cleanup
This commit is contained in:
adueck
parent
0c2948721b
commit
0846fee749
|
|
@ -16,19 +16,25 @@ import { makePsString, removeFVarients } from "./accent-and-ps-utils";
|
|||
* @param s
|
||||
*/
|
||||
export function accentOnFront(s: T.PsString): T.PsString;
|
||||
export function accentOnFront(s: T.LengthOptions<T.PsString>): T.LengthOptions<T.PsString>;
|
||||
export function accentOnFront(s: T.SingleOrLengthOpts<T.PsString>): T.SingleOrLengthOpts<T.PsString>;
|
||||
export function accentOnFront(s: T.SingleOrLengthOpts<T.PsString>): T.SingleOrLengthOpts<T.PsString> {
|
||||
if ("long" in s) {
|
||||
return {
|
||||
short: accentOnFront(s.short),
|
||||
long: accentOnFront(s.long),
|
||||
};
|
||||
}
|
||||
export function accentOnFront(
|
||||
s: T.LengthOptions<T.PsString>
|
||||
): T.LengthOptions<T.PsString>;
|
||||
export function accentOnFront(
|
||||
s: T.SingleOrLengthOpts<T.PsString>
|
||||
): T.SingleOrLengthOpts<T.PsString>;
|
||||
export function accentOnFront(
|
||||
s: T.SingleOrLengthOpts<T.PsString>
|
||||
): T.SingleOrLengthOpts<T.PsString> {
|
||||
if ("long" in s) {
|
||||
return {
|
||||
...s,
|
||||
f: accentLetter(removeAccents(s.f)),
|
||||
short: accentOnFront(s.short),
|
||||
long: accentOnFront(s.long),
|
||||
};
|
||||
}
|
||||
return {
|
||||
...s,
|
||||
f: accentLetter(removeAccents(s.f)),
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -37,33 +43,35 @@ export function accentOnFront(s: T.SingleOrLengthOpts<T.PsString>): T.SingleOrLe
|
|||
* @param s - the Pashto string (with Pashto and Phonetics) to ensure the accent on
|
||||
*/
|
||||
export function accentPastParticiple(s: T.PsString): T.PsString {
|
||||
// check for accent placing in words like wáayuley and azmóyuley
|
||||
const accentFallsOnThirdLast = (syls: string[]) => {
|
||||
if (syls.length < 3) return false;
|
||||
const secondLast = syls[syls.length-2];
|
||||
const thirdLast = syls[syls.length-3];
|
||||
const lastLetterOfThirdLast = thirdLast.slice(-1);
|
||||
return (
|
||||
(secondLast === "ul") && (lastLetterOfThirdLast === "y")
|
||||
);
|
||||
}
|
||||
// remove all accents
|
||||
const accentsRemoved = removeAccents(s.f);
|
||||
// split up the syllables (preserving the spaces)
|
||||
const syllables = splitUpSyllables(accentsRemoved);
|
||||
// add an accent on the appropriate syllable
|
||||
const n = accentFallsOnThirdLast(syllables) ? 2 : 1;
|
||||
const accentedF = accentFSylsOnNFromEnd(syllables, n);
|
||||
return makePsString(s.p, accentedF);
|
||||
// check for accent placing in words like wáayuley and azmóyuley
|
||||
const accentFallsOnThirdLast = (syls: string[]) => {
|
||||
if (syls.length < 3) return false;
|
||||
const secondLast = syls[syls.length - 2];
|
||||
const thirdLast = syls[syls.length - 3];
|
||||
const lastLetterOfThirdLast = thirdLast.slice(-1);
|
||||
return secondLast === "ul" && lastLetterOfThirdLast === "y";
|
||||
};
|
||||
// remove all accents
|
||||
const accentsRemoved = removeAccents(s.f);
|
||||
// split up the syllables (preserving the spaces)
|
||||
const syllables = splitUpSyllables(accentsRemoved);
|
||||
// add an accent on the appropriate syllable
|
||||
const n = accentFallsOnThirdLast(syllables) ? 2 : 1;
|
||||
const accentedF = accentFSylsOnNFromEnd(syllables, n);
|
||||
return makePsString(s.p, accentedF);
|
||||
}
|
||||
|
||||
export function splitUpSyllables(f: string): string[] {
|
||||
return f.match(/ |([^a|á|e|é|i|í|o|ó|u|ú| ]*(aa|áa|a|á|ey|éy|ee|ée|e|é|oo|óo|o|ó|i|í|u|ú)[^a|á|e|é|i|í|o|ó|u|ú| ]*)/ig) || [] as string[];
|
||||
return (
|
||||
f.match(
|
||||
/ |([^a|á|e|é|i|í|o|ó|u|ú| ]*(aa|áa|a|á|ey|éy|ee|ée|e|é|oo|óo|o|ó|i|í|u|ú)[^a|á|e|é|i|í|o|ó|u|ú| ]*)/gi
|
||||
) || ([] as string[])
|
||||
);
|
||||
}
|
||||
|
||||
export function countSyllables(f: T.PsString | string): number {
|
||||
if (typeof f !== "string") return countSyllables(f.f);
|
||||
return splitUpSyllables(removeFVarients(removeAccents(f))).length;
|
||||
if (typeof f !== "string") return countSyllables(f.f);
|
||||
return splitUpSyllables(removeFVarients(removeAccents(f))).length;
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -72,87 +80,91 @@ export function countSyllables(f: T.PsString | string): number {
|
|||
* @param syls - an array of syllables in phonetic strings without accents (including spaces as extra items)
|
||||
* @param n - the number of syllables from the end to put the accent
|
||||
*/
|
||||
export function accentFSylsOnNFromEnd(syls: string[] | string, n: number): string {
|
||||
if (typeof syls === "string") {
|
||||
return accentFSylsOnNFromEnd(splitUpSyllables(syls), n);
|
||||
}
|
||||
return [
|
||||
...syls.slice(0, syls.length-(n+1)), // before accent
|
||||
accentLetter(syls[syls.length-(n+1)]), // syllable to be accented
|
||||
...(n !== 0) ? syls.slice(syls.length-n) : [], // after syllable to be accented
|
||||
].join("");
|
||||
export function accentFSylsOnNFromEnd(
|
||||
syls: string[] | string,
|
||||
n: number
|
||||
): string {
|
||||
if (typeof syls === "string") {
|
||||
return accentFSylsOnNFromEnd(splitUpSyllables(syls), n);
|
||||
}
|
||||
return [
|
||||
...syls.slice(0, syls.length - (n + 1)), // before accent
|
||||
accentLetter(syls[syls.length - (n + 1)]), // syllable to be accented
|
||||
...(n !== 0 ? syls.slice(syls.length - n) : []), // after syllable to be accented
|
||||
].join("");
|
||||
}
|
||||
|
||||
export function accentOnNFromEnd(ps: T.PsString, n: number): T.PsString {
|
||||
const fNoAccents = removeAccents(ps.f);
|
||||
const fSyls = splitUpSyllables(fNoAccents);
|
||||
// TODO: enable this and fix the tests it breaks!!!
|
||||
// don't add accent if only one syllable
|
||||
// if (fSyls.length === 1) return makePsString(ps.p, fNoAccents);
|
||||
return makePsString(
|
||||
ps.p,
|
||||
accentFSylsOnNFromEnd(fSyls, n),
|
||||
);
|
||||
const fNoAccents = removeAccents(ps.f);
|
||||
const fSyls = splitUpSyllables(fNoAccents);
|
||||
// TODO: enable this and fix the tests it breaks!!!
|
||||
// don't add accent if only one syllable
|
||||
// if (fSyls.length === 1) return makePsString(ps.p, fNoAccents);
|
||||
return makePsString(ps.p, accentFSylsOnNFromEnd(fSyls, n));
|
||||
}
|
||||
|
||||
const accentReplacer = [
|
||||
{ vowel: "a", accented: "á" },
|
||||
{ vowel: "e", accented: "é" },
|
||||
{ vowel: "i", accented: "í" },
|
||||
{ vowel: "o", accented: "ó" },
|
||||
{ vowel: "u", accented: "ú" },
|
||||
{ vowel: "U", accented: "Ú" },
|
||||
{ vowel: "a", accented: "á" },
|
||||
{ vowel: "ă", accented: "á" },
|
||||
{ vowel: "e", accented: "é" },
|
||||
{ vowel: "i", accented: "í" },
|
||||
{ vowel: "o", accented: "ó" },
|
||||
{ vowel: "u", accented: "ú" },
|
||||
{ vowel: "U", accented: "Ú" },
|
||||
];
|
||||
|
||||
export function accentLetter(s: string): string {
|
||||
return s.replace(/a|e|i|o|u|U/, (match) => {
|
||||
const r = accentReplacer.find((x) => x.vowel === match);
|
||||
/* istanbul ignore next */
|
||||
return r?.accented || "";
|
||||
});
|
||||
return s.replace(/a|ă|e|i|o|u|U/, (match) => {
|
||||
const r = accentReplacer.find((x) => x.vowel === match);
|
||||
/* istanbul ignore next */
|
||||
return r?.accented || "";
|
||||
});
|
||||
}
|
||||
|
||||
export function accentPsSyllable(ps: T.PsString): T.PsString {
|
||||
return {
|
||||
p: ps.p,
|
||||
f: accentLetter(ps.f),
|
||||
};
|
||||
}
|
||||
|
||||
export function removeAccentsWLength(
|
||||
s: T.SingleOrLengthOpts<T.PsString[]>
|
||||
): T.SingleOrLengthOpts<T.PsString[]> {
|
||||
if ("long" in s) {
|
||||
return {
|
||||
p: ps.p,
|
||||
f: accentLetter(ps.f),
|
||||
long: removeAccentsWLength(s.long) as T.PsString[],
|
||||
short: removeAccentsWLength(s.short) as T.PsString[],
|
||||
...(s.mini
|
||||
? {
|
||||
mini: removeAccentsWLength(s.mini) as T.PsString[],
|
||||
}
|
||||
: {}),
|
||||
};
|
||||
}
|
||||
return removeAccents(s);
|
||||
}
|
||||
|
||||
|
||||
|
||||
export function removeAccentsWLength(s: T.SingleOrLengthOpts<T.PsString[]>): T.SingleOrLengthOpts<T.PsString[]> {
|
||||
if ("long" in s) {
|
||||
return {
|
||||
long: removeAccentsWLength(s.long) as T.PsString[],
|
||||
short: removeAccentsWLength(s.short) as T.PsString[],
|
||||
...s.mini ? {
|
||||
mini: removeAccentsWLength(s.mini) as T.PsString[],
|
||||
} : {},
|
||||
};
|
||||
}
|
||||
return removeAccents(s);
|
||||
}
|
||||
|
||||
|
||||
export function removeAccents(s: T.PsString): T.PsString;
|
||||
export function removeAccents(s: string): string;
|
||||
export function removeAccents(s: T.PsString[]): T.PsString[];
|
||||
export function removeAccents(s: T.PsString | string | T.PsString[]): T.PsString | string | T.PsString[] {
|
||||
if (Array.isArray(s)) {
|
||||
return s.map(t => removeAccents(t));
|
||||
}
|
||||
if (typeof s !== "string") {
|
||||
return {
|
||||
...s,
|
||||
f: removeAccents(s.f),
|
||||
};
|
||||
}
|
||||
return s.replace(/á|é|í|ó|ú|Ú/, (match) => {
|
||||
const r = accentReplacer.find((x) => x.accented === match);
|
||||
/* istanbul ignore next */
|
||||
return r?.vowel || "";
|
||||
});
|
||||
export function removeAccents(
|
||||
s: T.PsString | string | T.PsString[]
|
||||
): T.PsString | string | T.PsString[] {
|
||||
if (Array.isArray(s)) {
|
||||
return s.map((t) => removeAccents(t));
|
||||
}
|
||||
if (typeof s !== "string") {
|
||||
return {
|
||||
...s,
|
||||
f: removeAccents(s.f),
|
||||
};
|
||||
}
|
||||
return s.replace(/á|é|í|ó|ú|Ú/, (match) => {
|
||||
const r = accentReplacer.find((x) => x.accented === match);
|
||||
/* istanbul ignore next */
|
||||
return r?.vowel || "";
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
@ -161,6 +173,6 @@ export function removeAccents(s: T.PsString | string | T.PsString[]): T.PsString
|
|||
* @param s a string of Pashto phonetics
|
||||
*/
|
||||
export function hasAccents(s: string | T.PsString): boolean {
|
||||
if (typeof s !== "string") return hasAccents(s.f);
|
||||
return accentReplacer.some((x) => s.includes(x.accented));
|
||||
if (typeof s !== "string") return hasAccents(s.f);
|
||||
return accentReplacer.some((x) => s.includes(x.accented));
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue