWith(\"eed\")) {\n // If the stem (w without \"eed\") has m > 0, replace \"eed\" with \"ee\".\n const base = w.slice(0, -3);\n if (measureVC(w) > 0) w = base + \"ee\";\n }\n else if ((w.endsWith(\"ed\") && containsVowel(w.slice(0, -2))) ||\n (w.endsWith(\"ing\") && containsVowel(w.slice(0, -3)))) {\n // Remove \"ed\" or \"ing\" suffix.\n w = w.endsWith(\"ed\")? w.slice(0, w.length - 2) : w.slice(0, w.length - 3);\n // Special handling for endings after removal.\n if (w.endsWith(\"at\") || w.endsWith(\"bl\") || w.endsWith(\"iz\")) w += \"e\";\n else if (endsWithDoubleConsonant(w) && !\"lsz\".includes(w[w.length - 1])) w = w.slice(0, -1);\n else if (measureVC(w) === 1 && endsWithCVC(w, w.length-1)) w += \"e\";\n }\n // 1c. Replace terminal 'y' with 'i' if there is a vowel in the stem.\n if (w.endsWith(\"y\") && containsVowel(w)) w = w.slice(0, -1) + \"i\";\n // 2. Replace double-suffixes with single ones.\n for (const [suffix, replacement] of PSREPLACE2) {\n if (!w.endsWith(suffix)) continue;\n const base = w.slice(0, w.length - suffix.length);\n if (measureVC(w) > 0) w = base + replacement;\n break;\n }\n // 3. Further suffix stripping.\n for (const [suffix, replacement] of PSREPLACE3) {\n if (!w.endsWith(suffix)) continue;\n const base = w.slice(0, w.length - suffix.length);\n if (measureVC(w) > 0) w = base + replacement;\n break;\n }\n // 4. Remove certain suffixes if measure > 1.\n for (const suffix of PSSUFFIXES4) {\n if (!w.endsWith(suffix)) continue;\n const base = w.slice(0, w.length - suffix.length);\n // Special check for \"ion\": the stem must end with s or t.\n if (measureVC(w) > 1 && (suffix!==\"ion\" || (base.endsWith(\"s\") || base.endsWith(\"t\")))) w = base;\n break;\n }\n // 5. Clean up the ending.\n // Remove a trailing \"e\" if measure>1, or measure===1 but not cvc.\n if (w.endsWith(\"e\")) {\n const m = measureVC(w);\n if (m> 1 || (m=== 1 && !endsWithCVC(w, w.length - 2))) w = w.slice(0, -1);\n }\n // If the word ends with \"ll\" and measure>1, reduce it to single \"l\".\n if (w.endsWith(\"ll\") && measureVC(w)>1) w = w.slice(0, -1);\n return w;\n}\n//#endregion\n"],
|
|
5
|
+
"mappings": "AAEA,IAAMA,EAAc,CAClB,CAAC,EAAG,UAAW,EAAG,OAAO,EACzB,CAAC,EAAG,UAAW,EAAG,OAAO,EACzB,CAAC,EAAG,UAAW,EAAG,OAAO,EACzB,CAAC,EAAG,WAAY,EAAG,QAAQ,EAC3B,CAAC,EAAG,OAAQ,EAAG,IAAI,EACnB,CAAC,EAAG,OAAQ,EAAG,IAAI,EACnB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,OAAQ,EAAG,KAAK,EACpB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,OAAQ,EAAG,KAAK,EACpB,CAAC,EAAG,OAAQ,EAAG,KAAK,EACpB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,YAAa,EAAG,GAAG,EACvB,CAAC,EAAG,WAAY,EAAG,GAAG,EACtB,CAAC,EAAG,QAAS,EAAG,MAAM,EACtB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,OAAQ,EAAG,KAAK,EACpB,CAAC,EAAG,OAAQ,EAAG,KAAK,EACpB,CAAC,EAAG,MAAO,EAAG,GAAG,EACjB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,MAAO,EAAG,IAAI,EAClB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,EAAE,EACf,CAAC,EAAG,KAAM,EAAG,EAAE,EACf,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,KAAM,EAAG,GAAG,GAUX,SAASC,EAAmBC,EAAaC,EAAI,GAAK,CACvD,IAAIC,EAAIF,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EACjD,QAAWG,KAAKL,EACdI,EAAIA,EAAE,QAAQC,EAAE,EAAGA,EAAE,CAAC,EACxB,OAAAD,EAAID,EAAKC,GAAKA,EAAI,UAAU,UAAU,EAAG,CAAA,EAClCA,EAAE,YAAW,CACtB,CAiBA,IAAME,EAAqB,IAAM,IAC3BC,EAAqB,IAAM,GAC3BC,EAAqB,IAAM,IAC3BC,EAAsBC,GAAMA,IAAI,IAAK,IAAI,IACzCC,EAAsBD,GAAM,MAAM,QAAQA,CAAA,EAAG,EAAG,IAAI,IACpDE,EAAqB,IAAM,IAC3BC,EAAqB,IAAM,IAC3BC,EAAqB,CAACJ,EAAGK,EAAGC,IAAOA,GAAK,YAAY,QAAQN,CAAA,GAAM,GAAO,UAAU,QAAQA,CAAA,GAAM,GAAK,KAAK,QAAQK,CAAA,EAAK,EAAI,IAAM,IAClIE,EAAqB,CAACC,EAAIH,IAAM,MAAM,QAAQA,CAAA,EAAG,EAAG,KAAK,IACzDI,EAAqB,IAAM,IAC3BC,EAAqB,IAAM,IAC3BC,EAAqB,IAAM,IAC3BC,EAAqB,IAAM,IAG3BC,EAAW,IAAI,IAAsB,CACzC,CAAC,IAAKjB,GACN,CAAC,IAAKE,GACN,CAAC,IAAKM,GACN,CAAC,IAAKH,GACN,CAAC,IAAKL,GACN,CAAC,IAAKM,GACN,CAAC,IAAKC,GACN,CAAC,IAAKN,GACN,CAAC,IAAKD,GACN,CAAC,IAAKA,GACN,CAAC,IAAKO,GACN,CAAC,IAAKM,GACN,CAAC,IAAKC,GACN,CAAC,IAAKA,GACN,CAAC,IAAKd,GACN,CAAC,IAAKG,GACN,CAAC,IAAKI,GACN,CAAC,IAAKQ,GACN,CAAC,IAAKC,GACN,CAAC,IAAKX,GACN,CAAC,IAAKL,GACN,CAAC,IAAKM,GACN,CAAC,IAAKA,GACN,CAAC,IAAKK,GACN,CAAC,IAAKX,GACN,CAAC,IAAKgB,GACP,EAQM,SAASE,EAAgBtB,EAAW,CACzC,IAAME,EAAIF,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EAAG,QAAQ,UAAW,GAAA,EACrEa,EAAKQ,EAAS,IAAInB,EAAE,CAAA,CAAE,EAAeA,EAAE,CAAA,EAAI,IAAK,EAAA,EACpD,QAASY,EAAE,EAAGS,EAAErB,EAAE,OAAQsB,EAAGX,EAAGC,EAAES,EAAGT,IAAK,CACxC,IAAMW,EAAKJ,EAAS,IAAInB,EAAEY,CAAA,CAAE,EAAeZ,EAAEY,EAAE,CAAA,EAAIZ,EAAEY,EAAE,CAAA,EAAIA,IAAI,CAAA,EAC3DW,IAAID,GAAMC,IAAI,MAAKZ,GAAKY,GAC5BD,EAAKC,CACP,CACA,OAAOZ,CACT,CAQA,IAAMa,EAAa,CACjB,CAAC,EAAG,YAAa,EAAG,IAAI,EACxB,CAAC,EAAG,WAAY,EAAG,GAAG,EACtB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,WAAY,EAAG,KAAK,EACxB,CAAC,EAAG,YAAa,EAAG,KAAK,EACzB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,eAAgB,EAAG,KAAK,EAC5B,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,gBAAiB,EAAG,IAAI,EAC5B,CAAC,EAAG,aAAc,EAAG,IAAI,EACzB,CAAC,EAAG,kBAAmB,EAAG,OAAO,EACjC,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,oCAAqC,EAAG,OAAO,EACnD,CAAC,EAAG,MAAO,EAAG,GAAG,EACjB,CAAC,EAAG,MAAO,EAAG,GAAG,EACjB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,cAAe,EAAG,KAAK,EAC3B,CAAC,EAAG,YAAa,EAAG,KAAK,EACzB,CAAC,EAAG,MAAO,EAAG,GAAG,EACjB,CAAC,EAAG,OAAQ,EAAG,IAAI,EACnB,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,OAAQ,EAAG,GAAG,EAClB,CAAC,EAAG,kBAAmB,EAAG,IAAI,EAC9B,CAAC,EAAG,MAAO,EAAG,GAAG,EACjB,CAAC,EAAG,KAAM,EAAG,IAAI,EACjB,CAAC,EAAG,kBAAmB,EAAG,IAAI,EAC9B,CAAC,EAAG,KAAM,EAAG,GAAG,EAChB,CAAC,EAAG,cAAe,EAAG,IAAI,GASrB,SAASC,EAAkB3B,EAAW,CAC3C,IAAIa,EAAIb,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EACjD,QAAWG,KAAKuB,EACdb,EAAIA,EAAE,QAAQV,EAAE,EAAGA,EAAE,CAAC,EACxB,OAAOU,CACT,CAaO,SAASe,EAAY5B,EAAaC,EAAI,GAAK,CAChD,IAAIC,EAAIF,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EACjD,OAAAE,GAAKA,EAAE,CAAA,EAAKA,EAAE,UAAU,CAAA,EAAG,QAAQ,WAAY,EAAA,GAAK,QAAQ,UAAW,IAAA,EAChED,GAAOC,EAAE,QAAU,EAAGA,EAAIA,EAAE,UAAU,EAAG,CAAA,EAAKA,EAAE,UAAUA,EAAE,OAAS,CAAA,CAC9E,CAcA,IAAM2B,EAAW,SACXC,EAAW,WACXC,EAAO,OACPC,EAAO,WACPC,EAAO,KACPC,EAAO,IACPC,EAAO,KAUN,SAASC,EAAgBpC,EAAaC,EAAI,GAAK,CAEpDD,EAAMA,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EAC/C,IAAIqC,EAAK,EAAGC,EAAI,EAAGC,EAAI,GAAO1B,EAAI,GAElC,QAAWY,KAAKzB,EAEV8B,EAAS,QAAQL,CAAA,GAAO,EAAGa,EAAI,EAC1BP,EAAK,QAAQN,CAAA,GAAM,EAAGa,EAAI,EAC1BN,EAAK,QAAQP,CAAA,GAAM,EAAGa,EAAI,EAC1BL,EAAK,CAAA,IAAKR,GAAKQ,EAAK,CAAA,IAAKR,EAAGa,EAAI,EAChCJ,IAAOT,EAAGa,EAAI,EACdH,EAAK,CAAA,IAAKV,GAAKU,EAAK,CAAA,IAAKV,EAAGa,EAAI,EACpCA,EAAI,EAEJzB,EAAE,OACEyB,IAAMA,IAAID,GAAME,KAAI1B,GAAKyB,GADnBzB,GAAKY,EAAE,YAAW,EAGjCc,EAAID,EAAG,GAASC,GAAKV,EAAQ,QAAQJ,CAAA,GAAM,EAC3CY,EAAKC,GAAOD,EAGd,IAAMG,EAAI3B,EAAE,OACZ,OAAIZ,GAAO,CAACuC,EAAU3B,EAClB2B,EAAI,EAAU3B,EAAE,MAAM,UAAU,EAAG,EAAE2B,CAAA,EAClC3B,EAAE,UAAU,EAAG,CAAA,CACxB,CAQA,IAAM4B,EAAW,WACXC,EAAO,OACPC,EAAO,WACPC,EAAO,KACPC,EAAO,IACPC,EAAO,KAUN,SAASC,EAAmB/C,EAAaC,EAAI,GAAK,CAEvDD,EAAMA,EAAI,QAAQ,aAAc,EAAA,EAAI,YAAW,EAC/C,IAAIqC,EAAK,EAAGC,EAAI,EAAGzB,EAAI,GAEvB,QAAWY,KAAKzB,EAEVyC,EAAS,QAAQhB,CAAA,GAAO,EAAGa,EAAI,EAC1BI,EAAK,QAAQjB,CAAA,GAAM,EAAGa,EAAI,EAC1BK,EAAK,QAAQlB,CAAA,GAAM,EAAGa,EAAI,EAC1BM,EAAK,CAAA,IAAKnB,GAAKmB,EAAK,CAAA,IAAKnB,EAAGa,EAAI,EAChCO,IAAOpB,EAAGa,EAAI,EACdQ,EAAK,CAAA,IAAKrB,GAAKqB,EAAK,CAAA,IAAKrB,EAAGa,EAAI,EACpCA,EAAI,EAEJzB,EAAE,OACEyB,GAAKA,IAAID,IAAIxB,GAAKyB,GADZzB,GAAKY,EAAE,YAAW,EAE7Ba,IAAGD,EAAKC,GAGd,IAAM,EAAIzB,EAAE,OACZ,OAAIZ,GAAO,CAAC,EAAUY,EAClB,EAAI,EAAUA,EAAI,MAAM,UAAU,EAAG,EAAE,CAAA,EACpCA,EAAE,UAAU,EAAG,CAAA,CACxB,CAqBA,IAAMmC,EAAoB,CACxB,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,SAAW,EAAG,MAAO,EAC1B,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,UAAW,EAAG,KAAM,EACzB,CAAE,EAAG,SAAW,EAAG,KAAM,EACzB,CAAE,EAAG,SAAW,EAAG,MAAO,EAC1B,CAAE,EAAG,QAAW,EAAG,KAAM,EACzB,CAAE,EAAG,QAAW,EAAG,KAAM,EACzB,CAAE,EAAG,OAAW,EAAG,KAAM,EACzB,CAAE,EAAG,QAAW,EAAG,IAAK,EACxB,CAAE,EAAG,QAAW,EAAG,IAAK,EACxB,CAAE,EAAG,QAAW,EAAG,KAAM,EACzB,CAAE,EAAG,QAAW,EAAG,KAAM,EACzB,CAAE,EAAG,QAAW,EAAG,KAAM,EACzB,CAAE,EAAG,OAAW,EAAG,MAAO,EAC1B,CAAE,EAAG,OAAW,EAAG,MAAO,EAC1B,CAAE,EAAG,OAAW,EAAG,MAAO,EAC1B,CAAE,EAAG,OAAW,EAAG,KAAM,EACzB,CAAE,EAAG,OAAW,EAAG,KAAM,EACzB,CAAE,EAAG,OAAW,EAAG,IAAK,EACxB,CAAE,EAAG,OAAW,EAAG,IAAK,EACxB,CAAE,EAAG,QAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,OAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,GAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,IAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,IAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,IAAW,EAAG,GAAK,EAAG,EAAG,EAAG,EAAK,EACtC,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,MAAW,EAAG,EAAG,EACtB,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,GAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,KAAW,EAAG,IAAK,EAAG,CAAE,EAC7B,CAAE,EAAG,IAAW,EAAG,GAAK,EAAG,EAAG,EAAG,EAAK,GASxC,SAASC,EAASC,EAAY,CAC5B,MAAO,WAAW,KAAKA,CAAA,CACzB,CAQO,SAASC,EAAcD,EAAY,CACxC,GAAI,CAACA,EAAM,MAAO,GAClB,IAAME,EAAIF,EAAK,YAAW,EAC1B,QAAW/C,KAAK6C,EAAS,CACvB,GAAI,CAACI,EAAE,SAASjD,EAAE,CAAC,EAAG,SACtB,IAAMkD,EAAOD,EAAE,MAAM,EAAG,CAACjD,EAAE,EAAE,MAAM,EAAIA,EAAE,EACzC,GAAI,EAAAA,EAAE,GAAKkD,EAAK,OAASlD,EAAE,IACvB,EAAAA,EAAE,GAAK,CAAC8C,EAASI,CAAA,GAErB,OAAOF,EAAcE,CAAA,CACvB,CACA,OAAOD,CACT,CAQA,IAAME,EAAsC,CAC1C,CAAC,UAAW,OACZ,CAAC,SAAW,QACZ,CAAC,OAAW,QACZ,CAAC,OAAW,QACZ,CAAC,OAAW,OACZ,CAAC,OAAW,QACZ,CAAC,OAAW,MACZ,CAAC,QAAW,OACZ,CAAC,MAAW,KACZ,CAAC,QAAW,OACZ,CAAC,UAAW,OACZ,CAAC,QAAW,OACZ,CAAC,OAAW,OACZ,CAAC,QAAW,MACZ,CAAC,UAAW,OACZ,CAAC,UAAW,OACZ,CAAC,UAAW,OACZ,CAAC,QAAW,MACZ,CAAC,QAAW,OACZ,CAAC,SAAW,QAKRC,EAAsC,CAC1C,CAAC,QAAS,MACV,CAAC,QAAS,IACV,CAAC,QAAS,MACV,CAAC,QAAS,MACV,CAAC,OAAS,MACV,CAAC,MAAS,IACV,CAAC,OAAS,KAKNC,EAAc,CAClB,KACA,OACA,OACA,KACA,KACA,OACA,OACA,MACA,QACA,OACA,MACA,MACA,KACA,MACA,MACA,MACA,MACA,MACA,OAUF,SAASC,EAAYL,EAAWtC,EAAS,CACvC,MAAI,QAAQ,SAASsC,EAAEtC,CAAA,CAAE,EAAU,GAE/BsC,EAAEtC,CAAA,IAAK,IAAYA,IAAI,EAAG,GAAO,CAAC2C,EAAYL,EAAGtC,EAAE,CAAA,EAChD,EACT,CAQA,SAAS4C,EAAcN,EAAS,CAC9B,QAAStC,EAAE,EAAGA,EAAEsC,EAAE,OAAQtC,IACxB,GAAI,CAAC2C,EAAYL,EAAGtC,CAAA,EAAI,MAAO,GACjC,MAAO,EACT,CAQA,SAAS6C,EAAwBP,EAAS,CACxC,IAAMQ,EAAIR,EAAE,OACZ,OAAIQ,EAAE,EAAU,GACTR,EAAEQ,EAAE,CAAA,IAAOR,EAAEQ,EAAE,CAAA,GAAMH,EAAYL,EAAGQ,EAAE,CAAA,CAC/C,CAQA,SAASC,EAAUT,EAAS,CAC1B,IAAIU,EAAI,EAAGC,EAAI,GACf,QAASjD,EAAE,EAAGA,EAAEsC,EAAE,OAAQtC,IAEnB2C,EAAYL,EAAGtC,CAAA,EAEXiD,IAAKD,IAAKC,EAAI,IAFCA,EAAI,GAI9B,OAAOD,CACT,CASA,SAASE,EAAYZ,EAAWtC,EAAS,CAEvC,OADIA,EAAI,GACJ,CAAC2C,EAAYL,EAAGtC,CAAA,GAAM2C,EAAYL,EAAGtC,EAAE,CAAA,GAAM,CAAC2C,EAAYL,EAAGtC,EAAE,CAAA,EAAW,GACvE,CAAC,MAAM,SAASsC,EAAEtC,CAAA,CAAE,CAC7B,CAQO,SAASmD,GAAWf,EAAY,CACrC,IAAIE,EAAIF,EAAK,YAAW,EAAG,QAAQ,UAAW,EAAA,EAC9C,GAAIE,EAAE,OAAS,EAAG,OAAOA,EAOzB,GALIA,EAAE,SAAS,MAAA,GACNA,EAAE,SAAS,KAAA,EADQA,EAAIA,EAAE,MAAM,EAAG,EAAC,EAEnCA,EAAE,SAAS,IAAA,GACXA,EAAE,SAAS,GAAA,IAAMA,EAAIA,EAAE,MAAM,EAAG,EAAC,GAEtCA,EAAE,SAAS,KAAA,EAAQ,CAErB,IAAMC,EAAOD,EAAE,MAAM,EAAG,EAAC,EACrBS,EAAUT,CAAA,EAAK,IAAGA,EAAIC,EAAO,KACnC,MACUD,EAAE,SAAS,IAAA,GAAUM,EAAcN,EAAE,MAAM,EAAG,EAAC,CAAA,GAC/CA,EAAE,SAAS,KAAA,GAAUM,EAAcN,EAAE,MAAM,EAAG,EAAC,CAAA,KAEvDA,EAAIA,EAAE,SAAS,IAAA,EAAOA,EAAE,MAAM,EAAGA,EAAE,OAAS,CAAA,EAAKA,EAAE,MAAM,EAAGA,EAAE,OAAS,CAAA,EAEnEA,EAAE,SAAS,IAAA,GAASA,EAAE,SAAS,IAAA,GAASA,EAAE,SAAS,IAAA,EAAOA,GAAK,IAC1DO,EAAwBP,CAAA,GAAM,CAAC,MAAM,SAASA,EAAEA,EAAE,OAAS,CAAA,CAAE,EAAGA,EAAIA,EAAE,MAAM,EAAG,EAAC,EAChFS,EAAUT,CAAA,IAAO,GAAKY,EAAYZ,EAAGA,EAAE,OAAO,CAAA,IAAIA,GAAK,MAG9DA,EAAE,SAAS,GAAA,GAAQM,EAAcN,CAAA,IAAIA,EAAIA,EAAE,MAAM,EAAG,EAAC,EAAK,KAE9D,OAAW,CAACc,EAAQC,CAAA,IAAgBb,EAAY,CAC9C,GAAI,CAACF,EAAE,SAASc,CAAA,EAAS,SACzB,IAAMb,EAAOD,EAAE,MAAM,EAAGA,EAAE,OAASc,EAAO,MAAM,EAC5CL,EAAUT,CAAA,EAAK,IAAGA,EAAIC,EAAOc,GACjC,KACF,CAEA,OAAW,CAACD,EAAQC,CAAA,IAAgBZ,EAAY,CAC9C,GAAI,CAACH,EAAE,SAASc,CAAA,EAAS,SACzB,IAAMb,EAAOD,EAAE,MAAM,EAAGA,EAAE,OAASc,EAAO,MAAM,EAC5CL,EAAUT,CAAA,EAAK,IAAGA,EAAIC,EAAOc,GACjC,KACF,CAEA,QAAWD,KAAUV,EAAa,CAChC,GAAI,CAACJ,EAAE,SAASc,CAAA,EAAS,SACzB,IAAMb,EAAOD,EAAE,MAAM,EAAGA,EAAE,OAASc,EAAO,MAAM,EAE5CL,EAAUT,CAAA,EAAK,IAAMc,IAAS,OAAUb,EAAK,SAAS,GAAA,GAAQA,EAAK,SAAS,GAAA,KAAQD,EAAIC,GAC5F,KACF,CAGA,GAAID,EAAE,SAAS,GAAA,EAAM,CACnB,IAAMU,EAAID,EAAUT,CAAA,GAChBU,EAAG,GAAMA,IAAK,GAAK,CAACE,EAAYZ,EAAGA,EAAE,OAAS,CAAA,KAAKA,EAAIA,EAAE,MAAM,EAAG,EAAC,EACzE,CAEA,OAAIA,EAAE,SAAS,IAAA,GAASS,EAAUT,CAAA,EAAG,IAAGA,EAAIA,EAAE,MAAM,EAAG,EAAC,GACjDA,CACT",
|
|
6
|
+
"names": ["RCAVERPHONE", "caverphonePhonetic", "txt", "ext", "t", "r", "FAEIJOUY", "FH", "FB", "FP", "b", "FDT", "FFVW", "FGKQ", "FC", "a", "i", "FX", "_b", "FL", "FMN", "FR", "FSZ", "RCOLOGNE", "colognePhonetic", "I", "pc", "c", "RMETAPHONE", "metaphonePhonetic", "mraPhonetic", "SXVOWEL", "SXREMOVE", "SXD1", "SXD2", "SXD3", "SXD4", "SXD5", "soundexPhonetic", "dp", "d", "v", "l", "SSREMOVE", "SSD1", "SSD2", "SSD3", "SSD4", "SSD5", "soundexSqlPhonetic", "LSRULES", "hasVowel", "word", "lancasterStem", "w", "base", "PSREPLACE2", "PSREPLACE3", "PSSUFFIXES4", "isConsonant", "containsVowel", "endsWithDoubleConsonant", "W", "measureVC", "m", "f", "endsWithCVC", "porterStem", "suffix", "replacement"]
|
|
7
|
+
}
|
package/index.test.ts
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
import {assertEquals} from "@std/assert";
|
|
2
|
+
import {
|
|
3
|
+
caverphonePhonetic,
|
|
4
|
+
colognePhonetic,
|
|
5
|
+
metaphonePhonetic,
|
|
6
|
+
mraPhonetic,
|
|
7
|
+
soundexPhonetic,
|
|
8
|
+
soundexSqlPhonetic,
|
|
9
|
+
lancasterStem,
|
|
10
|
+
porterStem,
|
|
11
|
+
} from "./index.ts";
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
//#region PHONETIC TESTS
|
|
17
|
+
Deno.test("Caverphone Phonetic", () => {
|
|
18
|
+
assertEquals(caverphonePhonetic("Thompson"), "TMPSN1");
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
Deno.test("Cologne Phonetic", () => {
|
|
23
|
+
assertEquals(colognePhonetic("Hari"), "7");
|
|
24
|
+
});
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
Deno.test("Metaphone Phonetic", () => {
|
|
28
|
+
assertEquals(metaphonePhonetic("Lightyear"), "LHTYAR");
|
|
29
|
+
});
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
Deno.test("MRA Phonetic", () => {
|
|
33
|
+
assertEquals(mraPhonetic("Byrne"), "BYRN");
|
|
34
|
+
});
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
Deno.test("Soundex Phonetic", () => {
|
|
38
|
+
assertEquals(soundexPhonetic("Tymczak"), "T522");
|
|
39
|
+
});
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
Deno.test("Soundex SQL Phonetic", () => {
|
|
43
|
+
assertEquals(soundexSqlPhonetic("Tymczak"), "T520");
|
|
44
|
+
});
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
// english.nysiisPhonetic('Mackie');
|
|
48
|
+
// 'MCY'
|
|
49
|
+
//#endregion
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
|
|
53
|
+
|
|
54
|
+
//#region WORD STEM TESTS
|
|
55
|
+
Deno.test("Lancaster Stem", () => {
|
|
56
|
+
assertEquals(lancasterStem("running"), "run");
|
|
57
|
+
});
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
Deno.test("Porter Stem", () => {
|
|
61
|
+
assertEquals(porterStem("running"), "run");
|
|
62
|
+
});
|
|
63
|
+
//#endregion
|
package/package.json
CHANGED
|
@@ -1,6 +1,16 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "extra-english.web",
|
|
3
|
-
"version": "
|
|
4
|
-
"
|
|
5
|
-
"
|
|
3
|
+
"version": "1.2.0",
|
|
4
|
+
"type": "module",
|
|
5
|
+
"license": "MIT",
|
|
6
|
+
"main": "./index.js",
|
|
7
|
+
"types": "./index.d.ts",
|
|
8
|
+
"exports": {
|
|
9
|
+
".": {
|
|
10
|
+
"types": "./index.d.ts",
|
|
11
|
+
"import": "./index.js",
|
|
12
|
+
"default": "./index.js"
|
|
13
|
+
}
|
|
14
|
+
},
|
|
15
|
+
"dependencies": {}
|
|
6
16
|
}
|